Token | t |
Token ID | 83 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Conquest | +2.686 |
brook | +2.673 |
losers | +2.665 |
ocide | +2.503 |
ndra | +2.469 |
Neg logit contributions | |
detects | -2.394 |
netflix | -2.223 |
Vas | -2.187 |
Hamp | -2.155 |
imet | -2.136 |
Token | weet |
Token ID | 7277 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Conquest | +1.318 |
losers | +1.307 |
brook | +1.291 |
ocide | +1.234 |
ndra | +1.224 |
Neg logit contributions | |
detects | -0.693 |
netflix | -0.644 |
Vas | -0.614 |
thought | -0.607 |
imet | -0.604 |
Token | / |
Token ID | 14 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Conquest | +0.874 |
losers | +0.863 |
brook | +0.855 |
ocide | +0.803 |
ndra | +0.791 |
Neg logit contributions | |
detects | -0.889 |
netflix | -0.846 |
Vas | -0.818 |
Hamp | -0.808 |
thought | -0.808 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Conquest | +1.447 |
losers | +1.429 |
brook | +1.414 |
ocide | +1.322 |
ndra | +1.303 |
Neg logit contributions | |
detects | -1.656 |
netflix | -1.576 |
Vas | -1.530 |
Hamp | -1.513 |
imet | -1.513 |
Token | Story |
Token ID | 11605 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
detects | +0.296 |
netflix | +0.285 |
thought | +0.272 |
Vas | +0.272 |
imet | +0.268 |
Neg logit contributions | |
Conquest | -0.356 |
losers | -0.351 |
brook | -0.344 |
ocide | -0.327 |
ndra | -0.323 |
Token | highlights |
Token ID | 11330 |
Feature activation | +7.58e+00 |
Pos logit contributions | |
detects | +1.081 |
netflix | +0.993 |
Vas | +0.980 |
thought | +0.974 |
Hamp | +0.968 |
Neg logit contributions | |
Conquest | -1.318 |
losers | -1.311 |
brook | -1.283 |
ocide | -1.246 |
ndra | -1.208 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
detects | +4.862 |
Vas | +4.799 |
Hamp | +4.680 |
netflix | +4.583 |
thought | +4.424 |
Neg logit contributions | |
losers | -5.486 |
brook | -5.350 |
Conquest | -5.280 |
ocide | -5.181 |
ndra | -5.013 |
Token | of |
Token ID | 286 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
detects | +0.263 |
netflix | +0.248 |
Vas | +0.241 |
thought | +0.237 |
Hamp | +0.237 |
Neg logit contributions | |
Conquest | -0.313 |
losers | -0.310 |
brook | -0.306 |
ocide | -0.290 |
ndra | -0.286 |
Token | Defense |
Token ID | 5947 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Conquest | +0.043 |
losers | +0.042 |
brook | +0.042 |
ocide | +0.040 |
ndra | +0.039 |
Neg logit contributions | |
detects | -0.034 |
netflix | -0.032 |
Vas | -0.031 |
thought | -0.031 |
Hamp | -0.031 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
detects | +0.105 |
netflix | +0.096 |
Vas | +0.093 |
Hamp | +0.091 |
thought | +0.091 |
Neg logit contributions | |
Conquest | -0.181 |
losers | -0.178 |
brook | -0.177 |
ocide | -0.170 |
ndra | -0.167 |
Token | Hag |
Token ID | 21375 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
detects | +0.264 |
netflix | +0.205 |
Vas | +0.187 |
Hamp | +0.172 |
thought | +0.169 |
Neg logit contributions | |
Conquest | -1.846 |
losers | -1.828 |
brook | -1.815 |
ocide | -1.763 |
ndra | -1.749 |
Token | vote |
Token ID | 3015 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
Conquest | +0.059 |
losers | +0.058 |
brook | +0.058 |
ocide | +0.055 |
ndra | +0.055 |
Neg logit contributions | |
detects | -0.046 |
netflix | -0.043 |
Vas | -0.043 |
thought | -0.042 |
Hamp | -0.042 |
Token | accordingly |
Token ID | 16062 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Conquest | +0.581 |
losers | +0.573 |
brook | +0.567 |
ocide | +0.532 |
ndra | +0.524 |
Neg logit contributions | |
detects | -0.678 |
netflix | -0.646 |
Vas | -0.630 |
thought | -0.621 |
Hamp | -0.621 |
Token | . |
Token ID | 13 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
detects | +0.520 |
netflix | +0.495 |
Vas | +0.484 |
thought | +0.477 |
Hamp | +0.475 |
Neg logit contributions | |
Conquest | -0.481 |
losers | -0.471 |
brook | -0.470 |
ocide | -0.441 |
ndra | -0.436 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
detects | +0.525 |
netflix | +0.500 |
Vas | +0.495 |
Hamp | +0.487 |
thought | +0.482 |
Neg logit contributions | |
Conquest | -0.488 |
losers | -0.486 |
brook | -0.482 |
ocide | -0.453 |
ndra | -0.447 |
Token | Story |
Token ID | 11605 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
detects | +0.176 |
netflix | +0.169 |
thought | +0.162 |
Vas | +0.161 |
Hamp | +0.159 |
Neg logit contributions | |
Conquest | -0.211 |
losers | -0.209 |
brook | -0.204 |
ocide | -0.194 |
ndra | -0.192 |
Token | highlights |
Token ID | 11330 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
detects | +1.120 |
netflix | +1.028 |
Vas | +1.015 |
thought | +1.009 |
Hamp | +1.004 |
Neg logit contributions | |
Conquest | -1.368 |
losers | -1.363 |
brook | -1.334 |
ocide | -1.295 |
ndra | -1.253 |
Token | Police |
Token ID | 4287 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
detects | +4.723 |
Vas | +4.667 |
Hamp | +4.551 |
netflix | +4.459 |
thought | +4.300 |
Neg logit contributions | |
losers | -5.329 |
brook | -5.204 |
Conquest | -5.130 |
ocide | -5.029 |
ndra | -4.866 |
Token | chief |
Token ID | 4039 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Conquest | +0.149 |
losers | +0.148 |
brook | +0.146 |
ocide | +0.139 |
ndra | +0.137 |
Neg logit contributions | |
detects | -0.115 |
netflix | -0.109 |
Vas | -0.105 |
thought | -0.103 |
imet | -0.103 |
Token | vows |
Token ID | 36605 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
detects | +0.133 |
netflix | +0.124 |
Vas | +0.120 |
thought | +0.118 |
Hamp | +0.118 |
Neg logit contributions | |
Conquest | -0.201 |
losers | -0.199 |
brook | -0.197 |
ocide | -0.188 |
ndra | -0.186 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Conquest | +0.641 |
losers | +0.634 |
brook | +0.625 |
ocide | +0.588 |
ndra | +0.581 |
Neg logit contributions | |
detects | -0.627 |
netflix | -0.596 |
Vas | -0.575 |
thought | -0.571 |
imet | -0.570 |
Token | suspect |
Token ID | 4099 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
detects | +2.055 |
netflix | +1.952 |
Vas | +1.918 |
Hamp | +1.874 |
thought | +1.850 |
Neg logit contributions | |
Conquest | -2.153 |
brook | -2.128 |
losers | -2.105 |
ocide | -2.010 |
ndra | -1.977 |
Token | Reading |
Token ID | 11725 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
detects | +0.111 |
netflix | +0.106 |
Vas | +0.103 |
thought | +0.101 |
Hamp | +0.101 |
Neg logit contributions | |
Conquest | -0.107 |
losers | -0.106 |
brook | -0.104 |
ocide | -0.098 |
ndra | -0.097 |
Token | Below |
Token ID | 10383 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
detects | +0.180 |
netflix | +0.170 |
Vas | +0.165 |
Hamp | +0.163 |
thought | +0.163 |
Neg logit contributions | |
Conquest | -0.207 |
losers | -0.205 |
brook | -0.203 |
ocide | -0.192 |
ndra | -0.190 |
Token | Advertisement |
Token ID | 39711 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
detects | +1.755 |
netflix | +1.661 |
Vas | +1.624 |
Hamp | +1.602 |
thought | +1.589 |
Neg logit contributions | |
Conquest | -1.831 |
losers | -1.816 |
brook | -1.795 |
ocide | -1.699 |
ndra | -1.666 |
Token |
|
Token ID | 198 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
detects | +0.170 |
netflix | +0.162 |
Vas | +0.157 |
thought | +0.156 |
Hamp | +0.155 |
Neg logit contributions | |
Conquest | -0.150 |
losers | -0.148 |
brook | -0.146 |
ocide | -0.137 |
ndra | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
detects | +0.581 |
netflix | +0.558 |
Vas | +0.549 |
thought | +0.544 |
Hamp | +0.539 |
Neg logit contributions | |
Conquest | -0.446 |
losers | -0.441 |
brook | -0.428 |
ocide | -0.406 |
ndra | -0.398 |
Token | 9 |
Token ID | 24 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
detects | +0.323 |
netflix | +0.308 |
thought | +0.294 |
Vas | +0.293 |
Hamp | +0.289 |
Neg logit contributions | |
Conquest | -0.468 |
losers | -0.461 |
brook | -0.453 |
ocide | -0.432 |
ndra | -0.428 |
Token | Work |
Token ID | 5521 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
detects | +4.014 |
Vas | +3.916 |
Hamp | +3.795 |
netflix | +3.788 |
thought | +3.681 |
Neg logit contributions | |
losers | -4.730 |
brook | -4.678 |
Conquest | -4.667 |
ocide | -4.493 |
ndra | -4.408 |
Token | place |
Token ID | 5372 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
detects | +0.889 |
netflix | +0.834 |
Vas | +0.818 |
thought | +0.807 |
imet | +0.804 |
Neg logit contributions | |
Conquest | -0.933 |
losers | -0.929 |
brook | -0.917 |
ocide | -0.868 |
ndra | -0.856 |
Token | Safety |
Token ID | 11233 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
detects | +0.988 |
netflix | +0.921 |
Vas | +0.919 |
Hamp | +0.898 |
thought | +0.889 |
Neg logit contributions | |
Conquest | -1.149 |
losers | -1.144 |
brook | -1.134 |
ocide | -1.078 |
ndra | -1.061 |
Token | is |
Token ID | 318 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
detects | +0.542 |
netflix | +0.512 |
Vas | +0.497 |
Hamp | +0.490 |
thought | +0.490 |
Neg logit contributions | |
Conquest | -0.604 |
losers | -0.599 |
brook | -0.591 |
ocide | -0.560 |
ndra | -0.553 |
Token | Terr |
Token ID | 38859 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
detects | +1.426 |
netflix | +1.357 |
Vas | +1.330 |
Hamp | +1.302 |
thought | +1.300 |
Neg logit contributions | |
Conquest | -1.608 |
losers | -1.602 |
brook | -1.592 |
ocide | -1.506 |
ndra | -1.487 |
Token |
|
Token ID | 198 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Conquest | +0.335 |
losers | +0.330 |
brook | +0.324 |
ocide | +0.302 |
ndra | +0.297 |
Neg logit contributions | |
detects | -0.475 |
netflix | -0.455 |
Vas | -0.444 |
thought | -0.440 |
Hamp | -0.439 |
Token | Read |
Token ID | 5569 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
Conquest | +0.277 |
losers | +0.272 |
brook | +0.266 |
ocide | +0.254 |
ndra | +0.250 |
Neg logit contributions | |
detects | -0.236 |
netflix | -0.226 |
Vas | -0.218 |
thought | -0.217 |
Hamp | -0.215 |
Token | or |
Token ID | 393 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Conquest | +0.415 |
losers | +0.411 |
brook | +0.407 |
ocide | +0.379 |
ndra | +0.375 |
Neg logit contributions | |
detects | -0.461 |
netflix | -0.440 |
Vas | -0.423 |
thought | -0.420 |
imet | -0.420 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
detects | +1.393 |
netflix | +1.271 |
Vas | +1.226 |
Hamp | +1.195 |
imet | +1.191 |
Neg logit contributions | |
Conquest | -2.604 |
losers | -2.585 |
brook | -2.543 |
ocide | -2.458 |
ndra | -2.442 |
Token | this |
Token ID | 428 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
detects | +0.145 |
netflix | +0.138 |
Vas | +0.134 |
thought | +0.133 |
Hamp | +0.133 |
Neg logit contributions | |
Conquest | -0.112 |
losers | -0.110 |
brook | -0.109 |
ocide | -0.101 |
ndra | -0.100 |
Token | story |
Token ID | 1621 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
detects | +2.522 |
netflix | +2.337 |
Vas | +2.333 |
Hamp | +2.293 |
thought | +2.272 |
Neg logit contributions | |
Conquest | -2.480 |
losers | -2.452 |
brook | -2.402 |
ocide | -2.283 |
ndra | -2.255 |
Token | : |
Token ID | 25 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
detects | +2.548 |
netflix | +2.313 |
Vas | +2.262 |
thought | +2.220 |
Hamp | +2.087 |
Neg logit contributions | |
Conquest | -6.094 |
losers | -6.025 |
brook | -5.848 |
ocide | -5.792 |
ndra | -5.641 |
Token | http |
Token ID | 2638 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
detects | +2.331 |
netflix | +2.171 |
Vas | +2.161 |
Hamp | +2.127 |
thought | +2.088 |
Neg logit contributions | |
losers | -2.314 |
Conquest | -2.310 |
brook | -2.262 |
ocide | -2.162 |
ndra | -2.121 |
Token | :// |
Token ID | 1378 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
detects | +3.412 |
netflix | +3.269 |
thought | +3.210 |
Vas | +3.187 |
Hamp | +3.120 |
Neg logit contributions | |
Conquest | -3.113 |
losers | -3.075 |
brook | -2.842 |
ocide | -2.766 |
ndra | -2.663 |
Token | cin |
Token ID | 17879 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
detects | +2.185 |
netflix | +2.040 |
thought | +2.019 |
Vas | +2.008 |
imet | +1.983 |
Neg logit contributions | |
Conquest | -2.464 |
losers | -2.447 |
brook | -2.259 |
ocide | -2.221 |
ndra | -2.194 |
Token | . |
Token ID | 13 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
detects | +0.861 |
netflix | +0.822 |
Vas | +0.798 |
thought | +0.792 |
imet | +0.791 |
Neg logit contributions | |
Conquest | -0.705 |
losers | -0.695 |
brook | -0.680 |
ocide | -0.637 |
ndra | -0.629 |
Token |
|
Token ID | 198 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Conquest | +0.054 |
losers | +0.053 |
brook | +0.052 |
ocide | +0.049 |
ndra | +0.048 |
Neg logit contributions | |
detects | -0.073 |
netflix | -0.070 |
Vas | -0.069 |
thought | -0.068 |
Hamp | -0.068 |
Token | Read |
Token ID | 5569 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
Conquest | +0.275 |
losers | +0.271 |
brook | +0.265 |
ocide | +0.250 |
ndra | +0.246 |
Neg logit contributions | |
detects | -0.315 |
netflix | -0.302 |
Vas | -0.292 |
thought | -0.290 |
Hamp | -0.289 |
Token | or |
Token ID | 393 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
detects | +0.055 |
netflix | +0.052 |
Vas | +0.051 |
thought | +0.050 |
imet | +0.050 |
Neg logit contributions | |
Conquest | -0.047 |
losers | -0.046 |
brook | -0.046 |
ocide | -0.043 |
ndra | -0.042 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
detects | +1.357 |
netflix | +1.252 |
Vas | +1.200 |
Hamp | +1.174 |
imet | +1.165 |
Neg logit contributions | |
Conquest | -2.473 |
losers | -2.460 |
brook | -2.419 |
ocide | -2.330 |
ndra | -2.314 |
Token | this |
Token ID | 428 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Conquest | +0.113 |
losers | +0.111 |
brook | +0.110 |
ocide | +0.102 |
ndra | +0.101 |
Neg logit contributions | |
detects | -0.147 |
netflix | -0.140 |
Vas | -0.137 |
thought | -0.135 |
imet | -0.135 |
Token | story |
Token ID | 1621 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
detects | +2.422 |
netflix | +2.271 |
Vas | +2.240 |
Hamp | +2.201 |
thought | +2.190 |
Neg logit contributions | |
Conquest | -2.308 |
losers | -2.283 |
brook | -2.239 |
ocide | -2.123 |
ndra | -2.084 |
Token | : |
Token ID | 25 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
detects | +2.519 |
netflix | +2.297 |
Vas | +2.230 |
thought | +2.193 |
Hamp | +2.057 |
Neg logit contributions | |
Conquest | -6.101 |
losers | -6.025 |
brook | -5.836 |
ocide | -5.779 |
ndra | -5.624 |
Token | http |
Token ID | 2638 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
detects | +2.441 |
netflix | +2.313 |
Vas | +2.269 |
Hamp | +2.238 |
thought | +2.202 |
Neg logit contributions | |
Conquest | -2.410 |
losers | -2.387 |
brook | -2.353 |
ocide | -2.240 |
ndra | -2.180 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
detects | +3.099 |
netflix | +2.976 |
Vas | +2.906 |
thought | +2.894 |
Hamp | +2.839 |
Neg logit contributions | |
Conquest | -2.716 |
losers | -2.690 |
brook | -2.503 |
ocide | -2.411 |
ndra | -2.316 |
Token | usat |
Token ID | 37937 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
detects | +1.333 |
netflix | +1.260 |
thought | +1.194 |
Vas | +1.174 |
Hamp | +1.158 |
Neg logit contributions | |
Conquest | -2.743 |
losers | -2.704 |
brook | -2.586 |
ocide | -2.531 |
ndra | -2.481 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Conquest | +0.061 |
losers | +0.061 |
brook | +0.059 |
ocide | +0.056 |
ndra | +0.055 |
Neg logit contributions | |
detects | -0.071 |
netflix | -0.068 |
Vas | -0.067 |
thought | -0.066 |
Hamp | -0.065 |
Token | r |
Token ID | 81 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Conquest | +0.140 |
losers | +0.139 |
brook | +0.137 |
ocide | +0.129 |
ndra | +0.127 |
Neg logit contributions | |
detects | -0.126 |
netflix | -0.120 |
Vas | -0.116 |
thought | -0.114 |
Hamp | -0.114 |
Token | ga |
Token ID | 4908 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Conquest | +0.084 |
losers | +0.083 |
brook | +0.082 |
ocide | +0.078 |
ndra | +0.076 |
Neg logit contributions | |
detects | -0.080 |
netflix | -0.076 |
Vas | -0.073 |
thought | -0.073 |
Hamp | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Conquest | +0.094 |
losers | +0.093 |
brook | +0.092 |
ocide | +0.086 |
ndra | +0.084 |
Neg logit contributions | |
detects | -0.106 |
netflix | -0.101 |
Vas | -0.099 |
thought | -0.097 |
Hamp | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
detects | +0.590 |
netflix | +0.566 |
Vas | +0.556 |
thought | +0.552 |
Hamp | +0.546 |
Neg logit contributions | |
Conquest | -0.451 |
losers | -0.446 |
brook | -0.432 |
ocide | -0.410 |
ndra | -0.401 |
Token | Read |
Token ID | 5569 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
detects | +0.339 |
netflix | +0.328 |
Vas | +0.316 |
thought | +0.315 |
Hamp | +0.312 |
Neg logit contributions | |
Conquest | -0.341 |
losers | -0.334 |
brook | -0.328 |
ocide | -0.308 |
ndra | -0.304 |
Token | Next |
Token ID | 7406 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
detects | +0.804 |
netflix | +0.755 |
Vas | +0.727 |
thought | +0.718 |
Hamp | +0.716 |
Neg logit contributions | |
Conquest | -1.107 |
losers | -1.096 |
brook | -1.084 |
ocide | -1.030 |
ndra | -1.019 |
Token |
|
Token ID | 198 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
detects | +3.773 |
Vas | +3.623 |
netflix | +3.496 |
Hamp | +3.426 |
thought | +3.323 |
Neg logit contributions | |
losers | -4.706 |
brook | -4.667 |
Conquest | -4.662 |
ocide | -4.463 |
ndra | -4.220 |
Token |
|
Token ID | 198 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
Conquest | +0.388 |
losers | +0.383 |
brook | +0.375 |
ocide | +0.350 |
ndra | +0.344 |
Neg logit contributions | |
detects | -0.547 |
netflix | -0.524 |
Vas | -0.511 |
thought | -0.507 |
Hamp | -0.505 |
Token | L |
Token ID | 43 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Conquest | +0.591 |
losers | +0.582 |
brook | +0.574 |
ocide | +0.543 |
ndra | +0.536 |
Neg logit contributions | |
detects | -0.507 |
netflix | -0.483 |
Vas | -0.467 |
thought | -0.462 |
Hamp | -0.459 |
Token | AT |
Token ID | 1404 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
detects | +0.193 |
netflix | +0.184 |
Vas | +0.179 |
thought | +0.177 |
imet | +0.177 |
Neg logit contributions | |
Conquest | -0.199 |
losers | -0.196 |
brook | -0.194 |
ocide | -0.182 |
ndra | -0.180 |
Token | EST |
Token ID | 6465 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
detects | +1.081 |
netflix | +1.013 |
Vas | +0.984 |
thought | +0.954 |
imet | +0.953 |
Neg logit contributions | |
Conquest | -1.755 |
losers | -1.722 |
brook | -1.718 |
ocide | -1.646 |
ndra | -1.617 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Conquest | +0.999 |
losers | +0.984 |
brook | +0.978 |
ocide | +0.895 |
ndra | +0.885 |
Neg logit contributions | |
detects | -1.540 |
netflix | -1.474 |
Vas | -1.429 |
imet | -1.423 |
Hamp | -1.419 |
Token | Read |
Token ID | 5569 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
Conquest | +1.344 |
losers | +1.333 |
brook | +1.326 |
ocide | +1.245 |
ndra | +1.231 |
Neg logit contributions | |
detects | -1.340 |
netflix | -1.265 |
Vas | -1.229 |
Hamp | -1.213 |
imet | -1.211 |
Token | or |
Token ID | 393 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
detects | +0.065 |
netflix | +0.062 |
Vas | +0.060 |
thought | +0.059 |
imet | +0.059 |
Neg logit contributions | |
Conquest | -0.060 |
losers | -0.060 |
brook | -0.059 |
ocide | -0.055 |
ndra | -0.054 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
detects | +1.477 |
netflix | +1.353 |
Vas | +1.306 |
Hamp | +1.272 |
imet | +1.267 |
Neg logit contributions | |
Conquest | -2.697 |
losers | -2.686 |
brook | -2.635 |
ocide | -2.551 |
ndra | -2.532 |
Token | this |
Token ID | 428 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Conquest | +0.122 |
losers | +0.121 |
brook | +0.119 |
ocide | +0.111 |
ndra | +0.110 |
Neg logit contributions | |
detects | -0.161 |
netflix | -0.154 |
Vas | -0.149 |
thought | -0.148 |
imet | -0.148 |
Token | story |
Token ID | 1621 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
detects | +2.502 |
netflix | +2.346 |
Vas | +2.314 |
Hamp | +2.276 |
thought | +2.269 |
Neg logit contributions | |
Conquest | -2.372 |
losers | -2.347 |
brook | -2.298 |
ocide | -2.180 |
ndra | -2.143 |
Token | : |
Token ID | 25 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
detects | +2.529 |
netflix | +2.298 |
Vas | +2.233 |
thought | +2.198 |
Hamp | +2.075 |
Neg logit contributions | |
Conquest | -5.859 |
losers | -5.791 |
brook | -5.627 |
ocide | -5.550 |
ndra | -5.412 |
Token | http |
Token ID | 2638 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
detects | +2.284 |
netflix | +2.163 |
Vas | +2.121 |
Hamp | +2.093 |
thought | +2.078 |
Neg logit contributions | |
Conquest | -2.173 |
losers | -2.161 |
brook | -2.124 |
ocide | -2.017 |
ndra | -1.966 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
detects | +2.882 |
netflix | +2.765 |
Vas | +2.705 |
thought | +2.697 |
Hamp | +2.654 |
Neg logit contributions | |
Conquest | -2.460 |
losers | -2.440 |
brook | -2.281 |
ocide | -2.191 |
ndra | -2.108 |
Token | usat |
Token ID | 37937 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
detects | +1.365 |
netflix | +1.290 |
thought | +1.231 |
Vas | +1.205 |
Hamp | +1.197 |
Neg logit contributions | |
Conquest | -2.811 |
losers | -2.775 |
brook | -2.644 |
ocide | -2.591 |
ndra | -2.528 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Conquest | +0.412 |
losers | +0.407 |
brook | +0.398 |
ocide | +0.374 |
ndra | +0.368 |
Neg logit contributions | |
detects | -0.496 |
netflix | -0.474 |
Vas | -0.462 |
thought | -0.458 |
Hamp | -0.455 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Conquest | +0.139 |
losers | +0.138 |
brook | +0.135 |
ocide | +0.126 |
ndra | +0.124 |
Neg logit contributions | |
detects | -0.195 |
netflix | -0.187 |
Vas | -0.183 |
thought | -0.181 |
Hamp | -0.180 |
Token | Read |
Token ID | 5569 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
detects | +0.099 |
netflix | +0.093 |
Vas | +0.090 |
thought | +0.090 |
Hamp | +0.089 |
Neg logit contributions | |
Conquest | -0.125 |
losers | -0.124 |
brook | -0.122 |
ocide | -0.116 |
ndra | -0.115 |
Token | or |
Token ID | 393 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Conquest | +0.302 |
losers | +0.299 |
brook | +0.296 |
ocide | +0.280 |
ndra | +0.277 |
Neg logit contributions | |
detects | -0.261 |
netflix | -0.247 |
Vas | -0.238 |
thought | -0.236 |
Hamp | -0.235 |
Token | Share |
Token ID | 8734 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
detects | +1.346 |
netflix | +1.246 |
Vas | +1.214 |
thought | +1.182 |
imet | +1.179 |
Neg logit contributions | |
Conquest | -2.194 |
losers | -2.190 |
brook | -2.160 |
ocide | -2.061 |
ndra | -2.056 |
Token | this |
Token ID | 428 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
detects | +0.411 |
netflix | +0.393 |
Vas | +0.382 |
thought | +0.378 |
Hamp | +0.377 |
Neg logit contributions | |
Conquest | -0.325 |
losers | -0.321 |
brook | -0.315 |
ocide | -0.295 |
ndra | -0.291 |
Token | story |
Token ID | 1621 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
detects | +2.145 |
netflix | +2.027 |
Vas | +1.991 |
Hamp | +1.958 |
thought | +1.954 |
Neg logit contributions | |
Conquest | -1.970 |
losers | -1.953 |
brook | -1.918 |
