Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
orem | +0.681 |
ril | +0.669 |
nerv | +0.646 |
riors | +0.626 |
wills | +0.623 |
Neg logit contributions | |
hatt | -0.625 |
Beer | -0.603 |
coat | -0.541 |
andr | -0.540 |
ness | -0.535 |
Token | former |
Token ID | 1966 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
orem | +0.731 |
ril | +0.714 |
nerv | +0.690 |
riors | +0.667 |
wills | +0.667 |
Neg logit contributions | |
hatt | -0.670 |
Beer | -0.644 |
andr | -0.579 |
coat | -0.578 |
ness | -0.573 |
Token | CEO |
Token ID | 6123 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
orem | +0.850 |
ril | +0.828 |
nerv | +0.802 |
wills | +0.774 |
riors | +0.772 |
Neg logit contributions | |
hatt | -0.818 |
Beer | -0.786 |
andr | -0.710 |
coat | -0.709 |
ness | -0.698 |
Token | of |
Token ID | 286 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
orem | +0.625 |
ril | +0.610 |
nerv | +0.582 |
riors | +0.564 |
wills | +0.561 |
Neg logit contributions | |
hatt | -0.754 |
Beer | -0.727 |
coat | -0.664 |
andr | -0.664 |
ness | -0.659 |
Token | USA |
Token ID | 4916 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
orem | +0.286 |
ril | +0.280 |
nerv | +0.269 |
wills | +0.261 |
riors | +0.260 |
Neg logit contributions | |
hatt | -0.282 |
Beer | -0.270 |
andr | -0.244 |
coat | -0.244 |
ness | -0.242 |
Token | Track |
Token ID | 17762 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
orem | +2.297 |
ril | +2.268 |
nerv | +2.200 |
rior | +2.133 |
riors | +2.128 |
Neg logit contributions | |
hatt | -1.466 |
Beer | -1.378 |
andr | -1.224 |
coat | -1.196 |
ness | -1.194 |
Token | & |
Token ID | 1222 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
hatt | +5.794 |
Beer | +5.526 |
coat | +5.078 |
ness | +5.027 |
andr | +4.955 |
Neg logit contributions | |
orem | -7.000 |
ril | -6.816 |
nerv | -6.549 |
wills | -6.433 |
riors | -6.334 |
Token | Field |
Token ID | 7663 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
orem | +1.089 |
ril | +1.065 |
nerv | +1.017 |
riors | +0.983 |
wills | +0.982 |
Neg logit contributions | |
hatt | -1.137 |
Beer | -1.090 |
andr | -0.992 |
coat | -0.986 |
ness | -0.982 |
Token | who |
Token ID | 508 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
hatt | +0.291 |
Beer | +0.279 |
andr | +0.251 |
coat | +0.250 |
ness | +0.248 |
Neg logit contributions | |
orem | -0.323 |
ril | -0.316 |
nerv | -0.303 |
riors | -0.296 |
wills | -0.294 |
Token | now |
Token ID | 783 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
orem | +0.638 |
ril | +0.625 |
nerv | +0.599 |
wills | +0.582 |
riors | +0.581 |
Neg logit contributions | |
hatt | -0.676 |
Beer | -0.651 |
andr | -0.590 |
coat | -0.589 |
ness | -0.583 |
Token | works |
Token ID | 2499 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
orem | +0.827 |
ril | +0.809 |
nerv | +0.771 |
wills | +0.747 |
riors | +0.745 |
Neg logit contributions | |
hatt | -1.033 |
Beer | -0.997 |
andr | -0.915 |
coat | -0.910 |
ness | -0.902 |
Token | Rock |
Token ID | 4631 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
orem | +0.233 |
ril | +0.228 |
nerv | +0.219 |
riors | +0.214 |
wills | +0.213 |
Neg logit contributions | |
hatt | -0.190 |
Beer | -0.182 |
andr | -0.163 |
coat | -0.163 |
ness | -0.161 |
Token | by |
Token ID | 416 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
hatt | +0.046 |
Beer | +0.044 |
andr | +0.040 |
coat | +0.040 |
ness | +0.039 |
Neg logit contributions | |
orem | -0.052 |
ril | -0.051 |
nerv | -0.049 |
riors | -0.048 |
wills | -0.048 |
Token | Conservative |
Token ID | 11132 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
hatt | +0.996 |
Beer | +0.959 |
andr | +0.866 |
coat | +0.861 |
ness | +0.856 |
Neg logit contributions | |
orem | -1.026 |
ril | -1.004 |
nerv | -0.960 |
riors | -0.936 |
wills | -0.934 |
Token | candidate |
Token ID | 4540 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
hatt | +0.758 |
Beer | +0.729 |
andr | +0.660 |
coat | +0.657 |
ness | +0.647 |
Neg logit contributions | |
orem | -0.757 |
ril | -0.742 |
nerv | -0.710 |
riors | -0.693 |
wills | -0.689 |
Token | Dianne |
Token ID | 49197 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
hatt | +1.203 |
Beer | +1.152 |
coat | +1.033 |
andr | +1.032 |
ness | +1.025 |
Neg logit contributions | |
orem | -1.434 |
ril | -1.405 |
nerv | -1.349 |
riors | -1.316 |
wills | -1.311 |
Token | Watts |
Token ID | 27555 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
hatt | +1.788 |
Beer | +1.719 |
coat | +1.562 |
ness | +1.555 |
andr | +1.551 |
Neg logit contributions | |
orem | -1.839 |
ril | -1.800 |
nerv | -1.725 |
riors | -1.679 |
wills | -1.673 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
hatt | +6.019 |
Beer | +5.699 |
ness | +5.307 |
coat | +5.244 |
andr | +5.155 |
Neg logit contributions | |
orem | -6.448 |
ril | -6.287 |
nerv | -5.915 |
riors | -5.855 |
igation | -5.740 |
Token | is |
Token ID | 318 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
hatt | +0.327 |
Beer | +0.314 |
andr | +0.284 |
coat | +0.283 |
ness | +0.281 |
Neg logit contributions | |
orem | -0.336 |
ril | -0.329 |
nerv | -0.315 |
riors | -0.307 |
wills | -0.306 |
Token | being |
Token ID | 852 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
hatt | +0.682 |
Beer | +0.655 |
andr | +0.590 |
coat | +0.590 |
ness | +0.586 |
Neg logit contributions | |
orem | -0.742 |
ril | -0.726 |
nerv | -0.696 |
riors | -0.678 |
wills | -0.675 |
Token | called |
Token ID | 1444 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
orem | +0.177 |
ril | +0.173 |
nerv | +0.166 |
riors | +0.160 |
wills | +0.160 |
Neg logit contributions | |
hatt | -0.194 |
Beer | -0.188 |
andr | -0.171 |
coat | -0.170 |
ness | -0.169 |
Token | absurd |
Token ID | 12986 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
orem | +0.881 |
ril | +0.868 |
nerv | +0.834 |
riors | +0.809 |
wills | +0.807 |
Neg logit contributions | |
hatt | -0.815 |
Beer | -0.781 |
andr | -0.706 |
coat | -0.702 |
ness | -0.693 |
Token | / |
Token ID | 14 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
hatt | +3.074 |
Beer | +2.939 |
ness | +2.710 |
coat | +2.697 |
andr | +2.670 |
Neg logit contributions | |
orem | -3.163 |
ril | -3.081 |
nerv | -2.953 |
riors | -2.900 |
igation | -2.861 |
Token | new |
Token ID | 3605 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
hatt | +1.364 |
Beer | +1.306 |
coat | +1.172 |
andr | +1.171 |
ness | +1.164 |
Neg logit contributions | |
orem | -1.612 |
ril | -1.577 |
nerv | -1.516 |
riors | -1.478 |
wills | -1.473 |
Token | - |
Token ID | 12 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
hatt | +1.471 |
Beer | +1.411 |
coat | +1.279 |
ness | +1.277 |
andr | +1.269 |
Neg logit contributions | |
orem | -1.746 |
ril | -1.695 |
nerv | -1.636 |
riors | -1.593 |
wills | -1.587 |
Token | age |
Token ID | 496 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
hatt | +0.296 |
Beer | +0.287 |
andr | +0.247 |
coat | +0.241 |
ness | +0.233 |
Neg logit contributions | |
ril | -0.506 |
orem | -0.505 |
riors | -0.475 |
nerv | -0.474 |
wills | -0.468 |
Token | music |
Token ID | 2647 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
hatt | +1.098 |
Beer | +1.055 |
andr | +0.953 |
coat | +0.953 |
ness | +0.946 |
Neg logit contributions | |
orem | -1.140 |
ril | -1.116 |
nerv | -1.069 |
riors | -1.040 |
wills | -1.036 |
Token | tracks |
Token ID | 8339 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
hatt | +2.465 |
Beer | +2.355 |
ness | +2.154 |
coat | +2.149 |
andr | +2.143 |
Neg logit contributions | |
orem | -2.553 |
ril | -2.479 |
nerv | -2.376 |
riors | -2.320 |
wills | -2.296 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
hatt | +5.930 |
Beer | +5.627 |
ness | +5.291 |
coat | +5.210 |
andr | +5.113 |
Neg logit contributions | |
orem | -6.366 |
ril | -6.118 |
nerv | -5.798 |
riors | -5.763 |
rior | -5.670 |
Token | many |
Token ID | 867 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
hatt | +0.250 |
Beer | +0.240 |
coat | +0.218 |
andr | +0.218 |
ness | +0.217 |
Neg logit contributions | |
orem | -0.241 |
ril | -0.235 |
nerv | -0.225 |
riors | -0.219 |
wills | -0.218 |
Token | photos |
Token ID | 5205 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
orem | +1.517 |
ril | +1.482 |
nerv | +1.433 |
wills | +1.391 |
riors | +1.381 |
Neg logit contributions | |
hatt | -1.471 |
Beer | -1.422 |
andr | -1.285 |
coat | -1.271 |
ness | -1.252 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
hatt | +1.054 |
Beer | +1.008 |
coat | +0.913 |
andr | +0.912 |
ness | +0.910 |
Neg logit contributions | |
orem | -1.119 |
ril | -1.090 |
nerv | -1.043 |
riors | -1.019 |
wills | -1.014 |
Token | m |
Token ID | 285 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
hatt | +0.022 |
Beer | +0.021 |
andr | +0.019 |
coat | +0.019 |
ness | +0.019 |
Neg logit contributions | |
orem | -0.022 |
ril | -0.021 |
nerv | -0.021 |
wills | -0.020 |
riors | -0.020 |
Token | following |
Token ID | 1708 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
hatt | +0.542 |
Beer | +0.521 |
coat | +0.471 |
andr | +0.470 |
ness | +0.468 |
Neg logit contributions | |
orem | -0.576 |
ril | -0.565 |
nerv | -0.538 |
riors | -0.527 |
wills | -0.523 |
Token | pioneering |
Token ID | 36304 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
hatt | +1.403 |
Beer | +1.346 |
andr | +1.221 |
coat | +1.221 |
ness | +1.221 |
Neg logit contributions | |
orem | -1.416 |
ril | -1.388 |
nerv | -1.328 |
riors | -1.297 |
wills | -1.286 |
Token | authors |
Token ID | 7035 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
hatt | +1.574 |
Beer | +1.514 |
coat | +1.374 |
andr | +1.373 |
ness | +1.372 |
Neg logit contributions | |
orem | -1.537 |
ril | -1.504 |
nerv | -1.435 |
riors | -1.401 |
wills | -1.389 |
Token | such |
Token ID | 884 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
hatt | +0.705 |
Beer | +0.677 |
coat | +0.610 |
andr | +0.610 |
ness | +0.606 |
Neg logit contributions | |
orem | -0.765 |
ril | -0.749 |
nerv | -0.718 |
riors | -0.699 |
wills | -0.696 |
Token | as |
Token ID | 355 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
hatt | +1.637 |
Beer | +1.580 |
andr | +1.442 |
coat | +1.442 |
ness | +1.427 |
Neg logit contributions | |
orem | -1.368 |
ril | -1.336 |
nerv | -1.275 |
riors | -1.235 |
wills | -1.230 |
Token | Hansen |
Token ID | 27667 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
hatt | +0.583 |
Beer | +0.560 |
coat | +0.505 |
andr | +0.505 |
ness | +0.502 |
Neg logit contributions | |
orem | -0.615 |
ril | -0.602 |
nerv | -0.576 |
riors | -0.561 |
wills | -0.559 |
Token | ( |
Token ID | 357 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
hatt | +5.089 |
Beer | +4.697 |
ness | +4.342 |
coat | +4.277 |
andr | +4.203 |
Neg logit contributions | |
orem | -7.098 |
ril | -6.920 |
riors | -6.621 |
nerv | -6.581 |
wills | -6.528 |
Token | 1984 |
Token ID | 28296 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
hatt | +2.090 |
Beer | +2.002 |
coat | +1.789 |
andr | +1.786 |
ness | +1.776 |
Neg logit contributions | |
orem | -2.592 |
ril | -2.537 |
nerv | -2.444 |
riors | -2.383 |
wills | -2.376 |
Token | ), |
Token ID | 828 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
hatt | +1.487 |
Beer | +1.417 |
coat | +1.272 |
andr | +1.271 |
ness | +1.267 |
Neg logit contributions | |
orem | -1.857 |
ril | -1.812 |
nerv | -1.738 |
riors | -1.706 |
wills | -1.699 |
Token | assume |
Token ID | 7048 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
orem | +0.659 |
ril | +0.643 |
nerv | +0.618 |
riors | +0.598 |
wills | +0.597 |
Neg logit contributions | |
hatt | -0.646 |
Beer | -0.622 |
andr | -0.562 |
coat | -0.562 |
ness | -0.557 |
Token | that |
Token ID | 326 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
orem | +0.083 |
ril | +0.081 |
nerv | +0.077 |
riors | +0.075 |
wills | +0.075 |
Neg logit contributions | |
hatt | -0.079 |
Beer | -0.076 |
coat | -0.069 |
andr | -0.069 |
ness | -0.068 |
Token | ; |
Token ID | 26 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
hatt | +1.092 |
Beer | +1.049 |
coat | +0.947 |
andr | +0.946 |
ness | +0.940 |
Neg logit contributions | |
orem | -1.164 |
ril | -1.140 |
nerv | -1.093 |
riors | -1.064 |
wills | -1.058 |
Token | ten |
Token ID | 3478 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
orem | +0.836 |
ril | +0.822 |
nerv | +0.790 |
riors | +0.765 |
wills | +0.762 |
Neg logit contributions | |
hatt | -0.819 |
Beer | -0.788 |
andr | -0.713 |
coat | -0.712 |
ness | -0.704 |
Token | confident |
Token ID | 6563 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
orem | +0.616 |
ril | +0.604 |
nerv | +0.574 |
riors | +0.558 |
wills | +0.556 |
Neg logit contributions | |
hatt | -0.638 |
Beer | -0.615 |
andr | -0.559 |
coat | -0.557 |
ness | -0.550 |
Token | , |
Token ID | 11 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
hatt | +0.635 |
Beer | +0.609 |
coat | +0.548 |
andr | +0.548 |
ness | +0.544 |
Neg logit contributions | |
orem | -0.709 |
ril | -0.694 |
nerv | -0.665 |
riors | -0.648 |
wills | -0.646 |
Token | cinematic |
Token ID | 29932 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
orem | +0.133 |
ril | +0.130 |
nerv | +0.125 |
riors | +0.122 |
wills | +0.122 |
Neg logit contributions | |
hatt | -0.109 |
Beer | -0.105 |
andr | -0.094 |
coat | -0.094 |
ness | -0.093 |
Token | tracks |
Token ID | 8339 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
orem | +1.609 |
ril | +1.585 |
nerv | +1.530 |
wills | +1.483 |
riors | +1.483 |
Neg logit contributions | |
hatt | -1.484 |
Beer | -1.433 |
andr | -1.292 |
coat | -1.290 |
ness | -1.254 |
Token | for |
Token ID | 329 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
hatt | +5.705 |
Beer | +5.370 |
ness | +5.076 |
coat | +5.017 |
andr | +4.876 |
Neg logit contributions | |
orem | -6.491 |
ril | -6.212 |
riors | -5.777 |
nerv | -5.773 |
wills | -5.716 |
Token | young |
Token ID | 1862 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
hatt | +0.019 |
Beer | +0.019 |
andr | +0.017 |
coat | +0.017 |
ness | +0.017 |
Neg logit contributions | |
orem | -0.020 |
ril | -0.019 |
nerv | -0.019 |
riors | -0.018 |
wills | -0.018 |
Token | st |
Token ID | 336 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
hatt | +0.848 |
Beer | +0.813 |
andr | +0.731 |
coat | +0.730 |
ness | +0.718 |
Neg logit contributions | |
orem | -0.971 |
ril | -0.952 |
nerv | -0.918 |
riors | -0.891 |
wills | -0.888 |
