Token | - |
Token ID | 12 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
izoph | +2.652 |
iris | +2.608 |
stadt | +2.496 |
Afric | +2.466 |
Reaper | +2.365 |
Neg logit contributions | |
asi | -3.052 |
wen | -3.012 |
selage | -2.962 |
terness | -2.889 |
ascus | -2.829 |
Token | Ray |
Token ID | 19591 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
asi | +0.021 |
wen | +0.020 |
selage | +0.019 |
terness | +0.019 |
ascus | +0.019 |
Neg logit contributions | |
izoph | -0.023 |
iris | -0.022 |
stadt | -0.022 |
Afric | -0.021 |
Lite | -0.020 |
Token | Spect |
Token ID | 13058 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
asi | +1.285 |
wen | +1.270 |
selage | +1.206 |
terness | +1.203 |
abad | +1.173 |
Neg logit contributions | |
izoph | -0.961 |
iris | -0.915 |
stadt | -0.894 |
Afric | -0.863 |
flakes | -0.802 |
Token | rom |
Token ID | 398 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
asi | +0.745 |
wen | +0.727 |
selage | +0.660 |
terness | +0.656 |
abad | +0.628 |
Neg logit contributions | |
izoph | -1.496 |
iris | -1.440 |
stadt | -1.429 |
Afric | -1.402 |
flakes | -1.340 |
Token | eter |
Token ID | 2357 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
asi | +0.825 |
wen | +0.818 |
selage | +0.775 |
terness | +0.771 |
abad | +0.749 |
Neg logit contributions | |
izoph | -0.776 |
iris | -0.747 |
stadt | -0.730 |
Afric | -0.707 |
Lite | -0.666 |
Token | ( |
Token ID | 357 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
asi | +1.613 |
wen | +1.579 |
selage | +1.478 |
terness | +1.474 |
abad | +1.435 |
Neg logit contributions | |
izoph | -1.819 |
iris | -1.733 |
stadt | -1.699 |
Afric | -1.650 |
flakes | -1.550 |
Token | AP |
Token ID | 2969 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
asi | +11.281 |
abad | +10.563 |
asm | +10.438 |
wen | +10.299 |
ult | +9.929 |
Neg logit contributions | |
izoph | -8.771 |
stadt | -7.522 |
Afric | -7.252 |
iris | -7.139 |
flakes | -6.897 |
Token | X |
Token ID | 55 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
asi | +2.657 |
wen | +2.460 |
selage | +2.125 |
terness | +2.101 |
ascus | +1.999 |
Neg logit contributions | |
izoph | -8.849 |
stadt | -8.323 |
Afric | -8.200 |
iris | -8.147 |
flakes | -7.894 |
Token | S |
Token ID | 50 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
izoph | +0.961 |
iris | +0.942 |
stadt | +0.915 |
Afric | +0.890 |
Lite | +0.854 |
Neg logit contributions | |
wen | -0.819 |
asi | -0.816 |
selage | -0.772 |
terness | -0.762 |
abad | -0.737 |
Token | ) |
Token ID | 8 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
izoph | +0.243 |
iris | +0.234 |
stadt | +0.230 |
Afric | +0.223 |
Lite | +0.211 |
Neg logit contributions | |
asi | -0.225 |
wen | -0.222 |
selage | -0.209 |
terness | -0.208 |
abad | -0.202 |
Token | instrument |
Token ID | 8875 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
asi | +2.344 |
wen | +2.290 |
selage | +2.160 |
terness | +2.160 |
ascus | +2.107 |
Neg logit contributions | |
izoph | -2.154 |
iris | -2.030 |
stadt | -1.999 |
Afric | -1.921 |
flakes | -1.784 |
Token | : |
Token ID | 25 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
asi | +2.518 |
wen | +2.457 |
terness | +2.306 |
selage | +2.299 |
abad | +2.208 |
Neg logit contributions | |
izoph | -2.971 |
iris | -2.849 |
stadt | -2.779 |
Afric | -2.693 |
flakes | -2.556 |
Token | Relic |
Token ID | 43437 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
asi | +1.140 |
wen | +1.130 |
selage | +1.060 |
terness | +1.059 |
asm | +1.033 |
Neg logit contributions | |
izoph | -1.011 |
iris | -0.960 |
stadt | -0.944 |
Afric | -0.898 |
flakes | -0.851 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
izoph | +0.063 |
iris | +0.061 |
stadt | +0.060 |
Afric | +0.058 |
Lite | +0.055 |
Neg logit contributions | |
asi | -0.063 |
wen | -0.062 |
selage | -0.059 |
terness | -0.059 |
abad | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
izoph | +1.168 |
iris | +1.125 |
stadt | +1.105 |
Afric | +1.071 |
Lite | +1.008 |
Neg logit contributions | |
asi | -1.341 |
wen | -1.328 |
selage | -1.263 |
terness | -1.252 |
abad | -1.222 |
Token |
|
Token ID | 198 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
asi | +1.946 |
wen | +1.932 |
selage | +1.793 |
asm | +1.762 |
abad | +1.757 |
Neg logit contributions | |
izoph | -2.024 |
iris | -1.908 |
stadt | -1.858 |
Afric | -1.833 |
flakes | -1.715 |
Token | Gen |
Token ID | 13746 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
asi | +3.425 |
wen | +3.373 |
selage | +3.115 |
asm | +3.074 |
terness | +3.048 |
Neg logit contributions | |
izoph | -3.099 |
iris | -2.902 |
stadt | -2.866 |
Afric | -2.846 |
flakes | -2.691 |
Token | re |
Token ID | 260 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
asi | +3.974 |
wen | +3.326 |
selage | +3.142 |
terness | +2.894 |
quet | +2.756 |
Neg logit contributions | |
izoph | -15.538 |
iris | -14.807 |
Afric | -14.707 |
stadt | -14.559 |
flakes | -14.230 |
Token | : |
Token ID | 25 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
asi | +2.784 |
wen | +2.743 |
terness | +2.566 |
selage | +2.548 |
asm | +2.445 |
Neg logit contributions | |
izoph | -3.239 |
iris | -3.133 |
stadt | -3.072 |
Afric | -2.958 |
flakes | -2.829 |
Token | Strategy |
Token ID | 20561 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
asi | +2.813 |
wen | +2.749 |
selage | +2.571 |
terness | +2.555 |
asm | +2.532 |
Neg logit contributions | |
izoph | -2.658 |
iris | -2.547 |
stadt | -2.490 |
Afric | -2.352 |
flakes | -2.275 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
izoph | +1.011 |
iris | +0.967 |
stadt | +0.949 |
Afric | +0.927 |
Lite | +0.878 |
Neg logit contributions | |
asi | -1.097 |
wen | -1.090 |
selage | -1.032 |
terness | -1.029 |
abad | -1.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
asi | +0.095 |
wen | +0.094 |
selage | +0.089 |
terness | +0.089 |
abad | +0.086 |
Neg logit contributions | |
izoph | -0.083 |
iris | -0.080 |
stadt | -0.078 |
Afric | -0.076 |
Lite | -0.071 |
Token | Z |
Token ID | 57 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
asi | +5.391 |
wen | +5.338 |
asm | +4.810 |
selage | +4.770 |
abad | +4.761 |
Neg logit contributions | |
izoph | -6.089 |
stadt | -5.612 |
Afric | -5.607 |
iris | -5.606 |
flakes | -5.321 |
Token | k |
Token ID | 74 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
asi | +5.172 |
wen | +5.149 |
asm | +4.609 |
selage | +4.583 |
abad | +4.566 |
Neg logit contributions | |
izoph | -6.005 |
Afric | -5.538 |
iris | -5.521 |
stadt | -5.520 |
flakes | -5.257 |
Token | A |
Token ID | 32 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
asi | +7.487 |
wen | +7.408 |
asm | +6.673 |
abad | +6.545 |
selage | +6.509 |
Neg logit contributions | |
izoph | -8.366 |
Afric | -7.687 |
stadt | -7.626 |
iris | -7.512 |
flakes | -7.348 |
Token | lf |
Token ID | 1652 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
asi | +3.712 |
wen | +3.668 |
selage | +3.297 |
asm | +3.249 |
abad | +3.247 |
Neg logit contributions | |
izoph | -4.580 |
iris | -4.270 |
Afric | -4.219 |
stadt | -4.207 |
flakes | -4.013 |
Token | ax |
Token ID | 897 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
asi | +6.749 |
wen | +6.698 |
asm | +6.054 |
abad | +5.927 |
selage | +5.891 |
Neg logit contributions | |
izoph | -7.720 |
Afric | -7.093 |
stadt | -7.018 |
iris | -6.977 |
flakes | -6.783 |
Token | Ob |
Token ID | 5944 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
asi | +6.666 |
wen | +6.620 |
asm | +5.936 |
abad | +5.869 |
selage | +5.794 |
Neg logit contributions | |
izoph | -7.734 |
iris | -7.028 |
Afric | -6.995 |
stadt | -6.991 |
flakes | -6.718 |
Token | pg |
Token ID | 6024 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
asi | +9.228 |
wen | +9.136 |
asm | +8.284 |
abad | +8.045 |
selage | +7.982 |
Neg logit contributions | |
izoph | -9.991 |
stadt | -9.000 |
Afric | -8.990 |
iris | -8.891 |
flakes | -8.758 |
Token | after |
Token ID | 706 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
asi | +2.955 |
wen | +2.920 |
selage | +2.675 |
terness | +2.637 |
abad | +2.637 |
Neg logit contributions | |
izoph | -3.553 |
iris | -3.336 |
stadt | -3.311 |
Afric | -3.220 |
flakes | -3.073 |
Token | my |
Token ID | 616 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
izoph | +1.438 |
iris | +1.387 |
stadt | +1.352 |
Afric | +1.314 |
Lite | +1.239 |
Neg logit contributions | |
asi | -1.638 |
wen | -1.618 |
selage | -1.542 |
terness | -1.535 |
abad | -1.488 |
Token | finals |
Token ID | 18576 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
izoph | +2.227 |
iris | +2.135 |
stadt | +2.081 |
Afric | +2.027 |
flakes | +1.928 |
Neg logit contributions | |
asi | -2.447 |
wen | -2.419 |
selage | -2.309 |
terness | -2.298 |
abad | -2.220 |
Token | and |
Token ID | 290 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
izoph | +0.454 |
iris | +0.437 |
stadt | +0.428 |
Afric | +0.416 |
Lite | +0.391 |
Neg logit contributions | |
asi | -0.452 |
wen | -0.447 |
selage | -0.422 |
terness | -0.419 |
abad | -0.408 |
Token | pack |
Token ID | 8002 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
asi | +2.062 |
wen | +2.022 |
selage | +1.862 |
terness | +1.822 |
asm | +1.807 |
Neg logit contributions | |
izoph | -3.071 |
iris | -2.951 |
stadt | -2.888 |
Afric | -2.836 |
flakes | -2.697 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
izoph | +2.559 |
iris | +2.510 |
stadt | +2.447 |
Afric | +2.371 |
Lite | +2.283 |
Neg logit contributions | |
asi | -3.093 |
wen | -3.072 |
terness | -2.940 |
selage | -2.918 |
ascus | -2.845 |
Token | Data |
Token ID | 6060 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
izoph | +2.404 |
iris | +2.357 |
stadt | +2.269 |
Afric | +2.214 |
Lite | +2.131 |
Neg logit contributions | |
asi | -3.172 |
wen | -3.127 |
terness | -3.012 |
selage | -2.995 |
ascus | -2.896 |
Token | into |
Token ID | 656 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
izoph | +1.398 |
iris | +1.346 |
stadt | +1.304 |
Afric | +1.253 |
Lite | +1.177 |
Neg logit contributions | |
asi | -2.442 |
wen | -2.430 |
terness | -2.348 |
selage | -2.315 |
ascus | -2.269 |
Token | your |
Token ID | 534 |
Feature activation | +8.53e+00 |
Pos logit contributions | |
asi | +1.366 |
wen | +1.348 |
selage | +1.270 |
terness | +1.260 |
asm | +1.231 |
Neg logit contributions | |
izoph | -1.301 |
iris | -1.241 |
stadt | -1.213 |
Afric | -1.176 |
flakes | -1.101 |
Token | Skyrim |
Token ID | 21789 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
asi | +6.252 |
wen | +6.075 |
asm | +5.728 |
selage | +5.632 |
terness | +5.592 |
Neg logit contributions | |
izoph | -5.792 |
stadt | -5.337 |
iris | -5.323 |
Afric | -4.991 |
anooga | -4.665 |
Token | folder |
Token ID | 9483 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
asi | +8.785 |
wen | +8.503 |
asm | +8.079 |
selage | +7.857 |
abad | +7.700 |
Neg logit contributions | |
izoph | -9.926 |
stadt | -9.316 |
iris | -9.039 |
Afric | -8.531 |
anooga | -8.093 |
Token | or |
Token ID | 393 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
asi | +1.244 |
wen | +1.231 |
selage | +1.153 |
terness | +1.147 |
abad | +1.115 |
Neg logit contributions | |
izoph | -1.369 |
iris | -1.311 |
stadt | -1.285 |
Afric | -1.254 |
flakes | -1.180 |
Token | install |
Token ID | 2721 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
asi | +3.103 |
wen | +3.064 |
selage | +2.864 |
asm | +2.825 |
terness | +2.795 |
Neg logit contributions | |
izoph | -3.008 |
iris | -2.830 |
stadt | -2.794 |
Afric | -2.693 |
flakes | -2.504 |
Token | with |
Token ID | 351 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
izoph | +0.057 |
iris | +0.055 |
stadt | +0.054 |
Afric | +0.052 |
Lite | +0.049 |
Neg logit contributions | |
asi | -0.061 |
wen | -0.060 |
selage | -0.057 |
terness | -0.057 |
abad | -0.055 |
Token | N |
Token ID | 399 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
asi | +2.402 |
wen | +2.391 |
selage | +2.206 |
asm | +2.200 |
terness | +2.179 |
Neg logit contributions | |
izoph | -2.351 |
iris | -2.211 |
stadt | -2.162 |
Afric | -2.108 |
flakes | -1.952 |
Token | Bel |
Token ID | 3944 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
asi | +1.364 |
wen | +1.350 |
selage | +1.265 |
terness | +1.255 |
abad | +1.228 |
Neg logit contributions | |
izoph | -1.375 |
iris | -1.307 |
stadt | -1.279 |
Afric | -1.235 |
flakes | -1.169 |
Token | ton |
Token ID | 1122 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
izoph | +1.715 |
iris | +1.681 |
stadt | +1.654 |
Afric | +1.578 |
Lite | +1.499 |
Neg logit contributions | |
asi | -1.431 |
wen | -1.420 |
selage | -1.350 |
terness | -1.342 |
ascus | -1.294 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
asi | +0.405 |
wen | +0.401 |
selage | +0.377 |
terness | +0.375 |
abad | +0.365 |
Neg logit contributions | |
izoph | -0.420 |
iris | -0.402 |
stadt | -0.393 |
Afric | -0.382 |
flakes | -0.360 |
Token | a |
Token ID | 257 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
asi | +0.770 |
wen | +0.762 |
selage | +0.721 |
terness | +0.718 |
abad | +0.699 |
Neg logit contributions | |
izoph | -0.698 |
iris | -0.669 |
stadt | -0.655 |
Afric | -0.635 |
flakes | -0.596 |
Token | World |
Token ID | 2159 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
asi | +0.466 |
wen | +0.461 |
selage | +0.436 |
terness | +0.434 |
abad | +0.423 |
Neg logit contributions | |
izoph | -0.420 |
iris | -0.402 |
stadt | -0.393 |
Afric | -0.381 |
flakes | -0.358 |
Token | War |
Token ID | 1810 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
asi | +2.989 |
wen | +2.968 |
terness | +2.764 |
selage | +2.759 |
abad | +2.747 |
Neg logit contributions | |
izoph | -2.227 |
iris | -2.130 |
stadt | -2.035 |
Afric | -1.948 |
flakes | -1.838 |
Token | II |
Token ID | 2873 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
asi | +5.659 |
wen | +5.595 |
selage | +4.846 |
abad | +4.805 |
terness | +4.802 |
Neg logit contributions | |
izoph | -12.800 |
iris | -11.986 |
stadt | -11.752 |
Afric | -11.432 |
iHUD | -10.821 |
Token | vet |
Token ID | 20202 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
asi | +3.634 |
wen | +3.533 |
selage | +3.357 |
abad | +3.278 |
terness | +3.267 |
Neg logit contributions | |
izoph | -4.069 |
iris | -3.931 |
stadt | -3.800 |
Afric | -3.585 |
flakes | -3.443 |
Token |
|
Token ID | 198 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
asi | +2.016 |
wen | +1.996 |
selage | +1.865 |
terness | +1.838 |
abad | +1.805 |
Neg logit contributions | |
izoph | -2.340 |
iris | -2.209 |
stadt | -2.176 |
Afric | -2.094 |
flakes | -1.987 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
asi | +0.360 |
wen | +0.356 |
selage | +0.338 |
terness | +0.338 |
ascus | +0.328 |
Neg logit contributions | |
izoph | -0.313 |
iris | -0.300 |
stadt | -0.294 |
Afric | -0.285 |
Lite | -0.267 |
Token | Del |
Token ID | 13856 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
asi | +1.432 |
wen | +1.413 |
selage | +1.299 |
terness | +1.282 |
abad | +1.269 |
Neg logit contributions | |
izoph | -1.665 |
iris | -1.575 |
stadt | -1.550 |
Afric | -1.526 |
flakes | -1.443 |
Token | ," |
Token ID | 553 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
izoph | +2.169 |
iris | +2.111 |
stadt | +2.066 |
Afric | +2.014 |
Lite | +1.934 |
Neg logit contributions | |
asi | -2.408 |
wen | -2.382 |
selage | -2.277 |
terness | -2.259 |
ascus | -2.189 |
Token | the |
Token ID | 262 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
izoph | +0.714 |
iris | +0.689 |
stadt | +0.674 |
Afric | +0.657 |
Lite | +0.618 |
Neg logit contributions | |
asi | -0.754 |
wen | -0.745 |
selage | -0.706 |
terness | -0.704 |
ascus | -0.683 |
Token | 1976 |
Token ID | 15408 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
izoph | +0.498 |
iris | +0.479 |
stadt | +0.470 |
Afric | +0.458 |
Lite | +0.431 |
Neg logit contributions | |
asi | -0.493 |
wen | -0.487 |
selage | -0.461 |
terness | -0.459 |
abad | -0.445 |
Token | Martin |
Token ID | 5780 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
izoph | +2.695 |
iris | +2.640 |
stadt | +2.606 |
Afric | +2.550 |
Lite | +2.420 |
Neg logit contributions | |
asi | -3.184 |
wen | -3.130 |
terness | -3.042 |
selage | -3.034 |
ascus | -2.912 |
Token | Sc |
Token ID | 1446 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
asi | +0.813 |
wen | +0.800 |
selage | +0.752 |
terness | +0.747 |
abad | +0.733 |
Neg logit contributions | |
izoph | -0.852 |
iris | -0.817 |
stadt | -0.798 |
Afric | -0.777 |
flakes | -0.732 |
Token | ors |
Token ID | 669 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
asi | +2.775 |
wen | +2.668 |
asm | +2.365 |
selage | +2.365 |
abad | +2.355 |
Neg logit contributions | |
izoph | -5.482 |
iris | -5.347 |
Afric | -5.261 |
stadt | -5.082 |
flakes | -4.969 |
Token | ese |
Token ID | 2771 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
asi | +3.943 |
wen | +3.568 |
hess | +2.868 |
abad | +2.867 |
imum | +2.847 |
Neg logit contributions | |
izoph | -13.985 |
Afric | -12.937 |
stadt | -12.696 |
iris | -12.365 |
Kuro | -12.304 |
Token | film |
Token ID | 2646 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
asi | +0.180 |
wen | +0.178 |
selage | +0.168 |
terness | +0.167 |
abad | +0.163 |
Neg logit contributions | |
izoph | -0.162 |
iris | -0.155 |
stadt | -0.152 |
Afric | -0.147 |
flakes | -0.138 |
Token | that |
Token ID | 326 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
asi | +0.610 |
wen | +0.603 |
selage | +0.570 |
terness | +0.567 |
abad | +0.552 |
Neg logit contributions | |
izoph | -0.587 |
iris | -0.564 |
stadt | -0.552 |
Afric | -0.536 |
flakes | -0.504 |
Token | 's |
Token ID | 338 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
asi | +0.766 |
wen | +0.757 |
selage | +0.715 |
terness | +0.707 |
abad | +0.690 |
Neg logit contributions | |
izoph | -0.789 |
iris | -0.756 |
stadt | -0.740 |
Afric | -0.718 |
Lite | -0.675 |
Token | celebrating |
Token ID | 17499 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
izoph | +1.002 |
iris | +0.970 |
stadt | +0.952 |
Afric | +0.930 |
Lite | +0.872 |
Neg logit contributions | |
asi | -1.092 |
wen | -1.082 |
terness | -1.028 |
selage | -1.027 |
abad | -0.991 |
Token | é |
Token ID | 2634 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
asi | +3.946 |
wen | +3.786 |
asm | +3.555 |
selage | +3.533 |
terness | +3.396 |
Neg logit contributions | |
izoph | -5.341 |
iris | -5.076 |
Afric | -5.060 |
stadt | -5.060 |
Lite | -4.787 |
Token | l |
Token ID | 75 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
asi | +2.526 |
wen | +2.508 |
selage | +2.368 |
terness | +2.358 |
ascus | +2.295 |
Neg logit contributions | |
izoph | -1.962 |
iris | -1.839 |
stadt | -1.816 |
Afric | -1.758 |
Lite | -1.632 |
Token | ange |
Token ID | 858 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
asi | +0.491 |
wen | +0.481 |
selage | +0.437 |
terness | +0.426 |
ascus | +0.414 |
Neg logit contributions | |
izoph | -1.002 |
iris | -0.958 |
stadt | -0.952 |
Afric | -0.939 |
Lite | -0.896 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
izoph | +0.568 |
iris | +0.548 |
stadt | +0.537 |
Afric | +0.522 |
flakes | +0.494 |
Neg logit contributions | |
asi | -0.544 |
wen | -0.539 |
selage | -0.509 |
terness | -0.506 |
abad | -0.492 |
Token | the |
Token ID | 262 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
izoph | +1.105 |
iris | +1.063 |
stadt | +1.045 |
Afric | +1.013 |
flakes | +0.958 |
Neg logit contributions | |
asi | -1.198 |
wen | -1.185 |
selage | -1.121 |
terness | -1.119 |
abad | -1.088 |
Token | j |
Token ID | 474 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
izoph | +0.493 |
iris | +0.473 |
stadt | +0.463 |
Afric | +0.449 |
flakes | +0.423 |
Neg logit contributions | |
asi | -0.551 |
wen | -0.545 |
selage | -0.516 |
terness | -0.515 |
abad | -0.500 |
Token | umble |
Token ID | 10344 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
asi | +5.656 |
wen | +5.342 |
asm | +4.951 |
abad | +4.795 |
quet | +4.755 |
Neg logit contributions | |
izoph | -11.227 |
Afric | -10.858 |
Lite | -10.479 |
stadt | -10.458 |
Hitman | -10.352 |
Token | of |
Token ID | 286 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
izoph | +2.227 |
iris | +2.164 |
stadt | +2.133 |
Afric | +2.070 |
flakes | +1.983 |
Neg logit contributions | |
asi | -2.250 |
wen | -2.236 |
selage | -2.133 |
terness | -2.102 |
abad | -2.052 |
Token | floating |
Token ID | 12462 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
izoph | +1.223 |
iris | +1.173 |
stadt | +1.144 |
Afric | +1.115 |
flakes | +1.061 |
Neg logit contributions | |
asi | -1.548 |
wen | -1.536 |
terness | -1.459 |
selage | -1.458 |
ascus | -1.412 |
Token | ice |
Token ID | 4771 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
asi | +0.146 |
wen | +0.144 |
selage | +0.137 |
terness | +0.136 |
abad | +0.133 |
Neg logit contributions | |
izoph | -0.112 |
iris | -0.107 |
stadt | -0.104 |
Afric | -0.101 |
Lite | -0.094 |
Token | downstream |
Token ID | 33218 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
asi | +0.249 |
wen | +0.247 |
selage | +0.233 |
terness | +0.232 |
abad | +0.226 |
Neg logit contributions | |
izoph | -0.231 |
iris | -0.221 |
stadt | -0.216 |
Afric | -0.210 |
Lite | -0.197 |
Token | -( |
Token ID | 30420 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
asi | +0.532 |
wen | +0.528 |
selage | +0.500 |
terness | +0.498 |
abad | +0.484 |
Neg logit contributions | |
izoph | -0.471 |
iris | -0.451 |
stadt | -0.442 |
Afric | -0.428 |
Lite | -0.402 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
asi | +4.360 |
wen | +4.265 |
selage | +3.866 |
terness | +3.853 |
abad | +3.848 |
Neg logit contributions | |
izoph | -6.016 |
iris | -5.740 |
stadt | -5.638 |
Afric | -5.632 |
flakes | -5.283 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
asi | +3.334 |
wen | +3.245 |
selage | +3.058 |
terness | +3.019 |
abad | +2.974 |
Neg logit contributions | |
izoph | -3.545 |
iris | -3.406 |
stadt | -3.335 |
Afric | -3.254 |
Lite | -3.035 |
Token | 6 |
Token ID | 21 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
asi | +2.307 |
wen | +2.275 |
selage | +2.105 |
terness | +2.069 |
abad | +2.037 |
Neg logit contributions | |
izoph | -2.997 |
iris | -2.872 |
stadt | -2.826 |
Afric | -2.778 |
flakes | -2.617 |
Token | - |
Token ID | 12 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
asi | +0.674 |
wen | +0.667 |
selage | +0.630 |
terness | +0.628 |
abad | +0.610 |
Neg logit contributions | |
izoph | -0.647 |
iris | -0.621 |
stadt | -0.609 |
Afric | -0.590 |
flakes | -0.556 |
Token | dim |
Token ID | 27740 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
asi | +2.447 |
wen | +2.415 |
selage | +2.233 |
terness | +2.215 |
abad | +2.181 |
Neg logit contributions | |
