Token | like |
Token ID | 588 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
mas | +1.290 |
Fall | +1.254 |
seeing | +1.234 |
hey | +1.159 |
look | +1.152 |
Neg logit contributions | |
relations | -1.164 |
suicide | -1.118 |
ulum | -1.068 |
nton | -1.057 |
grounds | -1.032 |
Token | Netflix |
Token ID | 12074 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
mas | +4.636 |
Fall | +4.393 |
seeing | +4.262 |
look | +4.063 |
hey | +3.995 |
Neg logit contributions | |
relations | -7.310 |
suicide | -7.143 |
ulum | -7.118 |
uctor | -6.914 |
nton | -6.872 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
mas | +7.289 |
Fall | +7.073 |
seeing | +6.993 |
look | +6.589 |
hey | +6.477 |
Neg logit contributions | |
relations | -6.008 |
suicide | -5.804 |
ulum | -5.722 |
nton | -5.546 |
uctor | -5.409 |
Token | YouTube |
Token ID | 7444 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
mas | +3.659 |
Fall | +3.542 |
seeing | +3.497 |
look | +3.263 |
hey | +3.261 |
Neg logit contributions | |
relations | -4.094 |
suicide | -3.966 |
ulum | -3.899 |
nton | -3.798 |
uctor | -3.719 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
mas | +5.345 |
Fall | +5.191 |
seeing | +5.079 |
look | +4.761 |
hey | +4.744 |
Neg logit contributions | |
relations | -4.710 |
suicide | -4.561 |
ulum | -4.417 |
nton | -4.305 |
grounds | -4.186 |
Token | Hulu |
Token ID | 39739 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
mas | +4.298 |
Fall | +4.126 |
seeing | +4.063 |
look | +3.806 |
hey | +3.777 |
Neg logit contributions | |
relations | -5.717 |
suicide | -5.568 |
ulum | -5.484 |
nton | -5.323 |
uctor | -5.226 |
Token | , |
Token ID | 11 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
mas | +11.279 |
Fall | +11.014 |
seeing | +10.821 |
look | +10.084 |
作 | +9.889 |
Neg logit contributions | |
relations | -10.665 |
ulum | -10.554 |
suicide | -10.416 |
nton | -10.071 |
uctor | -9.883 |
Token | and |
Token ID | 290 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
mas | +4.574 |
Fall | +4.411 |
seeing | +4.333 |
look | +4.081 |
hey | +4.045 |
Neg logit contributions | |
relations | -5.334 |
suicide | -5.172 |
ulum | -5.083 |
nton | -4.952 |
uctor | -4.847 |
Token | Amazon |
Token ID | 6186 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
mas | +1.810 |
Fall | +1.750 |
seeing | +1.720 |
hey | +1.606 |
look | +1.599 |
Neg logit contributions | |
relations | -2.009 |
suicide | -1.939 |
ulum | -1.872 |
nton | -1.848 |
grounds | -1.803 |
Token | Prime |
Token ID | 5537 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
mas | +5.912 |
Fall | +5.698 |
seeing | +5.513 |
look | +5.210 |
hey | +5.043 |
Neg logit contributions | |
relations | -7.343 |
ulum | -7.141 |
suicide | -7.090 |
nton | -6.997 |
uctor | -6.790 |
Token | among |
Token ID | 1871 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
mas | +9.297 |
Fall | +9.236 |
seeing | +8.993 |
look | +8.517 |
hey | +8.178 |
Neg logit contributions | |
ulum | -9.106 |
relations | -8.952 |
nton | -8.786 |
suicide | -8.604 |
uctor | -8.338 |
Token | Taylor |
Token ID | 8121 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
mas | +2.231 |
Fall | +2.157 |
seeing | +2.118 |
hey | +1.981 |
look | +1.970 |
Neg logit contributions | |
relations | -2.448 |
suicide | -2.356 |
ulum | -2.284 |
nton | -2.252 |
grounds | -2.195 |
Token | - |
Token ID | 12 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
relations | +0.433 |
suicide | +0.409 |
ulum | +0.382 |
nton | +0.377 |
grounds | +0.364 |
Neg logit contributions | |
mas | -0.851 |
Fall | -0.832 |
seeing | -0.822 |
hey | -0.783 |
look | -0.780 |
Token | Johnson |
Token ID | 25378 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
mas | +0.959 |
Fall | +0.920 |
seeing | +0.891 |
hey | +0.800 |
look | +0.792 |
Neg logit contributions | |
relations | -2.081 |
suicide | -2.025 |
ulum | -1.965 |
nton | -1.948 |
grounds | -1.917 |
Token | , |
Token ID | 11 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
relations | +0.522 |
suicide | +0.497 |
ulum | +0.462 |
nton | +0.459 |
grounds | +0.447 |
Neg logit contributions | |
mas | -0.871 |
Fall | -0.850 |
seeing | -0.841 |
hey | -0.798 |
look | -0.794 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
mas | +1.933 |
Fall | +1.875 |
seeing | +1.845 |
hey | +1.729 |
look | +1.721 |
Neg logit contributions | |
relations | -1.853 |
suicide | -1.783 |
ulum | -1.715 |
nton | -1.696 |
grounds | -1.650 |
Token | Gos |
Token ID | 30007 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
mas | +1.417 |
Fall | +1.367 |
seeing | +1.341 |
hey | +1.233 |
look | +1.224 |
Neg logit contributions | |
relations | -1.985 |
suicide | -1.921 |
ulum | -1.853 |
nton | -1.838 |
grounds | -1.800 |
Token | ling |
Token ID | 1359 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
mas | +7.205 |
seeing | +5.727 |
hey | +5.702 |
hell | +5.660 |
look | +5.537 |
Neg logit contributions | |
relations | -15.780 |
ancest | -15.526 |
suicide | -14.960 |
magistrate | -14.689 |
ulum | -14.633 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
mas | +0.250 |
Fall | +0.244 |
seeing | +0.240 |
hey | +0.228 |
look | +0.227 |
Neg logit contributions | |
relations | -0.153 |
suicide | -0.146 |
ulum | -0.138 |
nton | -0.136 |
grounds | -0.132 |
Token | Alex |
Token ID | 4422 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
mas | +3.182 |
Fall | +3.086 |
seeing | +3.037 |
hey | +2.849 |
look | +2.842 |
Neg logit contributions | |
relations | -3.101 |
suicide | -2.988 |
ulum | -2.895 |
nton | -2.863 |
grounds | -2.767 |
Token | Petty |
Token ID | 41505 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
mas | +3.265 |
Fall | +3.180 |
seeing | +3.100 |
hey | +2.924 |
look | +2.910 |
Neg logit contributions | |
relations | -3.440 |
suicide | -3.301 |
ulum | -3.228 |
nton | -3.165 |
grounds | -3.086 |
Token | fer |
Token ID | 2232 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
mas | +1.370 |
Fall | +1.333 |
seeing | +1.317 |
hey | +1.250 |
look | +1.241 |
Neg logit contributions | |
relations | -0.887 |
suicide | -0.843 |
ulum | -0.801 |
nton | -0.785 |
grounds | -0.764 |
Token | catalog |
Token ID | 18388 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
mas | +1.776 |
Fall | +1.725 |
seeing | +1.698 |
hey | +1.599 |
look | +1.596 |
Neg logit contributions | |
relations | -1.430 |
suicide | -1.370 |
ulum | -1.310 |
nton | -1.299 |
grounds | -1.256 |
Token | s |
Token ID | 82 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
relations | +0.088 |
suicide | +0.084 |
ulum | +0.081 |
nton | +0.079 |
grounds | +0.078 |
Neg logit contributions | |
mas | -0.094 |
Fall | -0.092 |
seeing | -0.090 |
hey | -0.085 |
look | -0.084 |
Token | of |
Token ID | 286 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
mas | +2.341 |
Fall | +2.269 |
seeing | +2.232 |
hey | +2.087 |
look | +2.077 |
Neg logit contributions | |
relations | -2.386 |
suicide | -2.299 |
ulum | -2.212 |
nton | -2.195 |
grounds | -2.128 |
Token | Netflix |
Token ID | 12074 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
mas | +0.677 |
Fall | +0.657 |
seeing | +0.647 |
hey | +0.607 |
look | +0.601 |
Neg logit contributions | |
relations | -0.615 |
suicide | -0.591 |
ulum | -0.560 |
nton | -0.554 |
grounds | -0.547 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
mas | +6.063 |
Fall | +5.888 |
seeing | +5.763 |
look | +5.465 |
hey | +5.432 |
Neg logit contributions | |
relations | -4.110 |
suicide | -3.937 |
ulum | -3.843 |
nton | -3.771 |
uctor | -3.637 |
Token | Hulu |
Token ID | 39739 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
mas | +3.519 |
Fall | +3.377 |
seeing | +3.272 |
look | +3.024 |
hey | +3.000 |
Neg logit contributions | |
relations | -6.536 |
suicide | -6.362 |
ulum | -6.288 |
nton | -6.159 |
uctor | -6.057 |
Token | Plus |
Token ID | 8227 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
mas | +11.472 |
Fall | +11.130 |
seeing | +10.820 |
look | +10.149 |
作 | +10.043 |
Neg logit contributions | |
relations | -8.841 |
ulum | -8.786 |
suicide | -8.721 |
nton | -8.542 |
uctor | -8.330 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
mas | +8.328 |
Fall | +8.138 |
seeing | +7.908 |
hell | +7.491 |
look | +7.482 |
Neg logit contributions | |
relations | -6.036 |
suicide | -5.865 |
ulum | -5.750 |
nton | -5.609 |
uctor | -5.441 |
Token | and |
Token ID | 290 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
mas | +3.928 |
Fall | +3.798 |
seeing | +3.714 |
look | +3.469 |
hey | +3.459 |
Neg logit contributions | |
relations | -4.805 |
suicide | -4.650 |
ulum | -4.536 |
nton | -4.457 |
uctor | -4.340 |
Token | Amazon |
Token ID | 6186 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
mas | +1.153 |
Fall | +1.116 |
seeing | +1.096 |
hey | +1.018 |
look | +1.009 |
Neg logit contributions | |
relations | -1.366 |
suicide | -1.317 |
ulum | -1.265 |
nton | -1.253 |
grounds | -1.231 |
Token | Prime |
Token ID | 5537 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
mas | +4.843 |
Fall | +4.631 |
seeing | +4.379 |
look | +4.194 |
hey | +4.068 |
Neg logit contributions | |
relations | -6.940 |
suicide | -6.750 |
ulum | -6.726 |
nton | -6.659 |
EStreamFrame | -6.461 |
Token | Apple |
Token ID | 4196 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
mas | +4.879 |
Fall | +4.681 |
seeing | +4.658 |
look | +4.321 |
hey | +4.300 |
Neg logit contributions | |
relations | -5.055 |
suicide | -4.873 |
ulum | -4.802 |
nton | -4.775 |
EStreamFrame | -4.599 |
Token | � |
Token ID | 447 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
mas | +5.130 |
Fall | +5.000 |
seeing | +4.903 |
hey | +4.638 |
look | +4.637 |
Neg logit contributions | |
relations | -3.343 |
suicide | -3.191 |
ulum | -3.073 |
nton | -3.020 |
ancest | -2.908 |
Token | � |
Token ID | 247 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
mas | +3.227 |
Fall | +3.101 |
seeing | +3.007 |
hey | +2.780 |
look | +2.728 |
Neg logit contributions | |
relations | -5.546 |
suicide | -5.404 |
nton | -5.274 |
ulum | -5.205 |
ancest | -5.073 |
Token | s |
Token ID | 82 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
mas | +4.109 |
Fall | +3.939 |
seeing | +3.852 |
hey | +3.595 |
look | +3.583 |
Neg logit contributions | |
relations | -4.777 |
suicide | -4.619 |
ulum | -4.444 |
nton | -4.393 |
grounds | -4.297 |
Token | original |
Token ID | 2656 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
mas | +3.815 |
Fall | +3.692 |
seeing | +3.579 |
look | +3.334 |
hey | +3.326 |
Neg logit contributions | |
relations | -5.055 |
suicide | -4.887 |
ulum | -4.751 |
nton | -4.729 |
uctor | -4.584 |
Token | iPhone |
Token ID | 7133 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
mas | +3.195 |
Fall | +3.096 |
seeing | +3.032 |
look | +2.833 |
hey | +2.830 |
Neg logit contributions | |
relations | -3.547 |
suicide | -3.413 |
ulum | -3.298 |
nton | -3.267 |
grounds | -3.180 |
Token | and |
Token ID | 290 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
mas | +11.314 |
Fall | +11.082 |
seeing | +10.659 |
look | +10.117 |
hey | +10.087 |
Neg logit contributions | |
relations | -8.991 |
ulum | -8.634 |
suicide | -8.571 |
nton | -8.537 |
EStreamFrame | -8.275 |
Token | Tesla |
Token ID | 11938 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
mas | +0.833 |
Fall | +0.799 |
seeing | +0.787 |
hey | +0.725 |
look | +0.716 |
Neg logit contributions | |
relations | -1.163 |
suicide | -1.127 |
ulum | -1.080 |
nton | -1.073 |
grounds | -1.055 |
Token | Motors |
Token ID | 19292 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
mas | +1.951 |
Fall | +1.897 |
seeing | +1.865 |
hey | +1.757 |
look | +1.746 |
Neg logit contributions | |
relations | -1.650 |
suicide | -1.583 |
ulum | -1.517 |
nton | -1.497 |
grounds | -1.456 |
Token | � |
Token ID | 447 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
mas | +6.001 |
Fall | +5.867 |
seeing | +5.743 |
hey | +5.445 |
hell | +5.413 |
Neg logit contributions | |
relations | -4.470 |
suicide | -4.286 |
ulum | -4.179 |
nton | -4.097 |
uctor | -3.922 |
Token | � |
Token ID | 247 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
mas | +2.305 |
Fall | +2.209 |
seeing | +2.156 |
hey | +1.991 |
look | +1.951 |
Neg logit contributions | |
relations | -3.849 |
suicide | -3.740 |
nton | -3.640 |
ulum | -3.620 |
ancest | -3.501 |
Token | West |
Token ID | 2688 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
mas | +0.313 |
Fall | +0.304 |
seeing | +0.300 |
hey | +0.282 |
look | +0.280 |
Neg logit contributions | |
relations | -0.261 |
suicide | -0.250 |
ulum | -0.238 |
nton | -0.235 |
grounds | -0.230 |
Token | Wing |
Token ID | 13405 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
mas | +0.579 |
Fall | +0.563 |
seeing | +0.554 |
hey | +0.521 |
look | +0.518 |
Neg logit contributions | |
relations | -0.514 |
suicide | -0.493 |
ulum | -0.471 |
nton | -0.466 |
grounds | -0.455 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
mas | +2.231 |
Fall | +2.169 |
seeing | +2.141 |
hey | +2.022 |
look | +2.009 |
Neg logit contributions | |
relations | -1.670 |
suicide | -1.599 |
ulum | -1.530 |
nton | -1.509 |
grounds | -1.455 |
Token | including |
Token ID | 1390 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
mas | +1.005 |
Fall | +0.977 |
seeing | +0.960 |
hey | +0.904 |
look | +0.898 |
Neg logit contributions | |
relations | -0.877 |
suicide | -0.840 |
ulum | -0.799 |
nton | -0.791 |
grounds | -0.774 |
Token | Sebastian |
Token ID | 26190 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
mas | +2.954 |
Fall | +2.869 |
seeing | +2.850 |
hey | +2.664 |
look | +2.652 |
Neg logit contributions | |
relations | -2.439 |
suicide | -2.351 |
ulum | -2.306 |
nton | -2.255 |
uctor | -2.181 |
Token | Gork |
Token ID | 49882 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
mas | +1.852 |
Fall | +1.783 |
seeing | +1.755 |
hey | +1.650 |
look | +1.626 |
Neg logit contributions | |
relations | -1.761 |
suicide | -1.701 |
ulum | -1.636 |
nton | -1.623 |
uctor | -1.573 |
Token | a |
Token ID | 64 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
mas | +7.498 |
Fall | +7.158 |
seeing | +6.764 |
hey | +6.731 |
hell | +6.187 |
Neg logit contributions | |
relations | -13.176 |
suicide | -12.650 |
EStreamFrame | -12.504 |
ancest | -12.443 |
uctor | -12.406 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
mas | +2.616 |
Fall | +2.542 |
seeing | +2.512 |
hey | +2.387 |
look | +2.367 |
Neg logit contributions | |
relations | -1.662 |
suicide | -1.584 |
ulum | -1.506 |
nton | -1.477 |
grounds | -1.429 |
Token | have |
Token ID | 423 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
mas | +3.025 |
Fall | +2.928 |
seeing | +2.887 |
hey | +2.723 |
look | +2.710 |
Neg logit contributions | |
relations | -2.632 |
suicide | -2.532 |
ulum | -2.469 |
nton | -2.419 |
uctor | -2.352 |
Token | received |
Token ID | 2722 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
relations | +2.095 |
suicide | +1.993 |
ulum | +1.844 |
grounds | +1.844 |
nton | +1.833 |
Neg logit contributions | |
mas | -2.626 |
Fall | -2.549 |
seeing | -2.514 |
hey | -2.362 |
look | -2.345 |
Token | enormous |
Token ID | 9812 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
mas | +0.606 |
Fall | +0.589 |
seeing | +0.579 |
hey | +0.546 |
look | +0.542 |
Neg logit contributions | |
relations | -0.510 |
suicide | -0.489 |
ulum | -0.463 |
nton | -0.458 |
grounds | -0.449 |
Token | Buy |
Token ID | 11763 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
mas | +0.895 |
Fall | +0.865 |
seeing | +0.849 |
hey | +0.788 |
look | +0.783 |
Neg logit contributions | |
relations | -1.090 |
suicide | -1.052 |
ulum | -1.013 |
nton | -1.003 |
grounds | -0.982 |
Token | will |
Token ID | 481 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
mas | +1.213 |
Fall | +1.183 |
seeing | +1.166 |
hey | +1.106 |
look | +1.100 |
Neg logit contributions | |
relations | -0.790 |
suicide | -0.752 |
ulum | -0.714 |
nton | -0.704 |
grounds | -0.681 |
Token | have |
Token ID | 423 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
mas | +0.675 |
Fall | +0.655 |
seeing | +0.646 |
hey | +0.604 |
look | +0.599 |
Neg logit contributions | |
relations | -0.655 |
suicide | -0.632 |
ulum | -0.601 |
nton | -0.596 |
grounds | -0.586 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
relations | +0.147 |
suicide | +0.140 |
ulum | +0.132 |
grounds | +0.130 |
nton | +0.130 |
Neg logit contributions | |
mas | -0.177 |
Fall | -0.171 |
seeing | -0.170 |
hey | -0.160 |
look | -0.158 |
Token | Google |
Token ID | 3012 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
mas | +2.784 |
Fall | +2.702 |
seeing | +2.609 |
look | +2.409 |
hey | +2.392 |
Neg logit contributions | |
relations | -4.409 |
suicide | -4.277 |
ulum | -4.180 |
nton | -4.162 |
uctor | -4.042 |
Token | Nexus |
Token ID | 16756 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
mas | +3.601 |
Fall | +3.516 |
seeing | +3.276 |
look | +3.068 |
hey | +3.001 |
Neg logit contributions | |
relations | -6.940 |
suicide | -6.788 |
nton | -6.777 |
ulum | -6.725 |
EStreamFrame | -6.552 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Fall | +7.580 |
mas | +7.441 |
seeing | +6.961 |
look | +6.823 |
hell | +6.392 |
Neg logit contributions | |
relations | -12.176 |
nton | -12.078 |
ulum | -12.016 |
suicide | -11.791 |
uctor | -11.569 |
Token | in |
Token ID | 287 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
mas | +5.738 |
Fall | +5.657 |
seeing | +5.438 |
look | +5.187 |
hey | +5.152 |
Neg logit contributions | |
relations | -5.081 |
suicide | -4.842 |
ulum | -4.772 |
nton | -4.699 |
uctor | -4.536 |
Token | stock |
Token ID | 4283 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
mas | +4.188 |
Fall | +4.132 |
seeing | +4.004 |
look | +3.791 |
hey | +3.785 |
Neg logit contributions | |
relations | -3.495 |
suicide | -3.357 |
ulum | -3.287 |
nton | -3.234 |
uctor | -3.130 |
Token | on |
Token ID | 319 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
relations | +1.001 |
suicide | +0.952 |
ulum | +0.891 |
nton | +0.881 |
grounds | +0.880 |
Neg logit contributions | |
mas | -1.203 |
Fall | -1.160 |
seeing | -1.147 |
hey | -1.082 |
look | -1.075 |
Token | November |
Token ID | 3389 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
mas | +1.416 |
Fall | +1.367 |
seeing | +1.340 |
hey | +1.242 |
look | +1.234 |
Neg logit contributions | |
relations | -1.823 |
suicide | -1.762 |
ulum | -1.701 |
nton | -1.684 |
grounds | -1.648 |
Token | AMD |
Token ID | 10324 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
mas | +1.617 |
Fall | +1.569 |
seeing | +1.544 |
hey | +1.450 |
look | +1.441 |
Neg logit contributions | |
relations | -1.502 |
suicide | -1.443 |
ulum | -1.384 |
nton | -1.369 |
grounds | -1.333 |
Token | 's |
Token ID | 338 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
relations | +3.322 |
suicide | +3.185 |
ulum | +3.032 |
grounds | +2.941 |
nton | +2.909 |
Neg logit contributions | |
mas | -4.338 |
Fall | -4.221 |
seeing | -4.206 |
hey | -3.907 |
hell | -3.905 |
Token | 28 |
Token ID | 2579 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
mas | +3.390 |
Fall | +3.284 |
seeing | +3.213 |
hey | +3.011 |
look | +2.987 |
Neg logit contributions | |
relations | -3.837 |
suicide | -3.695 |
ulum | -3.565 |
nton | -3.557 |
grounds | -3.442 |
Token | nm |
Token ID | 21533 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
relations | +1.129 |
suicide | +1.088 |
ulum | +1.039 |
nton | +1.023 |
grounds | +0.995 |
Neg logit contributions | |
mas | -1.390 |
Fall | -1.358 |
seeing | -1.341 |
hey | -1.258 |
look | -1.249 |
Token | Radeon |
Token ID | 13082 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
relations | +1.249 |
suicide | +1.205 |
ulum | +1.147 |
nton | +1.124 |
grounds | +1.122 |
Neg logit contributions | |
mas | -1.200 |
Fall | -1.166 |
seeing | -1.140 |
hey | -1.067 |
look | -1.052 |
Token | HD |
Token ID | 5572 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
mas | +2.988 |
Fall | +2.891 |
seeing | +2.815 |
look | +2.579 |
hey | +2.558 |
Neg logit contributions | |
relations | -5.076 |
suicide | -4.933 |
nton | -4.820 |
ulum | -4.791 |
ancest | -4.634 |
Token | 78 |
Token ID | 8699 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
mas | +7.808 |
Fall | +7.190 |
seeing | +6.872 |
hey | +6.665 |
look | +6.446 |
Neg logit contributions | |
relations | -12.199 |
nton | -11.660 |
suicide | -11.587 |
EStreamFrame | -11.347 |
oppos | -11.256 |
Token | 70 |
Token ID | 2154 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
mas | +1.383 |
Fall | +1.323 |
seeing | +1.285 |
look | +1.178 |
hey | +1.178 |
Neg logit contributions | |
relations | -2.436 |
suicide | -2.362 |
ulum | -2.281 |
nton | -2.271 |
ancest | -2.218 |
Token | GPU |
Token ID | 11362 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
mas | +0.073 |
Fall | +0.071 |
seeing | +0.070 |
hey | +0.066 |
look | +0.066 |
Neg logit contributions | |
relations | -0.061 |
suicide | -0.058 |
ulum | -0.055 |
nton | -0.055 |
grounds | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
mas | +2.026 |
Fall | +1.973 |
seeing | +1.944 |
hey | +1.834 |
look | +1.825 |
Neg logit contributions | |
relations | -1.555 |
suicide | -1.488 |
ulum | -1.421 |
nton | -1.406 |
grounds | -1.361 |
Token | MSI |
Token ID | 30781 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
mas | +1.446 |
Fall | +1.401 |
seeing | +1.373 |
hey | +1.280 |
look | +1.270 |
Neg logit contributions | |
relations | -1.685 |
suicide | -1.627 |
ulum | -1.566 |
nton | -1.551 |
grounds | -1.514 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
relations | +1.102 |
suicide | +1.047 |
ulum | +0.994 |
nton | +0.990 |
grounds | +0.957 |
Neg logit contributions | |
mas | -1.773 |
Fall | -1.716 |
seeing | -1.707 |
hey | -1.613 |
look | -1.599 |
Token | GPU |
Token ID | 33346 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
relations | +0.527 |
suicide | +0.512 |
ulum | +0.494 |
nton | +0.491 |
grounds | +0.481 |
Neg logit contributions | |
mas | -0.367 |
Fall | -0.349 |
seeing | -0.349 |
hey | -0.318 |
look | -0.315 |
Token | : |
Token ID | 25 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
relations | +0.308 |
suicide | +0.294 |
ulum | +0.279 |
nton | +0.274 |
grounds | +0.271 |
Neg logit contributions | |
mas | -0.383 |
Fall | -0.371 |
seeing | -0.369 |
hey | -0.347 |
look | -0.343 |
Token | AMD |
Token ID | 10324 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
mas | +2.229 |
Fall | +2.160 |
seeing | +2.116 |
hey | +1.978 |
look | +1.966 |
Neg logit contributions | |
relations | -2.478 |
suicide | -2.388 |
ulum | -2.301 |
nton | -2.276 |
grounds | -2.221 |
Token | Radeon |
Token ID | 13082 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
relations | +2.513 |
suicide | +2.408 |
ulum | +2.297 |
grounds | +2.230 |
nton | +2.222 |
Neg logit contributions | |
mas | -2.856 |
seeing | -2.762 |
Fall | -2.755 |
hey | -2.559 |
hell | -2.534 |
Token | HD |
Token ID | 5572 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
mas | +4.267 |
Fall | +4.232 |
seeing | +4.069 |
look | +3.801 |
hey | +3.783 |
Neg logit contributions | |
