Token | ) |
Token ID | 8 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
edom | +2.096 |
Afric | +1.962 |
Ange | +1.914 |
IOR | +1.856 |
trump | +1.792 |
Neg logit contributions | |
interstitial | -2.958 |
farious | -2.855 |
benefit | -2.816 |
propri | -2.655 |
oult | -2.632 |
Token | could |
Token ID | 714 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
edom | +0.890 |
Afric | +0.830 |
Ange | +0.816 |
IOR | +0.808 |
trump | +0.793 |
Neg logit contributions | |
interstitial | -0.862 |
farious | -0.843 |
benefit | -0.815 |
propri | -0.767 |
oult | -0.753 |
Token | be |
Token ID | 307 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
edom | +1.343 |
Afric | +1.219 |
IOR | +1.206 |
trump | +1.195 |
Ange | +1.194 |
Neg logit contributions | |
interstitial | -1.711 |
farious | -1.661 |
benefit | -1.587 |
propri | -1.533 |
oult | -1.493 |
Token | re |
Token ID | 302 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
edom | +0.758 |
Afric | +0.706 |
Ange | +0.691 |
IOR | +0.684 |
trump | +0.667 |
Neg logit contributions | |
interstitial | -0.865 |
farious | -0.848 |
benefit | -0.827 |
propri | -0.782 |
oult | -0.769 |
Token | ph |
Token ID | 746 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
interstitial | +2.496 |
farious | +2.435 |
benefit | +2.396 |
propri | +2.278 |
oult | +2.219 |
Neg logit contributions | |
edom | -2.211 |
Afric | -2.067 |
Ange | -2.029 |
IOR | -2.016 |
trump | -1.931 |
Token | r |
Token ID | 81 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
interstitial | +1.712 |
farious | +1.654 |
benefit | +1.608 |
propri | +1.506 |
oult | +1.445 |
Neg logit contributions | |
edom | -2.592 |
Afric | -2.447 |
Ange | -2.406 |
IOR | -2.394 |
trump | -2.331 |
Token | ased |
Token ID | 839 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
interstitial | +6.084 |
benefit | +5.911 |
farious | +5.828 |
oult | +5.579 |
ayer | +5.478 |
Neg logit contributions | |
edom | -8.702 |
Afric | -8.527 |
IOR | -8.248 |
Ange | -7.987 |
BuyableInstoreAndOnline | -7.844 |
Token | as |
Token ID | 355 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
interstitial | +0.783 |
farious | +0.763 |
benefit | +0.746 |
propri | +0.709 |
oult | +0.688 |
Neg logit contributions | |
edom | -0.766 |
Afric | -0.716 |
Ange | -0.701 |
IOR | -0.696 |
trump | -0.673 |
Token | � |
Token ID | 564 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
interstitial | +1.661 |
farious | +1.623 |
benefit | +1.589 |
propri | +1.528 |
oult | +1.482 |
Neg logit contributions | |
edom | -1.288 |
Afric | -1.189 |
Ange | -1.159 |
IOR | -1.154 |
trump | -1.106 |
Token | � |
Token ID | 246 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
interstitial | +1.938 |
farious | +1.903 |
benefit | +1.865 |
propri | +1.786 |
oult | +1.746 |
Neg logit contributions | |
edom | -1.230 |
Afric | -1.128 |
Ange | -1.098 |
IOR | -1.081 |
trump | -1.034 |
Token | del |
Token ID | 12381 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
interstitial | +1.858 |
farious | +1.811 |
benefit | +1.777 |
propri | +1.692 |
oult | +1.655 |
Neg logit contributions | |
edom | -1.480 |
Afric | -1.378 |
Ange | -1.343 |
IOR | -1.324 |
trump | -1.283 |
Token | doi |
Token ID | 34023 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
interstitial | +3.346 |
farious | +3.229 |
benefit | +3.164 |
propri | +2.970 |
oult | +2.866 |
Neg logit contributions | |
edom | -5.053 |
Afric | -4.835 |
Ange | -4.736 |
IOR | -4.717 |
trump | -4.555 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
interstitial | +3.566 |
benefit | +3.504 |
farious | +3.497 |
549 | +3.252 |
propri | +3.252 |
Neg logit contributions | |
edom | -4.108 |
Afric | -3.890 |
Ange | -3.703 |
IOR | -3.680 |
trump | -3.567 |
Token | org |
Token ID | 2398 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
interstitial | +4.949 |
farious | +4.766 |
benefit | +4.753 |
propri | +4.440 |
549 | +4.327 |
Neg logit contributions | |
edom | -5.856 |
Afric | -5.539 |
Ange | -5.416 |
IOR | -5.371 |
trump | -5.171 |
Token | / |
Token ID | 14 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
interstitial | +3.829 |
farious | +3.757 |
benefit | +3.755 |
propri | +3.580 |
549 | +3.541 |
Neg logit contributions | |
edom | -2.731 |
Afric | -2.495 |
Ange | -2.414 |
IOR | -2.389 |
trump | -2.269 |
Token | 10 |
Token ID | 940 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
interstitial | +3.911 |
farious | +3.698 |
benefit | +3.684 |
propri | +3.328 |
oult | +3.233 |
Neg logit contributions | |
edom | -7.534 |
Afric | -7.175 |
Ange | -7.078 |
IOR | -6.974 |
trump | -6.842 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
interstitial | +3.331 |
farious | +3.251 |
benefit | +3.242 |
propri | +3.049 |
549 | +3.022 |
Neg logit contributions | |
edom | -3.613 |
Afric | -3.390 |
Ange | -3.287 |
IOR | -3.235 |
trump | -3.162 |
Token | 13 |
Token ID | 1485 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
benefit | +3.429 |
interstitial | +3.390 |
farious | +2.980 |
propri | +2.881 |
549 | +2.857 |
Neg logit contributions | |
edom | -11.300 |
Afric | -11.052 |
Ange | -10.722 |
IOR | -10.557 |
trump | -10.354 |
Token | 71 |
Token ID | 4869 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
interstitial | +2.859 |
benefit | +2.723 |
farious | +2.688 |
propri | +2.490 |
oult | +2.438 |
Neg logit contributions | |
edom | -4.255 |
Afric | -4.031 |
Ange | -3.941 |
IOR | -3.870 |
trump | -3.780 |
Token | / |
Token ID | 14 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
interstitial | +3.233 |
farious | +3.143 |
benefit | +3.134 |
propri | +2.976 |
549 | +2.953 |
Neg logit contributions | |
edom | -2.221 |
Afric | -2.036 |
Ange | -1.958 |
IOR | -1.942 |
trump | -1.844 |
Token | journal |
Token ID | 24891 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
interstitial | +1.933 |
farious | +1.837 |
benefit | +1.808 |
propri | +1.681 |
oult | +1.631 |
Neg logit contributions | |
edom | -3.159 |
Afric | -2.979 |
Ange | -2.928 |
IOR | -2.905 |
trump | -2.839 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
interstitial | +3.326 |
farious | +3.237 |
benefit | +3.201 |
propri | +3.017 |
oult | +2.956 |
Neg logit contributions | |
edom | -3.356 |
Afric | -3.158 |
Ange | -3.057 |
IOR | -3.024 |
trump | -2.933 |
Token | it |
Token ID | 340 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
interstitial | +0.675 |
farious | +0.660 |
benefit | +0.647 |
propri | +0.621 |
oult | +0.604 |
Neg logit contributions | |
edom | -0.525 |
Afric | -0.485 |
Ange | -0.472 |
IOR | -0.470 |
trump | -0.450 |
Token | 's |
Token ID | 338 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
edom | +0.429 |
Afric | +0.400 |
Ange | +0.393 |
IOR | +0.391 |
trump | +0.380 |
Neg logit contributions | |
interstitial | -0.427 |
farious | -0.415 |
benefit | -0.405 |
propri | -0.382 |
oult | -0.372 |
Token | not |
Token ID | 407 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
interstitial | +0.711 |
farious | +0.693 |
benefit | +0.678 |
propri | +0.646 |
oult | +0.627 |
Neg logit contributions | |
edom | -0.664 |
Afric | -0.619 |
Ange | -0.605 |
IOR | -0.602 |
trump | -0.581 |
Token | as |
Token ID | 355 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
interstitial | +0.754 |
farious | +0.735 |
benefit | +0.720 |
propri | +0.686 |
oult | +0.667 |
Neg logit contributions | |
edom | -0.682 |
Afric | -0.635 |
Ange | -0.621 |
IOR | -0.618 |
trump | -0.595 |
Token | f |
Token ID | 277 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
interstitial | +3.124 |
farious | +3.091 |
benefit | +3.004 |
propri | +2.920 |
oult | +2.855 |
Neg logit contributions | |
edom | -2.905 |
Afric | -2.685 |
Ange | -2.603 |
IOR | -2.592 |
trump | -2.498 |
Token | **** |
Token ID | 2466 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
interstitial | +3.170 |
farious | +3.140 |
benefit | +3.058 |
propri | +2.899 |
oult | +2.843 |
Neg logit contributions | |
edom | -3.031 |
Afric | -2.876 |
Ange | -2.802 |
IOR | -2.788 |
trump | -2.685 |
Token | d |
Token ID | 67 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
farious | +6.237 |
interstitial | +6.213 |
benefit | +6.017 |
ayer | +5.552 |
propri | +5.525 |
Neg logit contributions | |
edom | -7.895 |
Afric | -7.674 |
IOR | -7.446 |
Ange | -7.305 |
TPS | -7.093 |
Token | up |
Token ID | 510 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
interstitial | +4.100 |
farious | +4.076 |
benefit | +3.954 |
propri | +3.849 |
oult | +3.684 |
Neg logit contributions | |
edom | -5.184 |
Afric | -4.832 |
IOR | -4.675 |
Ange | -4.656 |
trump | -4.512 |
Token | as |
Token ID | 355 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
interstitial | +2.168 |
farious | +2.127 |
benefit | +2.086 |
propri | +2.001 |
oult | +1.925 |
Neg logit contributions | |
edom | -2.540 |
Afric | -2.364 |
IOR | -2.301 |
Ange | -2.298 |
trump | -2.210 |
Token | to |
Token ID | 284 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
interstitial | +2.358 |
farious | +2.301 |
benefit | +2.261 |
propri | +2.196 |
oult | +2.109 |
Neg logit contributions | |
edom | -1.974 |
Afric | -1.820 |
IOR | -1.762 |
Ange | -1.753 |
trump | -1.674 |
Token | not |
Token ID | 407 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
interstitial | +1.366 |
farious | +1.334 |
benefit | +1.310 |
propri | +1.253 |
oult | +1.214 |
Neg logit contributions | |
edom | -1.296 |
Afric | -1.209 |
Ange | -1.178 |
IOR | -1.174 |
trump | -1.126 |
Token | 414 |
Token ID | 37309 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
interstitial | +2.744 |
farious | +2.629 |
benefit | +2.622 |
549 | +2.445 |
propri | +2.414 |
Neg logit contributions | |
edom | -5.081 |
Afric | -4.781 |
Ange | -4.690 |
IOR | -4.655 |
trump | -4.572 |
Token | ; |
Token ID | 26 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
interstitial | +0.899 |
farious | +0.879 |
benefit | +0.865 |
propri | +0.827 |
oult | +0.804 |
Neg logit contributions | |
edom | -0.742 |
Afric | -0.686 |
Ange | -0.669 |
IOR | -0.668 |
trump | -0.641 |
Token | doi |
Token ID | 23899 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
interstitial | +0.365 |
farious | +0.356 |
benefit | +0.349 |
propri | +0.334 |
oult | +0.325 |
Neg logit contributions | |
edom | -0.283 |
Afric | -0.262 |
Ange | -0.256 |
IOR | -0.254 |
trump | -0.244 |
Token | : |
Token ID | 25 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
interstitial | +2.289 |
farious | +2.224 |
benefit | +2.201 |
propri | +2.080 |
549 | +2.032 |
Neg logit contributions | |
edom | -2.295 |
Afric | -2.139 |
Ange | -2.085 |
IOR | -2.075 |
trump | -2.004 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
interstitial | +5.588 |
farious | +5.350 |
benefit | +5.289 |
propri | +5.158 |
549 | +4.995 |
Neg logit contributions | |
edom | -8.047 |
Afric | -7.375 |
IOR | -7.361 |
Ange | -7.226 |
trump | -7.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
interstitial | +3.966 |
benefit | +3.868 |
farious | +3.865 |
549 | +3.656 |
propri | +3.653 |
Neg logit contributions | |
edom | -4.581 |
Afric | -4.233 |
Ange | -4.094 |
IOR | -4.079 |
trump | -3.978 |
Token | 10 |
Token ID | 940 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
interstitial | +4.060 |
benefit | +4.005 |
549 | +3.752 |
farious | +3.750 |
propri | +3.502 |
Neg logit contributions | |
edom | -10.178 |
Afric | -9.541 |
Ange | -9.465 |
IOR | -9.361 |
trump | -9.160 |
Token | 71 |
Token ID | 4869 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
interstitial | +3.143 |
farious | +3.049 |
benefit | +2.970 |
propri | +2.803 |
oult | +2.704 |
Neg logit contributions | |
edom | -4.067 |
Afric | -3.830 |
Ange | -3.759 |
IOR | -3.743 |
trump | -3.630 |
Token | / |
Token ID | 14 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
interstitial | +4.143 |
benefit | +4.045 |
farious | +4.042 |
549 | +3.840 |
propri | +3.823 |
Neg logit contributions | |
edom | -3.052 |
Afric | -2.790 |
Ange | -2.664 |
IOR | -2.631 |
trump | -2.524 |
Token | Z |
Token ID | 57 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
interstitial | +2.044 |
farious | +1.980 |
benefit | +1.935 |
propri | +1.826 |
oult | +1.768 |
Neg logit contributions | |
edom | -2.551 |
Afric | -2.398 |
Ange | -2.354 |
IOR | -2.339 |
trump | -2.272 |
Token | O |
Token ID | 46 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
interstitial | +1.199 |
farious | +1.168 |
benefit | +1.156 |
propri | +1.093 |
oult | +1.072 |
Neg logit contributions | |
edom | -1.121 |
Afric | -1.049 |
Ange | -1.022 |
IOR | -1.007 |
trump | -0.980 |
Token | I |
Token ID | 314 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
interstitial | +0.253 |
farious | +0.248 |
benefit | +0.242 |
propri | +0.232 |
oult | +0.226 |
Neg logit contributions | |
edom | -0.192 |
Afric | -0.177 |
Ange | -0.173 |
IOR | -0.172 |
trump | -0.166 |
Token | � |
Token ID | 447 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
edom | +1.489 |
Afric | +1.361 |
Ange | +1.348 |
IOR | +1.343 |
trump | +1.324 |
Neg logit contributions | |
interstitial | -1.659 |
farious | -1.639 |
benefit | -1.569 |
propri | -1.498 |
oult | -1.459 |
Token | � |
Token ID | 247 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
interstitial | +0.777 |
farious | +0.749 |
benefit | +0.733 |
propri | +0.691 |
oult | +0.667 |
Neg logit contributions | |
edom | -1.001 |
Afric | -0.944 |
Ange | -0.924 |
IOR | -0.919 |
trump | -0.892 |
Token | m |
Token ID | 76 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
edom | +0.142 |
Afric | +0.132 |
Ange | +0.129 |
IOR | +0.128 |
trump | +0.124 |
Neg logit contributions | |
interstitial | -0.163 |
farious | -0.159 |
benefit | -0.155 |
propri | -0.148 |
oult | -0.144 |
Token | paraph |
Token ID | 38624 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
edom | +0.124 |
Afric | +0.117 |
Ange | +0.116 |
IOR | +0.114 |
trump | +0.113 |
Neg logit contributions | |
interstitial | -0.077 |
farious | -0.075 |
benefit | -0.072 |
propri | -0.066 |
oult | -0.064 |
Token | r |
Token ID | 81 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
edom | +0.653 |
Afric | +0.597 |
Ange | +0.596 |
IOR | +0.588 |
trump | +0.583 |
Neg logit contributions | |
interstitial | -0.512 |
farious | -0.505 |
benefit | -0.497 |
propri | -0.462 |
oult | -0.449 |
Token | asing |
Token ID | 2313 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
interstitial | +5.436 |
benefit | +5.276 |
farious | +5.182 |
ayer | +4.878 |
oult | +4.834 |
Neg logit contributions | |
edom | -8.283 |
Afric | -8.239 |
IOR | -7.854 |
Ange | -7.680 |
trump | -7.622 |
Token | here |
Token ID | 994 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
interstitial | +0.720 |
farious | +0.705 |
benefit | +0.685 |
propri | +0.649 |
oult | +0.638 |
Neg logit contributions | |
edom | -0.655 |
Afric | -0.608 |
Ange | -0.598 |
IOR | -0.591 |
trump | -0.575 |
Token | , |
Token ID | 11 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
interstitial | +0.314 |
farious | +0.307 |
benefit | +0.299 |
propri | +0.285 |
oult | +0.279 |
Neg logit contributions | |
edom | -0.276 |
Afric | -0.255 |
Ange | -0.250 |
IOR | -0.249 |
trump | -0.241 |
Token | that |
Token ID | 326 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
edom | +1.472 |
Afric | +1.354 |
Ange | +1.321 |
IOR | +1.309 |
trump | +1.269 |
Neg logit contributions | |
interstitial | -2.122 |
farious | -2.079 |
benefit | -2.034 |
propri | -1.939 |
oult | -1.913 |
Token | � |
Token ID | 564 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
edom | +0.624 |
Afric | +0.583 |
Ange | +0.571 |
IOR | +0.567 |
trump | +0.551 |
Neg logit contributions | |
interstitial | -0.688 |
farious | -0.675 |
benefit | -0.656 |
propri | -0.621 |
oult | -0.611 |
Token | to |
Token ID | 284 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
interstitial | +0.193 |
farious | +0.188 |
benefit | +0.183 |
propri | +0.174 |
oult | +0.170 |
Neg logit contributions | |
edom | -0.177 |
Afric | -0.164 |
Ange | -0.161 |
IOR | -0.160 |
trump | -0.155 |
Token | be |
Token ID | 307 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
edom | +0.305 |
Afric | +0.283 |
Ange | +0.277 |
IOR | +0.276 |
trump | +0.269 |
Neg logit contributions | |
interstitial | -0.328 |
farious | -0.318 |
benefit | -0.309 |
propri | -0.295 |
oult | -0.287 |
Token | included |
Token ID | 3017 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
edom | +0.141 |
Afric | +0.132 |
Ange | +0.129 |
IOR | +0.128 |
trump | +0.124 |
Neg logit contributions | |
interstitial | -0.163 |
farious | -0.158 |
benefit | -0.154 |
propri | -0.146 |
oult | -0.144 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
interstitial | +1.724 |
farious | +1.680 |
benefit | +1.646 |
propri | +1.563 |
oult | +1.513 |
Neg logit contributions | |
edom | -1.831 |
Afric | -1.715 |
Ange | -1.678 |
IOR | -1.670 |
trump | -1.611 |
Token | for |
Token ID | 329 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
interstitial | +0.594 |
farious | +0.579 |
benefit | +0.564 |
propri | +0.538 |
oult | +0.525 |
Neg logit contributions | |
edom | -0.505 |
Afric | -0.470 |
Ange | -0.459 |
IOR | -0.456 |
trump | -0.441 |
Token | God |
Token ID | 1793 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
interstitial | +2.524 |
farious | +2.477 |
benefit | +2.448 |
propri | +2.334 |
oult | +2.223 |
Neg logit contributions | |
edom | -2.578 |
Afric | -2.411 |
IOR | -2.361 |
Ange | -2.356 |
trump | -2.254 |
Token | � |
Token ID | 447 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
benefit | +5.950 |
farious | +5.856 |
interstitial | +5.736 |
propri | +5.590 |
ayer | +5.336 |
Neg logit contributions | |
edom | -7.621 |
Afric | -7.433 |
IOR | -7.344 |
Ange | -7.239 |
TPS | -6.725 |
Token | � |
Token ID | 247 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
interstitial | +0.612 |
farious | +0.597 |
benefit | +0.579 |
propri | +0.547 |
oult | +0.528 |
Neg logit contributions | |
edom | -0.779 |
Afric | -0.732 |
Ange | -0.721 |
IOR | -0.717 |
trump | -0.696 |
Token | s |
Token ID | 82 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
interstitial | +0.992 |
farious | +0.969 |
benefit | +0.925 |
propri | +0.883 |
oult | +0.853 |
Neg logit contributions | |
edom | -1.205 |
Afric | -1.116 |
Ange | -1.108 |
IOR | -1.101 |
trump | -1.078 |
Token | sake |
Token ID | 11060 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
interstitial | +0.918 |
farious | +0.875 |
benefit | +0.835 |
propri | +0.774 |
oult | +0.744 |
Neg logit contributions | |
edom | -1.891 |
Afric | -1.802 |
Ange | -1.772 |
IOR | -1.760 |
trump | -1.728 |
Token | ." |
Token ID | 526 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
edom | +0.997 |
Afric | +0.933 |
Ange | +0.918 |
IOR | +0.913 |
trump | +0.890 |
Neg logit contributions | |
interstitial | -0.862 |
farious | -0.828 |
benefit | -0.806 |
propri | -0.762 |
oult | -0.741 |
Token | 401 |
Token ID | 22219 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
interstitial | +0.771 |
farious | +0.754 |
benefit | +0.737 |
propri | +0.703 |
oult | +0.685 |
Neg logit contributions | |
edom | -0.629 |
Afric | -0.583 |
Ange | -0.570 |
IOR | -0.565 |
trump | -0.544 |
Token | - |
Token ID | 12 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
interstitial | +2.838 |
farious | +2.789 |
benefit | +2.743 |
propri | +2.584 |
549 | +2.567 |
Neg logit contributions | |
edom | -3.699 |
Afric | -3.475 |
Ange | -3.410 |
IOR | -3.394 |
trump | -3.300 |
Token | 414 |
Token ID | 37309 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
interstitial | +2.744 |
farious | +2.629 |
benefit | +2.622 |
549 | +2.445 |
propri | +2.414 |
Neg logit contributions | |
edom | -5.081 |
Afric | -4.781 |
Ange | -4.690 |
IOR | -4.655 |
trump | -4.572 |
Token | ; |
Token ID | 26 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
interstitial | +0.899 |
farious | +0.879 |
benefit | +0.865 |
propri | +0.827 |
oult | +0.804 |
Neg logit contributions | |
edom | -0.742 |
Afric | -0.686 |
Ange | -0.669 |
IOR | -0.668 |
trump | -0.641 |
Token | doi |
Token ID | 23899 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
interstitial | +0.365 |
farious | +0.356 |
benefit | +0.349 |
propri | +0.334 |
oult | +0.325 |
Neg logit contributions | |
edom | -0.283 |
Afric | -0.262 |
Ange | -0.256 |
IOR | -0.254 |
trump | -0.244 |
Token | : |
Token ID | 25 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
interstitial | +2.289 |
farious | +2.224 |
benefit | +2.201 |
propri | +2.080 |
549 | +2.032 |
Neg logit contributions | |
edom | -2.295 |
Afric | -2.139 |
Ange | -2.085 |
IOR | -2.075 |
trump | -2.004 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
interstitial | +5.588 |
farious | +5.350 |
benefit | +5.289 |
propri | +5.158 |
549 | +4.995 |
Neg logit contributions | |
edom | -8.047 |
Afric | -7.375 |
IOR | -7.361 |
Ange | -7.226 |
trump | -7.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
interstitial | +3.966 |
benefit | +3.868 |
farious | +3.865 |
549 | +3.656 |
propri | +3.653 |
Neg logit contributions | |
edom | -4.581 |
Afric | -4.233 |
Ange | -4.094 |
IOR | -4.079 |
trump | -3.978 |
Token | 10 |
Token ID | 940 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
interstitial | +4.060 |
benefit | +4.005 |
549 | +3.752 |
farious | +3.750 |
propri | +3.502 |
Neg logit contributions | |
edom | -10.178 |
Afric | -9.541 |
Ange | -9.465 |
IOR | -9.361 |
trump | -9.160 |
Token | 71 |
Token ID | 4869 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
interstitial | +3.143 |
farious | +3.049 |
benefit | +2.970 |
propri | +2.803 |
oult | +2.704 |
Neg logit contributions | |
edom | -4.067 |
Afric | -3.830 |
Ange | -3.759 |
IOR | -3.743 |
trump | -3.630 |
Token | / |
Token ID | 14 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
interstitial | +4.143 |
benefit | +4.045 |
farious | +4.042 |
549 | +3.840 |
propri | +3.823 |
Neg logit contributions | |
edom | -3.052 |
Afric | -2.790 |
Ange | -2.664 |
IOR | -2.631 |
trump | -2.524 |
Token | is |
Token ID | 318 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
edom | +0.088 |
Afric | +0.083 |
Ange | +0.081 |
IOR | +0.080 |
trump | +0.078 |
Neg logit contributions | |
interstitial | -0.086 |
farious | -0.084 |
benefit | -0.081 |
propri | -0.077 |
oult | -0.075 |
Token | how |
Token ID | 703 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
edom | +2.005 |
Afric | +1.893 |
Ange | +1.852 |
IOR | +1.813 |
trump | +1.759 |
Neg logit contributions | |
interstitial | -2.381 |
farious | -2.344 |
benefit | -2.268 |
propri | -2.140 |
oult | -2.119 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
edom | +2.445 |
Afric | +2.342 |
Ange | +2.305 |
IOR | +2.219 |
trump | +2.183 |
Neg logit contributions | |
interstitial | -2.824 |
farious | -2.786 |
benefit | -2.691 |
propri | -2.514 |
oult | -2.507 |
Token | government |
Token ID | 1230 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
interstitial | +0.599 |
farious | +0.585 |
benefit | +0.573 |
propri | +0.547 |
oult | +0.532 |
Neg logit contributions | |
edom | -0.500 |
Afric | -0.464 |
Ange | -0.453 |
IOR | -0.450 |
trump | -0.433 |
Token | hy |
Token ID | 2537 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
interstitial | +2.208 |
farious | +2.138 |
benefit | +2.112 |
propri | +2.039 |
oult | +1.947 |
Neg logit contributions | |
edom | -2.240 |
Afric | -2.069 |
Ange | -2.042 |
IOR | -2.034 |
trump | -1.937 |
Token | dr |
Token ID | 7109 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
edom | +1.623 |
Afric | +1.483 |
Ange | +1.457 |
IOR | +1.436 |
trump | +1.416 |
Neg logit contributions | |
interstitial | -1.627 |
farious | -1.608 |
benefit | -1.556 |