Token | on |
Token ID | 261 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
hatt | +1.581 |
Beer | +1.509 |
andr | +1.365 |
coat | +1.361 |
ness | +1.360 |
Neg logit contributions | |
orem | -1.735 |
ril | -1.695 |
nerv | -1.639 |
wills | -1.597 |
riors | -1.589 |
Token | ers |
Token ID | 364 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
orem | +0.242 |
ril | +0.238 |
nerv | +0.229 |
riors | +0.225 |
wills | +0.223 |
Neg logit contributions | |
hatt | -0.137 |
Beer | -0.130 |
andr | -0.113 |
coat | -0.113 |
ness | -0.111 |
Token | country |
Token ID | 1499 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
hatt | +0.145 |
Beer | +0.139 |
coat | +0.126 |
andr | +0.126 |
ness | +0.126 |
Neg logit contributions | |
orem | -0.147 |
ril | -0.144 |
nerv | -0.137 |
riors | -0.134 |
wills | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
hatt | +1.729 |
Beer | +1.652 |
coat | +1.496 |
ness | +1.489 |
andr | +1.482 |
Neg logit contributions | |
orem | -1.940 |
ril | -1.886 |
nerv | -1.806 |
riors | -1.765 |
wills | -1.761 |
Token | To |
Token ID | 1675 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
hatt | +0.331 |
Beer | +0.319 |
coat | +0.287 |
andr | +0.287 |
ness | +0.286 |
Neg logit contributions | |
orem | -0.351 |
ril | -0.342 |
nerv | -0.329 |
riors | -0.320 |
wills | -0.319 |
Token | help |
Token ID | 1037 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
hatt | +1.308 |
Beer | +1.257 |
coat | +1.142 |
andr | +1.140 |
ness | +1.136 |
Neg logit contributions | |
orem | -1.281 |
ril | -1.251 |
nerv | -1.197 |
riors | -1.165 |
wills | -1.161 |
Token | you |
Token ID | 345 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
hatt | +0.032 |
Beer | +0.030 |
coat | +0.028 |
andr | +0.028 |
ness | +0.027 |
Neg logit contributions | |
orem | -0.031 |
ril | -0.031 |
nerv | -0.029 |
riors | -0.028 |
wills | -0.028 |
Token | track |
Token ID | 2610 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
hatt | +1.629 |
Beer | +1.557 |
ness | +1.410 |
coat | +1.410 |
andr | +1.408 |
Neg logit contributions | |
orem | -1.770 |
ril | -1.730 |
nerv | -1.657 |
riors | -1.615 |
wills | -1.612 |
Token | down |
Token ID | 866 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
hatt | +5.272 |
Beer | +4.931 |
ness | +4.556 |
coat | +4.528 |
andr | +4.434 |
Neg logit contributions | |
orem | -6.550 |
ril | -6.392 |
nerv | -6.086 |
riors | -5.983 |
igation | -5.869 |
Token | a |
Token ID | 257 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
hatt | +0.190 |
Beer | +0.183 |
coat | +0.165 |
andr | +0.165 |
ness | +0.164 |
Neg logit contributions | |
orem | -0.186 |
ril | -0.181 |
nerv | -0.173 |
riors | -0.169 |
wills | -0.168 |
Token | copy |
Token ID | 4866 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
hatt | +0.384 |
Beer | +0.370 |
coat | +0.338 |
andr | +0.337 |
ness | +0.336 |
Neg logit contributions | |
orem | -0.330 |
ril | -0.322 |
nerv | -0.307 |
riors | -0.298 |
wills | -0.296 |
Token | of |
Token ID | 286 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
hatt | +0.839 |
Beer | +0.803 |
coat | +0.732 |
ness | +0.731 |
andr | +0.730 |
Neg logit contributions | |
orem | -0.851 |
ril | -0.831 |
nerv | -0.794 |
riors | -0.773 |
wills | -0.772 |
Token | your |
Token ID | 534 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
hatt | +0.516 |
Beer | +0.495 |
coat | +0.447 |
andr | +0.446 |
ness | +0.444 |
Neg logit contributions | |
orem | -0.556 |
ril | -0.545 |
nerv | -0.522 |
riors | -0.509 |
wills | -0.506 |
Token | : |
Token ID | 25 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
orem | +0.383 |
ril | +0.377 |
nerv | +0.359 |
riors | +0.351 |
wills | +0.348 |
Neg logit contributions | |
hatt | -0.349 |
Beer | -0.332 |
andr | -0.302 |
coat | -0.300 |
ness | -0.296 |
Token | The |
Token ID | 383 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
orem | +0.969 |
ril | +0.950 |
nerv | +0.908 |
riors | +0.880 |
wills | +0.877 |
Neg logit contributions | |
hatt | -1.002 |
Beer | -0.961 |
coat | -0.874 |
andr | -0.873 |
ness | -0.866 |
Token | Formula |
Token ID | 19639 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
orem | +0.124 |
ril | +0.121 |
nerv | +0.116 |
riors | +0.113 |
wills | +0.112 |
Neg logit contributions | |
hatt | -0.125 |
Beer | -0.120 |
coat | -0.109 |
andr | -0.109 |
ness | -0.107 |
Token | One |
Token ID | 1881 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
hatt | +0.104 |
Beer | +0.100 |
coat | +0.091 |
andr | +0.091 |
ness | +0.090 |
Neg logit contributions | |
orem | -0.095 |
ril | -0.093 |
nerv | -0.089 |
riors | -0.087 |
wills | -0.086 |
Token | race |
Token ID | 3234 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
hatt | +1.899 |
Beer | +1.825 |
coat | +1.652 |
andr | +1.650 |
ness | +1.644 |
Neg logit contributions | |
orem | -1.936 |
ril | -1.894 |
nerv | -1.813 |
riors | -1.765 |
wills | -1.758 |
Token | track |
Token ID | 2610 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
hatt | +3.554 |
Beer | +3.391 |
coat | +3.059 |
ness | +3.031 |
andr | +3.021 |
Neg logit contributions | |
orem | -4.763 |
ril | -4.598 |
nerv | -4.433 |
riors | -4.333 |
wills | -4.319 |
Token | in |
Token ID | 287 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
hatt | +5.294 |
Beer | +5.021 |
ness | +4.658 |
coat | +4.575 |
andr | +4.530 |
Neg logit contributions | |
orem | -6.375 |
ril | -6.182 |
nerv | -5.946 |
riors | -5.772 |
wills | -5.744 |
Token | Mon |
Token ID | 2892 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
hatt | +0.362 |
Beer | +0.348 |
coat | +0.316 |
andr | +0.316 |
ness | +0.314 |
Neg logit contributions | |
orem | -0.352 |
ril | -0.344 |
nerv | -0.329 |
riors | -0.319 |
wills | -0.319 |
Token | za |
Token ID | 4496 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
orem | +0.772 |
ril | +0.759 |
nerv | +0.716 |
riors | +0.705 |
igation | +0.699 |
Neg logit contributions | |
hatt | -0.570 |
Beer | -0.554 |
andr | -0.492 |
coat | -0.490 |
ness | -0.482 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
hatt | +1.531 |
Beer | +1.455 |
coat | +1.300 |
andr | +1.293 |
ness | +1.290 |
Neg logit contributions | |
orem | -2.045 |
ril | -2.002 |
nerv | -1.928 |
riors | -1.889 |
wills | -1.877 |
Token | Italy |
Token ID | 8031 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
hatt | +0.295 |
Beer | +0.285 |
andr | +0.261 |
coat | +0.260 |
ness | +0.258 |
Neg logit contributions | |
orem | -0.247 |
ril | -0.241 |
nerv | -0.230 |
wills | -0.223 |
riors | -0.223 |
Token | stadt |
Token ID | 38863 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
orem | +1.639 |
ril | +1.593 |
nerv | +1.499 |
riors | +1.456 |
wills | +1.450 |
Neg logit contributions | |
hatt | -2.101 |
Beer | -2.050 |
coat | -1.857 |
andr | -1.848 |
ness | -1.837 |
Token | 04 |
Token ID | 8702 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
hatt | +2.235 |
Beer | +2.136 |
andr | +1.923 |
coat | +1.918 |
ness | +1.915 |
Neg logit contributions | |
orem | -2.719 |
ril | -2.655 |
nerv | -2.538 |
wills | -2.491 |
riors | -2.487 |
Token | , |
Token ID | 11 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
hatt | +0.848 |
Beer | +0.813 |
coat | +0.731 |
andr | +0.729 |
ness | +0.722 |
Neg logit contributions | |
orem | -0.977 |
ril | -0.959 |
nerv | -0.923 |
riors | -0.897 |
wills | -0.891 |
Token | Ed |
Token ID | 1717 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
hatt | +0.106 |
Beer | +0.102 |
coat | +0.092 |
andr | +0.092 |
ness | +0.091 |
Neg logit contributions | |
orem | -0.108 |
ril | -0.106 |
nerv | -0.102 |
riors | -0.099 |
wills | -0.098 |
Token | son |
Token ID | 1559 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
hatt | +0.731 |
Beer | +0.699 |
andr | +0.629 |
coat | +0.628 |
ness | +0.625 |
Neg logit contributions | |
orem | -0.847 |
ril | -0.827 |
nerv | -0.796 |
riors | -0.776 |
wills | -0.774 |
Token | Budd |
Token ID | 8578 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
hatt | +0.456 |
Beer | +0.440 |
coat | +0.396 |
andr | +0.391 |
ness | +0.389 |
Neg logit contributions | |
orem | -0.508 |
ril | -0.499 |
nerv | -0.477 |
riors | -0.465 |
wills | -0.462 |
Token | le |
Token ID | 293 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
hatt | +4.689 |
Beer | +4.361 |
ness | +4.028 |
andr | +3.915 |
coat | +3.911 |
Neg logit contributions | |
orem | -7.082 |
ril | -6.855 |
nerv | -6.498 |
wills | -6.483 |
riors | -6.477 |
Token | � |
Token ID | 447 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
hatt | +0.543 |
Beer | +0.521 |
coat | +0.468 |
andr | +0.468 |
ness | +0.465 |
Neg logit contributions | |
orem | -0.617 |
ril | -0.604 |
nerv | -0.580 |
riors | -0.565 |
wills | -0.563 |
Token | � |
Token ID | 247 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
orem | +0.271 |
ril | +0.265 |
nerv | +0.252 |
riors | +0.245 |
wills | +0.242 |
Neg logit contributions | |
hatt | -0.331 |
Beer | -0.319 |
coat | -0.292 |
andr | -0.292 |
ness | -0.290 |
Token | s |
Token ID | 82 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
hatt | +0.178 |
Beer | +0.168 |
coat | +0.145 |
andr | +0.144 |
ness | +0.142 |
Neg logit contributions | |
orem | -0.328 |
ril | -0.323 |
nerv | -0.311 |
riors | -0.306 |
wills | -0.303 |
Token | current |
Token ID | 1459 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
orem | +0.783 |
ril | +0.763 |
nerv | +0.739 |
riors | +0.718 |
wills | +0.707 |
Neg logit contributions | |
hatt | -0.713 |
Beer | -0.687 |
coat | -0.616 |
andr | -0.610 |
ness | -0.603 |
Token | yesterday |
Token ID | 7415 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
hatt | +0.464 |
Beer | +0.446 |
andr | +0.403 |
coat | +0.403 |
ness | +0.400 |
Neg logit contributions | |
orem | -0.468 |
ril | -0.458 |
nerv | -0.439 |
riors | -0.426 |
wills | -0.426 |
Token | to |
Token ID | 284 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
hatt | +0.434 |
Beer | +0.417 |
andr | +0.375 |
coat | +0.374 |
ness | +0.371 |
Neg logit contributions | |
orem | -0.495 |
ril | -0.485 |
nerv | -0.465 |
riors | -0.453 |
wills | -0.452 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
hatt | +0.446 |
Beer | +0.428 |
coat | +0.385 |
andr | +0.385 |
ness | +0.383 |
Neg logit contributions | |
orem | -0.493 |
ril | -0.482 |
nerv | -0.462 |
riors | -0.451 |
wills | -0.449 |
Token | latest |
Token ID | 3452 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
hatt | +0.195 |
Beer | +0.187 |
coat | +0.168 |
andr | +0.168 |
ness | +0.166 |
Neg logit contributions | |
orem | -0.235 |
ril | -0.230 |
nerv | -0.222 |
riors | -0.216 |
wills | -0.215 |
Token | race |
Token ID | 3234 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
hatt | +1.798 |
Beer | +1.723 |
ness | +1.561 |
coat | +1.558 |
andr | +1.557 |
Neg logit contributions | |
orem | -1.959 |
ril | -1.916 |
nerv | -1.828 |
riors | -1.784 |
wills | -1.772 |
Token | track |
Token ID | 2610 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
hatt | +3.559 |
Beer | +3.364 |
coat | +3.063 |
andr | +3.031 |
ness | +3.022 |
Neg logit contributions | |
orem | -4.345 |
ril | -4.190 |
nerv | -4.016 |
igation | -3.911 |
wills | -3.907 |
Token | scream |
Token ID | 8196 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
hatt | +5.688 |
Beer | +5.340 |
ness | +5.056 |
coat | +5.034 |
andr | +4.903 |
Neg logit contributions | |
orem | -5.826 |
ril | -5.639 |
nerv | -5.307 |
igation | -5.200 |
wills | -5.152 |
Token | ers |
Token ID | 364 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
orem | +0.169 |
ril | +0.166 |
nerv | +0.159 |
riors | +0.155 |
wills | +0.155 |
Neg logit contributions | |
hatt | -0.159 |
Beer | -0.153 |
coat | -0.137 |
andr | -0.137 |
ness | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
hatt | +0.266 |
Beer | +0.256 |
andr | +0.230 |
coat | +0.230 |
ness | +0.228 |
Neg logit contributions | |
orem | -0.297 |
ril | -0.291 |
nerv | -0.279 |
riors | -0.272 |
wills | -0.271 |
Token | each |
Token ID | 1123 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
hatt | +0.291 |
Beer | +0.279 |
coat | +0.251 |
andr | +0.251 |
ness | +0.249 |
Neg logit contributions | |
orem | -0.338 |
ril | -0.331 |
nerv | -0.318 |
riors | -0.310 |
wills | -0.309 |
Token | with |
Token ID | 351 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
hatt | +0.174 |
Beer | +0.167 |
coat | +0.148 |
andr | +0.148 |
ness | +0.146 |
Neg logit contributions | |
orem | -0.228 |
ril | -0.224 |
nerv | -0.216 |
wills | -0.210 |
riors | -0.210 |
Token | Land |
Token ID | 6379 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
hatt | +2.651 |
Beer | +2.540 |
andr | +2.318 |
coat | +2.301 |
ness | +2.300 |
Neg logit contributions | |
orem | -2.666 |
ril | -2.595 |
nerv | -2.503 |
riors | -2.433 |
wills | -2.423 |
Token | au |
Token ID | 559 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
hatt | +1.009 |
Beer | +0.963 |
coat | +0.875 |
ness | +0.872 |
andr | +0.870 |
Neg logit contributions | |
orem | -1.121 |
ril | -1.092 |
nerv | -1.062 |
riors | -1.028 |
wills | -1.026 |
Token | , |
Token ID | 11 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
hatt | +0.855 |
Beer | +0.817 |
coat | +0.735 |
andr | +0.735 |
ness | +0.731 |
Neg logit contributions | |
orem | -0.995 |
ril | -0.971 |
nerv | -0.933 |
riors | -0.911 |
wills | -0.908 |
Token | including |
Token ID | 1390 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
hatt | +0.686 |
Beer | +0.659 |
coat | +0.595 |
andr | +0.595 |
ness | +0.592 |
Neg logit contributions | |
orem | -0.739 |
ril | -0.722 |
nerv | -0.691 |
riors | -0.675 |
wills | -0.670 |
Token | sound |
Token ID | 2128 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
hatt | +0.709 |
Beer | +0.680 |
coat | +0.612 |
andr | +0.612 |
ness | +0.609 |
Neg logit contributions | |
orem | -0.798 |
ril | -0.780 |
nerv | -0.748 |
riors | -0.730 |
wills | -0.726 |
Token | tracks |
Token ID | 46074 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
hatt | +0.343 |
Beer | +0.316 |
coat | +0.254 |
andr | +0.253 |
ness | +0.250 |
Neg logit contributions | |
orem | -1.041 |
ril | -1.025 |
nerv | -0.996 |
riors | -0.979 |
wills | -0.976 |
Token | for |
Token ID | 329 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
hatt | +5.319 |
Beer | +5.127 |
ness | +4.731 |
coat | +4.699 |
andr | +4.623 |
Neg logit contributions | |
orem | -6.133 |
ril | -5.853 |
nerv | -5.595 |
riors | -5.510 |
wills | -5.504 |
Token | seasons |