izoph | -3.118 |
iris | -2.970 |
stadt | -2.941 |
Afric | -2.901 |
flakes | -2.730 |
Token | eth |
Token ID | 2788 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
asi | +4.662 |
wen | +4.505 |
quet | +3.745 |
ascus | +3.735 |
asm | +3.717 |
Neg logit contributions | |
izoph | -12.244 |
Afric | -11.733 |
iris | -11.600 |
stadt | -11.250 |
flakes | -10.991 |
Token | oxy |
Token ID | 23536 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
asi | +0.376 |
wen | +0.371 |
terness | +0.351 |
selage | +0.349 |
ascus | +0.339 |
Neg logit contributions | |
izoph | -0.464 |
iris | -0.450 |
stadt | -0.440 |
Afric | -0.425 |
Lite | -0.407 |
Token | - |
Token ID | 12 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
asi | +1.138 |
wen | +1.125 |
selage | +1.060 |
terness | +1.054 |
abad | +1.024 |
Neg logit contributions | |
izoph | -1.196 |
iris | -1.149 |
stadt | -1.128 |
Afric | -1.096 |
flakes | -1.035 |
Token | 4 |
Token ID | 19 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
asi | +1.096 |
wen | +1.082 |
selage | +1.011 |
terness | +1.005 |
abad | +0.973 |
Neg logit contributions | |
izoph | -1.448 |
iris | -1.396 |
stadt | -1.372 |
Afric | -1.339 |
flakes | -1.271 |
Token | - |
Token ID | 12 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
asi | +3.986 |
wen | +3.856 |
selage | +3.624 |
terness | +3.582 |
quet | +3.559 |
Neg logit contributions | |
izoph | -4.383 |
iris | -4.180 |
stadt | -4.089 |
Afric | -3.976 |
Lite | -3.707 |
Token | local |
Token ID | 1957 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
asi | +1.059 |
wen | +1.043 |
selage | +0.985 |
terness | +0.974 |
abad | +0.953 |
Neg logit contributions | |
izoph | -1.085 |
iris | -1.038 |
stadt | -1.020 |
Afric | -0.989 |
flakes | -0.930 |
Token | book |
Token ID | 1492 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
asi | +0.883 |
wen | +0.871 |
selage | +0.819 |
terness | +0.816 |
abad | +0.795 |
Neg logit contributions | |
izoph | -0.921 |
iris | -0.884 |
stadt | -0.866 |
Afric | -0.840 |
flakes | -0.793 |
Token | seller |
Token ID | 32932 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
izoph | +2.072 |
iris | +2.024 |
stadt | +1.995 |
Afric | +1.902 |
Lite | +1.802 |
Neg logit contributions | |
asi | -2.522 |
wen | -2.500 |
selage | -2.405 |
terness | -2.384 |
ascus | -2.309 |
Token | or |
Token ID | 393 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
asi | +0.957 |
wen | +0.945 |
selage | +0.889 |
terness | +0.885 |
abad | +0.862 |
Neg logit contributions | |
izoph | -0.994 |
iris | -0.954 |
stadt | -0.934 |
Afric | -0.907 |
flakes | -0.855 |
Token | from |
Token ID | 422 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
izoph | +1.746 |
iris | +1.681 |
stadt | +1.644 |
Afric | +1.610 |
Lite | +1.510 |
Neg logit contributions | |
wen | -1.970 |
asi | -1.967 |
terness | -1.874 |
selage | -1.873 |
abad | -1.814 |
Token | am |
Token ID | 716 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
izoph | +0.430 |
iris | +0.414 |
stadt | +0.405 |
Afric | +0.394 |
Lite | +0.369 |
Neg logit contributions | |
asi | -0.489 |
wen | -0.486 |
selage | -0.462 |
terness | -0.460 |
abad | -0.446 |
Token | azon |
Token ID | 5168 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
asi | +5.117 |
wen | +4.863 |
asm | +4.184 |
abad | +4.149 |
selage | +4.053 |
Neg logit contributions | |
izoph | -11.366 |
Afric | -10.626 |
iris | -10.621 |
stadt | -10.522 |
flakes | -10.291 |
Token | . |
Token ID | 13 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
asi | +3.318 |
wen | +3.239 |
selage | +2.941 |
ascus | +2.920 |
terness | +2.915 |
Neg logit contributions | |
izoph | -4.046 |
iris | -3.845 |
stadt | -3.735 |
Afric | -3.698 |
Lite | -3.470 |
Token | com |
Token ID | 785 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
izoph | +0.165 |
iris | +0.159 |
stadt | +0.155 |
Afric | +0.151 |
Lite | +0.142 |
Neg logit contributions | |
asi | -0.158 |
wen | -0.156 |
selage | -0.147 |
terness | -0.147 |
abad | -0.142 |
Token | or |
Token ID | 393 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
asi | +1.113 |
wen | +1.102 |
selage | +1.031 |
terness | +1.027 |
abad | +1.001 |
Neg logit contributions | |
izoph | -1.173 |
iris | -1.124 |
stadt | -1.100 |
Afric | -1.067 |
flakes | -1.007 |
Token | in |
Token ID | 287 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
asi | +1.729 |
wen | +1.696 |
selage | +1.595 |
terness | +1.578 |
abad | +1.549 |
Neg logit contributions | |
izoph | -1.722 |
iris | -1.644 |
stadt | -1.612 |
Afric | -1.556 |
Lite | -1.469 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
izoph | +0.615 |
iris | +0.599 |
stadt | +0.590 |
Afric | +0.569 |
flakes | +0.540 |
Neg logit contributions | |
asi | -0.622 |
wen | -0.616 |
terness | -0.583 |
selage | -0.582 |
ascus | -0.562 |
Token | who |
Token ID | 508 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
izoph | +1.362 |
iris | +1.327 |
stadt | +1.297 |
Afric | +1.257 |
Lite | +1.191 |
Neg logit contributions | |
asi | -1.596 |
wen | -1.595 |
selage | -1.520 |
terness | -1.513 |
ascus | -1.461 |
Token | had |
Token ID | 550 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
izoph | +1.467 |
iris | +1.442 |
stadt | +1.419 |
Afric | +1.371 |
flakes | +1.313 |
Neg logit contributions | |
asi | -1.471 |
wen | -1.459 |
terness | -1.390 |
selage | -1.379 |
ascus | -1.333 |
Token | 139 |
Token ID | 23666 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
izoph | +0.560 |
iris | +0.542 |
stadt | +0.532 |
Afric | +0.516 |
Lite | +0.487 |
Neg logit contributions | |
asi | -0.577 |
wen | -0.571 |
selage | -0.541 |
terness | -0.538 |
abad | -0.522 |
Token | goals |
Token ID | 4661 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
izoph | +1.072 |
iris | +1.038 |
stadt | +1.016 |
Afric | +0.982 |
flakes | +0.927 |
Neg logit contributions | |
asi | -1.340 |
wen | -1.329 |
selage | -1.273 |
terness | -1.268 |
ascus | -1.220 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
asi | +1.607 |
wen | +1.582 |
selage | +1.491 |
terness | +1.472 |
abad | +1.442 |
Neg logit contributions | |
izoph | -1.829 |
iris | -1.734 |
stadt | -1.700 |
Afric | -1.666 |
flakes | -1.562 |
Token | 166 |
Token ID | 26753 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
asi | +6.607 |
wen | +6.418 |
abad | +5.969 |
selage | +5.873 |
ascus | +5.810 |
Neg logit contributions | |
izoph | -9.877 |
iris | -9.051 |
stadt | -8.732 |
Afric | -8.319 |
iHUD | -7.969 |
Token | assists |
Token ID | 13648 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
asi | +0.291 |
wen | +0.289 |
selage | +0.276 |
terness | +0.275 |
abad | +0.268 |
Neg logit contributions | |
izoph | -0.204 |
iris | -0.195 |
stadt | -0.190 |
Afric | -0.183 |
flakes | -0.171 |
Token | for |
Token ID | 329 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
asi | +2.623 |
wen | +2.573 |
selage | +2.412 |
terness | +2.370 |
abad | +2.341 |
Neg logit contributions | |
izoph | -3.323 |
iris | -3.115 |
stadt | -3.055 |
Afric | -2.991 |
flakes | -2.786 |
Token | the |
Token ID | 262 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
asi | +5.802 |
wen | +5.723 |
selage | +5.294 |
abad | +5.294 |
terness | +5.225 |
Neg logit contributions | |
izoph | -7.307 |
iris | -6.745 |
stadt | -6.507 |
Afric | -6.324 |
flakes | -5.934 |
Token | Jets |
Token ID | 14728 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
asi | +3.097 |
wen | +3.021 |
selage | +2.886 |
ascus | +2.817 |
asm | +2.803 |
Neg logit contributions | |
izoph | -2.837 |
iris | -2.701 |
stadt | -2.646 |
Afric | -2.532 |
flakes | -2.372 |
Token | on |
Token ID | 319 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
asi | +0.238 |
wen | +0.236 |
selage | +0.222 |
terness | +0.221 |
abad | +0.215 |
Neg logit contributions | |
izoph | -0.245 |
iris | -0.235 |
stadt | -0.230 |
Afric | -0.224 |
flakes | -0.211 |
Token | Maggie |
Token ID | 33014 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
izoph | +0.697 |
iris | +0.671 |
stadt | +0.657 |
Afric | +0.641 |
Lite | +0.601 |
Neg logit contributions | |
asi | -0.779 |
wen | -0.773 |
selage | -0.733 |
terness | -0.730 |
abad | -0.710 |
Token | Rita |
Token ID | 42605 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
asi | +0.790 |
wen | +0.780 |
selage | +0.736 |
terness | +0.728 |
abad | +0.714 |
Neg logit contributions | |
izoph | -0.780 |
iris | -0.743 |
stadt | -0.724 |
Afric | -0.703 |
flakes | -0.662 |
Token | 's |
Token ID | 338 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
izoph | +0.335 |
iris | +0.323 |
stadt | +0.316 |
Afric | +0.307 |
Lite | +0.289 |
Neg logit contributions | |
asi | -0.334 |
wen | -0.330 |
selage | -0.312 |
terness | -0.310 |
abad | -0.301 |
Token | across |
Token ID | 1973 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
asi | +0.130 |
wen | +0.128 |
selage | +0.121 |
terness | +0.120 |
abad | +0.117 |
Neg logit contributions | |
izoph | -0.133 |
iris | -0.127 |
stadt | -0.125 |
Afric | -0.121 |
flakes | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
wen | +4.519 |
asi | +4.462 |
selage | +4.140 |
terness | +4.134 |
abad | +4.111 |
Neg logit contributions | |
izoph | -4.964 |
iris | -4.603 |
stadt | -4.491 |
Afric | -4.348 |
flakes | -4.135 |
Token | street |
Token ID | 4675 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
asi | +5.408 |
wen | +5.332 |
asm | +5.044 |
abad | +4.997 |
selage | +4.723 |
Neg logit contributions | |
izoph | -10.493 |
iris | -9.890 |
stadt | -9.592 |
Afric | -9.278 |
flakes | -8.877 |
Token | , |
Token ID | 11 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
asi | +1.817 |
wen | +1.804 |
selage | +1.678 |
terness | +1.660 |
abad | +1.629 |
Neg logit contributions | |
izoph | -2.043 |
iris | -1.929 |
stadt | -1.895 |
Afric | -1.841 |
Lite | -1.738 |
Token | though |
Token ID | 996 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
asi | +0.007 |
wen | +0.007 |
selage | +0.006 |
terness | +0.006 |
abad | +0.006 |
Neg logit contributions | |
izoph | -0.007 |
iris | -0.007 |
stadt | -0.007 |
Afric | -0.007 |
Lite | -0.006 |
Token | .) |
Token ID | 2014 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
asi | +2.511 |
wen | +2.484 |
selage | +2.301 |
terness | +2.296 |
asm | +2.243 |
Neg logit contributions | |
izoph | -2.808 |
iris | -2.645 |
stadt | -2.610 |
Afric | -2.492 |
flakes | -2.358 |
Token |
|
Token ID | 198 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
izoph | +1.389 |
iris | +1.352 |
stadt | +1.317 |
Afric | +1.297 |
Lite | +1.218 |
Neg logit contributions | |
asi | -1.658 |
wen | -1.644 |
selage | -1.570 |
terness | -1.563 |
ascus | -1.533 |
Token | at |
Token ID | 379 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
izoph | +0.140 |
iris | +0.135 |
stadt | +0.133 |
Afric | +0.129 |
flakes | +0.122 |
Neg logit contributions | |
asi | -0.142 |
wen | -0.140 |
selage | -0.132 |
terness | -0.132 |
abad | -0.128 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
asi | +0.612 |
wen | +0.606 |
selage | +0.573 |
terness | +0.570 |
abad | +0.556 |
Neg logit contributions | |
izoph | -0.562 |
iris | -0.539 |
stadt | -0.527 |
Afric | -0.510 |
Lite | -0.479 |
Token | entrance |
Token ID | 10384 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
izoph | +0.923 |
iris | +0.892 |
stadt | +0.878 |
Afric | +0.863 |
Lite | +0.806 |
Neg logit contributions | |
asi | -0.955 |
wen | -0.944 |
selage | -0.893 |
terness | -0.892 |
abad | -0.863 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
izoph | +0.939 |
iris | +0.908 |
stadt | +0.895 |
Afric | +0.865 |
flakes | +0.817 |
Neg logit contributions | |
asi | -0.930 |
wen | -0.920 |
selage | -0.868 |
terness | -0.866 |
abad | -0.840 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
asi | +0.886 |
wen | +0.876 |
selage | +0.829 |
terness | +0.825 |
abad | +0.804 |
Neg logit contributions | |
izoph | -0.803 |
iris | -0.769 |
stadt | -0.751 |
Afric | -0.725 |
flakes | -0.683 |
Token | ch |
Token ID | 442 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
asi | +1.738 |
wen | +1.721 |
selage | +1.622 |
terness | +1.606 |
abad | +1.576 |
Neg logit contributions | |
izoph | -1.743 |
iris | -1.671 |
stadt | -1.629 |
Afric | -1.570 |
flakes | -1.489 |
Token | ow |
Token ID | 322 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
asi | +7.029 |
asm | +6.766 |
wen | +6.745 |
abad | +6.385 |
ivas | +6.150 |
Neg logit contributions | |
izoph | -8.920 |
Afric | -8.678 |
iris | -8.531 |
stadt | -8.530 |
Lite | -8.087 |
Token | hall |
Token ID | 6899 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
asi | +0.188 |
wen | +0.186 |
selage | +0.175 |
terness | +0.174 |
abad | +0.169 |
Neg logit contributions | |
izoph | -0.211 |
iris | -0.204 |
stadt | -0.200 |
Afric | -0.195 |
flakes | -0.184 |
Token | , |
Token ID | 11 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
izoph | +3.701 |
stadt | +3.701 |
iris | +3.673 |
Afric | +3.472 |
Lite | +3.298 |
Neg logit contributions | |
asi | -4.302 |
wen | -4.267 |
selage | -4.070 |
terness | -4.053 |
ascus | -3.979 |
Token | known |
Token ID | 1900 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
izoph | +1.288 |
iris | +1.247 |
stadt | +1.227 |
Afric | +1.187 |
flakes | +1.120 |
Neg logit contributions | |
asi | -1.636 |
wen | -1.615 |
terness | -1.537 |
selage | -1.530 |
ascus | -1.491 |
Token | as |
Token ID | 355 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
izoph | +2.422 |
iris | +2.384 |
stadt | +2.323 |
Afric | +2.270 |
Lite | +2.126 |
Neg logit contributions | |
asi | -2.586 |
wen | -2.563 |
selage | -2.440 |
terness | -2.436 |
ascus | -2.358 |
Token | RG |
Token ID | 48192 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
asi | +3.441 |
wen | +3.419 |
selage | +3.097 |
asm | +3.055 |
abad | +3.052 |
Neg logit contributions | |
izoph | -4.081 |
iris | -3.823 |
stadt | -3.805 |
Afric | -3.758 |
flakes | -3.566 |
Token | v |
Token ID | 85 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
asi | +3.958 |
wen | +3.946 |
selage | +3.529 |
asm | +3.520 |
abad | +3.483 |
Neg logit contributions | |
izoph | -4.818 |
iris | -4.509 |
stadt | -4.453 |
Afric | -4.434 |
flakes | -4.212 |
Token | Ch |
Token ID | 1925 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
asi | +5.470 |
wen | +5.414 |
asm | +4.882 |
selage | +4.842 |
abad | +4.815 |
Neg logit contributions | |
izoph | -6.340 |
iris | -5.859 |
Afric | -5.846 |
stadt | -5.835 |
flakes | -5.564 |
Token | 5 |
Token ID | 20 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
asi | +6.813 |
wen | +6.767 |
asm | +6.102 |
abad | +6.000 |
selage | +5.931 |
Neg logit contributions | |
izoph | -7.637 |
Afric | -7.040 |
stadt | -6.979 |
iris | -6.957 |
flakes | -6.680 |
Token | Z |
Token ID | 57 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
asi | +5.391 |
wen | +5.338 |
asm | +4.810 |
selage | +4.770 |
abad | +4.761 |
Neg logit contributions | |
izoph | -6.089 |
stadt | -5.612 |
Afric | -5.607 |
iris | -5.606 |
flakes | -5.321 |
Token | k |
Token ID | 74 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
asi | +5.172 |
wen | +5.149 |
asm | +4.609 |
selage | +4.583 |
abad | +4.566 |
Neg logit contributions | |
izoph | -6.005 |
Afric | -5.538 |
iris | -5.521 |
stadt | -5.520 |
flakes | -5.257 |
Token | A |
Token ID | 32 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
asi | +7.487 |
wen | +7.408 |
asm | +6.673 |
abad | +6.545 |
selage | +6.509 |
Neg logit contributions | |
izoph | -8.366 |
Afric | -7.687 |
stadt | -7.626 |
iris | -7.512 |
flakes | -7.348 |
Token | lf |
Token ID | 1652 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
asi | +3.712 |
wen | +3.668 |
selage | +3.297 |
asm | +3.249 |
abad | +3.247 |
Neg logit contributions | |
izoph | -4.580 |
iris | -4.270 |
Afric | -4.219 |
stadt | -4.207 |
flakes | -4.013 |
Token | ax |
Token ID | 897 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
asi | +6.749 |
wen | +6.698 |
asm | +6.054 |
abad | +5.927 |
selage | +5.891 |
Neg logit contributions | |
izoph | -7.720 |
Afric | -7.093 |
stadt | -7.018 |
iris | -6.977 |
flakes | -6.783 |
Token | Ob |
Token ID | 5944 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
asi | +6.666 |
wen | +6.620 |
asm | +5.936 |
abad | +5.869 |
selage | +5.794 |
Neg logit contributions | |
izoph | -7.734 |
iris | -7.028 |
Afric | -6.995 |
stadt | -6.991 |
flakes | -6.718 |
Token | pg |
Token ID | 6024 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
asi | +9.228 |
wen | +9.136 |
asm | +8.284 |
abad | +8.045 |
selage | +7.982 |
Neg logit contributions | |
izoph | -9.991 |
stadt | -9.000 |
Afric | -8.990 |
iris | -8.891 |
flakes | -8.758 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
izoph | +0.818 |
iris | +0.793 |
stadt | +0.780 |
Afric | +0.757 |
flakes | +0.719 |
Neg logit contributions | |
asi | -0.769 |
wen | -0.760 |
selage | -0.719 |
terness | -0.715 |
ascus | -0.692 |
Token | we |
Token ID | 356 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
izoph | +1.384 |
iris | +1.327 |
stadt | +1.317 |
Afric | +1.290 |
flakes | +1.200 |
Neg logit contributions | |
asi | -1.602 |
wen | -1.586 |
selage | -1.509 |
terness | -1.508 |
abad | -1.461 |
Token | must |
Token ID | 1276 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
izoph | +0.281 |
iris | +0.272 |
stadt | +0.267 |
Afric | +0.258 |
flakes | +0.241 |
Neg logit contributions | |
asi | -0.332 |
wen | -0.330 |
selage | -0.315 |
terness | -0.313 |
ascus | -0.303 |
Token | place |
Token ID | 1295 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
asi | +0.466 |
wen | +0.461 |
selage | +0.439 |
terness | +0.436 |
abad | +0.425 |
Neg logit contributions | |
izoph | -0.397 |
iris | -0.381 |
stadt | -0.373 |
Afric | -0.361 |
flakes | -0.338 |
Token | it |
Token ID | 340 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
izoph | +2.476 |
stadt | +2.382 |
iris | +2.372 |
Afric | +2.361 |
Lite | +2.188 |
Neg logit contributions | |
asi | -3.125 |
wen | -3.124 |
selage | -2.977 |
terness | -2.973 |
abad | -2.892 |
Token | front |
Token ID | 2166 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
izoph | +1.560 |
iris | +1.529 |
stadt | +1.509 |
Afric | +1.469 |
Lite | +1.388 |
Neg logit contributions | |
asi | -1.593 |
wen | -1.580 |
selage | -1.505 |
terness | -1.499 |
ascus | -1.434 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
wen | +6.135 |
asi | +6.100 |
abad | +5.606 |
selage | +5.578 |
quet | +5.570 |
Neg logit contributions | |
izoph | -9.762 |
iris | -9.001 |
stadt | -8.623 |
Afric | -8.364 |
Reaper | -8.193 |
Token | center |
Token ID | 3641 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
asi | +3.127 |
wen | +3.042 |
selage | +2.849 |
abad | +2.756 |
terness | +2.700 |
Neg logit contributions | |
izoph | -5.682 |
iris | -5.323 |
stadt | -5.293 |
Afric | -5.092 |
flakes | -4.849 |
Token | . |
Token ID | 13 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
asi | +0.986 |
wen | +0.976 |
selage | +0.918 |
terness | +0.912 |
abad | +0.889 |
Neg logit contributions | |
izoph | -1.073 |
iris | -1.027 |
stadt | -1.007 |
Afric | -0.980 |
flakes | -0.925 |
Token | Dec |
Token ID | 4280 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
asi | +0.588 |
wen | +0.581 |
selage | +0.549 |
terness | +0.546 |
abad | +0.532 |
Neg logit contributions | |
izoph | -0.557 |
iris | -0.534 |
stadt | -0.523 |
Afric | -0.506 |
flakes | -0.477 |
Token | ades |
Token ID | 2367 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
asi | +0.269 |
wen | +0.266 |
selage | +0.247 |
terness | +0.245 |
abad | +0.236 |
Neg logit contributions | |
izoph | -0.415 |
iris | -0.402 |
stadt | -0.396 |
Afric | -0.386 |
flakes | -0.368 |
Token | ed |
Token ID | 276 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
asi | +1.749 |
wen | +1.723 |
selage | +1.587 |
terness | +1.573 |
abad | +1.535 |
Neg logit contributions | |
izoph | -2.654 |
iris | -2.552 |
stadt | -2.509 |
Afric | -2.458 |
flakes | -2.335 |
Token | < |
Token ID | 1279 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
asi | +3.680 |
wen | +3.631 |
terness | +3.389 |
selage | +3.350 |
asm | +3.325 |
Neg logit contributions | |
izoph | -3.389 |
iris | -3.193 |
stadt | -3.126 |
Afric | -3.035 |
flakes | -2.846 |
Token | T |
Token ID | 309 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
asi | +2.206 |
wen | +2.160 |
selage | +2.014 |
terness | +1.999 |
abad | +1.929 |
Neg logit contributions | |
izoph | -3.451 |
iris | -3.369 |
stadt | -3.307 |
Afric | -3.195 |
flakes | -3.044 |
Token | > |
Token ID | 1875 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
asi | +0.295 |
wen | +0.292 |
selage | +0.277 |
terness | +0.276 |
abad | +0.269 |
Neg logit contributions | |
izoph | -0.253 |
iris | -0.243 |
stadt | -0.237 |
Afric | -0.230 |
Lite | -0.215 |
Token | { |
Token ID | 1391 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
asi | +1.528 |
wen | +1.516 |
terness | +1.405 |
selage | +1.402 |
abad | +1.363 |
Neg logit contributions | |
izoph | -1.855 |
iris | -1.784 |
stadt | -1.756 |
Afric | -1.701 |
flakes | -1.608 |
Token | pub |
Token ID | 2240 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
asi | +4.841 |
wen | +4.690 |
selage | +4.482 |
asm | +4.383 |
terness | +4.376 |
Neg logit contributions | |
izoph | -4.881 |
iris | -4.628 |
stadt | -4.588 |
Afric | -4.437 |
flakes | -4.086 |
Token | fn |
Token ID | 24714 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
wen | +7.605 |
asi | +7.584 |
asm | +6.958 |
terness | +6.833 |
hess | +6.789 |
Neg logit contributions | |
izoph | -8.086 |
iris | -7.701 |
stadt | -7.544 |
Afric | -7.180 |
anooga | -6.615 |
Token | new |
Token ID | 649 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
asi | +3.666 |
wen | +3.662 |
selage | +3.361 |
terness | +3.328 |
abad | +3.319 |
Neg logit contributions | |
izoph | -3.665 |
iris | -3.543 |
stadt | -3.426 |
Afric | -3.325 |
Lite | -3.063 |
Token | ( |
Token ID | 357 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
asi | +3.001 |
wen | +2.974 |
terness | +2.761 |
selage | +2.719 |
abad | +2.687 |
Neg logit contributions | |
izoph | -3.296 |
iris | -3.142 |
stadt | -3.089 |
Afric | -3.002 |
flakes | -2.824 |
Token | t |
Token ID | 256 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
izoph | +0.402 |
iris | +0.388 |
stadt | +0.381 |
Afric | +0.370 |
Lite | +0.352 |
Neg logit contributions | |
asi | -0.316 |
wen | -0.312 |
selage | -0.293 |
terness | -0.293 |
abad | -0.283 |
Token | : |
Token ID | 1058 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
asi | +4.064 |
wen | +4.007 |
terness | +3.708 |
selage | +3.680 |
asm | +3.625 |
Neg logit contributions | |
izoph | -4.499 |
iris | -4.329 |
stadt | -4.265 |
Afric | -4.117 |
Lite | -3.856 |
Token | E |
Token ID | 412 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
asi | +1.413 |