propri | -1.469 |
549 | -1.426 |
Token | ates |
Token ID | 689 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
interstitial | +4.622 |
farious | +4.341 |
benefit | +4.330 |
oult | +4.010 |
propri | +3.999 |
Neg logit contributions | |
edom | -8.923 |
Afric | -8.514 |
IOR | -8.247 |
Ange | -8.165 |
trump | -8.112 |
Token | tens |
Token ID | 11192 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
interstitial | +1.250 |
farious | +1.213 |
benefit | +1.193 |
propri | +1.143 |
oult | +1.104 |
Neg logit contributions | |
edom | -1.128 |
Afric | -1.043 |
Ange | -1.021 |
IOR | -1.020 |
trump | -0.977 |
Token | of |
Token ID | 286 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
interstitial | +0.234 |
farious | +0.228 |
benefit | +0.224 |
propri | +0.214 |
oult | +0.209 |
Neg logit contributions | |
edom | -0.194 |
Afric | -0.180 |
Ange | -0.177 |
IOR | -0.175 |
trump | -0.168 |
Token | thousands |
Token ID | 4138 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
interstitial | +2.266 |
farious | +2.193 |
benefit | +2.157 |
propri | +2.053 |
oult | +1.956 |
Neg logit contributions | |
edom | -2.740 |
Afric | -2.546 |
IOR | -2.509 |
Ange | -2.498 |
trump | -2.404 |
Token | of |
Token ID | 286 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
interstitial | +0.628 |
farious | +0.611 |
benefit | +0.603 |
propri | +0.576 |
oult | +0.559 |
Neg logit contributions | |
edom | -0.535 |
Afric | -0.493 |
Ange | -0.484 |
IOR | -0.483 |
trump | -0.461 |
Token | . |
Token ID | 13 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
interstitial | +0.954 |
farious | +0.930 |
benefit | +0.910 |
propri | +0.867 |
oult | +0.843 |
Neg logit contributions | |
edom | -0.872 |
Afric | -0.812 |
Ange | -0.794 |
IOR | -0.790 |
trump | -0.761 |
Token | You |
Token ID | 921 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
interstitial | +0.040 |
farious | +0.039 |
benefit | +0.038 |
propri | +0.037 |
oult | +0.036 |
Neg logit contributions | |
edom | -0.031 |
Afric | -0.029 |
Ange | -0.028 |
IOR | -0.028 |
trump | -0.027 |
Token | even |
Token ID | 772 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
interstitial | +3.296 |
farious | +3.223 |
benefit | +3.216 |
propri | +3.047 |
oult | +2.974 |
Neg logit contributions | |
edom | -3.231 |
Afric | -3.049 |
Ange | -2.963 |
IOR | -2.932 |
trump | -2.752 |
Token | went |
Token ID | 1816 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
interstitial | +2.500 |
farious | +2.435 |
benefit | +2.393 |
propri | +2.281 |
oult | +2.198 |
Neg logit contributions | |
edom | -2.617 |
Afric | -2.447 |
Ange | -2.391 |
IOR | -2.379 |
trump | -2.261 |
Token | as |
Token ID | 355 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
edom | +0.269 |
Afric | +0.251 |
Ange | +0.243 |
IOR | +0.241 |
trump | +0.234 |
Neg logit contributions | |
interstitial | -0.353 |
farious | -0.346 |
benefit | -0.338 |
propri | -0.322 |
oult | -0.314 |
Token | far |
Token ID | 1290 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
interstitial | +2.552 |
farious | +2.464 |
benefit | +2.382 |
propri | +2.220 |
oult | +2.114 |
Neg logit contributions | |
edom | -4.721 |
Afric | -4.456 |
Ange | -4.388 |
IOR | -4.373 |
trump | -4.238 |
Token | as |
Token ID | 355 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
interstitial | +5.463 |
farious | +5.118 |
benefit | +5.061 |
propri | +4.779 |
ayer | +4.656 |
Neg logit contributions | |
edom | -7.803 |
Afric | -7.515 |
Ange | -7.481 |
IOR | -7.211 |
TPS | -6.913 |
Token | to |
Token ID | 284 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
interstitial | +4.090 |
farious | +3.896 |
benefit | +3.871 |
propri | +3.721 |
oult | +3.591 |
Neg logit contributions | |
edom | -4.408 |
Afric | -4.182 |
Ange | -4.099 |
IOR | -4.069 |
TPS | -3.829 |
Token | tell |
Token ID | 1560 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
interstitial | +1.553 |
farious | +1.508 |
benefit | +1.478 |
propri | +1.401 |
oult | +1.354 |
Neg logit contributions | |
edom | -1.812 |
Afric | -1.700 |
Ange | -1.666 |
IOR | -1.658 |
trump | -1.598 |
Token | a |
Token ID | 257 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
edom | +0.012 |
Afric | +0.011 |
Ange | +0.011 |
IOR | +0.011 |
trump | +0.011 |
Neg logit contributions | |
interstitial | -0.012 |
farious | -0.012 |
benefit | -0.012 |
propri | -0.011 |
oult | -0.011 |
Token | story |
Token ID | 1621 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
interstitial | +1.369 |
farious | +1.332 |
benefit | +1.301 |
propri | +1.235 |
oult | +1.196 |
Neg logit contributions | |
edom | -1.483 |
Afric | -1.390 |
Ange | -1.361 |
IOR | -1.355 |
trump | -1.310 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
interstitial | +0.014 |
farious | +0.013 |
benefit | +0.013 |
propri | +0.012 |
oult | +0.012 |
Neg logit contributions | |
edom | -0.012 |
Afric | -0.011 |
Ange | -0.011 |
IOR | -0.011 |
trump | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
interstitial | +0.176 |
farious | +0.171 |
benefit | +0.168 |
propri | +0.160 |
oult | +0.156 |
Neg logit contributions | |
edom | -0.146 |
Afric | -0.136 |
Ange | -0.134 |
IOR | -0.132 |
trump | -0.127 |
Token | even |
Token ID | 772 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
interstitial | +0.287 |
farious | +0.278 |
benefit | +0.272 |
propri | +0.258 |
oult | +0.251 |
Neg logit contributions | |
edom | -0.286 |
Afric | -0.266 |
Ange | -0.262 |
IOR | -0.259 |
trump | -0.253 |
Token | went |
Token ID | 1816 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
interstitial | +3.239 |
farious | +3.184 |
benefit | +3.101 |
propri | +3.012 |
549 | +2.871 |
Neg logit contributions | |
edom | -3.398 |
Afric | -3.184 |
IOR | -3.107 |
Ange | -3.086 |
TPS | -2.901 |
Token | so |
Token ID | 523 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
interstitial | +0.271 |
farious | +0.265 |
benefit | +0.260 |
propri | +0.247 |
oult | +0.242 |
Neg logit contributions | |
edom | -0.200 |
Afric | -0.185 |
Ange | -0.180 |
IOR | -0.178 |
trump | -0.173 |
Token | far |
Token ID | 1290 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
interstitial | +2.283 |
farious | +2.222 |
benefit | +2.137 |
propri | +2.010 |
oult | +1.900 |
Neg logit contributions | |
edom | -4.156 |
Afric | -3.918 |
Ange | -3.865 |
IOR | -3.860 |
trump | -3.727 |
Token | as |
Token ID | 355 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
interstitial | +5.330 |
farious | +5.113 |
benefit | +4.949 |
propri | +4.795 |
ayer | +4.551 |
Neg logit contributions | |
edom | -7.857 |
Afric | -7.455 |
Ange | -7.379 |
IOR | -7.299 |
TPS | -6.966 |
Token | to |
Token ID | 284 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
interstitial | +4.611 |
farious | +4.436 |
benefit | +4.315 |
propri | +4.226 |
oult | +4.030 |
Neg logit contributions | |
edom | -5.197 |
Afric | -4.958 |
IOR | -4.795 |
Ange | -4.770 |
TPS | -4.512 |
Token | announce |
Token ID | 5453 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
interstitial | +2.868 |
farious | +2.804 |
benefit | +2.766 |
propri | +2.655 |
oult | +2.552 |
Neg logit contributions | |
edom | -3.091 |
Afric | -2.880 |
IOR | -2.809 |
Ange | -2.806 |
trump | -2.639 |
Token | inn |
Token ID | 3527 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
interstitial | +2.439 |
farious | +2.383 |
benefit | +2.327 |
propri | +2.236 |
oult | +2.165 |
Neg logit contributions | |
edom | -2.154 |
Afric | -2.005 |
IOR | -1.956 |
Ange | -1.943 |
trump | -1.860 |
Token | ew |
Token ID | 413 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
interstitial | +0.854 |
farious | +0.833 |
benefit | +0.817 |
propri | +0.781 |
oult | +0.761 |
Neg logit contributions | |
edom | -0.645 |
Afric | -0.596 |
Ange | -0.582 |
IOR | -0.578 |
trump | -0.555 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
edom | +1.524 |
Afric | +1.435 |
Ange | +1.410 |
IOR | +1.365 |
trump | +1.363 |
Neg logit contributions | |
interstitial | -1.653 |
farious | -1.619 |
benefit | -1.573 |
propri | -1.470 |
oult | -1.454 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
interstitial | +0.097 |
farious | +0.095 |
benefit | +0.092 |
propri | +0.088 |
oult | +0.085 |
Neg logit contributions | |
edom | -0.091 |
Afric | -0.085 |
Ange | -0.083 |
IOR | -0.082 |
trump | -0.080 |
Token | From |
Token ID | 3574 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
interstitial | +0.131 |
farious | +0.127 |
benefit | +0.124 |
propri | +0.119 |
oult | +0.116 |
Neg logit contributions | |
edom | -0.102 |
Afric | -0.096 |
Ange | -0.094 |
IOR | -0.092 |
trump | -0.089 |
Token | M |
Token ID | 337 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
interstitial | +2.892 |
farious | +2.805 |
benefit | +2.761 |
propri | +2.653 |
oult | +2.559 |
Neg logit contributions | |
edom | -2.733 |
Afric | -2.512 |
IOR | -2.502 |
Ange | -2.455 |
trump | -2.357 |
Token | iley |
Token ID | 9618 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
interstitial | +1.159 |
farious | +1.131 |
benefit | +1.108 |
propri | +1.055 |
oult | +1.042 |
Neg logit contributions | |
edom | -1.081 |
Afric | -1.018 |
Ange | -0.988 |
IOR | -0.987 |
trump | -0.949 |
Token | Cyrus |
Token ID | 34305 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
edom | +0.376 |
Afric | +0.355 |
Ange | +0.349 |
IOR | +0.344 |
trump | +0.336 |
Neg logit contributions | |
interstitial | -0.381 |
farious | -0.371 |
benefit | -0.363 |
propri | -0.343 |
oult | -0.332 |
Token | phot |
Token ID | 2825 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
interstitial | +6.118 |
farious | +5.799 |
benefit | +5.743 |
propri | +5.557 |
oult | +5.411 |
Neg logit contributions | |
edom | -7.095 |
IOR | -6.572 |
Afric | -6.537 |
Ange | -6.308 |
TPS | -6.119 |
Token | ob |
Token ID | 672 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
interstitial | +2.837 |
farious | +2.809 |
benefit | +2.754 |
propri | +2.624 |
oult | +2.572 |
Neg logit contributions | |
edom | -2.774 |
Afric | -2.620 |
Ange | -2.545 |
IOR | -2.523 |
trump | -2.431 |
Token | omb |
Token ID | 2381 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
interstitial | +1.419 |
farious | +1.382 |
benefit | +1.352 |
propri | +1.295 |
549 | +1.252 |
Neg logit contributions | |
edom | -1.174 |
Afric | -1.073 |
Ange | -1.053 |
IOR | -1.044 |
trump | -1.012 |
Token | ing |
Token ID | 278 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
interstitial | +1.303 |
farious | +1.268 |
benefit | +1.238 |
propri | +1.174 |
oult | +1.137 |
Neg logit contributions | |
edom | -1.431 |
Afric | -1.341 |
Ange | -1.315 |
IOR | -1.308 |
trump | -1.266 |
Token | David |
Token ID | 3271 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
interstitial | +2.890 |
farious | +2.808 |
benefit | +2.766 |
propri | +2.655 |
oult | +2.542 |
Neg logit contributions | |
edom | -2.773 |
Afric | -2.563 |
IOR | -2.542 |
Ange | -2.489 |
trump | -2.381 |
Token | shutdown |
Token ID | 18325 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
interstitial | +0.522 |
farious | +0.507 |
benefit | +0.495 |
propri | +0.467 |
oult | +0.460 |
Neg logit contributions | |
edom | -0.498 |
Afric | -0.471 |
Ange | -0.460 |
IOR | -0.452 |
trump | -0.442 |
Token | forced |
Token ID | 4137 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
interstitial | +1.584 |
farious | +1.542 |
benefit | +1.505 |
propri | +1.430 |
oult | +1.391 |
Neg logit contributions | |
edom | -1.588 |
Afric | -1.484 |
Ange | -1.453 |
IOR | -1.445 |
trump | -1.398 |
Token | the |
Token ID | 262 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
interstitial | +1.092 |
farious | +1.061 |
benefit | +1.032 |
propri | +0.981 |
oult | +0.957 |
Neg logit contributions | |
edom | -1.059 |
Afric | -0.998 |
Ange | -0.977 |
IOR | -0.965 |
trump | -0.935 |
Token | Centers |
Token ID | 22223 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
interstitial | +0.277 |
farious | +0.269 |
benefit | +0.262 |
propri | +0.247 |
oult | +0.242 |
Neg logit contributions | |
edom | -0.285 |
Afric | -0.271 |
Ange | -0.265 |
IOR | -0.260 |
trump | -0.254 |
Token | for |
Token ID | 329 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
farious | +4.909 |
benefit | +4.906 |
interstitial | +4.875 |
propri | +4.611 |
ayer | +4.546 |
Neg logit contributions | |
edom | -5.052 |
IOR | -4.747 |
Afric | -4.621 |
Ange | -4.526 |
trump | -4.469 |
Token | Disease |
Token ID | 17344 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
interstitial | +2.417 |
farious | +2.352 |
benefit | +2.316 |
propri | +2.178 |
oult | +2.059 |
Neg logit contributions | |
edom | -3.784 |
Afric | -3.525 |
IOR | -3.501 |
Ange | -3.454 |
trump | -3.400 |
Token | Control |
Token ID | 6779 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
benefit | +4.153 |
interstitial | +4.112 |
farious | +4.076 |
propri | +3.630 |
ayer | +3.592 |
Neg logit contributions | |
edom | -9.177 |
Afric | -8.591 |
IOR | -8.421 |
Ange | -8.303 |
trump | -8.192 |
Token | and |
Token ID | 290 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
interstitial | +2.133 |
farious | +2.082 |
benefit | +2.051 |
propri | +1.951 |
oult | +1.894 |
Neg logit contributions | |
edom | -2.039 |
Afric | -1.890 |
IOR | -1.850 |
Ange | -1.846 |
trump | -1.772 |
Token | Prevention |
Token ID | 18313 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
interstitial | +2.573 |
farious | +2.514 |
benefit | +2.470 |
propri | +2.338 |
oult | +2.264 |
Neg logit contributions | |
edom | -2.768 |
Afric | -2.586 |
Ange | -2.522 |
IOR | -2.520 |
trump | -2.434 |
Token | in |
Token ID | 287 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
interstitial | +2.480 |
farious | +2.421 |
benefit | +2.379 |
propri | +2.258 |
oult | +2.187 |
Neg logit contributions | |
edom | -2.627 |
Afric | -2.433 |
IOR | -2.387 |
Ange | -2.383 |
trump | -2.289 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
interstitial | +0.718 |
farious | +0.700 |
benefit | +0.679 |
propri | +0.643 |
oult | +0.622 |
Neg logit contributions | |
edom | -0.851 |
Afric | -0.800 |
Ange | -0.788 |
IOR | -0.779 |
trump | -0.757 |
Token | that |
Token ID | 326 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
edom | +1.469 |
Afric | +1.335 |
IOR | +1.309 |
Ange | +1.309 |
trump | +1.257 |
Neg logit contributions | |
interstitial | -2.102 |
farious | -2.060 |
benefit | -2.000 |
propri | -1.889 |
oult | -1.876 |
Token | it |
Token ID | 340 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
edom | +0.677 |
Afric | +0.625 |
Ange | +0.612 |
IOR | +0.611 |
trump | +0.587 |
Neg logit contributions | |
interstitial | -0.861 |
farious | -0.845 |
benefit | -0.820 |
propri | -0.773 |
oult | -0.769 |
Token | is |
Token ID | 318 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
edom | +0.752 |
Afric | +0.697 |
Ange | +0.680 |
IOR | +0.678 |
trump | +0.663 |
Neg logit contributions | |
interstitial | -0.775 |
farious | -0.757 |
benefit | -0.732 |
propri | -0.695 |
oult | -0.678 |
Token | not |
Token ID | 407 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
interstitial | +1.181 |
farious | +1.150 |
benefit | +1.132 |
propri | +1.083 |
oult | +1.048 |
Neg logit contributions | |
edom | -1.042 |
Afric | -0.968 |
Ange | -0.947 |
IOR | -0.940 |
trump | -0.903 |
Token | as |
Token ID | 355 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
interstitial | +0.429 |
farious | +0.418 |
benefit | +0.407 |
propri | +0.387 |
oult | +0.377 |
Neg logit contributions | |
edom | -0.408 |
Afric | -0.381 |
Ange | -0.372 |
IOR | -0.370 |
trump | -0.358 |
Token | universal |
Token ID | 10112 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
interstitial | +1.999 |
farious | +1.955 |
benefit | +1.924 |
propri | +1.837 |
oult | +1.770 |
Neg logit contributions | |
edom | -2.014 |
Afric | -1.881 |
Ange | -1.844 |
IOR | -1.832 |
trump | -1.768 |
Token | of |
Token ID | 286 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
interstitial | +5.476 |
benefit | +5.435 |
farious | +5.425 |
propri | +5.150 |
applic | +4.962 |
Neg logit contributions | |
edom | -7.534 |
Afric | -7.077 |
Ange | -6.975 |
IOR | -6.883 |
trump | -6.732 |
Token | an |
Token ID | 281 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
interstitial | +2.328 |
farious | +2.261 |
benefit | +2.207 |
propri | +2.090 |
oult | +2.018 |
Neg logit contributions | |
edom | -2.766 |
Afric | -2.599 |
Ange | -2.550 |
IOR | -2.537 |
trump | -2.458 |
Token | I |
Token ID | 314 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
interstitial | +1.400 |
farious | +1.365 |
benefit | +1.341 |
propri | +1.282 |
oult | +1.242 |
Neg logit contributions | |
edom | -1.213 |
Afric | -1.127 |
Ange | -1.102 |
IOR | -1.095 |
trump | -1.055 |
Token | PC |
Token ID | 5662 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
edom | +0.584 |
IOR | +0.542 |
Afric | +0.539 |
Ange | +0.530 |
trump | +0.511 |
Neg logit contributions | |
interstitial | -0.609 |
farious | -0.599 |
benefit | -0.567 |
propri | -0.549 |
oult | -0.525 |
Token | primitive |
Token ID | 20049 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
interstitial | +2.291 |
farious | +2.230 |
benefit | +2.196 |
propri | +2.092 |
oult | +2.008 |
Neg logit contributions | |
edom | -2.647 |
Afric | -2.485 |
Ange | -2.443 |
IOR | -2.415 |
trump | -2.345 |
Token | . |
Token ID | 13 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
interstitial | +2.536 |
farious | +2.469 |
benefit | +2.440 |
propri | +2.307 |
549 | +2.248 |
Neg logit contributions | |
edom | -2.529 |
Afric | -2.350 |
Ange | -2.286 |
IOR | -2.281 |
trump | -2.202 |
Token | M |
Token ID | 337 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
interstitial | +1.839 |
farious | +1.801 |
benefit | +1.766 |
propri | +1.693 |
549 | +1.644 |
Neg logit contributions | |
edom | -1.466 |
Afric | -1.331 |
IOR | -1.310 |
Ange | -1.300 |
trump | -1.253 |
Token | ural |
Token ID | 1523 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
edom | +0.419 |
Afric | +0.391 |
Ange | +0.383 |
IOR | +0.381 |
trump | +0.367 |
Neg logit contributions | |
interstitial | -0.418 |
farious | -0.408 |
benefit | -0.399 |
propri | -0.379 |
oult | -0.365 |
Token | by |
Token ID | 416 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
edom | +2.180 |
Afric | +2.055 |
Ange | +1.979 |
IOR | +1.946 |
trump | +1.900 |
Neg logit contributions | |
interstitial | -2.627 |
farious | -2.563 |
benefit | -2.491 |
propri | -2.364 |
oult | -2.308 |
Token | Ph |
Token ID | 1380 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
interstitial | +0.202 |
farious | +0.197 |
benefit | +0.193 |
propri | +0.184 |
oult | +0.179 |
Neg logit contributions | |
edom | -0.174 |
Afric | -0.162 |
Ange | -0.159 |
IOR | -0.157 |
trump | -0.152 |
Token | leg |
Token ID | 1455 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
interstitial | +1.561 |
farious | +1.526 |
benefit | +1.493 |
propri | +1.425 |
oult | +1.391 |
Neg logit contributions | |
edom | -1.318 |
Afric | -1.227 |
Ange | -1.197 |
IOR | -1.191 |
trump | -1.146 |
Token | m |
Token ID | 76 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
interstitial | +6.117 |
farious | +5.974 |
benefit | +5.908 |
propri | +5.521 |
ayer | +5.488 |
Neg logit contributions | |
edom | -6.639 |
Afric | -6.330 |
IOR | -6.219 |
trump | -6.107 |
Ange | -6.093 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
interstitial | +3.467 |
farious | +3.399 |
benefit | +3.321 |
propri | +3.162 |
oult | +3.146 |
Neg logit contributions | |
edom | -2.975 |
Afric | -2.725 |
IOR | -2.714 |
Ange | -2.665 |
trump | -2.583 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
edom | +0.757 |
Afric | +0.721 |
Ange | +0.700 |
IOR | +0.689 |
trump | +0.675 |
Neg logit contributions | |
interstitial | -0.822 |
farious | -0.800 |
benefit | -0.782 |
propri | -0.738 |
oult | -0.723 |
Token | St |
Token ID | 520 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
interstitial | +1.356 |
farious | +1.322 |
benefit | +1.296 |
propri | +1.232 |
oult | +1.199 |
Neg logit contributions | |
edom | -1.283 |
Afric | -1.189 |
Ange | -1.162 |
IOR | -1.161 |
trump | -1.118 |
Token | . |
Token ID | 13 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
interstitial | +2.638 |
farious | +2.627 |
benefit | +2.557 |
propri | +2.420 |
ayer | +2.399 |
Neg logit contributions | |
edom | -2.649 |
Afric | -2.429 |
IOR | -2.386 |
Ange | -2.375 |
trump | -2.283 |
Token | rarely |
Token ID | 8365 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
interstitial | +3.090 |
farious | +3.000 |
benefit | +2.958 |
propri | +2.822 |
oult | +2.730 |
Neg logit contributions | |
edom | -3.164 |
Afric | -2.954 |
Ange | -2.894 |
IOR | -2.880 |
trump | -2.772 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
interstitial | +1.868 |
farious | +1.820 |
benefit | +1.783 |
propri | +1.698 |
oult | +1.649 |
Neg logit contributions | |
edom | -1.764 |
Afric | -1.647 |
Ange | -1.609 |
IOR | -1.601 |
trump | -1.543 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
interstitial | +0.741 |
farious | +0.724 |
benefit | +0.709 |
propri | +0.677 |
oult | +0.658 |
Neg logit contributions | |
edom | -0.628 |
Afric | -0.581 |
Ange | -0.567 |
IOR | -0.565 |
trump | -0.544 |
Token |
|
Token ID | 198 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
edom | +0.614 |
Ange | +0.574 |
Afric | +0.571 |
IOR | +0.565 |
trump | +0.540 |
Neg logit contributions | |
interstitial | -0.940 |
farious | -0.916 |
benefit | -0.870 |
propri | -0.852 |
oult | -0.823 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
interstitial | +0.342 |
farious | +0.334 |
benefit | +0.324 |
propri | +0.310 |
oult | +0.299 |
Neg logit contributions | |
edom | -0.385 |
Afric | -0.360 |
Ange | -0.354 |
IOR | -0.354 |
trump | -0.340 |
Token | Continue |
Token ID | 10054 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
interstitial | +0.955 |
farious | +0.934 |
benefit | +0.910 |
propri | +0.870 |
oult | +0.845 |
Neg logit contributions | |
edom | -0.883 |
Afric | -0.824 |
Ange | -0.809 |
IOR | -0.802 |
trump | -0.776 |
Token | reading |
Token ID | 3555 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
interstitial | +3.949 |
benefit | +3.626 |
farious | +3.510 |
propri | +3.459 |
549 | +3.247 |
Neg logit contributions | |
edom | -9.208 |
IOR | -8.750 |
Afric | -8.601 |
Ange | -8.282 |
BuyableInstoreAndOnline | -8.228 |
Token | the |
Token ID | 262 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
interstitial | +2.307 |
farious | +2.233 |
benefit | +2.216 |
propri | +2.112 |
549 | +2.044 |
Neg logit contributions | |
edom | -2.235 |
Afric | -2.072 |
IOR | -2.023 |
Ange | -2.012 |
trump | -1.934 |
Token | main |
Token ID | 1388 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
interstitial | +1.737 |
farious | +1.701 |
benefit | +1.671 |
propri | +1.606 |
oult | +1.570 |
Neg logit contributions | |
edom | -1.016 |
Afric | -0.926 |
Ange | -0.900 |
IOR | -0.892 |
trump | -0.851 |
Token | story |
Token ID | 1621 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
interstitial | +4.038 |
farious | +3.926 |
benefit | +3.878 |
propri | +3.735 |
549 | +3.623 |
Neg logit contributions | |
edom | -3.319 |
Afric | -3.063 |
IOR | -2.984 |
Ange | -2.964 |
trump | -2.777 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
edom | +0.454 |
Afric | +0.427 |
Ange | +0.425 |
IOR | +0.415 |
trump | +0.401 |
Neg logit contributions | |
interstitial | -0.644 |
farious | -0.634 |
benefit | -0.612 |
propri | -0.591 |
oult | -0.577 |
Token | pharmac |
Token ID | 25702 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
edom | +0.271 |
Afric | +0.253 |
Ange | +0.248 |
IOR | +0.246 |
