Token | Hide |
Token ID | 10415 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
ascript | +0.321 |
forgiven | +0.314 |
heads | +0.283 |
forgiveness | +0.263 |
perfection | +0.258 |
Neg logit contributions | |
Interstitial | -0.541 |
loc | -0.526 |
ME | -0.518 |
方 | -0.508 |
psc | -0.503 |
Token | Caption |
Token ID | 11260 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
ascript | +1.066 |
forgiven | +1.058 |
heads | +0.968 |
forgiveness | +0.875 |
perfection | +0.857 |
Neg logit contributions | |
Interstitial | -2.166 |
loc | -2.108 |
ME | -2.075 |
方 | -2.042 |
psc | -2.026 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
ascript | +1.086 |
forgiven | +1.070 |
heads | +0.992 |
forgiveness | +0.934 |
perfection | +0.920 |
Neg logit contributions | |
Interstitial | -1.238 |
loc | -1.197 |
ME | -1.173 |
方 | -1.150 |
psc | -1.134 |
Token | of |
Token ID | 286 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ascript | +0.721 |
forgiven | +0.696 |
heads | +0.623 |
forgiveness | +0.582 |
perfection | +0.570 |
Neg logit contributions | |
Interstitial | -1.204 |
loc | -1.180 |
ME | -1.159 |
方 | -1.134 |
psc | -1.122 |
Token | 15 |
Token ID | 1315 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
ascript | +0.580 |
forgiven | +0.573 |
heads | +0.537 |
forgiveness | +0.512 |
perfection | +0.505 |
Neg logit contributions | |
Interstitial | -0.462 |
loc | -0.443 |
ME | -0.433 |
方 | -0.422 |
psc | -0.415 |
Token | Photos |
Token ID | 9434 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ascript | +0.121 |
forgiven | +0.119 |
heads | +0.111 |
forgiveness | +0.105 |
perfection | +0.104 |
Neg logit contributions | |
Interstitial | -0.113 |
loc | -0.109 |
ME | -0.107 |
方 | -0.104 |
psc | -0.103 |
Token | : |
Token ID | 25 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
forgiven | +3.734 |
ascript | +3.676 |
heads | +3.569 |
bull | +3.293 |
forgiveness | +3.280 |
Neg logit contributions | |
Interstitial | -3.995 |
loc | -3.708 |
ME | -3.614 |
psc | -3.599 |
方 | -3.593 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ascript | +0.735 |
forgiven | +0.722 |
heads | +0.664 |
forgiveness | +0.624 |
perfection | +0.614 |
Neg logit contributions | |
Interstitial | -0.924 |
loc | -0.896 |
ME | -0.880 |
方 | -0.862 |
psc | -0.850 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
forgiven | +2.289 |
ascript | +2.263 |
heads | +2.170 |
forgiveness | +2.022 |
perfection | +1.998 |
Neg logit contributions | |
Interstitial | -2.380 |
loc | -2.256 |
ME | -2.204 |
方 | -2.190 |
psc | -2.131 |
Token | 's |
Token ID | 338 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ascript | +1.166 |
forgiven | +1.127 |
heads | +1.031 |
forgiveness | +0.985 |
perfection | +0.966 |
Neg logit contributions | |
Interstitial | -1.288 |
loc | -1.261 |
ME | -1.230 |
方 | -1.192 |
psc | -1.181 |
Token | political |
Token ID | 1964 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ascript | +0.413 |
forgiven | +0.395 |
heads | +0.356 |
forgiveness | +0.337 |
perfection | +0.333 |
Neg logit contributions | |
Interstitial | -0.540 |
loc | -0.533 |
ME | -0.524 |
方 | -0.506 |
psc | -0.499 |
Token | Hide |
Token ID | 10415 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
ascript | +0.255 |
forgiven | +0.249 |
heads | +0.225 |
forgiveness | +0.209 |
perfection | +0.204 |
Neg logit contributions | |
Interstitial | -0.435 |
loc | -0.423 |
ME | -0.416 |
方 | -0.409 |
psc | -0.405 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ascript | +1.114 |
forgiven | +1.109 |
heads | +1.017 |
forgiveness | +0.917 |
perfection | +0.898 |
Neg logit contributions | |
Interstitial | -2.311 |
loc | -2.249 |
ME | -2.214 |
方 | -2.176 |
psc | -2.160 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ascript | +0.897 |
forgiven | +0.874 |
heads | +0.803 |
forgiveness | +0.759 |
perfection | +0.747 |
Neg logit contributions | |
Interstitial | -1.077 |
loc | -1.047 |
ME | -1.026 |
方 | -1.002 |
psc | -0.990 |
Token | of |
Token ID | 286 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ascript | +0.548 |
forgiven | +0.526 |
heads | +0.470 |
forgiveness | +0.442 |
perfection | +0.433 |
Neg logit contributions | |
Interstitial | -0.870 |
loc | -0.857 |
ME | -0.840 |
方 | -0.822 |
psc | -0.813 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
ascript | +0.510 |
forgiven | +0.504 |
heads | +0.472 |
forgiveness | +0.450 |
perfection | +0.444 |
Neg logit contributions | |
Interstitial | -0.407 |
loc | -0.391 |
ME | -0.382 |
方 | -0.372 |
psc | -0.366 |
Token | Photos |
Token ID | 9434 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ascript | +0.111 |
forgiven | +0.109 |
heads | +0.101 |
forgiveness | +0.096 |
perfection | +0.095 |
Neg logit contributions | |
Interstitial | -0.104 |
loc | -0.101 |
ME | -0.098 |
方 | -0.096 |
psc | -0.095 |
Token | : |
Token ID | 25 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
forgiven | +3.650 |
ascript | +3.588 |
heads | +3.480 |
forgiveness | +3.213 |
bull | +3.213 |
Neg logit contributions | |
Interstitial | -3.878 |
loc | -3.596 |
ME | -3.511 |
方 | -3.496 |
psc | -3.479 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ascript | +0.705 |
forgiven | +0.692 |
heads | +0.635 |
forgiveness | +0.599 |
perfection | +0.589 |
Neg logit contributions | |
Interstitial | -0.867 |
loc | -0.841 |
ME | -0.828 |
方 | -0.809 |
psc | -0.798 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
forgiven | +2.089 |
ascript | +2.076 |
heads | +1.974 |
forgiveness | +1.849 |
perfection | +1.823 |
Neg logit contributions | |
Interstitial | -2.159 |
loc | -2.056 |
ME | -1.998 |
方 | -1.981 |
psc | -1.924 |
Token | 's |
Token ID | 338 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ascript | +0.960 |
forgiven | +0.923 |
heads | +0.841 |
forgiveness | +0.807 |
perfection | +0.793 |
Neg logit contributions | |
Interstitial | -1.015 |
loc | -0.997 |
ME | -0.969 |
方 | -0.938 |
psc | -0.934 |
Token | political |
Token ID | 1964 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
ascript | +0.449 |
forgiven | +0.426 |
heads | +0.382 |
forgiveness | +0.366 |
perfection | +0.361 |
Neg logit contributions | |
Interstitial | -0.552 |
loc | -0.548 |
ME | -0.538 |
方 | -0.518 |
psc | -0.510 |
Token | Hide |
Token ID | 10415 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
ascript | +0.277 |
forgiven | +0.272 |
heads | +0.246 |
forgiveness | +0.230 |
perfection | +0.225 |
Neg logit contributions | |
Interstitial | -0.439 |
loc | -0.426 |
ME | -0.419 |
方 | -0.412 |
psc | -0.407 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
ascript | +1.089 |
forgiven | +1.083 |
heads | +0.987 |
forgiveness | +0.896 |
perfection | +0.878 |
Neg logit contributions | |
Interstitial | -2.207 |
loc | -2.151 |
ME | -2.117 |
方 | -2.079 |
psc | -2.063 |
Token | 7 |
Token ID | 767 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ascript | +0.848 |
forgiven | +0.845 |
heads | +0.798 |
forgiveness | +0.741 |
perfection | +0.732 |
Neg logit contributions | |
Interstitial | -0.997 |
loc | -0.959 |
ME | -0.936 |
方 | -0.923 |
psc | -0.909 |
Token | of |
Token ID | 286 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ascript | +0.838 |
forgiven | +0.808 |
heads | +0.724 |
forgiveness | +0.677 |
perfection | +0.663 |
Neg logit contributions | |
Interstitial | -1.394 |
loc | -1.368 |
ME | -1.342 |
方 | -1.315 |
psc | -1.302 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
ascript | +0.559 |
forgiven | +0.552 |
heads | +0.517 |
forgiveness | +0.493 |
perfection | +0.487 |
Neg logit contributions | |
Interstitial | -0.444 |
loc | -0.426 |
ME | -0.416 |
方 | -0.406 |
psc | -0.399 |
Token | Photos |
Token ID | 9434 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ascript | +0.095 |
forgiven | +0.093 |
heads | +0.086 |
forgiveness | +0.082 |
perfection | +0.081 |
Neg logit contributions | |
Interstitial | -0.088 |
loc | -0.085 |
ME | -0.083 |
方 | -0.081 |
psc | -0.080 |
Token | : |
Token ID | 25 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
forgiven | +3.615 |
ascript | +3.556 |
heads | +3.444 |
forgiveness | +3.183 |
bull | +3.181 |
Neg logit contributions | |
Interstitial | -3.813 |
loc | -3.541 |
ME | -3.453 |
方 | -3.440 |
psc | -3.418 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ascript | +0.764 |
forgiven | +0.750 |
heads | +0.688 |
forgiveness | +0.649 |
perfection | +0.638 |
Neg logit contributions | |
Interstitial | -0.941 |
loc | -0.913 |
ME | -0.898 |
方 | -0.879 |
psc | -0.866 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
forgiven | +2.053 |
ascript | +2.042 |
heads | +1.938 |
forgiveness | +1.818 |
perfection | +1.792 |
Neg logit contributions | |
Interstitial | -2.110 |
loc | -2.012 |
ME | -1.953 |
方 | -1.937 |
ordes | -1.880 |
Token | 's |
Token ID | 338 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ascript | +0.924 |
forgiven | +0.889 |
heads | +0.809 |
forgiveness | +0.777 |
perfection | +0.763 |
Neg logit contributions | |
Interstitial | -0.975 |
loc | -0.957 |
ME | -0.931 |
方 | -0.901 |
psc | -0.898 |
Token | political |
Token ID | 1964 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ascript | +0.529 |
forgiven | +0.501 |
heads | +0.450 |
forgiveness | +0.430 |
perfection | +0.425 |
Neg logit contributions | |
Interstitial | -0.657 |
loc | -0.651 |
ME | -0.638 |
方 | -0.616 |
psc | -0.607 |
Token | Hide |
Token ID | 10415 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ascript | +0.137 |
forgiven | +0.135 |
heads | +0.125 |
forgiveness | +0.119 |
perfection | +0.117 |
Neg logit contributions | |
Interstitial | -0.133 |
loc | -0.128 |
ME | -0.126 |
方 | -0.123 |
psc | -0.121 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ascript | +0.490 |
forgiven | +0.481 |
heads | +0.434 |
forgiveness | +0.399 |
perfection | +0.391 |
Neg logit contributions | |
Interstitial | -0.898 |
loc | -0.873 |
ME | -0.859 |
方 | -0.845 |
psc | -0.835 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ascript | +0.370 |
forgiven | +0.365 |
heads | +0.339 |
forgiveness | +0.320 |
perfection | +0.316 |
Neg logit contributions | |
Interstitial | -0.388 |
loc | -0.375 |
ME | -0.367 |
方 | -0.360 |
psc | -0.354 |
Token | of |
Token ID | 286 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ascript | +0.227 |
forgiven | +0.220 |
heads | +0.198 |
forgiveness | +0.184 |
perfection | +0.180 |
Neg logit contributions | |
Interstitial | -0.392 |
loc | -0.382 |
ME | -0.376 |
方 | -0.368 |
psc | -0.363 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
ascript | +0.236 |
forgiven | +0.231 |
heads | +0.213 |
forgiveness | +0.202 |
perfection | +0.199 |
Neg logit contributions | |
Interstitial | -0.239 |
loc | -0.232 |
ME | -0.227 |
方 | -0.222 |
psc | -0.218 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Interstitial | +0.180 |
loc | +0.173 |
ME | +0.169 |
方 | +0.165 |
psc | +0.162 |
Neg logit contributions | |
ascript | -0.195 |
forgiven | -0.192 |
heads | -0.178 |
forgiveness | -0.170 |
perfection | -0.168 |
Token | : |
Token ID | 25 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
forgiven | +3.661 |
ascript | +3.626 |
heads | +3.486 |
forgiveness | +3.233 |
perfection | +3.230 |
Neg logit contributions | |
Interstitial | -3.698 |
loc | -3.489 |
ME | -3.378 |
psc | -3.346 |
方 | -3.344 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ascript | +0.777 |
forgiven | +0.769 |
heads | +0.719 |
forgiveness | +0.681 |
perfection | +0.672 |
Neg logit contributions | |
Interstitial | -0.729 |
loc | -0.702 |
ME | -0.685 |
方 | -0.671 |
psc | -0.662 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
ascript | +2.033 |
forgiven | +2.011 |
heads | +1.933 |
forgiveness | +1.790 |
perfection | +1.775 |
Neg logit contributions | |
Interstitial | -2.044 |
loc | -1.940 |
ME | -1.900 |
方 | -1.867 |
psc | -1.845 |
Token | 's |
Token ID | 338 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
ascript | +0.987 |
forgiven | +0.973 |
heads | +0.900 |
forgiveness | +0.846 |
perfection | +0.833 |
Neg logit contributions | |
Interstitial | -1.168 |
loc | -1.129 |
ME | -1.107 |
方 | -1.086 |
psc | -1.071 |
Token | political |
Token ID | 1964 |
Feature activation | -2.62e-04 |
Pos logit contributions | |
ascript | +0.150 |
forgiven | +0.147 |
heads | +0.135 |
forgiveness | +0.127 |
perfection | +0.125 |
Neg logit contributions | |
Interstitial | -0.188 |
loc | -0.182 |
ME | -0.179 |
方 | -0.175 |
psc | -0.172 |
Token | Hide |
Token ID | 10415 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
ascript | +0.283 |
forgiven | +0.277 |
heads | +0.249 |
forgiveness | +0.232 |
perfection | +0.227 |
Neg logit contributions | |
Interstitial | -0.478 |
loc | -0.465 |
ME | -0.457 |
方 | -0.449 |
psc | -0.445 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ascript | +0.987 |
forgiven | +0.979 |
heads | +0.892 |
forgiveness | +0.810 |
perfection | +0.794 |
Neg logit contributions | |
Interstitial | -1.979 |
loc | -1.926 |
ME | -1.897 |
方 | -1.863 |
psc | -1.848 |
Token | 8 |
Token ID | 807 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ascript | +0.830 |
forgiven | +0.817 |
heads | +0.753 |
forgiveness | +0.713 |
perfection | +0.702 |
Neg logit contributions | |
Interstitial | -0.919 |
loc | -0.890 |
ME | -0.873 |
方 | -0.855 |
psc | -0.841 |
Token | of |
Token ID | 286 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ascript | +0.512 |
forgiven | +0.490 |
heads | +0.438 |
forgiveness | +0.412 |
perfection | +0.404 |
Neg logit contributions | |
Interstitial | -0.803 |
loc | -0.792 |
ME | -0.776 |
方 | -0.758 |
psc | -0.752 |
Token | 15 |
Token ID | 1315 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
ascript | +0.398 |
forgiven | +0.393 |
heads | +0.367 |
forgiveness | +0.351 |
perfection | +0.346 |
Neg logit contributions | |
Interstitial | -0.312 |
loc | -0.300 |
ME | -0.293 |
方 | -0.285 |
psc | -0.280 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Interstitial | +0.148 |
loc | +0.143 |
ME | +0.140 |
方 | +0.136 |
psc | +0.135 |
Neg logit contributions | |
ascript | -0.162 |
forgiven | -0.159 |
heads | -0.148 |
forgiveness | -0.141 |
perfection | -0.139 |
Token | : |
Token ID | 25 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
forgiven | +3.457 |
ascript | +3.406 |
heads | +3.289 |
forgiveness | +3.047 |
bull | +3.038 |
Neg logit contributions | |
Interstitial | -3.594 |
loc | -3.343 |
ME | -3.262 |
方 | -3.246 |
psc | -3.222 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ascript | +0.620 |
forgiven | +0.608 |
heads | +0.557 |
forgiveness | +0.527 |
perfection | +0.518 |
Neg logit contributions | |
Interstitial | -0.752 |
loc | -0.730 |
ME | -0.718 |
方 | -0.702 |
psc | -0.692 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
forgiven | +2.058 |
ascript | +2.047 |
heads | +1.941 |
forgiveness | +1.822 |
perfection | +1.796 |
Neg logit contributions | |
Interstitial | -2.118 |
loc | -2.019 |
ME | -1.960 |
方 | -1.943 |
ordes | -1.887 |
Token | 's |
Token ID | 338 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ascript | +0.902 |
forgiven | +0.869 |
heads | +0.790 |
forgiveness | +0.759 |
perfection | +0.745 |
Neg logit contributions | |
Interstitial | -0.951 |
loc | -0.933 |
ME | -0.908 |
方 | -0.879 |
psc | -0.876 |
Token | political |
Token ID | 1964 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ascript | +0.518 |
forgiven | +0.491 |
heads | +0.441 |
forgiveness | +0.422 |
perfection | +0.417 |
Neg logit contributions | |
Interstitial | -0.644 |
loc | -0.637 |
ME | -0.626 |
方 | -0.605 |
psc | -0.595 |
Token | Hide |
Token ID | 10415 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
ascript | +0.325 |
forgiven | +0.319 |
heads | +0.291 |
forgiveness | +0.273 |
perfection | +0.268 |
Neg logit contributions | |
Interstitial | -0.448 |
loc | -0.435 |
ME | -0.427 |
方 | -0.419 |
psc | -0.414 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ascript | +0.941 |
forgiven | +0.934 |
heads | +0.851 |
forgiveness | +0.773 |
perfection | +0.758 |
Neg logit contributions | |
Interstitial | -1.880 |
loc | -1.829 |
ME | -1.801 |
方 | -1.769 |
psc | -1.753 |
Token | 9 |
Token ID | 860 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ascript | +0.677 |
forgiven | +0.670 |
heads | +0.616 |
forgiveness | +0.575 |
perfection | +0.565 |
Neg logit contributions | |
Interstitial | -0.943 |
loc | -0.915 |
ME | -0.896 |
方 | -0.883 |
psc | -0.872 |
Token | of |
Token ID | 286 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ascript | +0.888 |
forgiven | +0.850 |
heads | +0.760 |
forgiveness | +0.713 |
perfection | +0.699 |
Neg logit contributions | |
Interstitial | -1.428 |
loc | -1.407 |
ME | -1.380 |
方 | -1.347 |
psc | -1.333 |
Token | 15 |
Token ID | 1315 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
ascript | +0.453 |
forgiven | +0.446 |
heads | +0.417 |
forgiveness | +0.399 |
perfection | +0.393 |
Neg logit contributions | |
Interstitial | -0.352 |
loc | -0.339 |
ME | -0.331 |
方 | -0.322 |
psc | -0.317 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Interstitial | +0.106 |
loc | +0.103 |
ME | +0.101 |
方 | +0.098 |
psc | +0.097 |
Neg logit contributions | |
ascript | -0.117 |
forgiven | -0.115 |
heads | -0.106 |
forgiveness | -0.102 |
perfection | -0.100 |
Token | : |
Token ID | 25 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
forgiven | +3.424 |
ascript | +3.377 |
heads | +3.257 |
forgiveness | +3.020 |
bull | +3.007 |
Neg logit contributions | |
Interstitial | -3.545 |
loc | -3.297 |
ME | -3.215 |
方 | -3.202 |
psc | -3.178 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ascript | +0.629 |
forgiven | +0.616 |
heads | +0.564 |
forgiveness | +0.534 |
perfection | +0.525 |
Neg logit contributions | |
Interstitial | -0.763 |
loc | -0.741 |
ME | -0.729 |
方 | -0.713 |
psc | -0.702 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
forgiven | +1.912 |
ascript | +1.905 |
heads | +1.801 |
forgiveness | +1.694 |
perfection | +1.670 |
Neg logit contributions | |
Interstitial | -1.934 |
loc | -1.845 |
ME | -1.792 |
方 | -1.773 |
psc | -1.723 |
Token | 's |
Token ID | 338 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ascript | +0.753 |
forgiven | +0.724 |
heads | +0.658 |
forgiveness | +0.632 |
perfection | +0.621 |
Neg logit contributions | |
Interstitial | -0.786 |
loc | -0.772 |
ME | -0.751 |
方 | -0.726 |
psc | -0.724 |
Token | political |
Token ID | 1964 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ascript | +0.466 |
forgiven | +0.442 |
heads | +0.397 |
forgiveness | +0.379 |
perfection | +0.374 |
Neg logit contributions | |
Interstitial | -0.577 |
loc | -0.571 |
ME | -0.561 |
方 | -0.541 |
psc | -0.533 |
Token | Hide |
Token ID | 10415 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
ascript | +0.198 |
forgiven | +0.193 |
heads | +0.175 |
forgiveness | +0.166 |
perfection | +0.162 |
Neg logit contributions | |
Interstitial | -0.271 |
loc | -0.264 |
ME | -0.258 |
方 | -0.254 |
psc | -0.251 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
ascript | +0.891 |
forgiven | +0.884 |
heads | +0.804 |
forgiveness | +0.732 |
perfection | +0.718 |
Neg logit contributions | |
Interstitial | -1.765 |
loc | -1.717 |
ME | -1.690 |
方 | -1.661 |
psc | -1.645 |
Token | 10 |
Token ID | 838 |
Feature activation | +7.04e-03 |
Pos logit contributions | |
ascript | +0.866 |
forgiven | +0.858 |
heads | +0.807 |
forgiveness | +0.768 |
perfection | +0.758 |
Neg logit contributions | |
Interstitial | -0.676 |
loc | -0.648 |
ME | -0.631 |
方 | -0.618 |
psc | -0.607 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ascript | +0.011 |
forgiven | +0.010 |
heads | +0.009 |
forgiveness | +0.009 |
perfection | +0.009 |
Neg logit contributions | |
Interstitial | -0.016 |
loc | -0.016 |
ME | -0.015 |
方 | -0.015 |
psc | -0.015 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ascript | +0.252 |
forgiven | +0.248 |
heads | +0.232 |
forgiveness | +0.222 |
perfection | +0.219 |
Neg logit contributions | |
Interstitial | -0.197 |
loc | -0.189 |
ME | -0.185 |
方 | -0.180 |
psc | -0.177 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Interstitial | +0.237 |
loc | +0.230 |
ME | +0.224 |
方 | +0.219 |
psc | +0.216 |
Neg logit contributions | |
ascript | -0.261 |
forgiven | -0.257 |
heads | -0.238 |
forgiveness | -0.227 |
perfection | -0.224 |
Token | : |
Token ID | 25 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
forgiven | +3.389 |
ascript | +3.343 |
heads | +3.221 |
forgiveness | +2.989 |
bull | +2.976 |
Neg logit contributions | |
Interstitial | -3.504 |
loc | -3.260 |
ME | -3.180 |
方 | -3.167 |
psc | -3.140 |
Token | Carly |
Token ID | 35982 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
ascript | +0.557 |
forgiven | +0.546 |
heads | +0.500 |
forgiveness | +0.474 |
perfection | +0.465 |
Neg logit contributions | |
Interstitial | -0.669 |
loc | -0.649 |
ME | -0.639 |
方 | -0.624 |
psc | -0.615 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
forgiven | +1.819 |
ascript | +1.814 |
heads | +1.711 |
forgiveness | +1.611 |
perfection | +1.589 |
Neg logit contributions | |
Interstitial | -1.830 |
loc | -1.746 |
ME | -1.695 |
方 | -1.678 |
ordes | -1.630 |
Token | 's |
Token ID | 338 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ascript | +0.654 |
forgiven | +0.629 |
heads | +0.572 |
forgiveness | +0.550 |
perfection | +0.540 |
Neg logit contributions | |
Interstitial | -0.681 |
loc | -0.670 |
ME | -0.651 |
方 | -0.629 |
psc | -0.628 |
Token | political |
Token ID | 1964 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
ascript | +0.398 |
forgiven | +0.376 |
heads | +0.337 |
forgiveness | +0.323 |
perfection | +0.319 |
Neg logit contributions | |
Interstitial | -0.485 |
loc | -0.480 |
ME | -0.471 |
方 | -0.454 |
psc | -0.448 |
Token | Transport |
Token ID | 19940 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ascript | +0.942 |
forgiven | +0.929 |
heads | +0.866 |
forgiveness | +0.821 |
perfection | +0.810 |
Neg logit contributions | |
Interstitial | -0.894 |
loc | -0.861 |
ME | -0.843 |
方 | -0.824 |
psc | -0.811 |
Token | Minister |
Token ID | 4139 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ascript | +0.368 |
forgiven | +0.364 |
heads | +0.339 |
forgiveness | +0.320 |
perfection | +0.316 |
Neg logit contributions | |
Interstitial | -0.375 |
loc | -0.361 |
ME | -0.354 |
方 | -0.346 |
psc | -0.341 |
Token | of |
Token ID | 286 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Interstitial | +0.510 |
loc | +0.493 |
ME | +0.484 |
方 | +0.472 |
psc | +0.466 |
Neg logit contributions | |
ascript | -0.482 |
forgiven | -0.473 |
heads | -0.437 |
forgiveness | -0.415 |
perfection | -0.408 |
Token | Raj |
Token ID | 13308 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ascript | +0.545 |
forgiven | +0.542 |
heads | +0.511 |
forgiveness | +0.480 |
perfection | +0.477 |
Neg logit contributions | |
Interstitial | -0.535 |
loc | -0.512 |
ME | -0.498 |
方 | -0.492 |
psc | -0.485 |
Token | as |
Token ID | 292 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Interstitial | +0.897 |
loc | +0.865 |
ME | +0.849 |
方 | +0.833 |
psc | +0.821 |
Neg logit contributions | |
ascript | -0.743 |
forgiven | -0.732 |
heads | -0.678 |
forgiveness | -0.636 |
perfection | -0.626 |
Token | than |
Token ID | 14813 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ascript | +0.494 |
forgiven | +0.480 |
heads | +0.418 |
forgiveness | +0.371 |
bull | +0.360 |
Neg logit contributions | |
Interstitial | -1.391 |
loc | -1.331 |
ME | -1.318 |
方 | -1.312 |
psc | -1.304 |
Token | held |
Token ID | 2714 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
forgiven | +3.037 |
ascript | +3.023 |
heads | +2.914 |
perfection | +2.643 |
forgiveness | +2.615 |
Neg logit contributions | |
Interstitial | -3.780 |
loc | -3.602 |
ME | -3.538 |
方 | -3.508 |
ordes | -3.452 |
Token | three |
