Token | vim |
Token ID | 43907 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
RED | +0.234 |
士 | +0.224 |
quished | +0.218 |
gio | +0.213 |
Thrones | +0.212 |
Neg logit contributions | |
ofer | -0.342 |
ele | -0.262 |
etz | -0.260 |
wards | -0.257 |
itness | -0.257 |
Token | < |
Token ID | 27 |
Feature activation | +6.79e+00 |
Pos logit contributions | |
ofer | +0.735 |
ele | +0.515 |
etz | +0.509 |
wards | +0.503 |
itness | +0.500 |
Neg logit contributions | |
RED | -0.866 |
士 | -0.839 |
quished | -0.822 |
Thrones | -0.806 |
gio | -0.805 |
Token | 570 |
Token ID | 39254 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ofer | +5.530 |
ele | +4.020 |
wards | +3.945 |
etz | +3.848 |
itness | +3.838 |
Neg logit contributions | |
RED | -5.898 |
quished | -5.768 |
士 | -5.714 |
Thrones | -5.676 |
Enix | -5.549 |
Token | : |
Token ID | 25 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ofer | +2.643 |
ele | +2.048 |
etz | +2.012 |
wards | +2.003 |
itness | +1.986 |
Neg logit contributions | |
RED | -1.848 |
士 | -1.781 |
quished | -1.741 |
Thrones | -1.707 |
gio | -1.685 |
Token | set |
Token ID | 900 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ofer | +1.826 |
ele | +1.427 |
etz | +1.415 |
wards | +1.404 |
itness | +1.399 |
Neg logit contributions | |
RED | -1.077 |
士 | -1.028 |
quished | -0.997 |
Thrones | -0.969 |
gio | -0.967 |
Token | sw |
Token ID | 1509 |
Feature activation | +1.73e+01 |
Pos logit contributions | |
ofer | +0.215 |
ele | +0.165 |
etz | +0.164 |
itness | +0.162 |
wards | +0.162 |
Neg logit contributions | |
RED | -0.149 |
士 | -0.142 |
quished | -0.138 |
gio | -0.135 |
Thrones | -0.135 |
Token | = |
Token ID | 28 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
ofer | +15.051 |
itness | +11.593 |
ele | +11.567 |
wards | +11.308 |
etz | +11.293 |
Neg logit contributions | |
RED | -11.726 |
士 | -11.666 |
Thrones | -11.336 |
Enix | -10.854 |
quished | -10.654 |
Token | 4 |
Token ID | 19 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ofer | +6.484 |
ele | +4.697 |
wards | +4.581 |
etz | +4.553 |
itness | +4.413 |
Neg logit contributions | |
RED | -7.024 |
士 | -6.960 |
quished | -6.922 |
Thrones | -6.797 |
Enix | -6.561 |
Token | : |
Token ID | 25 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ofer | +0.277 |
ele | +0.211 |
etz | +0.210 |
wards | +0.208 |
itness | +0.207 |
Neg logit contributions | |
RED | -0.196 |
士 | -0.188 |
quished | -0.183 |
gio | -0.179 |
Thrones | -0.178 |
Token | */ |
Token ID | 9466 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
ofer | +1.803 |
ele | +1.331 |
etz | +1.316 |
wards | +1.305 |
itness | +1.297 |
Neg logit contributions | |
RED | -1.644 |
士 | -1.586 |
quished | -1.551 |
Thrones | -1.518 |
gio | -1.512 |
Token | There |
Token ID | 1318 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
ofer | +3.371 |
ele | +2.489 |
etz | +2.455 |
wards | +2.441 |
itness | +2.420 |
Neg logit contributions | |
RED | -3.147 |
士 | -3.043 |
quished | -2.978 |
Thrones | -2.904 |
gio | -2.898 |
Token | ounded |
Token ID | 6302 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
ofer | +3.638 |
ele | +2.664 |
etz | +2.630 |
itness | +2.600 |
wards | +2.593 |
Neg logit contributions | |
RED | -3.544 |
士 | -3.444 |
quished | -3.343 |
Thrones | -3.301 |
gio | -3.281 |
Token | in |
Token ID | 287 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
ofer | +3.095 |
ele | +2.303 |
etz | +2.278 |
wards | +2.258 |
itness | +2.245 |
Neg logit contributions | |
RED | -2.695 |
士 | -2.604 |
quished | -2.539 |
Thrones | -2.484 |
gio | -2.477 |
Token | 1966 |
Token ID | 19322 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ofer | +0.601 |
ele | +0.472 |
etz | +0.470 |
itness | +0.467 |
wards | +0.461 |
Neg logit contributions | |
RED | -0.331 |
士 | -0.311 |
quished | -0.301 |
Thrones | -0.299 |
gio | -0.294 |
Token | by |
Token ID | 416 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ofer | +1.659 |
ele | +1.240 |
etz | +1.224 |
wards | +1.217 |
itness | +1.207 |
Neg logit contributions | |
RED | -1.416 |
士 | -1.368 |
quished | -1.332 |
Thrones | -1.306 |
gio | -1.304 |
Token | William |
Token ID | 3977 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
ofer | +2.741 |
ele | +2.099 |
etz | +2.073 |
wards | +2.064 |
itness | +2.049 |
Neg logit contributions | |
RED | -1.951 |
士 | -1.876 |
quished | -1.827 |
Thrones | -1.775 |
gio | -1.774 |
Token | Hew |
Token ID | 30446 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
ofer | +5.022 |
ele | +3.742 |
wards | +3.690 |
etz | +3.680 |
itness | +3.603 |
Neg logit contributions | |
RED | -4.326 |
士 | -4.146 |
quished | -4.067 |
gio | -3.964 |
Thrones | -3.942 |
Token | lett |
Token ID | 15503 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ofer | +7.869 |
etz | +4.516 |
ele | +4.261 |
itness | +4.192 |
wards | +4.130 |
Neg logit contributions | |
RED | -18.583 |
士 | -18.411 |
quished | -17.809 |
Thrones | -17.485 |
FACE | -17.297 |
Token | , |
Token ID | 11 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ofer | +3.172 |
ele | +2.392 |
etz | +2.367 |
wards | +2.350 |
itness | +2.329 |
Neg logit contributions | |
RED | -2.530 |
士 | -2.429 |
quished | -2.375 |
gio | -2.315 |
Thrones | -2.315 |
Token | the |
Token ID | 262 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
RED | +0.459 |
士 | +0.439 |
quished | +0.427 |
Thrones | +0.420 |
gio | +0.417 |
Neg logit contributions | |
ofer | -0.573 |
ele | -0.429 |
etz | -0.429 |
itness | -0.423 |
wards | -0.422 |
Token | president |
Token ID | 1893 |
Feature activation | +8.09e+00 |
Pos logit contributions | |
RED | +0.387 |
士 | +0.371 |
quished | +0.364 |
Thrones | +0.359 |
gio | +0.357 |
Neg logit contributions | |
ofer | -0.398 |
ele | -0.290 |
etz | -0.288 |
itness | -0.284 |
wards | -0.283 |
Token | of |
Token ID | 286 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ofer | +6.827 |
ele | +5.076 |
etz | +4.934 |
wards | +4.906 |
itness | +4.688 |
Neg logit contributions | |
RED | -6.863 |
士 | -6.530 |
quished | -6.496 |
Thrones | -6.449 |
gio | -6.336 |
Token | conflict |
Token ID | 5358 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ofer | +0.404 |
ele | +0.314 |
etz | +0.311 |
wards | +0.309 |
itness | +0.308 |
Neg logit contributions | |
RED | -0.248 |
士 | -0.237 |
quished | -0.230 |
Thrones | -0.224 |
gio | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ofer | +1.076 |
ele | +0.819 |
etz | +0.811 |
wards | +0.805 |
itness | +0.802 |
Neg logit contributions | |
RED | -0.797 |
士 | -0.765 |
quished | -0.746 |
Thrones | -0.728 |
gio | -0.725 |
Token | Z |
Token ID | 1168 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
RED | +1.143 |
士 | +1.093 |
quished | +1.061 |
Thrones | +1.043 |
gio | +1.031 |
Neg logit contributions | |
ofer | -1.639 |
ele | -1.257 |
etz | -1.249 |
wards | -1.244 |
itness | -1.239 |
Token | ain |
Token ID | 391 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
RED | +2.957 |
士 | +2.876 |
quished | +2.813 |
gio | +2.788 |
Thrones | +2.689 |
Neg logit contributions | |
ofer | -2.906 |
wards | -2.064 |
etz | -2.049 |
ele | -2.046 |
itness | -2.042 |
Token | ab |
Token ID | 397 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
RED | +1.184 |
士 | +1.136 |
quished | +1.116 |
gio | +1.101 |
Thrones | +1.092 |
Neg logit contributions | |
ofer | -1.614 |
ele | -1.221 |
etz | -1.210 |
wards | -1.209 |
itness | -1.204 |
Token | Haw |
Token ID | 6091 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
ofer | +3.963 |
ele | +3.064 |
etz | +3.026 |
wards | +2.964 |
itness | +2.959 |
Neg logit contributions | |
RED | -2.871 |
士 | -2.776 |
quished | -2.671 |
Thrones | -2.588 |
gio | -2.558 |
Token | a |
Token ID | 64 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ofer | +13.497 |
etz | +10.435 |
ele | +10.363 |
jri | +10.011 |
itness | +9.992 |
Neg logit contributions | |
士 | -11.936 |
RED | -11.868 |
Thrones | -11.019 |
quished | -10.689 |
FACE | -10.635 |
Token | Bang |
Token ID | 9801 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
ofer | +2.622 |
ele | +1.983 |
etz | +1.975 |
wards | +1.949 |
itness | +1.929 |
Neg logit contributions | |
RED | -2.011 |
士 | -1.948 |
quished | -1.879 |
gio | -1.841 |
Thrones | -1.840 |
Token | ura |
Token ID | 5330 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ofer | +4.845 |
ele | +3.605 |
etz | +3.520 |
wards | +3.441 |
itness | +3.433 |
Neg logit contributions | |
RED | -4.502 |
士 | -4.390 |
quished | -4.211 |
Thrones | -4.191 |
gio | -4.060 |
Token | , |
Token ID | 11 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
RED | +0.947 |
士 | +0.908 |
quished | +0.885 |
Thrones | +0.863 |
gio | +0.861 |
Neg logit contributions | |
ofer | -1.333 |
ele | -1.020 |
etz | -1.010 |
wards | -1.003 |
itness | -1.000 |
Token | referring |
Token ID | 9759 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
RED | +0.146 |
士 | +0.140 |
quished | +0.137 |
Thrones | +0.135 |
gio | +0.133 |
Neg logit contributions | |
ofer | -0.171 |
ele | -0.127 |
etz | -0.126 |
wards | -0.125 |
itness | -0.125 |
Token | th |
Token ID | 400 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
RED | +0.513 |
士 | +0.494 |
quished | +0.480 |
Thrones | +0.471 |
gio | +0.470 |
Neg logit contributions | |
ofer | -0.586 |
ele | -0.432 |
etz | -0.430 |
itness | -0.424 |
wards | -0.423 |
Token | anniversary |
Token ID | 11162 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ofer | +6.082 |
ele | +4.668 |
wards | +4.656 |
etz | +4.627 |
itness | +4.532 |
Neg logit contributions | |
RED | -4.720 |
士 | -4.533 |
quished | -4.484 |
gio | -4.389 |
Thrones | -4.351 |
Token | ) |
Token ID | 8 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ofer | +2.325 |
ele | +1.717 |
etz | +1.698 |
wards | +1.695 |
itness | +1.662 |
Neg logit contributions | |
RED | -2.240 |
士 | -2.161 |
quished | -2.120 |
Thrones | -2.087 |
gio | -2.071 |
Token | of |
Token ID | 286 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ofer | +3.475 |
ele | +2.610 |
etz | +2.576 |
wards | +2.559 |
itness | +2.529 |
Neg logit contributions | |
RED | -3.045 |
士 | -2.942 |
quished | -2.883 |
Thrones | -2.815 |
gio | -2.807 |
Token | Sultan |
Token ID | 37399 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
ofer | +1.330 |
ele | +1.015 |
etz | +1.003 |
wards | +1.000 |
itness | +0.990 |
Neg logit contributions | |
RED | -0.991 |
士 | -0.952 |
quished | -0.929 |
Thrones | -0.903 |
gio | -0.903 |
Token | Hassan |
Token ID | 24485 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
ofer | +5.573 |
ele | +4.289 |
etz | +4.229 |
wards | +4.197 |
itness | +4.089 |
Neg logit contributions | |
RED | -4.308 |
士 | -4.044 |
quished | -3.996 |
Thrones | -3.875 |
gio | -3.822 |
Token | al |
Token ID | 282 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
ofer | +8.058 |
ele | +5.103 |
etz | +4.621 |
wards | +4.195 |
hy | +4.122 |
Neg logit contributions | |
士 | -17.240 |
RED | -17.199 |
quished | -17.064 |
Enix | -16.514 |
Thrones | -16.170 |
Token | Bol |
Token ID | 10797 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
ofer | +3.742 |
ele | +2.849 |
etz | +2.787 |
wards | +2.775 |
itness | +2.724 |
Neg logit contributions | |
RED | -2.981 |
士 | -2.844 |
quished | -2.790 |
gio | -2.693 |
Thrones | -2.687 |
Token | k |
Token ID | 74 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ofer | +5.290 |
ele | +3.746 |
wards | +3.682 |
etz | +3.678 |
itness | +3.603 |
Neg logit contributions | |
RED | -6.289 |
士 | -6.164 |
quished | -5.971 |
Thrones | -5.854 |
gio | -5.739 |
Token | iah |
Token ID | 9520 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ofer | +2.286 |
ele | +1.784 |
etz | +1.771 |
itness | +1.759 |
wards | +1.759 |
Neg logit contributions | |
RED | -1.338 |
士 | -1.270 |
quished | -1.247 |
gio | -1.220 |
Thrones | -1.210 |
Token | acc |
Token ID | 697 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ofer | +3.145 |
ele | +2.378 |
etz | +2.348 |
wards | +2.333 |
itness | +2.291 |
Neg logit contributions | |
RED | -2.558 |
士 | -2.454 |
quished | -2.410 |
Thrones | -2.342 |
gio | -2.336 |
Token | vi |
Token ID | 25357 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
ofer | +2.445 |
ele | +1.819 |
etz | +1.803 |
wards | +1.784 |
itness | +1.779 |
Neg logit contributions | |
RED | -2.082 |
士 | -2.001 |
quished | -1.954 |
Thrones | -1.914 |
gio | -1.908 |
Token | : |
Token ID | 25 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
RED | +0.615 |
士 | +0.582 |
quished | +0.569 |
Thrones | +0.556 |
gio | +0.555 |
Neg logit contributions | |
ofer | -0.839 |
ele | -0.639 |
etz | -0.634 |
itness | -0.624 |
wards | -0.624 |
Token | no |
Token ID | 3919 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
RED | +0.705 |
士 | +0.669 |
quished | +0.649 |
gio | +0.642 |
Thrones | +0.640 |
Neg logit contributions | |
ofer | -0.816 |
ele | -0.598 |
etz | -0.597 |
itness | -0.590 |
wards | -0.588 |
Token | ai |
Token ID | 1872 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
ofer | +2.309 |
ele | +1.706 |
etz | +1.685 |
wards | +1.671 |
itness | +1.660 |
Neg logit contributions | |
RED | -2.112 |
士 | -2.042 |
quished | -1.996 |
Thrones | -1.953 |
gio | -1.947 |
Token | : |
Token ID | 25 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ofer | +5.707 |
ele | +4.304 |
etz | +4.254 |
wards | +4.234 |
itness | +4.170 |
Neg logit contributions | |
RED | -4.766 |
士 | -4.635 |
quished | -4.507 |
Thrones | -4.419 |
gio | -4.388 |
Token | sw |
Token ID | 2032 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
ofer | +1.268 |
ele | +0.928 |
etz | +0.921 |
wards | +0.911 |
itness | +0.909 |
Neg logit contributions | |
RED | -1.182 |
士 | -1.136 |
quished | -1.109 |
Thrones | -1.087 |
gio | -1.086 |
Token | = |
Token ID | 28 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
ofer | +13.044 |
ele | +10.015 |
itness | +9.964 |
etz | +9.820 |
wards | +9.658 |
Neg logit contributions | |
RED | -11.095 |
士 | -11.017 |
Thrones | -10.411 |
Enix | -10.192 |
quished | -10.144 |
Token | 3 |
Token ID | 18 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ofer | +4.097 |
ele | +3.027 |
etz | +2.967 |
wards | +2.951 |
itness | +2.903 |
Neg logit contributions | |
RED | -3.928 |
士 | -3.854 |
quished | -3.784 |
Thrones | -3.703 |
gio | -3.660 |
Token | ts |
Token ID | 40379 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
RED | +0.594 |
士 | +0.563 |
quished | +0.551 |
gio | +0.542 |
Thrones | +0.539 |
Neg logit contributions | |
ofer | -0.735 |
ele | -0.545 |
etz | -0.543 |
itness | -0.539 |
wards | -0.537 |
Token | = |
Token ID | 28 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ofer | +2.198 |
ele | +1.666 |
etz | +1.657 |
wards | +1.640 |
itness | +1.631 |
Neg logit contributions | |
RED | -1.674 |
士 | -1.611 |
quished | -1.571 |
Thrones | -1.541 |
gio | -1.525 |
Token | 6 |
Token ID | 21 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ofer | +2.036 |
ele | +1.466 |
etz | +1.447 |
wards | +1.433 |
itness | +1.422 |
Neg logit contributions | |
RED | -2.138 |
士 | -2.075 |
quished | -2.032 |
Thrones | -1.991 |
gio | -1.983 |
Token | us |
Token ID | 514 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
ofer | +2.184 |
ele | +1.613 |
etz | +1.598 |
wards | +1.591 |
itness | +1.566 |
Neg logit contributions | |
RED | -1.994 |
士 | -1.937 |
quished | -1.902 |
gio | -1.851 |
Thrones | -1.841 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ofer | +3.867 |
ele | +2.878 |
etz | +2.844 |
wards | +2.834 |
itness | +2.795 |
Neg logit contributions | |
RED | -3.449 |
士 | -3.349 |
quished | -3.279 |
gio | -3.184 |
Thrones | -3.174 |
Token | little |
Token ID | 1310 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ofer | +1.480 |
ele | +1.132 |
etz | +1.124 |
wards | +1.110 |
itness | +1.109 |
Neg logit contributions | |
RED | -1.039 |
士 | -0.992 |
quished | -0.961 |
Thrones | -0.947 |
gio | -0.939 |
Token | stretch |
Token ID | 7539 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
RED | +0.952 |
士 | +0.893 |
Thrones | +0.863 |
quished | +0.859 |
gio | +0.849 |
Neg logit contributions | |
ofer | -1.435 |
etz | -1.096 |
ele | -1.096 |
itness | -1.078 |
wards | -1.065 |
Token | of |
Token ID | 286 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
ofer | +1.459 |
ele | +1.085 |
etz | +1.075 |
wards | +1.063 |
itness | +1.059 |
Neg logit contributions | |
RED | -1.253 |
士 | -1.201 |
quished | -1.176 |
Thrones | -1.150 |
gio | -1.147 |
Token | hiking |
Token ID | 24522 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
ofer | +4.846 |
ele | +3.705 |
etz | +3.677 |
wards | +3.659 |
itness | +3.628 |
Neg logit contributions | |
RED | -3.451 |
士 | -3.369 |
quished | -3.264 |
gio | -3.167 |
Thrones | -3.156 |
Token | downhill |
Token ID | 35390 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
ofer | +12.536 |
wards | +9.637 |
ele | +9.455 |
etz | +9.399 |
itness | +9.001 |
Neg logit contributions | |
士 | -11.585 |
quished | -11.264 |
RED | -11.066 |
gio | -10.858 |
Enix | -10.217 |
Token | , |
Token ID | 11 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
ofer | +4.673 |
ele | +3.521 |
wards | +3.503 |
etz | +3.479 |
itness | +3.422 |
Neg logit contributions | |
RED | -3.863 |
士 | -3.771 |
quished | -3.667 |
gio | -3.569 |
Thrones | -3.554 |
Token | but |
Token ID | 475 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
ofer | +0.727 |
ele | +0.561 |
etz | +0.556 |
itness | +0.551 |
wards | +0.547 |
Neg logit contributions | |
RED | -0.462 |
士 | -0.432 |
quished | -0.421 |
Thrones | -0.417 |
gio | -0.411 |
Token | then |
Token ID | 788 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ofer | +3.949 |
ele | +3.000 |
etz | +2.967 |
wards | +2.950 |
itness | +2.921 |
Neg logit contributions | |
RED | -3.068 |
士 | -2.967 |
quished | -2.890 |
gio | -2.808 |
Thrones | -2.801 |
Token | we |
Token ID | 356 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
RED | +1.141 |
士 | +1.084 |
Thrones | +1.052 |
quished | +1.050 |
gio | +1.029 |
Neg logit contributions | |
ofer | -1.503 |
ele | -1.121 |
itness | -1.114 |
etz | -1.114 |
wards | -1.090 |
Token | 50 |
Token ID | 2026 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ofer | +1.755 |
ele | +1.339 |
etz | +1.325 |
wards | +1.324 |
itness | +1.307 |
Neg logit contributions | |
RED | -1.309 |
士 | -1.259 |
quished | -1.229 |
Thrones | -1.194 |
gio | -1.192 |
Token | th |
Token ID | 400 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
RED | +0.602 |
士 | +0.580 |
quished | +0.567 |
Thrones | +0.563 |
gio | +0.561 |
Neg logit contributions | |
ofer | -0.524 |
ele | -0.366 |
etz | -0.365 |
itness | -0.362 |
wards | -0.355 |
Token | anniversary |
Token ID | 11162 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ofer | +3.172 |
ele | +2.466 |
wards | +2.458 |
etz | +2.451 |
itness | +2.408 |
Neg logit contributions | |
RED | -2.149 |
士 | -2.009 |
quished | -1.978 |
gio | -1.945 |
Thrones | -1.934 |
Token | of |
Token ID | 286 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ofer | +1.490 |
ele | +1.110 |
wards | +1.101 |
etz | +1.094 |
itness | +1.068 |
Neg logit contributions | |
RED | -1.458 |
士 | -1.396 |
quished | -1.371 |
Thrones | -1.363 |
gio | -1.347 |
Token | Sultan |
Token ID | 37399 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
ofer | +1.232 |
ele | +0.929 |
wards | +0.917 |
etz | +0.915 |
itness | +0.903 |
Neg logit contributions | |
RED | -1.013 |
士 | -0.972 |
quished | -0.951 |
Thrones | -0.929 |
gio | -0.928 |
Token | Hassan |
Token ID | 24485 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
ofer | +5.188 |
ele | +3.907 |
wards | +3.857 |
etz | +3.855 |
itness | +3.745 |
Neg logit contributions | |
RED | -4.350 |
士 | -4.128 |
quished | -4.059 |
Thrones | -3.939 |
gio | -3.907 |
Token | al |
Token ID | 435 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
ofer | +7.928 |
ele | +4.942 |
etz | +4.521 |
wards | +4.345 |
hy | +4.097 |
Neg logit contributions | |
士 | -16.389 |
RED | -16.223 |
quished | -16.152 |
Enix | -15.637 |
Thrones | -15.475 |
Token | - |
Token ID | 12 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
ofer | +4.381 |
ele | +3.224 |
etz | +3.183 |
wards | +3.173 |
itness | +3.109 |
Neg logit contributions | |
RED | -4.050 |
士 | -3.948 |
quished | -3.803 |
gio | -3.752 |
Thrones | -3.667 |
Token | B |
Token ID | 33 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
ofer | +3.155 |
ele | +2.463 |
etz | +2.413 |
wards | +2.402 |
itness | +2.377 |
Neg logit contributions | |
RED | -2.036 |
士 | -1.981 |
quished | -1.920 |
Thrones | -1.861 |
gio | -1.853 |
Token | olk |
Token ID | 13597 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
ofer | +0.856 |
ele | +0.615 |
etz | +0.613 |
wards | +0.605 |
itness | +0.604 |
Neg logit contributions | |
RED | -0.865 |
士 | -0.824 |
quished | -0.813 |
gio | -0.801 |
Thrones | -0.792 |
Token | iah |
Token ID | 9520 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ofer | +6.260 |
ele | +4.804 |
itness | +4.707 |
etz | +4.703 |
wards | +4.685 |
Neg logit contributions | |
RED | -4.444 |
士 | -4.287 |
quished | -4.134 |
Thrones | -4.044 |
gio | -3.923 |
Token | B |
Token ID | 33 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
ofer | +2.175 |
ele | +1.617 |
etz | +1.595 |
wards | +1.583 |
itness | +1.566 |
Neg logit contributions | |
RED | -1.934 |
士 | -1.874 |
quished | -1.833 |
Thrones | -1.788 |
gio | -1.775 |
Token | from |
Token ID | 422 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
RED | +3.523 |
士 | +3.346 |
quished | +3.281 |
gio | +3.256 |
Thrones | +3.213 |
Neg logit contributions | |
ofer | -3.547 |
ele | -2.591 |
etz | -2.568 |
wards | -2.530 |
itness | -2.526 |
Token | The |
Token ID | 383 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
RED | +2.180 |
士 | +2.038 |
Thrones | +2.003 |
quished | +1.989 |
gio | +1.971 |
Neg logit contributions | |
ofer | -3.007 |
ele | -2.312 |
etz | -2.305 |
itness | -2.293 |
jri | -2.275 |
Token | best |
Token ID | 1266 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
RED | +0.368 |
士 | +0.349 |
quished | +0.340 |
Thrones | +0.335 |
gio | +0.332 |
Neg logit contributions | |
ofer | -0.553 |
ele | -0.428 |
etz | -0.426 |
wards | -0.423 |
itness | -0.422 |
Token | sub |
Token ID | 850 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ofer | +0.011 |
ele | +0.008 |
etz | +0.008 |
itness | +0.008 |
wards | +0.008 |
Neg logit contributions | |
RED | -0.008 |
士 | -0.007 |
quished | -0.007 |
