Token | uck |
Token ID | 1347 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ortium | +0.262 |
ania | +0.257 |
schild | +0.254 |
odder | +0.247 |
phabet | +0.241 |
Neg logit contributions | |
Dark | -0.295 |
dark | -0.293 |
Dark | -0.289 |
── | -0.287 |
inous | -0.285 |
Token | ley |
Token ID | 1636 |
Feature activation | -6.51e-04 |
Pos logit contributions | |
ortium | +0.878 |
ania | +0.878 |
schild | +0.857 |
odder | +0.836 |
phabet | +0.807 |
Neg logit contributions | |
dark | -1.352 |
Dark | -1.351 |
Dark | -1.332 |
── | -1.326 |
inous | -1.304 |
Token | NBA |
Token ID | 32470 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
Dark | +0.002 |
dark | +0.002 |
Dark | +0.001 |
── | +0.001 |
inous | +0.001 |
Neg logit contributions | |
ortium | -0.002 |
ania | -0.002 |
schild | -0.002 |
odder | -0.002 |
phabet | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ortium | +0.241 |
ania | +0.241 |
schild | +0.239 |
odder | +0.230 |
ibel | +0.224 |
Neg logit contributions | |
Dark | -0.247 |
dark | -0.245 |
Dark | -0.242 |
── | -0.239 |
inous | -0.234 |
Token | Ted |
Token ID | 38972 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Dark | +0.299 |
── | +0.291 |
dark | +0.291 |
Dark | +0.287 |
inous | +0.279 |
Neg logit contributions | |
ortium | -0.372 |
ania | -0.366 |
schild | -0.361 |
odder | -0.354 |
phabet | -0.347 |
Token | Nug |
Token ID | 45777 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ortium | +0.568 |
ania | +0.563 |
schild | +0.554 |
odder | +0.544 |
phabet | +0.534 |
Neg logit contributions | |
dark | -0.415 |
Dark | -0.411 |
Dark | -0.410 |
── | -0.405 |
inous | -0.395 |
Token | ent |
Token ID | 298 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ortium | +4.056 |
ania | +4.039 |
schild | +3.962 |
odder | +3.908 |
phabet | +3.850 |
Neg logit contributions | |
dark | -2.084 |
Dark | -2.083 |
── | -2.054 |
Dark | -2.036 |
inous | -1.976 |
Token | promised |
Token ID | 8072 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
dark | +0.344 |
Dark | +0.341 |
Dark | +0.341 |
── | +0.337 |
inous | +0.329 |
Neg logit contributions | |
ortium | -0.417 |
ania | -0.416 |
schild | -0.406 |
odder | -0.405 |
phabet | -0.394 |
Token | Thursday |
Token ID | 3635 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
ortium | +0.427 |
ania | +0.426 |
schild | +0.415 |
odder | +0.411 |
phabet | +0.400 |
Neg logit contributions | |
dark | -0.299 |
Dark | -0.297 |
── | -0.295 |
Dark | -0.293 |
inous | -0.285 |
Token | that |
Token ID | 326 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
dark | +0.051 |
Dark | +0.050 |
── | +0.050 |
Dark | +0.050 |
inous | +0.048 |
Neg logit contributions | |
ortium | -0.075 |
ania | -0.075 |
schild | -0.073 |
odder | -0.072 |
phabet | -0.070 |
Token | he |
Token ID | 339 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
dark | +0.417 |
Dark | +0.409 |
── | +0.408 |
Dark | +0.407 |
inous | +0.390 |
Neg logit contributions | |
ortium | -0.687 |
ania | -0.684 |
schild | -0.672 |
odder | -0.663 |
phabet | -0.646 |
Token | first |
Token ID | 717 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
dark | +0.274 |
Dark | +0.274 |
── | +0.273 |
Dark | +0.268 |
inous | +0.264 |
Neg logit contributions | |
ortium | -0.339 |
ania | -0.337 |
schild | -0.328 |
odder | -0.326 |
phabet | -0.316 |
Token | to |
Token ID | 284 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
dark | +0.108 |
Dark | +0.107 |
── | +0.107 |
Dark | +0.105 |
inous | +0.102 |
Neg logit contributions | |
ortium | -0.177 |
ania | -0.176 |
schild | -0.172 |
odder | -0.171 |
phabet | -0.167 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Dark | +0.167 |
dark | +0.167 |
── | +0.166 |
Dark | +0.164 |
inous | +0.161 |
Neg logit contributions | |
ortium | -0.167 |
ania | -0.166 |
schild | -0.161 |
odder | -0.160 |
ibel | -0.154 |
Token | about |
Token ID | 546 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
dark | +0.360 |
Dark | +0.359 |
── | +0.358 |
Dark | +0.354 |
inous | +0.348 |
Neg logit contributions | |
ortium | -0.381 |
ania | -0.380 |
schild | -0.369 |
odder | -0.365 |
phabet | -0.353 |
Token | Nation |
Token ID | 8741 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
── | +0.324 |
Dark | +0.323 |
dark | +0.322 |
Dark | +0.314 |
inous | +0.310 |
Neg logit contributions | |
ortium | -0.586 |
ania | -0.586 |
schild | -0.570 |
odder | -0.565 |
phabet | -0.550 |
Token | Travels |
Token ID | 48899 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ortium | +0.043 |
ania | +0.042 |
odder | +0.042 |
schild | +0.041 |
phabet | +0.040 |
Neg logit contributions | |
dark | -0.051 |
Dark | -0.051 |
Dark | -0.050 |
── | -0.049 |
inous | -0.048 |
Token | destinations |
Token ID | 23982 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ania | +3.156 |
ortium | +3.061 |
odder | +3.037 |
schild | +3.011 |
ubb | +2.834 |
Neg logit contributions | |
Dark | -2.790 |
── | -2.783 |
inous | -2.731 |
dark | -2.715 |
| -2.617 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
dark | +0.072 |
Dark | +0.071 |
── | +0.071 |
Dark | +0.070 |
inous | +0.067 |
Neg logit contributions | |
ortium | -0.108 |
ania | -0.107 |
schild | -0.105 |
odder | -0.104 |
phabet | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
dark | +1.090 |
Dark | +1.059 |
── | +1.057 |
Dark | +1.053 |
inous | +1.020 |
Neg logit contributions | |
ortium | -1.282 |
ania | -1.258 |
odder | -1.230 |
schild | -1.222 |
phabet | -1.204 |
Token | explore |
Token ID | 7301 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Dark | +0.692 |
dark | +0.691 |
── | +0.689 |
Dark | +0.683 |
inous | +0.675 |
Neg logit contributions | |
ortium | -0.414 |
ania | -0.413 |
schild | -0.396 |
odder | -0.389 |
phabet | -0.372 |
Token | the |
Token ID | 262 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ortium | +0.405 |
ania | +0.399 |
odder | +0.388 |
schild | +0.388 |
ibel | +0.377 |
Neg logit contributions | |
dark | -0.351 |
Dark | -0.346 |
Dark | -0.346 |
── | -0.344 |
inous | -0.324 |
Token | went |
Token ID | 1816 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ortium | +0.136 |
ania | +0.135 |
schild | +0.132 |
odder | +0.132 |
phabet | +0.127 |
Neg logit contributions | |
dark | -0.132 |
── | -0.129 |
Dark | -0.129 |
Dark | -0.128 |
inous | -0.124 |
Token | to |
Token ID | 284 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
dark | +0.308 |
── | +0.298 |
Dark | +0.298 |
Dark | +0.297 |
inous | +0.285 |
Neg logit contributions | |
ortium | -0.475 |
ania | -0.468 |
schild | -0.460 |
odder | -0.453 |
phabet | -0.444 |
Token | sleep |
Token ID | 3993 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
dark | +0.429 |
Dark | +0.419 |
Dark | +0.417 |
── | +0.414 |
inous | +0.396 |
Neg logit contributions | |
ortium | -0.516 |
ania | -0.505 |
schild | -0.495 |
odder | -0.488 |
phabet | -0.474 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ania | +1.427 |
ortium | +1.417 |
schild | +1.382 |
odder | +1.372 |
phabet | +1.333 |
Neg logit contributions | |
Dark | -1.044 |
── | -1.033 |
dark | -1.032 |
Dark | -1.016 |
inous | -1.008 |
Token | I |
Token ID | 314 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
ortium | +0.039 |
ania | +0.039 |
schild | +0.038 |
odder | +0.037 |
phabet | +0.036 |
Neg logit contributions | |
dark | -0.031 |
── | -0.030 |
Dark | -0.030 |
Dark | -0.030 |
inous | -0.028 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
dark | +0.140 |
── | +0.137 |
Dark | +0.136 |
Dark | +0.135 |
inous | +0.131 |
Neg logit contributions | |
ortium | -0.165 |
ania | -0.163 |
schild | -0.159 |
odder | -0.159 |
phabet | -0.154 |
Token | up |
Token ID | 510 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ania | +3.017 |
ortium | +2.949 |
odder | +2.874 |
schild | +2.852 |
ubb | +2.770 |
Neg logit contributions | |
Dark | -2.853 |
── | -2.810 |
inous | -2.786 |
dark | -2.785 |
Dark | -2.755 |
Token | and |
Token ID | 290 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
ortium | +0.366 |
ania | +0.364 |
schild | +0.356 |
odder | +0.352 |
phabet | +0.342 |
Neg logit contributions | |
dark | -0.284 |
Dark | -0.281 |
── | -0.281 |
Dark | -0.278 |
inous | -0.271 |
Token | my |
Token ID | 616 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
dark | +0.115 |
── | +0.112 |
Dark | +0.112 |
Dark | +0.112 |
inous | +0.106 |
Neg logit contributions | |
ortium | -0.145 |
ania | -0.143 |
schild | -0.141 |
odder | -0.138 |
phabet | -0.134 |
Token | mouth |
Token ID | 5422 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
dark | +0.162 |
Dark | +0.159 |
Dark | +0.158 |
── | +0.158 |
inous | +0.153 |
Neg logit contributions | |
ortium | -0.202 |
ania | -0.200 |
schild | -0.196 |
odder | -0.194 |
phabet | -0.188 |
Token | was |
Token ID | 373 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ortium | +0.250 |
ania | +0.246 |
schild | +0.241 |
odder | +0.241 |
phabet | +0.232 |
Neg logit contributions | |
dark | -0.234 |
── | -0.230 |
Dark | -0.228 |
Dark | -0.227 |
inous | -0.219 |
Token | Center |
Token ID | 3337 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
ortium | +1.138 |
ania | +1.137 |
schild | +1.108 |
odder | +1.097 |
phabet | +1.073 |
Neg logit contributions | |
dark | -0.819 |
Dark | -0.810 |
Dark | -0.804 |
── | -0.801 |
inous | -0.774 |
Token | filed |
Token ID | 5717 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ania | +0.150 |
ortium | +0.149 |
odder | +0.145 |
schild | +0.145 |
phabet | +0.142 |
Neg logit contributions | |
dark | -0.090 |
Dark | -0.089 |
── | -0.088 |
Dark | -0.088 |
inous | -0.086 |
Token | an |
Token ID | 281 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ortium | +0.614 |
ania | +0.614 |
schild | +0.598 |
odder | +0.590 |
phabet | +0.573 |
Neg logit contributions | |
dark | -0.541 |
Dark | -0.535 |
── | -0.533 |
Dark | -0.530 |
inous | -0.515 |
Token | am |
Token ID | 716 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ortium | +0.570 |
ania | +0.567 |
schild | +0.553 |
odder | +0.546 |
phabet | +0.532 |
Neg logit contributions | |
dark | -0.540 |
Dark | -0.535 |
── | -0.534 |
Dark | -0.530 |
inous | -0.518 |
Token | icus |
Token ID | 24552 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
ortium | +0.736 |
ania | +0.734 |
schild | +0.707 |
odder | +0.696 |
phabet | +0.665 |
Neg logit contributions | |
dark | -1.217 |
Dark | -1.213 |
── | -1.209 |
Dark | -1.200 |
inous | -1.182 |
Token | brief |
Token ID | 4506 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ortium | +1.020 |
ania | +1.006 |
schild | +0.974 |
odder | +0.972 |
phabet | +0.938 |
Neg logit contributions | |
Dark | -1.050 |
dark | -1.048 |
── | -1.041 |
Dark | -1.034 |
inous | -1.021 |
Token | calling |
Token ID | 4585 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ortium | +3.057 |
ania | +3.037 |
schild | +2.958 |
odder | +2.907 |
ibel | +2.820 |
Neg logit contributions | |
Dark | -2.702 |
dark | -2.663 |
── | -2.650 |
Dark | -2.638 |
inous | -2.613 |
Token | for |
Token ID | 329 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
ortium | +1.388 |
ania | +1.385 |
schild | +1.347 |
odder | +1.335 |
phabet | +1.297 |
Neg logit contributions | |
dark | -1.096 |
Dark | -1.092 |
── | -1.088 |
Dark | -1.075 |
inous | -1.053 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-04 |
Pos logit contributions | |
ortium | +0.170 |
ania | +0.170 |
schild | +0.166 |
odder | +0.164 |
phabet | +0.159 |
Neg logit contributions | |
dark | -0.142 |
── | -0.140 |
Dark | -0.139 |
Dark | -0.138 |
inous | -0.133 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ortium | +0.000 |
ania | +0.000 |
schild | +0.000 |
odder | +0.000 |
phabet | +0.000 |
Neg logit contributions | |
dark | -0.000 |
Dark | -0.000 |
── | -0.000 |
Dark | -0.000 |
inous | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
dark | +0.224 |
Dark | +0.224 |
── | +0.222 |
Dark | +0.220 |
inous | +0.215 |
Neg logit contributions | |
ortium | -0.348 |
ania | -0.348 |
schild | -0.339 |
odder | -0.336 |
phabet | -0.327 |
Token | download |
Token ID | 4321 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ortium | +0.121 |
ania | +0.121 |
schild | +0.118 |
odder | +0.117 |
phabet | +0.114 |
Neg logit contributions | |
dark | -0.069 |
Dark | -0.068 |
── | -0.068 |
Dark | -0.067 |
inous | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
── | +1.003 |
dark | +1.001 |
Dark | +0.993 |
Dark | +0.989 |
inous | +0.928 |
Neg logit contributions | |
ortium | -1.388 |
ania | -1.358 |
schild | -1.327 |
odder | -1.326 |
phabet | -1.291 |
Token | Includes |
Token ID | 29581 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Dark | +0.998 |
Dark | +0.987 |
── | +0.975 |
dark | +0.968 |
| +0.927 |
Neg logit contributions | |
ortium | -1.387 |
ania | -1.332 |
odder | -1.311 |
schild | -1.306 |
phabet | -1.273 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ortium | +0.060 |
ania | +0.060 |
schild | +0.058 |
odder | +0.058 |
phabet | +0.056 |
Neg logit contributions | |
dark | -0.056 |
Dark | -0.056 |
── | -0.055 |
Dark | -0.055 |
inous | -0.053 |
Token | Catholic |
Token ID | 7835 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
dark | +0.267 |
Dark | +0.265 |
Dark | +0.264 |
── | +0.257 |
inous | +0.252 |
Neg logit contributions | |
ortium | -0.389 |
ania | -0.387 |
schild | -0.373 |
odder | -0.370 |
phabet | -0.364 |
Token | Encyclopedia |
Token ID | 36732 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ortium | +0.021 |
ania | +0.021 |
schild | +0.020 |
odder | +0.020 |
phabet | +0.018 |
Neg logit contributions | |
dark | -0.039 |
Dark | -0.039 |
── | -0.039 |
Dark | -0.039 |
inous | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ania | +2.807 |
ortium | +2.664 |
odder | +2.657 |
schild | +2.622 |
ubb | +2.520 |
Neg logit contributions | |
Dark | -2.744 |
── | -2.722 |
dark | -2.710 |
inous | -2.681 |
Dark | -2.640 |
Token | Church |
Token ID | 4564 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
dark | +0.440 |
Dark | +0.437 |
── | +0.434 |
Dark | +0.433 |
inous | +0.419 |
Neg logit contributions | |
ortium | -0.591 |
ania | -0.590 |
schild | -0.575 |
odder | -0.568 |
phabet | -0.550 |
Token | Fathers |
Token ID | 30969 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
ortium | +0.411 |
ania | +0.410 |
schild | +0.394 |
odder | +0.391 |
phabet | +0.376 |
Neg logit contributions | |
dark | -0.546 |
Dark | -0.545 |
── | -0.544 |
Dark | -0.538 |
inous | -0.530 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ortium | +0.247 |
ania | +0.247 |
schild | +0.239 |
odder | +0.237 |
phabet | +0.231 |
Neg logit contributions | |
Dark | -0.192 |
dark | -0.191 |
── | -0.191 |
Dark | -0.188 |
inous | -0.184 |
Token | Sum |
Token ID | 5060 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Dark | +0.360 |
── | +0.359 |
dark | +0.357 |
Dark | +0.351 |
inous | +0.349 |
Neg logit contributions | |
ortium | -0.445 |
ania | -0.443 |
schild | -0.429 |
odder | -0.425 |
phabet | -0.418 |
Token | ocking |
Token ID | 8629 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ortium | +0.748 |
ania | +0.738 |
schild | +0.725 |
odder | +0.713 |
phabet | +0.695 |
Neg logit contributions | |
dark | -0.764 |
Dark | -0.757 |
── | -0.755 |
Dark | -0.749 |
inous | -0.737 |
Token | stability |
Token ID | 10159 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
ortium | +0.909 |
ania | +0.903 |
schild | +0.881 |
odder | +0.873 |
phabet | +0.850 |
Neg logit contributions | |
dark | -0.690 |
── | -0.683 |
Dark | -0.682 |
Dark | -0.676 |
inous | -0.657 |
Token | . |
Token ID | 13 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
ortium | +1.711 |
ania | +1.708 |
schild | +1.661 |
odder | +1.645 |
phabet | +1.597 |
Neg logit contributions | |
dark | -1.385 |
Dark | -1.379 |
── | -1.374 |
Dark | -1.359 |
inous | -1.330 |
Token | As |
Token ID | 1081 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Dark | +0.230 |
dark | +0.229 |
Dark | +0.228 |
── | +0.227 |
inous | +0.217 |
Neg logit contributions | |
ortium | -0.254 |
ania | -0.252 |
schild | -0.247 |
odder | -0.244 |
phabet | -0.240 |
Token | for |
Token ID | 329 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
dark | +0.720 |
Dark | +0.710 |
Dark | +0.708 |
── | +0.697 |
inous | +0.673 |
Neg logit contributions | |
ortium | -0.879 |
ania | -0.869 |
schild | -0.864 |
odder | -0.852 |
phabet | -0.837 |
Token | thermal |
Token ID | 18411 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
dark | +0.047 |
Dark | +0.046 |
── | +0.046 |
Dark | +0.046 |
inous | +0.044 |
Neg logit contributions | |
ortium | -0.059 |
ania | -0.058 |
schild | -0.057 |
odder | -0.057 |
phabet | -0.055 |
Token | solution |
Token ID | 4610 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
ania | +3.096 |
ortium | +3.069 |
schild | +2.995 |
odder | +2.958 |
phabet | +2.876 |
Neg logit contributions | |
Dark | -2.476 |
dark | -2.457 |
── | -2.457 |
Dark | -2.417 |
inous | -2.411 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
dark | +0.064 |
Dark | +0.063 |
── | +0.063 |
Dark | +0.063 |
inous | +0.060 |
Neg logit contributions | |
ortium | -0.086 |
ania | -0.086 |
schild | -0.084 |
odder | -0.083 |
phabet | -0.081 |
Token | MSI |
Token ID | 30781 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
dark | +0.032 |
Dark | +0.032 |
Dark | +0.032 |
── | +0.032 |
inous | +0.031 |
Neg logit contributions | |
ortium | -0.029 |
ania | -0.029 |
schild | -0.028 |
odder | -0.028 |
phabet | -0.027 |
Token | R |
Token ID | 371 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
dark | +0.350 |
Dark | +0.347 |
Dark | +0.345 |
── | +0.344 |
inous | +0.332 |
Neg logit contributions | |
ortium | -0.407 |
ania | -0.405 |
schild | -0.395 |
odder | -0.392 |
phabet | -0.382 |
Token | 78 |
Token ID | 3695 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ania | +0.101 |
ortium | +0.101 |
schild | +0.098 |
odder | +0.098 |
phabet | +0.095 |
Neg logit contributions | |
dark | -0.054 |
Dark | -0.054 |
── | -0.054 |
Dark | -0.053 |
inous | -0.052 |
Token | take |
Token ID | 1011 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ortium | +0.151 |
ania | +0.149 |
schild | +0.146 |
odder | +0.144 |
phabet | +0.141 |
Neg logit contributions | |
dark | -0.119 |
── | -0.117 |
Dark | -0.116 |
Dark | -0.116 |
inous | -0.112 |
Token | his |
Token ID | 465 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
ortium | +0.434 |
ania | +0.428 |
schild | +0.421 |
odder | +0.412 |
phabet | +0.406 |
Neg logit contributions | |
dark | -0.333 |
Dark | -0.324 |
Dark | -0.321 |
── | -0.318 |
inous | -0.305 |
Token | life |
Token ID | 1204 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
dark | +0.070 |
Dark | +0.069 |
Dark | +0.069 |
── | +0.068 |
inous | +0.066 |
Neg logit contributions | |
ortium | -0.084 |
ania | -0.084 |
schild | -0.082 |
odder | -0.081 |
phabet | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ortium | +0.260 |
ania | +0.259 |
schild | +0.252 |
odder | +0.250 |
phabet | +0.244 |
Neg logit contributions | |
dark | -0.196 |
Dark | -0.194 |
── | -0.194 |
Dark | -0.192 |
inous | -0.187 |
Token | He |
Token ID | 679 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ortium | +0.465 |
ania | +0.460 |
schild | +0.450 |
odder | +0.445 |
phabet | +0.435 |
Neg logit contributions | |
dark | -0.361 |
Dark | -0.361 |
Dark | -0.361 |
── | -0.355 |
inous | -0.341 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ortium | +0.527 |
ania | +0.521 |
schild | +0.509 |
odder | +0.507 |
phabet | +0.492 |
Neg logit contributions | |
dark | -0.468 |
── | -0.459 |
Dark | -0.456 |
Dark | -0.456 |
inous | -0.446 |
Token | from |
Token ID | 422 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
ania | +2.938 |
ortium | +2.908 |
odder | +2.816 |
schild | +2.816 |
phabet | +2.713 |
Neg logit contributions | |
Dark | -2.552 |
── | -2.528 |
dark | -2.497 |
inous | -2.477 |
Dark | -2.472 |
Token | a |
Token ID | 257 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
ortium | +0.891 |
ania | +0.885 |
schild | +0.864 |
odder | +0.855 |
phabet | +0.834 |
Neg logit contributions | |
dark | -0.712 |
Dark | -0.701 |
Dark | -0.695 |
── | -0.695 |
inous | -0.669 |
Token | coma |
Token ID | 33658 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
dark | +0.140 |
Dark | +0.135 |
Dark | +0.135 |
── | +0.133 |
inous | +0.128 |
Neg logit contributions | |
ortium | -0.210 |
ania | -0.209 |
schild | -0.206 |
odder | -0.204 |
phabet | -0.198 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
dark | +0.118 |
── | +0.116 |
Dark | +0.116 |
Dark | +0.115 |
inous | +0.111 |
Neg logit contributions | |
ortium | -0.154 |
ania | -0.153 |
schild | -0.150 |
odder | -0.148 |
phabet | -0.145 |
Token | find |
Token ID | 1064 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
dark | +0.357 |
Dark | +0.348 |
Dark | +0.347 |
── | +0.346 |
inous | +0.332 |
Neg logit contributions | |
ortium | -0.407 |
ania | -0.402 |
schild | -0.392 |
odder | -0.389 |
phabet | -0.377 |
Token | first |
Token ID | 717 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
dark | +0.730 |
Dark | +0.722 |
── | +0.717 |
Dark | +0.715 |
inous | +0.694 |
Neg logit contributions | |
ortium | -0.956 |
ania | -0.954 |
schild | -0.929 |
odder | -0.920 |
phabet | -0.897 |
Token | to |
Token ID | 284 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
dark | +0.429 |
── | +0.425 |
Dark | +0.424 |
Dark | +0.419 |
inous | +0.404 |
Neg logit contributions | |
ortium | -0.723 |
ania | -0.716 |
schild | -0.702 |
odder | -0.698 |
phabet | -0.680 |
Token | hear |
Token ID | 3285 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
Dark | +0.212 |
dark | +0.210 |
── | +0.209 |
Dark | +0.208 |
inous | +0.204 |
Neg logit contributions | |
ania | -0.208 |
ortium | -0.207 |
schild | -0.200 |
odder | -0.199 |
ibel | -0.192 |
Token | about |
Token ID | 546 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
dark | +1.099 |
Dark | +1.086 |
── | +1.085 |
Dark | +1.077 |
inous | +1.044 |
Neg logit contributions | |
ortium | -1.238 |
ania | -1.225 |
schild | -1.192 |
odder | -1.183 |
phabet | -1.153 |
Token | Nation |
Token ID | 8741 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
dark | +0.303 |
Dark | +0.300 |
── | +0.298 |
Dark | +0.297 |
inous | +0.285 |
Neg logit contributions | |
ortium | -0.611 |
ania | -0.609 |
schild | -0.596 |
odder | -0.591 |
phabet | -0.578 |
Token | Travels |
Token ID | 48899 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
dark | +0.400 |
Dark | +0.397 |
Dark | +0.395 |
── | +0.395 |
inous | +0.384 |
Neg logit contributions | |
ortium | -0.295 |
ania | -0.294 |
schild | -0.283 |
odder | -0.279 |
phabet | -0.270 |