trump | +0.240 |
Neg logit contributions | |
interstitial | -0.270 |
farious | -0.264 |
benefit | -0.256 |
propri | -0.238 |
oult | -0.238 |
Token | ological |
Token ID | 2770 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
interstitial | +0.666 |
farious | +0.622 |
benefit | +0.587 |
propri | +0.501 |
oult | +0.453 |
Neg logit contributions | |
edom | -2.925 |
Afric | -2.816 |
Ange | -2.774 |
IOR | -2.765 |
trump | -2.709 |
Token | and |
Token ID | 290 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
interstitial | +2.031 |
farious | +1.971 |
benefit | +1.930 |
propri | +1.848 |
oult | +1.758 |
Neg logit contributions | |
edom | -2.435 |
Afric | -2.287 |
IOR | -2.239 |
Ange | -2.233 |
trump | -2.149 |
Token | elect |
Token ID | 1742 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
interstitial | +1.805 |
farious | +1.751 |
benefit | +1.716 |
propri | +1.641 |
oult | +1.566 |
Neg logit contributions | |
edom | -2.208 |
Afric | -2.066 |
Ange | -2.030 |
IOR | -2.025 |
trump | -1.951 |
Token | roph |
Token ID | 10051 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
interstitial | +3.722 |
farious | +3.638 |
benefit | +3.595 |
propri | +3.460 |
oult | +3.350 |
Neg logit contributions | |
edom | -3.827 |
Afric | -3.608 |
Ange | -3.519 |
IOR | -3.481 |
trump | -3.364 |
Token | ys |
Token ID | 893 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
interstitial | +1.286 |
farious | +1.266 |
benefit | +1.241 |
propri | +1.196 |
oult | +1.172 |
Neg logit contributions | |
edom | -0.729 |
Afric | -0.664 |
Ange | -0.647 |
IOR | -0.642 |
trump | -0.610 |
Token | iological |
Token ID | 15071 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
farious | +3.605 |
interstitial | +3.557 |
benefit | +3.386 |
propri | +3.139 |
oult | +2.883 |
Neg logit contributions | |
edom | -9.274 |
Ange | -8.910 |
Afric | -8.863 |
trump | -8.717 |
IOR | -8.711 |
Token | procedures |
Token ID | 9021 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
interstitial | +1.185 |
farious | +1.148 |
benefit | +1.119 |
propri | +1.059 |
oult | +1.016 |
Neg logit contributions | |
edom | -1.598 |
Afric | -1.506 |
Ange | -1.477 |
IOR | -1.473 |
trump | -1.426 |
Token | . |
Token ID | 13 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
interstitial | +0.544 |
farious | +0.531 |
benefit | +0.517 |
propri | +0.492 |
oult | +0.480 |
Neg logit contributions | |
edom | -0.484 |
Afric | -0.449 |
Ange | -0.441 |
IOR | -0.437 |
trump | -0.423 |
Token | This |
Token ID | 770 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
interstitial | +3.274 |
farious | +3.216 |
benefit | +3.158 |
propri | +3.026 |
549 | +2.936 |
Neg logit contributions | |
edom | -2.944 |
Afric | -2.699 |
IOR | -2.627 |
Ange | -2.617 |
trump | -2.538 |
Token | paper |
Token ID | 3348 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
interstitial | +1.507 |
farious | +1.461 |
benefit | +1.420 |
propri | +1.335 |
oult | +1.289 |
Neg logit contributions | |
edom | -2.075 |
Afric | -1.958 |
Ange | -1.923 |
IOR | -1.914 |
trump | -1.860 |
Token | ny |
Token ID | 3281 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
edom | +0.570 |
Afric | +0.527 |
Ange | +0.522 |
IOR | +0.521 |
trump | +0.518 |
Neg logit contributions | |
interstitial | -0.306 |
farious | -0.292 |
benefit | -0.275 |
propri | -0.263 |
oult | -0.247 |
Token | has |
Token ID | 468 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
edom | +0.112 |
Afric | +0.104 |
Ange | +0.102 |
IOR | +0.101 |
trump | +0.099 |
Neg logit contributions | |
interstitial | -0.123 |
farious | -0.120 |
benefit | -0.117 |
propri | -0.112 |
oult | -0.109 |
Token | been |
Token ID | 587 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
edom | +0.681 |
Afric | +0.634 |
Ange | +0.618 |
IOR | +0.612 |
trump | +0.598 |
Neg logit contributions | |
interstitial | -0.873 |
farious | -0.855 |
benefit | -0.834 |
propri | -0.794 |
oult | -0.775 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
interstitial | +2.056 |
farious | +2.004 |
benefit | +1.961 |
propri | +1.868 |
oult | +1.813 |
Neg logit contributions | |
edom | -1.943 |
Afric | -1.811 |
Ange | -1.772 |
IOR | -1.764 |
trump | -1.698 |
Token | least |
Token ID | 1551 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
edom | +0.457 |
Afric | +0.440 |
Ange | +0.429 |
trump | +0.422 |
IOR | +0.421 |
Neg logit contributions | |
interstitial | -0.368 |
farious | -0.356 |
benefit | -0.344 |
propri | -0.318 |
oult | -0.318 |
Token | lucky |
Token ID | 9670 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
edom | +0.514 |
Afric | +0.486 |
Ange | +0.473 |
IOR | +0.469 |
trump | +0.458 |
Neg logit contributions | |
interstitial | -0.559 |
farious | -0.540 |
benefit | -0.525 |
propri | -0.497 |
oult | -0.489 |
Token | : |
Token ID | 25 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
interstitial | +6.175 |
benefit | +5.966 |
farious | +5.873 |
propri | +5.734 |
549 | +5.477 |
Neg logit contributions | |
edom | -6.822 |
IOR | -6.237 |
Afric | -6.163 |
Ange | -6.163 |
TPS | -5.784 |
Token | he |
Token ID | 339 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
interstitial | +2.015 |
farious | +1.962 |
benefit | +1.919 |
propri | +1.829 |
oult | +1.775 |
Neg logit contributions | |
edom | -1.926 |
Afric | -1.795 |
Ange | -1.756 |
IOR | -1.750 |
trump | -1.684 |
Token | was |
Token ID | 373 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
edom | +0.103 |
Afric | +0.096 |
Ange | +0.093 |
IOR | +0.093 |
trump | +0.091 |
Neg logit contributions | |
interstitial | -0.101 |
farious | -0.099 |
benefit | -0.096 |
propri | -0.091 |
oult | -0.088 |
Token | attacked |
Token ID | 7384 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
interstitial | +0.479 |
farious | +0.467 |
benefit | +0.455 |
propri | +0.433 |
oult | +0.422 |
Neg logit contributions | |
edom | -0.425 |
Afric | -0.398 |
Ange | -0.388 |
IOR | -0.384 |
trump | -0.376 |
Token | with |
Token ID | 351 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
interstitial | +0.639 |
farious | +0.625 |
benefit | +0.608 |
propri | +0.579 |
oult | +0.565 |
Neg logit contributions | |
edom | -0.563 |
Afric | -0.525 |
Ange | -0.513 |
IOR | -0.509 |
trump | -0.494 |
Token | all |
Token ID | 477 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
edom | +1.158 |
Afric | +1.073 |
Ange | +1.057 |
IOR | +1.048 |
trump | +1.020 |
Neg logit contributions | |
interstitial | -1.357 |
farious | -1.328 |
benefit | -1.302 |
propri | -1.229 |
oult | -1.205 |
Token | of |
Token ID | 286 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
interstitial | +1.462 |
farious | +1.423 |
benefit | +1.392 |
propri | +1.345 |
549 | +1.299 |
Neg logit contributions | |
edom | -1.270 |
Afric | -1.173 |
Ange | -1.143 |
IOR | -1.139 |
trump | -1.088 |
Token | them |
Token ID | 606 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
interstitial | +2.601 |
farious | +2.530 |
benefit | +2.494 |
propri | +2.411 |
549 | +2.311 |
Neg logit contributions | |
edom | -2.574 |
Afric | -2.364 |
IOR | -2.312 |
Ange | -2.297 |
trump | -2.203 |
Token | . |
Token ID | 13 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
interstitial | +0.414 |
farious | +0.403 |
benefit | +0.395 |
propri | +0.377 |
oult | +0.366 |
Neg logit contributions | |
edom | -0.362 |
Afric | -0.337 |
Ange | -0.329 |
IOR | -0.327 |
trump | -0.315 |
Token | The |
Token ID | 383 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
interstitial | +1.817 |
farious | +1.782 |
benefit | +1.747 |
propri | +1.668 |
549 | +1.625 |
Neg logit contributions | |
edom | -1.554 |
Afric | -1.426 |
IOR | -1.389 |
Ange | -1.388 |
trump | -1.335 |
Token | Ir |
Token ID | 5686 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
interstitial | +0.912 |
farious | +0.891 |
benefit | +0.873 |
propri | +0.834 |
oult | +0.813 |
Neg logit contributions | |
edom | -0.723 |
Afric | -0.669 |
Ange | -0.653 |
IOR | -0.649 |
trump | -0.624 |
Token | regular |
Token ID | 16338 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
farious | +5.342 |
interstitial | +5.340 |
benefit | +5.174 |
oult | +4.835 |
propri | +4.741 |
Neg logit contributions | |
edom | -7.253 |
Afric | -7.153 |
Ange | -6.869 |
IOR | -6.752 |
trump | -6.667 |
Token | s |
Token ID | 82 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
interstitial | +3.837 |
farious | +3.741 |
benefit | +3.707 |
propri | +3.527 |
549 | +3.437 |
Neg logit contributions | |
edom | -3.327 |
Afric | -3.098 |
Ange | -3.024 |
IOR | -3.023 |
trump | -2.867 |
Token | theme |
Token ID | 7505 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
interstitial | +1.597 |
farious | +1.554 |
benefit | +1.534 |
propri | +1.459 |
oult | +1.418 |
Neg logit contributions | |
edom | -1.537 |
Afric | -1.430 |
Ange | -1.399 |
IOR | -1.398 |
trump | -1.335 |
Token | represents |
Token ID | 6870 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
edom | +0.245 |
Afric | +0.229 |
Ange | +0.224 |
IOR | +0.222 |
trump | +0.215 |
Neg logit contributions | |
interstitial | -0.249 |
farious | -0.243 |
benefit | -0.237 |
propri | -0.225 |
oult | -0.219 |
Token | the |
Token ID | 262 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
edom | +0.306 |
Afric | +0.286 |
Ange | +0.280 |
IOR | +0.278 |
trump | +0.269 |
Neg logit contributions | |
interstitial | -0.325 |
farious | -0.317 |
benefit | -0.309 |
propri | -0.293 |
oult | -0.285 |
Token | EM |
Token ID | 3620 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
edom | +0.267 |
Afric | +0.251 |
Ange | +0.246 |
IOR | +0.245 |
trump | +0.237 |
Neg logit contributions | |
interstitial | -0.232 |
farious | -0.225 |
benefit | -0.220 |
propri | -0.208 |
oult | -0.201 |
Token | IC |
Token ID | 2149 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
edom | +0.734 |
Afric | +0.687 |
IOR | +0.685 |
Ange | +0.679 |
trump | +0.647 |
Neg logit contributions | |
interstitial | -0.891 |
farious | -0.872 |
benefit | -0.844 |
propri | -0.806 |
oult | -0.786 |
Token | AL |
Token ID | 8355 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
edom | +0.166 |
Afric | +0.155 |
IOR | +0.153 |
Ange | +0.152 |
trump | +0.145 |
Neg logit contributions | |
interstitial | -0.200 |
farious | -0.195 |
benefit | -0.191 |
propri | -0.182 |
oult | -0.176 |
Token | ERT |
Token ID | 17395 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
interstitial | +1.289 |
farious | +1.257 |
benefit | +1.231 |
propri | +1.175 |
oult | +1.141 |
Neg logit contributions | |
edom | -1.200 |
Afric | -1.119 |
Ange | -1.090 |
IOR | -1.077 |
trump | -1.046 |
Token | PH |
Token ID | 9370 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
edom | +0.862 |
Afric | +0.811 |
Ange | +0.804 |
IOR | +0.799 |
trump | +0.765 |
Neg logit contributions | |
interstitial | -1.056 |
farious | -1.025 |
benefit | -1.011 |
propri | -0.962 |
oult | -0.935 |
Token | AS |
Token ID | 1921 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
interstitial | +0.196 |
farious | +0.191 |
benefit | +0.187 |
propri | +0.179 |
oult | +0.173 |
Neg logit contributions | |
edom | -0.154 |
Afric | -0.143 |
IOR | -0.140 |
Ange | -0.140 |
trump | -0.134 |
Token | ES |
Token ID | 1546 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
interstitial | +5.736 |
benefit | +5.713 |
farious | +5.699 |
549 | +5.509 |
propri | +5.380 |
Neg logit contributions | |
edom | -6.662 |
Afric | -6.252 |
Ange | -6.113 |
trump | -5.950 |
IOR | -5.852 |
Token | Phase |
Token ID | 18983 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
interstitial | +2.742 |
farious | +2.680 |
benefit | +2.634 |
propri | +2.516 |
oult | +2.458 |
Neg logit contributions | |
edom | -2.357 |
Afric | -2.158 |
IOR | -2.097 |
Ange | -2.091 |
trump | -2.007 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
interstitial | +3.527 |
farious | +3.452 |
benefit | +3.379 |
propri | +3.222 |
oult | +3.152 |
Neg logit contributions | |
edom | -3.102 |
Afric | -2.904 |
Ange | -2.818 |
IOR | -2.792 |
trump | -2.666 |
Token | : |
Token ID | 25 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
interstitial | +0.910 |
farious | +0.887 |
benefit | +0.865 |
propri | +0.825 |
oult | +0.798 |
Neg logit contributions | |
edom | -0.874 |
Afric | -0.818 |
Ange | -0.802 |
IOR | -0.797 |
trump | -0.771 |
Token | No |
Token ID | 1400 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
interstitial | +2.160 |
farious | +2.111 |
benefit | +2.070 |
propri | +1.978 |
oult | +1.927 |
Neg logit contributions | |
edom | -1.757 |
Afric | -1.621 |
Ange | -1.580 |
IOR | -1.575 |
trump | -1.509 |
Token | of |
Token ID | 286 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
interstitial | +0.830 |
farious | +0.811 |
benefit | +0.796 |
propri | +0.762 |
oult | +0.738 |
Neg logit contributions | |
edom | -0.705 |
Afric | -0.654 |
Ange | -0.639 |
IOR | -0.636 |
trump | -0.609 |
Token | Belle |
Token ID | 31974 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
interstitial | +1.377 |
farious | +1.342 |
benefit | +1.310 |
propri | +1.245 |
oult | +1.211 |
Neg logit contributions | |
edom | -1.348 |
Afric | -1.261 |
Ange | -1.234 |
IOR | -1.225 |
trump | -1.186 |
Token | w |
Token ID | 86 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
edom | +0.350 |
Afric | +0.327 |
Ange | +0.321 |
IOR | +0.317 |
trump | +0.312 |
Neg logit contributions | |
interstitial | -0.360 |
farious | -0.349 |
benefit | -0.337 |
propri | -0.325 |
oult | -0.309 |
Token | particularly |
Token ID | 3573 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
interstitial | +1.855 |
farious | +1.809 |
benefit | +1.773 |
propri | +1.697 |
oult | +1.642 |
Neg logit contributions | |
edom | -1.678 |
Afric | -1.573 |
Ange | -1.527 |
IOR | -1.525 |
trump | -1.452 |
Token | cr |
Token ID | 1067 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
edom | +1.826 |
Afric | +1.714 |
Ange | +1.688 |
IOR | +1.665 |
trump | +1.639 |
Neg logit contributions | |
interstitial | -2.109 |
farious | -2.035 |
benefit | -1.990 |
propri | -1.865 |
oult | -1.855 |
Token | ass |
Token ID | 562 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
interstitial | +1.481 |
farious | +1.443 |
benefit | +1.406 |
propri | +1.329 |
oult | +1.290 |
Neg logit contributions | |
edom | -1.776 |
Afric | -1.687 |
Ange | -1.642 |
IOR | -1.637 |
trump | -1.584 |
Token | was |
Token ID | 373 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
interstitial | +5.877 |
farious | +5.683 |
benefit | +5.650 |
propri | +5.453 |
ayer | +5.247 |
Neg logit contributions | |
edom | -6.621 |
Afric | -6.399 |
IOR | -6.195 |
Ange | -6.173 |
TPS | -5.798 |
Token | that |
Token ID | 326 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
edom | +1.595 |
Afric | +1.466 |
Ange | +1.450 |
IOR | +1.400 |
trump | +1.394 |
Neg logit contributions | |
interstitial | -2.133 |
farious | -2.097 |
benefit | -2.021 |
propri | -1.920 |
oult | -1.897 |
Token | an |
Token ID | 281 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
edom | +1.766 |
Afric | +1.675 |
Ange | +1.644 |
IOR | +1.586 |
trump | +1.582 |
Neg logit contributions | |
interstitial | -1.949 |
farious | -1.914 |
benefit | -1.848 |
propri | -1.738 |
oult | -1.725 |
Token | hour |
Token ID | 1711 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
edom | +0.112 |
Afric | +0.105 |
Ange | +0.103 |
IOR | +0.102 |
trump | +0.098 |
Neg logit contributions | |
interstitial | -0.120 |
farious | -0.118 |
benefit | -0.115 |
propri | -0.109 |
oult | -0.106 |
Token | or |
Token ID | 393 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
edom | +1.190 |
Afric | +1.086 |
IOR | +1.064 |
Ange | +1.052 |
trump | +1.027 |
Neg logit contributions | |
interstitial | -1.830 |
farious | -1.824 |
benefit | -1.763 |
propri | -1.682 |
oult | -1.656 |
Token | � |
Token ID | 247 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
edom | +1.153 |
Afric | +1.079 |
Ange | +1.069 |
IOR | +1.066 |
trump | +1.030 |
Neg logit contributions | |
interstitial | -0.986 |
farious | -0.969 |
benefit | -0.932 |
propri | -0.885 |
oult | -0.854 |
Token | t |
Token ID | 83 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
edom | +0.818 |
Afric | +0.753 |
Ange | +0.740 |
IOR | +0.738 |
trump | +0.712 |
Neg logit contributions | |
interstitial | -0.955 |
farious | -0.935 |
benefit | -0.905 |
propri | -0.872 |
oult | -0.842 |
Token | Break |
Token ID | 12243 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
edom | +0.567 |
Afric | +0.526 |
Ange | +0.513 |
IOR | +0.502 |
trump | +0.488 |
Neg logit contributions | |
interstitial | -0.861 |
farious | -0.845 |
benefit | -0.822 |
propri | -0.791 |
oult | -0.771 |
Token | US |
Token ID | 1294 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
interstitial | +1.631 |
farious | +1.593 |
benefit | +1.559 |
propri | +1.490 |
oult | +1.448 |
Neg logit contributions | |
edom | -1.379 |
Afric | -1.282 |
Ange | -1.251 |
IOR | -1.247 |
trump | -1.197 |
Token | - |
Token ID | 12 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
interstitial | +1.011 |
farious | +0.990 |
benefit | +0.968 |
propri | +0.930 |
oult | +0.904 |
Neg logit contributions | |
edom | -0.757 |
Afric | -0.699 |
Ange | -0.682 |
IOR | -0.679 |
trump | -0.650 |
Token | Philipp |
Token ID | 49680 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
edom | +2.652 |
Afric | +2.476 |
IOR | +2.433 |
Ange | +2.394 |
TPS | +2.284 |
Neg logit contributions | |
interstitial | -3.156 |
farious | -3.094 |
benefit | -2.979 |
propri | -2.930 |
oult | -2.834 |
Token | ines |
Token ID | 1127 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
edom | +6.190 |
Afric | +5.511 |
Ange | +5.301 |
)( | +5.145 |
IOR | +5.101 |
Neg logit contributions | |
interstitial | -10.297 |
farious | -10.000 |
propri | -9.696 |
benefit | -9.636 |
oult | -9.262 |
Token | T |
Token ID | 309 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
edom | +2.882 |
Afric | +2.728 |
Ange | +2.646 |
IOR | +2.512 |
trump | +2.495 |
Neg logit contributions | |
interstitial | -4.198 |
farious | -4.073 |
benefit | -4.028 |
propri | -3.777 |
oult | -3.738 |
Token | ies |
Token ID | 444 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
edom | +0.458 |
Afric | +0.424 |
Ange | +0.417 |
IOR | +0.414 |
trump | +0.398 |
Neg logit contributions | |
interstitial | -0.539 |
farious | -0.526 |
benefit | -0.516 |
propri | -0.491 |
oult | -0.477 |
Token | C |
Token ID | 327 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
interstitial | +1.112 |
farious | +1.085 |
benefit | +1.063 |
propri | +1.014 |
oult | +0.986 |
Neg logit contributions | |
edom | -0.962 |
Afric | -0.895 |
Ange | -0.874 |
IOR | -0.869 |
trump | -0.836 |
Token | ement |
Token ID | 972 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
edom | +1.042 |
Afric | +0.968 |
Ange | +0.950 |
IOR | +0.948 |
trump | +0.914 |
Neg logit contributions | |
interstitial | -0.942 |
farious | -0.922 |
benefit | -0.897 |
propri | -0.845 |
oult | -0.818 |
Token | ; |
Token ID | 26 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
edom | +2.229 |
Afric | +2.056 |
Ange | +2.010 |
IOR | +1.983 |
trump | +1.921 |
Neg logit contributions | |
interstitial | -3.221 |
farious | -3.126 |
benefit | -3.063 |
propri | -2.918 |
oult | -2.851 |
Token | th |
Token ID | 294 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
edom | +1.974 |
Afric | +1.823 |
Ange | +1.765 |
IOR | +1.744 |
trump | +1.737 |
Neg logit contributions | |
interstitial | -2.434 |
farious | -2.361 |
benefit | -2.301 |
propri | -2.179 |
oult | -2.125 |
Token | om |
Token ID | 296 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
edom | +1.634 |
Afric | +1.406 |
IOR | +1.386 |
Ange | +1.352 |
trump | +1.349 |
Neg logit contributions | |
interstitial | -2.307 |
farious | -2.209 |
benefit | -2.125 |
propri | -2.070 |
549 | -2.000 |
Token | son |
Token ID | 1559 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
interstitial | +0.240 |
farious | +0.232 |
benefit | +0.224 |
propri | +0.216 |
549 | +0.207 |
Neg logit contributions | |
edom | -0.243 |
Afric | -0.220 |
Ange | -0.217 |
IOR | -0.215 |
trump | -0.210 |
Token | . |
Token ID | 13 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
edom | +1.594 |
Afric | +1.480 |
Ange | +1.449 |
IOR | +1.443 |
trump | +1.397 |
Neg logit contributions | |
interstitial | -1.712 |
farious | -1.664 |
benefit | -1.621 |
propri | -1.553 |
oult | -1.501 |
Token | co |
Token ID | 1073 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
edom | +2.926 |
Afric | +2.676 |
Ange | +2.594 |
IOR | +2.589 |
trump | +2.503 |
Neg logit contributions | |
interstitial | -3.856 |
farious | -3.726 |
benefit | -3.610 |
propri | -3.528 |
oult | -3.381 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
edom | +4.849 |
)( | +4.830 |
Ange | +4.575 |
IOR | +4.426 |
trump | +4.363 |
Neg logit contributions | |
interstitial | -10.330 |
farious | -10.181 |
propri | -9.259 |
benefit | -8.942 |
arij | -8.873 |
Token | uk |
Token ID | 2724 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
edom | +1.011 |
Afric | +0.920 |
Ange | +0.909 |
IOR | +0.891 |
trump | +0.875 |
Neg logit contributions | |
interstitial | -1.195 |
farious | -1.173 |
benefit | -1.099 |
propri | -1.097 |
549 | -1.031 |
Token | / |
Token ID | 14 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
edom | +2.834 |
Afric | +2.565 |
Ange | +2.411 |
IOR | +2.382 |
trump | +2.293 |
Neg logit contributions | |
interstitial | -5.993 |
farious | -5.821 |
benefit | -5.754 |
propri | -5.491 |
oult | -5.392 |
Token | cru |
Token ID | 32838 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
edom | +3.438 |
Afric | +3.182 |
Ange | +3.092 |
IOR | +3.082 |
trump | +3.020 |
Neg logit contributions | |
interstitial | -3.179 |
farious | -3.108 |
benefit | -2.946 |
propri | -2.857 |
oult | -2.748 |
Token | ise |
Token ID | 786 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
edom | +1.460 |
Afric | +1.323 |
Ange | +1.295 |
IOR | +1.286 |
trump | +1.243 |
Neg logit contributions | |
interstitial | -1.747 |
farious | -1.673 |
benefit | -1.639 |
propri | -1.579 |
oult | -1.515 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
interstitial | +0.409 |
farious | +0.397 |
benefit | +0.386 |
propri | +0.365 |
oult | +0.358 |
Neg logit contributions | |
edom | -0.364 |
Afric | -0.341 |
Ange | -0.334 |
IOR | -0.331 |
trump | -0.324 |
Token | ." |
Token ID | 526 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
interstitial | +0.284 |
farious | +0.276 |
benefit | +0.270 |
propri | +0.256 |
oult | +0.249 |
Neg logit contributions | |
edom | -0.279 |
Afric | -0.261 |
Ange | -0.256 |
IOR | -0.254 |
trump | -0.247 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
interstitial | +2.744 |
farious | +2.704 |
benefit | +2.630 |
propri | +2.515 |
549 | +2.451 |
Neg logit contributions | |
edom | -2.562 |
Afric | -2.319 |
IOR | -2.290 |
Ange | -2.249 |
trump | -2.183 |
Token |
|
Token ID | 198 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
interstitial | +0.872 |
farious | +0.852 |
benefit | +0.826 |
propri | +0.796 |
oult | +0.772 |
Neg logit contributions | |
edom | -0.658 |
Afric | -0.610 |
Ange | -0.602 |
IOR | -0.598 |
trump | -0.573 |
Token | President |
Token ID | 10364 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
interstitial | +2.011 |
farious | +1.949 |
benefit | +1.923 |
propri | +1.803 |
549 | +1.775 |
Neg logit contributions | |
edom | -1.890 |
Afric | -1.768 |
Ange | -1.719 |
IOR | -1.692 |
trump | -1.658 |
Token | Rodrigo |
Token ID | 46198 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
interstitial | +0.859 |
farious | +0.839 |
benefit | +0.821 |
propri | +0.784 |
oult | +0.763 |