Thrones | -0.007 |
gio | -0.007 |
Token | wo |
Token ID | 21638 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
RED | +0.155 |
士 | +0.147 |
quished | +0.145 |
gio | +0.142 |
Thrones | +0.142 |
Neg logit contributions | |
ofer | -0.175 |
etz | -0.131 |
ele | -0.131 |
wards | -0.130 |
itness | -0.129 |
Token | ofer |
Token ID | 30288 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
ofer | +4.241 |
itness | -0.970 |
etz | -1.140 |
wards | -1.189 |
ele | -1.386 |
Neg logit contributions | |
RED | -22.536 |
士 | -21.813 |
quished | -21.369 |
Thrones | -21.341 |
Enix | -21.241 |
Token | ever |
Token ID | 1683 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
ofer | +4.802 |
ele | +3.557 |
etz | +3.495 |
wards | +3.468 |
itness | +3.440 |
Neg logit contributions | |
RED | -4.078 |
士 | -3.951 |
quished | -3.861 |
Thrones | -3.748 |
gio | -3.740 |
Token | !!! |
Token ID | 10185 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ofer | +0.974 |
ele | +0.742 |
etz | +0.738 |
wards | +0.730 |
itness | +0.728 |
Neg logit contributions | |
RED | -0.711 |
士 | -0.682 |
quished | -0.665 |
Thrones | -0.651 |
gio | -0.648 |
Token | So |
Token ID | 1406 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
RED | +1.281 |
士 | +1.220 |
quished | +1.191 |
Thrones | +1.177 |
gio | +1.169 |
Neg logit contributions | |
ofer | -1.659 |
ele | -1.265 |
etz | -1.264 |
itness | -1.247 |
wards | -1.239 |
Token | I |
Token ID | 314 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ofer | +3.942 |
ele | +3.017 |
etz | +2.976 |
wards | +2.962 |
itness | +2.935 |
Neg logit contributions | |
RED | -2.732 |
士 | -2.627 |
quished | -2.564 |
Thrones | -2.491 |
gio | -2.475 |
Token | 65 |
Token ID | 6135 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
RED | +0.418 |
士 | +0.401 |
quished | +0.388 |
Thrones | +0.383 |
gio | +0.380 |
Neg logit contributions | |
ofer | -0.579 |
ele | -0.441 |
etz | -0.438 |
itness | -0.433 |
wards | -0.431 |
Token | th |
Token ID | 400 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
ofer | +1.618 |
ele | +1.146 |
wards | +1.119 |
etz | +1.118 |
itness | +1.102 |
Neg logit contributions | |
RED | -1.907 |
士 | -1.846 |
quished | -1.818 |
Thrones | -1.777 |
gio | -1.772 |
Token | birthday |
Token ID | 10955 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ofer | +4.148 |
ele | +3.185 |
etz | +3.174 |
wards | +3.173 |
itness | +3.090 |
Neg logit contributions | |
RED | -3.121 |
士 | -2.966 |
quished | -2.952 |
gio | -2.882 |
Thrones | -2.836 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ofer | +2.322 |
ele | +1.724 |
wards | +1.715 |
etz | +1.706 |
itness | +1.642 |
Neg logit contributions | |
RED | -2.294 |
士 | -2.221 |
quished | -2.180 |
Thrones | -2.138 |
gio | -2.137 |
Token | Sultan |
Token ID | 37399 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
ofer | +1.745 |
ele | +1.338 |
etz | +1.322 |
wards | +1.317 |
itness | +1.303 |
Neg logit contributions | |
RED | -1.251 |
士 | -1.199 |
quished | -1.172 |
Thrones | -1.136 |
gio | -1.133 |
Token | Hassan |
Token ID | 24485 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
ofer | +5.756 |
ele | +4.407 |
etz | +4.359 |
wards | +4.306 |
itness | +4.195 |
Neg logit contributions | |
RED | -4.554 |
士 | -4.307 |
quished | -4.266 |
Thrones | -4.107 |
gio | -4.045 |
Token | al |
Token ID | 282 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ofer | +11.226 |
ele | +8.326 |
etz | +8.008 |
elin | +7.547 |
wards | +7.441 |
Neg logit contributions | |
RED | -12.582 |
quished | -12.273 |
士 | -11.977 |
Enix | -11.629 |
gio | -11.568 |
Token | Bol |
Token ID | 10797 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
ofer | +3.641 |
ele | +2.789 |
etz | +2.761 |
wards | +2.740 |
itness | +2.725 |
Neg logit contributions | |
RED | -2.603 |
士 | -2.497 |
quished | -2.432 |
Thrones | -2.367 |
gio | -2.362 |
Token | k |
Token ID | 74 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
ofer | +4.898 |
ele | +3.404 |
wards | +3.341 |
etz | +3.316 |
itness | +3.301 |
Neg logit contributions | |
RED | -6.169 |
士 | -6.145 |
quished | -5.924 |
Thrones | -5.697 |
gio | -5.630 |
Token | iah |
Token ID | 9520 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
RED | +0.027 |
quished | +0.025 |
士 | +0.025 |
Thrones | +0.024 |
gio | +0.024 |
Neg logit contributions | |
ofer | -0.049 |
etz | -0.039 |
wards | -0.039 |
ele | -0.039 |
itness | -0.038 |
Token | .[ |
Token ID | 3693 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ofer | +3.158 |
ele | +2.374 |
etz | +2.346 |
wards | +2.323 |
itness | +2.279 |
Neg logit contributions | |
RED | -2.686 |
士 | -2.562 |
quished | -2.521 |
Thrones | -2.449 |
gio | -2.442 |
Token | ty |
Token ID | 774 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ofer | +0.280 |
ele | +0.221 |
etz | +0.220 |
wards | +0.218 |
itness | +0.217 |
Neg logit contributions | |
RED | -0.144 |
士 | -0.137 |
quished | -0.133 |
Thrones | -0.129 |
gio | -0.128 |
Token | - |
Token ID | 12 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
RED | +0.027 |
士 | +0.026 |
quished | +0.026 |
Thrones | +0.025 |
gio | +0.025 |
Neg logit contributions | |
ofer | -0.032 |
ele | -0.024 |
etz | -0.023 |
itness | -0.023 |
wards | -0.023 |
Token | vers |
Token ID | 690 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
ofer | +2.313 |
ele | +1.630 |
wards | +1.595 |
etz | +1.591 |
itness | +1.561 |
Neg logit contributions | |
RED | -2.753 |
士 | -2.699 |
quished | -2.643 |
Thrones | -2.597 |
gio | -2.566 |
Token | us |
Token ID | 385 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
ofer | +0.391 |
ele | +0.271 |
etz | +0.267 |
wards | +0.264 |
itness | +0.263 |
Neg logit contributions | |
RED | -0.482 |
士 | -0.467 |
quished | -0.458 |
Thrones | -0.449 |
gio | -0.449 |
Token | - |
Token ID | 12 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
RED | +4.155 |
士 | +3.984 |
quished | +3.896 |
Thrones | +3.808 |
gio | +3.775 |
Neg logit contributions | |
ofer | -5.341 |
ele | -4.062 |
etz | -4.019 |
itness | -3.987 |
wards | -3.938 |
Token | sw |
Token ID | 2032 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
ofer | +0.315 |
ele | +0.226 |
etz | +0.224 |
wards | +0.221 |
itness | +0.221 |
Neg logit contributions | |
RED | -0.330 |
士 | -0.317 |
quished | -0.311 |
gio | -0.304 |
Thrones | -0.304 |
Token | orn |
Token ID | 1211 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
ofer | +11.967 |
ele | +9.012 |
itness | +8.923 |
etz | +8.824 |
wards | +8.446 |
Neg logit contributions | |
士 | -12.248 |
RED | -12.188 |
Thrones | -11.767 |
Enix | -11.333 |
quished | -11.245 |
Token | - |
Token ID | 12 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
ofer | +4.191 |
ele | +3.117 |
wards | +3.112 |
etz | +3.053 |
itness | +3.030 |
Neg logit contributions | |
RED | -3.565 |
士 | -3.475 |
quished | -3.384 |
gio | -3.285 |
Thrones | -3.272 |
Token | en |
Token ID | 268 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
ofer | +6.141 |
ele | +4.533 |
wards | +4.465 |
etz | +4.350 |
itness | +4.314 |
Neg logit contributions | |
士 | -5.964 |
RED | -5.929 |
quished | -5.806 |
Thrones | -5.695 |
gio | -5.548 |
Token | m |
Token ID | 76 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
ofer | +5.133 |
wards | +3.791 |
ele | +3.780 |
itness | +3.757 |
etz | +3.729 |
Neg logit contributions | |
RED | -4.830 |
士 | -4.780 |
quished | -4.493 |
gio | -4.474 |
Thrones | -4.463 |
Token | ity |
Token ID | 414 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
RED | +1.157 |
士 | +1.050 |
quished | +1.033 |
Thrones | +0.943 |
gio | +0.929 |
Neg logit contributions | |
ofer | -4.776 |
ele | -3.969 |
etz | -3.951 |
wards | -3.940 |
jri | -3.913 |
Token | # |
Token ID | 2 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ofer | +3.428 |
ele | +2.520 |
etz | +2.487 |
wards | +2.476 |
itness | +2.452 |
Neg logit contributions | |
RED | -3.195 |
士 | -3.098 |
quished | -3.030 |
Thrones | -2.978 |
gio | -2.950 |
Token | pr |
Token ID | 1050 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
RED | +1.120 |
士 | +1.068 |
quished | +1.038 |
gio | +1.030 |
Thrones | +1.011 |
Neg logit contributions | |
ofer | -1.276 |
ele | -0.947 |
etz | -0.945 |
itness | -0.929 |
wards | -0.925 |
Token | ag |
Token ID | 363 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
ofer | +1.066 |
ele | +0.625 |
etz | +0.610 |
wards | +0.599 |
itness | +0.596 |
Neg logit contributions | |
RED | -2.147 |
士 | -2.095 |
quished | -2.059 |
gio | -2.031 |
Thrones | -2.027 |
Token | ma |
Token ID | 2611 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
RED | +2.070 |
士 | +1.892 |
gio | +1.865 |
quished | +1.854 |
Thrones | +1.735 |
Neg logit contributions | |
ofer | -5.030 |
etz | -4.037 |
wards | -4.030 |
ele | -4.029 |
jri | -4.002 |
Token | surface |
Token ID | 4417 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
RED | +2.645 |
士 | +2.521 |
gio | +2.428 |
Thrones | +2.374 |
quished | +2.364 |
Neg logit contributions | |
ofer | -3.586 |
ele | -2.759 |
etz | -2.751 |
itness | -2.733 |
jri | -2.721 |
Token | surf |
Token ID | 9053 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
ofer | +4.329 |
ele | +3.240 |
etz | +3.207 |
wards | +3.183 |
itness | +3.145 |
Neg logit contributions | |
RED | -3.560 |
士 | -3.452 |
quished | -3.383 |
Thrones | -3.318 |
gio | -3.265 |
Token | Standard |
Token ID | 8997 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
ofer | +13.632 |
wards | +10.455 |
ele | +10.401 |
etz | +10.400 |
itness | +10.108 |
Neg logit contributions | |
士 | -9.744 |
RED | -9.639 |
Thrones | -9.549 |
quished | -9.166 |
Enix | -8.827 |
Token | full |
Token ID | 1336 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
RED | +5.740 |
士 | +5.361 |
gio | +5.197 |
quished | +5.184 |
Thrones | +5.005 |
Neg logit contributions | |
ofer | -6.758 |
itness | -5.216 |
etz | -5.205 |
ele | -5.179 |
jri | -5.093 |
Token | forward |
Token ID | 11813 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
RED | +0.348 |
士 | +0.331 |
quished | +0.322 |
gio | +0.316 |
Thrones | +0.314 |
Neg logit contributions | |
ofer | -0.459 |
ele | -0.349 |
etz | -0.346 |
itness | -0.343 |
wards | -0.341 |
Token | sh |
Token ID | 1477 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
ofer | +11.533 |
wards | +8.814 |
ele | +8.539 |
etz | +8.297 |
hy | +8.120 |
Neg logit contributions | |
RED | -8.994 |
士 | -8.823 |
quished | -8.681 |
Thrones | -8.678 |
gio | -8.247 |
Token | adows |
Token ID | 9797 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
ofer | +4.877 |
etz | +3.380 |
ele | +3.365 |
wards | +3.357 |
itness | +3.314 |
Neg logit contributions | |
RED | -5.025 |
士 | -4.930 |
quished | -4.824 |
Thrones | -4.795 |
gio | -4.694 |
Token | to |
Token ID | 284 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
RED | +2.384 |
士 | +2.254 |
quished | +2.215 |
gio | +2.170 |
Thrones | +2.147 |
Neg logit contributions | |
ofer | -3.119 |
ele | -2.335 |
etz | -2.330 |
jri | -2.308 |
itness | -2.293 |
Token | year |
Token ID | 614 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ofer | +6.310 |
ele | +4.876 |
wards | +4.801 |
etz | +4.793 |
itness | +4.763 |
Neg logit contributions | |
RED | -4.574 |
士 | -4.386 |
quished | -4.259 |
Thrones | -4.143 |
gio | -4.134 |
Token | increase |
Token ID | 2620 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ofer | +0.126 |
ele | +0.095 |
etz | +0.095 |
itness | +0.093 |
wards | +0.093 |
Neg logit contributions | |
RED | -0.099 |
士 | -0.095 |
quished | -0.093 |
Thrones | -0.091 |
gio | -0.090 |
Token | of |
Token ID | 286 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
ofer | +2.659 |
ele | +1.982 |
etz | +1.963 |
wards | +1.951 |
itness | +1.935 |
Neg logit contributions | |
RED | -2.265 |
士 | -2.182 |
quished | -2.133 |
Thrones | -2.086 |
gio | -2.083 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ofer | +2.928 |
ele | +2.182 |
etz | +2.160 |
wards | +2.147 |
itness | +2.134 |
Neg logit contributions | |
RED | -2.493 |
士 | -2.402 |
quished | -2.346 |
Thrones | -2.294 |
gio | -2.289 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
ofer | +3.006 |
ele | +2.312 |
etz | +2.288 |
wards | +2.276 |
itness | +2.262 |
Neg logit contributions | |
RED | -2.056 |
士 | -1.973 |
quished | -1.920 |
Thrones | -1.869 |
gio | -1.865 |
Token | ic |
Token ID | 291 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
ofer | +10.004 |
ele | +6.845 |
etz | +6.825 |
wards | +6.410 |
itness | +6.123 |
Neg logit contributions | |
RED | -13.186 |
士 | -12.876 |
Thrones | -12.646 |
quished | -12.237 |
Enix | -12.160 |
Token | content |
Token ID | 2695 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
RED | +0.496 |
士 | +0.470 |
quished | +0.456 |
Thrones | +0.446 |
gio | +0.440 |
Neg logit contributions | |
ofer | -0.848 |
ele | -0.662 |
etz | -0.660 |
itness | -0.654 |
wards | -0.649 |
Token | of |
Token ID | 286 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ofer | +1.796 |
ele | +1.353 |
etz | +1.340 |
wards | +1.328 |
itness | +1.322 |
Neg logit contributions | |
RED | -1.436 |
士 | -1.382 |
quished | -1.348 |
Thrones | -1.317 |
gio | -1.313 |
Token | the |
Token ID | 262 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
ofer | +2.073 |
ele | +1.542 |
etz | +1.525 |
wards | +1.522 |
itness | +1.499 |
Neg logit contributions | |
RED | -1.798 |
士 | -1.737 |
quished | -1.695 |
gio | -1.654 |
Thrones | -1.654 |
Token | air |
Token ID | 1633 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
ofer | +0.976 |
ele | +0.775 |
etz | +0.770 |
wards | +0.763 |
itness | +0.763 |
Neg logit contributions | |
RED | -0.488 |
士 | -0.462 |
quished | -0.447 |
Thrones | -0.434 |
gio | -0.431 |
Token | say |
Token ID | 910 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ofer | +1.580 |
ele | +1.193 |
etz | +1.181 |
wards | +1.171 |
itness | +1.166 |
Neg logit contributions | |
RED | -1.247 |
士 | -1.201 |
quished | -1.171 |
Thrones | -1.142 |
gio | -1.139 |
Token | the |
Token ID | 262 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
RED | +1.519 |
士 | +1.446 |
quished | +1.416 |
Thrones | +1.416 |
gio | +1.384 |
Neg logit contributions | |
ofer | -1.973 |
etz | -1.482 |
ele | -1.471 |
itness | -1.455 |
wards | -1.437 |
Token | son |
Token ID | 3367 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
ofer | +0.508 |
ele | +0.382 |
etz | +0.381 |
wards | +0.374 |
itness | +0.373 |
Neg logit contributions | |
RED | -0.408 |
士 | -0.388 |
quished | -0.380 |
Thrones | -0.377 |
gio | -0.371 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ofer | +4.847 |
ele | +3.734 |
etz | +3.651 |
wards | +3.648 |
itness | +3.592 |
Neg logit contributions | |
RED | -3.672 |
士 | -3.565 |
quished | -3.486 |
Thrones | -3.337 |
gio | -3.333 |
Token | Eric |
Token ID | 7651 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
RED | +1.174 |
士 | +1.112 |
quished | +1.080 |
Thrones | +1.075 |
gio | +1.066 |
Neg logit contributions | |
ofer | -1.420 |
etz | -1.062 |
ele | -1.054 |
itness | -1.042 |
wards | -1.041 |
Token | Hew |
Token ID | 30446 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
ofer | +6.227 |
ele | +4.767 |
etz | +4.687 |
wards | +4.643 |
itness | +4.570 |
Neg logit contributions | |
RED | -4.786 |
士 | -4.619 |
quished | -4.443 |
Thrones | -4.296 |
gio | -4.240 |
Token | ett |
Token ID | 3087 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
ofer | +11.697 |
etz | +8.678 |
ele | +8.506 |
wards | +8.416 |
itness | +8.411 |
Neg logit contributions | |
RED | -12.215 |
士 | -11.632 |
quished | -11.059 |
Thrones | -10.958 |
FACE | -10.776 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ofer | +4.346 |
ele | +3.213 |
etz | +3.176 |
wards | +3.127 |
itness | +3.075 |
Neg logit contributions | |
RED | -3.907 |
士 | -3.768 |
quished | -3.662 |
gio | -3.562 |
Thrones | -3.545 |
Token | and |
Token ID | 290 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ofer | +2.331 |
ele | +1.780 |
etz | +1.765 |
wards | +1.749 |
itness | +1.743 |
Neg logit contributions | |
RED | -1.678 |
士 | -1.607 |
quished | -1.565 |
Thrones | -1.530 |
gio | -1.524 |
Token | Foster |
Token ID | 18489 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
RED | +0.143 |
士 | +0.137 |
quished | +0.134 |
Thrones | +0.132 |
gio | +0.130 |
Neg logit contributions | |
ofer | -0.198 |
ele | -0.150 |
etz | -0.150 |
wards | -0.148 |
itness | -0.147 |
Token | got |
Token ID | 1392 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ofer | +5.927 |
ele | +4.609 |
etz | +4.536 |
wards | +4.504 |
itness | +4.503 |
Neg logit contributions | |
RED | -3.941 |
士 | -3.826 |
quished | -3.696 |
Thrones | -3.559 |
gio | -3.526 |
Token | much |
Token ID | 881 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ofer | +2.274 |
ele | +1.740 |
etz | +1.725 |
wards | +1.708 |
itness | +1.702 |
Neg logit contributions | |
RED | -1.618 |
士 | -1.551 |
quished | -1.511 |
Thrones | -1.476 |
gio | -1.469 |
Token | smoother |
Token ID | 32686 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ofer | +1.742 |
ele | +1.333 |
etz | +1.322 |
wards | +1.309 |
itness | +1.305 |
Neg logit contributions | |
RED | -1.237 |
士 | -1.184 |
quished | -1.155 |
Thrones | -1.126 |
gio | -1.122 |
Token | series |
Token ID | 2168 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ofer | +3.510 |
ele | +2.667 |
etz | +2.642 |
wards | +2.628 |
itness | +2.608 |
Neg logit contributions | |
RED | -2.638 |
士 | -2.535 |
quished | -2.469 |
gio | -2.406 |
Thrones | -2.405 |
Token | of |
Token ID | 286 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
RED | +1.119 |
士 | +1.060 |
quished | +1.034 |
Thrones | +1.024 |
gio | +1.008 |
Neg logit contributions | |
ofer | -1.495 |
ele | -1.128 |
etz | -1.123 |
itness | -1.111 |
wards | -1.107 |
Token | the |
Token ID | 262 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ofer | +1.585 |
ele | +1.190 |
etz | +1.179 |
wards | +1.164 |
itness | +1.161 |
Neg logit contributions | |
RED | -1.288 |
士 | -1.238 |
quished | -1.209 |
Thrones | -1.183 |
gio | -1.176 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
ofer | +1.838 |
ele | +1.414 |
etz | +1.403 |
wards | +1.388 |
itness | +1.387 |
Neg logit contributions | |
RED | -1.248 |
士 | -1.192 |
quished | -1.162 |
Thrones | -1.136 |
gio | -1.129 |
Token | ic |
Token ID | 291 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
ofer | +10.560 |
etz | +7.452 |
ele | +7.411 |
wards | +7.095 |
itness | +6.940 |
Neg logit contributions | |
RED | -12.473 |
士 | -12.103 |
Thrones | -11.776 |
gio | -11.552 |
quished | -11.438 |
Token | emissions |
Token ID | 8971 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
RED | +0.564 |
士 | +0.539 |
quished | +0.527 |
Thrones | +0.512 |
gio | +0.511 |
Neg logit contributions | |
ofer | -0.815 |
ele | -0.623 |
etz | -0.620 |
itness | -0.612 |
wards | -0.612 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ofer | +3.983 |
ele | +3.017 |
etz | +2.984 |
wards | +2.970 |
itness | +2.940 |
Neg logit contributions | |
RED | -3.123 |
士 | -3.013 |
quished | -2.939 |
Thrones | -2.860 |
gio | -2.856 |
Token | but |
Token ID | 475 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
RED | +0.320 |
士 | +0.304 |
quished | +0.294 |
Thrones | +0.292 |
gio | +0.289 |
Neg logit contributions | |
ofer | -0.438 |
ele | -0.332 |
etz | -0.330 |
wards | -0.327 |
itness | -0.325 |
Token | mimic |
Token ID | 26332 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
ofer | +3.801 |
ele | +2.922 |
etz | +2.896 |
wards | +2.878 |
itness | +2.861 |
Neg logit contributions | |
RED | -2.654 |
士 | -2.550 |
quished | -2.486 |
gio | -2.406 |
Thrones | -2.405 |
Token | The |
Token ID | 464 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
RED | +0.052 |
士 | +0.050 |
quished | +0.048 |
gio | +0.047 |
Thrones | +0.047 |
Neg logit contributions | |
ofer | -0.060 |
ele | -0.044 |
etz | -0.044 |
wards | -0.044 |
itness | -0.044 |
Token | picture |
Token ID | 4286 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
RED | +1.228 |
士 | +1.149 |
Thrones | +1.117 |
quished | +1.107 |
gio | +1.080 |
Neg logit contributions | |
ofer | -2.183 |
ele | -1.722 |
etz | -1.704 |
itness | -1.676 |
wards | -1.670 |
Token | was |
Token ID | 373 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
RED | +3.569 |
士 | +3.289 |
Thrones | +3.240 |
quished | +3.167 |
gio | +3.136 |
Neg logit contributions | |
ofer | -5.319 |
ele | -4.072 |
etz | -4.057 |
itness | -4.048 |
wards | -3.937 |
Token | refuted |
Token ID | 49402 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
RED | +1.027 |
士 | +0.956 |
quished | +0.936 |
Thrones | +0.935 |
gio | +0.914 |
Neg logit contributions | |
ofer | -1.588 |
ele | -1.234 |
etz | -1.222 |
itness | -1.208 |
wards | -1.191 |
Token | by |
Token ID | 416 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
RED | +1.729 |
士 | +1.644 |
quished | +1.607 |
Thrones | +1.582 |
gio | +1.577 |
Neg logit contributions | |
ofer | -2.195 |
ele | -1.660 |
etz | -1.641 |
itness | -1.628 |
wards | -1.607 |
Token | twe |
Token ID | 4184 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
RED | +1.359 |
士 | +1.286 |
quished | +1.258 |
Thrones | +1.243 |
gio | +1.220 |
Neg logit contributions | |
ofer | -1.930 |
ele | -1.484 |
etz | -1.467 |
itness | -1.437 |
wards | -1.436 |
Token | eter |
Token ID | 2357 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
ofer | +10.223 |
ele | +7.296 |
etz | +7.061 |
itness | +6.910 |
elin | +6.806 |
Neg logit contributions | |
RED | -13.403 |
士 | -13.293 |
quished | -12.638 |
Thrones | -12.376 |
gio | -12.291 |
Token | Av |
Token ID | 5184 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
ofer | +2.848 |
ele | +2.176 |
etz | +2.152 |
wards | +2.133 |
itness | +2.122 |
Neg logit contributions | |
RED | -2.067 |
士 | -1.991 |
quished | -1.942 |
gio | -1.883 |
Thrones | -1.883 |
Token | i |
Token ID | 72 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
RED | +2.267 |
士 | +2.159 |
quished | +2.156 |
gio | +2.138 |
Thrones | +2.084 |
Neg logit contributions | |
ofer | -2.291 |
ele | -1.661 |
etz | -1.636 |
itness | -1.625 |
wards | -1.604 |
Token | Mayer |
Token ID | 33996 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
RED | +3.855 |
quished | +3.639 |
士 | +3.632 |
Thrones | +3.588 |
gio | +3.536 |
Neg logit contributions | |
ofer | -5.587 |
ele | -4.270 |
itness | -4.251 |
etz | -4.193 |
wards | -4.191 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
RED | +1.227 |
士 | +1.175 |