Token | destinations |
Token ID | 23982 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ania | +2.963 |
ortium | +2.907 |
schild | +2.850 |
odder | +2.845 |
ubb | +2.682 |
Neg logit contributions | |
Dark | -2.493 |
── | -2.486 |
inous | -2.437 |
dark | -2.436 |
Dark | -2.361 |
Token | , |
Token ID | 11 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
dark | +0.479 |
Dark | +0.478 |
── | +0.476 |
Dark | +0.472 |
inous | +0.446 |
Neg logit contributions | |
ortium | -0.720 |
ania | -0.706 |
schild | -0.695 |
odder | -0.689 |
phabet | -0.680 |
Token | and |
Token ID | 290 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
dark | +1.025 |
── | +1.012 |
Dark | +1.012 |
Dark | +1.005 |
| +0.957 |
Neg logit contributions | |
ortium | -1.228 |
odder | -1.193 |
ania | -1.192 |
schild | -1.181 |
phabet | -1.155 |
Token | explore |
Token ID | 7301 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
dark | +0.714 |
── | +0.709 |
Dark | +0.707 |
Dark | +0.702 |
inous | +0.690 |
Neg logit contributions | |
ortium | -0.463 |
ania | -0.462 |
schild | -0.444 |
odder | -0.439 |
phabet | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
dark | +0.063 |
── | +0.063 |
Dark | +0.063 |
Dark | +0.062 |
inous | +0.060 |
Neg logit contributions | |
ortium | -0.071 |
ania | -0.070 |
odder | -0.068 |
schild | -0.068 |
phabet | -0.066 |
Token | word |
Token ID | 4775 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ania | +0.088 |
ortium | +0.088 |
schild | +0.085 |
odder | +0.084 |
phabet | +0.080 |
Neg logit contributions | |
dark | -0.133 |
── | -0.133 |
Dark | -0.132 |
Dark | -0.131 |
inous | -0.130 |
Token | by |
Token ID | 416 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
schild | +0.379 |
ortium | +0.376 |
ania | +0.374 |
odder | +0.371 |
ibel | +0.362 |
Neg logit contributions | |
dark | -0.319 |
Dark | -0.314 |
── | -0.313 |
Dark | -0.312 |
Heaven | -0.293 |
Token | Patrick |
Token ID | 9925 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ania | +0.044 |
ortium | +0.044 |
schild | +0.041 |
odder | +0.041 |
phabet | +0.039 |
Neg logit contributions | |
Dark | -0.103 |
── | -0.102 |
dark | -0.102 |
Dark | -0.101 |
inous | -0.100 |
Token | J |
Token ID | 449 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
── | +0.693 |
dark | +0.686 |
Dark | +0.685 |
Dark | +0.666 |
inous | +0.665 |
Neg logit contributions | |
ania | -0.644 |
ortium | -0.642 |
schild | -0.620 |
odder | -0.616 |
ibel | -0.596 |
Token | . |
Token ID | 13 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
ortium | +0.556 |
ania | +0.540 |
schild | +0.533 |
odder | +0.520 |
phabet | +0.513 |
Neg logit contributions | |
dark | -0.363 |
Dark | -0.362 |
Dark | -0.357 |
inous | -0.348 |
── | -0.346 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
── | +0.069 |
dark | +0.068 |
Dark | +0.067 |
inous | +0.066 |
Dark | +0.066 |
Neg logit contributions | |
ania | -0.077 |
ortium | -0.075 |
schild | -0.074 |
odder | -0.074 |
ubb | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ortium | +2.926 |
ania | +2.914 |
odder | +2.755 |
schild | +2.754 |
ubb | +2.653 |
Neg logit contributions | |
Dark | -2.502 |
── | -2.494 |
dark | -2.482 |
inous | -2.461 |
Dark | -2.411 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
── | +0.602 |
dark | +0.602 |
Dark | +0.601 |
Dark | +0.592 |
inous | +0.589 |
Neg logit contributions | |
ortium | -0.573 |
ania | -0.572 |
schild | -0.558 |
odder | -0.548 |
ibel | -0.531 |
Token | critical |
Token ID | 4688 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
inous | +0.296 |
── | +0.293 |
Dark | +0.290 |
dark | +0.286 |
Dark | +0.281 |
Neg logit contributions | |
ania | -0.236 |
ortium | -0.235 |
schild | -0.228 |
ubb | -0.222 |
ibel | -0.221 |
Token | essays |
Token ID | 27126 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ortium | +0.021 |
ania | +0.020 |
odder | +0.020 |
schild | +0.020 |
ibel | +0.019 |
Neg logit contributions | |
Dark | -0.031 |
── | -0.030 |
inous | -0.030 |
dark | -0.030 |
| -0.030 |
Token | by |
Token ID | 416 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
dark | +0.588 |
── | +0.583 |
Dark | +0.582 |
Dark | +0.578 |
inous | +0.562 |
Neg logit contributions | |
ortium | -0.593 |
ania | -0.587 |
schild | -0.576 |
odder | -0.566 |
phabet | -0.548 |
Token | ) |
Token ID | 8 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
dark | +0.152 |
Dark | +0.151 |
── | +0.150 |
Dark | +0.149 |
inous | +0.145 |
Neg logit contributions | |
ortium | -0.246 |
ania | -0.245 |
schild | -0.239 |
odder | -0.237 |
phabet | -0.231 |
Token | up |
Token ID | 510 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
dark | +0.010 |
Dark | +0.010 |
── | +0.010 |
Dark | +0.010 |
inous | +0.010 |
Neg logit contributions | |
ortium | -0.015 |
ania | -0.015 |
schild | -0.015 |
odder | -0.015 |
phabet | -0.014 |
Token | ?" |
Token ID | 1701 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
dark | +0.072 |
Dark | +0.071 |
── | +0.071 |
Dark | +0.070 |
inous | +0.068 |
Neg logit contributions | |
ortium | -0.120 |
ania | -0.118 |
schild | -0.117 |
odder | -0.115 |
phabet | -0.113 |
Token | when |
Token ID | 618 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
dark | +0.892 |
Dark | +0.880 |
Dark | +0.872 |
── | +0.866 |
inous | +0.821 |
Neg logit contributions | |
ortium | -1.238 |
ania | -1.215 |
schild | -1.195 |
odder | -1.175 |
phabet | -1.153 |
Token | he |
Token ID | 339 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ortium | +1.123 |
ania | +1.119 |
schild | +1.095 |
odder | +1.086 |
phabet | +1.060 |
Neg logit contributions | |
dark | -0.607 |
Dark | -0.601 |
── | -0.599 |
Dark | -0.592 |
inous | -0.573 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ortium | +0.320 |
ania | +0.317 |
schild | +0.309 |
odder | +0.307 |
phabet | +0.300 |
Neg logit contributions | |
dark | -0.288 |
── | -0.284 |
Dark | -0.282 |
Dark | -0.281 |
inous | -0.274 |
Token | up |
Token ID | 510 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ania | +2.868 |
ortium | +2.828 |
odder | +2.738 |
schild | +2.735 |
ubb | +2.643 |
Neg logit contributions | |
Dark | -2.517 |
── | -2.479 |
dark | -2.469 |
inous | -2.452 |
Dark | -2.438 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ortium | +0.432 |
ania | +0.426 |
schild | +0.419 |
odder | +0.414 |
phabet | +0.404 |
Neg logit contributions | |
dark | -0.331 |
── | -0.325 |
Dark | -0.325 |
Dark | -0.323 |
inous | -0.311 |
Token | authorities |
Token ID | 4773 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ortium | +0.065 |
ania | +0.064 |
schild | +0.063 |
odder | +0.062 |
phabet | +0.061 |
Neg logit contributions | |
dark | -0.048 |
Dark | -0.047 |
Dark | -0.046 |
── | -0.046 |
inous | -0.044 |
Token | said |
Token ID | 531 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ortium | +0.539 |
ania | +0.534 |
schild | +0.523 |
odder | +0.519 |
phabet | +0.503 |
Neg logit contributions | |
dark | -0.494 |
Dark | -0.486 |
── | -0.484 |
Dark | -0.483 |
inous | -0.471 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
ortium | +0.603 |
ania | +0.601 |
schild | +0.585 |
odder | +0.578 |
phabet | +0.562 |
Neg logit contributions | |
dark | -0.510 |
Dark | -0.507 |
── | -0.506 |
Dark | -0.501 |
inous | -0.489 |
Token | Francisco |
Token ID | 6033 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ortium | +0.310 |
ania | +0.309 |
schild | +0.300 |
odder | +0.295 |
phabet | +0.284 |
Neg logit contributions | |
dark | -0.398 |
Dark | -0.397 |
── | -0.395 |
Dark | -0.393 |
inous | -0.387 |
Token | , |
Token ID | 11 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
ortium | +0.358 |
ania | +0.355 |
schild | +0.347 |
odder | +0.343 |
phabet | +0.333 |
Neg logit contributions | |
dark | -0.319 |
Dark | -0.316 |
── | -0.315 |
Dark | -0.314 |
inous | -0.305 |
Token | CA |
Token ID | 7257 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
dark | +0.125 |
Dark | +0.124 |
Dark | +0.123 |
── | +0.122 |
inous | +0.117 |
Neg logit contributions | |
ortium | -0.141 |
ania | -0.140 |
schild | -0.138 |
odder | -0.136 |
phabet | -0.132 |
Token |
|
Token ID | 198 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
ortium | +0.568 |
ania | +0.566 |
schild | +0.557 |
odder | +0.548 |
phabet | +0.534 |
Neg logit contributions | |
dark | -0.392 |
── | -0.387 |
Dark | -0.386 |
Dark | -0.383 |
inous | -0.370 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ortium | +0.210 |
ania | +0.208 |
schild | +0.203 |
odder | +0.201 |
phabet | +0.197 |
Neg logit contributions | |
dark | -0.180 |
Dark | -0.180 |
── | -0.179 |
Dark | -0.177 |
inous | -0.172 |
Token | Dear |
Token ID | 20266 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ortium | +0.052 |
ania | +0.051 |
schild | +0.050 |
odder | +0.049 |
phabet | +0.048 |
Neg logit contributions | |
Dark | -0.046 |
── | -0.045 |
dark | -0.045 |
Dark | -0.044 |
inous | -0.043 |
Token | Supervisor |
Token ID | 45673 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
ortium | +2.718 |
ania | +2.712 |
schild | +2.631 |
odder | +2.602 |
phabet | +2.519 |
Neg logit contributions | |
dark | -2.657 |
Dark | -2.648 |
── | -2.639 |
Dark | -2.611 |
inous | -2.563 |
Token | Camp |
Token ID | 5425 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ortium | +0.125 |
ania | +0.124 |
schild | +0.122 |
odder | +0.119 |
phabet | +0.116 |
Neg logit contributions | |
Dark | -0.121 |
dark | -0.120 |
── | -0.120 |
Dark | -0.119 |
| -0.113 |
Token | os |
Token ID | 418 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ortium | +0.929 |
ania | +0.918 |
schild | +0.902 |
odder | +0.895 |
phabet | +0.871 |
Neg logit contributions | |
dark | -0.635 |
Dark | -0.632 |
── | -0.628 |
Dark | -0.622 |
inous | -0.616 |
Token | : |
Token ID | 25 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
ortium | +0.977 |
ania | +0.975 |
schild | +0.947 |
odder | +0.938 |
phabet | +0.909 |
Neg logit contributions | |
dark | -0.889 |
Dark | -0.886 |
── | -0.883 |
Dark | -0.875 |
inous | -0.856 |
Token |
|
Token ID | 198 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ortium | +0.265 |
ania | +0.264 |
schild | +0.257 |
odder | +0.256 |
phabet | +0.249 |
Neg logit contributions | |
Dark | -0.221 |
dark | -0.221 |
Dark | -0.220 |
── | -0.218 |
inous | -0.211 |
Token | Round |
Token ID | 22685 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
dark | +0.286 |
── | +0.284 |
Dark | +0.281 |
Dark | +0.275 |
inous | +0.267 |
Neg logit contributions | |
ortium | -1.029 |
ania | -1.029 |
schild | -1.008 |
odder | -1.000 |
phabet | -0.981 |
Token | " |
Token ID | 366 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ortium | +0.131 |
ania | +0.128 |
odder | +0.125 |
schild | +0.125 |
ubb | +0.118 |
Neg logit contributions | |
dark | -0.166 |
Dark | -0.165 |
── | -0.165 |
Dark | -0.163 |
inous | -0.160 |
Token | 11 |
Token ID | 1157 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Dark | +0.342 |
dark | +0.337 |
── | +0.336 |
Dark | +0.332 |
inous | +0.318 |
Neg logit contributions | |
ortium | -0.434 |
ania | -0.425 |
schild | -0.417 |
odder | -0.414 |
phabet | -0.406 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ortium | +1.184 |
ania | +1.178 |
schild | +1.152 |
odder | +1.142 |
phabet | +1.111 |
Neg logit contributions | |
dark | -0.698 |
Dark | -0.696 |
── | -0.694 |
Dark | -0.684 |
inous | -0.658 |
Token | [ |
Token ID | 685 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
ortium | +0.405 |
ania | +0.393 |
schild | +0.389 |
odder | +0.382 |
phabet | +0.374 |
Neg logit contributions | |
dark | -0.335 |
Dark | -0.332 |
Dark | -0.332 |
── | -0.328 |
inous | -0.312 |
Token | White |
Token ID | 12256 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Dark | +0.260 |
dark | +0.259 |
── | +0.248 |
Dark | +0.244 |
inous | +0.217 |
Neg logit contributions | |
ortium | -1.352 |
ania | -1.346 |
schild | -1.323 |
odder | -1.321 |
phabet | -1.295 |
Token | " |
Token ID | 366 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ania | +2.104 |
ortium | +2.060 |
schild | +1.939 |
odder | +1.913 |
ibel | +1.892 |
Neg logit contributions | |
── | -3.222 |
dark | -3.220 |
Dark | -3.197 |
inous | -3.168 |
Dark | -3.158 |
Token | Ab |
Token ID | 4826 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Dark | +0.385 |
dark | +0.376 |
── | +0.375 |
Dark | +0.371 |
inous | +0.361 |
Neg logit contributions | |
ortium | -0.407 |
ania | -0.402 |
schild | -0.391 |
odder | -0.386 |
phabet | -0.377 |
Token | as |
Token ID | 292 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Dark | +0.399 |
dark | +0.396 |
Dark | +0.391 |
── | +0.389 |
inous | +0.382 |
Neg logit contributions | |
ortium | -0.447 |
ania | -0.438 |
schild | -0.432 |
odder | -0.427 |
phabet | -0.418 |
Token | ov |
Token ID | 709 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ortium | +0.733 |
ania | +0.717 |
schild | +0.710 |
odder | +0.700 |
phabet | +0.683 |
Neg logit contributions | |
dark | -0.653 |
Dark | -0.649 |
Dark | -0.647 |
── | -0.638 |
inous | -0.627 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
ortium | +0.843 |
ania | +0.838 |
schild | +0.819 |
odder | +0.812 |
phabet | +0.792 |
Neg logit contributions | |
dark | -0.579 |
Dark | -0.576 |
── | -0.572 |
Dark | -0.568 |
inous | -0.552 |
Token | couple |
Token ID | 3155 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
dark | +0.212 |
Dark | +0.206 |
Dark | +0.205 |
── | +0.203 |
inous | +0.196 |
Neg logit contributions | |
ortium | -0.266 |
ania | -0.265 |
schild | -0.259 |
odder | -0.256 |
phabet | -0.252 |
Token | 's |
Token ID | 338 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ortium | +0.084 |
ania | +0.083 |
schild | +0.082 |
odder | +0.081 |
phabet | +0.079 |
Neg logit contributions | |
dark | -0.057 |
Dark | -0.056 |
── | -0.056 |
Dark | -0.056 |
inous | -0.054 |
Token | home |
Token ID | 1363 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
dark | +0.559 |
Dark | +0.545 |
Dark | +0.542 |
── | +0.537 |
inous | +0.521 |
Neg logit contributions | |
ortium | -0.659 |
ania | -0.653 |
schild | -0.644 |
odder | -0.635 |
phabet | -0.626 |
Token | when |
Token ID | 618 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ortium | +0.039 |
ania | +0.039 |
schild | +0.038 |
odder | +0.038 |
phabet | +0.037 |
Neg logit contributions | |
dark | -0.028 |
Dark | -0.028 |
── | -0.028 |
Dark | -0.027 |
inous | -0.027 |
Token | he |
Token ID | 339 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ortium | +0.512 |
ania | +0.509 |
schild | +0.499 |
odder | +0.494 |
phabet | +0.483 |
Neg logit contributions | |
dark | -0.302 |
── | -0.297 |
Dark | -0.297 |
Dark | -0.295 |
inous | -0.284 |
Token | woke |
Token ID | 19092 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ortium | +0.546 |
ania | +0.539 |
schild | +0.531 |
odder | +0.526 |
phabet | +0.518 |
Neg logit contributions | |
dark | -0.429 |
── | -0.417 |
Dark | -0.415 |
Dark | -0.414 |
inous | -0.402 |
Token | up |
Token ID | 510 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ania | +2.753 |
ortium | +2.696 |
odder | +2.624 |
schild | +2.606 |
ubb | +2.527 |
Neg logit contributions | |
Dark | -2.534 |
── | -2.493 |
dark | -2.478 |
inous | -2.472 |
Dark | -2.451 |
Token | around |
Token ID | 1088 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ortium | +0.347 |
ania | +0.344 |
schild | +0.337 |
odder | +0.333 |
phabet | +0.325 |
Neg logit contributions | |
dark | -0.269 |
── | -0.265 |
Dark | -0.265 |
Dark | -0.263 |
inous | -0.255 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ortium | +0.938 |
ania | +0.938 |
schild | +0.916 |
odder | +0.909 |
phabet | +0.885 |
Neg logit contributions | |
dark | -0.475 |
Dark | -0.474 |
── | -0.472 |
Dark | -0.463 |
inous | -0.453 |
Token | : |
Token ID | 25 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
ortium | +0.463 |
ania | +0.459 |
schild | +0.446 |
odder | +0.441 |
phabet | +0.429 |
Neg logit contributions | |
dark | -0.434 |
Dark | -0.429 |
── | -0.426 |
Dark | -0.425 |
inous | -0.412 |
Token | 48 |
Token ID | 2780 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
ortium | +0.183 |
ania | +0.180 |
schild | +0.176 |
odder | +0.174 |
phabet | +0.171 |
Neg logit contributions | |
Dark | -0.181 |
dark | -0.180 |
── | -0.179 |
Dark | -0.178 |
inous | -0.172 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Dark | +0.349 |
dark | +0.348 |
── | +0.346 |
Dark | +0.344 |
| +0.329 |
Neg logit contributions | |
ortium | -0.422 |
ania | -0.414 |
schild | -0.406 |
odder | -0.402 |
phabet | -0.395 |
Token | Book |
Token ID | 10482 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Dark | +0.264 |
── | +0.258 |
dark | +0.256 |
Dark | +0.253 |
inous | +0.247 |
Neg logit contributions | |
ortium | -0.278 |
ania | -0.272 |
schild | -0.269 |
odder | -0.263 |
phabet | -0.255 |
Token | mark |
Token ID | 4102 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
ortium | +0.467 |
ania | +0.465 |
schild | +0.451 |
odder | +0.450 |
phabet | +0.435 |
Neg logit contributions | |
dark | -0.371 |
Dark | -0.369 |
Dark | -0.364 |
── | -0.361 |
inous | -0.353 |
Token | with |
Token ID | 351 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
ortium | +1.943 |
ania | +1.937 |
schild | +1.900 |
odder | +1.877 |
phabet | +1.829 |
Neg logit contributions | |
dark | -1.256 |
Dark | -1.244 |
Dark | -1.231 |
── | -1.231 |
inous | -1.188 |
Token | : |
Token ID | 25 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ortium | +0.132 |
ania | +0.127 |
schild | +0.126 |
odder | +0.124 |
phabet | +0.120 |
Neg logit contributions | |
dark | -0.147 |
Dark | -0.144 |
Dark | -0.144 |
── | -0.143 |
inous | -0.139 |
Token | Delicious |
Token ID | 39528 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
dark | +0.253 |
Dark | +0.252 |
Dark | +0.251 |
── | +0.251 |
| +0.242 |
Neg logit contributions | |
ortium | -0.247 |
ania | -0.243 |
schild | -0.237 |
odder | -0.232 |
ibel | -0.224 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
ania | +2.592 |
ortium | +2.551 |
schild | +2.450 |
odder | +2.448 |
ubb | +2.391 |
Neg logit contributions | |
dark | -2.682 |
── | -2.674 |
inous | -2.666 |
Dark | -2.666 |
Dark | -2.601 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Dark | +0.905 |
dark | +0.891 |
── | +0.890 |
Dark | +0.888 |
| +0.850 |
Neg logit contributions | |
ortium | -1.130 |
ania | -1.100 |
schild | -1.079 |
odder | -1.062 |
phabet | -1.046 |
Token | D |
Token ID | 35 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Dark | +0.993 |
dark | +0.982 |
Dark | +0.972 |
── | +0.968 |
inous | +0.938 |
Neg logit contributions | |
ortium | -1.062 |
ania | -1.049 |
schild | -1.018 |
odder | -0.986 |
ibel | -0.967 |
Token | igg |
Token ID | 6950 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
dark | +0.572 |
Dark | +0.572 |
Dark | +0.565 |
── | +0.560 |
inous | +0.554 |
Neg logit contributions | |
ortium | -0.547 |
ania | -0.533 |
schild | -0.523 |
odder | -0.506 |
phabet | -0.495 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
dark | +0.259 |
── | +0.258 |
Dark | +0.258 |
Dark | +0.253 |
inous | +0.252 |
Neg logit contributions | |
ania | -0.271 |
ortium | -0.271 |
schild | -0.262 |
odder | -0.261 |
phabet | -0.252 |
Token | v |
Token ID | 410 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ania | +0.625 |
ortium | +0.624 |
schild | +0.614 |
odder | +0.605 |
phabet | +0.585 |
Neg logit contributions | |
dark | -0.659 |
Dark | -0.656 |
Dark | -0.655 |
── | -0.651 |
inous | -0.634 |
Token | . |
Token ID | 13 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
ortium | +0.071 |
ania | +0.071 |
schild | +0.069 |
odder | +0.068 |
phabet | +0.066 |
Neg logit contributions | |
dark | -0.058 |
Dark | -0.058 |
── | -0.057 |
Dark | -0.057 |
inous | -0.056 |
Token | NFL |
Token ID | 5134 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ortium | +0.266 |
ania | +0.265 |
schild | +0.260 |
odder | +0.259 |
phabet | +0.252 |
Neg logit contributions | |
Dark | -0.201 |
dark | -0.199 |
Dark | -0.199 |
── | -0.197 |
inous | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ortium | +0.404 |
ania | +0.403 |
schild | +0.397 |
odder | +0.391 |
phabet | +0.381 |
Neg logit contributions | |
dark | -0.344 |
Dark | -0.344 |
Dark | -0.341 |
── | -0.339 |
inous | -0.333 |
Token |
|
Token ID | 198 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ortium | +0.888 |
ania | +0.884 |
schild | +0.860 |
odder | +0.851 |
phabet | +0.827 |
Neg logit contributions | |
dark | -0.796 |
Dark | -0.794 |
── | -0.791 |
Dark | -0.783 |
inous | -0.765 |
Token | Common |
Token ID | 17227 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ortium | +0.947 |
ania | +0.940 |
schild | +0.928 |
odder | +0.911 |
phabet | +0.887 |
Neg logit contributions | |
Dark | -0.782 |
── | -0.769 |
dark | -0.764 |
Dark | -0.756 |
inous | -0.738 |
Token | Bounty |
Token ID | 38166 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ortium | +3.040 |
ania | +3.001 |
schild | +2.923 |
odder | +2.889 |
phabet | +2.807 |
Neg logit contributions | |
── | -2.195 |
dark | -2.190 |
Dark | -2.173 |
Dark | -2.128 |
inous | -2.098 |
Token | gate |
Token ID | 10494 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ortium | +1.177 |
ania | +1.175 |
schild | +1.152 |
odder | +1.137 |
phabet | +1.105 |
Neg logit contributions | |
dark | -0.933 |
Dark | -0.931 |
Dark | -0.924 |
── | -0.922 |
inous | -0.898 |
Token | Lit |
Token ID | 25659 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
dark | +0.264 |
Dark | +0.263 |
Dark | +0.262 |
── | +0.260 |
inous | +0.253 |
Neg logit contributions | |
ania | -0.277 |
ortium | -0.277 |
schild | -0.272 |
odder | -0.269 |
phabet | -0.262 |
Token | igation |
Token ID | 7065 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Dark | +0.142 |
dark | +0.142 |
── | +0.140 |
Dark | +0.140 |
inous | +0.135 |
Neg logit contributions | |
ortium | -0.229 |
ania | -0.229 |
schild | -0.226 |
odder | -0.222 |
phabet | -0.216 |
Token | Q |
Token ID | 1195 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ortium | +0.796 |
ania | +0.794 |
schild | +0.780 |
odder | +0.769 |
phabet | +0.746 |
Neg logit contributions | |
dark | -0.715 |
Dark | -0.712 |
Dark | -0.710 |
── | -0.706 |
inous | -0.682 |
Token | 1941 |
Token ID | 23234 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
ortium | +0.380 |
ania | +0.376 |
schild | +0.369 |
odder | +0.363 |
phabet | +0.354 |
Neg logit contributions | |
dark | -0.362 |
Dark | -0.359 |
── | -0.358 |
Dark | -0.357 |
inous | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ortium | +0.042 |
ania | +0.042 |
schild | +0.041 |
odder | +0.041 |
phabet | +0.040 |
Neg logit contributions | |