Token ID | 7028 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
hatt | +0.564 |
Beer | +0.542 |
coat | +0.491 |
andr | +0.490 |
ness | +0.488 |
Neg logit contributions | |
orem | -0.580 |
ril | -0.566 |
nerv | -0.542 |
riors | -0.529 |
wills | -0.525 |
Token | 9 |
Token ID | 860 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
hatt | +0.744 |
Beer | +0.716 |
coat | +0.652 |
andr | +0.651 |
ness | +0.648 |
Neg logit contributions | |
orem | -0.679 |
ril | -0.663 |
nerv | -0.632 |
riors | -0.615 |
wills | -0.612 |
Token | through |
Token ID | 832 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
hatt | +0.020 |
Beer | +0.019 |
coat | +0.017 |
andr | +0.017 |
ness | +0.017 |
Neg logit contributions | |
orem | -0.024 |
ril | -0.024 |
nerv | -0.023 |
riors | -0.022 |
wills | -0.022 |
Token | 27 |
Token ID | 2681 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
hatt | +0.446 |
Beer | +0.430 |
coat | +0.391 |
andr | +0.391 |
ness | +0.389 |
Neg logit contributions | |
orem | -0.405 |
ril | -0.395 |
nerv | -0.377 |
riors | -0.366 |
wills | -0.365 |
Token | to |
Token ID | 284 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
hatt | +0.156 |
Beer | +0.151 |
coat | +0.136 |
andr | +0.136 |
ness | +0.134 |
Neg logit contributions | |
orem | -0.158 |
ril | -0.155 |
nerv | -0.149 |
wills | -0.143 |
riors | -0.143 |
Token | be |
Token ID | 307 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
orem | +0.335 |
ril | +0.328 |
nerv | +0.315 |
wills | +0.304 |
riors | +0.303 |
Neg logit contributions | |
hatt | -0.353 |
Beer | -0.342 |
andr | -0.309 |
coat | -0.308 |
ness | -0.305 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
hatt | +0.555 |
Beer | +0.532 |
andr | +0.476 |
coat | +0.476 |
ness | +0.472 |
Neg logit contributions | |
orem | -0.666 |
ril | -0.652 |
nerv | -0.627 |
riors | -0.611 |
wills | -0.609 |
Token | by |
Token ID | 416 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
orem | +0.260 |
ril | +0.254 |
nerv | +0.244 |
riors | +0.237 |
wills | +0.236 |
Neg logit contributions | |
hatt | -0.243 |
Beer | -0.233 |
andr | -0.210 |
coat | -0.210 |
ness | -0.207 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
hatt | +0.664 |
Beer | +0.636 |
coat | +0.570 |
andr | +0.569 |
ness | +0.566 |
Neg logit contributions | |
orem | -0.803 |
ril | -0.787 |
nerv | -0.756 |
riors | -0.737 |
wills | -0.734 |
Token | bump |
Token ID | 13852 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
hatt | +3.410 |
Beer | +3.235 |
ness | +2.944 |
coat | +2.913 |
andr | +2.900 |
Neg logit contributions | |
orem | -4.114 |
ril | -4.015 |
nerv | -3.811 |
riors | -3.789 |
wills | -3.713 |
Token | ing |
Token ID | 278 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
hatt | +2.506 |
Beer | +2.229 |
ness | +1.770 |
coat | +1.752 |
andr | +1.738 |
Neg logit contributions | |
orem | -9.142 |
ril | -8.926 |
nerv | -8.669 |
riors | -8.570 |
wills | -8.480 |
Token | the |
Token ID | 262 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
orem | +0.030 |
ril | +0.030 |
nerv | +0.028 |
wills | +0.028 |
riors | +0.027 |
Neg logit contributions | |
hatt | -0.033 |
Beer | -0.032 |
coat | -0.029 |
andr | -0.029 |
ness | -0.029 |
Token | shif |
Token ID | 7143 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
hatt | +0.206 |
Beer | +0.198 |
andr | +0.178 |
coat | +0.178 |
ness | +0.175 |
Neg logit contributions | |
orem | -0.230 |
ril | -0.225 |
nerv | -0.217 |
wills | -0.211 |
riors | -0.210 |
Token | ter |
Token ID | 353 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
hatt | +0.903 |
Beer | +0.865 |
coat | +0.771 |
andr | +0.770 |
ness | +0.765 |
Neg logit contributions | |
orem | -1.142 |
ril | -1.120 |
nerv | -1.075 |
riors | -1.050 |
wills | -1.045 |
Token | into |
Token ID | 656 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
orem | +0.728 |
ril | +0.715 |
nerv | +0.690 |
wills | +0.668 |
riors | +0.667 |
Neg logit contributions | |
hatt | -0.704 |
Beer | -0.681 |
andr | -0.608 |
coat | -0.607 |
ness | -0.597 |
Token | Rye |
Token ID | 45014 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
hatt | +0.180 |
Beer | +0.173 |
coat | +0.157 |
andr | +0.157 |
ness | +0.155 |
Neg logit contributions | |
orem | -0.177 |
ril | -0.173 |
nerv | -0.166 |
riors | -0.161 |
wills | -0.160 |
Token | House |
Token ID | 2097 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
orem | +0.558 |
ril | +0.545 |
nerv | +0.521 |
riors | +0.508 |
wills | +0.505 |
Neg logit contributions | |
hatt | -0.525 |
Beer | -0.504 |
andr | -0.455 |
coat | -0.454 |
ness | -0.451 |
Token | k |
Token ID | 479 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
hatt | +1.009 |
Beer | +0.965 |
andr | +0.863 |
coat | +0.861 |
ness | +0.854 |
Neg logit contributions | |
orem | -1.256 |
ril | -1.228 |
nerv | -1.182 |
riors | -1.154 |
wills | -1.148 |
Token | art |
Token ID | 433 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
orem | +0.976 |
ril | +0.949 |
nerv | +0.858 |
riors | +0.849 |
rior | +0.839 |
Neg logit contributions | |
hatt | -1.596 |
Beer | -1.562 |
coat | -1.442 |
andr | -1.435 |
ness | -1.434 |
Token | ing |
Token ID | 278 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
orem | +1.206 |
ril | +1.187 |
nerv | +1.144 |
riors | +1.132 |
igation | +1.121 |
Neg logit contributions | |
hatt | -0.450 |
Beer | -0.416 |
andr | -0.347 |
coat | -0.335 |
ness | -0.325 |
Token | track |
Token ID | 2610 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
orem | +0.314 |
ril | +0.306 |
nerv | +0.295 |
riors | +0.289 |
wills | +0.286 |
Neg logit contributions | |
hatt | -0.282 |
Beer | -0.270 |
andr | -0.245 |
coat | -0.241 |
ness | -0.240 |
Token | in |
Token ID | 287 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
hatt | +5.053 |
Beer | +4.821 |
coat | +4.402 |
ness | +4.337 |
andr | +4.323 |
Neg logit contributions | |
orem | -6.219 |
ril | -6.138 |
nerv | -5.861 |
wills | -5.736 |
riors | -5.683 |
Token | Hert |
Token ID | 40030 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
hatt | +0.277 |
Beer | +0.266 |
andr | +0.242 |
coat | +0.242 |
ness | +0.240 |
Neg logit contributions | |
orem | -0.261 |
ril | -0.255 |
nerv | -0.245 |
wills | -0.237 |
riors | -0.237 |
Token | ford |
Token ID | 3841 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
hatt | +0.642 |
Beer | +0.614 |
coat | +0.555 |
ness | +0.553 |
andr | +0.552 |
Neg logit contributions | |
orem | -0.745 |
ril | -0.725 |
nerv | -0.702 |
riors | -0.682 |
wills | -0.681 |
Token | shire |
Token ID | 10932 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
orem | +0.270 |
ril | +0.265 |
nerv | +0.251 |
riors | +0.244 |
wills | +0.243 |
Neg logit contributions | |
hatt | -0.328 |
Beer | -0.317 |
andr | -0.290 |
coat | -0.289 |
ness | -0.287 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
hatt | +0.052 |
Beer | +0.050 |
andr | +0.045 |
coat | +0.045 |
ness | +0.044 |
Neg logit contributions | |
orem | -0.056 |
ril | -0.055 |
nerv | -0.053 |
riors | -0.051 |
wills | -0.051 |
Token | een |
Token ID | 6429 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
hatt | +0.680 |
Beer | +0.658 |
coat | +0.603 |
andr | +0.602 |
ness | +0.598 |
Neg logit contributions | |
orem | -0.531 |
ril | -0.519 |
nerv | -0.489 |
riors | -0.476 |
wills | -0.473 |
Token | , |
Token ID | 11 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
hatt | +0.500 |
Beer | +0.481 |
coat | +0.438 |
andr | +0.437 |
ness | +0.435 |
Neg logit contributions | |
orem | -0.464 |
ril | -0.454 |
nerv | -0.433 |
riors | -0.421 |
wills | -0.419 |
Token | run |
Token ID | 1057 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
orem | +0.074 |
ril | +0.072 |
nerv | +0.070 |
riors | +0.068 |
wills | +0.068 |
Neg logit contributions | |
hatt | -0.065 |
Beer | -0.063 |
andr | -0.056 |
coat | -0.056 |
ness | -0.056 |
Token | by |
Token ID | 416 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
hatt | +0.788 |
Beer | +0.758 |
coat | +0.684 |
andr | +0.683 |
ness | +0.681 |
Neg logit contributions | |
orem | -0.836 |
ril | -0.816 |
nerv | -0.782 |
riors | -0.762 |
wills | -0.760 |
Token | Indian |
Token ID | 3942 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
hatt | +1.292 |
Beer | +1.240 |
coat | +1.123 |
andr | +1.122 |
ness | +1.117 |
Neg logit contributions | |
orem | -1.325 |
ril | -1.297 |
nerv | -1.241 |
riors | -1.209 |
wills | -1.200 |
Token | Rail |
Token ID | 12950 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
hatt | +0.506 |
Beer | +0.487 |
coat | +0.442 |
andr | +0.442 |
ness | +0.440 |
Neg logit contributions | |
orem | -0.489 |
ril | -0.478 |
nerv | -0.457 |
riors | -0.444 |
wills | -0.442 |
Token | ways |
Token ID | 1322 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
hatt | +2.240 |
Beer | +2.020 |
andr | +1.571 |
coat | +1.551 |
ness | +1.551 |
Neg logit contributions | |
orem | -9.024 |
ril | -8.936 |
nerv | -8.731 |
wills | -8.558 |
riors | -8.486 |
Token | , |
Token ID | 11 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
hatt | +2.032 |
Beer | +1.953 |
coat | +1.761 |
andr | +1.759 |
ness | +1.756 |
Neg logit contributions | |
orem | -2.240 |
ril | -2.193 |
nerv | -2.104 |
riors | -2.052 |
wills | -2.037 |
Token | operates |
Token ID | 14051 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
hatt | +0.491 |
Beer | +0.473 |
coat | +0.430 |
andr | +0.430 |
ness | +0.428 |
Neg logit contributions | |
orem | -0.445 |
ril | -0.435 |
nerv | -0.415 |
riors | -0.403 |
wills | -0.401 |
Token | from |
Token ID | 422 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
hatt | +0.125 |
Beer | +0.120 |
andr | +0.109 |
coat | +0.109 |
ness | +0.108 |
Neg logit contributions | |
orem | -0.131 |
ril | -0.128 |
nerv | -0.123 |
riors | -0.120 |
wills | -0.120 |
Token | Room |
Token ID | 10096 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
hatt | +0.465 |
Beer | +0.448 |
coat | +0.405 |
andr | +0.405 |
ness | +0.403 |
Neg logit contributions | |
orem | -0.463 |
ril | -0.452 |
nerv | -0.433 |
riors | -0.421 |
wills | -0.419 |
Token | . |
Token ID | 13 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
hatt | +0.518 |
Beer | +0.497 |
coat | +0.447 |
andr | +0.447 |
ness | +0.444 |
Neg logit contributions | |
orem | -0.584 |
ril | -0.571 |
nerv | -0.548 |
riors | -0.534 |
wills | -0.532 |
Token | With |
Token ID | 2080 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
orem | +0.073 |
ril | +0.072 |
nerv | +0.069 |
riors | +0.067 |
wills | +0.067 |
Neg logit contributions | |
hatt | -0.070 |
Beer | -0.067 |
coat | -0.061 |
andr | -0.061 |
ness | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
hatt | +0.506 |
Beer | +0.489 |
andr | +0.440 |
coat | +0.440 |
ness | +0.435 |
Neg logit contributions | |
orem | -0.534 |
ril | -0.522 |
nerv | -0.503 |
riors | -0.488 |
wills | -0.487 |
Token | new |
Token ID | 649 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
orem | +0.071 |
ril | +0.069 |
nerv | +0.067 |
wills | +0.064 |
riors | +0.064 |
Neg logit contributions | |
hatt | -0.066 |
Beer | -0.063 |
andr | -0.057 |
coat | -0.057 |
ness | -0.056 |
Token | forecast |
Token ID | 11092 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
hatt | +0.595 |
Beer | +0.574 |
andr | +0.514 |
coat | +0.510 |
ness | +0.499 |
Neg logit contributions | |
orem | -0.690 |
ril | -0.673 |
nerv | -0.652 |
wills | -0.632 |
riors | -0.629 |
Token | track |
Token ID | 2610 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
hatt | +1.675 |
Beer | +1.604 |
coat | +1.438 |
andr | +1.435 |
ness | +1.431 |
Neg logit contributions | |
orem | -2.019 |
ril | -1.976 |
nerv | -1.897 |
riors | -1.853 |
wills | -1.844 |
Token | shifting |
Token ID | 15852 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
hatt | +5.049 |
Beer | +4.778 |
ness | +4.441 |
coat | +4.383 |
andr | +4.266 |
Neg logit contributions | |
orem | -6.170 |
ril | -6.036 |
nerv | -5.752 |
riors | -5.641 |
wills | -5.613 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
hatt | +1.248 |
Beer | +1.195 |
coat | +1.075 |
andr | +1.074 |
ness | +1.070 |
Neg logit contributions | |
orem | -1.425 |
ril | -1.395 |
nerv | -1.338 |
riors | -1.305 |
wills | -1.298 |
Token | cone |
Token ID | 27763 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
hatt | +0.164 |
Beer | +0.157 |
andr | +0.141 |
coat | +0.140 |
ness | +0.139 |
Neg logit contributions | |
orem | -0.196 |
ril | -0.191 |
nerv | -0.184 |
wills | -0.179 |
riors | -0.179 |
Token | of |
Token ID | 286 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
orem | +0.400 |
ril | +0.393 |
nerv | +0.376 |
wills | +0.366 |
riors | +0.365 |
Neg logit contributions | |
hatt | -0.395 |
Beer | -0.382 |
andr | -0.344 |
coat | -0.343 |
ness | -0.338 |
Token | concern |
Token ID | 2328 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
hatt | +0.321 |
Beer | +0.309 |
andr | +0.280 |
coat | +0.279 |
ness | +0.275 |
Neg logit contributions | |
orem | -0.322 |
ril | -0.315 |
nerv | -0.303 |
wills | -0.294 |
riors | -0.293 |
Token | equipment |
Token ID | 5112 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
hatt | +0.626 |
Beer | +0.602 |
andr | +0.544 |
coat | +0.543 |
ness | +0.538 |
Neg logit contributions | |
orem | -0.648 |
ril | -0.634 |
nerv | -0.606 |
wills | -0.590 |
riors | -0.589 |
Token | regulations |
Token ID | 6647 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
hatt | +1.762 |
Beer | +1.692 |
coat | +1.532 |
andr | +1.530 |
ness | +1.523 |
Neg logit contributions | |
orem | -1.825 |
ril | -1.786 |
nerv | -1.710 |
riors | -1.664 |
wills | -1.656 |
Token | borrowed |
Token ID | 22546 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
hatt | +2.214 |
Beer | +2.122 |
coat | +1.910 |
andr | +1.908 |
ness | +1.903 |
Neg logit contributions | |
orem | -2.487 |
ril | -2.436 |
nerv | -2.336 |
riors | -2.278 |
wills | -2.266 |
Token | from |
Token ID | 422 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
hatt | +0.603 |
Beer | +0.579 |
coat | +0.524 |
andr | +0.523 |
ness | +0.520 |
Neg logit contributions | |
orem | -0.625 |
ril | -0.611 |
nerv | -0.585 |
riors | -0.570 |
wills | -0.567 |
Token | modern |
Token ID | 3660 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
hatt | +0.243 |
Beer | +0.233 |
coat | +0.211 |
andr | +0.211 |
ness | +0.209 |
Neg logit contributions | |
orem | -0.238 |
ril | -0.232 |
nerv | -0.223 |
wills | -0.216 |
riors | -0.215 |
Token | track |
Token ID | 2610 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