Neg logit contributions | |
edom | -0.729 |
Afric | -0.677 |
Ange | -0.662 |
IOR | -0.658 |
trump | -0.633 |
Token | Duterte |
Token ID | 25763 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
Ange | +2.126 |
trump | +1.980 |
edom | +1.859 |
Chin | +1.837 |
Afric | +1.836 |
Neg logit contributions | |
interstitial | -12.431 |
farious | -12.326 |
benefit | -12.247 |
oult | -11.756 |
propri | -11.540 |
Token | had |
Token ID | 550 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
edom | +2.255 |
Afric | +2.133 |
Ange | +2.097 |
trump | +2.086 |
IOR | +2.029 |
Neg logit contributions | |
interstitial | -2.455 |
farious | -2.396 |
benefit | -2.315 |
propri | -2.167 |
oult | -2.153 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
edom | +0.298 |
Afric | +0.279 |
Ange | +0.273 |
IOR | +0.270 |
trump | +0.264 |
Neg logit contributions | |
interstitial | -0.318 |
farious | -0.311 |
benefit | -0.303 |
propri | -0.286 |
oult | -0.281 |
Token | but |
Token ID | 475 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
interstitial | +0.497 |
farious | +0.490 |
benefit | +0.479 |
propri | +0.460 |
oult | +0.442 |
Neg logit contributions | |
edom | -0.478 |
Afric | -0.446 |
IOR | -0.436 |
Ange | -0.436 |
trump | -0.417 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
interstitial | +0.078 |
farious | +0.076 |
benefit | +0.074 |
propri | +0.070 |
oult | +0.069 |
Neg logit contributions | |
edom | -0.069 |
Afric | -0.064 |
Ange | -0.063 |
IOR | -0.062 |
trump | -0.061 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
interstitial | +2.792 |
farious | +2.725 |
benefit | +2.660 |
propri | +2.589 |
549 | +2.508 |
Neg logit contributions | |
edom | -2.357 |
Afric | -2.171 |
Ange | -2.090 |
IOR | -2.084 |
trump | -1.993 |
Token | . |
Token ID | 13 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
interstitial | +1.696 |
farious | +1.648 |
benefit | +1.620 |
propri | +1.542 |
oult | +1.497 |
Neg logit contributions | |
edom | -1.647 |
Afric | -1.535 |
Ange | -1.495 |
IOR | -1.490 |
trump | -1.436 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
interstitial | +1.851 |
farious | +1.799 |
benefit | +1.716 |
propri | +1.612 |
549 | +1.585 |
Neg logit contributions | |
edom | -3.055 |
Afric | -2.853 |
IOR | -2.743 |
Ange | -2.743 |
trump | -2.716 |
Token | / |
Token ID | 14 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
interstitial | +2.536 |
farious | +2.482 |
benefit | +2.439 |
propri | +2.344 |
oult | +2.289 |
Neg logit contributions | |
edom | -1.547 |
Afric | -1.412 |
Ange | -1.370 |
IOR | -1.360 |
trump | -1.298 |
Token | En |
Token ID | 4834 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
interstitial | +1.009 |
farious | +0.986 |
benefit | +0.966 |
propri | +0.920 |
549 | +0.898 |
Neg logit contributions | |
edom | -0.805 |
Afric | -0.748 |
Ange | -0.724 |
IOR | -0.718 |
trump | -0.695 |
Token | rique |
Token ID | 33865 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
interstitial | +1.161 |
farious | +1.133 |
benefit | +1.117 |
propri | +1.067 |
oult | +1.038 |
Neg logit contributions | |
edom | -0.804 |
Afric | -0.739 |
Ange | -0.723 |
IOR | -0.712 |
trump | -0.685 |
Token | de |
Token ID | 390 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
Ange | +5.567 |
Afric | +5.453 |
edom | +5.301 |
trump | +5.204 |
Chin | +5.151 |
Neg logit contributions | |
interstitial | -9.136 |
benefit | -9.013 |
farious | -8.985 |
arij | -8.944 |
ogeneity | -8.447 |
Token | la |
Token ID | 8591 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
edom | +2.936 |
Ange | +2.812 |
Afric | +2.702 |
trump | +2.635 |
IOR | +2.625 |
Neg logit contributions | |
interstitial | -3.975 |
farious | -3.939 |
benefit | -3.831 |
propri | -3.608 |
oult | -3.571 |
Token | Os |
Token ID | 8834 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
edom | +2.556 |
Ange | +2.467 |
Afric | +2.363 |
trump | +2.328 |
IOR | +2.304 |
Neg logit contributions | |
interstitial | -4.116 |
farious | -3.998 |
benefit | -3.958 |
arij | -3.667 |
propri | -3.658 |
Token | a |
Token ID | 64 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
edom | +0.240 |
Afric | +0.223 |
Ange | +0.223 |
IOR | +0.217 |
trump | +0.212 |
Neg logit contributions | |
interstitial | -0.244 |
farious | -0.241 |
benefit | -0.236 |
propri | -0.221 |
oult | -0.215 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
edom | +1.500 |
Afric | +1.388 |
Ange | +1.354 |
IOR | +1.346 |
trump | +1.293 |
Neg logit contributions | |
interstitial | -1.906 |
farious | -1.862 |
benefit | -1.825 |
propri | -1.746 |
oult | -1.700 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
edom | +2.408 |
Afric | +2.250 |
Ange | +2.219 |
IOR | +2.143 |
trump | +2.132 |
Neg logit contributions | |
interstitial | -3.150 |
farious | -3.091 |
benefit | -3.039 |
propri | -2.879 |
oult | -2.865 |
Token | Marxist |
Token ID | 26305 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
edom | +1.136 |
Afric | +1.074 |
Ange | +1.053 |
IOR | +1.019 |
trump | +1.016 |
Neg logit contributions | |
interstitial | -1.306 |
farious | -1.267 |
benefit | -1.245 |
propri | -1.169 |
oult | -1.157 |
Token | takeover |
Token ID | 27011 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
interstitial | +1.951 |
farious | +1.900 |
benefit | +1.860 |
propri | +1.782 |
oult | +1.726 |
Neg logit contributions | |
edom | -1.828 |
Afric | -1.697 |
IOR | -1.661 |
Ange | -1.652 |
trump | -1.587 |
Token | of |
Token ID | 286 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
edom | +0.206 |
Afric | +0.191 |
Ange | +0.186 |
IOR | +0.184 |
trump | +0.178 |
Neg logit contributions | |
interstitial | -0.271 |
farious | -0.265 |
benefit | -0.260 |
propri | -0.248 |
oult | -0.242 |
Token | V |
Token ID | 569 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
edom | +0.134 |
Afric | +0.125 |
Ange | +0.122 |
IOR | +0.121 |
trump | +0.117 |
Neg logit contributions | |
interstitial | -0.158 |
farious | -0.155 |
benefit | -0.151 |
propri | -0.144 |
oult | -0.141 |
Token | enez |
Token ID | 11437 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
edom | +0.725 |
Afric | +0.681 |
Ange | +0.666 |
IOR | +0.663 |
trump | +0.641 |
Neg logit contributions | |
interstitial | -0.693 |
farious | -0.674 |
benefit | -0.659 |
propri | -0.626 |
oult | -0.609 |
Token | ue |
Token ID | 518 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
edom | +5.224 |
Afric | +4.315 |
Ange | +4.217 |
IOR | +4.001 |
trump | +3.911 |
Neg logit contributions | |
interstitial | -9.857 |
benefit | -9.339 |
farious | -9.269 |
propri | -8.705 |
549 | -8.637 |
Token | ... |
Token ID | 986 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
interstitial | +0.342 |
farious | +0.333 |
benefit | +0.326 |
propri | +0.311 |
oult | +0.301 |
Neg logit contributions | |
edom | -0.331 |
Afric | -0.309 |
Ange | -0.303 |
IOR | -0.302 |
trump | -0.291 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
edom | +1.896 |
Afric | +1.763 |
Ange | +1.717 |
IOR | +1.706 |
trump | +1.643 |
Neg logit contributions | |
interstitial | -2.436 |
farious | -2.372 |
benefit | -2.330 |
propri | -2.225 |
oult | -2.171 |
Token |
|
Token ID | 198 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
edom | +1.035 |
Ange | +0.979 |
IOR | +0.963 |
Afric | +0.961 |
trump | +0.921 |
Neg logit contributions | |
interstitial | -1.760 |
farious | -1.717 |
benefit | -1.619 |
propri | -1.592 |
arij | -1.545 |
Token | From |
Token ID | 4863 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
edom | +0.308 |
Afric | +0.285 |
IOR | +0.281 |
Ange | +0.280 |
trump | +0.269 |
Neg logit contributions | |
interstitial | -0.322 |
farious | -0.316 |
benefit | -0.307 |
propri | -0.296 |
oult | -0.286 |
Token | arrest |
Token ID | 3251 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
edom | +0.069 |
Afric | +0.064 |
Ange | +0.062 |
IOR | +0.061 |
trump | +0.059 |
Neg logit contributions | |
interstitial | -0.108 |
farious | -0.106 |
benefit | -0.104 |
propri | -0.099 |
oult | -0.097 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
interstitial | +1.448 |
farious | +1.411 |
benefit | +1.387 |
propri | +1.325 |
oult | +1.282 |
Neg logit contributions | |
edom | -1.313 |
Afric | -1.221 |
Ange | -1.190 |
IOR | -1.188 |
trump | -1.136 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
interstitial | +2.447 |
farious | +2.373 |
benefit | +2.345 |
propri | +2.239 |
549 | +2.162 |
Neg logit contributions | |
edom | -2.412 |
Afric | -2.243 |
IOR | -2.194 |
Ange | -2.185 |
trump | -2.080 |
Token | the |
Token ID | 262 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
interstitial | +1.496 |
farious | +1.457 |
benefit | +1.428 |
propri | +1.365 |
oult | +1.322 |
Neg logit contributions | |
edom | -1.402 |
Afric | -1.305 |
Ange | -1.274 |
IOR | -1.270 |
trump | -1.222 |
Token | Man |
Token ID | 1869 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
interstitial | +1.558 |
farious | +1.521 |
benefit | +1.492 |
propri | +1.429 |
oult | +1.390 |
Neg logit contributions | |
edom | -1.207 |
Afric | -1.114 |
Ange | -1.086 |
IOR | -1.082 |
trump | -1.037 |
Token | ate |
Token ID | 378 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
interstitial | +0.125 |
farious | +0.122 |
benefit | +0.119 |
propri | +0.114 |
oult | +0.110 |
Neg logit contributions | |
edom | -0.115 |
Afric | -0.107 |
Ange | -0.105 |
IOR | -0.104 |
trump | -0.100 |
Token | e |
Token ID | 68 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
edom | +5.555 |
Afric | +5.020 |
Ange | +4.753 |
IOR | +4.405 |
trump | +4.250 |
Neg logit contributions | |
interstitial | -9.613 |
benefit | -8.863 |
farious | -8.858 |
propri | -8.587 |
arij | -8.427 |
Token | County |
Token ID | 3418 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
edom | +0.156 |
Afric | +0.141 |
Ange | +0.136 |
IOR | +0.135 |
trump | +0.128 |
Neg logit contributions | |
interstitial | -0.315 |
farious | -0.309 |
benefit | -0.304 |
propri | -0.293 |
oult | -0.287 |
Token | Sheriff |
Token ID | 12874 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
interstitial | +1.959 |
farious | +1.910 |
benefit | +1.881 |
propri | +1.815 |
oult | +1.751 |
Neg logit contributions | |
edom | -1.648 |
Afric | -1.518 |
Ange | -1.485 |
IOR | -1.484 |
trump | -1.415 |
Token | 's |
Token ID | 338 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
interstitial | +0.588 |
farious | +0.577 |
benefit | +0.564 |
propri | +0.538 |
oult | +0.521 |
Neg logit contributions | |
edom | -0.586 |
Afric | -0.545 |
Ange | -0.534 |
IOR | -0.532 |
trump | -0.512 |
Token | Office |
Token ID | 4452 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
edom | +1.475 |
Afric | +1.394 |
Ange | +1.360 |
IOR | +1.331 |
trump | +1.302 |
Neg logit contributions | |
interstitial | -1.550 |
farious | -1.505 |
benefit | -1.458 |
propri | -1.379 |
oult | -1.360 |
Token | ; |
Token ID | 26 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
edom | +0.975 |
Afric | +0.923 |
Ange | +0.904 |
IOR | +0.900 |
trump | +0.877 |
Neg logit contributions | |
interstitial | -0.770 |
farious | -0.747 |
benefit | -0.723 |
propri | -0.679 |
oult | -0.658 |
Token | th |
Token ID | 294 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
edom | +0.929 |
Afric | +0.865 |
Ange | +0.840 |
IOR | +0.831 |
trump | +0.825 |
Neg logit contributions | |
interstitial | -1.031 |
farious | -1.001 |
benefit | -0.973 |
propri | -0.918 |
oult | -0.897 |
Token | om |
Token ID | 296 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
edom | +0.790 |
Afric | +0.715 |
IOR | +0.700 |
Ange | +0.697 |
trump | +0.681 |
Neg logit contributions | |
interstitial | -0.909 |
farious | -0.878 |
benefit | -0.849 |
propri | -0.819 |
549 | -0.787 |
Token | son |
Token ID | 1559 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
interstitial | +0.667 |
farious | +0.649 |
benefit | +0.634 |
propri | +0.601 |
oult | +0.582 |
Neg logit contributions | |
edom | -0.742 |
Afric | -0.697 |
Ange | -0.683 |
IOR | -0.680 |
trump | -0.657 |
Token | . |
Token ID | 13 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
edom | +0.853 |
Afric | +0.783 |
Ange | +0.769 |
IOR | +0.769 |
trump | +0.745 |
Neg logit contributions | |
interstitial | -0.843 |
farious | -0.821 |
benefit | -0.792 |
propri | -0.765 |
oult | -0.733 |
Token | co |
Token ID | 1073 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
edom | +1.714 |
Afric | +1.523 |
Ange | +1.461 |
IOR | +1.453 |
trump | +1.397 |
Neg logit contributions | |
interstitial | -2.892 |
farious | -2.838 |
benefit | -2.729 |
propri | -2.672 |
oult | -2.576 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
edom | +5.941 |
Afric | +5.136 |
IOR | +5.108 |
)( | +5.049 |
Ange | +5.031 |
Neg logit contributions | |
interstitial | -8.602 |
farious | -8.433 |
benefit | -7.959 |
oult | -7.684 |
propri | -7.680 |
Token | uk |
Token ID | 2724 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
edom | +1.735 |
Afric | +1.591 |
Ange | +1.549 |
IOR | +1.536 |
trump | +1.490 |
Neg logit contributions | |
interstitial | -1.835 |
farious | -1.789 |
benefit | -1.725 |
propri | -1.678 |
oult | -1.606 |
Token | ) |
Token ID | 8 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
edom | +2.566 |
Afric | +2.287 |
Ange | +2.144 |
IOR | +2.128 |
trump | +2.033 |
Neg logit contributions | |
interstitial | -6.068 |
farious | -5.909 |
benefit | -5.836 |
propri | -5.594 |
oult | -5.503 |
Token | has |
Token ID | 468 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
edom | +1.087 |
Afric | +1.024 |
Ange | +0.997 |
IOR | +0.981 |
trump | +0.971 |
Neg logit contributions | |
interstitial | -1.118 |
farious | -1.088 |
benefit | -1.050 |
propri | -0.997 |
oult | -0.970 |
Token | options |
Token ID | 3689 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
edom | +0.764 |
Afric | +0.716 |
Ange | +0.699 |
IOR | +0.691 |
trump | +0.674 |
Neg logit contributions | |
interstitial | -0.778 |
farious | -0.760 |
benefit | -0.739 |
propri | -0.699 |
oult | -0.681 |
Token | like |
Token ID | 588 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
interstitial | +0.767 |
farious | +0.749 |
benefit | +0.734 |
propri | +0.701 |
oult | +0.682 |
Neg logit contributions | |
edom | -0.625 |
Afric | -0.580 |
Ange | -0.567 |
IOR | -0.562 |
trump | -0.542 |
Token | east |
Token ID | 7627 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
interstitial | +2.047 |
farious | +1.986 |
benefit | +1.947 |
propri | +1.859 |
oult | +1.800 |
Neg logit contributions | |
edom | -1.961 |
Afric | -1.820 |
IOR | -1.782 |
Ange | -1.780 |
trump | -1.709 |
Token | of |
Token ID | 286 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
edom | +0.772 |
Afric | +0.721 |
Ange | +0.703 |
IOR | +0.694 |
trump | +0.678 |
Neg logit contributions | |
interstitial | -0.919 |
farious | -0.897 |
benefit | -0.874 |
propri | -0.835 |
oult | -0.808 |
Token | the |
Token ID | 262 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
interstitial | +2.294 |
farious | +2.235 |
benefit | +2.191 |
propri | +2.091 |
oult | +2.024 |
Neg logit contributions | |
edom | -2.149 |
Afric | -1.992 |
IOR | -1.955 |
Ange | -1.944 |
trump | -1.863 |
Token | An |
Token ID | 1052 |
Feature activation | +9.01e-03 |
Pos logit contributions | |
interstitial | +1.533 |
farious | +1.492 |
benefit | +1.457 |
propri | +1.390 |
oult | +1.346 |
Neg logit contributions | |
edom | -1.514 |
Afric | -1.413 |
Ange | -1.382 |
IOR | -1.380 |
trump | -1.328 |
Token | ac |
Token ID | 330 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
interstitial | +0.031 |
farious | +0.031 |
benefit | +0.030 |
propri | +0.028 |
oult | +0.027 |
Neg logit contributions | |
edom | -0.039 |
Afric | -0.037 |
Ange | -0.036 |
IOR | -0.036 |
trump | -0.035 |
Token | ost |
Token ID | 455 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
edom | +5.350 |
Ange | +4.608 |
Afric | +4.555 |
trump | +4.357 |
)( | +4.260 |
Neg logit contributions | |
interstitial | -9.359 |
farious | -9.028 |
benefit | -8.872 |
propri | -8.507 |
549 | -8.031 |
Token | ia |
Token ID | 544 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
edom | +0.970 |
Afric | +0.883 |
Ange | +0.859 |
IOR | +0.824 |
trump | +0.806 |
Neg logit contributions | |
interstitial | -1.924 |
farious | -1.891 |
benefit | -1.842 |
propri | -1.791 |
oult | -1.750 |
Token | River |
Token ID | 5866 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
edom | +0.192 |
Afric | +0.178 |
Ange | +0.174 |
IOR | +0.172 |
trump | +0.166 |
Neg logit contributions | |
interstitial | -0.248 |
farious | -0.243 |
benefit | -0.237 |
propri | -0.227 |
oult | -0.221 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
interstitial | +1.079 |
farious | +1.055 |
benefit | +1.033 |
propri | +0.989 |
oult | +0.963 |
Neg logit contributions | |
edom | -0.833 |
Afric | -0.770 |
Ange | -0.752 |
IOR | -0.747 |
trump | -0.717 |
Token | Washington |
Token ID | 2669 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
edom | +0.043 |
Afric | +0.040 |
Ange | +0.040 |
IOR | +0.039 |
trump | +0.038 |
Neg logit contributions | |
interstitial | -0.046 |
farious | -0.045 |
benefit | -0.044 |
propri | -0.042 |
oult | -0.041 |
Token | loans |
Token ID | 10021 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
edom | +1.517 |
Afric | +1.399 |
Ange | +1.349 |
IOR | +1.340 |
trump | +1.325 |
Neg logit contributions | |
interstitial | -1.986 |
farious | -1.925 |
benefit | -1.888 |
oult | -1.773 |
propri | -1.768 |
Token | in |
Token ID | 287 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
edom | +1.639 |
Afric | +1.519 |
Ange | +1.477 |
IOR | +1.461 |
trump | +1.443 |
Neg logit contributions | |
interstitial | -1.995 |
farious | -1.936 |
benefit | -1.890 |
propri | -1.804 |
oult | -1.774 |
Token | the |
Token ID | 262 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
edom | +0.435 |
Afric | +0.406 |
Ange | +0.395 |
IOR | +0.391 |
trump | +0.379 |
Neg logit contributions | |
interstitial | -0.505 |
farious | -0.494 |
benefit | -0.482 |
propri | -0.458 |
oult | -0.450 |
Token | lead |
Token ID | 1085 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
interstitial | +0.024 |
farious | +0.023 |
benefit | +0.022 |
propri | +0.021 |
oult | +0.021 |
Neg logit contributions | |
edom | -0.021 |
Afric | -0.020 |
Ange | -0.019 |
IOR | -0.019 |
trump | -0.018 |
Token | - |
Token ID | 12 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
edom | +1.869 |
Afric | +1.735 |
Ange | +1.688 |
IOR | +1.676 |
trump | +1.625 |
Neg logit contributions | |
interstitial | -2.248 |
farious | -2.197 |
benefit | -2.147 |
propri | -2.058 |
oult | -2.013 |
Token | up |
Token ID | 929 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
edom | +1.308 |
Afric | +1.198 |
Ange | +1.152 |
IOR | +1.143 |
trump | +1.116 |
Neg logit contributions | |
interstitial | -1.851 |
farious | -1.822 |
benefit | -1.768 |
propri | -1.733 |
oult | -1.682 |
Token | to |
Token ID | 284 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
edom | +4.501 |
Ange | +4.187 |
trump | +4.173 |
IOR | +4.008 |
)( | +4.003 |
Neg logit contributions | |
farious | -9.381 |
interstitial | -8.992 |
propri | -8.318 |
benefit | -8.266 |
oult | -8.022 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
edom | +2.009 |
Afric | +1.868 |
Ange | +1.805 |
IOR | +1.782 |
trump | +1.766 |
Neg logit contributions | |
interstitial | -2.634 |
farious | -2.547 |
benefit | -2.483 |
oult | -2.391 |
propri | -2.362 |
Token | financial |
Token ID | 3176 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
edom | +1.008 |
Afric | +0.946 |
Ange | +0.912 |
trump | +0.889 |
IOR | +0.888 |
Neg logit contributions | |
interstitial | -1.404 |
farious | -1.349 |
benefit | -1.324 |
oult | -1.257 |
propri | -1.245 |
Token | crisis |
Token ID | 4902 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
interstitial | +0.723 |
farious | +0.695 |
benefit | +0.676 |
propri | +0.631 |
oult | +0.612 |
Neg logit contributions | |
edom | -1.082 |
Afric | -1.022 |
Ange | -1.004 |
IOR | -0.999 |
trump | -0.976 |
Token | — |
Token ID | 960 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
edom | +1.477 |
Afric | +1.368 |
Ange | +1.333 |
IOR | +1.322 |
trump | +1.288 |
Neg logit contributions | |
interstitial | -1.803 |
farious | -1.756 |
benefit | -1.715 |
propri | -1.640 |
oult | -1.602 |
Token | ( |
Token ID | 357 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
edom | +0.377 |
Afric | +0.351 |
Ange | +0.341 |
IOR | +0.338 |
trump | +0.327 |
Neg logit contributions | |
interstitial | -0.425 |
farious | -0.414 |
benefit | -0.403 |
propri | -0.384 |
oult | -0.374 |
Token | s |
Token ID | 82 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
edom | +3.883 |
Afric | +3.647 |
IOR | +3.637 |
Ange | +3.588 |
trump | +3.476 |
Neg logit contributions | |
interstitial | -2.534 |
farious | -2.507 |
benefit | -2.338 |
propri | -2.301 |
ogeneity | -2.138 |
Token | uns |
Token ID | 13271 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
interstitial | +0.632 |
farious | +0.615 |
benefit | +0.599 |
propri | +0.569 |
oult | +0.549 |
Neg logit contributions | |
edom | -0.706 |
Afric | -0.661 |
Ange | -0.648 |
IOR | -0.645 |
trump | -0.624 |
Token | ail |
Token ID | 603 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
edom | +0.217 |
Afric | +0.204 |
Ange | +0.200 |
IOR | +0.200 |
trump | +0.194 |
Neg logit contributions | |
interstitial | -0.160 |
farious | -0.156 |
benefit | -0.151 |
propri | -0.143 |
oult | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
edom | +1.842 |
Afric | +1.684 |
IOR | +1.650 |
Ange | +1.640 |
trump | +1.590 |
Neg logit contributions | |
interstitial | -1.885 |
farious | -1.849 |
benefit | -1.765 |
propri | -1.715 |
oult | -1.644 |
Token | co |
Token ID | 1073 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
edom | +2.096 |
Afric | +1.899 |
Ange | +1.833 |
IOR | +1.833 |
trump | +1.769 |
Neg logit contributions | |
interstitial | -2.555 |
farious | -2.492 |
benefit | -2.374 |
propri | -2.361 |
oult | -2.250 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
edom | +5.757 |
Afric | +5.078 |
IOR | +4.998 |
Ange | +4.997 |
)( | +4.932 |
Neg logit contributions | |
interstitial | -8.262 |
farious | -8.027 |
benefit | -7.653 |
propri | -7.467 |
oult | -7.325 |
Token | uk |
Token ID | 2724 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
edom | +1.032 |
Afric | +0.942 |
Ange | +0.920 |
IOR | +0.912 |
trump | +0.888 |
Neg logit contributions | |
interstitial | -1.178 |
farious | -1.145 |
benefit | -1.091 |
propri | -1.083 |
549 | -1.031 |
Token | ) |
Token ID | 8 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
edom | +2.469 |
Afric | +2.214 |
Ange | +2.085 |
IOR | +2.061 |
trump | +1.968 |
Neg logit contributions | |
interstitial | -5.758 |
farious | -5.607 |
benefit | -5.522 |
propri | -5.295 |
oult | -5.215 |
Token | has |
Token ID | 468 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
edom | +2.456 |
Afric | +2.325 |
Ange | +2.237 |
IOR | +2.214 |
trump | +2.206 |
Neg logit contributions | |
interstitial | -2.740 |
farious | -2.671 |
benefit | -2.549 |
propri | -2.408 |
arij | -2.376 |
Token | a |
Token ID | 257 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
edom | +1.081 |
Afric | +1.011 |
Ange | +0.984 |
IOR | +0.974 |
trump | +0.950 |
Neg logit contributions | |
interstitial | -1.148 |
farious | -1.123 |
benefit | -1.088 |
propri | -1.028 |
oult | -1.006 |
Token | 5 |
Token ID | 642 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
interstitial | +0.751 |
farious | +0.730 |
benefit | +0.718 |
propri | +0.687 |
549 | +0.662 |
Neg logit contributions | |
edom | -0.694 |