ocide | -1.811 |
ndra | -1.793 |
Token | : |
Token ID | 25 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
detects | +2.546 |
netflix | +2.286 |
Vas | +2.262 |
thought | +2.209 |
Hamp | +2.100 |
Neg logit contributions | |
Conquest | -5.785 |
losers | -5.750 |
brook | -5.602 |
ocide | -5.509 |
ndra | -5.383 |
Token | http |
Token ID | 2638 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
detects | +2.158 |
netflix | +2.044 |
Vas | +2.012 |
Hamp | +1.979 |
thought | +1.966 |
Neg logit contributions | |
Conquest | -2.084 |
losers | -2.080 |
brook | -2.042 |
ocide | -1.936 |
ndra | -1.901 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
detects | +2.869 |
netflix | +2.758 |
Vas | +2.698 |
thought | +2.677 |
Hamp | +2.638 |
Neg logit contributions | |
Conquest | -2.398 |
losers | -2.371 |
brook | -2.239 |
ocide | -2.142 |
ndra | -2.070 |
Token | on |
Token ID | 261 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
detects | +1.628 |
netflix | +1.571 |
thought | +1.502 |
Vas | +1.485 |
Hamp | +1.471 |
Neg logit contributions | |
Conquest | -2.290 |
losers | -2.250 |
brook | -2.127 |
ocide | -2.077 |
ndra | -2.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
detects | +1.537 |
netflix | +1.481 |
Vas | +1.424 |
thought | +1.424 |
imet | +1.419 |
Neg logit contributions | |
Conquest | -1.326 |
losers | -1.297 |
brook | -1.259 |
ocide | -1.189 |
ndra | -1.169 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Conquest | +0.252 |
losers | +0.249 |
brook | +0.246 |
ocide | +0.231 |
ndra | +0.227 |
Neg logit contributions | |
detects | -0.277 |
netflix | -0.263 |
Vas | -0.255 |
thought | -0.253 |
Hamp | -0.252 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Conquest | +0.079 |
losers | +0.079 |
brook | +0.078 |
ocide | +0.073 |
ndra | +0.072 |
Neg logit contributions | |
detects | -0.081 |
netflix | -0.077 |
Vas | -0.076 |
Hamp | -0.075 |
thought | -0.074 |
Token | Abstract |
Token ID | 23839 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
detects | +0.230 |
netflix | +0.221 |
thought | +0.211 |
Vas | +0.211 |
imet | +0.208 |
Neg logit contributions | |
Conquest | -0.277 |
losers | -0.273 |
brook | -0.267 |
ocide | -0.254 |
ndra | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
detects | +4.108 |
Vas | +3.976 |
netflix | +3.867 |
Hamp | +3.853 |
imet | +3.785 |
Neg logit contributions | |
losers | -3.640 |
Conquest | -3.544 |
brook | -3.525 |
ocide | -3.346 |
ndra | -3.302 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
detects | +0.062 |
netflix | +0.059 |
Vas | +0.058 |
thought | +0.058 |
Hamp | +0.057 |
Neg logit contributions | |
Conquest | -0.046 |
losers | -0.045 |
brook | -0.044 |
ocide | -0.042 |
ndra | -0.041 |
Token | Background |
Token ID | 21756 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
detects | +0.168 |
netflix | +0.160 |
Vas | +0.155 |
thought | +0.154 |
imet | +0.152 |
Neg logit contributions | |
Conquest | -0.183 |
losers | -0.181 |
brook | -0.178 |
ocide | -0.168 |
ndra | -0.166 |
Token | Depression |
Token ID | 22483 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
detects | +3.837 |
Vas | +3.711 |
Hamp | +3.535 |
netflix | +3.505 |
thought | +3.422 |
Neg logit contributions | |
losers | -4.341 |
Conquest | -4.224 |
brook | -4.189 |
ocide | -4.029 |
ndra | -3.969 |
Token | presents |
Token ID | 10969 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
detects | +0.313 |
netflix | +0.295 |
Vas | +0.288 |
imet | +0.284 |
thought | +0.284 |
Neg logit contributions | |
Conquest | -0.308 |
losers | -0.304 |
brook | -0.302 |
ocide | -0.284 |
ndra | -0.282 |
Token | a |
Token ID | 257 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
detects | +1.948 |
netflix | +1.794 |
Vas | +1.793 |
thought | +1.731 |
Hamp | +1.730 |
Neg logit contributions | |
brook | -2.479 |
Conquest | -2.466 |
losers | -2.420 |
ocide | -2.345 |
ndra | -2.335 |
Token | significant |
Token ID | 2383 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
detects | +0.917 |
netflix | +0.872 |
Vas | +0.850 |
thought | +0.838 |
Hamp | +0.833 |
Neg logit contributions | |
Conquest | -0.969 |
brook | -0.956 |
losers | -0.955 |
ocide | -0.901 |
ndra | -0.893 |
Token | burden |
Token ID | 10538 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
detects | +1.238 |
netflix | +1.179 |
Vas | +1.145 |
Hamp | +1.124 |
thought | +1.121 |
Neg logit contributions | |
Conquest | -1.437 |
brook | -1.427 |
losers | -1.404 |
ndra | -1.341 |
ocide | -1.337 |
Token | So |
Token ID | 2396 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
detects | +0.356 |
netflix | +0.342 |
Vas | +0.329 |
thought | +0.328 |
Hamp | +0.325 |
Neg logit contributions | |
Conquest | -0.437 |
losers | -0.431 |
brook | -0.422 |
ocide | -0.400 |
ndra | -0.396 |
Token | when |
Token ID | 618 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
detects | +0.291 |
netflix | +0.273 |
Vas | +0.267 |
Hamp | +0.262 |
thought | +0.260 |
Neg logit contributions | |
Conquest | -0.341 |
losers | -0.336 |
brook | -0.335 |
ocide | -0.318 |
ndra | -0.313 |
Token | was |
Token ID | 373 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
detects | +0.688 |
netflix | +0.646 |
Vas | +0.631 |
Hamp | +0.621 |
thought | +0.620 |
Neg logit contributions | |
Conquest | -0.803 |
losers | -0.794 |
brook | -0.788 |
ocide | -0.748 |
ndra | -0.736 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
detects | +0.495 |
netflix | +0.465 |
Vas | +0.456 |
thought | +0.452 |
Hamp | +0.451 |
Neg logit contributions | |
Conquest | -0.564 |
losers | -0.558 |
brook | -0.556 |
ocide | -0.525 |
ndra | -0.516 |
Token | last |
Token ID | 938 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
detects | +2.021 |
netflix | +1.925 |
Vas | +1.906 |
Hamp | +1.901 |
thought | +1.878 |
Neg logit contributions | |
Conquest | -1.755 |
brook | -1.745 |
losers | -1.739 |
ocide | -1.622 |
ndra | -1.608 |
Token | time |
Token ID | 640 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
detects | +1.761 |
netflix | +1.657 |
Vas | +1.634 |
Hamp | +1.617 |
thought | +1.603 |
Neg logit contributions | |
Conquest | -1.957 |
brook | -1.952 |
losers | -1.937 |
ocide | -1.844 |
ndra | -1.814 |
Token | Gilbert |
Token ID | 24023 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
detects | +3.220 |
Vas | +3.023 |
netflix | +2.970 |
Hamp | +2.967 |
thought | +2.899 |
Neg logit contributions | |
Conquest | -4.675 |
brook | -4.639 |
losers | -4.577 |
ocide | -4.409 |
ndra | -4.252 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
detects | +1.898 |
netflix | +1.773 |
Vas | +1.746 |
thought | +1.724 |
Hamp | +1.703 |
Neg logit contributions | |
Conquest | -2.074 |
losers | -2.038 |
brook | -2.013 |
ocide | -1.920 |
ndra | -1.887 |
Token | the |
Token ID | 262 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
detects | +1.435 |
netflix | +1.356 |
Vas | +1.322 |
Hamp | +1.302 |
thought | +1.298 |
Neg logit contributions | |
Conquest | -1.724 |
losers | -1.712 |
brook | -1.694 |
ocide | -1.603 |
ndra | -1.582 |
Token | civil |
Token ID | 3026 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
detects | +0.152 |
netflix | +0.141 |
Vas | +0.136 |
Hamp | +0.133 |
thought | +0.133 |
Neg logit contributions | |
Conquest | -0.273 |
losers | -0.270 |
brook | -0.268 |
ocide | -0.256 |
ndra | -0.253 |
Token | rights |
Token ID | 2489 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
detects | +0.274 |
netflix | +0.251 |
Vas | +0.243 |
Hamp | +0.240 |
imet | +0.238 |
Neg logit contributions | |
Conquest | -0.514 |
losers | -0.505 |
brook | -0.504 |
ocide | -0.485 |
ndra | -0.478 |
Token | - |
Token ID | 12 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
detects | +0.354 |
netflix | +0.335 |
Vas | +0.325 |
thought | +0.322 |
imet | +0.321 |
Neg logit contributions | |
Conquest | -0.359 |
losers | -0.355 |
brook | -0.351 |
ocide | -0.331 |
ndra | -0.327 |
Token | technology |
Token ID | 45503 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
Conquest | +1.772 |
brook | +1.764 |
losers | +1.761 |
ocide | +1.633 |
ndra | +1.602 |
Neg logit contributions | |
detects | -2.393 |
netflix | -2.272 |
Vas | -2.242 |
Hamp | -2.215 |
imet | -2.193 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Conquest | +0.389 |
losers | +0.385 |
brook | +0.379 |
ocide | +0.355 |
ndra | +0.350 |
Neg logit contributions | |
detects | -0.458 |
netflix | -0.437 |
Vas | -0.424 |
thought | -0.420 |
Hamp | -0.420 |
Token | The |
Token ID | 464 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
detects | +0.146 |
netflix | +0.140 |
thought | +0.134 |
Vas | +0.134 |
imet | +0.132 |
Neg logit contributions | |
Conquest | -0.176 |
losers | -0.173 |
brook | -0.170 |
ocide | -0.161 |
ndra | -0.159 |
Token | People |
Token ID | 4380 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
detects | +0.024 |
netflix | +0.022 |
Vas | +0.022 |
Hamp | +0.021 |
thought | +0.021 |
Neg logit contributions | |
Conquest | -0.026 |
losers | -0.026 |
brook | -0.025 |
ocide | -0.024 |
ndra | -0.024 |
Token | v |
Token ID | 410 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
Conquest | +0.458 |
losers | +0.453 |
brook | +0.447 |
ocide | +0.421 |
ndra | +0.415 |
Neg logit contributions | |
detects | -0.464 |
netflix | -0.441 |
Vas | -0.427 |
thought | -0.423 |
Hamp | -0.422 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
detects | +3.948 |
netflix | +3.827 |
Vas | +3.827 |
Hamp | +3.743 |
imet | +3.666 |
Neg logit contributions | |
Conquest | -3.782 |
losers | -3.776 |
brook | -3.698 |
ocide | -3.453 |
ndra | -3.384 |
Token | O |
Token ID | 440 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
detects | +1.453 |
Vas | +1.411 |
netflix | +1.383 |
Hamp | +1.363 |
thought | +1.326 |
Neg logit contributions | |
losers | -1.766 |
Conquest | -1.760 |
brook | -1.727 |
ocide | -1.656 |
ndra | -1.593 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
detects | +0.577 |
Vas | +0.546 |
netflix | +0.538 |
thought | +0.535 |
imet | +0.534 |
Neg logit contributions | |
Conquest | -0.521 |
losers | -0.511 |
brook | -0.500 |
ocide | -0.472 |
ndra | -0.451 |
Token | J |
Token ID | 41 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Conquest | +0.188 |
losers | +0.186 |
brook | +0.184 |
ocide | +0.175 |
ndra | +0.173 |
Neg logit contributions | |
detects | -0.148 |
netflix | -0.140 |
Vas | -0.134 |
thought | -0.133 |
imet | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Conquest | +0.192 |
losers | +0.190 |
brook | +0.186 |
ocide | +0.174 |
ndra | +0.171 |
Neg logit contributions | |
detects | -0.244 |
netflix | -0.234 |
Vas | -0.225 |
thought | -0.225 |
Hamp | -0.224 |
Token | ) |
Token ID | 8 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
detects | +0.041 |
netflix | +0.038 |
Vas | +0.037 |
thought | +0.036 |
Hamp | +0.036 |
Neg logit contributions | |
Conquest | -0.053 |
losers | -0.053 |
brook | -0.052 |
ocide | -0.050 |
ndra | -0.049 |
Token | image |
Token ID | 2939 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
detects | +0.566 |
netflix | +0.520 |
Vas | +0.507 |
Hamp | +0.496 |
imet | +0.494 |
Neg logit contributions | |
Conquest | -0.868 |
losers | -0.855 |
brook | -0.850 |
ocide | -0.808 |
ndra | -0.804 |
Token | = |
Token ID | 796 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
detects | +1.219 |
netflix | +1.143 |
Vas | +1.101 |
thought | +1.080 |
Hamp | +1.078 |
Neg logit contributions | |
losers | -2.250 |
Conquest | -2.242 |
brook | -2.189 |
ocide | -2.108 |
ndra | -2.078 |
Token | im |
Token ID | 545 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
detects | +1.128 |
netflix | +1.064 |
Vas | +1.041 |
Hamp | +1.029 |
imet | +1.026 |
Neg logit contributions | |
Conquest | -0.937 |
losers | -0.919 |
brook | -0.916 |
ocide | -0.857 |
ndra | -0.850 |
Token | utils |
Token ID | 26791 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
detects | +0.273 |
netflix | +0.249 |
Vas | +0.233 |
thought | +0.229 |
imet | +0.228 |
Neg logit contributions | |
Conquest | -0.730 |
losers | -0.723 |
brook | -0.716 |
ocide | -0.688 |
ndra | -0.682 |
Token | . |
Token ID | 13 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
detects | +2.751 |
netflix | +2.620 |
Vas | +2.591 |
thought | +2.559 |
Hamp | +2.524 |
Neg logit contributions | |
Conquest | -2.705 |
losers | -2.684 |
brook | -2.587 |
ocide | -2.472 |
ndra | -2.438 |
Token | res |
Token ID | 411 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
detects | +3.632 |
netflix | +3.490 |
thought | +3.348 |
Vas | +3.314 |
imet | +3.292 |
Neg logit contributions | |
Conquest | -4.282 |
losers | -4.196 |
brook | -4.021 |
ndra | -3.846 |
ocide | -3.834 |
Token | ize |
Token ID | 1096 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
detects | +0.774 |
netflix | +0.730 |
thought | +0.688 |
Vas | +0.686 |
imet | +0.682 |
Neg logit contributions | |
Conquest | -1.356 |
losers | -1.350 |
brook | -1.315 |
ocide | -1.260 |
ndra | -1.255 |
Token | ( |
Token ID | 7 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
detects | +1.592 |
netflix | +1.519 |
thought | +1.474 |
Vas | +1.473 |
Hamp | +1.442 |
Neg logit contributions | |
Conquest | -1.991 |
losers | -1.975 |
brook | -1.913 |
ocide | -1.839 |
ndra | -1.817 |
Token | image |
Token ID | 9060 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Conquest | +0.206 |
losers | +0.204 |
brook | +0.200 |
ocide | +0.189 |
ndra | +0.187 |
Neg logit contributions | |
detects | -0.182 |
netflix | -0.173 |
Vas | -0.167 |
thought | -0.166 |
imet | -0.165 |
Token | , |
Token ID | 11 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
detects | +1.168 |
netflix | +1.110 |
Vas | +1.075 |
thought | +1.063 |
Hamp | +1.058 |
Neg logit contributions | |
Conquest | -1.294 |
losers | -1.284 |
brook | -1.260 |
ocide | -1.197 |
ndra | -1.181 |
Token | s |
Token ID | 82 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
detects | +0.089 |
netflix | +0.083 |
Vas | +0.080 |
thought | +0.079 |
imet | +0.079 |
Neg logit contributions | |
Conquest | -0.139 |
losers | -0.138 |
brook | -0.136 |
ocide | -0.130 |
ndra | -0.128 |
Token | a |
Token ID | 257 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
detects | +0.237 |
netflix | +0.224 |
Vas | +0.219 |
thought | +0.216 |
Hamp | +0.215 |
Neg logit contributions | |
Conquest | -0.265 |
losers | -0.261 |
brook | -0.258 |
ocide | -0.245 |
ndra | -0.242 |
Token | start |
Token ID | 923 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Conquest | +0.570 |
losers | +0.562 |
brook | +0.556 |
ocide | +0.524 |
ndra | +0.518 |
Neg logit contributions | |
detects | -0.552 |
netflix | -0.524 |
Vas | -0.508 |
thought | -0.503 |
Hamp | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Conquest | +0.252 |
losers | +0.249 |
brook | +0.246 |
ocide | +0.231 |
ndra | +0.227 |
Neg logit contributions | |
detects | -0.277 |
netflix | -0.263 |
Vas | -0.255 |
thought | -0.253 |
Hamp | -0.252 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Conquest | +0.079 |
losers | +0.079 |
brook | +0.078 |
ocide | +0.073 |
ndra | +0.072 |
Neg logit contributions | |
detects | -0.081 |
netflix | -0.077 |
Vas | -0.076 |
Hamp | -0.075 |
thought | -0.074 |
Token | Abstract |
Token ID | 23839 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
detects | +0.230 |
netflix | +0.221 |
thought | +0.211 |
Vas | +0.211 |
imet | +0.208 |
Neg logit contributions | |
Conquest | -0.277 |
losers | -0.273 |
brook | -0.267 |
ocide | -0.254 |
ndra | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
detects | +4.108 |
Vas | +3.976 |
netflix | +3.867 |
Hamp | +3.853 |
imet | +3.785 |
Neg logit contributions | |
losers | -3.640 |
Conquest | -3.544 |
brook | -3.525 |
ocide | -3.346 |
ndra | -3.302 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
detects | +0.062 |
netflix | +0.059 |
Vas | +0.058 |
thought | +0.058 |
Hamp | +0.057 |
Neg logit contributions | |
Conquest | -0.046 |
losers | -0.045 |
brook | -0.044 |
ocide | -0.042 |
ndra | -0.041 |
Token | Background |
Token ID | 21756 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
detects | +0.168 |
netflix | +0.160 |
Vas | +0.155 |
thought | +0.154 |
imet | +0.152 |
Neg logit contributions | |
Conquest | -0.183 |
losers | -0.181 |
brook | -0.178 |
ocide | -0.168 |
ndra | -0.166 |
Token | Depression |
Token ID | 22483 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
detects | +3.837 |
Vas | +3.711 |
Hamp | +3.535 |
netflix | +3.505 |
thought | +3.422 |
Neg logit contributions | |
losers | -4.341 |
Conquest | -4.224 |
brook | -4.189 |
ocide | -4.029 |
ndra | -3.969 |
Token | presents |
Token ID | 10969 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
detects | +0.313 |
netflix | +0.295 |
Vas | +0.288 |
imet | +0.284 |
thought | +0.284 |
Neg logit contributions | |
Conquest | -0.308 |
losers | -0.304 |
brook | -0.302 |
ocide | -0.284 |
ndra | -0.282 |
Token | there |
Token ID | 612 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
detects | +0.102 |
netflix | +0.097 |
Vas | +0.095 |
Hamp | +0.093 |
thought | +0.093 |
Neg logit contributions | |
Conquest | -0.107 |
losers | -0.106 |
brook | -0.105 |
ocide | -0.100 |
ndra | -0.098 |
Token | seems |
Token ID | 2331 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
detects | +0.330 |
netflix | +0.310 |
Vas | +0.304 |
thought | +0.299 |
imet | +0.298 |
Neg logit contributions | |
Conquest | -0.322 |
losers | -0.316 |
brook | -0.314 |
ocide | -0.295 |
ndra | -0.291 |
Token | to |
Token ID | 284 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
detects | +0.169 |
netflix | +0.161 |
Vas | +0.156 |
thought | +0.154 |
imet | +0.154 |
Neg logit contributions | |
Conquest | -0.157 |
losers | -0.156 |
brook | -0.153 |
ocide | -0.144 |
ndra | -0.142 |
Token | me |
Token ID | 502 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
detects | +0.302 |
netflix | +0.287 |
Vas | +0.278 |
thought | +0.275 |
Hamp | +0.274 |
Neg logit contributions | |
Conquest | -0.312 |
losers | -0.309 |
brook | -0.305 |
ocide | -0.287 |
ndra | -0.284 |
Token | almost |
Token ID | 2048 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
detects | +2.270 |
netflix | +2.133 |
Vas | +2.110 |
Hamp | +2.079 |
thought | +2.079 |
Neg logit contributions | |
Conquest | -2.668 |
losers | -2.622 |
brook | -2.601 |
ocide | -2.494 |
ndra | -2.412 |
Token | zero |
Token ID | 6632 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
detects | +0.385 |
netflix | +0.366 |
Vas | +0.357 |
thought | +0.353 |
imet | +0.353 |
Neg logit contributions | |
Conquest | -0.336 |
losers | -0.331 |
brook | -0.328 |
ocide | -0.308 |
ndra | -0.303 |
Token | chance |
Token ID | 2863 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
detects | +2.925 |
Vas | +2.691 |
thought | +2.634 |
netflix | +2.614 |
Hamp | +2.614 |
Neg logit contributions | |
Conquest | -4.795 |
brook | -4.752 |
losers | -4.696 |
ocide | -4.577 |
ndra | -4.522 |
Token | that |
Token ID | 326 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
detects | +0.748 |
netflix | +0.702 |
Vas | +0.691 |
Hamp | +0.679 |
thought | +0.677 |
Neg logit contributions | |
Conquest | -0.944 |
losers | -0.932 |
brook | -0.924 |
ocide | -0.882 |
ndra | -0.863 |
Token | the |
Token ID | 262 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Conquest | +0.589 |
losers | +0.582 |
brook | +0.575 |
ocide | +0.541 |
ndra | +0.533 |
Neg logit contributions | |
detects | -0.611 |
netflix | -0.580 |
Vas | -0.564 |
thought | -0.557 |
Hamp | -0.556 |
Token | judge |
Token ID | 5052 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
detects | +0.377 |
netflix | +0.353 |
Vas | +0.350 |
Hamp | +0.345 |
thought | +0.341 |
Neg logit contributions | |
Conquest | -0.437 |
losers | -0.430 |
brook | -0.427 |
ocide | -0.407 |
ndra | -0.400 |
Token | will |
Token ID | 481 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Conquest | +0.351 |
losers | +0.347 |
brook | +0.342 |
ocide | +0.324 |
ndra | +0.319 |
Neg logit contributions | |
detects | -0.338 |
netflix | -0.318 |
Vas | -0.310 |
thought | -0.306 |
imet | -0.305 |
Token |
|
Token ID | 198 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Conquest | +0.446 |
losers | +0.440 |
brook | +0.433 |
ocide | +0.403 |
ndra | +0.396 |
Neg logit contributions | |
detects | -0.609 |
netflix | -0.583 |
Vas | -0.567 |
thought | -0.562 |
imet | -0.561 |
Token |
|
Token ID | 198 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
Conquest | +0.322 |
losers | +0.318 |
brook | +0.312 |
ocide | +0.291 |
ndra | +0.286 |
Neg logit contributions | |
detects | -0.460 |
netflix | -0.440 |
Vas | -0.430 |
thought | -0.426 |
Hamp | -0.424 |
Token | V |
Token ID | 53 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Conquest | +0.047 |
losers | +0.047 |
brook | +0.046 |
ocide | +0.044 |
ndra | +0.043 |
Neg logit contributions | |
detects | -0.037 |
netflix | -0.035 |
Vas | -0.034 |
thought | -0.034 |
Hamp | -0.033 |
Token | il |
Token ID | 346 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
detects | +0.870 |
netflix | +0.821 |
Vas | +0.808 |
imet | +0.796 |
thought | +0.792 |
Neg logit contributions | |
Conquest | -1.001 |
losers | -0.996 |
brook | -0.983 |
ocide | -0.917 |
ndra | -0.916 |
Token | ma |
Token ID | 2611 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
detects | +1.263 |
netflix | +1.199 |
Vas | +1.183 |
imet | +1.170 |
thought | +1.160 |
Neg logit contributions | |
Conquest | -1.247 |
losers | -1.242 |
brook | -1.211 |
ndra | -1.138 |
ocide | -1.136 |
Token | v |
Token ID | 410 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
detects | +1.673 |
Vas | +1.559 |
netflix | +1.558 |
Hamp | +1.518 |
thought | +1.501 |
Neg logit contributions | |
Conquest | -1.876 |
losers | -1.869 |
brook | -1.843 |
ocide | -1.748 |
ndra | -1.736 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
detects | +3.770 |
Vas | +3.636 |
netflix | +3.591 |
Hamp | +3.549 |
imet | +3.472 |
Neg logit contributions | |
brook | -3.782 |
losers | -3.770 |
Conquest | -3.759 |
ocide | -3.496 |
ndra | -3.457 |
Token | Goodell |
Token ID | 41648 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
detects | +1.217 |
netflix | +1.144 |
Vas | +1.141 |
Hamp | +1.119 |
thought | +1.090 |
Neg logit contributions | |
losers | -1.761 |
Conquest | -1.751 |
brook | -1.744 |
ocide | -1.668 |
ndra | -1.647 |
Token | Def |
Token ID | 2896 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
detects | +0.981 |
netflix | +0.925 |
Vas | +0.904 |
Hamp | +0.890 |
thought | +0.884 |
Neg logit contributions | |
Conquest | -1.051 |
losers | -1.044 |
brook | -1.032 |
ocide | -0.979 |
ndra | -0.966 |
Token | amation |
Token ID | 14755 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
detects | +1.290 |
netflix | +1.226 |
thought | +1.201 |
Vas | +1.196 |
imet | +1.185 |
Neg logit contributions | |
Conquest | -0.893 |
losers | -0.875 |
brook | -0.855 |
ocide | -0.793 |
ndra | -0.774 |
Token | / |
Token ID | 1220 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
detects | +0.321 |
netflix | +0.304 |
Vas | +0.296 |
Hamp | +0.292 |
thought | +0.291 |
Neg logit contributions | |
Conquest | -0.331 |
losers | -0.328 |
brook | -0.324 |
ocide | -0.306 |
ndra | -0.302 |
Token |
|
Token ID | 198 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Conquest | +0.541 |
losers | +0.535 |
brook | +0.529 |
ocide | +0.499 |
ndra | +0.493 |
Neg logit contributions | |
detects | -0.484 |