relations | -5.327 |
suicide | -5.161 |
nton | -5.102 |
ulum | -4.977 |
uctor | -4.831 |
Token | 78 |
Token ID | 8699 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
Fall | +6.737 |
mas | +6.593 |
seeing | +5.764 |
hey | +5.708 |
look | +5.516 |
Neg logit contributions | |
relations | -13.731 |
EStreamFrame | -13.187 |
suicide | -12.796 |
nton | -12.692 |
oppos | -12.515 |
Token | 70 |
Token ID | 2154 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
mas | +0.109 |
Fall | +0.105 |
seeing | +0.103 |
hey | +0.094 |
look | +0.093 |
Neg logit contributions | |
relations | -0.163 |
suicide | -0.158 |
ulum | -0.153 |
nton | -0.151 |
grounds | -0.149 |
Token | - |
Token ID | 532 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
relations | +1.089 |
suicide | +1.048 |
ulum | +1.001 |
nton | +0.988 |
grounds | +0.966 |
Neg logit contributions | |
mas | -1.205 |
Fall | -1.169 |
seeing | -1.155 |
hey | -1.082 |
look | -1.075 |
Token | 1100 |
Token ID | 36566 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
mas | +1.470 |
Fall | +1.424 |
seeing | +1.397 |
hey | +1.302 |
look | +1.293 |
Neg logit contributions | |
relations | -1.693 |
suicide | -1.632 |
ulum | -1.574 |
nton | -1.556 |
grounds | -1.520 |
Token | MHz |
Token ID | 19805 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
relations | +2.602 |
suicide | +2.487 |
ulum | +2.398 |
nton | +2.365 |
grounds | +2.310 |
Neg logit contributions | |
mas | -2.588 |
seeing | -2.552 |
Fall | -2.548 |
hey | -2.346 |
look | -2.339 |
Token | and |
Token ID | 290 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
relations | +1.176 |
suicide | +1.128 |
ulum | +1.061 |
nton | +1.054 |
grounds | +1.050 |
Neg logit contributions | |
mas | -1.191 |
Fall | -1.160 |
seeing | -1.136 |
hey | -1.072 |
look | -1.060 |
Token | not |
Token ID | 407 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
relations | +2.499 |
suicide | +2.388 |
ulum | +2.245 |
nton | +2.237 |
grounds | +2.235 |
Neg logit contributions | |
mas | -2.527 |
Fall | -2.456 |
seeing | -2.394 |
hey | -2.271 |
look | -2.251 |
Token | least |
Token ID | 1551 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
relations | +1.550 |
suicide | +1.487 |
nton | +1.401 |
ulum | +1.394 |
grounds | +1.384 |
Neg logit contributions | |
mas | -1.557 |
Fall | -1.528 |
seeing | -1.484 |
hey | -1.396 |
look | -1.386 |
Token | from |
Token ID | 422 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
mas | +1.263 |
Fall | +1.223 |
seeing | +1.206 |
hey | +1.125 |
look | +1.117 |
Neg logit contributions | |
relations | -1.314 |
suicide | -1.266 |
ulum | -1.221 |
nton | -1.206 |
grounds | -1.174 |
Token | Michael |
Token ID | 3899 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
mas | +0.048 |
Fall | +0.047 |
seeing | +0.046 |
hey | +0.044 |
look | +0.044 |
Neg logit contributions | |
relations | -0.037 |
suicide | -0.035 |
ulum | -0.033 |
nton | -0.033 |
grounds | -0.032 |
Token | Ign |
Token ID | 16583 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
mas | +1.414 |
Fall | +1.361 |
seeing | +1.331 |
hey | +1.227 |
look | +1.218 |
Neg logit contributions | |
relations | -2.026 |
suicide | -1.961 |
ulum | -1.897 |
nton | -1.877 |
grounds | -1.841 |
Token | at |
Token ID | 265 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
mas | +6.155 |
seeing | +5.347 |
look | +5.230 |
hey | +5.225 |
Fall | +5.069 |
Neg logit contributions | |
exting | -14.912 |
relations | -14.725 |
suicide | -14.080 |
practition | -14.072 |
ancest | -13.437 |
Token | ie |
Token ID | 494 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
mas | +1.781 |
Fall | +1.709 |
seeing | +1.703 |
hey | +1.614 |
look | +1.599 |
Neg logit contributions | |
relations | -1.553 |
suicide | -1.498 |
ulum | -1.417 |
nton | -1.403 |
ancest | -1.381 |
Token | ff |
Token ID | 487 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
mas | +3.072 |
Fall | +2.969 |
seeing | +2.783 |
hey | +2.614 |
look | +2.543 |
Neg logit contributions | |
relations | -7.454 |
suicide | -7.203 |
ulum | -7.017 |
ancest | -6.942 |
uctor | -6.809 |
Token | , |
Token ID | 11 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
mas | +1.422 |
Fall | +1.380 |
seeing | +1.360 |
hey | +1.282 |
look | +1.274 |
Neg logit contributions | |
relations | -1.162 |
suicide | -1.114 |
ulum | -1.066 |
nton | -1.051 |
grounds | -1.021 |
Token | all |
Token ID | 477 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
mas | +1.705 |
Fall | +1.657 |
seeing | +1.632 |
hey | +1.535 |
look | +1.526 |
Neg logit contributions | |
relations | -1.465 |
suicide | -1.405 |
ulum | -1.343 |
nton | -1.327 |
grounds | -1.294 |
Token | BS |
Token ID | 4462 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
mas | +1.822 |
Fall | +1.769 |
seeing | +1.742 |
hey | +1.635 |
look | +1.625 |
Neg logit contributions | |
relations | -1.674 |
suicide | -1.608 |
ulum | -1.541 |
nton | -1.523 |
grounds | -1.485 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
mas | +0.572 |
Fall | +0.559 |
seeing | +0.554 |
hey | +0.524 |
look | +0.522 |
Neg logit contributions | |
relations | -0.344 |
suicide | -0.327 |
ulum | -0.305 |
nton | -0.302 |
grounds | -0.295 |
Token | Food |
Token ID | 7318 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
mas | +3.527 |
Fall | +3.418 |
seeing | +3.347 |
hey | +3.148 |
look | +3.129 |
Neg logit contributions | |
relations | -3.619 |
suicide | -3.484 |
ulum | -3.377 |
nton | -3.320 |
uctor | -3.225 |
Token | Network |
Token ID | 7311 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
mas | +3.025 |
Fall | +2.875 |
seeing | +2.743 |
look | +2.397 |
hey | +2.342 |
Neg logit contributions | |
relations | -8.984 |
suicide | -8.792 |
ulum | -8.694 |
nton | -8.598 |
ancest | -8.418 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
mas | +1.730 |
Fall | +1.687 |
seeing | +1.666 |
hey | +1.583 |
look | +1.572 |
Neg logit contributions | |
relations | -1.103 |
suicide | -1.047 |
ulum | -0.985 |
nton | -0.976 |
grounds | -0.949 |
Token | HG |
Token ID | 48698 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
mas | +3.057 |
Fall | +2.961 |
seeing | +2.905 |
hey | +2.719 |
look | +2.706 |
Neg logit contributions | |
relations | -3.257 |
suicide | -3.137 |
ulum | -3.029 |
nton | -2.987 |
grounds | -2.909 |
Token | TV |
Token ID | 6849 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
mas | +4.356 |
Fall | +3.778 |
hey | +3.137 |
seeing | +3.005 |
look | +2.945 |
Neg logit contributions | |
relations | -15.998 |
suicide | -15.633 |
uctor | -15.306 |
nton | -15.280 |
ulum | -15.007 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
mas | +4.685 |
Fall | +4.573 |
seeing | +4.463 |
look | +4.229 |
hey | +4.222 |
Neg logit contributions | |
relations | -3.103 |
suicide | -2.972 |
ulum | -2.877 |
nton | -2.807 |
grounds | -2.692 |
Token | Cartoon |
Token ID | 46838 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
mas | +3.743 |
Fall | +3.624 |
seeing | +3.546 |
hey | +3.329 |
look | +3.316 |
Neg logit contributions | |
relations | -4.042 |
suicide | -3.889 |
ulum | -3.777 |
nton | -3.712 |
uctor | -3.615 |
Token | Network |
Token ID | 7311 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
mas | +0.473 |
Fall | +0.450 |
seeing | +0.435 |
hey | +0.385 |
look | +0.382 |
Neg logit contributions | |
relations | -1.158 |
suicide | -1.126 |
ulum | -1.095 |
nton | -1.087 |
grounds | -1.067 |
Token | , |
Token ID | 11 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
mas | +2.733 |
Fall | +2.670 |
seeing | +2.626 |
hey | +2.484 |
look | +2.476 |
Neg logit contributions | |
relations | -1.754 |
suicide | -1.676 |
ulum | -1.599 |
nton | -1.571 |
grounds | -1.512 |
Token | video |
Token ID | 2008 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
mas | +0.120 |
Fall | +0.117 |
seeing | +0.115 |
hey | +0.108 |
look | +0.108 |
Neg logit contributions | |
relations | -0.097 |
suicide | -0.093 |
ulum | -0.088 |
nton | -0.087 |
grounds | -0.085 |
Token | of |
Token ID | 286 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
mas | +0.587 |
Fall | +0.573 |
seeing | +0.563 |
hey | +0.531 |
look | +0.527 |
Neg logit contributions | |
relations | -0.507 |
suicide | -0.487 |
ulum | -0.461 |
nton | -0.456 |
grounds | -0.447 |
Token | himself |
Token ID | 2241 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
relations | +0.185 |
suicide | +0.177 |
ulum | +0.169 |
nton | +0.167 |
grounds | +0.163 |
Neg logit contributions | |
mas | -0.222 |
Fall | -0.216 |
seeing | -0.213 |
hey | -0.201 |
look | -0.199 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
mas | +2.139 |
Fall | +2.066 |
seeing | +2.051 |
hey | +1.929 |
look | +1.914 |
Neg logit contributions | |
relations | -1.704 |
suicide | -1.621 |
ulum | -1.584 |
nton | -1.555 |
uctor | -1.501 |
Token | Pokemon |
Token ID | 14878 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
relations | +0.290 |
suicide | +0.280 |
ulum | +0.261 |
nton | +0.259 |
grounds | +0.255 |
Neg logit contributions | |
mas | -0.351 |
Fall | -0.342 |
seeing | -0.338 |
hey | -0.319 |
look | -0.316 |
Token | Go |
Token ID | 1514 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
mas | +4.337 |
Fall | +4.116 |
seeing | +3.986 |
hey | +3.695 |
look | +3.690 |
Neg logit contributions | |
relations | -5.787 |
suicide | -5.522 |
ulum | -5.471 |
nton | -5.358 |
uctor | -5.230 |
Token | in |
Token ID | 287 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
mas | +10.013 |
seeing | +9.379 |
Fall | +9.326 |
look | +8.807 |
hey | +8.687 |
Neg logit contributions | |
relations | -8.927 |
ulum | -8.656 |
suicide | -8.430 |
nton | -8.277 |
uctor | -8.258 |
Token | the |
Token ID | 262 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
mas | +2.835 |
Fall | +2.751 |
seeing | +2.697 |
hey | +2.528 |
look | +2.524 |
Neg logit contributions | |
relations | -2.521 |
suicide | -2.421 |
ulum | -2.404 |
nton | -2.343 |
uctor | -2.266 |
Token | city |
Token ID | 1748 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
mas | +1.897 |
Fall | +1.847 |
seeing | +1.821 |
hey | +1.724 |
look | +1.721 |
Neg logit contributions | |
relations | -1.182 |
suicide | -1.125 |
ulum | -1.086 |
nton | -1.068 |
uctor | -1.023 |
Token | cathedral |
Token ID | 41756 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
relations | +0.265 |
suicide | +0.252 |
ulum | +0.239 |
nton | +0.237 |
grounds | +0.232 |
Neg logit contributions | |
mas | -0.363 |
Fall | -0.354 |
seeing | -0.349 |
hey | -0.330 |
look | -0.328 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
relations | +2.649 |
suicide | +2.521 |
grounds | +2.384 |
ulum | +2.362 |
nton | +2.346 |
Neg logit contributions | |
mas | -3.399 |
Fall | -3.336 |
seeing | -3.288 |
hey | -3.104 |
look | -3.084 |
Token | N |
Token ID | 399 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
relations | +0.935 |
suicide | +0.897 |
ulum | +0.857 |
nton | +0.854 |
grounds | +0.832 |
Neg logit contributions | |
mas | -0.864 |
Fall | -0.837 |
seeing | -0.829 |
hey | -0.768 |
look | -0.760 |
Token | iant |
Token ID | 3014 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
mas | +2.618 |
Fall | +2.565 |
seeing | +2.519 |
hey | +2.418 |
look | +2.404 |
Neg logit contributions | |
relations | -1.236 |
suicide | -1.175 |
ulum | -1.103 |
nton | -1.070 |
grounds | -1.044 |
Token | ic |
Token ID | 291 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
mas | +1.352 |
Fall | +1.309 |
seeing | +1.273 |
hey | +1.201 |
look | +1.196 |
Neg logit contributions | |
relations | -1.412 |
suicide | -1.366 |
ulum | -1.312 |
nton | -1.291 |
grounds | -1.265 |
Token | released |
Token ID | 2716 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
mas | +1.314 |
Fall | +1.276 |
seeing | +1.253 |
hey | +1.177 |
look | +1.169 |
Neg logit contributions | |
relations | -1.265 |
suicide | -1.217 |
ulum | -1.169 |
nton | -1.153 |
grounds | -1.126 |
Token | Pokémon |
Token ID | 9887 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
mas | +3.247 |
Fall | +3.151 |
seeing | +3.088 |
hey | +2.878 |
look | +2.871 |
Neg logit contributions | |
relations | -3.479 |
suicide | -3.349 |
ulum | -3.258 |
nton | -3.219 |
uctor | -3.123 |
Token | Go |
Token ID | 1514 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
mas | +2.980 |
Fall | +2.873 |
seeing | +2.764 |
look | +2.470 |
hey | +2.467 |
Neg logit contributions | |
relations | -5.693 |
suicide | -5.480 |
ulum | -5.430 |
nton | -5.319 |
uctor | -5.231 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
mas | +10.361 |
Fall | +10.091 |
seeing | +9.896 |
hey | +9.131 |
hell | +9.094 |
Neg logit contributions | |
relations | -8.429 |
ulum | -8.236 |
suicide | -7.863 |
EStreamFrame | -7.804 |
nton | -7.737 |
Token | a |
Token ID | 257 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
mas | +3.769 |
Fall | +3.644 |
seeing | +3.607 |
hey | +3.361 |
look | +3.338 |
Neg logit contributions | |
relations | -3.813 |
suicide | -3.668 |
ulum | -3.585 |
nton | -3.515 |
uctor | -3.430 |
Token | smartphone |
Token ID | 11745 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
mas | +1.226 |
Fall | +1.191 |
seeing | +1.173 |
hey | +1.102 |
look | +1.096 |
Neg logit contributions | |
relations | -1.080 |
suicide | -1.036 |
ulum | -0.995 |
nton | -0.982 |
grounds | -0.956 |
Token | game |
Token ID | 983 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
mas | +2.201 |
Fall | +2.144 |
seeing | +2.114 |
hey | +1.985 |
look | +1.979 |
Neg logit contributions | |
relations | -1.696 |
suicide | -1.613 |
ulum | -1.589 |
nton | -1.550 |
uctor | -1.509 |
Token | that |
Token ID | 326 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
mas | +4.605 |
seeing | +4.395 |
Fall | +4.394 |
hey | +4.061 |
look | +4.030 |
Neg logit contributions | |
relations | -4.943 |
suicide | -4.787 |
ulum | -4.766 |
nton | -4.665 |
uctor | -4.595 |
Token | the |
Token ID | 262 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
relations | +0.597 |
suicide | +0.573 |
ulum | +0.536 |
nton | +0.533 |
grounds | +0.522 |
Neg logit contributions | |
mas | -0.784 |
Fall | -0.761 |
seeing | -0.751 |
hey | -0.714 |
look | -0.707 |
Token | struggles |
Token ID | 12766 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
mas | +0.198 |
Fall | +0.193 |
seeing | +0.190 |
hey | +0.180 |
look | +0.178 |
Neg logit contributions | |
relations | -0.155 |
suicide | -0.149 |
ulum | -0.140 |
nton | -0.139 |
grounds | -0.136 |
Token | of |
Token ID | 286 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
mas | +0.991 |
Fall | +0.965 |
seeing | +0.948 |
hey | +0.891 |
look | +0.884 |
Neg logit contributions | |
relations | -0.950 |
suicide | -0.912 |
ulum | -0.865 |
nton | -0.858 |
grounds | -0.842 |
Token | his |
Token ID | 465 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
relations | +0.067 |
suicide | +0.064 |
ulum | +0.061 |
nton | +0.060 |
grounds | +0.058 |
Neg logit contributions | |
mas | -0.094 |
Fall | -0.091 |
seeing | -0.090 |
hey | -0.086 |
look | -0.085 |
Token | son |
Token ID | 3367 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
mas | +2.073 |
Fall | +2.015 |
seeing | +1.983 |
hey | +1.866 |
look | +1.858 |
Neg logit contributions | |
relations | -1.578 |
suicide | -1.512 |
ulum | -1.473 |
nton | -1.445 |
uctor | -1.397 |
Token | Theo |
Token ID | 43999 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
mas | +2.771 |
Fall | +2.676 |
seeing | +2.628 |
hey | +2.471 |
look | +2.455 |
Neg logit contributions | |
relations | -2.541 |
suicide | -2.444 |
ulum | -2.378 |
nton | -2.326 |
grounds | -2.269 |
Token | to |
Token ID | 284 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
mas | +10.500 |
seeing | +9.934 |
Fall | +9.872 |
hey | +9.577 |
hell | +9.367 |
Neg logit contributions | |
relations | -8.068 |
ulum | -7.748 |
suicide | -7.651 |
uctor | -7.512 |
nton | -7.466 |
Token | survive |
Token ID | 7866 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
mas | +0.762 |
Fall | +0.741 |
seeing | +0.730 |
hey | +0.685 |
look | +0.675 |
Neg logit contributions | |
relations | -0.760 |
suicide | -0.734 |
ulum | -0.693 |
nton | -0.686 |
grounds | -0.678 |
Token | induced |
Token ID | 18268 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
relations | +0.223 |
suicide | +0.213 |
ulum | +0.201 |
nton | +0.199 |
grounds | +0.195 |
Neg logit contributions | |
mas | -0.272 |
Fall | -0.265 |
seeing | -0.261 |
hey | -0.246 |
look | -0.245 |
Token | a |
Token ID | 257 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
mas | +0.315 |
Fall | +0.306 |
seeing | +0.301 |
hey | +0.284 |
look | +0.282 |
Neg logit contributions | |
relations | -0.277 |
suicide | -0.266 |
ulum | -0.253 |
nton | -0.250 |
grounds | -0.245 |
Token | case |
Token ID | 1339 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
relations | +1.159 |
suicide | +1.132 |
ulum | +1.029 |
nton | +1.026 |
grounds | +1.017 |
Neg logit contributions | |
mas | -1.481 |
Fall | -1.443 |
seeing | -1.423 |
hey | -1.354 |
look | -1.344 |
Token | in |
Token ID | 287 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
relations | +0.334 |
suicide | +0.319 |
ulum | +0.304 |
nton | +0.300 |
grounds | +0.296 |
Neg logit contributions | |
mas | -0.394 |
Fall | -0.383 |
seeing | -0.378 |
hey | -0.355 |
look | -0.352 |
Token | February |
Token ID | 3945 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
relations | +0.237 |
suicide | +0.227 |
nton | +0.214 |
ulum | +0.214 |
grounds | +0.210 |
Neg logit contributions | |
mas | -0.262 |
Fall | -0.253 |
seeing | -0.250 |
hey | -0.236 |
look | -0.234 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
relations | +4.797 |
suicide | +4.570 |
grounds | +4.360 |
nton | +4.352 |
ulum | +4.333 |
Neg logit contributions | |
mas | -4.073 |
Fall | -4.033 |
seeing | -3.965 |
urrection | -3.621 |
hey | -3.611 |
Token | ( |
Token ID | 357 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
relations | +1.216 |
suicide | +1.167 |
ulum | +1.118 |
nton | +1.115 |
grounds | +1.086 |
Neg logit contributions | |
mas | -1.312 |
Fall | -1.272 |
seeing | -1.256 |
hey | -1.174 |
look | -1.167 |
Token | Steve |
Token ID | 19206 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
relations | +0.083 |
suicide | +0.081 |
ulum | +0.078 |
nton | +0.078 |
grounds | +0.076 |
Neg logit contributions | |
mas | -0.056 |
Fall | -0.054 |
seeing | -0.053 |
hey | -0.048 |
look | -0.048 |
Token | Hel |
Token ID | 5053 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
mas | +0.297 |
Fall | +0.288 |
seeing | +0.286 |
hey | +0.261 |
look | +0.256 |
Neg logit contributions | |
relations | -0.431 |
suicide | -0.416 |
ulum | -0.400 |
nton | -0.399 |
grounds | -0.388 |
Token | ber |
Token ID | 527 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
mas | +6.455 |
mes | +5.459 |
bler | +5.257 |
Fall | +5.159 |
hell | +4.879 |
Neg logit contributions | |
relations | -12.940 |
suicide | -12.690 |
ancest | -12.600 |
grounds | -12.370 |
uctor | -12.306 |
Token | / |
Token ID | 14 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
relations | +1.437 |
suicide | +1.300 |
nton | +1.172 |
ulum | +1.160 |
grounds | +1.120 |
Neg logit contributions | |
mas | -4.810 |
Fall | -4.753 |
seeing | -4.700 |
hey | -4.480 |
hell | -4.454 |
Token | AP |
Token ID | 2969 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
mas | +1.577 |
Fall | +1.516 |
seeing | +1.481 |
hey | +1.370 |
look | +1.357 |
Neg logit contributions | |
relations | -2.294 |
suicide | -2.223 |
ulum | -2.155 |
nton | -2.130 |
grounds | -2.086 |
Token | ) |
Token ID | 8 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
mas | +0.239 |
Fall | +0.233 |
seeing | +0.229 |
hey | +0.216 |
look | +0.215 |
Neg logit contributions | |
relations | -0.195 |
suicide | -0.187 |
ulum | -0.179 |
nton | -0.176 |
grounds | -0.172 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
relations | +1.994 |
suicide | +1.889 |
ulum | +1.794 |
nton | +1.783 |
grounds | +1.718 |
Neg logit contributions | |
mas | -3.076 |
Fall | -2.986 |
seeing | -2.956 |
hey | -2.785 |
look | -2.770 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
mas | +5.345 |
Fall | +5.191 |
seeing | +5.079 |
look | +4.761 |
hey | +4.744 |
Neg logit contributions | |
relations | -4.710 |
suicide | -4.561 |
ulum | -4.417 |
nton | -4.305 |
grounds | -4.186 |
Token | Hulu |
Token ID | 39739 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
mas | +4.298 |
Fall | +4.126 |
seeing | +4.063 |
look | +3.806 |
hey | +3.777 |
Neg logit contributions | |
relations | -5.717 |
suicide | -5.568 |
ulum | -5.484 |
nton | -5.323 |
uctor | -5.226 |
Token | , |
Token ID | 11 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
mas | +11.279 |
Fall | +11.014 |
seeing | +10.821 |
look | +10.084 |
作 | +9.889 |
Neg logit contributions | |
relations | -10.665 |
ulum | -10.554 |
suicide | -10.416 |
nton | -10.071 |
uctor | -9.883 |
Token | and |
Token ID | 290 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
mas | +4.574 |
Fall | +4.411 |
seeing | +4.333 |
look | +4.081 |
hey | +4.045 |
Neg logit contributions | |
relations | -5.334 |
suicide | -5.172 |
ulum | -5.083 |
nton | -4.952 |
uctor | -4.847 |
Token | Amazon |
Token ID | 6186 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
mas | +1.810 |
Fall | +1.750 |
seeing | +1.720 |
hey | +1.606 |
look | +1.599 |
Neg logit contributions | |
relations | -2.009 |
suicide | -1.939 |
ulum | -1.872 |
nton | -1.848 |
grounds | -1.803 |
Token | Prime |
Token ID | 5537 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
mas | +5.912 |
Fall | +5.698 |
seeing | +5.513 |
look | +5.210 |
hey | +5.043 |
Neg logit contributions | |
relations | -7.343 |
ulum | -7.141 |
suicide | -7.090 |
nton | -6.997 |
uctor | -6.790 |
Token | among |
Token ID | 1871 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
mas | +9.297 |
Fall | +9.236 |
seeing | +8.993 |
look | +8.517 |
hey | +8.178 |
Neg logit contributions | |
ulum | -9.106 |
relations | -8.952 |
nton | -8.786 |
suicide | -8.604 |
uctor | -8.338 |
Token | others |
Token ID | 1854 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
mas | +1.355 |
Fall | +1.316 |
seeing | +1.295 |
hey | +1.215 |
look | +1.208 |
Neg logit contributions | |
relations | -1.252 |
suicide | -1.202 |
ulum | -1.154 |
nton | -1.140 |
grounds | -1.110 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
mas | +2.504 |
Fall | +2.431 |
seeing | +2.401 |
hey | +2.268 |
look | +2.251 |
Neg logit contributions | |
relations | -1.954 |
suicide | -1.871 |
ulum | -1.794 |
nton | -1.766 |
grounds | -1.711 |
Token |
|
Token ID | 198 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
relations | +0.065 |
suicide | +0.062 |
ulum | +0.060 |
nton | +0.059 |
grounds | +0.058 |
Neg logit contributions | |
mas | -0.073 |
Fall | -0.071 |
seeing | -0.070 |
hey | -0.066 |
look | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
relations | +0.974 |
suicide | +0.926 |
ulum | +0.880 |
nton | +0.872 |
grounds | +0.846 |
Neg logit contributions | |
mas | -1.537 |
Fall | -1.498 |
seeing | -1.479 |
hey | -1.399 |
look | -1.389 |
Token | further |
Token ID | 2252 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
relations | +2.165 |
suicide | +2.090 |