Afric | -0.643 |
Ange | -0.628 |
IOR | -0.628 |
trump | -0.601 |
Token | 84 |
Token ID | 5705 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
interstitial | +1.037 |
farious | +1.001 |
benefit | +0.981 |
propri | +0.920 |
oult | +0.879 |
Neg logit contributions | |
edom | -1.546 |
Afric | -1.449 |
IOR | -1.428 |
Ange | -1.421 |
trump | -1.384 |
Token | million |
Token ID | 1510 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
edom | +1.280 |
Afric | +1.194 |
Ange | +1.165 |
IOR | +1.162 |
trump | +1.119 |
Neg logit contributions | |
interstitial | -1.474 |
farious | -1.439 |
benefit | -1.405 |
propri | -1.341 |
oult | -1.307 |
Token | miles |
Token ID | 4608 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
edom | +2.678 |
Afric | +2.566 |
Ange | +2.517 |
IOR | +2.498 |
trump | +2.435 |
Neg logit contributions | |
interstitial | -2.102 |
farious | -2.049 |
benefit | -1.972 |
propri | -1.851 |
oult | -1.807 |
Token | ( |
Token ID | 357 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
edom | +3.090 |
Afric | +2.920 |
Ange | +2.860 |
IOR | +2.811 |
trump | +2.767 |
Neg logit contributions | |
interstitial | -3.350 |
farious | -3.304 |
benefit | -3.172 |
propri | -3.016 |
oult | -2.982 |
Token | 940 |
Token ID | 46899 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
edom | +4.531 |
Afric | +4.144 |
IOR | +4.137 |
Ange | +4.088 |
trump | +3.999 |
Neg logit contributions | |
interstitial | -2.986 |
farious | -2.928 |
benefit | -2.690 |
oult | -2.591 |
propri | -2.586 |
Token | million |
Token ID | 1510 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
edom | +4.861 |
Afric | +4.610 |
IOR | +4.493 |
trump | +4.479 |
Ange | +4.395 |
Neg logit contributions | |
interstitial | -8.684 |
farious | -8.518 |
benefit | -8.299 |
oult | -7.981 |
arij | -7.701 |
Token | km |
Token ID | 10571 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
edom | +4.205 |
Afric | +3.984 |
Ange | +3.914 |
IOR | +3.879 |
trump | +3.810 |
Neg logit contributions | |
interstitial | -3.690 |
farious | -3.579 |
benefit | -3.477 |
propri | -3.221 |
oult | -3.153 |
Token | ) |
Token ID | 8 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
edom | +3.125 |
Afric | +2.761 |
Ange | +2.652 |
IOR | +2.604 |
)( | +2.515 |
Neg logit contributions | |
interstitial | -8.475 |
farious | -8.340 |
benefit | -8.158 |
propri | -7.831 |
oult | -7.801 |
Token | by |
Token ID | 416 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
edom | +2.270 |
Afric | +2.133 |
Ange | +2.109 |
IOR | +2.069 |
trump | +2.030 |
Neg logit contributions | |
interstitial | -2.596 |
farious | -2.543 |
benefit | -2.430 |
propri | -2.326 |
oult | -2.290 |
Token | |
Token ID | 3907 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
edom | +2.556 |
Afric | +2.419 |
Ange | +2.361 |
IOR | +2.286 |
trump | +2.268 |
Neg logit contributions | |
interstitial | -3.501 |
farious | -3.429 |
benefit | -3.300 |
propri | -3.121 |
oult | -3.121 |
Token | � |
Token ID | 447 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
edom | +0.370 |
Afric | +0.343 |
Ange | +0.335 |
IOR | +0.332 |
trump | +0.325 |
Neg logit contributions | |
interstitial | -0.449 |
farious | -0.436 |
benefit | -0.425 |
propri | -0.404 |
oult | -0.398 |
Token | � |
Token ID | 251 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
interstitial | +0.226 |
farious | +0.221 |
benefit | +0.216 |
propri | +0.207 |
oult | +0.201 |
Neg logit contributions | |
edom | -0.186 |
Afric | -0.173 |
Ange | -0.169 |
IOR | -0.168 |
trump | -0.162 |
Token | Ign |
Token ID | 16583 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
edom | +0.047 |
Afric | +0.044 |
Ange | +0.043 |
IOR | +0.043 |
trump | +0.042 |
Neg logit contributions | |
interstitial | -0.051 |
farious | -0.050 |
benefit | -0.049 |
propri | -0.046 |
oult | -0.045 |
Token | at |
Token ID | 265 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
edom | +0.804 |
Afric | +0.735 |
Ange | +0.731 |
IOR | +0.718 |
trump | +0.705 |
Neg logit contributions | |
interstitial | -0.850 |
farious | -0.827 |
benefit | -0.789 |
propri | -0.766 |
549 | -0.720 |
Token | ius |
Token ID | 3754 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
edom | +1.862 |
IOR | +1.676 |
Afric | +1.655 |
Ange | +1.614 |
trump | +1.570 |
Neg logit contributions | |
interstitial | -2.765 |
farious | -2.702 |
benefit | -2.621 |
propri | -2.519 |
oult | -2.456 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
edom | +3.085 |
Afric | +2.910 |
Ange | +2.867 |
IOR | +2.852 |
trump | +2.839 |
Neg logit contributions | |
interstitial | -2.369 |
farious | -2.248 |
benefit | -2.224 |
propri | -2.044 |
oult | -2.003 |
Token | of |
Token ID | 286 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
edom | +5.761 |
Afric | +5.213 |
trump | +5.180 |
Ange | +5.167 |
IOR | +5.081 |
Neg logit contributions | |
interstitial | -8.101 |
farious | -7.804 |
benefit | -7.710 |
oult | -7.281 |
propri | -7.227 |
Token | Truman |
Token ID | 33027 |
Feature activation | +7.28e-03 |
Pos logit contributions | |
edom | +1.535 |
Afric | +1.405 |
Ange | +1.377 |
IOR | +1.363 |
trump | +1.336 |
Neg logit contributions | |
interstitial | -2.185 |
farious | -2.134 |
benefit | -2.084 |
propri | -1.982 |
oult | -1.963 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
interstitial | +0.030 |
farious | +0.030 |
benefit | +0.029 |
propri | +0.028 |
oult | +0.027 |
Neg logit contributions | |
edom | -0.027 |
Afric | -0.025 |
Ange | -0.024 |
IOR | -0.024 |
trump | -0.023 |
Token | � |
Token ID | 564 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
edom | +1.536 |
Afric | +1.422 |
Ange | +1.396 |
IOR | +1.372 |
trump | +1.323 |
Neg logit contributions | |
interstitial | -2.245 |
farious | -2.160 |
benefit | -2.129 |
propri | -2.042 |
oult | -2.005 |
Token | � |
Token ID | 250 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
edom | +1.355 |
Afric | +1.228 |
IOR | +1.227 |
Ange | +1.213 |
trump | +1.167 |
Neg logit contributions | |
interstitial | -2.171 |
farious | -2.122 |
benefit | -2.060 |
propri | -1.987 |
oult | -1.946 |
Token | the |
Token ID | 262 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
interstitial | +0.029 |
farious | +0.029 |
benefit | +0.028 |
propri | +0.027 |
oult | +0.026 |
Neg logit contributions | |
edom | -0.027 |
Afric | -0.026 |
Ange | -0.025 |
IOR | -0.025 |
trump | -0.024 |
Token | West |
Token ID | 2688 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
edom | +0.170 |
Afric | +0.160 |
Ange | +0.156 |
IOR | +0.154 |
trump | +0.150 |
Neg logit contributions | |
interstitial | -0.183 |
farious | -0.178 |
benefit | -0.174 |
propri | -0.165 |
oult | -0.161 |
Token | Wing |
Token ID | 13405 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
edom | +0.185 |
Afric | +0.172 |
Ange | +0.167 |
IOR | +0.167 |
trump | +0.160 |
Neg logit contributions | |
interstitial | -0.233 |
farious | -0.228 |
benefit | -0.223 |
propri | -0.214 |
oult | -0.208 |
Token | , |
Token ID | 11 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
interstitial | +2.348 |
farious | +2.284 |
benefit | +2.262 |
propri | +2.154 |
oult | +2.075 |
Neg logit contributions | |
edom | -2.303 |
Afric | -2.143 |
IOR | -2.097 |
Ange | -2.091 |
trump | -1.998 |
Token | including |
Token ID | 1390 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
edom | +0.874 |
Afric | +0.827 |
Ange | +0.811 |
IOR | +0.796 |
trump | +0.783 |
Neg logit contributions | |
interstitial | -1.006 |
farious | -0.984 |
benefit | -0.959 |
propri | -0.904 |
oult | -0.891 |
Token | Sebastian |
Token ID | 26190 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
interstitial | +0.044 |
farious | +0.043 |
benefit | +0.042 |
propri | +0.040 |
oult | +0.039 |
Neg logit contributions | |
edom | -0.040 |
Afric | -0.038 |
Ange | -0.037 |
IOR | -0.036 |
trump | -0.035 |
Token | Gork |
Token ID | 49882 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
edom | +2.720 |
Ange | +2.511 |
Afric | +2.417 |
trump | +2.366 |
IOR | +2.212 |
Neg logit contributions | |
interstitial | -10.870 |
benefit | -10.493 |
farious | -10.458 |
oult | -10.080 |
arij | -9.999 |
Token | a |
Token ID | 64 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
edom | +1.212 |
Afric | +1.119 |
Ange | +1.117 |
IOR | +1.114 |
trump | +1.085 |
Neg logit contributions | |
interstitial | -1.213 |
farious | -1.166 |
benefit | -1.147 |
propri | -1.102 |
549 | -1.044 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
interstitial | +0.303 |
farious | +0.296 |
benefit | +0.289 |
propri | +0.276 |
oult | +0.268 |
Neg logit contributions | |
edom | -0.269 |
Afric | -0.250 |
Ange | -0.245 |
IOR | -0.243 |
trump | -0.235 |
Token | have |
Token ID | 423 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
edom | +0.059 |
Afric | +0.056 |
Ange | +0.055 |
IOR | +0.054 |
trump | +0.053 |
Neg logit contributions | |
interstitial | -0.066 |
farious | -0.064 |
benefit | -0.063 |
propri | -0.059 |
oult | -0.058 |
Token | received |
Token ID | 2722 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
edom | +1.728 |
Afric | +1.614 |
Ange | +1.593 |
IOR | +1.560 |
trump | +1.556 |
Neg logit contributions | |
interstitial | -2.023 |
farious | -1.971 |
benefit | -1.922 |
propri | -1.796 |
oult | -1.787 |
Token | ; |
Token ID | 26 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
interstitial | +0.403 |
farious | +0.395 |
benefit | +0.387 |
propri | +0.370 |
oult | +0.359 |
Neg logit contributions | |
edom | -0.350 |
Afric | -0.326 |
Ange | -0.318 |
IOR | -0.317 |
trump | -0.304 |
Token | trek |
Token ID | 30784 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
edom | +1.193 |
Afric | +1.098 |
Ange | +1.076 |
IOR | +1.057 |
trump | +1.045 |
Neg logit contributions | |
interstitial | -1.478 |
farious | -1.436 |
benefit | -1.402 |
propri | -1.330 |
549 | -1.298 |
Token | amer |
Token ID | 2382 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
interstitial | +0.061 |
farious | +0.059 |
benefit | +0.058 |
propri | +0.055 |
oult | +0.053 |
Neg logit contributions | |
edom | -0.062 |
Afric | -0.058 |
Ange | -0.057 |
IOR | -0.057 |
trump | -0.055 |
Token | ica |
Token ID | 3970 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
edom | +0.860 |
Afric | +0.787 |
Ange | +0.771 |
IOR | +0.761 |
trump | +0.738 |
Neg logit contributions | |
interstitial | -1.017 |
farious | -0.985 |
benefit | -0.963 |
propri | -0.923 |
oult | -0.892 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
edom | +2.488 |
Afric | +2.289 |
Ange | +2.243 |
IOR | +2.231 |
trump | +2.163 |
Neg logit contributions | |
interstitial | -2.794 |
farious | -2.720 |
benefit | -2.636 |
propri | -2.549 |
oult | -2.455 |
Token | co |
Token ID | 1073 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
edom | +1.327 |
Afric | +1.199 |
Ange | +1.157 |
IOR | +1.143 |
trump | +1.101 |
Neg logit contributions | |
interstitial | -2.114 |
farious | -2.070 |
benefit | -1.999 |
propri | -1.957 |
oult | -1.891 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
edom | +4.781 |
)( | +4.385 |
Ange | +4.136 |
trump | +4.086 |
IOR | +4.024 |
Neg logit contributions | |
interstitial | -8.863 |
farious | -8.834 |
propri | -8.002 |
benefit | -7.859 |
arij | -7.651 |
Token | uk |
Token ID | 2724 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
edom | +0.671 |
Afric | +0.611 |
Ange | +0.600 |
IOR | +0.592 |
trump | +0.577 |
Neg logit contributions | |
interstitial | -0.745 |
farious | -0.733 |
benefit | -0.691 |
propri | -0.684 |
549 | -0.652 |
Token | ) |
Token ID | 8 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
edom | +2.184 |
Afric | +1.955 |
Ange | +1.856 |
IOR | +1.835 |
trump | +1.742 |
Neg logit contributions | |
interstitial | -4.990 |
farious | -4.871 |
benefit | -4.803 |
propri | -4.616 |
oult | -4.534 |
Token | has |
Token ID | 468 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
edom | +1.311 |
Afric | +1.234 |
Ange | +1.199 |
IOR | +1.177 |
trump | +1.172 |
Neg logit contributions | |
interstitial | -1.408 |
farious | -1.368 |
benefit | -1.318 |
propri | -1.249 |
oult | -1.223 |
Token | an |
Token ID | 281 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
edom | +0.887 |
Afric | +0.830 |
Ange | +0.811 |
IOR | +0.799 |
trump | +0.782 |
Neg logit contributions | |
interstitial | -0.904 |
farious | -0.886 |
benefit | -0.857 |
propri | -0.808 |
oult | -0.793 |
Token | Cash |
Token ID | 16210 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
interstitial | +0.603 |
farious | +0.588 |
benefit | +0.576 |
propri | +0.549 |
oult | +0.534 |
Neg logit contributions | |
edom | -0.517 |
Afric | -0.481 |
Ange | -0.470 |
IOR | -0.467 |
trump | -0.450 |
Token | � |
Token ID | 447 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
interstitial | +3.007 |
farious | +2.953 |
benefit | +2.907 |
propri | +2.761 |
549 | +2.694 |
Neg logit contributions | |
edom | -2.771 |
Afric | -2.582 |
Ange | -2.509 |
IOR | -2.499 |
trump | -2.403 |
Token | � |
Token ID | 251 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
interstitial | +0.100 |
farious | +0.098 |
benefit | +0.096 |
propri | +0.092 |
oult | +0.089 |
Neg logit contributions | |
edom | -0.080 |
Afric | -0.074 |
Ange | -0.072 |
IOR | -0.071 |
trump | -0.069 |
Token | ( |
Token ID | 357 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
edom | +0.846 |
Afric | +0.785 |
Ange | +0.775 |
IOR | +0.768 |
trump | +0.744 |
Neg logit contributions | |
interstitial | -0.969 |
farious | -0.935 |
benefit | -0.914 |
propri | -0.875 |
oult | -0.851 |
Token | Polit |
Token ID | 39866 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
edom | +2.780 |
IOR | +2.557 |
Afric | +2.556 |
Ange | +2.551 |
trump | +2.443 |
Neg logit contributions | |
interstitial | -2.643 |
farious | -2.573 |
benefit | -2.463 |
propri | -2.407 |
arij | -2.320 |
Token | ico |
Token ID | 3713 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
edom | +0.416 |
Afric | +0.384 |
Ange | +0.376 |
IOR | +0.375 |
trump | +0.360 |
Neg logit contributions | |
interstitial | -0.507 |
farious | -0.494 |
benefit | -0.484 |
propri | -0.463 |
oult | -0.450 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
edom | +5.048 |
Ange | +4.725 |
Afric | +4.672 |
trump | +4.576 |
)( | +4.518 |
Neg logit contributions | |
interstitial | -8.574 |
farious | -7.971 |
benefit | -7.922 |
propri | -7.522 |
arij | -7.504 |
Token | July |
Token ID | 2901 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
edom | +2.973 |
Ange | +2.834 |
Afric | +2.820 |
trump | +2.696 |
IOR | +2.651 |
Neg logit contributions | |
interstitial | -5.049 |
farious | -4.833 |
benefit | -4.728 |
oult | -4.471 |
propri | -4.464 |
Token | 7 |
Token ID | 767 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
edom | +2.593 |
Afric | +2.537 |
Ange | +2.527 |
IOR | +2.443 |
trump | +2.390 |
Neg logit contributions | |
interstitial | -4.000 |
farious | -3.883 |
benefit | -3.752 |
propri | -3.554 |
oult | -3.539 |
Token | ) |
Token ID | 8 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
interstitial | +0.536 |
farious | +0.525 |
benefit | +0.514 |
propri | +0.493 |
oult | +0.478 |
Neg logit contributions | |
edom | -0.424 |
Afric | -0.393 |
Ange | -0.382 |
IOR | -0.380 |
trump | -0.365 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
edom | +1.285 |
Afric | +1.201 |
Ange | +1.179 |
IOR | +1.170 |
trump | +1.133 |
Neg logit contributions | |
interstitial | -1.441 |
farious | -1.383 |
benefit | -1.361 |
propri | -1.296 |
oult | -1.267 |
Token | gave |
Token ID | 2921 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
interstitial | +0.198 |
farious | +0.194 |
benefit | +0.188 |
propri | +0.178 |
oult | +0.175 |
Neg logit contributions | |
edom | -0.194 |
Afric | -0.183 |
Ange | -0.180 |
IOR | -0.178 |
trump | -0.174 |
Token | Congress |
Token ID | 3162 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
edom | +1.296 |
Afric | +1.227 |
Ange | +1.209 |
IOR | +1.192 |
trump | +1.162 |
Neg logit contributions | |
interstitial | -1.373 |
farious | -1.353 |
benefit | -1.312 |
propri | -1.243 |
oult | -1.228 |
Token | six |
Token ID | 2237 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
edom | +0.828 |
Afric | +0.774 |
Ange | +0.758 |
IOR | +0.751 |
trump | +0.733 |
Neg logit contributions | |
interstitial | -0.971 |
farious | -0.955 |
benefit | -0.924 |
propri | -0.878 |
oult | -0.865 |
Token | months |
Token ID | 1933 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
edom | +0.532 |
Afric | +0.502 |
Ange | +0.491 |
IOR | +0.487 |
trump | +0.478 |
Neg logit contributions | |
interstitial | -0.502 |
farious | -0.487 |
benefit | -0.475 |
propri | -0.446 |
oult | -0.436 |
Token | to |
Token ID | 284 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
edom | +2.786 |
Afric | +2.575 |
Ange | +2.520 |
IOR | +2.513 |
trump | +2.438 |
Neg logit contributions | |
interstitial | -3.346 |
farious | -3.279 |
benefit | -3.183 |
propri | -3.032 |
oult | -2.964 |
Token | write |
Token ID | 3551 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
edom | +2.835 |
trump | +2.756 |
Afric | +2.732 |
IOR | +2.664 |
Ange | +2.626 |
Neg logit contributions | |
interstitial | -3.706 |
farious | -3.535 |
benefit | -3.263 |
arij | -3.121 |
oult | -3.091 |
Token | it |
Token ID | 340 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
edom | +5.775 |
Ange | +5.508 |
IOR | +5.498 |
Afric | +5.441 |
trump | +5.385 |
Neg logit contributions | |
interstitial | -7.305 |
farious | -7.195 |
benefit | -6.820 |
oult | -6.741 |
arij | -6.557 |
Token | into |
Token ID | 656 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
edom | +1.637 |
Afric | +1.533 |
IOR | +1.502 |
Ange | +1.494 |
trump | +1.459 |
Neg logit contributions | |
interstitial | -1.657 |
farious | -1.612 |
benefit | -1.556 |
propri | -1.462 |
oult | -1.458 |
Token | law |
Token ID | 1099 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
edom | +0.188 |
Afric | +0.177 |
Ange | +0.173 |
IOR | +0.172 |
trump | +0.167 |
Neg logit contributions | |
interstitial | -0.158 |
farious | -0.153 |
benefit | -0.149 |
propri | -0.141 |
oult | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
interstitial | +0.332 |
farious | +0.324 |
benefit | +0.317 |
propri | +0.302 |
oult | +0.294 |
Neg logit contributions | |
edom | -0.301 |
Afric | -0.280 |
Ange | -0.274 |
IOR | -0.273 |
trump | -0.263 |
Token | a |
Token ID | 257 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
interstitial | +0.547 |
farious | +0.535 |
benefit | +0.521 |
propri | +0.492 |
oult | +0.483 |
Neg logit contributions | |
edom | -0.514 |
Afric | -0.482 |
Ange | -0.473 |
IOR | -0.469 |
trump | -0.458 |
Token | � |
Token ID | 447 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
interstitial | +1.368 |
farious | +1.335 |
benefit | +1.308 |
propri | +1.250 |
oult | +1.212 |
Neg logit contributions | |
edom | -1.194 |
Afric | -1.108 |
Ange | -1.083 |
IOR | -1.079 |
trump | -1.034 |
Token | � |
Token ID | 251 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
interstitial | +1.303 |
farious | +1.266 |
benefit | +1.245 |
propri | +1.185 |
oult | +1.149 |
Neg logit contributions | |
edom | -1.214 |
Afric | -1.133 |
Ange | -1.104 |
IOR | -1.097 |
trump | -1.056 |
Token | Ign |
Token ID | 16583 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
interstitial | +0.178 |
farious | +0.174 |
benefit | +0.170 |
propri | +0.162 |
oult | +0.159 |
Neg logit contributions | |
edom | -0.154 |
Afric | -0.143 |
Ange | -0.140 |
IOR | -0.139 |
trump | -0.135 |
Token | at |
Token ID | 265 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
edom | +0.434 |
Afric | +0.399 |
Ange | +0.396 |
IOR | +0.389 |
trump | +0.381 |
Neg logit contributions | |
interstitial | -0.441 |
farious | -0.430 |
benefit | -0.411 |
propri | -0.397 |
549 | -0.375 |
Token | ius |
Token ID | 3754 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
edom | +1.934 |
IOR | +1.722 |
Afric | +1.719 |
Ange | +1.676 |
trump | +1.615 |
Neg logit contributions | |
interstitial | -2.908 |
farious | -2.827 |
benefit | -2.740 |
propri | -2.641 |
oult | -2.575 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
edom | +2.495 |
Afric | +2.337 |
Ange | +2.300 |
IOR | +2.292 |
trump | +2.260 |
Neg logit contributions | |
interstitial | -2.156 |
farious | -2.060 |
benefit | -2.039 |
propri | -1.902 |
oult | -1.848 |
Token | . |
Token ID | 13 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
edom | +5.590 |
Afric | +5.099 |
Ange | +5.017 |
trump | +4.997 |
IOR | +4.953 |
Neg logit contributions | |
interstitial | -7.805 |
farious | -7.506 |
benefit | -7.389 |
propri | -6.962 |
oult | -6.921 |
Token |
|
Token ID | 198 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
edom | +2.246 |
Afric | +2.101 |
Ange | +2.056 |
IOR | +2.016 |
trump | +1.965 |
Neg logit contributions | |
interstitial | -2.959 |
farious | -2.830 |
benefit | -2.794 |
propri | -2.674 |
oult | -2.630 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
edom | +1.494 |
Ange | +1.423 |
IOR | +1.399 |
Afric | +1.383 |
trump | +1.333 |
Neg logit contributions | |
interstitial | -2.603 |
farious | -2.535 |
benefit | -2.374 |
propri | -2.346 |
arij | -2.281 |
Token | � |
Token ID | 447 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
edom | +0.671 |
Afric | +0.617 |
IOR | +0.606 |
Ange | +0.604 |
trump | +0.580 |
Neg logit contributions | |
interstitial | -0.825 |
farious | -0.804 |
benefit | -0.785 |
propri | -0.756 |
oult | -0.735 |
Token | � |
Token ID | 250 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
edom | +0.311 |
Afric | +0.285 |
IOR | +0.283 |
Ange | +0.280 |
trump | +0.268 |
Neg logit contributions | |
interstitial | -0.465 |
farious | -0.455 |
benefit | -0.442 |
propri | -0.426 |
oult | -0.414 |
Token | idea |
Token ID | 2126 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
edom | +2.508 |
Afric | +2.348 |
Ange | +2.307 |
IOR | +2.279 |
trump | +2.205 |
Neg logit contributions | |
farious | -2.363 |
interstitial | -2.362 |
benefit | -2.295 |
549 | -2.109 |
propri | -2.109 |
Token | that |
Token ID | 326 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
edom | +1.521 |
Afric | +1.429 |
Ange | +1.425 |
IOR | +1.381 |
trump | +1.359 |
Neg logit contributions | |
interstitial | -2.009 |
farious | -1.961 |
benefit | -1.916 |
propri | -1.808 |
oult | -1.775 |
Token | eventually |
Token ID | 4191 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
edom | +1.409 |
Afric | +1.326 |
Ange | +1.322 |
IOR | +1.285 |
trump | +1.271 |
Neg logit contributions | |
interstitial | -1.496 |
farious | -1.472 |
benefit | -1.412 |
propri | -1.336 |
oult | -1.307 |
Token | led |
Token ID | 2957 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
edom | +1.833 |
Afric | +1.718 |
Ange | +1.699 |
trump | +1.680 |
IOR | +1.668 |
Neg logit contributions | |
interstitial | -1.819 |
farious | -1.789 |
benefit | -1.726 |
propri | -1.623 |
oult | -1.602 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
edom | +0.975 |
Afric | +0.910 |
Ange | +0.895 |
IOR | +0.884 |
trump | +0.855 |
Neg logit contributions | |
interstitial | -1.089 |
farious | -1.062 |
benefit | -1.038 |
propri | -0.990 |
oult | -0.959 |
Token | Christopher |
Token ID | 12803 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
edom | +0.749 |
Afric | +0.696 |
Ange | +0.691 |
IOR | +0.675 |
trump | +0.656 |
Neg logit contributions | |
interstitial | -0.889 |
farious | -0.866 |
benefit | -0.848 |
propri | -0.803 |
oult | -0.786 |
Token | Nolan |
Token ID | 27788 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
edom | +4.337 |
Ange | +4.283 |
Afric | +4.171 |
IOR | +4.032 |
Chin | +3.841 |