netflix | -0.458 |
Vas | -0.442 |
thought | -0.438 |
imet | -0.437 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Conquest | +0.498 |
losers | +0.491 |
brook | +0.483 |
ocide | +0.448 |
ndra | +0.441 |
Neg logit contributions | |
detects | -0.727 |
netflix | -0.696 |
Vas | -0.677 |
thought | -0.671 |
imet | -0.670 |
Token | Santa |
Token ID | 42694 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Conquest | +0.247 |
losers | +0.244 |
brook | +0.242 |
ocide | +0.229 |
ndra | +0.226 |
Neg logit contributions | |
detects | -0.204 |
netflix | -0.193 |
Vas | -0.186 |
thought | -0.184 |
Hamp | -0.184 |
Token | Clara |
Token ID | 27443 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
detects | +0.601 |
netflix | +0.553 |
Vas | +0.537 |
Hamp | +0.525 |
thought | +0.517 |
Neg logit contributions | |
Conquest | -1.187 |
losers | -1.177 |
brook | -1.162 |
ocide | -1.124 |
ndra | -1.109 |
Token | County |
Token ID | 3418 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
Conquest | +0.362 |
losers | +0.357 |
brook | +0.351 |
ocide | +0.329 |
ndra | +0.323 |
Neg logit contributions | |
detects | -0.490 |
netflix | -0.468 |
Vas | -0.457 |
Hamp | -0.451 |
thought | -0.450 |
Token | v |
Token ID | 410 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
detects | +0.362 |
netflix | +0.338 |
Vas | +0.330 |
Hamp | +0.325 |
thought | +0.322 |
Neg logit contributions | |
Conquest | -0.451 |
losers | -0.446 |
brook | -0.442 |
ocide | -0.422 |
ndra | -0.415 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
detects | +3.609 |
Vas | +3.552 |
Hamp | +3.462 |
netflix | +3.412 |
thought | +3.338 |
Neg logit contributions | |
losers | -3.807 |
Conquest | -3.801 |
brook | -3.732 |
ocide | -3.593 |
ndra | -3.517 |
Token | Southern |
Token ID | 8050 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
detects | +1.367 |
netflix | +1.301 |
Vas | +1.277 |
Hamp | +1.259 |
thought | +1.243 |
Neg logit contributions | |
Conquest | -1.428 |
losers | -1.421 |
brook | -1.401 |
ocide | -1.328 |
ndra | -1.313 |
Token | Pacific |
Token ID | 8211 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
detects | +0.348 |
netflix | +0.326 |
Vas | +0.315 |
Hamp | +0.310 |
thought | +0.309 |
Neg logit contributions | |
Conquest | -0.529 |
losers | -0.526 |
brook | -0.519 |
ocide | -0.495 |
ndra | -0.489 |
Token | Railroad |
Token ID | 36289 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Conquest | +0.008 |
losers | +0.008 |
brook | +0.008 |
ocide | +0.007 |
ndra | +0.007 |
Neg logit contributions | |
detects | -0.012 |
netflix | -0.012 |
Vas | -0.012 |
thought | -0.011 |
Hamp | -0.011 |
Token | Company |
Token ID | 5834 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
detects | +0.133 |
netflix | +0.127 |
Vas | +0.123 |
thought | +0.122 |
Hamp | +0.122 |
Neg logit contributions | |
Conquest | -0.125 |
losers | -0.124 |
brook | -0.122 |
ocide | -0.115 |
ndra | -0.113 |
Token | Comments |
Token ID | 19502 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
detects | +0.018 |
netflix | +0.017 |
Vas | +0.017 |
Hamp | +0.016 |
thought | +0.016 |
Neg logit contributions | |
Conquest | -0.018 |
losers | -0.018 |
brook | -0.018 |
ocide | -0.017 |
ndra | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
detects | +0.730 |
netflix | +0.694 |
Vas | +0.677 |
Hamp | +0.668 |
thought | +0.667 |
Neg logit contributions | |
Conquest | -0.665 |
losers | -0.660 |
brook | -0.650 |
ocide | -0.611 |
ndra | -0.602 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
detects | +0.249 |
netflix | +0.239 |
Vas | +0.234 |
thought | +0.232 |
Hamp | +0.230 |
Neg logit contributions | |
Conquest | -0.181 |
losers | -0.179 |
brook | -0.175 |
ocide | -0.164 |
ndra | -0.161 |
Token | NFL |
Token ID | 32078 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
detects | +0.126 |
netflix | +0.120 |
Vas | +0.115 |
thought | +0.114 |
Hamp | +0.114 |
Neg logit contributions | |
Conquest | -0.172 |
losers | -0.170 |
brook | -0.168 |
ocide | -0.159 |
ndra | -0.158 |
Token | Players |
Token ID | 13094 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
detects | +0.437 |
netflix | +0.412 |
Vas | +0.402 |
thought | +0.396 |
Hamp | +0.396 |
Neg logit contributions | |
Conquest | -0.432 |
losers | -0.426 |
brook | -0.424 |
ocide | -0.398 |
ndra | -0.393 |
Token | v |
Token ID | 410 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
detects | +0.658 |
netflix | +0.625 |
Vas | +0.612 |
Hamp | +0.602 |
thought | +0.600 |
Neg logit contributions | |
Conquest | -0.657 |
losers | -0.652 |
brook | -0.646 |
ocide | -0.612 |
ndra | -0.603 |
Token | . |
Token ID | 13 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
detects | +3.764 |
Vas | +3.623 |
netflix | +3.603 |
Hamp | +3.556 |
thought | +3.453 |
Neg logit contributions | |
brook | -3.721 |
Conquest | -3.697 |
losers | -3.663 |
ocide | -3.421 |
ndra | -3.412 |
Token | NFL |
Token ID | 5134 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
detects | +1.305 |
netflix | +1.231 |
Vas | +1.226 |
Hamp | +1.200 |
thought | +1.171 |
Neg logit contributions | |
losers | -1.900 |
Conquest | -1.895 |
brook | -1.893 |
ocide | -1.800 |
ndra | -1.783 |
Token | Key |
Token ID | 7383 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
detects | +1.305 |
netflix | +1.233 |
Vas | +1.210 |
Hamp | +1.190 |
imet | +1.183 |
Neg logit contributions | |
Conquest | -1.196 |
losers | -1.179 |
brook | -1.178 |
ocide | -1.105 |
ndra | -1.091 |
Token | Documents |
Token ID | 33267 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
detects | +1.233 |
netflix | +1.166 |
Vas | +1.149 |
Hamp | +1.134 |
thought | +1.124 |
Neg logit contributions | |
Conquest | -1.172 |
losers | -1.160 |
brook | -1.146 |
ocide | -1.091 |
ndra | -1.070 |
Token | : |
Token ID | 25 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
detects | +1.309 |
netflix | +1.239 |
Vas | +1.211 |
Hamp | +1.195 |
thought | +1.185 |
Neg logit contributions | |
Conquest | -1.310 |
losers | -1.305 |
brook | -1.290 |
ocide | -1.225 |
ndra | -1.201 |
Token | of |
Token ID | 286 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Conquest | +1.686 |
losers | +1.663 |
brook | +1.630 |
ocide | +1.528 |
ndra | +1.507 |
Neg logit contributions | |
detects | -1.474 |
netflix | -1.437 |
Vas | -1.352 |
thought | -1.349 |
Hamp | -1.334 |
Token | block |
Token ID | 2512 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Conquest | +1.686 |
losers | +1.673 |
brook | +1.640 |
ocide | +1.542 |
ndra | +1.517 |
Neg logit contributions | |
detects | -1.500 |
netflix | -1.447 |
Vas | -1.378 |
thought | -1.373 |
Hamp | -1.362 |
Token | syntax |
Token ID | 15582 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
detects | +0.194 |
netflix | +0.185 |
Vas | +0.181 |
thought | +0.179 |
imet | +0.178 |
Neg logit contributions | |
Conquest | -0.150 |
losers | -0.148 |
brook | -0.146 |
ocide | -0.137 |
ndra | -0.135 |
Token | besides |
Token ID | 13769 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Conquest | +1.830 |
losers | +1.812 |
brook | +1.787 |
ocide | +1.690 |
ndra | +1.685 |
Neg logit contributions | |
detects | -1.113 |
netflix | -1.057 |
Vas | -0.993 |
thought | -0.990 |
imet | -0.977 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Conquest | +0.220 |
losers | +0.218 |
brook | +0.215 |
ocide | +0.203 |
ndra | +0.200 |
Neg logit contributions | |
detects | -0.202 |
netflix | -0.192 |
Vas | -0.185 |
thought | -0.183 |
Hamp | -0.183 |
Token | fact |
Token ID | 1109 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
detects | +0.251 |
netflix | +0.234 |
Vas | +0.231 |
imet | +0.227 |
Hamp | +0.227 |
Neg logit contributions | |
Conquest | -0.262 |
losers | -0.259 |
brook | -0.258 |
ocide | -0.244 |
ndra | -0.240 |
Token | that |
Token ID | 326 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
detects | +3.085 |
netflix | +2.820 |
Vas | +2.795 |
imet | +2.763 |
Hamp | +2.738 |
Neg logit contributions | |
Conquest | -4.427 |
losers | -4.383 |
brook | -4.358 |
ocide | -4.198 |
ndra | -4.121 |
Token | one |
Token ID | 530 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
detects | +1.984 |
netflix | +1.801 |
Vas | +1.798 |
Hamp | +1.774 |
imet | +1.764 |
Neg logit contributions | |
Conquest | -2.343 |
losers | -2.311 |
brook | -2.307 |
ocide | -2.212 |
ndra | -2.172 |
Token | is |
Token ID | 318 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
detects | +0.311 |
netflix | +0.291 |
Vas | +0.284 |
thought | +0.280 |
Hamp | +0.280 |
Neg logit contributions | |
Conquest | -0.299 |
losers | -0.296 |
brook | -0.293 |
ocide | -0.276 |
ndra | -0.272 |
Token | predominantly |
Token ID | 20736 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Conquest | +0.110 |
losers | +0.108 |
brook | +0.107 |
ocide | +0.101 |
ndra | +0.100 |
Neg logit contributions | |
detects | -0.098 |
netflix | -0.092 |
Vas | -0.089 |
thought | -0.088 |
Hamp | -0.088 |
Token | used |
Token ID | 973 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
detects | +0.447 |
netflix | +0.416 |
Vas | +0.410 |
Hamp | +0.403 |
thought | +0.402 |
Neg logit contributions | |
Conquest | -0.467 |
losers | -0.463 |
brook | -0.459 |
ocide | -0.435 |
ndra | -0.429 |
Token | / |
Token ID | 14 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Conquest | +0.326 |
losers | +0.322 |
brook | +0.317 |
ocide | +0.297 |
ndra | +0.293 |
Neg logit contributions | |
detects | -0.403 |
netflix | -0.383 |
Vas | -0.375 |
thought | -0.370 |
Hamp | -0.369 |
Token | Getty |
Token ID | 6633 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
detects | +1.110 |
netflix | +1.049 |
Vas | +1.023 |
thought | +1.002 |
Hamp | +1.001 |
Neg logit contributions | |
Conquest | -1.704 |
losers | -1.695 |
brook | -1.665 |
ocide | -1.595 |
ndra | -1.575 |
Token | Images |
Token ID | 5382 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Conquest | +0.221 |
losers | +0.219 |
brook | +0.217 |
ocide | +0.208 |
ndra | +0.206 |
Neg logit contributions | |
detects | -0.084 |
netflix | -0.076 |
Vas | -0.072 |
thought | -0.070 |
imet | -0.070 |
Token | ) |
Token ID | 8 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
detects | +0.109 |
netflix | +0.103 |
Vas | +0.099 |
thought | +0.098 |
Hamp | +0.097 |
Neg logit contributions | |
Conquest | -0.140 |
losers | -0.138 |
brook | -0.137 |
ocide | -0.130 |
ndra | -0.128 |
Token | Story |
Token ID | 8362 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
detects | +0.920 |
netflix | +0.874 |
Vas | +0.856 |
Hamp | +0.844 |
thought | +0.840 |
Neg logit contributions | |
Conquest | -0.839 |
losers | -0.828 |
brook | -0.817 |
ocide | -0.771 |
ndra | -0.760 |
Token | Highlights |
Token ID | 30776 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
detects | +0.943 |
netflix | +0.872 |
Vas | +0.856 |
thought | +0.846 |
Hamp | +0.844 |
Neg logit contributions | |
Conquest | -1.039 |
losers | -1.028 |
brook | -1.013 |
ocide | -0.971 |
ndra | -0.949 |
Token | The |
Token ID | 383 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
detects | +3.538 |
Hamp | +3.359 |
Vas | +3.334 |
netflix | +3.293 |
thought | +3.193 |
Neg logit contributions | |
Conquest | -3.836 |
losers | -3.820 |
brook | -3.754 |
ocide | -3.660 |
ndra | -3.505 |
Token | United |
Token ID | 1578 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
detects | +0.131 |
netflix | +0.123 |
Vas | +0.120 |
Hamp | +0.119 |
thought | +0.118 |
Neg logit contributions | |
Conquest | -0.148 |
losers | -0.146 |
brook | -0.145 |
ocide | -0.137 |
ndra | -0.135 |
Token | States |
Token ID | 1829 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
detects | +0.973 |
netflix | +0.903 |
Vas | +0.878 |
Hamp | +0.862 |
thought | +0.858 |
Neg logit contributions | |
Conquest | -1.467 |
losers | -1.453 |
brook | -1.437 |
ocide | -1.368 |
ndra | -1.351 |
Token | will |
Token ID | 481 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Conquest | +0.038 |
losers | +0.038 |
brook | +0.037 |
ocide | +0.035 |
ndra | +0.035 |
Neg logit contributions | |
detects | -0.037 |
netflix | -0.035 |
Vas | -0.034 |
Hamp | -0.033 |
thought | -0.033 |
Token | run |
Token ID | 1057 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
detects | +0.070 |
netflix | +0.065 |
Vas | +0.064 |
Hamp | +0.063 |
imet | +0.063 |
Neg logit contributions | |
Conquest | -0.077 |
brook | -0.075 |
losers | -0.075 |
ocide | -0.071 |
ndra | -0.070 |
Token | weekend |
Token ID | 5041 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
detects | +0.749 |
netflix | +0.716 |
Vas | +0.701 |
Hamp | +0.696 |
thought | +0.690 |
Neg logit contributions | |
Conquest | -0.626 |
losers | -0.619 |
brook | -0.613 |
ocide | -0.581 |
ndra | -0.574 |
Token | , |
Token ID | 11 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
detects | +0.367 |
netflix | +0.347 |
Vas | +0.337 |
Hamp | +0.333 |
thought | +0.332 |
Neg logit contributions | |
Conquest | -0.406 |
losers | -0.402 |
brook | -0.398 |
ocide | -0.377 |
ndra | -0.371 |
Token | Amazon |
Token ID | 6186 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Conquest | +0.621 |
losers | +0.615 |
brook | +0.607 |
ocide | +0.575 |
ndra | +0.568 |
Neg logit contributions | |
detects | -0.535 |
netflix | -0.506 |
Vas | -0.489 |
thought | -0.483 |
Hamp | -0.482 |
Token | quietly |
Token ID | 12703 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
Conquest | +0.224 |
losers | +0.222 |
brook | +0.220 |
ocide | +0.208 |
ndra | +0.205 |
Neg logit contributions | |
detects | -0.188 |
netflix | -0.177 |
Vas | -0.171 |
thought | -0.169 |
Hamp | -0.169 |
Token | rolled |
Token ID | 11686 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
detects | +0.340 |
netflix | +0.316 |
Vas | +0.306 |
thought | +0.302 |
Hamp | +0.301 |
Neg logit contributions | |
Conquest | -0.474 |
losers | -0.468 |
brook | -0.464 |
ocide | -0.443 |
ndra | -0.437 |
Token | out |
Token ID | 503 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
detects | +0.926 |
netflix | +0.879 |
Vas | +0.855 |
thought | +0.846 |
Hamp | +0.842 |
Neg logit contributions | |
Conquest | -0.895 |
losers | -0.889 |
brook | -0.876 |
ocide | -0.828 |
ndra | -0.816 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
detects | +3.118 |
netflix | +2.933 |
Vas | +2.889 |
thought | +2.831 |
Hamp | +2.807 |
Neg logit contributions | |
losers | -4.164 |
Conquest | -4.163 |
brook | -4.131 |
ocide | -3.946 |
ndra | -3.926 |
Token | series |
Token ID | 2168 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
detects | +1.203 |
netflix | +1.144 |
Vas | +1.112 |
thought | +1.098 |
Hamp | +1.095 |
Neg logit contributions | |
Conquest | -1.264 |
losers | -1.252 |
brook | -1.241 |
ocide | -1.173 |
ndra | -1.157 |
Token | of |
Token ID | 286 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
detects | +0.181 |
netflix | +0.171 |
Vas | +0.166 |
thought | +0.164 |
Hamp | +0.163 |
Neg logit contributions | |
Conquest | -0.213 |
losers | -0.211 |
brook | -0.208 |
ocide | -0.197 |
ndra | -0.195 |
Token | changes |
Token ID | 2458 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
detects | +0.145 |
netflix | +0.137 |
Vas | +0.132 |
thought | +0.130 |
imet | +0.130 |
Neg logit contributions | |
Conquest | -0.172 |
losers | -0.170 |
brook | -0.168 |
ocide | -0.159 |
ndra | -0.157 |
Token | to |
Token ID | 284 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
detects | +0.165 |
netflix | +0.157 |
Vas | +0.152 |
thought | +0.151 |
Hamp | +0.150 |
Neg logit contributions | |
Conquest | -0.162 |
losers | -0.160 |
brook | -0.158 |
ocide | -0.149 |
ndra | -0.147 |
Token | an |
Token ID | 281 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
detects | +0.538 |
netflix | +0.511 |
Vas | +0.497 |
Hamp | +0.489 |
thought | +0.488 |
Neg logit contributions | |
Conquest | -0.557 |
losers | -0.547 |
brook | -0.546 |
ocide | -0.517 |
ndra | -0.511 |
Token | enchantment |
Token ID | 43706 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
detects | +0.395 |
netflix | +0.373 |
Vas | +0.363 |
Hamp | +0.358 |
imet | +0.357 |
Neg logit contributions | |
Conquest | -0.409 |
losers | -0.402 |
brook | -0.400 |
ocide | -0.378 |
ndra | -0.373 |
Token | that |
Token ID | 326 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Conquest | +1.927 |
losers | +1.915 |
brook | +1.877 |
ocide | +1.758 |
ndra | +1.737 |
Neg logit contributions | |
detects | -1.853 |
netflix | -1.763 |
Vas | -1.706 |
imet | -1.696 |
Hamp | -1.692 |
Token | you |
Token ID | 345 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Conquest | +0.288 |
losers | +0.284 |
brook | +0.282 |
ocide | +0.267 |
ndra | +0.264 |
Neg logit contributions | |
detects | -0.231 |
netflix | -0.216 |
Vas | -0.209 |
Hamp | -0.206 |
thought | -0.206 |
Token | can |
Token ID | 460 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Conquest | +0.336 |
losers | +0.331 |
brook | +0.330 |
ocide | +0.313 |
ndra | +0.307 |
Neg logit contributions | |
detects | -0.299 |
netflix | -0.279 |
Vas | -0.274 |
thought | -0.269 |
Hamp | -0.268 |
Token | sacrifice |
Token ID | 11728 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
Conquest | +0.614 |
losers | +0.604 |
brook | +0.600 |
ocide | +0.565 |
ndra | +0.556 |
Neg logit contributions | |
detects | -0.627 |
netflix | -0.588 |
Vas | -0.578 |
thought | -0.567 |
Hamp | -0.566 |
Token | to |
Token ID | 284 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Conquest | +4.517 |
losers | +4.516 |
brook | +4.399 |
ocide | +4.074 |
ndra | +3.985 |
Neg logit contributions | |
detects | -5.288 |
netflix | -5.140 |
imet | -4.863 |
thought | -4.863 |
Vas | -4.858 |
Token | damage |
Token ID | 2465 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Conquest | +1.390 |
losers | +1.372 |
brook | +1.360 |
ocide | +1.283 |
ndra | +1.267 |
Neg logit contributions | |
detects | -1.355 |
netflix | -1.280 |
Vas | -1.248 |
Hamp | -1.230 |
thought | -1.228 |
Token | tapped |
Token ID | 22499 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
Conquest | +1.532 |
losers | +1.518 |
brook | +1.496 |
ocide | +1.413 |
ndra | +1.394 |
Neg logit contributions | |
detects | -1.368 |
netflix | -1.296 |
Vas | -1.250 |
thought | -1.238 |
imet | -1.238 |
Token | creatures |
Token ID | 8109 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
Conquest | +3.675 |
losers | +3.672 |
brook | +3.597 |
ocide | +3.372 |
ndra | +3.312 |
Neg logit contributions | |
detects | -3.620 |
netflix | -3.497 |
imet | -3.318 |
Vas | -3.314 |
thought | -3.304 |
Token | , |
Token ID | 11 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Conquest | +2.405 |
losers | +2.389 |
brook | +2.341 |
ocide | +2.195 |
ndra | +2.159 |
Neg logit contributions | |
detects | -2.645 |
netflix | -2.542 |
Vas | -2.446 |
imet | -2.429 |
thought | -2.427 |
Token | . |
Token ID | 13 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
detects | +1.743 |
netflix | +1.633 |
Vas | +1.629 |
imet | +1.597 |
thought | +1.593 |
Neg logit contributions | |
Conquest | -1.789 |
losers | -1.714 |
brook | -1.709 |
ocide | -1.626 |
ndra | -1.618 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
detects | +0.409 |
netflix | +0.387 |
Vas | +0.382 |
Hamp | +0.376 |
thought | +0.373 |
Neg logit contributions | |
Conquest | -0.423 |
losers | -0.421 |
brook | -0.415 |
ocide | -0.395 |
ndra | -0.388 |
Token |
|
Token ID | 198 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
detects | +0.212 |
netflix | +0.203 |
Vas | +0.199 |
thought | +0.198 |
Hamp | +0.196 |
Neg logit contributions | |
Conquest | -0.159 |
losers | -0.157 |
brook | -0.153 |
ocide | -0.144 |
ndra | -0.141 |
Token | 6 |
Token ID | 21 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
detects | +0.477 |
netflix | +0.452 |
Vas | +0.437 |
thought | +0.435 |
Hamp | +0.431 |
Neg logit contributions | |
Conquest | -0.551 |
losers | -0.544 |
brook | -0.536 |
ocide | -0.508 |
ndra | -0.503 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
detects | +0.549 |
netflix | +0.524 |
Vas | +0.513 |
thought | +0.508 |
Hamp | +0.505 |
Neg logit contributions | |
Conquest | -0.469 |
losers | -0.464 |
brook | -0.453 |
ocide | -0.428 |
ndra | -0.420 |
Token | Drain |
Token ID | 36024 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
detects | +0.838 |
netflix | +0.783 |
Vas | +0.777 |
Hamp | +0.761 |
thought | +0.751 |
Neg logit contributions | |
Conquest | -1.146 |
losers | -1.144 |
brook | -1.127 |
ocide | -1.080 |
ndra | -1.068 |
Token | on |
Token ID | 319 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
losers | +4.308 |
Conquest | +4.273 |
brook | +4.232 |
ocide | +3.863 |
ndra | +3.823 |
Neg logit contributions | |
detects | -4.478 |
netflix | -4.274 |
imet | -4.115 |
thought | -4.095 |
Hamp | -4.071 |
Token | a |
Token ID | 257 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Conquest | +0.019 |
losers | +0.019 |
brook | +0.019 |
ocide | +0.018 |
ndra | +0.018 |
Neg logit contributions | |
detects | -0.024 |
netflix | -0.022 |
Vas | -0.022 |
thought | -0.022 |
Hamp | -0.022 |
Token | paper |
Token ID | 3348 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Conquest | +0.122 |
losers | +0.121 |
brook | +0.120 |
ocide | +0.113 |
ndra | +0.111 |
Neg logit contributions | |
detects | -0.134 |
netflix | -0.127 |
Vas | -0.124 |
Hamp | -0.122 |
thought | -0.122 |
Token | towel |
Token ID | 24808 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Conquest | +0.963 |
losers | +0.952 |
brook | +0.939 |
ocide | +0.882 |
ndra | +0.870 |
Neg logit contributions | |
detects | -1.040 |
netflix | -0.989 |
Vas | -0.959 |
thought | -0.949 |
Hamp | -0.947 |
Token | - |
Token ID | 12 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
Conquest | +1.849 |
losers | +1.831 |
brook | +1.803 |
ocide | +1.692 |
ndra | +1.668 |
Neg logit contributions | |
detects | -1.882 |
netflix | -1.803 |
Vas | -1.717 |
thought | -1.713 |
imet | -1.712 |
Token | am |
Token ID | 716 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
detects | +0.264 |
netflix | +0.247 |
Vas | +0.238 |
thought | +0.236 |
Hamp | +0.234 |
Neg logit contributions | |
Conquest | -0.379 |
losers | -0.374 |
brook | -0.370 |
ocide | -0.353 |
ndra | -0.348 |
Token | not |
Token ID | 407 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
detects | +0.255 |
netflix | +0.240 |
Vas | +0.236 |
thought | +0.233 |
Hamp | +0.232 |
Neg logit contributions | |
Conquest | -0.249 |
losers | -0.246 |
brook | -0.244 |
ocide | -0.231 |
ndra | -0.228 |
Token | surprised |
Token ID | 6655 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
Conquest | +0.389 |
losers | +0.384 |
brook | +0.380 |
ocide | +0.358 |
ndra | +0.354 |
Neg logit contributions | |
detects | -0.383 |
netflix | -0.363 |
Vas | -0.353 |
thought | -0.349 |
Hamp | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Conquest | +3.439 |
losers | +3.426 |
brook | +3.327 |
ocide | +3.057 |
ndra | +3.057 |
Neg logit contributions | |
detects | -3.787 |
netflix | -3.651 |
imet | -3.501 |
thought | -3.438 |
ゼ | -3.433 |
Token | not |
Token ID | 407 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Conquest | +0.604 |
losers | +0.596 |
brook | +0.593 |
ocide | +0.564 |
ndra | +0.555 |
Neg logit contributions | |
detects | -0.564 |
netflix | -0.531 |
Vas | -0.521 |
Hamp | -0.516 |
thought | -0.512 |
Token | surprised |
Token ID | 6655 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
Conquest | +1.171 |
losers | +1.160 |
brook | +1.144 |
ocide | +1.077 |