Token ID | 1115 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ascript | +0.923 |
forgiven | +0.908 |
heads | +0.856 |
forgiveness | +0.802 |
perfection | +0.793 |
Neg logit contributions | |
Interstitial | -0.970 |
loc | -0.928 |
ME | -0.913 |
方 | -0.896 |
psc | -0.883 |
Token | meetings |
Token ID | 8292 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ascript | +0.216 |
forgiven | +0.212 |
heads | +0.199 |
forgiveness | +0.186 |
perfection | +0.183 |
Neg logit contributions | |
Interstitial | -0.246 |
loc | -0.236 |
ME | -0.232 |
方 | -0.228 |
psc | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ascript | +0.195 |
forgiven | +0.191 |
heads | +0.173 |
forgiveness | +0.164 |
perfection | +0.161 |
Neg logit contributions | |
Interstitial | -0.263 |
loc | -0.257 |
ME | -0.252 |
方 | -0.247 |
psc | -0.244 |
Token | A |
Token ID | 317 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ascript | +0.541 |
forgiven | +0.535 |
heads | +0.503 |
forgiveness | +0.473 |
perfection | +0.467 |
Neg logit contributions | |
Interstitial | -0.526 |
loc | -0.506 |
ME | -0.494 |
方 | -0.485 |
psc | -0.477 |
Token | Hide |
Token ID | 10415 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
ascript | +0.132 |
forgiven | +0.129 |
heads | +0.116 |
forgiveness | +0.108 |
perfection | +0.106 |
Neg logit contributions | |
Interstitial | -0.228 |
loc | -0.222 |
ME | -0.218 |
方 | -0.215 |
psc | -0.212 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ascript | +0.726 |
forgiven | +0.717 |
heads | +0.650 |
forgiveness | +0.594 |
perfection | +0.582 |
Neg logit contributions | |
Interstitial | -1.394 |
loc | -1.356 |
ME | -1.334 |
方 | -1.311 |
psc | -1.298 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ascript | +0.688 |
forgiven | +0.681 |
heads | +0.635 |
forgiveness | +0.601 |
perfection | +0.592 |
Neg logit contributions | |
Interstitial | -0.677 |
loc | -0.652 |
ME | -0.638 |
方 | -0.626 |
psc | -0.616 |
Token | of |
Token ID | 286 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ascript | +0.154 |
forgiven | +0.146 |
heads | +0.130 |
forgiveness | +0.123 |
perfection | +0.121 |
Neg logit contributions | |
Interstitial | -0.232 |
loc | -0.231 |
ME | -0.225 |
方 | -0.220 |
psc | -0.218 |
Token | 15 |
Token ID | 1315 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ascript | +0.256 |
forgiven | +0.253 |
heads | +0.237 |
forgiveness | +0.226 |
perfection | +0.223 |
Neg logit contributions | |
Interstitial | -0.202 |
loc | -0.194 |
ME | -0.190 |
方 | -0.185 |
psc | -0.182 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Interstitial | +0.127 |
loc | +0.123 |
ME | +0.120 |
方 | +0.117 |
psc | +0.116 |
Neg logit contributions | |
ascript | -0.138 |
forgiven | -0.135 |
heads | -0.126 |
forgiveness | -0.120 |
perfection | -0.118 |
Token | : |
Token ID | 25 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
forgiven | +3.269 |
ascript | +3.227 |
heads | +3.107 |
forgiveness | +2.884 |
bull | +2.869 |
Neg logit contributions | |
Interstitial | -3.350 |
loc | -3.120 |
ME | -3.042 |
方 | -3.027 |
psc | -3.001 |
Token | Carly |
Token ID | 35982 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
ascript | +0.337 |
forgiven | +0.330 |
heads | +0.301 |
forgiveness | +0.286 |
perfection | +0.281 |
Neg logit contributions | |
Interstitial | -0.397 |
loc | -0.386 |
ME | -0.380 |
方 | -0.371 |
psc | -0.366 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
forgiven | +1.693 |
ascript | +1.690 |
heads | +1.593 |
forgiveness | +1.500 |
perfection | +1.479 |
Neg logit contributions | |
Interstitial | -1.695 |
loc | -1.617 |
ME | -1.570 |
方 | -1.554 |
psc | -1.510 |
Token | 's |
Token ID | 338 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ascript | +0.570 |
forgiven | +0.548 |
heads | +0.498 |
forgiveness | +0.479 |
perfection | +0.470 |
Neg logit contributions | |
Interstitial | -0.597 |
loc | -0.587 |
ME | -0.572 |
方 | -0.553 |
psc | -0.550 |
Token | political |
Token ID | 1964 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
ascript | +0.383 |
forgiven | +0.361 |
heads | +0.323 |
forgiveness | +0.310 |
perfection | +0.307 |
Neg logit contributions | |
Interstitial | -0.466 |
loc | -0.462 |
ME | -0.453 |
方 | -0.437 |
psc | -0.431 |
Token | ( |
Token ID | 357 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ascript | +0.274 |
forgiven | +0.268 |
heads | +0.243 |
forgiveness | +0.226 |
perfection | +0.222 |
Neg logit contributions | |
Interstitial | -0.444 |
loc | -0.433 |
ME | -0.425 |
方 | -0.417 |
psc | -0.412 |
Token | high |
Token ID | 8929 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ascript | +0.503 |
forgiven | +0.496 |
heads | +0.461 |
forgiveness | +0.435 |
perfection | +0.429 |
Neg logit contributions | |
Interstitial | -0.528 |
loc | -0.508 |
ME | -0.499 |
方 | -0.489 |
psc | -0.481 |
Token | voltage |
Token ID | 15004 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Interstitial | +0.956 |
loc | +0.923 |
ME | +0.904 |
方 | +0.884 |
psc | +0.871 |
Neg logit contributions | |
ascript | -0.969 |
forgiven | -0.952 |
heads | -0.879 |
forgiveness | -0.835 |
perfection | -0.823 |
Token | ) |
Token ID | 8 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Interstitial | +0.578 |
loc | +0.560 |
ME | +0.548 |
方 | +0.536 |
psc | +0.529 |
Neg logit contributions | |
ascript | -0.520 |
forgiven | -0.510 |
heads | -0.467 |
forgiveness | -0.444 |
perfection | -0.437 |
Token | or |
Token ID | 393 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Interstitial | +0.473 |
loc | +0.461 |
ME | +0.451 |
方 | +0.441 |
psc | +0.436 |
Neg logit contributions | |
ascript | -0.328 |
forgiven | -0.320 |
heads | -0.291 |
forgiveness | -0.273 |
perfection | -0.268 |
Token | overhe |
Token ID | 34789 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
forgiven | +0.554 |
ascript | +0.553 |
heads | +0.517 |
forgiveness | +0.485 |
perfection | +0.478 |
Neg logit contributions | |
Interstitial | -0.653 |
loc | -0.632 |
ME | -0.620 |
方 | -0.608 |
psc | -0.603 |
Token | ating |
Token ID | 803 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
ascript | +3.420 |
forgiven | +3.386 |
heads | +3.166 |
forgiveness | +2.980 |
ache | +2.978 |
Neg logit contributions | |
Interstitial | -3.242 |
方 | -2.973 |
ME | -2.955 |
loc | -2.954 |
Pwr | -2.880 |
Token | . |
Token ID | 13 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
Interstitial | +0.045 |
loc | +0.044 |
ME | +0.043 |
方 | +0.042 |
psc | +0.042 |
Neg logit contributions | |
ascript | -0.029 |
forgiven | -0.029 |
heads | -0.026 |
forgiveness | -0.024 |
perfection | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
ascript | +0.118 |
forgiven | +0.116 |
heads | +0.109 |
forgiveness | +0.103 |
perfection | +0.102 |
Neg logit contributions | |
Interstitial | -0.108 |
loc | -0.103 |
ME | -0.101 |
方 | -0.099 |
psc | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ascript | +0.146 |
forgiven | +0.145 |
heads | +0.135 |
forgiveness | +0.127 |
perfection | +0.126 |
Neg logit contributions | |
Interstitial | -0.147 |
loc | -0.141 |
ME | -0.138 |
方 | -0.136 |
psc | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Interstitial | +0.567 |
loc | +0.552 |
ME | +0.540 |
方 | +0.521 |
psc | +0.515 |
Neg logit contributions | |
ascript | -0.649 |
forgiven | -0.633 |
heads | -0.586 |
forgiveness | -0.561 |
perfection | -0.553 |
Token | Hide |
Token ID | 10415 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
ascript | +0.167 |
forgiven | +0.163 |
heads | +0.147 |
forgiveness | +0.137 |
perfection | +0.135 |
Neg logit contributions | |
Interstitial | -0.270 |
loc | -0.263 |
ME | -0.258 |
方 | -0.254 |
psc | -0.251 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
ascript | +0.736 |
forgiven | +0.727 |
heads | +0.660 |
forgiveness | +0.603 |
perfection | +0.590 |
Neg logit contributions | |
Interstitial | -1.418 |
loc | -1.379 |
ME | -1.357 |
方 | -1.334 |
psc | -1.321 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
ascript | +0.637 |
forgiven | +0.620 |
heads | +0.558 |
forgiveness | +0.533 |
perfection | +0.523 |
Neg logit contributions | |
Interstitial | -0.828 |
loc | -0.809 |
ME | -0.794 |
方 | -0.775 |
psc | -0.764 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ascript | +0.170 |
forgiven | +0.161 |
heads | +0.144 |
forgiveness | +0.136 |
perfection | +0.133 |
Neg logit contributions | |
Interstitial | -0.258 |
loc | -0.256 |
ME | -0.250 |
方 | -0.243 |
psc | -0.241 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ascript | +0.237 |
forgiven | +0.233 |
heads | +0.218 |
forgiveness | +0.208 |
perfection | +0.206 |
Neg logit contributions | |
Interstitial | -0.185 |
loc | -0.178 |
ME | -0.174 |
方 | -0.169 |
psc | -0.166 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Interstitial | +0.226 |
loc | +0.220 |
ME | +0.215 |
方 | +0.209 |
psc | +0.206 |
Neg logit contributions | |
ascript | -0.249 |
forgiven | -0.244 |
heads | -0.226 |
forgiveness | -0.216 |
perfection | -0.213 |
Token | : |
Token ID | 25 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
forgiven | +3.234 |
ascript | +3.195 |
heads | +3.072 |
forgiveness | +2.855 |
bull | +2.838 |
Neg logit contributions | |
Interstitial | -3.292 |
loc | -3.068 |
ME | -2.991 |
方 | -2.976 |
psc | -2.949 |
Token | Carly |
Token ID | 35982 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
ascript | +0.278 |
forgiven | +0.272 |
heads | +0.248 |
forgiveness | +0.236 |
perfection | +0.232 |
Neg logit contributions | |
Interstitial | -0.324 |
loc | -0.315 |
ME | -0.311 |
方 | -0.303 |
psc | -0.299 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
forgiven | +1.615 |
ascript | +1.613 |
heads | +1.518 |
forgiveness | +1.431 |
perfection | +1.411 |
Neg logit contributions | |
Interstitial | -1.601 |
loc | -1.528 |
ME | -1.485 |
方 | -1.469 |
psc | -1.428 |
Token | 's |
Token ID | 338 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ascript | +0.525 |
forgiven | +0.506 |
heads | +0.460 |
forgiveness | +0.442 |
perfection | +0.434 |
Neg logit contributions | |
Interstitial | -0.551 |
loc | -0.543 |
ME | -0.529 |
方 | -0.511 |
psc | -0.509 |
Token | political |
Token ID | 1964 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
ascript | +0.328 |
forgiven | +0.310 |
heads | +0.277 |
forgiveness | +0.265 |
perfection | +0.263 |
Neg logit contributions | |
Interstitial | -0.398 |
loc | -0.395 |
ME | -0.387 |
方 | -0.373 |
psc | -0.368 |
Token | was |
Token ID | 373 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
Interstitial | +0.091 |
loc | +0.089 |
ME | +0.087 |
方 | +0.085 |
psc | +0.084 |
Neg logit contributions | |
ascript | -0.078 |
forgiven | -0.076 |
heads | -0.070 |
forgiveness | -0.066 |
perfection | -0.065 |
Token | about |
Token ID | 546 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ascript | +0.165 |
forgiven | +0.160 |
heads | +0.148 |
forgiveness | +0.139 |
perfection | +0.136 |
Neg logit contributions | |
Interstitial | -0.193 |
loc | -0.187 |
ME | -0.183 |
方 | -0.180 |
psc | -0.177 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
Interstitial | +0.501 |
loc | +0.488 |
ME | +0.476 |
方 | +0.462 |
psc | +0.457 |
Neg logit contributions | |
ascript | -0.509 |
forgiven | -0.489 |
heads | -0.453 |
forgiveness | -0.425 |
perfection | -0.419 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ascript | +0.104 |
forgiven | +0.100 |
heads | +0.092 |
forgiveness | +0.087 |
perfection | +0.085 |
Neg logit contributions | |
Interstitial | -0.131 |
loc | -0.127 |
ME | -0.125 |
方 | -0.122 |
psc | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ascript | +0.326 |
forgiven | +0.321 |
heads | +0.299 |
forgiveness | +0.284 |
perfection | +0.280 |
Neg logit contributions | |
Interstitial | -0.308 |
loc | -0.296 |
ME | -0.291 |
方 | -0.283 |
psc | -0.279 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ascript | +0.186 |
forgiven | +0.184 |
heads | +0.170 |
forgiveness | +0.161 |
perfection | +0.158 |
Neg logit contributions | |
Interstitial | -0.206 |
loc | -0.200 |
ME | -0.196 |
方 | -0.191 |
psc | -0.189 |
Token | : |
Token ID | 25 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ascript | +3.310 |
forgiven | +3.308 |
heads | +3.128 |
forgiveness | +2.933 |
perfection | +2.905 |
Neg logit contributions | |
Interstitial | -3.194 |
loc | -2.985 |
ME | -2.929 |
方 | -2.915 |
ordes | -2.841 |
Token | k |
Token ID | 479 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
Interstitial | +0.298 |
loc | +0.288 |
ME | +0.282 |
方 | +0.276 |
psc | +0.272 |
Neg logit contributions | |
ascript | -0.286 |
forgiven | -0.281 |
heads | -0.260 |
forgiveness | -0.246 |
perfection | -0.242 |
Token | imp |
Token ID | 11011 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Interstitial | +0.094 |
loc | +0.091 |
ME | +0.089 |
方 | +0.087 |
psc | +0.086 |
Neg logit contributions | |
ascript | -0.100 |
forgiven | -0.099 |
heads | -0.092 |
forgiveness | -0.088 |
perfection | -0.086 |
Token | unk |
Token ID | 2954 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Interstitial | +0.836 |
loc | +0.818 |
ME | +0.798 |
方 | +0.777 |
psc | +0.770 |
Neg logit contributions | |
ascript | -0.817 |
forgiven | -0.812 |
heads | -0.751 |
forgiveness | -0.713 |
perfection | -0.702 |
Token | rock |
Token ID | 10823 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Interstitial | +1.185 |
loc | +1.170 |
ME | +1.142 |
方 | +1.109 |
psc | +1.099 |
Neg logit contributions | |
ascript | -0.990 |
forgiven | -0.989 |
heads | -0.896 |
forgiveness | -0.854 |
perfection | -0.837 |
Token | Hide |
Token ID | 10415 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
ascript | +0.086 |
forgiven | +0.085 |
heads | +0.077 |
forgiveness | +0.072 |
perfection | +0.070 |
Neg logit contributions | |
Interstitial | -0.133 |
loc | -0.129 |
ME | -0.127 |
方 | -0.125 |
psc | -0.123 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ascript | +0.641 |
forgiven | +0.632 |
heads | +0.572 |
forgiveness | +0.524 |
perfection | +0.513 |
Neg logit contributions | |
Interstitial | -1.222 |
loc | -1.189 |
ME | -1.170 |
方 | -1.150 |
psc | -1.138 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
forgiven | +0.593 |
ascript | +0.589 |
heads | +0.556 |
forgiveness | +0.525 |
perfection | +0.519 |
Neg logit contributions | |
Interstitial | -0.556 |
loc | -0.532 |
ME | -0.519 |
方 | -0.513 |
psc | -0.504 |
Token | of |
Token ID | 286 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Interstitial | +0.317 |
loc | +0.315 |
ME | +0.308 |
方 | +0.298 |
psc | +0.296 |
Neg logit contributions | |
ascript | -0.220 |
forgiven | -0.207 |
heads | -0.184 |
forgiveness | -0.176 |
perfection | -0.172 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ascript | +0.283 |
forgiven | +0.279 |
heads | +0.261 |
forgiveness | +0.249 |
perfection | +0.246 |
Neg logit contributions | |
Interstitial | -0.220 |
loc | -0.212 |
ME | -0.207 |
方 | -0.201 |
psc | -0.198 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Interstitial | +0.219 |
loc | +0.212 |
ME | +0.207 |
方 | +0.202 |
psc | +0.199 |
Neg logit contributions | |
ascript | -0.240 |
forgiven | -0.236 |
heads | -0.219 |
forgiveness | -0.209 |
perfection | -0.206 |
Token | : |
Token ID | 25 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
forgiven | +3.208 |
ascript | +3.171 |
heads | +3.046 |
forgiveness | +2.831 |
bull | +2.814 |
Neg logit contributions | |
Interstitial | -3.255 |
loc | -3.034 |
ME | -2.961 |
方 | -2.944 |
psc | -2.916 |
Token | Carly |
Token ID | 35982 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
ascript | +0.407 |
forgiven | +0.399 |
heads | +0.364 |
forgiveness | +0.346 |
perfection | +0.340 |
Neg logit contributions | |
Interstitial | -0.483 |
loc | -0.469 |
ME | -0.462 |
方 | -0.451 |
psc | -0.445 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
forgiven | +1.681 |
ascript | +1.677 |
heads | +1.581 |
forgiveness | +1.489 |
perfection | +1.468 |
Neg logit contributions | |
Interstitial | -1.680 |
loc | -1.603 |
ME | -1.556 |
方 | -1.540 |
psc | -1.497 |
Token | 's |
Token ID | 338 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ascript | +0.570 |
forgiven | +0.548 |
heads | +0.498 |
forgiveness | +0.480 |
perfection | +0.471 |
Neg logit contributions | |
Interstitial | -0.594 |
loc | -0.585 |
ME | -0.569 |
方 | -0.549 |
psc | -0.548 |
Token | political |
Token ID | 1964 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ascript | +0.381 |
forgiven | +0.360 |
heads | +0.323 |
forgiveness | +0.309 |
perfection | +0.306 |
Neg logit contributions | |
Interstitial | -0.469 |
loc | -0.464 |
ME | -0.456 |
方 | -0.440 |
psc | -0.433 |
Token | Hide |
Token ID | 10415 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
Interstitial | +0.019 |
loc | +0.018 |
ME | +0.018 |
方 | +0.017 |
psc | +0.017 |
Neg logit contributions | |
ascript | -0.011 |
forgiven | -0.011 |
heads | -0.010 |
forgiveness | -0.009 |
perfection | -0.009 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ascript | +0.609 |
forgiven | +0.600 |
heads | +0.543 |
forgiveness | +0.498 |
perfection | +0.488 |
Neg logit contributions | |
Interstitial | -1.148 |
loc | -1.116 |
ME | -1.099 |
方 | -1.080 |
psc | -1.069 |
Token | 12 |
Token ID | 1105 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ascript | +0.507 |
forgiven | +0.490 |
heads | +0.452 |
forgiveness | +0.432 |
perfection | +0.424 |
Neg logit contributions | |
Interstitial | -0.486 |
loc | -0.475 |
ME | -0.464 |
方 | -0.450 |
psc | -0.444 |
Token | of |
Token ID | 286 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
Interstitial | +0.421 |
loc | +0.420 |
ME | +0.410 |
方 | +0.399 |
psc | +0.395 |
Neg logit contributions | |
ascript | -0.292 |
forgiven | -0.276 |
heads | -0.246 |
forgiveness | -0.234 |
perfection | -0.230 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ascript | +0.178 |
forgiven | +0.175 |
heads | +0.164 |
forgiveness | +0.157 |
perfection | +0.155 |
Neg logit contributions | |
Interstitial | -0.138 |
loc | -0.133 |
ME | -0.130 |
方 | -0.126 |
psc | -0.124 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Interstitial | +0.346 |
loc | +0.336 |
ME | +0.328 |
方 | +0.319 |
psc | +0.315 |
Neg logit contributions | |
ascript | -0.382 |
forgiven | -0.376 |
heads | -0.348 |
forgiveness | -0.333 |
perfection | -0.327 |
Token | : |
Token ID | 25 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
forgiven | +3.135 |
ascript | +3.100 |
heads | +2.975 |
forgiveness | +2.768 |
bull | +2.751 |
Neg logit contributions | |
Interstitial | -3.168 |
loc | -2.955 |
ME | -2.882 |
方 | -2.865 |
psc | -2.837 |
Token | Carly |
Token ID | 35982 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
ascript | +0.300 |
forgiven | +0.294 |
heads | +0.268 |
forgiveness | +0.255 |
perfection | +0.251 |
Neg logit contributions | |
Interstitial | -0.351 |
loc | -0.341 |
ME | -0.336 |
方 | -0.328 |
psc | -0.323 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
forgiven | +1.662 |
ascript | +1.660 |
heads | +1.564 |
forgiveness | +1.473 |
perfection | +1.452 |
Neg logit contributions | |
Interstitial | -1.664 |
loc | -1.588 |
ME | -1.542 |
方 | -1.526 |
psc | -1.483 |
Token | 's |
Token ID | 338 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ascript | +0.593 |
forgiven | +0.572 |
heads | +0.519 |
forgiveness | +0.500 |
perfection | +0.490 |
Neg logit contributions | |
Interstitial | -0.620 |
loc | -0.610 |
ME | -0.593 |
方 | -0.573 |
psc | -0.570 |
Token | political |
Token ID | 1964 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
ascript | +0.343 |
forgiven | +0.324 |
heads | +0.290 |
forgiveness | +0.278 |
perfection | +0.276 |
Neg logit contributions | |
Interstitial | -0.417 |
loc | -0.414 |
ME | -0.406 |
方 | -0.391 |
psc | -0.386 |
Token | iff |
Token ID | 733 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Interstitial | +0.028 |
loc | +0.027 |
ME | +0.027 |
方 | +0.026 |
psc | +0.026 |
Neg logit contributions | |
ascript | -0.033 |
forgiven | -0.032 |
heads | -0.030 |
forgiveness | -0.029 |
perfection | -0.028 |
Token | Tra |
Token ID | 15721 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ascript | +0.604 |
forgiven | +0.595 |
heads | +0.550 |
forgiveness | +0.516 |
perfection | +0.508 |
Neg logit contributions | |
Interstitial | -0.728 |
loc | -0.704 |
ME | -0.691 |
方 | -0.678 |
psc | -0.668 |
Token | x |
Token ID | 87 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Interstitial | +0.749 |
loc | +0.745 |
ME | +0.724 |
psc | +0.696 |
方 | +0.688 |
Neg logit contributions | |
ascript | -0.846 |
forgiven | -0.843 |
heads | -0.776 |
forgiveness | -0.749 |
perfection | -0.735 |
Token |
|
Token ID | 198 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
ascript | +1.156 |
forgiven | +1.139 |
heads | +1.063 |
forgiveness | +1.001 |
perfection | +0.989 |
Neg logit contributions | |
Interstitial | -1.166 |
loc | -1.125 |
ME | -1.099 |
方 | -1.082 |
psc | -1.064 |
Token |
|
Token ID | 198 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
Interstitial | +0.089 |
loc | +0.087 |
ME | +0.085 |
方 | +0.082 |
psc | +0.081 |
Neg logit contributions | |
ascript | -0.099 |
forgiven | -0.097 |
heads | -0.090 |
forgiveness | -0.086 |
perfection | -0.084 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Interstitial | +0.191 |
loc | +0.185 |
ME | +0.182 |
方 | +0.178 |
psc | +0.176 |
Neg logit contributions | |
ascript | -0.158 |
forgiven | -0.155 |
heads | -0.143 |
forgiveness | -0.135 |
perfection | -0.133 |
Token | : |
Token ID | 25 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ascript | +3.210 |
forgiven | +3.202 |
heads | +3.027 |
forgiveness | +2.842 |
perfection | +2.818 |
Neg logit contributions | |
Interstitial | -3.090 |
loc | -2.891 |
ME | -2.824 |
方 | -2.819 |
psc | -2.749 |
Token | V |
Token ID | 569 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Interstitial | +0.659 |
loc | +0.638 |
ME | +0.626 |
方 | +0.611 |
psc | +0.601 |
Neg logit contributions | |
ascript | -0.641 |
forgiven | -0.627 |
heads | -0.579 |
forgiveness | -0.548 |
perfection | -0.540 |
Token | the |
Token ID | 1169 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ascript | +0.704 |
forgiven | +0.695 |
heads | +0.649 |
forgiveness | +0.615 |
perfection | +0.607 |
Neg logit contributions | |
Interstitial | -0.661 |
loc | -0.636 |
ME | -0.623 |
方 | -0.609 |
psc | -0.599 |
Token | Happy |
Token ID | 25082 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Interstitial | +0.781 |
loc | +0.757 |
ME | +0.743 |
方 | +0.721 |
psc | +0.712 |
Neg logit contributions | |
ascript | -0.783 |
forgiven | -0.775 |
heads | -0.721 |
forgiveness | -0.683 |
perfection | -0.673 |
Token | L |
Token ID | 43 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
Interstitial | +0.210 |
loc | +0.204 |
ME | +0.200 |
方 | +0.195 |
psc | +0.192 |
Neg logit contributions | |
ascript | -0.197 |
forgiven | -0.194 |
heads | -0.180 |
forgiveness | -0.170 |
perfection | -0.168 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Interstitial | +0.561 |
loc | +0.535 |
ME | +0.526 |
方 | +0.508 |
psc | +0.498 |
Neg logit contributions | |
ascript | -0.880 |
forgiven | -0.853 |
heads | -0.785 |
forgiveness | -0.764 |
perfection | -0.758 |
Token | boys |
Token ID | 13202 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
Interstitial | +0.622 |
loc | +0.620 |
ME | +0.609 |
psc | +0.585 |
方 | +0.575 |
Neg logit contributions | |
ascript | -0.589 |
forgiven | -0.573 |
heads | -0.532 |
forgiveness | -0.506 |
perfection | -0.500 |
Token | beware |
Token ID | 40600 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Interstitial | +0.011 |
loc | +0.010 |
ME | +0.010 |
方 | +0.010 |
psc | +0.010 |
Neg logit contributions | |
ascript | -0.009 |
forgiven | -0.009 |
heads | -0.008 |
forgiveness | -0.008 |
perfection | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-03 |
Pos logit contributions | |
ascript | +1.121 |