quished | +1.144 |
gio | +1.124 |
Thrones | +1.123 |
Neg logit contributions | |
ofer | -1.572 |
ele | -1.188 |
etz | -1.175 |
itness | -1.173 |
wards | -1.169 |
Token | high |
Token ID | 1029 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
ofer | +3.546 |
ele | +2.719 |
wards | +2.687 |
etz | +2.684 |
itness | +2.657 |
Neg logit contributions | |
RED | -2.485 |
士 | -2.385 |
quished | -2.327 |
gio | -2.270 |
Thrones | -2.250 |
Token | - |
Token ID | 12 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
ofer | +4.305 |
ele | +3.192 |
wards | +3.138 |
etz | +3.082 |
itness | +3.061 |
Neg logit contributions | |
RED | -4.135 |
士 | -3.986 |
quished | -3.904 |
gio | -3.803 |
Thrones | -3.781 |
Token | performance |
Token ID | 26585 |
Feature activation | +6.89e+00 |
Pos logit contributions | |
ofer | +3.938 |
ele | +2.782 |
wards | +2.694 |
etz | +2.660 |
itness | +2.644 |
Neg logit contributions | |
RED | -4.821 |
士 | -4.703 |
quished | -4.642 |
Thrones | -4.554 |
gio | -4.474 |
Token | off |
Token ID | 572 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ofer | +6.721 |
ele | +5.073 |
wards | +5.030 |
etz | +4.970 |
itness | +4.879 |
Neg logit contributions | |
RED | -5.127 |
士 | -4.903 |
quished | -4.844 |
gio | -4.785 |
Thrones | -4.615 |
Token | - |
Token ID | 12 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
ofer | +1.706 |
ele | +1.254 |
etz | +1.244 |
wards | +1.242 |
itness | +1.209 |
Neg logit contributions | |
RED | -1.617 |
士 | -1.572 |
quished | -1.535 |
gio | -1.504 |
Thrones | -1.477 |
Token | road |
Token ID | 6344 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
ofer | +5.925 |
ele | +4.419 |
wards | +4.297 |
etz | +4.268 |
itness | +4.149 |
Neg logit contributions | |
RED | -5.502 |
士 | -5.435 |
quished | -5.376 |
Thrones | -5.162 |
gio | -5.112 |
Token | pickup |
Token ID | 19422 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
ofer | +12.852 |
ele | +9.612 |
wards | +9.594 |
itness | +9.243 |
etz | +9.230 |
Neg logit contributions | |
RED | -10.146 |
gio | -9.644 |
quished | -9.514 |
士 | -9.447 |
Thrones | -8.914 |
Token | in |
Token ID | 287 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
ofer | +6.337 |
ele | +4.768 |
wards | +4.639 |
etz | +4.633 |
itness | +4.519 |
Neg logit contributions | |
RED | -5.093 |
士 | -4.950 |
quished | -4.850 |
gio | -4.761 |
Thrones | -4.654 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ofer | +0.623 |
ele | +0.467 |
etz | +0.463 |
wards | +0.458 |
itness | +0.457 |
Neg logit contributions | |
RED | -0.508 |
士 | -0.488 |
quished | -0.476 |
Thrones | -0.467 |
gio | -0.464 |
Token | company |
Token ID | 1664 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
RED | +0.812 |
士 | +0.770 |
Thrones | +0.742 |
quished | +0.737 |
gio | +0.721 |
Neg logit contributions | |
ofer | -1.338 |
etz | -1.035 |
ele | -1.034 |
wards | -1.032 |
itness | -1.026 |
Token | 's |
Token ID | 338 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ofer | +1.209 |
ele | +0.878 |
etz | +0.870 |
itness | +0.864 |
wards | +0.862 |
Neg logit contributions | |
RED | -1.163 |
士 | -1.116 |
quished | -1.088 |
Thrones | -1.073 |
gio | -1.065 |
Token | lett |
Token ID | 15503 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ofer | +7.869 |
etz | +4.516 |
ele | +4.261 |
itness | +4.192 |
wards | +4.130 |
Neg logit contributions | |
RED | -18.583 |
士 | -18.411 |
quished | -17.809 |
Thrones | -17.485 |
FACE | -17.297 |
Token | , |
Token ID | 11 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ofer | +3.172 |
ele | +2.392 |
etz | +2.367 |
wards | +2.350 |
itness | +2.329 |
Neg logit contributions | |
RED | -2.530 |
士 | -2.429 |
quished | -2.375 |
gio | -2.315 |
Thrones | -2.315 |
Token | the |
Token ID | 262 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
RED | +0.459 |
士 | +0.439 |
quished | +0.427 |
Thrones | +0.420 |
gio | +0.417 |
Neg logit contributions | |
ofer | -0.573 |
ele | -0.429 |
etz | -0.429 |
itness | -0.423 |
wards | -0.422 |
Token | president |
Token ID | 1893 |
Feature activation | +8.09e+00 |
Pos logit contributions | |
RED | +0.387 |
士 | +0.371 |
quished | +0.364 |
Thrones | +0.359 |
gio | +0.357 |
Neg logit contributions | |
ofer | -0.398 |
ele | -0.290 |
etz | -0.288 |
itness | -0.284 |
wards | -0.283 |
Token | of |
Token ID | 286 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ofer | +6.827 |
ele | +5.076 |
etz | +4.934 |
wards | +4.906 |
itness | +4.688 |
Neg logit contributions | |
RED | -6.863 |
士 | -6.530 |
quished | -6.496 |
Thrones | -6.449 |
gio | -6.336 |
Token | Hew |
Token ID | 30446 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
ofer | +3.225 |
ele | +2.302 |
etz | +2.270 |
wards | +2.260 |
itness | +2.233 |
Neg logit contributions | |
RED | -3.534 |
士 | -3.422 |
quished | -3.346 |
gio | -3.284 |
Thrones | -3.275 |
Token | lett |
Token ID | 15503 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ofer | +6.867 |
etz | +3.916 |
ele | +3.712 |
wards | +3.644 |
itness | +3.562 |
Neg logit contributions | |
RED | -16.630 |
士 | -16.431 |
quished | -15.996 |
Thrones | -15.701 |
gio | -15.557 |
Token | Pack |
Token ID | 6400 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ofer | +2.687 |
ele | +2.037 |
etz | +2.025 |
wards | +2.011 |
itness | +1.991 |
Neg logit contributions | |
RED | -2.041 |
士 | -1.955 |
quished | -1.913 |
Thrones | -1.861 |
gio | -1.860 |
Token | ard |
Token ID | 446 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
RED | +2.062 |
士 | +2.028 |
quished | +1.933 |
gio | +1.930 |
Thrones | +1.905 |
Neg logit contributions | |
ofer | -2.442 |
ele | -1.843 |
etz | -1.785 |
itness | -1.773 |
jri | -1.769 |
Token | ( |
Token ID | 357 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
RED | +0.914 |
士 | +0.888 |
quished | +0.854 |
Thrones | +0.831 |
gio | +0.821 |
Neg logit contributions | |
ofer | -1.390 |
ele | -1.067 |
etz | -1.061 |
itness | -1.060 |
wards | -1.056 |
Token | HP |
Token ID | 14082 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
RED | +0.265 |
士 | +0.255 |
quished | +0.247 |
gio | +0.243 |
Thrones | +0.241 |
Neg logit contributions | |
ofer | -0.262 |
ele | -0.188 |
etz | -0.188 |
itness | -0.185 |
wards | -0.185 |
Token | actually |
Token ID | 1682 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ofer | +0.005 |
ele | +0.003 |
etz | +0.003 |
itness | +0.003 |
wards | +0.003 |
Neg logit contributions | |
RED | -0.004 |
士 | -0.003 |
Thrones | -0.003 |
quished | -0.003 |
gio | -0.003 |
Token | called |
Token ID | 1444 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ofer | +3.996 |
ele | +3.007 |
etz | +2.975 |
wards | +2.961 |
itness | +2.926 |
Neg logit contributions | |
RED | -3.244 |
士 | -3.141 |
quished | -3.069 |
gio | -2.975 |
Thrones | -2.969 |
Token | the |
Token ID | 262 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ofer | +2.547 |
ele | +1.925 |
etz | +1.904 |
wards | +1.897 |
itness | +1.876 |
Neg logit contributions | |
RED | -2.004 |
士 | -1.936 |
quished | -1.887 |
gio | -1.833 |
Thrones | -1.829 |
Token | � |
Token ID | 564 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
ofer | +3.616 |
ele | +2.764 |
etz | +2.745 |
wards | +2.723 |
itness | +2.694 |
Neg logit contributions | |
RED | -2.635 |
士 | -2.552 |
quished | -2.480 |
gio | -2.408 |
Thrones | -2.382 |
Token | � |
Token ID | 250 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ofer | +0.034 |
ele | +0.026 |
etz | +0.026 |
wards | +0.026 |
itness | +0.026 |
Neg logit contributions | |
RED | -0.020 |
士 | -0.019 |
quished | -0.019 |
Thrones | -0.018 |
gio | -0.018 |
Token | w |
Token ID | 86 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
ofer | +2.001 |
ele | +1.493 |
etz | +1.476 |
wards | +1.464 |
itness | +1.454 |
Neg logit contributions | |
RED | -1.715 |
士 | -1.656 |
quished | -1.618 |
Thrones | -1.580 |
gio | -1.576 |
Token | hip |
Token ID | 1056 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
ofer | +12.467 |
itness | +9.615 |
etz | +9.348 |
ele | +9.221 |
wards | +8.940 |
Neg logit contributions | |
士 | -10.731 |
RED | -10.674 |
quished | -10.163 |
gio | -10.022 |
Thrones | -9.978 |
Token | � |
Token ID | 447 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
ofer | +2.249 |
ele | +1.694 |
etz | +1.678 |
wards | +1.666 |
itness | +1.652 |
Neg logit contributions | |
RED | -1.803 |
士 | -1.742 |
quished | -1.701 |
Thrones | -1.655 |
gio | -1.652 |
Token | � |
Token ID | 251 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
ofer | +6.975 |
ele | +5.135 |
etz | +4.997 |
wards | +4.963 |
itness | +4.911 |
Neg logit contributions | |
RED | -5.698 |
士 | -5.461 |
quished | -5.370 |
gio | -5.252 |
Thrones | -5.245 |
Token | stitch |
Token ID | 24695 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
ofer | +3.698 |
ele | +2.823 |
etz | +2.787 |
wards | +2.769 |
itness | +2.743 |
Neg logit contributions | |
RED | -2.786 |
士 | -2.697 |
quished | -2.635 |
gio | -2.550 |
Thrones | -2.550 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ofer | +3.482 |
ele | +2.656 |
etz | +2.631 |
wards | +2.604 |
itness | +2.580 |
Neg logit contributions | |
RED | -2.599 |
士 | -2.531 |
quished | -2.457 |
gio | -2.387 |
Thrones | -2.387 |
Token | , |
Token ID | 11 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
ofer | +0.830 |
ele | +0.632 |
etz | +0.625 |
wards | +0.620 |
itness | +0.617 |
Neg logit contributions | |
RED | -0.631 |
士 | -0.608 |
quished | -0.592 |
gio | -0.578 |
Thrones | -0.576 |
Token | Liam |
Token ID | 31684 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
RED | +2.386 |
士 | +2.224 |
Thrones | +2.182 |
quished | +2.182 |
gio | +2.116 |
Neg logit contributions | |
ofer | -3.587 |
etz | -2.757 |
ele | -2.734 |
itness | -2.713 |
wards | -2.703 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ofer | +4.721 |
ele | +3.583 |
etz | +3.499 |
wards | +3.485 |
itness | +3.429 |
Neg logit contributions | |
RED | -3.807 |
士 | -3.696 |
quished | -3.588 |
gio | -3.476 |
Thrones | -3.442 |
Token | Stella |
Token ID | 45856 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
ofer | +0.239 |
ele | +0.181 |
etz | +0.181 |
itness | +0.180 |
wards | +0.178 |
Neg logit contributions | |
RED | -0.175 |
士 | -0.166 |
quished | -0.162 |
Thrones | -0.160 |
gio | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
RED | +0.657 |
士 | +0.632 |
quished | +0.616 |
Thrones | +0.601 |
gio | +0.599 |
Neg logit contributions | |
ofer | -0.866 |
ele | -0.657 |
etz | -0.651 |
wards | -0.645 |
itness | -0.642 |
Token | Hatt |
Token ID | 48509 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
RED | +0.320 |
士 | +0.305 |
quished | +0.297 |
Thrones | +0.292 |
gio | +0.289 |
Neg logit contributions | |
ofer | -0.460 |
ele | -0.352 |
etz | -0.350 |
wards | -0.347 |
itness | -0.347 |
Token | ie |
Token ID | 494 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ofer | +9.296 |
ele | +6.347 |
etz | +5.748 |
elin | +5.540 |
wards | +5.521 |
Neg logit contributions | |
士 | -14.336 |
RED | -14.160 |
quished | -13.657 |
Thrones | -13.424 |
Enix | -13.142 |
Token | and |
Token ID | 290 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ofer | +3.591 |
ele | +2.732 |
etz | +2.665 |
wards | +2.618 |
itness | +2.588 |
Neg logit contributions | |
RED | -3.052 |
士 | -2.975 |
quished | -2.897 |
gio | -2.805 |
Thrones | -2.801 |
Token | Finn |
Token ID | 15368 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ofer | +1.852 |
ele | +1.427 |
etz | +1.412 |
wards | +1.403 |
itness | +1.395 |
Neg logit contributions | |
RED | -1.257 |
士 | -1.207 |
quished | -1.174 |
Thrones | -1.140 |
gio | -1.139 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ofer | +4.060 |
ele | +3.100 |
etz | +3.038 |
itness | +2.989 |
wards | +2.989 |
Neg logit contributions | |
RED | -3.197 |
士 | -3.069 |
quished | -2.984 |
gio | -2.899 |
Thrones | -2.894 |
Token | and |
Token ID | 290 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
RED | +0.670 |
士 | +0.629 |
quished | +0.614 |
Thrones | +0.603 |
gio | +0.595 |
Neg logit contributions | |
ofer | -1.186 |
ele | -0.922 |
etz | -0.921 |
wards | -0.910 |
itness | -0.907 |
Token | $ |
Token ID | 720 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
RED | +0.331 |
士 | +0.313 |
quished | +0.305 |
Thrones | +0.302 |
gio | +0.301 |
Neg logit contributions | |
ofer | -0.463 |
ele | -0.355 |
etz | -0.353 |
itness | -0.348 |
wards | -0.347 |
Token | 50 |
Token ID | 1120 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
ofer | +0.557 |
ele | +0.387 |
etz | +0.386 |
itness | +0.381 |
wards | +0.379 |
Neg logit contributions | |
RED | -0.667 |
士 | -0.639 |
quished | -0.623 |
gio | -0.615 |
Thrones | -0.614 |
Token | million |
Token ID | 1510 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
RED | +0.508 |
士 | +0.486 |
quished | +0.475 |
Thrones | +0.461 |
gio | +0.460 |
Neg logit contributions | |
ofer | -0.719 |
ele | -0.551 |
etz | -0.546 |
wards | -0.542 |
itness | -0.540 |
Token | targeting |
Token ID | 10822 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
RED | +0.045 |
士 | +0.043 |
quished | +0.042 |
Thrones | +0.041 |
gio | +0.041 |
Neg logit contributions | |
ofer | -0.062 |
ele | -0.048 |
etz | -0.047 |
wards | -0.047 |
itness | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ofer | +4.561 |
ele | +3.435 |
wards | +3.388 |
etz | +3.387 |
itness | +3.348 |
Neg logit contributions | |
RED | -3.669 |
士 | -3.563 |
quished | -3.482 |
gio | -3.362 |
Thrones | -3.362 |
Token | education |
Token ID | 3707 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
ofer | +2.466 |
ele | +1.870 |
etz | +1.856 |
wards | +1.836 |
itness | +1.831 |
Neg logit contributions | |
RED | -1.871 |
士 | -1.794 |
quished | -1.743 |
Thrones | -1.712 |
gio | -1.705 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ofer | +11.260 |
ele | +8.428 |
wards | +8.240 |
itness | +7.900 |
etz | +7.868 |
Neg logit contributions | |
RED | -11.355 |
quished | -11.251 |
士 | -11.246 |
gio | -10.791 |
Thrones | -10.649 |
Token | technology |
Token ID | 3037 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
ofer | +2.108 |
ele | +1.592 |
etz | +1.576 |
wards | +1.562 |
itness | +1.555 |
Neg logit contributions | |
RED | -1.657 |
士 | -1.593 |
quished | -1.553 |
Thrones | -1.518 |
gio | -1.513 |
Token | sector |
Token ID | 6567 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ofer | +3.280 |
ele | +2.401 |
etz | +2.370 |
wards | +2.352 |
itness | +2.336 |
Neg logit contributions | |
RED | -3.150 |
士 | -3.044 |
quished | -2.980 |
Thrones | -2.913 |
gio | -2.907 |
Token | . |
Token ID | 13 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
ofer | +3.345 |
ele | +2.564 |
etz | +2.537 |
wards | +2.519 |
itness | +2.498 |
Neg logit contributions | |
RED | -2.385 |
士 | -2.296 |
quished | -2.239 |
Thrones | -2.178 |
gio | -2.170 |
Token |
|
Token ID | 198 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ofer | +0.068 |
ele | +0.051 |
etz | +0.050 |
wards | +0.050 |
itness | +0.050 |
Neg logit contributions | |
RED | -0.055 |
士 | -0.053 |
quished | -0.052 |
Thrones | -0.051 |
gio | -0.051 |
Token | ack |
Token ID | 441 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
ofer | +0.860 |
ele | +0.623 |
wards | +0.619 |
itness | +0.605 |
jri | +0.597 |
Neg logit contributions | |
RED | -0.895 |
士 | -0.858 |
quished | -0.841 |
gio | -0.838 |
Thrones | -0.818 |
Token | en |
Token ID | 268 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
RED | +0.568 |
士 | +0.531 |
quished | +0.526 |
gio | +0.523 |
Thrones | +0.516 |
Neg logit contributions | |
ofer | -0.634 |
ele | -0.465 |
itness | -0.464 |
wards | -0.462 |
etz | -0.460 |
Token | bush |
Token ID | 50231 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
ofer | +4.098 |
ele | +2.919 |
etz | +2.886 |
wards | +2.871 |
itness | +2.813 |
Neg logit contributions | |
RED | -4.472 |
士 | -4.343 |
quished | -4.235 |
Thrones | -4.131 |
gio | -4.101 |
Token | , |
Token ID | 11 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
ofer | +6.503 |
ele | +4.888 |
etz | +4.824 |
wards | +4.806 |
jri | +4.620 |
Neg logit contributions | |
RED | -5.674 |
士 | -5.480 |
quished | -5.302 |
Thrones | -5.181 |
gio | -5.172 |
Token | to |
Token ID | 284 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
RED | +0.487 |
士 | +0.468 |
quished | +0.454 |
Thrones | +0.451 |
gio | +0.447 |
Neg logit contributions | |
ofer | -0.555 |
ele | -0.410 |
etz | -0.407 |
itness | -0.404 |
wards | -0.399 |
Token | Triple |
Token ID | 19817 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
RED | +1.359 |
士 | +1.298 |
Thrones | +1.252 |
quished | +1.249 |
gio | +1.241 |
Neg logit contributions | |
ofer | -1.866 |
ele | -1.424 |
etz | -1.417 |
itness | -1.391 |
wards | -1.390 |
Token | - |
Token ID | 12 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
RED | +9.602 |
Thrones | +8.355 |
Breaker | +7.867 |
Enix | +7.670 |
Champions | +7.619 |
Neg logit contributions | |
ofer | -19.807 |
etz | -16.425 |
jri | -16.216 |
itness | -16.136 |
wards | -15.852 |
Token | A |
Token ID | 32 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
RED | +5.494 |
士 | +4.546 |
gio | +4.532 |
Thrones | +4.363 |
quished | +4.251 |
Neg logit contributions | |
ofer | -11.794 |
etz | -9.610 |
jri | -9.430 |
wards | -9.415 |
ele | -9.413 |
Token | to |
Token ID | 284 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
RED | +2.042 |
士 | +1.919 |
quished | +1.905 |
Thrones | +1.867 |
gio | +1.827 |
Neg logit contributions | |
ofer | -3.352 |
etz | -2.585 |
ele | -2.572 |
wards | -2.562 |
itness | -2.558 |
Token | tw |
Token ID | 665 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
RED | +2.137 |
士 | +1.991 |
gio | +1.960 |
Thrones | +1.947 |
quished | +1.921 |
Neg logit contributions | |
ofer | -3.190 |
ele | -2.485 |
etz | -2.451 |
wards | -2.444 |
itness | -2.432 |
Token | iddle |
Token ID | 2509 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
ofer | +3.999 |
ele | +2.866 |
etz | +2.853 |
itness | +2.791 |
wards | +2.737 |
Neg logit contributions | |
RED | -4.214 |
士 | -4.074 |
quished | -4.033 |
Thrones | -3.925 |
gio | -3.846 |
Token | of |
Token ID | 286 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
RED | +3.897 |
士 | +3.736 |
Thrones | +3.525 |
gio | +3.509 |
quished | +3.496 |
Neg logit contributions | |
ofer | -5.311 |
ele | -4.125 |
itness | -4.101 |
etz | -4.086 |
jri | -3.982 |
Token | lying |
Token ID | 9105 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ofer | +0.378 |
ele | +0.292 |
etz | +0.290 |
itness | +0.286 |
wards | +0.285 |
Neg logit contributions | |
RED | -0.254 |
士 | -0.243 |
quished | -0.235 |
Thrones | -0.231 |
gio | -0.229 |
Token | is |
Token ID | 318 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
ofer | +1.377 |
ele | +1.053 |
etz | +1.045 |
itness | +1.035 |
wards | +1.031 |
Neg logit contributions | |
RED | -0.978 |
士 | -0.938 |
quished | -0.906 |
Thrones | -0.893 |
gio | -0.887 |
Token | worse |
Token ID | 4785 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ofer | +0.604 |
ele | +0.457 |
etz | +0.455 |
itness | +0.450 |
wards | +0.440 |
Neg logit contributions | |
RED | -0.472 |
士 | -0.447 |
Thrones | -0.434 |
quished | -0.429 |
gio | -0.427 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
RED | +1.043 |
士 | +0.995 |
quished | +0.968 |
Thrones | +0.950 |
gio | +0.937 |
Neg logit contributions | |
ofer | -1.506 |
ele | -1.153 |
etz | -1.149 |
itness | -1.139 |
wards | -1.127 |
Token | Double |
Token ID | 11198 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
ofer | +1.068 |
ele | +0.810 |
etz | +0.803 |
itness | +0.797 |
wards | +0.791 |
Neg logit contributions | |
RED | -0.826 |
士 | -0.791 |
Thrones | -0.763 |
quished | -0.763 |
gio | -0.755 |
Token | - |
Token ID | 12 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
RED | +10.205 |
Thrones | +9.799 |
士 | +9.345 |
cups | +9.188 |
cup | +9.173 |
Neg logit contributions | |
ofer | -15.992 |
etz | -12.781 |
ele | -12.593 |
itness | -12.522 |
jri | -12.494 |
Token | think |
Token ID | 14925 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
RED | +6.566 |
士 | +5.918 |
quished | +5.883 |
Thrones | +5.836 |
gio | +5.767 |
Neg logit contributions | |
ofer | -8.171 |
etz | -6.190 |
ele | -6.130 |
itness | -6.102 |
jri | -6.012 |
Token | runs |
Token ID | 4539 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
RED | +1.660 |
士 | +1.590 |
quished | +1.539 |
Thrones | +1.510 |
gio | +1.499 |
Neg logit contributions | |
ofer | -2.501 |
ele | -1.928 |
etz | -1.918 |
itness | -1.903 |
wards | -1.882 |
Token | strong |
Token ID | 1913 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
ofer | +3.936 |
ele | +2.953 |
etz | +2.925 |
wards | +2.922 |
itness | +2.871 |
Neg logit contributions | |
RED | -3.176 |
士 | -3.061 |
quished | -3.007 |
gio | -2.899 |
Thrones | -2.896 |
Token | through |
Token ID | 832 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
RED | +0.457 |
士 | +0.438 |
quished | +0.429 |
Thrones | +0.420 |
gio | +0.417 |
Neg logit contributions | |
ofer | -0.571 |
ele | -0.429 |
etz | -0.427 |
itness | -0.421 |
wards | -0.418 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ofer | +0.675 |
ele | +0.517 |
etz | +0.512 |
wards | +0.509 |
itness | +0.505 |
Neg logit contributions | |
RED | -0.477 |
士 | -0.458 |
quished | -0.446 |
Thrones | -0.434 |
gio | -0.434 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
RED | +0.343 |
士 | +0.326 |
quished | +0.320 |
Thrones | +0.316 |
gio | +0.311 |
Neg logit contributions | |
ofer | -0.430 |
ele | -0.325 |
etz | -0.324 |
wards | -0.320 |
itness | -0.320 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
RED | +1.687 |
士 | +1.475 |
gio | +1.462 |
Thrones | +1.442 |
quished | +1.406 |
Neg logit contributions | |
ofer | -2.447 |
challeng | -2.007 |
jri | -1.935 |
etz | -1.896 |
itness | -1.890 |
Token | COM |
Token ID | 9858 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
RED | +1.184 |
士 | +1.083 |
quished | +1.066 |
gio | +1.042 |
Thrones | +1.036 |
Neg logit contributions | |
ofer | -1.385 |
etz | -1.034 |
itness | -1.031 |
ele | -1.029 |
wards | -1.019 |
Token | IC |
Token ID | 2149 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
RED | +3.289 |
士 | +2.913 |
Thrones | +2.743 |
quished | +2.714 |
gio | +2.624 |
Neg logit contributions | |
ofer | -6.985 |
jri | -5.748 |
wards | -5.677 |
ele | -5.588 |
etz | -5.576 |
Token | V |
Token ID | 569 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