ndra | +1.063 |
Neg logit contributions | |
detects | -1.136 |
netflix | -1.080 |
Vas | -1.044 |
imet | -1.032 |
thought | -1.032 |
Token | at |
Token ID | 379 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
losers | +3.694 |
Conquest | +3.685 |
brook | +3.619 |
ocide | +3.315 |
ndra | +3.294 |
Neg logit contributions | |
detects | -4.393 |
netflix | -4.257 |
imet | -4.060 |
Vas | -4.028 |
ゼ | -4.016 |
Token | all |
Token ID | 477 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Conquest | +1.064 |
losers | +1.052 |
brook | +1.040 |
ocide | +0.983 |
ndra | +0.970 |
Neg logit contributions | |
detects | -1.004 |
netflix | -0.950 |
Vas | -0.922 |
thought | -0.913 |
Hamp | -0.911 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Conquest | +1.771 |
losers | +1.760 |
brook | +1.728 |
ocide | +1.610 |
ndra | +1.588 |
Neg logit contributions | |
detects | -2.005 |
netflix | -1.927 |
Vas | -1.851 |
imet | -1.843 |
thought | -1.832 |
Token | It |
Token ID | 632 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Conquest | +0.874 |
losers | +0.869 |
brook | +0.857 |
ocide | +0.812 |
ndra | +0.802 |
Neg logit contributions | |
detects | -0.773 |
netflix | -0.731 |
Vas | -0.711 |
Hamp | -0.702 |
thought | -0.700 |
Token | is |
Token ID | 318 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Conquest | +0.241 |
losers | +0.238 |
brook | +0.235 |
ocide | +0.222 |
ndra | +0.218 |
Neg logit contributions | |
detects | -0.252 |
netflix | -0.238 |
Vas | -0.231 |
thought | -0.229 |
Hamp | -0.228 |
Token | Mess |
Token ID | 36479 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Conquest | +0.042 |
losers | +0.041 |
brook | +0.041 |
ocide | +0.038 |
ndra | +0.038 |
Neg logit contributions | |
detects | -0.033 |
netflix | -0.032 |
Vas | -0.031 |
thought | -0.030 |
Hamp | -0.030 |
Token | aging |
Token ID | 3039 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
detects | +0.171 |
netflix | +0.160 |
Vas | +0.155 |
thought | +0.153 |
imet | +0.153 |
Neg logit contributions | |
Conquest | -0.231 |
losers | -0.229 |
brook | -0.226 |
ocide | -0.215 |
ndra | -0.213 |
Token | — |
Token ID | 851 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Conquest | +0.376 |
losers | +0.372 |
brook | +0.368 |
ocide | +0.347 |
ndra | +0.343 |
Neg logit contributions | |
detects | -0.348 |
netflix | -0.329 |
Vas | -0.319 |
thought | -0.316 |
Hamp | -0.315 |
Token | FA |
Token ID | 9677 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Conquest | +1.089 |
losers | +1.077 |
brook | +1.062 |
ocide | +1.003 |
ndra | +0.990 |
Neg logit contributions | |
detects | -1.018 |
netflix | -0.966 |
Vas | -0.933 |
thought | -0.923 |
imet | -0.922 |
Token | IL |
Token ID | 4146 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Conquest | +0.621 |
losers | +0.608 |
brook | +0.593 |
ocide | +0.529 |
ndra | +0.515 |
Neg logit contributions | |
detects | -1.669 |
netflix | -1.611 |
Vas | -1.577 |
thought | -1.565 |
Hamp | -1.563 |
Token | ED |
Token ID | 1961 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
Conquest | +1.378 |
losers | +1.360 |
brook | +1.342 |
ocide | +1.253 |
ndra | +1.235 |
Neg logit contributions | |
detects | -1.706 |
netflix | -1.630 |
Vas | -1.581 |
thought | -1.565 |
imet | -1.565 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
Conquest | +2.985 |
losers | +2.933 |
brook | +2.859 |
ocide | +2.633 |
ndra | +2.504 |
Neg logit contributions | |
detects | -5.097 |
netflix | -4.924 |
thought | -4.734 |
imet | -4.720 |
Hamp | -4.698 |
Token |
|
Token ID | 198 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Conquest | +2.117 |
brook | +2.101 |
losers | +2.067 |
ocide | +1.849 |
ndra | +1.845 |
Neg logit contributions | |
detects | -3.840 |
netflix | -3.668 |
imet | -3.561 |
Hamp | -3.524 |
Vas | -3.514 |
Token | Israel |
Token ID | 14040 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Conquest | +1.818 |
losers | +1.799 |
brook | +1.786 |
ocide | +1.692 |
ndra | +1.669 |
Neg logit contributions | |
detects | -1.512 |
netflix | -1.418 |
Vas | -1.369 |
Hamp | -1.351 |
imet | -1.349 |
Token | � |
Token ID | 447 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Conquest | +0.380 |
losers | +0.376 |
brook | +0.371 |
ocide | +0.350 |
ndra | +0.346 |
Neg logit contributions | |
detects | -0.352 |
netflix | -0.333 |
Vas | -0.323 |
thought | -0.319 |
imet | -0.318 |
Token | � |
Token ID | 247 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
detects | +0.938 |
netflix | +0.900 |
Vas | +0.884 |
thought | +0.878 |
Hamp | +0.878 |
Neg logit contributions | |
Conquest | -0.536 |
losers | -0.526 |
brook | -0.516 |
ocide | -0.473 |
ndra | -0.463 |
Token | } |
Token ID | 92 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
detects | +0.506 |
netflix | +0.483 |
Vas | +0.472 |
thought | +0.469 |
imet | +0.465 |
Neg logit contributions | |
Conquest | -0.375 |
losers | -0.372 |
brook | -0.362 |
ocide | -0.343 |
ndra | -0.337 |
Token | -> |
Token ID | 4613 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Conquest | +0.366 |
losers | +0.363 |
brook | +0.358 |
ocide | +0.337 |
ndra | +0.333 |
Neg logit contributions | |
detects | -0.416 |
netflix | -0.394 |
Vas | -0.384 |
Hamp | -0.379 |
thought | -0.379 |
Token | " |
Token ID | 366 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Conquest | +0.257 |
losers | +0.254 |
brook | +0.251 |
ocide | +0.237 |
ndra | +0.234 |
Neg logit contributions | |
detects | -0.276 |
netflix | -0.261 |
Vas | -0.255 |
thought | -0.251 |
Hamp | -0.251 |
Token | E |
Token ID | 36 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Conquest | +1.522 |
losers | +1.506 |
brook | +1.488 |
ocide | +1.405 |
ndra | +1.387 |
Neg logit contributions | |
detects | -1.401 |
netflix | -1.328 |
Vas | -1.284 |
thought | -1.270 |
Hamp | -1.267 |
Token | ", |
Token ID | 1600 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Conquest | +1.459 |
losers | +1.440 |
brook | +1.425 |
ocide | +1.336 |
ndra | +1.322 |
Neg logit contributions | |
detects | -1.576 |
netflix | -1.503 |
Vas | -1.455 |
Hamp | -1.440 |
thought | -1.439 |
Token | { |
Token ID | 1391 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
Conquest | +1.628 |
losers | +1.609 |
brook | +1.587 |
ocide | +1.488 |
ndra | +1.468 |
Neg logit contributions | |
detects | -1.801 |
netflix | -1.716 |
Vas | -1.665 |
thought | -1.650 |
imet | -1.647 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Conquest | +4.150 |
losers | +4.075 |
brook | +4.069 |
ocide | +3.828 |
ndra | +3.740 |
Neg logit contributions | |
detects | -3.915 |
netflix | -3.684 |
Hamp | -3.574 |
Vas | -3.565 |
imet | -3.548 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Conquest | +1.058 |
losers | +1.047 |
brook | +1.034 |
ocide | +0.976 |
ndra | +0.963 |
Neg logit contributions | |
detects | -0.991 |
netflix | -0.939 |
Vas | -0.909 |
thought | -0.899 |
Hamp | -0.897 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Conquest | +0.120 |
losers | +0.120 |
brook | +0.119 |
ocide | +0.112 |
ndra | +0.111 |
Neg logit contributions | |
detects | -0.123 |
netflix | -0.116 |
Vas | -0.115 |
Hamp | -0.113 |
thought | -0.113 |
Token | } |
Token ID | 92 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Conquest | +1.072 |
losers | +1.057 |
brook | +1.033 |
ocide | +0.951 |
ndra | +0.930 |
Neg logit contributions | |
detects | -1.947 |
netflix | -1.871 |
Vas | -1.828 |
thought | -1.815 |
Hamp | -1.808 |
Token | -> |
Token ID | 4613 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Conquest | +0.066 |
losers | +0.066 |
brook | +0.065 |
ocide | +0.061 |
ndra | +0.060 |
Neg logit contributions | |
detects | -0.080 |
netflix | -0.076 |
Vas | -0.074 |
Hamp | -0.073 |
thought | -0.073 |
Token | s |
Token ID | 82 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
detects | +0.173 |
netflix | +0.159 |
Vas | +0.156 |
thought | +0.154 |
Hamp | +0.153 |
Neg logit contributions | |
Conquest | -0.255 |
losers | -0.252 |
brook | -0.250 |
ocide | -0.239 |
ndra | -0.236 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Conquest | +1.307 |
losers | +1.296 |
brook | +1.276 |
ocide | +1.208 |
ndra | +1.193 |
Neg logit contributions | |
detects | -1.139 |
netflix | -1.079 |
Vas | -1.040 |
Hamp | -1.029 |
imet | -1.027 |
Token | K |
Token ID | 509 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
Conquest | +1.253 |
losers | +1.244 |
brook | +1.217 |
ocide | +1.147 |
ndra | +1.131 |
Neg logit contributions | |
detects | -1.303 |
netflix | -1.247 |
Vas | -1.196 |
imet | -1.194 |
thought | -1.191 |
Token | b |
Token ID | 65 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
detects | +0.368 |
netflix | +0.346 |
Vas | +0.337 |
thought | +0.336 |
imet | +0.332 |
Neg logit contributions | |
Conquest | -0.431 |
losers | -0.424 |
brook | -0.417 |
ocide | -0.396 |
ndra | -0.391 |
Token | 7 |
Token ID | 22 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Conquest | +0.416 |
losers | +0.412 |
brook | +0.408 |
ocide | +0.388 |
ndra | +0.384 |
Neg logit contributions | |
detects | -0.310 |
netflix | -0.289 |
Vas | -0.281 |
thought | -0.279 |
imet | -0.277 |
Token | { |
Token ID | 1391 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
Conquest | +1.452 |
losers | +1.441 |
brook | +1.412 |
ocide | +1.334 |
ndra | +1.309 |
Neg logit contributions | |
detects | -1.387 |
netflix | -1.328 |
Vas | -1.273 |
imet | -1.267 |
Hamp | -1.264 |
Token | ( |
Token ID | 7 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
Conquest | +3.860 |
losers | +3.811 |
brook | +3.746 |
ocide | +3.545 |
ndra | +3.405 |
Neg logit contributions | |
detects | -3.999 |
netflix | -3.772 |
Vas | -3.679 |
Hamp | -3.636 |
imet | -3.626 |
Token | 3 |
Token ID | 18 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Conquest | +3.165 |
losers | +3.131 |
brook | +3.113 |
ocide | +2.942 |
ndra | +2.901 |
Neg logit contributions | |
detects | -2.597 |
netflix | -2.431 |
Vas | -2.350 |
Hamp | -2.323 |
imet | -2.311 |
Token | s |
Token ID | 82 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Conquest | +1.804 |
losers | +1.793 |
brook | +1.771 |
ocide | +1.683 |
ndra | +1.665 |
Neg logit contributions | |
detects | -1.223 |
netflix | -1.151 |
Vas | -1.101 |
thought | -1.088 |
Hamp | -1.086 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
Conquest | +1.521 |
losers | +1.510 |
brook | +1.484 |
ocide | +1.405 |
ndra | +1.386 |
Neg logit contributions | |
detects | -1.337 |
netflix | -1.267 |
Vas | -1.222 |
Hamp | -1.211 |
imet | -1.207 |
Token | 52 |
Token ID | 6740 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Conquest | +1.959 |
losers | +1.949 |
brook | +1.894 |
ocide | +1.794 |
ndra | +1.769 |
Neg logit contributions | |
detects | -1.845 |
netflix | -1.770 |
imet | -1.690 |
thought | -1.684 |
Vas | -1.683 |
Token | [ |
Token ID | 685 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Conquest | +0.280 |
losers | +0.275 |
brook | +0.273 |
ocide | +0.256 |
ndra | +0.252 |
Neg logit contributions | |
detects | -0.339 |
netflix | -0.322 |
Vas | -0.314 |
thought | -0.311 |
Hamp | -0.310 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Conquest | +0.400 |
losers | +0.396 |
brook | +0.390 |
ocide | +0.370 |
ndra | +0.365 |
Neg logit contributions | |
detects | -0.349 |
netflix | -0.331 |
Vas | -0.319 |
thought | -0.317 |
Hamp | -0.315 |
Token | : |
Token ID | 25 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Conquest | +1.220 |
losers | +1.207 |
brook | +1.206 |
ocide | +1.137 |
ndra | +1.131 |
Neg logit contributions | |
detects | -0.774 |
netflix | -0.722 |
imet | -0.683 |
Vas | -0.682 |
Hamp | -0.677 |
Token | 47 |
Token ID | 2857 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Conquest | +1.194 |
losers | +1.184 |
brook | +1.168 |
ocide | +1.099 |
ndra | +1.086 |
Neg logit contributions | |
detects | -1.091 |
netflix | -1.037 |
Vas | -1.001 |
Hamp | -0.993 |
thought | -0.989 |
Token | ] |
Token ID | 60 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Conquest | +0.787 |
losers | +0.777 |
brook | +0.773 |
ocide | +0.722 |
ndra | +0.714 |
Neg logit contributions | |
detects | -0.832 |
netflix | -0.789 |
Vas | -0.761 |
imet | -0.757 |
Hamp | -0.754 |
Token | <@ |
Token ID | 32406 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
Conquest | +0.217 |
losers | +0.215 |
brook | +0.212 |
ocide | +0.199 |
ndra | +0.197 |
Neg logit contributions | |
detects | -0.227 |
netflix | -0.216 |
Vas | -0.209 |
thought | -0.207 |
Hamp | -0.207 |
Token | t |
Token ID | 83 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
brook | +4.166 |
Conquest | +4.141 |
losers | +4.123 |
ocide | +3.854 |
ndra | +3.852 |
Neg logit contributions | |
detects | -3.598 |
netflix | -3.355 |
Vas | -3.260 |
Hamp | -3.231 |
imet | -3.192 |
Token | ay |
Token ID | 323 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Conquest | +0.698 |
losers | +0.693 |
brook | +0.685 |
ocide | +0.655 |
ndra | +0.649 |
Neg logit contributions | |
detects | -0.355 |
netflix | -0.329 |
Vas | -0.313 |
thought | -0.308 |
imet | -0.307 |
Token | l |
Token ID | 75 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
detects | +1.303 |
netflix | +1.248 |
thought | +1.209 |
imet | +1.204 |
Vas | +1.199 |
Neg logit contributions | |
Conquest | -1.352 |
losers | -1.338 |
brook | -1.284 |
ocide | -1.231 |
ndra | -1.202 |
Token | ort |
Token ID | 419 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
detects | +0.801 |
netflix | +0.767 |
thought | +0.744 |
Vas | +0.744 |
imet | +0.742 |
Neg logit contributions | |
Conquest | -0.563 |
losers | -0.558 |
brook | -0.540 |
ocide | -0.503 |
ndra | -0.494 |
Token | ot |
Token ID | 313 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
detects | +0.726 |
netflix | +0.691 |
thought | +0.663 |
Vas | +0.663 |
imet | +0.660 |
Neg logit contributions | |
Conquest | -0.862 |
losers | -0.854 |
brook | -0.835 |
ocide | -0.794 |
ndra | -0.786 |
Token | as |
Token ID | 355 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Conquest | +1.488 |
losers | +1.472 |
brook | +1.460 |
ocide | +1.350 |
ndra | +1.343 |
Neg logit contributions | |
detects | -1.639 |
netflix | -1.569 |
Vas | -1.501 |
Hamp | -1.501 |
imet | -1.501 |
Token | too |
Token ID | 1165 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
Conquest | +0.820 |
losers | +0.805 |
brook | +0.791 |
ocide | +0.731 |
ndra | +0.714 |
Neg logit contributions | |
detects | -1.395 |
netflix | -1.339 |
Vas | -1.306 |
thought | -1.297 |
Hamp | -1.293 |
Token | big |
Token ID | 1263 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Conquest | +0.393 |
losers | +0.385 |
brook | +0.382 |
ocide | +0.364 |
ndra | +0.358 |
Neg logit contributions | |
detects | -0.295 |
netflix | -0.277 |
Vas | -0.269 |
thought | -0.265 |
Hamp | -0.263 |
Token | of |
Token ID | 286 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Conquest | +1.287 |
losers | +1.277 |
brook | +1.262 |
ocide | +1.183 |
ndra | +1.174 |
Neg logit contributions | |
detects | -1.213 |
netflix | -1.151 |
Vas | -1.103 |
imet | -1.101 |
Hamp | -1.095 |
Token | a |
Token ID | 257 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
losers | +2.420 |
Conquest | +2.396 |
brook | +2.361 |
ndra | +2.222 |
ocide | +2.217 |
Neg logit contributions | |
detects | -2.130 |
netflix | -2.028 |
Vas | -1.920 |
imet | -1.917 |
ゼ | -1.913 |
Token | concern |
Token ID | 2328 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
Conquest | +2.817 |
losers | +2.796 |
brook | +2.756 |
ocide | +2.594 |
ndra | +2.559 |
Neg logit contributions | |
detects | -2.887 |
netflix | -2.765 |
Vas | -2.656 |
Hamp | -2.623 |
thought | -2.620 |
Token | though |
Token ID | 996 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
Conquest | +2.460 |
losers | +2.388 |
brook | +2.371 |
ndra | +2.073 |
ocide | +2.059 |
Neg logit contributions | |
detects | -5.318 |
netflix | -5.061 |
imet | -4.946 |
Vas | -4.930 |
Hamp | -4.917 |
Token | since |
Token ID | 1201 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Conquest | +3.236 |
losers | +3.151 |
brook | +3.105 |
ndra | +2.937 |
ocide | +2.933 |
Neg logit contributions | |
detects | -3.119 |
netflix | -2.925 |
imet | -2.854 |
Vas | -2.796 |
Hamp | -2.778 |
Token | most |
Token ID | 749 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Conquest | +1.134 |
losers | +1.125 |
brook | +1.099 |
ocide | +1.030 |
ndra | +1.020 |
Neg logit contributions | |
detects | -1.242 |
netflix | -1.191 |
imet | -1.147 |
Vas | -1.130 |
thought | -1.127 |
Token | of |
Token ID | 286 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Conquest | +0.920 |
losers | +0.910 |
brook | +0.900 |
ocide | +0.845 |
ndra | +0.838 |
Neg logit contributions | |
detects | -0.851 |
netflix | -0.808 |
Vas | -0.773 |
imet | -0.773 |
Hamp | -0.768 |
Token | the |
Token ID | 262 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Conquest | +0.237 |
losers | +0.234 |
brook | +0.231 |
ocide | +0.218 |
ndra | +0.216 |
Neg logit contributions | |
detects | -0.218 |
netflix | -0.207 |
Vas | -0.200 |
thought | -0.198 |
imet | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
Conquest | +0.710 |
losers | +0.703 |
brook | +0.694 |
ocide | +0.653 |
ndra | +0.646 |
Neg logit contributions | |
detects | -0.733 |
netflix | -0.696 |
Vas | -0.677 |
thought | -0.669 |
Hamp | -0.666 |
Token | and |
Token ID | 290 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
detects | +0.310 |
netflix | +0.291 |
Vas | +0.287 |
thought | +0.282 |
Hamp | +0.280 |
Neg logit contributions | |
Conquest | -0.292 |
brook | -0.288 |
losers | -0.287 |
ocide | -0.271 |
ndra | -0.268 |
Token | both |
Token ID | 1111 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Conquest | +0.273 |
losers | +0.270 |
brook | +0.269 |
ocide | +0.256 |
ndra | +0.253 |
Neg logit contributions | |
detects | -0.239 |
netflix | -0.221 |
Vas | -0.218 |
thought | -0.213 |
Hamp | -0.213 |
Token | of |
Token ID | 286 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
detects | +0.085 |
netflix | +0.079 |
Vas | +0.078 |
Hamp | +0.076 |
thought | +0.076 |
Neg logit contributions | |
Conquest | -0.105 |
losers | -0.104 |
brook | -0.103 |
ocide | -0.098 |
ndra | -0.097 |
Token | them |
Token ID | 606 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
Conquest | +1.174 |
losers | +1.162 |
brook | +1.149 |
ocide | +1.088 |
ndra | +1.074 |
Neg logit contributions | |
detects | -1.010 |
netflix | -0.954 |
Vas | -0.923 |
thought | -0.912 |
Hamp | -0.910 |
Token | fall |
Token ID | 2121 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
Conquest | +1.887 |
losers | +1.873 |
brook | +1.839 |
ocide | +1.732 |
ndra | +1.707 |
Neg logit contributions | |
detects | -1.933 |
netflix | -1.849 |
Vas | -1.780 |
thought | -1.769 |
imet | -1.766 |
Token | into |
Token ID | 656 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
losers | +3.407 |
Conquest | +3.360 |
brook | +3.280 |
ocide | +3.072 |
ndra | +2.988 |
Neg logit contributions | |
detects | -4.006 |
netflix | -3.863 |
Vas | -3.667 |
imet | -3.666 |
Hamp | -3.645 |
Token | the |
Token ID | 262 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
Conquest | +1.063 |
losers | +1.053 |
brook | +1.035 |
ocide | +0.980 |
ndra | +0.963 |
Neg logit contributions | |
detects | -0.949 |
netflix | -0.900 |
Vas | -0.858 |
imet | -0.855 |
thought | -0.852 |
Token | abyss |
Token ID | 37678 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Conquest | +0.496 |
losers | +0.490 |
brook | +0.485 |
ocide | +0.460 |
ndra | +0.454 |
Neg logit contributions | |
detects | -0.500 |
netflix | -0.473 |
Vas | -0.466 |
Hamp | -0.457 |
thought | -0.457 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Conquest | +0.215 |
losers | +0.213 |
brook | +0.210 |
ocide | +0.197 |
ndra | +0.196 |
Neg logit contributions | |
detects | -0.222 |
netflix | -0.211 |
Vas | -0.205 |
thought | -0.203 |
imet | -0.202 |
Token | The |
Token ID | 383 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Conquest | +0.806 |
losers | +0.804 |
brook | +0.792 |
ocide | +0.752 |
ndra | +0.741 |
Neg logit contributions | |
detects | -0.751 |
netflix | -0.710 |
Vas | -0.699 |
Hamp | -0.685 |
thought | -0.684 |
Token | IM |
Token ID | 3955 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
Conquest | +1.067 |
losers | +1.048 |
brook | +1.034 |
ocide | +0.950 |
ndra | +0.925 |
Neg logit contributions | |
detects | -1.951 |
netflix | -1.877 |
Vas | -1.825 |
thought | -1.812 |
imet | -1.811 |
Token | O |
Token ID | 46 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Conquest | +2.671 |
losers | +2.630 |
brook | +2.619 |
ocide | +2.470 |
ndra | +2.424 |
Neg logit contributions | |
detects | -2.444 |
netflix | -2.316 |
imet | -2.222 |
Vas | -2.215 |
Hamp | -2.205 |
Token | T |
Token ID | 309 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
detects | +0.273 |
netflix | +0.259 |
Vas | +0.253 |
Hamp | +0.249 |
thought | +0.249 |
Neg logit contributions | |
Conquest | -0.229 |
losers | -0.227 |
brook | -0.224 |
ocide | -0.210 |
ndra | -0.207 |
Token | OC |
Token ID | 4503 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Conquest | +0.368 |
losers | +0.364 |
brook | +0.357 |
ocide | +0.338 |
ndra | +0.337 |
Neg logit contributions | |
detects | -0.287 |
netflix | -0.272 |
Vas | -0.263 |
thought | -0.258 |
imet | -0.257 |
Token | IN |
Token ID | 3268 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Conquest | +1.024 |
losers | +1.011 |
brook | +0.997 |
ocide | +0.936 |
ndra | +0.922 |
Neg logit contributions | |
detects | -1.111 |
netflix | -1.061 |
Vas | -1.026 |
thought | -1.018 |
imet | -1.018 |
Token | IT |
Token ID | 2043 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
Conquest | +1.345 |
losers | +1.329 |
brook | +1.311 |
ocide | +1.233 |
ndra | +1.216 |
Neg logit contributions | |
detects | -1.411 |
netflix | -1.343 |
Vas | -1.300 |
thought | -1.287 |
imet | -1.286 |
Token | I |
Token ID | 40 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Conquest | +3.818 |
losers | +3.762 |
brook | +3.705 |
ocide | +3.528 |
ndra | +3.394 |
Neg logit contributions | |
detects | -3.469 |
netflix | -3.396 |
thought | -3.240 |
Vas | -3.207 |
Hamp | -3.206 |
Token | ATES |
Token ID | 29462 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Conquest | +1.141 |
losers | +1.122 |
brook | +1.105 |
ocide | +1.026 |
ndra | +0.998 |
Neg logit contributions | |
detects | -1.739 |
netflix | -1.676 |
Vas | -1.623 |
thought | -1.616 |
imet | -1.615 |
Token | D |
Token ID | 360 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
Conquest | +0.102 |
losers | +0.101 |
brook | +0.099 |
ocide | +0.094 |
ndra | +0.093 |
Neg logit contributions | |
detects | -0.111 |
netflix | -0.105 |
Vas | -0.103 |
Hamp | -0.101 |
thought | -0.101 |
Token | UST |
Token ID | 7759 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
Conquest | +0.611 |
losers | +0.604 |
brook | +0.595 |
ocide | +0.561 |
ndra | +0.554 |
Neg logit contributions | |
detects | -0.629 |
netflix | -0.597 |
Vas | -0.580 |
thought | -0.573 |
Hamp | -0.572 |
Token | W |
Token ID | 54 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Conquest | +0.631 |
losers | +0.624 |
brook | +0.614 |
ocide | +0.576 |
ndra | +0.569 |
Neg logit contributions | |
detects | -0.766 |
netflix | -0.728 |
Vas | -0.710 |
thought | -0.703 |
Hamp | -0.701 |
Token | deep |
Token ID | 2769 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