forgiven | +1.110 |
heads | +1.033 |
forgiveness | +0.976 |
perfection | +0.962 |
Neg logit contributions | |
Interstitial | -1.152 |
loc | -1.109 |
ME | -1.085 |
方 | -1.066 |
psc | -1.047 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
Interstitial | +0.009 |
loc | +0.008 |
ME | +0.008 |
方 | +0.008 |
psc | +0.008 |
Neg logit contributions | |
ascript | -0.010 |
forgiven | -0.009 |
heads | -0.009 |
forgiveness | -0.008 |
perfection | -0.008 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Interstitial | +0.072 |
loc | +0.070 |
ME | +0.069 |
方 | +0.067 |
psc | +0.066 |
Neg logit contributions | |
ascript | -0.061 |
forgiven | -0.060 |
heads | -0.056 |
forgiveness | -0.052 |
perfection | -0.052 |
Token | : |
Token ID | 25 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ascript | +3.221 |
forgiven | +3.210 |
heads | +3.033 |
forgiveness | +2.851 |
perfection | +2.826 |
Neg logit contributions | |
Interstitial | -3.042 |
loc | -2.854 |
ME | -2.789 |
方 | -2.776 |
psc | -2.710 |
Token | j |
Token ID | 474 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
Interstitial | +0.496 |
loc | +0.481 |
ME | +0.471 |
方 | +0.460 |
psc | +0.453 |
Neg logit contributions | |
ascript | -0.479 |
forgiven | -0.469 |
heads | -0.433 |
forgiveness | -0.410 |
perfection | -0.404 |
Token | wt |
Token ID | 46569 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
Interstitial | +0.148 |
loc | +0.143 |
ME | +0.140 |
方 | +0.137 |
psc | +0.135 |
Neg logit contributions | |
ascript | -0.154 |
forgiven | -0.152 |
heads | -0.142 |
forgiveness | -0.134 |
perfection | -0.133 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ascript | +0.069 |
forgiven | +0.069 |
heads | +0.064 |
forgiveness | +0.060 |
perfection | +0.059 |
Neg logit contributions | |
Interstitial | -0.071 |
loc | -0.069 |
ME | -0.068 |
方 | -0.066 |
psc | -0.065 |
Token | - |
Token ID | 532 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Interstitial | +0.477 |
loc | +0.466 |
ME | +0.460 |
方 | +0.446 |
psc | +0.440 |
Neg logit contributions | |
ascript | -0.365 |
forgiven | -0.364 |
heads | -0.329 |
forgiveness | -0.311 |
perfection | -0.306 |
Token | criminals |
Token ID | 12954 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ascript | +0.160 |
forgiven | +0.155 |
heads | +0.140 |
forgiveness | +0.133 |
bull | +0.132 |
Neg logit contributions | |
Interstitial | -0.207 |
loc | -0.201 |
ME | -0.197 |
方 | -0.193 |
psc | -0.190 |
Token | , |
Token ID | 11 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Interstitial | +0.265 |
loc | +0.256 |
ME | +0.250 |
方 | +0.244 |
psc | +0.241 |
Neg logit contributions | |
ascript | -0.281 |
forgiven | -0.276 |
heads | -0.257 |
forgiveness | -0.245 |
perfection | -0.241 |
Token | terrorists |
Token ID | 10509 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
ascript | +0.294 |
forgiven | +0.285 |
heads | +0.259 |
forgiveness | +0.243 |
bull | +0.238 |
Neg logit contributions | |
Interstitial | -0.419 |
loc | -0.407 |
ME | -0.400 |
方 | -0.392 |
psc | -0.385 |
Token | , |
Token ID | 11 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ascript | +0.882 |
forgiven | +0.872 |
heads | +0.815 |
forgiveness | +0.768 |
perfection | +0.758 |
Neg logit contributions | |
Interstitial | -0.879 |
loc | -0.847 |
ME | -0.830 |
方 | -0.813 |
psc | -0.801 |
Token | or |
Token ID | 393 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ascript | +0.531 |
forgiven | +0.518 |
heads | +0.476 |
forgiveness | +0.450 |
perfection | +0.441 |
Neg logit contributions | |
Interstitial | -0.622 |
loc | -0.603 |
ME | -0.591 |
方 | -0.578 |
psc | -0.568 |
Token | rogue |
Token ID | 23586 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ascript | +0.751 |
forgiven | +0.735 |
heads | +0.674 |
forgiveness | +0.634 |
perfection | +0.622 |
Neg logit contributions | |
Interstitial | -0.949 |
loc | -0.921 |
ME | -0.903 |
方 | -0.885 |
psc | -0.870 |
Token | governments |
Token ID | 6905 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
forgiven | +2.966 |
ascript | +2.953 |
heads | +2.836 |
perfection | +2.623 |
forgiveness | +2.622 |
Neg logit contributions | |
Interstitial | -3.240 |
loc | -3.091 |
ME | -3.037 |
方 | -2.994 |
psc | -2.966 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ascript | +0.472 |
forgiven | +0.466 |
heads | +0.434 |
forgiveness | +0.410 |
perfection | +0.405 |
Neg logit contributions | |
Interstitial | -0.472 |
loc | -0.455 |
ME | -0.446 |
方 | -0.437 |
psc | -0.430 |
Token | can |
Token ID | 460 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ascript | +0.285 |
forgiven | +0.280 |
heads | +0.258 |
forgiveness | +0.243 |
perfection | +0.239 |
Neg logit contributions | |
Interstitial | -0.349 |
loc | -0.337 |
ME | -0.331 |
方 | -0.325 |
psc | -0.320 |
Token | use |
Token ID | 779 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ascript | +0.442 |
forgiven | +0.437 |
heads | +0.408 |
forgiveness | +0.382 |
perfection | +0.378 |
Neg logit contributions | |
Interstitial | -0.512 |
loc | -0.492 |
ME | -0.483 |
方 | -0.476 |
psc | -0.468 |
Token | their |
Token ID | 511 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ascript | +0.429 |
forgiven | +0.421 |
heads | +0.387 |
forgiveness | +0.364 |
perfection | +0.357 |
Neg logit contributions | |
Interstitial | -0.542 |
loc | -0.526 |
ME | -0.516 |
方 | -0.506 |
psc | -0.498 |
Token | pulling |
Token ID | 10427 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Interstitial | +0.746 |
loc | +0.721 |
ME | +0.708 |
方 | +0.693 |
psc | +0.683 |
Neg logit contributions | |
ascript | -0.655 |
forgiven | -0.644 |
heads | -0.596 |
forgiveness | -0.561 |
perfection | -0.553 |
Token | that |
Token ID | 326 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Interstitial | +0.726 |
loc | +0.704 |
ME | +0.691 |
方 | +0.678 |
psc | +0.667 |
Neg logit contributions | |
ascript | -0.608 |
forgiven | -0.597 |
heads | -0.546 |
forgiveness | -0.516 |
perfection | -0.507 |
Token | out |
Token ID | 503 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ascript | +0.038 |
forgiven | +0.037 |
heads | +0.034 |
forgiveness | +0.032 |
perfection | +0.031 |
Neg logit contributions | |
Interstitial | -0.053 |
loc | -0.052 |
ME | -0.051 |
方 | -0.050 |
psc | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
ascript | +0.306 |
forgiven | +0.299 |
heads | +0.271 |
forgiveness | +0.254 |
perfection | +0.250 |
Neg logit contributions | |
Interstitial | -0.451 |
loc | -0.441 |
ME | -0.433 |
方 | -0.424 |
psc | -0.420 |
Token | In |
Token ID | 554 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ascript | +0.142 |
forgiven | +0.141 |
heads | +0.131 |
forgiveness | +0.124 |
perfection | +0.122 |
Neg logit contributions | |
Interstitial | -0.143 |
loc | -0.138 |
ME | -0.135 |
方 | -0.132 |
psc | -0.130 |
Token | hindsight |
Token ID | 36412 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ascript | +0.557 |
forgiven | +0.549 |
heads | +0.508 |
forgiveness | +0.479 |
perfection | +0.471 |
Neg logit contributions | |
Interstitial | -0.622 |
loc | -0.602 |
ME | -0.590 |
方 | -0.578 |
psc | -0.570 |
Token | , |
Token ID | 11 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
forgiven | +2.902 |
ascript | +2.866 |
heads | +2.704 |
forgiveness | +2.562 |
perfection | +2.521 |
Neg logit contributions | |
Interstitial | -3.278 |
loc | -3.138 |
ME | -3.056 |
方 | -3.025 |
psc | -2.975 |
Token | I |
Token ID | 314 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
Interstitial | +0.086 |
loc | +0.083 |
ME | +0.082 |
方 | +0.080 |
psc | +0.079 |
Neg logit contributions | |
ascript | -0.083 |
forgiven | -0.081 |
heads | -0.075 |
forgiveness | -0.071 |
perfection | -0.070 |
Token | think |
Token ID | 892 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
ascript | +0.020 |
forgiven | +0.019 |
heads | +0.018 |
forgiveness | +0.017 |
perfection | +0.017 |
Neg logit contributions | |
Interstitial | -0.021 |
loc | -0.020 |
ME | -0.020 |
方 | -0.020 |
psc | -0.019 |
Token | we |
Token ID | 356 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
ascript | +0.094 |
forgiven | +0.093 |
heads | +0.086 |
forgiveness | +0.081 |
perfection | +0.080 |
Neg logit contributions | |
Interstitial | -0.102 |
loc | -0.098 |
ME | -0.096 |
方 | -0.094 |
psc | -0.093 |
Token | 've |
Token ID | 1053 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
Interstitial | +0.088 |
loc | +0.085 |
ME | +0.083 |
方 | +0.081 |
psc | +0.081 |
Neg logit contributions | |
ascript | -0.068 |
forgiven | -0.067 |
heads | -0.061 |
forgiveness | -0.058 |
perfection | -0.057 |
Token | But |
Token ID | 887 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Interstitial | +0.442 |
loc | +0.427 |
ME | +0.419 |
方 | +0.409 |
psc | +0.403 |
Neg logit contributions | |
ascript | -0.467 |
forgiven | -0.456 |
heads | -0.423 |
forgiveness | -0.403 |
perfection | -0.398 |
Token | Fox |
Token ID | 5426 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Interstitial | +1.110 |
loc | +1.086 |
ME | +1.060 |
方 | +1.039 |
psc | +1.020 |
Neg logit contributions | |
ascript | -0.926 |
forgiven | -0.897 |
heads | -0.820 |
forgiveness | -0.773 |
bull | -0.762 |
Token | News |
Token ID | 3000 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
ascript | +0.805 |
forgiven | +0.793 |
heads | +0.736 |
forgiveness | +0.683 |
perfection | +0.674 |
Neg logit contributions | |
Interstitial | -1.069 |
loc | -1.030 |
ME | -1.009 |
方 | -0.994 |
psc | -0.982 |
Token | / |
Token ID | 14 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Interstitial | +0.093 |
loc | +0.090 |
ME | +0.088 |
方 | +0.086 |
psc | +0.085 |
Neg logit contributions | |
ascript | -0.076 |
forgiven | -0.075 |
heads | -0.069 |
forgiveness | -0.065 |
perfection | -0.064 |
Token | O |
Token ID | 46 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
Interstitial | +1.108 |
loc | +1.079 |
ME | +1.057 |
方 | +1.023 |
psc | +1.006 |
Neg logit contributions | |
ascript | -1.175 |
forgiven | -1.153 |
heads | -1.069 |
forgiveness | -1.020 |
perfection | -1.004 |
Token | pin |
Token ID | 11635 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Interstitial | +0.123 |
loc | +0.117 |
ME | +0.115 |
方 | +0.114 |
psc | +0.112 |
Neg logit contributions | |
ascript | -0.093 |
forgiven | -0.091 |
heads | -0.085 |
forgiveness | -0.078 |
perfection | -0.077 |
Token | ion |
Token ID | 295 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ascript | +3.653 |
forgiven | +3.627 |
heads | +3.450 |
forgiveness | +3.294 |
perfection | +3.252 |
Neg logit contributions | |
Interstitial | -2.527 |
loc | -2.318 |
方 | -2.286 |
ME | -2.261 |
psc | -2.233 |
Token | Dynamics |
Token ID | 33806 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
ascript | +0.625 |
forgiven | +0.617 |
heads | +0.580 |
forgiveness | +0.552 |
perfection | +0.545 |
Neg logit contributions | |
Interstitial | -0.489 |
loc | -0.469 |
ME | -0.458 |
方 | -0.447 |
psc | -0.438 |
Token | did |
Token ID | 750 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ascript | +0.074 |
forgiven | +0.073 |
heads | +0.067 |
forgiveness | +0.064 |
perfection | +0.063 |
Neg logit contributions | |
Interstitial | -0.083 |
loc | -0.080 |
ME | -0.079 |
方 | -0.077 |
psc | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
Interstitial | +0.241 |
loc | +0.234 |
ME | +0.229 |
方 | +0.225 |
psc | +0.220 |
Neg logit contributions | |
ascript | -0.225 |
forgiven | -0.222 |
heads | -0.205 |
forgiveness | -0.194 |
perfection | -0.190 |
Token | poll |
Token ID | 3278 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
Interstitial | +0.150 |
loc | +0.146 |
ME | +0.143 |
方 | +0.141 |
psc | +0.139 |
Neg logit contributions | |
ascript | -0.110 |
forgiven | -0.107 |
heads | -0.097 |
forgiveness | -0.092 |
bull | -0.090 |
Token | er |
Token ID | 263 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ascript | +1.581 |
forgiven | +1.568 |
heads | +1.444 |
forgiveness | +1.350 |
bull | +1.338 |
Neg logit contributions | |
Interstitial | -2.143 |
loc | -2.046 |
ME | -2.015 |
方 | -2.004 |
psc | -1.955 |
Token | magnet |
Token ID | 19972 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
ascript | +0.725 |
forgiven | +0.723 |
heads | +0.684 |
forgiveness | +0.653 |
perfection | +0.648 |
Neg logit contributions | |
Interstitial | -0.497 |
loc | -0.468 |
ME | -0.457 |
方 | -0.450 |
psc | -0.440 |
Token | ? |
Token ID | 30 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Interstitial | +1.829 |
loc | +1.792 |
ME | +1.767 |
方 | +1.705 |
psc | +1.679 |
Neg logit contributions | |
ascript | -1.749 |
forgiven | -1.712 |
heads | -1.593 |
forgiveness | -1.490 |
perfection | -1.472 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
Interstitial | +0.448 |
loc | +0.432 |
ME | +0.426 |
方 | +0.414 |
psc | +0.409 |
Neg logit contributions | |
ascript | -0.437 |
forgiven | -0.430 |
heads | -0.400 |
forgiveness | -0.378 |
perfection | -0.373 |
Token |
|
Token ID | 198 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
Interstitial | +0.031 |
loc | +0.030 |
ME | +0.029 |
方 | +0.029 |
psc | +0.028 |
Neg logit contributions | |
ascript | -0.034 |
forgiven | -0.034 |
heads | -0.031 |
forgiveness | -0.030 |
perfection | -0.029 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Interstitial | +0.078 |
loc | +0.076 |
ME | +0.075 |
方 | +0.073 |
psc | +0.072 |
Neg logit contributions | |
ascript | -0.067 |
forgiven | -0.066 |
heads | -0.061 |
forgiveness | -0.058 |
perfection | -0.057 |
Token | : |
Token ID | 25 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ascript | +3.116 |
forgiven | +3.109 |
heads | +2.942 |
forgiveness | +2.759 |
perfection | +2.735 |
Neg logit contributions | |
Interstitial | -2.984 |
loc | -2.800 |
ME | -2.733 |
方 | -2.727 |
psc | -2.660 |
Token | hey |
Token ID | 17207 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Interstitial | +0.367 |
loc | +0.356 |
ME | +0.349 |
方 | +0.340 |
psc | +0.335 |
Neg logit contributions | |
ascript | -0.361 |
forgiven | -0.354 |
heads | -0.328 |
forgiveness | -0.311 |
perfection | -0.306 |
Token | _ |
Token ID | 62 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Interstitial | +0.196 |
loc | +0.191 |
ME | +0.187 |
方 | +0.182 |
psc | +0.180 |
Neg logit contributions | |
ascript | -0.186 |
forgiven | -0.183 |
heads | -0.169 |
forgiveness | -0.160 |
perfection | -0.158 |
Token | ler |
Token ID | 1754 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
Interstitial | +1.588 |
loc | +1.569 |
ME | +1.535 |
方 | +1.476 |
psc | +1.467 |
Neg logit contributions | |
ascript | -1.494 |
forgiven | -1.469 |
heads | -1.358 |
forgiveness | -1.291 |
perfection | -1.274 |
Token | oy |
Token ID | 726 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ascript | +1.221 |
forgiven | +1.201 |
heads | +1.119 |
forgiveness | +1.055 |
perfection | +1.042 |
Neg logit contributions | |
Interstitial | -1.265 |
loc | -1.216 |
ME | -1.193 |
方 | -1.173 |
psc | -1.150 |
Token | like |
Token ID | 588 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Interstitial | +1.007 |
loc | +0.987 |
ME | +0.970 |
方 | +0.950 |
psc | +0.935 |
Neg logit contributions | |
ascript | -0.706 |
forgiven | -0.688 |
heads | -0.622 |
forgiveness | -0.589 |
perfection | -0.571 |
Token | Warcraft |
Token ID | 26952 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
Interstitial | +0.491 |
loc | +0.473 |
ME | +0.463 |
方 | +0.453 |
psc | +0.445 |
Neg logit contributions | |
ascript | -0.524 |
forgiven | -0.517 |
heads | -0.482 |
forgiveness | -0.457 |
perfection | -0.451 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Interstitial | +1.931 |
loc | +1.879 |
ME | +1.849 |
方 | +1.806 |
psc | +1.776 |
Neg logit contributions | |
ascript | -1.719 |
forgiven | -1.679 |
heads | -1.539 |
forgiveness | -1.465 |
perfection | -1.430 |
Token | Age |
Token ID | 7129 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Interstitial | +0.252 |
loc | +0.243 |
ME | +0.238 |
方 | +0.233 |
psc | +0.229 |
Neg logit contributions | |
ascript | -0.254 |
forgiven | -0.250 |
heads | -0.233 |
forgiveness | -0.220 |
perfection | -0.217 |
Token | of |
Token ID | 286 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Interstitial | +1.399 |
loc | +1.373 |
ME | +1.351 |
方 | +1.322 |
psc | +1.309 |
Neg logit contributions | |
ascript | -0.817 |
forgiven | -0.802 |
heads | -0.724 |
forgiveness | -0.667 |
perfection | -0.655 |
Token | Empires |
Token ID | 35102 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Interstitial | +0.362 |
loc | +0.346 |
ME | +0.339 |
方 | +0.331 |
psc | +0.326 |
Neg logit contributions | |
ascript | -0.448 |
forgiven | -0.444 |
heads | -0.417 |
forgiveness | -0.396 |
perfection | -0.391 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Interstitial | +3.044 |
loc | +2.942 |
ME | +2.911 |
方 | +2.839 |
ordes | +2.783 |
Neg logit contributions | |
ascript | -3.149 |
forgiven | -3.101 |
heads | -2.834 |
forgiveness | -2.729 |
bull | -2.676 |
Token | many |
Token ID | 867 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Interstitial | +0.202 |
loc | +0.194 |
ME | +0.190 |
方 | +0.186 |
psc | +0.183 |
Neg logit contributions | |
ascript | -0.213 |
forgiven | -0.211 |
heads | -0.197 |
forgiveness | -0.186 |
perfection | -0.184 |
Token | RPGs |
Token ID | 46697 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
Interstitial | +1.027 |
loc | +0.995 |
ME | +0.972 |
方 | +0.951 |
psc | +0.933 |
Neg logit contributions | |
ascript | -1.044 |
forgiven | -1.028 |
heads | -0.953 |
forgiveness | -0.904 |
perfection | -0.889 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Interstitial | +1.710 |
loc | +1.676 |
ME | +1.652 |
方 | +1.615 |
psc | +1.590 |
Neg logit contributions | |
ascript | -1.138 |
forgiven | -1.109 |
heads | -0.999 |
forgiveness | -0.947 |
bull | -0.921 |
Token | You |
Token ID | 921 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Interstitial | +0.342 |
loc | +0.332 |
ME | +0.326 |
方 | +0.318 |
psc | +0.312 |
Neg logit contributions | |
ascript | -0.320 |
forgiven | -0.314 |
heads | -0.289 |
forgiveness | -0.275 |
perfection | -0.270 |
Token | insurers |
Token ID | 24668 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
Interstitial | +1.018 |
loc | +0.984 |
ME | +0.966 |
方 | +0.942 |
psc | +0.930 |
Neg logit contributions | |
ascript | -0.979 |
forgiven | -0.958 |
heads | -0.883 |
forgiveness | -0.837 |
perfection | -0.825 |
Token | United |
Token ID | 1578 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ascript | +0.093 |
forgiven | +0.092 |
heads | +0.084 |
forgiveness | +0.079 |
perfection | +0.077 |
Neg logit contributions | |
Interstitial | -0.131 |
loc | -0.127 |
ME | -0.125 |
方 | -0.123 |
psc | -0.121 |
Token | Health |
Token ID | 18081 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
ascript | +0.487 |
forgiven | +0.482 |
heads | +0.456 |
forgiveness | +0.435 |
perfection | +0.431 |
Neg logit contributions | |
Interstitial | -0.301 |
loc | -0.286 |
ME | -0.278 |
方 | -0.271 |
psc | -0.265 |
Token | Group |
Token ID | 4912 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Interstitial | +0.433 |
loc | +0.414 |
ME | +0.405 |
方 | +0.389 |
psc | +0.382 |
Neg logit contributions | |
ascript | -0.707 |
forgiven | -0.695 |
heads | -0.656 |
forgiveness | -0.631 |
perfection | -0.623 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
ascript | +0.295 |
forgiven | +0.290 |
heads | +0.268 |
forgiveness | +0.252 |
perfection | +0.248 |
Neg logit contributions | |
Interstitial | -0.361 |
loc | -0.349 |
ME | -0.342 |
方 | -0.336 |
psc | -0.331 |
Token | Hum |
Token ID | 11054 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ascript | +0.080 |
forgiven | +0.079 |
heads | +0.073 |
forgiveness | +0.070 |
perfection | +0.069 |
Neg logit contributions | |
Interstitial | -0.075 |
loc | -0.072 |
ME | -0.071 |
方 | -0.069 |
psc | -0.068 |
Token | ana |
Token ID | 2271 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
loc | +2.093 |
Interstitial | +2.061 |
ME | +2.001 |
psc | +1.920 |
方 | +1.836 |
Neg logit contributions | |
ascript | -3.689 |
forgiven | -3.631 |
heads | -3.428 |
forgiveness | -3.308 |
perfection | -3.298 |
Token | and |
Token ID | 290 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
Interstitial | +0.306 |
loc | +0.294 |
ME | +0.290 |
方 | +0.281 |
psc | +0.278 |
Neg logit contributions | |
ascript | -0.320 |
forgiven | -0.315 |
heads | -0.293 |
forgiveness | -0.278 |
perfection | -0.275 |
Token | A |
Token ID | 317 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
ascript | +0.139 |
forgiven | +0.138 |
heads | +0.129 |
forgiveness | +0.122 |
perfection | +0.120 |
Neg logit contributions | |
Interstitial | -0.133 |
loc | -0.128 |
ME | -0.125 |
方 | -0.123 |
psc | -0.120 |
Token | et |
Token ID | 316 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
ascript | +0.108 |
forgiven | +0.106 |
heads | +0.099 |
forgiveness | +0.094 |
perfection | +0.092 |
Neg logit contributions | |
Interstitial | -0.105 |
loc | -0.101 |
ME | -0.099 |
方 | -0.096 |
psc | -0.095 |
Token | na |
Token ID | 2616 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
Interstitial | +0.223 |
loc | +0.218 |
ME | +0.216 |
方 | +0.210 |
psc | +0.210 |
Neg logit contributions | |
ascript | -0.086 |
forgiven | -0.083 |
heads | -0.073 |
forgiveness | -0.066 |
perfection | -0.063 |
Token | where |
Token ID | 810 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Interstitial | +0.659 |
loc | +0.644 |
ME | +0.634 |
方 | +0.617 |
psc | +0.609 |
Neg logit contributions | |
ascript | -0.530 |
forgiven | -0.515 |
heads | -0.470 |
forgiveness | -0.448 |
perfection | -0.437 |
Token | many |
Token ID | 867 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Interstitial | +0.396 |
loc | +0.386 |
ME | +0.377 |
方 | +0.368 |
psc | +0.362 |
Neg logit contributions | |
ascript | -0.381 |
forgiven | -0.372 |
heads | -0.342 |
forgiveness | -0.324 |
bull | -0.319 |
Token | workers |
Token ID | 3259 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Interstitial | +1.418 |
loc | +1.387 |
ME | +1.356 |
方 | +1.325 |
psc | +1.314 |
Neg logit contributions | |
ascript | -1.032 |
forgiven | -0.999 |
heads | -0.897 |
forgiveness | -0.856 |
perfection | -0.839 |
Token | drive |
Token ID | 3708 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
Interstitial | +1.103 |
loc | +1.080 |
ME | +1.057 |
方 | +1.031 |
psc | +1.023 |
Neg logit contributions | |
ascript | -0.895 |
forgiven | -0.876 |
heads | -0.799 |
forgiveness | -0.761 |
perfection | -0.744 |
Token | long |
Token ID | 890 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Interstitial | +1.645 |
loc | +1.627 |
ME | +1.574 |
方 | +1.530 |
psc | +1.508 |
Neg logit contributions | |
ascript | -1.480 |
forgiven | -1.434 |
heads | -1.295 |
forgiveness | -1.249 |
bull | -1.228 |
Token | distances |
Token ID | 18868 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Interstitial | +0.421 |
loc | +0.401 |
ME | +0.386 |
方 | +0.371 |
psc | +0.362 |
Neg logit contributions | |
ascript | -0.928 |
forgiven | -0.919 |
heads | -0.870 |
forgiveness | -0.839 |
perfection | -0.830 |
Token | to |
Token ID | 284 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
loc | +3.131 |
Interstitial | +3.104 |
ME | +3.015 |
方 | +2.954 |
psc | +2.909 |
Neg logit contributions | |
ascript | -2.599 |
forgiven | -2.472 |
heads | -2.212 |
forgiveness | -2.156 |
bull | -2.148 |
Token | jobs |
Token ID | 3946 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Interstitial | +0.252 |
loc | +0.244 |
ME | +0.239 |
方 | +0.235 |
psc | +0.231 |
Neg logit contributions | |
ascript | -0.216 |
forgiven | -0.213 |
heads | -0.197 |
forgiveness | -0.185 |
perfection | -0.183 |
Token | that |
Token ID | 326 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
Interstitial | +1.492 |
loc | +1.479 |
ME | +1.445 |
方 | +1.401 |
psc | +1.388 |