wen | +1.393 |
selage | +1.293 |
terness | +1.275 |
abad | +1.233 |
Neg logit contributions | |
izoph | -2.305 |
iris | -2.246 |
stadt | -2.208 |
Afric | -2.146 |
flakes | -2.048 |
Token | - |
Token ID | 12 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
asi | +1.298 |
wen | +1.287 |
selage | +1.208 |
terness | +1.203 |
abad | +1.171 |
Neg logit contributions | |
izoph | -1.267 |
iris | -1.220 |
stadt | -1.193 |
Afric | -1.159 |
flakes | -1.090 |
Token | mail |
Token ID | 4529 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
izoph | +1.951 |
iris | +1.875 |
stadt | +1.840 |
Afric | +1.789 |
Lite | +1.690 |
Neg logit contributions | |
asi | -1.765 |
wen | -1.740 |
selage | -1.645 |
terness | -1.639 |
abad | -1.585 |
Token | this |
Token ID | 428 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
izoph | +2.325 |
iris | +2.219 |
stadt | +2.177 |
Afric | +2.097 |
flakes | +1.971 |
Neg logit contributions | |
asi | -3.159 |
wen | -3.134 |
terness | -3.019 |
selage | -2.979 |
abad | -2.898 |
Token | to |
Token ID | 284 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
asi | +1.319 |
wen | +1.307 |
selage | +1.221 |
terness | +1.209 |
abad | +1.191 |
Neg logit contributions | |
izoph | -1.491 |
iris | -1.435 |
stadt | -1.406 |
Afric | -1.364 |
flakes | -1.286 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
asi | +4.118 |
wen | +3.950 |
abad | +3.683 |
selage | +3.589 |
asm | +3.549 |
Neg logit contributions | |
izoph | -5.336 |
iris | -4.968 |
stadt | -4.904 |
Afric | -4.796 |
Lite | -4.396 |
Token | friend |
Token ID | 1545 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
asi | +5.414 |
wen | +4.940 |
uckles | +4.789 |
selage | +4.594 |
abad | +4.557 |
Neg logit contributions | |
izoph | -10.852 |
Afric | -10.146 |
stadt | -10.050 |
iris | -10.005 |
flakes | -9.002 |
Token | Print |
Token ID | 12578 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
izoph | +0.631 |
iris | +0.608 |
stadt | +0.598 |
Afric | +0.587 |
Lite | +0.559 |
Neg logit contributions | |
asi | -0.608 |
wen | -0.608 |
terness | -0.578 |
selage | -0.576 |
ascus | -0.554 |
Token | able |
Token ID | 540 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
asi | +2.266 |
wen | +2.239 |
selage | +2.101 |
terness | +2.086 |
abad | +2.028 |
Neg logit contributions | |
izoph | -2.679 |
iris | -2.583 |
stadt | -2.539 |
Afric | -2.466 |
flakes | -2.329 |
Token | version |
Token ID | 2196 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
asi | +4.720 |
wen | +4.488 |
selage | +4.317 |
quet | +4.248 |
asm | +4.198 |
Neg logit contributions | |
izoph | -3.934 |
stadt | -3.797 |
iris | -3.764 |
Afric | -3.576 |
flakes | -3.294 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
asi | +3.467 |
wen | +3.401 |
selage | +3.210 |
terness | +3.177 |
abad | +3.170 |
Neg logit contributions | |
izoph | -3.178 |
iris | -3.015 |
stadt | -2.958 |
Afric | -2.834 |
flakes | -2.656 |
Token | Farm |
Token ID | 11272 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
izoph | +3.366 |
iris | +3.292 |
stadt | +3.286 |
Afric | +3.145 |
flakes | +3.043 |
Neg logit contributions | |
asi | -3.896 |
wen | -3.858 |
selage | -3.757 |
terness | -3.743 |
ascus | -3.604 |
Token | plant |
Token ID | 4618 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
izoph | +3.275 |
iris | +3.230 |
stadt | +3.212 |
Afric | +3.084 |
flakes | +2.979 |
Neg logit contributions | |
wen | -3.581 |
asi | -3.578 |
selage | -3.442 |
terness | -3.378 |
ascus | -3.266 |
Token | ain |
Token ID | 391 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
asi | +0.065 |
wen | +0.064 |
selage | +0.058 |
terness | +0.058 |
abad | +0.056 |
Neg logit contributions | |
izoph | -0.130 |
iris | -0.126 |
stadt | -0.125 |
Afric | -0.122 |
Lite | -0.117 |
Token | flour |
Token ID | 10601 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
izoph | +0.922 |
iris | +0.885 |
stadt | +0.871 |
Afric | +0.844 |
flakes | +0.803 |
Neg logit contributions | |
asi | -1.073 |
wen | -1.064 |
selage | -1.014 |
terness | -1.010 |
abad | -0.977 |
Token | from |
Token ID | 422 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
izoph | +0.351 |
iris | +0.338 |
stadt | +0.332 |
Afric | +0.322 |
flakes | +0.304 |
Neg logit contributions | |
asi | -0.335 |
wen | -0.332 |
selage | -0.313 |
terness | -0.311 |
abad | -0.302 |
Token | am |
Token ID | 716 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
izoph | +0.038 |
iris | +0.036 |
stadt | +0.035 |
Afric | +0.034 |
flakes | +0.032 |
Neg logit contributions | |
asi | -0.041 |
wen | -0.041 |
selage | -0.039 |
terness | -0.039 |
abad | -0.038 |
Token | azon |
Token ID | 5168 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
asi | +6.659 |
wen | +6.506 |
abad | +5.897 |
asm | +5.802 |
imum | +5.747 |
Neg logit contributions | |
izoph | -8.992 |
Afric | -8.433 |
iris | -8.300 |
stadt | -8.297 |
Hitman | -7.988 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
asi | +2.819 |
wen | +2.769 |
selage | +2.545 |
terness | +2.537 |
abad | +2.522 |
Neg logit contributions | |
izoph | -3.242 |
iris | -3.084 |
stadt | -2.983 |
Afric | -2.940 |
Lite | -2.747 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
izoph | +2.343 |
iris | +2.312 |
stadt | +2.266 |
Afric | +2.223 |
Lite | +2.097 |
Neg logit contributions | |
asi | -2.587 |
wen | -2.577 |
selage | -2.492 |
terness | -2.444 |
ascus | -2.411 |
Token |
|
Token ID | 198 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
izoph | +1.351 |
iris | +1.323 |
stadt | +1.305 |
Afric | +1.240 |
Lite | +1.194 |
Neg logit contributions | |
asi | -1.828 |
wen | -1.805 |
terness | -1.778 |
aution | -1.749 |
selage | -1.744 |
Token | Sweet |
Token ID | 36087 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
izoph | +0.733 |
iris | +0.709 |
stadt | +0.696 |
Afric | +0.676 |
Lite | +0.641 |
Neg logit contributions | |
asi | -0.616 |
wen | -0.609 |
selage | -0.574 |
terness | -0.572 |
abad | -0.552 |
Token | joy |
Token ID | 8716 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
izoph | +0.217 |
iris | +0.208 |
stadt | +0.203 |
Afric | +0.197 |
flakes | +0.185 |
Neg logit contributions | |
asi | -0.246 |
wen | -0.244 |
selage | -0.231 |
terness | -0.230 |
abad | -0.224 |
Token | cry |
Token ID | 3960 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
izoph | +1.392 |
iris | +1.343 |
stadt | +1.333 |
Afric | +1.277 |
Lite | +1.207 |
Neg logit contributions | |
asi | -1.483 |
wen | -1.477 |
selage | -1.399 |
terness | -1.380 |
ascus | -1.351 |
Token | resolved |
Token ID | 12939 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
izoph | +0.853 |
iris | +0.828 |
stadt | +0.815 |
Afric | +0.787 |
flakes | +0.747 |
Neg logit contributions | |
asi | -0.776 |
wen | -0.769 |
selage | -0.728 |
terness | -0.720 |
abad | -0.700 |
Token | into |
Token ID | 656 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
asi | +0.188 |
wen | +0.186 |
selage | +0.175 |
terness | +0.175 |
abad | +0.170 |
Neg logit contributions | |
izoph | -0.192 |
iris | -0.185 |
stadt | -0.181 |
Afric | -0.176 |
flakes | -0.166 |
Token | a |
Token ID | 257 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
asi | +0.228 |
wen | +0.226 |
selage | +0.214 |
terness | +0.213 |
abad | +0.207 |
Neg logit contributions | |
izoph | -0.207 |
iris | -0.198 |
stadt | -0.194 |
Afric | -0.188 |
Lite | -0.176 |
Token | j |
Token ID | 474 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
asi | +4.880 |
wen | +4.858 |
selage | +4.519 |
asm | +4.478 |
terness | +4.475 |
Neg logit contributions | |
izoph | -5.009 |
iris | -4.732 |
stadt | -4.560 |
Afric | -4.404 |
Lite | -4.117 |
Token | ub |
Token ID | 549 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
asi | +5.558 |
wen | +5.248 |
asm | +5.042 |
abad | +4.808 |
quet | +4.663 |
Neg logit contributions | |
izoph | -10.172 |
Afric | -9.921 |
iris | -9.493 |
stadt | -9.461 |
Lite | -9.299 |
Token | il |
Token ID | 346 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
izoph | +2.331 |
iris | +2.240 |
stadt | +2.118 |
Afric | +1.918 |
Lite | +1.755 |
Neg logit contributions | |
wen | -7.609 |
asi | -7.573 |
selage | -7.361 |
terness | -7.337 |
abad | -7.188 |
Token | ating |
Token ID | 803 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
izoph | +1.334 |
iris | +1.267 |
stadt | +1.236 |
Afric | +1.181 |
Lite | +1.090 |
Neg logit contributions | |
asi | -2.216 |
wen | -2.208 |
selage | -2.115 |
terness | -2.111 |
ascus | -2.050 |
Token | chant |
Token ID | 33541 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
izoph | +0.045 |
iris | +0.044 |
stadt | +0.043 |
Afric | +0.042 |
flakes | +0.039 |
Neg logit contributions | |
asi | -0.045 |
wen | -0.044 |
selage | -0.042 |
terness | -0.041 |
abad | -0.040 |
Token | : |
Token ID | 25 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
asi | +1.288 |
wen | +1.274 |
selage | +1.194 |
terness | +1.190 |
abad | +1.157 |
Neg logit contributions | |
izoph | -1.417 |
iris | -1.353 |
stadt | -1.329 |
Afric | -1.295 |
Lite | -1.220 |
Token | wrote |
Token ID | 2630 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
asi | +0.997 |
wen | +0.986 |
selage | +0.930 |
terness | +0.924 |
abad | +0.901 |
Neg logit contributions | |
izoph | -0.991 |
iris | -0.952 |
stadt | -0.933 |
Afric | -0.906 |
Lite | -0.853 |
Token | , |
Token ID | 11 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
asi | +0.118 |
wen | +0.116 |
selage | +0.110 |
terness | +0.109 |
abad | +0.106 |
Neg logit contributions | |
izoph | -0.126 |
iris | -0.122 |
stadt | -0.119 |
Afric | -0.116 |
Lite | -0.110 |
Token | � |
Token ID | 564 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
izoph | +0.893 |
iris | +0.864 |
stadt | +0.853 |
Afric | +0.835 |
Lite | +0.800 |
Neg logit contributions | |
asi | -0.442 |
wen | -0.434 |
selage | -0.399 |
terness | -0.395 |
abad | -0.377 |
Token | � |
Token ID | 250 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
asi | +1.525 |
wen | +1.516 |
selage | +1.428 |
terness | +1.424 |
abad | +1.391 |
Neg logit contributions | |
izoph | -1.364 |
iris | -1.311 |
stadt | -1.275 |
Afric | -1.246 |
flakes | -1.162 |
Token | More |
Token ID | 5167 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
asi | +3.028 |
wen | +2.985 |
terness | +2.724 |
selage | +2.704 |
asm | +2.679 |
Neg logit contributions | |
izoph | -3.514 |
iris | -3.363 |
stadt | -3.341 |
Afric | -3.245 |
flakes | -3.111 |
Token | subtle |
Token ID | 11800 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
asi | +3.959 |
wen | +3.827 |
terness | +3.616 |
selage | +3.585 |
asm | +3.489 |
Neg logit contributions | |
izoph | -4.360 |
iris | -4.292 |
stadt | -4.173 |
Afric | -4.056 |
flakes | -3.784 |
Token | and |
Token ID | 290 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
asi | +5.527 |
wen | +5.193 |
asm | +4.814 |
terness | +4.793 |
quet | +4.721 |
Neg logit contributions | |
izoph | -9.725 |
iris | -9.354 |
stadt | -9.152 |
Afric | -8.833 |
flakes | -8.361 |
Token | more |
Token ID | 517 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
asi | +5.135 |
wen | +4.888 |
asm | +4.561 |
abad | +4.444 |
selage | +4.354 |
Neg logit contributions | |
izoph | -7.185 |
iris | -6.885 |
stadt | -6.597 |
Afric | -6.547 |
flakes | -6.094 |
Token | insidious |
Token ID | 43732 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
izoph | +0.334 |
iris | +0.322 |
stadt | +0.317 |
Afric | +0.309 |
Lite | +0.293 |
Neg logit contributions | |
asi | -0.247 |
wen | -0.244 |
selage | -0.229 |
terness | -0.228 |
abad | -0.220 |
Token | was |
Token ID | 373 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
asi | +2.208 |
wen | +2.169 |
terness | +2.027 |
selage | +2.009 |
abad | +1.957 |
Neg logit contributions | |
izoph | -2.342 |
iris | -2.264 |
stadt | -2.227 |
Afric | -2.143 |
flakes | -2.036 |
Token | the |
Token ID | 262 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
asi | +2.001 |
wen | +1.992 |
selage | +1.857 |
terness | +1.847 |
abad | +1.808 |
Neg logit contributions | |
izoph | -1.911 |
iris | -1.811 |
stadt | -1.776 |
Afric | -1.728 |
flakes | -1.623 |
Token | great |
Token ID | 1049 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
asi | +2.504 |
wen | +2.491 |
selage | +2.354 |
terness | +2.309 |
abad | +2.278 |
Neg logit contributions | |
izoph | -2.419 |
iris | -2.304 |
stadt | -2.239 |
Afric | -2.169 |
flakes | -2.037 |
Token | trade |
Token ID | 3292 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
asi | +0.628 |
wen | +0.622 |
selage | +0.586 |
terness | +0.583 |
abad | +0.568 |
Neg logit contributions | |
izoph | -0.633 |
iris | -0.608 |
stadt | -0.596 |
Afric | -0.578 |
flakes | -0.545 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
asi | +1.462 |
wen | +1.452 |
terness | +1.338 |
selage | +1.337 |
abad | +1.305 |
Neg logit contributions | |
izoph | -1.732 |
iris | -1.674 |
stadt | -1.633 |
Afric | -1.587 |
flakes | -1.509 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
asi | +1.001 |
wen | +0.987 |
selage | +0.924 |
terness | +0.921 |
abad | +0.900 |
Neg logit contributions | |
izoph | -1.108 |
iris | -1.064 |
stadt | -1.041 |
Afric | -1.010 |
flakes | -0.958 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
izoph | +0.697 |
iris | +0.677 |
stadt | +0.666 |
Afric | +0.636 |
Lite | +0.605 |
Neg logit contributions | |
asi | -0.878 |
wen | -0.866 |
terness | -0.841 |
selage | -0.831 |
ascus | -0.818 |
Token | Correction |
Token ID | 43267 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
izoph | +0.213 |
iris | +0.206 |
stadt | +0.202 |
Afric | +0.196 |
Lite | +0.185 |
Neg logit contributions | |
asi | -0.189 |
wen | -0.187 |
selage | -0.176 |
terness | -0.175 |
abad | -0.169 |
Token | : |
Token ID | 25 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
asi | +6.629 |
wen | +6.305 |
asm | +5.752 |
abad | +5.731 |
selage | +5.718 |
Neg logit contributions | |
izoph | -8.750 |
iris | -8.244 |
stadt | -7.956 |
Afric | -7.888 |
flakes | -7.453 |
Token | I |
Token ID | 314 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
asi | +2.526 |
wen | +2.481 |
selage | +2.323 |
terness | +2.314 |
abad | +2.265 |
Neg logit contributions | |
izoph | -2.708 |
iris | -2.599 |
stadt | -2.512 |
Afric | -2.452 |
flakes | -2.313 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
asi | +0.964 |
wen | +0.954 |
selage | +0.902 |
terness | +0.898 |
abad | +0.871 |
Neg logit contributions | |
izoph | -0.951 |
iris | -0.913 |
stadt | -0.899 |
Afric | -0.869 |
flakes | -0.819 |
Token | switched |
Token ID | 15293 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
asi | +2.101 |
wen | +2.080 |
selage | +1.959 |
terness | +1.943 |
abad | +1.895 |
Neg logit contributions | |
izoph | -2.140 |
iris | -2.054 |
stadt | -2.007 |
Afric | -1.954 |
Lite | -1.837 |
Token | Dar |
Token ID | 7491 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
izoph | +0.319 |
iris | +0.306 |
stadt | +0.300 |
Afric | +0.292 |
flakes | +0.274 |
Neg logit contributions | |
asi | -0.339 |
wen | -0.336 |
selage | -0.318 |
terness | -0.317 |
abad | -0.307 |
Token | if |
Token ID | 611 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
asi | +2.658 |
wen | +2.615 |
selage | +2.442 |
terness | +2.436 |
asm | +2.395 |
Neg logit contributions | |
izoph | -2.690 |
iris | -2.571 |
stadt | -2.493 |
Afric | -2.406 |
flakes | -2.257 |
Token | it |
Token ID | 340 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
asi | +1.447 |
wen | +1.431 |
selage | +1.342 |
terness | +1.340 |
abad | +1.314 |
Neg logit contributions | |
izoph | -1.368 |
iris | -1.310 |
stadt | -1.279 |
Afric | -1.235 |
flakes | -1.156 |
Token | 's |
Token ID | 338 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
izoph | +2.157 |
iris | +2.121 |
stadt | +2.060 |
Afric | +1.989 |
flakes | +1.913 |
Neg logit contributions | |
asi | -2.622 |
wen | -2.580 |
terness | -2.487 |
selage | -2.474 |
ascus | -2.405 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
izoph | +0.296 |
iris | +0.284 |
stadt | +0.279 |
Afric | +0.271 |
Lite | +0.256 |
Neg logit contributions | |
asi | -0.308 |
wen | -0.305 |
selage | -0.289 |
terness | -0.288 |
abad | -0.278 |
Token | mum |
Token ID | 25682 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
asi | +0.874 |
wen | +0.865 |
selage | +0.816 |
terness | +0.809 |
abad | +0.794 |
Neg logit contributions | |
izoph | -0.795 |
iris | -0.759 |
stadt | -0.740 |
Afric | -0.716 |
flakes | -0.668 |
Token | and |
Token ID | 290 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
asi | +0.645 |
wen | +0.639 |
selage | +0.600 |
terness | +0.596 |
abad | +0.581 |
Neg logit contributions | |
izoph | -0.667 |
iris | -0.639 |
stadt | -0.624 |
Afric | -0.607 |
flakes | -0.572 |
Token | dad |
Token ID | 9955 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
flakes | +6.818 |
iris | +6.713 |
Afric | +6.665 |
stadt | +6.609 |
presenter | +6.543 |
Neg logit contributions | |
terness | -13.100 |
selage | -12.792 |
wen | -12.681 |
asi | -12.584 |
imum | -12.531 |
Token | business |
Token ID | 1597 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
izoph | +0.388 |
iris | +0.373 |
stadt | +0.366 |
Afric | +0.355 |
Lite | +0.334 |
Neg logit contributions | |
asi | -0.403 |
wen | -0.398 |
selage | -0.377 |
terness | -0.375 |
abad | -0.364 |
Token | that |
Token ID | 326 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
asi | +2.146 |
wen | +2.115 |
selage | +1.977 |
terness | +1.966 |
abad | +1.935 |
Neg logit contributions | |
izoph | -2.341 |
iris | -2.213 |
stadt | -2.169 |
Afric | -2.108 |
flakes | -1.985 |
Token | 's |
Token ID | 338 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
asi | +0.916 |
wen | +0.907 |
selage | +0.853 |
terness | +0.849 |
abad | +0.832 |
Neg logit contributions | |
izoph | -0.865 |
iris | -0.825 |
stadt | -0.808 |
Afric | -0.783 |
Lite | -0.733 |
Token | not |
Token ID | 407 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
asi | +0.742 |
wen | +0.733 |
selage | +0.691 |
terness | +0.687 |
abad | +0.670 |
Neg logit contributions | |
izoph | -0.753 |
iris | -0.722 |
stadt | -0.707 |
Afric | -0.686 |
flakes | -0.645 |
Token | t |
Token ID | 256 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
asi | +1.571 |
wen | +1.561 |
selage | +1.470 |
terness | +1.469 |
abad | +1.437 |
Neg logit contributions | |
izoph | -1.378 |
iris | -1.315 |
stadt | -1.281 |
Afric | -1.243 |
Lite | -1.157 |
Token | ê |
Token ID | 25792 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
izoph | +0.325 |
iris | +0.314 |
stadt | +0.308 |
Afric | +0.299 |
flakes | +0.285 |
Neg logit contributions | |
asi | -0.245 |
wen | -0.242 |
selage | -0.227 |
terness | -0.226 |
abad | -0.217 |
Token | te |
Token ID | 660 |
Feature activation | -9.55e+00 |
Pos logit contributions | |
asi | +0.285 |
wen | +0.282 |
selage | +0.270 |
terness | +0.268 |
abad | +0.263 |
Neg logit contributions | |
izoph | -0.161 |
iris | -0.152 |
stadt | -0.149 |
Afric | -0.142 |
Lite | -0.130 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
izoph | +5.438 |
Afric | +5.272 |
iris | +5.257 |
stadt | +5.100 |
flakes | +4.838 |
Neg logit contributions | |
wen | -7.598 |
asi | -7.499 |
selage | -7.457 |
terness | -7.405 |
abad | -7.083 |
Token | à |
Token ID | 24247 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
iris | +7.610 |
izoph | +7.230 |
stadt | +7.174 |
Lite | +6.876 |
video | +6.855 |
Neg logit contributions | |
terness | -7.294 |
selage | -7.250 |
aution | -7.024 |
asi | -6.958 |
wen | -6.894 |
Token | - |
Token ID | 12 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
iris | +3.978 |
stadt | +3.898 |
izoph | +3.893 |
Lite | +3.783 |
Afric | +3.685 |
Neg logit contributions | |
asi | -6.589 |
terness | -6.576 |
aution | -6.475 |
wen | -6.435 |
selage | -6.431 |
Token | t |
Token ID | 83 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
iris | +7.247 |
video | +6.729 |
stadt | +6.250 |
rocket | +6.211 |
Lite | +6.033 |
Neg logit contributions | |
aution | -11.168 |
terness | -10.827 |
ascus | -10.784 |
selage | -10.638 |
asi | -10.307 |
Token | ê |
Token ID | 25792 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
iris | +6.146 |
izoph | +5.558 |
stadt | +5.495 |
oche | +5.089 |
video | +5.075 |
Neg logit contributions | |
terness | -6.196 |
aution | -6.115 |
asi | -6.108 |
ascus | -6.041 |
selage | -6.035 |
Token | te |
Token ID | 660 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
izoph | +2.690 |
iris | +2.689 |
stadt | +2.549 |
Afric | +2.404 |
Lite | +2.302 |
Neg logit contributions | |
asi | -6.515 |
wen | -6.465 |
aution | -6.393 |
terness | -6.386 |
selage | -6.336 |
Token | with |
Token ID | 351 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
izoph | +3.207 |
stadt | +3.100 |
iris | +3.094 |
Afric | +2.988 |
Lite | +2.873 |
Neg logit contributions | |
asi | -3.797 |
wen | -3.780 |
selage | -3.600 |
terness | -3.550 |
ascus | -3.445 |
Token | Short |
Token ID | 10073 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
izoph | +0.228 |
iris | +0.219 |
stadt | +0.215 |
Afric | +0.209 |
Lite | +0.196 |
Neg logit contributions | |
asi | -0.241 |
wen | -0.239 |
selage | -0.226 |
terness | -0.225 |
abad | -0.218 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
asi | +0.632 |
wen | +0.625 |
terness | +0.592 |
selage | +0.590 |
ascus | +0.573 |
Neg logit contributions | |
izoph | -0.634 |
iris | -0.613 |
stadt | -0.602 |
Afric | -0.584 |
Lite | -0.553 |
Token | services |
Token ID | 2594 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
asi | +0.199 |
wen | +0.195 |
selage | +0.190 |
terness | +0.189 |
ascus | +0.185 |
Neg logit contributions | |
izoph | -0.152 |
iris | -0.147 |
stadt | -0.144 |
Afric | -0.140 |
flakes | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
iris | +3.340 |
stadt | +3.282 |
izoph | +3.273 |
Afric | +3.159 |
Lite | +3.102 |
Neg logit contributions | |
aution | -4.791 |
terness | -4.742 |
asi | -4.713 |
ascus | -4.644 |
wen | -4.544 |
Token | Thank |
Token ID | 6952 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
asi | +0.088 |
wen | +0.087 |
terness | +0.084 |
selage | +0.083 |
ascus | +0.082 |
Neg logit contributions | |
izoph | -0.068 |
iris | -0.066 |
stadt | -0.064 |
Afric | -0.062 |
Lite | -0.059 |
Token | you |
Token ID | 345 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
izoph | +2.233 |
iris | +2.201 |
stadt | +2.148 |
Afric | +2.028 |
Lite | +1.979 |
Neg logit contributions | |
asi | -3.480 |
wen | -3.439 |
terness | -3.369 |
aution | -3.354 |
ascus | -3.315 |
Token | for |
Token ID | 329 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
izoph | +3.149 |
iris | +3.142 |
stadt | +3.113 |
Afric | +2.882 |
Lite | +2.850 |
Neg logit contributions | |
terness | -4.551 |
asi | -4.481 |
aution | -4.398 |
wen | -4.323 |
ascus | -4.234 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