grounds | +1.912 |
ulum | +1.877 |
nton | +1.877 |
Neg logit contributions | |
mas | -2.459 |
Fall | -2.372 |
seeing | -2.324 |
hey | -2.235 |
look | -2.195 |
Token | bombings |
Token ID | 26579 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
relations | +0.406 |
suicide | +0.388 |
ulum | +0.367 |
nton | +0.362 |
grounds | +0.354 |
Neg logit contributions | |
mas | -0.555 |
Fall | -0.540 |
seeing | -0.532 |
hey | -0.504 |
look | -0.501 |
Token | , |
Token ID | 11 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
mas | +0.509 |
Fall | +0.497 |
seeing | +0.488 |
hey | +0.460 |
look | +0.457 |
Neg logit contributions | |
relations | -0.416 |
suicide | -0.399 |
ulum | -0.377 |
nton | -0.373 |
grounds | -0.367 |
Token | the |
Token ID | 262 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
mas | +1.143 |
Fall | +1.114 |
seeing | +1.098 |
hey | +1.036 |
look | +1.033 |
Neg logit contributions | |
relations | -0.792 |
suicide | -0.753 |
ulum | -0.723 |
nton | -0.712 |
grounds | -0.688 |
Token | 2003 |
Token ID | 5816 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
mas | +1.122 |
Fall | +1.092 |
seeing | +1.077 |
hey | +1.018 |
look | +1.013 |
Neg logit contributions | |
relations | -0.810 |
suicide | -0.774 |
ulum | -0.736 |
nton | -0.726 |
grounds | -0.706 |
Token | invasion |
Token ID | 11796 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
mas | +0.721 |
Fall | +0.701 |
seeing | +0.693 |
hey | +0.657 |
look | +0.652 |
Neg logit contributions | |
relations | -0.505 |
suicide | -0.484 |
ulum | -0.457 |
nton | -0.450 |
grounds | -0.438 |
Token | , |
Token ID | 11 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
mas | +9.672 |
Fall | +9.353 |
seeing | +8.971 |
hell | +8.567 |
look | +8.358 |
Neg logit contributions | |
relations | -8.584 |
nton | -8.439 |
ulum | -8.283 |
uctor | -8.201 |
EStreamFrame | -8.195 |
Token | and |
Token ID | 290 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
mas | +2.223 |
Fall | +2.160 |
seeing | +2.125 |
hey | +1.986 |
look | +1.981 |
Neg logit contributions | |
relations | -2.040 |
suicide | -1.955 |
ulum | -1.893 |
nton | -1.868 |
grounds | -1.814 |
Token | nine |
Token ID | 5193 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
relations | +1.051 |
suicide | +1.013 |
ulum | +0.938 |
nton | +0.930 |
grounds | +0.922 |
Neg logit contributions | |
mas | -1.243 |
Fall | -1.205 |
seeing | -1.184 |
hey | -1.130 |
look | -1.114 |
Token | years |
Token ID | 812 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
relations | +0.763 |
suicide | +0.739 |
ulum | +0.695 |
nton | +0.684 |
grounds | +0.681 |
Neg logit contributions | |
mas | -0.762 |
Fall | -0.738 |
seeing | -0.723 |
hey | -0.684 |
look | -0.678 |
Token | of |
Token ID | 286 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
relations | +0.157 |
suicide | +0.151 |
ulum | +0.143 |
nton | +0.142 |
grounds | +0.140 |
Neg logit contributions | |
mas | -0.147 |
Fall | -0.143 |
seeing | -0.139 |
hey | -0.131 |
look | -0.130 |
Token | as |
Token ID | 355 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
mas | +2.119 |
Fall | +2.061 |
seeing | +2.032 |
hey | +1.915 |
look | +1.904 |
Neg logit contributions | |
relations | -1.689 |
suicide | -1.619 |
ulum | -1.549 |
nton | -1.530 |
grounds | -1.483 |
Token | opposed |
Token ID | 6886 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
mas | +1.016 |
Fall | +0.986 |
seeing | +0.971 |
hey | +0.910 |
look | +0.905 |
Neg logit contributions | |
relations | -0.956 |
suicide | -0.919 |
ulum | -0.880 |
nton | -0.869 |
grounds | -0.850 |
Token | to |
Token ID | 284 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
mas | +1.984 |
Fall | +1.917 |
seeing | +1.890 |
hey | +1.759 |
look | +1.740 |
Neg logit contributions | |
relations | -2.265 |
suicide | -2.181 |
ulum | -2.116 |
nton | -2.083 |
uctor | -2.036 |
Token | the |
Token ID | 262 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
mas | +1.312 |
Fall | +1.274 |
seeing | +1.254 |
hey | +1.176 |
look | +1.170 |
Neg logit contributions | |
relations | -1.218 |
suicide | -1.171 |
ulum | -1.117 |
nton | -1.104 |
grounds | -1.081 |
Token | Google |
Token ID | 3012 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
mas | +1.238 |
Fall | +1.198 |
seeing | +1.179 |
hey | +1.099 |
look | +1.090 |
Neg logit contributions | |
relations | -1.372 |
suicide | -1.324 |
ulum | -1.268 |
nton | -1.254 |
grounds | -1.232 |
Token | Play |
Token ID | 3811 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
mas | +6.116 |
Fall | +6.028 |
seeing | +5.692 |
look | +5.513 |
hey | +5.379 |
Neg logit contributions | |
relations | -6.301 |
nton | -6.137 |
suicide | -6.061 |
ulum | -6.052 |
EStreamFrame | -5.768 |
Token | Store |
Token ID | 9363 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Fall | +9.510 |
mas | +9.398 |
seeing | +8.967 |
look | +8.833 |
hey | +8.403 |
Neg logit contributions | |
ulum | -8.423 |
relations | -8.399 |
nton | -8.395 |
suicide | -8.097 |
uctor | -7.901 |
Token | edition |
Token ID | 8313 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
mas | +3.942 |
Fall | +3.844 |
seeing | +3.769 |
hey | +3.558 |
look | +3.549 |
Neg logit contributions | |
relations | -3.200 |
suicide | -3.075 |
ulum | -3.007 |
nton | -2.989 |
uctor | -2.855 |
Token | which |
Token ID | 543 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
mas | +4.230 |
Fall | +4.124 |
seeing | +4.056 |
hey | +3.795 |
look | +3.794 |
Neg logit contributions | |
relations | -3.611 |
suicide | -3.476 |
ulum | -3.369 |
nton | -3.358 |
uctor | -3.201 |
Token | is |
Token ID | 318 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
relations | +1.526 |
suicide | +1.446 |
ulum | +1.348 |
grounds | +1.336 |
nton | +1.321 |
Neg logit contributions | |
mas | -2.244 |
Fall | -2.187 |
seeing | -2.173 |
hey | -2.043 |
hell | -2.015 |
Token | completely |
Token ID | 3190 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
relations | +3.183 |
suicide | +3.072 |
grounds | +2.833 |
ulum | +2.794 |
nton | +2.786 |
Neg logit contributions | |
mas | -3.802 |
Fall | -3.688 |
seeing | -3.631 |
look | -3.399 |
hey | -3.396 |
Token | the |
Token ID | 262 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
mas | +2.190 |
Fall | +2.109 |
seeing | +2.077 |
hey | +1.971 |
look | +1.962 |
Neg logit contributions | |
relations | -1.988 |
suicide | -1.901 |
ulum | -1.844 |
nton | -1.805 |
uctor | -1.775 |
Token | Anaheim |
Token ID | 31100 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
mas | +0.940 |
Fall | +0.912 |
seeing | +0.898 |
hey | +0.842 |
look | +0.837 |
Neg logit contributions | |
relations | -0.882 |
suicide | -0.848 |
ulum | -0.813 |
nton | -0.803 |
grounds | -0.784 |
Token | Ducks |
Token ID | 27622 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
mas | +1.865 |
Fall | +1.752 |
seeing | +1.709 |
look | +1.593 |
hey | +1.585 |
Neg logit contributions | |
relations | -3.233 |
suicide | -3.125 |
ulum | -3.043 |
nton | -3.000 |
ancest | -2.974 |
Token | . |
Token ID | 13 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
mas | +4.744 |
Fall | +4.571 |
seeing | +4.500 |
hey | +4.298 |
look | +4.291 |
Neg logit contributions | |
relations | -3.949 |
suicide | -3.767 |
ulum | -3.707 |
nton | -3.573 |
uctor | -3.557 |
Token | Justin |
Token ID | 10799 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
mas | +2.296 |
Fall | +2.225 |
seeing | +2.184 |
hey | +2.064 |
look | +2.050 |
Neg logit contributions | |
relations | -2.365 |
suicide | -2.273 |
ulum | -2.203 |
nton | -2.160 |
uctor | -2.125 |
Token | Faul |
Token ID | 44760 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
mas | +2.928 |
Fall | +2.840 |
seeing | +2.770 |
hey | +2.592 |
look | +2.577 |
Neg logit contributions | |
relations | -3.215 |
suicide | -3.105 |
ulum | -2.975 |
nton | -2.955 |
ancest | -2.884 |
Token | k |
Token ID | 74 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
mas | +6.841 |
seeing | +6.137 |
hey | +6.041 |
Fall | +5.991 |
look | +5.652 |
Neg logit contributions | |
relations | -12.144 |
suicide | -11.616 |
magistrate | -11.412 |
ulum | -11.358 |
ancest | -11.329 |
Token | , |
Token ID | 11 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
mas | +2.255 |
Fall | +2.183 |
seeing | +2.154 |
hey | +2.036 |
look | +2.026 |
Neg logit contributions | |
relations | -1.823 |
suicide | -1.746 |
ulum | -1.673 |
nton | -1.645 |
grounds | -1.597 |
Token | one |
Token ID | 530 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
mas | +2.323 |
Fall | +2.256 |
seeing | +2.221 |
hey | +2.088 |
look | +2.076 |
Neg logit contributions | |
relations | -2.072 |
suicide | -1.988 |
ulum | -1.907 |
nton | -1.882 |
grounds | -1.834 |
Token | of |
Token ID | 286 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
relations | +1.093 |
suicide | +1.059 |
ulum | +1.006 |
nton | +0.996 |
grounds | +0.984 |
Neg logit contributions | |
mas | -1.003 |
Fall | -0.973 |
seeing | -0.956 |
hey | -0.888 |
look | -0.883 |
Token | the |
Token ID | 262 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
mas | +0.269 |
Fall | +0.261 |
seeing | +0.257 |
hey | +0.241 |
look | +0.240 |
Neg logit contributions | |
relations | -0.238 |
suicide | -0.229 |
ulum | -0.219 |
nton | -0.216 |
grounds | -0.211 |
Token | media |
Token ID | 2056 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
relations | +1.898 |
suicide | +1.797 |
ulum | +1.650 |
grounds | +1.628 |
nton | +1.611 |
Neg logit contributions | |
mas | -3.392 |
Fall | -3.314 |
seeing | -3.259 |
hey | -3.107 |
look | -3.082 |
Token | platforms |
Token ID | 9554 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
mas | +2.990 |
Fall | +2.889 |
seeing | +2.863 |
look | +2.697 |
hey | +2.695 |
Neg logit contributions | |
relations | -2.139 |
suicide | -2.055 |
ulum | -1.990 |
nton | -1.968 |
uctor | -1.896 |
Token | like |
Token ID | 588 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
mas | +4.016 |
Fall | +3.856 |
seeing | +3.822 |
hey | +3.613 |
look | +3.601 |
Neg logit contributions | |
relations | -3.116 |
suicide | -2.991 |
ulum | -2.923 |
nton | -2.882 |
uctor | -2.793 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
mas | +4.347 |
Fall | +4.146 |
seeing | +4.028 |
look | +3.831 |
hey | +3.766 |
Neg logit contributions | |
relations | -6.067 |
suicide | -5.822 |
ulum | -5.817 |
nton | -5.702 |
uctor | -5.625 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
mas | +3.731 |
Fall | +3.607 |
seeing | +3.568 |
hey | +3.361 |
look | +3.352 |
Neg logit contributions | |
relations | -2.823 |
suicide | -2.721 |
ulum | -2.619 |
nton | -2.585 |
uctor | -2.493 |
Token | Instagram |
Token ID | 10767 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
mas | +3.125 |
Fall | +3.029 |
seeing | +2.980 |
look | +2.794 |
hey | +2.792 |
Neg logit contributions | |
relations | -3.092 |
suicide | -2.969 |
ulum | -2.904 |
nton | -2.862 |
uctor | -2.772 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
mas | +9.697 |
Fall | +9.329 |
seeing | +9.103 |
hey | +8.695 |
look | +8.680 |
Neg logit contributions | |
relations | -8.318 |
suicide | -8.136 |
ulum | -8.003 |
EStreamFrame | -7.767 |
nton | -7.759 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
mas | +2.504 |
Fall | +2.407 |
seeing | +2.357 |
look | +2.192 |
hey | +2.186 |
Neg logit contributions | |
relations | -3.520 |
suicide | -3.392 |
ulum | -3.342 |
nton | -3.275 |
uctor | -3.215 |
Token | , |
Token ID | 11 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
mas | +5.655 |
Fall | +5.472 |
seeing | +5.444 |
hey | +5.151 |
look | +5.133 |
Neg logit contributions | |
relations | -4.049 |
suicide | -3.931 |
ulum | -3.833 |
nton | -3.741 |
uctor | -3.649 |
Token | vital |
Token ID | 9204 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
mas | +1.180 |
Fall | +1.148 |
seeing | +1.131 |
hey | +1.065 |
look | +1.059 |
Neg logit contributions | |
relations | -0.965 |
suicide | -0.925 |
ulum | -0.883 |
nton | -0.871 |
grounds | -0.850 |
Token | sources |
Token ID | 4237 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
mas | +0.162 |
Fall | +0.158 |
seeing | +0.156 |
hey | +0.148 |
look | +0.147 |
Neg logit contributions | |
relations | -0.094 |
suicide | -0.089 |
ulum | -0.085 |
nton | -0.083 |
grounds | -0.080 |
Token | like |
Token ID | 588 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
mas | +2.701 |
Fall | +2.576 |
seeing | +2.518 |
hey | +2.326 |
look | +2.291 |
Neg logit contributions | |
relations | -4.362 |
suicide | -4.232 |
ulum | -4.153 |
nton | -4.107 |
uctor | -4.017 |
Token | trolls |
Token ID | 24727 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
mas | +4.888 |
Fall | +4.776 |
seeing | +4.725 |
hey | +4.475 |
look | +4.425 |
Neg logit contributions | |
relations | -3.335 |
ulum | -3.187 |
suicide | -3.107 |
nton | -3.072 |
uctor | -2.999 |
Token | , |
Token ID | 11 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
mas | +2.516 |
Fall | +2.435 |
seeing | +2.405 |
hey | +2.275 |
look | +2.257 |
Neg logit contributions | |
relations | -1.865 |
suicide | -1.783 |
ulum | -1.708 |
nton | -1.684 |
grounds | -1.632 |
Token | a |
Token ID | 257 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
mas | +2.727 |
Fall | +2.656 |
seeing | +2.618 |
hey | +2.482 |
look | +2.469 |
Neg logit contributions | |
relations | -1.828 |
suicide | -1.726 |
ulum | -1.678 |
nton | -1.645 |
uctor | -1.585 |
Token | Russian |
Token ID | 3394 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
relations | +0.561 |
suicide | +0.543 |
ulum | +0.511 |
nton | +0.508 |
grounds | +0.493 |
Neg logit contributions | |
mas | -0.693 |
Fall | -0.675 |
seeing | -0.664 |
hey | -0.624 |
look | -0.622 |
Token | invasion |
Token ID | 11796 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
relations | +1.112 |
suicide | +1.071 |
nton | +0.986 |
ulum | +0.982 |
grounds | +0.962 |
Neg logit contributions | |
mas | -1.483 |
Fall | -1.442 |
seeing | -1.432 |
hey | -1.348 |
look | -1.341 |
Token | , |
Token ID | 11 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
mas | +9.906 |
Fall | +9.625 |
seeing | +9.249 |
look | +8.838 |
hell | +8.797 |
Neg logit contributions | |
relations | -7.721 |
ulum | -7.550 |
suicide | -7.338 |
nton | -7.294 |
uctor | -7.220 |
Token | lake |
Token ID | 13546 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
mas | +2.593 |
Fall | +2.524 |
seeing | +2.489 |
hey | +2.344 |
look | +2.338 |
Neg logit contributions | |
relations | -1.935 |
suicide | -1.839 |
ulum | -1.794 |
nton | -1.756 |
uctor | -1.699 |
Token | monsters |
Token ID | 10963 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
relations | +0.313 |
suicide | +0.298 |
ulum | +0.285 |
nton | +0.280 |
grounds | +0.271 |
Neg logit contributions | |
mas | -0.456 |
Fall | -0.445 |
seeing | -0.438 |
hey | -0.415 |
look | -0.413 |
Token | , |
Token ID | 11 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
mas | +5.959 |
Fall | +5.746 |
seeing | +5.677 |
hey | +5.383 |
hell | +5.348 |
Neg logit contributions | |
relations | -4.503 |
suicide | -4.310 |
ulum | -4.223 |
nton | -4.132 |
uctor | -4.054 |
Token | and |
Token ID | 290 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
mas | +2.598 |
Fall | +2.529 |
seeing | +2.492 |
hey | +2.350 |
look | +2.342 |
Neg logit contributions | |
relations | -1.958 |
suicide | -1.861 |
ulum | -1.808 |
nton | -1.777 |
grounds | -1.716 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
relations | +1.621 |
suicide | +1.567 |
ulum | +1.490 |
grounds | +1.458 |
nton | +1.452 |
Neg logit contributions | |
mas | -1.731 |
Fall | -1.722 |
seeing | -1.665 |
hey | -1.580 |
look | -1.545 |
Token | the |
Token ID | 262 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
relations | +2.548 |
suicide | +2.403 |
ulum | +2.276 |
grounds | +2.239 |
nton | +2.186 |
Neg logit contributions | |
mas | -3.451 |
Fall | -3.400 |
seeing | -3.319 |
hey | -3.150 |
look | -3.078 |
Token | headquarters |
Token ID | 10043 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
relations | +1.315 |
suicide | +1.247 |
ulum | +1.173 |
grounds | +1.150 |
nton | +1.141 |
Neg logit contributions | |
mas | -1.976 |
Fall | -1.940 |
seeing | -1.902 |
hey | -1.810 |
look | -1.795 |
Token | of |
Token ID | 286 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
relations | +3.832 |
suicide | +3.638 |
ulum | +3.478 |
grounds | +3.476 |
nton | +3.379 |
Neg logit contributions | |
mas | -4.056 |
Fall | -3.962 |
seeing | -3.871 |
hey | -3.680 |
look | -3.611 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
relations | +4.166 |
suicide | +3.836 |
ulum | +3.667 |
grounds | +3.509 |
nton | +3.477 |
Neg logit contributions | |
mas | -6.096 |
Fall | -6.028 |
seeing | -5.872 |
hey | -5.626 |
look | -5.484 |
Token | regional |
Token ID | 7915 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
relations | +2.235 |
suicide | +1.963 |
ulum | +1.761 |
grounds | +1.677 |
nton | +1.613 |
Neg logit contributions | |
mas | -6.665 |
Fall | -6.591 |
seeing | -6.496 |
hey | -6.250 |
look | -6.188 |
Token | government |
Token ID | 1230 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
relations | +4.814 |
suicide | +4.072 |
grounds | +3.554 |
magistrate | +3.424 |
bloc | +3.413 |
Neg logit contributions | |
mas | -16.063 |
Fall | -15.830 |
seeing | -15.689 |
urrection | -15.371 |
ドラ | -15.235 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
relations | +3.813 |
suicide | +3.551 |
grounds | +3.297 |
ulum | +3.275 |
nton | +3.207 |
Neg logit contributions | |
mas | -5.625 |
Fall | -5.596 |
seeing | -5.452 |
hey | -5.197 |
look | -5.139 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
relations | +2.645 |
suicide | +2.509 |
ulum | +2.393 |
nton | +2.350 |
grounds | +2.310 |
Neg logit contributions | |
mas | -3.832 |
Fall | -3.755 |
seeing | -3.688 |
hey | -3.509 |
hell | -3.482 |
Token |
|
Token ID | 198 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
relations | +2.611 |
suicide | +2.437 |
ulum | +2.326 |
nton | +2.317 |
grounds | +2.253 |
Neg logit contributions | |
mas | -4.930 |
Fall | -4.810 |
seeing | -4.740 |
achu | -4.557 |
urrection | -4.529 |
Token | Similar |
Token ID | 18925 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
relations | +2.197 |
suicide | +2.116 |
ulum | +2.069 |
nton | +2.056 |
grounds | +1.995 |
Neg logit contributions | |
mas | -1.601 |
Fall | -1.507 |
seeing | -1.506 |
hey | -1.396 |
hell | -1.374 |
Token | I |
Token ID | 314 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
relations | +0.283 |
suicide | +0.271 |
ulum | +0.258 |
nton | +0.254 |
grounds | +0.250 |
Neg logit contributions | |
mas | -0.323 |
Fall | -0.315 |
seeing | -0.309 |
hey | -0.290 |
look | -0.289 |
Token | � |
Token ID | 447 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
relations | +0.259 |
suicide | +0.249 |
ulum | +0.237 |
nton | +0.235 |
grounds | +0.230 |
Neg logit contributions | |
mas | -0.289 |
Fall | -0.282 |
seeing | -0.278 |
hey | -0.260 |
look | -0.258 |
Token | � |
Token ID | 247 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
mas | +1.088 |
Fall | +1.049 |
seeing | +1.026 |
hey | +0.948 |
look | +0.941 |
Neg logit contributions | |
relations | -1.547 |
suicide | -1.499 |
ulum | -1.447 |
nton | -1.438 |
grounds | -1.402 |
Token | m |
Token ID | 76 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
mas | +2.472 |
Fall | +2.354 |
seeing | +2.330 |
hey | +2.163 |
look | +2.157 |
Neg logit contributions | |
relations | -3.133 |
suicide | -3.036 |
ulum | -2.931 |
nton | -2.893 |
grounds | -2.836 |
Token | a |
Token ID | 257 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
relations | +1.382 |
suicide | +1.325 |
ulum | +1.248 |
nton | +1.233 |
grounds | +1.219 |
Neg logit contributions | |
mas | -1.625 |
Fall | -1.599 |
seeing | -1.556 |
hey | -1.467 |
look | -1.463 |
Token | Christian |
Token ID | 4302 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
relations | +0.777 |
suicide | +0.741 |
ulum | +0.693 |
nton | +0.681 |
grounds | +0.665 |
Neg logit contributions | |
mas | -1.289 |
Fall | -1.267 |
seeing | -1.248 |
hey | -1.179 |
look | -1.178 |
Token | ? |
Token ID | 30 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
relations | +8.729 |
suicide | +8.380 |
grounds | +7.688 |
prayer | +7.685 |
ulum | +7.570 |
Neg logit contributions | |
Fall | -10.622 |
mas | -10.342 |
seeing | -10.263 |
look | -9.770 |
urrection | -9.646 |
Token | � |
Token ID | 447 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
relations | +0.603 |
suicide | +0.578 |
ulum | +0.553 |
nton | +0.545 |
grounds | +0.535 |
Neg logit contributions | |
mas | -0.685 |
Fall | -0.666 |
seeing | -0.656 |
hey | -0.615 |
look | -0.611 |
Token | � |
Token ID | 251 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
relations | +2.074 |
suicide | +2.011 |
ulum | +1.930 |
nton | +1.906 |
grounds | +1.889 |
Neg logit contributions | |
mas | -1.574 |
Fall | -1.516 |
seeing | -1.490 |
hey | -1.374 |
look | -1.365 |
Token |
|
Token ID | 198 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
relations | +2.766 |
suicide | +2.639 |
ulum | +2.500 |
nton | +2.456 |
grounds | +2.374 |
Neg logit contributions | |
mas | -4.623 |
Fall | -4.522 |
seeing | -4.451 |
hey | -4.172 |
look | -4.160 |
Token |
|
Token ID | 198 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
relations | +0.765 |
suicide | +0.728 |
ulum | +0.693 |
nton | +0.685 |
grounds | +0.665 |
Neg logit contributions | |
mas | -1.172 |
Fall | -1.143 |
seeing | -1.128 |
hey | -1.066 |
look | -1.059 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
mas | +0.929 |
Fall | +0.896 |
seeing | +0.882 |
hey | +0.820 |
look | +0.813 |
Neg logit contributions | |
relations | -1.100 |
suicide | -1.062 |
ulum | -1.018 |
nton | -1.012 |
grounds | -0.990 |
Token | . |
Token ID | 13 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
relations | +3.142 |
suicide | +2.975 |
nton | +2.842 |
ulum | +2.783 |
grounds | +2.727 |
Neg logit contributions | |
mas | -4.990 |
Fall | -4.859 |
seeing | -4.804 |
hey | -4.565 |
look | -4.504 |
Token | [ |
Token ID | 685 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
relations | +1.268 |
suicide | +1.230 |
ulum | +1.158 |
nton | +1.144 |
grounds | +1.125 |
Neg logit contributions | |
mas | -1.541 |
Fall | -1.486 |
seeing | -1.470 |
hey | -1.388 |
look | -1.373 |
Token | color |
Token ID | 8043 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
mas | +1.079 |
Fall | +1.043 |
seeing | +1.024 |
hey | +0.953 |
look | +0.947 |
Neg logit contributions | |
relations | -1.255 |
suicide | -1.211 |
ulum | -1.166 |
nton | -1.154 |
grounds | -1.129 |
Token | = |
Token ID | 28 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
relations | +1.171 |
suicide | +1.110 |
ulum | +1.051 |
nton | +1.041 |
grounds | +1.006 |
Neg logit contributions | |
mas | -1.906 |
Fall | -1.855 |
seeing | -1.831 |
hey | -1.739 |
look | -1.729 |
Token | red |
Token ID | 445 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
mas | +2.523 |
Fall | +2.416 |
seeing | +2.356 |
hey | +2.144 |
look | +2.137 |
Neg logit contributions | |
relations | -4.298 |
suicide | -4.136 |
ulum | -4.031 |
nton | -3.962 |