Neg logit contributions | |
ascript | -1.284 |
forgiven | -1.238 |
heads | -1.137 |
forgiveness | -1.076 |
bull | -1.058 |
Token | pay |
Token ID | 1414 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ascript | +0.159 |
forgiven | +0.158 |
heads | +0.146 |
forgiveness | +0.138 |
perfection | +0.136 |
Neg logit contributions | |
Interstitial | -0.185 |
loc | -0.177 |
ME | -0.174 |
方 | -0.171 |
psc | -0.168 |
Token | $ |
Token ID | 720 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ascript | +0.744 |
forgiven | +0.732 |
heads | +0.677 |
forgiveness | +0.638 |
perfection | +0.628 |
Neg logit contributions | |
Interstitial | -0.853 |
loc | -0.827 |
ME | -0.810 |
方 | -0.794 |
psc | -0.782 |
Token | maps |
Token ID | 8739 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Interstitial | +0.098 |
loc | +0.095 |
ME | +0.093 |
方 | +0.091 |
psc | +0.090 |
Neg logit contributions | |
ascript | -0.086 |
forgiven | -0.084 |
heads | -0.078 |
forgiveness | -0.074 |
perfection | -0.073 |
Token | exclusive |
Token ID | 8568 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ascript | +0.926 |
forgiven | +0.912 |
heads | +0.841 |
forgiveness | +0.790 |
perfection | +0.777 |
Neg logit contributions | |
Interstitial | -1.141 |
loc | -1.104 |
ME | -1.083 |
方 | -1.063 |
psc | -1.048 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ascript | +0.374 |
forgiven | +0.366 |
heads | +0.334 |
forgiveness | +0.314 |
perfection | +0.307 |
Neg logit contributions | |
Interstitial | -0.521 |
loc | -0.507 |
ME | -0.496 |
方 | -0.487 |
psc | -0.480 |
Token | Halo |
Token ID | 18597 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Interstitial | +0.022 |
loc | +0.022 |
ME | +0.021 |
方 | +0.021 |
psc | +0.020 |
Neg logit contributions | |
ascript | -0.025 |
forgiven | -0.024 |
heads | -0.023 |
forgiveness | -0.021 |
perfection | -0.021 |
Token | : |
Token ID | 25 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Interstitial | +0.554 |
loc | +0.538 |
ME | +0.529 |
方 | +0.513 |
psc | +0.502 |
Neg logit contributions | |
ascript | -0.657 |
forgiven | -0.639 |
heads | -0.593 |
forgiveness | -0.568 |
bull | -0.559 |
Token | Combat |
Token ID | 14487 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Interstitial | +0.287 |
loc | +0.275 |
ME | +0.271 |
方 | +0.262 |
psc | +0.257 |
Neg logit contributions | |
ascript | -0.391 |
forgiven | -0.386 |
heads | -0.361 |
forgiveness | -0.346 |
perfection | -0.341 |
Token | Ev |
Token ID | 4319 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
Interstitial | +2.029 |
loc | +1.949 |
ME | +1.889 |
方 | +1.825 |
psc | +1.786 |
Neg logit contributions | |
ascript | -3.725 |
forgiven | -3.647 |
heads | -3.438 |
forgiveness | -3.313 |
perfection | -3.273 |
Token | olved |
Token ID | 5634 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ascript | +0.141 |
forgiven | +0.139 |
heads | +0.128 |
forgiveness | +0.121 |
perfection | +0.118 |
Neg logit contributions | |
Interstitial | -0.188 |
loc | -0.184 |
ME | -0.181 |
方 | -0.176 |
psc | -0.175 |
Token | PC |
Token ID | 4217 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
ascript | +1.089 |
forgiven | +1.076 |
heads | +0.993 |
forgiveness | +0.928 |
perfection | +0.913 |
Neg logit contributions | |
Interstitial | -1.410 |
loc | -1.365 |
ME | -1.338 |
方 | -1.317 |
psc | -1.300 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Interstitial | +1.235 |
loc | +1.203 |
ME | +1.198 |
方 | +1.156 |
psc | +1.138 |
Neg logit contributions | |
ascript | -0.891 |
forgiven | -0.860 |
heads | -0.779 |
forgiveness | -0.736 |
bull | -0.720 |
Token | Taking |
Token ID | 20879 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Interstitial | +0.324 |
loc | +0.314 |
ME | +0.307 |
方 | +0.298 |
psc | +0.295 |
Neg logit contributions | |
ascript | -0.349 |
forgiven | -0.342 |
heads | -0.317 |
forgiveness | -0.302 |
perfection | -0.297 |
Token | Sach |
Token ID | 20678 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
Interstitial | +0.299 |
loc | +0.289 |
ME | +0.283 |
方 | +0.274 |
psc | +0.270 |
Neg logit contributions | |
ascript | -0.365 |
forgiven | -0.359 |
heads | -0.332 |
forgiveness | -0.319 |
perfection | -0.314 |
Token | dev |
Token ID | 7959 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Interstitial | +1.366 |
loc | +1.345 |
ME | +1.311 |
psc | +1.277 |
方 | +1.257 |
Neg logit contributions | |
ascript | -1.355 |
forgiven | -1.343 |
heads | -1.230 |
forgiveness | -1.183 |
perfection | -1.153 |
Token | is |
Token ID | 318 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ascript | +0.696 |
forgiven | +0.687 |
heads | +0.641 |
forgiveness | +0.596 |
perfection | +0.588 |
Neg logit contributions | |
Interstitial | -0.856 |
loc | -0.825 |
ME | -0.809 |
方 | -0.795 |
psc | -0.784 |
Token | a |
Token ID | 257 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Interstitial | +0.191 |
loc | +0.186 |
ME | +0.182 |
方 | +0.177 |
psc | +0.174 |
Neg logit contributions | |
ascript | -0.209 |
forgiven | -0.205 |
heads | -0.190 |
forgiveness | -0.181 |
perfection | -0.178 |
Token | Dist |
Token ID | 4307 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
Interstitial | +0.284 |
loc | +0.276 |
ME | +0.270 |
方 | +0.265 |
psc | +0.261 |
Neg logit contributions | |
ascript | -0.254 |
forgiven | -0.248 |
heads | -0.228 |
forgiveness | -0.216 |
perfection | -0.212 |
Token | inguished |
Token ID | 46709 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Interstitial | +0.418 |
loc | +0.406 |
ME | +0.392 |
方 | +0.365 |
psc | +0.360 |
Neg logit contributions | |
ascript | -1.018 |
forgiven | -1.009 |
heads | -0.952 |
forgiveness | -0.925 |
perfection | -0.922 |
Token | Research |
Token ID | 4992 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Interstitial | +2.408 |
loc | +2.341 |
ME | +2.300 |
方 | +2.204 |
psc | +2.155 |
Neg logit contributions | |
ascript | -3.194 |
forgiven | -3.085 |
heads | -2.880 |
forgiveness | -2.772 |
perfection | -2.730 |
Token | Vis |
Token ID | 6911 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
ascript | +0.243 |
forgiven | +0.242 |
heads | +0.226 |
forgiveness | +0.213 |
perfection | +0.210 |
Neg logit contributions | |
Interstitial | -0.251 |
loc | -0.240 |
ME | -0.234 |
方 | -0.231 |
psc | -0.228 |
Token | iting |
Token ID | 1780 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ascript | +0.121 |
forgiven | +0.119 |
heads | +0.109 |
forgiveness | +0.102 |
perfection | +0.100 |
Neg logit contributions | |
Interstitial | -0.173 |
loc | -0.169 |
ME | -0.166 |
方 | -0.161 |
psc | -0.161 |
Token | Chair |
Token ID | 9369 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
ascript | +0.314 |
forgiven | +0.312 |
heads | +0.294 |
forgiveness | +0.278 |
perfection | +0.275 |
Neg logit contributions | |
Interstitial | -0.274 |
loc | -0.262 |
ME | -0.256 |
方 | -0.251 |
psc | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Interstitial | +1.058 |
loc | +1.037 |
ME | +1.018 |
方 | +0.992 |
psc | +0.977 |
Neg logit contributions | |
ascript | -0.690 |
forgiven | -0.678 |
heads | -0.612 |
forgiveness | -0.572 |
perfection | -0.564 |
Token | acoustic |
Token ID | 26071 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Interstitial | +0.107 |
loc | +0.103 |
ME | +0.101 |
方 | +0.099 |
psc | +0.098 |
Neg logit contributions | |
ascript | -0.085 |
forgiven | -0.083 |
heads | -0.077 |
forgiveness | -0.072 |
perfection | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
Interstitial | +1.355 |
loc | +1.318 |
ME | +1.290 |
方 | +1.265 |
psc | +1.251 |
Neg logit contributions | |
ascript | -1.066 |
forgiven | -1.030 |
heads | -0.931 |
forgiveness | -0.886 |
bull | -0.861 |
Token | with |
Token ID | 351 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Interstitial | +0.171 |
loc | +0.166 |
ME | +0.163 |
方 | +0.159 |
psc | +0.158 |
Neg logit contributions | |
ascript | -0.131 |
forgiven | -0.126 |
heads | -0.115 |
forgiveness | -0.109 |
bull | -0.107 |
Token | lots |
Token ID | 6041 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
ascript | +0.406 |
forgiven | +0.399 |
heads | +0.368 |
forgiveness | +0.348 |
perfection | +0.343 |
Neg logit contributions | |
Interstitial | -0.442 |
loc | -0.428 |
ME | -0.420 |
方 | -0.411 |
psc | -0.404 |
Token | of |
Token ID | 286 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ascript | +0.045 |
forgiven | +0.043 |
heads | +0.039 |
forgiveness | +0.036 |
perfection | +0.035 |
Neg logit contributions | |
Interstitial | -0.076 |
loc | -0.074 |
ME | -0.073 |
方 | -0.071 |
psc | -0.071 |
Token | string |
Token ID | 4731 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Interstitial | +0.597 |
loc | +0.582 |
ME | +0.569 |
方 | +0.556 |
psc | +0.545 |
Neg logit contributions | |
ascript | -0.553 |
forgiven | -0.533 |
heads | -0.488 |
forgiveness | -0.463 |
bull | -0.457 |
Token | ed |
Token ID | 276 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
Interstitial | +2.769 |
loc | +2.757 |
ME | +2.669 |
方 | +2.572 |
psc | +2.550 |
Neg logit contributions | |
ascript | -2.756 |
forgiven | -2.667 |
heads | -2.442 |
forgiveness | -2.346 |
bull | -2.299 |
Token | instruments |
Token ID | 12834 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Interstitial | +0.051 |
loc | +0.049 |
ME | +0.048 |
方 | +0.047 |
psc | +0.046 |
Neg logit contributions | |
ascript | -0.052 |
forgiven | -0.051 |
heads | -0.047 |
forgiveness | -0.045 |
perfection | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
Interstitial | +0.796 |
loc | +0.780 |
ME | +0.761 |
方 | +0.747 |
psc | +0.740 |
Neg logit contributions | |
ascript | -0.613 |
forgiven | -0.589 |
heads | -0.538 |
forgiveness | -0.514 |
perfection | -0.500 |
Token | It |
Token ID | 632 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
Interstitial | +0.178 |
loc | +0.173 |
ME | +0.169 |
方 | +0.165 |
psc | +0.163 |
Neg logit contributions | |
ascript | -0.177 |
forgiven | -0.174 |
heads | -0.161 |
forgiveness | -0.153 |
perfection | -0.150 |
Token | was |
Token ID | 373 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
Interstitial | +0.008 |
loc | +0.008 |
ME | +0.007 |
方 | +0.007 |
psc | +0.007 |
Neg logit contributions | |
ascript | -0.007 |
forgiven | -0.007 |
heads | -0.007 |
forgiveness | -0.006 |
perfection | -0.006 |
Token | glers |
Token ID | 33641 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Interstitial | +0.439 |
loc | +0.420 |
ME | +0.401 |
方 | +0.388 |
psc | +0.376 |
Neg logit contributions | |
ascript | -1.008 |
forgiven | -0.997 |
heads | -0.940 |
forgiveness | -0.912 |
perfection | -0.902 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Interstitial | +0.334 |
loc | +0.323 |
ME | +0.316 |
方 | +0.309 |
psc | +0.305 |
Neg logit contributions | |
ascript | -0.329 |
forgiven | -0.323 |
heads | -0.299 |
forgiveness | -0.285 |
perfection | -0.279 |
Token | the |
Token ID | 262 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
Interstitial | +0.202 |
loc | +0.195 |
ME | +0.191 |
方 | +0.187 |
psc | +0.184 |
Neg logit contributions | |
ascript | -0.198 |
forgiven | -0.194 |
heads | -0.179 |
forgiveness | -0.170 |
perfection | -0.167 |
Token | crazy |
Token ID | 7165 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Interstitial | +0.160 |
loc | +0.155 |
ME | +0.152 |
方 | +0.149 |
psc | +0.147 |
Neg logit contributions | |
ascript | -0.134 |
forgiven | -0.132 |
heads | -0.121 |
forgiveness | -0.114 |
perfection | -0.112 |
Token | ac |
Token ID | 936 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ascript | +0.957 |
forgiven | +0.947 |
heads | +0.884 |
forgiveness | +0.822 |
perfection | +0.814 |
Neg logit contributions | |
Interstitial | -1.179 |
loc | -1.135 |
ME | -1.116 |
方 | -1.097 |
psc | -1.081 |
Token | robat |
Token ID | 40655 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ascript | +0.571 |
forgiven | +0.563 |
heads | +0.530 |
forgiveness | +0.501 |
perfection | +0.496 |
Neg logit contributions | |
Interstitial | -0.486 |
loc | -0.463 |
ME | -0.454 |
方 | -0.447 |
psc | -0.436 |
Token | ics |
Token ID | 873 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
Interstitial | +2.850 |
loc | +2.782 |
ME | +2.674 |
方 | +2.618 |
psc | +2.586 |
Neg logit contributions | |
ascript | -2.703 |
forgiven | -2.645 |
heads | -2.378 |
forgiveness | -2.324 |
bull | -2.250 |
Token | – |
Token ID | 784 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Interstitial | +1.284 |
loc | +1.256 |
ME | +1.228 |
方 | +1.200 |
psc | +1.191 |
Neg logit contributions | |
ascript | -1.069 |
forgiven | -1.034 |
heads | -0.938 |
forgiveness | -0.900 |
bull | -0.873 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
ascript | +0.357 |
forgiven | +0.350 |
heads | +0.322 |
forgiveness | +0.303 |
perfection | +0.298 |
Neg logit contributions | |
Interstitial | -0.445 |
loc | -0.432 |
ME | -0.423 |
方 | -0.415 |
psc | -0.409 |
Token | you |
Token ID | 345 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Interstitial | +0.675 |
loc | +0.654 |
ME | +0.642 |
方 | +0.628 |
psc | +0.619 |
Neg logit contributions | |
ascript | -0.558 |
forgiven | -0.545 |
heads | -0.500 |
forgiveness | -0.471 |
bull | -0.462 |
Token | get |
Token ID | 651 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Interstitial | +0.415 |
loc | +0.403 |
ME | +0.395 |
方 | +0.388 |
psc | +0.384 |
Neg logit contributions | |
ascript | -0.306 |
forgiven | -0.297 |
heads | -0.273 |
forgiveness | -0.256 |
perfection | -0.250 |
Token | privacy |
Token ID | 6782 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
Interstitial | +0.075 |
loc | +0.073 |
ME | +0.071 |
方 | +0.070 |
psc | +0.069 |
Neg logit contributions | |
ascript | -0.069 |
forgiven | -0.068 |
heads | -0.063 |
forgiveness | -0.060 |
perfection | -0.059 |
Token | component |
Token ID | 7515 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
Interstitial | +0.026 |
loc | +0.025 |
ME | +0.025 |
方 | +0.024 |
psc | +0.024 |
Neg logit contributions | |
ascript | -0.029 |
forgiven | -0.028 |
heads | -0.026 |
forgiveness | -0.025 |
perfection | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Interstitial | +1.738 |
loc | +1.703 |
ME | +1.681 |
方 | +1.647 |
psc | +1.619 |
Neg logit contributions | |
ascript | -1.105 |
forgiven | -1.092 |
heads | -0.986 |
forgiveness | -0.923 |
perfection | -0.905 |
Token | the |
Token ID | 262 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
ascript | +0.240 |
forgiven | +0.238 |
heads | +0.222 |
forgiveness | +0.210 |
perfection | +0.207 |
Neg logit contributions | |
Interstitial | -0.239 |
loc | -0.230 |
ME | -0.224 |
方 | -0.220 |
psc | -0.218 |
Token | original |
Token ID | 2656 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Interstitial | +0.049 |
loc | +0.048 |
ME | +0.046 |
方 | +0.045 |
psc | +0.045 |
Neg logit contributions | |
ascript | -0.054 |
forgiven | -0.053 |
heads | -0.050 |
forgiveness | -0.047 |
perfection | -0.047 |
Token | IEEE |
Token ID | 40552 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Interstitial | +0.656 |
loc | +0.633 |
ME | +0.620 |
方 | +0.605 |
psc | +0.596 |
Neg logit contributions | |
ascript | -0.701 |
forgiven | -0.691 |
heads | -0.644 |
forgiveness | -0.611 |
perfection | -0.602 |
Token | 802 |
Token ID | 33121 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Interstitial | +2.446 |
loc | +2.411 |
ME | +2.385 |
方 | +2.290 |
ordes | +2.227 |
Neg logit contributions | |
ascript | -2.982 |
forgiven | -2.950 |
heads | -2.705 |
forgiveness | -2.601 |
bull | -2.566 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Interstitial | +0.773 |
loc | +0.763 |
ME | +0.752 |
方 | +0.731 |
psc | +0.726 |
Neg logit contributions | |
ascript | -0.445 |
forgiven | -0.434 |
heads | -0.389 |
forgiveness | -0.361 |
perfection | -0.351 |
Token | 11 |
Token ID | 1157 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
Interstitial | +0.206 |
loc | +0.197 |
ME | +0.192 |
方 | +0.187 |
psc | +0.183 |
Neg logit contributions | |
ascript | -0.286 |
forgiven | -0.282 |
heads | -0.266 |
forgiveness | -0.254 |
perfection | -0.251 |
Token | standard |
Token ID | 3210 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Interstitial | +0.846 |
loc | +0.821 |
ME | +0.802 |
方 | +0.782 |
psc | +0.768 |
Neg logit contributions | |
ascript | -0.953 |
forgiven | -0.943 |
heads | -0.876 |
forgiveness | -0.834 |
perfection | -0.821 |
Token | ratified |
Token ID | 39067 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Interstitial | +0.575 |
loc | +0.565 |
ME | +0.553 |
方 | +0.541 |
psc | +0.533 |
Neg logit contributions | |
ascript | -0.440 |
forgiven | -0.431 |
heads | -0.393 |
forgiveness | -0.371 |
perfection | -0.363 |
Token | man |
Token ID | 805 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Interstitial | +1.115 |
loc | +1.093 |
ME | +1.071 |
方 | +1.035 |
psc | +1.028 |
Neg logit contributions | |
ascript | -1.073 |
forgiven | -1.063 |
heads | -0.979 |
forgiveness | -0.939 |
perfection | -0.922 |
Token | and |
Token ID | 290 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
ascript | +0.629 |
forgiven | +0.619 |
heads | +0.570 |
forgiveness | +0.532 |
perfection | +0.523 |
Neg logit contributions | |
Interstitial | -0.844 |
loc | -0.817 |
ME | -0.803 |
方 | -0.788 |
psc | -0.777 |
Token | her |
Token ID | 607 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
Interstitial | +0.074 |
loc | +0.072 |
ME | +0.071 |
方 | +0.069 |
psc | +0.068 |
Neg logit contributions | |
ascript | -0.057 |
forgiven | -0.055 |
heads | -0.050 |
forgiveness | -0.047 |
perfection | -0.047 |
Token | student |
Token ID | 3710 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
Interstitial | +0.184 |
loc | +0.179 |
ME | +0.175 |
方 | +0.171 |
psc | +0.169 |
Neg logit contributions | |
ascript | -0.158 |
forgiven | -0.155 |
heads | -0.143 |
forgiveness | -0.135 |
perfection | -0.132 |
Token | Andrea |
Token ID | 23174 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
ascript | +0.111 |
forgiven | +0.109 |
heads | +0.100 |
forgiveness | +0.095 |
perfection | +0.093 |
Neg logit contributions | |
Interstitial | -0.127 |
loc | -0.123 |
ME | -0.121 |
方 | -0.118 |
psc | -0.117 |
Token | Morrow |
Token ID | 34693 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Interstitial | +0.894 |
loc | +0.868 |
ME | +0.849 |
方 | +0.826 |
psc | +0.815 |
Neg logit contributions | |
ascript | -0.976 |
forgiven | -0.962 |
heads | -0.890 |
forgiveness | -0.849 |
perfection | -0.839 |
Token | , |
Token ID | 11 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
Interstitial | +2.964 |
loc | +2.961 |
ME | +2.859 |
方 | +2.804 |
psc | +2.785 |
Neg logit contributions | |
ascript | -2.353 |
forgiven | -2.339 |
heads | -2.084 |
forgiveness | -2.041 |
perfection | -1.997 |
Token | from |
Token ID | 422 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Interstitial | +0.118 |
loc | +0.116 |
ME | +0.113 |
方 | +0.111 |
psc | +0.109 |
Neg logit contributions | |
ascript | -0.076 |
forgiven | -0.073 |
heads | -0.065 |
forgiveness | -0.062 |
perfection | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
ascript | +0.251 |
forgiven | +0.248 |
heads | +0.232 |
forgiveness | +0.220 |
perfection | +0.217 |
Neg logit contributions | |
Interstitial | -0.231 |
loc | -0.222 |
ME | -0.218 |
方 | -0.213 |
psc | -0.209 |
Token | Grand |
Token ID | 5675 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Interstitial | +0.081 |
loc | +0.078 |
ME | +0.076 |
方 | +0.074 |
psc | +0.072 |
Neg logit contributions | |
ascript | -0.118 |
forgiven | -0.116 |
heads | -0.109 |
forgiveness | -0.105 |
perfection | -0.104 |
Token | Valley |
Token ID | 6916 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
Interstitial | +0.335 |
loc | +0.324 |
ME | +0.317 |
方 | +0.310 |
psc | +0.304 |
Neg logit contributions | |
ascript | -0.356 |
forgiven | -0.349 |
heads | -0.327 |
forgiveness | -0.309 |
perfection | -0.306 |
Token | up |
Token ID | 510 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Interstitial | +1.036 |
loc | +1.029 |
ME | +1.001 |
方 | +0.972 |
psc | +0.963 |
Neg logit contributions | |
ascript | -0.793 |
forgiven | -0.767 |
heads | -0.695 |
forgiveness | -0.658 |
perfection | -0.649 |
Token | with |
Token ID | 351 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ascript | +0.187 |
forgiven | +0.183 |
heads | +0.165 |
forgiveness | +0.156 |
perfection | +0.153 |
Neg logit contributions | |
Interstitial | -0.256 |
loc | -0.251 |
ME | -0.245 |
方 | -0.240 |
psc | -0.236 |
Token | the |
Token ID | 262 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
ascript | +0.227 |
forgiven | +0.223 |
heads | +0.207 |
forgiveness | +0.195 |
perfection | +0.192 |
Neg logit contributions | |
Interstitial | -0.245 |
loc | -0.238 |
ME | -0.233 |
方 | -0.228 |
psc | -0.224 |
Token | English |
Token ID | 3594 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
Interstitial | +0.122 |
loc | +0.118 |
ME | +0.116 |
方 | +0.114 |
psc | +0.112 |
Neg logit contributions | |
ascript | -0.109 |
forgiven | -0.107 |
heads | -0.099 |
forgiveness | -0.094 |
perfection | -0.092 |
Token | dead |
Token ID | 2636 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
ascript | +0.123 |
forgiven | +0.121 |
heads | +0.111 |
forgiveness | +0.104 |
perfection | +0.103 |
Neg logit contributions | |
Interstitial | -0.152 |
loc | -0.147 |
ME | -0.144 |
方 | -0.141 |
psc | -0.139 |
Token | ,' |
Token ID | 4032 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Interstitial | +1.222 |
loc | +1.195 |
ME | +1.157 |
方 | +1.132 |
ordes | +1.119 |
Neg logit contributions | |
ascript | -0.999 |
forgiven | -0.952 |
heads | -0.868 |
forgiveness | -0.832 |
perfection | -0.825 |
Token | said |
Token ID | 531 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Interstitial | +2.733 |
loc | +2.696 |
ME | +2.634 |
方 | +2.536 |
ordes | +2.508 |
Neg logit contributions | |
ascript | -2.651 |
forgiven | -2.516 |
heads | -2.290 |
forgiveness | -2.220 |
perfection | -2.176 |
Token | one |
Token ID | 530 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
ascript | +0.207 |
forgiven | +0.204 |
heads | +0.189 |
forgiveness | +0.179 |
perfection | +0.177 |
Neg logit contributions | |
Interstitial | -0.207 |
loc | -0.200 |
ME | -0.196 |
方 | -0.192 |
psc | -0.189 |
Token | SNP |
Token ID | 25632 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ascript | +0.094 |
forgiven | +0.092 |
heads | +0.084 |
forgiveness | +0.079 |
perfection | +0.078 |
Neg logit contributions | |
Interstitial | -0.117 |
loc | -0.115 |
ME | -0.112 |
方 | -0.110 |
psc | -0.108 |
Token | insider |
Token ID | 25851 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
Interstitial | +0.406 |
loc | +0.396 |
ME | +0.388 |
方 | +0.379 |
psc | +0.373 |
Neg logit contributions | |
ascript | -0.337 |
forgiven | -0.329 |
heads | -0.302 |
forgiveness | -0.285 |
perfection | -0.280 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Interstitial | +0.061 |
loc | +0.059 |
ME | +0.058 |
方 | +0.057 |
psc | +0.056 |
Neg logit contributions | |
ascript | -0.039 |
forgiven | -0.038 |
heads | -0.034 |
forgiveness | -0.032 |
perfection | -0.031 |
Token | is |
Token ID | 318 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
Interstitial | +0.259 |
loc | +0.252 |
ME | +0.248 |
方 | +0.241 |
psc | +0.238 |
Neg logit contributions | |
ascript | -0.254 |
forgiven | -0.249 |
heads | -0.230 |
forgiveness | -0.219 |
perfection | -0.215 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Interstitial | +0.104 |
loc | +0.100 |
ME | +0.098 |
方 | +0.096 |
psc | +0.094 |
Neg logit contributions | |
ascript | -0.105 |
forgiven | -0.103 |
heads | -0.096 |
forgiveness | -0.091 |
perfection | -0.090 |
Token | security |
Token ID | 2324 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Interstitial | +0.275 |
loc | +0.267 |
ME | +0.262 |
方 | +0.257 |
psc | +0.253 |
Neg logit contributions | |
ascript | -0.225 |