stadt | +0.652 |
subscribing | +0.547 |
iris | +0.287 |
Agency | +0.021 |
Reaper | -0.085 |
Neg logit contributions | |
terness | -17.678 |
aution | -17.556 |
ascus | -16.859 |
asi | -16.764 |
selage | -16.621 |
Token | . |
Token ID | 13 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
izoph | +1.478 |
iris | +1.433 |
stadt | +1.431 |
Afric | +1.369 |
Lite | +1.326 |
Neg logit contributions | |
asi | -1.764 |
wen | -1.726 |
terness | -1.723 |
ascus | -1.690 |
aution | -1.685 |
Token | An |
Token ID | 1052 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Afric | +3.192 |
Reaper | +3.133 |
iris | +3.129 |
Agency | +3.126 |
Lite | +3.106 |
Neg logit contributions | |
ascus | -5.401 |
aution | -5.205 |
terness | -5.148 |
selage | -5.070 |
asi | -5.065 |
Token | error |
Token ID | 4049 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
izoph | +0.214 |
iris | +0.206 |
stadt | +0.203 |
Afric | +0.194 |
flakes | +0.182 |
Neg logit contributions | |
asi | -0.281 |
wen | -0.277 |
selage | -0.265 |
terness | -0.265 |
ascus | -0.258 |
Token | has |
Token ID | 468 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
izoph | +0.024 |
iris | +0.023 |
stadt | +0.023 |
Afric | +0.022 |
Lite | +0.021 |
Neg logit contributions | |
asi | -0.026 |
wen | -0.026 |
terness | -0.025 |
selage | -0.025 |
ascus | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
asi | +1.058 |
wen | +1.046 |
selage | +0.986 |
terness | +0.982 |
abad | +0.953 |
Neg logit contributions | |
izoph | -1.103 |
iris | -1.062 |
stadt | -1.041 |
Afric | -1.012 |
Lite | -0.954 |
Token | services |
Token ID | 2594 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
asi | +0.241 |
wen | +0.237 |
selage | +0.231 |
terness | +0.229 |
ascus | +0.224 |
Neg logit contributions | |
izoph | -0.185 |
iris | -0.180 |
stadt | -0.175 |
Afric | -0.170 |
flakes | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
iris | +3.135 |
stadt | +3.081 |
izoph | +3.070 |
Afric | +2.970 |
Lite | +2.926 |
Neg logit contributions | |
aution | -4.485 |
terness | -4.453 |
asi | -4.413 |
ascus | -4.348 |
wen | -4.263 |
Token | Thank |
Token ID | 6952 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
asi | +0.746 |
wen | +0.739 |
selage | +0.704 |
terness | +0.703 |
ascus | +0.684 |
Neg logit contributions | |
izoph | -0.609 |
iris | -0.586 |
stadt | -0.573 |
Afric | -0.555 |
Lite | -0.520 |
Token | you |
Token ID | 345 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
izoph | +1.999 |
iris | +1.969 |
stadt | +1.918 |
Afric | +1.821 |
Lite | +1.763 |
Neg logit contributions | |
asi | -3.061 |
wen | -3.028 |
terness | -2.956 |
aution | -2.919 |
selage | -2.912 |
Token | for |
Token ID | 329 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
iris | +3.072 |
izoph | +3.060 |
stadt | +3.036 |
Afric | +2.818 |
Agency | +2.785 |
Neg logit contributions | |
terness | -4.564 |
asi | -4.444 |
aution | -4.387 |
wen | -4.300 |
selage | -4.214 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
stadt | +0.639 |
subscribing | +0.588 |
iris | +0.278 |
Agency | +0.061 |
Reaper | -0.054 |
Neg logit contributions | |
terness | -17.671 |
aution | -17.558 |
ascus | -16.755 |
asi | -16.694 |
selage | -16.552 |
Token | . |
Token ID | 13 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
izoph | +1.588 |
stadt | +1.543 |
iris | +1.542 |
Afric | +1.476 |
Lite | +1.431 |
Neg logit contributions | |
asi | -1.952 |
terness | -1.919 |
wen | -1.907 |
ascus | -1.884 |
aution | -1.882 |
Token | An |
Token ID | 1052 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Afric | +3.157 |
Agency | +3.103 |
Reaper | +3.090 |
iris | +3.071 |
stadt | +3.047 |
Neg logit contributions | |
ascus | -5.414 |
aution | -5.226 |
terness | -5.197 |
selage | -5.107 |
asi | -5.083 |
Token | error |
Token ID | 4049 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
asi | +0.201 |
wen | +0.199 |
selage | +0.190 |
terness | +0.189 |
ascus | +0.184 |
Neg logit contributions | |
izoph | -0.158 |
iris | -0.152 |
stadt | -0.149 |
Afric | -0.143 |
flakes | -0.134 |
Token | has |
Token ID | 468 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
izoph | +0.106 |
iris | +0.103 |
stadt | +0.103 |
Afric | +0.098 |
Lite | +0.094 |
Neg logit contributions | |
asi | -0.115 |
wen | -0.114 |
terness | -0.111 |
selage | -0.109 |
ascus | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
asi | +1.316 |
wen | +1.302 |
selage | +1.226 |
terness | +1.218 |
abad | +1.186 |
Neg logit contributions | |
izoph | -1.396 |
iris | -1.342 |
stadt | -1.315 |
Afric | -1.278 |
flakes | -1.205 |
Token | services |
Token ID | 2594 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
asi | +0.401 |
wen | +0.394 |
selage | +0.382 |
terness | +0.380 |
ascus | +0.371 |
Neg logit contributions | |
izoph | -0.313 |
iris | -0.303 |
stadt | -0.296 |
Afric | -0.288 |
flakes | -0.270 |
Token | . |
Token ID | 13 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
iris | +3.312 |
stadt | +3.260 |
izoph | +3.231 |
Afric | +3.134 |
Lite | +3.084 |
Neg logit contributions | |
aution | -4.785 |
terness | -4.740 |
asi | -4.698 |
ascus | -4.628 |
wen | -4.527 |
Token | Thank |
Token ID | 6952 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
asi | +0.742 |
wen | +0.735 |
selage | +0.701 |
terness | +0.700 |
ascus | +0.683 |
Neg logit contributions | |
izoph | -0.598 |
iris | -0.576 |
stadt | -0.563 |
Afric | -0.545 |
Lite | -0.512 |
Token | you |
Token ID | 345 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
izoph | +2.187 |
iris | +2.157 |
stadt | +2.104 |
Afric | +1.991 |
Lite | +1.940 |
Neg logit contributions | |
asi | -3.412 |
wen | -3.373 |
terness | -3.295 |
aution | -3.278 |
selage | -3.246 |
Token | for |
Token ID | 329 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
izoph | +2.920 |
iris | +2.917 |
stadt | +2.883 |
Afric | +2.686 |
Reaper | +2.640 |
Neg logit contributions | |
terness | -4.176 |
asi | -4.117 |
aution | -4.026 |
wen | -3.976 |
selage | -3.880 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
stadt | +0.604 |
subscribing | +0.508 |
iris | +0.220 |
Agency | +0.010 |
Reaper | -0.114 |
Neg logit contributions | |
terness | -17.486 |
aution | -17.386 |
ascus | -16.643 |
asi | -16.583 |
selage | -16.449 |
Token | . |
Token ID | 13 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
izoph | +1.121 |
iris | +1.085 |
stadt | +1.080 |
Afric | +1.037 |
Lite | +1.001 |
Neg logit contributions | |
asi | -1.301 |
wen | -1.274 |
terness | -1.262 |
selage | -1.237 |
ascus | -1.236 |
Token | An |
Token ID | 1052 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
Afric | +3.006 |
iris | +2.952 |
Reaper | +2.936 |
Agency | +2.932 |
stadt | +2.922 |
Neg logit contributions | |
ascus | -4.948 |
aution | -4.767 |
terness | -4.733 |
selage | -4.670 |
asi | -4.663 |
Token | error |
Token ID | 4049 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
izoph | +0.052 |
iris | +0.050 |
stadt | +0.050 |
Afric | +0.048 |
flakes | +0.044 |
Neg logit contributions | |
asi | -0.068 |
wen | -0.067 |
selage | -0.064 |
terness | -0.064 |
ascus | -0.062 |
Token | has |
Token ID | 468 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
izoph | +0.060 |
iris | +0.058 |
stadt | +0.058 |
Afric | +0.055 |
Lite | +0.053 |
Neg logit contributions | |
asi | -0.064 |
wen | -0.064 |
terness | -0.062 |
selage | -0.061 |
ascus | -0.060 |
Token | people |
Token ID | 661 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
izoph | +1.006 |
iris | +0.963 |
stadt | +0.951 |
Afric | +0.927 |
Lite | +0.874 |
Neg logit contributions | |
asi | -0.992 |
wen | -0.981 |
selage | -0.935 |
terness | -0.923 |
ascus | -0.896 |
Token | , |
Token ID | 11 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
izoph | +1.064 |
iris | +1.031 |
stadt | +1.016 |
Afric | +0.985 |
flakes | +0.929 |
Neg logit contributions | |
asi | -1.075 |
wen | -1.064 |
selage | -1.014 |
terness | -1.007 |
ascus | -0.973 |
Token | this |
Token ID | 428 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
izoph | +0.591 |
iris | +0.567 |
stadt | +0.556 |
Afric | +0.541 |
Lite | +0.508 |
Neg logit contributions | |
asi | -0.644 |
wen | -0.638 |
selage | -0.606 |
terness | -0.603 |
abad | -0.586 |
Token | dé |
Token ID | 39073 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
izoph | +0.116 |
iris | +0.111 |
stadt | +0.109 |
Afric | +0.105 |
Lite | +0.099 |
Neg logit contributions | |
asi | -0.126 |
wen | -0.125 |
selage | -0.118 |
terness | -0.118 |
abad | -0.114 |
Token | j |
Token ID | 73 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
asi | +1.189 |
wen | +1.172 |
selage | +1.086 |
terness | +1.082 |
abad | +1.034 |
Neg logit contributions | |
izoph | -1.930 |
iris | -1.868 |
stadt | -1.850 |
Afric | -1.803 |
flakes | -1.713 |
Token | à |
Token ID | 24247 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
izoph | +2.777 |
iris | +2.726 |
stadt | +2.617 |
Afric | +2.600 |
Lite | +2.486 |
Neg logit contributions | |
wen | -1.751 |
asi | -1.732 |
terness | -1.638 |
selage | -1.620 |
ascus | -1.543 |
Token | v |
Token ID | 410 |
Feature activation | -9.06e+00 |
Pos logit contributions | |
iris | +3.783 |
izoph | +3.328 |
Afric | +3.081 |
Lite | +3.034 |
Reaper | +2.809 |
Neg logit contributions | |
wen | -14.045 |
selage | -13.639 |
terness | -13.514 |
ascus | -13.358 |
asi | -13.311 |
Token | u |
Token ID | 84 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
iris | +6.328 |
izoph | +6.148 |
stadt | +5.789 |
Afric | +5.572 |
Lite | +5.567 |
Neg logit contributions | |
terness | -6.030 |
wen | -5.928 |
asi | -5.894 |
selage | -5.859 |
ascus | -5.710 |
Token | isn |
Token ID | 2125 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
izoph | +3.746 |
iris | +3.732 |
stadt | +3.704 |
Afric | +3.490 |
flakes | +3.395 |
Neg logit contributions | |
asi | -4.748 |
wen | -4.664 |
selage | -4.615 |
terness | -4.443 |
ascus | -4.328 |
Token | � |
Token ID | 447 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
asi | +1.424 |
wen | +1.408 |
selage | +1.299 |
terness | +1.280 |
abad | +1.254 |
Neg logit contributions | |
izoph | -2.160 |
iris | -2.078 |
stadt | -2.036 |
Afric | -2.006 |
flakes | -1.904 |
Token | � |
Token ID | 247 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
izoph | +0.632 |
iris | +0.604 |
stadt | +0.593 |
Afric | +0.571 |
Lite | +0.537 |
Neg logit contributions | |
asi | -0.757 |
wen | -0.750 |
selage | -0.712 |
terness | -0.708 |
ascus | -0.693 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
asi | +1.471 |
wen | +1.459 |
selage | +1.351 |
terness | +1.320 |
abad | +1.307 |
Neg logit contributions | |
izoph | -1.949 |
iris | -1.862 |
stadt | -1.828 |
Afric | -1.792 |
flakes | -1.702 |
Token | { |
Token ID | 1391 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
izoph | +1.416 |
iris | +1.378 |
stadt | +1.350 |
Afric | +1.327 |
Lite | +1.269 |
Neg logit contributions | |
asi | -1.148 |
wen | -1.133 |
terness | -1.079 |
selage | -1.066 |
ascus | -1.043 |
Token | ( |
Token ID | 7 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
asi | +1.207 |
wen | +1.199 |
selage | +1.100 |
terness | +1.075 |
abad | +1.069 |
Neg logit contributions | |
izoph | -1.749 |
iris | -1.679 |
stadt | -1.648 |
Afric | -1.618 |
flakes | -1.535 |
Token | 153 |
Token ID | 21395 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
asi | +0.085 |
wen | +0.084 |
selage | +0.079 |
terness | +0.078 |
abad | +0.076 |
Neg logit contributions | |
izoph | -0.101 |
iris | -0.098 |
stadt | -0.096 |
Afric | -0.093 |
Lite | -0.088 |
Token | s |
Token ID | 82 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
izoph | +2.500 |
iris | +2.486 |
stadt | +2.454 |
Afric | +2.344 |
Lite | +2.239 |
Neg logit contributions | |
asi | -2.634 |
wen | -2.612 |
terness | -2.560 |
selage | -2.537 |
aution | -2.475 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
izoph | +1.962 |
iris | +1.914 |
stadt | +1.872 |
Afric | +1.769 |
Lite | +1.706 |
Neg logit contributions | |
asi | -2.510 |
wen | -2.477 |
terness | -2.408 |
ascus | -2.384 |
selage | -2.374 |
Token | 25 |
Token ID | 1679 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
iris | +5.228 |
Afric | +5.095 |
izoph | +5.085 |
Reaper | +4.725 |
stadt | +4.698 |
Neg logit contributions | |
wen | -11.664 |
asi | -11.651 |
terness | -11.441 |
ascus | -11.390 |
selage | -11.361 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
izoph | +1.057 |
iris | +1.026 |
stadt | +1.013 |
Afric | +0.977 |
Lite | +0.933 |
Neg logit contributions | |
asi | -1.126 |
wen | -1.112 |
terness | -1.082 |
selage | -1.060 |
ascus | -1.048 |
Token | B |
Token ID | 347 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
izoph | +1.130 |
iris | +1.090 |
stadt | +1.070 |
Afric | +1.052 |
Lite | +0.984 |
Neg logit contributions | |
asi | -1.185 |
wen | -1.178 |
terness | -1.117 |
selage | -1.115 |
ascus | -1.080 |
Token | xc |
Token ID | 25306 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
izoph | +1.699 |
iris | +1.646 |
stadt | +1.616 |
Afric | +1.565 |
flakes | +1.470 |
Neg logit contributions | |
asi | -1.699 |
wen | -1.680 |
terness | -1.611 |
selage | -1.601 |
ascus | -1.547 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
izoph | +0.728 |
iris | +0.703 |
stadt | +0.691 |
Afric | +0.671 |
Lite | +0.634 |
Neg logit contributions | |
asi | -0.685 |
wen | -0.679 |
terness | -0.640 |
selage | -0.639 |
abad | -0.617 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
izoph | +1.535 |
iris | +1.487 |
stadt | +1.448 |
Afric | +1.405 |
flakes | +1.343 |
Neg logit contributions | |
asi | -1.532 |
wen | -1.514 |
selage | -1.442 |
terness | -1.432 |
abad | -1.395 |
Token | So |
Token ID | 1406 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
izoph | +2.856 |
iris | +2.826 |
stadt | +2.766 |
Afric | +2.670 |
Lite | +2.572 |
Neg logit contributions | |
asi | -3.311 |
wen | -3.288 |
selage | -3.164 |
terness | -3.152 |
ascus | -3.099 |
Token | , |
Token ID | 11 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
izoph | +3.276 |
iris | +3.248 |
stadt | +3.127 |
Afric | +3.017 |
Lite | +2.910 |
Neg logit contributions | |
asi | -3.639 |
wen | -3.561 |
terness | -3.420 |
selage | -3.406 |
ascus | -3.341 |
Token | choose |
Token ID | 3853 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
izoph | +3.284 |
iris | +3.245 |
stadt | +3.141 |
Afric | +3.036 |
Lite | +2.923 |
Neg logit contributions | |
asi | -3.697 |
wen | -3.628 |
terness | -3.485 |
selage | -3.469 |
ascus | -3.388 |
Token | wisely |
Token ID | 32773 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
izoph | +2.226 |
iris | +2.136 |
stadt | +2.094 |
Afric | +2.026 |
Lite | +1.931 |
Neg logit contributions | |
asi | -2.590 |
wen | -2.566 |
selage | -2.449 |
terness | -2.426 |
ascus | -2.377 |
Token | when |
Token ID | 618 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
izoph | +3.671 |
iris | +3.547 |
stadt | +3.479 |
Afric | +3.386 |
Lite | +3.235 |
Neg logit contributions | |
asi | -4.076 |
wen | -4.015 |
terness | -3.811 |
selage | -3.808 |
ascus | -3.754 |
Token | shooting |
Token ID | 4395 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
izoph | +7.129 |
stadt | +7.125 |
iris | +6.965 |
Afric | +6.695 |
Lite | +6.642 |
Neg logit contributions | |
asi | -9.718 |
terness | -9.483 |
wen | -9.442 |
selage | -9.153 |
ascus | -9.091 |
Token | : |
Token ID | 25 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
izoph | +1.740 |
iris | +1.674 |
stadt | +1.637 |
Afric | +1.589 |
Lite | +1.512 |
Neg logit contributions | |
asi | -1.923 |
wen | -1.900 |
terness | -1.809 |
selage | -1.802 |
abad | -1.749 |
Token | you |
Token ID | 345 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
izoph | +3.812 |
iris | +3.696 |
stadt | +3.624 |
Afric | +3.495 |
Lite | +3.359 |
Neg logit contributions | |
asi | -4.522 |
wen | -4.486 |
terness | -4.325 |
selage | -4.317 |
ascus | -4.239 |
Token | gain |
Token ID | 4461 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
asi | +1.599 |
wen | +1.582 |
selage | +1.491 |
terness | +1.481 |
abad | +1.445 |
Neg logit contributions | |
izoph | -1.517 |
iris | -1.452 |
stadt | -1.425 |
Afric | -1.384 |
Lite | -1.296 |
Token | some |
Token ID | 617 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
izoph | +0.371 |
iris | +0.356 |
stadt | +0.349 |
Afric | +0.338 |
Lite | +0.318 |
Neg logit contributions | |
asi | -0.401 |
wen | -0.397 |
selage | -0.376 |
terness | -0.374 |
abad | -0.364 |
Token | b |
Token ID | 275 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
izoph | +0.655 |
iris | +0.629 |
stadt | +0.616 |
Afric | +0.598 |
Lite | +0.562 |
Neg logit contributions | |
asi | -0.711 |
wen | -0.704 |
selage | -0.667 |
terness | -0.664 |
abad | -0.645 |
Token | iz |
Token ID | 528 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
asi | +1.457 |
wen | +1.438 |
selage | +1.322 |
terness | +1.308 |
abad | +1.278 |
Neg logit contributions | |
izoph | -2.250 |
iris | -2.176 |
stadt | -2.147 |
Afric | -2.122 |
Lite | -2.007 |
Token | arro |
Token ID | 34852 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
asi | +0.564 |
wen | +0.556 |
selage | +0.519 |
terness | +0.517 |
abad | +0.499 |
Neg logit contributions | |
izoph | -0.750 |
iris | -0.722 |
stadt | -0.712 |
Afric | -0.694 |
Lite | -0.657 |
Token | dé |
Token ID | 39073 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
izoph | +0.350 |
iris | +0.337 |
stadt | +0.330 |
Afric | +0.320 |
Lite | +0.301 |
Neg logit contributions | |
asi | -0.389 |
wen | -0.384 |
selage | -0.366 |
terness | -0.364 |
abad | -0.353 |
Token | j |
Token ID | 73 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
izoph | +0.127 |
iris | +0.122 |
stadt | +0.120 |
Afric | +0.116 |
flakes | +0.110 |
Neg logit contributions | |
asi | -0.121 |
wen | -0.120 |
selage | -0.113 |
terness | -0.112 |
abad | -0.109 |
Token | à |
Token ID | 24247 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
izoph | +2.786 |
iris | +2.767 |
stadt | +2.618 |
Afric | +2.608 |
flakes | +2.494 |
Neg logit contributions | |
wen | -1.799 |
asi | -1.782 |
terness | -1.702 |
selage | -1.671 |
ascus | -1.595 |
Token | v |
Token ID | 410 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
iris | +4.042 |
izoph | +3.256 |
Afric | +2.956 |
Lite | +2.918 |
stadt | +2.706 |
Neg logit contributions | |
wen | -13.523 |
selage | -13.099 |
ascus | -13.037 |
asi | -13.010 |
terness | -12.921 |
Token | u |
Token ID | 84 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
iris | +6.319 |
izoph | +6.135 |
stadt | +5.925 |
Lite | +5.666 |
Afric | +5.506 |
Neg logit contributions | |
terness | -6.003 |
wen | -5.881 |
selage | -5.871 |
asi | -5.855 |
ascus | -5.668 |
Token | — |
Token ID | 960 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
izoph | +2.523 |
iris | +2.443 |
stadt | +2.402 |
Afric | +2.329 |
flakes | +2.234 |
Neg logit contributions | |
asi | -2.684 |
wen | -2.663 |
selage | -2.528 |
terness | -2.513 |
ascus | -2.429 |
Token | that |
Token ID | 5562 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
izoph | +0.849 |
iris | +0.825 |
stadt | +0.809 |
Afric | +0.783 |
Lite | +0.744 |
Neg logit contributions | |
asi | -0.749 |
wen | -0.738 |
selage | -0.701 |
terness | -0.694 |
ascus | -0.672 |
Token | rare |
Token ID | 4071 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
asi | +1.021 |
wen | +1.010 |
terness | +0.951 |
selage | +0.948 |
abad | +0.924 |
Neg logit contributions | |
izoph | -1.000 |
iris | -0.957 |
stadt | -0.936 |
Afric | -0.909 |
Lite | -0.850 |
Token | ) |
Token ID | 8 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
izoph | +1.601 |
iris | +1.582 |
stadt | +1.566 |
Afric | +1.495 |
Lite | +1.440 |
Neg logit contributions | |
asi | -1.662 |
wen | -1.641 |
terness | -1.619 |
selage | -1.583 |
aution | -1.582 |
Token | ( |
Token ID | 357 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
asi | +1.466 |
wen | +1.448 |
selage | +1.347 |
terness | +1.329 |
abad | +1.312 |
Neg logit contributions | |
izoph | -1.745 |
iris | -1.670 |
stadt | -1.630 |
Afric | -1.590 |
flakes | -1.502 |
Token | 17 |
Token ID | 1558 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
izoph | +0.497 |
iris | +0.486 |
stadt | +0.477 |
Afric | +0.458 |
Lite | +0.435 |
Neg logit contributions | |
asi | -0.512 |
wen | -0.506 |
terness | -0.486 |
selage | -0.483 |
ascus | -0.469 |
Token | ) |
Token ID | 8 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
izoph | +2.110 |
iris | +2.104 |
stadt | +2.086 |
Afric | +1.982 |
Lite | +1.925 |
Neg logit contributions | |
asi | -2.299 |
wen | -2.269 |
terness | -2.263 |
aution | -2.233 |
ascus | -2.214 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
asi | +0.060 |
wen | +0.059 |
selage | +0.056 |
terness | +0.056 |
abad | +0.054 |
Neg logit contributions | |
izoph | -0.054 |
iris | -0.051 |
stadt | -0.050 |
Afric | -0.049 |
flakes | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
asi | +0.121 |
wen | +0.120 |
selage | +0.114 |
terness | +0.114 |
ascus | +0.111 |
Neg logit contributions | |
izoph | -0.105 |
iris | -0.101 |
stadt | -0.099 |
Afric | -0.095 |
Lite | -0.090 |
Token | 9 |
Token ID | 24 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
stadt | +7.221 |
iris | +6.955 |
izoph | +6.953 |
Afric | +6.586 |
Reaper | +6.351 |
Neg logit contributions | |
terness | -9.078 |
asi | -9.043 |
selage | -8.933 |
wen | -8.642 |
aution | -8.531 |
Token | . |
Token ID | 13 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
izoph | +0.980 |
iris | +0.953 |
stadt | +0.947 |
Afric | +0.910 |
Lite | +0.875 |
Neg logit contributions | |
asi | -1.033 |
wen | -1.019 |
terness | -0.989 |
selage | -0.976 |
ascus | -0.960 |
Token | Ali |
Token ID | 12104 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
asi | +0.401 |
wen | +0.396 |
selage | +0.371 |
terness | +0.369 |
abad | +0.359 |
Neg logit contributions | |
izoph | -0.465 |
iris | -0.447 |
stadt | -0.438 |
Afric | -0.426 |
flakes | -0.403 |
Token | Price |
Token ID | 7886 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
asi | +0.701 |
wen | +0.690 |
selage | +0.634 |
terness | +0.629 |
abad | +0.604 |
Neg logit contributions | |
izoph | -1.314 |
iris | -1.274 |
stadt | -1.255 |
Afric | -1.227 |
flakes | -1.173 |
Token | ( |
Token ID | 357 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
asi | +0.662 |
wen | +0.655 |
selage | +0.617 |
terness | +0.615 |
abad | +0.595 |
Neg logit contributions | |
izoph | -0.727 |
iris | -0.701 |
stadt | -0.688 |
Afric | -0.669 |
Lite | -0.632 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
izoph | +0.571 |
iris | +0.553 |
stadt | +0.546 |
Afric | +0.531 |
Lite | +0.505 |
Neg logit contributions | |
asi | -0.411 |
wen | -0.406 |
terness | -0.380 |
selage | -0.378 |
ascus | -0.362 |
Token | { |