dark | -0.031 |
Dark | -0.030 |
── | -0.030 |
Dark | -0.030 |
inous | -0.029 |
Token | Germany |
Token ID | 4486 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
ortium | +0.638 |
ania | +0.634 |
schild | +0.620 |
odder | +0.613 |
phabet | +0.596 |
Neg logit contributions | |
dark | -0.495 |
Dark | -0.489 |
Dark | -0.486 |
── | -0.486 |
inous | -0.472 |
Token | launched |
Token ID | 5611 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
ortium | +0.277 |
ania | +0.275 |
schild | +0.269 |
odder | +0.267 |
phabet | +0.260 |
Neg logit contributions | |
dark | -0.217 |
Dark | -0.215 |
── | -0.214 |
Dark | -0.213 |
inous | -0.208 |
Token | Operation |
Token ID | 14680 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
dark | +0.053 |
Dark | +0.052 |
── | +0.052 |
Dark | +0.052 |
inous | +0.050 |
Neg logit contributions | |
ortium | -0.065 |
ania | -0.064 |
schild | -0.063 |
odder | -0.062 |
phabet | -0.060 |
Token | Barbar |
Token ID | 45952 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ortium | +1.135 |
ania | +1.128 |
schild | +1.098 |
odder | +1.087 |
phabet | +1.058 |
Neg logit contributions | |
dark | -1.010 |
Dark | -1.006 |
── | -1.001 |
Dark | -0.999 |
inous | -0.968 |
Token | oss |
Token ID | 793 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ania | +1.678 |
ortium | +1.643 |
schild | +1.562 |
odder | +1.552 |
ubb | +1.471 |
Neg logit contributions | |
dark | -3.522 |
Dark | -3.516 |
── | -3.506 |
Dark | -3.478 |
inous | -3.425 |
Token | a |
Token ID | 64 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ortium | +0.313 |
ania | +0.303 |
schild | +0.297 |
odder | +0.293 |
phabet | +0.282 |
Neg logit contributions | |
dark | -0.456 |
Dark | -0.453 |
── | -0.451 |
Dark | -0.450 |
inous | -0.441 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
ortium | +0.501 |
ania | +0.499 |
schild | +0.487 |
odder | +0.482 |
phabet | +0.469 |
Neg logit contributions | |
dark | -0.388 |
Dark | -0.386 |
── | -0.385 |
Dark | -0.381 |
inous | -0.372 |
Token | an |
Token ID | 281 |
Feature activation | -2.11e-04 |
Pos logit contributions | |
ortium | +0.072 |
ania | +0.071 |
schild | +0.070 |
odder | +0.069 |
phabet | +0.067 |
Neg logit contributions | |
dark | -0.060 |
Dark | -0.059 |
Dark | -0.059 |
── | -0.059 |
inous | -0.057 |
Token | invasion |
Token ID | 11796 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
dark | +0.000 |
Dark | +0.000 |
── | +0.000 |
Dark | +0.000 |
inous | +0.000 |
Neg logit contributions | |
ortium | -0.001 |
ania | -0.001 |
schild | -0.001 |
odder | -0.001 |
phabet | -0.001 |
Token | in |
Token ID | 259 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
dark | +0.080 |
Dark | +0.079 |
Dark | +0.078 |
── | +0.078 |
inous | +0.077 |
Neg logit contributions | |
ortium | -0.098 |
ania | -0.097 |
schild | -0.095 |
odder | -0.095 |
phabet | -0.093 |
Token | said |
Token ID | 531 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ortium | +0.444 |
ania | +0.441 |
schild | +0.430 |
odder | +0.427 |
phabet | +0.415 |
Neg logit contributions | |
dark | -0.342 |
Dark | -0.340 |
── | -0.339 |
Dark | -0.337 |
inous | -0.328 |
Token | at |
Token ID | 379 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ortium | +0.470 |
ania | +0.469 |
schild | +0.457 |
odder | +0.452 |
phabet | +0.439 |
Neg logit contributions | |
dark | -0.364 |
Dark | -0.362 |
── | -0.361 |
Dark | -0.357 |
inous | -0.348 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ortium | +0.419 |
ania | +0.414 |
schild | +0.405 |
odder | +0.398 |
phabet | +0.388 |
Neg logit contributions | |
dark | -0.355 |
Dark | -0.349 |
Dark | -0.349 |
── | -0.348 |
inous | -0.335 |
Token | news |
Token ID | 1705 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ortium | +0.298 |
ania | +0.296 |
schild | +0.290 |
odder | +0.286 |
phabet | +0.278 |
Neg logit contributions | |
dark | -0.227 |
── | -0.223 |
Dark | -0.223 |
Dark | -0.222 |
inous | -0.213 |
Token | conference |
Token ID | 4495 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ortium | +1.099 |
ania | +1.094 |
schild | +1.066 |
odder | +1.057 |
phabet | +1.025 |
Neg logit contributions | |
dark | -0.830 |
Dark | -0.825 |
── | -0.820 |
Dark | -0.811 |
inous | -0.792 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ania | +2.856 |
ortium | +2.813 |
schild | +2.746 |
odder | +2.716 |
ibel | +2.638 |
Neg logit contributions | |
Dark | -2.294 |
dark | -2.270 |
── | -2.254 |
Dark | -2.235 |
inous | -2.218 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ortium | +0.332 |
ania | +0.329 |
schild | +0.322 |
odder | +0.318 |
phabet | +0.308 |
Neg logit contributions | |
dark | -0.278 |
Dark | -0.278 |
── | -0.277 |
Dark | -0.276 |
inous | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
Dark | +0.027 |
dark | +0.027 |
── | +0.027 |
Dark | +0.027 |
inous | +0.026 |
Neg logit contributions | |
ortium | -0.033 |
ania | -0.032 |
schild | -0.031 |
odder | -0.031 |
phabet | -0.030 |
Token | The |
Token ID | 464 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
ortium | +0.109 |
ania | +0.107 |
schild | +0.106 |
odder | +0.103 |
phabet | +0.100 |
Neg logit contributions | |
Dark | -0.081 |
── | -0.080 |
dark | -0.080 |
Dark | -0.078 |
inous | -0.076 |
Token | bill |
Token ID | 2855 |
Feature activation | -1.80e-05 |
Pos logit contributions | |
ania | +0.232 |
ortium | +0.232 |
schild | +0.227 |
odder | +0.224 |
phabet | +0.218 |
Neg logit contributions | |
dark | -0.151 |
── | -0.148 |
Dark | -0.148 |
Dark | -0.148 |
inous | -0.141 |
Token | described |
Token ID | 3417 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ortium | +0.327 |
ania | +0.325 |
schild | +0.317 |
odder | +0.314 |
phabet | +0.305 |
Neg logit contributions | |
dark | -0.257 |
Dark | -0.254 |
── | -0.253 |
Dark | -0.252 |
inous | -0.244 |
Token | earlier |
Token ID | 2961 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ortium | +1.225 |
ania | +1.221 |
schild | +1.186 |
odder | +1.174 |
phabet | +1.138 |
Neg logit contributions | |
dark | -1.094 |
Dark | -1.086 |
── | -1.084 |
Dark | -1.074 |
inous | -1.051 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
ortium | +1.084 |
ania | +1.080 |
schild | +1.050 |
odder | +1.040 |
phabet | +1.010 |
Neg logit contributions | |
dark | -0.893 |
Dark | -0.887 |
── | -0.885 |
Dark | -0.876 |
inous | -0.856 |
Token |
|
Token ID | 198 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
dark | +0.097 |
Dark | +0.096 |
── | +0.096 |
Dark | +0.096 |
inous | +0.092 |
Neg logit contributions | |
ortium | -0.122 |
ania | -0.122 |
schild | -0.119 |
odder | -0.118 |
phabet | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ortium | +0.113 |
ania | +0.112 |
schild | +0.109 |
odder | +0.108 |
phabet | +0.105 |
Neg logit contributions | |
dark | -0.097 |
Dark | -0.097 |
── | -0.096 |
Dark | -0.095 |
inous | -0.092 |
Token | (* |
Token ID | 46491 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ortium | +0.049 |
ania | +0.049 |
schild | +0.048 |
odder | +0.047 |
ibel | +0.046 |
Neg logit contributions | |
Dark | -0.040 |
── | -0.040 |
dark | -0.040 |
Dark | -0.039 |
inous | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
ania | +2.831 |
ortium | +2.824 |
schild | +2.742 |
odder | +2.715 |
phabet | +2.653 |
Neg logit contributions | |
Dark | -2.256 |
dark | -2.244 |
── | -2.241 |
Dark | -2.205 |
inous | -2.198 |
Token | the |
Token ID | 262 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
dark | +0.146 |
Dark | +0.143 |
── | +0.143 |
Dark | +0.142 |
inous | +0.138 |
Neg logit contributions | |
ortium | -0.187 |
ania | -0.185 |
schild | -0.181 |
odder | -0.179 |
phabet | -0.174 |
Token | it |
Token ID | 340 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
ortium | +0.244 |
ania | +0.243 |
schild | +0.238 |
odder | +0.235 |
phabet | +0.228 |
Neg logit contributions | |
dark | -0.195 |
Dark | -0.193 |
── | -0.192 |
Dark | -0.192 |
inous | -0.186 |
Token | h |
Token ID | 71 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ortium | +0.058 |
ania | +0.057 |
schild | +0.056 |
odder | +0.056 |
phabet | +0.054 |
Neg logit contributions | |
dark | -0.052 |
Dark | -0.051 |
── | -0.051 |
Dark | -0.051 |
inous | -0.050 |
Token | entry |
Token ID | 5726 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ortium | +0.669 |
ania | +0.663 |
schild | +0.651 |
odder | +0.643 |
phabet | +0.622 |
Neg logit contributions | |
dark | -0.540 |
Dark | -0.536 |
── | -0.532 |
Dark | -0.529 |
inous | -0.517 |
Token | ] |
Token ID | 60 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
ortium | +0.041 |
ania | +0.040 |
schild | +0.040 |
odder | +0.039 |
phabet | +0.039 |
Neg logit contributions | |
Dark | -0.034 |
dark | -0.034 |
── | -0.034 |
Dark | -0.034 |
inous | -0.033 |
Token | < |
Token ID | 1279 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
ortium | +1.430 |
ania | +1.429 |
schild | +1.378 |
odder | +1.364 |
phabet | +1.320 |
Neg logit contributions | |
dark | -1.614 |
Dark | -1.614 |
── | -1.608 |
Dark | -1.589 |
inous | -1.569 |
Token | k |
Token ID | 74 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ortium | +1.336 |
ania | +1.331 |
schild | +1.294 |
odder | +1.282 |
phabet | +1.241 |
Neg logit contributions | |
Dark | -1.259 |
dark | -1.256 |
── | -1.244 |
Dark | -1.234 |
inous | -1.209 |
Token | link |
Token ID | 8726 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ortium | +0.554 |
ania | +0.548 |
schild | +0.539 |
odder | +0.528 |
phabet | +0.515 |
Neg logit contributions | |
Dark | -0.575 |
dark | -0.574 |
── | -0.568 |
Dark | -0.565 |
inous | -0.558 |
Token | ttp |
Token ID | 29281 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
ortium | +0.920 |
ania | +0.916 |
schild | +0.898 |
odder | +0.884 |
phabet | +0.862 |
Neg logit contributions | |
Dark | -0.861 |
dark | -0.860 |
── | -0.848 |
Dark | -0.846 |
inous | -0.835 |
Token | > |
Token ID | 29 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ortium | +0.145 |
ania | +0.144 |
schild | +0.140 |
odder | +0.138 |
phabet | +0.135 |
Neg logit contributions | |
dark | -0.139 |
Dark | -0.139 |
── | -0.136 |
Dark | -0.136 |
inous | -0.134 |
Token | lol |
Token ID | 19462 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
ortium | +2.851 |
ania | +2.850 |
schild | +2.765 |
odder | +2.738 |
phabet | +2.669 |
Neg logit contributions | |
── | -2.050 |
Dark | -2.049 |
dark | -2.038 |
Dark | -1.996 |
inous | -1.992 |
Token | m |
Token ID | 285 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ortium | +0.134 |
ania | +0.133 |
schild | +0.130 |
odder | +0.128 |
phabet | +0.125 |
Neg logit contributions | |
dark | -0.098 |
Dark | -0.096 |
Dark | -0.096 |
── | -0.095 |
inous | -0.092 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
dark | +0.430 |
Dark | +0.430 |
Dark | +0.421 |
── | +0.420 |
inous | +0.407 |
Neg logit contributions | |
ortium | -0.589 |
ania | -0.573 |
schild | -0.568 |
odder | -0.562 |
phabet | -0.551 |
Token | k |
Token ID | 74 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
dark | +0.164 |
Dark | +0.163 |
── | +0.162 |
Dark | +0.161 |
inous | +0.157 |
Neg logit contributions | |
ortium | -0.103 |
ania | -0.100 |
schild | -0.096 |
odder | -0.096 |
phabet | -0.093 |
Token | [ |
Token ID | 685 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
dark | +0.128 |
Dark | +0.126 |
Dark | +0.125 |
── | +0.125 |
inous | +0.121 |
Neg logit contributions | |
ortium | -0.145 |
ania | -0.143 |
schild | -0.141 |
odder | -0.138 |
phabet | -0.135 |
Token | had |
Token ID | 550 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ortium | +0.679 |
ania | +0.677 |
schild | +0.659 |
odder | +0.653 |
phabet | +0.634 |
Neg logit contributions | |
dark | -0.546 |
Dark | -0.543 |
── | -0.541 |
Dark | -0.535 |
inous | -0.524 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ortium | +0.058 |
ania | +0.058 |
schild | +0.057 |
odder | +0.056 |
phabet | +0.055 |
Neg logit contributions | |
dark | -0.049 |
Dark | -0.048 |
── | -0.048 |
Dark | -0.048 |
inous | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
dark | +1.491 |
Dark | +1.449 |
── | +1.431 |
Dark | +1.414 |
inous | +1.358 |
Neg logit contributions | |
ortium | -1.849 |
schild | -1.821 |
ania | -1.806 |
odder | -1.798 |
phabet | -1.748 |
Token | marginally |
Token ID | 44108 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ortium | +0.171 |
ania | +0.170 |
schild | +0.166 |
odder | +0.164 |
phabet | +0.160 |
Neg logit contributions | |
dark | -0.121 |
Dark | -0.119 |
── | -0.119 |
Dark | -0.118 |
inous | -0.115 |
Token | lower |
Token ID | 2793 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
ortium | +0.279 |
ania | +0.277 |
schild | +0.269 |
odder | +0.266 |
phabet | +0.258 |
Neg logit contributions | |
dark | -0.249 |
Dark | -0.245 |
── | -0.243 |
Dark | -0.243 |
inous | -0.236 |
Token | blur |
Token ID | 23671 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ortium | +0.169 |
ania | +0.168 |
schild | +0.164 |
odder | +0.163 |
phabet | +0.159 |
Neg logit contributions | |
dark | -0.122 |
Dark | -0.120 |
── | -0.120 |
Dark | -0.119 |
inous | -0.115 |
Token | when |
Token ID | 618 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ortium | +2.804 |
ania | +2.801 |
schild | +2.724 |
odder | +2.698 |
phabet | +2.624 |
Neg logit contributions | |
dark | -2.129 |
Dark | -2.123 |
── | -2.116 |
Dark | -2.089 |
inous | -2.043 |
Token | running |
Token ID | 2491 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ortium | +0.758 |
ania | +0.755 |
schild | +0.736 |
odder | +0.729 |
phabet | +0.708 |
Neg logit contributions | |
dark | -0.584 |
Dark | -0.578 |
── | -0.575 |
Dark | -0.572 |
inous | -0.555 |
Token | at |
Token ID | 379 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
ortium | +0.803 |
ania | +0.801 |
schild | +0.780 |
odder | +0.773 |
phabet | +0.751 |
Neg logit contributions | |
dark | -0.594 |
Dark | -0.590 |
── | -0.587 |
Dark | -0.582 |
inous | -0.568 |
Token | 144 |
Token ID | 20224 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
dark | +0.172 |
Dark | +0.168 |
Dark | +0.168 |
── | +0.166 |
inous | +0.160 |
Neg logit contributions | |
ortium | -0.294 |
ania | -0.292 |
schild | -0.286 |
odder | -0.283 |
phabet | -0.277 |
Token | Hz |
Token ID | 7399 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
ania | +1.654 |
ortium | +1.653 |
schild | +1.608 |
odder | +1.594 |
phabet | +1.549 |
Neg logit contributions | |
dark | -1.229 |
Dark | -1.224 |
── | -1.221 |
Dark | -1.205 |
inous | -1.179 |
Token | here |
Token ID | 994 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
dark | +0.574 |
── | +0.570 |
Dark | +0.564 |
Dark | +0.559 |
inous | +0.538 |
Neg logit contributions | |
ortium | -0.924 |
ania | -0.916 |
schild | -0.898 |
odder | -0.891 |
phabet | -0.866 |
Token | , |
Token ID | 11 |
Feature activation | -8.87e-04 |
Pos logit contributions | |
dark | +0.073 |
── | +0.072 |
Dark | +0.072 |
Dark | +0.071 |
inous | +0.069 |
Neg logit contributions | |
ortium | -0.121 |
ania | -0.120 |
schild | -0.118 |
odder | -0.117 |
phabet | -0.113 |
Token | they |
Token ID | 484 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
dark | +0.002 |
Dark | +0.002 |
── | +0.002 |
Dark | +0.002 |
inous | +0.002 |
Neg logit contributions | |
ortium | -0.003 |
ania | -0.003 |
schild | -0.003 |
odder | -0.003 |
phabet | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
dark | +0.155 |
── | +0.154 |
Dark | +0.153 |
Dark | +0.151 |
inous | +0.148 |
Neg logit contributions | |
ortium | -0.210 |
ania | -0.209 |
schild | -0.204 |
odder | -0.203 |
phabet | -0.197 |
Token | expecting |
Token ID | 12451 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
dark | +0.153 |
Dark | +0.151 |
── | +0.151 |
Dark | +0.149 |
inous | +0.145 |
Neg logit contributions | |
ortium | -0.223 |
ania | -0.221 |
schild | -0.216 |
odder | -0.215 |
phabet | -0.209 |
Token | Git |
Token ID | 15151 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ortium | +0.296 |
ania | +0.294 |
schild | +0.287 |
odder | +0.284 |
phabet | +0.276 |
Neg logit contributions | |
dark | -0.228 |
Dark | -0.225 |
── | -0.225 |
Dark | -0.223 |
inous | -0.217 |
Token | mo |
Token ID | 5908 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
dark | +3.788 |
Dark | +3.746 |
Dark | +3.740 |
── | +3.733 |
inous | +3.660 |
Neg logit contributions | |
ortium | -2.108 |
schild | -2.079 |
odder | -2.007 |
phabet | -1.833 |
ania | -1.790 |
Token | criticisms |
Token ID | 25094 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
dark | +0.202 |
── | +0.202 |
Dark | +0.200 |
Dark | +0.198 |
inous | +0.190 |
Neg logit contributions | |
ortium | -0.319 |
ania | -0.315 |
schild | -0.311 |
odder | -0.308 |
phabet | -0.300 |
Token | of |
Token ID | 286 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
dark | +0.068 |
── | +0.068 |
Dark | +0.067 |
Dark | +0.067 |
inous | +0.064 |
Neg logit contributions | |
ortium | -0.093 |
ania | -0.093 |
schild | -0.091 |
odder | -0.090 |
phabet | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
dark | +0.110 |
── | +0.108 |
Dark | +0.107 |
Dark | +0.107 |
inous | +0.103 |
Neg logit contributions | |
ortium | -0.151 |
ania | -0.150 |
schild | -0.147 |
odder | -0.146 |
phabet | -0.142 |
Token | detainees |
Token ID | 25027 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
dark | +0.324 |
Dark | +0.315 |
── | +0.314 |
Dark | +0.313 |
inous | +0.298 |
Neg logit contributions | |
ortium | -0.505 |
ania | -0.504 |
schild | -0.493 |
odder | -0.490 |
phabet | -0.480 |
Token | , |
Token ID | 11 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
ortium | +0.401 |
ania | +0.399 |
schild | +0.390 |
odder | +0.386 |
phabet | +0.376 |
Neg logit contributions | |
dark | -0.292 |
Dark | -0.290 |
── | -0.289 |
Dark | -0.286 |
inous | -0.279 |
Token | police |
Token ID | 1644 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ortium | +0.134 |
ania | +0.134 |
schild | +0.131 |
odder | +0.130 |
phabet | +0.127 |
Neg logit contributions | |
dark | -0.061 |
Dark | -0.060 |
── | -0.060 |
Dark | -0.060 |
inous | -0.057 |
Token | arrested |
Token ID | 5169 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
dark | +0.442 |
Dark | +0.430 |
── | +0.430 |
Dark | +0.430 |
inous | +0.417 |
Neg logit contributions | |
ortium | -0.546 |
ania | -0.533 |
schild | -0.528 |
odder | -0.521 |
phabet | -0.507 |
Token | a |
Token ID | 257 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
ortium | +0.200 |
ania | +0.199 |
schild | +0.194 |
odder | +0.193 |
phabet | +0.188 |
Neg logit contributions | |
dark | -0.146 |
Dark | -0.143 |
── | -0.143 |
Dark | -0.143 |
inous | -0.138 |
Token | man |
Token ID | 582 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
dark | +0.181 |
Dark | +0.178 |
── | +0.178 |
Dark | +0.176 |
inous | +0.171 |
Neg logit contributions | |
ortium | -0.293 |
ania | -0.291 |
schild | -0.285 |
odder | -0.282 |
phabet | -0.275 |
Token | wearing |
Token ID | 5762 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
dark | +0.360 |
── | +0.353 |
Dark | +0.351 |
Dark | +0.351 |
inous | +0.339 |
Neg logit contributions | |
ortium | -0.543 |
ania | -0.538 |
schild | -0.528 |
odder | -0.525 |
phabet | -0.514 |
Token | a |
Token ID | 257 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
dark | +2.530 |
Dark | +2.399 |
Dark | +2.368 |
── | +2.323 |
inous | +2.224 |
Neg logit contributions | |
ortium | -3.237 |
ania | -3.236 |
schild | -3.177 |
odder | -3.125 |
phabet | -3.105 |
Token | Trump |
Token ID | 1301 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
dark | +0.078 |
Dark | +0.076 |
── | +0.076 |
Dark | +0.075 |
inous | +0.073 |
Neg logit contributions | |
ortium | -0.148 |
ania | -0.148 |
schild | -0.145 |
odder | -0.144 |
phabet | -0.140 |
Token | shirt |
Token ID | 10147 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
dark | +0.069 |
Dark | +0.068 |
── | +0.068 |
Dark | +0.068 |
inous | +0.066 |
Neg logit contributions | |
ortium | -0.111 |
ania | -0.111 |
schild | -0.108 |
odder | -0.107 |
phabet | -0.105 |
Token | after |
Token ID | 706 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
dark | +0.168 |
── | +0.165 |
Dark | +0.165 |
Dark | +0.163 |
inous | +0.159 |
Neg logit contributions | |
ortium | -0.239 |
ania | -0.237 |
schild | -0.232 |
odder | -0.230 |
phabet | -0.225 |
Token | he |
Token ID | 339 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
dark | +0.468 |
Dark | +0.460 |
── | +0.459 |
Dark | +0.456 |
inous | +0.440 |
Neg logit contributions | |
ortium | -0.706 |
ania | -0.701 |
schild | -0.685 |
odder | -0.678 |
phabet | -0.663 |
Token | Sa |
Token ID | 10318 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
ania | +0.187 |
ortium | +0.187 |
schild | +0.182 |
odder | +0.180 |
phabet | +0.174 |
Neg logit contributions | |
dark | -0.156 |
Dark | -0.156 |
── | -0.155 |
Dark | -0.154 |
inous | -0.149 |
Token | � |
Token ID | 447 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
dark | +0.006 |
Dark | +0.006 |
── | +0.006 |
Dark | +0.006 |
inous | +0.006 |
Neg logit contributions | |
ortium | -0.011 |
ania | -0.011 |
schild | -0.011 |
odder | -0.011 |
phabet | -0.010 |
Token | � |
Token ID | 246 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ortium | +0.523 |
ania | +0.522 |
schild | +0.510 |
odder | +0.506 |
phabet | +0.494 |
Neg logit contributions | |
dark | -0.276 |
Dark | -0.274 |
── | -0.273 |
Dark | -0.269 |
inous | -0.262 |
Token | d |
Token ID | 67 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
ortium | +0.614 |
ania | +0.606 |
schild | +0.591 |
odder | +0.588 |
phabet | +0.570 |
Neg logit contributions | |
dark | -0.527 |
Dark | -0.525 |
── | -0.524 |
Dark | -0.518 |
inous | -0.507 |
Token | 's |
Token ID | 338 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
dark | +0.126 |
── | +0.125 |
Dark | +0.125 |
Dark | +0.123 |
inous | +0.120 |
Neg logit contributions | |
ortium | -0.169 |
ania | -0.166 |
schild | -0.163 |
odder | -0.162 |
phabet | -0.157 |
Token | judgment |
Token ID | 8492 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
dark | +0.118 |
Dark | +0.116 |
── | +0.116 |
Dark | +0.116 |
inous | +0.112 |
Neg logit contributions | |
ortium | -0.139 |
ania | -0.138 |
schild | -0.134 |
odder | -0.133 |
phabet | -0.129 |
Token | was |
Token ID | 373 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
dark | +2.457 |
── | +2.453 |
Dark | +2.378 |
Dark | +2.375 |
inous | +2.298 |
Neg logit contributions | |
ortium | -3.138 |
ania | -3.121 |
odder | -3.060 |
schild | -3.057 |
phabet | -2.919 |
Token | no |
Token ID | 645 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
dark | +0.578 |
── | +0.570 |