orem | +1.626 |
ril | +1.571 |
nerv | +1.512 |
wills | +1.489 |
riors | +1.471 |
Neg logit contributions | |
hatt | -1.311 |
Beer | -1.254 |
andr | -1.115 |
coat | -1.106 |
ness | -1.072 |
Token | pursuit |
Token ID | 14748 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
hatt | +5.098 |
Beer | +4.877 |
coat | +4.464 |
ness | +4.431 |
andr | +4.342 |
Neg logit contributions | |
orem | -6.088 |
ril | -5.967 |
nerv | -5.714 |
riors | -5.583 |
wills | -5.537 |
Token | bikes |
Token ID | 16715 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
hatt | +1.043 |
Beer | +0.998 |
coat | +0.892 |
andr | +0.891 |
ness | +0.886 |
Neg logit contributions | |
orem | -1.300 |
ril | -1.274 |
nerv | -1.224 |
riors | -1.195 |
wills | -1.190 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
hatt | +1.524 |
Beer | +1.450 |
coat | +1.306 |
andr | +1.301 |
ness | +1.301 |
Neg logit contributions | |
orem | -1.855 |
ril | -1.821 |
nerv | -1.744 |
wills | -1.704 |
riors | -1.703 |
Token | UC |
Token ID | 14417 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
hatt | +0.177 |
Beer | +0.170 |
andr | +0.154 |
coat | +0.154 |
ness | +0.153 |
Neg logit contributions | |
orem | -0.181 |
ril | -0.178 |
nerv | -0.170 |
riors | -0.166 |
wills | -0.164 |
Token | I |
Token ID | 40 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
hatt | +1.270 |
Beer | +1.214 |
andr | +1.073 |
coat | +1.072 |
ness | +1.065 |
Neg logit contributions | |
orem | -1.809 |
ril | -1.774 |
nerv | -1.711 |
riors | -1.671 |
wills | -1.664 |
Token | philosopher |
Token ID | 23723 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
orem | +1.513 |
ril | +1.470 |
nerv | +1.420 |
riors | +1.380 |
wills | +1.376 |
Neg logit contributions | |
hatt | -1.575 |
Beer | -1.520 |
coat | -1.382 |
andr | -1.376 |
ness | -1.336 |
Token | - |
Token ID | 12 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
orem | +2.997 |
ril | +2.958 |
nerv | +2.836 |
riors | +2.789 |
wills | +2.748 |
Neg logit contributions | |
hatt | -2.864 |
Beer | -2.782 |
andr | -2.513 |
coat | -2.501 |
ness | -2.458 |
Token | k |
Token ID | 74 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
orem | +0.487 |
ril | +0.478 |
nerv | +0.460 |
riors | +0.451 |
wills | +0.448 |
Neg logit contributions | |
hatt | -0.356 |
Beer | -0.342 |
coat | -0.303 |
andr | -0.302 |
ness | -0.299 |
Token | ings |
Token ID | 654 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
orem | +0.912 |
ril | +0.893 |
nerv | +0.863 |
wills | +0.837 |
riors | +0.835 |
Neg logit contributions | |
hatt | -0.746 |
Beer | -0.709 |
andr | -0.636 |
coat | -0.634 |
ness | -0.634 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
hatt | +0.035 |
Beer | +0.034 |
coat | +0.030 |
andr | +0.030 |
ness | +0.030 |
Neg logit contributions | |
orem | -0.042 |
ril | -0.041 |
nerv | -0.039 |
riors | -0.038 |
wills | -0.038 |
Token | Watts |
Token ID | 27555 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
hatt | +0.373 |
Beer | +0.359 |
coat | +0.325 |
andr | +0.325 |
ness | +0.323 |
Neg logit contributions | |
orem | -0.377 |
ril | -0.369 |
nerv | -0.353 |
riors | -0.344 |
wills | -0.342 |
Token | Up |
Token ID | 4933 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
hatt | +5.381 |
Beer | +5.172 |
coat | +4.746 |
ness | +4.709 |
andr | +4.708 |
Neg logit contributions | |
orem | -5.794 |
ril | -5.707 |
nerv | -5.348 |
riors | -5.301 |
terior | -5.222 |
Token | With |
Token ID | 3152 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
hatt | +1.025 |
Beer | +0.969 |
andr | +0.847 |
coat | +0.847 |
ness | +0.836 |
Neg logit contributions | |
orem | -1.721 |
ril | -1.692 |
nerv | -1.632 |
riors | -1.599 |
wills | -1.593 |
Token | That |
Token ID | 2504 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
hatt | +0.859 |
Beer | +0.761 |
andr | +0.725 |
coat | +0.698 |
ness | +0.677 |
Neg logit contributions | |
orem | -1.402 |
ril | -1.400 |
nerv | -1.329 |
igation | -1.315 |
wills | -1.306 |
Token | is |
Token ID | 318 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
hatt | +2.003 |
Beer | +1.931 |
ness | +1.750 |
coat | +1.749 |
andr | +1.745 |
Neg logit contributions | |
orem | -1.967 |
ril | -1.925 |
nerv | -1.842 |
riors | -1.787 |
wills | -1.779 |
Token | now |
Token ID | 783 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
hatt | +0.756 |
Beer | +0.725 |
coat | +0.654 |
andr | +0.653 |
ness | +0.649 |
Neg logit contributions | |
orem | -0.824 |
ril | -0.806 |
nerv | -0.773 |
riors | -0.753 |
wills | -0.750 |
Token | Barack |
Token ID | 8732 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
orem | +1.681 |
ril | +1.644 |
nerv | +1.573 |
riors | +1.545 |
wills | +1.533 |
Neg logit contributions | |
hatt | -1.367 |
Beer | -1.304 |
andr | -1.184 |
coat | -1.166 |
ness | -1.160 |
Token | Obama |
Token ID | 2486 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
hatt | +1.162 |
Beer | +1.117 |
coat | +1.010 |
andr | +1.009 |
ness | +1.003 |
Neg logit contributions | |
orem | -1.199 |
ril | -1.173 |
nerv | -1.123 |
riors | -1.093 |
wills | -1.089 |
Token | gets |
Token ID | 3011 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
hatt | +1.010 |
Beer | +0.970 |
coat | +0.875 |
andr | +0.874 |
ness | +0.870 |
Neg logit contributions | |
orem | -1.084 |
ril | -1.060 |
nerv | -1.015 |
riors | -0.989 |
wills | -0.985 |
Token | fast |
Token ID | 3049 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
hatt | +1.129 |
Beer | +1.084 |
coat | +0.979 |
andr | +0.976 |
ness | +0.972 |
Neg logit contributions | |
orem | -1.222 |
ril | -1.196 |
nerv | -1.144 |
riors | -1.117 |
wills | -1.111 |
Token | - |
Token ID | 12 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
hatt | +1.027 |
Beer | +0.985 |
andr | +0.881 |
coat | +0.878 |
ness | +0.870 |
Neg logit contributions | |
orem | -1.267 |
ril | -1.241 |
nerv | -1.194 |
riors | -1.163 |
wills | -1.161 |
Token | track |
Token ID | 11659 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
hatt | +0.034 |
Beer | +0.032 |
andr | +0.027 |
coat | +0.027 |
ness | +0.027 |
Neg logit contributions | |
orem | -0.068 |
ril | -0.067 |
nerv | -0.064 |
riors | -0.063 |
wills | -0.063 |
Token | approval |
Token ID | 7546 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
hatt | +4.840 |
Beer | +4.619 |
ness | +4.248 |
coat | +4.174 |
andr | +4.038 |
Neg logit contributions | |
orem | -6.302 |
ril | -6.233 |
nerv | -5.997 |
riors | -5.888 |
rior | -5.805 |
Token | for |
Token ID | 329 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
hatt | +2.616 |
Beer | +2.499 |
coat | +2.271 |
ness | +2.269 |
andr | +2.248 |
Neg logit contributions | |
orem | -2.779 |
ril | -2.706 |
nerv | -2.584 |
riors | -2.523 |
wills | -2.508 |
Token | TP |
Token ID | 24525 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
hatt | +0.292 |
Beer | +0.281 |
coat | +0.254 |
andr | +0.254 |
ness | +0.253 |
Neg logit contributions | |
orem | -0.303 |
ril | -0.296 |
nerv | -0.284 |
riors | -0.276 |
wills | -0.275 |
Token | PA |
Token ID | 4537 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
hatt | +0.050 |
Beer | +0.048 |
andr | +0.043 |
coat | +0.043 |
ness | +0.042 |
Neg logit contributions | |
orem | -0.065 |
ril | -0.063 |
nerv | -0.061 |
riors | -0.059 |
wills | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
hatt | +0.639 |
Beer | +0.613 |
andr | +0.555 |
coat | +0.554 |
ness | +0.548 |
Neg logit contributions | |
orem | -0.672 |
ril | -0.658 |
nerv | -0.630 |
riors | -0.614 |
wills | -0.613 |
Token | On |
Token ID | 2202 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
hatt | +0.067 |
Beer | +0.063 |
andr | +0.057 |
coat | +0.057 |
ness | +0.056 |
Neg logit contributions | |
orem | -0.083 |
ril | -0.082 |
nerv | -0.078 |
riors | -0.077 |
igation | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
hatt | +0.860 |
Beer | +0.824 |
coat | +0.749 |
andr | +0.747 |
ness | +0.746 |
Neg logit contributions | |
orem | -0.874 |
ril | -0.854 |
nerv | -0.817 |
riors | -0.797 |
wills | -0.792 |
Token | reverse |
Token ID | 9575 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
hatt | +0.214 |
Beer | +0.207 |
coat | +0.190 |
andr | +0.189 |
ness | +0.189 |
Neg logit contributions | |
orem | -0.174 |
ril | -0.170 |
nerv | -0.162 |
riors | -0.157 |
wills | -0.156 |
Token | side |
Token ID | 1735 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
hatt | +1.339 |
Beer | +1.282 |
coat | +1.162 |
ness | +1.161 |
andr | +1.134 |
Neg logit contributions | |
orem | -1.844 |
ril | -1.809 |
nerv | -1.727 |
riors | -1.704 |
wills | -1.688 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
hatt | +1.404 |
Beer | +1.352 |
coat | +1.237 |
ness | +1.230 |
andr | +1.221 |
Neg logit contributions | |
orem | -1.497 |
ril | -1.464 |
nerv | -1.391 |
riors | -1.361 |
wills | -1.358 |
Token | Watts |
Token ID | 27555 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
hatt | +0.166 |
Beer | +0.160 |
coat | +0.145 |
andr | +0.145 |
ness | +0.144 |
Neg logit contributions | |
orem | -0.161 |
ril | -0.157 |
nerv | -0.150 |
riors | -0.146 |
wills | -0.145 |
Token | is |
Token ID | 318 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
hatt | +5.899 |
Beer | +5.603 |
ness | +5.347 |
coat | +5.180 |
andr | +5.134 |
Neg logit contributions | |
orem | -5.213 |
ril | -5.099 |
nerv | -4.680 |
riors | -4.650 |
igation | -4.604 |
Token | pictured |
Token ID | 17915 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
hatt | +0.911 |
Beer | +0.875 |
coat | +0.796 |
andr | +0.793 |
ness | +0.792 |
Neg logit contributions | |
orem | -0.885 |
ril | -0.864 |
nerv | -0.825 |
riors | -0.805 |
wills | -0.799 |
Token | below |
Token ID | 2174 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
orem | +0.404 |
ril | +0.397 |
nerv | +0.380 |
wills | +0.368 |
riors | +0.368 |
Neg logit contributions | |
hatt | -0.415 |
Beer | -0.401 |
andr | -0.364 |
coat | -0.362 |
ness | -0.358 |
Token | a |
Token ID | 257 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
hatt | +2.228 |
Beer | +2.125 |
coat | +1.947 |
ness | +1.938 |
andr | +1.909 |
Neg logit contributions | |
orem | -2.407 |
ril | -2.340 |
nerv | -2.229 |
riors | -2.196 |
wills | -2.173 |
Token | line |
Token ID | 1627 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
hatt | +0.400 |
Beer | +0.385 |
coat | +0.350 |
ness | +0.348 |
andr | +0.348 |
Neg logit contributions | |
orem | -0.398 |
ril | -0.390 |
nerv | -0.371 |
riors | -0.364 |
wills | -0.360 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
orem | +0.452 |
ril | +0.443 |
nerv | +0.424 |
riors | +0.413 |
wills | +0.410 |
Neg logit contributions | |
hatt | -0.433 |
Beer | -0.415 |
andr | -0.376 |
coat | -0.376 |
ness | -0.373 |
Token |
|
Token ID | 198 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
hatt | +0.305 |
Beer | +0.292 |
andr | +0.269 |
coat | +0.266 |
ness | +0.260 |
Neg logit contributions | |
orem | -0.270 |
ril | -0.267 |
nerv | -0.250 |
riors | -0.247 |
rior | -0.246 |
Token | The |
Token ID | 464 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
orem | +0.138 |
ril | +0.135 |
nerv | +0.128 |
riors | +0.126 |
rior | +0.125 |
Neg logit contributions | |
hatt | -0.113 |
Beer | -0.107 |
andr | -0.097 |
coat | -0.097 |
ness | -0.095 |
Token | renovations |
Token ID | 44481 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
orem | +0.878 |
ril | +0.853 |
nerv | +0.818 |
riors | +0.793 |
wills | +0.793 |
Neg logit contributions | |
hatt | -0.879 |
Beer | -0.845 |
andr | -0.768 |
coat | -0.766 |
ness | -0.759 |
Token | include |
Token ID | 2291 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
orem | +0.011 |
ril | +0.011 |
nerv | +0.010 |
riors | +0.010 |
wills | +0.010 |
Neg logit contributions | |
hatt | -0.011 |
Beer | -0.010 |
coat | -0.009 |
andr | -0.009 |
ness | -0.009 |
Token | bump |
Token ID | 13852 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
orem | +2.279 |
ril | +2.247 |
nerv | +2.151 |
wills | +2.089 |
riors | +2.081 |
Neg logit contributions | |
hatt | -2.260 |
Beer | -2.171 |
andr | -1.974 |
coat | -1.963 |
ness | -1.938 |
Token | ing |
Token ID | 278 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
hatt | +4.703 |
Beer | +4.449 |
coat | +3.987 |
ness | +3.984 |
andr | +3.966 |
Neg logit contributions | |
orem | -6.427 |
ril | -6.235 |
nerv | -6.004 |
riors | -5.922 |
igation | -5.845 |
Token | the |
Token ID | 262 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
orem | +0.485 |
ril | +0.476 |
nerv | +0.459 |
wills | +0.448 |
riors | +0.447 |
Neg logit contributions | |
hatt | -0.357 |
Beer | -0.342 |
andr | -0.303 |
coat | -0.303 |
ness | -0.300 |
Token | capacity |
Token ID | 5339 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
orem | +0.513 |
ril | +0.497 |
nerv | +0.477 |
wills | +0.462 |
riors | +0.460 |
Neg logit contributions | |
hatt | -0.565 |
Beer | -0.545 |
andr | -0.498 |
coat | -0.496 |
ness | -0.492 |
Token | from |
Token ID | 422 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
hatt | +1.201 |
Beer | +1.152 |
coat | +1.038 |
ness | +1.035 |
andr | +1.035 |
Neg logit contributions | |
orem | -1.326 |
ril | -1.299 |
nerv | -1.241 |
riors | -1.213 |
wills | -1.206 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
orem | +0.474 |
ril | +0.463 |
nerv | +0.444 |
riors | +0.430 |
wills | +0.429 |
Neg logit contributions | |
hatt | -0.511 |
Beer | -0.493 |
andr | -0.448 |
coat | -0.448 |
ness | -0.444 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
orem | +1.645 |
ril | +1.598 |
nerv | +1.543 |
wills | +1.490 |
igation | +1.472 |
Neg logit contributions | |
hatt | -1.828 |
Beer | -1.811 |
andr | -1.622 |
coat | -1.619 |
ness | -1.588 |
Token | it |
Token ID | 340 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
orem | +0.576 |
ril | +0.562 |
nerv | +0.537 |
wills | +0.521 |
riors | +0.520 |
Neg logit contributions | |
hatt | -0.639 |
Beer | -0.615 |
coat | -0.561 |
andr | -0.561 |
ness | -0.554 |
Token | listed |
Token ID | 5610 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
orem | +0.512 |
ril | +0.501 |
nerv | +0.480 |
riors | +0.466 |
wills | +0.464 |
Neg logit contributions | |
hatt | -0.500 |
Beer | -0.482 |
andr | -0.435 |
coat | -0.435 |
ness | -0.431 |
Token | for |
Token ID | 329 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
orem | +0.544 |
ril | +0.533 |
nerv | +0.511 |
riors | +0.494 |
wills | +0.494 |
Neg logit contributions | |
hatt | -0.539 |
Beer | -0.521 |
andr | -0.470 |