Neg logit contributions | |
interstitial | -9.079 |
farious | -8.363 |
benefit | -8.282 |
propri | -8.084 |
arij | -8.059 |
Token | � |
Token ID | 447 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
edom | +0.924 |
Afric | +0.858 |
Ange | +0.849 |
IOR | +0.836 |
trump | +0.812 |
Neg logit contributions | |
interstitial | -1.138 |
farious | -1.107 |
benefit | -1.091 |
propri | -1.037 |
arij | -1.004 |
Token | � |
Token ID | 247 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
edom | +1.022 |
Afric | +0.958 |
IOR | +0.955 |
Ange | +0.953 |
trump | +0.922 |
Neg logit contributions | |
interstitial | -0.846 |
farious | -0.841 |
benefit | -0.803 |
propri | -0.763 |
oult | -0.734 |
Token | s |
Token ID | 82 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
interstitial | +0.790 |
farious | +0.767 |
benefit | +0.738 |
propri | +0.703 |
oult | +0.677 |
Neg logit contributions | |
edom | -0.961 |
Afric | -0.891 |
Ange | -0.884 |
IOR | -0.880 |
trump | -0.858 |
Token | Batman |
Token ID | 9827 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
interstitial | +0.833 |
farious | +0.815 |
benefit | +0.799 |
propri | +0.766 |
oult | +0.746 |
Neg logit contributions | |
edom | -0.630 |
Afric | -0.582 |
Ange | -0.567 |
IOR | -0.565 |
trump | -0.541 |
Token | : |
Token ID | 25 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
interstitial | +0.417 |
farious | +0.408 |
benefit | +0.392 |
propri | +0.378 |
oult | +0.366 |
Neg logit contributions | |
edom | -0.348 |
Afric | -0.326 |
Ange | -0.323 |
IOR | -0.319 |
trump | -0.308 |
Token | 47 |
Token ID | 2857 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
interstitial | +1.829 |
farious | +1.794 |
benefit | +1.726 |
549 | +1.601 |
propri | +1.587 |
Neg logit contributions | |
edom | -3.151 |
Afric | -3.029 |
Ange | -2.976 |
IOR | -2.970 |
trump | -2.831 |
Token | ] |
Token ID | 60 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
interstitial | +1.301 |
farious | +1.273 |
benefit | +1.237 |
propri | +1.192 |
oult | +1.160 |
Neg logit contributions | |
edom | -0.901 |
Afric | -0.833 |
Ange | -0.821 |
IOR | -0.811 |
trump | -0.779 |
Token | < |
Token ID | 1279 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
edom | +1.377 |
Afric | +1.274 |
Ange | +1.246 |
IOR | +1.241 |
trump | +1.196 |
Neg logit contributions | |
interstitial | -1.856 |
farious | -1.808 |
benefit | -1.776 |
propri | -1.694 |
oult | -1.650 |
Token | and |
Token ID | 392 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
edom | +0.094 |
Afric | +0.088 |
Ange | +0.086 |
IOR | +0.085 |
trump | +0.082 |
Neg logit contributions | |
interstitial | -0.090 |
farious | -0.088 |
benefit | -0.086 |
propri | -0.082 |
oult | -0.079 |
Token | amar |
Token ID | 39236 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
edom | +1.946 |
Afric | +1.774 |
Ange | +1.758 |
IOR | +1.745 |
trump | +1.705 |
Neg logit contributions | |
interstitial | -1.869 |
farious | -1.814 |
benefit | -1.772 |
propri | -1.703 |
oult | -1.608 |
Token | ok |
Token ID | 482 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
edom | +7.071 |
Afric | +6.249 |
IOR | +6.199 |
trump | +6.177 |
Ange | +6.090 |
Neg logit contributions | |
interstitial | -6.199 |
farious | -5.861 |
benefit | -5.667 |
propri | -5.598 |
applic | -5.104 |
Token | k |
Token ID | 74 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
edom | +2.624 |
Afric | +2.288 |
IOR | +2.246 |
Ange | +2.244 |
trump | +2.189 |
Neg logit contributions | |
interstitial | -3.582 |
farious | -3.452 |
benefit | -3.400 |
propri | -3.299 |
oult | -3.107 |
Token | > |
Token ID | 29 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
edom | +1.992 |
Afric | +1.749 |
IOR | +1.710 |
Ange | +1.710 |
trump | +1.668 |
Neg logit contributions | |
interstitial | -3.043 |
farious | -2.946 |
benefit | -2.892 |
propri | -2.796 |
oult | -2.676 |
Token | k |
Token ID | 479 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
edom | +3.854 |
Ange | +3.691 |
Afric | +3.688 |
trump | +3.576 |
IOR | +3.479 |
Neg logit contributions | |
interstitial | -5.057 |
farious | -4.953 |
benefit | -4.781 |
oult | -4.447 |
propri | -4.426 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
edom | +2.310 |
Afric | +2.126 |
Ange | +2.110 |
IOR | +2.095 |
trump | +2.047 |
Neg logit contributions | |
interstitial | -2.330 |
farious | -2.234 |
benefit | -2.188 |
propri | -2.068 |
oult | -1.995 |
Token | under |
Token ID | 739 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
interstitial | +2.508 |
farious | +2.464 |
benefit | +2.446 |
propri | +2.330 |
ayer | +2.232 |
Neg logit contributions | |
edom | -2.889 |
Afric | -2.670 |
Ange | -2.634 |
IOR | -2.607 |
trump | -2.480 |
Token | control |
Token ID | 1630 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
interstitial | +0.825 |
farious | +0.788 |
benefit | +0.758 |
propri | +0.691 |
oult | +0.651 |
Neg logit contributions | |
edom | -2.057 |
Afric | -1.962 |
Ange | -1.935 |
IOR | -1.927 |
trump | -1.881 |
Token | . |
Token ID | 13 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
interstitial | +0.430 |
farious | +0.420 |
benefit | +0.410 |
propri | +0.391 |
oult | +0.380 |
Neg logit contributions | |
edom | -0.390 |
Afric | -0.364 |
Ange | -0.356 |
IOR | -0.354 |
trump | -0.342 |
Token | ( |
Token ID | 357 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
interstitial | +1.492 |
farious | +1.458 |
benefit | +1.423 |
propri | +1.351 |
549 | +1.307 |
Neg logit contributions | |
edom | -1.634 |
Afric | -1.520 |
Ange | -1.485 |
IOR | -1.483 |
trump | -1.433 |
Token | Man |
Token ID | 5124 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
edom | +1.162 |
Afric | +1.096 |
IOR | +1.085 |
Ange | +1.079 |
trump | +1.038 |
Neg logit contributions | |
interstitial | -0.781 |
farious | -0.758 |
benefit | -0.728 |
propri | -0.692 |
oult | -0.665 |
Token | it |
Token ID | 270 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
edom | +3.282 |
Afric | +3.038 |
Ange | +3.015 |
IOR | +2.984 |
trump | +2.875 |
Neg logit contributions | |
interstitial | -3.009 |
farious | -2.980 |
benefit | -2.904 |
propri | -2.746 |
arij | -2.641 |
Token | oba |
Token ID | 19981 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
edom | +5.615 |
Afric | +5.326 |
trump | +5.108 |
Ange | +4.991 |
IOR | +4.934 |
Neg logit contributions | |
interstitial | -7.530 |
benefit | -7.250 |
farious | -6.894 |
oult | -6.638 |
propri | -6.465 |
Token | Chambers |
Token ID | 30717 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
edom | +3.721 |
Afric | +3.496 |
IOR | +3.399 |
Ange | +3.336 |
trump | +3.222 |
Neg logit contributions | |
interstitial | -4.462 |
farious | -4.286 |
benefit | -4.180 |
propri | -3.956 |
oult | -3.928 |
Token | of |
Token ID | 286 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
edom | +0.733 |
Afric | +0.676 |
Ange | +0.660 |
IOR | +0.656 |
trump | +0.629 |
Neg logit contributions | |
interstitial | -0.962 |
farious | -0.942 |
benefit | -0.924 |
propri | -0.885 |
oult | -0.859 |
Token | Commerce |
Token ID | 16127 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
edom | +1.049 |
Afric | +0.944 |
Ange | +0.919 |
IOR | +0.898 |
trump | +0.851 |
Neg logit contributions | |
interstitial | -2.277 |
farious | -2.235 |
benefit | -2.184 |
propri | -2.105 |
oult | -2.071 |
Token | ) |
Token ID | 8 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
edom | +1.237 |
Afric | +1.131 |
Ange | +1.094 |
IOR | +1.084 |
trump | +1.032 |
Neg logit contributions | |
interstitial | -2.423 |
farious | -2.369 |
benefit | -2.325 |
propri | -2.226 |
oult | -2.196 |
Token | eye |
Token ID | 25379 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
edom | +0.857 |
Afric | +0.808 |
Ange | +0.792 |
IOR | +0.788 |
trump | +0.766 |
Neg logit contributions | |
interstitial | -0.656 |
farious | -0.636 |
benefit | -0.612 |
propri | -0.584 |
oult | -0.561 |
Token | view |
Token ID | 1570 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
interstitial | +1.309 |
farious | +1.273 |
benefit | +1.244 |
propri | +1.181 |
oult | +1.143 |
Neg logit contributions | |
edom | -1.421 |
Afric | -1.331 |
Ange | -1.303 |
IOR | -1.297 |
trump | -1.254 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
interstitial | +2.741 |
farious | +2.657 |
benefit | +2.625 |
propri | +2.505 |
oult | +2.426 |
Neg logit contributions | |
edom | -2.445 |
Afric | -2.283 |
Ange | -2.215 |
IOR | -2.209 |
trump | -2.118 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
interstitial | +1.104 |
farious | +1.078 |
benefit | +1.057 |
propri | +1.010 |
oult | +0.982 |
Neg logit contributions | |
edom | -0.911 |
Afric | -0.844 |
Ange | -0.824 |
IOR | -0.820 |
trump | -0.789 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
edom | +0.573 |
IOR | +0.534 |
Afric | +0.532 |
Ange | +0.530 |
trump | +0.500 |
Neg logit contributions | |
interstitial | -0.851 |
farious | -0.833 |
benefit | -0.795 |
propri | -0.781 |
oult | -0.753 |
Token | Photo |
Token ID | 6191 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
interstitial | +0.721 |
farious | +0.703 |
benefit | +0.687 |
propri | +0.655 |
oult | +0.636 |
Neg logit contributions | |
edom | -0.666 |
Afric | -0.620 |
Ange | -0.607 |
IOR | -0.604 |
trump | -0.582 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
interstitial | +4.161 |
farious | +4.014 |
benefit | +4.002 |
propri | +3.784 |
oult | +3.676 |
Neg logit contributions | |
edom | -4.470 |
Afric | -4.162 |
IOR | -4.039 |
Ange | -4.004 |
trump | -3.859 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
interstitial | +0.480 |
farious | +0.468 |
benefit | +0.453 |
propri | +0.437 |
oult | +0.424 |
Neg logit contributions | |
edom | -0.356 |
Afric | -0.330 |
Ange | -0.326 |
IOR | -0.323 |
trump | -0.310 |
Token | Pitt |
Token ID | 47627 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
interstitial | +1.295 |
farious | +1.257 |
benefit | +1.241 |
propri | +1.169 |
549 | +1.142 |
Neg logit contributions | |
edom | -1.253 |
Afric | -1.172 |
Ange | -1.140 |
IOR | -1.127 |
trump | -1.101 |
Token | sburgh |
Token ID | 11931 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
interstitial | +1.942 |
farious | +1.860 |
benefit | +1.826 |
propri | +1.655 |
oult | +1.549 |
Neg logit contributions | |
edom | -5.187 |
Afric | -4.987 |
IOR | -4.871 |
Ange | -4.855 |
trump | -4.739 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
interstitial | +1.079 |
farious | +1.050 |
benefit | +1.030 |
propri | +0.979 |
oult | +0.947 |
Neg logit contributions | |
edom | -1.110 |
Afric | -1.036 |
Ange | -1.014 |
IOR | -1.012 |
trump | -0.974 |
Token | Ramadan |
Token ID | 37604 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
edom | +2.116 |
Afric | +1.983 |
Ange | +1.919 |
IOR | +1.908 |
trump | +1.855 |
Neg logit contributions | |
interstitial | -2.354 |
farious | -2.320 |
benefit | -2.256 |
propri | -2.107 |
oult | -2.091 |
Token | argues |
Token ID | 11673 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
interstitial | +1.148 |
farious | +1.118 |
benefit | +1.094 |
propri | +1.041 |
oult | +1.011 |
Neg logit contributions | |
edom | -1.080 |
Afric | -1.009 |
Ange | -0.987 |
IOR | -0.981 |
trump | -0.947 |
Token | that |
Token ID | 326 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
edom | +1.023 |
Afric | +0.949 |
Ange | +0.928 |
IOR | +0.918 |
trump | +0.890 |
Neg logit contributions | |
interstitial | -1.328 |
farious | -1.284 |
benefit | -1.257 |
propri | -1.191 |
oult | -1.171 |
Token | Muhammad |
Token ID | 15870 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
interstitial | +0.172 |
farious | +0.168 |
benefit | +0.164 |
propri | +0.155 |
oult | +0.153 |
Neg logit contributions | |
edom | -0.147 |
Afric | -0.138 |
Ange | -0.135 |
IOR | -0.133 |
trump | -0.129 |
Token | dev |
Token ID | 1614 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
interstitial | +0.691 |
farious | +0.674 |
benefit | +0.659 |
propri | +0.628 |
oult | +0.610 |
Neg logit contributions | |
edom | -0.643 |
Afric | -0.599 |
Ange | -0.586 |
IOR | -0.583 |
trump | -0.563 |
Token | iated |
Token ID | 12931 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
interstitial | +0.680 |
farious | +0.658 |
benefit | +0.645 |
propri | +0.616 |
549 | +0.592 |
Neg logit contributions | |
edom | -0.658 |
Afric | -0.612 |
Ange | -0.600 |
IOR | -0.597 |
trump | -0.577 |
Token | from |
Token ID | 422 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
interstitial | +3.609 |
farious | +3.585 |
benefit | +3.562 |
propri | +3.450 |
549 | +3.254 |
Neg logit contributions | |
edom | -3.957 |
Afric | -3.648 |
IOR | -3.600 |
Ange | -3.597 |
trump | -3.429 |
Token | his |
Token ID | 465 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
interstitial | +2.861 |
farious | +2.791 |
benefit | +2.757 |
propri | +2.690 |
549 | +2.535 |
Neg logit contributions | |
edom | -2.741 |
Afric | -2.529 |
IOR | -2.503 |
Ange | -2.476 |
trump | -2.360 |
Token | earlier |
Token ID | 2961 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
interstitial | +0.216 |
farious | +0.210 |
benefit | +0.205 |
propri | +0.193 |
oult | +0.190 |
Neg logit contributions | |
edom | -0.194 |
Afric | -0.182 |
Ange | -0.177 |
IOR | -0.176 |
trump | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
interstitial | +1.224 |
farious | +1.190 |
benefit | +1.163 |
propri | +1.100 |
oult | +1.071 |
Neg logit contributions | |
edom | -1.266 |
Afric | -1.187 |
Ange | -1.162 |
IOR | -1.154 |
trump | -1.119 |
Token | more |
Token ID | 517 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
edom | +0.319 |
Afric | +0.302 |
Ange | +0.296 |
IOR | +0.292 |
trump | +0.287 |
Neg logit contributions | |
interstitial | -0.322 |
farious | -0.311 |
benefit | -0.304 |
propri | -0.284 |
oult | -0.280 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e-03 |
Pos logit contributions | |
interstitial | +0.589 |
farious | +0.571 |
benefit | +0.560 |
propri | +0.536 |
oult | +0.523 |
Neg logit contributions | |
edom | -0.463 |
Afric | -0.432 |
Ange | -0.423 |
IOR | -0.417 |
trump | -0.403 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
edom | +0.007 |
Afric | +0.007 |
Ange | +0.007 |
IOR | +0.007 |
trump | +0.006 |
Neg logit contributions | |
interstitial | -0.010 |
farious | -0.010 |
benefit | -0.010 |
propri | -0.010 |
oult | -0.009 |
Token | Yet |
Token ID | 11486 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
interstitial | +0.725 |
farious | +0.705 |
benefit | +0.687 |
propri | +0.658 |
oult | +0.638 |
Neg logit contributions | |
edom | -0.701 |
Afric | -0.653 |
Ange | -0.641 |
IOR | -0.640 |
trump | -0.614 |
Token | so |
Token ID | 523 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
interstitial | +1.678 |
farious | +1.636 |
benefit | +1.599 |
propri | +1.525 |
oult | +1.484 |
Neg logit contributions | |
edom | -1.506 |
Afric | -1.403 |
Ange | -1.372 |
IOR | -1.363 |
trump | -1.316 |
Token | far |
Token ID | 1290 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
interstitial | +3.802 |
farious | +3.700 |
benefit | +3.622 |
propri | +3.496 |
ayer | +3.338 |
Neg logit contributions | |
edom | -4.783 |
Afric | -4.488 |
IOR | -4.387 |
Ange | -4.356 |
trump | -4.115 |
Token | as |
Token ID | 355 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
interstitial | +5.010 |
farious | +4.879 |
benefit | +4.799 |
propri | +4.603 |
ayer | +4.410 |
Neg logit contributions | |
edom | -5.503 |
Afric | -5.192 |
Ange | -5.058 |
IOR | -5.040 |
TPS | -4.767 |
Token | it |
Token ID | 340 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
interstitial | +5.059 |
farious | +4.943 |
benefit | +4.864 |
propri | +4.731 |
549 | +4.442 |
Neg logit contributions | |
edom | -4.959 |
Afric | -4.573 |
IOR | -4.541 |
Ange | -4.427 |
TPS | -4.234 |
Token | was |
Token ID | 373 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
interstitial | +1.132 |
farious | +1.101 |
benefit | +1.074 |
propri | +1.017 |
oult | +0.981 |
Neg logit contributions | |
edom | -1.378 |
Afric | -1.296 |
Ange | -1.271 |
IOR | -1.267 |
trump | -1.223 |
Token | a |
Token ID | 257 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
interstitial | +1.105 |
farious | +1.074 |
benefit | +1.050 |
propri | +0.997 |
oult | +0.968 |
Neg logit contributions | |
edom | -1.119 |
Afric | -1.047 |
Ange | -1.025 |
IOR | -1.019 |
trump | -0.987 |
Token | national |
Token ID | 2260 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
interstitial | +1.874 |
farious | +1.828 |
benefit | +1.787 |
propri | +1.700 |
oult | +1.644 |
Neg logit contributions | |
edom | -1.945 |
Afric | -1.818 |
Ange | -1.781 |
IOR | -1.773 |
trump | -1.708 |
Token | unity |
Token ID | 14111 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
interstitial | +2.737 |
farious | +2.676 |
benefit | +2.622 |
propri | +2.497 |
oult | +2.397 |
Neg logit contributions | |
edom | -3.350 |
Afric | -3.130 |
IOR | -3.085 |
Ange | -3.082 |
trump | -2.937 |
Token | bert |
Token ID | 4835 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
edom | +1.719 |
Afric | +1.608 |
Ange | +1.585 |
IOR | +1.569 |
trump | +1.515 |
Neg logit contributions | |
interstitial | -1.663 |
farious | -1.624 |
benefit | -1.593 |
propri | -1.509 |
oult | -1.456 |
Token | " |
Token ID | 366 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
edom | +2.708 |
Afric | +2.554 |
Ange | +2.529 |
IOR | +2.444 |
trump | +2.410 |
Neg logit contributions | |
interstitial | -3.253 |
farious | -3.169 |
benefit | -3.115 |
propri | -2.959 |
oult | -2.888 |
Token | Short |
Token ID | 16438 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
edom | +2.920 |
IOR | +2.699 |
Afric | +2.689 |
Ange | +2.660 |
TPS | +2.535 |
Neg logit contributions | |
interstitial | -3.524 |
farious | -3.475 |
benefit | -3.278 |
propri | -3.277 |
oult | -3.117 |
Token | y |
Token ID | 88 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
edom | +3.174 |
Afric | +2.997 |
Ange | +2.915 |
IOR | +2.817 |
trump | +2.783 |
Neg logit contributions | |
interstitial | -3.474 |
farious | -3.354 |
benefit | -3.260 |
propri | -3.116 |
oult | -3.051 |
Token | " |
Token ID | 1 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
edom | +1.084 |
Afric | +1.013 |
Ange | +0.992 |
IOR | +0.987 |
trump | +0.953 |
Neg logit contributions | |
interstitial | -1.069 |
farious | -1.042 |
benefit | -1.018 |
propri | -0.968 |
oult | -0.939 |
Token | Bel |
Token ID | 3944 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
edom | +0.289 |
Afric | +0.267 |
Ange | +0.261 |
IOR | +0.260 |
trump | +0.249 |
Neg logit contributions | |
interstitial | -0.360 |
farious | -0.352 |
benefit | -0.345 |
propri | -0.330 |
oult | -0.321 |
Token | ton |
Token ID | 1122 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
interstitial | +3.586 |
farious | +3.510 |
benefit | +3.376 |
propri | +3.180 |
oult | +3.172 |
Neg logit contributions | |
edom | -3.891 |
Afric | -3.716 |
IOR | -3.634 |
Ange | -3.618 |
trump | -3.498 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
interstitial | +0.628 |
farious | +0.612 |
benefit | +0.598 |
propri | +0.570 |
oult | +0.553 |
Neg logit contributions | |
edom | -0.605 |
Afric | -0.565 |
Ange | -0.552 |
IOR | -0.549 |
trump | -0.530 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
edom | +0.692 |
Afric | +0.660 |
Ange | +0.646 |
IOR | +0.633 |
trump | +0.621 |
Neg logit contributions | |
interstitial | -0.853 |
farious | -0.838 |
benefit | -0.817 |
propri | -0.771 |
oult | -0.756 |
Token | World |
Token ID | 2159 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
interstitial | +0.607 |
farious | +0.592 |
benefit | +0.578 |
propri | +0.548 |
oult | +0.534 |
Neg logit contributions | |
edom | -0.544 |
Afric | -0.512 |
Ange | -0.499 |
IOR | -0.495 |
trump | -0.482 |
Token | War |
Token ID | 1810 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
interstitial | +2.542 |
farious | +2.513 |
benefit | +2.462 |
propri | +2.357 |
549 | +2.310 |
Neg logit contributions | |
edom | -1.859 |
Afric | -1.670 |
IOR | -1.633 |
Ange | -1.622 |
trump | -1.554 |
Token | a |
Token ID | 257 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
edom | +1.001 |
Afric | +0.940 |
Ange | +0.928 |
IOR | +0.910 |
trump | +0.893 |
Neg logit contributions | |
interstitial | -1.045 |
farious | -1.023 |
benefit | -0.996 |
propri | -0.931 |
oult | -0.924 |
Token | Martian |
Token ID | 32508 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
interstitial | +1.312 |
farious | +1.277 |
benefit | +1.248 |
propri | +1.187 |
oult | +1.152 |
Neg logit contributions | |
edom | -1.302 |
Afric | -1.217 |
Ange | -1.192 |
IOR | -1.185 |
trump | -1.145 |
Token | car |
Token ID | 1097 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
interstitial | +1.367 |
farious | +1.331 |
benefit | +1.300 |
propri | +1.241 |
oult | +1.200 |
Neg logit contributions | |
edom | -1.416 |
Afric | -1.324 |
Ange | -1.297 |
IOR | -1.291 |
trump | -1.244 |
Token | wash |
Token ID | 34670 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
edom | +2.274 |
Afric | +2.119 |
IOR | +2.052 |
Ange | +2.043 |
trump | +2.007 |
Neg logit contributions | |
interstitial | -2.627 |
farious | -2.540 |
benefit | -2.446 |
propri | -2.331 |
549 | -2.274 |
Token | ," |
Token ID | 553 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
interstitial | +0.765 |
farious | +0.739 |
benefit | +0.721 |
propri | +0.679 |
oult | +0.664 |
Neg logit contributions | |
edom | -0.772 |
Afric | -0.719 |
Ange | -0.709 |
IOR | -0.702 |
trump | -0.683 |
Token | said |
Token ID | 531 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
interstitial | +4.552 |
farious | +4.478 |
benefit | +4.317 |
propri | +4.180 |
549 | +4.021 |
Neg logit contributions | |
edom | -5.407 |
Afric | -5.044 |
IOR | -4.855 |
Ange | -4.792 |
trump | -4.680 |
Token | Chris |
Token ID | 5180 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
interstitial | +4.017 |
farious | +3.932 |
benefit | +3.853 |
propri | +3.731 |
549 | +3.582 |
Neg logit contributions | |
edom | -3.773 |
Afric | -3.466 |
IOR | -3.388 |
Ange | -3.330 |
trump | -3.224 |
Token | Rou |
Token ID | 13876 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
edom | +1.902 |
Afric | +1.782 |
Ange | +1.776 |
IOR | +1.704 |
trump | +1.655 |
Neg logit contributions | |
interstitial | -2.446 |
farious | -2.350 |
benefit | -2.315 |
propri | -2.214 |
oult | -2.163 |
Token | mel |
Token ID | 17694 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
interstitial | +0.730 |
farious | +0.710 |
benefit | +0.693 |
propri | +0.659 |
oult | +0.637 |
Neg logit contributions | |
edom | -0.793 |
Afric | -0.742 |
Ange | -0.727 |
IOR | -0.722 |
trump | -0.700 |
Token | iot |
Token ID | 5151 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
interstitial | +0.518 |
farious | +0.504 |
benefit | +0.492 |
propri | +0.468 |
oult | +0.455 |
Neg logit contributions | |
edom | -0.516 |
Afric | -0.483 |
Ange | -0.473 |
IOR | -0.471 |
trump | -0.454 |
Token | is |
Token ID | 271 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
edom | +0.637 |
Afric | +0.594 |
Ange | +0.580 |
IOR | +0.574 |
trump | +0.556 |
Neg logit contributions | |
interstitial | -0.724 |
farious | -0.703 |
benefit | -0.690 |
propri | -0.655 |
oult | -0.635 |
Token | the |
Token ID | 262 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
interstitial | +0.347 |
farious | +0.339 |
benefit | +0.332 |
propri | +0.317 |
oult | +0.309 |
Neg logit contributions | |
edom | -0.289 |
Afric | -0.268 |
Ange | -0.262 |
IOR | -0.260 |
trump | -0.251 |
Token | iceberg |
Token ID | 34849 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