detects | +1.075 |
Vas | +0.945 |
netflix | +0.943 |
thought | +0.910 |
imet | +0.869 |
Neg logit contributions | |
Conquest | -2.967 |
losers | -2.881 |
brook | -2.867 |
ocide | -2.824 |
ndra | -2.764 |
Token | fried |
Token ID | 23018 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
detects | +0.878 |
netflix | +0.812 |
Vas | +0.797 |
thought | +0.795 |
Hamp | +0.775 |
Neg logit contributions | |
Conquest | -1.215 |
losers | -1.176 |
brook | -1.175 |
ocide | -1.133 |
ndra | -1.109 |
Token | . |
Token ID | 13 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
detects | +1.551 |
netflix | +1.486 |
Vas | +1.461 |
thought | +1.438 |
Hamp | +1.426 |
Neg logit contributions | |
Conquest | -1.427 |
losers | -1.401 |
brook | -1.375 |
ocide | -1.308 |
ndra | -1.279 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Conquest | +0.447 |
losers | +0.442 |
brook | +0.436 |
ocide | +0.405 |
ndra | +0.395 |
Neg logit contributions | |
detects | -0.614 |
netflix | -0.586 |
Vas | -0.570 |
imet | -0.565 |
thought | -0.563 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
detects | +0.999 |
netflix | +0.952 |
Vas | +0.935 |
thought | +0.927 |
Hamp | +0.919 |
Neg logit contributions | |
Conquest | -0.881 |
losers | -0.870 |
brook | -0.847 |
ocide | -0.806 |
ndra | -0.789 |
Token | Drain |
Token ID | 36024 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
detects | +1.704 |
netflix | +1.600 |
Vas | +1.589 |
Hamp | +1.554 |
thought | +1.533 |
Neg logit contributions | |
Conquest | -2.000 |
losers | -1.993 |
brook | -1.968 |
ocide | -1.859 |
ndra | -1.827 |
Token | on |
Token ID | 319 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Conquest | +3.076 |
brook | +3.056 |
losers | +3.039 |
ndra | +2.748 |
ocide | +2.744 |
Neg logit contributions | |
detects | -4.212 |
netflix | -4.000 |
imet | -3.911 |
Hamp | -3.871 |
thought | -3.850 |
Token | a |
Token ID | 257 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
detects | +0.220 |
netflix | +0.206 |
Vas | +0.199 |
thought | +0.196 |
Hamp | +0.196 |
Neg logit contributions | |
Conquest | -0.306 |
losers | -0.303 |
brook | -0.300 |
ocide | -0.285 |
ndra | -0.282 |
Token | paper |
Token ID | 3348 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
detects | +0.580 |
netflix | +0.551 |
Vas | +0.545 |
thought | +0.536 |
Hamp | +0.534 |
Neg logit contributions | |
Conquest | -0.465 |
losers | -0.455 |
brook | -0.449 |
ocide | -0.422 |
ndra | -0.411 |
Token | towel |
Token ID | 24808 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
detects | +0.249 |
netflix | +0.235 |
Vas | +0.231 |
thought | +0.227 |
imet | +0.226 |
Neg logit contributions | |
Conquest | -0.264 |
losers | -0.257 |
brook | -0.253 |
ocide | -0.241 |
ndra | -0.236 |
Token | - |
Token ID | 12 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Conquest | +0.306 |
losers | +0.304 |
brook | +0.300 |
ocide | +0.281 |
ndra | +0.279 |
Neg logit contributions | |
detects | -0.293 |
netflix | -0.279 |
Vas | -0.269 |
Hamp | -0.266 |
imet | -0.265 |
Token | {{ |
Token ID | 22935 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
Conquest | +1.584 |
losers | +1.567 |
brook | +1.542 |
ocide | +1.444 |
ndra | +1.424 |
Neg logit contributions | |
detects | -1.826 |
netflix | -1.742 |
Vas | -1.689 |
thought | -1.677 |
imet | -1.674 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Conquest | +2.928 |
losers | +2.901 |
brook | +2.885 |
ocide | +2.706 |
ndra | +2.667 |
Neg logit contributions | |
detects | -2.691 |
netflix | -2.532 |
Vas | -2.460 |
Hamp | -2.440 |
imet | -2.434 |
Token | , |
Token ID | 11 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
Conquest | +1.353 |
losers | +1.340 |
brook | +1.323 |
ocide | +1.247 |
ndra | +1.233 |
Neg logit contributions | |
detects | -1.280 |
netflix | -1.214 |
Vas | -1.174 |
thought | -1.162 |
Hamp | -1.159 |
Token | 6 |
Token ID | 718 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Conquest | +0.562 |
losers | +0.557 |
brook | +0.550 |
ocide | +0.518 |
ndra | +0.512 |
Neg logit contributions | |
detects | -0.615 |
netflix | -0.586 |
Vas | -0.570 |
thought | -0.563 |
Hamp | -0.561 |
Token | }, |
Token ID | 5512 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Conquest | +0.248 |
losers | +0.243 |
brook | +0.237 |
ocide | +0.210 |
ndra | +0.205 |
Neg logit contributions | |
detects | -0.684 |
netflix | -0.660 |
Vas | -0.646 |
thought | -0.642 |
Hamp | -0.641 |
Token | {{ |
Token ID | 22935 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
Conquest | +1.046 |
losers | +1.034 |
brook | +1.018 |
ocide | +0.951 |
ndra | +0.936 |
Neg logit contributions | |
detects | -1.282 |
netflix | -1.222 |
Vas | -1.187 |
thought | -1.180 |
imet | -1.179 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Conquest | +3.804 |
losers | +3.761 |
brook | +3.757 |
ocide | +3.545 |
ndra | +3.464 |
Neg logit contributions | |
detects | -3.502 |
netflix | -3.251 |
Hamp | -3.185 |
Vas | -3.164 |
imet | -3.160 |
Token | , |
Token ID | 11 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
Conquest | +1.010 |
losers | +0.999 |
brook | +0.989 |
ocide | +0.930 |
ndra | +0.920 |
Neg logit contributions | |
detects | -0.962 |
netflix | -0.912 |
Vas | -0.881 |
thought | -0.871 |
imet | -0.871 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Conquest | +0.427 |
losers | +0.423 |
brook | +0.418 |
ocide | +0.393 |
ndra | +0.389 |
Neg logit contributions | |
detects | -0.484 |
netflix | -0.461 |
Vas | -0.450 |
thought | -0.443 |
Hamp | -0.442 |
Token | }, |
Token ID | 5512 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Conquest | +0.076 |
losers | +0.075 |
brook | +0.073 |
ocide | +0.065 |
ndra | +0.063 |
Neg logit contributions | |
detects | -0.209 |
netflix | -0.202 |
Vas | -0.197 |
thought | -0.196 |
Hamp | -0.196 |
Token | { |
Token ID | 1391 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Conquest | +1.266 |
losers | +1.253 |
brook | +1.233 |
ocide | +1.153 |
ndra | +1.136 |
Neg logit contributions | |
detects | -1.461 |
netflix | -1.390 |
Vas | -1.349 |
thought | -1.345 |
imet | -1.343 |
Token | you |
Token ID | 345 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Conquest | +0.288 |
losers | +0.284 |
brook | +0.282 |
ocide | +0.267 |
ndra | +0.264 |
Neg logit contributions | |
detects | -0.231 |
netflix | -0.216 |
Vas | -0.209 |
Hamp | -0.206 |
thought | -0.206 |
Token | can |
Token ID | 460 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Conquest | +0.336 |
losers | +0.331 |
brook | +0.330 |
ocide | +0.313 |
ndra | +0.307 |
Neg logit contributions | |
detects | -0.299 |
netflix | -0.279 |
Vas | -0.274 |
thought | -0.269 |
Hamp | -0.268 |
Token | sacrifice |
Token ID | 11728 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
Conquest | +0.614 |
losers | +0.604 |
brook | +0.600 |
ocide | +0.565 |
ndra | +0.556 |
Neg logit contributions | |
detects | -0.627 |
netflix | -0.588 |
Vas | -0.578 |
thought | -0.567 |
Hamp | -0.566 |
Token | to |
Token ID | 284 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Conquest | +4.517 |
losers | +4.516 |
brook | +4.399 |
ocide | +4.074 |
ndra | +3.985 |
Neg logit contributions | |
detects | -5.288 |
netflix | -5.140 |
imet | -4.863 |
thought | -4.863 |
Vas | -4.858 |
Token | damage |
Token ID | 2465 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Conquest | +1.390 |
losers | +1.372 |
brook | +1.360 |
ocide | +1.283 |
ndra | +1.267 |
Neg logit contributions | |
detects | -1.355 |
netflix | -1.280 |
Vas | -1.248 |
Hamp | -1.230 |
thought | -1.228 |
Token | tapped |
Token ID | 22499 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
Conquest | +1.532 |
losers | +1.518 |
brook | +1.496 |
ocide | +1.413 |
ndra | +1.394 |
Neg logit contributions | |
detects | -1.368 |
netflix | -1.296 |
Vas | -1.250 |
thought | -1.238 |
imet | -1.238 |
Token | creatures |
Token ID | 8109 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
Conquest | +3.675 |
losers | +3.672 |
brook | +3.597 |
ocide | +3.372 |
ndra | +3.312 |
Neg logit contributions | |
detects | -3.620 |
netflix | -3.497 |
imet | -3.318 |
Vas | -3.314 |
thought | -3.304 |
Token | , |
Token ID | 11 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Conquest | +2.405 |
losers | +2.389 |
brook | +2.341 |
ocide | +2.195 |
ndra | +2.159 |
Neg logit contributions | |
detects | -2.645 |
netflix | -2.542 |
Vas | -2.446 |
imet | -2.429 |
thought | -2.427 |
Token | and |
Token ID | 290 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
Conquest | +0.241 |
losers | +0.238 |
brook | +0.237 |
ocide | +0.223 |
ndra | +0.221 |
Neg logit contributions | |
detects | -0.247 |
netflix | -0.232 |
Vas | -0.228 |
Hamp | -0.224 |
thought | -0.224 |
Token | Hot |
Token ID | 6964 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Conquest | +0.514 |
losers | +0.509 |
brook | +0.504 |
ocide | +0.477 |
ndra | +0.471 |
Neg logit contributions | |
detects | -0.483 |
netflix | -0.457 |
Vas | -0.444 |
Hamp | -0.437 |
thought | -0.437 |
Token | Soup |
Token ID | 34011 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Conquest | +0.997 |
losers | +0.991 |
brook | +0.981 |
ocide | +0.926 |
ndra | +0.919 |
Neg logit contributions | |
detects | -0.769 |
netflix | -0.719 |
Vas | -0.695 |
imet | -0.689 |
thought | -0.687 |
Token | vec |
Token ID | 35138 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
detects | +0.584 |
netflix | +0.546 |
Vas | +0.521 |
thought | +0.517 |
imet | +0.513 |
Neg logit contributions | |
Conquest | -0.995 |
losers | -0.983 |
brook | -0.965 |
ocide | -0.924 |
ndra | -0.917 |
Token | () |
Token ID | 3419 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
Conquest | +0.532 |
losers | +0.527 |
brook | +0.521 |
ocide | +0.492 |
ndra | +0.486 |
Neg logit contributions | |
detects | -0.469 |
netflix | -0.444 |
Vas | -0.429 |
thought | -0.424 |
Hamp | -0.423 |
Token | -> |
Token ID | 3784 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
Conquest | +0.022 |
losers | +0.022 |
brook | +0.022 |
ocide | +0.020 |
ndra | +0.020 |
Neg logit contributions | |
detects | -0.030 |
netflix | -0.028 |
Vas | -0.028 |
thought | -0.027 |
imet | -0.027 |
Token | y |
Token ID | 88 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
detects | +0.007 |
netflix | +0.007 |
Vas | +0.006 |
thought | +0.006 |
imet | +0.006 |
Neg logit contributions | |
Conquest | -0.007 |
losers | -0.007 |
brook | -0.007 |
ocide | -0.007 |
ndra | -0.007 |
Token | () |
Token ID | 3419 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
detects | +1.347 |
netflix | +1.266 |
Vas | +1.225 |
imet | +1.213 |
thought | +1.209 |
Neg logit contributions | |
Conquest | -1.688 |
losers | -1.670 |
brook | -1.647 |
ocide | -1.560 |
ndra | -1.538 |
Token | == |
Token ID | 6624 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
Conquest | +0.110 |
losers | +0.109 |
brook | +0.107 |
ocide | +0.100 |
ndra | +0.099 |
Neg logit contributions | |
detects | -0.141 |
netflix | -0.134 |
Vas | -0.131 |
imet | -0.129 |
Hamp | -0.129 |
Token | 0 |
Token ID | 657 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Conquest | +3.283 |
losers | +3.270 |
brook | +3.172 |
ocide | +2.978 |
ndra | +2.919 |
Neg logit contributions | |
detects | -3.934 |
netflix | -3.787 |
imet | -3.650 |
thought | -3.647 |
Vas | -3.616 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Conquest | +0.982 |
losers | +0.970 |
brook | +0.955 |
ocide | +0.893 |
ndra | +0.879 |
Neg logit contributions | |
detects | -1.217 |
netflix | -1.161 |
Vas | -1.129 |
thought | -1.118 |
Hamp | -1.116 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Conquest | +0.871 |
losers | +0.862 |
brook | +0.853 |
ocide | +0.805 |
ndra | +0.795 |
Neg logit contributions | |
detects | -0.807 |
netflix | -0.763 |
Vas | -0.740 |
Hamp | -0.730 |
thought | -0.729 |
Token | f |
Token ID | 69 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
detects | +0.073 |
netflix | +0.069 |
Vas | +0.066 |
thought | +0.065 |
Hamp | +0.065 |
Neg logit contributions | |
Conquest | -0.104 |
losers | -0.103 |
brook | -0.102 |
ocide | -0.097 |
ndra | -0.096 |
Token | ); |
Token ID | 1776 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Conquest | +1.393 |
losers | +1.378 |
brook | +1.360 |
ocide | +1.282 |
ndra | +1.266 |
Neg logit contributions | |
detects | -1.351 |
netflix | -1.283 |
Vas | -1.241 |
thought | -1.229 |
Hamp | -1.226 |
Token | that |
Token ID | 326 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
detects | +0.256 |
netflix | +0.242 |
Vas | +0.235 |
thought | +0.232 |
imet | +0.232 |
Neg logit contributions | |
Conquest | -0.236 |
losers | -0.231 |
brook | -0.228 |
ocide | -0.216 |
ndra | -0.213 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
detects | +0.021 |
netflix | +0.020 |
Vas | +0.019 |
thought | +0.019 |
Hamp | +0.019 |
Neg logit contributions | |
Conquest | -0.024 |
losers | -0.024 |
brook | -0.024 |
ocide | -0.022 |
ndra | -0.022 |
Token | Russian |
Token ID | 3394 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
detects | +0.950 |
netflix | +0.899 |
Vas | +0.876 |
thought | +0.865 |
Hamp | +0.864 |
Neg logit contributions | |
Conquest | -1.021 |
losers | -1.008 |
brook | -1.000 |
ocide | -0.943 |
ndra | -0.934 |
Token | truck |
Token ID | 7779 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Conquest | +0.433 |
losers | +0.428 |
brook | +0.423 |
ocide | +0.399 |
ndra | +0.393 |
Neg logit contributions | |
detects | -0.420 |
netflix | -0.399 |
Vas | -0.385 |
thought | -0.382 |
imet | -0.382 |
Token | convoy |
Token ID | 32860 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Conquest | +0.075 |
losers | +0.074 |
brook | +0.073 |
ocide | +0.069 |
ndra | +0.068 |
Neg logit contributions | |
detects | -0.081 |
netflix | -0.076 |
Vas | -0.074 |
thought | -0.073 |
imet | -0.073 |
Token | bearing |
Token ID | 14121 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
Conquest | +1.660 |
losers | +1.648 |
brook | +1.621 |
ocide | +1.523 |
ndra | +1.498 |
Neg logit contributions | |
detects | -1.663 |
netflix | -1.605 |
Vas | -1.535 |
imet | -1.530 |
thought | -1.525 |
Token | humanitarian |
Token ID | 15706 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Conquest | +3.769 |
losers | +3.732 |
brook | +3.599 |
ocide | +3.441 |
ndra | +3.340 |
Neg logit contributions | |
detects | -3.486 |
netflix | -3.351 |
imet | -3.207 |
thought | -3.191 |
ゼ | -3.124 |
Token | aid |
Token ID | 6133 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Conquest | +0.727 |
losers | +0.718 |
brook | +0.708 |
ocide | +0.663 |
ndra | +0.654 |
Neg logit contributions | |
detects | -0.861 |
netflix | -0.821 |
Vas | -0.798 |
thought | -0.789 |
Hamp | -0.788 |
Token | might |
Token ID | 1244 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
detects | +0.453 |
netflix | +0.421 |
Vas | +0.416 |
thought | +0.409 |
Hamp | +0.408 |
Neg logit contributions | |
Conquest | -0.440 |
losers | -0.431 |
brook | -0.429 |
ocide | -0.407 |
ndra | -0.403 |
Token | now |
Token ID | 783 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Conquest | +0.390 |
losers | +0.384 |
brook | +0.379 |
ocide | +0.358 |
ndra | +0.355 |
Neg logit contributions | |
detects | -0.371 |
netflix | -0.350 |
Vas | -0.340 |
thought | -0.336 |
imet | -0.335 |
Token | enter |
Token ID | 3802 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
detects | +0.724 |
netflix | +0.677 |
Vas | +0.662 |
thought | +0.650 |
Hamp | +0.649 |
Neg logit contributions | |
Conquest | -0.779 |
losers | -0.763 |
brook | -0.753 |
ocide | -0.712 |
ndra | -0.711 |
Token | Republican |
Token ID | 3415 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
detects | +1.052 |
netflix | +0.988 |
Vas | +0.972 |
Hamp | +0.966 |
thought | +0.961 |
Neg logit contributions | |
Conquest | -1.188 |
losers | -1.173 |
brook | -1.162 |
ocide | -1.106 |
ndra | -1.087 |
Token | Party |
Token ID | 3615 |
Feature activation | -5.93e-05 |
Pos logit contributions | |
Conquest | +0.003 |
losers | +0.003 |
brook | +0.003 |
ocide | +0.002 |
ndra | +0.002 |
Neg logit contributions | |
detects | -0.004 |
netflix | -0.004 |
Vas | -0.003 |
thought | -0.003 |
Hamp | -0.003 |
Token | if |
Token ID | 611 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Conquest | +0.000 |
losers | +0.000 |
brook | +0.000 |
ocide | +0.000 |
ndra | +0.000 |
Neg logit contributions | |
detects | -0.000 |
netflix | -0.000 |
Vas | -0.000 |
thought | -0.000 |
Hamp | -0.000 |
Token | they |
Token ID | 484 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
detects | +0.135 |
netflix | +0.127 |
Vas | +0.123 |
thought | +0.122 |
Hamp | +0.122 |
Neg logit contributions | |
Conquest | -0.166 |
losers | -0.164 |
brook | -0.163 |
ocide | -0.155 |
ndra | -0.152 |
Token | do |
Token ID | 466 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
detects | +0.588 |
netflix | +0.548 |
Vas | +0.535 |
thought | +0.528 |
Hamp | +0.524 |
Neg logit contributions | |
Conquest | -0.707 |
brook | -0.691 |
losers | -0.689 |
ocide | -0.658 |
ndra | -0.647 |
Token | lose |
Token ID | 4425 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
detects | +0.281 |
netflix | +0.263 |
Vas | +0.258 |
thought | +0.255 |
Hamp | +0.254 |
Neg logit contributions | |
Conquest | -0.315 |
losers | -0.309 |
brook | -0.307 |
ocide | -0.293 |
ndra | -0.290 |
Token | , |
Token ID | 11 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
losers | +3.267 |
Conquest | +3.259 |
brook | +3.148 |
ocide | +2.867 |
ndra | +2.833 |
Neg logit contributions | |
detects | -3.951 |
netflix | -3.860 |
ゼ | -3.625 |
imet | -3.614 |
Vas | -3.596 |
Token | but |
Token ID | 475 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Conquest | +0.550 |
losers | +0.543 |
brook | +0.539 |
ocide | +0.509 |
ndra | +0.502 |
Neg logit contributions | |
detects | -0.561 |
netflix | -0.531 |
Vas | -0.518 |
thought | -0.511 |
Hamp | -0.511 |
Token | it |
Token ID | 340 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Conquest | +0.077 |
losers | +0.076 |
brook | +0.076 |
ocide | +0.072 |
ndra | +0.071 |
Neg logit contributions | |
detects | -0.069 |
netflix | -0.065 |
Vas | -0.063 |
Hamp | -0.062 |
thought | -0.062 |
Token | is |
Token ID | 318 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
detects | +0.228 |
netflix | +0.213 |
Vas | +0.208 |
thought | +0.205 |
Hamp | +0.204 |
Neg logit contributions | |
Conquest | -0.224 |
losers | -0.220 |
brook | -0.218 |
ocide | -0.207 |
ndra | -0.203 |
Token | an |
Token ID | 281 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
detects | +0.307 |
netflix | +0.288 |
Vas | +0.282 |
thought | +0.279 |
Hamp | +0.278 |
Neg logit contributions | |
Conquest | -0.328 |
losers | -0.323 |
brook | -0.322 |
ocide | -0.306 |
ndra | -0.301 |
Token | -> |
Token ID | 4613 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
detects | +0.904 |
netflix | +0.855 |
Vas | +0.840 |
thought | +0.826 |
Hamp | +0.823 |
Neg logit contributions | |
Conquest | -0.791 |
losers | -0.782 |
brook | -0.769 |
ocide | -0.727 |
ndra | -0.712 |
Token | " |
Token ID | 366 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
detects | +1.029 |
netflix | +0.982 |
Vas | +0.962 |
thought | +0.952 |
Hamp | +0.940 |
Neg logit contributions | |
Conquest | -1.054 |
losers | -1.047 |
brook | -1.018 |
ocide | -0.978 |
ndra | -0.963 |
Token | S |
Token ID | 50 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Conquest | +1.560 |
losers | +1.543 |
brook | +1.527 |
ocide | +1.428 |
ndra | +1.411 |
Neg logit contributions | |
detects | -1.704 |
netflix | -1.623 |
Vas | -1.570 |
imet | -1.558 |
Hamp | -1.555 |
Token | " |
Token ID | 1 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
detects | +0.136 |
netflix | +0.129 |
Vas | +0.125 |
thought | +0.124 |
imet | +0.124 |
Neg logit contributions | |
Conquest | -0.128 |
losers | -0.127 |
brook | -0.125 |
ocide | -0.118 |
ndra | -0.116 |
Token | | |
Token ID | 91 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Conquest | +0.381 |
losers | +0.375 |
brook | +0.370 |
ocide | +0.346 |
ndra | +0.341 |
Neg logit contributions | |
detects | -0.484 |
netflix | -0.461 |
Vas | -0.448 |
thought | -0.444 |
Hamp | -0.443 |
Token | > |
Token ID | 29 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
Conquest | +0.252 |
losers | +0.250 |
brook | +0.247 |
ocide | +0.235 |
ndra | +0.232 |
Neg logit contributions | |
detects | -0.181 |
netflix | -0.170 |
Vas | -0.163 |
thought | -0.161 |
Hamp | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Conquest | +2.782 |
losers | +2.769 |
brook | +2.730 |
ocide | +2.482 |
ndra | +2.396 |
Neg logit contributions | |
detects | -4.338 |
netflix | -4.194 |
imet | -4.112 |
Vas | -4.096 |
thought | -4.074 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Conquest | +1.220 |
losers | +1.201 |
brook | +1.191 |
ocide | +1.092 |
ndra | +1.077 |
Neg logit contributions | |
detects | -1.881 |
netflix | -1.801 |
Vas | -1.747 |
imet | -1.740 |
Hamp | -1.736 |
Token | The |
Token ID | 464 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
Conquest | +1.608 |
losers | +1.592 |
brook | +1.576 |
ocide | +1.489 |
ndra | +1.471 |
Neg logit contributions | |
detects | -1.389 |
netflix | -1.312 |
Vas | -1.271 |
Hamp | -1.253 |
thought | -1.251 |
Token | output |
Token ID | 5072 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
detects | +0.421 |
netflix | +0.395 |
Vas | +0.385 |
Hamp | +0.379 |
thought | +0.379 |
Neg logit contributions | |
Conquest | -0.433 |
losers | -0.427 |
brook | -0.424 |
ocide | -0.402 |
ndra | -0.398 |
Token | is |
Token ID | 318 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
Conquest | +0.458 |
losers | +0.453 |
brook | +0.447 |
ocide | +0.423 |
ndra | +0.418 |
Neg logit contributions | |
detects | -0.432 |
netflix | -0.407 |
Vas | -0.395 |
thought | -0.390 |
imet | -0.389 |
Token | ER |
Token ID | 1137 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Conquest | +0.532 |
losers | +0.525 |
brook | +0.520 |
ocide | +0.493 |
ndra | +0.485 |
Neg logit contributions | |
detects | -0.471 |
netflix | -0.444 |
Vas | -0.431 |
thought | -0.426 |
Hamp | -0.425 |
Token | : |
Token ID | 25 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
detects | +0.696 |
netflix | +0.637 |
Vas | +0.618 |
Hamp | +0.600 |
thought | +0.599 |
Neg logit contributions | |
Conquest | -1.254 |
losers | -1.244 |
brook | -1.234 |
ocide | -1.185 |
ndra | -1.171 |
Token | I |
Token ID | 314 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
detects | +1.209 |
Vas | +1.152 |
Hamp | +1.131 |
netflix | +1.130 |
thought | +1.095 |
Neg logit contributions | |
losers | -1.705 |
Conquest | -1.678 |
brook | -1.671 |
ocide | -1.620 |
ndra | -1.594 |
Token | am |
Token ID | 716 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
detects | +0.264 |
netflix | +0.247 |
Vas | +0.238 |
thought | +0.236 |
Hamp | +0.234 |
Neg logit contributions | |
Conquest | -0.379 |
losers | -0.374 |
brook | -0.370 |
ocide | -0.353 |
ndra | -0.348 |
Token | not |
Token ID | 407 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
detects | +0.255 |
netflix | +0.240 |
Vas | +0.236 |
thought | +0.233 |
Hamp | +0.232 |
Neg logit contributions | |
Conquest | -0.249 |
losers | -0.246 |
brook | -0.244 |
ocide | -0.231 |
ndra | -0.228 |
Token | surprised |
Token ID | 6655 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
Conquest | +0.389 |
losers | +0.384 |
brook | +0.380 |
ocide | +0.358 |