Dark | +0.567 |
Dark | +0.565 |
inous | +0.545 |
Neg logit contributions | |
ortium | -0.741 |
ania | -0.734 |
schild | -0.722 |
odder | -0.717 |
phabet | -0.694 |
Token | doubt |
Token ID | 4719 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
dark | +0.102 |
── | +0.100 |
Dark | +0.100 |
Dark | +0.100 |
inous | +0.096 |
Neg logit contributions | |
ortium | -0.137 |
ania | -0.136 |
schild | -0.134 |
odder | -0.132 |
phabet | -0.128 |
Token | directed |
Token ID | 7924 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
dark | +0.726 |
── | +0.712 |
Dark | +0.706 |
Dark | +0.705 |
inous | +0.680 |
Neg logit contributions | |
ortium | -0.994 |
ania | -0.982 |
schild | -0.971 |
odder | -0.962 |
phabet | -0.933 |
Token | mainly |
Token ID | 8384 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
dark | +0.339 |
── | +0.333 |
Dark | +0.333 |
Dark | +0.329 |
inous | +0.320 |
Neg logit contributions | |
ortium | -0.566 |
ania | -0.563 |
schild | -0.552 |
odder | -0.548 |
phabet | -0.532 |
Token | a |
Token ID | 257 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
dark | +0.064 |
Dark | +0.063 |
── | +0.063 |
Dark | +0.062 |
inous | +0.061 |
Neg logit contributions | |
ortium | -0.084 |
ania | -0.083 |
schild | -0.081 |
odder | -0.080 |
phabet | -0.079 |
Token | group |
Token ID | 1448 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
dark | +0.253 |
Dark | +0.247 |
Dark | +0.247 |
── | +0.246 |
inous | +0.237 |
Neg logit contributions | |
ortium | -0.367 |
ania | -0.363 |
schild | -0.356 |
odder | -0.353 |
phabet | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
ortium | +0.111 |
ania | +0.110 |
schild | +0.108 |
odder | +0.107 |
phabet | +0.104 |
Neg logit contributions | |
dark | -0.076 |
Dark | -0.075 |
── | -0.075 |
Dark | -0.074 |
inous | -0.072 |
Token | classmates |
Token ID | 28999 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
dark | +0.143 |
Dark | +0.140 |
── | +0.140 |
Dark | +0.140 |
inous | +0.135 |
Neg logit contributions | |
ortium | -0.226 |
ania | -0.225 |
schild | -0.220 |
odder | -0.218 |
phabet | -0.213 |
Token | who |
Token ID | 508 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
dark | +0.537 |
── | +0.530 |
Dark | +0.523 |
Dark | +0.522 |
inous | +0.504 |
Neg logit contributions | |
ortium | -0.866 |
ania | -0.856 |
schild | -0.843 |
odder | -0.835 |
phabet | -0.819 |
Token | wore |
Token ID | 12408 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ortium | +0.642 |
ania | +0.639 |
schild | +0.623 |
odder | +0.617 |
phabet | +0.600 |
Neg logit contributions | |
dark | -0.518 |
Dark | -0.514 |
── | -0.513 |
Dark | -0.507 |
inous | -0.497 |
Token | small |
Token ID | 1402 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
dark | +2.296 |
Dark | +2.168 |
Dark | +2.134 |
── | +2.113 |
inous | +2.012 |
Neg logit contributions | |
ortium | -3.405 |
ania | -3.370 |
schild | -3.360 |
odder | -3.286 |
phabet | -3.246 |
Token | s |
Token ID | 264 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ortium | +0.315 |
ania | +0.315 |
schild | +0.308 |
odder | +0.304 |
phabet | +0.297 |
Neg logit contributions | |
dark | -0.203 |
Dark | -0.201 |
── | -0.200 |
Dark | -0.198 |
inous | -0.193 |
Token | omb |
Token ID | 2381 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
dark | +0.069 |
Dark | +0.068 |
── | +0.068 |
Dark | +0.067 |
inous | +0.066 |
Neg logit contributions | |
ortium | -0.083 |
ania | -0.082 |
schild | -0.080 |
odder | -0.079 |
phabet | -0.077 |
Token | rero |
Token ID | 34785 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ortium | +0.383 |
ania | +0.375 |
schild | +0.370 |
odder | +0.367 |
phabet | +0.358 |
Neg logit contributions | |
dark | -0.291 |
Dark | -0.287 |
Dark | -0.284 |
inous | -0.281 |
── | -0.281 |
Token | hats |
Token ID | 23910 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
dark | +0.337 |
Dark | +0.336 |
── | +0.334 |
Dark | +0.331 |
inous | +0.324 |
Neg logit contributions | |
ortium | -0.435 |
ania | -0.434 |
schild | -0.423 |
odder | -0.419 |
phabet | -0.407 |
Token | satisf |
Token ID | 5244 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
dark | +0.063 |
Dark | +0.062 |
── | +0.062 |
Dark | +0.061 |
inous | +0.060 |
Neg logit contributions | |
ortium | -0.084 |
ania | -0.084 |
schild | -0.082 |
odder | -0.081 |
phabet | -0.079 |
Token | actor |
Token ID | 11218 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
── | +0.638 |
Dark | +0.638 |
dark | +0.637 |
Dark | +0.630 |
inous | +0.615 |
Neg logit contributions | |
ortium | -0.382 |
ania | -0.370 |
schild | -0.360 |
odder | -0.358 |
phabet | -0.343 |
Token | ily |
Token ID | 813 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
dark | +0.340 |
── | +0.337 |
Dark | +0.336 |
Dark | +0.330 |
inous | +0.320 |
Neg logit contributions | |
ortium | -0.701 |
ania | -0.690 |
schild | -0.676 |
odder | -0.675 |
phabet | -0.661 |
Token | all |
Token ID | 477 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ortium | +0.918 |
ania | +0.917 |
schild | +0.891 |
odder | +0.882 |
phabet | +0.859 |
Neg logit contributions | |
dark | -0.703 |
Dark | -0.702 |
── | -0.697 |
Dark | -0.690 |
inous | -0.677 |
Token | D |
Token ID | 360 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
dark | +0.286 |
Dark | +0.283 |
── | +0.280 |
Dark | +0.280 |
inous | +0.271 |
Neg logit contributions | |
ortium | -0.414 |
ania | -0.413 |
schild | -0.403 |
odder | -0.400 |
phabet | -0.389 |
Token | DoS |
Token ID | 46498 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
dark | +0.662 |
Dark | +0.660 |
── | +0.652 |
Dark | +0.645 |
inous | +0.625 |
Neg logit contributions | |
ortium | -1.341 |
ania | -1.332 |
schild | -1.308 |
odder | -1.292 |
phabet | -1.265 |
Token | traffic |
Token ID | 4979 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
dark | +1.815 |
Dark | +1.771 |
Dark | +1.766 |
── | +1.737 |
inous | +1.645 |
Neg logit contributions | |
ortium | -3.741 |
ania | -3.703 |
schild | -3.644 |
odder | -3.598 |
phabet | -3.526 |
Token | would |
Token ID | 561 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
dark | +0.339 |
Dark | +0.337 |
── | +0.335 |
Dark | +0.332 |
inous | +0.324 |
Neg logit contributions | |
ortium | -0.450 |
ania | -0.448 |
schild | -0.437 |
odder | -0.433 |
phabet | -0.421 |
Token | be |
Token ID | 307 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
dark | +0.180 |
Dark | +0.178 |
── | +0.178 |
Dark | +0.176 |
inous | +0.172 |
Neg logit contributions | |
ortium | -0.216 |
ania | -0.215 |
schild | -0.210 |
odder | -0.207 |
phabet | -0.202 |
Token | mit |
Token ID | 10255 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
dark | +0.462 |
Dark | +0.452 |
Dark | +0.450 |
── | +0.449 |
inous | +0.429 |
Neg logit contributions | |
ortium | -0.725 |
ania | -0.716 |
schild | -0.703 |
odder | -0.699 |
phabet | -0.683 |
Token | igated |
Token ID | 26963 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
dark | +1.532 |
── | +1.494 |
Dark | +1.485 |
Dark | +1.484 |
inous | +1.449 |
Neg logit contributions | |
ortium | -2.361 |
ania | -2.354 |
schild | -2.327 |
odder | -2.290 |
phabet | -2.273 |
Token | seeking |
Token ID | 6095 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ortium | +0.171 |
ania | +0.168 |
schild | +0.166 |
odder | +0.165 |
phabet | +0.160 |
Neg logit contributions | |
dark | -0.122 |
Dark | -0.118 |
Dark | -0.118 |
── | -0.118 |
inous | -0.114 |
Token | rate |
Token ID | 2494 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
dark | +0.231 |
── | +0.223 |
Dark | +0.223 |
Dark | +0.221 |
inous | +0.213 |
Neg logit contributions | |
ortium | -0.327 |
ania | -0.324 |
schild | -0.323 |
odder | -0.314 |
phabet | -0.305 |
Token | increases |
Token ID | 5732 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
dark | +0.531 |
── | +0.521 |
Dark | +0.513 |
Dark | +0.509 |
inous | +0.481 |
Neg logit contributions | |
ortium | -1.299 |
ania | -1.291 |
schild | -1.276 |
odder | -1.247 |
phabet | -1.214 |
Token | well |
Token ID | 880 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
dark | +0.733 |
── | +0.719 |
Dark | +0.707 |
Dark | +0.695 |
inous | +0.679 |
Neg logit contributions | |
ortium | -1.092 |
ania | -1.071 |
schild | -1.064 |
odder | -1.042 |
phabet | -1.023 |
Token | in |
Token ID | 287 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
ortium | +0.115 |
ania | +0.113 |
schild | +0.112 |
odder | +0.110 |
phabet | +0.108 |
Neg logit contributions | |
dark | -0.062 |
── | -0.061 |
Dark | -0.059 |
Dark | -0.059 |
inous | -0.057 |
Token | excess |
Token ID | 6992 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ortium | +0.300 |
ania | +0.298 |
schild | +0.292 |
odder | +0.288 |
phabet | +0.282 |
Neg logit contributions | |
dark | -0.150 |
Dark | -0.147 |
── | -0.146 |
Dark | -0.145 |
inous | -0.140 |
Token | of |
Token ID | 286 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
dark | +1.971 |
── | +1.895 |
Dark | +1.891 |
Dark | +1.830 |
inous | +1.759 |
Neg logit contributions | |
ortium | -3.520 |
ania | -3.450 |
odder | -3.409 |
schild | -3.389 |
phabet | -3.321 |
Token | the |
Token ID | 262 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ortium | +0.401 |
ania | +0.400 |
schild | +0.392 |
odder | +0.388 |
phabet | +0.375 |
Neg logit contributions | |
dark | -0.300 |
── | -0.295 |
Dark | -0.294 |
Dark | -0.294 |
inous | -0.283 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ortium | +0.168 |
ania | +0.167 |
schild | +0.164 |
odder | +0.162 |
phabet | +0.157 |
Neg logit contributions | |
dark | -0.135 |
── | -0.133 |
Dark | -0.133 |
Dark | -0.132 |
inous | -0.128 |
Token | of |
Token ID | 286 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
dark | +0.036 |
── | +0.036 |
Dark | +0.036 |
Dark | +0.036 |
inous | +0.034 |
Neg logit contributions | |
ortium | -0.045 |
ania | -0.045 |
schild | -0.045 |
odder | -0.043 |
phabet | -0.042 |
Token | inflation |
Token ID | 10610 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
dark | +0.141 |
── | +0.139 |
Dark | +0.138 |
Dark | +0.137 |
inous | +0.133 |
Neg logit contributions | |
ortium | -0.222 |
ania | -0.221 |
schild | -0.216 |
odder | -0.213 |
phabet | -0.208 |
Token | future |
Token ID | 2003 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ortium | +0.160 |
ania | +0.159 |
schild | +0.156 |
odder | +0.154 |
phabet | +0.150 |
Neg logit contributions | |
dark | -0.131 |
── | -0.129 |
Dark | -0.129 |
Dark | -0.128 |
inous | -0.125 |
Token | projections |
Token ID | 19887 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
dark | +0.493 |
── | +0.484 |
Dark | +0.483 |
Dark | +0.483 |
inous | +0.467 |
Neg logit contributions | |
ortium | -0.620 |
ania | -0.617 |
schild | -0.602 |
odder | -0.593 |
phabet | -0.582 |
Token | . |
Token ID | 13 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
ortium | +0.117 |
ania | +0.116 |
schild | +0.113 |
odder | +0.112 |
phabet | +0.110 |
Neg logit contributions | |
dark | -0.087 |
── | -0.085 |
Dark | -0.085 |
Dark | -0.084 |
inous | -0.082 |
Token | In |
Token ID | 554 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ortium | +0.011 |
ania | +0.010 |
schild | +0.010 |
odder | +0.010 |
phabet | +0.010 |
Neg logit contributions | |
Dark | -0.009 |
Dark | -0.009 |
dark | -0.009 |
── | -0.008 |
inous | -0.008 |
Token | these |
Token ID | 777 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
dark | +0.264 |
Dark | +0.259 |
Dark | +0.259 |
── | +0.256 |
inous | +0.248 |
Neg logit contributions | |
ortium | -0.291 |
ania | -0.286 |
schild | -0.277 |
odder | -0.273 |
phabet | -0.269 |
Token | cases |
Token ID | 2663 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ortium | +0.121 |
ania | +0.120 |
schild | +0.117 |
odder | +0.116 |
phabet | +0.113 |
Neg logit contributions | |
dark | -0.082 |
Dark | -0.080 |
── | -0.080 |
Dark | -0.080 |
inous | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
dark | +2.220 |
── | +2.179 |
Dark | +2.171 |
Dark | +2.162 |
inous | +2.085 |
Neg logit contributions | |
ortium | -3.207 |
ania | -3.193 |
schild | -3.125 |
odder | -3.101 |
phabet | -2.997 |
Token | it |
Token ID | 340 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
dark | +0.232 |
Dark | +0.227 |
Dark | +0.226 |
── | +0.226 |
inous | +0.218 |
Neg logit contributions | |
ortium | -0.289 |
ania | -0.287 |
schild | -0.280 |
odder | -0.277 |
phabet | -0.269 |
Token | seems |
Token ID | 2331 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
dark | +0.094 |
Dark | +0.093 |
── | +0.093 |
Dark | +0.092 |
inous | +0.089 |
Neg logit contributions | |
ortium | -0.131 |
ania | -0.130 |
schild | -0.127 |
odder | -0.126 |
phabet | -0.123 |
Token | like |
Token ID | 588 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
dark | +0.126 |
Dark | +0.124 |
── | +0.124 |
Dark | +0.123 |
inous | +0.119 |
Neg logit contributions | |
ortium | -0.167 |
ania | -0.166 |
schild | -0.162 |
odder | -0.160 |
phabet | -0.156 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
dark | +0.110 |
Dark | +0.108 |
── | +0.108 |
Dark | +0.107 |
inous | +0.104 |
Neg logit contributions | |
ortium | -0.137 |
ania | -0.137 |
schild | -0.133 |
odder | -0.132 |
phabet | -0.128 |
Token | be |
Token ID | 307 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
dark | +0.136 |
── | +0.134 |
Dark | +0.133 |
Dark | +0.133 |
inous | +0.129 |
Neg logit contributions | |
ortium | -0.158 |
ania | -0.157 |
schild | -0.153 |
odder | -0.152 |
phabet | -0.148 |
Token | a |
Token ID | 257 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
dark | +0.022 |
Dark | +0.021 |
── | +0.021 |
Dark | +0.021 |
inous | +0.020 |
Neg logit contributions | |
ortium | -0.028 |
ania | -0.028 |
schild | -0.027 |
odder | -0.027 |
phabet | -0.026 |
Token | good |
Token ID | 922 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
dark | +0.140 |
Dark | +0.137 |
── | +0.136 |
Dark | +0.136 |
inous | +0.131 |
Neg logit contributions | |
ortium | -0.212 |
ania | -0.211 |
schild | -0.206 |
odder | -0.204 |
phabet | -0.199 |
Token | plan |
Token ID | 1410 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
dark | +0.123 |
── | +0.121 |
Dark | +0.120 |
Dark | +0.120 |
inous | +0.116 |
Neg logit contributions | |
ortium | -0.158 |
ania | -0.157 |
schild | -0.153 |
odder | -0.151 |
phabet | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
dark | +0.315 |
── | +0.313 |
Dark | +0.310 |
Dark | +0.309 |
inous | +0.296 |
Neg logit contributions | |
ortium | -0.441 |
ania | -0.439 |
schild | -0.428 |
odder | -0.421 |
phabet | -0.413 |
Token | except |
Token ID | 2845 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
dark | +0.378 |
Dark | +0.370 |
Dark | +0.369 |
── | +0.367 |
inous | +0.350 |
Neg logit contributions | |
ortium | -0.460 |
ania | -0.457 |
schild | -0.445 |
odder | -0.439 |
phabet | -0.427 |
Token | the |
Token ID | 262 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
dark | +2.363 |
Dark | +2.321 |
── | +2.320 |
Dark | +2.281 |
inous | +2.165 |
Neg logit contributions | |
ortium | -3.104 |
ania | -3.038 |
schild | -2.997 |
odder | -2.951 |
phabet | -2.860 |
Token | format |
Token ID | 5794 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
dark | +0.188 |
Dark | +0.185 |
Dark | +0.184 |
── | +0.183 |
inous | +0.177 |
Neg logit contributions | |
ortium | -0.228 |
ania | -0.226 |
schild | -0.221 |
odder | -0.219 |
phabet | -0.213 |
Token | bar |
Token ID | 2318 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
dark | +0.751 |
Dark | +0.741 |
── | +0.738 |
Dark | +0.736 |
inous | +0.714 |
Neg logit contributions | |
ortium | -0.697 |
ania | -0.687 |
schild | -0.669 |
odder | -0.662 |
phabet | -0.637 |
Token | is |
Token ID | 318 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ortium | +0.789 |
ania | +0.788 |
schild | +0.766 |
odder | +0.759 |
phabet | +0.738 |
Neg logit contributions | |
dark | -0.599 |
Dark | -0.597 |
── | -0.594 |
Dark | -0.587 |
inous | -0.575 |
Token | now |
Token ID | 783 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
dark | +0.440 |
── | +0.432 |
Dark | +0.431 |
Dark | +0.428 |
inous | +0.413 |
Neg logit contributions | |
ortium | -0.601 |
ania | -0.595 |
schild | -0.583 |
odder | -0.579 |
phabet | -0.563 |
Token | would |
Token ID | 561 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
dark | +0.239 |
── | +0.235 |
Dark | +0.234 |
Dark | +0.233 |
inous | +0.228 |
Neg logit contributions | |
ortium | -0.313 |
ania | -0.311 |
schild | -0.305 |
odder | -0.304 |
phabet | -0.294 |
Token | indeed |
Token ID | 5600 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
dark | +0.042 |
── | +0.041 |
Dark | +0.041 |
Dark | +0.041 |
inous | +0.040 |
Neg logit contributions | |
ortium | -0.053 |
ania | -0.052 |
schild | -0.051 |
odder | -0.051 |
phabet | -0.049 |
Token | abide |
Token ID | 27851 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ortium | +0.692 |
ania | +0.690 |
schild | +0.672 |
odder | +0.666 |
phabet | +0.647 |
Neg logit contributions | |
dark | -0.535 |
Dark | -0.532 |
── | -0.530 |
Dark | -0.525 |
inous | -0.513 |
Token | by |
Token ID | 416 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
dark | +0.948 |
── | +0.931 |
Dark | +0.922 |
Dark | +0.921 |
inous | +0.884 |
Neg logit contributions | |
ortium | -1.173 |
ania | -1.138 |
schild | -1.133 |
odder | -1.120 |
phabet | -1.078 |
Token | his |
Token ID | 465 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ortium | +0.075 |
ania | +0.074 |
schild | +0.073 |
odder | +0.072 |
phabet | +0.070 |
Neg logit contributions | |
dark | -0.060 |
── | -0.059 |
Dark | -0.059 |
Dark | -0.059 |
inous | -0.057 |
Token | judgment |
Token ID | 8492 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
dark | +0.640 |
Dark | +0.625 |
Dark | +0.623 |
── | +0.622 |
inous | +0.598 |
Neg logit contributions | |
ortium | -0.829 |
ania | -0.821 |
odder | -0.801 |
schild | -0.801 |
phabet | -0.781 |
Token | , |
Token ID | 11 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
── | +2.113 |
dark | +2.104 |
Dark | +2.027 |
Dark | +2.005 |
inous | +1.964 |
Neg logit contributions | |
ortium | -3.215 |
ania | -3.167 |
odder | -3.117 |
schild | -3.094 |
phabet | -2.997 |
Token | Sa |
Token ID | 10318 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
ortium | +0.202 |
ania | +0.201 |
schild | +0.197 |
odder | +0.195 |
phabet | +0.188 |
Neg logit contributions | |
dark | -0.153 |
Dark | -0.151 |
── | -0.151 |
Dark | -0.150 |
inous | -0.145 |
Token | � |
Token ID | 447 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
dark | +0.065 |
Dark | +0.065 |
── | +0.065 |
Dark | +0.064 |
inous | +0.062 |
Neg logit contributions | |
ortium | -0.133 |
ania | -0.132 |
schild | -0.130 |
odder | -0.128 |
phabet | -0.125 |
Token | � |
Token ID | 246 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
ortium | +0.453 |
ania | +0.452 |
schild | +0.441 |
odder | +0.437 |
phabet | +0.426 |
Neg logit contributions | |
dark | -0.286 |
Dark | -0.284 |
── | -0.283 |
Dark | -0.279 |
inous | -0.273 |
Token | d |
Token ID | 67 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ortium | +1.031 |
ania | +1.026 |
schild | +1.000 |
odder | +0.991 |
phabet | +0.965 |
Neg logit contributions | |
dark | -0.773 |
Dark | -0.771 |
── | -0.767 |
Dark | -0.758 |
inous | -0.741 |
Token | company |
Token ID | 1664 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ortium | +0.051 |
ania | +0.051 |
schild | +0.050 |
odder | +0.050 |
phabet | +0.048 |
Neg logit contributions | |
dark | -0.035 |
Dark | -0.034 |
── | -0.034 |
Dark | -0.034 |
inous | -0.033 |
Token | � |
Token ID | 447 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
dark | +0.627 |
Dark | +0.619 |
── | +0.618 |
Dark | +0.614 |
inous | +0.594 |
Neg logit contributions | |
ortium | -0.884 |
ania | -0.883 |
schild | -0.866 |
odder | -0.857 |
phabet | -0.836 |
Token | � |
Token ID | 247 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
ortium | +0.116 |
ania | +0.115 |
schild | +0.112 |
odder | +0.111 |
phabet | +0.108 |
Neg logit contributions | |
dark | -0.070 |
── | -0.070 |
Dark | -0.070 |
Dark | -0.068 |
inous | -0.066 |
Token | s |
Token ID | 82 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
ortium | +0.101 |
ania | +0.101 |
schild | +0.098 |
odder | +0.097 |
phabet | +0.094 |
Neg logit contributions | |
dark | -0.080 |
── | -0.080 |
Dark | -0.080 |
Dark | -0.079 |
inous | -0.077 |
Token | D |
Token ID | 360 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
dark | +0.088 |
Dark | +0.086 |
Dark | +0.086 |
── | +0.086 |
inous | +0.082 |
Neg logit contributions | |
ortium | -0.148 |
ania | -0.148 |
schild | -0.145 |
odder | -0.143 |
phabet | -0.140 |
Token | DoS |
Token ID | 46498 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
dark | +0.761 |
Dark | +0.751 |
── | +0.740 |
Dark | +0.738 |
inous | +0.708 |
Neg logit contributions | |
ortium | -1.489 |
ania | -1.460 |
schild | -1.448 |
odder | -1.429 |
phabet | -1.396 |
Token | mitigation |
Token ID | 33585 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
dark | +2.139 |
Dark | +2.100 |
Dark | +2.098 |
── | +2.066 |
inous | +1.948 |
Neg logit contributions | |
ortium | -3.119 |
ania | -3.089 |
schild | -3.015 |
odder | -2.968 |
phabet | -2.917 |
Token | defenses |
Token ID | 18370 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
dark | +0.214 |
── | +0.209 |
Dark | +0.209 |
Dark | +0.208 |
inous | +0.195 |
Neg logit contributions | |
ortium | -0.416 |
ania | -0.416 |
schild | -0.408 |
odder | -0.405 |
phabet | -0.396 |
Token | to |
Token ID | 284 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
dark | +0.244 |
── | +0.242 |
Dark | +0.241 |
Dark | +0.239 |
inous | +0.230 |
Neg logit contributions | |
ania | -0.324 |
ortium | -0.322 |
schild | -0.315 |
odder | -0.313 |
phabet | -0.304 |
Token | penetrate |
Token ID | 28302 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
dark | +0.038 |
Dark | +0.037 |
── | +0.037 |
Dark | +0.037 |
inous | +0.036 |
Neg logit contributions | |
ortium | -0.053 |
ania | -0.052 |
schild | -0.051 |
odder | -0.051 |
phabet | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
dark | +0.793 |
Dark | +0.780 |
── | +0.776 |
Dark | +0.776 |
inous | +0.741 |
Neg logit contributions | |
ortium | -1.024 |
ania | -1.019 |
schild | -0.996 |
odder | -0.987 |
phabet | -0.956 |
Token | understand |
Token ID | 1833 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ortium | +0.825 |
ania | +0.824 |
schild | +0.798 |
odder | +0.788 |
phabet | +0.761 |
Neg logit contributions | |
Dark | -0.878 |
dark | -0.877 |
── | -0.873 |
Dark | -0.864 |
inous | -0.852 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ortium | +0.281 |