interstitial | +0.200 |
farious | +0.194 |
benefit | +0.188 |
propri | +0.177 |
oult | +0.172 |
Neg logit contributions | |
edom | -0.255 |
Afric | -0.241 |
Ange | -0.237 |
IOR | -0.235 |
trump | -0.229 |
Token | is |
Token ID | 318 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
interstitial | +1.568 |
farious | +1.524 |
benefit | +1.489 |
propri | +1.422 |
oult | +1.358 |
Neg logit contributions | |
edom | -1.957 |
Afric | -1.845 |
IOR | -1.813 |
Ange | -1.808 |
trump | -1.737 |
Token | detached |
Token ID | 30795 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
interstitial | +1.249 |
farious | +1.218 |
benefit | +1.193 |
propri | +1.140 |
oult | +1.102 |
Neg logit contributions | |
edom | -1.192 |
Afric | -1.112 |
Ange | -1.088 |
IOR | -1.085 |
trump | -1.042 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
interstitial | +1.963 |
farious | +1.920 |
benefit | +1.886 |
propri | +1.808 |
549 | +1.739 |
Neg logit contributions | |
edom | -1.929 |
Afric | -1.809 |
Ange | -1.765 |
IOR | -1.757 |
trump | -1.694 |
Token | it |
Token ID | 340 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
interstitial | +0.495 |
farious | +0.483 |
benefit | +0.473 |
propri | +0.452 |
oult | +0.440 |
Neg logit contributions | |
edom | -0.419 |
Afric | -0.389 |
Ange | -0.380 |
IOR | -0.378 |
trump | -0.363 |
Token | quickly |
Token ID | 2952 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
interstitial | +0.741 |
farious | +0.722 |
benefit | +0.705 |
propri | +0.671 |
oult | +0.649 |
Neg logit contributions | |
edom | -0.799 |
Afric | -0.749 |
Ange | -0.733 |
IOR | -0.730 |
trump | -0.705 |
Token | begins |
Token ID | 6140 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
edom | +0.381 |
Afric | +0.357 |
Ange | +0.349 |
IOR | +0.345 |
trump | +0.340 |
Neg logit contributions | |
interstitial | -0.353 |
farious | -0.342 |
benefit | -0.335 |
propri | -0.312 |
oult | -0.306 |
Token | to |
Token ID | 284 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
interstitial | +2.742 |
farious | +2.642 |
benefit | +2.584 |
propri | +2.531 |
oult | +2.409 |
Neg logit contributions | |
edom | -2.977 |
Afric | -2.818 |
IOR | -2.776 |
Ange | -2.743 |
trump | -2.576 |
Token | cap |
Token ID | 1451 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
interstitial | +0.520 |
farious | +0.506 |
benefit | +0.495 |
propri | +0.470 |
oult | +0.456 |
Neg logit contributions | |
edom | -0.527 |
Afric | -0.493 |
Ange | -0.482 |
IOR | -0.480 |
trump | -0.464 |
Token | size |
Token ID | 7857 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
interstitial | +1.711 |
farious | +1.655 |
benefit | +1.612 |
propri | +1.502 |
oult | +1.444 |
Neg logit contributions | |
edom | -2.885 |
Afric | -2.741 |
Ange | -2.688 |
IOR | -2.682 |
trump | -2.607 |
Token | write |
Token ID | 3551 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
edom | +0.551 |
Afric | +0.513 |
Ange | +0.507 |
trump | +0.501 |
IOR | +0.498 |
Neg logit contributions | |
interstitial | -0.569 |
farious | -0.555 |
benefit | -0.525 |
propri | -0.492 |
oult | -0.487 |
Token | without |
Token ID | 1231 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
edom | +2.367 |
Afric | +2.194 |
Ange | +2.157 |
IOR | +2.134 |
trump | +2.102 |
Neg logit contributions | |
interstitial | -2.615 |
farious | -2.550 |
benefit | -2.480 |
oult | -2.330 |
propri | -2.307 |
Token | sn |
Token ID | 3013 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
interstitial | +1.796 |
farious | +1.735 |
benefit | +1.712 |
propri | +1.644 |
oult | +1.573 |
Neg logit contributions | |
edom | -1.837 |
Afric | -1.709 |
IOR | -1.672 |
Ange | -1.666 |
trump | -1.583 |
Token | orting |
Token ID | 24707 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
interstitial | +0.674 |
farious | +0.652 |
benefit | +0.635 |
propri | +0.603 |
oult | +0.577 |
Neg logit contributions | |
edom | -0.898 |
Afric | -0.840 |
Ange | -0.830 |
IOR | -0.824 |
trump | -0.799 |
Token | with |
Token ID | 351 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
interstitial | +0.315 |
farious | +0.307 |
benefit | +0.300 |
propri | +0.286 |
oult | +0.277 |
Neg logit contributions | |
edom | -0.307 |
Afric | -0.286 |
Ange | -0.280 |
IOR | -0.279 |
trump | -0.269 |
Token | incred |
Token ID | 4878 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
interstitial | +0.204 |
farious | +0.198 |
benefit | +0.193 |
propri | +0.183 |
oult | +0.179 |
Neg logit contributions | |
edom | -0.212 |
Afric | -0.198 |
Ange | -0.195 |
IOR | -0.193 |
trump | -0.188 |
Token | ul |
Token ID | 377 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
interstitial | +0.301 |
farious | +0.291 |
benefit | +0.284 |
propri | +0.268 |
oult | +0.258 |
Neg logit contributions | |
edom | -0.383 |
Afric | -0.359 |
Ange | -0.353 |
IOR | -0.351 |
trump | -0.341 |
Token | ity |
Token ID | 414 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
edom | +0.297 |
Afric | +0.275 |
Ange | +0.269 |
IOR | +0.268 |
trump | +0.260 |
Neg logit contributions | |
interstitial | -0.306 |
farious | -0.297 |
benefit | -0.289 |
propri | -0.275 |
oult | -0.268 |
Token | — |
Token ID | 851 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
edom | +2.432 |
Afric | +2.254 |
Ange | +2.209 |
IOR | +2.176 |
trump | +2.165 |
Neg logit contributions | |
interstitial | -2.569 |
farious | -2.475 |
benefit | -2.424 |
propri | -2.291 |
oult | -2.281 |
Token | Danish |
Token ID | 20849 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
interstitial | +0.458 |
farious | +0.446 |
benefit | +0.436 |
propri | +0.415 |
oult | +0.404 |
Neg logit contributions | |
edom | -0.437 |
Afric | -0.408 |
Ange | -0.400 |
IOR | -0.396 |
trump | -0.384 |
Token | companies |
Token ID | 2706 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
interstitial | +0.858 |
farious | +0.837 |
benefit | +0.819 |
propri | +0.781 |
oult | +0.758 |
Neg logit contributions | |
edom | -0.786 |
Afric | -0.732 |
Ange | -0.716 |
IOR | -0.712 |
trump | -0.686 |
Token | eligibility |
Token ID | 20069 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
interstitial | +0.598 |
farious | +0.582 |
benefit | +0.567 |
propri | +0.539 |
oult | +0.524 |
Neg logit contributions | |
edom | -0.598 |
Afric | -0.559 |
Ange | -0.548 |
IOR | -0.544 |
trump | -0.528 |
Token | " |
Token ID | 366 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
interstitial | +0.931 |
farious | +0.908 |
benefit | +0.889 |
propri | +0.848 |
oult | +0.825 |
Neg logit contributions | |
edom | -0.810 |
Afric | -0.753 |
Ange | -0.736 |
IOR | -0.731 |
trump | -0.705 |
Token | to |
Token ID | 1462 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
edom | +0.914 |
Afric | +0.849 |
IOR | +0.837 |
Ange | +0.833 |
trump | +0.799 |
Neg logit contributions | |
interstitial | -0.965 |
farious | -0.950 |
benefit | -0.901 |
propri | -0.886 |
oult | -0.855 |
Token | deter |
Token ID | 2206 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
edom | +0.581 |
Afric | +0.545 |
Ange | +0.532 |
IOR | +0.530 |
trump | +0.516 |
Neg logit contributions | |
interstitial | -0.644 |
farious | -0.624 |
benefit | -0.606 |
propri | -0.579 |
oult | -0.565 |
Token | people |
Token ID | 661 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
edom | +0.444 |
Afric | +0.414 |
Ange | +0.407 |
IOR | +0.407 |
trump | +0.396 |
Neg logit contributions | |
interstitial | -0.436 |
farious | -0.421 |
benefit | -0.409 |
propri | -0.390 |
oult | -0.384 |
Token | from |
Token ID | 422 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
interstitial | +0.501 |
farious | +0.487 |
benefit | +0.476 |
propri | +0.454 |
oult | +0.441 |
Neg logit contributions | |
edom | -0.460 |
Afric | -0.429 |
Ange | -0.420 |
IOR | -0.417 |
trump | -0.403 |
Token | waiting |
Token ID | 4953 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
interstitial | +1.562 |
farious | +1.523 |
benefit | +1.494 |
propri | +1.418 |
oult | +1.364 |
Neg logit contributions | |
edom | -1.754 |
Afric | -1.638 |
Ange | -1.604 |
IOR | -1.602 |
trump | -1.530 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
edom | +1.535 |
IOR | +1.424 |
Afric | +1.420 |
Ange | +1.408 |
trump | +1.371 |
Neg logit contributions | |
interstitial | -1.830 |
farious | -1.765 |
benefit | -1.703 |
propri | -1.621 |
oult | -1.594 |
Token | sign |
Token ID | 1051 |
Feature activation | +8.37e-03 |
Pos logit contributions | |
interstitial | +0.592 |
farious | +0.571 |
benefit | +0.549 |
propri | +0.528 |
oult | +0.514 |
Neg logit contributions | |
edom | -0.521 |
Afric | -0.488 |
Ange | -0.476 |
IOR | -0.475 |
trump | -0.466 |
Token | up |
Token ID | 510 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
interstitial | +0.035 |
farious | +0.034 |
benefit | +0.033 |
propri | +0.032 |
oult | +0.031 |
Neg logit contributions | |
edom | -0.031 |
Afric | -0.029 |
Ange | -0.028 |
IOR | -0.028 |
trump | -0.027 |
Token | for |
Token ID | 329 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
edom | +1.359 |
Afric | +1.255 |
Ange | +1.239 |
IOR | +1.234 |
trump | +1.207 |
Neg logit contributions | |
interstitial | -1.694 |
farious | -1.639 |
benefit | -1.582 |
propri | -1.515 |
oult | -1.487 |
Token | probably |
Token ID | 2192 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
edom | +0.993 |
Afric | +0.910 |
trump | +0.897 |
Ange | +0.897 |
IOR | +0.896 |
Neg logit contributions | |
interstitial | -1.191 |
farious | -1.145 |
benefit | -1.090 |
propri | -1.046 |
oult | -1.033 |
Token | result |
Token ID | 1255 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
interstitial | +0.558 |
farious | +0.543 |
benefit | +0.528 |
propri | +0.505 |
oult | +0.491 |
Neg logit contributions | |
edom | -0.500 |
Afric | -0.464 |
Ange | -0.455 |
IOR | -0.452 |
trump | -0.439 |
Token | in |
Token ID | 287 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
interstitial | +0.714 |
farious | +0.699 |
benefit | +0.687 |
propri | +0.651 |
549 | +0.625 |
Neg logit contributions | |
edom | -0.824 |
Afric | -0.775 |
Ange | -0.760 |
IOR | -0.752 |
trump | -0.724 |
Token | a |
Token ID | 257 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
edom | +0.382 |
Afric | +0.357 |
Ange | +0.353 |
IOR | +0.345 |
trump | +0.341 |
Neg logit contributions | |
interstitial | -0.376 |
farious | -0.367 |
benefit | -0.353 |
propri | -0.334 |
oult | -0.331 |
Token | penal |
Token ID | 23634 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
edom | +0.111 |
Afric | +0.104 |
Ange | +0.102 |
IOR | +0.101 |
trump | +0.100 |
Neg logit contributions | |
interstitial | -0.106 |
farious | -0.103 |
benefit | -0.099 |
propri | -0.093 |
oult | -0.092 |
Token | isation |
Token ID | 5612 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
edom | +1.190 |
Afric | +1.119 |
Ange | +1.099 |
IOR | +1.097 |
trump | +1.084 |
Neg logit contributions | |
interstitial | -0.904 |
farious | -0.865 |
benefit | -0.830 |
propri | -0.777 |
oult | -0.764 |
Token | of |
Token ID | 286 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
edom | +0.181 |
Afric | +0.168 |
Ange | +0.163 |
IOR | +0.162 |
trump | +0.157 |
Neg logit contributions | |
interstitial | -0.230 |
farious | -0.224 |
benefit | -0.218 |
propri | -0.209 |
oult | -0.204 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
edom | +0.268 |
Afric | +0.248 |
Ange | +0.244 |
IOR | +0.240 |
trump | +0.234 |
Neg logit contributions | |
interstitial | -0.321 |
farious | -0.313 |
benefit | -0.305 |
propri | -0.291 |
oult | -0.286 |
Token | secession |
Token ID | 43314 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
edom | +0.481 |
Afric | +0.446 |
Ange | +0.441 |
IOR | +0.432 |
trump | +0.424 |
Neg logit contributions | |
interstitial | -0.547 |
farious | -0.532 |
benefit | -0.518 |
propri | -0.491 |
oult | -0.482 |
Token | ist |
Token ID | 396 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
interstitial | +1.801 |
farious | +1.741 |
benefit | +1.691 |
propri | +1.566 |
oult | +1.498 |
Neg logit contributions | |
edom | -3.416 |
Afric | -3.260 |
IOR | -3.195 |
Ange | -3.192 |
trump | -3.087 |
Token | bloc |
Token ID | 24003 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
interstitial | +0.685 |
farious | +0.666 |
benefit | +0.648 |
propri | +0.613 |
oult | +0.595 |
Neg logit contributions | |
edom | -0.775 |
Afric | -0.727 |
Ange | -0.715 |
IOR | -0.708 |
trump | -0.690 |
Token | Thailand |
Token ID | 16952 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
edom | +0.887 |
Afric | +0.833 |
Ange | +0.820 |
IOR | +0.803 |
trump | +0.781 |
Neg logit contributions | |
interstitial | -1.034 |
farious | -1.008 |
benefit | -0.982 |
propri | -0.932 |
oult | -0.914 |
Token | and |
Token ID | 290 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
edom | +2.365 |
Afric | +2.191 |
Ange | +2.155 |
IOR | +2.135 |
trump | +2.077 |
Neg logit contributions | |
interstitial | -3.010 |
farious | -2.919 |
benefit | -2.839 |
propri | -2.714 |
oult | -2.658 |
Token | Vietnam |
Token ID | 10836 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
edom | +0.748 |
Afric | +0.707 |
Ange | +0.689 |
IOR | +0.675 |
trump | +0.657 |
Neg logit contributions | |
interstitial | -0.945 |
farious | -0.922 |
benefit | -0.898 |
propri | -0.857 |
oult | -0.836 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
edom | +1.030 |
Afric | +0.958 |
Ange | +0.939 |
IOR | +0.932 |
trump | +0.903 |
Neg logit contributions | |
interstitial | -1.179 |
farious | -1.148 |
benefit | -1.120 |
propri | -1.069 |
oult | -1.038 |
Token | Due |
Token ID | 14444 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
interstitial | +0.138 |
farious | +0.134 |
benefit | +0.131 |
propri | +0.126 |
oult | +0.122 |
Neg logit contributions | |
edom | -0.111 |
Afric | -0.104 |
Ange | -0.101 |
IOR | -0.101 |
trump | -0.097 |
Token | to |
Token ID | 284 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
interstitial | +0.542 |
farious | +0.529 |
benefit | +0.523 |
propri | +0.499 |
oult | +0.481 |
Neg logit contributions | |
edom | -0.569 |
Afric | -0.531 |
Ange | -0.520 |
IOR | -0.516 |
trump | -0.496 |
Token | the |
Token ID | 262 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
interstitial | +0.168 |
farious | +0.164 |
benefit | +0.161 |
propri | +0.154 |
oult | +0.149 |
Neg logit contributions | |
edom | -0.136 |
Afric | -0.125 |
Ange | -0.122 |
IOR | -0.122 |
trump | -0.117 |
Token | unstable |
Token ID | 21354 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
edom | +0.369 |
Afric | +0.350 |
Ange | +0.343 |
IOR | +0.338 |
trump | +0.331 |
Neg logit contributions | |
interstitial | -0.355 |
farious | -0.345 |
benefit | -0.335 |
propri | -0.316 |
oult | -0.309 |
Token | situation |
Token ID | 3074 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
edom | +0.771 |
Afric | +0.726 |
Ange | +0.713 |
IOR | +0.701 |
trump | +0.687 |
Neg logit contributions | |
interstitial | -0.789 |
farious | -0.769 |
benefit | -0.751 |
propri | -0.704 |
oult | -0.692 |
Token | in |
Token ID | 287 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
edom | +1.038 |
Afric | +0.974 |
Ange | +0.955 |
IOR | +0.940 |
trump | +0.918 |
Neg logit contributions | |
interstitial | -1.171 |
farious | -1.142 |
benefit | -1.116 |
propri | -1.058 |
oult | -1.034 |
Token | Baghdad |
Token ID | 19761 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
edom | +0.728 |
Afric | +0.678 |
Ange | +0.663 |
IOR | +0.657 |
trump | +0.635 |
Neg logit contributions | |
interstitial | -0.844 |
farious | -0.824 |
benefit | -0.806 |
propri | -0.768 |
oult | -0.748 |
Token | Garg |
Token ID | 39013 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
edom | +0.748 |
Afric | +0.710 |
Ange | +0.690 |
IOR | +0.674 |
trump | +0.654 |
Neg logit contributions | |
interstitial | -1.194 |
farious | -1.169 |
benefit | -1.138 |
propri | -1.085 |
oult | -1.071 |
Token | ant |
Token ID | 415 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
edom | +1.122 |
Afric | +1.027 |
Ange | +1.021 |
IOR | +1.003 |
trump | +0.977 |
Neg logit contributions | |
farious | -1.558 |
interstitial | -1.550 |
benefit | -1.481 |
propri | -1.418 |
oult | -1.361 |
Token | ua |
Token ID | 6413 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
edom | +0.168 |
Afric | +0.148 |
IOR | +0.142 |
Ange | +0.141 |
trump | +0.134 |
Neg logit contributions | |
interstitial | -0.465 |
farious | -0.458 |
benefit | -0.450 |
propri | -0.434 |
oult | -0.423 |
Token | is |
Token ID | 318 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
edom | +1.987 |
Afric | +1.870 |
Ange | +1.830 |
trump | +1.809 |
IOR | +1.807 |
Neg logit contributions | |
interstitial | -1.956 |
farious | -1.942 |
benefit | -1.837 |
propri | -1.732 |
oult | -1.682 |
Token | probably |
Token ID | 2192 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
edom | +1.074 |
Afric | +1.015 |
Ange | +0.987 |
IOR | +0.984 |
trump | +0.966 |
Neg logit contributions | |
interstitial | -1.204 |
farious | -1.182 |
benefit | -1.135 |
propri | -1.077 |
oult | -1.050 |
Token | one |
Token ID | 530 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
interstitial | +0.515 |
farious | +0.503 |
benefit | +0.490 |
propri | +0.467 |
oult | +0.454 |
Neg logit contributions | |
edom | -0.463 |
Afric | -0.432 |
Ange | -0.422 |
IOR | -0.420 |
trump | -0.405 |
Token | of |
Token ID | 286 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
edom | +2.191 |
Afric | +2.034 |
Ange | +1.974 |
IOR | +1.961 |
trump | +1.905 |
Neg logit contributions | |
interstitial | -3.092 |
farious | -3.029 |
benefit | -2.948 |
propri | -2.819 |
oult | -2.748 |
Token | the |
Token ID | 262 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
edom | +1.110 |
Afric | +1.034 |
Ange | +1.011 |
IOR | +1.008 |
trump | +0.975 |
Neg logit contributions | |
interstitial | -1.316 |
farious | -1.284 |
benefit | -1.248 |
propri | -1.189 |
oult | -1.161 |
Token | best |
Token ID | 1266 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
edom | +1.978 |
Afric | +1.897 |
Ange | +1.837 |
IOR | +1.829 |
trump | +1.817 |
Neg logit contributions | |
interstitial | -2.249 |
farious | -2.192 |
benefit | -2.101 |
propri | -1.969 |
oult | -1.967 |
Token | for |
Token ID | 329 |
Feature activation | -3.62e-04 |
Pos logit contributions | |
edom | +1.470 |
Afric | +1.392 |
IOR | +1.354 |
Ange | +1.347 |
trump | +1.327 |
Neg logit contributions | |
interstitial | -1.708 |
farious | -1.661 |
benefit | -1.620 |
propri | -1.508 |
oult | -1.497 |
Token | newer |
Token ID | 15064 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
edom | +0.001 |
Afric | +0.001 |
IOR | +0.001 |
Ange | +0.001 |
trump | +0.001 |
Neg logit contributions | |
interstitial | -0.001 |
farious | -0.001 |
benefit | -0.001 |
propri | -0.001 |
oult | -0.001 |
Token | Planned |
Token ID | 18451 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
edom | +0.189 |
Afric | +0.181 |
Ange | +0.178 |
IOR | +0.177 |
trump | +0.173 |
Neg logit contributions | |
interstitial | -0.087 |
farious | -0.083 |
benefit | -0.080 |
propri | -0.073 |
oult | -0.070 |
Token | Parenthood |
Token ID | 18461 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
edom | +0.741 |
Afric | +0.680 |
Ange | +0.673 |
IOR | +0.632 |
trump | +0.619 |
Neg logit contributions | |
interstitial | -1.910 |
farious | -1.886 |
benefit | -1.804 |
propri | -1.751 |
oult | -1.726 |
Token | , |
Token ID | 11 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
edom | +0.040 |
Afric | +0.037 |
Ange | +0.036 |
IOR | +0.036 |
trump | +0.035 |
Neg logit contributions | |
interstitial | -0.044 |
farious | -0.043 |
benefit | -0.042 |
propri | -0.040 |
oult | -0.039 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
edom | +0.463 |
Afric | +0.433 |
Ange | +0.422 |
IOR | +0.415 |
trump | +0.408 |
Neg logit contributions | |
interstitial | -0.597 |
farious | -0.581 |
benefit | -0.567 |
propri | -0.541 |
oult | -0.533 |
Token | should |
Token ID | 815 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
edom | +0.289 |
Afric | +0.271 |
Ange | +0.266 |
IOR | +0.264 |
trump | +0.258 |
Neg logit contributions | |
interstitial | -0.283 |
farious | -0.276 |
benefit | -0.268 |
propri | -0.254 |
oult | -0.247 |
Token | be |
Token ID | 307 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
edom | +1.082 |
Afric | +0.999 |
trump | +0.975 |
Ange | +0.973 |
IOR | +0.971 |
Neg logit contributions | |
interstitial | -1.283 |
farious | -1.226 |
benefit | -1.167 |
propri | -1.121 |
oult | -1.092 |
Token | defending |
Token ID | 11749 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
edom | +0.628 |
Afric | +0.585 |
Ange | +0.575 |
trump | +0.568 |
IOR | +0.564 |
Neg logit contributions | |
interstitial | -0.672 |
farious | -0.648 |
benefit | -0.628 |
propri | -0.594 |
oult | -0.587 |
Token | them |
Token ID | 606 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
edom | +0.711 |
Afric | +0.678 |
Ange | +0.667 |
IOR | +0.660 |
trump | +0.649 |
Neg logit contributions | |
interstitial | -0.427 |
farious | -0.411 |
benefit | -0.395 |
propri | -0.367 |
oult | -0.358 |
Token | on |
Token ID | 319 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
interstitial | +0.810 |
farious | +0.785 |
benefit | +0.764 |
propri | +0.728 |
oult | +0.711 |
Neg logit contributions | |
edom | -0.741 |
Afric | -0.689 |
Ange | -0.675 |
IOR | -0.671 |
trump | -0.652 |
Token | this |
Token ID | 428 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
interstitial | +0.777 |
farious | +0.759 |
benefit | +0.743 |
propri | +0.712 |
oult | +0.687 |
Neg logit contributions | |
edom | -0.703 |
Afric | -0.653 |
Ange | -0.639 |
IOR | -0.637 |
trump | -0.608 |
Token | point |
Token ID | 966 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
edom | +0.951 |
Afric | +0.901 |
Ange | +0.882 |
IOR | +0.874 |
trump | +0.869 |
Neg logit contributions | |
interstitial | -0.839 |
farious | -0.810 |
benefit | -0.779 |
propri | -0.729 |
oult | -0.719 |
Token | groups |
Token ID | 2628 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
edom | +2.850 |
Ange | +2.657 |
Afric | +2.605 |
IOR | +2.564 |
trump | +2.540 |
Neg logit contributions | |
interstitial | -3.458 |
farious | -3.357 |
benefit | -3.269 |
oult | -3.080 |
propri | -3.075 |
Token | filed |
Token ID | 5717 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
edom | +2.502 |
Afric | +2.352 |
Ange | +2.315 |
trump | +2.295 |
IOR | +2.250 |
Neg logit contributions | |
interstitial | -3.018 |
farious | -2.943 |
benefit | -2.803 |
propri | -2.705 |
oult | -2.636 |
Token | Federal |
Token ID | 5618 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
edom | +1.694 |
Afric | +1.582 |
Ange | +1.560 |
IOR | +1.548 |
trump | +1.521 |
Neg logit contributions | |
interstitial | -1.725 |
farious | -1.707 |
benefit | -1.644 |
propri | -1.558 |
oult | -1.548 |
Token | Election |
Token ID | 14219 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
edom | +0.674 |
Afric | +0.611 |
Ange | +0.596 |
IOR | +0.592 |
trump | +0.568 |
Neg logit contributions | |
interstitial | -1.130 |
farious | -1.104 |
benefit | -1.081 |
propri | -1.039 |
oult | -1.020 |
Token | Commission |
Token ID | 4513 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
interstitial | +1.538 |
farious | +1.500 |
benefit | +1.465 |
propri | +1.391 |
oult | +1.346 |
Neg logit contributions | |
edom | -1.638 |
Afric | -1.534 |
Ange | -1.502 |
IOR | -1.494 |
trump | -1.445 |
Token | complaints |
Token ID | 9687 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
edom | +4.273 |
Afric | +4.031 |
Ange | +3.988 |
trump | +3.896 |
IOR | +3.849 |
Neg logit contributions | |
interstitial | -4.803 |
farious | -4.679 |