grounds | -3.932 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
relations | +7.034 |
suicide | +6.825 |
ulum | +6.243 |
grounds | +6.198 |
nton | +6.089 |
Neg logit contributions | |
mas | -11.840 |
Fall | -11.577 |
seeing | -11.427 |
hey | -10.964 |
look | -10.855 |
Token | b |
Token ID | 65 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
mas | +2.674 |
Fall | +2.572 |
seeing | +2.522 |
look | +2.321 |
hey | +2.302 |
Neg logit contributions | |
relations | -4.146 |
suicide | -4.013 |
ulum | -3.853 |
nton | -3.826 |
grounds | -3.767 |
Token | ] |
Token ID | 60 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
relations | +3.455 |
suicide | +3.275 |
nton | +3.168 |
ulum | +3.156 |
grounds | +3.046 |
Neg logit contributions | |
mas | -5.897 |
Fall | -5.710 |
seeing | -5.647 |
hey | -5.361 |
look | -5.278 |
Token | U |
Token ID | 52 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
relations | +2.386 |
suicide | +2.340 |
ulum | +2.247 |
nton | +2.246 |
grounds | +2.186 |
Neg logit contributions | |
mas | -1.456 |
seeing | -1.361 |
Fall | -1.334 |
hey | -1.237 |
look | -1.211 |
Token | f |
Token ID | 69 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
mas | +0.492 |
Fall | +0.477 |
seeing | +0.471 |
hey | +0.439 |
look | +0.435 |
Neg logit contributions | |
relations | -0.524 |
suicide | -0.507 |
ulum | -0.486 |
nton | -0.481 |
grounds | -0.470 |
Token | were |
Token ID | 547 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
mas | +0.470 |
Fall | +0.460 |
seeing | +0.452 |
hey | +0.426 |
look | +0.423 |
Neg logit contributions | |
relations | -0.377 |
suicide | -0.360 |
ulum | -0.343 |
nton | -0.339 |
grounds | -0.331 |
Token | elected |
Token ID | 7018 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
relations | +0.506 |
suicide | +0.481 |
ulum | +0.453 |
nton | +0.447 |
grounds | +0.434 |
Neg logit contributions | |
mas | -0.833 |
Fall | -0.815 |
seeing | -0.802 |
hey | -0.761 |
look | -0.757 |
Token | to |
Token ID | 284 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
mas | +4.478 |
Fall | +4.256 |
seeing | +4.215 |
hey | +3.950 |
look | +3.934 |
Neg logit contributions | |
relations | -3.898 |
suicide | -3.764 |
ulum | -3.711 |
nton | -3.653 |
uctor | -3.483 |
Token | local |
Token ID | 1957 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
mas | +1.104 |
Fall | +1.077 |
seeing | +1.062 |
hey | +1.006 |
look | +1.000 |
Neg logit contributions | |
relations | -0.731 |
suicide | -0.696 |
ulum | -0.660 |
nton | -0.651 |
grounds | -0.632 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
relations | +3.817 |
suicide | +3.432 |
grounds | +3.173 |
ulum | +3.084 |
nton | +3.054 |
Neg logit contributions | |
Fall | -7.352 |
mas | -7.329 |
seeing | -7.203 |
hey | -6.877 |
look | -6.763 |
Token | provincial |
Token ID | 15818 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
relations | +3.540 |
suicide | +3.376 |
grounds | +3.075 |
nton | +3.067 |
ulum | +3.015 |
Neg logit contributions | |
mas | -5.476 |
Fall | -5.418 |
seeing | -5.322 |
hey | -5.082 |
look | -5.068 |
Token | people |
Token ID | 661 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
relations | +6.396 |
suicide | +5.527 |
grounds | +5.271 |
magistrate | +5.039 |
oppos | +4.845 |
Neg logit contributions | |
Fall | -12.766 |
mas | -12.537 |
seeing | -12.491 |
hey | -11.862 |
iPhone | -11.835 |
Token | � |
Token ID | 447 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
relations | +1.109 |
suicide | +1.040 |
ulum | +0.974 |
nton | +0.960 |
grounds | +0.929 |
Neg logit contributions | |
mas | -2.131 |
Fall | -2.092 |
seeing | -2.060 |
hey | -1.961 |
look | -1.953 |
Token | � |
Token ID | 247 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
relations | +0.526 |
suicide | +0.508 |
ulum | +0.490 |
nton | +0.485 |
grounds | +0.477 |
Neg logit contributions | |
mas | -0.393 |
Fall | -0.379 |
seeing | -0.372 |
hey | -0.343 |
look | -0.341 |
Token | s |
Token ID | 82 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
mas | +1.140 |
Fall | +1.104 |
seeing | +1.090 |
hey | +1.027 |
look | +1.021 |
Neg logit contributions | |
relations | -0.920 |
suicide | -0.885 |
ulum | -0.845 |
nton | -0.833 |
grounds | -0.810 |
Token | assemblies |
Token ID | 37398 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
mas | +0.614 |
Fall | +0.595 |
seeing | +0.586 |
hey | +0.552 |
look | +0.548 |
Neg logit contributions | |
relations | -0.533 |
suicide | -0.514 |
ulum | -0.491 |
nton | -0.486 |
grounds | -0.472 |
Token | RANT |
Token ID | 32506 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
mas | +1.511 |
Fall | +1.456 |
seeing | +1.433 |
hey | +1.327 |
look | +1.317 |
Neg logit contributions | |
relations | -1.939 |
suicide | -1.872 |
ulum | -1.806 |
nton | -1.785 |
grounds | -1.749 |
Token | food |
Token ID | 2057 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
relations | +4.832 |
suicide | +4.641 |
ulum | +4.311 |
nton | +4.293 |
grounds | +4.275 |
Neg logit contributions | |
mas | -4.839 |
Fall | -4.745 |
seeing | -4.679 |
hey | -4.351 |
look | -4.308 |
Token | from |
Token ID | 422 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
mas | +1.840 |
Fall | +1.784 |
seeing | +1.758 |
hey | +1.654 |
look | +1.646 |
Neg logit contributions | |
relations | -1.617 |
suicide | -1.556 |
ulum | -1.501 |
nton | -1.475 |
grounds | -1.430 |
Token | a |
Token ID | 257 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
mas | +1.328 |
Fall | +1.285 |
seeing | +1.263 |
hey | +1.184 |
look | +1.175 |
Neg logit contributions | |
relations | -1.341 |
suicide | -1.290 |
ulum | -1.241 |
nton | -1.227 |
grounds | -1.196 |
Token | good |
Token ID | 922 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
relations | +1.059 |
suicide | +1.013 |
ulum | +0.957 |
nton | +0.947 |
grounds | +0.924 |
Neg logit contributions | |
mas | -1.395 |
Fall | -1.364 |
seeing | -1.342 |
look | -1.262 |
hey | -1.259 |
Token | Christian |
Token ID | 4302 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
relations | +2.165 |
suicide | +2.035 |
ulum | +1.916 |
nton | +1.896 |
grounds | +1.852 |
Neg logit contributions | |
mas | -3.329 |
Fall | -3.263 |
seeing | -3.207 |
look | -3.023 |
hey | -3.015 |
Token | ! |
Token ID | 0 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
relations | +9.725 |
suicide | +9.166 |
nton | +8.711 |
ulum | +8.668 |
grounds | +8.642 |
Neg logit contributions | |
mas | -8.730 |
Fall | -8.706 |
seeing | -8.451 |
look | -7.844 |
urrection | -7.725 |
Token | � |
Token ID | 447 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
mas | +1.688 |
Fall | +1.639 |
seeing | +1.610 |
hey | +1.515 |
look | +1.504 |
Neg logit contributions | |
relations | -1.594 |
suicide | -1.532 |
ulum | -1.470 |
nton | -1.453 |
grounds | -1.414 |
Token | � |
Token ID | 251 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
relations | +1.722 |
suicide | +1.668 |
ulum | +1.602 |
nton | +1.588 |
grounds | +1.566 |
Neg logit contributions | |
mas | -1.278 |
Fall | -1.229 |
seeing | -1.207 |
hey | -1.114 |
look | -1.104 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
relations | +2.348 |
suicide | +2.242 |
ulum | +2.115 |
nton | +2.108 |
grounds | +2.035 |
Neg logit contributions | |
mas | -3.909 |
Fall | -3.804 |
seeing | -3.765 |
hey | -3.533 |
look | -3.519 |
Token |
|
Token ID | 198 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
relations | +0.478 |
suicide | +0.456 |
ulum | +0.433 |
nton | +0.428 |
grounds | +0.415 |
Neg logit contributions | |
mas | -0.719 |
Fall | -0.701 |
seeing | -0.692 |
hey | -0.654 |
look | -0.650 |
Token | adr |
Token ID | 41909 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
mas | +4.194 |
Fall | +3.888 |
seeing | +3.833 |
hey | +3.550 |
look | +3.422 |
Neg logit contributions | |
relations | -8.514 |
suicide | -8.143 |
ancest | -7.906 |
ulum | -7.768 |
exting | -7.734 |
Token | should |
Token ID | 815 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
relations | +0.516 |
suicide | +0.492 |
ulum | +0.467 |
nton | +0.460 |
grounds | +0.446 |
Neg logit contributions | |
mas | -0.794 |
Fall | -0.775 |
seeing | -0.764 |
hey | -0.724 |
look | -0.720 |
Token | be |
Token ID | 307 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
relations | +1.952 |
suicide | +1.890 |
nton | +1.767 |
ulum | +1.758 |
grounds | +1.742 |
Neg logit contributions | |
mas | -2.029 |
Fall | -1.982 |
seeing | -1.965 |
hey | -1.832 |
look | -1.800 |
Token | transferred |
Token ID | 11172 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
relations | +2.214 |
suicide | +2.145 |
grounds | +1.981 |
ulum | +1.980 |
nton | +1.949 |
Neg logit contributions | |
mas | -2.962 |
Fall | -2.904 |
seeing | -2.842 |
hey | -2.687 |
look | -2.663 |
Token | to |
Token ID | 284 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
relations | +1.498 |
suicide | +1.448 |
ulum | +1.361 |
nton | +1.348 |
grounds | +1.348 |
Neg logit contributions | |
mas | -1.543 |
Fall | -1.495 |
seeing | -1.470 |
hey | -1.381 |
look | -1.367 |
Token | provincial |
Token ID | 15818 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
relations | +0.947 |
suicide | +0.908 |
ulum | +0.851 |
nton | +0.840 |
grounds | +0.828 |
Neg logit contributions | |
mas | -1.320 |
Fall | -1.291 |
seeing | -1.274 |
hey | -1.203 |
look | -1.197 |
Token | jail |
Token ID | 7356 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
relations | +6.394 |
suicide | +6.133 |
grounds | +5.626 |
magistrate | +5.171 |
nton | +5.155 |
Neg logit contributions | |
mas | -12.258 |
Fall | -12.058 |
seeing | -12.043 |
urrection | -11.427 |
hey | -11.257 |
Token | , |
Token ID | 11 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
relations | +3.095 |
suicide | +2.947 |
grounds | +2.772 |
nton | +2.737 |
ulum | +2.733 |
Neg logit contributions | |
mas | -4.231 |
Fall | -4.130 |
seeing | -4.060 |
hey | -3.809 |
look | -3.801 |
Token | court |
Token ID | 2184 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
relations | +2.027 |
suicide | +1.931 |
grounds | +1.773 |
ulum | +1.771 |
nton | +1.764 |
Neg logit contributions | |
mas | -2.855 |
Fall | -2.785 |
seeing | -2.765 |
hey | -2.596 |
look | -2.579 |
Token | rules |
Token ID | 3173 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
relations | +5.383 |
suicide | +4.903 |
grounds | +4.747 |
ulum | +4.406 |
magistrate | +4.361 |
Neg logit contributions | |
mas | -9.363 |
seeing | -9.210 |
Fall | -9.169 |
hey | -8.778 |
urrection | -8.735 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
relations | +2.929 |
suicide | +2.784 |
ulum | +2.627 |
nton | +2.568 |
grounds | +2.566 |
Neg logit contributions | |
mas | -4.814 |
Fall | -4.666 |
seeing | -4.665 |
hey | -4.405 |
look | -4.371 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
mas | +1.064 |
Fall | +1.030 |
seeing | +1.013 |
hey | +0.945 |
look | +0.940 |
Neg logit contributions | |
relations | -1.044 |
suicide | -1.005 |
ulum | -0.962 |
nton | -0.951 |
grounds | -0.929 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
relations | +1.418 |
suicide | +1.370 |
ulum | +1.302 |
nton | +1.298 |
grounds | +1.264 |
Neg logit contributions | |
mas | -1.459 |
Fall | -1.420 |
seeing | -1.404 |
hey | -1.307 |
look | -1.295 |
Token | [ |
Token ID | 685 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
relations | +1.460 |
suicide | +1.425 |
ulum | +1.351 |
nton | +1.350 |
grounds | +1.326 |
Neg logit contributions | |
mas | -1.142 |
Fall | -1.091 |
seeing | -1.080 |
hey | -0.994 |
hell | -0.979 |
Token | color |
Token ID | 8043 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
mas | +0.444 |
Fall | +0.425 |
seeing | +0.418 |
hey | +0.383 |
look | +0.378 |
Neg logit contributions | |
relations | -0.652 |
suicide | -0.634 |
ulum | -0.610 |
nton | -0.607 |
grounds | -0.594 |
Token | = |
Token ID | 28 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
relations | +3.447 |
suicide | +3.345 |
nton | +3.031 |
ulum | +3.029 |
grounds | +3.007 |
Neg logit contributions | |
mas | -4.248 |
Fall | -4.146 |
seeing | -4.037 |
hey | -3.841 |
hell | -3.794 |
Token | red |
Token ID | 445 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
mas | +1.925 |
Fall | +1.861 |
seeing | +1.819 |
hey | +1.680 |
look | +1.671 |
Neg logit contributions | |
relations | -2.622 |
suicide | -2.528 |
ulum | -2.447 |
nton | -2.419 |
grounds | -2.376 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
relations | +8.131 |
suicide | +8.044 |
grounds | +7.348 |
ulum | +7.283 |
nton | +7.160 |
Neg logit contributions | |
mas | -9.806 |
seeing | -9.544 |
Fall | -9.511 |
hey | -8.973 |
作 | -8.786 |
Token | b |
Token ID | 65 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
mas | +2.440 |
Fall | +2.351 |
seeing | +2.304 |
hey | +2.137 |
look | +2.136 |
Neg logit contributions | |
relations | -3.143 |
suicide | -3.026 |
ulum | -2.918 |
nton | -2.880 |
grounds | -2.834 |
Token | ] |
Token ID | 60 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
relations | +3.988 |
suicide | +3.909 |
nton | +3.783 |
ulum | +3.734 |
grounds | +3.588 |
Neg logit contributions | |
mas | -4.677 |
Fall | -4.548 |
seeing | -4.537 |
hey | -4.276 |
hell | -4.181 |
Token | B |
Token ID | 33 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
relations | +3.542 |
suicide | +3.478 |
ulum | +3.333 |
nton | +3.324 |
grounds | +3.234 |
Neg logit contributions | |
mas | -2.234 |
Fall | -2.081 |
seeing | -2.073 |
hey | -1.874 |
hell | -1.836 |
Token | ionic |
Token ID | 26523 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
suicide | +7.530 |
relations | +7.485 |
ulum | +7.213 |
nton | +7.192 |
ribe | +6.956 |
Neg logit contributions | |
mas | -6.696 |
Fall | -6.520 |
seeing | -6.512 |
作 | -6.053 |
hey | -5.979 |
Token | a |
Token ID | 257 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
relations | +0.260 |
suicide | +0.249 |
ulum | +0.236 |
nton | +0.232 |
grounds | +0.230 |
Neg logit contributions | |
mas | -0.326 |
Fall | -0.319 |
seeing | -0.313 |
hey | -0.296 |
look | -0.292 |
Token | European |
Token ID | 3427 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
relations | +2.223 |
suicide | +2.161 |
ulum | +1.973 |
grounds | +1.969 |
nton | +1.912 |
Neg logit contributions | |
mas | -2.920 |
Fall | -2.863 |
seeing | -2.798 |
hey | -2.674 |
look | -2.635 |
Token | , |
Token ID | 11 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
relations | +1.802 |
suicide | +1.719 |
ulum | +1.546 |
grounds | +1.531 |
nton | +1.491 |
Neg logit contributions | |
mas | -3.852 |
Fall | -3.770 |
seeing | -3.736 |
hey | -3.555 |
look | -3.516 |
Token | national |
Token ID | 2260 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
relations | +0.069 |
suicide | +0.066 |
ulum | +0.063 |
nton | +0.062 |
grounds | +0.061 |
Neg logit contributions | |
mas | -0.086 |
Fall | -0.083 |
seeing | -0.082 |
hey | -0.077 |
look | -0.077 |
Token | or |
Token ID | 393 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
relations | +4.274 |
suicide | +4.106 |
grounds | +3.802 |
ulum | +3.607 |
nton | +3.485 |
Neg logit contributions | |
mas | -7.417 |
Fall | -7.350 |
seeing | -7.210 |
hey | -6.884 |
urrection | -6.806 |
Token | regional |
Token ID | 7915 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
mas | +0.016 |
Fall | +0.015 |
seeing | +0.015 |
hey | +0.014 |
look | +0.014 |
Neg logit contributions | |
relations | -0.012 |
suicide | -0.011 |
ulum | -0.011 |
nton | -0.010 |
grounds | -0.010 |
Token | level |
Token ID | 1241 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
relations | +4.732 |
suicide | +4.685 |
grounds | +4.341 |
bloc | +3.555 |
magistrate | +3.476 |
Neg logit contributions | |
mas | -13.700 |
Fall | -13.605 |
seeing | -13.371 |
urrection | -12.965 |
hey | -12.904 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
relations | +1.863 |
suicide | +1.756 |
ulum | +1.646 |
nton | +1.627 |
grounds | +1.626 |
Neg logit contributions | |
mas | -2.788 |
Fall | -2.740 |
seeing | -2.689 |
hey | -2.549 |
look | -2.530 |
Token | Public |
Token ID | 5094 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
relations | +0.327 |
suicide | +0.312 |
ulum | +0.299 |
nton | +0.296 |
grounds | +0.292 |
Neg logit contributions | |
mas | -0.322 |
Fall | -0.312 |
seeing | -0.308 |
hey | -0.288 |
look | -0.285 |
Token | debate |
Token ID | 4384 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
relations | +3.143 |
suicide | +2.872 |
grounds | +2.568 |
nton | +2.562 |
ulum | +2.561 |
Neg logit contributions | |
mas | -5.558 |
Fall | -5.478 |
seeing | -5.341 |
hey | -5.113 |
look | -5.064 |
Token | is |
Token ID | 318 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
relations | +0.990 |
suicide | +0.939 |
ulum | +0.893 |
nton | +0.877 |
grounds | +0.864 |
Neg logit contributions | |
mas | -1.368 |
Fall | -1.342 |
seeing | -1.319 |
hey | -1.251 |
look | -1.235 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
mas | +1.083 |
Fall | +1.045 |
seeing | +1.028 |
hey | +0.954 |
look | +0.947 |
Neg logit contributions | |
relations | -1.326 |
suicide | -1.282 |
ulum | -1.233 |
nton | -1.223 |
grounds | -1.197 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
relations | +1.472 |
suicide | +1.398 |
ulum | +1.336 |
nton | +1.333 |
grounds | +1.289 |
Neg logit contributions | |
mas | -2.140 |
Fall | -2.082 |
seeing | -2.055 |
hey | -1.942 |
look | -1.928 |
Token | [ |
Token ID | 685 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
relations | +0.758 |
suicide | +0.731 |
ulum | +0.692 |
nton | +0.681 |
grounds | +0.668 |
Neg logit contributions | |
mas | -0.942 |
Fall | -0.912 |
seeing | -0.902 |
hey | -0.851 |
look | -0.843 |
Token | color |
Token ID | 8043 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
mas | +1.598 |
Fall | +1.543 |
seeing | +1.518 |
hey | +1.406 |
look | +1.405 |
Neg logit contributions | |
relations | -1.920 |
suicide | -1.855 |
ulum | -1.782 |
nton | -1.762 |
grounds | -1.727 |
Token | = |
Token ID | 28 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
relations | +0.460 |
suicide | +0.438 |
ulum | +0.415 |
nton | +0.410 |
grounds | +0.397 |
Neg logit contributions | |
mas | -0.721 |
Fall | -0.702 |
seeing | -0.693 |
hey | -0.657 |
look | -0.654 |
Token | red |
Token ID | 445 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
mas | +2.645 |
Fall | +2.535 |
seeing | +2.465 |
look | +2.231 |
hey | +2.226 |
Neg logit contributions | |
relations | -4.732 |
suicide | -4.555 |
ulum | -4.434 |
nton | -4.361 |
ancest | -4.342 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
relations | +6.639 |
suicide | +6.423 |
ulum | +5.902 |
grounds | +5.801 |
nton | +5.744 |
Neg logit contributions | |
mas | -11.287 |
Fall | -11.018 |
seeing | -10.868 |
hey | -10.389 |
look | -10.355 |
Token | b |
Token ID | 65 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
mas | +2.784 |
Fall | +2.670 |
seeing | +2.643 |
look | +2.431 |
hey | +2.402 |
Neg logit contributions | |
relations | -4.463 |
suicide | -4.331 |
ulum | -4.144 |
nton | -4.098 |
grounds | -4.062 |
Token | ] |
Token ID | 60 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
relations | +3.036 |
suicide | +2.886 |
ulum | +2.797 |
nton | +2.793 |
grounds | +2.685 |
Neg logit contributions | |
mas | -5.159 |
Fall | -5.005 |
seeing | -4.951 |
hey | -4.691 |
look | -4.623 |
Token | Mega |
Token ID | 43471 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
relations | +1.829 |
suicide | +1.783 |
ulum | +1.730 |
nton | +1.716 |
grounds | +1.669 |
Neg logit contributions | |
mas | -1.153 |
seeing | -1.083 |
Fall | -1.064 |
hey | -0.983 |
look | -0.974 |
Token | Pony |
Token ID | 30377 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
mas | +2.927 |
Fall | +2.827 |
seeing | +2.700 |
hey | +2.537 |
look | +2.506 |
Neg logit contributions | |
relations | -4.692 |
suicide | -4.508 |
ulum | -4.388 |
nton | -4.357 |
uctor | -4.303 |
Token | of |
Token ID | 286 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
mas | +2.759 |
Fall | +2.658 |
seeing | +2.617 |
hey | +2.426 |
look | +2.413 |
Neg logit contributions | |
relations | -3.148 |
suicide | -3.050 |
ulum | -2.948 |
nton | -2.936 |
grounds | -2.845 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
relations | +0.159 |
suicide | +0.153 |
ulum | +0.144 |
nton | +0.142 |
grounds | +0.140 |
Neg logit contributions | |
mas | -0.183 |
Fall | -0.180 |
seeing | -0.176 |
hey | -0.166 |
look | -0.165 |
Token | being |
Token ID | 852 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
relations | +0.304 |
suicide | +0.293 |
ulum | +0.277 |
nton | +0.273 |
grounds | +0.270 |
Neg logit contributions | |
mas | -0.314 |
Fall | -0.307 |
seeing | -0.302 |
hey | -0.283 |
look | -0.280 |
Token | a |
Token ID | 257 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
relations | +1.755 |
suicide | +1.672 |
ulum | +1.581 |
nton | +1.542 |
grounds | +1.534 |
Neg logit contributions | |
mas | -2.035 |
Fall | -2.017 |
seeing | -1.979 |
hey | -1.848 |
look | -1.844 |
Token | more |
Token ID | 517 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
relations | +1.928 |
suicide | +1.845 |
ulum | +1.730 |
nton | +1.695 |
grounds | +1.664 |
Neg logit contributions | |
mas | -2.609 |
Fall | -2.596 |
seeing | -2.547 |
hey | -2.387 |
look | -2.383 |
Token | mature |
Token ID | 15345 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
relations | +0.238 |
suicide | +0.226 |
ulum | +0.214 |
nton | +0.209 |
grounds | +0.206 |
Neg logit contributions | |
mas | -0.344 |
Fall | -0.340 |
seeing | -0.334 |
hey | -0.316 |
look | -0.314 |
Token | lover |
Token ID | 18854 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
relations | +7.023 |
suicide | +6.428 |
grounds | +5.836 |
ulum | +5.740 |
ancest | +5.599 |
Neg logit contributions | |
Fall | -10.971 |
mas | -10.800 |
seeing | -10.717 |
urrection | -10.361 |
作 | -10.296 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
mas | +1.237 |
Fall | +1.203 |
seeing | +1.184 |
hey | +1.116 |
look | +1.110 |
Neg logit contributions | |
relations | -1.012 |
suicide | -0.970 |
ulum | -0.926 |
nton | -0.915 |
grounds | -0.891 |
Token | I |
Token ID | 314 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
mas | +0.381 |
Fall | +0.370 |
seeing | +0.364 |
hey | +0.340 |
look | +0.337 |
Neg logit contributions | |
relations | -0.392 |
suicide | -0.378 |
ulum | -0.362 |
nton | -0.358 |
grounds | -0.351 |
Token | know |
Token ID | 760 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
mas | +0.971 |
Fall | +0.942 |
seeing | +0.926 |
hey | +0.869 |
look | +0.864 |
Neg logit contributions | |
relations | -0.932 |
suicide | -0.896 |
ulum | -0.860 |
nton | -0.849 |
grounds | -0.829 |
Token | this |
Token ID | 428 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
mas | +3.098 |
Fall | +2.991 |
seeing | +2.958 |
hey | +2.760 |
look | +2.750 |
Neg logit contributions | |
relations | -3.056 |
suicide | -2.947 |
ulum | -2.883 |
nton | -2.852 |
uctor | -2.763 |
Token | slander |
Token ID | 47397 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
mas | +0.405 |
Fall | +0.394 |
seeing | +0.388 |
hey | +0.365 |
look | +0.363 |
Neg logit contributions | |
relations | -0.337 |
suicide | -0.323 |