RED | +8.627 |
Thrones | +7.215 |
FACE | +7.176 |
quished | +7.081 |
士 | +6.904 |
Neg logit contributions | |
ofer | -14.547 |
jri | -12.482 |
etz | -11.970 |
wards | -11.943 |
itness | -11.879 |
Token | INE |
Token ID | 8881 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
RED | +10.383 |
士 | +9.071 |
Thrones | +9.024 |
quished | +8.590 |
ULAR | +8.251 |
Neg logit contributions | |
ofer | -16.053 |
jri | -12.899 |
itness | -12.726 |
wards | -12.304 |
ele | -12.116 |
Token | : |
Token ID | 25 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
RED | +6.781 |
quished | +5.897 |
Thrones | +5.877 |
士 | +5.826 |
gio | +5.544 |
Neg logit contributions | |
ofer | -11.489 |
itness | -9.149 |
jri | -9.051 |
ele | -9.043 |
etz | -8.976 |
Token | When |
Token ID | 1649 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
RED | +1.268 |
Thrones | +1.173 |
士 | +1.172 |
quished | +1.143 |
gio | +1.135 |
Neg logit contributions | |
ofer | -1.594 |
jri | -1.203 |
itness | -1.202 |
ele | -1.200 |
etz | -1.197 |
Token | you |
Token ID | 345 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
RED | +0.842 |
士 | +0.791 |
Thrones | +0.779 |
quished | +0.775 |
gio | +0.758 |
Neg logit contributions | |
ofer | -1.083 |
ele | -0.818 |
etz | -0.812 |
itness | -0.810 |
jri | -0.794 |
Token | think |
Token ID | 892 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
ofer | +0.999 |
ele | +0.774 |
etz | +0.767 |
wards | +0.759 |
itness | +0.756 |
Neg logit contributions | |
RED | -0.642 |
士 | -0.605 |
quished | -0.590 |
Thrones | -0.583 |
gio | -0.576 |
Token | mask |
Token ID | 27932 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
ofer | +0.479 |
ele | +0.354 |
etz | +0.350 |
wards | +0.347 |
itness | +0.345 |
Neg logit contributions | |
RED | -0.434 |
士 | -0.419 |
quished | -0.409 |
Thrones | -0.400 |
gio | -0.399 |
Token | ed |
Token ID | 276 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
RED | +3.631 |
士 | +3.421 |
quished | +3.407 |
Thrones | +3.279 |
gio | +3.268 |
Neg logit contributions | |
ofer | -4.379 |
ele | -3.253 |
itness | -3.236 |
wards | -3.228 |
etz | -3.204 |
Token | . |
Token ID | 13 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
RED | +0.022 |
士 | +0.021 |
quished | +0.021 |
Thrones | +0.020 |
gio | +0.020 |
Neg logit contributions | |
ofer | -0.032 |
ele | -0.024 |
etz | -0.024 |
wards | -0.024 |
itness | -0.024 |
Token | com |
Token ID | 785 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
RED | +2.931 |
士 | +2.740 |
quished | +2.708 |
gio | +2.672 |
Thrones | +2.668 |
Neg logit contributions | |
ofer | -3.472 |
ele | -2.574 |
wards | -2.553 |
etz | -2.548 |
itness | -2.539 |
Token | and |
Token ID | 290 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
ofer | +0.362 |
ele | +0.275 |
etz | +0.273 |
wards | +0.270 |
itness | +0.269 |
Neg logit contributions | |
RED | -0.274 |
士 | -0.264 |
quished | -0.257 |
Thrones | -0.251 |
gio | -0.250 |
Token | V |
Token ID | 569 |
Feature activation | -1.65e+01 |
Pos logit contributions | |
RED | +2.358 |
士 | +2.195 |
Thrones | +2.173 |
quished | +2.154 |
gio | +2.081 |
Neg logit contributions | |
ofer | -3.427 |
ele | -2.632 |
etz | -2.623 |
itness | -2.588 |
jri | -2.565 |
Token | odka |
Token ID | 28601 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
RED | +13.778 |
quished | +12.809 |
Thrones | +12.283 |
士 | +12.229 |
Breaker | +11.992 |
Neg logit contributions | |
ofer | -11.602 |
wards | -8.522 |
jri | -8.407 |
ele | -8.306 |
etz | -8.228 |
Token | O |
Token ID | 440 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
RED | +4.686 |
士 | +4.375 |
quished | +4.290 |
Thrones | +4.282 |
gio | +4.185 |
Neg logit contributions | |
ofer | -6.188 |
ele | -4.733 |
etz | -4.694 |
itness | -4.665 |
wards | -4.628 |
Token | ' |
Token ID | 6 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
RED | +1.032 |
士 | +0.993 |
quished | +0.976 |
Thrones | +0.960 |
gio | +0.956 |
Neg logit contributions | |
ofer | -0.988 |
ele | -0.710 |
etz | -0.702 |
wards | -0.699 |
itness | -0.693 |
Token | Clock |
Token ID | 44758 |
Feature activation | -6.36e+00 |
Pos logit contributions | |
RED | +2.132 |
士 | +2.017 |
Thrones | +1.970 |
quished | +1.967 |
gio | +1.922 |
Neg logit contributions | |
ofer | -2.950 |
ele | -2.243 |
etz | -2.235 |
wards | -2.224 |
itness | -2.206 |
Token | Podcast |
Token ID | 16036 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
RED | +4.466 |
士 | +4.232 |
Thrones | +4.183 |
quished | +4.143 |
gio | +4.041 |
Neg logit contributions | |
ofer | -6.343 |
ele | -4.895 |
etz | -4.802 |
jri | -4.782 |
itness | -4.758 |
Token | your |
Token ID | 534 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
RED | +0.430 |
士 | +0.411 |
quished | +0.402 |
Thrones | +0.394 |
gio | +0.391 |
Neg logit contributions | |
ofer | -0.550 |
ele | -0.416 |
etz | -0.412 |
wards | -0.407 |
itness | -0.406 |
Token | different |
Token ID | 1180 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
RED | +0.363 |
士 | +0.342 |
quished | +0.333 |
Thrones | +0.330 |
gio | +0.322 |
Neg logit contributions | |
ofer | -0.650 |
etz | -0.509 |
ele | -0.508 |
wards | -0.499 |
itness | -0.499 |
Token | media |
Token ID | 2056 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
RED | +2.982 |
士 | +2.777 |
Thrones | +2.759 |
quished | +2.730 |
gio | +2.631 |
Neg logit contributions | |
ofer | -4.573 |
etz | -3.495 |
ele | -3.491 |
jri | -3.448 |
itness | -3.428 |
Token | outlets |
Token ID | 12527 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
RED | +1.248 |
士 | +1.186 |
quished | +1.156 |
Thrones | +1.142 |
gio | +1.124 |
Neg logit contributions | |
ofer | -1.798 |
etz | -1.371 |
ele | -1.360 |
itness | -1.347 |
wards | -1.342 |
Token | . |
Token ID | 13 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
RED | +0.017 |
士 | +0.016 |
quished | +0.016 |
Thrones | +0.015 |
gio | +0.015 |
Neg logit contributions | |
ofer | -0.023 |
ele | -0.018 |
etz | -0.018 |
wards | -0.018 |
itness | -0.018 |
Token | Pixel |
Token ID | 11349 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
RED | +0.212 |
士 | +0.201 |
Thrones | +0.195 |
quished | +0.194 |
gio | +0.193 |
Neg logit contributions | |
ofer | -0.312 |
ele | -0.240 |
etz | -0.237 |
itness | -0.236 |
jri | -0.236 |
Token | pipe |
Token ID | 34360 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
RED | +9.945 |
gio | +8.917 |
士 | +8.722 |
cups | +8.478 |
plates | +8.469 |
Neg logit contributions | |
ofer | -14.363 |
challeng | -11.648 |
ele | -11.389 |
etz | -11.286 |
itness | -11.116 |
Token | supports |
Token ID | 6971 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
RED | +2.933 |
士 | +2.777 |
Thrones | +2.707 |
quished | +2.644 |
gio | +2.642 |
Neg logit contributions | |
ofer | -5.067 |
ele | -3.907 |
itness | -3.882 |
jri | -3.869 |
etz | -3.861 |
Token | over |
Token ID | 625 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
RED | +0.422 |
士 | +0.399 |
Thrones | +0.389 |
quished | +0.388 |
gio | +0.381 |
Neg logit contributions | |
ofer | -0.598 |
ele | -0.455 |
etz | -0.452 |
itness | -0.449 |
wards | -0.444 |
Token | 110 |
Token ID | 9796 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
ofer | +4.871 |
ele | +3.664 |
etz | +3.599 |
wards | +3.586 |
itness | +3.545 |
Neg logit contributions | |
RED | -4.188 |
士 | -4.108 |
quished | -3.984 |
Thrones | -3.858 |
gio | -3.854 |
Token | services |
Token ID | 2594 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
ofer | +0.774 |
ele | +0.601 |
etz | +0.596 |
wards | +0.591 |
itness | +0.589 |
Neg logit contributions | |
RED | -0.487 |
士 | -0.465 |
quished | -0.452 |
Thrones | -0.440 |
gio | -0.439 |
Token | z |
Token ID | 89 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
ofer | +0.149 |
ele | +0.111 |
etz | +0.110 |
wards | +0.110 |
itness | +0.109 |
Neg logit contributions | |
RED | -0.124 |
士 | -0.118 |
quished | -0.115 |
gio | -0.113 |
Thrones | -0.112 |
Token | p |
Token ID | 79 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
ofer | +4.704 |
ele | +3.585 |
etz | +3.540 |
wards | +3.495 |
itness | +3.467 |
Neg logit contributions | |
RED | -3.640 |
士 | -3.568 |
quished | -3.461 |
Thrones | -3.424 |
gio | -3.326 |
Token | X |
Token ID | 55 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ofer | +4.808 |
ele | +3.665 |
etz | +3.627 |
wards | +3.577 |
itness | +3.552 |
Neg logit contributions | |
RED | -3.638 |
士 | -3.579 |
quished | -3.473 |
Thrones | -3.424 |
gio | -3.337 |
Token | e |
Token ID | 68 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
ofer | +0.382 |
ele | +0.282 |
etz | +0.280 |
wards | +0.277 |
itness | +0.276 |
Neg logit contributions | |
RED | -0.340 |
士 | -0.326 |
quished | -0.319 |
gio | -0.312 |
Thrones | -0.311 |
Token | — |
Token ID | 851 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ofer | +6.228 |
ele | +4.581 |
etz | +4.381 |
wards | +4.350 |
itness | +4.275 |
Neg logit contributions | |
RED | -6.614 |
士 | -6.507 |
quished | -6.459 |
Thrones | -6.201 |
gio | -6.201 |
Token | Color |
Token ID | 5315 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
RED | +0.948 |
士 | +0.907 |
quished | +0.880 |
Thrones | +0.868 |
gio | +0.859 |
Neg logit contributions | |
ofer | -1.438 |
ele | -1.107 |
etz | -1.101 |
wards | -1.091 |
itness | -1.089 |
Token | lines |
Token ID | 6615 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
RED | +13.059 |
Thrones | +11.994 |
士 | +11.860 |
quished | +11.685 |
Verge | +11.598 |
Neg logit contributions | |
ofer | -11.491 |
ele | -8.684 |
itness | -8.589 |
etz | -8.378 |
wards | -8.283 |
Token | . |
Token ID | 13 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
RED | +1.450 |
士 | +1.386 |
quished | +1.346 |
Thrones | +1.327 |
gio | +1.312 |
Neg logit contributions | |
ofer | -1.939 |
ele | -1.479 |
etz | -1.461 |
itness | -1.453 |
wards | -1.447 |
Token | com |
Token ID | 785 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
RED | +3.792 |
士 | +3.580 |
quished | +3.503 |
gio | +3.466 |
Thrones | +3.429 |
Neg logit contributions | |
ofer | -4.277 |
ele | -3.145 |
etz | -3.141 |
wards | -3.116 |
itness | -3.103 |
Token | (@ |
Token ID | 4275 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ofer | +0.206 |
ele | +0.155 |
etz | +0.154 |
wards | +0.152 |
itness | +0.152 |
Neg logit contributions | |
RED | -0.165 |
士 | -0.159 |
quished | -0.155 |
Thrones | -0.151 |
gio | -0.151 |
Token | Color |
Token ID | 10258 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
ofer | +2.609 |
ele | +2.008 |
etz | +1.974 |
wards | +1.965 |
itness | +1.948 |
Neg logit contributions | |
RED | -1.902 |
士 | -1.871 |
quished | -1.813 |
Thrones | -1.790 |
gio | -1.747 |
Token | wel |
Token ID | 5029 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
RED | +2.426 |
士 | +2.323 |
quished | +2.221 |
Thrones | +2.204 |
gio | +2.164 |
Neg logit contributions | |
ofer | -4.038 |
etz | -3.165 |
ele | -3.143 |
itness | -3.069 |
jri | -3.041 |
Token | ter |
Token ID | 353 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ofer | +3.663 |
ele | +2.499 |
wards | +2.456 |
itness | +2.449 |
etz | +2.437 |
Neg logit contributions | |
RED | -4.449 |
士 | -4.344 |
quished | -4.243 |
Thrones | -4.192 |
gio | -4.145 |
Token | weight |
Token ID | 6551 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
RED | +0.913 |
士 | +0.813 |
quished | +0.811 |
Thrones | +0.738 |
gio | +0.736 |
Neg logit contributions | |
ofer | -3.548 |
etz | -2.965 |
ele | -2.950 |
wards | -2.922 |
itness | -2.920 |
Token | while |
Token ID | 981 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
ofer | +0.897 |
ele | +0.703 |
etz | +0.698 |
wards | +0.692 |
itness | +0.690 |
Neg logit contributions | |
RED | -0.514 |
士 | -0.491 |
quished | -0.476 |
Thrones | -0.462 |
gio | -0.461 |
Token | suffering |
Token ID | 7195 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
RED | +4.019 |
士 | +3.706 |
Thrones | +3.630 |
quished | +3.598 |
gio | +3.533 |
Neg logit contributions | |
ofer | -6.737 |
etz | -5.311 |
ele | -5.252 |
itness | -5.108 |
wards | -5.099 |
Token | double |
Token ID | 4274 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
RED | +3.254 |
士 | +3.117 |
quished | +3.006 |
Thrones | +2.990 |
gio | +2.970 |
Neg logit contributions | |
ofer | -3.782 |
etz | -2.797 |
ele | -2.773 |
itness | -2.752 |
wards | -2.682 |
Token | vision |
Token ID | 5761 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
RED | +8.560 |
cup | +7.983 |
cups | +7.881 |
Thrones | +7.879 |
士 | +7.809 |
Neg logit contributions | |
ofer | -15.792 |
etz | -13.209 |
jri | -12.632 |
itness | -12.398 |
ele | -12.187 |
Token | and |
Token ID | 290 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
RED | +1.010 |
士 | +0.971 |
quished | +0.950 |
Thrones | +0.922 |
gio | +0.917 |
Neg logit contributions | |
ofer | -1.466 |
ele | -1.121 |
etz | -1.115 |
wards | -1.101 |
itness | -1.100 |
Token | a |
Token ID | 257 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
RED | +0.628 |
士 | +0.594 |
quished | +0.578 |
Thrones | +0.569 |
gio | +0.566 |
Neg logit contributions | |
ofer | -0.946 |
ele | -0.727 |
etz | -0.725 |
itness | -0.718 |
wards | -0.711 |
Token | ring |
Token ID | 5858 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
ofer | +0.216 |
ele | +0.167 |
etz | +0.166 |
wards | +0.165 |
itness | +0.165 |
Neg logit contributions | |
RED | -0.134 |
士 | -0.127 |
quished | -0.124 |
Thrones | -0.121 |
gio | -0.120 |
Token | that |
Token ID | 326 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
RED | +3.237 |
士 | +3.029 |
gio | +2.935 |
Thrones | +2.913 |
quished | +2.899 |
Neg logit contributions | |
ofer | -4.562 |
etz | -3.510 |
ele | -3.459 |
wards | -3.449 |
itness | -3.410 |
Token | career |
Token ID | 3451 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
RED | +0.194 |
士 | +0.186 |
quished | +0.181 |
Thrones | +0.179 |
gio | +0.178 |
Neg logit contributions | |
ofer | -0.266 |
etz | -0.202 |
ele | -0.201 |
wards | -0.196 |
itness | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
RED | +1.131 |
士 | +1.082 |
quished | +1.055 |
Thrones | +1.038 |
gio | +1.034 |
Neg logit contributions | |
ofer | -1.505 |
etz | -1.135 |
ele | -1.130 |
itness | -1.111 |
wards | -1.100 |
Token | I |
Token ID | 314 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ofer | +0.163 |
ele | +0.122 |
etz | +0.122 |
itness | +0.120 |
wards | +0.119 |
Neg logit contributions | |
RED | -0.132 |
士 | -0.127 |
quished | -0.124 |
Thrones | -0.122 |
gio | -0.121 |
Token | got |
Token ID | 1392 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
RED | +0.103 |
士 | +0.098 |
quished | +0.095 |
gio | +0.094 |
Thrones | +0.093 |
Neg logit contributions | |
ofer | -0.157 |
ele | -0.121 |
etz | -0.120 |
wards | -0.119 |
itness | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
RED | +1.037 |
士 | +0.983 |
quished | +0.963 |
Thrones | +0.958 |
gio | +0.953 |
Neg logit contributions | |
ofer | -1.272 |
ele | -0.942 |
etz | -0.942 |
itness | -0.927 |
wards | -0.912 |
Token | double |
Token ID | 4274 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
RED | +0.907 |
士 | +0.862 |
quished | +0.840 |
Thrones | +0.837 |
gio | +0.834 |
Neg logit contributions | |
ofer | -1.102 |
ele | -0.823 |
etz | -0.822 |
itness | -0.805 |
wards | -0.800 |
Token | hundred |
Token ID | 3470 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
RED | +9.123 |
cup | +8.512 |
Champions | +8.236 |
gio | +8.144 |
Thrones | +8.083 |
Neg logit contributions | |
ofer | -15.193 |
etz | -12.014 |
wards | -11.562 |
itness | -11.530 |
jri | -11.433 |
Token | at |
Token ID | 379 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
RED | +2.027 |
士 | +1.925 |
quished | +1.902 |
gio | +1.876 |
Thrones | +1.853 |
Neg logit contributions | |
ofer | -2.931 |
etz | -2.239 |
ele | -2.217 |
itness | -2.188 |
wards | -2.181 |
Token | Adelaide |
Token ID | 27139 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
RED | +0.204 |
士 | +0.195 |
quished | +0.190 |
Thrones | +0.187 |
gio | +0.187 |
Neg logit contributions | |
ofer | -0.268 |
ele | -0.202 |
etz | -0.201 |
itness | -0.198 |
wards | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ofer | +5.094 |
ele | +3.919 |
wards | +3.903 |
etz | +3.847 |
itness | +3.818 |
Neg logit contributions | |
RED | -3.924 |
士 | -3.787 |
quished | -3.743 |
Thrones | -3.579 |
gio | -3.556 |
Token | I |
Token ID | 314 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
RED | +1.221 |
士 | +1.156 |
quished | +1.127 |
gio | +1.119 |
Thrones | +1.113 |
Neg logit contributions | |
ofer | -1.533 |
etz | -1.144 |
ele | -1.139 |
itness | -1.125 |
wards | -1.114 |
Token | mask |
Token ID | 27932 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
RED | +0.357 |
士 | +0.332 |
quished | +0.329 |
gio | +0.322 |
Thrones | +0.318 |
Neg logit contributions | |
ofer | -0.500 |
ele | -0.380 |
etz | -0.377 |
itness | -0.374 |
wards | -0.372 |
Token | ed |
Token ID | 276 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
RED | +4.400 |
quished | +3.932 |
士 | +3.918 |
gio | +3.806 |
Thrones | +3.757 |
Neg logit contributions | |
ofer | -6.911 |
challeng | -5.834 |
jri | -5.490 |
itness | -5.370 |
ele | -5.256 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
RED | +0.127 |
士 | +0.123 |
quished | +0.120 |
Thrones | +0.117 |
gio | +0.116 |
Neg logit contributions | |
ofer | -0.179 |
ele | -0.137 |
etz | -0.136 |
wards | -0.135 |
itness | -0.134 |
Token | com |
Token ID | 785 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
RED | +1.716 |
士 | +1.650 |
quished | +1.617 |
Thrones | +1.583 |
gio | +1.581 |
Neg logit contributions | |
ofer | -1.832 |
ele | -1.343 |
etz | -1.329 |
wards | -1.319 |
itness | -1.311 |
Token | and |
Token ID | 290 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
ofer | +0.674 |
ele | +0.512 |
etz | +0.509 |
wards | +0.504 |
itness | +0.501 |
Neg logit contributions | |
RED | -0.498 |
士 | -0.481 |
quished | -0.467 |
gio | -0.455 |
Thrones | -0.455 |
Token | V |
Token ID | 569 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
RED | +1.365 |
士 | +1.289 |
quished | +1.256 |
Thrones | +1.232 |
gio | +1.213 |
Neg logit contributions | |
ofer | -2.336 |
ele | -1.829 |
etz | -1.819 |
wards | -1.801 |
itness | -1.797 |
Token | odka |
Token ID | 28601 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
RED | +6.704 |
quished | +5.861 |
Thrones | +5.682 |
gio | +5.548 |
士 | +5.345 |
Neg logit contributions | |
ofer | -16.423 |
challeng | -14.595 |
jri | -13.667 |
wards | -13.595 |
ele | -13.359 |
Token | O |
Token ID | 440 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
RED | +4.623 |
Thrones | +4.353 |
士 | +4.276 |
quished | +4.272 |
gio | +3.970 |
Neg logit contributions | |
ofer | -10.056 |
itness | -8.254 |
ele | -8.231 |
etz | -8.158 |
wards | -8.144 |
Token | ' |
Token ID | 6 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
RED | +2.958 |
Thrones | +2.744 |
士 | +2.731 |
gio | +2.674 |
quished | +2.666 |
Neg logit contributions | |
ofer | -3.351 |
ele | -2.521 |
itness | -2.493 |
challeng | -2.464 |
wards | -2.454 |
Token | Clock |
Token ID | 44758 |
Feature activation | -6.36e+00 |
Pos logit contributions | |
RED | +2.004 |
士 | +1.816 |
Thrones | +1.801 |
gio | +1.740 |
quished | +1.736 |
Neg logit contributions | |
ofer | -3.643 |
itness | -2.865 |
etz | -2.864 |
jri | -2.863 |
wards | -2.853 |
Token | Podcast |
Token ID | 16036 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
RED | +2.958 |
士 | +2.729 |
quished | +2.686 |
Thrones | +2.643 |
gio | +2.523 |
Neg logit contributions | |
ofer | -7.892 |
ele | -6.446 |
etz | -6.361 |
wards | -6.346 |
itness | -6.326 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
RED | +0.335 |
士 | +0.307 |
gio | +0.303 |
Thrones | +0.299 |
quished | +0.295 |
Neg logit contributions | |
ofer | -0.462 |
challeng | -0.352 |
etz | -0.352 |
jri | -0.351 |
itness | -0.350 |
Token | Though |
Token ID | 10915 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
RED | +0.220 |
士 | +0.210 |
quished | +0.206 |
gio | +0.201 |
Thrones | +0.200 |
Neg logit contributions | |
ofer | -0.229 |
ele | -0.167 |
etz | -0.166 |
wards | -0.163 |
itness | -0.163 |
Token | he |
Token ID | 339 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ofer | +1.415 |
ele | +1.071 |
etz | +1.059 |
wards | +1.055 |
itness | +1.047 |
Neg logit contributions | |
RED | -1.107 |
士 | -1.065 |
quished | -1.039 |
Thrones | -1.012 |
gio | -1.010 |
Token | scored |
Token ID | 7781 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
ofer | +1.273 |
ele | +0.976 |
etz | +0.968 |
wards | +0.959 |
itness | +0.958 |
Neg logit contributions | |
RED | -0.883 |
士 | -0.847 |
quished | -0.824 |
Thrones | -0.803 |
gio | -0.801 |
Token | five |
Token ID | 1936 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
RED | +2.424 |
士 | +2.281 |
gio | +2.233 |
Thrones | +2.223 |
quished | +2.213 |
Neg logit contributions | |
ofer | -3.267 |
etz | -2.478 |
ele | -2.441 |
itness | -2.412 |
wards | -2.359 |
Token | double |
Token ID | 4274 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
RED | +2.286 |
士 | +2.199 |
gio | +2.105 |
quished | +2.096 |
Thrones | +2.080 |
Neg logit contributions | |
ofer | -3.664 |
etz | -2.852 |
ele | -2.809 |
itness | -2.768 |
wards | -2.756 |
Token | Test |
Token ID | 6208 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
RED | +7.634 |
cups | +7.438 |
Thrones | +7.042 |
士 | +7.037 |
cup | +7.037 |
Neg logit contributions | |
ofer | -16.659 |
etz | -13.478 |
itness | -12.479 |
ele | -12.428 |
jri | -12.321 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
RED | +2.196 |
士 | +2.096 |
gio | +2.005 |
quished | +2.000 |
Thrones | +1.964 |
Neg logit contributions | |
ofer | -3.854 |
etz | -3.009 |
ele | -2.960 |
itness | -2.930 |
wards | -2.914 |
Token | and |
Token ID | 290 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
RED | +1.810 |
士 | +1.741 |
quished | +1.702 |
gio | +1.667 |
Thrones | +1.659 |
Neg logit contributions | |
ofer | -2.432 |
etz | -1.827 |
ele | -1.826 |
itness | -1.801 |
wards | -1.792 |
Token | also |
Token ID | 635 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
RED | +2.028 |
士 | +1.938 |
gio | +1.866 |
quished | +1.859 |
Thrones | +1.850 |
Neg logit contributions | |
ofer | -3.002 |
etz | -2.274 |
ele | -2.267 |
itness | -2.264 |
jri | -2.206 |
Token | got |
Token ID | 1392 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ofer | +1.708 |
ele | +1.316 |