ndra | +0.354 |
Neg logit contributions | |
detects | -0.383 |
netflix | -0.363 |
Vas | -0.353 |
thought | -0.349 |
Hamp | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Conquest | +3.439 |
losers | +3.426 |
brook | +3.327 |
ocide | +3.057 |
ndra | +3.057 |
Neg logit contributions | |
detects | -3.787 |
netflix | -3.651 |
imet | -3.501 |
thought | -3.438 |
ゼ | -3.433 |
Token | not |
Token ID | 407 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Conquest | +0.604 |
losers | +0.596 |
brook | +0.593 |
ocide | +0.564 |
ndra | +0.555 |
Neg logit contributions | |
detects | -0.564 |
netflix | -0.531 |
Vas | -0.521 |
Hamp | -0.516 |
thought | -0.512 |
Token | surprised |
Token ID | 6655 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
Conquest | +1.171 |
losers | +1.160 |
brook | +1.144 |
ocide | +1.077 |
ndra | +1.063 |
Neg logit contributions | |
detects | -1.136 |
netflix | -1.080 |
Vas | -1.044 |
imet | -1.032 |
thought | -1.032 |
Token | at |
Token ID | 379 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
losers | +3.694 |
Conquest | +3.685 |
brook | +3.619 |
ocide | +3.315 |
ndra | +3.294 |
Neg logit contributions | |
detects | -4.393 |
netflix | -4.257 |
imet | -4.060 |
Vas | -4.028 |
ゼ | -4.016 |
Token | all |
Token ID | 477 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Conquest | +1.064 |
losers | +1.052 |
brook | +1.040 |
ocide | +0.983 |
ndra | +0.970 |
Neg logit contributions | |
detects | -1.004 |
netflix | -0.950 |
Vas | -0.922 |
thought | -0.913 |
Hamp | -0.911 |
Token | s |
Token ID | 82 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
Conquest | +0.451 |
losers | +0.447 |
brook | +0.442 |
ocide | +0.420 |
ndra | +0.416 |
Neg logit contributions | |
detects | -0.304 |
netflix | -0.285 |
Vas | -0.274 |
thought | -0.270 |
Hamp | -0.270 |
Token | )} |
Token ID | 38165 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
Conquest | +0.568 |
losers | +0.562 |
brook | +0.555 |
ocide | +0.526 |
ndra | +0.520 |
Neg logit contributions | |
detects | -0.474 |
netflix | -0.447 |
Vas | -0.432 |
thought | -0.427 |
imet | -0.426 |
Token | R |
Token ID | 371 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
Conquest | +0.655 |
losers | +0.649 |
brook | +0.638 |
ocide | +0.602 |
ndra | +0.594 |
Neg logit contributions | |
detects | -0.656 |
netflix | -0.624 |
Vas | -0.602 |
thought | -0.598 |
imet | -0.597 |
Token | f |
Token ID | 69 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Conquest | +0.497 |
losers | +0.490 |
brook | +0.484 |
ocide | +0.456 |
ndra | +0.449 |
Neg logit contributions | |
detects | -0.500 |
netflix | -0.475 |
Vas | -0.461 |
thought | -0.457 |
imet | -0.455 |
Token | 8 |
Token ID | 23 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
Conquest | +0.297 |
losers | +0.293 |
brook | +0.288 |
ocide | +0.275 |
ndra | +0.272 |
Neg logit contributions | |
detects | -0.222 |
netflix | -0.207 |
Vas | -0.201 |
thought | -0.201 |
imet | -0.200 |
Token | { |
Token ID | 1391 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
Conquest | +2.334 |
losers | +2.321 |
brook | +2.269 |
ocide | +2.122 |
ndra | +2.081 |
Neg logit contributions | |
detects | -2.738 |
netflix | -2.646 |
imet | -2.554 |
Vas | -2.552 |
Hamp | -2.526 |
Token | ( |
Token ID | 7 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
Conquest | +3.363 |
brook | +3.359 |
losers | +3.330 |
ocide | +3.086 |
ndra | +3.059 |
Neg logit contributions | |
detects | -3.844 |
netflix | -3.592 |
imet | -3.490 |
Vas | -3.488 |
Hamp | -3.482 |
Token | 206 |
Token ID | 22136 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Conquest | +2.794 |
losers | +2.761 |
brook | +2.745 |
ocide | +2.587 |
ndra | +2.556 |
Neg logit contributions | |
detects | -2.419 |
netflix | -2.278 |
Vas | -2.193 |
Hamp | -2.171 |
imet | -2.170 |
Token | s |
Token ID | 82 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
Conquest | +0.360 |
losers | +0.355 |
brook | +0.351 |
ocide | +0.336 |
ndra | +0.332 |
Neg logit contributions | |
detects | -0.224 |
netflix | -0.209 |
Vas | -0.201 |
thought | -0.199 |
imet | -0.197 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
detects | +0.001 |
netflix | +0.001 |
Vas | +0.001 |
thought | +0.001 |
imet | +0.001 |
Neg logit contributions | |
Conquest | -0.001 |
losers | -0.001 |
brook | -0.001 |
ocide | -0.001 |
ndra | -0.001 |
Token | 54 |
Token ID | 7175 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Conquest | +0.790 |
losers | +0.783 |
brook | +0.771 |
ocide | +0.729 |
ndra | +0.720 |
Neg logit contributions | |
detects | -0.719 |
netflix | -0.682 |
Vas | -0.658 |
thought | -0.651 |
imet | -0.651 |
Token | Mer |
Token ID | 13102 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
detects | +0.116 |
netflix | +0.110 |
Vas | +0.106 |
thought | +0.106 |
Hamp | +0.104 |
Neg logit contributions | |
Conquest | -0.143 |
losers | -0.142 |
brook | -0.140 |
ocide | -0.132 |
ndra | -0.131 |
Token | ger |
Token ID | 1362 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
detects | +0.073 |
netflix | +0.069 |
Vas | +0.067 |
thought | +0.066 |
imet | +0.066 |
Neg logit contributions | |
Conquest | -0.092 |
losers | -0.091 |
brook | -0.090 |
ocide | -0.085 |
ndra | -0.084 |
Token | — |
Token ID | 851 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
detects | +1.044 |
netflix | +0.975 |
Vas | +0.958 |
thought | +0.945 |
imet | +0.943 |
Neg logit contributions | |
Conquest | -1.206 |
losers | -1.192 |
brook | -1.183 |
ocide | -1.119 |
ndra | -1.115 |
Token | FA |
Token ID | 9677 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Conquest | +1.513 |
losers | +1.496 |
brook | +1.476 |
ocide | +1.393 |
ndra | +1.375 |
Neg logit contributions | |
detects | -1.430 |
netflix | -1.356 |
Vas | -1.311 |
thought | -1.297 |
imet | -1.295 |
Token | IL |
Token ID | 4146 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Conquest | +0.417 |
losers | +0.408 |
brook | +0.399 |
ocide | +0.357 |
ndra | +0.347 |
Neg logit contributions | |
detects | -1.074 |
netflix | -1.035 |
Vas | -1.018 |
thought | -1.011 |
Hamp | -1.007 |
Token | ED |
Token ID | 1961 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
Conquest | +1.310 |
losers | +1.294 |
brook | +1.276 |
ocide | +1.192 |
ndra | +1.175 |
Neg logit contributions | |
detects | -1.617 |
netflix | -1.544 |
Vas | -1.499 |
thought | -1.484 |
imet | -1.483 |
Token |
|
Token ID | 198 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Conquest | +2.673 |
losers | +2.636 |
brook | +2.552 |
ocide | +2.360 |
ndra | +2.256 |
Neg logit contributions | |
detects | -4.493 |
netflix | -4.345 |
thought | -4.175 |
imet | -4.162 |
Hamp | -4.136 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Conquest | +2.010 |
brook | +1.991 |
losers | +1.965 |
ocide | +1.760 |
ndra | +1.750 |
Neg logit contributions | |
detects | -3.599 |
netflix | -3.440 |
imet | -3.339 |
Hamp | -3.304 |
Vas | -3.294 |
Token | Along |
Token ID | 24035 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Conquest | +1.928 |
losers | +1.911 |
brook | +1.896 |
ocide | +1.799 |
ndra | +1.776 |
Neg logit contributions | |
detects | -1.535 |
netflix | -1.436 |
Vas | -1.382 |
Hamp | -1.366 |
imet | -1.366 |
Token | side |
Token ID | 1589 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Conquest | +0.427 |
losers | +0.422 |
brook | +0.417 |
ocide | +0.394 |
ndra | +0.390 |
Neg logit contributions | |
detects | -0.385 |
netflix | -0.364 |
Vas | -0.353 |
thought | -0.349 |
Hamp | -0.348 |
Token | efforts |
Token ID | 4040 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Conquest | +0.379 |
losers | +0.375 |
brook | +0.369 |
ocide | +0.350 |
ndra | +0.345 |
Neg logit contributions | |
detects | -0.318 |
netflix | -0.302 |
Vas | -0.290 |
thought | -0.287 |
imet | -0.286 |
Token | from |
Token ID | 422 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
detects | +1.548 |
netflix | +1.428 |
Vas | +1.418 |
Hamp | +1.380 |
thought | +1.374 |
Neg logit contributions | |
Conquest | -1.954 |
brook | -1.923 |
losers | -1.921 |
ocide | -1.840 |
ndra | -1.828 |
Token | looking |
Token ID | 2045 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Conquest | +0.264 |
losers | +0.261 |
brook | +0.258 |
ocide | +0.244 |
ndra | +0.241 |
Neg logit contributions | |
detects | -0.233 |
netflix | -0.220 |
Vas | -0.213 |
thought | -0.211 |
Hamp | -0.210 |
Token | at |
Token ID | 379 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
detects | +1.422 |
netflix | +1.344 |
Vas | +1.324 |
Hamp | +1.295 |
thought | +1.294 |
Neg logit contributions | |
Conquest | -1.241 |
losers | -1.211 |
brook | -1.195 |
ndra | -1.132 |
ocide | -1.132 |
Token | the |
Token ID | 262 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
detects | +1.316 |
netflix | +1.229 |
Vas | +1.215 |
Hamp | +1.190 |
thought | +1.183 |
Neg logit contributions | |
Conquest | -1.543 |
losers | -1.524 |
brook | -1.509 |
ocide | -1.439 |
ndra | -1.427 |
Token | face |
Token ID | 1986 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
detects | +0.337 |
netflix | +0.315 |
Vas | +0.309 |
Hamp | +0.304 |
thought | +0.303 |
Neg logit contributions | |
Conquest | -0.402 |
losers | -0.396 |
brook | -0.394 |
ocide | -0.374 |
ndra | -0.371 |
Token | of |
Token ID | 286 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
detects | +0.871 |
netflix | +0.818 |
Vas | +0.797 |
thought | +0.782 |
imet | +0.779 |
Neg logit contributions | |
Conquest | -1.009 |
losers | -0.995 |
brook | -0.979 |
ndra | -0.932 |
ocide | -0.931 |
Token | the |
Token ID | 262 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
detects | +2.647 |
Vas | +2.497 |
netflix | +2.463 |
Hamp | +2.426 |
thought | +2.416 |
Neg logit contributions | |
Conquest | -3.417 |
losers | -3.362 |
brook | -3.342 |
ocide | -3.202 |
ndra | -3.160 |
Token | document |
Token ID | 3188 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
detects | +1.908 |
Vas | +1.775 |
netflix | +1.756 |
Hamp | +1.737 |
thought | +1.728 |
Neg logit contributions | |
Conquest | -1.954 |
brook | -1.912 |
losers | -1.903 |
ocide | -1.802 |
ndra | -1.788 |
Token | whether |
Token ID | 1771 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Conquest | +0.142 |
losers | +0.141 |
brook | +0.139 |
ocide | +0.132 |
ndra | +0.131 |
Neg logit contributions | |
detects | -0.109 |
netflix | -0.103 |
Vas | -0.099 |
thought | -0.098 |
Hamp | -0.098 |
Token | it |
Token ID | 340 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
detects | +0.561 |
netflix | +0.524 |
Vas | +0.518 |
Hamp | +0.508 |
thought | +0.508 |
Neg logit contributions | |
Conquest | -0.602 |
losers | -0.595 |
brook | -0.590 |
ocide | -0.559 |
ndra | -0.551 |
Token | � |
Token ID | 447 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
Conquest | +0.053 |
losers | +0.052 |
brook | +0.051 |
ocide | +0.049 |
ndra | +0.048 |
Neg logit contributions | |
detects | -0.051 |
netflix | -0.048 |
Vas | -0.047 |
thought | -0.046 |
Hamp | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
detects | +0.009 |
netflix | +0.009 |
Vas | +0.008 |
thought | +0.008 |
imet | +0.008 |
Neg logit contributions | |
Conquest | -0.010 |
losers | -0.010 |
brook | -0.010 |
ocide | -0.010 |
ndra | -0.009 |
Token | business |
Token ID | 1597 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
detects | +0.357 |
netflix | +0.334 |
Vas | +0.320 |
thought | +0.315 |
Hamp | +0.314 |
Neg logit contributions | |
Conquest | -0.590 |
losers | -0.585 |
brook | -0.579 |
ocide | -0.552 |
ndra | -0.547 |
Token | due |
Token ID | 2233 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Conquest | +0.326 |
losers | +0.322 |
brook | +0.318 |
ocide | +0.301 |
ndra | +0.296 |
Neg logit contributions | |
detects | -0.318 |
netflix | -0.300 |
Vas | -0.292 |
thought | -0.289 |
imet | -0.288 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Conquest | +0.249 |
losers | +0.246 |
brook | +0.243 |
ocide | +0.228 |
ndra | +0.225 |
Neg logit contributions | |
detects | -0.264 |
netflix | -0.251 |
Vas | -0.244 |
thought | -0.241 |
imet | -0.241 |
Token | the |
Token ID | 262 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
detects | +1.461 |
netflix | +1.373 |
Vas | +1.340 |
thought | +1.324 |
Hamp | +1.316 |
Neg logit contributions | |
Conquest | -1.754 |
losers | -1.737 |
brook | -1.721 |
ocide | -1.638 |
ndra | -1.614 |
Token | fact |
Token ID | 1109 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
detects | +0.469 |
netflix | +0.443 |
Vas | +0.427 |
thought | +0.422 |
Hamp | +0.421 |
Neg logit contributions | |
Conquest | -0.576 |
losers | -0.570 |
brook | -0.563 |
ocide | -0.534 |
ndra | -0.527 |
Token | that |
Token ID | 326 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
detects | +2.531 |
netflix | +2.373 |
Vas | +2.347 |
thought | +2.310 |
Hamp | +2.289 |
Neg logit contributions | |
Conquest | -3.514 |
losers | -3.484 |
brook | -3.453 |
ocide | -3.326 |
ndra | -3.274 |
Token | I |
Token ID | 314 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
detects | +1.369 |
netflix | +1.290 |
Vas | +1.260 |
thought | +1.243 |
Hamp | +1.236 |
Neg logit contributions | |
Conquest | -1.569 |
losers | -1.551 |
brook | -1.536 |
ocide | -1.460 |
ndra | -1.440 |
Token | didn |
Token ID | 1422 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
detects | +0.807 |
netflix | +0.760 |
Vas | +0.737 |
thought | +0.730 |
imet | +0.726 |
Neg logit contributions | |
Conquest | -0.963 |
losers | -0.951 |
brook | -0.939 |
ocide | -0.890 |
ndra | -0.878 |
Token | � |
Token ID | 447 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
detects | +0.633 |
netflix | +0.597 |
Vas | +0.578 |
thought | +0.572 |
imet | +0.568 |
Neg logit contributions | |
Conquest | -0.792 |
losers | -0.785 |
brook | -0.774 |
ocide | -0.734 |
ndra | -0.725 |
Token | � |
Token ID | 247 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
Conquest | +0.059 |
losers | +0.058 |
brook | +0.057 |
ocide | +0.052 |
ndra | +0.051 |
Neg logit contributions | |
detects | -0.103 |
netflix | -0.099 |
Vas | -0.097 |
thought | -0.096 |
imet | -0.096 |
Token | � |
Token ID | 110 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
detects | +0.615 |
netflix | +0.568 |
Vas | +0.543 |
thought | +0.533 |
imet | +0.532 |
Neg logit contributions | |
Conquest | -1.234 |
losers | -1.223 |
brook | -1.211 |
ocide | -1.157 |
ndra | -1.146 |
Token | t |
Token ID | 256 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Conquest | +0.157 |
losers | +0.156 |
brook | +0.154 |
ocide | +0.146 |
ndra | +0.144 |
Neg logit contributions | |
detects | -0.126 |
netflix | -0.119 |
Vas | -0.115 |
thought | -0.113 |
Hamp | -0.113 |
Token | - |
Token ID | 12 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
detects | +1.694 |
netflix | +1.590 |
Vas | +1.550 |
imet | +1.537 |
thought | +1.534 |
Neg logit contributions | |
Conquest | -2.007 |
losers | -1.980 |
brook | -1.961 |
ocide | -1.853 |
ndra | -1.836 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
detects | +0.404 |
netflix | +0.382 |
Vas | +0.371 |
thought | +0.367 |
imet | +0.365 |
Neg logit contributions | |
Conquest | -0.478 |
losers | -0.473 |
brook | -0.467 |
ocide | -0.441 |
ndra | -0.436 |
Token | t |
Token ID | 256 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Conquest | +0.134 |
losers | +0.133 |
brook | +0.131 |
ocide | +0.125 |
ndra | +0.123 |
Neg logit contributions | |
detects | -0.098 |
netflix | -0.092 |
Vas | -0.089 |
thought | -0.088 |
Hamp | -0.088 |
Token | f |
Token ID | 277 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
detects | +1.984 |
netflix | +1.853 |
Vas | +1.820 |
imet | +1.811 |
Hamp | +1.796 |
Neg logit contributions | |
Conquest | -2.339 |
losers | -2.309 |
brook | -2.298 |
ocide | -2.166 |
ndra | -2.143 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
detects | +3.444 |
netflix | +3.265 |
Vas | +3.215 |
imet | +3.199 |
Hamp | +3.175 |
Neg logit contributions | |
Conquest | -2.556 |
brook | -2.512 |
losers | -2.506 |
ocide | -2.290 |
ndra | -2.289 |
Token | ic |
Token ID | 291 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
detects | +2.068 |
netflix | +1.959 |
imet | +1.878 |
Vas | +1.873 |
thought | +1.857 |
Neg logit contributions | |
Conquest | -3.195 |
losers | -3.169 |
brook | -3.077 |
ndra | -2.908 |
ocide | -2.874 |
Token | ( |
Token ID | 357 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
detects | +1.375 |
netflix | +1.305 |
Vas | +1.264 |
thought | +1.249 |
Hamp | +1.248 |
Neg logit contributions | |
Conquest | -1.408 |
losers | -1.392 |
brook | -1.377 |
ocide | -1.296 |
ndra | -1.281 |
Token | t |
Token ID | 83 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
detects | +1.817 |
netflix | +1.748 |
thought | +1.709 |
Vas | +1.679 |
imet | +1.668 |
Neg logit contributions | |
Conquest | -2.152 |
losers | -2.120 |
brook | -2.060 |
ocide | -1.971 |
ndra | -1.923 |
Token | � |
Token ID | 447 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
detects | +0.990 |
netflix | +0.933 |
Vas | +0.901 |
thought | +0.891 |
imet | +0.889 |
Neg logit contributions | |
Conquest | -1.226 |
losers | -1.213 |
brook | -1.199 |
ocide | -1.136 |
ndra | -1.123 |
Token | be |
Token ID | 1350 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
detects | +0.438 |
netflix | +0.412 |
Vas | +0.401 |
thought | +0.397 |
imet | +0.395 |
Neg logit contributions | |
Conquest | -0.500 |
losers | -0.495 |
brook | -0.482 |
ocide | -0.461 |
ndra | -0.454 |
Token | ek |
Token ID | 988 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
Conquest | +0.173 |
losers | +0.171 |
brook | +0.168 |
ocide | +0.160 |
ndra | +0.157 |
Neg logit contributions | |
detects | -0.172 |
netflix | -0.163 |
Vas | -0.159 |
Hamp | -0.157 |
imet | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
detects | +0.414 |
netflix | +0.388 |
Vas | +0.386 |
Hamp | +0.379 |
thought | +0.376 |
Neg logit contributions | |
Conquest | -0.406 |
losers | -0.402 |
brook | -0.391 |
ocide | -0.375 |
ndra | -0.368 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
detects | +0.222 |
netflix | +0.210 |
Vas | +0.208 |
Hamp | +0.204 |
imet | +0.202 |
Neg logit contributions | |
Conquest | -0.194 |
losers | -0.194 |
brook | -0.190 |
ocide | -0.180 |
ndra | -0.177 |
Token | Share |
Token ID | 11649 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
detects | +0.263 |
netflix | +0.253 |
thought | +0.241 |
Vas | +0.241 |
imet | +0.238 |
Neg logit contributions | |
Conquest | -0.316 |
losers | -0.312 |
brook | -0.305 |
ocide | -0.290 |
ndra | -0.286 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
Conquest | +0.477 |
losers | +0.472 |
brook | +0.465 |
ocide | +0.437 |
ndra | +0.430 |
Neg logit contributions | |
detects | -0.532 |
netflix | -0.507 |
Vas | -0.492 |
thought | -0.487 |
Hamp | -0.486 |
Token | We |
Token ID | 775 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
detects | +2.928 |
Vas | +2.802 |
netflix | +2.788 |
Hamp | +2.755 |
thought | +2.650 |
Neg logit contributions | |
losers | -3.217 |
brook | -3.151 |
Conquest | -3.121 |
ocide | -3.037 |
ndra | -2.998 |
Token | found |
Token ID | 1043 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
detects | +1.271 |
netflix | +1.186 |
Vas | +1.160 |
thought | +1.148 |
imet | +1.139 |
Neg logit contributions | |
Conquest | -1.672 |
losers | -1.636 |
brook | -1.635 |
ocide | -1.563 |
ndra | -1.534 |
Token | a |
Token ID | 257 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
detects | +0.287 |
netflix | +0.272 |
Vas | +0.266 |
thought | +0.261 |
Hamp | +0.261 |
Neg logit contributions | |
Conquest | -0.308 |
losers | -0.304 |
brook | -0.301 |
ocide | -0.287 |
ndra | -0.282 |
Token | home |
Token ID | 1363 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
Conquest | +0.281 |
losers | +0.277 |
brook | +0.276 |
ocide | +0.261 |
ndra | +0.257 |
Neg logit contributions | |
detects | -0.259 |
netflix | -0.245 |
Vas | -0.238 |
Hamp | -0.235 |
thought | -0.235 |
Token | for |
Token ID | 329 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
Conquest | +0.393 |
losers | +0.389 |
brook | +0.382 |
ocide | +0.361 |
ndra | +0.355 |
Neg logit contributions | |
detects | -0.464 |
netflix | -0.442 |
Vas | -0.431 |
thought | -0.425 |
Hamp | -0.424 |
Token | don |
Token ID | 836 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
detects | +0.588 |
netflix | +0.546 |
Vas | +0.532 |
Hamp | +0.524 |
thought | +0.523 |
Neg logit contributions | |
Conquest | -0.669 |
losers | -0.658 |
brook | -0.656 |
ocide | -0.623 |
ndra | -0.616 |
Token | � |
Token ID | 447 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
Conquest | +0.862 |
losers | +0.854 |
brook | +0.849 |
ocide | +0.803 |
ndra | +0.791 |
Neg logit contributions | |
detects | -0.764 |
netflix | -0.727 |
Vas | -0.692 |
Hamp | -0.689 |
imet | -0.687 |
Token | � |
Token ID | 247 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
detects | +0.659 |
netflix | +0.632 |
Vas | +0.618 |
thought | +0.613 |
Hamp | +0.612 |
Neg logit contributions | |
Conquest | -0.378 |
losers | -0.372 |
brook | -0.365 |
ocide | -0.336 |
ndra | -0.329 |
Token | t |
Token ID | 83 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
detects | +0.586 |
netflix | +0.552 |
Vas | +0.536 |
thought | +0.532 |
imet | +0.529 |
Neg logit contributions | |
Conquest | -0.625 |
losers | -0.617 |
brook | -0.607 |
ocide | -0.574 |
ndra | -0.563 |
Token | tell |
Token ID | 1560 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
Conquest | +1.293 |
losers | +1.283 |
brook | +1.267 |
ocide | +1.202 |
ndra | +1.187 |
Neg logit contributions | |
detects | -0.988 |
netflix | -0.936 |
Vas | -0.898 |
thought | -0.889 |
imet | -0.886 |
Token | me |
Token ID | 502 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
detects | +0.624 |
netflix | +0.575 |
Vas | +0.567 |
Hamp | +0.558 |
imet | +0.552 |
Neg logit contributions | |
Conquest | -0.760 |
brook | -0.746 |
losers | -0.744 |
ocide | -0.710 |
ndra | -0.700 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
detects | +2.840 |
netflix | +2.603 |
Vas | +2.600 |
Hamp | +2.522 |
imet | +2.494 |
Neg logit contributions | |
Conquest | -3.399 |
brook | -3.340 |
losers | -3.308 |
ocide | -3.202 |
ndra | -3.137 |
Token | Expect |
Token ID | 23600 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
detects | +1.499 |
Vas | +1.390 |
netflix | +1.388 |
Hamp | +1.366 |
thought | +1.339 |
Neg logit contributions | |
losers | -1.798 |
Conquest | -1.787 |
brook | -1.776 |
ocide | -1.708 |
ndra | -1.682 |
Token | some |
Token ID | 617 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Conquest | +2.247 |
losers | +2.238 |
brook | +2.193 |
ocide | +2.067 |
ndra | +2.042 |
Neg logit contributions | |
detects | -2.081 |
netflix | -1.989 |
Vas | -1.917 |
thought | -1.900 |
imet | -1.895 |
Token | failures |
Token ID | 15536 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Conquest | +0.525 |
losers | +0.516 |
brook | +0.514 |
ocide | +0.485 |
ndra | +0.480 |
Neg logit contributions | |
detects | -0.514 |
netflix | -0.484 |
Vas | -0.472 |
thought | -0.466 |
Hamp | -0.465 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
detects | +0.373 |
netflix | +0.349 |
Vas | +0.343 |
imet | +0.337 |
thought | +0.337 |
Neg logit contributions | |
Conquest | -0.360 |
losers | -0.354 |
brook | -0.352 |
ocide | -0.333 |
ndra | -0.328 |
Token | as |
Token ID | 355 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