forgiven | -0.221 |
heads | -0.203 |
forgiveness | -0.191 |
perfection | -0.188 |
Token | algorithm |
Token ID | 11862 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Interstitial | +0.322 |
loc | +0.312 |
ME | +0.307 |
方 | +0.301 |
psc | +0.297 |
Neg logit contributions | |
ascript | -0.267 |
forgiven | -0.262 |
heads | -0.241 |
forgiveness | -0.226 |
perfection | -0.222 |
Token | for |
Token ID | 329 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Interstitial | +0.259 |
loc | +0.253 |
ME | +0.250 |
方 | +0.243 |
psc | +0.241 |
Neg logit contributions | |
ascript | -0.177 |
forgiven | -0.174 |
heads | -0.158 |
forgiveness | -0.147 |
bull | -0.144 |
Token | IEEE |
Token ID | 40552 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Interstitial | +0.345 |
loc | +0.334 |
ME | +0.327 |
方 | +0.321 |
psc | +0.316 |
Neg logit contributions | |
ascript | -0.300 |
forgiven | -0.296 |
heads | -0.274 |
forgiveness | -0.258 |
perfection | -0.254 |
Token | 802 |
Token ID | 33121 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
loc | +2.381 |
Interstitial | +2.376 |
ME | +2.359 |
方 | +2.233 |
ordes | +2.212 |
Neg logit contributions | |
ascript | -2.882 |
forgiven | -2.869 |
heads | -2.602 |
forgiveness | -2.514 |
bull | -2.485 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Interstitial | +0.587 |
loc | +0.574 |
ME | +0.565 |
方 | +0.554 |
psc | +0.549 |
Neg logit contributions | |
ascript | -0.315 |
forgiven | -0.308 |
heads | -0.277 |
forgiveness | -0.255 |
perfection | -0.248 |
Token | 11 |
Token ID | 1157 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Interstitial | +0.182 |
loc | +0.173 |
ME | +0.168 |
方 | +0.166 |
psc | +0.161 |
Neg logit contributions | |
ascript | -0.234 |
forgiven | -0.232 |
heads | -0.218 |
forgiveness | -0.208 |
perfection | -0.205 |
Token | wireless |
Token ID | 12521 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
Interstitial | +1.036 |
loc | +1.003 |
ME | +0.982 |
方 | +0.958 |
psc | +0.946 |
Neg logit contributions | |
ascript | -1.043 |
forgiven | -1.029 |
heads | -0.955 |
forgiveness | -0.905 |
perfection | -0.891 |
Token | networks |
Token ID | 7686 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
Interstitial | +0.119 |
loc | +0.115 |
ME | +0.113 |
方 | +0.110 |
psc | +0.109 |
Neg logit contributions | |
ascript | -0.119 |
forgiven | -0.117 |
heads | -0.107 |
forgiveness | -0.102 |
perfection | -0.100 |
Token | for |
Token ID | 329 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
ascript | +0.408 |
forgiven | +0.402 |
heads | +0.372 |
forgiveness | +0.351 |
perfection | +0.346 |
Neg logit contributions | |
Interstitial | -0.443 |
loc | -0.429 |
ME | -0.420 |
方 | -0.412 |
psc | -0.405 |
Token | international |
Token ID | 3230 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
Interstitial | +0.137 |
loc | +0.132 |
ME | +0.129 |
方 | +0.127 |
psc | +0.125 |
Neg logit contributions | |
ascript | -0.134 |
forgiven | -0.132 |
heads | -0.123 |
forgiveness | -0.116 |
perfection | -0.114 |
Token | freedom |
Token ID | 4925 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Interstitial | +0.126 |
loc | +0.123 |
ME | +0.120 |
方 | +0.118 |
psc | +0.116 |
Neg logit contributions | |
ascript | -0.101 |
forgiven | -0.099 |
heads | -0.089 |
forgiveness | -0.084 |
bull | -0.083 |
Token | of |
Token ID | 286 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
Interstitial | +0.858 |
loc | +0.844 |
ME | +0.828 |
方 | +0.814 |
psc | +0.799 |
Neg logit contributions | |
ascript | -0.608 |
forgiven | -0.599 |
heads | -0.537 |
forgiveness | -0.506 |
perfection | -0.496 |
Token | expression |
Token ID | 5408 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Interstitial | +0.015 |
loc | +0.015 |
ME | +0.015 |
方 | +0.014 |
psc | +0.014 |
Neg logit contributions | |
ascript | -0.013 |
forgiven | -0.013 |
heads | -0.012 |
forgiveness | -0.011 |
perfection | -0.011 |
Token | Jill |
Token ID | 22772 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ascript | +0.048 |
forgiven | +0.047 |
heads | +0.043 |
forgiveness | +0.041 |
perfection | +0.040 |
Neg logit contributions | |
Interstitial | -0.053 |
loc | -0.051 |
ME | -0.050 |
方 | -0.049 |
psc | -0.048 |
Token | ian |
Token ID | 666 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Interstitial | +2.500 |
loc | +2.472 |
ME | +2.425 |
方 | +2.342 |
psc | +2.306 |
Neg logit contributions | |
ascript | -2.797 |
forgiven | -2.776 |
heads | -2.553 |
forgiveness | -2.447 |
perfection | -2.424 |
Token | C |
Token ID | 327 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Interstitial | +0.569 |
loc | +0.547 |
ME | +0.535 |
方 | +0.524 |
psc | +0.515 |
Neg logit contributions | |
ascript | -0.628 |
forgiven | -0.620 |
heads | -0.580 |
forgiveness | -0.550 |
perfection | -0.542 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Interstitial | +0.566 |
loc | +0.551 |
ME | +0.540 |
方 | +0.524 |
psc | +0.519 |
Neg logit contributions | |
ascript | -0.579 |
forgiven | -0.570 |
heads | -0.529 |
forgiveness | -0.504 |
perfection | -0.497 |
Token | York |
Token ID | 1971 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
Interstitial | +0.187 |
loc | +0.181 |
ME | +0.177 |
方 | +0.173 |
psc | +0.170 |
Neg logit contributions | |
ascript | -0.207 |
forgiven | -0.204 |
heads | -0.190 |
forgiveness | -0.181 |
perfection | -0.178 |
Token | added |
Token ID | 2087 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
ascript | +0.095 |
forgiven | +0.094 |
heads | +0.087 |
forgiveness | +0.082 |
perfection | +0.081 |
Neg logit contributions | |
Interstitial | -0.111 |
loc | -0.107 |
ME | -0.105 |
方 | -0.103 |
psc | -0.102 |
Token | Sh |
Token ID | 911 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
ascript | +0.055 |
forgiven | +0.054 |
heads | +0.051 |
forgiveness | +0.048 |
perfection | +0.047 |
Neg logit contributions | |
Interstitial | -0.052 |
loc | -0.050 |
ME | -0.049 |
方 | -0.048 |
psc | -0.048 |
Token | river |
Token ID | 38291 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
Interstitial | +0.177 |
loc | +0.172 |
ME | +0.168 |
方 | +0.164 |
psc | +0.162 |
Neg logit contributions | |
ascript | -0.185 |
forgiven | -0.182 |
heads | -0.170 |
forgiveness | -0.161 |
perfection | -0.159 |
Token | Award |
Token ID | 11289 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
Interstitial | +0.162 |
loc | +0.157 |
ME | +0.154 |
方 | +0.151 |
psc | +0.149 |
Neg logit contributions | |
ascript | -0.135 |
forgiven | -0.132 |
heads | -0.122 |
forgiveness | -0.115 |
perfection | -0.113 |
Token | for |
Token ID | 329 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
Interstitial | +1.094 |
loc | +1.060 |
ME | +1.043 |
方 | +1.017 |
psc | +0.999 |
Neg logit contributions | |
ascript | -1.106 |
forgiven | -1.084 |
heads | -1.002 |
forgiveness | -0.949 |
perfection | -0.938 |
Token | Dist |
Token ID | 4307 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Interstitial | +0.121 |
loc | +0.116 |
ME | +0.113 |
方 | +0.111 |
psc | +0.108 |
Neg logit contributions | |
ascript | -0.151 |
forgiven | -0.150 |
heads | -0.140 |
forgiveness | -0.134 |
perfection | -0.132 |
Token | inguished |
Token ID | 46709 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Interstitial | +0.153 |
loc | +0.146 |
ME | +0.141 |
方 | +0.136 |
psc | +0.133 |
Neg logit contributions | |
ascript | -0.321 |
forgiven | -0.317 |
heads | -0.301 |
forgiveness | -0.289 |
perfection | -0.287 |
Token | Human |
Token ID | 5524 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Interstitial | +2.198 |
loc | +2.133 |
ME | +2.066 |
方 | +2.003 |
psc | +1.963 |
Neg logit contributions | |
ascript | -3.153 |
forgiven | -3.054 |
heads | -2.856 |
forgiveness | -2.732 |
perfection | -2.699 |
Token | itarian |
Token ID | 8353 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ascript | +0.418 |
forgiven | +0.415 |
heads | +0.388 |
forgiveness | +0.362 |
perfection | +0.359 |
Neg logit contributions | |
Interstitial | -0.470 |
loc | -0.454 |
ME | -0.446 |
方 | -0.438 |
psc | -0.429 |
Token | Service |
Token ID | 4809 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
forgiven | +1.005 |
ascript | +0.999 |
heads | +0.947 |
forgiveness | +0.902 |
perfection | +0.893 |
Neg logit contributions | |
Interstitial | -0.812 |
loc | -0.773 |
ME | -0.756 |
方 | -0.742 |
psc | -0.725 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Interstitial | +0.131 |
loc | +0.126 |
ME | +0.124 |
方 | +0.121 |
psc | +0.119 |
Neg logit contributions | |
ascript | -0.122 |
forgiven | -0.121 |
heads | -0.112 |
forgiveness | -0.106 |
perfection | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ascript | +0.385 |
forgiven | +0.378 |
heads | +0.351 |
forgiveness | +0.334 |
perfection | +0.329 |
Neg logit contributions | |
Interstitial | -0.355 |
loc | -0.344 |
ME | -0.336 |
方 | -0.327 |
psc | -0.323 |
Token | of |
Token ID | 286 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ascript | +0.498 |
forgiven | +0.485 |
heads | +0.442 |
forgiveness | +0.415 |
perfection | +0.405 |
Neg logit contributions | |
Interstitial | -0.734 |
loc | -0.719 |
ME | -0.704 |
方 | -0.692 |
psc | -0.683 |
Token | the |
Token ID | 262 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ascript | +0.304 |
forgiven | +0.298 |
heads | +0.274 |
forgiveness | +0.260 |
perfection | +0.255 |
Neg logit contributions | |
Interstitial | -0.334 |
loc | -0.323 |
ME | -0.317 |
方 | -0.311 |
psc | -0.305 |
Token | lab |
Token ID | 2248 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
ascript | +0.318 |
forgiven | +0.313 |
heads | +0.289 |
forgiveness | +0.272 |
perfection | +0.268 |
Neg logit contributions | |
Interstitial | -0.376 |
loc | -0.364 |
ME | -0.357 |
方 | -0.350 |
psc | -0.345 |
Token | ia |
Token ID | 544 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ascript | +0.667 |
forgiven | +0.658 |
heads | +0.611 |
forgiveness | +0.571 |
perfection | +0.564 |
Neg logit contributions | |
Interstitial | -0.794 |
loc | -0.767 |
ME | -0.754 |
方 | -0.739 |
psc | -0.729 |
Token | str |
Token ID | 965 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Interstitial | +0.669 |
loc | +0.652 |
ME | +0.636 |
方 | +0.631 |
ordes | +0.612 |
Neg logit contributions | |
ascript | -0.544 |
forgiven | -0.525 |
heads | -0.475 |
forgiveness | -0.456 |
perfection | -0.446 |
Token | add |
Token ID | 2860 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Interstitial | +0.757 |
loc | +0.744 |
ME | +0.723 |
psc | +0.690 |
方 | +0.685 |
Neg logit contributions | |
ascript | -0.731 |
forgiven | -0.717 |
heads | -0.665 |
forgiveness | -0.637 |
perfection | -0.630 |
Token | ling |
Token ID | 1359 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Interstitial | +1.881 |
loc | +1.809 |
ME | +1.685 |
psc | +1.618 |
方 | +1.602 |
Neg logit contributions | |
ascript | -3.477 |
forgiven | -3.409 |
heads | -3.218 |
forgiveness | -3.138 |
perfection | -3.090 |
Token | the |
Token ID | 262 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ascript | +1.493 |
forgiven | +1.469 |
heads | +1.355 |
forgiveness | +1.276 |
perfection | +1.256 |
Neg logit contributions | |
Interstitial | -1.754 |
loc | -1.696 |
ME | -1.664 |
方 | -1.631 |
psc | -1.606 |
Token | clitor |
Token ID | 48852 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ascript | +0.073 |
forgiven | +0.071 |
heads | +0.065 |
forgiveness | +0.061 |
perfection | +0.060 |
Neg logit contributions | |
Interstitial | -0.092 |
loc | -0.089 |
ME | -0.088 |
方 | -0.086 |
psc | -0.085 |
Token | is |
Token ID | 271 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ascript | +1.461 |
forgiven | +1.443 |
heads | +1.361 |
forgiveness | +1.251 |
perfection | +1.238 |
Neg logit contributions | |
Interstitial | -1.786 |
loc | -1.706 |
ME | -1.688 |
方 | -1.681 |
psc | -1.643 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ascript | +0.320 |
forgiven | +0.312 |
heads | +0.284 |
forgiveness | +0.268 |
perfection | +0.262 |
Neg logit contributions | |
Interstitial | -0.439 |
loc | -0.428 |
ME | -0.419 |
方 | -0.411 |
psc | -0.406 |
Token | F |
Token ID | 376 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ascript | +0.079 |
forgiven | +0.078 |
heads | +0.073 |
forgiveness | +0.068 |
perfection | +0.067 |
Neg logit contributions | |
Interstitial | -0.095 |
loc | -0.092 |
ME | -0.090 |
方 | -0.088 |
psc | -0.087 |
Token | IT |
Token ID | 2043 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
Interstitial | +0.274 |
loc | +0.263 |
ME | +0.257 |
方 | +0.251 |
psc | +0.247 |
Neg logit contributions | |
ascript | -0.309 |
forgiven | -0.305 |
heads | -0.286 |
forgiveness | -0.271 |
perfection | -0.268 |
Token | in |
Token ID | 287 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
Interstitial | +1.215 |
loc | +1.174 |
ME | +1.153 |
方 | +1.127 |
psc | +1.108 |
Neg logit contributions | |
ascript | -1.199 |
forgiven | -1.181 |
heads | -1.097 |
forgiveness | -1.039 |
perfection | -1.023 |
Token | … |
Token ID | 3926 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Interstitial | +0.131 |
loc | +0.127 |
ME | +0.124 |
方 | +0.121 |
psc | +0.120 |
Neg logit contributions | |
ascript | -0.129 |
forgiven | -0.128 |
heads | -0.119 |
forgiveness | -0.112 |
perfection | -0.111 |
Token | C |
Token ID | 327 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ascript | +0.437 |
forgiven | +0.434 |
heads | +0.407 |
forgiveness | +0.383 |
perfection | +0.378 |
Neg logit contributions | |
Interstitial | -0.431 |
loc | -0.411 |
ME | -0.400 |
方 | -0.393 |
psc | -0.388 |
Token | ASH |
Token ID | 11211 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Interstitial | +0.835 |
loc | +0.801 |
ME | +0.781 |
方 | +0.765 |
psc | +0.752 |
Neg logit contributions | |
ascript | -0.980 |
forgiven | -0.968 |
heads | -0.908 |
forgiveness | -0.862 |
perfection | -0.851 |
Token | (= |
Token ID | 46121 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Interstitial | +2.708 |
loc | +2.634 |
ME | +2.609 |
方 | +2.548 |
psc | +2.486 |
Neg logit contributions | |
ascript | -2.580 |
forgiven | -2.518 |
heads | -2.325 |
forgiveness | -2.204 |
perfection | -2.176 |
Token | � |
Token ID | 564 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ascript | +0.862 |
forgiven | +0.851 |
heads | +0.798 |
forgiveness | +0.753 |
perfection | +0.742 |
Neg logit contributions | |
Interstitial | -0.860 |
loc | -0.826 |
ME | -0.805 |
方 | -0.790 |
psc | -0.780 |
Token | � |
Token ID | 246 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ascript | +0.224 |
forgiven | +0.221 |
heads | +0.204 |
forgiveness | +0.192 |
perfection | +0.189 |
Neg logit contributions | |
Interstitial | -0.276 |
loc | -0.267 |
ME | -0.262 |
方 | -0.257 |
psc | -0.253 |
Token | me |
Token ID | 1326 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
Interstitial | +0.422 |
loc | +0.407 |
ME | +0.398 |
方 | +0.389 |
psc | +0.382 |
Neg logit contributions | |
ascript | -0.468 |
forgiven | -0.462 |
heads | -0.431 |
forgiveness | -0.409 |
perfection | -0.404 |
Token | ans |
Token ID | 504 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ascript | +0.149 |
forgiven | +0.146 |
heads | +0.137 |
forgiveness | +0.129 |
perfection | +0.127 |
Neg logit contributions | |
Interstitial | -0.156 |
loc | -0.150 |
ME | -0.147 |
方 | -0.144 |
psc | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Interstitial | +1.585 |
loc | +1.538 |
ME | +1.507 |
方 | +1.471 |
psc | +1.446 |
Neg logit contributions | |
ascript | -1.469 |
forgiven | -1.441 |
heads | -1.325 |
forgiveness | -1.249 |
bull | -1.234 |
Token | rather |
Token ID | 2138 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Interstitial | +0.230 |
loc | +0.222 |
ME | +0.218 |
方 | +0.214 |
psc | +0.210 |
Neg logit contributions | |
ascript | -0.185 |
forgiven | -0.181 |
heads | -0.167 |
forgiveness | -0.157 |
perfection | -0.155 |
Token | than |
Token ID | 621 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ascript | +0.194 |
forgiven | +0.190 |
heads | +0.171 |
forgiveness | +0.157 |
perfection | +0.154 |
Neg logit contributions | |
Interstitial | -0.365 |
loc | -0.355 |
ME | -0.349 |
方 | -0.344 |
psc | -0.340 |
Token | increasing |
Token ID | 3649 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
ascript | +0.441 |
forgiven | +0.441 |
heads | +0.411 |
forgiveness | +0.392 |
perfection | +0.388 |
Neg logit contributions | |
Interstitial | -0.406 |
loc | -0.392 |
ME | -0.381 |
方 | -0.374 |
psc | -0.369 |
Token | their |
Token ID | 511 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Interstitial | +1.247 |
loc | +1.204 |
ME | +1.179 |
方 | +1.154 |
psc | +1.134 |
Neg logit contributions | |
ascript | -1.212 |
forgiven | -1.193 |
heads | -1.106 |
forgiveness | -1.044 |
perfection | -1.029 |
Token | immersion |
Token ID | 36375 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ascript | +0.196 |
forgiven | +0.194 |
heads | +0.181 |
forgiveness | +0.169 |
perfection | +0.166 |
Neg logit contributions | |
Interstitial | -0.260 |
loc | -0.251 |
ME | -0.246 |
方 | -0.243 |
psc | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
Interstitial | +3.183 |
loc | +3.111 |
ME | +3.043 |
方 | +3.011 |
psc | +2.944 |
Neg logit contributions | |
ascript | -2.083 |
forgiven | -2.031 |
heads | -1.829 |
forgiveness | -1.706 |
bull | -1.679 |
Token | engagement |
Token ID | 12352 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ascript | +0.124 |
forgiven | +0.123 |
heads | +0.114 |
forgiveness | +0.108 |
perfection | +0.106 |
Neg logit contributions | |
Interstitial | -0.149 |
loc | -0.144 |
ME | -0.141 |
方 | -0.138 |
psc | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-03 |
Pos logit contributions | |
Interstitial | +1.028 |
loc | +0.999 |
ME | +0.981 |
方 | +0.965 |
psc | +0.951 |
Neg logit contributions | |
ascript | -0.666 |
forgiven | -0.654 |
heads | -0.595 |
forgiveness | -0.553 |
perfection | -0.543 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Interstitial | +0.003 |
loc | +0.003 |
ME | +0.003 |
方 | +0.003 |
psc | +0.003 |
Neg logit contributions | |
ascript | -0.003 |
forgiven | -0.003 |
heads | -0.003 |
forgiveness | -0.002 |
perfection | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Interstitial | +0.270 |
loc | +0.263 |
ME | +0.257 |
方 | +0.248 |
psc | +0.245 |
Neg logit contributions | |
ascript | -0.307 |
forgiven | -0.300 |
heads | -0.278 |
forgiveness | -0.266 |
perfection | -0.262 |
Token | losses |
Token ID | 9089 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Interstitial | +1.199 |
loc | +1.165 |
ME | +1.136 |
方 | +1.104 |
psc | +1.087 |
Neg logit contributions | |
ascript | -1.149 |
forgiven | -1.113 |
heads | -1.020 |
forgiveness | -0.969 |
perfection | -0.947 |
Token | from |
Token ID | 422 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
Interstitial | +0.324 |
loc | +0.317 |
ME | +0.310 |
方 | +0.305 |
psc | +0.299 |
Neg logit contributions | |
ascript | -0.205 |
forgiven | -0.195 |
heads | -0.177 |
forgiveness | -0.164 |
perfection | -0.164 |
Token | customers |
Token ID | 4297 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Interstitial | +0.054 |
loc | +0.052 |
ME | +0.051 |
方 | +0.049 |
psc | +0.049 |
Neg logit contributions | |
ascript | -0.049 |
forgiven | -0.048 |
heads | -0.044 |
forgiveness | -0.042 |
perfection | -0.041 |
Token | who |
Token ID | 508 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
ascript | +0.196 |
forgiven | +0.191 |
heads | +0.176 |
forgiveness | +0.166 |
perfection | +0.163 |
Neg logit contributions | |
Interstitial | -0.239 |
loc | -0.231 |
ME | -0.227 |
方 | -0.222 |
psc | -0.219 |
Token | are |
Token ID | 389 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
ascript | +0.141 |
forgiven | +0.139 |
heads | +0.129 |
forgiveness | +0.121 |
perfection | +0.119 |
Neg logit contributions | |
Interstitial | -0.168 |
loc | -0.163 |
ME | -0.160 |
方 | -0.157 |
psc | -0.154 |
Token | cutting |
Token ID | 7720 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ascript | +0.149 |
forgiven | +0.147 |
heads | +0.136 |
forgiveness | +0.128 |
perfection | +0.125 |
Neg logit contributions | |
Interstitial | -0.180 |
loc | -0.174 |
ME | -0.171 |
方 | -0.168 |
psc | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Interstitial | +2.886 |
loc | +2.788 |
ME | +2.710 |
psc | +2.628 |
方 | +2.627 |
Neg logit contributions | |
ascript | -2.392 |
forgiven | -2.330 |
heads | -2.058 |
forgiveness | -1.996 |
bull | -1.949 |
Token | cable |
Token ID | 7862 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Interstitial | +0.336 |
loc | +0.324 |
ME | +0.317 |
方 | +0.309 |
psc | +0.304 |
Neg logit contributions | |
ascript | -0.384 |
forgiven | -0.378 |
heads | -0.352 |
forgiveness | -0.335 |
perfection | -0.331 |
Token | TV |
Token ID | 3195 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ascript | +0.247 |
forgiven | +0.242 |
heads | +0.223 |
forgiveness | +0.210 |
perfection | +0.207 |
Neg logit contributions | |
Interstitial | -0.292 |
loc | -0.282 |
ME | -0.277 |
方 | -0.271 |
psc | -0.267 |
Token | cord |
Token ID | 15050 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ascript | +0.225 |
forgiven | +0.222 |
heads | +0.205 |
forgiveness | +0.193 |
perfection | +0.190 |
Neg logit contributions | |
Interstitial | -0.255 |
loc | -0.247 |
ME | -0.242 |
方 | -0.237 |
psc | -0.234 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Interstitial | +0.836 |
loc | +0.815 |
ME | +0.799 |
方 | +0.781 |
psc | +0.772 |
Neg logit contributions | |
ascript | -0.589 |
forgiven | -0.575 |
heads | -0.522 |
forgiveness | -0.494 |
perfection | -0.485 |
Token | de |
Token ID | 390 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ascript | +0.004 |
forgiven | +0.004 |
heads | +0.004 |
forgiveness | +0.004 |
perfection | +0.004 |
Neg logit contributions | |
Interstitial | -0.004 |
loc | -0.004 |
ME | -0.004 |
方 | -0.004 |
psc | -0.004 |
Token | d |
Token ID | 288 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
Interstitial | +0.760 |
loc | +0.739 |
ME | +0.724 |
方 | +0.707 |
psc | +0.698 |
Neg logit contributions | |
ascript | -0.738 |
forgiven | -0.725 |
heads | -0.672 |
forgiveness | -0.636 |
perfection | -0.625 |
Token | és |
Token ID | 20954 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Interstitial | +1.881 |
loc | +1.862 |
ME | +1.822 |
ordes | +1.748 |
方 | +1.747 |
Neg logit contributions | |
ascript | -1.766 |
forgiven | -1.734 |
heads | -1.599 |
forgiveness | -1.523 |
perfection | -1.497 |
Token | acc |
Token ID | 4134 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Interstitial | +0.593 |
loc | +0.571 |
ME | +0.560 |
方 | +0.548 |
psc | +0.540 |
Neg logit contributions | |
ascript | -0.576 |
forgiven | -0.567 |
heads | -0.528 |
forgiveness | -0.498 |
perfection | -0.492 |
Token | ord |
Token ID | 585 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
Interstitial | +0.436 |
loc | +0.418 |
ME | +0.409 |
方 | +0.400 |
psc | +0.393 |
Neg logit contributions | |
ascript | -0.514 |
forgiven | -0.508 |
heads | -0.476 |
forgiveness | -0.452 |
perfection | -0.446 |
Token | ent |
Token ID | 920 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Interstitial | +0.042 |
loc | +0.040 |
ME | +0.039 |
方 | +0.038 |
psc | +0.038 |
Neg logit contributions | |
ascript | -0.043 |
forgiven | -0.043 |
heads | -0.040 |
forgiveness | -0.038 |
perfection | -0.037 |
Token | re |
Token ID | 260 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Interstitial | +2.884 |
loc | +2.816 |
ME | +2.754 |
方 | +2.679 |
psc | +2.658 |
Neg logit contributions | |
ascript | -2.347 |
forgiven | -2.292 |
heads | -2.119 |
forgiveness | -1.984 |
perfection | -1.968 |
Token | mem |
Token ID | 1066 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Interstitial | +0.402 |
loc | +0.387 |
ME | +0.379 |
方 | +0.372 |
psc | +0.367 |
Neg logit contributions | |
ascript | -0.370 |
forgiven | -0.365 |