etz | +1.305 |
wards | +1.295 |
itness | +1.290 |
Neg logit contributions | |
RED | -1.139 |
士 | -1.092 |
quished | -1.062 |
Thrones | -1.034 |
gio | -1.031 |
Token | Arn |
Token ID | 16644 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
RED | +2.827 |
士 | +2.715 |
quished | +2.619 |
gio | +2.594 |
Thrones | +2.587 |
Neg logit contributions | |
ofer | -3.943 |
etz | -3.001 |
ele | -2.997 |
itness | -2.954 |
wards | -2.884 |
Token | ott |
Token ID | 1252 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ofer | +1.957 |
ele | +1.486 |
wards | +1.444 |
itness | +1.443 |
etz | +1.432 |
Neg logit contributions | |
RED | -1.674 |
士 | -1.607 |
quished | -1.580 |
gio | -1.563 |
Thrones | -1.544 |
Token | � |
Token ID | 447 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
RED | +0.023 |
士 | +0.022 |
quished | +0.021 |
gio | +0.021 |
Thrones | +0.021 |
Neg logit contributions | |
ofer | -0.036 |
ele | -0.028 |
etz | -0.028 |
itness | -0.027 |
wards | -0.027 |
Token | � |
Token ID | 247 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
RED | +0.463 |
士 | +0.418 |
quished | +0.385 |
gio | +0.381 |
Thrones | +0.379 |
Neg logit contributions | |
ofer | -1.561 |
ele | -1.298 |
etz | -1.285 |
wards | -1.277 |
itness | -1.274 |
Token | s |
Token ID | 82 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
RED | +4.507 |
士 | +4.309 |
gio | +4.227 |
quished | +4.196 |
Thrones | +4.052 |
Neg logit contributions | |
ofer | -5.192 |
etz | -3.830 |
ele | -3.819 |
itness | -3.771 |
wards | -3.709 |
Token | double |
Token ID | 4274 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
RED | +0.732 |
士 | +0.688 |
quished | +0.668 |
Thrones | +0.666 |
gio | +0.663 |
Neg logit contributions | |
ofer | -1.058 |
ele | -0.811 |
etz | -0.807 |
itness | -0.787 |
wards | -0.782 |
Token | - |
Token ID | 12 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
RED | +9.085 |
士 | +8.026 |
cup | +7.960 |
quished | +7.953 |
Thrones | +7.776 |
Neg logit contributions | |
ofer | -15.154 |
etz | -12.235 |
itness | -11.579 |
ele | -11.422 |
jri | -11.293 |
Token | o |
Token ID | 78 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
RED | +4.104 |
士 | +3.818 |
gio | +3.801 |
quished | +3.754 |
Thrones | +3.671 |
Neg logit contributions | |
ofer | -4.713 |
etz | -3.507 |
itness | -3.443 |
ele | -3.425 |
jri | -3.373 |
Token | vert |
Token ID | 1851 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ofer | +1.559 |
ele | +1.040 |
etz | +1.022 |
wards | +1.014 |
itness | +1.005 |
Neg logit contributions | |
RED | -2.213 |
士 | -2.151 |
quished | -2.107 |
Thrones | -2.072 |
gio | -2.065 |
Token | ime |
Token ID | 524 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
RED | +1.666 |
士 | +1.547 |
quished | +1.505 |
Thrones | +1.459 |
gio | +1.432 |
Neg logit contributions | |
ofer | -3.264 |
wards | -2.558 |
ele | -2.553 |
etz | -2.552 |
itness | -2.522 |
Token | goal |
Token ID | 3061 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
RED | +0.944 |
士 | +0.892 |
quished | +0.881 |
gio | +0.859 |
Thrones | +0.855 |
Neg logit contributions | |
ofer | -1.311 |
etz | -0.995 |
ele | -0.995 |
itness | -0.966 |
wards | -0.964 |
Token | he |
Token ID | 339 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
RED | +1.450 |
士 | +1.364 |
Thrones | +1.359 |
quished | +1.327 |
gio | +1.291 |
Neg logit contributions | |
ofer | -2.030 |
etz | -1.553 |
itness | -1.528 |
ele | -1.526 |
jri | -1.497 |
Token | has |
Token ID | 468 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ofer | +0.715 |
ele | +0.547 |
etz | +0.544 |
itness | +0.540 |
wards | +0.539 |
Neg logit contributions | |
RED | -0.491 |
士 | -0.469 |
quished | -0.455 |
Thrones | -0.447 |
gio | -0.445 |
Token | to |
Token ID | 284 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ofer | +0.606 |
etz | +0.449 |
ele | +0.448 |
itness | +0.441 |
wards | +0.436 |
Neg logit contributions | |
RED | -0.504 |
士 | -0.482 |
quished | -0.469 |
Thrones | -0.468 |
gio | -0.460 |
Token | have |
Token ID | 423 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
RED | +1.279 |
士 | +1.205 |
Thrones | +1.175 |
gio | +1.158 |
quished | +1.156 |
Neg logit contributions | |
ofer | -1.882 |
etz | -1.456 |
ele | -1.443 |
wards | -1.413 |
jri | -1.412 |
Token | a |
Token ID | 257 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
RED | +0.964 |
士 | +0.908 |
Thrones | +0.904 |
quished | +0.884 |
gio | +0.874 |
Neg logit contributions | |
ofer | -1.222 |
etz | -0.917 |
ele | -0.905 |
itness | -0.891 |
jri | -0.877 |
Token | double |
Token ID | 4274 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
RED | +1.986 |
士 | +1.872 |
Thrones | +1.861 |
quished | +1.811 |
gio | +1.785 |
Neg logit contributions | |
ofer | -2.664 |
etz | -2.052 |
ele | -2.011 |
itness | -1.967 |
wards | -1.945 |
Token | standard |
Token ID | 3210 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
RED | +10.595 |
Thrones | +10.270 |
cup | +10.104 |
士 | +9.557 |
Enix | +9.481 |
Neg logit contributions | |
ofer | -12.830 |
jri | -9.933 |
etz | -9.904 |
itness | -9.544 |
ele | -9.264 |
Token | ," |
Token ID | 553 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
RED | +5.061 |
Thrones | +4.604 |
士 | +4.581 |
quished | +4.550 |
gio | +4.474 |
Neg logit contributions | |
ofer | -7.389 |
etz | -5.746 |
itness | -5.579 |
jri | -5.542 |
ele | -5.471 |
Token | says |
Token ID | 1139 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ofer | +2.442 |
ele | +1.855 |
etz | +1.834 |
wards | +1.824 |
itness | +1.812 |
Neg logit contributions | |
RED | -1.849 |
士 | -1.777 |
quished | -1.734 |
Thrones | -1.686 |
gio | -1.684 |
Token | Ad |
Token ID | 1215 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
ofer | +0.190 |
ele | +0.145 |
etz | +0.144 |
wards | +0.142 |
itness | +0.142 |
Neg logit contributions | |
RED | -0.140 |
士 | -0.135 |
quished | -0.131 |
Thrones | -0.129 |
gio | -0.128 |
Token | e |
Token ID | 68 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
ofer | +2.657 |
ele | +1.821 |
etz | +1.744 |
wards | +1.705 |
itness | +1.686 |
Neg logit contributions | |
RED | -3.921 |
士 | -3.815 |
quished | -3.707 |
Thrones | -3.667 |
gio | -3.611 |
Token | policy |
Token ID | 2450 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
RED | +1.264 |
士 | +1.201 |
quished | +1.182 |
Thrones | +1.175 |
gio | +1.147 |
Neg logit contributions | |
ofer | -1.264 |
ele | -0.919 |
etz | -0.915 |
itness | -0.905 |
wards | -0.900 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
RED | +0.632 |
士 | +0.602 |
quished | +0.584 |
Thrones | +0.573 |
gio | +0.570 |
Neg logit contributions | |
ofer | -0.977 |
etz | -0.750 |
ele | -0.750 |
itness | -0.741 |
wards | -0.739 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
RED | +2.132 |
士 | +2.021 |
Thrones | +1.997 |
gio | +1.952 |
quished | +1.948 |
Neg logit contributions | |
ofer | -2.878 |
ele | -2.191 |
etz | -2.175 |
jri | -2.165 |
itness | -2.165 |
Token |
|
Token ID | 198 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
RED | +0.805 |
士 | +0.731 |
gio | +0.726 |
Thrones | +0.713 |
quished | +0.699 |
Neg logit contributions | |
ofer | -1.149 |
challeng | -0.903 |
jri | -0.883 |
itness | -0.879 |
etz | -0.877 |
Token | US |
Token ID | 2937 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
RED | +0.463 |
士 | +0.430 |
quished | +0.420 |
gio | +0.413 |
Thrones | +0.409 |
Neg logit contributions | |
ofer | -0.569 |
etz | -0.426 |
ele | -0.425 |
itness | -0.423 |
wards | -0.422 |
Token | AT |
Token ID | 1404 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
RED | +7.971 |
士 | +7.342 |
quished | +7.103 |
Thrones | +7.021 |
Enix | +6.872 |
Neg logit contributions | |
ofer | -11.940 |
itness | -9.305 |
ele | -9.253 |
etz | -9.221 |
wards | -9.057 |
Token | OD |
Token ID | 3727 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
RED | +8.100 |
Thrones | +7.331 |
士 | +6.960 |
Enix | +6.460 |
FACE | +6.454 |
Neg logit contributions | |
ofer | -16.182 |
jri | -13.491 |
itness | -13.226 |
tons | -12.784 |
wards | -12.664 |
Token | AY |
Token ID | 4792 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
RED | +0.648 |
士 | +0.625 |
quished | +0.609 |
gio | +0.594 |
Thrones | +0.593 |
Neg logit contributions | |
ofer | -0.951 |
ele | -0.737 |
etz | -0.730 |
wards | -0.722 |
itness | -0.714 |
Token | OP |
Token ID | 13349 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
RED | +2.716 |
士 | +2.550 |
quished | +2.481 |
Thrones | +2.463 |
gio | +2.415 |
Neg logit contributions | |
ofer | -4.175 |
ele | -3.195 |
etz | -3.183 |
itness | -3.152 |
wards | -3.149 |
Token | IN |
Token ID | 1268 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
RED | +0.962 |
士 | +0.920 |
quished | +0.893 |
Thrones | +0.870 |
gio | +0.866 |
Neg logit contributions | |
ofer | -1.540 |
ele | -1.197 |
etz | -1.187 |
wards | -1.178 |
itness | -1.173 |
Token | ION |
Token ID | 2849 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
RED | +0.435 |
士 | +0.408 |
quished | +0.392 |
Thrones | +0.378 |
gio | +0.377 |
Neg logit contributions | |
ofer | -1.012 |
ele | -0.813 |
etz | -0.807 |
wards | -0.802 |
itness | -0.800 |
Token | brook |
Token ID | 19094 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
ofer | +0.947 |
ele | +0.674 |
etz | +0.666 |
wards | +0.659 |
itness | +0.655 |
Neg logit contributions | |
RED | -1.045 |
士 | -1.011 |
quished | -0.990 |
Thrones | -0.971 |
gio | -0.969 |
Token | on |
Token ID | 319 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
ofer | +5.656 |
ele | +4.370 |
etz | +4.280 |
wards | +4.278 |
itness | +4.207 |
Neg logit contributions | |
RED | -4.209 |
士 | -4.089 |
quished | -3.965 |
gio | -3.873 |
Thrones | -3.835 |
Token | the |
Token ID | 262 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
ofer | +0.883 |
ele | +0.659 |
etz | +0.652 |
wards | +0.646 |
itness | +0.643 |
Neg logit contributions | |
RED | -0.751 |
士 | -0.723 |
quished | -0.706 |
Thrones | -0.691 |
gio | -0.689 |
Token | map |
Token ID | 3975 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
RED | +0.611 |
士 | +0.580 |
quished | +0.571 |
Thrones | +0.565 |
gio | +0.559 |
Neg logit contributions | |
ofer | -0.605 |
ele | -0.435 |
etz | -0.432 |
itness | -0.427 |
wards | -0.424 |
Token | !) |
Token ID | 8133 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ofer | +0.990 |
ele | +0.735 |
etz | +0.725 |
wards | +0.719 |
itness | +0.713 |
Neg logit contributions | |
RED | -0.890 |
士 | -0.860 |
quished | -0.840 |
Thrones | -0.821 |
gio | -0.819 |
Token | Color |
Token ID | 5315 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
ofer | +2.160 |
ele | +1.634 |
etz | +1.619 |
wards | +1.604 |
itness | +1.599 |
Neg logit contributions | |
RED | -1.671 |
士 | -1.604 |
quished | -1.562 |
Thrones | -1.534 |
gio | -1.524 |
Token | and |
Token ID | 290 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
RED | +10.361 |
Thrones | +9.585 |
士 | +9.529 |
quished | +9.360 |
gio | +9.145 |
Neg logit contributions | |
ofer | -13.246 |
ele | -10.167 |
etz | -10.003 |
itness | -9.952 |
wards | -9.795 |
Token | size |
Token ID | 2546 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
RED | +2.948 |
士 | +2.779 |
Thrones | +2.751 |
quished | +2.668 |
gio | +2.652 |
Neg logit contributions | |
ofer | -4.125 |
ele | -3.143 |
etz | -3.104 |
wards | -3.093 |
itness | -3.083 |
Token | can |
Token ID | 460 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
RED | +2.964 |
士 | +2.807 |
Thrones | +2.701 |
quished | +2.689 |
gio | +2.658 |
Neg logit contributions | |
ofer | -4.540 |
etz | -3.501 |
ele | -3.487 |
itness | -3.481 |
wards | -3.427 |
Token | also |
Token ID | 635 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
RED | +1.573 |
士 | +1.499 |
quished | +1.436 |
Thrones | +1.429 |
gio | +1.424 |
Neg logit contributions | |
ofer | -2.635 |
ele | -2.063 |
etz | -2.046 |
wards | -2.031 |
itness | -2.029 |
Token | be |
Token ID | 307 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ofer | +0.255 |
ele | +0.194 |
etz | +0.193 |
wards | +0.191 |
itness | +0.190 |
Neg logit contributions | |
RED | -0.187 |
士 | -0.180 |
quished | -0.174 |
Thrones | -0.172 |
gio | -0.171 |
Token | like |
Token ID | 588 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
RED | +1.522 |
士 | +1.425 |
Thrones | +1.398 |
quished | +1.386 |
gio | +1.363 |
Neg logit contributions | |
ofer | -2.230 |
etz | -1.700 |
ele | -1.698 |
itness | -1.674 |
jri | -1.652 |
Token | salaries |
Token ID | 17058 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
ofer | +0.675 |
ele | +0.519 |
etz | +0.514 |
wards | +0.510 |
itness | +0.508 |
Neg logit contributions | |
RED | -0.460 |
士 | -0.441 |
quished | -0.429 |
Thrones | -0.418 |
gio | -0.417 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ofer | +4.347 |
ele | +3.258 |
etz | +3.247 |
wards | +3.182 |
itness | +3.128 |
Neg logit contributions | |
RED | -3.647 |
士 | -3.561 |
quished | -3.450 |
gio | -3.381 |
Thrones | -3.349 |
Token | upkeep |
Token ID | 47363 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
ofer | +0.144 |
ele | +0.111 |
etz | +0.110 |
wards | +0.109 |
itness | +0.108 |
Neg logit contributions | |
RED | -0.097 |
士 | -0.093 |
quished | -0.091 |
Thrones | -0.089 |
gio | -0.088 |
Token | ? |
Token ID | 30 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
ofer | +4.846 |
ele | +3.695 |
wards | +3.624 |
etz | +3.621 |
itness | +3.525 |
Neg logit contributions | |
RED | -4.021 |
士 | -3.921 |
quished | -3.795 |
gio | -3.719 |
Thrones | -3.663 |
Token | V |
Token ID | 569 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
ofer | +0.572 |
ele | +0.430 |
etz | +0.427 |
itness | +0.426 |
jri | +0.423 |
Neg logit contributions | |
RED | -0.450 |
士 | -0.425 |
Thrones | -0.417 |
quished | -0.413 |
gio | -0.411 |
Token | orn |
Token ID | 1211 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
RED | +11.425 |
quished | +10.942 |
士 | +10.697 |
gio | +10.330 |
Thrones | +10.307 |
Neg logit contributions | |
ofer | -11.531 |
wards | -9.013 |
jri | -8.674 |
etz | -8.667 |
itness | -8.594 |
Token | ado |
Token ID | 4533 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
RED | +1.242 |
quished | +1.155 |
士 | +1.146 |
gio | +1.144 |
Thrones | +1.098 |
Neg logit contributions | |
ofer | -3.726 |
ele | -3.081 |
itness | -3.058 |
jri | -3.052 |
etz | -3.031 |
Token | , |
Token ID | 11 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
RED | +3.167 |
士 | +3.011 |
quished | +2.950 |
Thrones | +2.947 |
gio | +2.860 |
Neg logit contributions | |
ofer | -3.798 |
ele | -2.815 |
itness | -2.788 |
etz | -2.777 |
wards | -2.773 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
RED | +3.119 |
士 | +2.907 |
Thrones | +2.898 |
quished | +2.883 |
gio | +2.787 |
Neg logit contributions | |
ofer | -4.097 |
etz | -3.065 |
itness | -3.049 |
ele | -3.044 |
wards | -3.033 |
Token | top |
Token ID | 1353 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
RED | +1.187 |
士 | +1.108 |
quished | +1.089 |
Thrones | +1.086 |
gio | +1.071 |
Neg logit contributions | |
ofer | -1.718 |
etz | -1.317 |
ele | -1.309 |
itness | -1.283 |
wards | -1.277 |
Token | why |
Token ID | 1521 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ofer | +1.144 |
ele | +0.839 |
etz | +0.833 |
itness | +0.820 |
wards | +0.819 |
Neg logit contributions | |
RED | -1.070 |
士 | -1.026 |
quished | -1.004 |
Thrones | -0.991 |
gio | -0.983 |
Token | L |
Token ID | 406 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ofer | +1.722 |
ele | +1.289 |
etz | +1.277 |
wards | +1.264 |
itness | +1.260 |
Neg logit contributions | |
RED | -1.432 |
士 | -1.377 |
quished | -1.344 |
Thrones | -1.317 |
gio | -1.311 |
Token | IGHT |
Token ID | 9947 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
RED | +1.849 |
士 | +1.732 |
quished | +1.698 |
gio | +1.661 |
Thrones | +1.646 |
Neg logit contributions | |
ofer | -2.377 |
ele | -1.821 |
etz | -1.792 |
wards | -1.784 |
itness | -1.776 |
Token | and |
Token ID | 290 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
RED | +7.790 |
士 | +6.898 |
Thrones | +6.870 |
quished | +6.640 |
FACE | +6.633 |
Neg logit contributions | |
ofer | -11.671 |
etz | -9.137 |
ele | -9.021 |
itness | -9.020 |
jri | -8.992 |
Token | COL |
Token ID | 20444 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
RED | +3.742 |
Thrones | +3.374 |
士 | +3.357 |
quished | +3.201 |
Enix | +3.163 |
Neg logit contributions | |
ofer | -6.229 |
ele | -4.832 |
etz | -4.828 |
itness | -4.815 |
jri | -4.807 |
Token | OR |
Token ID | 1581 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
RED | +5.097 |
士 | +4.380 |
Thrones | +4.252 |
quished | +4.103 |
gio | +4.093 |
Neg logit contributions | |
ofer | -7.974 |
etz | -6.307 |
ele | -6.268 |
jri | -6.185 |
itness | -6.134 |
Token | are |
Token ID | 389 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
RED | +9.081 |
士 | +8.122 |
Thrones | +8.057 |
FACE | +7.804 |
gio | +7.791 |
Neg logit contributions | |
ofer | -14.835 |
etz | -11.582 |
jri | -11.522 |
itness | -11.451 |
wards | -11.414 |
Token | such |
Token ID | 884 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
RED | +1.604 |
士 | +1.492 |
Thrones | +1.466 |
quished | +1.456 |
gio | +1.427 |
Neg logit contributions | |
ofer | -2.235 |
etz | -1.701 |
ele | -1.695 |
itness | -1.681 |
jri | -1.663 |
Token | important |
Token ID | 1593 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
ofer | +0.642 |
ele | +0.475 |
etz | +0.474 |
itness | +0.467 |
wards | +0.464 |
Neg logit contributions | |
RED | -0.556 |
士 | -0.531 |
quished | -0.520 |
Thrones | -0.513 |
gio | -0.509 |
Token | elements |
Token ID | 4847 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
ofer | +0.081 |
etz | +0.062 |
ele | +0.062 |
wards | +0.061 |
itness | +0.061 |
Neg logit contributions | |
RED | -0.055 |
士 | -0.053 |
quished | -0.051 |
Thrones | -0.050 |
gio | -0.050 |
Token | of |
Token ID | 286 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
RED | +0.781 |
士 | +0.744 |
quished | +0.732 |
Thrones | +0.719 |
gio | +0.712 |
Neg logit contributions | |
ofer | -0.868 |
ele | -0.640 |
etz | -0.637 |
wards | -0.628 |
itness | -0.626 |
Token | iding |
Token ID | 2530 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
RED | +2.328 |
quished | +2.217 |
士 | +2.206 |
gio | +2.168 |
Thrones | +2.141 |
Neg logit contributions | |
ofer | -2.318 |
ele | -1.674 |
wards | -1.633 |
etz | -1.632 |
itness | -1.630 |
Token | around |
Token ID | 1088 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ofer | +2.504 |
ele | +1.899 |
etz | +1.881 |
wards | +1.865 |
itness | +1.857 |
Neg logit contributions | |
RED | -1.907 |
士 | -1.832 |
quished | -1.786 |
Thrones | -1.744 |
gio | -1.739 |
Token | the |
Token ID | 262 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
ofer | +1.189 |
ele | +0.891 |
etz | +0.882 |
wards | +0.875 |
itness | +0.870 |
Neg logit contributions | |
RED | -0.985 |
士 | -0.950 |
quished | -0.927 |
Thrones | -0.904 |
gio | -0.903 |
Token | studio |
Token ID | 8034 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ofer | +0.084 |
ele | +0.065 |
etz | +0.064 |
wards | +0.064 |
itness | +0.063 |
Neg logit contributions | |
RED | -0.056 |
士 | -0.054 |
quished | -0.052 |
Thrones | -0.052 |
gio | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ofer | +3.375 |
ele | +2.570 |
etz | +2.538 |
wards | +2.532 |
itness | +2.503 |
Neg logit contributions | |
RED | -2.537 |
士 | -2.456 |
quished | -2.390 |
gio | -2.322 |
Thrones | -2.309 |
Token | red |
Token ID | 2266 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
RED | +0.839 |
士 | +0.804 |
quished | +0.784 |
Thrones | +0.774 |
gio | +0.767 |
Neg logit contributions | |
ofer | -0.963 |
ele | -0.711 |
etz | -0.704 |
itness | -0.698 |
wards | -0.696 |
Token | st |
Token ID | 336 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
RED | +8.676 |
cups | +8.062 |
gio | +8.045 |
cup | +8.019 |
Thrones | +8.009 |
Neg logit contributions | |
ofer | -14.981 |
etz | -11.321 |
itness | -11.173 |
jri | -10.990 |
ele | -10.977 |
Token | ile |
Token ID | 576 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ofer | +3.039 |
ele | +2.107 |
etz | +2.081 |
wards | +2.045 |
itness | +2.029 |
Neg logit contributions | |
RED | -3.894 |
士 | -3.791 |
quished | -3.704 |
Thrones | -3.640 |
gio | -3.611 |
Token | tt |
Token ID | 926 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
RED | +2.204 |
士 | +2.121 |
quished | +2.074 |
gio | +2.041 |
Thrones | +2.032 |
Neg logit contributions | |
ofer | -2.193 |
ele | -1.588 |
etz | -1.574 |
wards | -1.554 |
itness | -1.551 |
Token | os |
Token ID | 418 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
RED | +0.385 |
士 | +0.370 |
Thrones | +0.367 |
quished | +0.366 |
gio | +0.359 |
Neg logit contributions | |
ofer | -0.375 |
ele | -0.272 |
wards | -0.272 |
etz | -0.271 |
itness | -0.268 |
Token | , |
Token ID | 11 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
RED | +0.554 |
士 | +0.531 |
quished | +0.518 |
Thrones | +0.507 |
gio | +0.505 |
Neg logit contributions | |
ofer | -0.761 |
ele | -0.580 |
etz | -0.574 |
wards | -0.569 |
itness | -0.568 |
Token | with |
Token ID | 351 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
RED | +2.468 |
士 | +2.328 |
Thrones | +2.276 |
quished | +2.275 |
gio | +2.223 |
Neg logit contributions | |
ofer | -3.266 |
etz | -2.456 |
ele | -2.446 |
itness | -2.395 |
jri | -2.374 |
Token | family |
Token ID | 1641 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
RED | +1.181 |
士 | +1.121 |
Thrones | +1.098 |
quished | +1.085 |
gio | +1.062 |
Neg logit contributions | |
ofer | -1.664 |
etz | -1.268 |
ele | -1.266 |
itness | -1.242 |
wards | -1.236 |
Token | ," |
Token ID | 553 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ofer | +0.051 |
ele | +0.038 |
etz | +0.038 |
wards | +0.038 |
itness | +0.038 |
Neg logit contributions | |
RED | -0.039 |
士 | -0.037 |
quished | -0.037 |
Thrones | -0.036 |
gio | -0.036 |
Token | Walker |
Token ID | 10120 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
ofer | +2.695 |
ele | +2.049 |
etz | +2.042 |
wards | +2.041 |
itness | +1.998 |
Neg logit contributions | |
RED | -1.981 |
士 | -1.885 |
quished | -1.846 |
gio | -1.795 |
Thrones | -1.788 |
Token | told |
Token ID | 1297 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
ofer | +4.564 |
etz | +3.344 |
ele | +3.333 |
wards | +3.325 |
itness | +3.195 |
Neg logit contributions | |
RED | -4.331 |
士 | -4.127 |