ulum | -0.310 |
nton | -0.306 |
grounds | -0.297 |
Token | . |
Token ID | 13 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
mas | +0.042 |
Fall | +0.041 |
seeing | +0.040 |
hey | +0.038 |
look | +0.038 |
Neg logit contributions | |
relations | -0.031 |
suicide | -0.029 |
ulum | -0.028 |
nton | -0.028 |
grounds | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
relations | +0.195 |
suicide | +0.188 |
ulum | +0.180 |
nton | +0.178 |
grounds | +0.174 |
Neg logit contributions | |
mas | -0.197 |
Fall | -0.191 |
seeing | -0.188 |
hey | -0.175 |
look | -0.174 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
relations | +0.521 |
suicide | +0.496 |
ulum | +0.472 |
nton | +0.466 |
grounds | +0.452 |
Neg logit contributions | |
mas | -0.777 |
Fall | -0.757 |
seeing | -0.747 |
hey | -0.707 |
look | -0.702 |
Token | C |
Token ID | 34 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
mas | +0.503 |
Fall | +0.483 |
seeing | +0.473 |
hey | +0.435 |
look | +0.431 |
Neg logit contributions | |
relations | -0.752 |
suicide | -0.728 |
ulum | -0.704 |
nton | -0.698 |
grounds | -0.684 |
Token | red |
Token ID | 445 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
relations | +4.478 |
suicide | +4.325 |
ulum | +4.289 |
nton | +4.151 |
grounds | +4.032 |
Neg logit contributions | |
mas | -4.565 |
Fall | -4.431 |
seeing | -4.402 |
作 | -4.054 |
look | -4.031 |
Token | ential |
Token ID | 1843 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
relations | +8.017 |
ulum | +7.737 |
suicide | +7.498 |
nton | +7.363 |
uctor | +7.203 |
Neg logit contributions | |
mas | -9.182 |
seeing | -9.107 |
Fall | -9.103 |
look | -8.407 |
ドラ | -8.271 |
Token | ed |
Token ID | 276 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
relations | +2.393 |
suicide | +2.282 |
ulum | +2.119 |
nton | +2.093 |
grounds | +2.086 |
Neg logit contributions | |
mas | -3.345 |
Fall | -3.251 |
seeing | -3.199 |
hey | -3.030 |
look | -3.009 |
Token | media |
Token ID | 2056 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
relations | +5.123 |
suicide | +4.894 |
grounds | +4.555 |
nton | +4.525 |
ulum | +4.491 |
Neg logit contributions | |
mas | -5.858 |
Fall | -5.807 |
seeing | -5.682 |
hey | -5.278 |
achu | -5.254 |
Token | have |
Token ID | 423 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
relations | +1.386 |
suicide | +1.301 |
ulum | +1.217 |
nton | +1.209 |
grounds | +1.189 |
Neg logit contributions | |
mas | -1.910 |
Fall | -1.873 |
seeing | -1.839 |
hey | -1.741 |
look | -1.722 |
Token | a |
Token ID | 257 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
relations | +1.764 |
suicide | +1.675 |
ulum | +1.579 |
nton | +1.572 |
grounds | +1.562 |
Neg logit contributions | |
mas | -2.051 |
Fall | -1.996 |
seeing | -1.963 |
hey | -1.837 |
look | -1.821 |
Token | out |
Token ID | 503 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
mas | +4.197 |
Fall | +4.042 |
seeing | +4.000 |
hey | +3.785 |
look | +3.744 |
Neg logit contributions | |
relations | -3.776 |
suicide | -3.622 |
ulum | -3.500 |
nton | -3.464 |
uctor | -3.345 |
Token | of |
Token ID | 286 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
mas | +1.938 |
Fall | +1.884 |
seeing | +1.854 |
hey | +1.746 |
look | +1.733 |
Neg logit contributions | |
relations | -1.616 |
suicide | -1.551 |
ulum | -1.476 |
nton | -1.455 |
grounds | -1.423 |
Token | mid |
Token ID | 3095 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
mas | +1.051 |
Fall | +1.021 |
seeing | +1.005 |
hey | +0.946 |
look | +0.941 |
Neg logit contributions | |
relations | -0.893 |
suicide | -0.856 |
ulum | -0.820 |
nton | -0.810 |
grounds | -0.788 |
Token | as |
Token ID | 292 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
relations | +4.319 |
suicide | +4.141 |
ulum | +3.867 |
grounds | +3.834 |
nton | +3.776 |
Neg logit contributions | |
mas | -4.837 |
Fall | -4.767 |
seeing | -4.668 |
hey | -4.359 |
achu | -4.310 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
relations | +0.178 |
suicide | +0.170 |
ulum | +0.162 |
nton | +0.160 |
grounds | +0.156 |
Neg logit contributions | |
mas | -0.222 |
Fall | -0.217 |
seeing | -0.214 |
hey | -0.201 |
look | -0.200 |
Token | brown |
Token ID | 7586 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
relations | +2.587 |
suicide | +2.517 |
ulum | +2.325 |
grounds | +2.301 |
nton | +2.289 |
Neg logit contributions | |
mas | -2.997 |
Fall | -2.934 |
seeing | -2.896 |
hey | -2.679 |
look | -2.661 |
Token | boots |
Token ID | 14412 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
relations | +9.142 |
suicide | +8.972 |
grounds | +8.363 |
ulum | +8.322 |
iate | +8.156 |
Neg logit contributions | |
Fall | -8.191 |
mas | -7.835 |
seeing | -7.811 |
作 | -7.540 |
ドラ | -7.273 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
mas | +1.958 |
Fall | +1.901 |
seeing | +1.872 |
hey | +1.768 |
look | +1.758 |
Neg logit contributions | |
relations | -1.625 |
suicide | -1.557 |
ulum | -1.494 |
nton | -1.475 |
grounds | -1.429 |
Token | Even |
Token ID | 3412 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
mas | +0.362 |
Fall | +0.350 |
seeing | +0.344 |
hey | +0.321 |
look | +0.318 |
Neg logit contributions | |
relations | -0.384 |
suicide | -0.371 |
ulum | -0.355 |
nton | -0.352 |
grounds | -0.345 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
mas | +4.777 |
Fall | +4.653 |
seeing | +4.608 |
hey | +4.333 |
look | +4.327 |
Neg logit contributions | |
relations | -4.236 |
suicide | -4.020 |
ulum | -3.986 |
nton | -3.938 |
uctor | -3.814 |
Token | it |
Token ID | 340 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
mas | +0.623 |
Fall | +0.605 |
seeing | +0.594 |
hey | +0.556 |
look | +0.552 |
Neg logit contributions | |
relations | -0.627 |
suicide | -0.604 |
ulum | -0.578 |
nton | -0.571 |
grounds | -0.559 |
Token | And |
Token ID | 1870 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
relations | +1.854 |
suicide | +1.794 |
ulum | +1.749 |
nton | +1.735 |
grounds | +1.685 |
Neg logit contributions | |
mas | -1.251 |
Fall | -1.193 |
seeing | -1.174 |
look | -1.055 |
hey | -1.055 |
Token | you |
Token ID | 345 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
relations | +1.498 |
suicide | +1.439 |
ulum | +1.365 |
nton | +1.348 |
grounds | +1.329 |
Neg logit contributions | |
mas | -1.606 |
Fall | -1.575 |
seeing | -1.537 |
hey | -1.433 |
look | -1.431 |
Token | , |
Token ID | 11 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
mas | +0.667 |
Fall | +0.649 |
seeing | +0.637 |
hey | +0.596 |
look | +0.592 |
Neg logit contributions | |
relations | -0.665 |
suicide | -0.640 |
ulum | -0.613 |
nton | -0.606 |
grounds | -0.593 |
Token | a |
Token ID | 257 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
mas | +1.805 |
Fall | +1.751 |
seeing | +1.722 |
hey | +1.613 |
look | +1.603 |
Neg logit contributions | |
relations | -1.772 |
suicide | -1.705 |
ulum | -1.636 |
nton | -1.618 |
grounds | -1.579 |
Token | claimed |
Token ID | 4752 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
relations | +1.389 |
suicide | +1.333 |
ulum | +1.251 |
nton | +1.235 |
grounds | +1.201 |
Neg logit contributions | |
mas | -2.009 |
Fall | -1.976 |
seeing | -1.941 |
look | -1.828 |
hey | -1.826 |
Token | Christian |
Token ID | 4302 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
relations | +0.755 |
suicide | +0.722 |
ulum | +0.679 |
nton | +0.670 |
grounds | +0.656 |
Neg logit contributions | |
mas | -1.094 |
Fall | -1.068 |
seeing | -1.054 |
hey | -0.994 |
look | -0.991 |
Token | , |
Token ID | 11 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
relations | +7.720 |
suicide | +7.418 |
grounds | +6.877 |
ulum | +6.751 |
nton | +6.739 |
Neg logit contributions | |
Fall | -9.505 |
mas | -9.484 |
seeing | -9.324 |
look | -8.846 |
hey | -8.627 |
Token | hired |
Token ID | 9657 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
relations | +1.385 |
suicide | +1.328 |
ulum | +1.254 |
nton | +1.244 |
grounds | +1.225 |
Neg logit contributions | |
mas | -1.551 |
Fall | -1.527 |
seeing | -1.493 |
hey | -1.390 |
look | -1.387 |
Token | this |
Token ID | 428 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
mas | +0.645 |
Fall | +0.627 |
seeing | +0.617 |
hey | +0.576 |
look | +0.573 |
Neg logit contributions | |
relations | -0.638 |
suicide | -0.615 |
ulum | -0.588 |
nton | -0.581 |
grounds | -0.569 |
Token | sod |
Token ID | 32581 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
relations | +0.343 |
suicide | +0.328 |
ulum | +0.309 |
nton | +0.305 |
grounds | +0.298 |
Neg logit contributions | |
mas | -0.488 |
Fall | -0.477 |
seeing | -0.471 |
hey | -0.443 |
look | -0.442 |
Token | om |
Token ID | 296 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
relations | +0.084 |
suicide | +0.081 |
ulum | +0.077 |
nton | +0.076 |
grounds | +0.074 |
Neg logit contributions | |
mas | -0.094 |
Fall | -0.092 |
seeing | -0.091 |
hey | -0.085 |
look | -0.084 |
Token | f |
Token ID | 69 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
relations | +3.184 |
suicide | +3.091 |
ulum | +3.002 |
nton | +2.997 |
uctor | +2.877 |
Neg logit contributions | |
mas | -2.354 |
Fall | -2.280 |
seeing | -2.273 |
hey | -2.045 |
look | -2.040 |
Token | lynn |
Token ID | 12935 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
mas | +0.691 |
Fall | +0.662 |
seeing | +0.650 |
hey | +0.598 |
look | +0.592 |
Neg logit contributions | |
relations | -1.086 |
suicide | -1.053 |
ulum | -1.017 |
nton | -1.006 |
grounds | -0.990 |
Token | JR |
Token ID | 44817 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
relations | +2.906 |
suicide | +2.777 |
ulum | +2.661 |
nton | +2.645 |
grounds | +2.584 |
Neg logit contributions | |
mas | -2.512 |
Fall | -2.444 |
seeing | -2.436 |
hey | -2.214 |
look | -2.201 |
Token | Great |
Token ID | 3878 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
relations | +3.516 |
suicide | +3.377 |
ulum | +3.189 |
nton | +3.186 |
grounds | +3.100 |
Neg logit contributions | |
mas | -3.519 |
Fall | -3.448 |
seeing | -3.402 |
hey | -3.129 |
作 | -3.122 |
Token | day |
Token ID | 1110 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
relations | +0.817 |
suicide | +0.777 |
ulum | +0.739 |
nton | +0.728 |
grounds | +0.717 |
Neg logit contributions | |
mas | -0.935 |
Fall | -0.908 |
seeing | -0.893 |
hey | -0.845 |
look | -0.832 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
relations | +0.636 |
suicide | +0.610 |
ulum | +0.585 |
nton | +0.578 |
grounds | +0.567 |
Neg logit contributions | |
mas | -0.615 |
Fall | -0.600 |
seeing | -0.585 |
hey | -0.550 |
look | -0.547 |
Token | announce |
Token ID | 5453 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
relations | +9.253 |
suicide | +8.840 |
ulum | +8.435 |
nton | +8.381 |
grounds | +8.233 |
Neg logit contributions | |
Fall | -7.672 |
mas | -7.656 |
seeing | -7.293 |
作 | -7.214 |
urrection | -6.786 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
relations | +2.000 |
suicide | +1.932 |
ulum | +1.837 |
nton | +1.808 |
grounds | +1.765 |
Neg logit contributions | |
mas | -2.160 |
Fall | -2.125 |
seeing | -2.080 |
hey | -1.955 |
作 | -1.944 |
Token | the |
Token ID | 262 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
relations | +6.995 |
suicide | +6.658 |
nton | +6.256 |
ulum | +6.226 |
grounds | +6.166 |
Neg logit contributions | |
mas | -6.619 |
Fall | -6.578 |
seeing | -6.403 |
作 | -6.210 |
urrection | -5.957 |
Token | social |
Token ID | 1919 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
relations | +1.373 |
suicide | +1.319 |
ulum | +1.245 |
nton | +1.231 |
grounds | +1.215 |
Neg logit contributions | |
mas | -1.545 |
Fall | -1.507 |
seeing | -1.490 |
hey | -1.397 |
look | -1.377 |
Token | media |
Token ID | 2056 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
relations | +2.227 |
suicide | +2.130 |
ulum | +1.922 |
grounds | +1.916 |
nton | +1.860 |
Neg logit contributions | |
mas | -3.541 |
Fall | -3.454 |
seeing | -3.422 |
hey | -3.225 |
look | -3.206 |
Token | , |
Token ID | 11 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
relations | +2.981 |
suicide | +2.812 |
grounds | +2.605 |
nton | +2.566 |
ulum | +2.553 |
Neg logit contributions | |
mas | -3.590 |
Fall | -3.519 |
seeing | -3.448 |
hey | -3.254 |
look | -3.203 |
Token | drinking |
Token ID | 7722 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
relations | +0.705 |
suicide | +0.674 |
ulum | +0.614 |
nton | +0.610 |
grounds | +0.607 |
Neg logit contributions | |
mas | -1.079 |
Fall | -1.051 |
seeing | -1.037 |
hey | -0.985 |
look | -0.975 |
Token | in |
Token ID | 287 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
relations | +3.267 |
suicide | +3.085 |
grounds | +2.897 |
ulum | +2.816 |
nton | +2.775 |
Neg logit contributions | |
mas | -3.840 |
seeing | -3.704 |
Fall | -3.702 |
hey | -3.499 |
look | -3.451 |
Token | public |
Token ID | 1171 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
relations | +0.658 |
suicide | +0.622 |
ulum | +0.575 |
nton | +0.571 |
grounds | +0.565 |
Neg logit contributions | |
mas | -1.051 |
Fall | -1.025 |
seeing | -1.018 |
hey | -0.958 |
hell | -0.951 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
relations | +3.442 |
suicide | +3.191 |
grounds | +3.062 |
ulum | +2.934 |
nton | +2.927 |
Neg logit contributions | |
mas | -4.227 |
Fall | -4.168 |
seeing | -4.048 |
hey | -3.827 |
look | -3.811 |
Token | minor |
Token ID | 4159 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
relations | +2.755 |
suicide | +2.626 |
grounds | +2.400 |
ulum | +2.356 |
nton | +2.333 |
Neg logit contributions | |
mas | -3.851 |
Fall | -3.739 |
seeing | -3.674 |
hey | -3.500 |
hell | -3.467 |
Token | offences |
Token ID | 20819 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
relations | +7.055 |
suicide | +6.579 |
grounds | +6.216 |
nton | +5.738 |
prayer | +5.570 |
Neg logit contributions | |
mas | -11.034 |
Fall | -10.621 |
seeing | -10.491 |
hell | -10.226 |
hey | -10.127 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
mas | +0.044 |
Fall | +0.043 |
seeing | +0.042 |
hey | +0.040 |
look | +0.039 |
Neg logit contributions | |
relations | -0.038 |
suicide | -0.036 |
ulum | -0.034 |
nton | -0.034 |
grounds | -0.033 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
relations | +0.893 |
suicide | +0.855 |
ulum | +0.813 |
nton | +0.805 |
grounds | +0.784 |
Neg logit contributions | |
mas | -1.109 |
Fall | -1.079 |
seeing | -1.067 |
hey | -1.005 |
look | -0.996 |
Token | Hey |
Token ID | 10814 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
mas | +1.063 |
Fall | +1.020 |
seeing | +1.001 |
hey | +0.919 |
look | +0.912 |
Neg logit contributions | |
relations | -1.596 |
suicide | -1.546 |
ulum | -1.496 |
nton | -1.483 |
grounds | -1.452 |
Token | Ship |
Token ID | 16656 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
mas | +4.864 |
Fall | +4.706 |
seeing | +4.621 |
hey | +4.432 |
look | +4.354 |
Neg logit contributions | |
relations | -4.653 |
suicide | -4.487 |
nton | -4.349 |
ulum | -4.296 |
uctor | -4.180 |
Token | every |
Token ID | 790 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
relations | +0.197 |
suicide | +0.189 |
ulum | +0.180 |
nton | +0.178 |
grounds | +0.174 |
Neg logit contributions | |
mas | -0.237 |
Fall | -0.231 |
seeing | -0.228 |
hey | -0.214 |
look | -0.213 |
Token | American |
Token ID | 1605 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
mas | +5.866 |
Fall | +5.771 |
seeing | +5.584 |
hey | +5.363 |
look | +5.332 |
Neg logit contributions | |
relations | -4.161 |
suicide | -3.927 |
ulum | -3.834 |
nton | -3.778 |
uctor | -3.672 |
Token | — |
Token ID | 960 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
mas | +3.314 |
Fall | +3.231 |
seeing | +3.172 |
look | +2.995 |
hey | +2.991 |
Neg logit contributions | |
relations | -2.634 |
suicide | -2.525 |
ulum | -2.439 |
nton | -2.400 |
uctor | -2.333 |
Token | young |
Token ID | 35465 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
mas | +2.115 |
Fall | +2.030 |
seeing | +1.994 |
hey | +1.837 |
look | +1.825 |
Neg logit contributions | |
relations | -3.097 |
suicide | -2.996 |
ulum | -2.901 |
nton | -2.864 |
grounds | -2.825 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
relations | +2.259 |
suicide | +2.167 |
ulum | +2.065 |
nton | +2.034 |
grounds | +1.981 |
Neg logit contributions | |
mas | -2.833 |
Fall | -2.753 |
seeing | -2.750 |
hey | -2.579 |
look | -2.549 |
Token | mature |
Token ID | 15345 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
relations | +2.643 |
suicide | +2.498 |
ulum | +2.328 |
grounds | +2.304 |
nton | +2.285 |
Neg logit contributions | |
mas | -3.288 |
seeing | -3.255 |
Fall | -3.186 |
look | -2.998 |
hey | -2.988 |
Token | — |
Token ID | 960 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
relations | +7.808 |
suicide | +7.354 |
ulum | +6.946 |
grounds | +6.891 |
ancest | +6.636 |
Neg logit contributions | |
mas | -9.406 |
Fall | -9.132 |
seeing | -9.006 |
look | -8.597 |
hey | -8.518 |
Token | needs |
Token ID | 50032 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
relations | +0.259 |
suicide | +0.250 |
ulum | +0.242 |
nton | +0.240 |
grounds | +0.234 |
Neg logit contributions | |
mas | -0.202 |
Fall | -0.196 |
seeing | -0.191 |
hey | -0.177 |
hell | -0.174 |
Token | to |
Token ID | 284 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
mas | +3.271 |
Fall | +3.155 |
seeing | +3.126 |
hey | +2.898 |
look | +2.877 |
Neg logit contributions | |
relations | -3.610 |
suicide | -3.488 |
ulum | -3.386 |
nton | -3.336 |
uctor | -3.270 |
Token | know |
Token ID | 760 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
mas | +0.230 |
Fall | +0.222 |
seeing | +0.217 |
hey | +0.199 |
look | +0.196 |
Neg logit contributions | |
relations | -0.361 |
suicide | -0.351 |
ulum | -0.338 |
nton | -0.336 |
grounds | -0.330 |
Token | about |
Token ID | 546 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
mas | +1.264 |
Fall | +1.228 |
seeing | +1.209 |
hey | +1.138 |
look | +1.131 |
Neg logit contributions | |
relations | -1.087 |
suicide | -1.043 |
ulum | -0.998 |
nton | -0.986 |
grounds | -0.961 |
Token | supports |
Token ID | 6971 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
relations | +0.950 |
suicide | +0.903 |
ulum | +0.849 |
nton | +0.839 |
grounds | +0.821 |
Neg logit contributions | |
mas | -1.521 |
Fall | -1.491 |
seeing | -1.469 |
hey | -1.393 |
look | -1.381 |
Token | him |
Token ID | 683 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
relations | +3.595 |
suicide | +3.492 |
grounds | +3.178 |
ulum | +3.158 |
prayer | +3.142 |
Neg logit contributions | |
mas | -4.237 |
Fall | -4.194 |
seeing | -4.114 |
hey | -3.891 |
look | -3.849 |
Token | is |
Token ID | 318 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
mas | +0.527 |
Fall | +0.512 |
seeing | +0.506 |
hey | +0.479 |
look | +0.477 |
Neg logit contributions | |
relations | -0.355 |
suicide | -0.338 |
ulum | -0.322 |
nton | -0.317 |
grounds | -0.307 |
Token | not |
Token ID | 407 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
relations | +2.736 |
suicide | +2.666 |
ulum | +2.452 |
grounds | +2.443 |
nton | +2.431 |
Neg logit contributions | |
mas | -3.374 |
Fall | -3.311 |
seeing | -3.226 |
hey | -3.064 |
look | -3.046 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
relations | +1.958 |
suicide | +1.880 |
ulum | +1.765 |
nton | +1.743 |
grounds | +1.737 |
Neg logit contributions | |
mas | -2.405 |
Fall | -2.354 |
seeing | -2.301 |
hey | -2.178 |
look | -2.170 |
Token | Christian |
Token ID | 4302 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
relations | +0.856 |
suicide | +0.814 |
ulum | +0.748 |
nton | +0.735 |
grounds | +0.723 |
Neg logit contributions | |
mas | -1.692 |
Fall | -1.657 |
seeing | -1.639 |
hey | -1.558 |
look | -1.555 |
Token | . |
Token ID | 13 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
relations | +6.668 |
suicide | +6.472 |
grounds | +5.832 |
ulum | +5.757 |
prayer | +5.656 |
Neg logit contributions | |
Fall | -10.618 |
mas | -10.618 |
seeing | -10.415 |
look | -9.854 |
hey | -9.844 |
Token | She |
Token ID | 1375 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
relations | +1.030 |
suicide | +0.996 |
ulum | +0.955 |
nton | +0.950 |
grounds | +0.932 |
Neg logit contributions | |
mas | -0.849 |
Fall | -0.821 |
seeing | -0.809 |
hey | -0.750 |
look | -0.741 |
Token | challenged |
Token ID | 12827 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
relations | +1.281 |
suicide | +1.217 |
ulum | +1.148 |
nton | +1.136 |
grounds | +1.110 |
Neg logit contributions | |
mas | -2.042 |
Fall | -2.008 |
seeing | -1.974 |
hey | -1.871 |
look | -1.856 |
Token | her |
Token ID | 607 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
relations | +2.322 |
suicide | +2.232 |
ulum | +2.100 |
grounds | +2.078 |
nton | +2.069 |
Neg logit contributions | |
mas | -2.545 |
Fall | -2.484 |
seeing | -2.446 |
hey | -2.293 |
look | -2.283 |
Token | students |
Token ID | 2444 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
relations | +0.059 |
suicide | +0.056 |
ulum | +0.053 |
nton | +0.052 |
grounds | +0.050 |
Neg logit contributions | |
mas | -0.097 |
Fall | -0.094 |
seeing | -0.093 |
hey | -0.088 |
look | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
relations | +0.899 |
suicide | +0.853 |
ulum | +0.795 |
nton | +0.785 |
grounds | +0.779 |
Neg logit contributions | |
mas | -1.131 |
Fall | -1.102 |
seeing | -1.082 |
hey | -1.022 |
look | -1.017 |
Token | non |
Token ID | 1729 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
relations | +0.806 |
suicide | +0.763 |
ulum | +0.711 |
nton | +0.700 |
grounds | +0.694 |
Neg logit contributions | |
mas | -1.106 |
Fall | -1.077 |
seeing | -1.060 |
hey | -1.004 |
look | -1.000 |
Token | - |
Token ID | 12 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
relations | +0.088 |
suicide | +0.083 |
ulum | +0.078 |
nton | +0.076 |
grounds | +0.074 |
Neg logit contributions | |
mas | -0.178 |
Fall | -0.174 |
seeing | -0.172 |
hey | -0.164 |
look | -0.163 |
Token | aligned |
Token ID | 41634 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
mas | +3.605 |
Fall | +3.530 |
seeing | +3.487 |
hey | +3.313 |
look | +3.310 |
Neg logit contributions | |
relations | -1.630 |
suicide | -1.547 |
ulum | -1.453 |
nton | -1.415 |
grounds | -1.363 |
Token | and |
Token ID | 290 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
relations | +3.867 |
suicide | +3.580 |
grounds | +3.258 |
ulum | +3.149 |
nton | +3.096 |
Neg logit contributions | |
mas | -6.988 |
Fall | -6.840 |
seeing | -6.709 |
hey | -6.400 |
look | -6.391 |
Token | developing |
Token ID | 5922 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
relations | +3.020 |
suicide | +2.851 |
grounds | +2.595 |
ulum | +2.587 |
nton | +2.543 |
Neg logit contributions | |
mas | -4.520 |
Fall | -4.421 |
seeing | -4.336 |
look | -4.127 |
hey | -4.117 |
Token | countries |
Token ID | 2678 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
relations | +6.052 |
suicide | +5.329 |
grounds | +4.930 |
bloc | +4.837 |
oppos | +4.431 |
Neg logit contributions | |
mas | -11.856 |
Fall | -11.773 |