heads | -0.339 |
forgiveness | -0.320 |
perfection | -0.316 |
Token | b |
Token ID | 65 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Interstitial | +0.795 |
loc | +0.777 |
ME | +0.762 |
方 | +0.742 |
psc | +0.736 |
Neg logit contributions | |
ascript | -0.709 |
forgiven | -0.696 |
heads | -0.645 |
forgiveness | -0.610 |
perfection | -0.599 |
Token | res |
Token ID | 411 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Interstitial | +0.640 |
loc | +0.618 |
ME | +0.605 |
方 | +0.592 |
psc | +0.584 |
Neg logit contributions | |
ascript | -0.629 |
forgiven | -0.621 |
heads | -0.578 |
forgiveness | -0.546 |
perfection | -0.539 |
Token | , |
Token ID | 11 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
Interstitial | +0.569 |
loc | +0.549 |
ME | +0.537 |
方 | +0.526 |
psc | +0.517 |
Neg logit contributions | |
ascript | -0.583 |
forgiven | -0.575 |
heads | -0.536 |
forgiveness | -0.507 |
perfection | -0.500 |
Token | the |
Token ID | 262 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
Interstitial | +0.038 |
loc | +0.037 |
ME | +0.036 |
方 | +0.035 |
psc | +0.035 |
Neg logit contributions | |
ascript | -0.037 |
forgiven | -0.037 |
heads | -0.034 |
forgiveness | -0.032 |
perfection | -0.032 |
Token | hit |
Token ID | 2277 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Interstitial | +0.178 |
loc | +0.172 |
ME | +0.169 |
方 | +0.165 |
psc | +0.163 |
Neg logit contributions | |
ascript | -0.147 |
forgiven | -0.144 |
heads | -0.132 |
forgiveness | -0.125 |
perfection | -0.122 |
Token | series |
Token ID | 2168 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ascript | +0.265 |
forgiven | +0.261 |
heads | +0.241 |
forgiveness | +0.226 |
perfection | +0.223 |
Neg logit contributions | |
Interstitial | -0.333 |
loc | -0.323 |
ME | -0.317 |
方 | -0.311 |
psc | -0.307 |
Token | " |
Token ID | 366 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Interstitial | +0.331 |
loc | +0.320 |
ME | +0.313 |
方 | +0.305 |
psc | +0.301 |
Neg logit contributions | |
ascript | -0.351 |
forgiven | -0.344 |
heads | -0.320 |
forgiveness | -0.303 |
perfection | -0.299 |
Token | Teen |
Token ID | 45639 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ascript | +0.280 |
forgiven | +0.277 |
heads | +0.257 |
forgiveness | +0.243 |
perfection | +0.240 |
Neg logit contributions | |
Interstitial | -0.282 |
loc | -0.272 |
ME | -0.266 |
方 | -0.260 |
psc | -0.256 |
Token | Titans |
Token ID | 18711 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Interstitial | +0.687 |
loc | +0.671 |
ME | +0.658 |
方 | +0.642 |
psc | +0.630 |
Neg logit contributions | |
ascript | -0.741 |
forgiven | -0.732 |
heads | -0.677 |
forgiveness | -0.646 |
perfection | -0.636 |
Token | ." |
Token ID | 526 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Interstitial | +2.739 |
loc | +2.701 |
ME | +2.660 |
方 | +2.583 |
psc | +2.565 |
Neg logit contributions | |
forgiven | -2.378 |
ascript | -2.372 |
heads | -2.169 |
forgiveness | -2.078 |
bull | -2.023 |
Token | David |
Token ID | 3271 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ascript | +0.333 |
forgiven | +0.329 |
heads | +0.305 |
forgiveness | +0.289 |
perfection | +0.285 |
Neg logit contributions | |
Interstitial | -0.333 |
loc | -0.321 |
ME | -0.315 |
方 | -0.308 |
psc | -0.303 |
Token | took |
Token ID | 1718 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ascript | +0.408 |
forgiven | +0.401 |
heads | +0.369 |
forgiveness | +0.348 |
perfection | +0.342 |
Neg logit contributions | |
Interstitial | -0.496 |
loc | -0.481 |
ME | -0.472 |
方 | -0.463 |
psc | -0.456 |
Token | some |
Token ID | 617 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ascript | +0.226 |
forgiven | +0.221 |
heads | +0.202 |
forgiveness | +0.191 |
perfection | +0.187 |
Neg logit contributions | |
Interstitial | -0.266 |
loc | -0.259 |
ME | -0.255 |
方 | -0.249 |
psc | -0.246 |
Token | time |
Token ID | 640 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ascript | +0.407 |
forgiven | +0.396 |
heads | +0.364 |
forgiveness | +0.344 |
perfection | +0.340 |
Neg logit contributions | |
Interstitial | -0.445 |
loc | -0.433 |
ME | -0.423 |
方 | -0.414 |
psc | -0.407 |
Token | . |
Token ID | 13 |
Feature activation | -7.84e-03 |
Pos logit contributions | |
ascript | +1.208 |
forgiven | +1.187 |
heads | +1.084 |
forgiveness | +1.009 |
perfection | +0.991 |
Neg logit contributions | |
Interstitial | -1.814 |
loc | -1.760 |
ME | -1.730 |
方 | -1.699 |
psc | -1.678 |
Token | " |
Token ID | 366 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Interstitial | +0.015 |
loc | +0.014 |
ME | +0.014 |
方 | +0.013 |
psc | +0.013 |
Neg logit contributions | |
ascript | -0.015 |
forgiven | -0.015 |
heads | -0.014 |
forgiveness | -0.013 |
perfection | -0.013 |
Token | Companies |
Token ID | 49111 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
Interstitial | +0.246 |
loc | +0.238 |
ME | +0.233 |
方 | +0.228 |
psc | +0.225 |
Neg logit contributions | |
ascript | -0.216 |
forgiven | -0.213 |
heads | -0.197 |
forgiveness | -0.186 |
perfection | -0.183 |
Token | have |
Token ID | 423 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
Interstitial | +0.215 |
loc | +0.209 |
ME | +0.205 |
方 | +0.201 |
psc | +0.199 |
Neg logit contributions | |
ascript | -0.160 |
forgiven | -0.156 |
heads | -0.143 |
forgiveness | -0.135 |
perfection | -0.132 |
Token | been |
Token ID | 587 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Interstitial | +0.648 |
loc | +0.629 |
ME | +0.615 |
方 | +0.603 |
psc | +0.594 |
Neg logit contributions | |
ascript | -0.518 |
forgiven | -0.501 |
heads | -0.461 |
forgiveness | -0.435 |
perfection | -0.428 |
Token | cutting |
Token ID | 7720 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Interstitial | +0.715 |
loc | +0.693 |
ME | +0.679 |
方 | +0.664 |
psc | +0.654 |
Neg logit contributions | |
ascript | -0.624 |
forgiven | -0.605 |
heads | -0.562 |
forgiveness | -0.531 |
perfection | -0.521 |
Token | off |
Token ID | 572 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
Interstitial | +2.741 |
loc | +2.741 |
ME | +2.660 |
方 | +2.584 |
psc | +2.541 |
Neg logit contributions | |
ascript | -2.399 |
forgiven | -2.335 |
heads | -2.018 |
forgiveness | -1.993 |
bull | -1.963 |
Token | their |
Token ID | 511 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ascript | +1.069 |
forgiven | +1.049 |
heads | +0.968 |
forgiveness | +0.916 |
perfection | +0.903 |
Neg logit contributions | |
Interstitial | -1.182 |
loc | -1.145 |
ME | -1.122 |
方 | -1.097 |
psc | -1.081 |
Token | arms |
Token ID | 5101 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Interstitial | +0.210 |
loc | +0.204 |
ME | +0.200 |
方 | +0.195 |
psc | +0.191 |
Neg logit contributions | |
ascript | -0.199 |
forgiven | -0.194 |
heads | -0.177 |
forgiveness | -0.169 |
perfection | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ascript | +0.271 |
forgiven | +0.265 |
heads | +0.242 |
forgiveness | +0.228 |
perfection | +0.224 |
Neg logit contributions | |
Interstitial | -0.372 |
loc | -0.362 |
ME | -0.355 |
方 | -0.347 |
psc | -0.345 |
Token | save |
Token ID | 3613 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
Interstitial | +0.251 |
loc | +0.242 |
ME | +0.237 |
方 | +0.232 |
psc | +0.229 |
Neg logit contributions | |
ascript | -0.229 |
forgiven | -0.225 |
heads | -0.209 |
forgiveness | -0.197 |
perfection | -0.194 |
Token | report |
Token ID | 989 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Interstitial | +1.102 |
loc | +1.074 |
ME | +1.056 |
方 | +1.031 |
psc | +1.010 |
Neg logit contributions | |
ascript | -0.971 |
forgiven | -0.957 |
heads | -0.872 |
forgiveness | -0.828 |
perfection | -0.812 |
Token | , |
Token ID | 11 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Interstitial | +0.570 |
loc | +0.554 |
ME | +0.543 |
方 | +0.531 |
psc | +0.520 |
Neg logit contributions | |
ascript | -0.557 |
forgiven | -0.549 |
heads | -0.506 |
forgiveness | -0.480 |
perfection | -0.473 |
Token | 17 |
Token ID | 1596 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Interstitial | +0.375 |
loc | +0.365 |
ME | +0.358 |
方 | +0.348 |
psc | +0.345 |
Neg logit contributions | |
ascript | -0.334 |
forgiven | -0.328 |
heads | -0.300 |
forgiveness | -0.285 |
perfection | -0.279 |
Token | percent |
Token ID | 1411 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Interstitial | +0.210 |
loc | +0.204 |
ME | +0.200 |
方 | +0.195 |
psc | +0.193 |
Neg logit contributions | |
ascript | -0.200 |
forgiven | -0.198 |
heads | -0.180 |
forgiveness | -0.173 |
perfection | -0.170 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Interstitial | +0.610 |
loc | +0.596 |
ME | +0.587 |
方 | +0.575 |
psc | +0.568 |
Neg logit contributions | |
ascript | -0.351 |
forgiven | -0.344 |
heads | -0.310 |
forgiveness | -0.288 |
perfection | -0.282 |
Token | epis |
Token ID | 48177 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Interstitial | +0.318 |
loc | +0.310 |
ME | +0.304 |
方 | +0.296 |
psc | +0.294 |
Neg logit contributions | |
ascript | -0.236 |
forgiven | -0.231 |
heads | -0.207 |
forgiveness | -0.197 |
bull | -0.193 |
Token | odic |
Token ID | 29512 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
ascript | +2.290 |
forgiven | +2.232 |
heads | +2.125 |
forgiveness | +1.970 |
perfection | +1.952 |
Neg logit contributions | |
Interstitial | -2.320 |
方 | -2.184 |
loc | -2.179 |
ME | -2.178 |
Pwr | -2.081 |
Token | American |
Token ID | 1605 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
Interstitial | +0.789 |
loc | +0.764 |
ME | +0.752 |
方 | +0.730 |
psc | +0.723 |
Neg logit contributions | |
ascript | -0.622 |
forgiven | -0.608 |
heads | -0.548 |
forgiveness | -0.521 |
bull | -0.512 |
Token | TV |
Token ID | 3195 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
ascript | +0.028 |
forgiven | +0.027 |
heads | +0.025 |
forgiveness | +0.023 |
perfection | +0.023 |
Neg logit contributions | |
Interstitial | -0.036 |
loc | -0.035 |
ME | -0.034 |
方 | -0.034 |
psc | -0.033 |
Token | shows |
Token ID | 2523 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
ascript | +0.514 |
forgiven | +0.505 |
heads | +0.462 |
forgiveness | +0.433 |
perfection | +0.426 |
Neg logit contributions | |
Interstitial | -0.705 |
loc | -0.683 |
ME | -0.671 |
方 | -0.658 |
psc | -0.650 |
Token | were |
Token ID | 547 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ascript | +0.138 |
forgiven | +0.135 |
heads | +0.123 |
forgiveness | +0.116 |
perfection | +0.113 |
Neg logit contributions | |
Interstitial | -0.190 |
loc | -0.185 |
ME | -0.181 |
方 | -0.177 |
psc | -0.176 |
Token | upp |
Token ID | 7211 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ascript | +0.316 |
forgiven | +0.311 |
heads | +0.289 |
forgiveness | +0.273 |
perfection | +0.269 |
Neg logit contributions | |
Interstitial | -0.324 |
loc | -0.313 |
ME | -0.308 |
方 | -0.300 |
psc | -0.297 |
Token | e |
Token ID | 68 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Interstitial | +0.780 |
loc | +0.757 |
ME | +0.741 |
方 | +0.723 |
psc | +0.715 |
Neg logit contributions | |
ascript | -0.798 |
forgiven | -0.791 |
heads | -0.736 |
forgiveness | -0.694 |
perfection | -0.686 |
Token | Award |
Token ID | 11289 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
ascript | +0.665 |
forgiven | +0.656 |
heads | +0.606 |
forgiveness | +0.570 |
perfection | +0.558 |
Neg logit contributions | |
Interstitial | -0.864 |
loc | -0.837 |
ME | -0.818 |
方 | -0.806 |
psc | -0.795 |
Token | for |
Token ID | 329 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
Interstitial | +1.117 |
loc | +1.086 |
ME | +1.075 |
方 | +1.053 |
psc | +1.038 |
Neg logit contributions | |
ascript | -0.635 |
forgiven | -0.614 |
heads | -0.553 |
forgiveness | -0.506 |
perfection | -0.502 |
Token | Out |
Token ID | 3806 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Interstitial | +0.030 |
loc | +0.029 |
ME | +0.028 |
方 | +0.027 |
psc | +0.027 |
Neg logit contributions | |
ascript | -0.042 |
forgiven | -0.041 |
heads | -0.039 |
forgiveness | -0.037 |
perfection | -0.037 |
Token | standing |
Token ID | 5646 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ascript | +0.748 |
forgiven | +0.737 |
heads | +0.675 |
forgiveness | +0.631 |
perfection | +0.619 |
Neg logit contributions | |
Interstitial | -1.048 |
loc | -1.013 |
ME | -0.996 |
方 | -0.980 |
psc | -0.965 |
Token | Community |
Token ID | 8108 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
forgiven | +2.828 |
ascript | +2.758 |
heads | +2.686 |
forgiveness | +2.563 |
perfection | +2.511 |
Neg logit contributions | |
Interstitial | -2.134 |
loc | -2.018 |
ME | -1.972 |
方 | -1.938 |
psc | -1.901 |
Token | Service |
Token ID | 4809 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ascript | +0.371 |
forgiven | +0.368 |
heads | +0.347 |
forgiveness | +0.330 |
perfection | +0.325 |
Neg logit contributions | |
Interstitial | -0.296 |
loc | -0.284 |
ME | -0.277 |
方 | -0.271 |
psc | -0.266 |
Token |
|
Token ID | 198 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Interstitial | +0.613 |
loc | +0.591 |
ME | +0.579 |
方 | +0.567 |
psc | +0.558 |
Neg logit contributions | |
ascript | -0.620 |
forgiven | -0.610 |
heads | -0.568 |
forgiveness | -0.538 |
perfection | -0.530 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ascript | +0.488 |
forgiven | +0.480 |
heads | +0.447 |
forgiveness | +0.424 |
perfection | +0.418 |
Neg logit contributions | |
Interstitial | -0.455 |
loc | -0.440 |
ME | -0.431 |
方 | -0.420 |
psc | -0.414 |
Token | The |
Token ID | 464 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
ascript | +0.341 |
forgiven | +0.336 |
heads | +0.312 |
forgiveness | +0.295 |
perfection | +0.291 |
Neg logit contributions | |
Interstitial | -0.366 |
loc | -0.353 |
ME | -0.346 |
方 | -0.339 |
psc | -0.334 |
Token | Hawai |
Token ID | 10847 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
ascript | +0.607 |
forgiven | +0.599 |
heads | +0.558 |
forgiveness | +0.528 |
perfection | +0.521 |
Neg logit contributions | |
Interstitial | -0.599 |
loc | -0.577 |
ME | -0.565 |
方 | -0.553 |
psc | -0.545 |
Token | � |
Token ID | 134 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ascript | +0.890 |
forgiven | +0.875 |
heads | +0.798 |
forgiveness | +0.744 |
perfection | +0.730 |
Neg logit contributions | |
Interstitial | -1.340 |
loc | -1.301 |
ME | -1.279 |
方 | -1.256 |
psc | -1.240 |
Token | � |
Token ID | 119 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ascript | +0.324 |
forgiven | +0.319 |
heads | +0.290 |
forgiveness | +0.277 |
perfection | +0.273 |
Neg logit contributions | |
Interstitial | -0.378 |
loc | -0.371 |
ME | -0.366 |
方 | -0.357 |
psc | -0.350 |
Token | i |
Token ID | 72 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
ascript | +1.325 |
forgiven | +1.309 |
heads | +1.221 |
forgiveness | +1.154 |
perfection | +1.140 |
Neg logit contributions | |
Interstitial | -1.281 |
loc | -1.231 |
ME | -1.205 |
方 | -1.182 |
psc | -1.164 |
Token | me |
Token ID | 502 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ascript | +1.247 |
forgiven | +1.241 |
heads | +1.161 |
forgiveness | +1.094 |
perfection | +1.080 |
Neg logit contributions | |
Interstitial | -1.281 |
loc | -1.232 |
ME | -1.205 |
方 | -1.184 |
psc | -1.173 |
Token | Ke |
Token ID | 3873 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ascript | +0.186 |
forgiven | +0.184 |
heads | +0.170 |
forgiveness | +0.161 |
perfection | +0.159 |
Neg logit contributions | |
Interstitial | -0.200 |
loc | -0.193 |
ME | -0.189 |
方 | -0.185 |
psc | -0.183 |
Token | K |
Token ID | 509 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ascript | +2.060 |
forgiven | +2.041 |
heads | +1.902 |
forgiveness | +1.762 |
perfection | +1.743 |
Neg logit contributions | |
Interstitial | -2.742 |
loc | -2.636 |
ME | -2.590 |
方 | -2.562 |
psc | -2.533 |
Token | ula |
Token ID | 4712 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
ascript | +0.346 |
forgiven | +0.342 |
heads | +0.318 |
forgiveness | +0.302 |
perfection | +0.298 |
Neg logit contributions | |
Interstitial | -0.328 |
loc | -0.318 |
ME | -0.311 |
方 | -0.303 |
psc | -0.298 |
Token | Kai |
Token ID | 22091 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Interstitial | +0.072 |
loc | +0.070 |
ME | +0.068 |
方 | +0.067 |
psc | +0.066 |
Neg logit contributions | |
ascript | -0.071 |
forgiven | -0.070 |
heads | -0.066 |
forgiveness | -0.062 |
perfection | -0.061 |
Token | ap |
Token ID | 499 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ascript | +1.296 |
forgiven | +1.272 |
heads | +1.192 |
forgiveness | +1.126 |
perfection | +1.108 |
Neg logit contributions | |
Interstitial | -1.239 |
loc | -1.184 |
ME | -1.162 |
方 | -1.140 |
psc | -1.122 |
Token | uni |
Token ID | 35657 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ascript | +0.597 |
forgiven | +0.591 |
heads | +0.556 |
forgiveness | +0.532 |
perfection | +0.526 |
Neg logit contributions | |
Interstitial | -0.406 |
loc | -0.387 |
ME | -0.378 |
方 | -0.368 |
psc | -0.360 |
Token | egg |
Token ID | 5935 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
ascript | +0.095 |
forgiven | +0.094 |
heads | +0.088 |
forgiveness | +0.082 |
perfection | +0.081 |
Neg logit contributions | |
Interstitial | -0.105 |
loc | -0.101 |
ME | -0.099 |
方 | -0.097 |
psc | -0.096 |
Token | repl |
Token ID | 2186 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
ascript | +0.072 |
forgiven | +0.071 |
heads | +0.065 |
forgiveness | +0.062 |
perfection | +0.061 |
Neg logit contributions | |
Interstitial | -0.082 |
loc | -0.079 |
ME | -0.077 |
方 | -0.076 |
psc | -0.075 |
Token | acer |
Token ID | 11736 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ascript | +0.085 |
forgiven | +0.084 |
heads | +0.078 |
forgiveness | +0.073 |
perfection | +0.072 |
Neg logit contributions | |
Interstitial | -0.102 |
loc | -0.098 |
ME | -0.097 |
方 | -0.095 |
psc | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
Interstitial | +0.054 |
loc | +0.053 |
ME | +0.052 |
方 | +0.051 |
psc | +0.050 |
Neg logit contributions | |
ascript | -0.039 |
forgiven | -0.039 |
heads | -0.035 |
forgiveness | -0.033 |
perfection | -0.032 |
Token | set |
Token ID | 900 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
Interstitial | +0.024 |
loc | +0.024 |
ME | +0.023 |
方 | +0.023 |
psc | +0.022 |
Neg logit contributions | |
ascript | -0.022 |
forgiven | -0.022 |
heads | -0.020 |
forgiveness | -0.019 |
perfection | -0.019 |
Token | aside |
Token ID | 7263 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ascript | +0.113 |
forgiven | +0.112 |
heads | +0.104 |
forgiveness | +0.098 |
perfection | +0.096 |
Neg logit contributions | |
Interstitial | -0.123 |
loc | -0.119 |
ME | -0.117 |
方 | -0.114 |
psc | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
ascript | +1.687 |
forgiven | +1.651 |
heads | +1.527 |
forgiveness | +1.403 |
perfection | +1.378 |
Neg logit contributions | |
Interstitial | -2.904 |
loc | -2.801 |
ME | -2.751 |
方 | -2.719 |
psc | -2.690 |
Token |
|
Token ID | 198 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
ascript | +0.192 |
forgiven | +0.190 |
heads | +0.178 |
forgiveness | +0.169 |
perfection | +0.166 |
Neg logit contributions | |
Interstitial | -0.172 |
loc | -0.165 |
ME | -0.161 |
方 | -0.158 |
psc | -0.155 |
Token |
|
Token ID | 198 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
ascript | +0.122 |
forgiven | +0.120 |
heads | +0.112 |
forgiveness | +0.106 |
perfection | +0.105 |
Neg logit contributions | |
Interstitial | -0.119 |
loc | -0.114 |
ME | -0.112 |
方 | -0.109 |
psc | -0.108 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ascript | +0.079 |
forgiven | +0.077 |
heads | +0.072 |
forgiveness | +0.069 |
perfection | +0.068 |
Neg logit contributions | |
Interstitial | -0.073 |
loc | -0.070 |
ME | -0.069 |
方 | -0.067 |
psc | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
Interstitial | +0.655 |
loc | +0.644 |
ME | +0.634 |
方 | +0.616 |
psc | +0.612 |
Neg logit contributions | |
ascript | -0.384 |
forgiven | -0.373 |
heads | -0.330 |
forgiveness | -0.311 |
perfection | -0.303 |
Token | what |
Token ID | 644 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ascript | +0.378 |
forgiven | +0.370 |
heads | +0.341 |
forgiveness | +0.323 |
perfection | +0.318 |
Neg logit contributions | |
Interstitial | -0.380 |
loc | -0.370 |
ME | -0.364 |
方 | -0.353 |
psc | -0.348 |
Token | he |
Token ID | 339 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
Interstitial | +0.285 |
loc | +0.276 |
ME | +0.271 |
方 | +0.264 |
psc | +0.260 |
Neg logit contributions | |
ascript | -0.283 |
forgiven | -0.278 |
heads | -0.257 |
forgiveness | -0.244 |
perfection | -0.240 |
Token | called |
Token ID | 1444 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Interstitial | +0.190 |
loc | +0.186 |
ME | +0.183 |
方 | +0.179 |
psc | +0.177 |
Neg logit contributions | |
ascript | -0.120 |
forgiven | -0.117 |
heads | -0.106 |
forgiveness | -0.099 |
perfection | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ascript | +0.698 |
forgiven | +0.685 |
heads | +0.634 |
forgiveness | +0.603 |
perfection | +0.593 |
Neg logit contributions | |
Interstitial | -0.653 |
loc | -0.632 |
ME | -0.620 |
方 | -0.603 |
psc | -0.593 |
Token | Beng |
Token ID | 14964 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
ascript | +0.190 |
forgiven | +0.186 |
heads | +0.171 |
forgiveness | +0.162 |
perfection | +0.160 |
Neg logit contributions | |
Interstitial | -0.195 |
loc | -0.189 |
ME | -0.186 |
方 | -0.180 |
psc | -0.179 |
Token | alis |
Token ID | 27315 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ascript | +1.133 |
forgiven | +1.117 |
heads | +1.025 |
forgiveness | +0.948 |
perfection | +0.931 |
Neg logit contributions | |
Interstitial | -1.732 |
loc | -1.671 |
ME | -1.645 |
方 | -1.626 |
psc | -1.602 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ascript | +2.093 |
forgiven | +2.088 |
heads | +1.925 |
forgiveness | +1.790 |
perfection | +1.754 |
Neg logit contributions | |
Interstitial | -3.039 |
loc | -2.927 |
ME | -2.870 |
方 | -2.844 |
psc | -2.794 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ascript | +0.517 |
forgiven | +0.512 |
heads | +0.479 |
forgiveness | +0.452 |
perfection | +0.446 |
Neg logit contributions | |
Interstitial | -0.499 |
loc | -0.480 |
ME | -0.469 |
方 | -0.460 |
psc | -0.453 |
Token |
|
Token ID | 198 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
ascript | +0.042 |
forgiven | +0.042 |
heads | +0.039 |
forgiveness | +0.037 |
perfection | +0.036 |
Neg logit contributions | |
Interstitial | -0.040 |
loc | -0.039 |
ME | -0.038 |
方 | -0.037 |
psc | -0.037 |
Token | The |
Token ID | 464 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
ascript | +0.011 |
forgiven | +0.010 |
heads | +0.010 |
forgiveness | +0.009 |
perfection | +0.009 |
Neg logit contributions | |
Interstitial | -0.012 |
loc | -0.012 |
ME | -0.012 |
方 | -0.011 |
psc | -0.011 |
Token | BBC |
Token ID | 7823 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ascript | +0.070 |
forgiven | +0.069 |
heads | +0.063 |
forgiveness | +0.059 |
perfection | +0.059 |
Neg logit contributions | |
Interstitial | -0.086 |
loc | -0.084 |
ME | -0.082 |
方 | -0.080 |
psc | -0.079 |
Token | Battery |
Token ID | 23490 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Interstitial | +0.125 |
loc | +0.120 |
ME | +0.115 |
方 | +0.111 |
psc | +0.109 |
Neg logit contributions | |
ascript | -0.218 |
forgiven | -0.214 |
heads | -0.201 |
forgiveness | -0.193 |
perfection | -0.191 |
Token | Park |
Token ID | 3250 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
Interstitial | +0.754 |
loc | +0.746 |
ME | +0.733 |
psc | +0.709 |
方 | +0.708 |
Neg logit contributions | |
ascript | -0.531 |
forgiven | -0.504 |