quished | -4.091 |
gio | -3.983 |
Thrones | -3.953 |
Token | Triple |
Token ID | 19817 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
ofer | +0.893 |
ele | +0.693 |
etz | +0.687 |
wards | +0.680 |
itness | +0.680 |
Neg logit contributions | |
RED | -0.560 |
士 | -0.534 |
quished | -0.519 |
Thrones | -0.507 |
gio | -0.504 |
Token | M |
Token ID | 337 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
RED | +7.532 |
Enix | +6.404 |
Thrones | +6.390 |
gio | +6.191 |
Manip | +6.143 |
Neg logit contributions | |
ofer | -16.966 |
jri | -13.709 |
itness | -13.673 |
etz | -13.535 |
wards | -13.325 |
Token | . |
Token ID | 13 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
RED | +3.348 |
士 | +3.172 |
quished | +3.086 |
Thrones | +3.043 |
gio | +3.031 |
Neg logit contributions | |
ofer | -5.174 |
ele | -3.943 |
etz | -3.906 |
itness | -3.905 |
wards | -3.881 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
RED | +4.181 |
士 | +3.970 |
quished | +3.907 |
gio | +3.857 |
Thrones | +3.789 |
Neg logit contributions | |
ofer | -5.306 |
ele | -3.952 |
etz | -3.929 |
wards | -3.925 |
itness | -3.916 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
RED | +0.957 |
士 | +0.862 |
gio | +0.855 |
Thrones | +0.840 |
quished | +0.820 |
Neg logit contributions | |
ofer | -1.367 |
challeng | -1.084 |
jri | -1.055 |
itness | -1.045 |
etz | -1.043 |
Token | " |
Token ID | 1 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
RED | +0.186 |
士 | +0.179 |
quished | +0.176 |
gio | +0.172 |
Thrones | +0.172 |
Neg logit contributions | |
ofer | -0.156 |
ele | -0.109 |
etz | -0.108 |
itness | -0.106 |
wards | -0.106 |
Token | ANK |
Token ID | 15154 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
RED | +2.091 |
士 | +1.902 |
quished | +1.855 |
Thrones | +1.801 |
gio | +1.781 |
Neg logit contributions | |
ofer | -3.719 |
ele | -2.934 |
etz | -2.906 |
wards | -2.893 |
itness | -2.872 |
Token | M |
Token ID | 337 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
RED | +3.273 |
士 | +3.072 |
Thrones | +2.899 |
quished | +2.865 |
gio | +2.857 |
Neg logit contributions | |
ofer | -5.619 |
ele | -4.448 |
etz | -4.442 |
itness | -4.442 |
jri | -4.397 |
Token | ORD |
Token ID | 12532 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
RED | +2.252 |
士 | +2.091 |
quished | +2.042 |
gio | +1.962 |
Thrones | +1.957 |
Neg logit contributions | |
ofer | -3.284 |
ele | -2.540 |
wards | -2.513 |
itness | -2.502 |
etz | -2.499 |
Token | ICA |
Token ID | 25241 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
RED | +3.080 |
士 | +2.829 |
Thrones | +2.666 |
gio | +2.648 |
quished | +2.645 |
Neg logit contributions | |
ofer | -5.377 |
wards | -4.272 |
itness | -4.210 |
etz | -4.201 |
ele | -4.199 |
Token | , |
Token ID | 11 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
RED | +3.700 |
士 | +3.486 |
quished | +3.375 |
Thrones | +3.321 |
gio | +3.293 |
Neg logit contributions | |
ofer | -4.872 |
ele | -3.715 |
itness | -3.699 |
etz | -3.684 |
wards | -3.629 |
Token | V |
Token ID | 569 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
RED | +3.855 |
士 | +3.501 |
quished | +3.437 |
Thrones | +3.398 |
gio | +3.317 |
Neg logit contributions | |
ofer | -5.980 |
etz | -4.632 |
ele | -4.625 |
wards | -4.593 |
itness | -4.571 |
Token | AND |
Token ID | 6981 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
RED | +9.331 |
士 | +8.022 |
quished | +7.567 |
BOX | +7.481 |
Thrones | +7.416 |
Neg logit contributions | |
ofer | -14.657 |
wards | -11.626 |
ele | -11.587 |
etz | -11.410 |
jri | -11.405 |
Token | ER |
Token ID | 1137 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
RED | +1.946 |
士 | +1.710 |
quished | +1.627 |
gio | +1.587 |
Thrones | +1.584 |
Neg logit contributions | |
ofer | -4.216 |
wards | -3.367 |
jri | -3.362 |
itness | -3.353 |
etz | -3.337 |
Token | BIL |
Token ID | 19676 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
RED | +3.381 |
士 | +2.994 |
Thrones | +2.764 |
gio | +2.629 |
Enix | +2.598 |
Neg logit contributions | |
ofer | -8.450 |
ele | -7.003 |
etz | -6.966 |
itness | -6.932 |
wards | -6.892 |
Token | T |
Token ID | 51 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
RED | +1.809 |
士 | +1.671 |
quished | +1.635 |
Thrones | +1.619 |
gio | +1.595 |
Neg logit contributions | |
ofer | -3.010 |
ele | -2.366 |
etz | -2.350 |
wards | -2.335 |
itness | -2.306 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
RED | +2.442 |
士 | +2.300 |
quished | +2.210 |
Thrones | +2.192 |
gio | +2.144 |
Neg logit contributions | |
ofer | -3.675 |
ele | -2.863 |
etz | -2.841 |
itness | -2.813 |
jri | -2.798 |
Token | The |
Token ID | 383 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ofer | +0.081 |
etz | +0.061 |
ele | +0.061 |
itness | +0.060 |
wards | +0.060 |
Neg logit contributions | |
RED | -0.063 |
士 | -0.061 |
quished | -0.059 |
Thrones | -0.059 |
gio | -0.058 |
Token | perfect |
Token ID | 2818 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
RED | +1.296 |
士 | +1.231 |
quished | +1.198 |
Thrones | +1.183 |
gio | +1.166 |
Neg logit contributions | |
ofer | -1.910 |
etz | -1.465 |
ele | -1.465 |
wards | -1.442 |
itness | -1.438 |
Token | example |
Token ID | 1672 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
RED | +2.866 |
士 | +2.739 |
quished | +2.695 |
Thrones | +2.644 |
gio | +2.563 |
Neg logit contributions | |
ofer | -3.453 |
etz | -2.587 |
ele | -2.550 |
wards | -2.520 |
itness | -2.484 |
Token | of |
Token ID | 286 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
RED | +2.946 |
士 | +2.811 |
quished | +2.745 |
Thrones | +2.693 |
gio | +2.627 |
Neg logit contributions | |
ofer | -4.174 |
etz | -3.193 |
ele | -3.171 |
itness | -3.163 |
wards | -3.151 |
Token | these |
Token ID | 777 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ofer | +1.046 |
ele | +0.782 |
etz | +0.779 |
wards | +0.766 |
itness | +0.766 |
Neg logit contributions | |
RED | -0.864 |
士 | -0.831 |
quished | -0.810 |
Thrones | -0.795 |
gio | -0.790 |
Token | double |
Token ID | 4274 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
RED | +1.997 |
士 | +1.905 |
quished | +1.847 |
Thrones | +1.819 |
gio | +1.785 |
Neg logit contributions | |
ofer | -2.984 |
etz | -2.292 |
ele | -2.270 |
itness | -2.246 |
wards | -2.232 |
Token | standards |
Token ID | 5423 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
RED | +9.804 |
士 | +8.929 |
Thrones | +8.909 |
cups | +8.572 |
quished | +8.486 |
Neg logit contributions | |
ofer | -14.163 |
etz | -10.814 |
jri | -10.527 |
ele | -10.344 |
itness | -10.141 |
Token | is |
Token ID | 318 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
RED | +4.239 |
士 | +3.982 |
Thrones | +3.871 |
quished | +3.853 |
gio | +3.692 |
Neg logit contributions | |
ofer | -7.083 |
etz | -5.501 |
itness | -5.493 |
ele | -5.451 |
wards | -5.398 |
Token | the |
Token ID | 262 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ofer | +0.207 |
ele | +0.157 |
etz | +0.156 |
wards | +0.154 |
itness | +0.153 |
Neg logit contributions | |
RED | -0.158 |
士 | -0.151 |
quished | -0.148 |
Thrones | -0.145 |
gio | -0.144 |
Token | time |
Token ID | 640 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ofer | +0.037 |
ele | +0.028 |
etz | +0.028 |
wards | +0.028 |
itness | +0.028 |
Neg logit contributions | |
RED | -0.024 |
士 | -0.023 |
quished | -0.022 |
Thrones | -0.022 |
gio | -0.021 |
Token | required |
Token ID | 2672 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
RED | +1.536 |
士 | +1.469 |
quished | +1.433 |
Thrones | +1.407 |
gio | +1.389 |
Neg logit contributions | |
ofer | -1.972 |
etz | -1.496 |
ele | -1.492 |
wards | -1.456 |
itness | -1.455 |
Token | like |
Token ID | 588 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
RED | +0.893 |
士 | +0.850 |
quished | +0.830 |
Thrones | +0.818 |
gio | +0.812 |
Neg logit contributions | |
ofer | -1.121 |
ele | -0.840 |
etz | -0.836 |
itness | -0.830 |
wards | -0.826 |
Token | vinegar |
Token ID | 26600 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
RED | +0.102 |
士 | +0.096 |
quished | +0.094 |
Thrones | +0.092 |
gio | +0.091 |
Neg logit contributions | |
ofer | -0.155 |
ele | -0.119 |
itness | -0.118 |
etz | -0.118 |
wards | -0.117 |
Token | or |
Token ID | 393 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
RED | +3.289 |
士 | +3.057 |
quished | +2.988 |
Thrones | +2.957 |
gio | +2.899 |
Neg logit contributions | |
ofer | -5.023 |
itness | -3.876 |
ele | -3.846 |
etz | -3.799 |
jri | -3.783 |
Token | wine |
Token ID | 8237 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
RED | +0.884 |
士 | +0.829 |
quished | +0.812 |
Thrones | +0.803 |
gio | +0.796 |
Neg logit contributions | |
ofer | -1.353 |
ele | -1.036 |
itness | -1.034 |
etz | -1.031 |
wards | -1.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
RED | +1.088 |
士 | +1.036 |
quished | +1.011 |
Thrones | +0.989 |
gio | +0.983 |
Neg logit contributions | |
ofer | -1.581 |
ele | -1.211 |
etz | -1.197 |
itness | -1.194 |
wards | -1.190 |
Token | leading |
Token ID | 3756 |
Feature activation | +8.94e+00 |
Pos logit contributions | |
RED | +1.250 |
士 | +1.174 |
quished | +1.137 |
Thrones | +1.135 |
gio | +1.117 |
Neg logit contributions | |
ofer | -1.849 |
ele | -1.415 |
etz | -1.403 |
itness | -1.397 |
wards | -1.390 |
Token | Kon |
Token ID | 17431 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
ofer | +7.315 |
ele | +5.466 |
wards | +5.338 |
etz | +5.234 |
itness | +5.195 |
Neg logit contributions | |
RED | -7.550 |
士 | -7.465 |
quished | -7.328 |
gio | -7.100 |
Thrones | -6.814 |
Token | ig |
Token ID | 328 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ofer | +7.263 |
ele | +5.768 |
etz | +5.736 |
wards | +5.689 |
itness | +5.648 |
Neg logit contributions | |
RED | -3.639 |
士 | -3.465 |
quished | -3.351 |
Thrones | -3.245 |
gio | -3.184 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
RED | +2.170 |
士 | +2.094 |
quished | +2.031 |
Thrones | +2.019 |
gio | +2.017 |
Neg logit contributions | |
ofer | -1.812 |
ele | -1.256 |
etz | -1.255 |
itness | -1.232 |
wards | -1.229 |
Token | believe |
Token ID | 1975 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ofer | +1.319 |
ele | +1.010 |
etz | +1.005 |
wards | +0.991 |
itness | +0.990 |
Neg logit contributions | |
RED | -0.919 |
士 | -0.879 |
quished | -0.851 |
Thrones | -0.838 |
gio | -0.835 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
RED | +1.840 |
士 | +1.765 |
quished | +1.725 |
Thrones | +1.702 |
gio | +1.682 |
Neg logit contributions | |
ofer | -2.039 |
ele | -1.491 |
etz | -1.488 |
itness | -1.473 |
wards | -1.457 |
Token | linking |
Token ID | 17795 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
RED | +0.160 |
士 | +0.151 |
quished | +0.147 |
Thrones | +0.146 |
gio | +0.143 |
Neg logit contributions | |
ofer | -0.217 |
ele | -0.165 |
etz | -0.164 |
wards | -0.162 |
itness | -0.162 |
Token | more |
Token ID | 517 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
ofer | +5.098 |
ele | +3.931 |
wards | +3.866 |
etz | +3.856 |
itness | +3.836 |
Neg logit contributions | |
RED | -3.610 |
士 | -3.518 |
quished | -3.445 |
gio | -3.330 |
Thrones | -3.294 |
Token | than |
Token ID | 621 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
ofer | +3.852 |
ele | +2.965 |
etz | +2.934 |
wards | +2.917 |
itness | +2.900 |
Neg logit contributions | |
RED | -2.628 |
士 | -2.524 |
quished | -2.459 |
Thrones | -2.390 |
gio | -2.387 |
Token | 340 |
Token ID | 28560 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
ofer | +4.818 |
ele | +3.606 |
etz | +3.552 |
wards | +3.538 |
itness | +3.494 |
Neg logit contributions | |
RED | -4.166 |
士 | -4.042 |
quished | -3.950 |
gio | -3.834 |
Thrones | -3.828 |
Token | public |
Token ID | 1171 |
Feature activation | +6.72e+00 |
Pos logit contributions | |
ofer | +3.767 |
ele | +2.878 |
etz | +2.849 |
wards | +2.832 |
itness | +2.821 |
Neg logit contributions | |
RED | -2.703 |
士 | -2.602 |
quished | -2.537 |
Thrones | -2.474 |
gio | -2.467 |
Token | stair |
Token ID | 18761 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
ofer | +6.579 |
ele | +5.017 |
wards | +4.965 |
etz | +4.949 |
itness | +4.924 |
Neg logit contributions | |
RED | -4.873 |
士 | -4.774 |
quished | -4.616 |
gio | -4.531 |
Thrones | -4.503 |
Token | cases |
Token ID | 33964 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ofer | +7.092 |
ele | +5.256 |
wards | +5.191 |
itness | +5.080 |
etz | +5.063 |
Neg logit contributions | |
RED | -7.034 |
士 | -6.748 |
quished | -6.682 |
Thrones | -6.517 |
gio | -6.502 |
Token | over |
Token ID | 625 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
ofer | +2.515 |
ele | +1.888 |
etz | +1.868 |
wards | +1.852 |
itness | +1.843 |
Neg logit contributions | |
RED | -2.068 |
士 | -1.992 |
quished | -1.944 |
Thrones | -1.899 |
gio | -1.894 |
Token | some |
Token ID | 617 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ofer | +4.911 |
ele | +3.685 |
wards | +3.636 |
etz | +3.631 |
itness | +3.573 |
Neg logit contributions | |
RED | -4.199 |
士 | -4.098 |
quished | -3.994 |
gio | -3.874 |
Thrones | -3.863 |
Token | 220 |
Token ID | 15629 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ofer | +0.501 |
etz | +0.377 |
ele | +0.376 |
itness | +0.373 |
wards | +0.367 |
Neg logit contributions | |
RED | -0.397 |
士 | -0.374 |
quished | -0.366 |
Thrones | -0.364 |
gio | -0.358 |
Token | miles |
Token ID | 4608 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ofer | +1.478 |
ele | +1.126 |
etz | +1.114 |
wards | +1.105 |
itness | +1.100 |
Neg logit contributions | |
RED | -1.087 |
士 | -1.039 |
quished | -1.012 |
Thrones | -0.989 |
gio | -0.984 |
Token | al |
Token ID | 435 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
RED | +1.180 |
士 | +1.120 |
Thrones | +1.098 |
quished | +1.089 |
gio | +1.089 |
Neg logit contributions | |
ofer | -1.774 |
itness | -1.348 |
ele | -1.342 |
etz | -1.336 |
jri | -1.318 |
Token | . |
Token ID | 13 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
ofer | +3.283 |
ele | +2.513 |
etz | +2.504 |
wards | +2.454 |
itness | +2.393 |
Neg logit contributions | |
RED | -2.604 |
士 | -2.522 |
quished | -2.458 |
Thrones | -2.387 |
gio | -2.372 |
Token | ( |
Token ID | 357 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
RED | +0.541 |
士 | +0.522 |
quished | +0.509 |
Thrones | +0.497 |
gio | +0.495 |
Neg logit contributions | |
ofer | -0.658 |
ele | -0.494 |
etz | -0.489 |
wards | -0.484 |
itness | -0.481 |
Token | 2002 |
Token ID | 16942 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ofer | +1.286 |
ele | +0.978 |
etz | +0.975 |
itness | +0.967 |
wards | +0.961 |
Neg logit contributions | |
RED | -0.926 |
士 | -0.879 |
quished | -0.850 |
gio | -0.839 |
Thrones | -0.830 |
Token | ); |
Token ID | 1776 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
RED | +1.118 |
士 | +1.079 |
quished | +1.057 |
gio | +1.038 |
Thrones | +1.036 |
Neg logit contributions | |
ofer | -1.046 |
ele | -0.745 |
etz | -0.739 |
itness | -0.730 |
wards | -0.729 |
Token | Hoff |
Token ID | 21890 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
ofer | +1.448 |
ele | +1.107 |
etz | +1.098 |
wards | +1.089 |
itness | +1.083 |
Neg logit contributions | |
RED | -1.036 |
士 | -0.994 |
quished | -0.969 |
Thrones | -0.943 |
gio | -0.941 |
Token | ert |
Token ID | 861 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ofer | +6.251 |
ele | +4.272 |
etz | +4.259 |
wards | +4.072 |
itness | +3.907 |
Neg logit contributions | |
RED | -8.208 |
士 | -8.057 |
quished | -7.932 |
Thrones | -7.628 |
gio | -7.507 |
Token | & |
Token ID | 1222 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ofer | +1.847 |
ele | +1.374 |
etz | +1.359 |
wards | +1.343 |
itness | +1.333 |
Neg logit contributions | |
RED | -1.622 |
士 | -1.562 |
quished | -1.527 |
Thrones | -1.491 |
gio | -1.481 |
Token | Cove |
Token ID | 39534 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
RED | +0.236 |
士 | +0.226 |
quished | +0.220 |
Thrones | +0.216 |
gio | +0.215 |
Neg logit contributions | |
ofer | -0.337 |
ele | -0.259 |
etz | -0.256 |
wards | -0.254 |
itness | -0.254 |
Token | y |
Token ID | 88 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ofer | +0.649 |
ele | +0.452 |
etz | +0.446 |
wards | +0.442 |
itness | +0.440 |
Neg logit contributions | |
RED | -0.779 |
士 | -0.754 |
quished | -0.740 |
Thrones | -0.726 |
gio | -0.726 |
Token | ( |
Token ID | 357 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
RED | +0.274 |
士 | +0.265 |
quished | +0.258 |
Thrones | +0.252 |
gio | +0.250 |
Neg logit contributions | |
ofer | -0.323 |
ele | -0.242 |
etz | -0.240 |
wards | -0.237 |
itness | -0.235 |
Token | Center |
Token ID | 3337 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
RED | +1.872 |
士 | +1.804 |
quished | +1.745 |
Thrones | +1.714 |
gio | +1.685 |
Neg logit contributions | |
ofer | -2.671 |
etz | -2.034 |
ele | -2.026 |
itness | -2.007 |
wards | -1.999 |
Token | and |
Token ID | 290 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
ofer | +2.903 |
ele | +2.209 |
etz | +2.185 |
wards | +2.169 |
itness | +2.154 |
Neg logit contributions | |
RED | -2.184 |
士 | -2.102 |
quished | -2.048 |
Thrones | -1.999 |
gio | -1.994 |
Token | the |
Token ID | 262 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
RED | +0.524 |
士 | +0.501 |
quished | +0.482 |
Thrones | +0.481 |
gio | +0.471 |
Neg logit contributions | |
ofer | -0.729 |
ele | -0.552 |
etz | -0.551 |
itness | -0.546 |
jri | -0.541 |
Token | North |
Token ID | 2258 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
ofer | +0.079 |
ele | +0.061 |
etz | +0.061 |
wards | +0.060 |
itness | +0.060 |
Neg logit contributions | |
RED | -0.052 |
士 | -0.050 |
quished | -0.048 |
Thrones | -0.048 |
gio | -0.047 |
Token | woods |
Token ID | 39493 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
ofer | +4.952 |
ele | +3.931 |
wards | +3.916 |
etz | +3.894 |
itness | +3.856 |
Neg logit contributions | |
RED | -2.477 |
士 | -2.356 |
quished | -2.287 |
gio | -2.206 |
Thrones | -2.178 |
Token | Ecology |
Token ID | 39978 |
Feature activation | +8.88e+00 |
Pos logit contributions | |
ofer | +5.988 |
ele | +4.655 |
etz | +4.602 |
wards | +4.600 |
itness | +4.546 |
Neg logit contributions | |
RED | -3.872 |
士 | -3.752 |
quished | -3.632 |
gio | -3.555 |
Thrones | -3.498 |
Token | Hall |
Token ID | 4789 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ofer | +8.740 |
wards | +6.646 |
ele | +6.582 |
etz | +6.502 |
itness | +6.424 |
Neg logit contributions | |
RED | -6.373 |
士 | -6.202 |
quished | -6.108 |
gio | -5.928 |
Thrones | -5.756 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ofer | +2.028 |
ele | +1.531 |
etz | +1.517 |
wards | +1.504 |
itness | +1.497 |
Neg logit contributions | |
RED | -1.590 |
士 | -1.530 |
quished | -1.493 |
Thrones | -1.457 |
gio | -1.453 |
Token | Allen |
Token ID | 9659 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
RED | +0.955 |
士 | +0.914 |
Thrones | +0.884 |
quished | +0.873 |
gio | +0.867 |
Neg logit contributions | |
ofer | -1.316 |
ele | -1.001 |
etz | -0.991 |
jri | -0.988 |
itness | -0.988 |
Token | and |
Token ID | 290 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
ofer | +0.710 |
ele | +0.545 |
etz | +0.539 |
wards | +0.535 |
itness | +0.535 |
Neg logit contributions | |
RED | -0.498 |
士 | -0.479 |
quished | -0.464 |
Thrones | -0.454 |
gio | -0.452 |
Token | his |
Token ID | 465 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
RED | +2.460 |
士 | +2.355 |
quished | +2.283 |
Thrones | +2.262 |
gio | +2.209 |
Neg logit contributions | |
ofer | -3.859 |
ele | -2.976 |
itness | -2.942 |
etz | -2.931 |
wards | -2.910 |
Token | , |
Token ID | 11 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
RED | +3.065 |
士 | +2.845 |
Thrones | +2.820 |
quished | +2.774 |
gio | +2.732 |
Neg logit contributions | |
ofer | -4.442 |
ele | -3.440 |
itness | -3.349 |
wards | -3.346 |
etz | -3.339 |
Token | in |
Token ID | 287 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
RED | +0.512 |
士 | +0.484 |
quished | +0.472 |
Thrones | +0.464 |
gio | +0.459 |
Neg logit contributions | |
ofer | -0.800 |
ele | -0.618 |
etz | -0.612 |
itness | -0.607 |
wards | -0.607 |
Token | - |
Token ID | 12 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ofer | +0.892 |
ele | +0.662 |
etz | +0.655 |
wards | +0.649 |
itness | +0.648 |
Neg logit contributions | |
RED | -0.778 |
士 | -0.750 |
quished | -0.732 |
Thrones | -0.717 |
gio | -0.714 |
Token | house |
Token ID | 4803 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ofer | +2.450 |
ele | +1.707 |
etz | +1.677 |
wards | +1.663 |
itness | +1.643 |
Neg logit contributions | |
RED | -3.005 |
士 | -2.928 |
quished | -2.876 |
Thrones | -2.817 |
gio | -2.799 |
Token | online |
Token ID | 2691 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
ofer | +2.697 |
ele | +2.062 |
etz | +2.043 |
wards | +2.028 |
itness | +2.016 |
Neg logit contributions | |
RED | -1.933 |
士 | -1.859 |
quished | -1.809 |
Thrones | -1.759 |
gio | -1.759 |
Token | fundraising |
Token ID | 18066 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
ofer | +5.894 |
ele | +4.463 |
wards | +4.421 |
etz | +4.408 |
itness | +4.358 |
Neg logit contributions | |
RED | -4.485 |
士 | -4.407 |
quished | -4.258 |
gio | -4.145 |
Thrones | -4.091 |
Token | tool |
Token ID | 2891 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
ofer | +9.204 |
ele | +6.944 |
wards | +6.804 |
etz | +6.783 |
itness | +6.545 |
Neg logit contributions | |
士 | -7.395 |
RED | -7.349 |
quished | -7.177 |
gio | -6.933 |
Thrones | -6.800 |
Token | , |
Token ID | 11 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
RED | +0.476 |
士 | +0.457 |
quished | +0.447 |
Thrones | +0.440 |
gio | +0.436 |
Neg logit contributions | |
ofer | -0.549 |
ele | -0.405 |
etz | -0.401 |
itness | -0.398 |
wards | -0.398 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ofer | +0.668 |
ele | +0.509 |
etz | +0.505 |
itness | +0.501 |
wards | +0.500 |
Neg logit contributions | |
RED | -0.475 |
士 | -0.453 |
quished | -0.441 |
Thrones | -0.433 |
gio | -0.429 |
Token | can |
Token ID | 460 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
ofer | +1.758 |
ele | +1.347 |
etz | +1.334 |
wards | +1.324 |
itness | +1.319 |
Neg logit contributions | |
RED | -1.240 |
士 | -1.190 |
quished | -1.158 |
Thrones | -1.130 |
gio | -1.126 |
Token | lean |
Token ID | 10904 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