ania | +0.280 |
schild | +0.273 |
odder | +0.270 |
phabet | +0.262 |
Neg logit contributions | |
dark | -0.247 |
Dark | -0.245 |
── | -0.244 |
Dark | -0.243 |
inous | -0.236 |
Token | complexity |
Token ID | 13357 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ortium | +0.033 |
ania | +0.033 |
schild | +0.032 |
odder | +0.031 |
phabet | +0.031 |
Neg logit contributions | |
dark | -0.027 |
Dark | -0.026 |
── | -0.026 |
Dark | -0.026 |
inous | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
dark | +0.322 |
── | +0.317 |
Dark | +0.316 |
Dark | +0.314 |
inous | +0.303 |
Neg logit contributions | |
ortium | -0.460 |
ania | -0.457 |
schild | -0.445 |
odder | -0.445 |
phabet | -0.431 |
Token | D |
Token ID | 360 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ania | +0.340 |
ortium | +0.339 |
schild | +0.328 |
odder | +0.326 |
ibel | +0.317 |
Neg logit contributions | |
── | -0.245 |
Dark | -0.245 |
dark | -0.242 |
Dark | -0.238 |
inous | -0.237 |
Token | DoS |
Token ID | 46498 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
dark | +0.515 |
Dark | +0.514 |
── | +0.506 |
Dark | +0.501 |
inous | +0.485 |
Neg logit contributions | |
ortium | -1.059 |
ania | -1.051 |
schild | -1.033 |
odder | -1.019 |
phabet | -0.999 |
Token | attacks |
Token ID | 3434 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
dark | +1.871 |
Dark | +1.834 |
Dark | +1.822 |
── | +1.805 |
inous | +1.715 |
Neg logit contributions | |
ortium | -3.351 |
ania | -3.310 |
schild | -3.253 |
odder | -3.221 |
phabet | -3.148 |
Token | pose |
Token ID | 12705 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
dark | +0.493 |
── | +0.483 |
Dark | +0.482 |
Dark | +0.479 |
inous | +0.464 |
Neg logit contributions | |
ortium | -0.757 |
ania | -0.753 |
schild | -0.738 |
odder | -0.732 |
phabet | -0.717 |
Token | for |
Token ID | 329 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
dark | +0.122 |
Dark | +0.121 |
── | +0.121 |
Dark | +0.120 |
inous | +0.116 |
Neg logit contributions | |
ortium | -0.168 |
ania | -0.167 |
schild | -0.163 |
odder | -0.162 |
phabet | -0.157 |
Token | mitigation |
Token ID | 33585 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
ortium | +0.345 |
ania | +0.344 |
schild | +0.336 |
odder | +0.334 |
phabet | +0.325 |
Neg logit contributions | |
dark | -0.221 |
Dark | -0.218 |
── | -0.217 |
Dark | -0.217 |
inous | -0.209 |
Token | devices |
Token ID | 4410 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
dark | +0.168 |
Dark | +0.165 |
── | +0.165 |
Dark | +0.164 |
inous | +0.158 |
Neg logit contributions | |
ortium | -0.233 |
ania | -0.232 |
schild | -0.226 |
odder | -0.224 |
phabet | -0.219 |
Token | boys |
Token ID | 6510 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
dark | +0.335 |
Dark | +0.328 |
Dark | +0.325 |
── | +0.324 |
inous | +0.313 |
Neg logit contributions | |
ortium | -0.399 |
ania | -0.394 |
schild | -0.387 |
odder | -0.379 |
phabet | -0.370 |
Token | had |
Token ID | 550 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
dark | +0.155 |
── | +0.154 |
Dark | +0.152 |
Dark | +0.151 |
inous | +0.148 |
Neg logit contributions | |
ortium | -0.185 |
ania | -0.184 |
schild | -0.180 |
odder | -0.179 |
phabet | -0.173 |
Token | a |
Token ID | 257 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ortium | +0.308 |
ania | +0.306 |
schild | +0.300 |
odder | +0.297 |
phabet | +0.289 |
Neg logit contributions | |
dark | -0.242 |
── | -0.238 |
Dark | -0.238 |
Dark | -0.236 |
inous | -0.229 |
Token | really |
Token ID | 1107 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
dark | +0.413 |
── | +0.401 |
Dark | +0.399 |
Dark | +0.399 |
inous | +0.385 |
Neg logit contributions | |
ortium | -0.609 |
ania | -0.607 |
schild | -0.593 |
odder | -0.587 |
phabet | -0.570 |
Token | good |
Token ID | 922 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ortium | +0.418 |
ania | +0.417 |
schild | +0.406 |
odder | +0.402 |
phabet | +0.391 |
Neg logit contributions | |
dark | -0.307 |
── | -0.300 |
Dark | -0.300 |
Dark | -0.298 |
inous | -0.290 |
Token | lead |
Token ID | 1085 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
dark | +0.531 |
Dark | +0.515 |
── | +0.514 |
Dark | +0.508 |
inous | +0.491 |
Neg logit contributions | |
ortium | -0.685 |
ania | -0.673 |
schild | -0.664 |
odder | -0.658 |
phabet | -0.634 |
Token | out |
Token ID | 503 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
── | +2.176 |
dark | +2.151 |
Dark | +2.082 |
Dark | +2.080 |
inous | +2.005 |
Neg logit contributions | |
ortium | -3.048 |
ania | -3.019 |
schild | -2.977 |
odder | -2.900 |
phabet | -2.847 |
Token | for |
Token ID | 329 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
dark | +0.658 |
── | +0.653 |
Dark | +0.645 |
Dark | +0.642 |
inous | +0.620 |
Neg logit contributions | |
ortium | -0.904 |
ania | -0.899 |
schild | -0.876 |
odder | -0.870 |
phabet | -0.843 |
Token | me |
Token ID | 502 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
dark | +0.365 |
Dark | +0.358 |
── | +0.357 |
Dark | +0.356 |
inous | +0.343 |
Neg logit contributions | |
ortium | -0.470 |
ania | -0.464 |
schild | -0.452 |
odder | -0.449 |
phabet | -0.436 |
Token | and |
Token ID | 290 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
dark | +0.031 |
── | +0.030 |
Dark | +0.030 |
Dark | +0.030 |
inous | +0.029 |
Neg logit contributions | |
ortium | -0.040 |
ania | -0.039 |
schild | -0.038 |
odder | -0.038 |
phabet | -0.037 |
Token | I |
Token ID | 314 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
dark | +0.191 |
── | +0.190 |
Dark | +0.188 |
Dark | +0.187 |
inous | +0.180 |
Neg logit contributions | |
ortium | -0.243 |
ania | -0.242 |
schild | -0.238 |
odder | -0.235 |
phabet | -0.227 |
Token | div |
Token ID | 7146 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
dark | +0.406 |
Dark | +0.405 |
── | +0.404 |
Dark | +0.400 |
inous | +0.395 |
Neg logit contributions | |
ania | -0.197 |
ortium | -0.196 |
schild | -0.187 |
odder | -0.184 |
ubb | -0.174 |
Token | ide |
Token ID | 485 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
dark | +0.471 |
Dark | +0.466 |
── | +0.465 |
Dark | +0.459 |
inous | +0.448 |
Neg logit contributions | |
ortium | -0.733 |
ania | -0.729 |
schild | -0.718 |
odder | -0.708 |
ubb | -0.688 |
Token | ( |
Token ID | 7 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
dark | +0.140 |
Dark | +0.140 |
── | +0.139 |
Dark | +0.137 |
inous | +0.134 |
Neg logit contributions | |
ortium | -0.226 |
ania | -0.225 |
schild | -0.220 |
odder | -0.218 |
phabet | -0.212 |
Token | space |
Token ID | 2272 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
ortium | +0.071 |
ania | +0.070 |
schild | +0.068 |
odder | +0.067 |
phabet | +0.065 |
Neg logit contributions | |
dark | -0.067 |
Dark | -0.067 |
── | -0.066 |
Dark | -0.066 |
inous | -0.064 |
Token | ) |
Token ID | 1267 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
ortium | +0.070 |
ania | +0.070 |
schild | +0.068 |
odder | +0.068 |
phabet | +0.066 |
Neg logit contributions | |
dark | -0.048 |
Dark | -0.048 |
── | -0.048 |
Dark | -0.047 |
inous | -0.046 |
Token | { |
Token ID | 1391 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
dark | +1.162 |
── | +1.146 |
Dark | +1.135 |
Dark | +1.127 |
inous | +1.070 |
Neg logit contributions | |
ortium | -1.888 |
ania | -1.885 |
schild | -1.834 |
odder | -1.812 |
phabet | -1.776 |
Token | // |
Token ID | 3373 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
dark | +2.230 |
── | +2.168 |
Dark | +2.152 |
Dark | +2.138 |
| +2.040 |
Neg logit contributions | |
ortium | -2.988 |
ania | -2.947 |
schild | -2.858 |
odder | -2.841 |
phabet | -2.789 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ortium | +0.107 |
ania | +0.107 |
schild | +0.104 |
odder | +0.103 |
phabet | +0.100 |
Neg logit contributions | |
dark | -0.086 |
Dark | -0.085 |
── | -0.085 |
Dark | -0.084 |
inous | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ortium | +0.623 |
ania | +0.620 |
schild | +0.604 |
odder | +0.597 |
phabet | +0.582 |
Neg logit contributions | |
dark | -0.458 |
Dark | -0.454 |
── | -0.453 |
Dark | -0.448 |
inous | -0.436 |
Token | Fit |
Token ID | 25048 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ortium | +0.632 |
ania | +0.630 |
schild | +0.613 |
odder | +0.606 |
phabet | +0.590 |
Neg logit contributions | |
dark | -0.501 |
Dark | -0.497 |
── | -0.495 |
Dark | -0.491 |
inous | -0.475 |
Token | an |
Token ID | 281 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
dark | +0.299 |
Dark | +0.295 |
── | +0.294 |
Dark | +0.292 |
inous | +0.282 |
Neg logit contributions | |
ortium | -0.379 |
ania | -0.374 |
schild | -0.365 |
odder | -0.361 |
phabet | -0.352 |
Token | and |
Token ID | 290 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
ortium | +0.143 |
ania | +0.143 |
schild | +0.139 |
odder | +0.138 |
phabet | +0.133 |
Neg logit contributions | |
dark | -0.118 |
Dark | -0.116 |
── | -0.115 |
Dark | -0.114 |
inous | -0.111 |
Token | for |
Token ID | 329 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
dark | +0.203 |
── | +0.199 |
Dark | +0.199 |
Dark | +0.198 |
inous | +0.191 |
Neg logit contributions | |
ortium | -0.249 |
ania | -0.248 |
schild | -0.244 |
odder | -0.240 |
phabet | -0.232 |
Token | Nietzsche |
Token ID | 40258 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
dark | +0.417 |
Dark | +0.409 |
Dark | +0.409 |
── | +0.407 |
inous | +0.395 |
Neg logit contributions | |
ortium | -0.498 |
ania | -0.492 |
schild | -0.483 |
odder | -0.476 |
ibel | -0.462 |
Token | , |
Token ID | 11 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
dark | +0.025 |
Dark | +0.025 |
── | +0.025 |
Dark | +0.025 |
inous | +0.024 |
Neg logit contributions | |
ortium | -0.031 |
ania | -0.031 |
schild | -0.030 |
odder | -0.030 |
phabet | -0.029 |
Token | this |
Token ID | 428 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
ortium | +0.085 |
ania | +0.085 |
schild | +0.083 |
odder | +0.082 |
phabet | +0.079 |
Neg logit contributions | |
dark | -0.071 |
── | -0.070 |
Dark | -0.070 |
Dark | -0.070 |
inous | -0.068 |
Token | outward |
Token ID | 23537 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ortium | +0.214 |
ania | +0.213 |
schild | +0.209 |
odder | +0.206 |
phabet | +0.200 |
Neg logit contributions | |
dark | -0.174 |
── | -0.172 |
Dark | -0.171 |
Dark | -0.170 |
inous | -0.166 |
Token | - |
Token ID | 12 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
dark | +2.219 |
── | +2.174 |
Dark | +2.131 |
Dark | +2.101 |
inous | +2.075 |
Neg logit contributions | |
ortium | -2.919 |
ania | -2.871 |
schild | -2.861 |
odder | -2.838 |
phabet | -2.708 |
Token | looking |
Token ID | 11534 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ortium | +0.790 |
ania | +0.785 |
schild | +0.764 |
odder | +0.759 |
phabet | +0.737 |
Neg logit contributions | |
dark | -0.685 |
Dark | -0.682 |
── | -0.680 |
Dark | -0.672 |
inous | -0.661 |
Token | ethos |
Token ID | 39676 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ortium | +0.820 |
ania | +0.817 |
schild | +0.799 |
odder | +0.789 |
phabet | +0.767 |
Neg logit contributions | |
dark | -0.629 |
── | -0.620 |
Dark | -0.619 |
Dark | -0.614 |
inous | -0.598 |
Token | could |
Token ID | 714 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ortium | +0.813 |
ania | +0.810 |
schild | +0.790 |
odder | +0.782 |
phabet | +0.760 |
Neg logit contributions | |
dark | -0.652 |
Dark | -0.647 |
── | -0.647 |
Dark | -0.638 |
inous | -0.625 |
Token | never |
Token ID | 1239 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
ortium | +0.462 |
ania | +0.459 |
schild | +0.448 |
odder | +0.442 |
phabet | +0.432 |
Neg logit contributions | |
dark | -0.400 |
── | -0.392 |
Dark | -0.390 |
Dark | -0.387 |
inous | -0.380 |
Token | ( |
Token ID | 357 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
dark | +0.288 |
Dark | +0.285 |
── | +0.283 |
Dark | +0.281 |
inous | +0.276 |
Neg logit contributions | |
ortium | -0.342 |
ania | -0.341 |
schild | -0.333 |
odder | -0.328 |
phabet | -0.319 |
Token | & |
Token ID | 1222 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
dark | +0.420 |
Dark | +0.414 |
── | +0.412 |
Dark | +0.412 |
inous | +0.401 |
Neg logit contributions | |
ortium | -0.349 |
ania | -0.346 |
schild | -0.335 |
odder | -0.331 |
phabet | -0.320 |
Token | mut |
Token ID | 4517 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ortium | +0.938 |
ania | +0.935 |
schild | +0.912 |
odder | +0.905 |
phabet | +0.880 |
Neg logit contributions | |
dark | -0.605 |
Dark | -0.600 |
── | -0.598 |
Dark | -0.591 |
inous | -0.577 |
Token | self |
Token ID | 2116 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
dark | +0.595 |
Dark | +0.583 |
── | +0.576 |
Dark | +0.571 |
inous | +0.559 |
Neg logit contributions | |
ortium | -1.035 |
ania | -1.024 |
schild | -1.006 |
odder | -0.990 |
phabet | -0.975 |
Token | ) |
Token ID | 1267 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
dark | +0.332 |
Dark | +0.330 |
── | +0.329 |
Dark | +0.325 |
inous | +0.317 |
Neg logit contributions | |
ortium | -0.483 |
ania | -0.482 |
schild | -0.470 |
odder | -0.466 |
phabet | -0.453 |
Token | { |
Token ID | 1391 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
dark | +0.781 |
Dark | +0.772 |
── | +0.769 |
Dark | +0.755 |
inous | +0.725 |
Neg logit contributions | |
ortium | -2.090 |
ania | -2.086 |
schild | -2.043 |
odder | -2.027 |
phabet | -1.983 |
Token | let |
Token ID | 1309 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
dark | +2.323 |
Dark | +2.279 |
── | +2.252 |
Dark | +2.232 |
inous | +2.145 |
Neg logit contributions | |
ortium | -2.815 |
ania | -2.762 |
schild | -2.728 |
odder | -2.716 |
phabet | -2.621 |
Token | prev |
Token ID | 8654 |
Feature activation | -4.01e-03 |
Pos logit contributions | |
dark | +0.959 |
── | +0.934 |
Dark | +0.931 |
Dark | +0.929 |
inous | +0.901 |
Neg logit contributions | |
ortium | -1.374 |
ania | -1.354 |
schild | -1.334 |
odder | -1.318 |
phabet | -1.290 |
Token | _ |
Token ID | 62 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
dark | +0.010 |
Dark | +0.010 |
── | +0.010 |
Dark | +0.010 |
inous | +0.010 |
Neg logit contributions | |
ortium | -0.010 |
ania | -0.010 |
schild | -0.009 |
odder | -0.009 |
phabet | -0.009 |
Token | state |
Token ID | 5219 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
dark | +0.567 |
Dark | +0.563 |
── | +0.561 |
Dark | +0.553 |
inous | +0.544 |
Neg logit contributions | |
ortium | -0.800 |
ania | -0.792 |
schild | -0.772 |
odder | -0.769 |
phabet | -0.747 |
Token | = |
Token ID | 796 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
dark | +0.051 |
Dark | +0.050 |
── | +0.050 |
Dark | +0.050 |
inous | +0.048 |
Neg logit contributions | |
ortium | -0.071 |
ania | -0.070 |
schild | -0.068 |
odder | -0.068 |
phabet | -0.066 |
Token | at |
Token ID | 379 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ortium | +0.590 |
ania | +0.580 |
schild | +0.565 |
odder | +0.563 |
phabet | +0.551 |
Neg logit contributions | |
dark | -0.484 |
Dark | -0.468 |
── | -0.468 |
Dark | -0.467 |
inous | -0.448 |
Token | once |
Token ID | 1752 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ortium | +0.877 |
ania | +0.867 |
schild | +0.847 |
odder | +0.838 |
phabet | +0.825 |
Neg logit contributions | |
dark | -0.500 |
── | -0.485 |
Dark | -0.484 |
Dark | -0.482 |
inous | -0.469 |
Token | relentlessly |
Token ID | 37952 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
ortium | +1.202 |
ania | +1.192 |
schild | +1.160 |
odder | +1.153 |
phabet | +1.125 |
Neg logit contributions | |
dark | -0.924 |
Dark | -0.902 |
── | -0.901 |
Dark | -0.896 |
inous | -0.866 |
Token | cynical |
Token ID | 28858 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
ortium | +1.039 |
ania | +1.032 |
schild | +1.001 |
odder | +0.996 |
phabet | +0.972 |
Neg logit contributions | |
dark | -0.768 |
Dark | -0.745 |
── | -0.744 |
Dark | -0.741 |
inous | -0.716 |
Token | and |
Token ID | 290 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
dark | +0.107 |
Dark | +0.105 |
── | +0.105 |
Dark | +0.104 |
inous | +0.101 |
Neg logit contributions | |
ortium | -0.128 |
ania | -0.126 |
schild | -0.122 |
odder | -0.122 |
phabet | -0.119 |
Token | outward |
Token ID | 23537 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
dark | +0.054 |
Dark | +0.052 |
── | +0.052 |
Dark | +0.052 |
inous | +0.050 |
Neg logit contributions | |
ortium | -0.074 |
ania | -0.073 |
schild | -0.071 |
odder | -0.071 |
phabet | -0.069 |
Token | ly |
Token ID | 306 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
dark | +2.157 |
── | +2.109 |
Dark | +2.089 |
Dark | +2.081 |
inous | +2.019 |
Neg logit contributions | |
ortium | -3.004 |
ania | -2.952 |
schild | -2.888 |
odder | -2.871 |
phabet | -2.793 |
Token | optimistic |
Token ID | 16915 |
Feature activation | -1.88e-03 |
Pos logit contributions | |
ortium | +0.518 |
ania | +0.513 |
schild | +0.499 |
odder | +0.496 |
phabet | +0.484 |
Neg logit contributions | |
dark | -0.384 |
Dark | -0.376 |
── | -0.375 |
Dark | -0.373 |
inous | -0.362 |
Token | about |
Token ID | 546 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
dark | +0.004 |
── | +0.004 |
Dark | +0.004 |
Dark | +0.004 |
inous | +0.004 |
Neg logit contributions | |
ortium | -0.005 |
ania | -0.005 |
schild | -0.005 |
odder | -0.005 |
phabet | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ortium | +0.345 |
ania | +0.344 |
schild | +0.334 |
odder | +0.332 |
phabet | +0.322 |
Neg logit contributions | |
dark | -0.288 |
Dark | -0.286 |
── | -0.285 |
Dark | -0.283 |
inous | -0.276 |
Token | conce |
Token ID | 8571 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ortium | +0.059 |
ania | +0.059 |
schild | +0.057 |
odder | +0.057 |
phabet | +0.055 |
Neg logit contributions | |
dark | -0.046 |
Dark | -0.045 |
── | -0.045 |
Dark | -0.045 |
inous | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
dark | +0.366 |
Dark | +0.355 |
── | +0.353 |
Dark | +0.353 |
inous | +0.345 |
Neg logit contributions | |
ortium | -0.484 |
ania | -0.482 |
schild | -0.469 |
odder | -0.464 |
phabet | -0.455 |
Token | good |
Token ID | 922 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
dark | +0.249 |
Dark | +0.241 |
── | +0.240 |
Dark | +0.240 |
inous | +0.231 |
Neg logit contributions | |
ortium | -0.382 |
ania | -0.378 |
schild | -0.369 |
odder | -0.365 |
phabet | -0.359 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
dark | +0.079 |
Dark | +0.079 |
── | +0.079 |
Dark | +0.078 |
inous | +0.076 |
Neg logit contributions | |
ortium | -0.108 |
ania | -0.108 |
schild | -0.105 |
odder | -0.104 |
phabet | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
dark | +0.374 |
── | +0.366 |
Dark | +0.366 |
Dark | +0.365 |
inous | +0.352 |
Neg logit contributions | |
ortium | -0.509 |
ania | -0.508 |
schild | -0.496 |
odder | -0.491 |
phabet | -0.479 |
Token | not |
Token ID | 407 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
dark | +0.532 |
── | +0.522 |
Dark | +0.520 |
Dark | +0.519 |
inous | +0.499 |
Neg logit contributions | |
ortium | -0.700 |
ania | -0.696 |
schild | -0.683 |
odder | -0.672 |
phabet | -0.656 |
Token | least |
Token ID | 1551 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ortium | +0.124 |
ania | +0.123 |
schild | +0.120 |
odder | +0.119 |
phabet | +0.115 |
Neg logit contributions | |
dark | -0.124 |
── | -0.123 |
Dark | -0.123 |
Dark | -0.121 |
inous | -0.119 |
Token | from |
Token ID | 422 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
dark | +2.077 |
── | +2.036 |
Dark | +2.027 |
Dark | +1.996 |
inous | +1.910 |
Neg logit contributions | |
ortium | -2.979 |
ania | -2.943 |
schild | -2.912 |
odder | -2.889 |
phabet | -2.803 |
Token | Michael |
Token ID | 3899 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
ortium | +0.670 |
ania | +0.668 |
schild | +0.651 |
odder | +0.644 |
phabet | +0.626 |
Neg logit contributions | |
dark | -0.547 |
Dark | -0.542 |
── | -0.541 |
Dark | -0.536 |
inous | -0.522 |
Token | Ign |
Token ID | 16583 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
ortium | +0.258 |
ania | +0.257 |
schild | +0.251 |
odder | +0.249 |
phabet | +0.241 |
Neg logit contributions | |
dark | -0.224 |
Dark | -0.222 |
Dark | -0.221 |
── | -0.219 |
inous | -0.216 |
Token | at |
Token ID | 265 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ortium | +0.722 |
ania | +0.718 |
schild | +0.697 |
odder | +0.690 |
phabet | +0.669 |
Neg logit contributions | |
dark | -0.751 |
Dark | -0.748 |
── | -0.744 |
Dark | -0.738 |
inous | -0.725 |
Token | ie |
Token ID | 494 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ortium | +0.449 |
ania | +0.439 |
schild | +0.429 |
odder | +0.427 |
phabet | +0.416 |
Neg logit contributions | |
dark | -0.401 |
Dark | -0.400 |
── | -0.399 |
Dark | -0.393 |
inous | -0.389 |
Token | DoS |
Token ID | 46498 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
ortium | +0.224 |
ania | +0.219 |
schild | +0.217 |
odder | +0.211 |
phabet | +0.207 |
Neg logit contributions | |
dark | -0.203 |
Dark | -0.202 |
── | -0.200 |
Dark | -0.199 |
inous | -0.195 |
Token | Gap |
Token ID | 33899 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
dark | +1.204 |
Dark | +1.178 |
Dark | +1.176 |
── | +1.154 |
inous | +1.086 |
Neg logit contributions | |
ortium | -3.249 |
ania | -3.231 |
schild | -3.192 |
odder | -3.118 |
phabet | -3.101 |
Token | occurs |
Token ID | 8833 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
dark | +0.224 |
Dark | +0.223 |
Dark | +0.221 |
── | +0.220 |
inous | +0.214 |
Neg logit contributions | |
ortium | -0.279 |
ania | -0.278 |
schild | -0.271 |
odder | -0.269 |
phabet | -0.262 |
Token | whenever |
Token ID | 8797 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
dark | +1.264 |
── | +1.241 |
Dark | +1.237 |
Dark | +1.235 |
inous | +1.179 |
Neg logit contributions | |
ortium | -2.212 |
ania | -2.194 |
schild | -2.151 |
odder | -2.141 |
phabet | -2.093 |
Token | D |
Token ID | 360 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ortium | +0.074 |
ania | +0.074 |
schild | +0.072 |
odder | +0.072 |
phabet | +0.070 |
Neg logit contributions | |
dark | -0.062 |
Dark | -0.062 |
── | -0.062 |
Dark | -0.061 |
inous | -0.060 |
Token | DoS |
Token ID | 46498 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
dark | +0.631 |
Dark | +0.623 |
Dark | +0.611 |
── | +0.604 |
inous | +0.582 |
Neg logit contributions | |
ortium | -1.370 |
ania | -1.339 |
schild | -1.337 |
odder | -1.308 |
phabet | -1.288 |
Token | traffic |
Token ID | 4979 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