coat | -0.470 |
ness | -0.465 |
Token | the |
Token ID | 262 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
orem | +0.360 |
ril | +0.352 |
nerv | +0.336 |
riors | +0.326 |
wills | +0.324 |
Neg logit contributions | |
hatt | -0.404 |
Beer | -0.389 |
coat | -0.354 |
andr | -0.354 |
ness | -0.352 |
Token | coax |
Token ID | 37700 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
orem | +0.004 |
ril | +0.004 |
nerv | +0.004 |
riors | +0.004 |
wills | +0.004 |
Neg logit contributions | |
hatt | -0.005 |
Beer | -0.005 |
coat | -0.004 |
andr | -0.004 |
ness | -0.004 |
Token | connection |
Token ID | 4637 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
hatt | +5.804 |
Beer | +5.465 |
ness | +5.162 |
coat | +5.061 |
andr | +5.007 |
Neg logit contributions | |
orem | -5.103 |
ril | -5.035 |
nerv | -4.806 |
riors | -4.710 |
wills | -4.645 |
Token | . |
Token ID | 13 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
orem | +0.253 |
ril | +0.247 |
nerv | +0.237 |
riors | +0.231 |
wills | +0.230 |
Neg logit contributions | |
hatt | -0.225 |
Beer | -0.216 |
andr | -0.194 |
coat | -0.194 |
ness | -0.193 |
Token | Disable |
Token ID | 31529 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
hatt | +0.431 |
Beer | +0.415 |
coat | +0.375 |
andr | +0.375 |
ness | +0.373 |
Neg logit contributions | |
orem | -0.444 |
ril | -0.434 |
nerv | -0.416 |
riors | -0.405 |
wills | -0.404 |
Token | the |
Token ID | 262 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
hatt | +1.295 |
Beer | +1.245 |
coat | +1.132 |
ness | +1.129 |
andr | +1.128 |
Neg logit contributions | |
orem | -1.229 |
ril | -1.205 |
nerv | -1.152 |
riors | -1.122 |
wills | -1.111 |
Token | Wireless |
Token ID | 24365 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
hatt | +0.262 |
Beer | +0.252 |
andr | +0.229 |
coat | +0.229 |
ness | +0.227 |
Neg logit contributions | |
orem | -0.258 |
ril | -0.251 |
nerv | -0.241 |
riors | -0.234 |
wills | -0.233 |
Token |
|
Token ID | 198 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
hatt | +0.375 |
Beer | +0.359 |
andr | +0.331 |
coat | +0.326 |
ness | +0.319 |
Neg logit contributions | |
orem | -0.334 |
ril | -0.329 |
nerv | -0.308 |
riors | -0.305 |
rior | -0.302 |
Token | Ex |
Token ID | 3109 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
hatt | +0.103 |
Beer | +0.097 |
andr | +0.088 |
coat | +0.087 |
ness | +0.086 |
Neg logit contributions | |
orem | -0.137 |
ril | -0.135 |
nerv | -0.128 |
riors | -0.127 |
rior | -0.125 |
Token | amine |
Token ID | 9862 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
orem | +1.389 |
ril | +1.352 |
nerv | +1.273 |
riors | +1.244 |
rior | +1.230 |
Neg logit contributions | |
hatt | -1.774 |
Beer | -1.722 |
andr | -1.573 |
ness | -1.569 |
coat | -1.568 |
Token | all |
Token ID | 477 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
orem | +1.041 |
ril | +1.010 |
nerv | +0.970 |
wills | +0.943 |
riors | +0.937 |
Neg logit contributions | |
hatt | -1.092 |
Beer | -1.054 |
andr | -0.953 |
coat | -0.946 |
ness | -0.941 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
hatt | +0.356 |
Beer | +0.341 |
coat | +0.312 |
andr | +0.310 |
ness | +0.309 |
Neg logit contributions | |
orem | -0.334 |
ril | -0.328 |
nerv | -0.312 |
riors | -0.304 |
wills | -0.302 |
Token | vit |
Token ID | 9090 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
orem | +0.226 |
ril | +0.220 |
nerv | +0.210 |
riors | +0.204 |
wills | +0.204 |
Neg logit contributions | |
hatt | -0.237 |
Beer | -0.228 |
andr | -0.207 |
coat | -0.207 |
ness | -0.206 |
Token | rified |
Token ID | 41301 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ril | +7.498 |
orem | +7.299 |
igation | +6.773 |
riors | +6.720 |
nerv | +6.704 |
Neg logit contributions | |
hatt | -7.334 |
Beer | -7.156 |
coat | -6.375 |
andr | -6.331 |
ness | -6.254 |
Token | test |
Token ID | 1332 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
orem | +0.744 |
ril | +0.725 |
nerv | +0.694 |
wills | +0.673 |
riors | +0.672 |
Neg logit contributions | |
hatt | -0.822 |
Beer | -0.792 |
andr | -0.720 |
coat | -0.719 |
ness | -0.711 |
Token | chamber |
Token ID | 11847 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
hatt | +0.197 |
Beer | +0.189 |
coat | +0.171 |
andr | +0.170 |
ness | +0.170 |
Neg logit contributions | |
orem | -0.223 |
ril | -0.218 |
nerv | -0.210 |
riors | -0.204 |
wills | -0.203 |
Token | doors |
Token ID | 8215 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
hatt | +0.102 |
Beer | +0.098 |
andr | +0.089 |
coat | +0.089 |
ness | +0.088 |
Neg logit contributions | |
orem | -0.101 |
ril | -0.099 |
nerv | -0.095 |
riors | -0.092 |
wills | -0.092 |
Token | ( |
Token ID | 357 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
orem | +0.634 |
ril | +0.620 |
nerv | +0.595 |
riors | +0.576 |
wills | +0.574 |
Neg logit contributions | |
hatt | -0.635 |
Beer | -0.614 |
andr | -0.555 |
coat | -0.552 |
ness | -0.547 |
Token | is |
Token ID | 318 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
orem | +0.340 |
ril | +0.332 |
nerv | +0.317 |
riors | +0.308 |
wills | +0.307 |
Neg logit contributions | |
hatt | -0.389 |
Beer | -0.374 |
coat | -0.342 |
andr | -0.342 |
ness | -0.339 |
Token | on |
Token ID | 319 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
hatt | +0.706 |
Beer | +0.680 |
coat | +0.614 |
andr | +0.613 |
ness | +0.609 |
Neg logit contributions | |
orem | -0.764 |
ril | -0.748 |
nerv | -0.720 |
riors | -0.700 |
wills | -0.696 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
hatt | +0.091 |
Beer | +0.089 |
coat | +0.080 |
andr | +0.080 |
ness | +0.079 |
Neg logit contributions | |
orem | -0.087 |
ril | -0.085 |
nerv | -0.082 |
wills | -0.080 |
riors | -0.079 |
Token | edge |
Token ID | 5743 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
orem | +0.232 |
ril | +0.226 |
nerv | +0.219 |
wills | +0.212 |
riors | +0.212 |
Neg logit contributions | |
hatt | -0.219 |
Beer | -0.211 |
coat | -0.191 |
andr | -0.190 |
ness | -0.189 |
Token | of |
Token ID | 286 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
orem | +1.841 |
ril | +1.799 |
nerv | +1.719 |
riors | +1.663 |
wills | +1.646 |
Neg logit contributions | |
hatt | -2.282 |
Beer | -2.211 |
coat | -2.026 |
andr | -2.020 |
ness | -2.002 |
Token | vit |
Token ID | 9090 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
hatt | +0.070 |
Beer | +0.068 |
andr | +0.061 |
coat | +0.061 |
ness | +0.061 |
Neg logit contributions | |
orem | -0.073 |
ril | -0.071 |
nerv | -0.068 |
riors | -0.066 |
wills | -0.066 |
Token | icultural |
Token ID | 26823 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
ril | +5.676 |
orem | +5.521 |
igation | +5.124 |
rior | +4.911 |
nerv | +4.810 |
Neg logit contributions | |
hatt | -8.249 |
Beer | -8.187 |
andr | -7.374 |
coat | -7.362 |
ness | -7.295 |
Token | viability |
Token ID | 32141 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
hatt | +0.975 |
Beer | +0.935 |
coat | +0.841 |
andr | +0.840 |
ness | +0.832 |
Neg logit contributions | |
orem | -1.121 |
ril | -1.098 |
nerv | -1.056 |
riors | -1.028 |
wills | -1.025 |
Token | , |
Token ID | 11 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
orem | +1.925 |
ril | +1.888 |
nerv | +1.834 |
riors | +1.769 |
igation | +1.768 |
Neg logit contributions | |
hatt | -1.613 |
Beer | -1.552 |
andr | -1.404 |
coat | -1.391 |
ness | -1.355 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
hatt | +0.105 |
Beer | +0.101 |
coat | +0.092 |
andr | +0.092 |
ness | +0.091 |
Neg logit contributions | |
orem | -0.108 |
ril | -0.105 |
nerv | -0.101 |
riors | -0.098 |
wills | -0.098 |
Token | math |
Token ID | 10688 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
orem | +0.223 |
ril | +0.217 |
nerv | +0.210 |
riors | +0.203 |
wills | +0.203 |
Neg logit contributions | |
hatt | -0.206 |
Beer | -0.198 |
coat | -0.179 |
andr | -0.179 |
ness | -0.177 |
Token | arsenal |
Token ID | 24375 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
orem | +0.838 |
ril | +0.820 |
nerv | +0.787 |
riors | +0.766 |
wills | +0.764 |
Neg logit contributions | |
hatt | -0.754 |
Beer | -0.725 |
andr | -0.652 |
coat | -0.651 |
ness | -0.647 |
Token | of |
Token ID | 286 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
orem | +2.583 |
ril | +2.543 |
nerv | +2.424 |
wills | +2.350 |
riors | +2.350 |
Neg logit contributions | |
hatt | -3.232 |
Beer | -3.139 |
andr | -2.865 |
coat | -2.843 |
ness | -2.827 |
Token | the |
Token ID | 262 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
orem | +0.162 |
ril | +0.158 |
nerv | +0.150 |
riors | +0.146 |
wills | +0.145 |
Neg logit contributions | |
hatt | -0.191 |
Beer | -0.184 |
coat | -0.168 |
andr | -0.168 |
ness | -0.167 |
Token | Ban |
Token ID | 10274 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
orem | +0.129 |
ril | +0.126 |
nerv | +0.120 |
riors | +0.117 |
wills | +0.117 |
Neg logit contributions | |
hatt | -0.133 |
Beer | -0.128 |
andr | -0.116 |
coat | -0.116 |
ness | -0.116 |
Token | u |
Token ID | 84 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
hatt | +0.886 |
Beer | +0.833 |
andr | +0.745 |
ness | +0.743 |
coat | +0.743 |
Neg logit contributions | |
orem | -1.144 |
ril | -1.113 |
nerv | -1.081 |
riors | -1.053 |
wills | -1.052 |
Token | Qur |
Token ID | 17599 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
orem | +0.912 |
ril | +0.877 |
nerv | +0.813 |
riors | +0.774 |
wills | +0.768 |
Neg logit contributions | |
hatt | -2.154 |
Beer | -2.096 |
coat | -1.959 |
andr | -1.957 |
ness | -1.948 |
Token | ay |
Token ID | 323 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
orem | +6.205 |
ril | +6.088 |
nerv | +5.656 |
riors | +5.504 |
igation | +5.482 |
Neg logit contributions | |
Beer | -6.693 |
hatt | -6.652 |
coat | -6.047 |
andr | -5.967 |
ness | -5.928 |
Token | za |
Token ID | 4496 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
orem | +0.518 |
ril | +0.508 |
nerv | +0.482 |
riors | +0.474 |
rior | +0.465 |
Neg logit contributions | |
hatt | -0.503 |
Beer | -0.485 |
coat | -0.437 |
andr | -0.435 |
ness | -0.428 |
Token | which |
Token ID | 543 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
hatt | +1.715 |
Beer | +1.632 |
ness | +1.486 |
coat | +1.484 |
andr | +1.480 |
Neg logit contributions | |
orem | -1.750 |
ril | -1.703 |
nerv | -1.616 |
riors | -1.585 |
igation | -1.571 |
Token | consisted |
Token ID | 19954 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
hatt | +0.485 |
Beer | +0.465 |
coat | +0.423 |
andr | +0.423 |
ness | +0.421 |
Neg logit contributions | |
orem | -0.465 |
ril | -0.454 |
nerv | -0.435 |
riors | -0.422 |
wills | -0.419 |
Token | of |
Token ID | 286 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
orem | +2.077 |
ril | +2.044 |
nerv | +1.943 |
riors | +1.887 |
wills | +1.880 |
Neg logit contributions | |
hatt | -2.488 |
Beer | -2.405 |
andr | -2.193 |
coat | -2.188 |
ness | -2.176 |
Token | been |
Token ID | 587 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
orem | +0.621 |
ril | +0.609 |
nerv | +0.578 |
wills | +0.561 |
riors | +0.561 |
Neg logit contributions | |
hatt | -0.656 |
Beer | -0.639 |
andr | -0.577 |
coat | -0.571 |
ness | -0.566 |
Token | revealed |
Token ID | 4602 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
orem | +0.390 |
ril | +0.382 |
nerv | +0.368 |
wills | +0.359 |
riors | +0.357 |
Neg logit contributions | |
hatt | -0.314 |
Beer | -0.309 |
andr | -0.273 |
coat | -0.271 |
ness | -0.265 |
Token | . |
Token ID | 13 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
orem | +0.314 |
ril | +0.309 |
nerv | +0.295 |
riors | +0.287 |
wills | +0.286 |
Neg logit contributions | |
hatt | -0.279 |
Beer | -0.269 |
coat | -0.242 |
andr | -0.241 |
ness | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
orem | +0.093 |
ril | +0.091 |
nerv | +0.087 |
riors | +0.085 |
wills | +0.084 |
Neg logit contributions | |
hatt | -0.089 |
Beer | -0.086 |
coat | -0.077 |
andr | -0.077 |
ness | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
orem | +0.023 |
ril | +0.023 |
nerv | +0.021 |
riors | +0.021 |
rior | +0.021 |
Neg logit contributions | |
hatt | -0.026 |
Beer | -0.025 |
andr | -0.023 |
coat | -0.023 |
ness | -0.022 |
Token | Gil |
Token ID | 40747 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
orem | +0.459 |
ril | +0.452 |
nerv | +0.427 |
riors | +0.421 |
igation | +0.417 |
Neg logit contributions | |
hatt | -0.376 |
Beer | -0.356 |
coat | -0.322 |
andr | -0.322 |
ness | -0.318 |
Token | ad |
Token ID | 324 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
orem | +6.426 |
ril | +6.424 |
nerv | +5.987 |
wills | +5.876 |
riors | +5.846 |
Neg logit contributions | |
hatt | -6.318 |
Beer | -6.182 |
coat | -5.560 |
andr | -5.424 |
Feel | -5.373 |
Token | Perry |
Token ID | 14105 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
orem | +0.579 |
ril | +0.567 |
nerv | +0.543 |
riors | +0.529 |
wills | +0.526 |
Neg logit contributions | |
hatt | -0.552 |
Beer | -0.530 |
coat | -0.479 |
andr | -0.478 |
ness | -0.476 |
Token | , |
Token ID | 11 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
hatt | +1.242 |
Beer | +1.185 |
coat | +1.062 |
ness | +1.061 |
andr | +1.060 |
Neg logit contributions | |
orem | -1.536 |
ril | -1.503 |
nerv | -1.451 |
riors | -1.415 |
wills | -1.407 |
Token | D |
Token ID | 360 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
orem | +0.041 |
ril | +0.040 |
nerv | +0.039 |
riors | +0.038 |
wills | +0.038 |
Neg logit contributions | |
hatt | -0.038 |
Beer | -0.036 |
coat | -0.033 |
andr | -0.033 |
ness | -0.033 |
Token | ror |
Token ID | 1472 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
hatt | +1.906 |
Beer | +1.834 |
andr | +1.705 |
ness | +1.704 |
coat | +1.698 |
Neg logit contributions | |
orem | -1.141 |
ril | -1.104 |
nerv | -1.056 |
wills | -1.014 |
riors | -1.013 |
Token | last |
Token ID | 938 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
hatt | +1.398 |
Beer | +1.331 |
coat | +1.202 |
ness | +1.201 |
andr | +1.201 |
Neg logit contributions | |
orem | -1.576 |
ril | -1.535 |
nerv | -1.470 |
riors | -1.437 |
wills | -1.434 |
Token | year |
Token ID | 614 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
orem | +0.719 |
ril | +0.709 |
nerv | +0.689 |
wills | +0.673 |
riors | +0.673 |
Neg logit contributions | |
hatt | -0.281 |
Beer | -0.262 |
andr | -0.216 |
coat | -0.216 |
ness | -0.210 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