benefit | -4.455 |
arij | -4.294 |
oult | -4.280 |
Token | against |
Token ID | 1028 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
edom | +2.913 |
Afric | +2.691 |
Ange | +2.685 |
trump | +2.642 |
IOR | +2.569 |
Neg logit contributions | |
interstitial | -3.940 |
farious | -3.882 |
benefit | -3.744 |
propri | -3.577 |
oult | -3.550 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
edom | +1.324 |
Afric | +1.221 |
Ange | +1.208 |
trump | +1.178 |
IOR | +1.177 |
Neg logit contributions | |
interstitial | -1.888 |
farious | -1.852 |
benefit | -1.806 |
oult | -1.707 |
propri | -1.706 |
Token | Trump |
Token ID | 1301 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
edom | +0.695 |
Afric | +0.646 |
Ange | +0.634 |
IOR | +0.622 |
trump | +0.619 |
Neg logit contributions | |
interstitial | -0.937 |
farious | -0.916 |
benefit | -0.896 |
propri | -0.839 |
oult | -0.837 |
Token | campaign |
Token ID | 1923 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
interstitial | +1.099 |
farious | +1.066 |
benefit | +1.038 |
propri | +0.979 |
oult | +0.944 |
Neg logit contributions | |
edom | -1.471 |
Afric | -1.387 |
Ange | -1.362 |
IOR | -1.356 |
trump | -1.315 |
Token | for |
Token ID | 329 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
edom | +0.249 |
Afric | +0.231 |
Ange | +0.226 |
IOR | +0.224 |
trump | +0.217 |
Neg logit contributions | |
interstitial | -0.301 |
farious | -0.294 |
benefit | -0.287 |
propri | -0.274 |
oult | -0.267 |
Token | s |
Token ID | 82 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
interstitial | +1.471 |
farious | +1.428 |
benefit | +1.396 |
propri | +1.322 |
oult | +1.278 |
Neg logit contributions | |
edom | -1.701 |
Afric | -1.600 |
Ange | -1.565 |
IOR | -1.560 |
trump | -1.509 |
Token | mound |
Token ID | 31446 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
interstitial | +1.445 |
farious | +1.407 |
benefit | +1.377 |
propri | +1.311 |
oult | +1.272 |
Neg logit contributions | |
edom | -1.451 |
Afric | -1.355 |
Ange | -1.326 |
IOR | -1.321 |
trump | -1.273 |
Token | on |
Token ID | 319 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
interstitial | +0.352 |
farious | +0.344 |
benefit | +0.336 |
propri | +0.319 |
oult | +0.311 |
Neg logit contributions | |
edom | -0.310 |
Afric | -0.288 |
Ange | -0.282 |
IOR | -0.280 |
trump | -0.271 |
Token | a |
Token ID | 257 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
interstitial | +0.738 |
farious | +0.720 |
benefit | +0.705 |
propri | +0.671 |
oult | +0.654 |
Neg logit contributions | |
edom | -0.648 |
Afric | -0.604 |
Ange | -0.591 |
IOR | -0.586 |
trump | -0.565 |
Token | small |
Token ID | 1402 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
interstitial | +1.268 |
farious | +1.236 |
benefit | +1.208 |
propri | +1.149 |
oult | +1.118 |
Neg logit contributions | |
edom | -1.174 |
Afric | -1.096 |
Ange | -1.072 |
IOR | -1.065 |
trump | -1.029 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
interstitial | +2.129 |
farious | +2.078 |
benefit | +2.039 |
propri | +1.952 |
oult | +1.884 |
Neg logit contributions | |
edom | -2.051 |
Afric | -1.906 |
IOR | -1.868 |
Ange | -1.867 |
trump | -1.787 |
Token | dirt |
Token ID | 13647 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
edom | +1.424 |
Afric | +1.347 |
Ange | +1.322 |
IOR | +1.291 |
trump | +1.282 |
Neg logit contributions | |
interstitial | -1.600 |
farious | -1.562 |
benefit | -1.512 |
propri | -1.417 |
oult | -1.404 |
Token | soft |
Token ID | 2705 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
interstitial | +1.971 |
farious | +1.922 |
benefit | +1.883 |
propri | +1.789 |
oult | +1.723 |
Neg logit contributions | |
edom | -2.208 |
Afric | -2.065 |
Ange | -2.023 |
IOR | -2.018 |
trump | -1.945 |
Token | ball |
Token ID | 1894 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
interstitial | +0.623 |
farious | +0.604 |
benefit | +0.589 |
propri | +0.557 |
oult | +0.537 |
Neg logit contributions | |
edom | -0.792 |
Afric | -0.746 |
Ange | -0.732 |
IOR | -0.728 |
trump | -0.706 |
Token | field |
Token ID | 2214 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
interstitial | +0.797 |
farious | +0.769 |
benefit | +0.745 |
propri | +0.695 |
oult | +0.666 |
Neg logit contributions | |
edom | -1.346 |
Afric | -1.276 |
Ange | -1.255 |
IOR | -1.250 |
trump | -1.217 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
edom | +0.906 |
Afric | +0.838 |
Ange | +0.823 |
IOR | +0.818 |
trump | +0.793 |
Neg logit contributions | |
interstitial | -1.072 |
farious | -1.048 |
benefit | -1.016 |
propri | -0.962 |
oult | -0.943 |
Token | fresh |
Token ID | 4713 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
edom | +1.746 |
Afric | +1.610 |
Ange | +1.598 |
IOR | +1.572 |
trump | +1.550 |
Neg logit contributions | |
interstitial | -1.897 |
farious | -1.865 |
benefit | -1.785 |
propri | -1.701 |
oult | -1.663 |
Token | off |
Token ID | 572 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
interstitial | +0.106 |
farious | +0.103 |
benefit | +0.101 |
propri | +0.095 |
oult | +0.092 |
Neg logit contributions | |
edom | -0.121 |
Afric | -0.114 |
Ange | -0.111 |
IOR | -0.110 |
trump | -0.107 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
interstitial | +1.403 |
farious | +1.363 |
benefit | +1.344 |
propri | +1.279 |
oult | +1.238 |
Neg logit contributions | |
edom | -1.309 |
Afric | -1.220 |
IOR | -1.192 |
Ange | -1.187 |
trump | -1.137 |
Token | travel |
Token ID | 3067 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
interstitial | +0.425 |
farious | +0.415 |
benefit | +0.405 |
propri | +0.387 |
oult | +0.376 |
Neg logit contributions | |
edom | -0.385 |
Afric | -0.359 |
Ange | -0.351 |
IOR | -0.349 |
trump | -0.337 |
Token | from |
Token ID | 422 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
interstitial | +1.505 |
farious | +1.466 |
benefit | +1.435 |
propri | +1.365 |
oult | +1.324 |
Neg logit contributions | |
edom | -1.496 |
Afric | -1.398 |
Ange | -1.368 |
IOR | -1.361 |
trump | -1.313 |
Token | Down |
Token ID | 5588 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
interstitial | +2.129 |
farious | +2.076 |
benefit | +2.042 |
propri | +1.951 |
oult | +1.889 |
Neg logit contributions | |
edom | -1.925 |
Afric | -1.774 |
IOR | -1.742 |
Ange | -1.731 |
trump | -1.665 |
Token | Under |
Token ID | 4698 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
edom | +2.058 |
Afric | +1.896 |
Ange | +1.853 |
IOR | +1.808 |
trump | +1.766 |
Neg logit contributions | |
interstitial | -2.076 |
farious | -2.042 |
benefit | -1.952 |
propri | -1.876 |
oult | -1.802 |
Token | ? |
Token ID | 30 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
interstitial | +1.774 |
farious | +1.722 |
benefit | +1.697 |
propri | +1.613 |
oult | +1.559 |
Neg logit contributions | |
edom | -1.866 |
Afric | -1.752 |
IOR | -1.709 |
Ange | -1.704 |
trump | -1.642 |
Token | Not |
Token ID | 1892 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
interstitial | +0.280 |
farious | +0.273 |
benefit | +0.267 |
propri | +0.256 |
oult | +0.249 |
Neg logit contributions | |
edom | -0.226 |
Afric | -0.210 |
Ange | -0.206 |
IOR | -0.203 |
trump | -0.196 |
Token | something |
Token ID | 1223 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
interstitial | +0.544 |
farious | +0.530 |
benefit | +0.519 |
propri | +0.494 |
oult | +0.479 |
Neg logit contributions | |
edom | -0.537 |
Afric | -0.501 |
Ange | -0.491 |
IOR | -0.488 |
trump | -0.471 |
Token | I |
Token ID | 314 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
edom | +2.219 |
Afric | +2.075 |
Ange | +2.045 |
IOR | +1.975 |
trump | +1.951 |
Neg logit contributions | |
interstitial | -2.872 |
farious | -2.805 |
benefit | -2.716 |
propri | -2.568 |
oult | -2.521 |
Token | a |
Token ID | 257 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
edom | +1.804 |
Afric | +1.733 |
Ange | +1.714 |
trump | +1.643 |
IOR | +1.628 |
Neg logit contributions | |
interstitial | -1.954 |
farious | -1.900 |
benefit | -1.848 |
propri | -1.706 |
oult | -1.692 |
Token | look |
Token ID | 804 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
interstitial | +2.388 |
farious | +2.329 |
benefit | +2.280 |
propri | +2.173 |
oult | +2.103 |
Neg logit contributions | |
edom | -2.521 |
Afric | -2.347 |
Ange | -2.305 |
IOR | -2.304 |
trump | -2.201 |
Token | at |
Token ID | 379 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
edom | +3.568 |
Afric | +3.217 |
Ange | +3.136 |
IOR | +3.121 |
trump | +3.036 |
Neg logit contributions | |
interstitial | -4.517 |
farious | -4.342 |
benefit | -4.274 |
propri | -4.073 |
oult | -4.031 |
Token | the |
Token ID | 262 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
edom | +1.319 |
Afric | +1.240 |
Ange | +1.214 |
IOR | +1.181 |
trump | +1.160 |
Neg logit contributions | |
interstitial | -1.518 |
farious | -1.495 |
benefit | -1.453 |
propri | -1.366 |
oult | -1.350 |
Token | then |
Token ID | 788 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
edom | +0.325 |
Afric | +0.305 |
Ange | +0.298 |
IOR | +0.294 |
trump | +0.287 |
Neg logit contributions | |
interstitial | -0.339 |
farious | -0.330 |
benefit | -0.322 |
propri | -0.304 |
oult | -0.298 |
Token | - |
Token ID | 12 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
edom | +2.666 |
Afric | +2.479 |
Ange | +2.442 |
IOR | +2.398 |
trump | +2.361 |
Neg logit contributions | |
interstitial | -3.187 |
farious | -3.128 |
benefit | -3.064 |
propri | -2.892 |
oult | -2.854 |
Token | top |
Token ID | 4852 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
edom | +4.505 |
IOR | +4.148 |
Afric | +4.146 |
Ange | +4.126 |
trump | +3.981 |
Neg logit contributions | |
farious | -4.126 |
interstitial | -4.074 |
propri | -3.847 |
benefit | -3.837 |
arij | -3.698 |
Token | " |
Token ID | 366 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
edom | +0.857 |
Afric | +0.803 |
Ange | +0.785 |
IOR | +0.781 |
trump | +0.763 |
Neg logit contributions | |
interstitial | -0.907 |
farious | -0.893 |
benefit | -0.869 |
propri | -0.822 |
oult | -0.810 |
Token | jin |
Token ID | 18594 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
edom | +2.445 |
Afric | +2.269 |
IOR | +2.247 |
Ange | +2.232 |
trump | +2.138 |
Neg logit contributions | |
interstitial | -2.376 |
farious | -2.372 |
benefit | -2.246 |
propri | -2.211 |
oult | -2.120 |
Token | x |
Token ID | 87 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
edom | +3.400 |
Afric | +3.133 |
IOR | +3.101 |
Ange | +3.083 |
trump | +3.061 |
Neg logit contributions | |
interstitial | -2.804 |
farious | -2.684 |
benefit | -2.654 |
propri | -2.457 |
oult | -2.368 |
Token | ed |
Token ID | 276 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
edom | +0.398 |
Afric | +0.371 |
Ange | +0.363 |
IOR | +0.361 |
trump | +0.352 |
Neg logit contributions | |
interstitial | -0.393 |
farious | -0.383 |
benefit | -0.373 |
propri | -0.353 |
oult | -0.343 |
Token | easy |
Token ID | 2562 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
interstitial | +1.380 |
farious | +1.345 |
benefit | +1.316 |
propri | +1.253 |
oult | +1.215 |
Neg logit contributions | |
edom | -1.329 |
Afric | -1.239 |
Ange | -1.212 |
IOR | -1.207 |
trump | -1.163 |
Token | bank |
Token ID | 3331 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
interstitial | +1.393 |
farious | +1.358 |
benefit | +1.329 |
propri | +1.270 |
oult | +1.245 |
Neg logit contributions | |
edom | -1.098 |
Afric | -1.018 |
Ange | -0.990 |
IOR | -0.986 |
trump | -0.949 |
Token | loans |
Token ID | 10021 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
interstitial | +2.237 |
farious | +2.198 |
benefit | +2.149 |
propri | +2.054 |
549 | +1.967 |
Neg logit contributions | |
edom | -2.263 |
Afric | -2.123 |
Ange | -2.079 |
IOR | -2.057 |
trump | -1.979 |
Token | and |
Token ID | 290 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
interstitial | +1.214 |
farious | +1.188 |
benefit | +1.168 |
propri | +1.114 |
oult | +1.078 |
Neg logit contributions | |
edom | -1.123 |
Afric | -1.049 |
Ange | -1.027 |
IOR | -1.016 |
trump | -0.962 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
interstitial | +1.173 |
farious | +1.142 |
benefit | +1.119 |
propri | +1.067 |
oult | +1.030 |
Neg logit contributions | |
edom | -1.158 |
Afric | -1.080 |
Ange | -1.058 |
IOR | -1.054 |
trump | -1.013 |
Token | cac |
Token ID | 40428 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
edom | +0.475 |
Afric | +0.445 |
Ange | +0.436 |
IOR | +0.430 |
trump | +0.421 |
Neg logit contributions | |
interstitial | -0.481 |
farious | -0.468 |
benefit | -0.456 |
propri | -0.431 |
oult | -0.424 |
Token | het |
Token ID | 3202 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
edom | +5.006 |
trump | +4.275 |
Afric | +4.256 |
Ange | +4.254 |
IOR | +4.113 |
Neg logit contributions | |
interstitial | -6.433 |
farious | -6.211 |
benefit | -5.998 |
propri | -5.764 |
arij | -5.684 |
Token | of |
Token ID | 286 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
interstitial | +1.131 |
farious | +1.102 |
benefit | +1.085 |
propri | +1.039 |
549 | +0.999 |
Neg logit contributions | |
edom | -0.933 |
Afric | -0.863 |
Ange | -0.840 |
IOR | -0.839 |
trump | -0.790 |
Token | having |
Token ID | 1719 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
interstitial | +0.560 |
farious | +0.547 |
benefit | +0.533 |
propri | +0.506 |
oult | +0.497 |
Neg logit contributions | |
edom | -0.528 |
Afric | -0.493 |
Ange | -0.483 |
IOR | -0.478 |
trump | -0.466 |
Token | planes |
Token ID | 13016 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
edom | +0.638 |
Afric | +0.596 |
Ange | +0.583 |
IOR | +0.576 |
trump | +0.565 |
Neg logit contributions | |
interstitial | -0.686 |
farious | -0.673 |
benefit | -0.652 |
propri | -0.617 |
oult | -0.606 |
Token | land |
Token ID | 1956 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
edom | +0.333 |
Afric | +0.311 |
Ange | +0.304 |
IOR | +0.301 |
trump | +0.295 |
Neg logit contributions | |
interstitial | -0.347 |
farious | -0.337 |
benefit | -0.328 |
propri | -0.311 |
oult | -0.306 |
Token | without |
Token ID | 1231 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
interstitial | +0.300 |
farious | +0.292 |
benefit | +0.285 |
propri | +0.272 |
oult | +0.264 |
Neg logit contributions | |
edom | -0.273 |
Afric | -0.254 |
Ange | -0.249 |
IOR | -0.247 |
trump | -0.239 |
Token | players |
Token ID | 1938 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
interstitial | +1.466 |
farious | +1.426 |
benefit | +1.394 |
propri | +1.325 |
oult | +1.279 |
Neg logit contributions | |
edom | -1.605 |
Afric | -1.503 |
Ange | -1.471 |
IOR | -1.466 |
trump | -1.416 |
Token | such |
Token ID | 884 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
edom | +0.585 |
Afric | +0.545 |
Ange | +0.538 |
IOR | +0.524 |
trump | +0.512 |
Neg logit contributions | |
interstitial | -0.714 |
farious | -0.699 |
benefit | -0.680 |
propri | -0.649 |
oult | -0.633 |
Token | as |
Token ID | 355 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
edom | +0.123 |
Afric | +0.116 |
Ange | +0.114 |
IOR | +0.113 |
trump | +0.110 |
Neg logit contributions | |
interstitial | -0.132 |
farious | -0.131 |
benefit | -0.124 |
propri | -0.117 |
oult | -0.115 |
Token | Sad |
Token ID | 14668 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
edom | +0.372 |
Afric | +0.347 |
Ange | +0.342 |
IOR | +0.336 |
trump | +0.326 |
Neg logit contributions | |
interstitial | -0.429 |
farious | -0.417 |
benefit | -0.408 |
propri | -0.388 |
oult | -0.380 |
Token | io |
Token ID | 952 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
interstitial | +0.240 |
farious | +0.235 |
benefit | +0.230 |
propri | +0.220 |
oult | +0.214 |
Neg logit contributions | |
edom | -0.192 |
Afric | -0.178 |
Ange | -0.173 |
IOR | -0.173 |
trump | -0.166 |
Token | Man |
Token ID | 1869 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
edom | +3.555 |
Ange | +3.417 |
IOR | +2.905 |
Afric | +2.890 |
trump | +2.836 |
Neg logit contributions | |
interstitial | -9.461 |
farious | -9.109 |
benefit | -9.020 |
arij | -8.722 |
549 | -8.597 |
Token | é |
Token ID | 2634 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
interstitial | +1.078 |
farious | +1.040 |
benefit | +1.009 |
propri | +0.941 |
oult | +0.902 |
Neg logit contributions | |
edom | -1.821 |
Afric | -1.725 |
Ange | -1.697 |
IOR | -1.690 |
trump | -1.645 |
Token | , |
Token ID | 11 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
edom | +4.003 |
Afric | +3.670 |
Ange | +3.592 |
IOR | +3.510 |
trump | +3.469 |
Neg logit contributions | |
interstitial | -5.443 |
farious | -5.319 |
benefit | -5.154 |
propri | -4.918 |
549 | -4.879 |
Token | Adam |
Token ID | 7244 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
interstitial | +0.292 |
farious | +0.284 |
benefit | +0.278 |
propri | +0.264 |
oult | +0.259 |
Neg logit contributions | |
edom | -0.255 |
Afric | -0.238 |
Ange | -0.234 |
IOR | -0.231 |
trump | -0.223 |
Token | L |
Token ID | 406 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
edom | +0.536 |
Afric | +0.507 |
Ange | +0.501 |
IOR | +0.483 |
trump | +0.471 |
Neg logit contributions | |
interstitial | -0.698 |
farious | -0.669 |
benefit | -0.659 |
propri | -0.633 |
oult | -0.617 |
Token | NF |
Token ID | 21870 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
edom | +1.665 |
Afric | +1.550 |
IOR | +1.544 |
Ange | +1.521 |
trump | +1.448 |
Neg logit contributions | |
interstitial | -1.928 |
farious | -1.891 |
benefit | -1.820 |
propri | -1.743 |
oult | -1.700 |
Token | - |
Token ID | 12 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
edom | +2.118 |
Afric | +1.965 |
IOR | +1.937 |
Ange | +1.923 |
trump | +1.853 |
Neg logit contributions | |
interstitial | -2.571 |
farious | -2.495 |
benefit | -2.452 |
propri | -2.325 |
oult | -2.272 |
Token | 207 |
Token ID | 22745 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
interstitial | +0.844 |
farious | +0.812 |
benefit | +0.790 |
propri | +0.733 |
oult | +0.702 |
Neg logit contributions | |
edom | -1.473 |
Afric | -1.399 |
Ange | -1.377 |
IOR | -1.361 |
trump | -1.332 |
Token | , |
Token ID | 11 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
edom | +1.014 |
Afric | +0.949 |
Ange | +0.929 |
IOR | +0.925 |
trump | +0.892 |
Neg logit contributions | |
interstitial | -1.106 |
farious | -1.079 |
benefit | -1.051 |
propri | -0.993 |
oult | -0.971 |
Token | Mir |
Token ID | 7381 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
edom | +1.354 |
Afric | +1.277 |
Ange | +1.242 |
IOR | +1.236 |
trump | +1.191 |
Neg logit contributions | |
interstitial | -1.780 |
farious | -1.738 |
benefit | -1.690 |
propri | -1.594 |
oult | -1.571 |
Token | amar |
Token ID | 39236 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
interstitial | +2.840 |
farious | +2.784 |
benefit | +2.727 |
propri | +2.628 |
oult | +2.553 |
Neg logit contributions | |
edom | -2.248 |
Afric | -2.086 |
Ange | -2.043 |
IOR | -2.007 |
trump | -1.927 |
Token | tower |
Token ID | 10580 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
edom | +4.662 |
Afric | +4.515 |
Ange | +4.327 |
IOR | +4.309 |
trump | +4.240 |
Neg logit contributions | |
interstitial | -6.204 |
farious | -6.055 |
benefit | -5.872 |
oult | -5.414 |
propri | -5.408 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
edom | +0.886 |
Afric | +0.828 |
Ange | +0.810 |
IOR | +0.807 |
trump | +0.781 |
Neg logit contributions | |
interstitial | -0.956 |
farious | -0.934 |
benefit | -0.908 |
propri | -0.852 |
oult | -0.838 |
Token | Your |
Token ID | 3406 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
edom | +0.685 |
Afric | +0.644 |
Ange | +0.626 |
IOR | +0.622 |
trump | +0.591 |
Neg logit contributions | |
interstitial | -0.950 |
farious | -0.926 |
benefit | -0.904 |
propri | -0.859 |
oult | -0.845 |
Token | wings |
Token ID | 12098 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
interstitial | +1.851 |
farious | +1.805 |
benefit | +1.774 |
propri | +1.719 |
oult | +1.642 |
Neg logit contributions | |
edom | -1.658 |
Afric | -1.527 |
Ange | -1.492 |
IOR | -1.484 |
trump | -1.420 |
Token | are |
Token ID | 389 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
interstitial | +0.697 |
farious | +0.679 |
benefit | +0.664 |
propri | +0.632 |
oult | +0.613 |
Neg logit contributions | |
edom | -0.691 |
Afric | -0.646 |
Ange | -0.632 |
IOR | -0.629 |
trump | -0.607 |
Token | ighter |
Token ID | 4799 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
edom | +2.199 |
Afric | +1.897 |
IOR | +1.867 |
Ange | +1.865 |
trump | +1.829 |
Neg logit contributions | |
interstitial | -2.395 |
benefit | -2.280 |
farious | -2.271 |
propri | -2.217 |
oult | -2.109 |
Token | , |
Token ID | 11 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
edom | +2.279 |
Afric | +2.132 |
Ange | +2.068 |
IOR | +2.047 |
trump | +2.007 |
Neg logit contributions | |
interstitial | -2.680 |
farious | -2.616 |
benefit | -2.566 |
propri | -2.403 |
oult | -2.370 |
Token | has |
Token ID | 468 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
edom | +1.330 |
Afric | +1.248 |
Ange | +1.217 |
IOR | +1.205 |
trump | +1.179 |
Neg logit contributions | |
interstitial | -1.321 |
farious | -1.288 |
benefit | -1.249 |
propri | -1.180 |
oult | -1.149 |
Token | increased |
Token ID | 3220 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
edom | +1.125 |
Afric | +1.047 |
Ange | +1.022 |
IOR | +1.015 |
trump | +0.986 |
Neg logit contributions | |
interstitial | -1.264 |
farious | -1.237 |
benefit | -1.204 |
propri | -1.142 |
oult | -1.114 |
Token | Arctic |
Token ID | 15723 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
edom | +2.357 |
Afric | +2.199 |
IOR | +2.134 |
Ange | +2.131 |
trump | +2.073 |
Neg logit contributions | |
interstitial | -2.862 |
farious | -2.809 |
benefit | -2.705 |
propri | -2.541 |
oult | -2.499 |
Token | navigation |
Token ID | 16408 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
edom | +1.208 |
Afric | +1.123 |
Ange | +1.098 |
IOR | +1.090 |
trump | +1.058 |
Neg logit contributions | |
interstitial | -1.403 |
farious | -1.363 |
benefit | -1.328 |
propri | -1.257 |
oult | -1.232 |
Token | from |
Token ID | 422 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
edom | +3.972 |
Afric | +3.709 |
trump | +3.619 |
Ange | +3.617 |
IOR | +3.595 |
Neg logit contributions | |
interstitial | -4.978 |
farious | -4.857 |
benefit | -4.592 |
oult | -4.299 |
arij | -4.241 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
edom | +0.356 |
Afric | +0.331 |
Ange | +0.323 |
IOR | +0.320 |
trump | +0.310 |
Neg logit contributions | |
interstitial | -0.432 |
farious | -0.424 |
benefit | -0.413 |
propri | -0.392 |
oult | -0.384 |
Token | to |
Token ID | 284 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
edom | +0.081 |
Afric | +0.076 |
Ange | +0.074 |
IOR | +0.074 |
trump | +0.072 |
Neg logit contributions | |
interstitial | -0.083 |
farious | -0.081 |
benefit | -0.079 |
propri | -0.075 |
oult | -0.073 |
Token | 10 |
Token ID | 838 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
edom | +1.586 |
Afric | +1.493 |
Ange | +1.458 |
IOR | +1.432 |
trump | +1.408 |
Neg logit contributions | |
interstitial | -2.366 |
farious | -2.334 |
benefit | -2.251 |
propri | -2.126 |
oult | -2.103 |
Token | months |
Token ID | 1933 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
edom | +2.756 |
Afric | +2.608 |
Ange | +2.546 |
IOR | +2.528 |
trump | +2.485 |
Neg logit contributions | |
interstitial | -2.493 |
farious | -2.411 |
benefit | -2.346 |
propri | -2.174 |
oult | -2.143 |