seeing | -11.513 |
look | -11.020 |
urrection | -10.808 |
Token | today |
Token ID | 1909 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
relations | +2.405 |
suicide | +2.246 |
ulum | +2.030 |
grounds | +2.013 |
nton | +1.998 |
Neg logit contributions | |
mas | -3.886 |
Fall | -3.863 |
seeing | -3.724 |
hey | -3.592 |
look | -3.560 |
Token | is |
Token ID | 318 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
relations | +1.584 |
suicide | +1.469 |
ulum | +1.351 |
grounds | +1.311 |
nton | +1.310 |
Neg logit contributions | |
mas | -3.223 |
Fall | -3.188 |
seeing | -3.123 |
hey | -2.983 |
look | -2.963 |
Token | to |
Token ID | 284 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
relations | +2.366 |
suicide | +2.256 |
grounds | +2.053 |
ulum | +2.051 |
nton | +2.028 |
Neg logit contributions | |
mas | -2.716 |
Fall | -2.656 |
seeing | -2.584 |
hey | -2.469 |
look | -2.428 |
Token | do |
Token ID | 466 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
mas | +0.180 |
Fall | +0.176 |
seeing | +0.173 |
hey | +0.162 |
look | +0.160 |
Neg logit contributions | |
relations | -0.165 |
suicide | -0.158 |
ulum | -0.149 |
nton | -0.148 |
grounds | -0.146 |
Token | in |
Token ID | 287 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
relations | +1.271 |
suicide | +1.183 |
ulum | +1.101 |
nton | +1.091 |
grounds | +1.091 |
Neg logit contributions | |
mas | -1.892 |
Fall | -1.846 |
seeing | -1.814 |
hey | -1.724 |
look | -1.713 |
Token | a |
Token ID | 257 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
relations | +1.094 |
suicide | +1.039 |
ulum | +0.985 |
nton | +0.972 |
grounds | +0.958 |
Neg logit contributions | |
mas | -1.285 |
Fall | -1.250 |
seeing | -1.227 |
hey | -1.159 |
look | -1.150 |
Token | further |
Token ID | 2252 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
relations | +2.252 |
suicide | +2.154 |
ulum | +1.968 |
grounds | +1.954 |
nton | +1.935 |
Neg logit contributions | |
mas | -2.936 |
Fall | -2.869 |
seeing | -2.803 |
hey | -2.681 |
look | -2.639 |
Token | sign |
Token ID | 1051 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
relations | +3.885 |
suicide | +3.706 |
grounds | +3.399 |
ulum | +3.387 |
nton | +3.363 |
Neg logit contributions | |
mas | -4.218 |
Fall | -4.125 |
seeing | -4.015 |
hey | -3.829 |
look | -3.785 |
Token | of |
Token ID | 286 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
relations | +2.162 |
suicide | +2.047 |
ulum | +1.955 |
nton | +1.920 |
grounds | +1.908 |
Neg logit contributions | |
mas | -1.934 |
Fall | -1.869 |
seeing | -1.831 |
hey | -1.733 |
look | -1.715 |
Token | regional |
Token ID | 7915 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
relations | +2.270 |
suicide | +2.080 |
ulum | +1.909 |
grounds | +1.906 |
nton | +1.887 |
Neg logit contributions | |
mas | -3.124 |
Fall | -3.055 |
seeing | -2.986 |
hey | -2.853 |
look | -2.821 |
Token | eager |
Token ID | 11069 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
relations | +7.472 |
suicide | +6.545 |
grounds | +5.869 |
bloc | +5.796 |
oppos | +5.659 |
Neg logit contributions | |
mas | -10.588 |
Fall | -10.466 |
seeing | -10.356 |
作 | -10.221 |
achu | -10.070 |
Token | ness |
Token ID | 1108 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
mas | +1.676 |
Fall | +1.594 |
seeing | +1.567 |
look | +1.429 |
hey | +1.416 |
Neg logit contributions | |
relations | -2.750 |
suicide | -2.686 |
ulum | -2.627 |
nton | -2.604 |
uctor | -2.556 |
Token | to |
Token ID | 284 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
relations | +1.082 |
suicide | +1.021 |
ulum | +0.951 |
grounds | +0.945 |
nton | +0.943 |
Neg logit contributions | |
mas | -1.173 |
Fall | -1.154 |
seeing | -1.121 |
hey | -1.065 |
look | -1.045 |
Token | challenge |
Token ID | 4427 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
relations | +1.430 |
suicide | +1.360 |
ulum | +1.251 |
grounds | +1.249 |
nton | +1.239 |
Neg logit contributions | |
mas | -1.497 |
Fall | -1.462 |
seeing | -1.454 |
hey | -1.365 |
hell | -1.334 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
relations | +2.590 |
suicide | +2.414 |
ulum | +2.206 |
grounds | +2.205 |
nton | +2.195 |
Neg logit contributions | |
mas | -3.139 |
Fall | -3.086 |
seeing | -3.020 |
hey | -2.873 |
look | -2.834 |
Token | H |
Token ID | 367 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
mas | +2.354 |
Fall | +2.256 |
seeing | +2.222 |
hey | +2.090 |
look | +2.063 |
Neg logit contributions | |
relations | -2.401 |
suicide | -2.309 |
ulum | -2.214 |
nton | -2.195 |
grounds | -2.149 |
Token | oss |
Token ID | 793 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
mas | +6.162 |
Fall | +5.921 |
seeing | +5.771 |
hey | +5.567 |
hell | +5.457 |
Neg logit contributions | |
relations | -5.366 |
suicide | -5.091 |
EStreamFrame | -4.786 |
grounds | -4.781 |
ancest | -4.774 |
Token | ain |
Token ID | 391 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
mas | +5.737 |
seeing | +5.359 |
Fall | +5.241 |
hey | +5.046 |
look | +4.982 |
Neg logit contributions | |
relations | -6.654 |
suicide | -6.366 |
ancest | -6.122 |
EStreamFrame | -6.066 |
ulum | -6.040 |
Token | , |
Token ID | 11 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
relations | +0.758 |
suicide | +0.724 |
ulum | +0.683 |
nton | +0.675 |
grounds | +0.653 |
Neg logit contributions | |
mas | -1.185 |
Fall | -1.161 |
seeing | -1.141 |
hey | -1.082 |
look | -1.079 |
Token | chief |
Token ID | 4039 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
mas | +0.280 |
Fall | +0.273 |
seeing | +0.269 |
hey | +0.254 |
look | +0.252 |
Neg logit contributions | |
relations | -0.215 |
suicide | -0.206 |
ulum | -0.196 |
nton | -0.194 |
grounds | -0.189 |
Token | forest |
Token ID | 8222 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
relations | +1.981 |
suicide | +1.883 |
ulum | +1.764 |
nton | +1.742 |
grounds | +1.734 |
Neg logit contributions | |
mas | -2.766 |
Fall | -2.703 |
seeing | -2.641 |
hey | -2.522 |
look | -2.501 |
Token | official |
Token ID | 1743 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
relations | +6.637 |
suicide | +6.052 |
grounds | +5.588 |
magistrate | +5.464 |
nton | +5.462 |
Neg logit contributions | |
mas | -11.121 |
Fall | -10.834 |
seeing | -10.347 |
hey | -10.165 |
look | -10.036 |
Token | of |
Token ID | 286 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
relations | +2.305 |
suicide | +2.175 |
ulum | +2.058 |
nton | +2.037 |
grounds | +2.018 |
Neg logit contributions | |
mas | -2.819 |
Fall | -2.770 |
seeing | -2.676 |
hey | -2.544 |
look | -2.539 |
Token | the |
Token ID | 262 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
relations | +2.275 |
suicide | +2.183 |
ulum | +2.029 |
grounds | +2.008 |
nton | +2.000 |
Neg logit contributions | |
mas | -2.678 |
Fall | -2.603 |
seeing | -2.559 |
hey | -2.434 |
look | -2.390 |
Token | Sund |
Token ID | 3309 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
relations | +1.985 |
suicide | +1.919 |
ulum | +1.785 |
grounds | +1.774 |
nton | +1.762 |
Neg logit contributions | |
mas | -2.295 |
Fall | -2.232 |
seeing | -2.193 |
hey | -2.077 |
look | -2.052 |
Token | arb |
Token ID | 38039 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
mas | +2.064 |
Fall | +2.000 |
seeing | +1.965 |
hey | +1.865 |
look | +1.859 |
Neg logit contributions | |
relations | -1.534 |
suicide | -1.465 |
ulum | -1.382 |
nton | -1.365 |
ancest | -1.346 |
Token | � |
Token ID | 447 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
mas | +4.546 |
Fall | +4.397 |
seeing | +4.293 |
hey | +4.106 |
look | +3.983 |
Neg logit contributions | |
relations | -4.519 |
suicide | -4.407 |
ulum | -4.199 |
nton | -4.161 |
grounds | -4.070 |
Token | � |
Token ID | 247 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
mas | +1.060 |
Fall | +1.020 |
seeing | +1.000 |
hey | +0.925 |
look | +0.918 |
Neg logit contributions | |
relations | -1.443 |
suicide | -1.396 |
ulum | -1.347 |
nton | -1.335 |
grounds | -1.307 |
Token | s |
Token ID | 82 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
mas | +2.799 |
Fall | +2.679 |
seeing | +2.650 |
hey | +2.495 |
look | +2.482 |
Neg logit contributions | |
relations | -2.726 |
suicide | -2.628 |
ulum | -2.523 |
nton | -2.473 |
grounds | -2.428 |
Token | visit |
Token ID | 3187 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
mas | +0.654 |
Fall | +0.636 |
seeing | +0.625 |
hey | +0.585 |
look | +0.582 |
Neg logit contributions | |
relations | -0.631 |
suicide | -0.607 |
ulum | -0.582 |
nton | -0.576 |
grounds | -0.562 |
Token | Vietnam |
Token ID | 10836 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
mas | +2.614 |
Fall | +2.532 |
seeing | +2.497 |
hey | +2.334 |
look | +2.325 |
Neg logit contributions | |
relations | -2.478 |
suicide | -2.381 |
ulum | -2.298 |
nton | -2.274 |
uctor | -2.199 |
Token | every |
Token ID | 790 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
mas | +0.310 |
Fall | +0.300 |
seeing | +0.294 |
hey | +0.274 |
look | +0.271 |
Neg logit contributions | |
relations | -0.396 |
suicide | -0.382 |
ulum | -0.365 |
nton | -0.363 |
grounds | -0.359 |
Token | year |
Token ID | 614 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
mas | +6.896 |
Fall | +6.762 |
seeing | +6.558 |
look | +5.971 |
hell | +5.895 |
Neg logit contributions | |
relations | -8.170 |
ulum | -7.818 |
suicide | -7.769 |
nton | -7.709 |
uctor | -7.593 |
Token | just |
Token ID | 655 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
mas | +1.881 |
Fall | +1.830 |
seeing | +1.801 |
hey | +1.699 |
look | +1.689 |
Neg logit contributions | |
relations | -1.516 |
suicide | -1.452 |
ulum | -1.386 |
nton | -1.369 |
grounds | -1.334 |
Token | to |
Token ID | 284 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
mas | +3.232 |
Fall | +3.128 |
seeing | +3.093 |
hey | +2.873 |
look | +2.856 |
Neg logit contributions | |
relations | -3.528 |
suicide | -3.395 |
ulum | -3.297 |
nton | -3.241 |
uctor | -3.159 |
Token | stay |
Token ID | 2652 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
mas | +0.578 |
Fall | +0.561 |
seeing | +0.551 |
hey | +0.514 |
look | +0.509 |
Neg logit contributions | |
relations | -0.639 |
suicide | -0.616 |
ulum | -0.590 |
nton | -0.585 |
grounds | -0.574 |
Token | current |
Token ID | 1459 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
mas | +1.169 |
Fall | +1.133 |
seeing | +1.116 |
hey | +1.052 |
look | +1.045 |
Neg logit contributions | |
relations | -1.000 |
suicide | -0.964 |
ulum | -0.923 |
nton | -0.913 |
grounds | -0.884 |
Token | - |
Token ID | 12 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
relations | +3.443 |
suicide | +3.203 |
grounds | +2.869 |
ulum | +2.807 |
nton | +2.798 |
Neg logit contributions | |
mas | -7.013 |
Fall | -6.919 |
seeing | -6.850 |
hey | -6.524 |
look | -6.484 |
Token | business |
Token ID | 22680 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
relations | +1.124 |
suicide | +1.072 |
ulum | +1.015 |
nton | +1.012 |
grounds | +0.985 |
Neg logit contributions | |
mas | -1.392 |
Fall | -1.367 |
seeing | -1.343 |
hey | -1.264 |
look | -1.250 |
Token | owners |
Token ID | 4393 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
relations | +3.044 |
suicide | +2.859 |
grounds | +2.544 |
ulum | +2.513 |
nton | +2.498 |
Neg logit contributions | |
mas | -5.639 |
Fall | -5.554 |
seeing | -5.437 |
hey | -5.198 |
look | -5.151 |
Token | at |
Token ID | 379 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
mas | +1.299 |
Fall | +1.265 |
seeing | +1.246 |
hey | +1.175 |
look | +1.168 |
Neg logit contributions | |
relations | -1.026 |
suicide | -0.982 |
ulum | -0.936 |
nton | -0.925 |
grounds | -0.901 |
Token | ex |
Token ID | 409 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
relations | +1.664 |
suicide | +1.605 |
ulum | +1.500 |
nton | +1.483 |
grounds | +1.481 |
Neg logit contributions | |
mas | -1.948 |
Fall | -1.908 |
seeing | -1.892 |
hey | -1.769 |
look | -1.752 |
Token | orbit |
Token ID | 42594 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
mas | +1.641 |
Fall | +1.564 |
seeing | +1.522 |
hey | +1.420 |
look | +1.406 |
Neg logit contributions | |
relations | -2.220 |
suicide | -2.154 |
ulum | -2.090 |
nton | -2.059 |
uctor | -2.018 |
Token | ant |
Token ID | 415 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
mas | +5.703 |
Fall | +5.547 |
seeing | +5.450 |
hey | +5.053 |
look | +5.021 |
Neg logit contributions | |
relations | -6.768 |
suicide | -6.384 |
nton | -6.195 |
EStreamFrame | -6.126 |
uctor | -6.067 |
Token | rates |
Token ID | 3965 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
mas | +3.033 |
Fall | +2.952 |
seeing | +2.904 |
look | +2.745 |
hey | +2.742 |
Neg logit contributions | |
relations | -1.989 |
suicide | -1.884 |
ulum | -1.826 |
nton | -1.808 |
uctor | -1.760 |
Token | while |
Token ID | 981 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
mas | +0.587 |
Fall | +0.573 |
seeing | +0.564 |
hey | +0.532 |
look | +0.530 |
Neg logit contributions | |
relations | -0.450 |
suicide | -0.430 |
ulum | -0.409 |
nton | -0.403 |
grounds | -0.396 |
Token | protecting |
Token ID | 10192 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
relations | +1.719 |
suicide | +1.648 |
ulum | +1.534 |
nton | +1.525 |
grounds | +1.510 |
Neg logit contributions | |
mas | -2.172 |
Fall | -2.123 |
seeing | -2.084 |
hey | -1.968 |
look | -1.958 |
Token | Bay |
Token ID | 4696 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
relations | +1.186 |
suicide | +1.134 |
ulum | +1.067 |
nton | +1.055 |
grounds | +1.043 |
Neg logit contributions | |
mas | -1.436 |
Fall | -1.401 |
seeing | -1.380 |
hey | -1.299 |
look | -1.287 |
Token | Vision |
Token ID | 19009 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
relations | +0.698 |
suicide | +0.668 |
ulum | +0.630 |
nton | +0.624 |
grounds | +0.612 |
Neg logit contributions | |
mas | -0.868 |
Fall | -0.849 |
seeing | -0.834 |
hey | -0.784 |
look | -0.780 |
Token | Forum |
Token ID | 14867 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
mas | +3.845 |
Fall | +3.761 |
seeing | +3.686 |
hey | +3.450 |
look | +3.442 |
Neg logit contributions | |
relations | -3.445 |
suicide | -3.298 |
ulum | -3.184 |
nton | -3.128 |
uctor | -3.064 |
Token | even |
Token ID | 772 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
mas | +0.513 |
Fall | +0.500 |
seeing | +0.493 |
hey | +0.465 |
look | +0.463 |
Neg logit contributions | |
relations | -0.387 |
suicide | -0.370 |
ulum | -0.352 |
nton | -0.347 |
grounds | -0.338 |
Token | named |
Token ID | 3706 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
mas | +4.174 |
Fall | +4.028 |
seeing | +3.982 |
hey | +3.772 |
look | +3.757 |
Neg logit contributions | |
relations | -3.225 |
suicide | -3.089 |
ulum | -3.000 |
nton | -2.959 |
uctor | -2.865 |
Token | Michelle |
Token ID | 16738 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
mas | +3.588 |
Fall | +3.483 |
seeing | +3.421 |
look | +3.199 |
hey | +3.198 |
Neg logit contributions | |
relations | -3.380 |
suicide | -3.241 |
ulum | -3.155 |
nton | -3.127 |
uctor | -3.018 |
Token | Dug |
Token ID | 27436 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
mas | +3.317 |
Fall | +3.209 |
seeing | +3.154 |
hey | +2.960 |
look | +2.940 |
Neg logit contributions | |
relations | -3.144 |
suicide | -3.029 |
ulum | -2.930 |
nton | -2.890 |
grounds | -2.802 |
Token | gar |
Token ID | 4563 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
mas | +5.869 |
Fall | +5.406 |
seeing | +5.176 |
hey | +5.157 |
hell | +5.153 |
Neg logit contributions | |
relations | -6.618 |
suicide | -6.421 |
uctor | -6.350 |
ancest | -6.337 |
oppos | -6.266 |
Token | � |
Token ID | 564 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
mas | +3.080 |
Fall | +2.981 |
seeing | +2.914 |
hey | +2.768 |
look | +2.758 |
Neg logit contributions | |
relations | -2.624 |
suicide | -2.498 |
ulum | -2.426 |
nton | -2.387 |
uctor | -2.331 |
Token | � |
Token ID | 250 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
mas | +2.577 |
Fall | +2.431 |
seeing | +2.420 |
hey | +2.159 |
look | +2.124 |
Neg logit contributions | |
relations | -5.504 |
suicide | -5.385 |
ulum | -5.225 |
nton | -5.200 |
uctor | -5.083 |
Token | Mother |
Token ID | 31398 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
mas | +1.007 |
Fall | +0.977 |
seeing | +0.962 |
hey | +0.901 |
look | +0.895 |
Neg logit contributions | |
relations | -0.972 |
suicide | -0.936 |
ulum | -0.897 |
nton | -0.887 |
grounds | -0.866 |
Token | of |
Token ID | 286 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
relations | +0.583 |
suicide | +0.565 |
ulum | +0.538 |
nton | +0.531 |
grounds | +0.523 |
Neg logit contributions | |
mas | -0.540 |
Fall | -0.527 |
seeing | -0.522 |
hey | -0.484 |
look | -0.481 |
Token | or |
Token ID | 393 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
relations | +3.676 |
suicide | +3.479 |
grounds | +3.252 |
ulum | +3.193 |
nton | +3.160 |
Neg logit contributions | |
mas | -4.250 |
Fall | -4.181 |
seeing | -4.106 |
look | -3.869 |
hey | -3.863 |
Token | manufacturers |
Token ID | 11372 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
relations | +0.053 |
suicide | +0.050 |
ulum | +0.047 |
nton | +0.047 |
grounds | +0.045 |
Neg logit contributions | |
mas | -0.087 |
Fall | -0.085 |
seeing | -0.084 |
hey | -0.079 |
look | -0.079 |
Token | to |
Token ID | 284 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
relations | +2.999 |
suicide | +2.852 |
ulum | +2.670 |
grounds | +2.658 |
nton | +2.634 |
Neg logit contributions | |
mas | -3.198 |
Fall | -3.126 |
seeing | -3.069 |
hey | -2.882 |
look | -2.875 |
Token | include |
Token ID | 2291 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
mas | +0.936 |
Fall | +0.908 |
seeing | +0.892 |
hey | +0.838 |
look | +0.834 |
Neg logit contributions | |
relations | -0.876 |
suicide | -0.841 |
ulum | -0.809 |
nton | -0.798 |
grounds | -0.777 |
Token | Google |
Token ID | 3012 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
mas | +0.436 |
Fall | +0.424 |
seeing | +0.417 |
hey | +0.392 |
look | +0.389 |
Neg logit contributions | |
relations | -0.395 |
suicide | -0.379 |
ulum | -0.365 |
nton | -0.360 |
grounds | -0.350 |
Token | Search |
Token ID | 11140 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
mas | +5.382 |
Fall | +5.263 |
seeing | +5.061 |
look | +4.884 |
hey | +4.851 |
Neg logit contributions | |
relations | -3.527 |
suicide | -3.440 |
ulum | -3.402 |
nton | -3.370 |
EStreamFrame | -3.200 |
Token | or |
Token ID | 393 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
mas | +9.166 |
Fall | +8.717 |
seeing | +8.508 |
look | +8.229 |
mes | +8.167 |
Neg logit contributions | |
suicide | -7.672 |
ulum | -7.639 |
nton | -7.575 |
EStreamFrame | -7.492 |
relations | -7.445 |
Token | Google |
Token ID | 3012 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
mas | +1.828 |
Fall | +1.767 |
seeing | +1.731 |
hey | +1.620 |
look | +1.612 |
Neg logit contributions | |
relations | -2.099 |
suicide | -2.029 |
ulum | -1.963 |
nton | -1.943 |
grounds | -1.886 |
Token | applications |
Token ID | 5479 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
mas | +3.895 |
Fall | +3.714 |
seeing | +3.608 |
look | +3.394 |
hey | +3.383 |
Neg logit contributions | |
relations | -4.484 |
suicide | -4.390 |
nton | -4.288 |
ulum | -4.261 |
EStreamFrame | -4.169 |
Token | on |
Token ID | 319 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
mas | +0.058 |
Fall | +0.057 |
seeing | +0.056 |
hey | +0.053 |
look | +0.052 |
Neg logit contributions | |
relations | -0.047 |
suicide | -0.045 |
ulum | -0.043 |
nton | -0.042 |
grounds | -0.041 |
Token | Android |
Token ID | 5565 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
mas | +1.933 |
Fall | +1.880 |
seeing | +1.838 |
look | +1.750 |
hey | +1.742 |
Neg logit contributions | |
relations | -1.588 |
suicide | -1.528 |
ulum | -1.485 |
nton | -1.483 |
uctor | -1.410 |
Token | to |
Token ID | 284 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
mas | +0.196 |
Fall | +0.190 |
seeing | +0.187 |
hey | +0.177 |
look | +0.175 |
Neg logit contributions | |
relations | -0.174 |
suicide | -0.167 |
ulum | -0.158 |
nton | -0.156 |
grounds | -0.154 |
Token | force |
Token ID | 2700 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
mas | +2.614 |
Fall | +2.520 |
seeing | +2.484 |
look | +2.343 |
hey | +2.328 |
Neg logit contributions | |
relations | -2.207 |
suicide | -2.122 |
ulum | -2.074 |
nton | -2.035 |
uctor | -1.955 |
Token | back |
Token ID | 736 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
mas | +1.723 |
Fall | +1.672 |
seeing | +1.646 |
hey | +1.549 |
look | +1.540 |
Neg logit contributions | |
relations | -1.426 |
suicide | -1.372 |
ulum | -1.314 |
nton | -1.300 |
grounds | -1.260 |
Token | this |
Token ID | 428 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
relations | +0.691 |
suicide | +0.655 |
ulum | +0.623 |
nton | +0.615 |
grounds | +0.606 |
Neg logit contributions | |
mas | -0.787 |
Fall | -0.771 |
seeing | -0.757 |
hey | -0.716 |
look | -0.710 |
Token | unwelcome |
Token ID | 47207 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
relations | +0.431 |
suicide | +0.412 |
ulum | +0.388 |
nton | +0.385 |
grounds | +0.378 |
Neg logit contributions | |
mas | -0.544 |
Fall | -0.529 |
seeing | -0.522 |
hey | -0.494 |
look | -0.490 |
Token | intrusion |
Token ID | 34396 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
mas | +5.149 |
Fall | +4.982 |
seeing | +4.909 |
look | +4.619 |
hey | +4.576 |
Neg logit contributions | |
relations | -3.588 |
suicide | -3.507 |
ulum | -3.461 |
nton | -3.345 |
uctor | -3.225 |
Token | : |
Token ID | 25 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
mas | +6.944 |
Fall | +6.493 |
seeing | +6.380 |
hell | +6.044 |
hey | +5.934 |
Neg logit contributions | |
relations | -7.400 |
suicide | -7.377 |
ulum | -7.164 |
nton | -7.122 |
uctor | -6.907 |
Token | from |
Token ID | 422 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
mas | +1.362 |
Fall | +1.324 |
seeing | +1.302 |
hey | +1.223 |
look | +1.215 |
Neg logit contributions | |
relations | -1.253 |
suicide | -1.203 |
ulum | -1.149 |
nton | -1.136 |
grounds | -1.110 |
Token | id |
Token ID | 4686 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
mas | +2.790 |
Fall | +2.692 |
seeing | +2.659 |
hey | +2.484 |
look | +2.478 |
Neg logit contributions | |
relations | -2.475 |
suicide | -2.379 |
ulum | -2.296 |
nton | -2.275 |
grounds | -2.194 |
Token | to |
Token ID | 284 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
relations | +1.643 |
suicide | +1.566 |
ulum | +1.511 |
nton | +1.470 |
uctor | +1.450 |
Neg logit contributions | |
mas | -1.854 |
Fall | -1.819 |
seeing | -1.803 |
look | -1.679 |
hey | -1.677 |
Token | ego |
Token ID | 19225 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
mas | +1.211 |
Fall | +1.177 |
seeing | +1.159 |
hey | +1.092 |
look | +1.086 |
Neg logit contributions | |
relations | -0.993 |
suicide | -0.952 |
ulum | -0.910 |
nton | -0.899 |
grounds | -0.875 |
Token | EL |
Token ID | 3698 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