hatt | +0.610 |
Beer | +0.584 |
coat | +0.524 |
andr | +0.524 |
ness | +0.521 |
Neg logit contributions | |
orem | -0.725 |
ril | -0.710 |
nerv | -0.681 |
riors | -0.665 |
wills | -0.662 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
hatt | +0.278 |
Beer | +0.267 |
coat | +0.241 |
andr | +0.241 |
ness | +0.239 |
Neg logit contributions | |
orem | -0.293 |
ril | -0.286 |
nerv | -0.274 |
riors | -0.267 |
wills | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
hatt | +0.387 |
Beer | +0.370 |
andr | +0.341 |
coat | +0.337 |
ness | +0.330 |
Neg logit contributions | |
orem | -0.343 |
ril | -0.338 |
nerv | -0.316 |
riors | -0.312 |
rior | -0.311 |
Token | Gil |
Token ID | 40747 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
orem | +0.025 |
ril | +0.025 |
nerv | +0.024 |
riors | +0.023 |
rior | +0.023 |
Neg logit contributions | |
hatt | -0.018 |
Beer | -0.017 |
coat | -0.015 |
andr | -0.015 |
ness | -0.015 |
Token | bert |
Token ID | 4835 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ril | +4.333 |
orem | +4.245 |
riors | +3.746 |
igation | +3.724 |
nerv | +3.716 |
Neg logit contributions | |
hatt | -8.234 |
Beer | -8.114 |
Feel | -7.389 |
coat | -7.365 |
andr | -7.248 |
Token | is |
Token ID | 318 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
orem | +0.300 |
ril | +0.294 |
nerv | +0.282 |
riors | +0.273 |
wills | +0.273 |
Neg logit contributions | |
hatt | -0.315 |
Beer | -0.305 |
coat | -0.276 |
andr | -0.275 |
ness | -0.273 |
Token | known |
Token ID | 1900 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
hatt | +0.456 |
Beer | +0.438 |
coat | +0.395 |
andr | +0.394 |
ness | +0.392 |
Neg logit contributions | |
orem | -0.499 |
ril | -0.488 |
nerv | -0.468 |
riors | -0.456 |
wills | -0.454 |
Token | as |
Token ID | 355 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
hatt | +0.514 |
Beer | +0.495 |
coat | +0.450 |
andr | +0.450 |
ness | +0.448 |
Neg logit contributions | |
orem | -0.480 |
ril | -0.468 |
nerv | -0.447 |
riors | -0.435 |
wills | -0.433 |
Token | a |
Token ID | 257 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
orem | +0.078 |
ril | +0.076 |
nerv | +0.073 |
riors | +0.071 |
wills | +0.071 |
Neg logit contributions | |
hatt | -0.072 |
Beer | -0.069 |
coat | -0.062 |
andr | -0.062 |
ness | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
orem | +0.261 |
ril | +0.256 |
nerv | +0.244 |
riors | +0.238 |
wills | +0.237 |
Neg logit contributions | |
hatt | -0.271 |
Beer | -0.261 |
andr | -0.237 |
coat | -0.237 |
ness | -0.235 |
Token | men |
Token ID | 1450 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
orem | +0.399 |
ril | +0.390 |
nerv | +0.373 |
riors | +0.363 |
wills | +0.362 |
Neg logit contributions | |
hatt | -0.410 |
Beer | -0.394 |
andr | -0.358 |
coat | -0.358 |
ness | -0.355 |
Token | of |
Token ID | 286 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
orem | +1.127 |
ril | +1.108 |
nerv | +1.057 |
riors | +1.030 |
wills | +1.027 |
Neg logit contributions | |
hatt | -1.051 |
Beer | -1.019 |
andr | -0.914 |
coat | -0.913 |
ness | -0.900 |
Token | Ban |
Token ID | 10274 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
orem | +0.180 |
ril | +0.176 |
nerv | +0.168 |
wills | +0.164 |
riors | +0.164 |
Neg logit contributions | |
hatt | -0.183 |
Beer | -0.176 |
andr | -0.160 |
coat | -0.160 |
ness | -0.159 |
Token | u |
Token ID | 84 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
hatt | +0.922 |
Beer | +0.882 |
andr | +0.795 |
coat | +0.795 |
ness | +0.791 |
Neg logit contributions | |
orem | -1.020 |
ril | -0.997 |
nerv | -0.957 |
riors | -0.933 |
wills | -0.929 |
Token | Qur |
Token ID | 17599 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
orem | +1.797 |
ril | +1.747 |
nerv | +1.671 |
wills | +1.628 |
riors | +1.627 |
Neg logit contributions | |
hatt | -1.839 |
Beer | -1.772 |
coat | -1.624 |
andr | -1.615 |
ness | -1.595 |
Token | ay |
Token ID | 323 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
orem | +6.444 |
ril | +6.382 |
nerv | +5.917 |
riors | +5.804 |
igation | +5.748 |
Neg logit contributions | |
Beer | -5.918 |
hatt | -5.887 |
andr | -5.253 |
coat | -5.220 |
Feel | -5.170 |
Token | za |
Token ID | 4496 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
orem | +0.651 |
ril | +0.636 |
nerv | +0.612 |
riors | +0.596 |
wills | +0.596 |
Neg logit contributions | |
hatt | -0.541 |
Beer | -0.518 |
andr | -0.464 |
coat | -0.464 |
ness | -0.462 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
hatt | +1.921 |
Beer | +1.820 |
ness | +1.649 |
andr | +1.647 |
coat | +1.638 |
Neg logit contributions | |
orem | -2.175 |
ril | -2.128 |
nerv | -2.042 |
riors | -1.996 |
wills | -1.984 |
Token | the |
Token ID | 262 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
orem | +0.016 |
ril | +0.016 |
nerv | +0.015 |
riors | +0.015 |
wills | +0.015 |
Neg logit contributions | |
hatt | -0.015 |
Beer | -0.014 |
coat | -0.013 |
andr | -0.013 |
ness | -0.013 |
Token | ensl |
Token ID | 25563 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
orem | +0.308 |
ril | +0.301 |
nerv | +0.288 |
wills | +0.280 |
riors | +0.280 |
Neg logit contributions | |
hatt | -0.310 |
Beer | -0.298 |
andr | -0.271 |
coat | -0.270 |
ness | -0.268 |
Token | / |
Token ID | 14 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
orem | +0.166 |
ril | +0.164 |
nerv | +0.157 |
riors | +0.153 |
wills | +0.152 |
Neg logit contributions | |
hatt | -0.160 |
Beer | -0.155 |
andr | -0.140 |
coat | -0.139 |
ness | -0.137 |
Token | AP |
Token ID | 2969 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
hatt | +0.576 |
Beer | +0.550 |
andr | +0.488 |
coat | +0.487 |
ness | +0.484 |
Neg logit contributions | |
orem | -0.798 |
ril | -0.783 |
nerv | -0.752 |
riors | -0.737 |
wills | -0.733 |
Token | ) |
Token ID | 8 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
orem | +0.831 |
ril | +0.813 |
nerv | +0.784 |
riors | +0.765 |
wills | +0.763 |
Neg logit contributions | |
hatt | -0.613 |
Beer | -0.584 |
coat | -0.520 |
andr | -0.519 |
ness | -0.518 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
orem | +0.581 |
ril | +0.567 |
nerv | +0.546 |
wills | +0.530 |
riors | +0.529 |
Neg logit contributions | |
hatt | -0.549 |
Beer | -0.527 |
coat | -0.477 |
andr | -0.476 |
ness | -0.474 |
Token |
|
Token ID | 198 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
hatt | +0.298 |
Beer | +0.285 |
andr | +0.262 |
coat | +0.259 |
ness | +0.254 |
Neg logit contributions | |
orem | -0.269 |
ril | -0.265 |
nerv | -0.249 |
riors | -0.245 |
rior | -0.243 |
Token | Gil |
Token ID | 40747 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
orem | +0.067 |
ril | +0.066 |
nerv | +0.062 |
riors | +0.062 |
igation | +0.061 |
Neg logit contributions | |
hatt | -0.052 |
Beer | -0.049 |
andr | -0.044 |
coat | -0.044 |
ness | -0.044 |
Token | bert |
Token ID | 4835 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
orem | +4.394 |
ril | +4.352 |
riors | +3.845 |
nerv | +3.838 |
igation | +3.822 |
Neg logit contributions | |
hatt | -7.966 |
Beer | -7.841 |
coat | -7.131 |
Feel | -7.072 |
andr | -7.028 |
Token | and |
Token ID | 290 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
orem | +0.774 |
ril | +0.757 |
nerv | +0.729 |
wills | +0.710 |
riors | +0.704 |
Neg logit contributions | |
hatt | -0.757 |
Beer | -0.733 |
andr | -0.660 |
coat | -0.658 |
ness | -0.647 |
Token | the |
Token ID | 262 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
orem | +0.599 |
ril | +0.584 |
nerv | +0.556 |
riors | +0.540 |
wills | +0.538 |
Neg logit contributions | |
hatt | -0.654 |
Beer | -0.631 |
andr | -0.572 |
coat | -0.572 |
ness | -0.567 |
Token | ACLU |
Token ID | 24381 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
orem | +0.588 |
ril | +0.567 |
nerv | +0.534 |
wills | +0.516 |
riors | +0.516 |
Neg logit contributions | |
hatt | -0.886 |
Beer | -0.860 |
andr | -0.790 |
coat | -0.790 |
ness | -0.785 |
Token | have |
Token ID | 423 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
orem | +0.717 |
ril | +0.700 |
nerv | +0.666 |
wills | +0.646 |
riors | +0.645 |
Neg logit contributions | |
hatt | -0.858 |
Beer | -0.830 |
andr | -0.756 |
coat | -0.754 |
ness | -0.747 |
Token | Mohammad |
Token ID | 29674 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
hatt | +1.758 |
Beer | +1.687 |
ness | +1.530 |
andr | +1.523 |
coat | +1.513 |
Neg logit contributions | |
orem | -1.934 |
ril | -1.896 |
nerv | -1.804 |
riors | -1.766 |
wills | -1.751 |
Token | School |
Token ID | 3961 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
orem | +1.150 |
ril | +1.123 |
nerv | +1.082 |
riors | +1.047 |
wills | +1.045 |
Neg logit contributions | |
hatt | -1.139 |
Beer | -1.097 |
andr | -0.990 |
coat | -0.989 |
ness | -0.972 |
Token | teaching |
Token ID | 7743 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
hatt | +3.421 |
Beer | +3.289 |
ness | +3.034 |
coat | +3.017 |
andr | +2.981 |
Neg logit contributions | |
orem | -3.389 |
ril | -3.308 |
nerv | -3.153 |
riors | -3.074 |
wills | -3.060 |
Token | " |
Token ID | 366 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
hatt | +2.809 |
Beer | +2.694 |
ness | +2.476 |
coat | +2.459 |
andr | +2.436 |
Neg logit contributions | |
orem | -2.904 |
ril | -2.860 |
nerv | -2.723 |
riors | -2.666 |
igation | -2.625 |
Token | a |
Token ID | 64 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
hatt | +1.270 |
Beer | +1.216 |
andr | +1.088 |
coat | +1.088 |
ness | +1.079 |
Neg logit contributions | |
orem | -1.562 |
ril | -1.530 |
nerv | -1.468 |
riors | -1.434 |
wills | -1.428 |
Token | Qur |
Token ID | 17599 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
hatt | +0.492 |
Beer | +0.473 |
andr | +0.426 |
coat | +0.425 |
ness | +0.420 |
Neg logit contributions | |
orem | -0.543 |
ril | -0.531 |
nerv | -0.511 |
riors | -0.497 |
wills | -0.495 |
Token | ' |
Token ID | 6 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
orem | +6.029 |
ril | +5.945 |
nerv | +5.536 |
riors | +5.425 |
igation | +5.407 |
Neg logit contributions | |
hatt | -6.267 |
Beer | -6.241 |
coat | -5.602 |
andr | -5.578 |
ness | -5.431 |
Token | an |
Token ID | 272 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
orem | +0.018 |
ril | +0.018 |
nerv | +0.017 |
riors | +0.017 |
wills | +0.016 |
Neg logit contributions | |
hatt | -0.014 |
Beer | -0.013 |
coat | -0.012 |
andr | -0.012 |
ness | -0.012 |
Token | - |
Token ID | 12 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
orem | +0.622 |
ril | +0.609 |
nerv | +0.586 |
riors | +0.571 |
wills | +0.567 |
Neg logit contributions | |
hatt | -0.587 |
Beer | -0.566 |
andr | -0.511 |
coat | -0.509 |
ness | -0.503 |
Token | guided |
Token ID | 23657 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
orem | +0.148 |
ril | +0.146 |
nerv | +0.140 |
riors | +0.137 |
wills | +0.136 |
Neg logit contributions | |
hatt | -0.117 |
Beer | -0.113 |
andr | -0.101 |
coat | -0.100 |
ness | -0.099 |
Token | journey |
Token ID | 7002 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
hatt | +0.295 |
Beer | +0.285 |
coat | +0.257 |
andr | +0.257 |
ness | +0.251 |
Neg logit contributions | |
orem | -0.314 |
ril | -0.306 |
nerv | -0.295 |
riors | -0.286 |
wills | -0.286 |
Token | No |
Token ID | 2949 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
orem | +0.341 |
ril | +0.336 |
nerv | +0.318 |
riors | +0.314 |
igation | +0.311 |
Neg logit contributions | |
hatt | -0.253 |
Beer | -0.240 |
coat | -0.216 |
andr | -0.215 |
ness | -0.213 |
Token | woman |
Token ID | 2415 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
orem | +0.604 |
ril | +0.590 |
nerv | +0.565 |
riors | +0.551 |
wills | +0.550 |
Neg logit contributions | |
hatt | -0.534 |
Beer | -0.513 |
andr | -0.461 |
coat | -0.461 |
ness | -0.457 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
orem | +0.643 |
ril | +0.628 |
nerv | +0.600 |
riors | +0.583 |
wills | +0.581 |
Neg logit contributions | |
hatt | -0.703 |
Beer | -0.678 |
andr | -0.618 |
coat | -0.616 |
ness | -0.610 |
Token | Ban |
Token ID | 10274 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
orem | +0.170 |
ril | +0.166 |
nerv | +0.159 |
riors | +0.154 |
wills | +0.154 |
Neg logit contributions | |
hatt | -0.180 |
Beer | -0.173 |
andr | -0.158 |
coat | -0.157 |
ness | -0.156 |
Token | u |
Token ID | 84 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
hatt | +0.475 |
Beer | +0.447 |
andr | +0.400 |
ness | +0.399 |
coat | +0.398 |
Neg logit contributions | |
orem | -0.615 |
ril | -0.601 |
nerv | -0.584 |
wills | -0.570 |
riors | -0.570 |
Token | Qur |
Token ID | 17599 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
orem | +1.310 |
ril | +1.273 |
nerv | +1.209 |
riors | +1.166 |
wills | +1.162 |
Neg logit contributions | |
hatt | -1.879 |
Beer | -1.822 |
coat | -1.682 |
andr | -1.678 |
ness | -1.664 |
Token | ay |
Token ID | 323 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
orem | +5.443 |
ril | +5.362 |
igation | +4.773 |
nerv | +4.741 |
terior | +4.694 |
Neg logit contributions | |
Beer | -6.450 |
hatt | -6.281 |
coat | -5.711 |
Feel | -5.684 |
andr | -5.612 |
Token | za |
Token ID | 4496 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
orem | +0.674 |
ril | +0.662 |
nerv | +0.625 |
riors | +0.613 |
igation | +0.603 |
Neg logit contributions | |
hatt | -0.682 |
Beer | -0.659 |
coat | -0.594 |
andr | -0.590 |
ness | -0.577 |
Token | was |
Token ID | 373 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
hatt | +1.824 |
Beer | +1.737 |
ness | +1.600 |
coat | +1.584 |
andr | +1.574 |
Neg logit contributions | |
orem | -1.823 |
ril | -1.778 |
nerv | -1.690 |
riors | -1.655 |
igation | -1.634 |
Token | killed |
Token ID | 2923 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
hatt | +0.812 |
Beer | +0.777 |
coat | +0.703 |
ness | +0.701 |
andr | +0.699 |
Neg logit contributions | |
orem | -0.886 |
ril | -0.867 |
nerv | -0.829 |
riors | -0.810 |
wills | -0.804 |
Token | except |
Token ID | 2845 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
orem | +1.006 |
ril | +0.985 |
nerv | +0.949 |
wills | +0.918 |
riors | +0.917 |
Neg logit contributions | |
hatt | -1.006 |
Beer | -0.972 |
andr | -0.877 |
coat | -0.875 |
ness | -0.862 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
hatt | +0.239 |
Beer | +0.228 |
andr | +0.203 |
coat | +0.203 |
ness | +0.201 |
Neg logit contributions | |
orem | -0.310 |
ril | -0.304 |