Token ID | 1391 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
izoph | +1.538 |
iris | +1.493 |
stadt | +1.465 |
Afric | +1.450 |
Lite | +1.383 |
Neg logit contributions | |
asi | -1.276 |
wen | -1.267 |
terness | -1.200 |
selage | -1.190 |
ascus | -1.156 |
Token | ( |
Token ID | 7 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
asi | +0.861 |
wen | +0.853 |
selage | +0.790 |
terness | +0.779 |
abad | +0.763 |
Neg logit contributions | |
izoph | -1.198 |
iris | -1.153 |
stadt | -1.133 |
Afric | -1.108 |
flakes | -1.051 |
Token | 106 |
Token ID | 15801 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
asi | +0.802 |
wen | +0.792 |
selage | +0.740 |
terness | +0.735 |
abad | +0.715 |
Neg logit contributions | |
izoph | -1.004 |
iris | -0.964 |
stadt | -0.946 |
Afric | -0.922 |
flakes | -0.875 |
Token | s |
Token ID | 82 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
iris | +3.226 |
izoph | +3.188 |
stadt | +3.169 |
Afric | +3.016 |
Lite | +2.892 |
Neg logit contributions | |
asi | -3.547 |
wen | -3.508 |
terness | -3.503 |
selage | -3.450 |
aution | -3.432 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
izoph | +1.915 |
iris | +1.873 |
stadt | +1.831 |
Afric | +1.730 |
Lite | +1.666 |
Neg logit contributions | |
asi | -2.433 |
wen | -2.403 |
terness | -2.336 |
ascus | -2.312 |
selage | -2.304 |
Token | 19 |
Token ID | 678 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Afric | +4.887 |
izoph | +4.865 |
iris | +4.809 |
Kuro | +4.622 |
stadt | +4.583 |
Neg logit contributions | |
wen | -11.446 |
asi | -11.372 |
ascus | -10.979 |
selage | -10.970 |
terness | -10.906 |
Token | . |
Token ID | 13 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
izoph | +0.730 |
iris | +0.712 |
stadt | +0.700 |
Afric | +0.675 |
Lite | +0.644 |
Neg logit contributions | |
asi | -0.758 |
wen | -0.750 |
terness | -0.725 |
selage | -0.713 |
ascus | -0.701 |
Token | Q |
Token ID | 1195 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
izoph | +0.403 |
iris | +0.387 |
stadt | +0.379 |
Afric | +0.370 |
flakes | +0.346 |
Neg logit contributions | |
asi | -0.455 |
wen | -0.452 |
selage | -0.428 |
terness | -0.428 |
ascus | -0.414 |
Token | e |
Token ID | 68 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
izoph | +0.113 |
iris | +0.109 |
stadt | +0.107 |
Afric | +0.103 |
flakes | +0.097 |
Neg logit contributions | |
asi | -0.109 |
wen | -0.108 |
selage | -0.102 |
terness | -0.101 |
abad | -0.098 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
asi | +0.933 |
wen | +0.918 |
selage | +0.855 |
terness | +0.836 |
abad | +0.830 |
Neg logit contributions | |
izoph | -1.339 |
iris | -1.285 |
stadt | -1.260 |
Afric | -1.236 |
flakes | -1.175 |
Token | 7 |
Token ID | 22 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
asi | +0.996 |
wen | +0.988 |
selage | +0.917 |
terness | +0.898 |
abad | +0.886 |
Neg logit contributions | |
izoph | -1.280 |
iris | -1.226 |
stadt | -1.204 |
Afric | -1.179 |
flakes | -1.119 |
Token | { |
Token ID | 1391 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
izoph | +0.782 |
iris | +0.759 |
stadt | +0.744 |
Afric | +0.730 |
Lite | +0.698 |
Neg logit contributions | |
asi | -0.615 |
wen | -0.608 |
terness | -0.574 |
selage | -0.571 |
ascus | -0.557 |
Token | ( |
Token ID | 7 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
asi | +1.575 |
wen | +1.570 |
selage | +1.427 |
abad | +1.396 |
terness | +1.382 |
Neg logit contributions | |
izoph | -2.367 |
iris | -2.265 |
stadt | -2.222 |
Afric | -2.189 |
flakes | -2.074 |
Token | 17 |
Token ID | 1558 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
asi | +0.600 |
wen | +0.593 |
selage | +0.555 |
terness | +0.552 |
abad | +0.536 |
Neg logit contributions | |
izoph | -0.721 |
iris | -0.693 |
stadt | -0.680 |
Afric | -0.662 |
flakes | -0.627 |
Token | s |
Token ID | 82 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
izoph | +2.272 |
iris | +2.203 |
stadt | +2.173 |
Afric | +2.105 |
Lite | +2.002 |
Neg logit contributions | |
asi | -2.205 |
wen | -2.185 |
selage | -2.093 |
terness | -2.077 |
ascus | -2.010 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
izoph | +0.999 |
iris | +0.968 |
stadt | +0.947 |
Afric | +0.905 |
Lite | +0.863 |
Neg logit contributions | |
asi | -1.170 |
wen | -1.157 |
terness | -1.110 |
selage | -1.103 |
ascus | -1.087 |
Token | 27 |
Token ID | 2681 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
izoph | +5.755 |
iris | +5.649 |
Reaper | +5.573 |
Afric | +5.465 |
Kuro | +5.374 |
Neg logit contributions | |
wen | -10.490 |
asi | -10.461 |
ascus | -10.212 |
selage | -10.142 |
terness | -9.969 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
izoph | +1.234 |
iris | +1.200 |
stadt | +1.184 |
Afric | +1.142 |
Lite | +1.094 |
Neg logit contributions | |
asi | -1.332 |
wen | -1.318 |
terness | -1.286 |
selage | -1.260 |
aution | -1.247 |
Token | R |
Token ID | 371 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
izoph | +0.893 |
iris | +0.860 |
stadt | +0.844 |
Afric | +0.828 |
Lite | +0.775 |
Neg logit contributions | |
asi | -0.944 |
wen | -0.937 |
selage | -0.888 |
terness | -0.888 |
ascus | -0.858 |
Token | xd |
Token ID | 24954 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
izoph | +2.528 |
iris | +2.463 |
stadt | +2.415 |
Afric | +2.332 |
flakes | +2.196 |
Neg logit contributions | |
asi | -2.369 |
wen | -2.354 |
terness | -2.272 |
selage | -2.241 |
ascus | -2.163 |
Token | 8 |
Token ID | 23 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
asi | +0.750 |
wen | +0.741 |
selage | +0.690 |
terness | +0.681 |
abad | +0.664 |
Neg logit contributions | |
izoph | -1.070 |
iris | -1.031 |
stadt | -1.012 |
Afric | -0.989 |
flakes | -0.941 |
Token | Bon |
Token ID | 7979 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
izoph | +1.783 |
iris | +1.741 |
stadt | +1.726 |
Afric | +1.669 |
Lite | +1.601 |
Neg logit contributions | |
asi | -1.793 |
wen | -1.791 |
terness | -1.741 |
selage | -1.704 |
ascus | -1.686 |
Token | net |
Token ID | 3262 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
izoph | +1.951 |
iris | +1.893 |
stadt | +1.852 |
Afric | +1.791 |
Lite | +1.685 |
Neg logit contributions | |
asi | -1.892 |
wen | -1.887 |
selage | -1.792 |
terness | -1.785 |
ascus | -1.733 |
Token | ( |
Token ID | 357 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
izoph | +2.917 |
iris | +2.900 |
stadt | +2.855 |
Afric | +2.750 |
Lite | +2.613 |
Neg logit contributions | |
asi | -2.985 |
wen | -2.970 |
selage | -2.883 |
terness | -2.819 |
ascus | -2.784 |
Token | Equ |
Token ID | 23588 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
izoph | +1.307 |
iris | +1.259 |
stadt | +1.231 |
Afric | +1.194 |
Lite | +1.124 |
Neg logit contributions | |
asi | -1.372 |
wen | -1.358 |
selage | -1.287 |
terness | -1.283 |
abad | -1.244 |
Token | ipe |
Token ID | 3757 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
iris | +4.207 |
izoph | +4.115 |
stadt | +3.941 |
Lite | +3.553 |
Afric | +3.544 |
Neg logit contributions | |
terness | -4.631 |
wen | -4.524 |
asi | -4.382 |
aution | -4.331 |
selage | -4.240 |
Token | Cycl |
Token ID | 28007 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
izoph | +2.922 |
iris | +2.861 |
stadt | +2.816 |
Afric | +2.806 |
Lite | +2.694 |
Neg logit contributions | |
asi | -2.704 |
wen | -2.689 |
terness | -2.644 |
selage | -2.578 |
ascus | -2.535 |
Token | iste |
Token ID | 40833 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
iris | +2.276 |
stadt | +2.153 |
izoph | +1.936 |
Lite | +1.393 |
oche | +1.139 |
Neg logit contributions | |
aution | -14.282 |
terness | -14.051 |
wen | -13.529 |
asi | -13.350 |
Leban | -13.217 |
Token | FD |
Token ID | 30002 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
asi | +3.152 |
wen | +3.123 |
selage | +2.960 |
terness | +2.911 |
abad | +2.903 |
Neg logit contributions | |
izoph | -1.866 |
iris | -1.734 |
stadt | -1.685 |
Afric | -1.575 |
flakes | -1.469 |
Token | J |
Token ID | 41 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
iris | +3.537 |
izoph | +3.478 |
stadt | +3.432 |
Lite | +3.267 |
Afric | +3.190 |
Neg logit contributions | |
aution | -4.368 |
terness | -4.367 |
asi | -4.283 |
ascus | -4.280 |
wen | -4.256 |
Token | - |
Token ID | 532 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
asi | +0.206 |
wen | +0.203 |
selage | +0.192 |
terness | +0.192 |
ascus | +0.186 |
Neg logit contributions | |
izoph | -0.217 |
iris | -0.209 |
stadt | -0.206 |
Afric | -0.200 |
Lite | -0.189 |
Token | Big |
Token ID | 4403 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
izoph | +1.703 |
iris | +1.638 |
stadt | +1.591 |
Afric | +1.558 |
Lite | +1.463 |
Neg logit contributions | |
asi | -2.243 |
wen | -2.227 |
selage | -2.131 |
terness | -2.129 |
ascus | -2.059 |
Token | incorporates |
Token ID | 33181 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
izoph | +2.195 |
iris | +2.112 |
stadt | +2.087 |
Afric | +2.010 |
Lite | +1.959 |
Neg logit contributions | |
asi | -2.520 |
wen | -2.483 |
terness | -2.400 |
selage | -2.388 |
ascus | -2.289 |
Token | the |
Token ID | 262 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
izoph | +1.502 |
iris | +1.438 |
stadt | +1.418 |
Afric | +1.371 |
Lite | +1.309 |
Neg logit contributions | |
asi | -1.779 |
wen | -1.763 |
terness | -1.685 |
selage | -1.682 |
abad | -1.622 |
Token | next |
Token ID | 1306 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
izoph | +1.819 |
iris | +1.752 |
stadt | +1.719 |
Afric | +1.661 |
Lite | +1.585 |
Neg logit contributions | |
asi | -2.144 |
wen | -2.131 |
terness | -2.034 |
selage | -2.030 |
abad | -1.953 |
Token | - |
Token ID | 12 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
izoph | +3.135 |
iris | +3.074 |
stadt | +2.962 |
Afric | +2.798 |
Lite | +2.719 |
Neg logit contributions | |
asi | -5.196 |
wen | -5.145 |
terness | -5.058 |
selage | -4.960 |
abad | -4.833 |
Token | generation |
Token ID | 20158 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
iris | +3.197 |
izoph | +3.195 |
stadt | +3.093 |
Afric | +2.916 |
Lite | +2.792 |
Neg logit contributions | |
asi | -4.056 |
wen | -4.038 |
terness | -3.927 |
selage | -3.894 |
abad | -3.746 |
Token | Twin |
Token ID | 14968 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
izoph | +0.955 |
iris | +0.917 |
stadt | +0.902 |
Afric | +0.873 |
Lite | +0.829 |
Neg logit contributions | |
asi | -1.034 |
wen | -1.025 |
selage | -0.973 |
terness | -0.970 |
abad | -0.939 |
Token | Fro |
Token ID | 9734 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
izoph | +3.531 |
stadt | +3.263 |
iris | +3.173 |
Lite | +3.012 |
Afric | +2.835 |
Neg logit contributions | |
wen | -12.405 |
asi | -12.352 |
terness | -12.134 |
selage | -12.016 |
essen | -11.938 |
Token | z |
Token ID | 89 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
izoph | +1.730 |
iris | +1.685 |
stadt | +1.673 |
Afric | +1.573 |
Lite | +1.532 |
Neg logit contributions | |
asi | -1.605 |
wen | -1.581 |
terness | -1.520 |
selage | -1.498 |
ascus | -1.474 |
Token | r |
Token ID | 81 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
izoph | +0.609 |
iris | +0.595 |
stadt | +0.583 |
Afric | +0.556 |
Lite | +0.534 |
Neg logit contributions | |
asi | -0.575 |
wen | -0.565 |
terness | -0.537 |
selage | -0.536 |
ascus | -0.520 |
Token | IV |
Token ID | 8363 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
asi | +1.461 |
wen | +1.433 |
selage | +1.322 |
terness | +1.320 |
abad | +1.285 |
Neg logit contributions | |
izoph | -2.262 |
iris | -2.183 |
stadt | -2.146 |
Afric | -2.095 |
flakes | -1.977 |
Token | Thermal |
Token ID | 41590 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
izoph | +1.631 |
iris | +1.563 |
stadt | +1.537 |
Afric | +1.487 |
Lite | +1.431 |
Neg logit contributions | |
asi | -1.928 |
wen | -1.915 |
selage | -1.823 |
terness | -1.812 |
abad | -1.755 |
Token | � |
Token ID | 229 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
izoph | +4.393 |
iris | +4.269 |
stadt | +4.214 |
Afric | +4.005 |
Lite | +3.700 |
Neg logit contributions | |
asi | -6.514 |
wen | -6.505 |
terness | -6.350 |
selage | -6.227 |
abad | -6.142 |
Token | а |
Token ID | 16142 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
asi | +0.087 |
wen | +0.085 |
selage | +0.080 |
terness | +0.079 |
abad | +0.077 |
Neg logit contributions | |
izoph | -0.116 |
iris | -0.112 |
stadt | -0.110 |
Afric | -0.107 |
flakes | -0.102 |
Token | с |
Token ID | 21727 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
izoph | +0.441 |
iris | +0.428 |
stadt | +0.421 |
Afric | +0.412 |
Lite | +0.393 |
Neg logit contributions | |
asi | -0.262 |
wen | -0.259 |
selage | -0.240 |
terness | -0.239 |
abad | -0.229 |
Token | т |
Token ID | 20375 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
asi | +0.574 |
wen | +0.565 |
selage | +0.516 |
terness | +0.515 |
abad | +0.497 |
Neg logit contributions | |
izoph | -1.032 |
iris | -1.000 |
stadt | -0.984 |
Afric | -0.964 |
flakes | -0.920 |
Token | у |
Token ID | 35072 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
izoph | +2.049 |
iris | +1.992 |
stadt | +1.956 |
Afric | +1.909 |
Lite | +1.817 |
Neg logit contributions | |
asi | -1.493 |
wen | -1.491 |
selage | -1.400 |
terness | -1.394 |
ascus | -1.332 |
Token | � |
Token ID | 141 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
izoph | +3.743 |
iris | +3.639 |
stadt | +3.573 |
Afric | +3.512 |
Lite | +3.349 |
Neg logit contributions | |
wen | -2.718 |
asi | -2.712 |
terness | -2.574 |
selage | -2.561 |
ascus | -2.458 |
Token | � |
Token ID | 236 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
izoph | +6.033 |
stadt | +6.025 |
iris | +5.945 |
Afric | +5.531 |
Lite | +5.218 |
Neg logit contributions | |
wen | -9.819 |
asi | -9.618 |
terness | -9.328 |
selage | -9.314 |
ascus | -9.294 |
Token | � |
Token ID | 12466 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
izoph | +0.017 |
iris | +0.016 |
stadt | +0.016 |
Afric | +0.015 |
flakes | +0.015 |
Neg logit contributions | |
asi | -0.014 |
wen | -0.014 |
selage | -0.013 |
terness | -0.013 |
abad | -0.013 |
Token | � |
Token ID | 122 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
asi | +0.181 |
wen | +0.179 |
selage | +0.170 |
terness | +0.169 |
abad | +0.165 |
Neg logit contributions | |
izoph | -0.137 |
iris | -0.131 |
stadt | -0.128 |
Afric | -0.123 |
flakes | -0.115 |
Token | к |
Token ID | 31583 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
asi | +0.318 |
wen | +0.314 |
selage | +0.293 |
terness | +0.292 |
abad | +0.282 |
Neg logit contributions | |
izoph | -0.428 |
iris | -0.414 |
stadt | -0.407 |
Afric | -0.396 |
flakes | -0.376 |
Token | а |
Token ID | 16142 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
asi | +1.843 |
wen | +1.801 |
selage | +1.673 |
terness | +1.649 |
abad | +1.620 |
Neg logit contributions | |
izoph | -2.644 |
iris | -2.563 |
stadt | -2.506 |
Afric | -2.460 |
Lite | -2.338 |
Token | st |
Token ID | 336 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
izoph | +1.890 |
iris | +1.825 |
stadt | +1.790 |
Afric | +1.738 |
flakes | +1.691 |
Neg logit contributions | |
asi | -2.109 |
wen | -2.066 |
terness | -1.987 |
selage | -1.979 |
abad | -1.906 |
Token | on |
Token ID | 261 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
izoph | +1.519 |
iris | +1.471 |
stadt | +1.446 |
Afric | +1.390 |
flakes | +1.328 |
Neg logit contributions | |
asi | -1.337 |
wen | -1.319 |
terness | -1.255 |
selage | -1.253 |
abad | -1.202 |
Token | ework |
Token ID | 6433 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
izoph | +2.412 |
iris | +2.359 |
stadt | +2.319 |
Afric | +2.214 |
flakes | +2.156 |
Neg logit contributions | |
asi | -1.759 |
wen | -1.718 |
terness | -1.611 |
selage | -1.598 |
abad | -1.574 |
Token | with |
Token ID | 351 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
izoph | +2.026 |
iris | +1.964 |
stadt | +1.920 |
Afric | +1.860 |
flakes | +1.814 |
Neg logit contributions | |
asi | -2.151 |
wen | -2.125 |
selage | -2.026 |
terness | -2.012 |
abad | -1.975 |
Token | Val |
Token ID | 3254 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
izoph | +0.696 |
iris | +0.668 |
stadt | +0.653 |
Afric | +0.636 |
flakes | +0.598 |
Neg logit contributions | |
asi | -0.790 |
wen | -0.783 |
selage | -0.745 |
terness | -0.741 |
abad | -0.719 |
Token | le |
Token ID | 293 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
asi | +0.708 |
wen | +0.696 |
selage | +0.644 |
terness | +0.636 |
ascus | +0.624 |
Neg logit contributions | |
izoph | -0.831 |
iris | -0.789 |
stadt | -0.783 |
Afric | -0.765 |
flakes | -0.720 |
Token | jo |
Token ID | 7639 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
iris | +8.044 |
stadt | +7.758 |
izoph | +7.704 |
Afric | +7.596 |
Lite | +7.209 |
Neg logit contributions | |
asi | -7.690 |
terness | -7.566 |
selage | -7.507 |
wen | -7.480 |
aution | -7.241 |
Token | black |
Token ID | 2042 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
asi | +0.471 |
wen | +0.467 |
selage | +0.440 |
terness | +0.438 |
abad | +0.427 |
Neg logit contributions | |
izoph | -0.432 |
iris | -0.414 |
stadt | -0.406 |
Afric | -0.393 |
flakes | -0.368 |
Token | brown |
Token ID | 7586 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
izoph | +2.179 |
iris | +2.114 |
stadt | +2.073 |
Afric | +1.993 |
flakes | +1.928 |
Neg logit contributions | |
asi | -2.239 |
wen | -2.206 |
selage | -2.111 |
terness | -2.103 |
abad | -2.017 |
Token | to |
Token ID | 284 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
izoph | +2.123 |
iris | +2.067 |
stadt | +2.024 |
Afric | +1.945 |
flakes | +1.894 |
Neg logit contributions | |
asi | -2.199 |
wen | -2.166 |
selage | -2.077 |
terness | -2.066 |
abad | -1.987 |
Token | pick |
Token ID | 2298 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
izoph | +2.075 |
iris | +2.007 |
stadt | +1.950 |
Afric | +1.891 |
flakes | +1.825 |
Neg logit contributions | |
asi | -2.466 |
wen | -2.430 |
selage | -2.353 |
terness | -2.328 |
abad | -2.291 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
asi | +2.527 |
wen | +2.475 |
selage | +2.259 |
abad | +2.259 |
terness | +2.254 |
Neg logit contributions | |
izoph | -2.967 |
iris | -2.780 |
stadt | -2.711 |
Afric | -2.621 |
Reaper | -2.468 |
Token |
|
Token ID | 198 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
asi | +1.364 |
wen | +1.346 |
selage | +1.266 |
terness | +1.261 |
abad | +1.238 |
Neg logit contributions | |
izoph | -1.293 |
iris | -1.231 |
stadt | -1.200 |
Afric | -1.156 |
flakes | -1.100 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
izoph | +0.395 |
iris | +0.382 |
stadt | +0.375 |
Afric | +0.360 |
Lite | +0.340 |
Neg logit contributions | |
asi | -0.480 |
wen | -0.474 |
terness | -0.456 |
selage | -0.453 |
ascus | -0.443 |
Token | -- |
Token ID | 438 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
asi | +0.134 |
wen | +0.132 |
selage | +0.124 |
terness | +0.123 |
abad | +0.121 |
Neg logit contributions | |
izoph | -0.134 |
iris | -0.129 |
stadt | -0.126 |
Afric | -0.123 |
flakes | -0.116 |
Token | David |
Token ID | 3271 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
izoph | +2.342 |
iris | +2.265 |
stadt | +2.234 |
Afric | +2.167 |
Lite | +2.064 |
Neg logit contributions | |
asi | -2.408 |
wen | -2.365 |
selage | -2.272 |
terness | -2.254 |
ascus | -2.206 |
Token | Goldman |
Token ID | 18740 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
izoph | +4.036 |
stadt | +3.993 |
Afric | +3.921 |
iris | +3.915 |
Lite | +3.782 |
Neg logit contributions | |
asi | -4.397 |
terness | -4.279 |
wen | -4.248 |
selage | -4.176 |
ascus | -4.170 |
Token | contributed |
Token ID | 8639 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
stadt | +6.736 |
iris | +6.457 |
izoph | +6.103 |
Afric | +5.834 |
Lite | +5.806 |
Neg logit contributions | |
asi | -9.041 |
wen | -9.003 |
terness | -8.953 |
selage | -8.737 |
ascus | -8.571 |
Token | reporting |
Token ID | 6447 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
asi | +0.837 |
wen | +0.831 |
selage | +0.779 |
terness | +0.770 |
abad | +0.752 |
Neg logit contributions | |
izoph | -0.925 |
iris | -0.888 |
stadt | -0.859 |
Afric | -0.847 |
flakes | -0.791 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
izoph | +2.715 |
stadt | +2.676 |
iris | +2.667 |
Afric | +2.558 |
Lite | +2.451 |
Neg logit contributions | |
asi | -3.127 |
wen | -3.071 |
terness | -2.967 |
selage | -2.932 |
ascus | -2.862 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
izoph | +1.235 |
iris | +1.192 |
stadt | +1.169 |
Afric | +1.127 |
Lite | +1.053 |
Neg logit contributions | |
asi | -1.612 |
wen | -1.592 |
selage | -1.523 |
terness | -1.513 |
ascus | -1.480 |
Token | Media |
Token ID | 13152 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
izoph | +0.190 |
iris | +0.182 |
stadt | +0.179 |
Afric | +0.174 |
flakes | +0.164 |
Neg logit contributions | |
asi | -0.177 |
wen | -0.175 |
selage | -0.165 |
terness | -0.164 |
abad | -0.159 |
Token | are |
Token ID | 389 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
asi | +1.491 |
wen | +1.479 |
terness | +1.379 |
selage | +1.379 |
abad | +1.345 |
Neg logit contributions | |
izoph | -1.511 |
iris | -1.422 |
stadt | -1.396 |
Afric | -1.356 |
flakes | -1.271 |
Token | often |
Token ID | 1690 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
asi | +0.462 |
wen | +0.457 |
selage | +0.431 |
terness | +0.429 |
abad | +0.418 |
Neg logit contributions | |
izoph | -0.440 |
iris | -0.422 |
stadt | -0.413 |
Afric | -0.400 |
Lite | -0.376 |
Token | disliked |
Token ID | 43252 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
asi | +0.273 |
wen | +0.270 |
selage | +0.255 |
terness | +0.254 |
abad | +0.247 |
Neg logit contributions | |
izoph | -0.269 |
iris | -0.258 |
stadt | -0.253 |
Afric | -0.246 |
flakes | -0.231 |
Token | - |
Token ID | 532 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
izoph | +0.751 |
iris | +0.725 |
stadt | +0.710 |
Afric | +0.690 |
flakes | +0.654 |
Neg logit contributions | |
asi | -0.730 |
wen | -0.721 |
selage | -0.683 |
terness | -0.678 |
abad | -0.659 |
Token | in |
Token ID | 287 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
izoph | +0.297 |
iris | +0.286 |
stadt | +0.280 |
Afric | +0.272 |
flakes | +0.256 |
Neg logit contributions | |
asi | -0.313 |
wen | -0.309 |
selage | -0.293 |
terness | -0.291 |
abad | -0.283 |
Token | CS |
Token ID | 9429 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
izoph | +1.550 |
iris | +1.483 |
stadt | +1.466 |
Afric | +1.425 |
Lite | +1.345 |
Neg logit contributions | |
asi | -1.708 |
wen | -1.690 |
selage | -1.617 |
terness | -1.609 |
ascus | -1.555 |
Token | , |
Token ID | 11 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
izoph | +6.838 |