detects | +1.014 |
netflix | +0.959 |
Vas | +0.930 |
thought | +0.919 |
Hamp | +0.917 |
Neg logit contributions | |
Conquest | -1.052 |
losers | -1.039 |
brook | -1.028 |
ocide | -0.969 |
ndra | -0.956 |
Token | poor |
Token ID | 3595 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
detects | +0.874 |
netflix | +0.804 |
Vas | +0.798 |
Hamp | +0.781 |
thought | +0.777 |
Neg logit contributions | |
Conquest | -1.003 |
losers | -0.986 |
brook | -0.986 |
ocide | -0.939 |
ndra | -0.919 |
Token | shielding |
Token ID | 43539 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
detects | +0.160 |
netflix | +0.148 |
Vas | +0.147 |
thought | +0.144 |
Hamp | +0.144 |
Neg logit contributions | |
Conquest | -0.186 |
losers | -0.183 |
brook | -0.182 |
ocide | -0.173 |
ndra | -0.171 |
Token | in |
Token ID | 287 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
detects | +0.729 |
Vas | +0.673 |
netflix | +0.670 |
thought | +0.656 |
Hamp | +0.655 |
Neg logit contributions | |
Conquest | -0.771 |
losers | -0.758 |
brook | -0.751 |
ocide | -0.713 |
ndra | -0.702 |
Token | a |
Token ID | 257 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
detects | +0.292 |
netflix | +0.273 |
Vas | +0.269 |
Hamp | +0.264 |
thought | +0.263 |
Neg logit contributions | |
Conquest | -0.336 |
losers | -0.331 |
brook | -0.329 |
ocide | -0.314 |
ndra | -0.308 |
Token | radio |
Token ID | 5243 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
detects | +0.805 |
netflix | +0.758 |
Vas | +0.745 |
Hamp | +0.731 |
thought | +0.725 |
Neg logit contributions | |
Conquest | -0.850 |
losers | -0.840 |
brook | -0.835 |
ocide | -0.796 |
ndra | -0.778 |
Token | as |
Token ID | 355 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
detects | +0.247 |
netflix | +0.232 |
Vas | +0.226 |
thought | +0.222 |
Hamp | +0.222 |
Neg logit contributions | |
Conquest | -0.271 |
losers | -0.267 |
brook | -0.265 |
ocide | -0.251 |
ndra | -0.247 |
Token | determined |
Token ID | 5295 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
detects | +0.401 |
netflix | +0.377 |
Vas | +0.367 |
thought | +0.363 |
imet | +0.361 |
Neg logit contributions | |
Conquest | -0.445 |
losers | -0.440 |
brook | -0.435 |
ocide | -0.413 |
ndra | -0.405 |
Token | by |
Token ID | 416 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
Conquest | +0.250 |
losers | +0.245 |
brook | +0.243 |
ocide | +0.228 |
ndra | +0.224 |
Neg logit contributions | |
detects | -0.309 |
netflix | -0.293 |
Vas | -0.286 |
thought | -0.283 |
imet | -0.282 |
Token | step |
Token ID | 2239 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
detects | +0.021 |
netflix | +0.020 |
Vas | +0.020 |
thought | +0.019 |
Hamp | +0.019 |
Neg logit contributions | |
Conquest | -0.024 |
losers | -0.024 |
brook | -0.024 |
ocide | -0.022 |
ndra | -0.022 |
Token | ( |
Token ID | 357 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
detects | +0.261 |
netflix | +0.244 |
Vas | +0.240 |
imet | +0.237 |
thought | +0.237 |
Neg logit contributions | |
Conquest | -0.244 |
losers | -0.240 |
brook | -0.236 |
ocide | -0.224 |
ndra | -0.222 |
Token | if |
Token ID | 611 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Conquest | +1.728 |
losers | +1.723 |
brook | +1.688 |
ocide | +1.594 |
ndra | +1.570 |
Neg logit contributions | |
detects | -1.462 |
netflix | -1.392 |
Vas | -1.334 |
imet | -1.327 |
thought | -1.325 |
Token | something |
Token ID | 1223 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Conquest | +0.178 |
losers | +0.176 |
brook | +0.175 |
ocide | +0.165 |
ndra | +0.163 |
Neg logit contributions | |
detects | -0.150 |
netflix | -0.141 |
Vas | -0.137 |
thought | -0.135 |
Hamp | -0.135 |
Token | is |
Token ID | 318 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
Conquest | +0.121 |
losers | +0.119 |
brook | +0.118 |
ocide | +0.111 |
ndra | +0.110 |
Neg logit contributions | |
detects | -0.119 |
netflix | -0.112 |
Vas | -0.109 |
thought | -0.108 |
Hamp | -0.107 |
Token | biased |
Token ID | 21925 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
detects | +0.070 |
netflix | +0.066 |
Vas | +0.064 |
thought | +0.063 |
Hamp | +0.063 |
Neg logit contributions | |
Conquest | -0.073 |
losers | -0.071 |
brook | -0.071 |
ocide | -0.067 |
ndra | -0.066 |
Token | or |
Token ID | 393 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
detects | +0.514 |
netflix | +0.485 |
Vas | +0.476 |
thought | +0.469 |
imet | +0.466 |
Neg logit contributions | |
Conquest | -0.456 |
losers | -0.448 |
brook | -0.446 |
ocide | -0.417 |
ndra | -0.414 |
Token | even |
Token ID | 772 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
detects | +0.397 |
netflix | +0.371 |
Vas | +0.363 |
thought | +0.358 |
Hamp | +0.357 |
Neg logit contributions | |
Conquest | -0.404 |
losers | -0.397 |
brook | -0.394 |
ocide | -0.372 |
ndra | -0.369 |
Token | just |
Token ID | 655 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
detects | +0.292 |
netflix | +0.274 |
Vas | +0.268 |
thought | +0.264 |
Hamp | +0.263 |
Neg logit contributions | |
Conquest | -0.295 |
losers | -0.291 |
brook | -0.288 |
ocide | -0.271 |
ndra | -0.270 |
Token | flat |
Token ID | 6228 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Conquest | +1.691 |
losers | +1.687 |
brook | +1.653 |
ocide | +1.560 |
ndra | +1.528 |
Neg logit contributions | |
detects | -1.611 |
netflix | -1.553 |
Vas | -1.489 |
imet | -1.480 |
Hamp | -1.475 |
Token | made |
Token ID | 925 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
detects | +0.640 |
netflix | +0.597 |
Vas | +0.587 |
thought | +0.582 |
imet | +0.576 |
Neg logit contributions | |
Conquest | -0.632 |
losers | -0.615 |
brook | -0.613 |
ocide | -0.583 |
ndra | -0.573 |
Token | up |
Token ID | 510 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
detects | +0.276 |
netflix | +0.261 |
Vas | +0.254 |
thought | +0.252 |
imet | +0.251 |
Neg logit contributions | |
Conquest | -0.273 |
losers | -0.268 |
brook | -0.266 |
ocide | -0.251 |
ndra | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Conquest | +1.208 |
losers | +1.196 |
brook | +1.175 |
ocide | +1.101 |
ndra | +1.083 |
Neg logit contributions | |
detects | -1.438 |
netflix | -1.374 |
Vas | -1.331 |
thought | -1.319 |
imet | -1.318 |
Token | of |
Token ID | 286 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Conquest | +0.017 |
losers | +0.017 |
brook | +0.017 |
ocide | +0.016 |
ndra | +0.016 |
Neg logit contributions | |
detects | -0.014 |
netflix | -0.013 |
Vas | -0.013 |
imet | -0.013 |
Hamp | -0.013 |
Token | 14 |
Token ID | 1478 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
Conquest | +0.288 |
losers | +0.284 |
brook | +0.281 |
ocide | +0.265 |
ndra | +0.262 |
Neg logit contributions | |
detects | -0.269 |
netflix | -0.254 |
Vas | -0.246 |
thought | -0.244 |
Hamp | -0.243 |
Token | target |
Token ID | 2496 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
detects | +0.061 |
netflix | +0.057 |
Vas | +0.055 |
imet | +0.055 |
Hamp | +0.055 |
Neg logit contributions | |
Conquest | -0.067 |
losers | -0.066 |
brook | -0.065 |
ocide | -0.062 |
ndra | -0.061 |
Token | points |
Token ID | 2173 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
detects | +1.016 |
netflix | +0.940 |
Vas | +0.926 |
Hamp | +0.916 |
imet | +0.915 |
Neg logit contributions | |
Conquest | -1.032 |
losers | -1.007 |
brook | -0.996 |
ocide | -0.955 |
ndra | -0.941 |
Token | on |
Token ID | 319 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
detects | +1.259 |
netflix | +1.169 |
Vas | +1.158 |
Hamp | +1.134 |
thought | +1.134 |
Neg logit contributions | |
Conquest | -1.297 |
losers | -1.282 |
brook | -1.268 |
ocide | -1.204 |
ndra | -1.179 |
Token | the |
Token ID | 262 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
detects | +0.042 |
netflix | +0.040 |
Vas | +0.038 |
thought | +0.038 |
Hamp | +0.038 |
Neg logit contributions | |
Conquest | -0.048 |
losers | -0.048 |
brook | -0.047 |
ocide | -0.045 |
ndra | -0.044 |
Token | rock |
Token ID | 3881 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
detects | +0.268 |
netflix | +0.251 |
Vas | +0.245 |
Hamp | +0.242 |
imet | +0.242 |
Neg logit contributions | |
Conquest | -0.296 |
losers | -0.293 |
brook | -0.289 |
ocide | -0.276 |
ndra | -0.271 |
Token | , |
Token ID | 11 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
detects | +0.443 |
netflix | +0.416 |
Vas | +0.408 |
thought | +0.402 |
imet | +0.402 |
Neg logit contributions | |
Conquest | -0.434 |
losers | -0.430 |
brook | -0.424 |
ocide | -0.402 |
ndra | -0.394 |
Token | hitting |
Token ID | 9008 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
detects | +0.291 |
netflix | +0.274 |
Vas | +0.267 |
thought | +0.263 |
Hamp | +0.263 |
Neg logit contributions | |
Conquest | -0.309 |
losers | -0.306 |
brook | -0.303 |
ocide | -0.287 |
ndra | -0.283 |
Token | different |
Token ID | 1180 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
Conquest | +0.956 |
losers | +0.948 |
brook | +0.931 |
ocide | +0.875 |
ndra | +0.865 |
Neg logit contributions | |
detects | -0.925 |
netflix | -0.885 |
Vas | -0.850 |
thought | -0.846 |
imet | -0.843 |
Token | mineral |
Token ID | 18352 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
Conquest | +0.584 |
losers | +0.577 |
brook | +0.570 |
ocide | +0.538 |
ndra | +0.530 |
Neg logit contributions | |
detects | -0.588 |
netflix | -0.557 |
Vas | -0.541 |
thought | -0.534 |
Hamp | -0.534 |
Token | fo |
Token ID | 11511 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
detects | +0.166 |
netflix | +0.156 |
Vas | +0.153 |
Hamp | +0.151 |
thought | +0.151 |
Neg logit contributions | |
Conquest | -0.168 |
losers | -0.166 |
brook | -0.166 |
ocide | -0.156 |
ndra | -0.155 |
Token | iling |
Token ID | 4386 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
detects | +1.236 |
netflix | +1.179 |
thought | +1.149 |
imet | +1.142 |
Vas | +1.141 |
Neg logit contributions | |
Conquest | -1.013 |
losers | -0.996 |
brook | -0.981 |
ndra | -0.913 |
ocide | -0.911 |
Token | of |
Token ID | 286 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Conquest | +0.419 |
losers | +0.416 |
brook | +0.410 |
ocide | +0.386 |
ndra | +0.378 |
Neg logit contributions | |
detects | -0.388 |
netflix | -0.370 |
Vas | -0.355 |
imet | -0.353 |
Hamp | -0.352 |
Token | an |
Token ID | 281 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
Conquest | +0.801 |
losers | +0.791 |
brook | +0.777 |
ocide | +0.735 |
ndra | +0.725 |
Neg logit contributions | |
detects | -0.731 |
netflix | -0.693 |
Vas | -0.664 |
imet | -0.662 |
thought | -0.661 |
Token | Islamic |
Token ID | 5533 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Conquest | +0.480 |
losers | +0.475 |
brook | +0.469 |
ocide | +0.444 |
ndra | +0.438 |
Neg logit contributions | |
detects | -0.430 |
netflix | -0.407 |
Vas | -0.394 |
thought | -0.389 |
Hamp | -0.388 |
Token | Jihad |
Token ID | 35243 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
detects | +0.335 |
netflix | +0.318 |
Vas | +0.311 |
Hamp | +0.307 |
thought | +0.307 |
Neg logit contributions | |
Conquest | -0.338 |
losers | -0.337 |
brook | -0.332 |
ocide | -0.314 |
ndra | -0.311 |
Token | plan |
Token ID | 1410 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
detects | +0.625 |
netflix | +0.592 |
Vas | +0.577 |
thought | +0.570 |
Hamp | +0.568 |
Neg logit contributions | |
Conquest | -0.646 |
losers | -0.641 |
brook | -0.633 |
ocide | -0.599 |
ndra | -0.592 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
detects | +0.534 |
netflix | +0.505 |
Vas | +0.492 |
thought | +0.487 |
imet | +0.483 |
Neg logit contributions | |
Conquest | -0.517 |
losers | -0.512 |
brook | -0.503 |
ocide | -0.477 |
ndra | -0.470 |
Token | bomb |
Token ID | 5194 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Conquest | +0.687 |
losers | +0.678 |
brook | +0.670 |
ocide | +0.629 |
ndra | +0.624 |
Neg logit contributions | |
detects | -0.766 |
netflix | -0.727 |
Vas | -0.709 |
Hamp | -0.699 |
thought | -0.697 |
Token | the |
Token ID | 262 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
Conquest | +0.450 |
losers | +0.445 |
brook | +0.440 |
ocide | +0.416 |
ndra | +0.411 |
Neg logit contributions | |
detects | -0.361 |
netflix | -0.342 |
Vas | -0.328 |
thought | -0.325 |
imet | -0.324 |
Token | U |
Token ID | 471 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
detects | +0.576 |
netflix | +0.535 |
Vas | +0.533 |
Hamp | +0.522 |
thought | +0.517 |
Neg logit contributions | |
Conquest | -0.724 |
losers | -0.718 |
brook | -0.715 |
ocide | -0.681 |
ndra | -0.670 |
Token | wrong |
Token ID | 2642 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
detects | +0.590 |
netflix | +0.558 |
Vas | +0.543 |
thought | +0.537 |
Hamp | +0.535 |
Neg logit contributions | |
Conquest | -0.631 |
losers | -0.624 |
brook | -0.620 |
ocide | -0.584 |
ndra | -0.577 |
Token | to |
Token ID | 284 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
detects | +1.262 |
netflix | +1.197 |
Vas | +1.169 |
thought | +1.165 |
imet | +1.155 |
Neg logit contributions | |
Conquest | -1.258 |
losers | -1.238 |
brook | -1.228 |
ocide | -1.155 |
ndra | -1.145 |
Token | take |
Token ID | 1011 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Conquest | +0.767 |
losers | +0.761 |
brook | +0.750 |
ocide | +0.710 |
ndra | +0.699 |
Neg logit contributions | |
detects | -0.668 |
netflix | -0.634 |
Vas | -0.610 |
thought | -0.604 |
Hamp | -0.603 |
Token | into |
Token ID | 656 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
detects | +0.175 |
netflix | +0.166 |
Vas | +0.161 |
thought | +0.159 |
imet | +0.159 |
Neg logit contributions | |
Conquest | -0.171 |
losers | -0.169 |
brook | -0.167 |
ocide | -0.157 |
ndra | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Conquest | +0.170 |
losers | +0.169 |
brook | +0.166 |
ocide | +0.158 |
ndra | +0.155 |
Neg logit contributions | |
detects | -0.146 |
netflix | -0.138 |
Vas | -0.133 |
thought | -0.131 |
Hamp | -0.131 |
Token | counsel |
Token ID | 7739 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
detects | +0.418 |
netflix | +0.394 |
Vas | +0.387 |
Hamp | +0.382 |
thought | +0.380 |
Neg logit contributions | |
Conquest | -0.483 |
losers | -0.475 |
brook | -0.472 |
ocide | -0.449 |
ndra | -0.444 |
Token | s |
Token ID | 82 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
detects | +0.950 |
netflix | +0.898 |
Vas | +0.865 |
thought | +0.856 |
Hamp | +0.854 |
Neg logit contributions | |
Conquest | -1.093 |
losers | -1.082 |
brook | -1.070 |
ocide | -1.011 |
ndra | -0.998 |
Token | of |
Token ID | 286 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
detects | +1.609 |
netflix | +1.516 |
Vas | +1.477 |
imet | +1.455 |
Hamp | +1.453 |
Neg logit contributions | |
Conquest | -1.944 |
losers | -1.925 |
brook | -1.894 |
ocide | -1.803 |
ndra | -1.782 |
Token | the |
Token ID | 262 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
detects | +1.048 |
netflix | +0.986 |
Vas | +0.966 |
thought | +0.954 |
Hamp | +0.952 |
Neg logit contributions | |
Conquest | -1.219 |
losers | -1.203 |
brook | -1.200 |
ocide | -1.133 |
ndra | -1.123 |
Token | government |
Token ID | 1230 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
detects | +0.384 |
netflix | +0.362 |
Vas | +0.356 |
Hamp | +0.352 |
thought | +0.351 |
Neg logit contributions | |
Conquest | -0.427 |
brook | -0.420 |
losers | -0.419 |
ocide | -0.397 |
ndra | -0.392 |
Token | of |
Token ID | 286 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
detects | +0.398 |
netflix | +0.376 |
Vas | +0.366 |
thought | +0.362 |
imet | +0.361 |
Neg logit contributions | |
Conquest | -0.433 |
losers | -0.427 |
brook | -0.422 |
ocide | -0.399 |
ndra | -0.394 |
Token | . |
Token ID | 13 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
detects | +0.256 |
netflix | +0.245 |
Vas | +0.239 |
thought | +0.237 |
Hamp | +0.235 |
Neg logit contributions | |
Conquest | -0.219 |
losers | -0.216 |
brook | -0.211 |
ocide | -0.199 |
ndra | -0.196 |
Token | x |
Token ID | 87 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Conquest | +0.039 |
losers | +0.039 |
brook | +0.038 |
ocide | +0.035 |
ndra | +0.034 |
Neg logit contributions | |
detects | -0.065 |
netflix | -0.062 |
Vas | -0.061 |
thought | -0.060 |
imet | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Conquest | +0.185 |
losers | +0.182 |
brook | +0.178 |
ocide | +0.168 |
ndra | +0.165 |
Neg logit contributions | |
detects | -0.217 |
netflix | -0.208 |
Vas | -0.203 |
thought | -0.201 |
Hamp | -0.200 |
Token | 170 |
Token ID | 17279 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Conquest | +0.367 |
losers | +0.357 |
brook | +0.353 |
ocide | +0.334 |
ndra | +0.330 |
Neg logit contributions | |
detects | -0.320 |
netflix | -0.303 |
Vas | -0.297 |
thought | -0.296 |
imet | -0.290 |
Token | 108 |
Token ID | 15495 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Conquest | +1.458 |
losers | +1.441 |
brook | +1.423 |
ocide | +1.347 |
ndra | +1.326 |
Neg logit contributions | |
detects | -1.237 |
netflix | -1.172 |
Vas | -1.123 |
thought | -1.118 |
imet | -1.116 |
Token | 76 |
Token ID | 4304 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
detects | +0.822 |
netflix | +0.783 |
Vas | +0.762 |
thought | +0.758 |
Hamp | +0.748 |
Neg logit contributions | |
Conquest | -1.004 |
losers | -1.001 |
brook | -0.970 |
ocide | -0.931 |
ndra | -0.924 |
Token | 25 |
Token ID | 1495 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Conquest | +1.431 |
losers | +1.416 |
brook | +1.399 |
ocide | +1.321 |
ndra | +1.304 |
Neg logit contributions | |
detects | -1.304 |
netflix | -1.234 |
Vas | -1.194 |
thought | -1.180 |
Hamp | -1.178 |
Token | x |
Token ID | 2124 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
detects | +0.536 |
netflix | +0.501 |
Vas | +0.489 |
Hamp | +0.480 |
thought | +0.480 |
Neg logit contributions | |
Conquest | -0.730 |
losers | -0.727 |
brook | -0.715 |
ocide | -0.685 |
ndra | -0.675 |
Token | . |
Token ID | 13 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
detects | +0.998 |
netflix | +0.954 |
Vas | +0.937 |
thought | +0.929 |
Hamp | +0.918 |
Neg logit contributions | |
Conquest | -0.897 |
losers | -0.888 |
brook | -0.862 |
ocide | -0.820 |
ndra | -0.805 |
Token | x |
Token ID | 87 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
detects | +0.557 |
netflix | +0.537 |
Vas | +0.523 |
thought | +0.523 |
imet | +0.517 |
Neg logit contributions | |
Conquest | -0.354 |
losers | -0.349 |
brook | -0.337 |
ocide | -0.315 |
ndra | -0.308 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
detects | +0.573 |
netflix | +0.548 |
Vas | +0.536 |
thought | +0.533 |
Hamp | +0.527 |
Neg logit contributions | |
Conquest | -0.499 |
losers | -0.494 |
brook | -0.480 |
ocide | -0.455 |
ndra | -0.447 |
Token | an |
Token ID | 281 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Conquest | +0.546 |
losers | +0.542 |
brook | +0.534 |
ocide | +0.504 |
ndra | +0.497 |
Neg logit contributions | |
detects | -0.515 |
netflix | -0.490 |
Vas | -0.472 |
thought | -0.467 |
Hamp | -0.467 |
Token | indication |
Token ID | 12955 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Conquest | +0.301 |
losers | +0.295 |
brook | +0.293 |
ocide | +0.275 |
ndra | +0.272 |
Neg logit contributions | |
detects | -0.296 |
netflix | -0.278 |
Vas | -0.271 |
imet | -0.268 |
thought | -0.268 |
Token | that |
Token ID | 326 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Conquest | +1.632 |
losers | +1.618 |
brook | +1.595 |
ocide | +1.510 |
ndra | +1.491 |
Neg logit contributions | |
detects | -1.430 |
netflix | -1.360 |
Vas | -1.301 |
thought | -1.297 |
Hamp | -1.291 |
Token | the |
Token ID | 262 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Conquest | +0.460 |
losers | +0.455 |
brook | +0.449 |
ocide | +0.425 |
ndra | +0.420 |
Neg logit contributions | |
detects | -0.398 |
netflix | -0.376 |
Vas | -0.364 |
thought | -0.359 |
Hamp | -0.358 |
Token | accident |
Token ID | 5778 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Conquest | +0.192 |
losers | +0.190 |
brook | +0.188 |
ocide | +0.177 |
ndra | +0.175 |
Neg logit contributions | |
detects | -0.177 |
netflix | -0.166 |
Vas | -0.162 |
thought | -0.160 |
Hamp | -0.160 |
Token | has |
Token ID | 468 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
detects | +0.091 |
netflix | +0.086 |
Vas | +0.084 |
thought | +0.083 |
imet | +0.083 |
Neg logit contributions | |
Conquest | -0.090 |
losers | -0.088 |
brook | -0.088 |
ocide | -0.083 |
ndra | -0.082 |
Token | proceeded |
Token ID | 18814 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Conquest | +0.071 |
losers | +0.070 |
brook | +0.069 |
ocide | +0.065 |
ndra | +0.064 |
Neg logit contributions | |
detects | -0.069 |
netflix | -0.065 |
Vas | -0.063 |
thought | -0.062 |
imet | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
detects | +0.215 |
netflix | +0.204 |
Vas | +0.198 |
imet | +0.196 |
thought | +0.196 |
Neg logit contributions | |
Conquest | -0.224 |
losers | -0.221 |
brook | -0.219 |
ocide | -0.205 |
ndra | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Conquest | +0.287 |
losers | +0.284 |
brook | +0.280 |
ocide | +0.266 |
ndra | +0.263 |
Neg logit contributions | |
detects | -0.235 |
netflix | -0.222 |
Vas | -0.214 |
thought | -0.211 |
Hamp | -0.211 |
Token | next |
Token ID | 1306 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
detects | +0.010 |
netflix | +0.010 |
Vas | +0.010 |
Hamp | +0.010 |
thought | +0.010 |
Neg logit contributions | |
Conquest | -0.008 |
losers | -0.008 |
brook | -0.008 |
ocide | -0.007 |
ndra | -0.007 |
Token | step |
Token ID | 2239 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
detects | +0.430 |
netflix | +0.399 |
Vas | +0.392 |
Hamp | +0.388 |
imet | +0.387 |
Neg logit contributions | |
Conquest | -0.475 |
brook | -0.463 |
losers | -0.463 |
ocide | -0.437 |
ndra | -0.436 |
Token | regul |
Token ID | 3475 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
detects | +0.245 |
netflix | +0.229 |
Vas | +0.224 |
thought | +0.222 |
Hamp | +0.220 |
Neg logit contributions | |
Conquest | -0.282 |
losers | -0.279 |
brook | -0.276 |
ocide | -0.261 |
ndra | -0.259 |
Token | ative |
Token ID | 876 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Conquest | +1.475 |
losers | +1.461 |
brook | +1.449 |
ocide | +1.379 |
ndra | +1.363 |
Neg logit contributions | |
detects | -1.024 |
netflix | -0.961 |
Vas | -0.923 |
Hamp | -0.907 |
thought | -0.907 |
Token | ability |
Token ID | 2694 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Conquest | +0.285 |
losers | +0.282 |
brook | +0.279 |
ocide | +0.264 |
ndra | +0.261 |
Neg logit contributions | |
detects | -0.242 |
netflix | -0.229 |
Vas | -0.221 |
thought | -0.218 |
Hamp | -0.218 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
detects | +1.390 |
netflix | +1.315 |
Vas | +1.282 |
thought | +1.264 |
imet | +1.262 |
Neg logit contributions | |
Conquest | -1.350 |
losers | -1.335 |
brook | -1.320 |
ocide | -1.239 |
ndra | -1.224 |
Token | guide |
Token ID | 5698 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
detects | +0.838 |
netflix | +0.774 |
Vas | +0.755 |
thought | +0.744 |
imet | +0.739 |
Neg logit contributions | |
Conquest | -1.169 |
losers | -1.153 |
brook | -1.144 |
ocide | -1.087 |
ndra | -1.079 |
Token | our |
Token ID | 674 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