nerv | -0.293 |
riors | -0.286 |
wills | -0.285 |
Token | Survivor |
Token ID | 23740 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
hatt | +0.171 |
Beer | +0.165 |
coat | +0.150 |
andr | +0.150 |
ness | +0.149 |
Neg logit contributions | |
orem | -0.164 |
ril | -0.161 |
nerv | -0.154 |
riors | -0.149 |
wills | -0.149 |
Token | South |
Token ID | 2520 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
orem | +0.421 |
ril | +0.413 |
nerv | +0.394 |
riors | +0.384 |
wills | +0.382 |
Neg logit contributions | |
hatt | -0.429 |
Beer | -0.413 |
andr | -0.374 |
coat | -0.373 |
ness | -0.371 |
Token | Pacific |
Token ID | 8211 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
hatt | +0.041 |
Beer | +0.040 |
andr | +0.036 |
coat | +0.035 |
ness | +0.035 |
Neg logit contributions | |
orem | -0.047 |
ril | -0.046 |
nerv | -0.044 |
riors | -0.043 |
wills | -0.043 |
Token | ), |
Token ID | 828 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
orem | +0.818 |
ril | +0.802 |
nerv | +0.772 |
riors | +0.756 |
wills | +0.750 |
Neg logit contributions | |
hatt | -0.646 |
Beer | -0.618 |
andr | -0.551 |
coat | -0.549 |
ness | -0.543 |
Token | voic |
Token ID | 40268 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
orem | +0.822 |
ril | +0.805 |
nerv | +0.774 |
riors | +0.754 |
wills | +0.752 |
Neg logit contributions | |
hatt | -0.711 |
Beer | -0.681 |
coat | -0.612 |
andr | -0.611 |
ness | -0.607 |
Token | em |
Token ID | 368 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
orem | +4.349 |
ril | +4.244 |
nerv | +3.768 |
riors | +3.757 |
igation | +3.740 |
Neg logit contributions | |
hatt | -7.645 |
Beer | -7.438 |
coat | -6.884 |
andr | -6.843 |
ness | -6.690 |
Token | ails |
Token ID | 1768 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
orem | +0.208 |
ril | +0.197 |
nerv | +0.172 |
riors | +0.160 |
wills | +0.158 |
Neg logit contributions | |
hatt | -0.884 |
Beer | -0.866 |
coat | -0.815 |
andr | -0.815 |
ness | -0.811 |
Token | with |
Token ID | 351 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
orem | +2.339 |
ril | +2.291 |
nerv | +2.211 |
riors | +2.154 |
wills | +2.153 |
Neg logit contributions | |
hatt | -2.074 |
Beer | -1.995 |
coat | -1.790 |
andr | -1.780 |
ness | -1.749 |
Token | Mike |
Token ID | 4995 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
hatt | +0.541 |
Beer | +0.519 |
coat | +0.468 |
andr | +0.467 |
ness | +0.465 |
Neg logit contributions | |
orem | -0.598 |
ril | -0.585 |
nerv | -0.561 |
riors | -0.547 |
wills | -0.544 |
Token | Bloom |
Token ID | 11891 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
hatt | +0.172 |
Beer | +0.165 |
coat | +0.149 |
andr | +0.149 |
ness | +0.148 |
Neg logit contributions | |
orem | -0.188 |
ril | -0.184 |
nerv | -0.176 |
riors | -0.172 |
wills | -0.171 |
Token | for |
Token ID | 329 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
hatt | +0.592 |
Beer | +0.570 |
andr | +0.517 |
coat | +0.516 |
ness | +0.512 |
Neg logit contributions | |
orem | -0.580 |
ril | -0.568 |
nerv | -0.545 |
riors | -0.528 |
wills | -0.527 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
orem | +0.220 |
ril | +0.215 |
nerv | +0.205 |
riors | +0.199 |
wills | +0.198 |
Neg logit contributions | |
hatt | -0.264 |
Beer | -0.255 |
coat | -0.233 |
andr | -0.233 |
ness | -0.232 |
Token | Black |
Token ID | 2619 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
orem | +0.043 |
ril | +0.042 |
nerv | +0.040 |
riors | +0.039 |
wills | +0.039 |
Neg logit contributions | |
hatt | -0.051 |
Beer | -0.049 |
andr | -0.045 |
coat | -0.045 |
ness | -0.045 |
Token | berry |
Token ID | 8396 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
hatt | +1.129 |
Beer | +1.069 |
ness | +0.934 |
coat | +0.931 |
andr | +0.926 |
Neg logit contributions | |
orem | -2.013 |
ril | -1.957 |
nerv | -1.898 |
riors | -1.860 |
wills | -1.857 |
Token | or |
Token ID | 393 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
orem | +2.405 |
ril | +2.372 |
nerv | +2.283 |
riors | +2.207 |
wills | +2.196 |
Neg logit contributions | |
hatt | -2.427 |
Beer | -2.353 |
coat | -2.127 |
andr | -2.117 |
ness | -2.088 |
Token | Palm |
Token ID | 18358 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
orem | +0.077 |
ril | +0.075 |
nerv | +0.071 |
riors | +0.069 |
wills | +0.069 |
Neg logit contributions | |
hatt | -0.089 |
Beer | -0.086 |
andr | -0.079 |
coat | -0.079 |
ness | -0.079 |
Token | Pre |
Token ID | 3771 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
orem | +5.913 |
ril | +5.831 |
nerv | +5.614 |
riors | +5.432 |
igation | +5.405 |
Neg logit contributions | |
hatt | -5.860 |
Beer | -5.703 |
coat | -5.105 |
andr | -5.095 |
ness | -4.964 |
Token | ? |
Token ID | 30 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
hatt | +1.631 |
Beer | +1.563 |
coat | +1.410 |
ness | +1.408 |
andr | +1.406 |
Neg logit contributions | |
orem | -1.874 |
ril | -1.818 |
nerv | -1.753 |
riors | -1.708 |
wills | -1.702 |
Token | We |
Token ID | 775 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
orem | +0.359 |
ril | +0.352 |
nerv | +0.337 |
riors | +0.328 |
wills | +0.327 |
Neg logit contributions | |
hatt | -0.335 |
Beer | -0.322 |
coat | -0.291 |
andr | -0.290 |
ness | -0.288 |
Token | � |
Token ID | 447 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
orem | +0.067 |
ril | +0.065 |
nerv | +0.063 |
riors | +0.061 |
wills | +0.061 |
Neg logit contributions | |
hatt | -0.058 |
Beer | -0.056 |
andr | -0.050 |
coat | -0.050 |
ness | -0.049 |
Token | � |
Token ID | 247 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
hatt | +0.138 |
Beer | +0.131 |
coat | +0.116 |
andr | +0.116 |
ness | +0.115 |
Neg logit contributions | |
orem | -0.194 |
ril | -0.190 |
nerv | -0.183 |
riors | -0.179 |
wills | -0.178 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
hatt | +1.448 |
Beer | +1.388 |
coat | +1.249 |
ness | +1.247 |
andr | +1.243 |
Neg logit contributions | |
orem | -1.697 |
ril | -1.661 |
nerv | -1.588 |
riors | -1.556 |
wills | -1.544 |
Token | in |
Token ID | 287 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
hatt | +0.866 |
Beer | +0.832 |
coat | +0.751 |
andr | +0.750 |
ness | +0.746 |
Neg logit contributions | |
orem | -0.920 |
ril | -0.900 |
nerv | -0.862 |
riors | -0.840 |
wills | -0.836 |
Token | Syria |
Token ID | 4392 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
hatt | +0.576 |
Beer | +0.554 |
coat | +0.502 |
andr | +0.502 |
ness | +0.500 |
Neg logit contributions | |
orem | -0.558 |
ril | -0.545 |
nerv | -0.520 |
riors | -0.507 |
wills | -0.503 |
Token | and |
Token ID | 290 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
orem | +1.937 |
ril | +1.914 |
nerv | +1.871 |
riors | +1.803 |
wills | +1.786 |
Neg logit contributions | |
hatt | -1.676 |
Beer | -1.617 |
coat | -1.446 |
andr | -1.444 |
ness | -1.422 |
Token | Mes |
Token ID | 14937 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
hatt | +0.129 |
Beer | +0.124 |
coat | +0.113 |
andr | +0.113 |
ness | +0.113 |
Neg logit contributions | |
orem | -0.117 |
ril | -0.114 |
nerv | -0.109 |
riors | -0.106 |
wills | -0.106 |
Token | opot |
Token ID | 43372 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
orem | +0.863 |
ril | +0.838 |
nerv | +0.763 |
wills | +0.719 |
riors | +0.716 |
Neg logit contributions | |
hatt | -2.115 |
Beer | -2.063 |
coat | -1.928 |
andr | -1.927 |
ness | -1.915 |
Token | amia |
Token ID | 49442 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
orem | +2.739 |
ril | +2.535 |
nerv | +2.219 |
riors | +2.189 |
igation | +2.173 |
Neg logit contributions | |
Beer | -8.874 |
hatt | -8.830 |
coat | -8.338 |
Feel | -8.181 |
andr | -8.156 |
Token | . |
Token ID | 13 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
orem | +0.572 |
ril | +0.562 |
nerv | +0.546 |
riors | +0.527 |
wills | +0.524 |
Neg logit contributions | |
hatt | -0.520 |
Beer | -0.501 |
coat | -0.449 |
andr | -0.449 |
ness | -0.443 |
Token | As |
Token ID | 1081 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
hatt | +0.471 |
Beer | +0.454 |
andr | +0.410 |
coat | +0.409 |
ness | +0.408 |
Neg logit contributions | |
orem | -0.492 |
ril | -0.481 |
nerv | -0.460 |
riors | -0.448 |
wills | -0.448 |
Token | with |
Token ID | 351 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
orem | +0.104 |
ril | +0.102 |
nerv | +0.097 |
riors | +0.095 |
wills | +0.094 |
Neg logit contributions | |
hatt | -0.105 |
Beer | -0.101 |
coat | -0.092 |
andr | -0.092 |
ness | -0.091 |
Token | so |
Token ID | 523 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
hatt | +0.551 |
Beer | +0.530 |
coat | +0.483 |
andr | +0.483 |
ness | +0.481 |
Neg logit contributions | |
orem | -0.507 |
ril | -0.495 |
nerv | -0.472 |
riors | -0.459 |
wills | -0.456 |
Token | The |
Token ID | 464 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
orem | +0.498 |
ril | +0.490 |
nerv | +0.464 |
riors | +0.458 |
igation | +0.453 |
Neg logit contributions | |
hatt | -0.374 |
Beer | -0.352 |
andr | -0.317 |
coat | -0.317 |
ness | -0.314 |
Token | imminent |
Token ID | 21161 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
orem | +0.638 |
ril | +0.622 |
nerv | +0.596 |
riors | +0.579 |
wills | +0.577 |
Neg logit contributions | |
hatt | -0.629 |
Beer | -0.605 |
coat | -0.548 |
andr | -0.547 |
ness | -0.543 |
Token | merger |
Token ID | 24589 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
orem | +0.391 |
ril | +0.383 |
nerv | +0.367 |
riors | +0.356 |
wills | +0.356 |
Neg logit contributions | |
hatt | -0.370 |
Beer | -0.355 |
coat | -0.321 |
andr | -0.321 |
ness | -0.317 |
Token | between |
Token ID | 1022 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
orem | +1.278 |
ril | +1.251 |
nerv | +1.205 |
wills | +1.166 |
igation | +1.156 |
Neg logit contributions | |
hatt | -1.580 |
Beer | -1.523 |
andr | -1.398 |
coat | -1.393 |
ness | -1.366 |
Token | Time |
Token ID | 3862 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
orem | +0.528 |
ril | +0.514 |
nerv | +0.493 |
wills | +0.478 |
riors | +0.477 |
Neg logit contributions | |
hatt | -0.559 |
Beer | -0.537 |
andr | -0.489 |
coat | -0.488 |
ness | -0.485 |
Token | Warner |
Token ID | 14469 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
hatt | +0.465 |
Beer | +0.447 |
coat | +0.403 |
andr | +0.403 |
ness | +0.401 |
Neg logit contributions | |
orem | -0.490 |
ril | -0.479 |
nerv | -0.459 |
riors | -0.447 |
wills | -0.445 |
Token | Cable |
Token ID | 20249 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
orem | +5.459 |
ril | +5.421 |
nerv | +5.223 |
wills | +5.171 |
riors | +5.087 |
Neg logit contributions | |
hatt | -6.154 |
Beer | -5.863 |
andr | -5.412 |
coat | -5.246 |
ness | -5.228 |
Token | and |
Token ID | 290 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
orem | +0.770 |
ril | +0.755 |
nerv | +0.727 |
riors | +0.709 |
wills | +0.708 |
Neg logit contributions | |
hatt | -0.635 |
Beer | -0.609 |
coat | -0.544 |
andr | -0.543 |
ness | -0.538 |
Token | Comcast |
Token ID | 21830 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
hatt | +0.012 |
Beer | +0.011 |
andr | +0.010 |
coat | +0.010 |
ness | +0.010 |
Neg logit contributions | |
orem | -0.011 |
ril | -0.011 |
nerv | -0.011 |
wills | -0.010 |
riors | -0.010 |
Token | herald |
Token ID | 28783 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
orem | +2.795 |
ril | +2.706 |
nerv | +2.639 |
wills | +2.579 |
riors | +2.530 |
Neg logit contributions | |
hatt | -2.949 |
Beer | -2.828 |
coat | -2.562 |
andr | -2.562 |
ness | -2.485 |
Token | s |
Token ID | 82 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
orem | +0.195 |
ril | +0.193 |
nerv | +0.186 |
wills | +0.183 |
riors | +0.183 |
Neg logit contributions | |
hatt | -0.067 |
Beer | -0.061 |
andr | -0.049 |
coat | -0.049 |
ness | -0.048 |
Token | living |
Token ID | 2877 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hatt | +0.030 |
Beer | +0.029 |
coat | +0.026 |
andr | +0.026 |
ness | +0.026 |
Neg logit contributions | |
orem | -0.035 |
ril | -0.034 |
nerv | -0.032 |
riors | -0.032 |
wills | -0.032 |
Token | on |
Token ID | 319 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
orem | +1.568 |
ril | +1.540 |
nerv | +1.476 |
wills | +1.438 |
riors | +1.430 |
Neg logit contributions | |
hatt | -1.544 |
Beer | -1.491 |
andr | -1.342 |
coat | -1.335 |
ness | -1.322 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
hatt | +0.215 |
Beer | +0.207 |
andr | +0.188 |
coat | +0.188 |
ness | +0.186 |
Neg logit contributions | |
orem | -0.214 |
ril | -0.209 |
nerv | -0.200 |
riors | -0.195 |
wills | -0.194 |
Token | streets |
Token ID | 6483 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
orem | +0.205 |
ril | +0.200 |
nerv | +0.192 |
riors | +0.187 |
wills | +0.186 |
Neg logit contributions | |
hatt | -0.199 |
Beer | -0.191 |
andr | -0.173 |
coat | -0.173 |
ness | -0.171 |
Token | of |
Token ID | 286 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
hatt | +0.310 |
Beer | +0.297 |
coat | +0.269 |
andr | +0.268 |
ness | +0.267 |
Neg logit contributions | |
orem | -0.327 |
ril | -0.320 |
nerv | -0.306 |
riors | -0.298 |
wills | -0.297 |
Token | Gotham |
Token ID | 30129 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
orem | +0.312 |
ril | +0.304 |
nerv | +0.288 |
riors | +0.277 |
wills | +0.277 |
Neg logit contributions | |
hatt | -0.464 |
Beer | -0.450 |
andr | -0.414 |
coat | -0.413 |
ness | -0.412 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
orem | +5.247 |
ril | +5.139 |
nerv | +5.022 |
riors | +4.805 |
wills | +4.753 |
Neg logit contributions | |
hatt | -6.090 |
Beer | -6.042 |
andr | -5.512 |
coat | -5.323 |
ness | -5.263 |
Token | You |
Token ID | 921 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
hatt | +0.147 |
Beer | +0.141 |
coat | +0.126 |
andr | +0.126 |
ness | +0.125 |
Neg logit contributions | |
orem | -0.185 |
ril | -0.181 |
nerv | -0.174 |
riors | -0.170 |
wills | -0.169 |
Token | know |
Token ID | 760 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
hatt | +1.003 |
Beer | +0.960 |
coat | +0.858 |
andr | +0.857 |
ness | +0.851 |
Neg logit contributions | |
orem | -1.246 |
ril | -1.221 |
nerv | -1.174 |
riors | -1.146 |
wills | -1.141 |
Token | how |
Token ID | 703 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
hatt | +1.346 |
Beer | +1.287 |
coat | +1.158 |
andr | +1.155 |
ness | +1.154 |
Neg logit contributions | |
orem | -1.574 |
ril | -1.541 |
nerv | -1.476 |