iris | +6.489 |
stadt | +6.304 |
Lite | +6.169 |
Afric | +6.161 |
Neg logit contributions | |
wen | -8.554 |
asi | -8.482 |
selage | -8.451 |
terness | -8.353 |
ascus | -8.170 |
Token | they |
Token ID | 484 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
izoph | +2.354 |
iris | +2.264 |
stadt | +2.227 |
Afric | +2.191 |
Lite | +2.074 |
Neg logit contributions | |
asi | -2.683 |
wen | -2.648 |
selage | -2.564 |
terness | -2.547 |
ascus | -2.457 |
Token | are |
Token ID | 389 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
izoph | +0.278 |
iris | +0.268 |
stadt | +0.261 |
Afric | +0.253 |
flakes | +0.240 |
Neg logit contributions | |
asi | -0.327 |
wen | -0.324 |
selage | -0.309 |
terness | -0.307 |
abad | -0.298 |
Token | players |
Token ID | 1938 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
izoph | +1.761 |
iris | +1.702 |
stadt | +1.665 |
Afric | +1.631 |
flakes | +1.560 |
Neg logit contributions | |
asi | -1.919 |
wen | -1.903 |
selage | -1.827 |
terness | -1.810 |
abad | -1.754 |
Token | ' |
Token ID | 6 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
asi | +1.550 |
wen | +1.528 |
terness | +1.427 |
selage | +1.425 |
abad | +1.386 |
Neg logit contributions | |
izoph | -1.656 |
iris | -1.570 |
stadt | -1.546 |
Afric | -1.502 |
Lite | -1.402 |
Token | � |
Token ID | 564 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
izoph | +0.348 |
iris | +0.334 |
stadt | +0.327 |
Afric | +0.318 |
Lite | +0.299 |
Neg logit contributions | |
asi | -0.366 |
wen | -0.362 |
selage | -0.343 |
terness | -0.341 |
abad | -0.331 |
Token | � |
Token ID | 250 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
izoph | +1.659 |
iris | +1.584 |
stadt | +1.546 |
Afric | +1.490 |
Lite | +1.397 |
Neg logit contributions | |
asi | -2.191 |
wen | -2.172 |
selage | -2.066 |
terness | -2.047 |
ascus | -2.017 |
Token | Ts |
Token ID | 33758 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
izoph | +2.464 |
iris | +2.377 |
stadt | +2.323 |
Afric | +2.262 |
Lite | +2.149 |
Neg logit contributions | |
asi | -2.192 |
wen | -2.165 |
selage | -2.072 |
terness | -2.029 |
abad | -1.976 |
Token | umi |
Token ID | 12994 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
izoph | +1.772 |
iris | +1.728 |
stadt | +1.688 |
Afric | +1.633 |
Lite | +1.565 |
Neg logit contributions | |
asi | -1.056 |
wen | -1.043 |
selage | -0.975 |
terness | -0.960 |
ascus | -0.924 |
Token | no |
Token ID | 645 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
asi | +0.805 |
wen | +0.799 |
selage | +0.750 |
terness | +0.747 |
abad | +0.731 |
Neg logit contributions | |
izoph | -0.770 |
iris | -0.736 |
stadt | -0.722 |
Afric | -0.701 |
flakes | -0.658 |
Token | N |
Token ID | 399 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
izoph | +0.955 |
iris | +0.918 |
stadt | +0.895 |
Afric | +0.871 |
Lite | +0.816 |
Neg logit contributions | |
asi | -1.109 |
wen | -1.098 |
selage | -1.044 |
terness | -1.038 |
abad | -1.009 |
Token | ama |
Token ID | 1689 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
iris | +9.094 |
izoph | +8.680 |
stadt | +8.626 |
Afric | +7.904 |
oche | +7.835 |
Neg logit contributions | |
wen | -6.347 |
selage | -6.210 |
terness | -6.191 |
asi | -6.121 |
ascus | -5.788 |
Token | e |
Token ID | 68 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
izoph | +3.959 |
iris | +3.862 |
stadt | +3.767 |
Afric | +3.663 |
flakes | +3.460 |
Neg logit contributions | |
asi | -3.957 |
wen | -3.917 |
selage | -3.806 |
terness | -3.794 |
abad | -3.619 |
Token | � |
Token ID | 447 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
izoph | +3.407 |
iris | +3.324 |
stadt | +3.223 |
Afric | +3.149 |
Lite | +2.965 |
Neg logit contributions | |
asi | -3.618 |
wen | -3.571 |
selage | -3.482 |
terness | -3.438 |
abad | -3.322 |
Token | � |
Token ID | 251 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
izoph | +1.310 |
iris | +1.252 |
stadt | +1.226 |
Afric | +1.184 |
Lite | +1.113 |
Neg logit contributions | |
asi | -1.552 |
wen | -1.536 |
selage | -1.460 |
terness | -1.443 |
ascus | -1.423 |
Token | by |
Token ID | 416 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
izoph | +0.227 |
iris | +0.219 |
stadt | +0.215 |
Afric | +0.209 |
Lite | +0.197 |
Neg logit contributions | |
asi | -0.201 |
wen | -0.199 |
selage | -0.187 |
terness | -0.186 |
abad | -0.180 |
Token | China |
Token ID | 2807 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
asi | +0.529 |
wen | +0.524 |
selage | +0.496 |
terness | +0.493 |
abad | +0.483 |
Neg logit contributions | |
izoph | -0.418 |
iris | -0.399 |
stadt | -0.390 |
Afric | -0.375 |
flakes | -0.351 |
Token | following |
Token ID | 1708 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
asi | +1.002 |
wen | +0.991 |
selage | +0.935 |
terness | +0.929 |
abad | +0.904 |
Neg logit contributions | |
izoph | -1.022 |
iris | -0.982 |
stadt | -0.963 |
Afric | -0.935 |
flakes | -0.880 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
asi | +1.259 |
wen | +1.250 |
selage | +1.177 |
terness | +1.173 |
abad | +1.148 |
Neg logit contributions | |
izoph | -1.136 |
iris | -1.084 |
stadt | -1.060 |
Afric | -1.025 |
flakes | -0.962 |
Token | " |
Token ID | 366 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
asi | +1.933 |
wen | +1.921 |
selage | +1.795 |
terness | +1.780 |
abad | +1.755 |
Neg logit contributions | |
izoph | -1.835 |
iris | -1.751 |
stadt | -1.714 |
Afric | -1.646 |
flakes | -1.552 |
Token | s |
Token ID | 82 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
izoph | +1.837 |
iris | +1.788 |
stadt | +1.742 |
Afric | +1.689 |
Lite | +1.601 |
Neg logit contributions | |
asi | -1.653 |
wen | -1.628 |
selage | -1.561 |
terness | -1.555 |
abad | -1.493 |
Token | oph |
Token ID | 2522 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
izoph | +2.711 |
iris | +2.629 |
stadt | +2.543 |
Afric | +2.460 |
Lite | +2.340 |
Neg logit contributions | |
asi | -2.499 |
wen | -2.495 |
selage | -2.355 |
terness | -2.353 |
abad | -2.262 |
Token | istic |
Token ID | 2569 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
izoph | +4.843 |
iris | +4.693 |
stadt | +4.179 |
Afric | +3.617 |
Lite | +3.378 |
Neg logit contributions | |
wen | -10.707 |
selage | -10.684 |
asi | -10.423 |
aution | -10.412 |
terness | -10.382 |
Token | ated |
Token ID | 515 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
asi | +0.926 |
wen | +0.908 |
selage | +0.858 |
terness | +0.856 |
abad | +0.834 |
Neg logit contributions | |
izoph | -0.885 |
iris | -0.849 |
stadt | -0.835 |
Afric | -0.812 |
flakes | -0.763 |
Token | and |
Token ID | 290 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
asi | +1.614 |
wen | +1.599 |
selage | +1.495 |
terness | +1.488 |
abad | +1.456 |
Neg logit contributions | |
izoph | -1.729 |
iris | -1.658 |
stadt | -1.623 |
Afric | -1.569 |
flakes | -1.473 |
Token | targeted |
Token ID | 7977 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
asi | +3.147 |
wen | +3.131 |
selage | +2.882 |
terness | +2.856 |
abad | +2.837 |
Neg logit contributions | |
izoph | -3.131 |
iris | -3.012 |
stadt | -2.959 |
Afric | -2.816 |
flakes | -2.640 |
Token | " |
Token ID | 1 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
izoph | +0.070 |
iris | +0.068 |
stadt | +0.066 |
Afric | +0.065 |
Lite | +0.061 |
Neg logit contributions | |
asi | -0.068 |
wen | -0.067 |
selage | -0.064 |
terness | -0.063 |
abad | -0.061 |
Token | w |
Token ID | 266 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
izoph | +0.900 |
iris | +0.876 |
stadt | +0.859 |
Afric | +0.833 |
flakes | +0.790 |
Neg logit contributions | |
asi | -0.983 |
wen | -0.964 |
selage | -0.925 |
terness | -0.918 |
ascus | -0.892 |
Token | alt |
Token ID | 2501 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
izoph | +3.038 |
iris | +2.990 |
stadt | +2.903 |
Afric | +2.815 |
flakes | +2.708 |
Neg logit contributions | |
asi | -2.173 |
wen | -2.139 |
terness | -2.040 |
selage | -2.030 |
ascus | -1.939 |
Token | z |
Token ID | 89 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
izoph | +0.196 |
iris | +0.192 |
stadt | +0.189 |
Afric | +0.185 |
flakes | +0.178 |
Neg logit contributions | |
asi | -0.079 |
wen | -0.077 |
selage | -0.071 |
terness | -0.070 |
abad | -0.066 |
Token | with |
Token ID | 351 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
asi | +1.681 |
wen | +1.671 |
selage | +1.560 |
terness | +1.554 |
abad | +1.515 |
Neg logit contributions | |
izoph | -1.787 |
iris | -1.700 |
stadt | -1.666 |
Afric | -1.619 |
Lite | -1.522 |
Token | you |
Token ID | 345 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
asi | +2.358 |
wen | +2.344 |
selage | +2.179 |
terness | +2.155 |
asm | +2.137 |
Neg logit contributions | |
izoph | -2.476 |
iris | -2.352 |
stadt | -2.310 |
Afric | -2.230 |
Lite | -2.087 |
Token | , |
Token ID | 11 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
asi | +2.656 |
wen | +2.632 |
selage | +2.435 |
terness | +2.423 |
abad | +2.366 |
Neg logit contributions | |
izoph | -3.148 |
iris | -2.959 |
stadt | -2.931 |
Afric | -2.862 |
Lite | -2.678 |
Token | beware |
Token ID | 40600 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
asi | +4.764 |
wen | +4.721 |
selage | +4.328 |
asm | +4.318 |
terness | +4.310 |
Neg logit contributions | |
izoph | -5.102 |
iris | -4.820 |
stadt | -4.715 |
Afric | -4.592 |
Lite | -4.242 |
Token | not |
Token ID | 407 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
asi | +3.592 |
wen | +3.572 |
terness | +3.240 |
selage | +3.228 |
asm | +3.207 |
Neg logit contributions | |
izoph | -4.263 |
iris | -4.077 |
stadt | -3.983 |
Afric | -3.874 |
Lite | -3.629 |
Token | to |
Token ID | 284 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
asi | +3.032 |
wen | +3.001 |
terness | +2.740 |
selage | +2.721 |
asm | +2.717 |
Neg logit contributions | |
izoph | -3.851 |
iris | -3.644 |
stadt | -3.591 |
Afric | -3.475 |
Lite | -3.281 |
Token | press |
Token ID | 1803 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
asi | +3.743 |
wen | +3.715 |
terness | +3.443 |
selage | +3.415 |
asm | +3.400 |
Neg logit contributions | |
izoph | -3.886 |
iris | -3.720 |
stadt | -3.665 |
Afric | -3.517 |
Lite | -3.278 |
Token | her |
Token ID | 607 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
asi | +2.648 |
wen | +2.629 |
terness | +2.448 |
selage | +2.443 |
abad | +2.377 |
Neg logit contributions | |
izoph | -2.977 |
iris | -2.828 |
stadt | -2.791 |
Afric | -2.701 |
Lite | -2.540 |
Token | The |
Token ID | 383 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
asi | +1.046 |
wen | +1.033 |
selage | +0.975 |
terness | +0.971 |
abad | +0.946 |
Neg logit contributions | |
izoph | -0.993 |
iris | -0.953 |
stadt | -0.933 |
Afric | -0.903 |
flakes | -0.851 |
Token | lowest |
Token ID | 9016 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
izoph | +0.583 |
iris | +0.559 |
stadt | +0.548 |
Afric | +0.532 |
flakes | +0.500 |
Neg logit contributions | |
asi | -0.648 |
wen | -0.642 |
selage | -0.611 |
terness | -0.609 |
ascus | -0.590 |
Token | projected |
Token ID | 13301 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
asi | +1.126 |
wen | +1.112 |
selage | +1.047 |
terness | +1.041 |
abad | +1.022 |
Neg logit contributions | |
izoph | -1.073 |
iris | -1.029 |
stadt | -1.004 |
Afric | -0.976 |
Lite | -0.916 |
Token | levels |
Token ID | 2974 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
asi | +0.563 |
wen | +0.557 |
selage | +0.526 |
terness | +0.523 |
abad | +0.510 |
Neg logit contributions | |
izoph | -0.529 |
iris | -0.508 |
stadt | -0.497 |
Afric | -0.482 |
Lite | -0.453 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
asi | +0.976 |
wen | +0.965 |
selage | +0.913 |
terness | +0.908 |
abad | +0.886 |
Neg logit contributions | |
izoph | -0.872 |
iris | -0.834 |
stadt | -0.816 |
Afric | -0.792 |
flakes | -0.741 |
Token | overweight |
Token ID | 22652 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
izoph | +0.870 |
iris | +0.834 |
stadt | +0.820 |
Afric | +0.799 |
flakes | +0.757 |
Neg logit contributions | |
asi | -0.799 |
wen | -0.793 |
selage | -0.751 |
terness | -0.746 |
abad | -0.719 |
Token | and |
Token ID | 290 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
asi | +4.562 |
wen | +4.431 |
terness | +4.096 |
selage | +4.050 |
asm | +4.041 |
Neg logit contributions | |
izoph | -5.349 |
iris | -5.096 |
stadt | -4.932 |
Afric | -4.860 |
Reaper | -4.524 |
Token | obesity |
Token ID | 13825 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
izoph | +0.482 |
iris | +0.467 |
stadt | +0.459 |
Afric | +0.449 |
flakes | +0.429 |
Neg logit contributions | |
asi | -0.290 |
wen | -0.286 |
selage | -0.265 |
terness | -0.263 |
abad | -0.253 |
Token | were |
Token ID | 547 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
asi | +0.280 |
wen | +0.277 |
selage | +0.263 |
terness | +0.261 |
abad | +0.254 |
Neg logit contributions | |
izoph | -0.252 |
iris | -0.242 |
stadt | -0.237 |
Afric | -0.230 |
flakes | -0.216 |
Token | found |
Token ID | 1043 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
asi | +2.192 |
wen | +2.160 |
selage | +2.015 |
terness | +1.999 |
abad | +1.970 |
Neg logit contributions | |
izoph | -2.425 |
iris | -2.334 |
stadt | -2.268 |
Afric | -2.203 |
flakes | -2.085 |
Token | in |
Token ID | 287 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
asi | +1.260 |
wen | +1.244 |
selage | +1.164 |
terness | +1.152 |
abad | +1.134 |
Neg logit contributions | |
izoph | -1.467 |
iris | -1.410 |
stadt | -1.377 |
Afric | -1.340 |
flakes | -1.270 |
Token | asking |
Token ID | 4737 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
asi | +1.874 |
wen | +1.843 |
selage | +1.734 |
terness | +1.726 |
abad | +1.694 |
Neg logit contributions | |
izoph | -1.983 |
iris | -1.911 |
stadt | -1.865 |
Afric | -1.813 |
Lite | -1.696 |
Token | " |
Token ID | 366 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
asi | +0.069 |
wen | +0.068 |
selage | +0.064 |
terness | +0.064 |
abad | +0.062 |
Neg logit contributions | |
izoph | -0.068 |
iris | -0.065 |
stadt | -0.064 |
Afric | -0.062 |
flakes | -0.058 |
Token | when |
Token ID | 12518 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
izoph | +1.211 |
iris | +1.178 |
stadt | +1.148 |
Afric | +1.109 |
Lite | +1.049 |
Neg logit contributions | |
asi | -1.210 |
wen | -1.196 |
selage | -1.139 |
terness | -1.136 |
ascus | -1.098 |
Token | Sam |
Token ID | 3409 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
asi | +1.182 |
wen | +1.164 |
selage | +1.097 |
terness | +1.092 |
abad | +1.068 |
Neg logit contributions | |
izoph | -1.173 |
iris | -1.121 |
stadt | -1.100 |
Afric | -1.064 |
flakes | -0.998 |
Token | Bac |
Token ID | 35583 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
izoph | +0.028 |
iris | +0.027 |
stadt | +0.026 |
Afric | +0.025 |
Lite | +0.024 |
Neg logit contributions | |
asi | -0.027 |
wen | -0.027 |
selage | -0.025 |
terness | -0.025 |
abad | -0.024 |
Token | ile |
Token ID | 576 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
izoph | +0.916 |
iris | +0.878 |
stadt | +0.860 |
Afric | +0.834 |
flakes | +0.784 |
Neg logit contributions | |
asi | -0.981 |
wen | -0.971 |
selage | -0.918 |
terness | -0.914 |
abad | -0.889 |
Token | would |
Token ID | 561 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
asi | +5.100 |
wen | +4.996 |
selage | +4.629 |
terness | +4.520 |
abad | +4.493 |
Neg logit contributions | |
izoph | -5.612 |
iris | -5.218 |
stadt | -5.110 |
Afric | -4.972 |
anooga | -4.624 |
Token | be |
Token ID | 307 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
asi | +1.154 |
wen | +1.143 |
selage | +1.077 |
terness | +1.072 |
abad | +1.044 |
Neg logit contributions | |
izoph | -1.068 |
iris | -1.021 |
stadt | -1.000 |
Afric | -0.970 |
Lite | -0.909 |
Token | arrested |
Token ID | 5169 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
izoph | +0.002 |
iris | +0.002 |
stadt | +0.002 |
Afric | +0.002 |
flakes | +0.002 |
Neg logit contributions | |
asi | -0.002 |
wen | -0.002 |
selage | -0.002 |
terness | -0.002 |
abad | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
izoph | +0.193 |
iris | +0.187 |
stadt | +0.183 |
Afric | +0.178 |
flakes | +0.168 |
Neg logit contributions | |
asi | -0.188 |
wen | -0.186 |
selage | -0.176 |
terness | -0.175 |
abad | -0.169 |
Token | drew |
Token ID | 9859 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
asi | +2.013 |
wen | +1.975 |
selage | +1.855 |
terness | +1.837 |
abad | +1.811 |
Neg logit contributions | |
izoph | -2.186 |
iris | -2.092 |
stadt | -2.051 |
Afric | -1.998 |
Lite | -1.868 |
Token | par |
Token ID | 1582 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
izoph | +0.434 |
iris | +0.415 |
stadt | +0.406 |
Afric | +0.394 |
flakes | +0.371 |
Neg logit contributions | |
asi | -0.479 |
wen | -0.474 |
selage | -0.451 |
terness | -0.447 |
abad | -0.434 |
Token | asy |
Token ID | 4107 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
asi | +3.593 |
wen | +3.511 |
selage | +3.322 |
terness | +3.321 |
asm | +3.320 |
Neg logit contributions | |
izoph | -1.795 |
iris | -1.679 |
Afric | -1.647 |
stadt | -1.646 |
Lite | -1.477 |
Token | mp |
Token ID | 3149 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
asi | +0.315 |
wen | +0.311 |
terness | +0.288 |
selage | +0.288 |
abad | +0.276 |
Neg logit contributions | |
izoph | -0.505 |
iris | -0.490 |
stadt | -0.482 |
Afric | -0.468 |
flakes | -0.448 |
Token | athetic |
Token ID | 18874 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
iris | +4.279 |
izoph | +4.224 |
stadt | +4.002 |
Afric | +3.662 |
oche | +3.589 |
Neg logit contributions | |
wen | -4.141 |
asi | -4.110 |
terness | -3.933 |
aution | -3.893 |
selage | -3.886 |
Token | resting |
Token ID | 19186 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
asi | +2.914 |
wen | +2.870 |
terness | +2.731 |
selage | +2.691 |
abad | +2.662 |
Neg logit contributions | |
izoph | -2.580 |
iris | -2.498 |
stadt | -2.441 |
Afric | -2.383 |
Lite | -2.199 |
Token | tone |
Token ID | 8216 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
asi | +2.121 |
wen | +2.092 |
terness | +1.969 |
selage | +1.954 |
abad | +1.913 |
Neg logit contributions | |
izoph | -2.163 |
iris | -2.076 |
stadt | -2.040 |
Afric | -1.995 |
Lite | -1.858 |
Token | in |
Token ID | 287 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
asi | +4.075 |
wen | +4.029 |
terness | +3.746 |
selage | +3.666 |
asm | +3.644 |
Neg logit contributions | |
izoph | -5.976 |
iris | -5.714 |
stadt | -5.583 |
Afric | -5.533 |
Lite | -5.138 |
Token | the |
Token ID | 262 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
asi | +1.080 |
wen | +1.069 |
selage | +1.008 |
terness | +1.006 |
abad | +0.980 |
Neg logit contributions | |
izoph | -0.958 |
iris | -0.919 |
stadt | -0.899 |
Afric | -0.870 |
Lite | -0.813 |
Token | evening |
Token ID | 6180 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
izoph | +0.672 |
iris | +0.644 |
stadt | +0.629 |
Afric | +0.613 |
flakes | +0.581 |
Neg logit contributions | |
asi | -0.692 |
wen | -0.686 |
selage | -0.653 |
terness | -0.650 |
abad | -0.627 |
Token | during |
Token ID | 1141 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
asi | +1.701 |
wen | +1.685 |
selage | +1.574 |
terness | +1.570 |
abad | +1.529 |
Neg logit contributions | |
izoph | -1.901 |
iris | -1.825 |
stadt | -1.791 |
Afric | -1.745 |
Lite | -1.640 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
izoph | +0.575 |
iris | +0.551 |
stadt | +0.538 |
Afric | +0.522 |
flakes | +0.491 |
Neg logit contributions | |
asi | -0.660 |
wen | -0.653 |
selage | -0.621 |
terness | -0.618 |
abad | -0.600 |
Token | flat |
Token ID | 6228 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
izoph | +0.648 |
iris | +0.623 |
stadt | +0.610 |
Afric | +0.591 |
flakes | +0.558 |
Neg logit contributions | |
asi | -0.714 |
wen | -0.706 |
selage | -0.672 |
terness | -0.665 |
abad | -0.650 |
Token | tered |
Token ID | 4400 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
asi | +1.772 |
wen | +1.760 |
selage | +1.646 |
terness | +1.645 |
abad | +1.596 |
Neg logit contributions | |
izoph | -1.972 |
iris | -1.890 |
stadt | -1.852 |
Afric | -1.807 |
Lite | -1.704 |
Token | by |
Token ID | 416 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
izoph | +0.217 |
iris | +0.210 |
stadt | +0.206 |
Afric | +0.200 |
flakes | +0.190 |
Neg logit contributions | |
asi | -0.205 |
wen | -0.202 |
selage | -0.191 |
terness | -0.190 |
ascus | -0.185 |
Token | the |
Token ID | 262 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
asi | +2.008 |
wen | +1.982 |
selage | +1.854 |
terness | +1.850 |
abad | +1.811 |
Neg logit contributions | |
izoph | -1.962 |
iris | -1.891 |
stadt | -1.836 |
Afric | -1.784 |
flakes | -1.670 |
Token | extreme |
Token ID | 3257 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
asi | +2.373 |
wen | +2.344 |
selage | +2.204 |
terness | +2.187 |
abad | +2.150 |
Neg logit contributions | |
izoph | -2.276 |
iris | -2.200 |
stadt | -2.146 |
Afric | -2.064 |
flakes | -1.920 |
Token | effort |
Token ID | 3626 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
asi | +3.843 |
wen | +3.803 |
terness | +3.602 |
selage | +3.587 |
asm | +3.527 |
Neg logit contributions | |
izoph | -3.716 |
iris | -3.578 |
stadt | -3.437 |
Afric | -3.330 |
Lite | -3.093 |
Token | that |
Token ID | 326 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
asi | +4.761 |
wen | +4.584 |
terness | +4.332 |
selage | +4.286 |
asm | +4.244 |
Neg logit contributions | |
izoph | -5.514 |
iris | -5.273 |
stadt | -4.998 |
Afric | -4.971 |
flakes | -4.634 |
Token | obviously |
Token ID | 6189 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
asi | +2.618 |
wen | +2.570 |
terness | +2.402 |
selage | +2.397 |
abad | +2.378 |
Neg logit contributions | |
izoph | -2.573 |
iris | -2.480 |
stadt | -2.392 |
Afric | -2.339 |
flakes | -2.185 |
Token | went |
Token ID | 1816 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
asi | +3.660 |
wen | +3.532 |
selage | +3.288 |
abad | +3.268 |
terness | +3.251 |
Neg logit contributions | |
izoph | -4.593 |
iris | -4.397 |
Afric | -4.189 |
stadt | -4.170 |
flakes | -3.918 |
Token | into |
Token ID | 656 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
asi | +1.477 |
wen | +1.457 |
selage | +1.367 |
terness | +1.360 |
abad | +1.325 |
Neg logit contributions | |
izoph | -1.599 |
iris | -1.524 |
stadt | -1.492 |
Afric | -1.455 |
Lite | -1.370 |
Token | this |
Token ID | 428 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
asi | +1.913 |
wen | +1.897 |
selage | +1.787 |
terness | +1.777 |
asm | +1.732 |
Neg logit contributions | |
izoph | -1.820 |
iris | -1.751 |
stadt | -1.707 |
Afric | -1.649 |
flakes | -1.552 |
Token | able |