dark | +1.545 |
Dark | +1.517 |
Dark | +1.504 |
── | +1.475 |
inous | +1.392 |
Neg logit contributions | |
ortium | -3.529 |
ania | -3.471 |
schild | -3.433 |
odder | -3.364 |
phabet | -3.343 |
Token | bypass |
Token ID | 17286 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
dark | +0.405 |
Dark | +0.401 |
── | +0.398 |
Dark | +0.396 |
inous | +0.384 |
Neg logit contributions | |
ortium | -0.618 |
ania | -0.614 |
schild | -0.602 |
odder | -0.595 |
phabet | -0.582 |
Token | es |
Token ID | 274 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
dark | +0.719 |
Dark | +0.708 |
Dark | +0.703 |
── | +0.697 |
inous | +0.674 |
Neg logit contributions | |
ortium | -1.162 |
ania | -1.151 |
schild | -1.129 |
odder | -1.123 |
phabet | -1.097 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
dark | +0.108 |
Dark | +0.106 |
Dark | +0.106 |
── | +0.106 |
inous | +0.102 |
Neg logit contributions | |
ortium | -0.132 |
ania | -0.131 |
schild | -0.129 |
odder | -0.128 |
phabet | -0.124 |
Token | company |
Token ID | 1664 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ortium | +0.051 |
ania | +0.051 |
schild | +0.050 |
odder | +0.050 |
phabet | +0.048 |
Neg logit contributions | |
dark | -0.035 |
Dark | -0.034 |
── | -0.034 |
Dark | -0.034 |
inous | -0.033 |
Token | black |
Token ID | 2042 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
dark | +0.250 |
Dark | +0.243 |
Dark | +0.243 |
── | +0.242 |
inous | +0.231 |
Neg logit contributions | |
ortium | -0.374 |
ania | -0.372 |
schild | -0.364 |
odder | -0.362 |
phabet | -0.351 |
Token | top |
Token ID | 1353 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
dark | +0.124 |
Dark | +0.122 |
── | +0.122 |
Dark | +0.121 |
inous | +0.117 |
Neg logit contributions | |
ortium | -0.184 |
ania | -0.183 |
schild | -0.180 |
odder | -0.178 |
phabet | -0.173 |
Token | hat |
Token ID | 6877 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
ortium | +0.555 |
ania | +0.555 |
schild | +0.540 |
odder | +0.536 |
phabet | +0.523 |
Neg logit contributions | |
dark | -0.346 |
Dark | -0.345 |
── | -0.344 |
Dark | -0.339 |
inous | -0.331 |
Token | he |
Token ID | 339 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
dark | +0.130 |
Dark | +0.129 |
── | +0.129 |
Dark | +0.127 |
inous | +0.123 |
Neg logit contributions | |
ortium | -0.190 |
ania | -0.189 |
schild | -0.185 |
odder | -0.183 |
phabet | -0.178 |
Token | always |
Token ID | 1464 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ortium | +0.303 |
ania | +0.302 |
schild | +0.295 |
odder | +0.293 |
phabet | +0.286 |
Neg logit contributions | |
dark | -0.165 |
Dark | -0.164 |
── | -0.164 |
Dark | -0.161 |
inous | -0.157 |
Token | wore |
Token ID | 12408 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
dark | +0.444 |
── | +0.431 |
Dark | +0.426 |
Dark | +0.425 |
inous | +0.408 |
Neg logit contributions | |
ortium | -0.869 |
ania | -0.862 |
schild | -0.850 |
odder | -0.841 |
phabet | -0.832 |
Token | to |
Token ID | 284 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
dark | +2.074 |
── | +2.043 |
Dark | +2.000 |
Dark | +1.990 |
inous | +1.875 |
Neg logit contributions | |
ortium | -2.993 |
ania | -2.972 |
schild | -2.949 |
odder | -2.898 |
phabet | -2.850 |
Token | events |
Token ID | 2995 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
dark | +0.330 |
Dark | +0.323 |
Dark | +0.322 |
── | +0.320 |
inous | +0.306 |
Neg logit contributions | |
ortium | -0.386 |
ania | -0.382 |
schild | -0.375 |
odder | -0.372 |
phabet | -0.358 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
dark | +0.011 |
── | +0.011 |
Dark | +0.011 |
Dark | +0.011 |
inous | +0.011 |
Neg logit contributions | |
ortium | -0.016 |
ania | -0.016 |
schild | -0.015 |
odder | -0.015 |
phabet | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -5.55e-03 |
Pos logit contributions | |
ortium | +0.386 |
ania | +0.382 |
schild | +0.373 |
odder | +0.371 |
phabet | +0.358 |
Neg logit contributions | |
dark | -0.329 |
── | -0.325 |
Dark | -0.324 |
Dark | -0.321 |
inous | -0.312 |
Token | described |
Token ID | 3417 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
dark | +0.012 |
── | +0.012 |
Dark | +0.012 |
Dark | +0.011 |
inous | +0.011 |
Neg logit contributions | |
ortium | -0.016 |
ania | -0.016 |
schild | -0.015 |
odder | -0.015 |
phabet | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
dark | +1.074 |
Dark | +1.059 |
── | +1.059 |
Dark | +1.047 |
inous | +1.016 |
Neg logit contributions | |
ortium | -1.474 |
ania | -1.462 |
schild | -1.431 |
odder | -1.418 |
phabet | -1.374 |
Token | all |
Token ID | 477 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
dark | +0.083 |
Dark | +0.081 |
── | +0.081 |
Dark | +0.081 |
inous | +0.078 |
Neg logit contributions | |
ortium | -0.106 |
ania | -0.105 |
schild | -0.103 |
odder | -0.102 |
phabet | -0.099 |
Token | was |
Token ID | 373 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
dark | +0.848 |
── | +0.827 |
Dark | +0.827 |
Dark | +0.822 |
inous | +0.797 |
Neg logit contributions | |
ortium | -1.061 |
ania | -1.047 |
schild | -1.028 |
odder | -1.015 |
ibel | -0.980 |
Token | vanity |
Token ID | 39609 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
dark | +0.754 |
Dark | +0.737 |
── | +0.737 |
Dark | +0.731 |
inous | +0.707 |
Neg logit contributions | |
ortium | -1.117 |
ania | -1.108 |
schild | -1.083 |
odder | -1.072 |
phabet | -1.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ortium | +0.129 |
ania | +0.128 |
schild | +0.125 |
odder | +0.124 |
phabet | +0.120 |
Neg logit contributions | |
dark | -0.115 |
── | -0.113 |
Dark | -0.113 |
Dark | -0.112 |
inous | -0.109 |
Token | vex |
Token ID | 41548 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
dark | +0.239 |
Dark | +0.235 |
── | +0.235 |
Dark | +0.232 |
inous | +0.224 |
Neg logit contributions | |
ortium | -0.430 |
ania | -0.428 |
schild | -0.419 |
odder | -0.415 |
phabet | -0.404 |
Token | ation |
Token ID | 341 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
dark | +2.027 |
── | +2.006 |
Dark | +2.001 |
Dark | +1.989 |
inous | +1.962 |
Neg logit contributions | |
ortium | -2.964 |
schild | -2.926 |
odder | -2.860 |
ania | -2.859 |
phabet | -2.775 |
Token | of |
Token ID | 286 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
dark | +1.002 |
── | +0.988 |
Dark | +0.987 |
Dark | +0.976 |
inous | +0.950 |
Neg logit contributions | |
ortium | -1.469 |
ania | -1.457 |
schild | -1.426 |
odder | -1.413 |
phabet | -1.375 |
Token | spirit |
Token ID | 4437 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
dark | +0.071 |
Dark | +0.071 |
── | +0.070 |
Dark | +0.069 |
inous | +0.067 |
Neg logit contributions | |
ortium | -0.137 |
ania | -0.137 |
schild | -0.134 |
odder | -0.133 |
phabet | -0.129 |
Token | , |
Token ID | 11 |
Feature activation | -9.99e-03 |
Pos logit contributions | |
dark | +0.786 |
Dark | +0.777 |
── | +0.777 |
Dark | +0.768 |
inous | +0.746 |
Neg logit contributions | |
ortium | -1.127 |
ania | -1.117 |
schild | -1.094 |
odder | -1.082 |
phabet | -1.056 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
dark | +0.023 |
Dark | +0.023 |
── | +0.023 |
Dark | +0.023 |
inous | +0.023 |
Neg logit contributions | |
ortium | -0.026 |
ania | -0.026 |
schild | -0.025 |
odder | -0.025 |
phabet | -0.024 |
Token | independence |
Token ID | 39894 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
ortium | +0.124 |
ania | +0.123 |
schild | +0.119 |
odder | +0.118 |
phabet | +0.113 |
Neg logit contributions | |
Dark | -0.182 |
dark | -0.182 |
── | -0.181 |
Dark | -0.179 |
inous | -0.176 |
Token | parties |
Token ID | 4671 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
dark | +0.203 |
Dark | +0.200 |
── | +0.200 |
Dark | +0.199 |
inous | +0.192 |
Neg logit contributions | |
ortium | -0.261 |
ania | -0.258 |
schild | -0.252 |
odder | -0.250 |
phabet | -0.242 |
Token | form |
Token ID | 1296 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ortium | +1.068 |
ania | +1.066 |
schild | +1.040 |
odder | +1.030 |
phabet | +0.999 |
Neg logit contributions | |
dark | -0.882 |
Dark | -0.875 |
── | -0.873 |
Dark | -0.865 |
inous | -0.846 |
Token | a |
Token ID | 257 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
ortium | +0.728 |
ania | +0.726 |
schild | +0.707 |
odder | +0.700 |
phabet | +0.679 |
Neg logit contributions | |
dark | -0.605 |
Dark | -0.601 |
── | -0.599 |
Dark | -0.593 |
inous | -0.580 |
Token | legislative |
Token ID | 10828 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ortium | +1.194 |
ania | +1.191 |
schild | +1.162 |
odder | +1.152 |
phabet | +1.122 |
Neg logit contributions | |
dark | -0.753 |
Dark | -0.749 |
── | -0.746 |
Dark | -0.737 |
inous | -0.719 |
Token | majority |
Token ID | 3741 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
ortium | +1.044 |
ania | +1.041 |
schild | +1.019 |
odder | +1.006 |
phabet | +0.979 |
Neg logit contributions | |
dark | -0.742 |
Dark | -0.733 |
── | -0.731 |
Dark | -0.726 |
inous | -0.706 |
Token | of |
Token ID | 286 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ortium | +2.259 |
ania | +2.249 |
schild | +2.182 |
odder | +2.168 |
phabet | +2.114 |
Neg logit contributions | |
Dark | -1.696 |
dark | -1.687 |
── | -1.668 |
Dark | -1.656 |
inous | -1.630 |
Token | 53 |
Token ID | 7192 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ortium | +0.626 |
ania | +0.625 |
schild | +0.608 |
odder | +0.603 |
phabet | +0.586 |
Neg logit contributions | |
dark | -0.474 |
Dark | -0.471 |
── | -0.469 |
Dark | -0.464 |
inous | -0.454 |
Token | % |
Token ID | 4 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ortium | +0.727 |
ania | +0.724 |
schild | +0.707 |
odder | +0.700 |
phabet | +0.679 |
Neg logit contributions | |
dark | -0.534 |
Dark | -0.530 |
── | -0.529 |
Dark | -0.524 |
inous | -0.510 |
Token | of |
Token ID | 286 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
ortium | +1.103 |
ania | +1.101 |
schild | +1.072 |
odder | +1.062 |
phabet | +1.032 |
Neg logit contributions | |
dark | -0.830 |
Dark | -0.826 |
── | -0.823 |
Dark | -0.813 |
inous | -0.796 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ortium | +0.208 |
ania | +0.207 |
schild | +0.202 |
odder | +0.201 |
phabet | +0.193 |
Neg logit contributions | |
dark | -0.190 |
── | -0.188 |
Dark | -0.188 |
Dark | -0.187 |
inous | -0.182 |
Token | had |
Token ID | 550 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ortium | +0.679 |
ania | +0.677 |
schild | +0.659 |
odder | +0.653 |
phabet | +0.634 |
Neg logit contributions | |
dark | -0.546 |
Dark | -0.543 |
── | -0.541 |
Dark | -0.535 |
inous | -0.524 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ortium | +0.058 |
ania | +0.058 |
schild | +0.057 |
odder | +0.056 |
phabet | +0.055 |
Neg logit contributions | |
dark | -0.049 |
Dark | -0.048 |
── | -0.048 |
Dark | -0.048 |
inous | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
dark | +1.491 |
Dark | +1.449 |
── | +1.431 |
Dark | +1.414 |
inous | +1.358 |
Neg logit contributions | |
ortium | -1.849 |
schild | -1.821 |
ania | -1.806 |
odder | -1.798 |
phabet | -1.748 |
Token | marginally |
Token ID | 44108 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ortium | +0.171 |
ania | +0.170 |
schild | +0.166 |
odder | +0.164 |
phabet | +0.160 |
Neg logit contributions | |
dark | -0.121 |
Dark | -0.119 |
── | -0.119 |
Dark | -0.118 |
inous | -0.115 |
Token | lower |
Token ID | 2793 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
ortium | +0.279 |
ania | +0.277 |
schild | +0.269 |
odder | +0.266 |
phabet | +0.258 |
Neg logit contributions | |
dark | -0.249 |
Dark | -0.245 |
── | -0.243 |
Dark | -0.243 |
inous | -0.236 |
Token | blur |
Token ID | 23671 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ortium | +0.169 |
ania | +0.168 |
schild | +0.164 |
odder | +0.163 |
phabet | +0.159 |
Neg logit contributions | |
dark | -0.122 |
Dark | -0.120 |
── | -0.120 |
Dark | -0.119 |
inous | -0.115 |
Token | when |
Token ID | 618 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ortium | +2.804 |
ania | +2.801 |
schild | +2.724 |
odder | +2.698 |
phabet | +2.624 |
Neg logit contributions | |
dark | -2.129 |
Dark | -2.123 |
── | -2.116 |
Dark | -2.089 |
inous | -2.043 |
Token | running |
Token ID | 2491 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ortium | +0.758 |
ania | +0.755 |
schild | +0.736 |
odder | +0.729 |
phabet | +0.708 |
Neg logit contributions | |
dark | -0.584 |
Dark | -0.578 |
── | -0.575 |
Dark | -0.572 |
inous | -0.555 |
Token | at |
Token ID | 379 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
ortium | +0.803 |
ania | +0.801 |
schild | +0.780 |
odder | +0.773 |
phabet | +0.751 |
Neg logit contributions | |
dark | -0.594 |
Dark | -0.590 |
── | -0.587 |
Dark | -0.582 |
inous | -0.568 |
Token | 144 |
Token ID | 20224 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
dark | +0.172 |
Dark | +0.168 |
Dark | +0.168 |
── | +0.166 |
inous | +0.160 |
Neg logit contributions | |
ortium | -0.294 |
ania | -0.292 |
schild | -0.286 |
odder | -0.283 |
phabet | -0.277 |
Token | Hz |
Token ID | 7399 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
ania | +1.654 |
ortium | +1.653 |
schild | +1.608 |
odder | +1.594 |
phabet | +1.549 |
Neg logit contributions | |
dark | -1.229 |
Dark | -1.224 |
── | -1.221 |
Dark | -1.205 |
inous | -1.179 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
dark | +0.266 |
Dark | +0.262 |
Dark | +0.262 |
── | +0.262 |
inous | +0.253 |
Neg logit contributions | |
ortium | -0.304 |
ania | -0.301 |
schild | -0.293 |
odder | -0.290 |
phabet | -0.282 |
Token | European |
Token ID | 3427 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
dark | +0.438 |
Dark | +0.429 |
Dark | +0.428 |
── | +0.426 |
inous | +0.411 |
Neg logit contributions | |
ortium | -0.579 |
ania | -0.572 |
schild | -0.560 |
odder | -0.553 |
phabet | -0.541 |
Token | [ |
Token ID | 685 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
dark | +0.450 |
Dark | +0.442 |
Dark | +0.440 |
── | +0.439 |
inous | +0.421 |
Neg logit contributions | |
ortium | -0.586 |
ania | -0.575 |
schild | -0.566 |
odder | -0.559 |
phabet | -0.544 |
Token | un |
Token ID | 403 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Dark | +0.162 |
dark | +0.160 |
── | +0.159 |
Dark | +0.158 |
inous | +0.154 |
Neg logit contributions | |
ortium | -0.178 |
ania | -0.174 |
schild | -0.172 |
odder | -0.170 |
phabet | -0.164 |
Token | int |
Token ID | 600 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
ortium | +0.250 |
ania | +0.248 |
schild | +0.243 |
odder | +0.240 |
phabet | +0.232 |
Neg logit contributions | |
dark | -0.251 |
Dark | -0.250 |
── | -0.249 |
Dark | -0.247 |
inous | -0.244 |
Token | ellig |
Token ID | 2976 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Dark | +0.911 |
dark | +0.910 |
inous | +0.903 |
Dark | +0.899 |
── | +0.887 |
Neg logit contributions | |
ania | -1.390 |
ortium | -1.372 |
schild | -1.365 |
odder | -1.350 |
phabet | -1.297 |
Token | ible |
Token ID | 856 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
ortium | +2.528 |
ania | +2.523 |
schild | +2.481 |
odder | +2.464 |
phabet | +2.417 |
Neg logit contributions | |
dark | -0.634 |
Dark | -0.626 |
── | -0.622 |
Dark | -0.606 |
inous | -0.576 |
Token | ] |
Token ID | 60 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
dark | +0.648 |
── | +0.637 |
Dark | +0.634 |
Dark | +0.634 |
inous | +0.615 |
Neg logit contributions | |
ortium | -0.742 |
ania | -0.730 |
schild | -0.723 |
odder | -0.716 |
phabet | -0.686 |
Token | tradition |
Token ID | 6761 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ortium | +0.791 |
ania | +0.786 |
schild | +0.768 |
odder | +0.760 |
phabet | +0.738 |
Neg logit contributions | |
dark | -0.596 |
Dark | -0.591 |
── | -0.588 |
Dark | -0.584 |
inous | -0.569 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
ortium | +0.431 |
ania | +0.428 |
schild | +0.418 |
odder | +0.415 |
phabet | +0.404 |
Neg logit contributions | |
dark | -0.325 |
── | -0.321 |
Dark | -0.320 |
Dark | -0.318 |
inous | -0.309 |
Token | where |
Token ID | 810 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ortium | +0.091 |
ania | +0.090 |
schild | +0.088 |
odder | +0.087 |
phabet | +0.085 |
Neg logit contributions | |
dark | -0.074 |
Dark | -0.073 |
Dark | -0.073 |
── | -0.073 |
inous | -0.070 |
Token | chickens |
Token ID | 25972 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
dark | +0.223 |
Dark | +0.217 |
── | +0.216 |
Dark | +0.215 |
inous | +0.208 |
Neg logit contributions | |
ortium | -0.304 |
ania | -0.297 |
schild | -0.293 |
odder | -0.290 |
phabet | -0.285 |
Token | sleep |
Token ID | 3993 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
dark | +0.110 |
── | +0.108 |
Dark | +0.107 |
Dark | +0.107 |
inous | +0.103 |
Neg logit contributions | |
ortium | -0.151 |
ania | -0.149 |
schild | -0.147 |
odder | -0.145 |
phabet | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ortium | +0.454 |
ania | +0.450 |
schild | +0.440 |
odder | +0.434 |
phabet | +0.423 |
Neg logit contributions | |
dark | -0.333 |
Dark | -0.329 |
── | -0.329 |
Dark | -0.325 |
inous | -0.315 |
Token | they |
Token ID | 484 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
dark | +0.219 |
Dark | +0.213 |
Dark | +0.212 |
── | +0.211 |
inous | +0.201 |
Neg logit contributions | |
ortium | -0.354 |
ania | -0.349 |
schild | -0.344 |
odder | -0.338 |
phabet | -0.331 |
Token | also |
Token ID | 635 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
ortium | +0.119 |
ania | +0.119 |
schild | +0.116 |
odder | +0.115 |
phabet | +0.112 |
Neg logit contributions | |
dark | -0.087 |
── | -0.086 |
Dark | -0.086 |
Dark | -0.085 |
inous | -0.083 |
Token | dream |
Token ID | 4320 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
dark | +0.093 |
── | +0.092 |
Dark | +0.091 |
Dark | +0.091 |
inous | +0.088 |
Neg logit contributions | |
ortium | -0.114 |
ania | -0.114 |
schild | -0.111 |
odder | -0.110 |
phabet | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ania | +1.868 |
ortium | +1.857 |
schild | +1.813 |
odder | +1.798 |
phabet | +1.743 |
Neg logit contributions | |
Dark | -1.576 |
dark | -1.566 |
── | -1.563 |
Dark | -1.545 |
inous | -1.520 |
Token | About |
Token ID | 7994 |
Feature activation | -9.97e-03 |
Pos logit contributions | |
Dark | +0.233 |
Dark | +0.232 |
dark | +0.231 |
── | +0.228 |
inous | +0.217 |
Neg logit contributions | |
ortium | -0.310 |
ania | -0.305 |
schild | -0.300 |
odder | -0.295 |
phabet | -0.291 |
Token | what |
Token ID | 644 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
dark | +0.019 |
Dark | +0.019 |
── | +0.019 |
Dark | +0.018 |
inous | +0.018 |
Neg logit contributions | |
ortium | -0.031 |
ania | -0.030 |
schild | -0.030 |
odder | -0.030 |
phabet | -0.029 |
Token | we |
Token ID | 356 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
dark | +0.560 |
── | +0.546 |
Dark | +0.545 |
Dark | +0.544 |
inous | +0.520 |
Neg logit contributions | |
ortium | -0.755 |
ania | -0.739 |
schild | -0.730 |
odder | -0.716 |
phabet | -0.704 |
Token | � |
Token ID | 447 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
dark | +0.327 |
── | +0.323 |
Dark | +0.321 |
Dark | +0.318 |
inous | +0.311 |
Neg logit contributions | |
ortium | -0.405 |
ania | -0.401 |
schild | -0.393 |
odder | -0.388 |
phabet | -0.378 |
Token | Line |
Token ID | 6910 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
ortium | +0.058 |
ania | +0.058 |
schild | +0.057 |
odder | +0.056 |
phabet | +0.055 |
Neg logit contributions | |
dark | -0.046 |
Dark | -0.046 |
── | -0.045 |
Dark | -0.045 |
inous | -0.044 |
Token | 26 |
Token ID | 2608 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
dark | +0.142 |
Dark | +0.142 |
── | +0.141 |
Dark | +0.140 |
inous | +0.135 |
Neg logit contributions | |
ortium | -0.227 |
ania | -0.225 |
schild | -0.221 |
odder | -0.219 |
phabet | -0.213 |
Token | to |
Token ID | 284 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
dark | +0.222 |
Dark | +0.219 |
── | +0.219 |
Dark | +0.217 |
inous | +0.209 |
Neg logit contributions | |
ortium | -0.306 |
ania | -0.304 |
schild | -0.297 |
odder | -0.294 |
phabet | -0.287 |
Token | reduce |
Token ID | 4646 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
dark | +0.071 |
Dark | +0.070 |
Dark | +0.070 |
── | +0.070 |
inous | +0.067 |
Neg logit contributions | |
ortium | -0.095 |
ania | -0.094 |
schild | -0.091 |
odder | -0.091 |
phabet | -0.088 |
Token | high |
Token ID | 1029 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
ortium | +0.460 |
ania | +0.458 |
schild | +0.447 |
odder | +0.443 |
phabet | +0.430 |
Neg logit contributions | |
dark | -0.345 |
Dark | -0.342 |
── | -0.341 |
Dark | -0.338 |
inous | -0.329 |
Token | frequency |
Token ID | 8373 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ortium | +0.252 |
ania | +0.251 |
schild | +0.245 |
odder | +0.243 |
phabet | +0.235 |
Neg logit contributions | |
dark | -0.185 |
Dark | -0.182 |
── | -0.181 |
Dark | -0.181 |
inous | -0.175 |
Token | noise |
Token ID | 7838 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ania | +2.073 |
ortium | +2.048 |
schild | +2.002 |
odder | +1.980 |
ubb | +1.934 |
Neg logit contributions | |
Dark | -1.463 |
── | -1.460 |
dark | -1.422 |
inous | -1.422 |
Dark | -1.412 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ortium | +1.523 |
ania | +1.518 |
schild | +1.477 |
odder | +1.464 |
phabet | +1.422 |
Neg logit contributions | |
dark | -1.211 |
Dark | -1.204 |
── | -1.200 |
Dark | -1.188 |
inous | -1.161 |
Token | We |
Token ID | 775 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ortium | +0.450 |
ania | +0.449 |
schild | +0.436 |
odder | +0.432 |
phabet | +0.419 |
Neg logit contributions | |
dark | -0.390 |
Dark | -0.389 |
── | -0.387 |
Dark | -0.383 |
inous | -0.375 |
Token | then |
Token ID | 788 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ortium | +0.640 |
ania | +0.639 |
schild | +0.621 |
odder | +0.615 |
phabet | +0.597 |
Neg logit contributions | |
dark | -0.524 |
Dark | -0.523 |
── | -0.521 |
Dark | -0.515 |
inous | -0.505 |
Token | apply |
Token ID | 4174 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
dark | +0.651 |
── | +0.636 |
Dark | +0.636 |
Dark | +0.633 |
inous | +0.610 |
Neg logit contributions | |
ortium | -0.775 |
ania | -0.771 |
schild | -0.751 |
odder | -0.744 |
phabet | -0.725 |
Token |
|
Token ID | 198 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ortium | +0.039 |
ania | +0.038 |
schild | +0.037 |
odder | +0.037 |
phabet | +0.036 |
Neg logit contributions | |
dark | -0.032 |
Dark | -0.032 |