detects | +0.658 |
netflix | +0.619 |
Vas | +0.603 |
thought | +0.596 |
Hamp | +0.592 |
Neg logit contributions | |
Conquest | -0.753 |
losers | -0.745 |
brook | -0.738 |
ocide | -0.697 |
ndra | -0.691 |
Token | actions |
Token ID | 4028 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Conquest | +0.526 |
losers | +0.521 |
brook | +0.515 |
ocide | +0.488 |
ndra | +0.483 |
Neg logit contributions | |
detects | -0.418 |
netflix | -0.395 |
Vas | -0.380 |
thought | -0.375 |
Hamp | -0.375 |
Token | according |
Token ID | 1864 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Conquest | +0.160 |
losers | +0.158 |
brook | +0.156 |
ocide | +0.146 |
ndra | +0.144 |
Neg logit contributions | |
detects | -0.180 |
netflix | -0.172 |
Vas | -0.166 |
Hamp | -0.165 |
thought | -0.164 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Conquest | +1.960 |
losers | +1.925 |
brook | +1.872 |
ocide | +1.776 |
ndra | +1.715 |
Neg logit contributions | |
detects | -2.406 |
netflix | -2.301 |
imet | -2.216 |
Vas | -2.215 |
Hamp | -2.210 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
detects | +0.754 |
netflix | +0.708 |
Vas | +0.691 |
thought | +0.681 |
Hamp | +0.678 |
Neg logit contributions | |
Conquest | -0.895 |
losers | -0.889 |
brook | -0.882 |
ocide | -0.835 |
ndra | -0.827 |
Token | higher |
Token ID | 2440 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
detects | +0.788 |
netflix | +0.742 |
Vas | +0.726 |
thought | +0.718 |
Hamp | +0.713 |
Neg logit contributions | |
Conquest | -0.857 |
losers | -0.852 |
brook | -0.845 |
ocide | -0.795 |
ndra | -0.788 |
Token | � |
Token ID | 247 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
detects | +0.082 |
netflix | +0.079 |
Vas | +0.077 |
thought | +0.076 |
Hamp | +0.076 |
Neg logit contributions | |
Conquest | -0.044 |
losers | -0.043 |
brook | -0.042 |
ocide | -0.038 |
ndra | -0.038 |
Token | t |
Token ID | 83 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Conquest | +0.001 |
losers | +0.001 |
brook | +0.001 |
ocide | +0.001 |
ndra | +0.001 |
Neg logit contributions | |
detects | -0.001 |
netflix | -0.001 |
Vas | -0.001 |
thought | -0.001 |
imet | -0.001 |
Token | — |
Token ID | 851 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Conquest | +0.962 |
losers | +0.953 |
brook | +0.942 |
ocide | +0.890 |
ndra | +0.880 |
Neg logit contributions | |
detects | -0.826 |
netflix | -0.782 |
Vas | -0.755 |
thought | -0.746 |
Hamp | -0.744 |
Token | but |
Token ID | 475 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Conquest | +0.076 |
losers | +0.075 |
brook | +0.074 |
ocide | +0.070 |
ndra | +0.068 |
Neg logit contributions | |
detects | -0.109 |
netflix | -0.104 |
Vas | -0.102 |
thought | -0.101 |
imet | -0.101 |
Token | as |
Token ID | 355 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Conquest | +0.790 |
losers | +0.782 |
brook | +0.772 |
ocide | +0.729 |
ndra | +0.720 |
Neg logit contributions | |
detects | -0.717 |
netflix | -0.680 |
Vas | -0.656 |
thought | -0.649 |
imet | -0.648 |
Token | a |
Token ID | 257 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Conquest | +0.939 |
losers | +0.933 |
brook | +0.917 |
ocide | +0.864 |
ndra | +0.855 |
Neg logit contributions | |
detects | -0.803 |
netflix | -0.761 |
Vas | -0.730 |
thought | -0.725 |
imet | -0.725 |
Token | native |
Token ID | 6868 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
detects | +0.101 |
netflix | +0.095 |
Vas | +0.092 |
thought | +0.091 |
Hamp | +0.091 |
Neg logit contributions | |
Conquest | -0.126 |
losers | -0.125 |
brook | -0.124 |
ocide | -0.118 |
ndra | -0.116 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Conquest | +0.849 |
losers | +0.838 |
brook | +0.829 |
ocide | +0.777 |
ndra | +0.764 |
Neg logit contributions | |
detects | -0.782 |
netflix | -0.745 |
Vas | -0.711 |
imet | -0.709 |
thought | -0.708 |
Token | person |
Token ID | 1048 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
detects | +0.299 |
netflix | +0.283 |
Vas | +0.273 |
thought | +0.270 |
Hamp | +0.270 |
Neg logit contributions | |
Conquest | -0.328 |
losers | -0.324 |
brook | -0.320 |
ocide | -0.302 |
ndra | -0.298 |
Token | we |
Token ID | 356 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
detects | +0.419 |
netflix | +0.396 |
Vas | +0.385 |
thought | +0.380 |
Hamp | +0.379 |
Neg logit contributions | |
Conquest | -0.465 |
losers | -0.460 |
brook | -0.455 |
ocide | -0.430 |
ndra | -0.425 |
Token | strive |
Token ID | 22076 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Conquest | +0.350 |
losers | +0.348 |
brook | +0.343 |
ocide | +0.325 |
ndra | +0.322 |
Neg logit contributions | |
detects | -0.282 |
netflix | -0.267 |
Vas | -0.256 |
thought | -0.253 |
Hamp | -0.253 |
Token | could |
Token ID | 714 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Conquest | +1.104 |
losers | +1.091 |
brook | +1.077 |
ocide | +1.016 |
ndra | +1.002 |
Neg logit contributions | |
detects | -1.108 |
netflix | -1.052 |
Vas | -1.021 |
thought | -1.010 |
imet | -1.007 |
Token | go |
Token ID | 467 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
Conquest | +0.520 |
losers | +0.512 |
brook | +0.504 |
ocide | +0.480 |
ndra | +0.473 |
Neg logit contributions | |
detects | -0.436 |
netflix | -0.414 |
Vas | -0.400 |
thought | -0.393 |
imet | -0.393 |
Token | wrong |
Token ID | 2642 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Conquest | +0.679 |
losers | +0.669 |
brook | +0.661 |
ocide | +0.623 |
ndra | +0.616 |
Neg logit contributions | |
detects | -0.706 |
netflix | -0.670 |
Vas | -0.654 |
thought | -0.645 |
Hamp | -0.645 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
detects | +1.167 |
netflix | +1.105 |
Vas | +1.099 |
thought | +1.078 |
imet | +1.069 |
Neg logit contributions | |
Conquest | -1.177 |
losers | -1.149 |
brook | -1.139 |
ocide | -1.100 |
ndra | -1.082 |
Token | Ter |
Token ID | 3813 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
Conquest | +0.869 |
losers | +0.862 |
brook | +0.851 |
ocide | +0.807 |
ndra | +0.797 |
Neg logit contributions | |
detects | -0.725 |
netflix | -0.685 |
Vas | -0.664 |
thought | -0.655 |
Hamp | -0.654 |
Token | ribly |
Token ID | 16358 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Conquest | +0.004 |
losers | +0.004 |
brook | +0.004 |
ocide | +0.004 |
ndra | +0.004 |
Neg logit contributions | |
detects | -0.003 |
netflix | -0.003 |
Vas | -0.002 |
thought | -0.002 |
imet | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Conquest | +0.314 |
losers | +0.308 |
brook | +0.305 |
ocide | +0.286 |
ndra | +0.281 |
Neg logit contributions | |
detects | -0.402 |
netflix | -0.384 |
Vas | -0.376 |
thought | -0.371 |
Hamp | -0.369 |
Token | terribly |
Token ID | 22121 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
Conquest | +0.265 |
losers | +0.261 |
brook | +0.258 |
ocide | +0.241 |
ndra | +0.239 |
Neg logit contributions | |
detects | -0.316 |
netflix | -0.301 |
Vas | -0.294 |
thought | -0.291 |
Hamp | -0.290 |
Token | wrong |
Token ID | 2642 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Conquest | +0.029 |
losers | +0.028 |
brook | +0.028 |
ocide | +0.026 |
ndra | +0.026 |
Neg logit contributions | |
detects | -0.043 |
netflix | -0.041 |
Vas | -0.041 |
thought | -0.040 |
Hamp | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
detects | +0.431 |
netflix | +0.410 |
Vas | +0.402 |
thought | +0.397 |
imet | +0.395 |
Neg logit contributions | |
Conquest | -0.409 |
losers | -0.402 |
brook | -0.396 |
ocide | -0.377 |
ndra | -0.370 |
Token | And |
Token ID | 843 |
Feature activation | +8.47e-03 |
Pos logit contributions | |
losers | +0.040 |
Conquest | +0.040 |
brook | +0.039 |
ocide | +0.037 |
ndra | +0.036 |
Neg logit contributions | |
detects | -0.034 |
netflix | -0.032 |
Vas | -0.032 |
Hamp | -0.031 |
thought | -0.031 |
Token | Just |
Token ID | 2329 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Conquest | +0.453 |
losers | +0.449 |
brook | +0.442 |
ocide | +0.418 |
ndra | +0.413 |
Neg logit contributions | |
detects | -0.444 |
netflix | -0.421 |
Vas | -0.409 |
Hamp | -0.404 |
thought | -0.404 |
Token | head |
Token ID | 1182 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Conquest | +2.025 |
losers | +2.009 |
brook | +1.978 |
ocide | +1.860 |
ndra | +1.841 |
Neg logit contributions | |
detects | -1.688 |
netflix | -1.613 |
Vas | -1.540 |
imet | -1.528 |
Hamp | -1.524 |
Token | over |
Token ID | 625 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Conquest | +1.683 |
losers | +1.670 |
brook | +1.654 |
ocide | +1.539 |
ndra | +1.509 |
Neg logit contributions | |
detects | -2.023 |
netflix | -1.916 |
Vas | -1.862 |
thought | -1.851 |
imet | -1.848 |
Token | there |
Token ID | 612 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
detects | +0.151 |
netflix | +0.144 |
Vas | +0.140 |
thought | +0.138 |
Hamp | +0.138 |
Neg logit contributions | |
Conquest | -0.137 |
losers | -0.135 |
brook | -0.134 |
ocide | -0.126 |
ndra | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Conquest | +0.249 |
losers | +0.246 |
brook | +0.242 |
ocide | +0.228 |
ndra | +0.225 |
Neg logit contributions | |
detects | -0.258 |
netflix | -0.246 |
Vas | -0.238 |
thought | -0.235 |
Hamp | -0.235 |
Token | check |
Token ID | 2198 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
Conquest | +0.439 |
losers | +0.433 |
brook | +0.430 |
ocide | +0.408 |
ndra | +0.404 |
Neg logit contributions | |
detects | -0.358 |
netflix | -0.335 |
Vas | -0.326 |
Hamp | -0.321 |
thought | -0.320 |
Token | it |
Token ID | 340 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Conquest | +2.679 |
losers | +2.645 |
brook | +2.607 |
ocide | +2.380 |
ndra | +2.351 |
Neg logit contributions | |
detects | -2.960 |
netflix | -2.805 |
imet | -2.708 |
Vas | -2.704 |
thought | -2.702 |
Token | out |
Token ID | 503 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
Conquest | +1.246 |
losers | +1.240 |
brook | +1.217 |
ocide | +1.127 |
ndra | +1.114 |
Neg logit contributions | |
detects | -1.445 |
netflix | -1.379 |
Vas | -1.335 |
Hamp | -1.329 |
thought | -1.326 |
Token | . |
Token ID | 13 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
detects | +0.044 |
netflix | +0.041 |
Vas | +0.040 |
thought | +0.040 |
imet | +0.040 |
Neg logit contributions | |
Conquest | -0.043 |
losers | -0.042 |
brook | -0.042 |
ocide | -0.039 |
ndra | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
Conquest | +0.163 |
losers | +0.161 |
brook | +0.159 |
ocide | +0.148 |
ndra | +0.146 |
Neg logit contributions | |
detects | -0.198 |
netflix | -0.189 |
Vas | -0.184 |
thought | -0.182 |
Hamp | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Conquest | +0.450 |
losers | +0.444 |
brook | +0.437 |
ocide | +0.406 |
ndra | +0.399 |
Neg logit contributions | |
detects | -0.652 |
netflix | -0.624 |
Vas | -0.608 |
thought | -0.603 |
Hamp | -0.602 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
detects | +0.898 |
netflix | +0.839 |
Vas | +0.821 |
thought | +0.809 |
Hamp | +0.806 |
Neg logit contributions | |
Conquest | -1.020 |
losers | -1.009 |
brook | -1.000 |
ocide | -0.948 |
ndra | -0.934 |
Token | and |
Token ID | 290 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
detects | +1.293 |
netflix | +1.201 |
Vas | +1.194 |
thought | +1.173 |
Hamp | +1.172 |
Neg logit contributions | |
Conquest | -1.283 |
brook | -1.268 |
losers | -1.262 |
ocide | -1.198 |
ndra | -1.181 |
Token | it |
Token ID | 340 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
detects | +0.056 |
netflix | +0.052 |
Vas | +0.051 |
Hamp | +0.051 |
thought | +0.051 |
Neg logit contributions | |
Conquest | -0.059 |
losers | -0.059 |
brook | -0.058 |
ocide | -0.055 |
ndra | -0.054 |
Token | has |
Token ID | 468 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Conquest | +0.014 |
losers | +0.014 |
brook | +0.014 |
ocide | +0.013 |
ndra | +0.013 |
Neg logit contributions | |
detects | -0.013 |
netflix | -0.012 |
Vas | -0.012 |
thought | -0.012 |
imet | -0.012 |
Token | an |
Token ID | 281 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
detects | +0.192 |
netflix | +0.181 |
Vas | +0.177 |
Hamp | +0.174 |
thought | +0.174 |
Neg logit contributions | |
Conquest | -0.205 |
losers | -0.202 |
brook | -0.200 |
ocide | -0.189 |
ndra | -0.187 |
Token | M |
Token ID | 337 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
Conquest | +0.273 |
losers | +0.269 |
brook | +0.267 |
ocide | +0.251 |
ndra | +0.248 |
Neg logit contributions | |
detects | -0.275 |
netflix | -0.259 |
Vas | -0.253 |
Hamp | -0.250 |
imet | -0.250 |
Token | ( |
Token ID | 357 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Conquest | +2.820 |
losers | +2.793 |
brook | +2.762 |
ocide | +2.590 |
ndra | +2.547 |
Neg logit contributions | |
detects | -2.806 |
netflix | -2.695 |
Vas | -2.585 |
Hamp | -2.563 |
thought | -2.561 |
Token | mark |
Token ID | 4102 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Conquest | +0.667 |
losers | +0.660 |
brook | +0.651 |
ocide | +0.610 |
ndra | +0.601 |
Neg logit contributions | |
detects | -0.782 |
netflix | -0.745 |
Vas | -0.724 |
thought | -0.716 |
Hamp | -0.715 |
Token | ) |
Token ID | 8 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
Conquest | +1.304 |
losers | +1.287 |
brook | +1.279 |
ocide | +1.210 |
ndra | +1.188 |
Neg logit contributions | |
detects | -1.113 |
netflix | -1.055 |
Vas | -1.011 |
thought | -1.003 |
Hamp | -0.999 |
Token | in |
Token ID | 287 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Conquest | +0.634 |
losers | +0.627 |
brook | +0.619 |
ocide | +0.584 |
ndra | +0.577 |
Neg logit contributions | |
detects | -0.624 |
netflix | -0.590 |
Vas | -0.574 |
thought | -0.567 |
Hamp | -0.566 |
Token | . |
Token ID | 13 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
Conquest | +0.945 |
losers | +0.936 |
brook | +0.924 |
ocide | +0.876 |
ndra | +0.866 |
Neg logit contributions | |
detects | -0.727 |
netflix | -0.685 |
Vas | -0.659 |
thought | -0.651 |
imet | -0.650 |
Token | salt |
Token ID | 8268 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Conquest | +0.088 |
losers | +0.087 |
brook | +0.086 |
ocide | +0.081 |
ndra | +0.079 |
Neg logit contributions | |
detects | -0.077 |
netflix | -0.073 |
imet | -0.070 |
Vas | -0.070 |
thought | -0.070 |
Token | as |
Token ID | 355 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
detects | +0.103 |
netflix | +0.097 |
Vas | +0.095 |
thought | +0.093 |
imet | +0.093 |
Neg logit contributions | |
Conquest | -0.109 |
losers | -0.108 |
brook | -0.107 |
ocide | -0.101 |
ndra | -0.100 |
Token | I |
Token ID | 314 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
Conquest | +0.386 |
losers | +0.382 |
brook | +0.377 |
ocide | +0.356 |
ndra | +0.351 |
Neg logit contributions | |
detects | -0.363 |
netflix | -0.344 |
Vas | -0.334 |
thought | -0.330 |
Hamp | -0.329 |
Token | 've |
Token ID | 1053 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
detects | +0.537 |
netflix | +0.499 |
Vas | +0.488 |
thought | +0.483 |
Hamp | +0.477 |
Neg logit contributions | |
Conquest | -0.728 |
losers | -0.717 |
brook | -0.711 |
ocide | -0.678 |
ndra | -0.665 |
Token | only |
Token ID | 691 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
detects | +0.821 |
netflix | +0.767 |
Vas | +0.754 |
thought | +0.748 |
Hamp | +0.740 |
Neg logit contributions | |
Conquest | -0.929 |
losers | -0.916 |
brook | -0.911 |
ocide | -0.867 |
ndra | -0.849 |
Token | really |
Token ID | 1107 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Conquest | +0.545 |
losers | +0.540 |
brook | +0.533 |
ocide | +0.504 |
ndra | +0.497 |
Neg logit contributions | |
detects | -0.519 |
netflix | -0.491 |
Vas | -0.477 |
thought | -0.471 |
Hamp | -0.470 |
Token | done |
Token ID | 1760 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Conquest | +2.577 |
losers | +2.546 |
brook | +2.511 |
ndra | +2.339 |
ocide | +2.336 |
Neg logit contributions | |
detects | -2.397 |
netflix | -2.296 |
Vas | -2.180 |
imet | -2.175 |
Hamp | -2.168 |
Token | one |
Token ID | 530 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Conquest | +0.120 |
losers | +0.119 |
brook | +0.118 |
ocide | +0.112 |
ndra | +0.111 |
Neg logit contributions | |
detects | -0.121 |
netflix | -0.114 |
Vas | -0.112 |
thought | -0.110 |
Hamp | -0.110 |
Token | w |
Token ID | 266 |
Feature activation | +3.27e-03 |
Pos logit contributions | |
Conquest | +0.074 |
losers | +0.073 |
brook | +0.073 |
ocide | +0.069 |
ndra | +0.068 |
Neg logit contributions | |
detects | -0.073 |
netflix | -0.069 |
Vas | -0.068 |
thought | -0.067 |
Hamp | -0.067 |
Token | split |
Token ID | 35312 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
detects | +0.002 |
netflix | +0.002 |
Vas | +0.002 |
thought | +0.002 |
imet | +0.002 |
Neg logit contributions | |
Conquest | -0.003 |
losers | -0.003 |
brook | -0.003 |
ocide | -0.003 |
ndra | -0.003 |
Token | timed |
Token ID | 28805 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
detects | +0.109 |
netflix | +0.103 |
Vas | +0.100 |
thought | +0.099 |
imet | +0.099 |
Neg logit contributions | |
Conquest | -0.111 |
losers | -0.110 |
brook | -0.109 |
ocide | -0.103 |
ndra | -0.102 |
Token | one |
Token ID | 530 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
detects | +1.031 |
netflix | +0.964 |
Vas | +0.950 |
thought | +0.934 |
Hamp | +0.929 |
Neg logit contributions | |
Conquest | -1.186 |
brook | -1.162 |
losers | -1.161 |
ocide | -1.109 |
ndra | -1.094 |
Token | of |
Token ID | 286 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Conquest | +0.466 |
losers | +0.460 |
brook | +0.455 |
ocide | +0.431 |
ndra | +0.426 |
Neg logit contributions | |
detects | -0.427 |
netflix | -0.404 |
Vas | -0.392 |
thought | -0.388 |
Hamp | -0.387 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Conquest | +0.889 |
losers | +0.886 |
brook | +0.869 |
ocide | +0.825 |
ndra | +0.819 |
Neg logit contributions | |
detects | -0.660 |
netflix | -0.621 |
Vas | -0.593 |
imet | -0.587 |
thought | -0.586 |
Token | great |
Token ID | 1049 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
Conquest | +0.921 |
losers | +0.910 |
brook | +0.899 |
ocide | +0.846 |
ndra | +0.834 |
Neg logit contributions | |
detects | -0.962 |
netflix | -0.914 |
Vas | -0.887 |
thought | -0.877 |
Hamp | -0.875 |
Token | political |
Token ID | 1964 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Conquest | +0.571 |
losers | +0.565 |
brook | +0.557 |
ocide | +0.525 |
ndra | +0.519 |
Neg logit contributions | |
detects | -0.548 |
netflix | -0.519 |
Vas | -0.502 |
thought | -0.497 |
Hamp | -0.496 |
Token | |
Token ID | 22020 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
Conquest | +1.130 |
losers | +1.117 |
brook | +1.104 |
ocide | +1.042 |
ndra | +1.029 |
Neg logit contributions | |
detects | -1.046 |
netflix | -0.991 |
Vas | -0.959 |
thought | -0.948 |
Hamp | -0.946 |
Token | ups |
Token ID | 4739 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
losers | +2.688 |
Conquest | +2.676 |
brook | +2.671 |
ocide | +2.495 |
ndra | +2.471 |
Neg logit contributions | |
detects | -2.307 |
netflix | -2.131 |
Vas | -2.085 |
Hamp | -2.070 |
imet | -2.039 |
Token | ets |
Token ID | 1039 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
Conquest | +1.672 |
losers | +1.663 |
brook | +1.638 |
ocide | +1.543 |
ndra | +1.531 |
Neg logit contributions | |
detects | -1.509 |
netflix | -1.428 |
Vas | -1.382 |
Hamp | -1.370 |
thought | -1.370 |
Token | in |
Token ID | 287 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Conquest | +0.580 |
losers | +0.573 |
brook | +0.566 |
ocide | +0.535 |
ndra | +0.528 |
Neg logit contributions | |
detects | -0.540 |
netflix | -0.512 |
Vas | -0.496 |
thought | -0.490 |
Hamp | -0.489 |
Token | American |
Token ID | 1605 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
Conquest | +0.467 |
losers | +0.464 |
brook | +0.456 |
ocide | +0.431 |
ndra | +0.426 |
Neg logit contributions | |
detects | -0.391 |
netflix | -0.369 |
Vas | -0.354 |
imet | -0.351 |
thought | -0.351 |
Token | history |
Token ID | 2106 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Conquest | +0.570 |
losers | +0.564 |
brook | +0.553 |
ocide | +0.517 |
ndra | +0.508 |
Neg logit contributions | |
detects | -0.766 |
netflix | -0.732 |
Vas | -0.710 |
imet | -0.705 |
thought | -0.704 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Conquest | +0.245 |
losers | +0.243 |
brook | +0.239 |
ocide | +0.226 |
ndra | +0.223 |
Neg logit contributions | |
detects | -0.233 |
netflix | -0.221 |
Vas | -0.214 |
thought | -0.212 |
imet | -0.211 |
Token | sleep |
Token ID | 3993 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Conquest | +1.118 |
losers | +1.113 |
brook | +1.093 |
ocide | +1.032 |
ndra | +1.018 |
Neg logit contributions | |
detects | -0.955 |
netflix | -0.906 |
Vas | -0.870 |
thought | -0.861 |
imet | -0.860 |
Token | deficits |
Token ID | 22729 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Conquest | +0.887 |
losers | +0.884 |
brook | +0.868 |
ocide | +0.807 |
ndra | +0.797 |
Neg logit contributions | |
detects | -1.066 |
netflix | -1.021 |
Vas | -0.985 |
thought | -0.977 |
imet | -0.976 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Conquest | +1.223 |
losers | +1.219 |
brook | +1.197 |
ocide | +1.119 |
ndra | +1.113 |
Neg logit contributions | |
detects | -1.197 |
netflix | -1.144 |
Vas | -1.094 |
imet | -1.087 |
thought | -1.087 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Conquest | +0.816 |
losers | +0.807 |
brook | +0.797 |
ocide | +0.753 |
ndra | +0.744 |
Neg logit contributions | |
detects | -0.773 |
netflix | -0.731 |
Vas | -0.709 |
thought | -0.701 |
Hamp | -0.699 |
Token | doctors |
Token ID | 7519 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
Conquest | +1.227 |
losers | +1.218 |
brook | +1.203 |
ocide | +1.140 |
ndra | +1.128 |
Neg logit contributions | |
detects | -0.818 |
netflix | -0.772 |
Vas | -0.733 |
thought | -0.726 |
imet | -0.725 |
Token | note |
Token ID | 3465 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
losers | +3.334 |
Conquest | +3.330 |
brook | +3.287 |
ocide | +3.075 |
ndra | +3.042 |
Neg logit contributions | |
detects | -2.514 |
netflix | -2.426 |
imet | -2.282 |
Hamp | -2.278 |
ゼ | -2.276 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Conquest | +0.519 |
losers | +0.513 |
brook | +0.504 |
ocide | +0.469 |
ndra | +0.461 |
Neg logit contributions | |
detects | -0.647 |
netflix | -0.619 |
Vas | -0.598 |
imet | -0.593 |
Hamp | -0.592 |
Token | " |
Token ID | 366 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Conquest | +0.999 |
losers | +0.988 |
brook | +0.975 |
ocide | +0.919 |
ndra | +0.907 |
Neg logit contributions | |
detects | -1.008 |
netflix | -0.958 |
Vas | -0.928 |
thought | -0.918 |
Hamp | -0.916 |
Token | It |
Token ID | 1026 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Conquest | +0.585 |
losers | +0.579 |
brook | +0.572 |
ocide | +0.544 |
ndra | +0.537 |
Neg logit contributions | |
detects | -0.452 |
netflix | -0.427 |
Vas | -0.412 |
thought | -0.407 |
Hamp | -0.406 |
Token | 's |
Token ID | 338 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Conquest | +0.381 |
losers | +0.379 |
brook | +0.373 |
ocide | +0.351 |
ndra | +0.348 |
Neg logit contributions | |
detects | -0.362 |
netflix | -0.347 |
Vas | -0.334 |
thought | -0.331 |
Hamp | -0.331 |