Token ID | 540 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
izoph | +0.059 |
iris | +0.057 |
stadt | +0.056 |
Afric | +0.055 |
flakes | +0.052 |
Neg logit contributions | |
asi | -0.053 |
wen | -0.052 |
selage | -0.049 |
terness | -0.049 |
abad | -0.048 |
Token | with |
Token ID | 351 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
izoph | +0.033 |
iris | +0.032 |
stadt | +0.031 |
Afric | +0.031 |
Lite | +0.029 |
Neg logit contributions | |
asi | -0.032 |
wen | -0.031 |
selage | -0.029 |
terness | -0.029 |
abad | -0.028 |
Token | good |
Token ID | 922 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
izoph | +0.184 |
iris | +0.177 |
stadt | +0.173 |
Afric | +0.168 |
flakes | +0.158 |
Neg logit contributions | |
asi | -0.195 |
wen | -0.193 |
selage | -0.182 |
terness | -0.182 |
abad | -0.177 |
Token | corner |
Token ID | 5228 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
izoph | +2.211 |
iris | +2.144 |
stadt | +2.114 |
Afric | +2.062 |
flakes | +1.984 |
Neg logit contributions | |
asi | -2.398 |
wen | -2.375 |
selage | -2.285 |
terness | -2.281 |
ascus | -2.178 |
Token | backs |
Token ID | 10146 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
asi | +0.730 |
wen | +0.724 |
terness | +0.683 |
selage | +0.683 |
abad | +0.669 |
Neg logit contributions | |
izoph | -0.526 |
iris | -0.495 |
stadt | -0.481 |
Afric | -0.466 |
Lite | -0.432 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
izoph | +0.021 |
iris | +0.020 |
stadt | +0.020 |
Afric | +0.019 |
Lite | +0.018 |
Neg logit contributions | |
asi | -0.020 |
wen | -0.020 |
selage | -0.019 |
terness | -0.019 |
abad | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
asi | +1.418 |
wen | +1.397 |
selage | +1.307 |
terness | +1.306 |
abad | +1.278 |
Neg logit contributions | |
izoph | -1.453 |
iris | -1.373 |
stadt | -1.345 |
Afric | -1.291 |
flakes | -1.226 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
izoph | +0.009 |
iris | +0.009 |
stadt | +0.009 |
Afric | +0.008 |
Lite | +0.008 |
Neg logit contributions | |
asi | -0.011 |
wen | -0.011 |
terness | -0.010 |
selage | -0.010 |
ascus | -0.010 |
Token | Additionally |
Token ID | 23216 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
asi | +1.111 |
wen | +1.097 |
selage | +1.017 |
terness | +1.004 |
asm | +0.992 |
Neg logit contributions | |
izoph | -1.243 |
iris | -1.172 |
stadt | -1.160 |
Afric | -1.134 |
flakes | -1.071 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
asi | +0.448 |
wen | +0.443 |
selage | +0.417 |
terness | +0.415 |
abad | +0.402 |
Neg logit contributions | |
izoph | -0.509 |
iris | -0.490 |
stadt | -0.481 |
Afric | -0.468 |
flakes | -0.442 |
Token | when |
Token ID | 618 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
asi | +2.092 |
wen | +2.059 |
terness | +1.935 |
selage | +1.924 |
asm | +1.881 |
Neg logit contributions | |
izoph | -2.211 |
iris | -2.102 |
stadt | -2.058 |
Afric | -1.983 |
flakes | -1.857 |
Token | � |
Token ID | 247 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
izoph | +0.439 |
iris | +0.420 |
stadt | +0.410 |
Afric | +0.395 |
Lite | +0.369 |
Neg logit contributions | |
asi | -0.596 |
wen | -0.590 |
selage | -0.562 |
terness | -0.557 |
ascus | -0.546 |
Token | s |
Token ID | 82 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
izoph | +1.676 |
iris | +1.621 |
stadt | +1.603 |
Afric | +1.540 |
flakes | +1.459 |
Neg logit contributions | |
asi | -1.558 |
wen | -1.532 |
selage | -1.466 |
terness | -1.438 |
abad | -1.391 |
Token | part |
Token ID | 636 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
asi | +0.235 |
wen | +0.233 |
selage | +0.220 |
terness | +0.219 |
abad | +0.214 |
Neg logit contributions | |
izoph | -0.213 |
iris | -0.204 |
stadt | -0.200 |
Afric | -0.194 |
flakes | -0.182 |
Token | in |
Token ID | 287 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
asi | +2.763 |
wen | +2.696 |
terness | +2.516 |
selage | +2.487 |
quet | +2.437 |
Neg logit contributions | |
izoph | -3.454 |
iris | -3.221 |
stadt | -3.122 |
Afric | -3.118 |
flakes | -2.942 |
Token | destabil |
Token ID | 27397 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
asi | +0.494 |
wen | +0.489 |
selage | +0.463 |
terness | +0.461 |
abad | +0.449 |
Neg logit contributions | |
izoph | -0.449 |
iris | -0.430 |
stadt | -0.419 |
Afric | -0.406 |
Lite | -0.381 |
Token | izing |
Token ID | 2890 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
asi | +1.133 |
wen | +1.121 |
selage | +1.058 |
terness | +1.055 |
abad | +1.039 |
Neg logit contributions | |
izoph | -0.921 |
iris | -0.880 |
stadt | -0.852 |
Afric | -0.831 |
flakes | -0.777 |
Token | eastern |
Token ID | 10183 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
izoph | +0.010 |
iris | +0.010 |
stadt | +0.010 |
Afric | +0.009 |
flakes | +0.009 |
Neg logit contributions | |
asi | -0.012 |
wen | -0.012 |
selage | -0.011 |
terness | -0.011 |
abad | -0.011 |
Token | Ukraine |
Token ID | 7049 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
asi | +1.186 |
wen | +1.167 |
selage | +1.097 |
terness | +1.090 |
ascus | +1.078 |
Neg logit contributions | |
izoph | -1.136 |
iris | -1.088 |
stadt | -1.048 |
Afric | -1.018 |
Lite | -0.955 |
Token | . |
Token ID | 13 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
asi | +1.212 |
wen | +1.199 |
selage | +1.125 |
terness | +1.116 |
abad | +1.088 |
Neg logit contributions | |
izoph | -1.382 |
iris | -1.328 |
stadt | -1.292 |
Afric | -1.264 |
Lite | -1.192 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
asi | +0.653 |
wen | +0.646 |
selage | +0.609 |
terness | +0.607 |
abad | +0.594 |
Neg logit contributions | |
izoph | -0.613 |
iris | -0.585 |
stadt | -0.571 |
Afric | -0.552 |
flakes | -0.522 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
izoph | +1.252 |
iris | +1.226 |
stadt | +1.210 |
Afric | +1.153 |
Lite | +1.111 |
Neg logit contributions | |
asi | -1.695 |
wen | -1.673 |
terness | -1.646 |
aution | -1.614 |
selage | -1.611 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
izoph | +3.319 |
iris | +3.197 |
stadt | +3.195 |
Afric | +3.187 |
Lite | +2.914 |
Neg logit contributions | |
asi | -4.264 |
wen | -4.242 |
selage | -4.061 |
terness | -4.010 |
ascus | -4.007 |
Token | Hon |
Token ID | 8835 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
izoph | +1.028 |
iris | +0.986 |
stadt | +0.970 |
Afric | +0.948 |
Lite | +0.893 |
Neg logit contributions | |
asi | -1.158 |
wen | -1.151 |
terness | -1.095 |
selage | -1.092 |
ascus | -1.061 |
Token | ick |
Token ID | 624 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
izoph | +2.127 |
iris | +2.085 |
stadt | +2.021 |
Afric | +1.910 |
Lite | +1.803 |
Neg logit contributions | |
asi | -2.675 |
wen | -2.668 |
terness | -2.565 |
selage | -2.528 |
ascus | -2.462 |
Token | man |
Token ID | 805 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
izoph | +1.792 |
iris | +1.743 |
stadt | +1.716 |
Afric | +1.665 |
Lite | +1.585 |
Neg logit contributions | |
asi | -1.326 |
wen | -1.308 |
selage | -1.229 |
terness | -1.226 |
abad | -1.177 |
Token | children |
Token ID | 1751 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
izoph | +2.137 |
iris | +2.079 |
stadt | +2.035 |
Afric | +1.967 |
Lite | +1.858 |
Neg logit contributions | |
asi | -2.693 |
wen | -2.675 |
terness | -2.584 |
selage | -2.560 |
ascus | -2.486 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
asi | +3.261 |
wen | +3.216 |
selage | +2.988 |
abad | +2.952 |
terness | +2.912 |
Neg logit contributions | |
izoph | -3.796 |
iris | -3.539 |
stadt | -3.491 |
Afric | -3.386 |
flakes | -3.172 |
Token | Shirley |
Token ID | 40902 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
asi | +1.035 |
wen | +1.024 |
selage | +0.963 |
terness | +0.958 |
abad | +0.936 |
Neg logit contributions | |
izoph | -0.994 |
iris | -0.950 |
stadt | -0.932 |
Afric | -0.898 |
flakes | -0.848 |
Token | , |
Token ID | 11 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
asi | +2.322 |
wen | +2.307 |
selage | +2.149 |
terness | +2.137 |
abad | +2.081 |
Neg logit contributions | |
izoph | -2.461 |
iris | -2.347 |
stadt | -2.277 |
Afric | -2.205 |
flakes | -2.089 |
Token | is |
Token ID | 318 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
asi | +0.633 |
wen | +0.626 |
selage | +0.590 |
terness | +0.586 |
abad | +0.572 |
Neg logit contributions | |
izoph | -0.641 |
iris | -0.615 |
stadt | -0.603 |
Afric | -0.585 |
flakes | -0.550 |
Token | the |
Token ID | 262 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
asi | +0.092 |
wen | +0.091 |
selage | +0.086 |
terness | +0.086 |
abad | +0.084 |
Neg logit contributions | |
izoph | -0.087 |
iris | -0.084 |
stadt | -0.082 |
Afric | -0.080 |
flakes | -0.075 |
Token | mother |
Token ID | 2802 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
asi | +1.581 |
wen | +1.554 |
selage | +1.461 |
terness | +1.442 |
abad | +1.416 |
Neg logit contributions | |
izoph | -1.646 |
iris | -1.572 |
stadt | -1.538 |
Afric | -1.476 |
flakes | -1.405 |
Token | ille |
Token ID | 8270 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
izoph | +3.143 |
iris | +3.062 |
stadt | +2.970 |
Afric | +2.862 |
Lite | +2.716 |
Neg logit contributions | |
asi | -2.826 |
wen | -2.813 |
terness | -2.701 |
selage | -2.628 |
abad | -2.562 |
Token | ; |
Token ID | 26 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
asi | +0.920 |
wen | +0.911 |
selage | +0.858 |
terness | +0.852 |
abad | +0.828 |
Neg logit contributions | |
izoph | -0.970 |
iris | -0.931 |
stadt | -0.912 |
Afric | -0.885 |
Lite | -0.835 |
Token | do |
Token ID | 466 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
asi | +3.708 |
wen | +3.687 |
selage | +3.426 |
terness | +3.393 |
abad | +3.357 |
Neg logit contributions | |
izoph | -3.984 |
iris | -3.795 |
stadt | -3.695 |
Afric | -3.568 |
Lite | -3.338 |
Token | not |
Token ID | 407 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
asi | +3.437 |
wen | +3.431 |
selage | +3.151 |
terness | +3.120 |
asm | +3.087 |
Neg logit contributions | |
izoph | -4.035 |
iris | -3.821 |
stadt | -3.758 |
Afric | -3.647 |
Lite | -3.419 |
Token | drag |
Token ID | 6715 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
asi | +4.609 |
wen | +4.599 |
terness | +4.231 |
selage | +4.214 |
asm | +4.185 |
Neg logit contributions | |
izoph | -4.840 |
iris | -4.605 |
stadt | -4.520 |
Afric | -4.314 |
Reaper | -4.024 |
Token | her |
Token ID | 607 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
asi | +1.425 |
wen | +1.414 |
selage | +1.318 |
terness | +1.310 |
abad | +1.273 |
Neg logit contributions | |
izoph | -1.683 |
iris | -1.613 |
stadt | -1.589 |
Afric | -1.537 |
Lite | -1.455 |
Token | , |
Token ID | 11 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
izoph | +0.032 |
iris | +0.031 |
stadt | +0.030 |
Afric | +0.030 |
flakes | +0.028 |
Neg logit contributions | |
asi | -0.031 |
wen | -0.031 |
selage | -0.029 |
terness | -0.029 |
abad | -0.028 |
Token | nor |
Token ID | 4249 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
asi | +2.875 |
wen | +2.867 |
selage | +2.652 |
terness | +2.626 |
asm | +2.594 |
Neg logit contributions | |
izoph | -3.350 |
iris | -3.177 |
stadt | -3.127 |
Afric | -3.010 |
Lite | -2.825 |
Token | clasp |
Token ID | 47425 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
asi | +2.511 |
wen | +2.486 |
selage | +2.336 |
terness | +2.326 |
abad | +2.266 |
Neg logit contributions | |
izoph | -2.491 |
iris | -2.378 |
stadt | -2.333 |
Afric | -2.242 |
Lite | -2.104 |
Token | her |
Token ID | 607 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
asi | +0.022 |
wen | +0.021 |
selage | +0.020 |
terness | +0.020 |
abad | +0.019 |
Neg logit contributions | |
izoph | -0.024 |
iris | -0.024 |
stadt | -0.023 |
Afric | -0.023 |
flakes | -0.021 |
Token | hand |
Token ID | 1021 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
izoph | +1.494 |
iris | +1.450 |
stadt | +1.415 |
Afric | +1.382 |
flakes | +1.309 |
Neg logit contributions | |
asi | -1.563 |
wen | -1.535 |
selage | -1.466 |
terness | -1.466 |
abad | -1.406 |
Token | and |
Token ID | 290 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
izoph | +0.020 |
iris | +0.020 |
stadt | +0.019 |
Afric | +0.019 |
flakes | +0.018 |
Neg logit contributions | |
asi | -0.019 |
wen | -0.019 |
selage | -0.018 |
terness | -0.018 |
abad | -0.017 |
Token | Mes |
Token ID | 14937 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
izoph | +1.395 |
iris | +1.349 |
stadt | +1.328 |
Afric | +1.306 |
Lite | +1.226 |
Neg logit contributions | |
wen | -1.407 |
asi | -1.406 |
selage | -1.335 |
terness | -1.330 |
ascus | -1.271 |
Token | opot |
Token ID | 43372 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
asi | +0.495 |
wen | +0.482 |
selage | +0.444 |
terness | +0.441 |
abad | +0.432 |
Neg logit contributions | |
izoph | -0.692 |
iris | -0.663 |
stadt | -0.652 |
Afric | -0.637 |
flakes | -0.606 |
Token | amia |
Token ID | 49442 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
asi | +0.966 |
wen | +0.947 |
selage | +0.861 |
terness | +0.858 |
abad | +0.840 |
Neg logit contributions | |
izoph | -1.596 |
iris | -1.536 |
stadt | -1.522 |
Afric | -1.487 |
flakes | -1.422 |
Token | . |
Token ID | 13 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
asi | +0.927 |
wen | +0.915 |
selage | +0.857 |
terness | +0.852 |
abad | +0.832 |
Neg logit contributions | |
izoph | -1.027 |
iris | -0.985 |
stadt | -0.965 |
Afric | -0.938 |
Lite | -0.886 |
Token | As |
Token ID | 1081 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
izoph | +0.409 |
iris | +0.394 |
stadt | +0.386 |
Afric | +0.377 |
Lite | +0.353 |
Neg logit contributions | |
asi | -0.461 |
wen | -0.458 |
selage | -0.435 |
terness | -0.433 |
ascus | -0.422 |
Token | with |
Token ID | 351 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
asi | +0.842 |
wen | +0.833 |
selage | +0.786 |
terness | +0.782 |
abad | +0.761 |
Neg logit contributions | |
izoph | -0.783 |
iris | -0.750 |
stadt | -0.735 |
Afric | -0.710 |
Lite | -0.668 |
Token | so |
Token ID | 523 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
asi | +1.046 |
wen | +1.034 |
selage | +0.977 |
terness | +0.971 |
abad | +0.948 |
Neg logit contributions | |
izoph | -1.001 |
iris | -0.958 |
stadt | -0.935 |
Afric | -0.906 |
Lite | -0.852 |
Token | many |
Token ID | 867 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
izoph | +0.306 |
iris | +0.294 |
stadt | +0.287 |
Afric | +0.278 |
Lite | +0.260 |
Neg logit contributions | |
asi | -0.367 |
wen | -0.363 |
selage | -0.345 |
terness | -0.343 |
abad | -0.334 |
Token | parts |
Token ID | 3354 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
asi | +1.460 |
wen | +1.438 |
selage | +1.356 |
terness | +1.347 |
abad | +1.314 |
Neg logit contributions | |
izoph | -1.374 |
iris | -1.315 |
stadt | -1.286 |
Afric | -1.240 |
Lite | -1.168 |
Token | of |
Token ID | 286 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
asi | +2.158 |
wen | +2.112 |
selage | +1.971 |
terness | +1.964 |
abad | +1.893 |
Neg logit contributions | |
izoph | -2.665 |
iris | -2.534 |
stadt | -2.515 |
Afric | -2.418 |
Lite | -2.299 |
Token | : |
Token ID | 25 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
izoph | +0.776 |
iris | +0.757 |
stadt | +0.746 |
Afric | +0.718 |
Lite | +0.688 |
Neg logit contributions | |
asi | -0.879 |
wen | -0.865 |
terness | -0.837 |
selage | -0.827 |
ascus | -0.819 |
Token | Missouri |
Token ID | 11565 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
asi | +1.266 |
wen | +1.255 |
selage | +1.167 |
terness | +1.161 |
abad | +1.133 |
Neg logit contributions | |
izoph | -1.517 |
iris | -1.451 |
stadt | -1.424 |
Afric | -1.374 |
flakes | -1.309 |
Token |
|
Token ID | 198 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
izoph | +0.062 |
iris | +0.060 |
stadt | +0.059 |
Afric | +0.057 |
flakes | +0.053 |
Neg logit contributions | |
asi | -0.073 |
wen | -0.072 |
selage | -0.068 |
terness | -0.068 |
abad | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
asi | +1.906 |
wen | +1.896 |
selage | +1.763 |
abad | +1.724 |
asm | +1.724 |
Neg logit contributions | |
izoph | -1.937 |
iris | -1.829 |
stadt | -1.782 |
Afric | -1.756 |
flakes | -1.640 |
Token | Date |
Token ID | 10430 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
asi | +0.452 |
wen | +0.447 |
selage | +0.419 |
terness | +0.417 |
abad | +0.404 |
Neg logit contributions | |
izoph | -0.520 |
iris | -0.501 |
stadt | -0.492 |
Afric | -0.479 |
flakes | -0.453 |
Token | : |
Token ID | 25 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
asi | +1.434 |
wen | +1.421 |
selage | +1.333 |
terness | +1.318 |
abad | +1.293 |
Neg logit contributions | |
izoph | -1.513 |
iris | -1.449 |
stadt | -1.418 |
Afric | -1.381 |
flakes | -1.301 |
Token | Dec |
Token ID | 4280 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
izoph | +0.470 |
iris | +0.456 |
stadt | +0.450 |
Afric | +0.440 |
Lite | +0.419 |
Neg logit contributions | |
asi | -0.340 |
wen | -0.336 |
selage | -0.315 |
terness | -0.314 |
ascus | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
asi | +2.489 |
wen | +2.476 |
selage | +2.291 |
abad | +2.232 |
terness | +2.216 |
Neg logit contributions | |
izoph | -3.024 |
iris | -2.888 |
stadt | -2.812 |
Afric | -2.773 |
flakes | -2.608 |
Token | 7 |
Token ID | 767 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
izoph | +0.512 |
iris | +0.497 |
stadt | +0.489 |
Afric | +0.472 |
Lite | +0.447 |
Neg logit contributions | |
asi | -0.628 |
wen | -0.621 |
terness | -0.598 |
selage | -0.595 |
ascus | -0.581 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
asi | +0.752 |
wen | +0.743 |
selage | +0.700 |
terness | +0.698 |
ascus | +0.675 |
Neg logit contributions | |
izoph | -0.840 |
iris | -0.810 |
stadt | -0.796 |
Afric | -0.773 |
Lite | -0.732 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
asi | +2.352 |
wen | +2.331 |
selage | +2.140 |
terness | +2.104 |
asm | +2.079 |
Neg logit contributions | |
izoph | -3.445 |
iris | -3.306 |
stadt | -3.229 |
Afric | -3.110 |
flakes | -2.971 |
Token | of |
Token ID | 286 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
asi | +1.938 |
wen | +1.923 |
selage | +1.804 |
terness | +1.784 |
abad | +1.762 |
Neg logit contributions | |
izoph | -1.855 |
iris | -1.776 |
stadt | -1.736 |
Afric | -1.677 |
flakes | -1.578 |
Token | mine |
Token ID | 6164 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
asi | +0.341 |
wen | +0.337 |
selage | +0.319 |
terness | +0.318 |
abad | +0.309 |
Neg logit contributions | |
izoph | -0.306 |
iris | -0.293 |
stadt | -0.287 |
Afric | -0.278 |
flakes | -0.261 |
Token | and |
Token ID | 290 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
izoph | +0.722 |
iris | +0.696 |
stadt | +0.683 |
Afric | +0.664 |
Lite | +0.630 |
Neg logit contributions | |
asi | -0.708 |
wen | -0.701 |
selage | -0.666 |
terness | -0.665 |
ascus | -0.641 |
Token | the |
Token ID | 262 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
izoph | +1.077 |
iris | +1.030 |
stadt | +1.006 |
Afric | +0.984 |
Lite | +0.932 |
Neg logit contributions | |
asi | -1.222 |
wen | -1.216 |
selage | -1.161 |
terness | -1.160 |
ascus | -1.122 |
Token | image |
Token ID | 2939 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
asi | +0.538 |
wen | +0.532 |
selage | +0.504 |
terness | +0.501 |
abad | +0.489 |
Neg logit contributions | |
izoph | -0.481 |
iris | -0.461 |
stadt | -0.451 |
Afric | -0.437 |
flakes | -0.409 |
Token | below |
Token ID | 2174 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
asi | +3.678 |
wen | +3.583 |
selage | +3.335 |
terness | +3.311 |
asm | +3.262 |
Neg logit contributions | |
izoph | -3.899 |
iris | -3.705 |
stadt | -3.613 |
Afric | -3.540 |
flakes | -3.287 |
Token | , |
Token ID | 11 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
izoph | +0.536 |
iris | +0.518 |
stadt | +0.507 |
Afric | +0.494 |
Lite | +0.469 |
Neg logit contributions | |
asi | -0.500 |
wen | -0.495 |
selage | -0.467 |
terness | -0.466 |
abad | -0.450 |
Token | Best |
Token ID | 6705 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
izoph | +2.065 |
iris | +1.976 |
stadt | +1.956 |
Afric | +1.909 |
Lite | +1.800 |
Neg logit contributions | |
asi | -2.557 |
wen | -2.552 |
terness | -2.436 |
selage | -2.432 |
ascus | -2.350 |
Token | Buy |
Token ID | 11763 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
izoph | +0.952 |
iris | +0.929 |
stadt | +0.918 |
Afric | +0.900 |
Lite | +0.872 |
Neg logit contributions | |
asi | -0.568 |
wen | -0.558 |
terness | -0.533 |
selage | -0.522 |
ascus | -0.502 |
Token | will |
Token ID | 481 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
asi | +0.914 |
wen | +0.903 |
selage | +0.853 |
terness | +0.845 |
abad | +0.825 |
Neg logit contributions | |
izoph | -0.916 |
iris | -0.879 |
stadt | -0.860 |
Afric | -0.835 |
flakes | -0.786 |
Token | have |
Token ID | 423 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
izoph | +0.910 |
iris | +0.872 |
stadt | +0.858 |
Afric | +0.833 |
flakes | +0.785 |
Neg logit contributions | |
asi | -1.041 |
wen | -1.029 |
terness | -0.980 |
selage | -0.979 |
abad | -0.947 |
Token | sexual |
Token ID | 3206 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
asi | +2.178 |
wen | +2.143 |
selage | +2.005 |
terness | +1.975 |
asm | +1.946 |
Neg logit contributions | |
izoph | -2.632 |
iris | -2.528 |
stadt | -2.475 |
Afric | -2.401 |
flakes | -2.261 |
Token | act |
Token ID | 719 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
asi | +0.749 |
wen | +0.740 |
selage | +0.705 |
terness | +0.702 |
abad | +0.686 |
Neg logit contributions | |
izoph | -0.515 |
iris | -0.490 |
stadt | -0.478 |
Afric | -0.460 |
flakes | -0.425 |
Token | if |
Token ID | 611 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
asi | +0.743 |
wen | +0.735 |
selage | +0.690 |
terness | +0.687 |
abad | +0.668 |
Neg logit contributions | |
izoph | -0.804 |
iris | -0.772 |
stadt | -0.757 |
Afric | -0.736 |
flakes | -0.694 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
izoph | +0.047 |
iris | +0.046 |
stadt | +0.045 |
Afric | +0.043 |
Lite | +0.041 |
Neg logit contributions | |
asi | -0.052 |
wen | -0.051 |
selage | -0.049 |
terness | -0.048 |
abad | -0.047 |
Token | subject |
Token ID | 2426 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
izoph | +1.255 |
iris | +1.210 |
stadt | +1.188 |
Afric | +1.156 |
Lite | +1.101 |
Neg logit contributions | |
asi | -1.218 |
wen | -1.208 |
terness | -1.142 |
selage | -1.140 |
ascus | -1.101 |
Token | hasn |
Token ID | 5818 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
asi | +0.438 |
wen | +0.434 |
selage | +0.409 |
terness | +0.407 |
abad | +0.395 |
Neg logit contributions | |
izoph | -0.437 |
iris | -0.418 |
stadt | -0.409 |
Afric | -0.397 |
Lite | -0.373 |
Token | 't |