heads | -0.454 |
forgiveness | -0.434 |
perfection | -0.424 |
Token | in |
Token ID | 287 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ascript | +0.012 |
forgiven | +0.011 |
heads | +0.010 |
forgiveness | +0.010 |
perfection | +0.009 |
Neg logit contributions | |
Interstitial | -0.017 |
loc | -0.017 |
ME | -0.016 |
方 | -0.016 |
psc | -0.016 |
Token | Historic |
Token ID | 30426 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
ascript | +0.202 |
forgiven | +0.198 |
heads | +0.184 |
forgiveness | +0.175 |
perfection | +0.173 |
Neg logit contributions | |
Interstitial | -0.179 |
loc | -0.174 |
ME | -0.169 |
方 | -0.165 |
psc | -0.163 |
Token | New |
Token ID | 968 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ascript | +1.178 |
forgiven | +1.168 |
heads | +1.100 |
forgiveness | +1.044 |
perfection | +1.033 |
Neg logit contributions | |
Interstitial | -0.929 |
loc | -0.886 |
ME | -0.868 |
方 | -0.847 |
psc | -0.829 |
Token | Castle |
Token ID | 11312 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ascript | +0.292 |
forgiven | +0.288 |
heads | +0.269 |
forgiveness | +0.256 |
perfection | +0.253 |
Neg logit contributions | |
Interstitial | -0.260 |
loc | -0.251 |
ME | -0.245 |
方 | -0.240 |
psc | -0.236 |
Token | following |
Token ID | 1708 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
ascript | +0.438 |
forgiven | +0.426 |
heads | +0.384 |
forgiveness | +0.363 |
perfection | +0.354 |
Neg logit contributions | |
Interstitial | -0.642 |
loc | -0.628 |
ME | -0.615 |
方 | -0.602 |
psc | -0.596 |
Token | complaints |
Token ID | 9687 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Interstitial | +1.017 |
loc | +0.992 |
ME | +0.973 |
方 | +0.939 |
ordes | +0.923 |
Neg logit contributions | |
ascript | -1.031 |
forgiven | -1.003 |
heads | -0.910 |
forgiveness | -0.873 |
bull | -0.854 |
Token | by |
Token ID | 416 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ascript | +0.480 |
forgiven | +0.460 |
heads | +0.401 |
forgiveness | +0.378 |
perfection | +0.370 |
Neg logit contributions | |
Interstitial | -0.855 |
loc | -0.842 |
ME | -0.828 |
方 | -0.806 |
psc | -0.799 |
Token | local |
Token ID | 1957 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
Interstitial | +0.190 |
loc | +0.186 |
ME | +0.181 |
方 | +0.175 |
psc | +0.174 |
Neg logit contributions | |
ascript | -0.189 |
forgiven | -0.183 |
heads | -0.169 |
forgiveness | -0.161 |
perfection | -0.158 |
Token | residents |
Token ID | 5085 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ascript | +1.612 |
forgiven | +1.601 |
heads | +1.502 |
forgiveness | +1.413 |
perfection | +1.395 |
Neg logit contributions | |
Interstitial | -1.641 |
loc | -1.574 |
ME | -1.542 |
方 | -1.519 |
psc | -1.491 |
Token | ( |
Token ID | 357 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ascript | +0.066 |
forgiven | +0.065 |
heads | +0.060 |
forgiveness | +0.057 |
perfection | +0.056 |
Neg logit contributions | |
Interstitial | -0.072 |
loc | -0.069 |
ME | -0.068 |
方 | -0.066 |
psc | -0.066 |
Token | Free |
Token ID | 11146 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
ascript | +0.276 |
forgiven | +0.273 |
heads | +0.255 |
forgiveness | +0.242 |
perfection | +0.239 |
Neg logit contributions | |
Interstitial | -0.239 |
loc | -0.230 |
ME | -0.224 |
方 | -0.219 |
psc | -0.215 |
Token | ) |
Token ID | 8 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Interstitial | +0.076 |
loc | +0.073 |
ME | +0.071 |
方 | +0.070 |
psc | +0.069 |
Neg logit contributions | |
ascript | -0.077 |
forgiven | -0.076 |
heads | -0.070 |
forgiveness | -0.067 |
perfection | -0.066 |
Token | [ |
Token ID | 685 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Interstitial | +0.338 |
loc | +0.325 |
ME | +0.319 |
方 | +0.313 |
psc | +0.307 |
Neg logit contributions | |
ascript | -0.305 |
forgiven | -0.301 |
heads | -0.276 |
forgiveness | -0.263 |
perfection | -0.258 |
Token | Home |
Token ID | 16060 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Interstitial | +0.757 |
loc | +0.730 |
ME | +0.719 |
方 | +0.702 |
psc | +0.694 |
Neg logit contributions | |
ascript | -0.580 |
forgiven | -0.569 |
heads | -0.521 |
forgiveness | -0.491 |
perfection | -0.482 |
Token | page |
Token ID | 7700 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
Interstitial | +0.381 |
loc | +0.374 |
ME | +0.364 |
psc | +0.351 |
方 | +0.349 |
Neg logit contributions | |
ascript | -0.377 |
forgiven | -0.372 |
heads | -0.345 |
forgiveness | -0.330 |
perfection | -0.325 |
Token | ] |
Token ID | 60 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ascript | +1.257 |
forgiven | +1.244 |
heads | +1.153 |
forgiveness | +1.072 |
perfection | +1.056 |
Neg logit contributions | |
Interstitial | -1.714 |
loc | -1.657 |
ME | -1.624 |
方 | -1.603 |
psc | -1.578 |
Token | [ |
Token ID | 685 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ascript | +0.428 |
forgiven | +0.422 |
heads | +0.390 |
forgiveness | +0.368 |
perfection | +0.363 |
Neg logit contributions | |
Interstitial | -0.489 |
loc | -0.472 |
ME | -0.463 |
方 | -0.454 |
psc | -0.448 |
Token | App |
Token ID | 4677 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
Interstitial | +0.311 |
loc | +0.296 |
ME | +0.290 |
方 | +0.281 |
psc | +0.277 |
Neg logit contributions | |
ascript | -0.416 |
forgiven | -0.411 |
heads | -0.386 |
forgiveness | -0.369 |
perfection | -0.364 |
Token | Brain |
Token ID | 44687 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Interstitial | +0.061 |
loc | +0.059 |
ME | +0.059 |
方 | +0.057 |
psc | +0.056 |
Neg logit contributions | |
ascript | -0.051 |
forgiven | -0.050 |
heads | -0.046 |
forgiveness | -0.044 |
perfection | -0.043 |
Token | ] |
Token ID | 60 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
Interstitial | +1.446 |
loc | +1.409 |
ME | +1.388 |
方 | +1.340 |
psc | +1.329 |
Neg logit contributions | |
ascript | -1.281 |
forgiven | -1.248 |
heads | -1.130 |
forgiveness | -1.080 |
perfection | -1.064 |
Token | current |
Token ID | 1459 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Interstitial | +0.145 |
loc | +0.140 |
ME | +0.137 |
方 | +0.134 |
psc | +0.132 |
Neg logit contributions | |
ascript | -0.133 |
forgiven | -0.131 |
heads | -0.122 |
forgiveness | -0.115 |
perfection | -0.113 |
Token | scene |
Token ID | 3715 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Interstitial | +0.231 |
loc | +0.224 |
ME | +0.219 |
方 | +0.215 |
psc | +0.211 |
Neg logit contributions | |
ascript | -0.224 |
forgiven | -0.220 |
heads | -0.204 |
forgiveness | -0.193 |
perfection | -0.190 |
Token | , |
Token ID | 11 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
Interstitial | +0.480 |
loc | +0.468 |
ME | +0.460 |
方 | +0.450 |
psc | +0.445 |
Neg logit contributions | |
ascript | -0.377 |
forgiven | -0.368 |
heads | -0.336 |
forgiveness | -0.317 |
perfection | -0.313 |
Token | Re |
Token ID | 797 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
Interstitial | +0.052 |
loc | +0.051 |
ME | +0.050 |
方 | +0.048 |
psc | +0.048 |
Neg logit contributions | |
ascript | -0.057 |
forgiven | -0.056 |
heads | -0.052 |
forgiveness | -0.049 |
perfection | -0.049 |
Token | es |
Token ID | 274 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ascript | +0.188 |
forgiven | +0.185 |
heads | +0.173 |
forgiveness | +0.164 |
perfection | +0.163 |
Neg logit contributions | |
Interstitial | -0.171 |
loc | -0.165 |
ME | -0.162 |
方 | -0.156 |
psc | -0.155 |
Token | - |
Token ID | 12 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ascript | +1.076 |
forgiven | +1.062 |
heads | +1.006 |
forgiveness | +0.951 |
perfection | +0.940 |
Neg logit contributions | |
Interstitial | -0.830 |
loc | -0.791 |
ME | -0.773 |
方 | -0.757 |
psc | -0.742 |
Token | Jones |
Token ID | 25784 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ascript | +0.509 |
forgiven | +0.497 |
heads | +0.456 |
forgiveness | +0.431 |
perfection | +0.423 |
Neg logit contributions | |
Interstitial | -0.629 |
loc | -0.612 |
ME | -0.603 |
方 | -0.585 |
psc | -0.578 |
Token | sees |
Token ID | 7224 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
Interstitial | +0.849 |
loc | +0.834 |
ME | +0.816 |
方 | +0.796 |
psc | +0.788 |
Neg logit contributions | |
ascript | -0.700 |
forgiven | -0.680 |
heads | -0.619 |
forgiveness | -0.593 |
perfection | -0.581 |
Token | it |
Token ID | 340 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
ascript | +1.317 |
forgiven | +1.314 |
heads | +1.224 |
forgiveness | +1.153 |
perfection | +1.138 |
Neg logit contributions | |
Interstitial | -1.432 |
loc | -1.372 |
ME | -1.346 |
方 | -1.324 |
psc | -1.306 |
Token | this |
Token ID | 428 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Interstitial | +0.109 |
loc | +0.106 |
ME | +0.104 |
方 | +0.102 |
psc | +0.100 |
Neg logit contributions | |
ascript | -0.082 |
forgiven | -0.079 |
heads | -0.072 |
forgiveness | -0.068 |
perfection | -0.067 |
Token | way |
Token ID | 835 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ascript | +0.164 |
forgiven | +0.160 |
heads | +0.145 |
forgiveness | +0.135 |
perfection | +0.132 |
Neg logit contributions | |
Interstitial | -0.259 |
loc | -0.252 |
ME | -0.248 |
方 | -0.244 |
psc | -0.240 |
Token | take |
Token ID | 1011 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ascript | +0.322 |
forgiven | +0.314 |
heads | +0.291 |
forgiveness | +0.275 |
perfection | +0.270 |
Neg logit contributions | |
Interstitial | -0.351 |
loc | -0.341 |
ME | -0.334 |
方 | -0.326 |
psc | -0.322 |
Token | my |
Token ID | 616 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
ascript | +0.309 |
forgiven | +0.295 |
heads | +0.268 |
forgiveness | +0.248 |
bull | +0.246 |
Neg logit contributions | |
Interstitial | -0.445 |
loc | -0.438 |
ME | -0.429 |
方 | -0.420 |
psc | -0.416 |
Token | exams |
Token ID | 26420 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ascript | +0.156 |
forgiven | +0.154 |
heads | +0.142 |
forgiveness | +0.133 |
perfection | +0.131 |
Neg logit contributions | |
Interstitial | -0.186 |
loc | -0.180 |
ME | -0.177 |
方 | -0.173 |
psc | -0.171 |
Token | before |
Token ID | 878 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ascript | +0.590 |
forgiven | +0.567 |
heads | +0.521 |
forgiveness | +0.487 |
perfection | +0.480 |
Neg logit contributions | |
Interstitial | -0.794 |
loc | -0.780 |
ME | -0.763 |
方 | -0.747 |
psc | -0.739 |
Token | I |
Token ID | 314 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Interstitial | +0.497 |
loc | +0.484 |
ME | +0.473 |
方 | +0.458 |
psc | +0.453 |
Neg logit contributions | |
ascript | -0.505 |
forgiven | -0.487 |
heads | -0.451 |
forgiveness | -0.426 |
bull | -0.422 |
Token | gave |
Token ID | 2921 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
ascript | +0.642 |
forgiven | +0.633 |
heads | +0.585 |
forgiveness | +0.549 |
perfection | +0.540 |
Neg logit contributions | |
Interstitial | -0.782 |
loc | -0.756 |
ME | -0.742 |
方 | -0.728 |
psc | -0.718 |
Token | birth |
Token ID | 4082 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ascript | +1.184 |
forgiven | +1.165 |
heads | +1.073 |
forgiveness | +1.008 |
perfection | +0.992 |
Neg logit contributions | |
Interstitial | -1.471 |
loc | -1.426 |
ME | -1.399 |
方 | -1.372 |
psc | -1.352 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ascript | +0.466 |
forgiven | +0.457 |
heads | +0.414 |
forgiveness | +0.385 |
perfection | +0.378 |
Neg logit contributions | |
Interstitial | -0.747 |
loc | -0.728 |
ME | -0.714 |
方 | -0.700 |
psc | -0.694 |
Token | my |
Token ID | 616 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ascript | +0.268 |
forgiven | +0.260 |
heads | +0.240 |
forgiveness | +0.225 |
bull | +0.221 |
Neg logit contributions | |
Interstitial | -0.331 |
loc | -0.322 |
ME | -0.317 |
方 | -0.308 |
psc | -0.305 |
Token | daughter |
Token ID | 4957 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
ascript | +0.256 |
forgiven | +0.251 |
heads | +0.232 |
forgiveness | +0.218 |
perfection | +0.214 |
Neg logit contributions | |
Interstitial | -0.301 |
loc | -0.292 |
ME | -0.286 |
方 | -0.280 |
psc | -0.276 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ascript | +0.374 |
forgiven | +0.362 |
heads | +0.330 |
forgiveness | +0.309 |
perfection | +0.301 |
Neg logit contributions | |
Interstitial | -0.562 |
loc | -0.550 |
ME | -0.540 |
方 | -0.527 |
psc | -0.522 |
Token | making |
Token ID | 1642 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ascript | +0.177 |
forgiven | +0.174 |
heads | +0.161 |
forgiveness | +0.151 |
perfection | +0.149 |
Neg logit contributions | |
Interstitial | -0.219 |
loc | -0.212 |
ME | -0.208 |
方 | -0.204 |
psc | -0.201 |
Token | it |
Token ID | 340 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
ascript | +0.039 |
forgiven | +0.038 |
heads | +0.035 |
forgiveness | +0.033 |
perfection | +0.033 |
Neg logit contributions | |
Interstitial | -0.044 |
loc | -0.043 |
ME | -0.042 |
方 | -0.041 |
ordes | -0.040 |
Token | tougher |
Token ID | 20516 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ascript | +0.078 |
forgiven | +0.077 |
heads | +0.072 |
forgiveness | +0.067 |
perfection | +0.066 |
Neg logit contributions | |
Interstitial | -0.088 |
loc | -0.085 |
ME | -0.083 |
方 | -0.081 |
psc | -0.080 |
Token | for |
Token ID | 329 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ascript | +0.647 |
forgiven | +0.631 |
heads | +0.564 |
forgiveness | +0.520 |
perfection | +0.513 |
Neg logit contributions | |
Interstitial | -1.144 |
loc | -1.114 |
ME | -1.098 |
方 | -1.080 |
psc | -1.059 |
Token | her |
Token ID | 607 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
Interstitial | +0.024 |
loc | +0.023 |
ME | +0.023 |
方 | +0.022 |
psc | +0.022 |
Neg logit contributions | |
ascript | -0.020 |
forgiven | -0.020 |
heads | -0.018 |
forgiveness | -0.017 |
perfection | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ascript | +0.024 |
forgiven | +0.023 |
heads | +0.021 |
forgiveness | +0.020 |
perfection | +0.020 |
Neg logit contributions | |
Interstitial | -0.033 |
loc | -0.032 |
ME | -0.031 |
方 | -0.031 |
psc | -0.030 |
Token | survive |
Token ID | 7866 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ascript | +0.472 |
forgiven | +0.467 |
heads | +0.433 |
forgiveness | +0.406 |
perfection | +0.400 |
Neg logit contributions | |
Interstitial | -0.580 |
loc | -0.558 |
ME | -0.549 |
方 | -0.540 |
psc | -0.532 |
Token | mounting |
Token ID | 17260 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ascript | +0.650 |
forgiven | +0.639 |
heads | +0.589 |
forgiveness | +0.555 |
perfection | +0.547 |
Neg logit contributions | |
Interstitial | -0.773 |
loc | -0.749 |
ME | -0.734 |
方 | -0.720 |
psc | -0.708 |
Token | pressure |
Token ID | 3833 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ascript | +0.308 |
forgiven | +0.301 |
heads | +0.273 |
forgiveness | +0.255 |
perfection | +0.251 |
Neg logit contributions | |
Interstitial | -0.442 |
loc | -0.431 |
ME | -0.423 |
方 | -0.415 |
psc | -0.407 |
Token | in |
Token ID | 287 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Interstitial | +0.039 |
loc | +0.038 |
ME | +0.037 |
方 | +0.037 |
psc | +0.036 |
Neg logit contributions | |
ascript | -0.023 |
forgiven | -0.022 |
heads | -0.019 |
forgiveness | -0.018 |
perfection | -0.018 |
Token | Congress |
Token ID | 3162 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ascript | +0.363 |
forgiven | +0.358 |
heads | +0.332 |
forgiveness | +0.311 |
perfection | +0.306 |
Neg logit contributions | |
Interstitial | -0.442 |
loc | -0.427 |
ME | -0.419 |
方 | -0.412 |
psc | -0.406 |
Token | saying |
Token ID | 2282 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Interstitial | +0.094 |
loc | +0.091 |
ME | +0.089 |
方 | +0.087 |
psc | +0.086 |
Neg logit contributions | |
ascript | -0.083 |
forgiven | -0.081 |
heads | -0.075 |
forgiveness | -0.071 |
perfection | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
Interstitial | +0.385 |
loc | +0.372 |
ME | +0.364 |
方 | +0.357 |
psc | +0.352 |
Neg logit contributions | |
ascript | -0.352 |
forgiven | -0.347 |
heads | -0.322 |
forgiveness | -0.303 |
perfection | -0.299 |
Token | " |
Token ID | 366 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Interstitial | +0.119 |
loc | +0.115 |
ME | +0.113 |
方 | +0.110 |
psc | +0.109 |
Neg logit contributions | |
ascript | -0.124 |
forgiven | -0.122 |
heads | -0.113 |
forgiveness | -0.107 |
perfection | -0.106 |
Token | How |
Token ID | 2437 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
ascript | +0.334 |
forgiven | +0.329 |
heads | +0.305 |
forgiveness | +0.287 |
perfection | +0.282 |
Neg logit contributions | |
Interstitial | -0.390 |
loc | -0.377 |
ME | -0.370 |
方 | -0.363 |
psc | -0.358 |
Token | are |
Token ID | 389 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
ascript | +0.128 |
forgiven | +0.126 |
heads | +0.117 |
forgiveness | +0.111 |
perfection | +0.109 |
Neg logit contributions | |
Interstitial | -0.126 |
loc | -0.122 |
ME | -0.119 |
方 | -0.117 |
psc | -0.115 |
Token | we |
Token ID | 356 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
ascript | +0.554 |
forgiven | +0.544 |
heads | +0.496 |
forgiveness | +0.462 |
perfection | +0.454 |
Neg logit contributions | |
Interstitial | -0.821 |
loc | -0.797 |
ME | -0.782 |
方 | -0.769 |
psc | -0.759 |
Token | going |
Token ID | 1016 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ascript | +0.119 |
forgiven | +0.117 |
heads | +0.109 |
forgiveness | +0.102 |
perfection | +0.101 |
Neg logit contributions | |
Interstitial | -0.129 |
loc | -0.125 |
ME | -0.122 |
方 | -0.119 |
psc | -0.118 |
Token | to |
Token ID | 284 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Interstitial | +0.597 |
loc | +0.579 |
ME | +0.568 |
方 | +0.559 |
psc | +0.550 |
Neg logit contributions | |
ascript | -0.436 |
forgiven | -0.428 |
heads | -0.390 |
forgiveness | -0.366 |
perfection | -0.359 |
Token | make |
Token ID | 787 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ascript | +0.362 |
forgiven | +0.358 |
heads | +0.333 |
forgiveness | +0.314 |
perfection | +0.310 |
Neg logit contributions | |
Interstitial | -0.395 |
loc | -0.380 |
ME | -0.373 |
方 | -0.366 |
psc | -0.361 |
Token | this |
Token ID | 428 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ascript | +0.233 |
forgiven | +0.229 |
heads | +0.211 |
forgiveness | +0.198 |
perfection | +0.195 |
Neg logit contributions | |
Interstitial | -0.280 |
loc | -0.272 |
ME | -0.267 |
方 | -0.261 |
psc | -0.257 |
Token | easier |
Token ID | 4577 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ascript | +0.248 |
forgiven | +0.243 |
heads | +0.222 |
forgiveness | +0.206 |
perfection | +0.203 |
Neg logit contributions | |
Interstitial | -0.374 |
loc | -0.364 |
ME | -0.358 |
方 | -0.351 |
psc | -0.346 |
Token | comple |
Token ID | 1224 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ascript | +0.194 |
forgiven | +0.189 |
heads | +0.171 |
forgiveness | +0.160 |
bull | +0.157 |
Neg logit contributions | |
Interstitial | -0.278 |
loc | -0.271 |
ME | -0.267 |
方 | -0.261 |
psc | -0.257 |
Token | teness |
Token ID | 43205 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ascript | +0.374 |
forgiven | +0.367 |
heads | +0.330 |
forgiveness | +0.303 |
perfection | +0.296 |
Neg logit contributions | |
Interstitial | -0.715 |
loc | -0.697 |
ME | -0.685 |
方 | -0.674 |
psc | -0.667 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ascript | +0.955 |
forgiven | +0.941 |
heads | +0.875 |
forgiveness | +0.828 |
perfection | +0.816 |
Neg logit contributions | |
Interstitial | -0.967 |
loc | -0.934 |
ME | -0.915 |
方 | -0.896 |
psc | -0.881 |
Token | here |
Token ID | 994 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
ascript | +0.030 |
forgiven | +0.029 |
heads | +0.027 |
forgiveness | +0.025 |
perfection | +0.025 |
Neg logit contributions | |
Interstitial | -0.034 |
loc | -0.033 |
ME | -0.032 |
方 | -0.032 |
psc | -0.031 |
Token | is |
Token ID | 318 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Interstitial | +0.131 |
loc | +0.127 |
ME | +0.125 |
方 | +0.122 |
psc | +0.121 |
Neg logit contributions | |
ascript | -0.093 |
forgiven | -0.092 |
heads | -0.084 |
forgiveness | -0.078 |
perfection | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
ascript | +0.269 |
forgiven | +0.265 |
heads | +0.246 |
forgiveness | +0.233 |
perfection | +0.229 |
Neg logit contributions | |
Interstitial | -0.264 |
loc | -0.255 |
ME | -0.251 |
方 | -0.245 |
psc | -0.240 |
Token | real |
Token ID | 1103 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
ascript | +0.072 |
forgiven | +0.070 |
heads | +0.065 |
forgiveness | +0.061 |
perfection | +0.060 |
Neg logit contributions | |
Interstitial | -0.089 |
loc | -0.087 |
ME | -0.085 |
方 | -0.083 |
psc | -0.082 |
Token | - |
Token ID | 12 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ascript | +0.146 |
forgiven | +0.144 |
heads | +0.132 |
forgiveness | +0.125 |
perfection | +0.122 |
Neg logit contributions | |
Interstitial | -0.171 |
loc | -0.166 |
ME | -0.163 |
方 | -0.160 |
psc | -0.157 |
Token | time |
Token ID | 2435 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ascript | +0.238 |
forgiven | +0.234 |
heads | +0.217 |
forgiveness | +0.207 |
perfection | +0.202 |
Neg logit contributions | |
Interstitial | -0.246 |
loc | -0.241 |
ME | -0.236 |
方 | -0.229 |
psc | -0.226 |
Token | / |
Token ID | 1220 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
ascript | +0.182 |
forgiven | +0.179 |
heads | +0.163 |
forgiveness | +0.153 |
perfection | +0.150 |
Neg logit contributions | |
Interstitial | -0.257 |
loc | -0.249 |
ME | -0.245 |
方 | -0.241 |
psc | -0.237 |
Token | streaming |
Token ID | 11305 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
Interstitial | +0.129 |
loc | +0.126 |
ME | +0.123 |
方 | +0.121 |
psc | +0.119 |
Neg logit contributions | |
ascript | -0.096 |
forgiven | -0.094 |
heads | -0.086 |
forgiveness | -0.081 |
perfection | -0.080 |
Token | ruly |
Token ID | 34715 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Interstitial | +0.013 |
loc | +0.013 |
ME | +0.012 |
方 | +0.012 |
psc | +0.012 |
Neg logit contributions | |
ascript | -0.013 |
forgiven | -0.013 |
heads | -0.012 |
forgiveness | -0.011 |
perfection | -0.011 |
Token | slave |
Token ID | 11778 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ascript | +1.004 |
forgiven | +0.993 |
heads | +0.920 |
forgiveness | +0.865 |
perfection | +0.853 |
Neg logit contributions | |
Interstitial | -1.173 |
loc | -1.133 |
ME | -1.111 |
方 | -1.090 |
psc | -1.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Interstitial | +0.615 |
loc | +0.602 |
ME | +0.590 |
方 | +0.580 |
psc | +0.574 |
Neg logit contributions | |
ascript | -0.357 |
forgiven | -0.347 |
heads | -0.312 |
forgiveness | -0.290 |
perfection | -0.283 |
Token | The |
Token ID | 383 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
ascript | +0.272 |
forgiven | +0.268 |
heads | +0.249 |
forgiveness | +0.236 |
perfection | +0.233 |
Neg logit contributions | |
Interstitial | -0.260 |
loc | -0.251 |
ME | -0.246 |
方 | -0.240 |
psc | -0.236 |
Token | story |
Token ID | 1621 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Interstitial | +0.067 |
loc | +0.065 |
ME | +0.063 |
方 | +0.062 |
psc | +0.061 |
Neg logit contributions | |
ascript | -0.056 |
forgiven | -0.055 |
heads | -0.051 |
forgiveness | -0.048 |
perfection | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ascript | +0.372 |
forgiven | +0.366 |
heads | +0.336 |
forgiveness | +0.314 |
perfection | +0.308 |
Neg logit contributions | |
Interstitial | -0.522 |
loc | -0.506 |
ME | -0.497 |
方 | -0.488 |
psc | -0.482 |
Token | almost |
Token ID | 2048 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ascript | +0.305 |
forgiven | +0.300 |
heads | +0.276 |