RED | +2.049 |
士 | +1.907 |
Thrones | +1.865 |
gio | +1.840 |
quished | +1.829 |
Neg logit contributions | |
ofer | -2.974 |
ele | -2.297 |
etz | -2.276 |
wards | -2.245 |
itness | -2.243 |
Token | � |
Token ID | 447 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
RED | +0.018 |
士 | +0.017 |
quished | +0.016 |
gio | +0.016 |
Thrones | +0.016 |
Neg logit contributions | |
ofer | -0.018 |
etz | -0.013 |
ele | -0.013 |
itness | -0.013 |
wards | -0.013 |
Token | � |
Token ID | 250 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ofer | +0.917 |
etz | +0.694 |
ele | +0.693 |
wards | +0.684 |
itness | +0.682 |
Neg logit contributions | |
RED | -0.733 |
士 | -0.706 |
quished | -0.682 |
Thrones | -0.670 |
gio | -0.668 |
Token | Do |
Token ID | 5211 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
ofer | +1.747 |
ele | +1.301 |
etz | +1.294 |
wards | +1.280 |
itness | +1.278 |
Neg logit contributions | |
RED | -1.483 |
士 | -1.421 |
quished | -1.384 |
Thrones | -1.354 |
gio | -1.352 |
Token | you |
Token ID | 345 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ofer | +5.231 |
ele | +3.932 |
etz | +3.837 |
wards | +3.817 |
itness | +3.777 |
Neg logit contributions | |
RED | -4.831 |
士 | -4.664 |
quished | -4.629 |
gio | -4.465 |
Thrones | -4.458 |
Token | remember |
Token ID | 3505 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
ofer | +2.415 |
ele | +1.805 |
etz | +1.784 |
wards | +1.769 |
itness | +1.761 |
Neg logit contributions | |
RED | -2.048 |
士 | -1.975 |
quished | -1.931 |
Thrones | -1.885 |
gio | -1.879 |
Token | twelve |
Token ID | 14104 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
RED | +4.853 |
士 | +4.547 |
Thrones | +4.494 |
quished | +4.338 |
gio | +4.274 |
Neg logit contributions | |
ofer | -6.622 |
etz | -5.076 |
itness | -4.983 |
jri | -4.960 |
ele | -4.941 |
Token | years |
Token ID | 812 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
RED | +0.317 |
士 | +0.304 |
quished | +0.295 |
Thrones | +0.291 |
gio | +0.287 |
Neg logit contributions | |
ofer | -0.471 |
etz | -0.361 |
ele | -0.361 |
wards | -0.355 |
itness | -0.355 |
Token | ago |
Token ID | 2084 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
RED | +2.104 |
士 | +1.930 |
quished | +1.882 |
Thrones | +1.840 |
gio | +1.776 |
Neg logit contributions | |
ofer | -5.343 |
ele | -4.324 |
etz | -4.314 |
itness | -4.267 |
wards | -4.220 |
Token | in |
Token ID | 287 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ofer | +3.424 |
ele | +2.588 |
wards | +2.562 |
etz | +2.545 |
itness | +2.513 |
Neg logit contributions | |
RED | -2.739 |
士 | -2.629 |
quished | -2.585 |
gio | -2.529 |
Thrones | -2.504 |
Token | the |
Token ID | 262 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
ofer | +1.904 |
ele | +1.446 |
etz | +1.433 |
wards | +1.421 |
itness | +1.415 |
Neg logit contributions | |
RED | -1.431 |
士 | -1.374 |
quished | -1.340 |
Thrones | -1.308 |
gio | -1.303 |
Token | castle |
Token ID | 16669 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ofer | +0.075 |
ele | +0.058 |
etz | +0.057 |
wards | +0.057 |
itness | +0.057 |
Neg logit contributions | |
RED | -0.047 |
士 | -0.045 |
quished | -0.044 |
Thrones | -0.043 |
gio | -0.043 |
Token | ors |
Token ID | 669 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ofer | +2.189 |
ele | +1.287 |
etz | +1.260 |
wards | +1.234 |
itness | +1.178 |
Neg logit contributions | |
RED | -4.551 |
士 | -4.489 |
quished | -4.406 |
gio | -4.329 |
Thrones | -4.320 |
Token | where |
Token ID | 810 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
RED | +2.384 |
士 | +2.235 |
quished | +2.170 |
Thrones | +2.168 |
gio | +2.160 |
Neg logit contributions | |
ofer | -3.241 |
ele | -2.487 |
etz | -2.451 |
itness | -2.430 |
wards | -2.423 |
Token | you |
Token ID | 345 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
RED | +0.098 |
士 | +0.093 |
quished | +0.091 |
Thrones | +0.090 |
gio | +0.090 |
Neg logit contributions | |
ofer | -0.116 |
ele | -0.087 |
etz | -0.086 |
itness | -0.085 |
wards | -0.084 |
Token | still |
Token ID | 991 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ofer | +0.237 |
ele | +0.184 |
etz | +0.183 |
wards | +0.181 |
itness | +0.181 |
Neg logit contributions | |
RED | -0.145 |
士 | -0.138 |
quished | -0.133 |
Thrones | -0.131 |
gio | -0.131 |
Token | can |
Token ID | 460 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
RED | +0.362 |
士 | +0.342 |
Thrones | +0.328 |
quished | +0.328 |
gio | +0.327 |
Neg logit contributions | |
ofer | -0.571 |
ele | -0.440 |
etz | -0.439 |
itness | -0.433 |
wards | -0.431 |
Token | )" |
Token ID | 16725 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
RED | +0.785 |
士 | +0.737 |
quished | +0.718 |
gio | +0.714 |
Thrones | +0.711 |
Neg logit contributions | |
ofer | -1.127 |
ele | -0.865 |
etz | -0.858 |
itness | -0.845 |
wards | -0.842 |
Token | high |
Token ID | 8929 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ofer | +3.604 |
ele | +2.570 |
etz | +2.526 |
wards | +2.515 |
itness | +2.474 |
Neg logit contributions | |
RED | -3.928 |
士 | -3.851 |
quished | -3.778 |
Thrones | -3.707 |
gio | -3.655 |
Token | resolution |
Token ID | 6323 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ofer | +1.838 |
ele | +1.411 |
etz | +1.397 |
wards | +1.389 |
itness | +1.375 |
Neg logit contributions | |
RED | -1.316 |
士 | -1.283 |
quished | -1.241 |
Thrones | -1.212 |
gio | -1.203 |
Token | no |
Token ID | 645 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ofer | +0.412 |
ele | +0.311 |
etz | +0.308 |
wards | +0.305 |
itness | +0.304 |
Neg logit contributions | |
RED | -0.324 |
士 | -0.311 |
quished | -0.304 |
Thrones | -0.296 |
gio | -0.296 |
Token | j |
Token ID | 474 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
ofer | +0.564 |
ele | +0.459 |
etz | +0.455 |
wards | +0.452 |
itness | +0.452 |
Neg logit contributions | |
RED | -0.207 |
士 | -0.194 |
quished | -0.186 |
Thrones | -0.179 |
gio | -0.178 |
Token | agg |
Token ID | 9460 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ofer | +5.568 |
etz | +3.840 |
ele | +3.831 |
wards | +3.791 |
itness | +3.711 |
Neg logit contributions | |
RED | -6.882 |
士 | -6.652 |
quished | -6.524 |
Thrones | -6.500 |
Enix | -6.324 |
Token | Foundation |
Token ID | 5693 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
ofer | +6.062 |
ele | +4.618 |
wards | +4.591 |
etz | +4.570 |
itness | +4.480 |
Neg logit contributions | |
RED | -4.631 |
士 | -4.475 |
quished | -4.364 |
gio | -4.183 |
Thrones | -4.159 |
Token | : |
Token ID | 25 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ofer | +3.503 |
ele | +2.637 |
etz | +2.631 |
wards | +2.616 |
itness | +2.545 |
Neg logit contributions | |
RED | -2.985 |
士 | -2.891 |
quished | -2.832 |
Thrones | -2.787 |
gio | -2.742 |
Token | " |
Token ID | 366 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
RED | +0.325 |
士 | +0.315 |
quished | +0.308 |
Thrones | +0.302 |
gio | +0.302 |
Neg logit contributions | |
ofer | -0.296 |
ele | -0.211 |
etz | -0.208 |
wards | -0.206 |
itness | -0.205 |
Token | R |
Token ID | 49 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
ofer | +2.529 |
ele | +1.936 |
etz | +1.912 |
wards | +1.898 |
itness | +1.877 |
Neg logit contributions | |
RED | -1.880 |
士 | -1.831 |
quished | -1.780 |
Thrones | -1.753 |
gio | -1.735 |
Token | oc |
Token ID | 420 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
ofer | +0.773 |
ele | +0.536 |
etz | +0.529 |
wards | +0.522 |
itness | +0.520 |
Neg logit contributions | |
RED | -0.964 |
士 | -0.934 |
quished | -0.916 |
gio | -0.901 |
Thrones | -0.895 |
Token | kefeller |
Token ID | 31424 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
RED | +2.257 |
士 | +2.119 |
quished | +2.103 |
gio | +2.029 |
Thrones | +1.988 |
Neg logit contributions | |
ofer | -4.504 |
ele | -3.631 |
etz | -3.550 |
itness | -3.527 |
wards | -3.519 |
Token | Family |
Token ID | 7884 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ofer | +4.242 |
ele | +3.302 |
etz | +3.298 |
wards | +3.297 |
itness | +3.215 |
Neg logit contributions | |
RED | -2.574 |
士 | -2.430 |
quished | -2.332 |
gio | -2.272 |
Thrones | -2.270 |
Token | Fund |
Token ID | 7557 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ofer | +0.243 |
ele | +0.183 |
etz | +0.181 |
wards | +0.181 |
itness | +0.178 |
Neg logit contributions | |
RED | -0.196 |
士 | -0.189 |
quished | -0.184 |
Thrones | -0.179 |
gio | -0.178 |
Token | , |
Token ID | 11 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
ofer | +0.253 |
ele | +0.191 |
etz | +0.190 |
wards | +0.189 |
itness | +0.186 |
Neg logit contributions | |
RED | -0.202 |
士 | -0.195 |
quished | -0.190 |
Thrones | -0.186 |
gio | -0.185 |
Token | Inc |
Token ID | 3457 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
RED | +1.549 |
士 | +1.437 |
quished | +1.380 |
Thrones | +1.294 |
gio | +1.292 |
Neg logit contributions | |
ofer | -5.260 |
ele | -4.317 |
etz | -4.278 |
wards | -4.256 |
itness | -4.255 |
Token | .: |
Token ID | 11207 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ofer | +1.570 |
ele | +1.204 |
etz | +1.201 |
wards | +1.191 |
itness | +1.174 |
Neg logit contributions | |
RED | -1.146 |
士 | -1.111 |
quished | -1.072 |
Thrones | -1.060 |
gio | -1.054 |
Token | Perhaps |
Token ID | 13710 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ofer | +4.329 |
ele | +3.182 |
etz | +3.117 |
wards | +3.099 |
itness | +3.074 |
Neg logit contributions | |
RED | -4.175 |
士 | -4.083 |
quished | -3.999 |
Thrones | -3.950 |
gio | -3.899 |
Token | with |
Token ID | 351 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ofer | +2.569 |
ele | +1.938 |
etz | +1.917 |
wards | +1.903 |
itness | +1.889 |
Neg logit contributions | |
RED | -2.056 |
士 | -1.979 |
quished | -1.932 |
gio | -1.882 |
Thrones | -1.881 |
Token | some |
Token ID | 617 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
RED | +1.104 |
士 | +1.057 |
quished | +1.030 |
Thrones | +1.018 |
gio | +1.008 |
Neg logit contributions | |
ofer | -1.427 |
ele | -1.079 |
etz | -1.072 |
itness | -1.060 |
wards | -1.055 |
Token | apolog |
Token ID | 8453 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
RED | +1.019 |
士 | +0.972 |
quished | +0.944 |
Thrones | +0.939 |
gio | +0.924 |
Neg logit contributions | |
ofer | -1.353 |
ele | -1.026 |
etz | -1.023 |
itness | -1.007 |
wards | -1.003 |
Token | etic |
Token ID | 5139 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ofer | +2.055 |
ele | +1.367 |
etz | +1.355 |
itness | +1.312 |
wards | +1.310 |
Neg logit contributions | |
RED | -3.028 |
士 | -2.956 |
quished | -2.897 |
Thrones | -2.859 |
gio | -2.830 |
Token | intent |
Token ID | 6824 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
RED | +0.429 |
士 | +0.408 |
quished | +0.396 |
Thrones | +0.393 |
gio | +0.389 |
Neg logit contributions | |
ofer | -0.582 |
ele | -0.442 |
etz | -0.439 |
itness | -0.434 |
wards | -0.433 |
Token | , |
Token ID | 11 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
RED | +0.129 |
士 | +0.124 |
quished | +0.120 |
Thrones | +0.118 |
gio | +0.117 |
Neg logit contributions | |
ofer | -0.168 |
ele | -0.127 |
etz | -0.126 |
itness | -0.125 |
wards | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ofer | +0.835 |
ele | +0.631 |
etz | +0.625 |
wards | +0.620 |
itness | +0.618 |
Neg logit contributions | |
RED | -0.648 |
士 | -0.622 |
quished | -0.606 |
Thrones | -0.594 |
gio | -0.590 |
Token | late |
Token ID | 2739 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ofer | +1.147 |
ele | +0.884 |
etz | +0.877 |
wards | +0.870 |
itness | +0.866 |
Neg logit contributions | |
RED | -0.762 |
士 | -0.729 |
quished | -0.709 |
Thrones | -0.693 |
gio | -0.689 |
Token | English |
Token ID | 3594 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ofer | +2.259 |
ele | +1.739 |
etz | +1.724 |
wards | +1.711 |
itness | +1.701 |
Neg logit contributions | |
RED | -1.531 |
士 | -1.466 |
quished | -1.428 |
Thrones | -1.386 |
gio | -1.386 |
Token | scholar |
Token ID | 15606 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
ofer | +3.143 |
ele | +2.362 |
etz | +2.344 |
wards | +2.322 |
itness | +2.306 |
Neg logit contributions | |
RED | -2.499 |
士 | -2.399 |
quished | -2.339 |
gio | -2.286 |
Thrones | -2.275 |
Token | ir |
Token ID | 343 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
ofer | +2.648 |
ele | +1.686 |
etz | +1.658 |
wards | +1.637 |
itness | +1.622 |
Neg logit contributions | |
RED | -4.341 |
士 | -4.217 |
quished | -4.146 |
Thrones | -4.079 |
gio | -4.074 |
Token | istan |
Token ID | 4103 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
ofer | +3.986 |
ele | +2.830 |
wards | +2.804 |
etz | +2.772 |
itness | +2.718 |
Neg logit contributions | |
RED | -4.624 |
士 | -4.409 |
quished | -4.344 |
Thrones | -4.274 |
gio | -4.211 |
Token | air |
Token ID | 1633 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ofer | +5.759 |
ele | +4.378 |
wards | +4.305 |
etz | +4.280 |
itness | +4.244 |
Neg logit contributions | |
RED | -4.590 |
士 | -4.405 |
quished | -4.350 |
Thrones | -4.204 |
gio | -4.177 |
Token | raids |
Token ID | 20371 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ofer | +2.411 |
ele | +1.836 |
etz | +1.811 |
wards | +1.807 |
itness | +1.791 |
Neg logit contributions | |
RED | -1.829 |
士 | -1.762 |
quished | -1.710 |
Thrones | -1.671 |
gio | -1.665 |
Token | . |
Token ID | 13 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
ofer | +2.187 |
ele | +1.688 |
etz | +1.670 |
wards | +1.658 |
itness | +1.630 |
Neg logit contributions | |
RED | -1.627 |
士 | -1.577 |
quished | -1.527 |
Thrones | -1.492 |
gio | -1.486 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
RED | +0.643 |
士 | +0.620 |
quished | +0.605 |
Thrones | +0.590 |
gio | +0.589 |
Neg logit contributions | |
ofer | -0.744 |
ele | -0.555 |
etz | -0.548 |
wards | -0.544 |
itness | -0.541 |
Token |
|
Token ID | 198 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
RED | +0.356 |
gio | +0.321 |
士 | +0.321 |
Thrones | +0.315 |
quished | +0.308 |
Neg logit contributions | |
ofer | -0.499 |
challeng | -0.392 |
jri | -0.384 |
itness | -0.380 |
etz | -0.378 |
Token | K |
Token ID | 42 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ofer | +0.628 |
ele | +0.469 |
etz | +0.467 |
itness | +0.462 |
wards | +0.460 |
Neg logit contributions | |
RED | -0.513 |
士 | -0.484 |
quished | -0.474 |
gio | -0.464 |
Thrones | -0.460 |
Token | hy |
Token ID | 12114 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
RED | +0.246 |
士 | +0.236 |
quished | +0.231 |
gio | +0.226 |
Thrones | +0.225 |
Neg logit contributions | |
ofer | -0.250 |
ele | -0.182 |
etz | -0.181 |
wards | -0.180 |
itness | -0.178 |
Token | ber |
Token ID | 527 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
ofer | +1.972 |
ele | +1.328 |
etz | +1.311 |
wards | +1.293 |
itness | +1.280 |
Neg logit contributions | |
RED | -2.729 |
士 | -2.653 |
quished | -2.601 |
Thrones | -2.559 |
gio | -2.550 |
Token | raid |
Token ID | 9513 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
RED | +0.651 |
士 | +0.626 |
quished | +0.608 |
Thrones | +0.594 |
gio | +0.589 |
Neg logit contributions | |
ofer | -0.958 |
ele | -0.734 |
etz | -0.728 |
itness | -0.718 |
wards | -0.716 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
RED | +3.637 |
quished | +3.381 |
士 | +3.373 |
Thrones | +3.328 |
gio | +3.232 |
Neg logit contributions | |
ofer | -4.447 |
etz | -3.357 |
ele | -3.330 |
itness | -3.264 |
wards | -3.216 |
Token |
|
Token ID | 198 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
RED | +0.979 |
士 | +0.931 |
quished | +0.912 |
Thrones | +0.903 |
gio | +0.892 |
Neg logit contributions | |
ofer | -1.228 |
ele | -0.925 |
etz | -0.920 |
itness | -0.907 |
wards | -0.905 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
RED | +0.133 |
士 | +0.122 |
gio | +0.120 |
Thrones | +0.118 |
quished | +0.117 |
Neg logit contributions | |
ofer | -0.181 |
challeng | -0.138 |
jri | -0.137 |
etz | -0.137 |
itness | -0.137 |
Token | Happy |
Token ID | 25082 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
RED | +0.082 |
士 | +0.078 |
quished | +0.076 |
Thrones | +0.074 |
gio | +0.074 |
Neg logit contributions | |
ofer | -0.119 |
ele | -0.091 |
etz | -0.090 |
wards | -0.090 |
itness | -0.089 |
Token | that |
Token ID | 326 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
RED | +3.568 |
士 | +3.387 |
quished | +3.361 |
Thrones | +3.329 |
gio | +3.227 |
Neg logit contributions | |
ofer | -4.436 |
ele | -3.322 |
etz | -3.314 |
itness | -3.224 |
wards | -3.184 |
Token | I |
Token ID | 314 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
RED | +4.011 |
士 | +3.753 |
quished | +3.729 |
Thrones | +3.694 |
gio | +3.626 |
Neg logit contributions | |
ofer | -5.184 |
etz | -3.930 |
ele | -3.901 |
itness | -3.826 |
wards | -3.821 |
Token | made |
Token ID | 925 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
RED | +3.004 |
士 | +2.804 |
quished | +2.717 |
gio | +2.688 |
Thrones | +2.650 |
Neg logit contributions | |
ofer | -4.362 |
ele | -3.356 |
wards | -3.337 |
etz | -3.327 |
itness | -3.260 |
Token | it |
Token ID | 340 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ofer | +0.137 |
ele | +0.105 |
etz | +0.104 |
wards | +0.103 |
itness | +0.103 |
Neg logit contributions | |
RED | -0.098 |
士 | -0.093 |
quished | -0.091 |
Thrones | -0.089 |
gio | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ofer | +1.061 |
ele | +0.783 |
etz | +0.778 |
wards | +0.769 |
itness | +0.767 |
Neg logit contributions | |
RED | -0.954 |
士 | -0.915 |
quished | -0.896 |
Thrones | -0.879 |
gio | -0.872 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
RED | +1.219 |
士 | +1.151 |
Thrones | +1.126 |
quished | +1.120 |
gio | +1.107 |
Neg logit contributions | |
ofer | -1.654 |
ele | -1.257 |
etz | -1.252 |
itness | -1.236 |
jri | -1.226 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ofer | +0.215 |
etz | +0.162 |
jri | +0.162 |
itness | +0.162 |
ele | +0.161 |
Neg logit contributions | |
RED | -0.161 |
士 | -0.148 |
gio | -0.145 |
Thrones | -0.143 |
quished | -0.142 |
Token | for |
Token ID | 329 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ofer | +0.418 |
ele | +0.317 |
etz | +0.315 |
itness | +0.312 |
wards | +0.311 |
Neg logit contributions | |
RED | -0.309 |
士 | -0.295 |
quished | -0.288 |
Thrones | -0.283 |
gio | -0.281 |
Token | single |
Token ID | 2060 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
ofer | +1.948 |
ele | +1.479 |
etz | +1.469 |
itness | +1.451 |
wards | +1.447 |
Neg logit contributions | |
RED | -1.456 |
士 | -1.394 |
quished | -1.356 |
Thrones | -1.335 |
gio | -1.324 |
Token | or |
Token ID | 393 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
RED | +5.286 |
士 | +4.975 |
Thrones | +4.879 |
quished | +4.803 |
gio | +4.626 |
Neg logit contributions | |
ofer | -8.071 |
etz | -6.197 |
itness | -6.143 |
ele | -6.094 |
jri | -6.094 |
Token | multi |
Token ID | 5021 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ofer | +1.948 |
ele | +1.501 |
etz | +1.486 |
wards | +1.478 |
itness | +1.467 |
Neg logit contributions | |
RED | -1.320 |
士 | -1.266 |
quished | -1.232 |
Thrones | -1.198 |
gio | -1.193 |
Token | - |
Token ID | 12 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
RED | +3.121 |
士 | +2.979 |
quished | +2.912 |
Thrones | +2.857 |
gio | +2.816 |
Neg logit contributions | |
ofer | -4.074 |
etz | -3.075 |
ele | -3.058 |
itness | -3.021 |
wards | -3.014 |
Token | line |
Token ID | 1370 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
RED | +1.724 |
士 | +1.668 |
quished | +1.636 |
Thrones | +1.605 |
gio | +1.604 |
Neg logit contributions | |
ofer | -1.348 |
ele | -0.922 |
etz | -0.916 |
wards | -0.902 |
itness | -0.900 |
Token | blocks |
Token ID | 7021 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
RED | +0.934 |
士 | +0.883 |
quished | +0.859 |
Thrones | +0.846 |
gio | +0.838 |
Neg logit contributions | |
ofer | -1.462 |
etz | -1.124 |
ele | -1.123 |
itness | -1.115 |
wards | -1.101 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
RED | +1.351 |
士 | +1.294 |
quished | +1.248 |
Thrones | +1.247 |
gio | +1.229 |
Neg logit contributions | |
ofer | -1.807 |
ele | -1.359 |
itness | -1.355 |
etz | -1.347 |
wards | -1.329 |
Token | there |
Token ID | 612 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
ofer | +1.482 |
ele | +1.114 |
etz | +1.105 |
itness | +1.095 |
wards | +1.092 |
Neg logit contributions | |
RED | -1.170 |
士 | -1.122 |
quished | -1.092 |
Thrones | -1.075 |
gio | -1.068 |
Token | is |
Token ID | 318 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
ofer | +8.656 |
ele | +6.689 |
etz | +6.676 |
wards | +6.517 |
itness | +6.347 |
Neg logit contributions | |
RED | -5.844 |
士 | -5.620 |
quished | -5.588 |
Thrones | -5.314 |
gio | -5.209 |
Token | one |
Token ID | 530 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ofer | +8.254 |
ele | +6.509 |
wards | +6.479 |
etz | +6.449 |
itness | +6.296 |
Neg logit contributions | |
RED | -4.332 |
士 | -4.211 |
quished | -4.101 |
gio | -3.849 |
Thrones | -3.826 |
Token | certainly |
Token ID | 3729 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
ofer | +2.137 |
ele | +1.642 |
etz | +1.627 |
wards | +1.614 |
itness | +1.607 |
Neg logit contributions | |
RED | -1.474 |
士 | -1.413 |
quished | -1.376 |
Thrones | -1.340 |
gio | -1.336 |
Token | the |
Token ID | 262 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ofer | +5.195 |
ele | +3.900 |
wards | +3.880 |
etz | +3.855 |
itness | +3.766 |
Neg logit contributions | |
RED | -4.024 |
士 | -3.918 |
quished | -3.821 |
gio | -3.688 |
Thrones | -3.618 |
Token | Obama |
Token ID | 2486 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
ofer | +2.407 |
ele | +1.862 |
etz | +1.845 |
wards | +1.834 |
itness | +1.823 |
Neg logit contributions | |
RED | -1.556 |
士 | -1.493 |
quished | -1.453 |
gio | -1.407 |
Thrones | -1.406 |
Token | administration |
Token ID | 3662 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ofer | +5.881 |
ele | +4.300 |
etz | +4.227 |
wards | +4.200 |
itness | +4.086 |
Neg logit contributions | |
RED | -5.972 |
士 | -5.813 |
quished | -5.719 |
gio | -5.548 |
Thrones | -5.459 |
Token | pulled |
Token ID | 5954 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
ofer | +2.610 |
ele | +2.010 |
etz | +1.987 |
wards | +1.972 |
itness | +1.952 |
Neg logit contributions | |
RED | -1.810 |
士 | -1.749 |
quished | -1.705 |
gio | -1.646 |