Token ID | 470 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
izoph | +0.800 |
iris | +0.781 |
stadt | +0.771 |
Afric | +0.737 |
Lite | +0.709 |
Neg logit contributions | |
asi | -0.668 |
wen | -0.656 |
terness | -0.634 |
selage | -0.626 |
ascus | -0.612 |
Token | given |
Token ID | 1813 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
asi | +0.080 |
wen | +0.080 |
selage | +0.075 |
terness | +0.075 |
abad | +0.073 |
Neg logit contributions | |
izoph | -0.074 |
iris | -0.071 |
stadt | -0.069 |
Afric | -0.067 |
flakes | -0.063 |
Token | permission |
Token ID | 7170 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
izoph | +0.788 |
iris | +0.750 |
stadt | +0.734 |
Afric | +0.716 |
Lite | +0.668 |
Neg logit contributions | |
asi | -1.059 |
wen | -1.046 |
terness | -1.005 |
selage | -1.000 |
ascus | -0.972 |
Token | for |
Token ID | 329 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
izoph | +0.749 |
iris | +0.724 |
stadt | +0.712 |
Afric | +0.689 |
Lite | +0.653 |
Neg logit contributions | |
asi | -0.738 |
wen | -0.729 |
selage | -0.690 |
terness | -0.688 |
abad | -0.665 |
Token | it |
Token ID | 340 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
asi | +0.743 |
wen | +0.734 |
selage | +0.693 |
terness | +0.688 |
abad | +0.673 |
Neg logit contributions | |
izoph | -0.708 |
iris | -0.681 |
stadt | -0.665 |
Afric | -0.646 |
flakes | -0.604 |
Token | black |
Token ID | 2042 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
asi | +1.061 |
wen | +1.050 |
selage | +0.991 |
terness | +0.984 |
abad | +0.965 |
Neg logit contributions | |
izoph | -0.975 |
iris | -0.930 |
stadt | -0.908 |
Afric | -0.880 |
flakes | -0.826 |
Token | and |
Token ID | 290 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
izoph | +3.756 |
iris | +3.699 |
stadt | +3.620 |
Afric | +3.542 |
Lite | +3.345 |
Neg logit contributions | |
asi | -4.337 |
wen | -4.291 |
terness | -4.119 |
selage | -4.080 |
hess | -3.951 |
Token | white |
Token ID | 2330 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
asi | +2.422 |
wen | +2.386 |
selage | +2.253 |
terness | +2.213 |
abad | +2.209 |
Neg logit contributions | |
izoph | -2.288 |
iris | -2.158 |
stadt | -2.120 |
Afric | -2.004 |
flakes | -1.892 |
Token | love |
Token ID | 1842 |
Feature activation | -9.23e+00 |
Pos logit contributions | |
izoph | +0.559 |
iris | +0.537 |
stadt | +0.526 |
Afric | +0.511 |
Lite | +0.478 |
Neg logit contributions | |
asi | -0.645 |
wen | -0.639 |
selage | -0.606 |
terness | -0.605 |
abad | -0.587 |
Token | letter |
Token ID | 3850 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
izoph | +5.258 |
iris | +5.207 |
stadt | +5.084 |
Afric | +5.079 |
Lite | +4.789 |
Neg logit contributions | |
asi | -7.130 |
wen | -6.953 |
terness | -6.927 |
ascus | -6.767 |
selage | -6.766 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
izoph | +0.736 |
iris | +0.715 |
stadt | +0.703 |
Afric | +0.682 |
flakes | +0.644 |
Neg logit contributions | |
asi | -0.737 |
wen | -0.730 |
selage | -0.690 |
terness | -0.687 |
ascus | -0.666 |
Token | New |
Token ID | 968 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
izoph | +0.767 |
iris | +0.736 |
stadt | +0.722 |
Afric | +0.702 |
Lite | +0.657 |
Neg logit contributions | |
asi | -0.867 |
wen | -0.859 |
selage | -0.814 |
terness | -0.811 |
abad | -0.788 |
Token | York |
Token ID | 1971 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
asi | +0.373 |
wen | +0.366 |
selage | +0.341 |
terness | +0.340 |
abad | +0.332 |
Neg logit contributions | |
izoph | -0.477 |
iris | -0.455 |
stadt | -0.442 |
Afric | -0.427 |
flakes | -0.412 |
Token | City |
Token ID | 2254 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
asi | +2.562 |
wen | +2.518 |
selage | +2.367 |
terness | +2.328 |
abad | +2.322 |
Neg logit contributions | |
izoph | -2.651 |
iris | -2.536 |
stadt | -2.478 |
Afric | -2.402 |
flakes | -2.260 |
Token | may |
Token ID | 743 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
asi | +2.293 |
wen | +2.258 |
selage | +2.124 |
terness | +2.097 |
abad | +2.076 |
Neg logit contributions | |
izoph | -2.356 |
iris | -2.245 |
stadt | -2.202 |
Afric | -2.130 |
Lite | -2.002 |
Token | very |
Token ID | 845 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
asi | +2.512 |
wen | +2.490 |
terness | +2.315 |
selage | +2.309 |
asm | +2.259 |
Neg logit contributions | |
izoph | -2.545 |
iris | -2.417 |
stadt | -2.373 |
Afric | -2.330 |
Lite | -2.164 |
Token | any |
Token ID | 597 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
izoph | +1.610 |
iris | +1.557 |
stadt | +1.536 |
Afric | +1.500 |
Lite | +1.415 |
Neg logit contributions | |
asi | -1.821 |
wen | -1.799 |
selage | -1.705 |
terness | -1.705 |
ascus | -1.652 |
Token | potential |
Token ID | 2785 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
izoph | +1.426 |
iris | +1.380 |
stadt | +1.354 |
Afric | +1.326 |
flakes | +1.253 |
Neg logit contributions | |
asi | -1.441 |
wen | -1.423 |
selage | -1.349 |
terness | -1.342 |
abad | -1.296 |
Token | technical |
Token ID | 6276 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
izoph | +1.375 |
iris | +1.334 |
stadt | +1.313 |
Afric | +1.284 |
Lite | +1.217 |
Neg logit contributions | |
asi | -1.347 |
wen | -1.323 |
selage | -1.255 |
terness | -1.251 |
abad | -1.205 |
Token | interference |
Token ID | 14517 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
izoph | +0.060 |
iris | +0.057 |
stadt | +0.056 |
Afric | +0.055 |
flakes | +0.051 |
Neg logit contributions | |
asi | -0.066 |
wen | -0.065 |
selage | -0.062 |
terness | -0.062 |
abad | -0.060 |
Token | - |
Token ID | 532 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
asi | +0.359 |
wen | +0.355 |
selage | +0.334 |
terness | +0.333 |
abad | +0.323 |
Neg logit contributions | |
izoph | -0.380 |
iris | -0.366 |
stadt | -0.359 |
Afric | -0.349 |
Lite | -0.329 |
Token | LOC |
Token ID | 37347 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
izoph | +2.497 |
iris | +2.453 |
stadt | +2.412 |
Afric | +2.358 |
Lite | +2.229 |
Neg logit contributions | |
asi | -2.787 |
wen | -2.767 |
terness | -2.628 |
selage | -2.617 |
ascus | -2.541 |
Token | OG |
Token ID | 7730 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
izoph | +1.418 |
iris | +1.374 |
stadt | +1.348 |
Afric | +1.311 |
Lite | +1.246 |
Neg logit contributions | |
asi | -1.343 |
wen | -1.332 |
selage | -1.261 |
terness | -1.258 |
ascus | -1.211 |
Token | , |
Token ID | 11 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
izoph | +3.001 |
iris | +2.947 |
stadt | +2.865 |
Afric | +2.773 |
Lite | +2.678 |
Neg logit contributions | |
asi | -2.928 |
wen | -2.922 |
terness | -2.788 |
selage | -2.759 |
ascus | -2.676 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
izoph | +0.607 |
iris | +0.586 |
stadt | +0.571 |
Afric | +0.558 |
Lite | +0.523 |
Neg logit contributions | |
asi | -0.705 |
wen | -0.699 |
selage | -0.664 |
terness | -0.661 |
ascus | -0.641 |
Token | London |
Token ID | 3576 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
asi | +1.023 |
wen | +1.009 |
selage | +0.954 |
terness | +0.947 |
abad | +0.927 |
Neg logit contributions | |
izoph | -0.941 |
iris | -0.897 |
stadt | -0.881 |
Afric | -0.847 |
flakes | -0.798 |
Token | Olympics |
Token ID | 14935 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
izoph | +0.127 |
iris | +0.122 |
stadt | +0.119 |
Afric | +0.116 |
Lite | +0.109 |
Neg logit contributions | |
asi | -0.136 |
wen | -0.134 |
selage | -0.127 |
terness | -0.127 |
abad | -0.123 |
Token | need |
Token ID | 761 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
izoph | +0.741 |
iris | +0.716 |
stadt | +0.686 |
Afric | +0.675 |
flakes | +0.641 |
Neg logit contributions | |
asi | -0.860 |
wen | -0.849 |
terness | -0.817 |
selage | -0.812 |
abad | -0.789 |
Token | to |
Token ID | 284 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
izoph | +3.205 |
iris | +3.118 |
stadt | +3.030 |
Afric | +2.933 |
Lite | +2.800 |
Neg logit contributions | |
asi | -3.603 |
wen | -3.568 |
terness | -3.440 |
selage | -3.432 |
abad | -3.327 |
Token | . |
Token ID | 13 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
izoph | +3.333 |
iris | +3.262 |
stadt | +3.107 |
Afric | +3.026 |
Lite | +2.929 |
Neg logit contributions | |
asi | -3.839 |
wen | -3.762 |
terness | -3.713 |
selage | -3.679 |
abad | -3.582 |
Token | In |
Token ID | 554 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
izoph | +3.105 |
iris | +3.091 |
stadt | +2.977 |
Afric | +2.954 |
Lite | +2.828 |
Neg logit contributions | |
asi | -3.774 |
wen | -3.771 |
selage | -3.647 |
terness | -3.630 |
ascus | -3.559 |
Token | other |
Token ID | 584 |
Feature activation | -8.59e+00 |
Pos logit contributions | |
izoph | +3.240 |
iris | +3.143 |
stadt | +3.098 |
Afric | +2.994 |
Lite | +2.880 |
Neg logit contributions | |
asi | -4.075 |
wen | -4.037 |
selage | -3.881 |
terness | -3.866 |
abad | -3.773 |
Token | related |
Token ID | 3519 |
Feature activation | -8.15e+00 |
Pos logit contributions | |
izoph | +3.781 |
iris | +3.638 |
stadt | +3.467 |
Afric | +3.283 |
flakes | +3.150 |
Neg logit contributions | |
asi | -8.076 |
selage | -7.897 |
wen | -7.893 |
terness | -7.827 |
abad | -7.614 |
Token | areas |
Token ID | 3006 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
iris | +4.495 |
izoph | +4.478 |
stadt | +4.343 |
Afric | +4.185 |
Lite | +4.080 |
Neg logit contributions | |
asi | -6.602 |
wen | -6.488 |
selage | -6.443 |
terness | -6.439 |
ascus | -6.131 |
Token | this |
Token ID | 428 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
izoph | +3.508 |
iris | +3.443 |
stadt | +3.306 |
Afric | +3.218 |
Lite | +3.077 |
Neg logit contributions | |
asi | -3.882 |
wen | -3.846 |
selage | -3.707 |
terness | -3.692 |
abad | -3.591 |
Token | screen |
Token ID | 3159 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
izoph | +2.733 |
iris | +2.691 |
stadt | +2.606 |
Afric | +2.526 |
Lite | +2.422 |
Neg logit contributions | |
asi | -3.338 |
wen | -3.330 |
terness | -3.258 |
selage | -3.223 |
abad | -3.075 |
Token | also |
Token ID | 635 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
izoph | +0.410 |
iris | +0.396 |
stadt | +0.389 |
Afric | +0.376 |
Lite | +0.356 |
Neg logit contributions | |
asi | -0.447 |
wen | -0.443 |
selage | -0.420 |
terness | -0.420 |
abad | -0.405 |
Token | supports |
Token ID | 6971 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
izoph | +1.989 |
iris | +1.965 |
stadt | +1.923 |
Afric | +1.857 |
flakes | +1.810 |
Neg logit contributions | |
asi | -2.304 |
wen | -2.285 |
terness | -2.220 |
selage | -2.185 |
ascus | -2.107 |
Token | 18 |
Token ID | 1507 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
izoph | +1.607 |
iris | +1.560 |
stadt | +1.523 |
Afric | +1.458 |
Lite | +1.369 |
Neg logit contributions | |
asi | -2.091 |
wen | -2.063 |
terness | -1.988 |
selage | -1.980 |
ascus | -1.926 |
Token | 99 |
Token ID | 2079 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
asi | +1.808 |
wen | +1.790 |
selage | +1.647 |
terness | +1.618 |
abad | +1.610 |
Neg logit contributions | |
izoph | -2.430 |
iris | -2.327 |
stadt | -2.255 |
Afric | -2.202 |
flakes | -2.094 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
izoph | +0.142 |
iris | +0.136 |
stadt | +0.133 |
Afric | +0.129 |
flakes | +0.121 |
Neg logit contributions | |
asi | -0.158 |
wen | -0.157 |
selage | -0.148 |
terness | -0.147 |
abad | -0.143 |
Token |
|
Token ID | 198 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
asi | +0.014 |
wen | +0.014 |
terness | +0.013 |
selage | +0.013 |
ascus | +0.012 |
Neg logit contributions | |
izoph | -0.012 |
iris | -0.011 |
stadt | -0.011 |
Afric | -0.011 |
Lite | -0.010 |
Token | N |
Token ID | 45 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
izoph | +2.775 |
iris | +2.729 |
stadt | +2.676 |
Afric | +2.546 |
Lite | +2.406 |
Neg logit contributions | |
asi | -3.601 |
wen | -3.549 |
terness | -3.489 |
selage | -3.436 |
ascus | -3.372 |
Token | IN |
Token ID | 1268 |
Feature activation | -8.68e+00 |
Pos logit contributions | |
izoph | +2.839 |
iris | +2.782 |
stadt | +2.726 |
Afric | +2.600 |
Lite | +2.435 |
Neg logit contributions | |
asi | -3.314 |
wen | -3.297 |
selage | -3.200 |
terness | -3.192 |
ascus | -3.054 |
Token | JA |
Token ID | 37048 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
stadt | +5.657 |
iris | +5.422 |
izoph | +5.414 |
Afric | +5.295 |
Lite | +5.215 |
Neg logit contributions | |
wen | -5.936 |
asi | -5.922 |
aution | -5.877 |
terness | -5.839 |
ascus | -5.817 |
Token | / |
Token ID | 14 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
izoph | +1.358 |
iris | +1.302 |
stadt | +1.273 |
Afric | +1.241 |
Lite | +1.166 |
Neg logit contributions | |
asi | -1.792 |
wen | -1.772 |
selage | -1.691 |
terness | -1.691 |
ascus | -1.650 |
Token | SAM |
Token ID | 49302 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
izoph | +0.829 |
iris | +0.800 |
stadt | +0.785 |
Afric | +0.760 |
Lite | +0.718 |
Neg logit contributions | |
asi | -0.830 |
wen | -0.821 |
selage | -0.778 |
terness | -0.775 |
abad | -0.754 |
Token | URA |
Token ID | 45570 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
izoph | +1.302 |
iris | +1.257 |
stadt | +1.239 |
Afric | +1.183 |
Lite | +1.123 |
Neg logit contributions | |
asi | -1.719 |
wen | -1.696 |
terness | -1.624 |
selage | -1.612 |
ascus | -1.599 |
Token | I |
Token ID | 40 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
izoph | +2.853 |
iris | +2.820 |
stadt | +2.806 |
Afric | +2.745 |
Lite | +2.676 |
Neg logit contributions | |
asi | -3.476 |
aution | -3.475 |
ascus | -3.435 |
terness | -3.418 |
wen | -3.415 |
Token | Pr |
Token ID | 1736 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
izoph | +2.142 |
iris | +2.078 |
stadt | +2.013 |
Afric | +1.996 |
Lite | +1.878 |
Neg logit contributions | |
asi | -1.993 |
wen | -1.988 |
terness | -1.876 |
selage | -1.873 |
ascus | -1.827 |
Token | at |
Token ID | 265 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
izoph | +1.194 |
iris | +1.152 |
stadt | +1.126 |
Afric | +1.095 |
Lite | +1.039 |
Neg logit contributions | |
asi | -0.966 |
wen | -0.957 |
selage | -0.899 |
terness | -0.898 |
abad | -0.863 |
Token | iques |
Token ID | 6368 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
izoph | +4.467 |
iris | +4.421 |
stadt | +4.240 |
Afric | +4.152 |
flakes | +3.955 |
Neg logit contributions | |
wen | -3.680 |
asi | -3.662 |
selage | -3.517 |
terness | -3.464 |
ascus | -3.379 |
Token | qui |
Token ID | 45567 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
izoph | +1.616 |
iris | +1.559 |
stadt | +1.501 |
Afric | +1.492 |
flakes | +1.380 |
Neg logit contributions | |
asi | -1.886 |
wen | -1.881 |
selage | -1.783 |
terness | -1.778 |
abad | -1.725 |
Token | de |
Token ID | 390 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
izoph | +0.646 |
iris | +0.620 |
stadt | +0.602 |
Afric | +0.589 |
Lite | +0.550 |
Neg logit contributions | |
asi | -0.757 |
wen | -0.752 |
terness | -0.714 |
selage | -0.713 |
abad | -0.689 |
Token | ven |
Token ID | 574 |
Feature activation | -8.16e+00 |
Pos logit contributions | |
izoph | +1.650 |
iris | +1.611 |
stadt | +1.549 |
Afric | +1.527 |
Lite | +1.442 |
Neg logit contributions | |
asi | -1.521 |
wen | -1.508 |
selage | -1.424 |
terness | -1.423 |
abad | -1.369 |
Token | a |
Token ID | 64 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
iris | +6.080 |
izoph | +5.945 |
stadt | +5.645 |
Afric | +5.636 |
Lite | +5.282 |
Neg logit contributions | |
wen | -5.000 |
asi | -4.958 |
terness | -4.888 |
selage | -4.851 |
ascus | -4.701 |
Token | ient |
Token ID | 1153 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
izoph | +3.246 |
iris | +3.171 |
Afric | +3.034 |
stadt | +3.018 |
Lite | +2.839 |
Neg logit contributions | |
wen | -3.011 |
asi | -2.967 |
selage | -2.858 |
terness | -2.839 |
abad | -2.731 |
Token | tend |
Token ID | 4327 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
izoph | +3.433 |
iris | +3.349 |
Afric | +3.221 |
stadt | +3.174 |
Lite | +2.959 |
Neg logit contributions | |
wen | -4.038 |
asi | -4.012 |
selage | -3.840 |
terness | -3.829 |
ascus | -3.699 |
Token | anc |
Token ID | 1192 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
izoph | +5.049 |
iris | +5.027 |
stadt | +4.810 |
Afric | +4.666 |
Lite | +4.378 |
Neg logit contributions | |
wen | -3.946 |
asi | -3.873 |
terness | -3.776 |
selage | -3.719 |
ascus | -3.575 |
Token | ie |
Token ID | 494 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
izoph | +3.530 |
iris | +3.504 |
stadt | +3.405 |
Afric | +3.275 |
flakes | +3.078 |
Neg logit contributions | |
wen | -3.214 |
asi | -3.191 |
selage | -3.043 |
terness | -3.011 |
ascus | -2.967 |
Token | I |
Token ID | 314 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
asi | +1.457 |
wen | +1.444 |
selage | +1.355 |
terness | +1.353 |
abad | +1.319 |
Neg logit contributions | |
izoph | -1.332 |
iris | -1.267 |
stadt | -1.242 |
Afric | -1.200 |
Lite | -1.120 |
Token | love |
Token ID | 1842 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
izoph | +1.264 |
iris | +1.221 |
stadt | +1.193 |
Afric | +1.153 |
flakes | +1.097 |
Neg logit contributions | |
asi | -1.480 |
wen | -1.469 |
selage | -1.412 |
terness | -1.411 |
ascus | -1.370 |
Token | you |
Token ID | 345 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
izoph | +0.983 |
iris | +0.950 |
stadt | +0.935 |
Afric | +0.904 |
flakes | +0.855 |
Neg logit contributions | |
asi | -1.134 |
wen | -1.120 |
terness | -1.070 |
selage | -1.068 |
ascus | -1.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
izoph | +0.326 |
iris | +0.315 |
stadt | +0.309 |
Afric | +0.299 |
Lite | +0.283 |
Neg logit contributions | |
asi | -0.347 |
wen | -0.343 |
selage | -0.325 |
terness | -0.324 |
abad | -0.314 |
Token | You |
Token ID | 921 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
izoph | +1.013 |
iris | +0.986 |
stadt | +0.963 |
Afric | +0.941 |
Lite | +0.891 |
Neg logit contributions | |
asi | -1.240 |
wen | -1.227 |
selage | -1.180 |
terness | -1.171 |
ascus | -1.153 |
Token | make |
Token ID | 787 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
izoph | +1.112 |
iris | +1.079 |
stadt | +1.048 |
Afric | +1.016 |
flakes | +0.964 |
Neg logit contributions | |
asi | -1.237 |
wen | -1.226 |
selage | -1.168 |
terness | -1.166 |
abad | -1.129 |
Token | me |
Token ID | 502 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
iris | +6.077 |
stadt | +5.906 |
izoph | +5.898 |
Afric | +5.751 |
flakes | +5.597 |
Neg logit contributions | |
asi | -8.217 |
wen | -8.146 |
terness | -8.113 |
selage | -8.067 |
ascus | -7.739 |
Token | feel |
Token ID | 1254 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
asi | +0.358 |
wen | +0.354 |
selage | +0.334 |
terness | +0.332 |
abad | +0.325 |
Neg logit contributions | |
izoph | -0.317 |
iris | -0.302 |
stadt | -0.297 |
Afric | -0.287 |
Lite | -0.268 |
Token | all |
Token ID | 477 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
izoph | +1.041 |
iris | +1.007 |
stadt | +0.983 |
Afric | +0.951 |
flakes | +0.896 |
Neg logit contributions | |
asi | -1.218 |
wen | -1.206 |
selage | -1.150 |
terness | -1.147 |
ascus | -1.111 |
Token | sort |
Token ID | 3297 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
asi | +0.621 |
wen | +0.612 |
selage | +0.575 |
terness | +0.575 |
abad | +0.562 |
Neg logit contributions | |
izoph | -0.575 |
iris | -0.544 |
stadt | -0.531 |
Afric | -0.518 |
Lite | -0.483 |
Token | of |
Token ID | 286 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
izoph | +0.610 |
iris | +0.593 |
stadt | +0.581 |
Afric | +0.561 |
Lite | +0.533 |
Neg logit contributions | |
asi | -0.591 |
wen | -0.586 |
terness | -0.556 |
selage | -0.556 |
ascus | -0.539 |
Token | Free |
Token ID | 3232 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
izoph | +1.606 |
iris | +1.568 |
stadt | +1.558 |
Afric | +1.534 |
Lite | +1.503 |
Neg logit contributions | |
asi | -0.544 |
wen | -0.534 |
terness | -0.501 |
selage | -0.489 |
ascus | -0.473 |
Token | = |
Token ID | 796 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
asi | +1.591 |
wen | +1.575 |
selage | +1.460 |
terness | +1.448 |
abad | +1.407 |
Neg logit contributions | |
izoph | -2.065 |
iris | -1.986 |
stadt | -1.940 |
Afric | -1.897 |
flakes | -1.793 |
Token | 80 |
Token ID | 4019 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
izoph | +1.602 |
iris | +1.538 |
stadt | +1.504 |
Afric | +1.449 |
Lite | +1.364 |
Neg logit contributions | |
asi | -1.985 |
wen | -1.971 |
selage | -1.881 |
terness | -1.873 |
abad | -1.820 |
Token | ) |
Token ID | 8 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
izoph | +1.555 |
iris | +1.500 |
stadt | +1.472 |
Afric | +1.430 |
Lite | +1.360 |
Neg logit contributions | |
asi | -1.424 |
wen | -1.404 |
selage | -1.333 |
terness | -1.322 |
ascus | -1.283 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
izoph | +3.636 |
iris | +3.601 |
stadt | +3.407 |
Afric | +3.360 |
Lite | +3.201 |
Neg logit contributions | |
asi | -4.664 |
wen | -4.641 |
selage | -4.481 |
terness | -4.450 |
ascus | -4.326 |
Token |
|
Token ID | 198 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
asi | +0.001 |
wen | +0.001 |
selage | +0.001 |
terness | +0.001 |
ascus | +0.001 |
Neg logit contributions | |
izoph | -0.001 |
iris | -0.001 |
stadt | -0.001 |
Afric | -0.001 |
Lite | -0.001 |
Token | 27 |
Token ID | 1983 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
iris | +4.774 |
izoph | +4.745 |
stadt | +4.496 |
Afric | +4.140 |
Lite | +4.069 |
Neg logit contributions | |
asi | -6.386 |
wen | -6.294 |
terness | -6.259 |
selage | -6.200 |
ascus | -6.142 |
Token | " |
Token ID | 1 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
izoph | +2.751 |
iris | +2.677 |
stadt | +2.616 |
Afric | +2.503 |
Lite | +2.444 |
Neg logit contributions | |
asi | -3.079 |
wen | -3.035 |
selage | -2.935 |
terness | -2.916 |
ascus | -2.843 |
Token | 12 |
Token ID | 1105 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
izoph | +2.589 |
iris | +2.512 |
stadt | +2.408 |
Afric | +2.370 |
Lite | +2.244 |
Neg logit contributions | |
asi | -3.062 |
wen | -3.053 |
selage | -2.917 |
terness | -2.892 |
abad | -2.830 |
Token | ms |
Token ID | 907 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
izoph | +1.453 |
iris | +1.423 |
stadt | +1.381 |
Afric | +1.333 |
Lite | +1.274 |
Neg logit contributions | |
asi | -1.522 |
wen | -1.501 |
selage | -1.439 |
terness | -1.434 |
abad | -1.388 |
Token | G |
Token ID | 402 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
izoph | +2.554 |
iris | +2.514 |
stadt | +2.424 |
Afric | +2.368 |
Lite | +2.243 |
Neg logit contributions | |
asi | -4.004 |
wen | -3.997 |
terness | -3.866 |
selage | -3.823 |
ascus | -3.730 |