forgiveness | +0.260 |
perfection | +0.255 |
Neg logit contributions | |
Interstitial | -0.379 |
loc | -0.367 |
ME | -0.360 |
方 | -0.353 |
psc | -0.348 |
Token | certainly |
Token ID | 3729 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ascript | +0.403 |
forgiven | +0.397 |
heads | +0.366 |
forgiveness | +0.343 |
perfection | +0.338 |
Neg logit contributions | |
Interstitial | -0.514 |
loc | -0.498 |
ME | -0.489 |
方 | -0.480 |
psc | -0.474 |
Token | Greek |
Token ID | 8312 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
Interstitial | +0.428 |
loc | +0.420 |
ME | +0.411 |
方 | +0.401 |
psc | +0.394 |
Neg logit contributions | |
ascript | -0.307 |
forgiven | -0.296 |
heads | -0.271 |
forgiveness | -0.256 |
perfection | -0.251 |
Token | propaganda |
Token ID | 11613 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
Interstitial | +0.134 |
loc | +0.131 |
ME | +0.128 |
方 | +0.125 |
psc | +0.124 |
Neg logit contributions | |
ascript | -0.110 |
forgiven | -0.108 |
heads | -0.099 |
forgiveness | -0.093 |
perfection | -0.091 |
Token | designed |
Token ID | 3562 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Interstitial | +0.123 |
loc | +0.120 |
ME | +0.117 |
方 | +0.115 |
psc | +0.114 |
Neg logit contributions | |
ascript | -0.102 |
forgiven | -0.099 |
heads | -0.091 |
forgiveness | -0.086 |
bull | -0.084 |
Token | playing |
Token ID | 2712 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Interstitial | +0.512 |
loc | +0.496 |
ME | +0.487 |
方 | +0.477 |
psc | +0.470 |
Neg logit contributions | |
ascript | -0.410 |
forgiven | -0.401 |
heads | -0.369 |
forgiveness | -0.348 |
perfection | -0.341 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Interstitial | +0.604 |
loc | +0.585 |
ME | +0.573 |
方 | +0.562 |
psc | +0.554 |
Neg logit contributions | |
ascript | -0.525 |
forgiven | -0.517 |
heads | -0.477 |
forgiveness | -0.450 |
perfection | -0.443 |
Token | l |
Token ID | 300 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Interstitial | +0.284 |
loc | +0.275 |
ME | +0.270 |
方 | +0.265 |
psc | +0.261 |
Neg logit contributions | |
ascript | -0.224 |
forgiven | -0.220 |
heads | -0.203 |
forgiveness | -0.190 |
perfection | -0.187 |
Token | ute |
Token ID | 1133 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
ascript | +0.370 |
forgiven | +0.364 |
heads | +0.338 |
forgiveness | +0.319 |
perfection | +0.315 |
Neg logit contributions | |
Interstitial | -0.387 |
loc | -0.371 |
ME | -0.364 |
方 | -0.360 |
psc | -0.351 |
Token | – |
Token ID | 784 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
Interstitial | +1.706 |
loc | +1.659 |
ME | +1.625 |
方 | +1.588 |
psc | +1.561 |
Neg logit contributions | |
ascript | -1.580 |
forgiven | -1.549 |
heads | -1.425 |
forgiveness | -1.355 |
perfection | -1.320 |
Token | play |
Token ID | 711 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ascript | +0.118 |
forgiven | +0.117 |
heads | +0.108 |
forgiveness | +0.102 |
perfection | +0.101 |
Neg logit contributions | |
Interstitial | -0.143 |
loc | -0.139 |
ME | -0.136 |
方 | -0.134 |
psc | -0.132 |
Token | a |
Token ID | 257 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Interstitial | +0.378 |
loc | +0.364 |
ME | +0.357 |
方 | +0.351 |
psc | +0.346 |
Neg logit contributions | |
ascript | -0.316 |
forgiven | -0.312 |
heads | -0.290 |
forgiveness | -0.272 |
perfection | -0.268 |
Token | l |
Token ID | 300 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Interstitial | +0.364 |
loc | +0.351 |
ME | +0.345 |
方 | +0.338 |
psc | +0.333 |
Neg logit contributions | |
ascript | -0.297 |
forgiven | -0.294 |
heads | -0.273 |
forgiveness | -0.256 |
perfection | -0.252 |
Token | ute |
Token ID | 1133 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
ascript | +0.163 |
forgiven | +0.160 |
heads | +0.145 |
forgiveness | +0.134 |
perfection | +0.131 |
Neg logit contributions | |
Interstitial | -0.282 |
loc | -0.274 |
ME | -0.269 |
方 | -0.266 |
psc | -0.262 |
Token | on |
Token ID | 319 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Interstitial | +1.947 |
loc | +1.903 |
ME | +1.867 |
方 | +1.822 |
psc | +1.800 |
Neg logit contributions | |
ascript | -1.408 |
forgiven | -1.372 |
heads | -1.244 |
forgiveness | -1.172 |
perfection | -1.140 |
Token | your |
Token ID | 534 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Interstitial | +0.509 |
loc | +0.491 |
ME | +0.482 |
方 | +0.473 |
psc | +0.465 |
Neg logit contributions | |
ascript | -0.453 |
forgiven | -0.448 |
heads | -0.418 |
forgiveness | -0.393 |
perfection | -0.388 |
Token | sovereignty |
Token ID | 18582 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
Interstitial | +0.966 |
loc | +0.937 |
ME | +0.920 |
方 | +0.900 |
psc | +0.887 |
Neg logit contributions | |
ascript | -0.816 |
forgiven | -0.802 |
heads | -0.739 |
forgiveness | -0.695 |
perfection | -0.685 |
Token | , |
Token ID | 11 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
Interstitial | +0.110 |
loc | +0.107 |
ME | +0.105 |
方 | +0.103 |
psc | +0.101 |
Neg logit contributions | |
ascript | -0.100 |
forgiven | -0.098 |
heads | -0.091 |
forgiveness | -0.085 |
perfection | -0.084 |
Token | his |
Token ID | 465 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Interstitial | +0.009 |
loc | +0.008 |
ME | +0.008 |
方 | +0.008 |
psc | +0.008 |
Neg logit contributions | |
ascript | -0.009 |
forgiven | -0.009 |
heads | -0.008 |
forgiveness | -0.008 |
perfection | -0.008 |
Token | notion |
Token ID | 9495 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
Interstitial | +0.248 |
loc | +0.241 |
ME | +0.236 |
方 | +0.231 |
psc | +0.228 |
Neg logit contributions | |
ascript | -0.208 |
forgiven | -0.204 |
heads | -0.188 |
forgiveness | -0.177 |
perfection | -0.174 |
Token | is |
Token ID | 318 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
ascript | +0.014 |
forgiven | +0.014 |
heads | +0.013 |
forgiveness | +0.012 |
perfection | +0.012 |
Neg logit contributions | |
Interstitial | -0.023 |
loc | -0.022 |
ME | -0.022 |
方 | -0.021 |
psc | -0.021 |
Token | � |
Token ID | 564 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
Interstitial | +0.081 |
loc | +0.079 |
ME | +0.077 |
方 | +0.076 |
psc | +0.074 |
Neg logit contributions | |
ascript | -0.064 |
forgiven | -0.062 |
heads | -0.057 |
forgiveness | -0.054 |
perfection | -0.053 |
Token | � |
Token ID | 246 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Interstitial | +0.166 |
loc | +0.160 |
ME | +0.157 |
方 | +0.153 |
psc | +0.151 |
Neg logit contributions | |
ascript | -0.157 |
forgiven | -0.155 |
heads | -0.144 |
forgiveness | -0.136 |
perfection | -0.134 |
Token | nob |
Token ID | 34952 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Interstitial | +0.232 |
loc | +0.224 |
ME | +0.219 |
方 | +0.215 |
psc | +0.211 |
Neg logit contributions | |
ascript | -0.226 |
forgiven | -0.223 |
heads | -0.207 |
forgiveness | -0.196 |
perfection | -0.193 |
Token | ody |
Token ID | 1118 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Interstitial | +0.473 |
loc | +0.458 |
ME | +0.450 |
方 | +0.441 |
psc | +0.436 |
Neg logit contributions | |
ascript | -0.365 |
forgiven | -0.359 |
heads | -0.331 |
forgiveness | -0.310 |
perfection | -0.305 |
Token | gets |
Token ID | 3011 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
Interstitial | +0.444 |
loc | +0.434 |
ME | +0.425 |
方 | +0.416 |
psc | +0.409 |
Neg logit contributions | |
ascript | -0.369 |
forgiven | -0.360 |
heads | -0.328 |
forgiveness | -0.313 |
perfection | -0.308 |
Token | to |
Token ID | 284 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ascript | +0.053 |
forgiven | +0.051 |
heads | +0.047 |
forgiveness | +0.044 |
bull | +0.044 |
Neg logit contributions | |
Interstitial | -0.065 |
loc | -0.063 |
ME | -0.062 |
方 | -0.061 |
psc | -0.060 |
Token | get |
Token ID | 651 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
ascript | +0.180 |
forgiven | +0.178 |
heads | +0.163 |
forgiveness | +0.153 |
perfection | +0.150 |
Neg logit contributions | |
Interstitial | -0.239 |
loc | -0.231 |
ME | -0.227 |
方 | -0.223 |
psc | -0.220 |
Token | green |
Token ID | 4077 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
Interstitial | +0.041 |
loc | +0.041 |
ME | +0.040 |
方 | +0.039 |
psc | +0.038 |
Neg logit contributions | |
ascript | -0.038 |
forgiven | -0.037 |
heads | -0.034 |
forgiveness | -0.032 |
bull | -0.032 |
Token | cards |
Token ID | 4116 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ascript | +0.188 |
forgiven | +0.186 |
heads | +0.174 |
forgiveness | +0.166 |
perfection | +0.165 |
Neg logit contributions | |
Interstitial | -0.135 |
loc | -0.129 |
ME | -0.126 |
方 | -0.123 |
psc | -0.120 |
Token | for |
Token ID | 329 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
ascript | +0.533 |
forgiven | +0.513 |
heads | +0.471 |
forgiveness | +0.436 |
perfection | +0.434 |
Neg logit contributions | |
Interstitial | -0.774 |
loc | -0.759 |
ME | -0.747 |
方 | -0.731 |
psc | -0.720 |
Token | their |
Token ID | 511 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Interstitial | +0.089 |
loc | +0.087 |
ME | +0.085 |
方 | +0.083 |
psc | +0.082 |
Neg logit contributions | |
ascript | -0.077 |
forgiven | -0.075 |
heads | -0.069 |
forgiveness | -0.065 |
perfection | -0.064 |
Token | spouses |
Token ID | 30250 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
ascript | +0.443 |
forgiven | +0.437 |
heads | +0.404 |
forgiveness | +0.378 |
perfection | +0.372 |
Neg logit contributions | |
Interstitial | -0.565 |
loc | -0.546 |
ME | -0.536 |
方 | -0.526 |
psc | -0.519 |
Token | and |
Token ID | 290 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Interstitial | +1.707 |
loc | +1.687 |
ME | +1.656 |
方 | +1.602 |
psc | +1.573 |
Neg logit contributions | |
ascript | -1.513 |
forgiven | -1.441 |
heads | -1.322 |
forgiveness | -1.261 |
perfection | -1.253 |
Token | minor |
Token ID | 4159 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ascript | +0.103 |
forgiven | +0.099 |
heads | +0.090 |
forgiveness | +0.085 |
perfection | +0.084 |
Neg logit contributions | |
Interstitial | -0.127 |
loc | -0.125 |
ME | -0.122 |
方 | -0.119 |
psc | -0.117 |
Token | children |
Token ID | 1751 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ascript | +0.538 |
forgiven | +0.531 |
heads | +0.488 |
forgiveness | +0.455 |
perfection | +0.448 |
Neg logit contributions | |
Interstitial | -0.750 |
loc | -0.725 |
ME | -0.712 |
方 | -0.700 |
psc | -0.691 |
Token | . |
Token ID | 13 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
Interstitial | +0.373 |
loc | +0.365 |
ME | +0.359 |
方 | +0.349 |
psc | +0.344 |
Neg logit contributions | |
ascript | -0.282 |
forgiven | -0.269 |
heads | -0.247 |
forgiveness | -0.233 |
perfection | -0.231 |
Token |
|
Token ID | 198 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Interstitial | +0.093 |
loc | +0.090 |
ME | +0.088 |
方 | +0.086 |
psc | +0.085 |
Neg logit contributions | |
ascript | -0.097 |
forgiven | -0.096 |
heads | -0.089 |
forgiveness | -0.085 |
perfection | -0.084 |
Token | aza |
Token ID | 7056 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
Interstitial | +0.821 |
loc | +0.792 |
ME | +0.771 |
方 | +0.750 |
psc | +0.738 |
Neg logit contributions | |
ascript | -1.047 |
forgiven | -1.035 |
heads | -0.969 |
forgiveness | -0.926 |
perfection | -0.915 |
Token | Ha |
Token ID | 9398 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
Interstitial | +1.846 |
loc | +1.798 |
ME | +1.762 |
方 | +1.713 |
psc | +1.693 |
Neg logit contributions | |
ascript | -1.736 |
forgiven | -1.707 |
heads | -1.561 |
forgiveness | -1.495 |
perfection | -1.468 |
Token | ider |
Token ID | 1304 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Interstitial | +0.106 |
loc | +0.103 |
ME | +0.102 |
方 | +0.098 |
psc | +0.098 |
Neg logit contributions | |
ascript | -0.083 |
forgiven | -0.081 |
heads | -0.074 |
forgiveness | -0.070 |
perfection | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
Interstitial | +0.540 |
loc | +0.523 |
ME | +0.512 |
方 | +0.500 |
psc | +0.493 |
Neg logit contributions | |
ascript | -0.514 |
forgiven | -0.506 |
heads | -0.467 |
forgiveness | -0.444 |
perfection | -0.438 |
Token | an |
Token ID | 281 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Interstitial | +0.081 |
loc | +0.079 |
ME | +0.078 |
方 | +0.076 |
psc | +0.075 |
Neg logit contributions | |
ascript | -0.065 |
forgiven | -0.063 |
heads | -0.058 |
forgiveness | -0.055 |
perfection | -0.054 |
Token | associate |
Token ID | 11602 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Interstitial | +0.449 |
loc | +0.436 |
ME | +0.427 |
方 | +0.417 |
psc | +0.410 |
Neg logit contributions | |
ascript | -0.399 |
forgiven | -0.393 |
heads | -0.363 |
forgiveness | -0.343 |
perfection | -0.337 |
Token | professor |
Token ID | 6240 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Interstitial | +1.461 |
loc | +1.435 |
ME | +1.403 |
方 | +1.365 |
psc | +1.337 |
Neg logit contributions | |
ascript | -1.398 |
forgiven | -1.367 |
heads | -1.248 |
forgiveness | -1.194 |
perfection | -1.170 |
Token | at |
Token ID | 379 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Interstitial | +1.122 |
loc | +1.096 |
ME | +1.076 |
方 | +1.054 |
psc | +1.039 |
Neg logit contributions | |
ascript | -0.765 |
forgiven | -0.752 |
heads | -0.681 |
forgiveness | -0.640 |
perfection | -0.629 |
Token | the |
Token ID | 262 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Interstitial | +0.502 |
loc | +0.482 |
ME | +0.472 |
方 | +0.461 |
psc | +0.454 |
Neg logit contributions | |
ascript | -0.550 |
forgiven | -0.545 |
heads | -0.510 |
forgiveness | -0.483 |
perfection | -0.477 |
Token | Ted |
Token ID | 11396 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
Interstitial | +0.434 |
loc | +0.415 |
ME | +0.404 |
方 | +0.394 |
psc | +0.387 |
Neg logit contributions | |
ascript | -0.608 |
forgiven | -0.602 |
heads | -0.568 |
forgiveness | -0.541 |
perfection | -0.535 |
Token | Rogers |
Token ID | 15372 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ascript | +0.140 |
forgiven | +0.138 |
heads | +0.128 |
forgiveness | +0.121 |
perfection | +0.119 |
Neg logit contributions | |
Interstitial | -0.140 |
loc | -0.135 |
ME | -0.132 |
方 | -0.130 |
psc | -0.128 |
Token | already |
Token ID | 1541 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
Interstitial | +0.722 |
loc | +0.709 |
ME | +0.691 |
方 | +0.680 |
psc | +0.666 |
Neg logit contributions | |
ascript | -0.614 |
forgiven | -0.586 |
heads | -0.543 |
forgiveness | -0.518 |
bull | -0.508 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
Interstitial | +1.221 |
loc | +1.203 |
ME | +1.171 |
方 | +1.150 |
psc | +1.132 |
Neg logit contributions | |
ascript | -1.033 |
forgiven | -0.979 |
heads | -0.908 |
forgiveness | -0.875 |
perfection | -0.853 |
Token | much |
Token ID | 881 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Interstitial | +0.144 |
loc | +0.141 |
ME | +0.138 |
方 | +0.135 |
psc | +0.132 |
Neg logit contributions | |
ascript | -0.115 |
forgiven | -0.112 |
heads | -0.102 |
forgiveness | -0.096 |
bull | -0.095 |
Token | from |
Token ID | 422 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
loc | +1.161 |
Interstitial | +1.157 |
ME | +1.136 |
方 | +1.111 |
psc | +1.089 |
Neg logit contributions | |
ascript | -0.703 |
forgiven | -0.642 |
heads | -0.572 |
bull | -0.538 |
forgiveness | -0.526 |
Token | Ly |
Token ID | 9334 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Interstitial | +0.214 |
loc | +0.209 |
ME | +0.205 |
方 | +0.200 |
psc | +0.197 |
Neg logit contributions | |
ascript | -0.201 |
forgiven | -0.196 |
heads | -0.180 |
forgiveness | -0.171 |
perfection | -0.168 |
Token | uba |
Token ID | 22013 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
ascript | +0.145 |
forgiven | +0.143 |
heads | +0.130 |
forgiveness | +0.120 |
perfection | +0.118 |
Neg logit contributions | |
Interstitial | -0.261 |
loc | -0.258 |
ME | -0.251 |
psc | -0.245 |
方 | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
loc | +1.574 |
Interstitial | +1.571 |
ME | +1.523 |
方 | +1.491 |
psc | +1.465 |
Neg logit contributions | |
ascript | -1.444 |
forgiven | -1.391 |
heads | -1.261 |
forgiveness | -1.207 |
perfection | -1.189 |
Token | Work |
Token ID | 5521 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Interstitial | +0.310 |
loc | +0.302 |
ME | +0.295 |
方 | +0.288 |
psc | +0.283 |
Neg logit contributions | |
ascript | -0.342 |
forgiven | -0.334 |
heads | -0.309 |
forgiveness | -0.295 |
perfection | -0.292 |
Token | on |
Token ID | 319 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Interstitial | +0.847 |
loc | +0.826 |
ME | +0.810 |
方 | +0.795 |
psc | +0.784 |
Neg logit contributions | |
ascript | -0.634 |
forgiven | -0.622 |
heads | -0.569 |
forgiveness | -0.535 |
perfection | -0.526 |
Token | her |
Token ID | 607 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Interstitial | +0.647 |
loc | +0.628 |
ME | +0.615 |
方 | +0.602 |
psc | +0.592 |
Neg logit contributions | |
ascript | -0.610 |
forgiven | -0.600 |
heads | -0.554 |
forgiveness | -0.524 |
perfection | -0.515 |
Token | stomach |
Token ID | 11384 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Interstitial | +0.488 |
loc | +0.474 |
ME | +0.465 |
方 | +0.455 |
psc | +0.448 |
Neg logit contributions | |
ascript | -0.433 |
forgiven | -0.425 |
heads | -0.391 |
forgiveness | -0.370 |
perfection | -0.363 |
Token | 36 |
Token ID | 4570 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
Interstitial | +0.511 |
loc | +0.498 |
ME | +0.488 |
方 | +0.476 |
psc | +0.468 |
Neg logit contributions | |
ascript | -0.519 |
forgiven | -0.509 |
heads | -0.469 |
forgiveness | -0.447 |
perfection | -0.441 |
Token | MW |
Token ID | 29961 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ascript | +0.091 |
forgiven | +0.090 |
heads | +0.084 |
forgiveness | +0.080 |
perfection | +0.079 |
Neg logit contributions | |
Interstitial | -0.078 |
loc | -0.075 |
ME | -0.074 |
方 | -0.072 |
psc | -0.071 |
Token | gas |
Token ID | 3623 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Interstitial | +0.727 |
loc | +0.710 |
ME | +0.698 |
方 | +0.678 |
psc | +0.667 |
Neg logit contributions | |
ascript | -0.748 |
forgiven | -0.738 |
heads | -0.678 |
forgiveness | -0.650 |
perfection | -0.641 |
Token | turbines |
Token ID | 35658 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Interstitial | +0.498 |
loc | +0.481 |
ME | +0.471 |
方 | +0.460 |
psc | +0.452 |
Neg logit contributions | |
ascript | -0.534 |
forgiven | -0.524 |
heads | -0.485 |
forgiveness | -0.464 |
perfection | -0.457 |
Token | driving |
Token ID | 5059 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Interstitial | +1.369 |
loc | +1.367 |
ME | +1.345 |
方 | +1.299 |
psc | +1.285 |
Neg logit contributions | |
ascript | -1.104 |
forgiven | -1.063 |
heads | -0.955 |
forgiveness | -0.931 |
perfection | -0.911 |
Token | electric |
Token ID | 5186 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
Interstitial | +1.395 |
loc | +1.377 |
ME | +1.345 |
方 | +1.319 |
psc | +1.277 |
Neg logit contributions | |
ascript | -1.546 |
forgiven | -1.506 |
heads | -1.367 |
forgiveness | -1.321 |
bull | -1.304 |
Token | motors |
Token ID | 24699 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Interstitial | +1.387 |
loc | +1.347 |
ME | +1.320 |
方 | +1.283 |
psc | +1.254 |
Neg logit contributions | |
ascript | -1.892 |
forgiven | -1.852 |
heads | -1.688 |
forgiveness | -1.644 |
perfection | -1.619 |
Token | .) |
Token ID | 2014 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Interstitial | +1.183 |
loc | +1.164 |
ME | +1.142 |
方 | +1.111 |
psc | +1.102 |
Neg logit contributions | |
ascript | -0.893 |
forgiven | -0.868 |
heads | -0.774 |
forgiveness | -0.748 |
perfection | -0.732 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Interstitial | +0.644 |
loc | +0.623 |
ME | +0.612 |
方 | +0.596 |
psc | +0.586 |
Neg logit contributions | |
ascript | -0.700 |
forgiven | -0.686 |
heads | -0.636 |
forgiveness | -0.607 |
perfection | -0.598 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Interstitial | +0.565 |
loc | +0.544 |
ME | +0.536 |
方 | +0.520 |
psc | +0.511 |
Neg logit contributions | |
ascript | -0.629 |
forgiven | -0.616 |
heads | -0.573 |
forgiveness | -0.546 |
perfection | -0.538 |
Token | The |
Token ID | 464 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Interstitial | +0.634 |
loc | +0.614 |
ME | +0.605 |
方 | +0.586 |
psc | +0.579 |
Neg logit contributions | |
ascript | -0.592 |
forgiven | -0.579 |
heads | -0.538 |
forgiveness | -0.508 |
perfection | -0.501 |
Token | act |
Token ID | 719 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
ascript | +0.210 |
forgiven | +0.208 |
heads | +0.193 |
forgiveness | +0.182 |
perfection | +0.180 |
Neg logit contributions | |
Interstitial | -0.223 |
loc | -0.215 |
ME | -0.211 |
方 | -0.207 |
psc | -0.204 |
Token | on |
Token ID | 319 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ascript | +0.047 |
forgiven | +0.046 |
heads | +0.042 |
forgiveness | +0.039 |
perfection | +0.039 |
Neg logit contributions | |
Interstitial | -0.069 |
loc | -0.068 |
ME | -0.066 |
方 | -0.065 |
psc | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Interstitial | +0.229 |
loc | +0.222 |
ME | +0.217 |
方 | +0.212 |
psc | +0.209 |
Neg logit contributions | |
ascript | -0.216 |
forgiven | -0.213 |
heads | -0.197 |
forgiveness | -0.186 |
perfection | -0.183 |
Token | commissioner |
Token ID | 16248 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Interstitial | +0.165 |
loc | +0.160 |
ME | +0.157 |
方 | +0.154 |
psc | +0.152 |
Neg logit contributions | |
ascript | -0.143 |
forgiven | -0.141 |
heads | -0.130 |
forgiveness | -0.122 |
perfection | -0.120 |
Token | of |
Token ID | 286 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
ascript | +0.666 |
forgiven | +0.658 |
heads | +0.607 |
forgiveness | +0.569 |
perfection | +0.559 |
Neg logit contributions | |
Interstitial | -0.844 |
loc | -0.816 |
ME | -0.801 |
方 | -0.787 |
psc | -0.776 |
Token | official |
Token ID | 1743 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
ascript | +0.092 |
forgiven | +0.091 |
heads | +0.085 |
forgiveness | +0.080 |
perfection | +0.079 |
Neg logit contributions | |
Interstitial | -0.097 |
loc | -0.094 |
ME | -0.092 |
方 | -0.090 |
psc | -0.088 |
Token | language |
Token ID | 3303 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
Interstitial | +1.507 |
loc | +1.480 |
ME | +1.456 |
方 | +1.417 |
psc | +1.391 |
Neg logit contributions | |
ascript | -1.242 |
forgiven | -1.222 |
heads | -1.094 |
forgiveness | -1.038 |
bull | -1.031 |
Token | 's |
Token ID | 338 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
Interstitial | +0.055 |
loc | +0.053 |
ME | +0.052 |
方 | +0.051 |
psc | +0.050 |
Neg logit contributions | |
ascript | -0.049 |
forgiven | -0.047 |
heads | -0.044 |
forgiveness | -0.041 |
perfection | -0.040 |
Token | recommendation |
Token ID | 15602 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
Interstitial | +0.119 |
loc | +0.116 |
ME | +0.114 |
方 | +0.112 |
psc | +0.110 |
Neg logit contributions | |
ascript | -0.099 |
forgiven | -0.097 |
heads | -0.089 |
forgiveness | -0.083 |
perfection | -0.082 |
Token | that |
Token ID | 326 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ascript | +0.130 |
forgiven | +0.127 |
heads | +0.116 |
forgiveness | +0.109 |
perfection | +0.107 |
Neg logit contributions | |
Interstitial | -0.181 |
loc | -0.177 |
ME | -0.174 |
方 | -0.170 |
psc | -0.168 |
Token | all |
Token ID | 477 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ascript | +0.234 |
forgiven | +0.231 |
heads | +0.214 |
forgiveness | +0.202 |
perfection | +0.199 |
Neg logit contributions | |
Interstitial | -0.259 |
loc | -0.250 |
ME | -0.245 |
方 | -0.240 |
psc | -0.236 |