relations | +0.181 |
suicide | +0.174 |
ulum | +0.166 |
nton | +0.165 |
grounds | +0.161 |
Neg logit contributions | |
mas | -0.182 |
Fall | -0.177 |
seeing | -0.175 |
hey | -0.163 |
look | -0.162 |
Token | VE |
Token ID | 6089 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
relations | +0.663 |
suicide | +0.637 |
ulum | +0.611 |
nton | +0.607 |
grounds | +0.593 |
Neg logit contributions | |
mas | -0.619 |
Fall | -0.599 |
seeing | -0.592 |
hey | -0.550 |
look | -0.548 |
Token | ) |
Token ID | 8 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
relations | +1.207 |
suicide | +1.161 |
ulum | +1.092 |
nton | +1.081 |
grounds | +1.076 |
Neg logit contributions | |
mas | -1.256 |
Fall | -1.224 |
seeing | -1.206 |
hey | -1.125 |
look | -1.120 |
Token | quarterback |
Token ID | 7880 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
relations | +1.802 |
suicide | +1.728 |
grounds | +1.606 |
nton | +1.573 |
ulum | +1.558 |
Neg logit contributions | |
mas | -2.086 |
seeing | -2.020 |
Fall | -2.015 |
hey | -1.900 |
look | -1.852 |
Token | hur |
Token ID | 6990 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
relations | +1.296 |
suicide | +1.250 |
ulum | +1.179 |
nton | +1.174 |
grounds | +1.160 |
Neg logit contributions | |
mas | -1.218 |
Fall | -1.177 |
seeing | -1.163 |
hey | -1.090 |
look | -1.075 |
Token | ries |
Token ID | 1678 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
mas | +3.459 |
Fall | +3.316 |
seeing | +3.212 |
hey | +3.029 |
look | +3.020 |
Neg logit contributions | |
relations | -3.311 |
suicide | -3.209 |
ulum | -3.066 |
nton | -3.021 |
uctor | -2.963 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
mas | +1.073 |
Fall | +1.046 |
seeing | +1.031 |
hey | +0.976 |
look | +0.968 |
Neg logit contributions | |
relations | -0.789 |
suicide | -0.753 |
ulum | -0.712 |
nton | -0.704 |
grounds | -0.689 |
Token | He |
Token ID | 679 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
relations | +0.071 |
suicide | +0.068 |
ulum | +0.065 |
nton | +0.065 |
grounds | +0.064 |
Neg logit contributions | |
mas | -0.063 |
Fall | -0.061 |
seeing | -0.061 |
hey | -0.056 |
look | -0.056 |
Token | is |
Token ID | 318 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
mas | +1.138 |
Fall | +1.106 |
seeing | +1.092 |
hey | +1.035 |
look | +1.034 |
Neg logit contributions | |
relations | -0.736 |
suicide | -0.702 |
ulum | -0.669 |
nton | -0.656 |
uctor | -0.633 |
Token | a |
Token ID | 257 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
relations | +1.886 |
suicide | +1.806 |
nton | +1.683 |
ulum | +1.682 |
grounds | +1.667 |
Neg logit contributions | |
mas | -2.313 |
Fall | -2.255 |
seeing | -2.216 |
hey | -2.094 |
look | -2.070 |
Token | very |
Token ID | 845 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
relations | +0.648 |
suicide | +0.627 |
ulum | +0.587 |
nton | +0.584 |
grounds | +0.577 |
Neg logit contributions | |
mas | -0.737 |
Fall | -0.717 |
seeing | -0.710 |
hey | -0.666 |
look | -0.657 |
Token | forced |
Token ID | 4137 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
relations | +2.504 |
suicide | +2.413 |
ulum | +2.225 |
grounds | +2.221 |
nton | +2.207 |
Neg logit contributions | |
mas | -3.158 |
Fall | -3.072 |
seeing | -3.002 |
hey | -2.848 |
look | -2.822 |
Token | to |
Token ID | 284 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
mas | +2.341 |
Fall | +2.266 |
seeing | +2.226 |
hey | +2.077 |
look | +2.064 |
Neg logit contributions | |
relations | -2.507 |
suicide | -2.413 |
ulum | -2.331 |
nton | -2.304 |
grounds | -2.246 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
mas | +1.589 |
Fall | +1.541 |
seeing | +1.513 |
hey | +1.417 |
look | +1.410 |
Neg logit contributions | |
relations | -1.606 |
suicide | -1.545 |
ulum | -1.487 |
nton | -1.470 |
grounds | -1.434 |
Token | gru |
Token ID | 22848 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
mas | +3.260 |
Fall | +3.167 |
seeing | +3.108 |
hey | +2.927 |
look | +2.905 |
Neg logit contributions | |
relations | -2.921 |
suicide | -2.805 |
ulum | -2.736 |
nton | -2.691 |
uctor | -2.598 |
Token | el |
Token ID | 417 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
mas | +4.229 |
Fall | +3.850 |
seeing | +3.793 |
hey | +3.640 |
look | +3.594 |
Neg logit contributions | |
relations | -6.183 |
suicide | -5.982 |
ancest | -5.668 |
grounds | -5.620 |
ulum | -5.605 |
Token | for |
Token ID | 329 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
mas | +0.565 |
Fall | +0.550 |
seeing | +0.541 |
hey | +0.510 |
look | +0.507 |
Neg logit contributions | |
relations | -0.465 |
suicide | -0.446 |
ulum | -0.425 |
nton | -0.420 |
grounds | -0.410 |
Token | months |
Token ID | 1933 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
mas | +2.203 |
Fall | +2.139 |
seeing | +2.104 |
hey | +1.971 |
look | +1.960 |
Neg logit contributions | |
relations | -2.112 |
suicide | -2.031 |
ulum | -1.956 |
nton | -1.932 |
grounds | -1.878 |
Token | at |
Token ID | 379 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
mas | +1.283 |
Fall | +1.248 |
seeing | +1.230 |
hey | +1.159 |
look | +1.153 |
Neg logit contributions | |
relations | -1.030 |
suicide | -0.986 |
ulum | -0.942 |
nton | -0.930 |
grounds | -0.905 |
Token | a |
Token ID | 257 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
relations | +0.018 |
suicide | +0.017 |
ulum | +0.017 |
nton | +0.016 |
grounds | +0.016 |
Neg logit contributions | |
mas | -0.019 |
Fall | -0.018 |
seeing | -0.018 |
hey | -0.017 |
look | -0.017 |
Token | time |
Token ID | 640 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
relations | +0.931 |
suicide | +0.900 |
ulum | +0.856 |
nton | +0.844 |
grounds | +0.832 |
Neg logit contributions | |
mas | -0.935 |
Fall | -0.907 |
seeing | -0.892 |
hey | -0.838 |
look | -0.830 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
relations | +1.490 |
suicide | +1.416 |
ulum | +1.327 |
nton | +1.318 |
grounds | +1.305 |
Neg logit contributions | |
mas | -2.118 |
Fall | -2.076 |
seeing | -2.028 |
hey | -1.923 |
look | -1.912 |
Token | never |
Token ID | 1239 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
relations | +0.962 |
suicide | +0.909 |
ulum | +0.858 |
nton | +0.850 |
grounds | +0.836 |
Neg logit contributions | |
mas | -1.432 |
Fall | -1.405 |
seeing | -1.377 |
hey | -1.303 |
look | -1.295 |
Token | used |
Token ID | 973 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
mas | +4.268 |
Fall | +4.098 |
seeing | +4.078 |
look | +3.848 |
hey | +3.841 |
Neg logit contributions | |
relations | -3.809 |
suicide | -3.711 |
ulum | -3.592 |
nton | -3.520 |
uctor | -3.428 |
Token | the |
Token ID | 262 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
mas | +0.503 |
Fall | +0.488 |
seeing | +0.481 |
hey | +0.452 |
look | +0.449 |
Neg logit contributions | |
relations | -0.446 |
suicide | -0.428 |
ulum | -0.409 |
nton | -0.405 |
grounds | -0.395 |
Token | pian |
Token ID | 43923 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
mas | +1.492 |
Fall | +1.450 |
seeing | +1.426 |
hey | +1.347 |
look | +1.340 |
Neg logit contributions | |
relations | -1.185 |
suicide | -1.138 |
ulum | -1.093 |
nton | -1.077 |
grounds | -1.042 |
Token | ist |
Token ID | 396 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
relations | +2.406 |
suicide | +2.257 |
nton | +2.184 |
ulum | +2.172 |
uctor | +2.022 |
Neg logit contributions | |
mas | -5.729 |
Fall | -5.660 |
seeing | -5.574 |
hey | -5.267 |
look | -5.262 |
Token | 's |
Token ID | 338 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
relations | +0.768 |
suicide | +0.720 |
ulum | +0.678 |
nton | +0.667 |
grounds | +0.652 |
Neg logit contributions | |
mas | -1.427 |
Fall | -1.398 |
seeing | -1.380 |
hey | -1.308 |
look | -1.306 |
Token | substit |
Token ID | 21436 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
mas | +2.561 |
Fall | +2.496 |
seeing | +2.455 |
hey | +2.331 |
look | +2.325 |
Neg logit contributions | |
relations | -1.635 |
suicide | -1.565 |
ulum | -1.503 |
nton | -1.477 |
grounds | -1.411 |
Token | utions |
Token ID | 3508 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
relations | +0.076 |
suicide | +0.072 |
ulum | +0.069 |
nton | +0.068 |
grounds | +0.066 |
Neg logit contributions | |
mas | -0.110 |
Fall | -0.108 |
seeing | -0.107 |
hey | -0.101 |
look | -0.100 |
Token | at |
Token ID | 379 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
relations | +0.463 |
suicide | +0.439 |
ulum | +0.418 |
nton | +0.412 |
grounds | +0.407 |
Neg logit contributions | |
mas | -0.602 |
Fall | -0.589 |
seeing | -0.578 |
hey | -0.545 |
look | -0.543 |
Token | all |
Token ID | 477 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
relations | +0.591 |
suicide | +0.572 |
ulum | +0.545 |
nton | +0.538 |
grounds | +0.532 |
Neg logit contributions | |
mas | -0.576 |
Fall | -0.563 |
seeing | -0.554 |
hey | -0.515 |
look | -0.513 |
Token | during |
Token ID | 1141 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
mas | +1.932 |
Fall | +1.879 |
seeing | +1.852 |
hey | +1.753 |
look | +1.741 |
Neg logit contributions | |
relations | -1.402 |
suicide | -1.346 |
ulum | -1.281 |
nton | -1.266 |
grounds | -1.221 |
Token | going |
Token ID | 1016 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
mas | +0.022 |
Fall | +0.021 |
seeing | +0.021 |
hey | +0.020 |
look | +0.019 |
Neg logit contributions | |
relations | -0.019 |
suicide | -0.018 |
ulum | -0.017 |
nton | -0.017 |
grounds | -0.017 |
Token | through |
Token ID | 832 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
relations | +0.568 |
suicide | +0.548 |
ulum | +0.520 |
nton | +0.515 |
grounds | +0.508 |
Neg logit contributions | |
mas | -0.594 |
Fall | -0.579 |
seeing | -0.565 |
hey | -0.535 |
look | -0.529 |
Token | airline |
Token ID | 18091 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
relations | +1.240 |
suicide | +1.190 |
ulum | +1.105 |
nton | +1.090 |
grounds | +1.078 |
Neg logit contributions | |
mas | -1.969 |
Fall | -1.926 |
seeing | -1.892 |
hey | -1.802 |
hell | -1.784 |
Token | security |
Token ID | 2324 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
mas | +1.335 |
Fall | +1.299 |
seeing | +1.291 |
look | +1.224 |
hey | +1.217 |
Neg logit contributions | |
relations | -0.712 |
suicide | -0.671 |
ulum | -0.653 |
nton | -0.640 |
uctor | -0.614 |
Token | . |
Token ID | 13 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
mas | +2.724 |
Fall | +2.645 |
seeing | +2.644 |
look | +2.462 |
hey | +2.452 |
Neg logit contributions | |
relations | -2.045 |
suicide | -1.963 |
ulum | -1.911 |
nton | -1.870 |
uctor | -1.818 |
Token | Given |
Token ID | 11259 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
relations | +0.154 |
suicide | +0.149 |
ulum | +0.142 |
nton | +0.141 |
grounds | +0.138 |
Neg logit contributions | |
mas | -0.167 |
Fall | -0.161 |
seeing | -0.159 |
hey | -0.149 |
look | -0.148 |
Token | the |
Token ID | 262 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
mas | +1.514 |
Fall | +1.470 |
seeing | +1.448 |
hey | +1.355 |
look | +1.349 |
Neg logit contributions | |
relations | -1.465 |
suicide | -1.408 |
ulum | -1.356 |
nton | -1.341 |
grounds | -1.304 |
Token | sensitivity |
Token ID | 14233 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
mas | +2.338 |
Fall | +2.277 |
seeing | +2.240 |
hey | +2.112 |
look | +2.105 |
Neg logit contributions | |
relations | -1.810 |
suicide | -1.728 |
ulum | -1.664 |
nton | -1.643 |
uctor | -1.585 |
Token | of |
Token ID | 286 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
mas | +0.463 |
Fall | +0.449 |
seeing | +0.441 |
hey | +0.412 |
look | +0.409 |
Neg logit contributions | |
relations | -0.511 |
suicide | -0.491 |
ulum | -0.470 |
nton | -0.464 |
grounds | -0.457 |
Token | our |
Token ID | 674 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
relations | +1.268 |
suicide | +1.222 |
ulum | +1.132 |
grounds | +1.115 |
nton | +1.108 |
Neg logit contributions | |
mas | -1.548 |
Fall | -1.501 |
seeing | -1.474 |
hey | -1.405 |
hell | -1.389 |
Token | reading |
Token ID | 3555 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
relations | +0.214 |
suicide | +0.202 |
ulum | +0.189 |
grounds | +0.184 |
nton | +0.183 |
Neg logit contributions | |
mas | -0.318 |
Fall | -0.310 |
seeing | -0.305 |
hey | -0.291 |
look | -0.288 |
Token | doesn |
Token ID | 1595 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
mas | +1.646 |
Fall | +1.599 |
seeing | +1.578 |
hey | +1.496 |
look | +1.494 |
Neg logit contributions | |
relations | -1.053 |
suicide | -1.004 |
ulum | -0.957 |
nton | -0.948 |
uctor | -0.905 |
Token | � |
Token ID | 447 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
mas | +1.775 |
Fall | +1.726 |
seeing | +1.690 |
hey | +1.598 |
look | +1.591 |
Neg logit contributions | |
relations | -1.533 |
suicide | -1.477 |
ulum | -1.398 |
nton | -1.381 |
ancest | -1.359 |
Token | � |
Token ID | 247 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
mas | +1.145 |
Fall | +1.105 |
seeing | +1.079 |
hey | +0.999 |
look | +0.990 |
Neg logit contributions | |
relations | -1.632 |
suicide | -1.583 |
ulum | -1.523 |
nton | -1.514 |
grounds | -1.478 |
Token | t |
Token ID | 83 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
mas | +2.483 |
Fall | +2.357 |
seeing | +2.307 |
hey | +2.137 |
look | +2.115 |
Neg logit contributions | |
relations | -3.860 |
suicide | -3.746 |
ulum | -3.609 |
nton | -3.576 |
grounds | -3.517 |
Token | explicitly |
Token ID | 11777 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
mas | +2.250 |
Fall | +2.176 |
seeing | +2.135 |
hey | +2.003 |
look | +1.994 |
Neg logit contributions | |
relations | -2.282 |
suicide | -2.192 |
ulum | -2.119 |
nton | -2.095 |
grounds | -2.038 |
Token | tag |
Token ID | 7621 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
mas | +3.169 |
Fall | +3.054 |
seeing | +2.987 |
hey | +2.816 |
look | +2.809 |
Neg logit contributions | |
relations | -3.020 |
suicide | -2.897 |
ulum | -2.826 |
nton | -2.787 |
uctor | -2.701 |
Token | you |
Token ID | 345 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
mas | +0.900 |
Fall | +0.874 |
seeing | +0.860 |
hey | +0.807 |
look | +0.802 |
Neg logit contributions | |
relations | -0.828 |
suicide | -0.796 |
ulum | -0.761 |
nton | -0.752 |
grounds | -0.734 |
Token | as |
Token ID | 355 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
mas | +2.255 |
Fall | +2.185 |
seeing | +2.146 |
hey | +2.018 |
look | +1.987 |
Neg logit contributions | |
relations | -2.246 |
suicide | -2.165 |
ulum | -2.092 |
nton | -2.080 |
grounds | -2.011 |
Token | good |
Token ID | 922 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
mas | +1.464 |
Fall | +1.422 |
seeing | +1.399 |
hey | +1.314 |
look | +1.305 |
Neg logit contributions | |
relations | -1.341 |
suicide | -1.287 |
ulum | -1.236 |
nton | -1.222 |
grounds | -1.190 |
Token | or |
Token ID | 393 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
relations | +1.997 |
suicide | +1.900 |
ulum | +1.780 |
nton | +1.751 |
grounds | +1.730 |
Neg logit contributions | |
mas | -2.524 |
Fall | -2.450 |
seeing | -2.419 |
hey | -2.284 |
look | -2.271 |
Token | evil |
Token ID | 6181 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
relations | +1.461 |
suicide | +1.401 |
ulum | +1.316 |
nton | +1.293 |
grounds | +1.290 |
Neg logit contributions | |
mas | -1.683 |
Fall | -1.635 |
seeing | -1.620 |
look | -1.514 |
hey | -1.513 |
Token | minutes |
Token ID | 2431 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
relations | +1.566 |
suicide | +1.495 |
ulum | +1.380 |
nton | +1.370 |
grounds | +1.355 |
Neg logit contributions | |
mas | -2.646 |
Fall | -2.593 |
seeing | -2.571 |
hey | -2.426 |
look | -2.412 |
Token | , |
Token ID | 11 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
relations | +2.371 |
suicide | +2.258 |
ulum | +2.079 |
grounds | +2.071 |
nton | +2.064 |
Neg logit contributions | |
mas | -3.373 |
Fall | -3.298 |
seeing | -3.226 |
hey | -3.059 |
look | -3.035 |
Token | and |
Token ID | 290 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
relations | +0.097 |
suicide | +0.093 |
ulum | +0.088 |
nton | +0.087 |
grounds | +0.086 |
Neg logit contributions | |
mas | -0.109 |
Fall | -0.106 |
seeing | -0.104 |
hey | -0.098 |
look | -0.097 |
Token | anyone |
Token ID | 2687 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
relations | +2.434 |
suicide | +2.308 |
ulum | +2.160 |
grounds | +2.153 |
nton | +2.126 |
Neg logit contributions | |
mas | -2.831 |
Fall | -2.749 |
seeing | -2.727 |
hey | -2.549 |
作 | -2.524 |
Token | can |
Token ID | 460 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
mas | +2.149 |
Fall | +2.080 |
seeing | +2.062 |
hey | +1.933 |
look | +1.926 |
Neg logit contributions | |
relations | -1.718 |
suicide | -1.652 |
ulum | -1.591 |
nton | -1.564 |
uctor | -1.518 |
Token | play |
Token ID | 711 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
mas | +1.178 |
Fall | +1.144 |
seeing | +1.126 |
hey | +1.054 |
look | +1.045 |
Neg logit contributions | |
relations | -1.166 |
suicide | -1.122 |
ulum | -1.075 |
nton | -1.063 |
grounds | -1.040 |
Token | after |
Token ID | 706 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
mas | +0.412 |
Fall | +0.400 |
seeing | +0.395 |
hey | +0.371 |
look | +0.369 |
Neg logit contributions | |
relations | -0.352 |
suicide | -0.338 |
ulum | -0.321 |
nton | -0.317 |
grounds | -0.312 |
Token | five |
Token ID | 1936 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
mas | +1.596 |
Fall | +1.543 |
seeing | +1.518 |
hey | +1.412 |
look | +1.404 |
Neg logit contributions | |
relations | -1.829 |
suicide | -1.764 |
ulum | -1.702 |
nton | -1.682 |
grounds | -1.641 |
Token | minutes |
Token ID | 2431 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
relations | +1.391 |
suicide | +1.330 |
ulum | +1.254 |
nton | +1.241 |
grounds | +1.221 |
Neg logit contributions | |
mas | -1.979 |
Fall | -1.932 |
seeing | -1.904 |
hey | -1.797 |
look | -1.784 |
Token | of |
Token ID | 286 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
relations | +2.418 |
suicide | +2.309 |
ulum | +2.163 |
grounds | +2.140 |
nton | +2.138 |
Neg logit contributions | |
mas | -3.416 |
Fall | -3.345 |
seeing | -3.270 |
hey | -3.104 |
look | -3.093 |
Token | warm |
Token ID | 5814 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
relations | +1.625 |
suicide | +1.553 |
ulum | +1.458 |
nton | +1.437 |
grounds | +1.435 |
Neg logit contributions | |
mas | -2.046 |
Fall | -1.995 |
seeing | -1.951 |
hey | -1.845 |
look | -1.838 |
Token | , |
Token ID | 11 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
relations | +3.290 |
suicide | +3.118 |
grounds | +2.783 |
nton | +2.736 |
ulum | +2.736 |
Neg logit contributions | |
mas | -7.267 |
Fall | -7.056 |
seeing | -6.948 |
hey | -6.682 |
look | -6.619 |
Token | rather |
Token ID | 2138 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
relations | +1.326 |
suicide | +1.263 |
ulum | +1.177 |
nton | +1.174 |
grounds | +1.157 |
Neg logit contributions | |
mas | -1.591 |
Fall | -1.545 |
seeing | -1.510 |
hey | -1.427 |
look | -1.413 |
Token | than |
Token ID | 621 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
relations | +0.516 |
suicide | +0.492 |
ulum | +0.460 |
nton | +0.456 |
grounds | +0.450 |
Neg logit contributions | |
mas | -0.716 |
Fall | -0.700 |
seeing | -0.686 |
hey | -0.652 |
look | -0.649 |
Token | pushing |
Token ID | 7796 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
mas | +3.813 |
Fall | +3.688 |
seeing | +3.658 |
look | +3.417 |
hey | +3.414 |
Neg logit contributions | |
relations | -3.250 |
suicide | -3.126 |
ulum | -3.080 |
nton | -3.026 |
uctor | -2.927 |
Token | a |
Token ID | 257 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
relations | +0.501 |
suicide | +0.480 |
ulum | +0.455 |
nton | +0.451 |
grounds | +0.444 |
Neg logit contributions | |
mas | -0.545 |
Fall | -0.532 |
seeing | -0.523 |
hey | -0.492 |
look | -0.489 |
Token | program |
Token ID | 1430 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
mas | +0.252 |
Fall | +0.245 |
seeing | +0.242 |
hey | +0.228 |
look | +0.227 |
Neg logit contributions | |
relations | -0.195 |
suicide | -0.186 |
ulum | -0.177 |
nton | -0.175 |
grounds | -0.170 |
Token | he |
Token ID | 339 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
relations | +1.044 |
suicide | +1.009 |
ulum | +0.957 |
nton | +0.941 |
grounds | +0.932 |
Neg logit contributions | |
mas | -1.018 |
Fall | -1.011 |
seeing | -0.985 |
look | -0.917 |
hey | -0.915 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
mas | +2.170 |
Fall | +2.091 |
seeing | +2.074 |
hey | +1.967 |
look | +1.954 |
Neg logit contributions | |
relations | -1.542 |
suicide | -1.480 |
ulum | -1.419 |
nton | -1.390 |
uctor | -1.345 |
Token | was |
Token ID | 373 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
relations | +1.339 |
suicide | +1.281 |
ulum | +1.185 |
grounds | +1.169 |
nton | +1.159 |
Neg logit contributions | |
mas | -1.892 |
Fall | -1.852 |
seeing | -1.818 |
hey | -1.719 |
look | -1.702 |
Token | rational |
Token ID | 9377 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
relations | +2.535 |
suicide | +2.473 |
grounds | +2.271 |
ulum | +2.267 |
nton | +2.235 |
Neg logit contributions | |
mas | -2.815 |
Fall | -2.749 |
seeing | -2.692 |
look | -2.530 |
hey | -2.527 |
Token | over |
Token ID | 625 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
relations | +5.773 |
suicide | +5.425 |
grounds | +5.047 |
ulum | +4.933 |
nton | +4.782 |
Neg logit contributions | |
mas | -7.929 |
Fall | -7.882 |
seeing | -7.631 |
look | -7.277 |
hey | -7.253 |
Token |
|
Token ID | 198 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
relations | +1.038 |
suicide | +0.986 |
ulum | +0.939 |
nton | +0.928 |
grounds | +0.902 |
Neg logit contributions | |
mas | -1.670 |
Fall | -1.627 |
seeing | -1.608 |
hey | -1.519 |
look | -1.507 |
Token | Tomorrow |
Token ID | 49488 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
mas | +0.222 |
Fall | +0.212 |
seeing | +0.210 |
hey | +0.193 |
look | +0.191 |
Neg logit contributions | |
relations | -0.306 |
suicide | -0.295 |
ulum | -0.286 |
nton | -0.284 |
grounds | -0.277 |
Token | � |
Token ID | 447 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
relations | +0.643 |
suicide | +0.611 |
ulum | +0.579 |
nton | +0.569 |
grounds | +0.554 |
Neg logit contributions | |
mas | -1.019 |
Fall | -0.994 |
seeing | -0.980 |
hey | -0.930 |
look | -0.923 |
Token | � |
Token ID | 247 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
relations | +1.633 |
suicide | +1.575 |
ulum | +1.527 |
nton | +1.498 |
grounds | +1.483 |
Neg logit contributions | |
mas | -1.278 |
Fall | -1.235 |
seeing | -1.216 |
hey | -1.121 |
look | -1.114 |
Token | s |
Token ID | 82 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
mas | +0.229 |
Fall | +0.222 |
seeing | +0.218 |
hey | +0.205 |
look | +0.204 |
Neg logit contributions | |
relations | -0.208 |
suicide | -0.200 |
ulum | -0.191 |
nton | -0.189 |
grounds | -0.184 |
Token | stage |
Token ID | 3800 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