Thrones | -1.645 |
Token | the |
Token ID | 262 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
RED | +2.981 |
士 | +2.810 |
Thrones | +2.752 |
quished | +2.748 |
gio | +2.659 |
Neg logit contributions | |
ofer | -4.323 |
ele | -3.333 |
etz | -3.308 |
itness | -3.308 |
wards | -3.232 |
Token | rug |
Token ID | 14477 |
Feature activation | -9.69e+00 |
Pos logit contributions | |
RED | +1.181 |
士 | +1.118 |
Thrones | +1.082 |
quished | +1.081 |
gio | +1.051 |
Neg logit contributions | |
ofer | -2.121 |
ele | -1.669 |
etz | -1.646 |
itness | -1.644 |
wards | -1.626 |
Token | out |
Token ID | 503 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
RED | +5.948 |
士 | +5.393 |
Enix | +5.281 |
Thrones | +5.265 |
quished | +5.262 |
Neg logit contributions | |
ofer | -10.068 |
itness | -7.960 |
ele | -7.854 |
jri | -7.709 |
etz | -7.682 |
Token | from |
Token ID | 422 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ofer | +2.699 |
wards | +1.913 |
etz | +1.873 |
ele | +1.851 |
itness | +1.798 |
Neg logit contributions | |
RED | -3.169 |
士 | -3.129 |
quished | -3.032 |
gio | -3.025 |
Thrones | -3.008 |
Token | under |
Token ID | 739 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ofer | +0.021 |
ele | +0.016 |
etz | +0.016 |
itness | +0.016 |
wards | +0.016 |
Neg logit contributions | |
RED | -0.014 |
士 | -0.013 |
quished | -0.013 |
Thrones | -0.012 |
gio | -0.012 |
Token | them |
Token ID | 606 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
RED | +1.413 |
士 | +1.338 |
Thrones | +1.310 |
quished | +1.293 |
gio | +1.262 |
Neg logit contributions | |
ofer | -2.213 |
ele | -1.732 |
etz | -1.710 |
itness | -1.695 |
wards | -1.673 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ofer | +0.979 |
ele | +0.747 |
etz | +0.740 |
wards | +0.733 |
itness | +0.731 |
Neg logit contributions | |
RED | -0.716 |
士 | -0.684 |
quished | -0.665 |
Thrones | -0.652 |
gio | -0.650 |
Token | for |
Token ID | 329 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
ofer | +2.219 |
ele | +1.697 |
etz | +1.682 |
wards | +1.670 |
itness | +1.660 |
Neg logit contributions | |
RED | -1.588 |
士 | -1.527 |
quished | -1.488 |
Thrones | -1.446 |
gio | -1.443 |
Token | their |
Token ID | 511 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
ofer | +0.585 |
ele | +0.446 |
etz | +0.441 |
wards | +0.437 |
itness | +0.436 |
Neg logit contributions | |
RED | -0.433 |
士 | -0.415 |
quished | -0.403 |
Thrones | -0.395 |
gio | -0.394 |
Token | hot |
Token ID | 3024 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
RED | +0.317 |
士 | +0.303 |
quished | +0.292 |
Thrones | +0.289 |
gio | +0.287 |
Neg logit contributions | |
ofer | -0.460 |
ele | -0.353 |
etz | -0.351 |
wards | -0.346 |
itness | -0.345 |
Token | shot |
Token ID | 9442 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
RED | +2.918 |
士 | +2.727 |
quished | +2.640 |
Thrones | +2.612 |
gio | +2.596 |
Neg logit contributions | |
ofer | -4.681 |
ele | -3.639 |
etz | -3.574 |
itness | -3.548 |
wards | -3.542 |
Token | rivals |
Token ID | 14987 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ofer | +0.122 |
ele | +0.093 |
etz | +0.093 |
wards | +0.092 |
itness | +0.092 |
Neg logit contributions | |
RED | -0.085 |
士 | -0.081 |
quished | -0.079 |
Thrones | -0.077 |
gio | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
RED | +1.418 |
士 | +1.351 |
quished | +1.312 |
Thrones | +1.294 |
gio | +1.286 |
Neg logit contributions | |
ofer | -2.006 |
ele | -1.533 |
etz | -1.521 |
wards | -1.508 |
itness | -1.508 |
Token |
|
Token ID | 198 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
RED | +1.325 |
士 | +1.262 |
quished | +1.222 |
Thrones | +1.220 |
gio | +1.219 |
Neg logit contributions | |
ofer | -1.688 |
ele | -1.278 |
etz | -1.264 |
itness | -1.253 |
wards | -1.249 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
RED | +0.533 |
士 | +0.490 |
gio | +0.482 |
Thrones | +0.474 |
quished | +0.468 |
Neg logit contributions | |
ofer | -0.736 |
challeng | -0.562 |
itness | -0.559 |
jri | -0.559 |
etz | -0.559 |
Token | � |
Token ID | 447 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
RED | +0.236 |
士 | +0.224 |
quished | +0.219 |
gio | +0.216 |
Thrones | +0.213 |
Neg logit contributions | |
ofer | -0.244 |
ele | -0.177 |
etz | -0.177 |
itness | -0.175 |
wards | -0.175 |
Token | � |
Token ID | 250 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
RED | +1.526 |
士 | +1.462 |
quished | +1.410 |
Thrones | +1.386 |
gio | +1.385 |
Neg logit contributions | |
ofer | -1.995 |
etz | -1.535 |
ele | -1.527 |
wards | -1.512 |
itness | -1.504 |
Token | older |
Token ID | 4697 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ofer | +3.315 |
ele | +2.491 |
etz | +2.462 |
wards | +2.457 |
itness | +2.429 |
Neg logit contributions | |
RED | -2.716 |
士 | -2.638 |
quished | -2.582 |
gio | -2.503 |
Thrones | -2.489 |
Token | children |
Token ID | 1751 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
ofer | +1.731 |
ele | +1.276 |
etz | +1.271 |
itness | +1.254 |
wards | +1.248 |
Neg logit contributions | |
RED | -1.539 |
士 | -1.480 |
quished | -1.439 |
Thrones | -1.428 |
gio | -1.410 |
Token | how |
Token ID | 703 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ofer | +4.844 |
ele | +3.589 |
wards | +3.545 |
etz | +3.501 |
itness | +3.444 |
Neg logit contributions | |
RED | -4.779 |
士 | -4.711 |
quished | -4.655 |
gio | -4.463 |
Thrones | -4.406 |
Token | to |
Token ID | 284 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ofer | +3.181 |
wards | +2.103 |
ele | +2.088 |
etz | +2.056 |
itness | +1.996 |
Neg logit contributions | |
RED | -5.030 |
quished | -4.982 |
士 | -4.968 |
gio | -4.811 |
Thrones | -4.726 |
Token | sew |
Token ID | 34249 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ofer | +0.255 |
ele | +0.198 |
etz | +0.197 |
itness | +0.195 |
wards | +0.195 |
Neg logit contributions | |
RED | -0.160 |
士 | -0.151 |
Thrones | -0.145 |
quished | -0.144 |
gio | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ofer | +2.162 |
ele | +1.661 |
etz | +1.641 |
wards | +1.632 |
itness | +1.622 |
Neg logit contributions | |
RED | -1.538 |
士 | -1.484 |
quished | -1.446 |
Thrones | -1.403 |
gio | -1.402 |
Token |
|
Token ID | 198 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
RED | +1.429 |
士 | +1.351 |
Thrones | +1.310 |
quished | +1.308 |
gio | +1.285 |
Neg logit contributions | |
ofer | -1.851 |
ele | -1.399 |
etz | -1.397 |
wards | -1.383 |
jri | -1.376 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
RED | +2.077 |
gio | +1.850 |
士 | +1.844 |
Thrones | +1.808 |
quished | +1.735 |
Neg logit contributions | |
ofer | -3.175 |
challeng | -2.659 |
jri | -2.519 |
itness | -2.463 |
etz | -2.456 |
Token | Thread |
Token ID | 16818 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
RED | +1.716 |
士 | +1.580 |
quished | +1.534 |
gio | +1.516 |
Thrones | +1.498 |
Neg logit contributions | |
ofer | -1.725 |
etz | -1.252 |
itness | -1.237 |
jri | -1.229 |
wards | -1.228 |
Token | a |
Token ID | 257 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
RED | +2.591 |
士 | +2.456 |
quished | +2.401 |
Thrones | +2.391 |
gio | +2.357 |
Neg logit contributions | |
ofer | -3.152 |
ele | -2.345 |
etz | -2.343 |
itness | -2.321 |
wards | -2.299 |
Token | card |
Token ID | 2657 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
ofer | +1.104 |
ele | +0.856 |
etz | +0.849 |
wards | +0.842 |
itness | +0.839 |
Neg logit contributions | |
RED | -0.695 |
士 | -0.661 |
quished | -0.644 |
Thrones | -0.629 |
gio | -0.625 |
Token | . |
Token ID | 13 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ofer | +2.124 |
ele | +1.575 |
etz | +1.556 |
wards | +1.555 |
itness | +1.538 |
Neg logit contributions | |
RED | -1.893 |
士 | -1.839 |
quished | -1.793 |
gio | -1.750 |
Thrones | -1.749 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
RED | +0.257 |
士 | +0.247 |
quished | +0.240 |
Thrones | +0.237 |
gio | +0.235 |
Neg logit contributions | |
ofer | -0.288 |
ele | -0.212 |
etz | -0.211 |
wards | -0.208 |
itness | -0.208 |
Token | eyes |
Token ID | 2951 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
RED | +1.130 |
士 | +1.062 |
Thrones | +1.017 |
quished | +1.015 |
gio | +0.993 |
Neg logit contributions | |
ofer | -1.958 |
ele | -1.530 |
etz | -1.527 |
itness | -1.503 |
wards | -1.501 |
Token | were |
Token ID | 547 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
RED | +1.740 |
士 | +1.621 |
quished | +1.592 |
Thrones | +1.581 |
gio | +1.554 |
Neg logit contributions | |
ofer | -3.133 |
etz | -2.416 |
ele | -2.409 |
jri | -2.381 |
wards | -2.378 |
Token | still |
Token ID | 991 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
RED | +1.922 |
士 | +1.743 |
Thrones | +1.731 |
quished | +1.729 |
gio | +1.678 |
Neg logit contributions | |
ofer | -3.285 |
ele | -2.537 |
etz | -2.534 |
itness | -2.501 |
jri | -2.484 |
Token | red |
Token ID | 2266 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
RED | +0.963 |
士 | +0.892 |
quished | +0.878 |
Thrones | +0.861 |
gio | +0.849 |
Neg logit contributions | |
ofer | -1.633 |
ele | -1.270 |
etz | -1.262 |
itness | -1.250 |
wards | -1.240 |
Token | from |
Token ID | 422 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
RED | +7.203 |
quished | +6.601 |
士 | +6.526 |
Thrones | +6.436 |
cups | +6.168 |
Neg logit contributions | |
ofer | -10.750 |
etz | -8.160 |
ele | -8.056 |
itness | -7.936 |
jri | -7.906 |
Token | cutting |
Token ID | 7720 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
RED | +1.134 |
士 | +1.073 |
quished | +1.048 |
Thrones | +1.033 |
gio | +1.023 |
Neg logit contributions | |
ofer | -1.598 |
ele | -1.215 |
etz | -1.209 |
itness | -1.187 |
wards | -1.180 |
Token | up |
Token ID | 510 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
RED | +0.721 |
士 | +0.686 |
quished | +0.668 |
Thrones | +0.653 |
gio | +0.645 |
Neg logit contributions | |
ofer | -1.100 |
ele | -0.849 |
etz | -0.842 |
itness | -0.833 |
wards | -0.832 |
Token | the |
Token ID | 262 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
ofer | +0.046 |
ele | +0.035 |
etz | +0.035 |
wards | +0.034 |
itness | +0.034 |
Neg logit contributions | |
RED | -0.031 |
士 | -0.030 |
quished | -0.029 |
Thrones | -0.028 |
gio | -0.028 |
Token | onions |
Token ID | 24681 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ofer | +1.030 |
ele | +0.830 |
etz | +0.824 |
wards | +0.818 |
itness | +0.815 |
Neg logit contributions | |
RED | -0.430 |
士 | -0.406 |
quished | -0.390 |
Thrones | -0.376 |
gio | -0.375 |
Token | Sher |
Token ID | 6528 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ofer | +1.292 |
ele | +0.990 |
etz | +0.982 |
wards | +0.974 |
itness | +0.966 |
Neg logit contributions | |
RED | -0.910 |
士 | -0.872 |
quished | -0.850 |
Thrones | -0.825 |
gio | -0.823 |
Token | is |
Token ID | 318 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ofer | +1.870 |
ele | +1.369 |
etz | +1.353 |
wards | +1.347 |
itness | +1.329 |
Neg logit contributions | |
RED | -1.781 |
士 | -1.728 |
quished | -1.690 |
Thrones | -1.655 |
gio | -1.634 |
Token | CEO |
Token ID | 6123 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
RED | +2.036 |
士 | +1.937 |
quished | +1.885 |
Thrones | +1.868 |
gio | +1.854 |
Neg logit contributions | |
ofer | -2.245 |
ele | -1.642 |
etz | -1.624 |
itness | -1.606 |
wards | -1.605 |
Token | of |
Token ID | 286 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ofer | +2.331 |
ele | +1.720 |
etz | +1.703 |
wards | +1.698 |
itness | +1.685 |
Neg logit contributions | |
RED | -2.045 |
士 | -1.973 |
quished | -1.941 |
Thrones | -1.900 |
gio | -1.898 |
Token | Canadian |
Token ID | 5398 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
ofer | +0.356 |
ele | +0.273 |
etz | +0.270 |
wards | +0.268 |
itness | +0.267 |
Neg logit contributions | |
RED | -0.242 |
士 | -0.232 |
quished | -0.225 |
Thrones | -0.221 |
gio | -0.219 |
Token | Blood |
Token ID | 7235 |
Feature activation | -9.88e+00 |
Pos logit contributions | |
RED | +4.004 |
士 | +3.749 |
quished | +3.611 |
Thrones | +3.534 |
gio | +3.492 |
Neg logit contributions | |
ofer | -6.259 |
ele | -4.788 |
etz | -4.777 |
itness | -4.764 |
wards | -4.750 |
Token | Services |
Token ID | 6168 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
RED | +6.790 |
士 | +6.429 |
Thrones | +6.256 |
gio | +6.099 |
Manip | +6.036 |
Neg logit contributions | |
ofer | -9.523 |
itness | -7.133 |
ele | -7.123 |
jri | -7.066 |
etz | -7.044 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ofer | +3.482 |
ele | +2.677 |
etz | +2.658 |
wards | +2.614 |
itness | +2.595 |
Neg logit contributions | |
RED | -2.516 |
士 | -2.440 |
quished | -2.401 |
Thrones | -2.320 |
gio | -2.312 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
RED | +2.545 |
士 | +2.392 |
quished | +2.335 |
gio | +2.314 |
Thrones | +2.311 |
Neg logit contributions | |
ofer | -3.846 |
ele | -2.946 |
etz | -2.927 |
wards | -2.903 |
itness | -2.897 |
Token | Words |
Token ID | 37117 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
RED | +3.657 |
士 | +3.317 |
quished | +3.257 |
gio | +3.220 |
Thrones | +3.110 |
Neg logit contributions | |
ofer | -4.274 |
etz | -3.169 |
itness | -3.150 |
ele | -3.119 |
wards | -3.114 |
Token | have |
Token ID | 423 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
RED | +5.218 |
士 | +4.919 |
quished | +4.902 |
Thrones | +4.865 |
gio | +4.698 |
Neg logit contributions | |
ofer | -7.243 |
wards | -5.563 |
ele | -5.543 |
etz | -5.514 |
jri | -5.447 |
Token | ial |
Token ID | 498 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
RED | +1.774 |
士 | +1.685 |
quished | +1.665 |
gio | +1.656 |
Thrones | +1.639 |
Neg logit contributions | |
ofer | -1.460 |
ele | -1.017 |
etz | -1.012 |
itness | -1.007 |
wards | -0.975 |
Token | et |
Token ID | 316 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
RED | +6.119 |
士 | +5.858 |
gio | +5.838 |
quished | +5.754 |
Thrones | +5.640 |
Neg logit contributions | |
ofer | -5.332 |
challeng | -3.817 |
jri | -3.701 |
wards | -3.694 |
ele | -3.618 |
Token | � |
Token ID | 447 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
RED | +3.192 |
士 | +3.058 |
quished | +2.964 |
Thrones | +2.935 |
gio | +2.907 |
Neg logit contributions | |
ofer | -3.539 |
ele | -2.613 |
etz | -2.597 |
wards | -2.592 |
itness | -2.578 |
Token | � |
Token ID | 247 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ofer | +0.240 |
ele | +0.199 |
etz | +0.197 |
wards | +0.196 |
itness | +0.195 |
Neg logit contributions | |
RED | -0.071 |
士 | -0.066 |
quished | -0.061 |
Thrones | -0.059 |
gio | -0.059 |
Token | s |
Token ID | 82 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
RED | +2.862 |
士 | +2.719 |
gio | +2.678 |
Thrones | +2.635 |
quished | +2.600 |
Neg logit contributions | |
ofer | -3.300 |
etz | -2.417 |
jri | -2.415 |
itness | -2.410 |
ele | -2.387 |
Token | Silver |
Token ID | 7698 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
ofer | +0.920 |
ele | +0.707 |
etz | +0.700 |
wards | +0.694 |
itness | +0.691 |
Neg logit contributions | |
RED | -0.636 |
士 | -0.610 |
quished | -0.595 |
Thrones | -0.578 |
gio | -0.577 |
Token | Phantom |
Token ID | 14407 |
Feature activation | -9.52e+00 |
Pos logit contributions | |
RED | +6.806 |
士 | +6.774 |
Thrones | +6.404 |
quished | +6.321 |
gio | +6.093 |
Neg logit contributions | |
ofer | -14.378 |
itness | -11.554 |
wards | -11.542 |
etz | -11.536 |
jri | -11.493 |
Token | falls |
Token ID | 8953 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
RED | +6.904 |
士 | +6.562 |
Thrones | +6.374 |
quished | +6.294 |
gio | +6.168 |
Neg logit contributions | |
ofer | -8.777 |
itness | -6.750 |
wards | -6.747 |
etz | -6.722 |
ele | -6.692 |
Token | into |
Token ID | 656 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
RED | +2.284 |
士 | +2.156 |
quished | +2.107 |
Thrones | +2.090 |
gio | +2.041 |
Neg logit contributions | |
ofer | -3.788 |
etz | -2.968 |
ele | -2.966 |
itness | -2.902 |
jri | -2.859 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
RED | +4.131 |
士 | +3.892 |
Thrones | +3.878 |
quished | +3.807 |
gio | +3.736 |
Neg logit contributions | |
ofer | -5.415 |
etz | -4.110 |
ele | -4.105 |
itness | -4.097 |
jri | -4.060 |
Token | latter |
Token ID | 6846 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
RED | +2.497 |
士 | +2.386 |
Thrones | +2.312 |
quished | +2.292 |
gio | +2.262 |
Neg logit contributions | |
ofer | -3.601 |
etz | -2.758 |
ele | -2.757 |
wards | -2.719 |
itness | -2.709 |
Token | ambient |
Token ID | 25237 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
ofer | +1.093 |
ele | +0.842 |
etz | +0.837 |
wards | +0.828 |
itness | +0.827 |
Neg logit contributions | |
RED | -0.747 |
士 | -0.713 |
quished | -0.691 |
Thrones | -0.675 |
gio | -0.672 |
Token | density |
Token ID | 12109 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
ofer | +3.709 |
ele | +2.588 |
wards | +2.560 |
etz | +2.512 |
itness | +2.503 |
Neg logit contributions | |
RED | -4.309 |
士 | -4.193 |
quished | -4.139 |
Thrones | -4.054 |
gio | -4.019 |
Token | uniformly |
Token ID | 42096 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
ofer | +0.827 |
etz | +0.622 |
ele | +0.622 |
itness | +0.609 |
wards | +0.608 |
Neg logit contributions | |
RED | -0.680 |
士 | -0.651 |
quished | -0.633 |
Thrones | -0.622 |
gio | -0.622 |
Token | throughout |
Token ID | 3690 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
RED | +0.441 |
士 | +0.417 |
quished | +0.403 |
Thrones | +0.398 |
gio | +0.396 |
Neg logit contributions | |
ofer | -0.638 |
etz | -0.492 |
ele | -0.492 |
itness | -0.485 |
wards | -0.478 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ofer | +5.421 |
wards | +4.012 |
ele | +4.006 |
etz | +3.942 |
itness | +3.881 |
Neg logit contributions | |
RED | -4.945 |
士 | -4.784 |
quished | -4.726 |
gio | -4.570 |
Thrones | -4.565 |
Token | V |
Token ID | 569 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
ofer | +1.313 |
ele | +0.996 |
etz | +0.991 |
itness | +0.975 |
wards | +0.974 |
Neg logit contributions | |
RED | -1.016 |
士 | -0.970 |
quished | -0.942 |
Thrones | -0.928 |
gio | -0.923 |
Token | ort |
Token ID | 419 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
RED | +9.857 |
士 | +9.420 |
quished | +9.276 |
gio | +8.966 |
Thrones | +8.750 |
Neg logit contributions | |
ofer | -8.093 |
etz | -5.749 |
wards | -5.652 |
ele | -5.566 |
jri | -5.486 |
Token | ons |
Token ID | 684 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
RED | +1.156 |
士 | +1.130 |
quished | +1.110 |
Thrones | +1.095 |
gio | +1.093 |
Neg logit contributions | |
ofer | -0.501 |
ele | -0.274 |
etz | -0.266 |
wards | -0.261 |
itness | -0.256 |
Token | carry |
Token ID | 3283 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
RED | +2.364 |
士 | +2.224 |
Thrones | +2.179 |
quished | +2.139 |
gio | +2.117 |
Neg logit contributions | |
ofer | -3.803 |
ele | -2.944 |
etz | -2.937 |
wards | -2.890 |
itness | -2.881 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
RED | +0.555 |
士 | +0.530 |
quished | +0.509 |
gio | +0.503 |
Thrones | +0.502 |
Neg logit contributions | |
ofer | -0.713 |
etz | -0.543 |
ele | -0.541 |
itness | -0.530 |
wards | -0.524 |
Token | value |
Token ID | 1988 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ofer | +1.841 |
ele | +1.436 |
etz | +1.429 |
itness | +1.407 |
wards | +1.406 |
Neg logit contributions | |
RED | -1.121 |
士 | -1.068 |
quished | -1.030 |
Thrones | -1.007 |
gio | -1.005 |
Token | before |
Token ID | 878 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ofer | +0.853 |
ele | +0.641 |
etz | +0.637 |
itness | +0.633 |
wards | +0.632 |
Neg logit contributions | |
RED | -0.656 |
士 | -0.629 |
quished | -0.613 |
Thrones | -0.602 |
gio | -0.598 |
Token | March |
Token ID | 2805 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
RED | +1.080 |
士 | +1.038 |
quished | +1.002 |
Thrones | +0.991 |
gio | +0.978 |
Neg logit contributions | |
ofer | -1.510 |
ele | -1.141 |
etz | -1.135 |
itness | -1.122 |
wards | -1.111 |
Token | of |
Token ID | 286 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
RED | +3.995 |
士 | +3.720 |
Thrones | +3.696 |
Enix | +3.639 |
Breaker | +3.468 |
Neg logit contributions | |
ofer | -6.491 |
jri | -5.130 |
itness | -5.104 |
ele | -4.974 |
etz | -4.962 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ofer | +2.266 |
ele | +1.734 |
etz | +1.717 |
wards | +1.705 |
itness | +1.696 |
Neg logit contributions | |
RED | -1.618 |
士 | -1.555 |
quished | -1.514 |
Thrones | -1.474 |
gio | -1.472 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ofer | +3.123 |
ele | +2.394 |
etz | +2.372 |
wards | +2.349 |
itness | +2.316 |
Neg logit contributions | |
RED | -2.337 |
士 | -2.248 |
quished | -2.208 |
gio | -2.152 |
Thrones | -2.136 |
Token | Square |
Token ID | 9276 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
ofer | +1.047 |
ele | +0.787 |
etz | +0.780 |
wards | +0.772 |
itness | +0.770 |
Neg logit contributions | |
RED | -0.846 |
士 | -0.813 |
quished | -0.791 |
Thrones | -0.777 |
gio | -0.773 |
Token | Enix |
Token ID | 41361 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Enix | +4.805 |
RED | +4.381 |
士 | +3.909 |
Thrones | +3.790 |
quished | +3.718 |
Neg logit contributions | |
ofer | -15.088 |
ele | -12.411 |
itness | -12.374 |
jri | -12.340 |
etz | -12.306 |
Token | released |
Token ID | 2716 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
RED | +1.128 |
士 | +1.069 |
quished | +1.031 |
Thrones | +1.029 |
Enix | +1.013 |
Neg logit contributions | |
ofer | -1.778 |
ele | -1.371 |
itness | -1.358 |
etz | -1.357 |
wards | -1.344 |
Token | a |
Token ID | 257 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ofer | +0.267 |
ele | +0.202 |
etz | +0.199 |
itness | +0.197 |
wards | +0.196 |
Neg logit contributions | |
RED | -0.209 |
士 | -0.200 |
quished | -0.195 |
Thrones | -0.192 |
gio | -0.190 |
Token | lineup |
Token ID | 12750 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ofer | +1.808 |
ele | +1.379 |
etz | +1.366 |
itness | +1.349 |
wards | +1.341 |
Neg logit contributions | |
RED | -1.312 |
士 | -1.254 |
quished | -1.220 |
Thrones | -1.203 |
gio | -1.192 |
Token | of |
Token ID | 286 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
RED | +0.235 |
士 | +0.224 |
quished | +0.219 |
Thrones | +0.215 |
gio | +0.213 |
Neg logit contributions | |
ofer | -0.306 |
ele | -0.232 |
etz | -0.229 |
itness | -0.229 |
wards | -0.226 |