── | -0.032 |
Dark | -0.032 |
inous | -0.031 |
Token | � |
Token ID | 447 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Dark | +0.064 |
── | +0.063 |
dark | +0.063 |
Dark | +0.062 |
inous | +0.060 |
Neg logit contributions | |
ortium | -0.088 |
ania | -0.087 |
schild | -0.085 |
odder | -0.084 |
phabet | -0.082 |
Token | � |
Token ID | 250 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
── | +0.217 |
Dark | +0.215 |
dark | +0.215 |
Dark | +0.210 |
inous | +0.203 |
Neg logit contributions | |
ortium | -0.363 |
ania | -0.360 |
schild | -0.353 |
odder | -0.349 |
phabet | -0.340 |
Token | T |
Token ID | 51 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Dark | +0.132 |
── | +0.131 |
dark | +0.129 |
Dark | +0.127 |
inous | +0.123 |
Neg logit contributions | |
ortium | -0.163 |
ania | -0.160 |
schild | -0.158 |
odder | -0.155 |
phabet | -0.151 |
Token | akeru |
Token ID | 43246 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
── | +0.651 |
dark | +0.651 |
Dark | +0.647 |
Dark | +0.640 |
inous | +0.628 |
Neg logit contributions | |
ortium | -0.661 |
ania | -0.642 |
schild | -0.641 |
odder | -0.620 |
phabet | -0.610 |
Token | Kob |
Token ID | 23403 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
── | +1.470 |
dark | +1.457 |
Dark | +1.444 |
Dark | +1.438 |
inous | +1.377 |
Neg logit contributions | |
ortium | -1.616 |
ania | -1.597 |
odder | -1.569 |
schild | -1.567 |
phabet | -1.524 |
Token | ay |
Token ID | 323 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ortium | +0.314 |
ania | +0.312 |
schild | +0.299 |
odder | +0.294 |
phabet | +0.280 |
Neg logit contributions | |
dark | -0.623 |
Dark | -0.621 |
── | -0.619 |
Dark | -0.615 |
inous | -0.606 |
Token | ashi |
Token ID | 12144 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
ortium | +0.549 |
ania | +0.542 |
schild | +0.525 |
odder | +0.517 |
phabet | +0.494 |
Neg logit contributions | |
dark | -1.041 |
Dark | -1.039 |
── | -1.037 |
Dark | -1.028 |
inous | -1.012 |
Token | � |
Token ID | 447 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
dark | +0.081 |
── | +0.081 |
Dark | +0.080 |
Dark | +0.079 |
inous | +0.077 |
Neg logit contributions | |
ortium | -0.111 |
ania | -0.110 |
schild | -0.108 |
odder | -0.107 |
phabet | -0.104 |
Token | � |
Token ID | 247 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
ortium | +0.644 |
ania | +0.643 |
schild | +0.630 |
odder | +0.625 |
phabet | +0.611 |
Neg logit contributions | |
dark | -0.263 |
Dark | -0.261 |
── | -0.259 |
Dark | -0.255 |
inous | -0.246 |
Token | s |
Token ID | 82 |
Feature activation | +1.81e-03 |
Pos logit contributions | |
dark | +0.207 |
── | +0.206 |
Dark | +0.205 |
Dark | +0.203 |
inous | +0.198 |
Neg logit contributions | |
ortium | -0.264 |
ania | -0.262 |
schild | -0.256 |
odder | -0.255 |
phabet | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
dark | +0.432 |
── | +0.430 |
Dark | +0.424 |
Dark | +0.423 |
inous | +0.409 |
Neg logit contributions | |
ortium | -0.569 |
ania | -0.562 |
schild | -0.553 |
odder | -0.546 |
phabet | -0.531 |
Token | They |
Token ID | 1119 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
ortium | +0.141 |
ania | +0.140 |
schild | +0.137 |
odder | +0.135 |
phabet | +0.132 |
Neg logit contributions | |
dark | -0.118 |
Dark | -0.118 |
── | -0.117 |
Dark | -0.116 |
inous | -0.113 |
Token | � |
Token ID | 447 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
dark | +0.220 |
── | +0.217 |
Dark | +0.216 |
Dark | +0.214 |
inous | +0.209 |
Neg logit contributions | |
ortium | -0.263 |
ania | -0.262 |
schild | -0.256 |
odder | -0.254 |
phabet | -0.246 |
Token | � |
Token ID | 247 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
── | +0.871 |
dark | +0.865 |
Dark | +0.858 |
Dark | +0.844 |
inous | +0.830 |
Neg logit contributions | |
ortium | -0.756 |
ania | -0.750 |
schild | -0.734 |
odder | -0.730 |
phabet | -0.699 |
Token | ve |
Token ID | 303 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
dark | +0.408 |
── | +0.406 |
Dark | +0.403 |
Dark | +0.398 |
inous | +0.387 |
Neg logit contributions | |
ortium | -0.520 |
ania | -0.517 |
schild | -0.505 |
odder | -0.505 |
phabet | -0.492 |
Token | even |
Token ID | 772 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
dark | +0.129 |
── | +0.127 |
Dark | +0.127 |
Dark | +0.126 |
inous | +0.122 |
Neg logit contributions | |
ortium | -0.153 |
ania | -0.152 |
schild | -0.150 |
odder | -0.149 |
phabet | -0.144 |
Token | included |
Token ID | 3017 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
ortium | +1.020 |
ania | +1.019 |
schild | +0.987 |
odder | +0.976 |
phabet | +0.946 |
Neg logit contributions | |
dark | -0.927 |
Dark | -0.927 |
── | -0.922 |
Dark | -0.912 |
inous | -0.896 |
Token | a |
Token ID | 257 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
dark | +0.111 |
Dark | +0.110 |
── | +0.109 |
Dark | +0.109 |
inous | +0.106 |
Neg logit contributions | |
ortium | -0.136 |
ania | -0.135 |
schild | -0.132 |
odder | -0.131 |
phabet | -0.127 |
Token | section |
Token ID | 2665 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
dark | +0.136 |
Dark | +0.134 |
── | +0.134 |
Dark | +0.133 |
inous | +0.129 |
Neg logit contributions | |
ortium | -0.175 |
ania | -0.174 |
schild | -0.171 |
odder | -0.169 |
phabet | -0.164 |
Token | about |
Token ID | 546 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
dark | +0.362 |
── | +0.359 |
Dark | +0.356 |
Dark | +0.354 |
inous | +0.345 |
Neg logit contributions | |
ortium | -0.455 |
ania | -0.450 |
schild | -0.441 |
odder | -0.437 |
phabet | -0.422 |
Token | food |
Token ID | 2057 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
dark | +0.522 |
Dark | +0.515 |
── | +0.512 |
Dark | +0.512 |
inous | +0.494 |
Neg logit contributions | |
ortium | -0.693 |
ania | -0.689 |
schild | -0.674 |
odder | -0.669 |
phabet | -0.648 |
Token |
|
Token ID | 198 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
Dark | +0.139 |
dark | +0.139 |
Dark | +0.139 |
── | +0.138 |
inous | +0.132 |
Neg logit contributions | |
ortium | -0.161 |
ania | -0.160 |
schild | -0.156 |
odder | -0.154 |
phabet | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Dark | +0.081 |
dark | +0.081 |
── | +0.081 |
Dark | +0.080 |
inous | +0.077 |
Neg logit contributions | |
ortium | -0.098 |
ania | -0.096 |
schild | -0.095 |
odder | -0.094 |
phabet | -0.092 |
Token | Just |
Token ID | 5703 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
Dark | +0.251 |
── | +0.246 |
dark | +0.241 |
Dark | +0.239 |
| +0.230 |
Neg logit contributions | |
ortium | -0.385 |
ania | -0.376 |
schild | -0.375 |
odder | -0.367 |
phabet | -0.360 |
Token | check |
Token ID | 2198 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ortium | +0.952 |
ania | +0.946 |
schild | +0.925 |
odder | +0.912 |
phabet | +0.890 |
Neg logit contributions | |
dark | -0.772 |
Dark | -0.762 |
── | -0.761 |
Dark | -0.757 |
inous | -0.734 |
Token | out |
Token ID | 503 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
dark | +0.683 |
Dark | +0.668 |
Dark | +0.664 |
── | +0.660 |
inous | +0.629 |
Neg logit contributions | |
ortium | -1.067 |
ania | -1.050 |
schild | -1.035 |
odder | -1.023 |
phabet | -0.993 |
Token | this |
Token ID | 428 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
dark | +0.061 |
Dark | +0.060 |
Dark | +0.060 |
── | +0.059 |
inous | +0.057 |
Neg logit contributions | |
ortium | -0.069 |
ania | -0.069 |
schild | -0.067 |
odder | -0.066 |
phabet | -0.064 |
Token | demo |
Token ID | 13605 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ortium | +0.444 |
ania | +0.440 |
schild | +0.431 |
odder | +0.427 |
phabet | +0.413 |
Neg logit contributions | |
dark | -0.399 |
Dark | -0.391 |
Dark | -0.391 |
── | -0.390 |
inous | -0.378 |
Token | of |
Token ID | 286 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
ortium | +0.503 |
ania | +0.500 |
schild | +0.488 |
odder | +0.483 |
phabet | +0.468 |
Neg logit contributions | |
dark | -0.470 |
── | -0.465 |
Dark | -0.465 |
Dark | -0.462 |
inous | -0.448 |
Token | this |
Token ID | 428 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
ortium | +0.006 |
ania | +0.006 |
schild | +0.005 |
odder | +0.005 |
phabet | +0.005 |
Neg logit contributions | |
dark | -0.005 |
Dark | -0.005 |
Dark | -0.005 |
── | -0.005 |
inous | -0.005 |
Token | amazing |
Token ID | 4998 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
dark | +0.035 |
Dark | +0.034 |
── | +0.034 |
Dark | +0.034 |
inous | +0.033 |
Neg logit contributions | |
ortium | -0.048 |
ania | -0.047 |
schild | -0.046 |
odder | -0.046 |
phabet | -0.045 |
Token | product |
Token ID | 1720 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ortium | +0.173 |
ania | +0.172 |
schild | +0.169 |
odder | +0.167 |
phabet | +0.162 |
Neg logit contributions | |
dark | -0.128 |
Dark | -0.126 |
── | -0.126 |
Dark | -0.125 |
inous | -0.121 |
Token | their |
Token ID | 511 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ortium | +0.272 |
ania | +0.270 |
schild | +0.264 |
odder | +0.261 |
phabet | +0.254 |
Neg logit contributions | |
dark | -0.219 |
Dark | -0.216 |
── | -0.215 |
Dark | -0.214 |
inous | -0.208 |
Token | presence |
Token ID | 4931 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
dark | +0.249 |
Dark | +0.242 |
Dark | +0.241 |
── | +0.241 |
inous | +0.234 |
Neg logit contributions | |
ortium | -0.337 |
ania | -0.333 |
schild | -0.328 |
odder | -0.325 |
phabet | -0.316 |
Token | factors |
Token ID | 5087 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
ania | +0.402 |
ortium | +0.401 |
schild | +0.391 |
odder | +0.387 |
phabet | +0.376 |
Neg logit contributions | |
Dark | -0.276 |
dark | -0.276 |
── | -0.274 |
Dark | -0.271 |
inous | -0.265 |
Token | slightly |
Token ID | 4622 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
ortium | +0.226 |
ania | +0.226 |
schild | +0.220 |
odder | +0.218 |
phabet | +0.212 |
Neg logit contributions | |
dark | -0.158 |
Dark | -0.157 |
── | -0.157 |
Dark | -0.155 |
inous | -0.151 |
Token | into |
Token ID | 656 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
ortium | +0.211 |
ania | +0.210 |
schild | +0.205 |
odder | +0.203 |
phabet | +0.198 |
Neg logit contributions | |
dark | -0.142 |
Dark | -0.141 |
── | -0.141 |
Dark | -0.139 |
inous | -0.135 |
Token | the |
Token ID | 262 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
ortium | +0.124 |
ania | +0.123 |
schild | +0.120 |
odder | +0.118 |
phabet | +0.115 |
Neg logit contributions | |
dark | -0.103 |
Dark | -0.102 |
── | -0.102 |
Dark | -0.101 |
inous | -0.098 |
Token | tone |
Token ID | 8216 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ortium | +0.140 |
ania | +0.139 |
schild | +0.136 |
odder | +0.135 |
phabet | +0.132 |
Neg logit contributions | |
dark | -0.104 |
Dark | -0.102 |
Dark | -0.102 |
── | -0.102 |
inous | -0.098 |
Token | of |
Token ID | 286 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ortium | +0.537 |
ania | +0.535 |
schild | +0.521 |
odder | +0.517 |
phabet | +0.503 |
Neg logit contributions | |
dark | -0.386 |
── | -0.383 |
Dark | -0.382 |
Dark | -0.378 |
inous | -0.367 |
Token | the |
Token ID | 262 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
dark | +0.305 |
Dark | +0.300 |
Dark | +0.299 |
── | +0.297 |
inous | +0.287 |
Neg logit contributions | |
ortium | -0.348 |
ania | -0.346 |
schild | -0.338 |
odder | -0.335 |
phabet | -0.325 |
Token | ending |
Token ID | 7464 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
dark | +0.083 |
Dark | +0.081 |
Dark | +0.081 |
── | +0.081 |
inous | +0.078 |
Neg logit contributions | |
ortium | -0.099 |
ania | -0.098 |
schild | -0.096 |
odder | -0.095 |
phabet | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
dark | +0.086 |
── | +0.085 |
Dark | +0.085 |
Dark | +0.084 |
inous | +0.082 |
Neg logit contributions | |
ortium | -0.112 |
ania | -0.111 |
schild | -0.109 |
odder | -0.108 |
phabet | -0.105 |
Token | genome |
Token ID | 19270 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
dark | +0.240 |
Dark | +0.232 |
Dark | +0.231 |
── | +0.229 |
inous | +0.224 |
Neg logit contributions | |
ortium | -0.300 |
ania | -0.295 |
schild | -0.294 |
odder | -0.288 |
phabet | -0.279 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ortium | +0.124 |
ania | +0.123 |
schild | +0.120 |
odder | +0.120 |
phabet | +0.116 |
Neg logit contributions | |
dark | -0.091 |
Dark | -0.090 |
── | -0.089 |
Dark | -0.089 |
inous | -0.086 |
Token | using |
Token ID | 1262 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
ortium | +0.039 |
ania | +0.039 |
schild | +0.038 |
odder | +0.038 |
phabet | +0.036 |
Neg logit contributions | |
dark | -0.029 |
Dark | -0.028 |
Dark | -0.028 |
── | -0.028 |
inous | -0.027 |
Token | dozens |
Token ID | 9264 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ortium | +0.229 |
ania | +0.228 |
schild | +0.223 |
odder | +0.219 |
phabet | +0.214 |
Neg logit contributions | |
dark | -0.190 |
Dark | -0.185 |
Dark | -0.185 |
── | -0.183 |
inous | -0.177 |
Token | of |
Token ID | 286 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
ortium | +0.845 |
ania | +0.841 |
schild | +0.819 |
odder | +0.813 |
phabet | +0.791 |
Neg logit contributions | |
Dark | -0.617 |
dark | -0.616 |
── | -0.615 |
Dark | -0.605 |
inous | -0.593 |
Token | automated |
Token ID | 16359 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
ortium | +1.195 |
ania | +1.192 |
schild | +1.164 |
odder | +1.149 |
phabet | +1.118 |
Neg logit contributions | |
dark | -0.982 |
Dark | -0.968 |
Dark | -0.960 |
── | -0.959 |
inous | -0.930 |
Token | sequencing |
Token ID | 32841 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
ortium | +0.111 |
ania | +0.110 |
schild | +0.108 |
odder | +0.106 |
phabet | +0.104 |
Neg logit contributions | |
dark | -0.082 |
Dark | -0.080 |
Dark | -0.079 |
── | -0.079 |
inous | -0.076 |
Token | machines |
Token ID | 8217 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ortium | +0.093 |
ania | +0.093 |
schild | +0.091 |
odder | +0.090 |
phabet | +0.088 |
Neg logit contributions | |
dark | -0.055 |
Dark | -0.053 |
Dark | -0.053 |
── | -0.053 |
inous | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
ortium | +0.593 |
ania | +0.590 |
schild | +0.578 |
odder | +0.573 |
phabet | +0.560 |
Neg logit contributions | |
dark | -0.454 |
── | -0.448 |
Dark | -0.445 |
Dark | -0.443 |
inous | -0.429 |
Token |
|
Token ID | 198 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
ortium | +0.477 |
ania | +0.474 |
schild | +0.463 |
odder | +0.458 |
phabet | +0.446 |
Neg logit contributions | |
Dark | -0.400 |
dark | -0.400 |
Dark | -0.400 |
── | -0.395 |
inous | -0.378 |
Token |
|
Token ID | 198 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
ortium | +0.228 |
ania | +0.225 |
schild | +0.220 |
odder | +0.218 |
phabet | +0.213 |
Neg logit contributions | |
dark | -0.194 |
Dark | -0.193 |
── | -0.192 |
Dark | -0.191 |
inous | -0.184 |
Token | If |
Token ID | 1002 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
dark | +0.128 |
Dark | +0.127 |
Dark | +0.127 |
── | +0.127 |
inous | +0.121 |
Neg logit contributions | |
ortium | -0.173 |
ania | -0.171 |
schild | -0.167 |
odder | -0.166 |
phabet | -0.162 |
Token | you |
Token ID | 345 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
dark | +0.029 |
Dark | +0.029 |
── | +0.029 |
Dark | +0.029 |
inous | +0.028 |
Neg logit contributions | |
ortium | -0.035 |
ania | -0.035 |
schild | -0.034 |
odder | -0.034 |
phabet | -0.033 |
Token | don |
Token ID | 836 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
dark | +0.367 |
── | +0.360 |
Dark | +0.360 |
Dark | +0.358 |
inous | +0.349 |
Neg logit contributions | |
ortium | -0.440 |
ania | -0.435 |
schild | -0.427 |
odder | -0.423 |
phabet | -0.413 |
Token | 't |
Token ID | 470 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
dark | +0.372 |
Dark | +0.371 |
── | +0.370 |
Dark | +0.366 |
inous | +0.353 |
Neg logit contributions | |
ortium | -0.508 |
ania | -0.501 |
schild | -0.491 |
odder | -0.487 |
phabet | -0.477 |
Token | allow |
Token ID | 1249 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ortium | +0.270 |
ania | +0.269 |
schild | +0.262 |
odder | +0.259 |
phabet | +0.252 |
Neg logit contributions | |
dark | -0.246 |
Dark | -0.244 |
── | -0.244 |
Dark | -0.241 |
inous | -0.236 |
Token | their |
Token ID | 511 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ortium | +0.497 |
ania | +0.492 |
schild | +0.482 |
odder | +0.474 |
phabet | +0.465 |
Neg logit contributions | |
dark | -0.413 |
── | -0.407 |
Dark | -0.407 |
Dark | -0.404 |
inous | -0.394 |
Token | wives |
Token ID | 17743 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
dark | +0.340 |
Dark | +0.329 |
── | +0.327 |
Dark | +0.325 |
inous | +0.314 |
Neg logit contributions | |
ortium | -0.640 |
ania | -0.622 |
schild | -0.616 |
odder | -0.606 |
phabet | -0.605 |
Token | or |
Token ID | 393 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
ortium | +0.065 |
ania | +0.064 |
schild | +0.063 |
odder | +0.062 |
phabet | +0.061 |
Neg logit contributions | |
dark | -0.052 |
── | -0.051 |
Dark | -0.051 |
Dark | -0.051 |
inous | -0.049 |
Token | girlfriends |
Token ID | 47094 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
ortium | +0.116 |
ania | +0.114 |
schild | +0.112 |
odder | +0.110 |
phabet | +0.107 |
Neg logit contributions | |
dark | -0.115 |
── | -0.112 |
Dark | -0.112 |
Dark | -0.112 |
inous | -0.109 |
Token | on |
Token ID | 319 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ortium | +0.225 |
ania | +0.224 |
schild | +0.219 |
odder | +0.217 |
phabet | +0.212 |
Neg logit contributions | |
dark | -0.148 |
Dark | -0.147 |
── | -0.146 |
Dark | -0.145 |
inous | -0.141 |
Token | tour |
Token ID | 4205 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
dark | +0.409 |
Dark | +0.401 |
── | +0.399 |
Dark | +0.398 |
inous | +0.381 |
Neg logit contributions | |
ortium | -0.488 |
ania | -0.484 |
schild | -0.476 |
odder | -0.471 |
phabet | -0.463 |
Token | Tel |
Token ID | 12088 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
dark | +0.197 |
Dark | +0.193 |
Dark | +0.192 |
── | +0.189 |
inous | +0.183 |
Neg logit contributions | |
ortium | -0.419 |
ania | -0.413 |
schild | -0.407 |
odder | -0.406 |
phabet | -0.394 |
Token | Aviv |
Token ID | 28890 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
dark | +0.508 |
Dark | +0.504 |
Dark | +0.503 |
── | +0.499 |
inous | +0.485 |
Neg logit contributions | |
ortium | -0.744 |
schild | -0.727 |
ania | -0.724 |
odder | -0.716 |
phabet | -0.688 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
dark | +0.571 |
── | +0.569 |
Dark | +0.564 |
Dark | +0.561 |
inous | +0.544 |
Neg logit contributions | |
ortium | -0.792 |
ania | -0.781 |
schild | -0.769 |
odder | -0.761 |
phabet | -0.742 |
Token | Ankara |
Token ID | 28760 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
dark | +0.249 |
Dark | +0.243 |
Dark | +0.242 |
── | +0.240 |
inous | +0.232 |
Neg logit contributions | |
ortium | -0.554 |
ania | -0.547 |
schild | -0.540 |
odder | -0.537 |
phabet | -0.523 |
Token | . |
Token ID | 13 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
dark | +0.206 |
── | +0.205 |
Dark | +0.204 |
Dark | +0.202 |
inous | +0.197 |
Neg logit contributions | |
ortium | -0.283 |
ania | -0.281 |
schild | -0.276 |
odder | -0.272 |
phabet | -0.265 |
Token | The |
Token ID | 383 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
ortium | +0.176 |
ania | +0.174 |
schild | +0.171 |
odder | +0.170 |
phabet | +0.164 |
Neg logit contributions | |
dark | -0.138 |
Dark | -0.138 |
Dark | -0.137 |
── | -0.137 |
inous | -0.131 |
Token | Turkish |
Token ID | 9663 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
ortium | +0.040 |
ania | +0.040 |
schild | +0.039 |
odder | +0.039 |
phabet | +0.038 |
Neg logit contributions | |
dark | -0.031 |
Dark | -0.030 |
Dark | -0.030 |
── | -0.030 |
inous | -0.029 |
Token | parliament |
Token ID | 8540 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ortium | +0.186 |
ania | +0.185 |
schild | +0.182 |
odder | +0.180 |
phabet | +0.174 |
Neg logit contributions | |
dark | -0.122 |
Dark | -0.121 |
Dark | -0.120 |
── | -0.120 |
inous | -0.116 |
Token | will |
Token ID | 481 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ortium | +0.685 |
ania | +0.682 |
schild | +0.664 |
odder | +0.657 |
phabet | +0.636 |
Neg logit contributions | |
dark | -0.622 |
Dark | -0.618 |
── | -0.617 |
Dark | -0.611 |
inous | -0.599 |
Token | pass |
Token ID | 1208 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ortium | +0.289 |
ania | +0.288 |
schild | +0.281 |
odder | +0.278 |
phabet | +0.270 |
Neg logit contributions | |
dark | -0.237 |
── | -0.234 |
Dark | -0.234 |
Dark | -0.232 |
inous | -0.227 |
Token | a |
Token ID | 257 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
ortium | +1.427 |
ania | +1.427 |
schild | +1.384 |
odder | +1.371 |
phabet | +1.332 |
Neg logit contributions | |
dark | -1.266 |
Dark | -1.266 |
── | -1.259 |
Dark | -1.245 |
inous | -1.224 |
Token | love |
Token ID | 1842 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
ortium | +0.358 |
ania | +0.358 |
odder | +0.350 |
schild | +0.350 |
phabet | +0.337 |
Neg logit contributions | |
dark | -0.307 |
── | -0.303 |
Dark | -0.301 |
Dark | -0.300 |
inous | -0.292 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ortium | +0.150 |
ania | +0.149 |
schild | +0.146 |
odder | +0.145 |
phabet | +0.140 |
Neg logit contributions | |
dark | -0.121 |
Dark | -0.119 |
Dark | -0.118 |
── | -0.118 |
inous | -0.114 |
Token | playing |
Token ID | 2712 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
dark | +0.413 |
Dark | +0.405 |
Dark | +0.400 |
── | +0.398 |
inous | +0.382 |
Neg logit contributions | |
ortium | -0.523 |
ania | -0.517 |
schild | -0.508 |
odder | -0.504 |
phabet | -0.492 |
Token | group |
Token ID | 1448 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
dark | +0.104 |
── | +0.102 |
Dark | +0.102 |
Dark | +0.102 |
inous | +0.097 |
Neg logit contributions | |
ortium | -0.158 |
ania | -0.155 |
schild | -0.153 |
odder | -0.151 |
phabet | -0.148 |
Token | I |
Token ID | 314 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
dark | +0.211 |
── | +0.210 |
Dark | +0.208 |
Dark | +0.207 |
inous | +0.201 |
Neg logit contributions | |
ortium | -0.269 |
ania | -0.269 |
schild | -0.263 |
odder | -0.260 |
phabet | -0.251 |
Token | � |
Token ID | 447 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ortium | +0.348 |
ania | +0.347 |
schild | +0.341 |
odder | +0.338 |
phabet | +0.327 |
Neg logit contributions | |
dark | -0.328 |