relations | +0.520 |
suicide | +0.501 |
ulum | +0.475 |
nton | +0.465 |
grounds | +0.462 |
Neg logit contributions | |
mas | -0.573 |
Fall | -0.557 |
seeing | -0.547 |
hey | -0.513 |
look | -0.509 |
Token | covers |
Token ID | 8698 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
relations | +1.579 |
suicide | +1.490 |
ulum | +1.409 |
nton | +1.365 |
grounds | +1.364 |
Neg logit contributions | |
mas | -2.564 |
Fall | -2.495 |
seeing | -2.451 |
hey | -2.338 |
hell | -2.307 |
Token | 130 |
Token ID | 11323 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
mas | +1.114 |
Fall | +1.080 |
seeing | +1.062 |
hey | +0.996 |
look | +0.987 |
Neg logit contributions | |
relations | -1.118 |
suicide | -1.075 |
ulum | -1.030 |
nton | -1.017 |
grounds | -0.999 |
Token | kilometres |
Token ID | 23990 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
relations | +0.290 |
suicide | +0.279 |
ulum | +0.266 |
nton | +0.262 |
grounds | +0.259 |
Neg logit contributions | |
mas | -0.311 |
Fall | -0.304 |
seeing | -0.300 |
hey | -0.281 |
look | -0.279 |
Token | to |
Token ID | 284 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
relations | +0.259 |
suicide | +0.247 |
ulum | +0.236 |
nton | +0.231 |
grounds | +0.228 |
Neg logit contributions | |
mas | -0.324 |
Fall | -0.318 |
seeing | -0.310 |
hey | -0.294 |
look | -0.292 |
Token | Tan |
Token ID | 11818 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
relations | +1.363 |
suicide | +1.305 |
ulum | +1.238 |
grounds | +1.206 |
nton | +1.200 |
Neg logit contributions | |
mas | -1.390 |
Fall | -1.348 |
seeing | -1.332 |
hey | -1.256 |
作 | -1.220 |
Token | proves |
Token ID | 17021 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
mas | +3.459 |
Fall | +3.322 |
seeing | +3.314 |
look | +3.107 |
hey | +3.094 |
Neg logit contributions | |
relations | -2.449 |
suicide | -2.345 |
ulum | -2.254 |
nton | -2.229 |
uctor | -2.137 |
Token | to |
Token ID | 284 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
relations | +2.012 |
suicide | +1.968 |
grounds | +1.822 |
ulum | +1.821 |
nton | +1.783 |
Neg logit contributions | |
mas | -2.299 |
Fall | -2.255 |
seeing | -2.211 |
hey | -2.099 |
look | -2.088 |
Token | be |
Token ID | 307 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
relations | +0.997 |
suicide | +0.958 |
ulum | +0.909 |
nton | +0.889 |
grounds | +0.884 |
Neg logit contributions | |
mas | -1.085 |
Fall | -1.058 |
seeing | -1.042 |
hey | -0.979 |
look | -0.973 |
Token | wrong |
Token ID | 2642 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
relations | +1.838 |
suicide | +1.788 |
ulum | +1.665 |
grounds | +1.646 |
nton | +1.637 |
Neg logit contributions | |
mas | -2.241 |
Fall | -2.196 |
seeing | -2.153 |
hey | -2.044 |
look | -2.038 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
relations | +1.637 |
suicide | +1.555 |
ulum | +1.471 |
nton | +1.460 |
grounds | +1.434 |
Neg logit contributions | |
mas | -2.329 |
Fall | -2.287 |
seeing | -2.235 |
hey | -2.132 |
look | -2.114 |
Token |
|
Token ID | 198 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
relations | +1.072 |
suicide | +1.025 |
ulum | +0.975 |
nton | +0.963 |
grounds | +0.949 |
Neg logit contributions | |
mas | -1.323 |
Fall | -1.289 |
seeing | -1.270 |
hey | -1.195 |
look | -1.184 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
relations | +0.822 |
suicide | +0.782 |
ulum | +0.745 |
nton | +0.736 |
grounds | +0.714 |
Neg logit contributions | |
mas | -1.277 |
Fall | -1.245 |
seeing | -1.228 |
hey | -1.162 |
look | -1.153 |
Token | � |
Token ID | 447 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
mas | +0.271 |
Fall | +0.261 |
seeing | +0.257 |
hey | +0.238 |
look | +0.237 |
Neg logit contributions | |
relations | -0.333 |
suicide | -0.321 |
ulum | -0.310 |
nton | -0.307 |
grounds | -0.300 |
Token | � |
Token ID | 246 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
relations | +3.426 |
suicide | +3.314 |
ulum | +3.161 |
nton | +3.103 |
grounds | +3.071 |
Neg logit contributions | |
mas | -3.224 |
Fall | -3.093 |
seeing | -3.050 |
hey | -2.852 |
look | -2.851 |
Token | He |
Token ID | 1544 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
relations | +3.991 |
suicide | +3.846 |
ulum | +3.692 |
nton | +3.671 |
grounds | +3.632 |
Neg logit contributions | |
mas | -2.789 |
Fall | -2.635 |
seeing | -2.600 |
achu | -2.360 |
hey | -2.354 |
Token | has |
Token ID | 468 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
relations | +1.006 |
suicide | +0.956 |
ulum | +0.911 |
nton | +0.900 |
grounds | +0.879 |
Neg logit contributions | |
mas | -1.421 |
Fall | -1.404 |
seeing | -1.377 |
hey | -1.293 |
look | -1.283 |
Token | his |
Token ID | 465 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
mas | +1.292 |
Fall | +1.255 |
seeing | +1.236 |
hey | +1.162 |
look | +1.157 |
Neg logit contributions | |
relations | -1.099 |
suicide | -1.054 |
ulum | -1.011 |
nton | -0.999 |
grounds | -0.969 |
Token | tomb |
Token ID | 22234 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
mas | +1.004 |
Fall | +0.977 |
seeing | +0.963 |
hey | +0.909 |
look | +0.903 |
Neg logit contributions | |
relations | -0.790 |
suicide | -0.757 |
ulum | -0.718 |
nton | -0.708 |
grounds | -0.694 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
mas | +0.156 |
Fall | +0.152 |
seeing | +0.149 |
hey | +0.138 |
look | +0.137 |
Neg logit contributions | |
relations | -0.191 |
suicide | -0.185 |
ulum | -0.178 |
nton | -0.175 |
grounds | -0.173 |
Token |
|
Token ID | 198 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
mas | +0.462 |
Fall | +0.449 |
seeing | +0.443 |
hey | +0.415 |
look | +0.412 |
Neg logit contributions | |
relations | -0.427 |
suicide | -0.410 |
ulum | -0.393 |
nton | -0.388 |
grounds | -0.380 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
relations | +0.945 |
suicide | +0.898 |
ulum | +0.853 |
nton | +0.846 |
grounds | +0.821 |
Neg logit contributions | |
mas | -1.483 |
Fall | -1.443 |
seeing | -1.428 |
hey | -1.349 |
look | -1.340 |
Token | A |
Token ID | 32 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
relations | +0.047 |
suicide | +0.046 |
ulum | +0.045 |
nton | +0.044 |
grounds | +0.043 |
Neg logit contributions | |
mas | -0.034 |
Fall | -0.033 |
seeing | -0.032 |
hey | -0.030 |
look | -0.029 |
Token | photograph |
Token ID | 8408 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
relations | +1.137 |
suicide | +1.103 |
ulum | +1.043 |
nton | +1.031 |
grounds | +1.009 |
Neg logit contributions | |
mas | -1.296 |
Fall | -1.270 |
seeing | -1.244 |
hey | -1.169 |
look | -1.157 |
Token | on |
Token ID | 319 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
mas | +1.307 |
Fall | +1.268 |
seeing | +1.246 |
hey | +1.167 |
look | +1.159 |
Neg logit contributions | |
relations | -1.305 |
suicide | -1.256 |
ulum | -1.206 |
nton | -1.192 |
grounds | -1.164 |
Token | the |
Token ID | 262 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
mas | +0.485 |
Fall | +0.472 |
seeing | +0.463 |
hey | +0.436 |
look | +0.430 |
Neg logit contributions | |
relations | -0.453 |
suicide | -0.435 |
ulum | -0.415 |
nton | -0.410 |
grounds | -0.404 |
Token | cover |
Token ID | 3002 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
relations | +0.718 |
suicide | +0.691 |
ulum | +0.654 |
grounds | +0.648 |
nton | +0.641 |
Neg logit contributions | |
mas | -0.828 |
Fall | -0.807 |
seeing | -0.795 |
hey | -0.751 |
look | -0.738 |
Token | of |
Token ID | 286 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
mas | +2.296 |
Fall | +2.211 |
seeing | +2.178 |
look | +2.019 |
hey | +2.015 |
Neg logit contributions | |
relations | -2.740 |
suicide | -2.644 |
ulum | -2.556 |
nton | -2.531 |
uctor | -2.464 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
relations | +0.599 |
suicide | +0.570 |
ulum | +0.542 |
nton | +0.535 |
grounds | +0.520 |
Neg logit contributions | |
mas | -0.924 |
Fall | -0.901 |
seeing | -0.889 |
hey | -0.841 |
look | -0.835 |
Token | Article |
Token ID | 14906 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
mas | +0.262 |
Fall | +0.249 |
seeing | +0.246 |
hey | +0.224 |
look | +0.222 |
Neg logit contributions | |
relations | -0.409 |
suicide | -0.395 |
ulum | -0.384 |
nton | -0.382 |
grounds | -0.373 |
Token | IV |
Token ID | 8363 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
mas | +2.555 |
Fall | +2.468 |
seeing | +2.411 |
look | +2.225 |
hey | +2.220 |
Neg logit contributions | |
relations | -3.107 |
suicide | -3.022 |
ulum | -2.927 |
nton | -2.920 |
EStreamFrame | -2.815 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
relations | +1.581 |
suicide | +1.505 |
ulum | +1.416 |
nton | +1.395 |
grounds | +1.368 |
Neg logit contributions | |
mas | -2.551 |
Fall | -2.484 |
seeing | -2.459 |
hey | -2.331 |
look | -2.313 |
Token | Section |
Token ID | 7275 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
mas | +0.917 |
Fall | +0.895 |
seeing | +0.882 |
hey | +0.837 |
look | +0.832 |
Neg logit contributions | |
relations | -0.584 |
suicide | -0.556 |
ulum | -0.527 |
nton | -0.519 |
grounds | -0.503 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
mas | +1.873 |
Fall | +1.789 |
seeing | +1.766 |
look | +1.627 |
hey | +1.626 |
Neg logit contributions | |
relations | -2.565 |
suicide | -2.487 |
ulum | -2.422 |
nton | -2.390 |
uctor | -2.330 |
Token | begins |
Token ID | 6140 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
relations | +4.566 |
suicide | +4.334 |
grounds | +4.100 |
ulum | +3.992 |
nton | +3.987 |
Neg logit contributions | |
mas | -7.145 |
Fall | -7.006 |
seeing | -6.890 |
hey | -6.570 |
作 | -6.421 |
Token | with |
Token ID | 351 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
mas | +0.248 |
Fall | +0.242 |
seeing | +0.238 |
hey | +0.225 |
look | +0.224 |
Neg logit contributions | |
relations | -0.188 |
suicide | -0.180 |
ulum | -0.172 |
nton | -0.170 |
grounds | -0.164 |
Token | : |
Token ID | 25 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
relations | +0.157 |
suicide | +0.151 |
ulum | +0.143 |
nton | +0.142 |
grounds | +0.139 |
Neg logit contributions | |
mas | -0.183 |
Fall | -0.178 |
seeing | -0.175 |
hey | -0.165 |
look | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
mas | +1.378 |
Fall | +1.343 |
seeing | +1.322 |
hey | +1.247 |
look | +1.242 |
Neg logit contributions | |
relations | -1.081 |
suicide | -1.036 |
ulum | -0.992 |
nton | -0.983 |
grounds | -0.947 |
Token |
|
Token ID | 198 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
mas | +0.694 |
Fall | +0.677 |
seeing | +0.667 |
hey | +0.630 |
look | +0.628 |
Neg logit contributions | |
relations | -0.503 |
suicide | -0.481 |
ulum | -0.457 |
nton | -0.451 |
grounds | -0.437 |
Token | murder |
Token ID | 5123 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
mas | +3.569 |
Fall | +3.488 |
seeing | +3.454 |
hey | +3.260 |
look | +3.237 |
Neg logit contributions | |
relations | -1.793 |
ulum | -1.694 |
suicide | -1.650 |
nton | -1.649 |
uctor | -1.581 |
Token | only |
Token ID | 691 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
relations | +0.449 |
suicide | +0.428 |
ulum | +0.406 |
nton | +0.401 |
grounds | +0.392 |
Neg logit contributions | |
mas | -0.625 |
Fall | -0.610 |
seeing | -0.601 |
hey | -0.568 |
look | -0.565 |
Token | makes |
Token ID | 1838 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
relations | +0.228 |
suicide | +0.216 |
ulum | +0.204 |
nton | +0.201 |
grounds | +0.199 |
Neg logit contributions | |
mas | -0.339 |
Fall | -0.332 |
seeing | -0.326 |
hey | -0.309 |
look | -0.307 |
Token | sense |
Token ID | 2565 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
relations | +1.828 |
suicide | +1.754 |
grounds | +1.631 |
ulum | +1.623 |
nton | +1.601 |
Neg logit contributions | |
mas | -2.138 |
Fall | -2.094 |
seeing | -2.055 |
hey | -1.955 |
look | -1.925 |
Token | as |
Token ID | 355 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
relations | +0.227 |
suicide | +0.217 |
ulum | +0.207 |
nton | +0.204 |
grounds | +0.200 |
Neg logit contributions | |
mas | -0.276 |
Fall | -0.269 |
seeing | -0.264 |
hey | -0.249 |
look | -0.248 |
Token | youth |
Token ID | 6205 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
relations | +0.163 |
suicide | +0.156 |
ulum | +0.149 |
nton | +0.148 |
grounds | +0.143 |
Neg logit contributions | |
mas | -0.198 |
Fall | -0.193 |
seeing | -0.190 |
hey | -0.179 |
look | -0.178 |
Token | sentence |
Token ID | 6827 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
relations | +5.226 |
suicide | +4.947 |
grounds | +4.624 |
ulum | +4.483 |
nton | +4.450 |
Neg logit contributions | |
mas | -6.715 |
Fall | -6.576 |
seeing | -6.473 |
hey | -6.128 |
look | -6.056 |
Token | . |
Token ID | 13 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
relations | +2.193 |
suicide | +2.085 |
ulum | +1.968 |
nton | +1.928 |
grounds | +1.927 |
Neg logit contributions | |
mas | -2.980 |
Fall | -2.912 |
seeing | -2.864 |
hey | -2.713 |
look | -2.692 |
Token | And |
Token ID | 843 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
relations | +1.533 |
suicide | +1.466 |
ulum | +1.393 |
nton | +1.374 |
grounds | +1.365 |
Neg logit contributions | |
mas | -1.820 |
Fall | -1.767 |
seeing | -1.750 |
hey | -1.650 |
look | -1.635 |
Token | because |
Token ID | 780 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
relations | +1.094 |
suicide | +1.049 |
ulum | +0.998 |
nton | +0.984 |
grounds | +0.967 |
Neg logit contributions | |
mas | -1.255 |
Fall | -1.220 |
seeing | -1.199 |
hey | -1.129 |
look | -1.122 |
Token | he |
Token ID | 339 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
mas | +1.067 |
Fall | +1.037 |
seeing | +1.021 |
hey | +0.955 |
look | +0.953 |
Neg logit contributions | |
relations | -0.910 |
suicide | -0.874 |
ulum | -0.848 |
nton | -0.846 |
uctor | -0.815 |
Token | pass |
Token ID | 1208 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
relations | +1.557 |
suicide | +1.508 |
ulum | +1.410 |
nton | +1.398 |
grounds | +1.393 |
Neg logit contributions | |
mas | -1.557 |
Fall | -1.517 |
seeing | -1.508 |
hey | -1.403 |
hell | -1.378 |
Token | legislation |
Token ID | 5520 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
relations | +1.909 |
suicide | +1.837 |
ulum | +1.715 |
nton | +1.695 |
grounds | +1.682 |
Neg logit contributions | |
mas | -2.213 |
Fall | -2.157 |
seeing | -2.137 |
hey | -2.009 |
look | -1.984 |
Token | , |
Token ID | 11 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
relations | +0.792 |
suicide | +0.764 |
ulum | +0.728 |
nton | +0.720 |
grounds | +0.710 |
Neg logit contributions | |
mas | -0.729 |
Fall | -0.715 |
seeing | -0.699 |
hey | -0.648 |
look | -0.648 |
Token | � |
Token ID | 447 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
relations | +1.551 |
suicide | +1.484 |
ulum | +1.406 |
nton | +1.377 |
grounds | +1.369 |
Neg logit contributions | |
mas | -1.782 |
Fall | -1.736 |
seeing | -1.717 |
hey | -1.604 |
look | -1.585 |
Token | � |
Token ID | 251 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
relations | +3.253 |
suicide | +3.140 |
ulum | +2.996 |
nton | +2.964 |
grounds | +2.957 |
Neg logit contributions | |
mas | -2.774 |
Fall | -2.661 |
seeing | -2.614 |
hey | -2.419 |
look | -2.406 |
Token | said |
Token ID | 531 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
relations | +3.646 |
suicide | +3.450 |
ulum | +3.202 |
nton | +3.181 |
grounds | +3.145 |
Neg logit contributions | |
mas | -5.364 |
Fall | -5.235 |
seeing | -5.135 |
hey | -4.849 |
look | -4.810 |
Token | Representative |
Token ID | 19920 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
relations | +5.194 |
suicide | +4.901 |
ulum | +4.453 |
grounds | +4.445 |
nton | +4.418 |
Neg logit contributions | |
mas | -7.971 |
Fall | -7.707 |
seeing | -7.599 |
hey | -7.268 |
look | -7.161 |
Token | Baron |
Token ID | 21770 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
relations | +0.802 |
suicide | +0.767 |
ulum | +0.733 |
nton | +0.727 |
grounds | +0.710 |
Neg logit contributions | |
mas | -0.915 |
Fall | -0.893 |
seeing | -0.878 |
hey | -0.826 |
look | -0.821 |
Token | P |
Token ID | 350 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
relations | +2.187 |
suicide | +2.101 |
ulum | +1.993 |
nton | +1.992 |
grounds | +1.942 |
Neg logit contributions | |
mas | -2.584 |
Fall | -2.489 |
seeing | -2.478 |
hey | -2.333 |
look | -2.304 |
Token | . |
Token ID | 13 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
mas | +1.246 |
Fall | +1.206 |
seeing | +1.176 |
hey | +1.121 |
look | +1.112 |
Neg logit contributions | |
relations | -1.054 |
suicide | -0.997 |
ulum | -0.938 |
nton | -0.935 |
grounds | -0.927 |
Token | Hill |
Token ID | 3327 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
relations | +0.015 |
suicide | +0.014 |
ulum | +0.014 |
nton | +0.013 |
grounds | +0.013 |
Neg logit contributions | |
mas | -0.014 |
Fall | -0.014 |
seeing | -0.014 |
hey | -0.013 |
look | -0.013 |
Token | should |
Token ID | 815 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
relations | +1.467 |
suicide | +1.385 |
ulum | +1.287 |
grounds | +1.273 |
nton | +1.273 |
Neg logit contributions | |
mas | -2.408 |
Fall | -2.376 |
seeing | -2.321 |
hey | -2.211 |
look | -2.181 |
Token | not |
Token ID | 407 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
relations | +0.983 |
suicide | +0.952 |
ulum | +0.882 |
nton | +0.879 |
grounds | +0.877 |
Neg logit contributions | |
mas | -1.120 |
Fall | -1.096 |
seeing | -1.086 |
hey | -1.012 |
look | -0.994 |
Token | be |
Token ID | 307 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
relations | +0.855 |
suicide | +0.833 |
ulum | +0.773 |
grounds | +0.770 |
nton | +0.768 |
Neg logit contributions | |
mas | -0.918 |
seeing | -0.892 |
Fall | -0.888 |
hey | -0.821 |
作 | -0.808 |
Token | destroyed |
Token ID | 6572 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
relations | +1.455 |
suicide | +1.407 |
grounds | +1.303 |
ulum | +1.286 |
nton | +1.274 |
Neg logit contributions | |
mas | -1.806 |
Fall | -1.761 |
seeing | -1.742 |
hey | -1.626 |
look | -1.596 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
mas | +0.727 |
Fall | +0.708 |
seeing | +0.697 |
hey | +0.658 |
look | +0.653 |
Neg logit contributions | |
relations | -0.575 |
suicide | -0.550 |
ulum | -0.522 |
nton | -0.514 |
grounds | -0.505 |
Token | submitted |
Token ID | 8948 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
relations | +3.742 |
suicide | +3.570 |
grounds | +3.342 |
ulum | +3.218 |
nton | +3.163 |
Neg logit contributions | |
mas | -4.369 |
Fall | -4.218 |
seeing | -4.200 |
hey | -3.904 |
作 | -3.842 |
Token | that |
Token ID | 326 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
relations | +4.785 |
suicide | +4.603 |
grounds | +4.320 |
ulum | +4.106 |
prayer | +4.055 |
Neg logit contributions | |
mas | -5.795 |
Fall | -5.641 |
seeing | -5.628 |
hey | -5.228 |
look | -5.201 |
Token | he |
Token ID | 339 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
relations | +5.462 |
suicide | +5.211 |
grounds | +4.931 |
ulum | +4.617 |
prayer | +4.563 |
Neg logit contributions | |
mas | -6.700 |
Fall | -6.571 |
seeing | -6.416 |
作 | -6.043 |
hey | -6.033 |
Token | ( |
Token ID | 357 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
relations | +1.443 |
suicide | +1.371 |
ulum | +1.280 |
nton | +1.276 |
grounds | +1.268 |
Neg logit contributions | |
mas | -2.048 |
Fall | -2.022 |
seeing | -1.986 |
hey | -1.863 |
look | -1.846 |
Token | Gh |
Token ID | 41126 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
mas | +1.836 |
Fall | +1.772 |
seeing | +1.736 |
hey | +1.603 |
look | +1.591 |
Neg logit contributions | |
relations | -2.518 |
suicide | -2.439 |
ulum | -2.356 |
nton | -2.334 |
grounds | -2.285 |
Token | ai |
Token ID | 1872 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
mas | +3.907 |
seeing | +3.691 |
Fall | +3.622 |
hey | +3.418 |
look | +3.263 |
Neg logit contributions | |
relations | -7.139 |
suicide | -6.873 |
ulum | -6.571 |
nton | -6.565 |
grounds | -6.536 |
Token | ua |
Token ID | 6413 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
relations | +0.973 |
suicide | +0.917 |
ulum | +0.901 |
nton | +0.863 |
uctor | +0.842 |
Neg logit contributions | |
mas | -1.638 |
Fall | -1.613 |
seeing | -1.593 |
look | -1.499 |
hey | -1.494 |
Token | is |
Token ID | 318 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
relations | +0.341 |
suicide | +0.324 |
ulum | +0.307 |
nton | +0.299 |
grounds | +0.296 |
Neg logit contributions | |
mas | -0.526 |
Fall | -0.512 |
seeing | -0.507 |
hey | -0.479 |
look | -0.474 |
Token | the |
Token ID | 262 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
relations | +2.029 |
suicide | +1.964 |
ulum | +1.849 |
nton | +1.813 |
grounds | +1.805 |
Neg logit contributions | |
mas | -2.413 |
Fall | -2.344 |
seeing | -2.317 |
hey | -2.154 |
look | -2.153 |
Token | first |
Token ID | 717 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
mas | +1.353 |
Fall | +1.312 |
seeing | +1.292 |
hey | +1.207 |
look | +1.198 |
Neg logit contributions | |
relations | -1.365 |
suicide | -1.315 |
ulum | -1.259 |
nton | -1.243 |
grounds | -1.219 |
Token | of |
Token ID | 286 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
relations | +1.013 |
suicide | +0.979 |
ulum | +0.922 |
nton | +0.901 |
grounds | +0.900 |
Neg logit contributions | |
mas | -1.039 |
Fall | -0.999 |
seeing | -0.987 |
hey | -0.918 |
look | -0.903 |
Token | two |
Token ID | 734 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
relations | +2.619 |
suicide | +2.485 |
ulum | +2.375 |
nton | +2.322 |
grounds | +2.305 |
Neg logit contributions | |
mas | -2.709 |
Fall | -2.605 |
seeing | -2.550 |
hey | -2.395 |
hell | -2.366 |
Token | plastic |
Token ID | 7309 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
relations | +6.651 |
suicide | +6.418 |
grounds | +5.888 |
ancest | +5.774 |
oppos | +5.755 |
Neg logit contributions | |
mas | -6.473 |
seeing | -6.187 |
Fall | -6.159 |
urrection | -5.733 |
achu | -5.666 |
Token | yo |
Token ID | 27406 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
relations | +5.804 |
suicide | +5.622 |
ulum | +5.193 |
grounds | +5.130 |
nton | +5.040 |
Neg logit contributions | |
mas | -5.550 |
Fall | -5.434 |
seeing | -5.406 |
hey | -4.948 |
look | -4.892 |
Token | - |
Token ID | 12 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
mas | +2.571 |
Fall | +2.498 |
seeing | +2.457 |
hey | +2.365 |
look | +2.336 |
Neg logit contributions | |
relations | -1.405 |
suicide | -1.340 |
ulum | -1.270 |
nton | -1.247 |
uctor | -1.193 |
Token | yo |
Token ID | 8226 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
mas | +4.366 |
Fall | +4.108 |
seeing | +4.068 |
hey | +3.873 |
look | +3.857 |
Neg logit contributions | |
relations | -4.298 |
suicide | -4.183 |
ulum | -3.984 |
nton | -3.970 |
ancest | -3.868 |
Token | in |
Token ID | 287 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
relations | +0.040 |
suicide | +0.038 |
ulum | +0.036 |
nton | +0.036 |
grounds | +0.035 |
Neg logit contributions | |
mas | -0.048 |
Fall | -0.046 |
seeing | -0.046 |
hey | -0.043 |
look | -0.043 |