── | -0.323 |
Dark | -0.322 |
Dark | -0.320 |
inous | -0.313 |
Token | � |
Token ID | 247 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
── | +0.199 |
dark | +0.198 |
Dark | +0.197 |
Dark | +0.193 |
inous | +0.187 |
Neg logit contributions | |
ortium | -0.331 |
ania | -0.330 |
schild | -0.323 |
odder | -0.321 |
phabet | -0.312 |
Token | m |
Token ID | 76 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ortium | +0.515 |
ania | +0.509 |
schild | +0.501 |
odder | +0.496 |
phabet | +0.479 |
Neg logit contributions | |
── | -0.447 |
dark | -0.447 |
Dark | -0.446 |
Dark | -0.441 |
inous | -0.427 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ortium | +0.718 |
ania | +0.714 |
schild | +0.701 |
odder | +0.698 |
phabet | +0.677 |
Neg logit contributions | |
dark | -0.496 |
── | -0.491 |
Dark | -0.490 |
Dark | -0.486 |
inous | -0.470 |
Token | with |
Token ID | 351 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
dark | +0.446 |
── | +0.444 |
Dark | +0.440 |
Dark | +0.438 |
inous | +0.422 |
Neg logit contributions | |
ortium | -0.662 |
ania | -0.658 |
schild | -0.647 |
odder | -0.637 |
phabet | -0.620 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ortium | +0.299 |
ania | +0.299 |
schild | +0.292 |
odder | +0.288 |
phabet | +0.280 |
Neg logit contributions | |
dark | -0.236 |
── | -0.235 |
Dark | -0.234 |
Dark | -0.232 |
inous | -0.225 |
Token | premier |
Token ID | 18256 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
dark | +0.494 |
Dark | +0.486 |
Dark | +0.485 |
── | +0.481 |
inous | +0.465 |
Neg logit contributions | |
ortium | -0.555 |
ania | -0.553 |
schild | -0.536 |
odder | -0.535 |
phabet | -0.522 |
Token | technical |
Token ID | 6276 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
ortium | +0.340 |
ania | +0.339 |
schild | +0.331 |
odder | +0.328 |
phabet | +0.318 |
Neg logit contributions | |
dark | -0.248 |
Dark | -0.247 |
── | -0.246 |
Dark | -0.243 |
inous | -0.238 |
Token | university |
Token ID | 6403 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
dark | +1.138 |
Dark | +1.096 |
Dark | +1.086 |
── | +1.079 |
inous | +1.043 |
Neg logit contributions | |
ortium | -1.361 |
ania | -1.332 |
schild | -1.317 |
odder | -1.313 |
phabet | -1.270 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
dark | +0.541 |
── | +0.536 |
Dark | +0.534 |
Dark | +0.531 |
inous | +0.504 |
Neg logit contributions | |
ortium | -0.746 |
ania | -0.742 |
schild | -0.725 |
odder | -0.723 |
phabet | -0.703 |
Token | K |
Token ID | 509 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
dark | +0.257 |
Dark | +0.254 |
Dark | +0.252 |
── | +0.251 |
inous | +0.240 |
Neg logit contributions | |
ortium | -0.314 |
ania | -0.314 |
odder | -0.304 |
schild | -0.304 |
phabet | -0.296 |
Token | A |
Token ID | 32 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ortium | +0.046 |
ania | +0.045 |
schild | +0.045 |
odder | +0.043 |
phabet | +0.043 |
Neg logit contributions | |
Dark | -0.045 |
dark | -0.045 |
── | -0.045 |
Dark | -0.044 |
inous | -0.043 |
Token | IST |
Token ID | 8808 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
dark | +1.062 |
Dark | +1.049 |
Dark | +1.048 |
── | +1.047 |
inous | +1.010 |
Neg logit contributions | |
ortium | -1.304 |
ania | -1.282 |
schild | -1.265 |
odder | -1.248 |
phabet | -1.210 |
Token | . |
Token ID | 13 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
dark | +0.175 |
Dark | +0.173 |
── | +0.173 |
Dark | +0.172 |
inous | +0.166 |
Neg logit contributions | |
ortium | -0.227 |
ania | -0.225 |
schild | -0.219 |
odder | -0.219 |
phabet | -0.214 |
Token | But |
Token ID | 887 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
Dark | +0.199 |
Dark | +0.199 |
dark | +0.198 |
── | +0.195 |
| +0.185 |
Neg logit contributions | |
ortium | -0.243 |
ania | -0.241 |
schild | -0.234 |
odder | -0.233 |
phabet | -0.228 |
Token | there |
Token ID | 612 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
ortium | +0.064 |
ania | +0.064 |
schild | +0.062 |
odder | +0.061 |
phabet | +0.060 |
Neg logit contributions | |
dark | -0.051 |
Dark | -0.051 |
── | -0.051 |
Dark | -0.050 |
inous | -0.049 |
Token | 's |
Token ID | 338 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
dark | +0.166 |
Dark | +0.164 |
── | +0.163 |
Dark | +0.162 |
inous | +0.158 |
Neg logit contributions | |
ortium | -0.237 |
ania | -0.236 |
schild | -0.231 |
odder | -0.229 |
phabet | -0.222 |
Token | of |
Token ID | 286 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ortium | +0.128 |
ania | +0.127 |
schild | +0.124 |
odder | +0.123 |
phabet | +0.119 |
Neg logit contributions | |
dark | -0.092 |
Dark | -0.091 |
── | -0.091 |
Dark | -0.090 |
inous | -0.088 |
Token | Hawaii |
Token ID | 13708 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
dark | +0.494 |
Dark | +0.490 |
── | +0.488 |
Dark | +0.488 |
inous | +0.473 |
Neg logit contributions | |
ortium | -0.529 |
ania | -0.524 |
schild | -0.510 |
odder | -0.507 |
phabet | -0.491 |
Token | study |
Token ID | 2050 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ortium | +0.883 |
ania | +0.881 |
schild | +0.857 |
odder | +0.850 |
phabet | +0.826 |
Neg logit contributions | |
dark | -0.672 |
Dark | -0.669 |
── | -0.666 |
Dark | -0.659 |
inous | -0.644 |
Token | cited |
Token ID | 9181 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
dark | +0.366 |
── | +0.365 |
Dark | +0.362 |
Dark | +0.359 |
inous | +0.346 |
Neg logit contributions | |
ortium | -0.435 |
ania | -0.434 |
odder | -0.422 |
schild | -0.421 |
phabet | -0.409 |
Token | previously |
Token ID | 4271 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
dark | +0.352 |
── | +0.350 |
Dark | +0.346 |
Dark | +0.344 |
inous | +0.335 |
Neg logit contributions | |
ortium | -0.407 |
ania | -0.406 |
schild | -0.394 |
odder | -0.391 |
phabet | -0.380 |
Token | – |
Token ID | 784 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
dark | +0.696 |
── | +0.696 |
Dark | +0.685 |
Dark | +0.683 |
inous | +0.660 |
Neg logit contributions | |
ortium | -0.798 |
ania | -0.788 |
schild | -0.774 |
odder | -0.766 |
phabet | -0.748 |
Token | rely |
Token ID | 8814 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
dark | +0.924 |
── | +0.909 |
Dark | +0.906 |
Dark | +0.896 |
inous | +0.877 |
Neg logit contributions | |
ortium | -1.233 |
ania | -1.227 |
schild | -1.200 |
odder | -1.191 |
phabet | -1.157 |
Token | heavily |
Token ID | 7272 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
ortium | +0.356 |
ania | +0.355 |
schild | +0.346 |
odder | +0.343 |
phabet | +0.333 |
Neg logit contributions | |
dark | -0.251 |
Dark | -0.250 |
── | -0.249 |
Dark | -0.246 |
inous | -0.241 |
Token | on |
Token ID | 319 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ortium | +0.187 |
ania | +0.187 |
schild | +0.181 |
odder | +0.179 |
phabet | +0.174 |
Neg logit contributions | |
dark | -0.183 |
Dark | -0.183 |
── | -0.182 |
Dark | -0.180 |
inous | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
ortium | +0.298 |
ania | +0.297 |
schild | +0.289 |
odder | +0.287 |
phabet | +0.279 |
Neg logit contributions | |
dark | -0.222 |
Dark | -0.220 |
── | -0.219 |
Dark | -0.217 |
inous | -0.211 |
Token | cost |
Token ID | 1575 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
dark | +0.188 |
── | +0.184 |
Dark | +0.184 |
Dark | +0.183 |
inous | +0.176 |
Neg logit contributions | |
ortium | -0.253 |
ania | -0.252 |
schild | -0.246 |
odder | -0.245 |
phabet | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
dark | +0.108 |
── | +0.107 |
Dark | +0.107 |
Dark | +0.106 |
inous | +0.103 |
Neg logit contributions | |
ortium | -0.140 |
ania | -0.139 |
schild | -0.135 |
odder | -0.134 |
phabet | -0.131 |
Token | It |
Token ID | 632 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Dark | +0.089 |
Dark | +0.088 |
dark | +0.088 |
── | +0.087 |
| +0.083 |
Neg logit contributions | |
ortium | -0.108 |
ania | -0.107 |
schild | -0.104 |
odder | -0.104 |
phabet | -0.102 |
Token | � |
Token ID | 447 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
dark | +0.383 |
── | +0.379 |
Dark | +0.377 |
Dark | +0.372 |
inous | +0.364 |
Neg logit contributions | |
ortium | -0.566 |
ania | -0.562 |
schild | -0.549 |
odder | -0.546 |
phabet | -0.532 |
Token | � |
Token ID | 247 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
── | +0.252 |
dark | +0.252 |
Dark | +0.250 |
Dark | +0.246 |
inous | +0.242 |
Neg logit contributions | |
ortium | -0.204 |
ania | -0.202 |
schild | -0.197 |
odder | -0.195 |
phabet | -0.187 |
Token | s |
Token ID | 82 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
ortium | +0.089 |
ania | +0.089 |
schild | +0.087 |
odder | +0.086 |
phabet | +0.084 |
Neg logit contributions | |
dark | -0.059 |
Dark | -0.058 |
── | -0.058 |
Dark | -0.057 |
inous | -0.056 |
Token | effortlessly |
Token ID | 42241 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
dark | +0.194 |
── | +0.189 |
Dark | +0.189 |
Dark | +0.189 |
inous | +0.182 |
Neg logit contributions | |
ortium | -0.251 |
ania | -0.248 |
schild | -0.243 |
odder | -0.242 |
phabet | -0.236 |
Token | imaginative |
Token ID | 41138 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
dark | +1.444 |
Dark | +1.375 |
── | +1.373 |
Dark | +1.364 |
inous | +1.307 |
Neg logit contributions | |
ortium | -1.907 |
ania | -1.873 |
odder | -1.848 |
schild | -1.838 |
phabet | -1.790 |
Token | , |
Token ID | 11 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
dark | +0.343 |
── | +0.338 |
Dark | +0.337 |
Dark | +0.335 |
inous | +0.325 |
Neg logit contributions | |
ortium | -0.440 |
ania | -0.435 |
schild | -0.426 |
odder | -0.422 |
phabet | -0.411 |
Token | as |
Token ID | 355 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
dark | +0.200 |
Dark | +0.195 |
── | +0.194 |
Dark | +0.194 |
inous | +0.186 |
Neg logit contributions | |
ortium | -0.253 |
ania | -0.251 |
schild | -0.246 |
odder | -0.243 |
phabet | -0.237 |
Token | are |
Token ID | 389 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
dark | +0.336 |
Dark | +0.330 |
Dark | +0.330 |
── | +0.326 |
inous | +0.315 |
Neg logit contributions | |
ortium | -0.403 |
ania | -0.400 |
schild | -0.392 |
odder | -0.390 |
phabet | -0.378 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
dark | +0.124 |
Dark | +0.122 |
── | +0.122 |
Dark | +0.122 |
inous | +0.118 |
Neg logit contributions | |
ortium | -0.143 |
ania | -0.142 |
schild | -0.138 |
odder | -0.138 |
phabet | -0.134 |
Token | see |
Token ID | 3826 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Dark | +0.006 |
dark | +0.006 |
── | +0.006 |
Dark | +0.006 |
inous | +0.006 |
Neg logit contributions | |
ortium | -0.006 |
ania | -0.006 |
schild | -0.005 |
odder | -0.005 |
phabet | -0.005 |
Token | below |
Token ID | 2174 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ortium | +0.811 |
ania | +0.809 |
schild | +0.786 |
odder | +0.779 |
phabet | +0.756 |
Neg logit contributions | |
dark | -0.698 |
Dark | -0.694 |
── | -0.692 |
Dark | -0.685 |
inous | -0.670 |
Token | ). |
Token ID | 737 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
dark | +0.058 |
Dark | +0.057 |
── | +0.057 |
Dark | +0.057 |
inous | +0.055 |
Neg logit contributions | |
ortium | -0.097 |
ania | -0.097 |
schild | -0.095 |
odder | -0.094 |
phabet | -0.092 |
Token | Unfortunately |
Token ID | 8989 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
Dark | +0.097 |
dark | +0.097 |
Dark | +0.097 |
── | +0.097 |
inous | +0.091 |
Neg logit contributions | |
ortium | -0.119 |
ania | -0.118 |
schild | -0.115 |
odder | -0.113 |
phabet | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
ortium | +0.152 |
ania | +0.151 |
schild | +0.148 |
odder | +0.146 |
phabet | +0.142 |
Neg logit contributions | |
dark | -0.113 |
Dark | -0.112 |
── | -0.112 |
Dark | -0.111 |
inous | -0.108 |
Token | unlike |
Token ID | 5023 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
dark | +0.185 |
Dark | +0.183 |
Dark | +0.182 |
── | +0.182 |
inous | +0.175 |
Neg logit contributions | |
ortium | -0.225 |
ania | -0.224 |
schild | -0.218 |
odder | -0.216 |
phabet | -0.210 |
Token | Feed |
Token ID | 18272 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
dark | +1.522 |
Dark | +1.506 |
Dark | +1.491 |
── | +1.483 |
inous | +1.429 |
Neg logit contributions | |
ortium | -1.580 |
ania | -1.575 |
schild | -1.525 |
odder | -1.508 |
phabet | -1.463 |
Token | books |
Token ID | 12106 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ortium | +0.577 |
ania | +0.575 |
schild | +0.559 |
odder | +0.554 |
phabet | +0.538 |
Neg logit contributions | |
Dark | -0.401 |
dark | -0.401 |
── | -0.395 |
Dark | -0.394 |
inous | -0.382 |
Token | you |
Token ID | 345 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
ortium | +0.689 |
ania | +0.687 |
schild | +0.669 |
odder | +0.663 |
phabet | +0.644 |
Neg logit contributions | |
dark | -0.525 |
Dark | -0.523 |
── | -0.521 |
Dark | -0.515 |
inous | -0.503 |
Token | � |
Token ID | 447 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
ortium | +0.007 |
ania | +0.007 |
schild | +0.007 |
odder | +0.007 |
phabet | +0.007 |
Neg logit contributions | |
dark | -0.004 |
── | -0.004 |
Dark | -0.004 |
Dark | -0.004 |
inous | -0.004 |
Token | � |
Token ID | 247 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ortium | +0.222 |
ania | +0.221 |
schild | +0.215 |
odder | +0.213 |
phabet | +0.204 |
Neg logit contributions | |
dark | -0.266 |
── | -0.266 |
Dark | -0.264 |
Dark | -0.260 |
inous | -0.256 |
Token | philosophy |
Token ID | 8876 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
dark | +0.766 |
Dark | +0.749 |
Dark | +0.743 |
── | +0.742 |
inous | +0.720 |
Neg logit contributions | |
ortium | -1.070 |
ania | -1.058 |
schild | -1.039 |
odder | -1.033 |
phabet | -1.006 |
Token | of |
Token ID | 286 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
dark | +0.193 |
── | +0.189 |
Dark | +0.188 |
Dark | +0.188 |
inous | +0.180 |
Neg logit contributions | |
ortium | -0.263 |
ania | -0.262 |
schild | -0.256 |
odder | -0.255 |
phabet | -0.248 |
Token | improvement |
Token ID | 9025 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
dark | +0.273 |
Dark | +0.269 |
── | +0.267 |
Dark | +0.267 |
inous | +0.259 |
Neg logit contributions | |
ortium | -0.361 |
ania | -0.358 |
schild | -0.349 |
odder | -0.348 |
phabet | -0.338 |
Token | that |
Token ID | 326 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
dark | +0.505 |
── | +0.497 |
Dark | +0.494 |
Dark | +0.493 |
inous | +0.479 |
Neg logit contributions | |
ortium | -0.680 |
ania | -0.670 |
schild | -0.658 |
odder | -0.654 |
phabet | -0.634 |
Token | values |
Token ID | 3815 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
dark | +0.146 |
Dark | +0.143 |
Dark | +0.143 |
── | +0.142 |
inous | +0.138 |
Neg logit contributions | |
ortium | -0.187 |
ania | -0.186 |
schild | -0.182 |
odder | -0.181 |
phabet | -0.175 |
Token | defect |
Token ID | 11855 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
dark | +1.117 |
Dark | +1.089 |
Dark | +1.086 |
── | +1.083 |
inous | +1.049 |
Neg logit contributions | |
ortium | -1.368 |
ania | -1.351 |
schild | -1.321 |
odder | -1.313 |
phabet | -1.276 |
Token | prevention |
Token ID | 14196 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
dark | +1.396 |
── | +1.372 |
Dark | +1.353 |
Dark | +1.344 |
inous | +1.303 |
Neg logit contributions | |
ortium | -1.944 |
ania | -1.886 |
odder | -1.849 |
schild | -1.832 |
phabet | -1.783 |
Token | over |
Token ID | 625 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
dark | +0.756 |
Dark | +0.736 |
Dark | +0.735 |
── | +0.733 |
inous | +0.708 |
Neg logit contributions | |
ortium | -1.000 |
ania | -0.976 |
schild | -0.965 |
odder | -0.955 |
phabet | -0.935 |
Token | defect |
Token ID | 11855 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
dark | +0.146 |
Dark | +0.143 |
── | +0.143 |
Dark | +0.142 |
inous | +0.138 |
Neg logit contributions | |
ortium | -0.191 |
ania | -0.190 |
schild | -0.185 |
odder | -0.184 |
phabet | -0.179 |
Token | detection |
Token ID | 13326 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
dark | +0.418 |
── | +0.413 |
Dark | +0.411 |
Dark | +0.407 |
inous | +0.397 |
Neg logit contributions | |
ortium | -0.560 |
ania | -0.555 |
schild | -0.538 |
odder | -0.536 |
phabet | -0.520 |
Token | . |
Token ID | 13 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
dark | +0.589 |
── | +0.581 |
Dark | +0.579 |
Dark | +0.576 |
inous | +0.554 |
Neg logit contributions | |
ortium | -0.772 |
ania | -0.758 |
schild | -0.748 |
odder | -0.737 |
phabet | -0.718 |
Token | this |
Token ID | 428 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ortium | +0.062 |
ania | +0.061 |
schild | +0.060 |
odder | +0.059 |
phabet | +0.057 |
Neg logit contributions | |
dark | -0.047 |
── | -0.046 |
Dark | -0.046 |
Dark | -0.046 |
inous | -0.044 |
Token | season |
Token ID | 1622 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
dark | +0.254 |
Dark | +0.248 |
Dark | +0.247 |
── | +0.246 |
inous | +0.238 |
Neg logit contributions | |
ortium | -0.247 |
ania | -0.242 |
schild | -0.240 |
odder | -0.234 |
phabet | -0.229 |
Token | since |
Token ID | 1201 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
dark | +0.543 |
── | +0.541 |
Dark | +0.533 |
Dark | +0.531 |
inous | +0.514 |
Neg logit contributions | |
ortium | -0.741 |
ania | -0.732 |
schild | -0.718 |
odder | -0.711 |
phabet | -0.690 |
Token | he |
Token ID | 339 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
dark | +0.939 |
Dark | +0.920 |
── | +0.910 |
Dark | +0.901 |
inous | +0.859 |
Neg logit contributions | |
ortium | -1.582 |
ania | -1.561 |
schild | -1.538 |
odder | -1.515 |
phabet | -1.482 |
Token | 's |
Token ID | 338 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
ortium | +0.323 |
ania | +0.320 |
schild | +0.312 |
odder | +0.310 |
phabet | +0.302 |
Neg logit contributions | |
dark | -0.270 |
── | -0.266 |
Dark | -0.264 |
Dark | -0.263 |
inous | -0.259 |
Token | only |
Token ID | 691 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
ortium | +0.221 |
ania | +0.219 |
schild | +0.214 |
odder | +0.212 |
phabet | +0.207 |
Neg logit contributions | |
dark | -0.170 |
Dark | -0.167 |
── | -0.167 |
Dark | -0.166 |
inous | -0.162 |
Token | scored |
Token ID | 7781 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
dark | +1.281 |
Dark | +1.258 |
── | +1.244 |
Dark | +1.228 |
inous | +1.202 |
Neg logit contributions | |
ortium | -1.735 |
ania | -1.716 |
schild | -1.692 |
odder | -1.682 |
phabet | -1.666 |
Token | 20 |
Token ID | 1160 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
dark | +0.180 |
── | +0.177 |
Dark | +0.177 |
Dark | +0.177 |
inous | +0.172 |
Neg logit contributions | |
ortium | -0.254 |
ania | -0.252 |
schild | -0.246 |
odder | -0.243 |
phabet | -0.238 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ortium | +0.197 |
ania | +0.195 |
schild | +0.193 |
odder | +0.188 |
phabet | +0.185 |
Neg logit contributions | |
dark | -0.148 |
Dark | -0.147 |
── | -0.146 |
Dark | -0.145 |
inous | -0.144 |
Token | points |
Token ID | 2173 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ortium | +0.654 |
ania | +0.646 |
schild | +0.632 |
odder | +0.618 |
phabet | +0.608 |
Neg logit contributions | |
dark | -0.592 |
Dark | -0.587 |
Dark | -0.584 |
── | -0.584 |
inous | -0.570 |
Token | once |
Token ID | 1752 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
dark | +0.273 |
── | +0.270 |
Dark | +0.269 |
Dark | +0.268 |
inous | +0.261 |
Neg logit contributions | |
ortium | -0.360 |
ania | -0.357 |
schild | -0.351 |
odder | -0.344 |
phabet | -0.337 |
Token | photos |
Token ID | 5205 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
dark | +0.056 |
Dark | +0.055 |
── | +0.054 |
Dark | +0.054 |
inous | +0.053 |
Neg logit contributions | |
ortium | -0.070 |
ania | -0.069 |
schild | -0.068 |
odder | -0.067 |
phabet | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
dark | +0.216 |
── | +0.211 |
Dark | +0.209 |
Dark | +0.209 |
inous | +0.201 |
Neg logit contributions | |
ania | -0.326 |
ortium | -0.325 |
schild | -0.320 |
odder | -0.317 |
phabet | -0.310 |
Token | party |
Token ID | 2151 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ortium | +0.104 |
ania | +0.103 |
schild | +0.101 |
odder | +0.100 |
phabet | +0.098 |
Neg logit contributions | |
dark | -0.079 |
Dark | -0.078 |
── | -0.077 |
Dark | -0.077 |
inous | -0.075 |
Token | - |
Token ID | 12 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
ania | +0.652 |
ortium | +0.650 |
schild | +0.634 |
odder | +0.630 |
phabet | +0.613 |
Neg logit contributions | |
Dark | -0.367 |
dark | -0.366 |
── | -0.365 |
Dark | -0.359 |
inous | -0.350 |
Token | goers |
Token ID | 31006 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
dark | +0.006 |
Dark | +0.006 |
── | +0.006 |
Dark | +0.006 |
inous | +0.006 |
Neg logit contributions | |
ortium | -0.014 |
ania | -0.014 |
schild | -0.013 |
odder | -0.013 |
phabet | -0.013 |
Token | wearing |
Token ID | 5762 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
dark | +0.190 |
── | +0.188 |
Dark | +0.188 |
Dark | +0.185 |
inous | +0.180 |
Neg logit contributions | |
ortium | -0.313 |
ania | -0.312 |
schild | -0.306 |
odder | -0.302 |
phabet | -0.296 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
dark | +1.604 |
Dark | +1.533 |
Dark | +1.522 |
── | +1.499 |
inous | +1.448 |
Neg logit contributions | |
ortium | -2.336 |
ania | -2.329 |
schild | -2.277 |
odder | -2.263 |
phabet | -2.232 |
Token | miniature |
Token ID | 28685 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
dark | +0.037 |
Dark | +0.036 |
── | +0.036 |
Dark | +0.036 |
inous | +0.035 |
Neg logit contributions | |
ortium | -0.053 |
ania | -0.053 |
schild | -0.052 |
odder | -0.052 |
phabet | -0.050 |
Token | s |
Token ID | 264 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ania | +0.960 |
ortium | +0.960 |
schild | +0.934 |
odder | +0.926 |
phabet | +0.900 |
Neg logit contributions | |
Dark | -0.623 |
dark | -0.622 |
── | -0.621 |
Dark | -0.610 |
inous | -0.599 |
Token | omb |
Token ID | 2381 |
Feature activation | +4.83e-03 |
Pos logit contributions | |
dark | +0.212 |
Dark | +0.211 |
── | +0.210 |
Dark | +0.207 |
inous | +0.203 |
Neg logit contributions | |
ortium | -0.337 |
ania | -0.335 |
schild | -0.328 |
odder | -0.324 |
phabet | -0.318 |
Token | re |
Token ID | 260 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ortium | +0.013 |
ania | +0.013 |
schild | +0.012 |
odder | +0.012 |
phabet | +0.012 |
Neg logit contributions | |
dark | -0.011 |
Dark | -0.011 |
── | -0.011 |
Dark | -0.011 |
inous | -0.011 |