riors | -1.442 |
wills | -1.435 |
Token | Alfred |
Token ID | 22044 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
hatt | +1.388 |
Beer | +1.333 |
coat | +1.215 |
andr | +1.211 |
ness | +1.209 |
Neg logit contributions | |
orem | -1.333 |
ril | -1.295 |
nerv | -1.231 |
riors | -1.204 |
wills | -1.196 |
Token | the |
Token ID | 262 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
hatt | +0.102 |
Beer | +0.098 |
coat | +0.089 |
andr | +0.089 |
ness | +0.088 |
Neg logit contributions | |
orem | -0.097 |
ril | -0.095 |
nerv | -0.090 |
riors | -0.088 |
wills | -0.087 |
Token | venue |
Token ID | 14359 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
hatt | +0.131 |
Beer | +0.126 |
coat | +0.115 |
andr | +0.115 |
ness | +0.115 |
Neg logit contributions | |
orem | -0.116 |
ril | -0.114 |
nerv | -0.108 |
riors | -0.105 |
wills | -0.105 |
Token | � |
Token ID | 447 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
orem | +0.063 |
ril | +0.062 |
nerv | +0.059 |
riors | +0.058 |
wills | +0.057 |
Neg logit contributions | |
hatt | -0.055 |
Beer | -0.052 |
coat | -0.047 |
andr | -0.047 |
ness | -0.047 |
Token | � |
Token ID | 247 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
hatt | +0.072 |
Beer | +0.068 |
coat | +0.061 |
andr | +0.061 |
ness | +0.060 |
Neg logit contributions | |
orem | -0.091 |
ril | -0.089 |
nerv | -0.085 |
riors | -0.084 |
rior | -0.083 |
Token | s |
Token ID | 82 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
hatt | +0.120 |
Beer | +0.110 |
coat | +0.087 |
andr | +0.087 |
ness | +0.085 |
Neg logit contributions | |
orem | -0.390 |
ril | -0.384 |
nerv | -0.374 |
riors | -0.367 |
wills | -0.366 |
Token | voic |
Token ID | 40268 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
orem | +0.719 |
ril | +0.699 |
nerv | +0.670 |
wills | +0.651 |
riors | +0.648 |
Neg logit contributions | |
hatt | -0.787 |
Beer | -0.756 |
coat | -0.690 |
andr | -0.688 |
ness | -0.682 |
Token | email |
Token ID | 12888 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
orem | +3.794 |
ril | +3.753 |
igation | +3.266 |
nerv | +3.249 |
wills | +3.205 |
Neg logit contributions | |
hatt | -7.807 |
Beer | -7.639 |
coat | -7.119 |
andr | -7.010 |
ness | -6.896 |
Token | at |
Token ID | 379 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
orem | +3.234 |
ril | +3.153 |
nerv | +3.026 |
wills | +2.956 |
riors | +2.921 |
Neg logit contributions | |
hatt | -3.211 |
Beer | -3.082 |
coat | -2.816 |
andr | -2.774 |
ness | -2.735 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
hatt | +0.033 |
Beer | +0.031 |
coat | +0.029 |
andr | +0.029 |
ness | +0.028 |
Neg logit contributions | |
orem | -0.030 |
ril | -0.029 |
nerv | -0.028 |
riors | -0.027 |
wills | -0.027 |
Token | time |
Token ID | 640 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
orem | +0.215 |
ril | +0.210 |
nerv | +0.203 |
wills | +0.197 |
riors | +0.197 |
Neg logit contributions | |
hatt | -0.167 |
Beer | -0.159 |
coat | -0.143 |
andr | -0.143 |
ness | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
orem | +0.848 |
ril | +0.832 |
nerv | +0.798 |
riors | +0.778 |
wills | +0.774 |
Neg logit contributions | |
hatt | -0.756 |
Beer | -0.725 |
andr | -0.653 |
coat | -0.653 |
ness | -0.645 |
Token | Vu |
Token ID | 35816 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
orem | +0.671 |
ril | +0.657 |
nerv | +0.630 |
riors | +0.613 |
wills | +0.612 |
Neg logit contributions | |
hatt | -0.607 |
Beer | -0.582 |
coat | -0.523 |
andr | -0.523 |
ness | -0.520 |
Token | itton |
Token ID | 47304 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
orem | +1.121 |
ril | +1.072 |
nerv | +0.980 |
wills | +0.934 |
riors | +0.915 |
Neg logit contributions | |
hatt | -2.794 |
Beer | -2.715 |
coat | -2.531 |
andr | -2.529 |
ness | -2.518 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
orem | +0.800 |
ril | +0.785 |
nerv | +0.755 |
riors | +0.735 |
wills | +0.735 |
Neg logit contributions | |
hatt | -0.627 |
Beer | -0.600 |
andr | -0.535 |
coat | -0.533 |
ness | -0.528 |
Token | � |
Token ID | 564 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
hatt | +0.192 |
Beer | +0.184 |
coat | +0.166 |
andr | +0.166 |
ness | +0.165 |
Neg logit contributions | |
orem | -0.206 |
ril | -0.201 |
nerv | -0.193 |
riors | -0.188 |
wills | -0.187 |
Token | � |
Token ID | 250 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
orem | +0.675 |
ril | +0.665 |
nerv | +0.645 |
riors | +0.633 |
wills | +0.631 |
Neg logit contributions | |
hatt | -0.257 |
Beer | -0.238 |
andr | -0.197 |
coat | -0.197 |
ness | -0.194 |
Token | Gil |
Token ID | 40747 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
hatt | +0.238 |
Beer | +0.225 |
andr | +0.201 |
coat | +0.201 |
ness | +0.199 |
Neg logit contributions | |
orem | -0.326 |
ril | -0.321 |
nerv | -0.307 |
riors | -0.301 |
wills | -0.299 |
Token | more |
Token ID | 3549 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
orem | +5.390 |
ril | +5.374 |
nerv | +5.016 |
riors | +4.892 |
igation | +4.877 |
Neg logit contributions | |
hatt | -6.037 |
Beer | -5.816 |
coat | -5.312 |
andr | -5.255 |
ness | -5.173 |
Token | Girls |
Token ID | 12002 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
orem | +0.536 |
ril | +0.523 |
nerv | +0.500 |
riors | +0.486 |
wills | +0.482 |
Neg logit contributions | |
hatt | -0.583 |
Beer | -0.562 |
coat | -0.511 |
andr | -0.510 |
ness | -0.509 |
Token | , |
Token ID | 11 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
hatt | +0.113 |
Beer | +0.109 |
coat | +0.099 |
andr | +0.099 |
ness | +0.098 |
Neg logit contributions | |
orem | -0.115 |
ril | -0.112 |
nerv | -0.107 |
riors | -0.104 |
wills | -0.104 |
Token | � |
Token ID | 447 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
orem | +0.027 |
ril | +0.027 |
nerv | +0.025 |
riors | +0.025 |
wills | +0.025 |
Neg logit contributions | |
hatt | -0.027 |
Beer | -0.026 |
coat | -0.024 |
andr | -0.024 |
ness | -0.024 |
Token | � |
Token ID | 251 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
hatt | +0.061 |
Beer | +0.056 |
coat | +0.046 |
andr | +0.046 |
ness | +0.045 |
Neg logit contributions | |
orem | -0.182 |
ril | -0.179 |
nerv | -0.174 |
riors | -0.171 |
wills | -0.170 |
Token | San |
Token ID | 2986 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
hatt | +0.112 |
Beer | +0.108 |
andr | +0.098 |
coat | +0.098 |
ness | +0.097 |
Neg logit contributions | |
orem | -0.100 |
ril | -0.098 |
nerv | -0.093 |
riors | -0.091 |
wills | -0.090 |
Token | Diego |
Token ID | 9500 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
orem | +0.837 |
ril | +0.816 |
nerv | +0.769 |
riors | +0.746 |
wills | +0.738 |
Neg logit contributions | |
hatt | -1.258 |
Beer | -1.221 |
coat | -1.123 |
andr | -1.122 |
ness | -1.114 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
orem | +1.723 |
ril | +1.690 |
nerv | +1.627 |
riors | +1.591 |
wills | +1.585 |
Neg logit contributions | |
hatt | -1.223 |
Beer | -1.166 |
coat | -1.033 |
andr | -1.033 |
ness | -1.027 |
Token | Dallas |
Token ID | 8533 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
hatt | +0.237 |
Beer | +0.228 |
andr | +0.208 |
coat | +0.208 |
ness | +0.207 |
Neg logit contributions | |
orem | -0.218 |
ril | -0.213 |
nerv | -0.204 |
riors | -0.198 |
wills | -0.197 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
hatt | +0.257 |
Beer | +0.245 |
ness | +0.217 |
andr | +0.215 |
coat | +0.214 |
Neg logit contributions | |
orem | -0.389 |
ril | -0.382 |
nerv | -0.368 |
riors | -0.360 |
wills | -0.358 |
Token | Palm |
Token ID | 18358 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
hatt | +0.256 |
Beer | +0.246 |
andr | +0.225 |
coat | +0.224 |
ness | +0.224 |
Neg logit contributions | |
orem | -0.224 |
ril | -0.218 |
nerv | -0.208 |
riors | -0.202 |
wills | -0.201 |
Token | Beach |
Token ID | 8511 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
orem | +3.857 |
ril | +3.698 |
nerv | +3.387 |
riors | +3.298 |
igation | +3.286 |
Neg logit contributions | |
hatt | -7.606 |
Beer | -7.468 |
andr | -6.922 |
coat | -6.858 |
ness | -6.782 |
Token | , |
Token ID | 11 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
orem | +2.141 |
ril | +2.097 |
nerv | +2.020 |
riors | +1.971 |
wills | +1.963 |
Neg logit contributions | |
hatt | -1.654 |
Beer | -1.585 |
andr | -1.411 |
coat | -1.409 |
ness | -1.394 |
Token | Florida |
Token ID | 4744 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
hatt | +0.067 |
Beer | +0.064 |
andr | +0.059 |
coat | +0.059 |
ness | +0.058 |
Neg logit contributions | |
orem | -0.058 |
ril | -0.056 |
nerv | -0.054 |
riors | -0.052 |
wills | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
orem | +0.434 |
ril | +0.426 |
nerv | +0.409 |
riors | +0.401 |
wills | +0.398 |
Neg logit contributions | |
hatt | -0.301 |
Beer | -0.287 |
ness | -0.254 |
coat | -0.254 |
andr | -0.253 |
Token | Moreno |
Token ID | 43269 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
hatt | +0.154 |
Beer | +0.148 |
andr | +0.135 |
coat | +0.135 |
ness | +0.135 |
Neg logit contributions | |
orem | -0.135 |
ril | -0.132 |
nerv | -0.126 |
riors | -0.122 |
wills | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
orem | +0.698 |
ril | +0.684 |
nerv | +0.657 |
riors | +0.641 |
wills | +0.639 |
Neg logit contributions | |
hatt | -0.567 |
Beer | -0.543 |
coat | -0.486 |
andr | -0.484 |
ness | -0.483 |
Token | Mass |
Token ID | 5674 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
orem | +0.845 |
ril | +0.822 |
nerv | +0.789 |
wills | +0.770 |
riors | +0.764 |
Neg logit contributions | |
hatt | -0.982 |
Beer | -0.953 |
andr | -0.874 |
coat | -0.865 |
ness | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
hatt | +0.178 |
Beer | +0.170 |
coat | +0.153 |
ness | +0.153 |
andr | +0.152 |
Neg logit contributions | |
orem | -0.208 |
ril | -0.203 |
nerv | -0.196 |
riors | -0.190 |
wills | -0.190 |
Token | -- |
Token ID | 1377 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
orem | +1.244 |
ril | +1.215 |
nerv | +1.157 |
riors | +1.124 |
wills | +1.118 |
Neg logit contributions | |
hatt | -1.445 |
Beer | -1.393 |
andr | -1.272 |
coat | -1.272 |
ness | -1.264 |
Token | Boston |
Token ID | 6182 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
orem | +0.760 |
ril | +0.743 |
nerv | +0.711 |
riors | +0.692 |
wills | +0.689 |
Neg logit contributions | |
hatt | -0.777 |
Beer | -0.747 |
andr | -0.678 |
coat | -0.678 |
ness | -0.672 |
Token | Celtics |
Token ID | 24116 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
orem | +3.011 |
ril | +2.948 |
nerv | +2.756 |
wills | +2.665 |
riors | +2.644 |
Neg logit contributions | |
hatt | -5.700 |
Beer | -5.512 |
andr | -5.166 |
coat | -5.089 |
ness | -5.031 |
Token | swing |
Token ID | 9628 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
orem | +5.315 |
ril | +5.147 |
nerv | +4.922 |
wills | +4.874 |
riors | +4.847 |
Neg logit contributions | |
hatt | -5.856 |
Beer | -5.762 |
andr | -5.187 |
coat | -5.063 |
Feel | -4.890 |
Token | man |
Token ID | 805 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
orem | +2.416 |
ril | +2.369 |
nerv | +2.236 |
riors | +2.176 |
wills | +2.170 |
Neg logit contributions | |
hatt | -2.888 |
Beer | -2.802 |
coat | -2.518 |
andr | -2.514 |
ness | -2.491 |
Token | Jae |
Token ID | 34521 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
orem | +0.630 |
ril | +0.619 |
nerv | +0.593 |
wills | +0.580 |
riors | +0.578 |
Neg logit contributions | |
hatt | -0.596 |
Beer | -0.574 |
coat | -0.516 |
andr | -0.515 |
ness | -0.504 |
Token | Crow |
Token ID | 15502 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
hatt | +1.023 |
Beer | +0.991 |
coat | +0.915 |
andr | +0.914 |
ness | +0.910 |
Neg logit contributions | |
orem | -0.669 |
ril | -0.650 |
nerv | -0.616 |
riors | -0.594 |
wills | -0.591 |
Token | der |
Token ID | 1082 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
hatt | +0.666 |
Beer | +0.634 |
coat | +0.563 |
andr | +0.561 |
ness | +0.560 |
Neg logit contributions | |
orem | -0.912 |
ril | -0.893 |
nerv | -0.863 |
wills | -0.839 |
riors | -0.839 |
Token | " |
Token ID | 366 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
orem | +0.884 |
ril | +0.861 |
nerv | +0.823 |
wills | +0.804 |
riors | +0.799 |
Neg logit contributions | |
hatt | -0.885 |
Beer | -0.851 |
coat | -0.768 |
andr | -0.768 |
ness | -0.759 |
Token | Show |
Token ID | 15307 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
hatt | +1.084 |
Beer | +1.037 |
coat | +0.925 |
andr | +0.925 |
ness | +0.919 |
Neg logit contributions | |
orem | -1.376 |
ril | -1.349 |
nerv | -1.297 |
riors | -1.266 |
wills | -1.261 |
Token | Spe |
Token ID | 2531 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
hatt | +0.527 |
Beer | +0.508 |
ness | +0.461 |
coat | +0.461 |
andr | +0.460 |
Neg logit contributions | |
orem | -0.493 |
ril | -0.483 |
nerv | -0.461 |
riors | -0.449 |
wills | -0.445 |
Token | lling |
Token ID | 2680 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
hatt | +0.237 |
Beer | +0.228 |
coat | +0.206 |
andr | +0.206 |
ness | +0.206 |
Neg logit contributions | |
orem | -0.237 |
ril | -0.231 |
nerv | -0.222 |
riors | -0.216 |
wills | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
orem | +0.303 |
ril | +0.295 |
nerv | +0.282 |
riors | +0.274 |
wills | +0.273 |
Neg logit contributions | |
hatt | -0.326 |
Beer | -0.314 |
andr | -0.286 |
coat | -0.286 |
ness | -0.283 |
Token | Gram |
Token ID | 20159 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
orem | +0.147 |
ril | +0.143 |
nerv | +0.137 |
riors | +0.133 |
wills | +0.132 |
Neg logit contributions | |
hatt | -0.158 |
Beer | -0.152 |
coat | -0.139 |
andr | -0.139 |
ness | -0.138 |
Token | mar |
Token ID | 3876 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
orem | +3.980 |
ril | +3.910 |
nerv | +3.548 |
wills | +3.425 |
igation | +3.421 |
Neg logit contributions | |
hatt | -7.366 |
Beer | -7.127 |
andr | -6.586 |
coat | -6.475 |
Feel | -6.408 |
Token | " |
Token ID | 1 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
orem | +0.777 |
ril | +0.757 |
nerv | +0.724 |
riors | +0.703 |
wills | +0.701 |
Neg logit contributions | |
hatt | -0.835 |
Beer | -0.805 |
andr | -0.732 |
coat | -0.730 |
ness | -0.723 |
Token | from |
Token ID | 422 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
orem | +0.100 |
ril | +0.098 |
nerv | +0.093 |
riors | +0.091 |
wills | +0.091 |
Neg logit contributions | |
hatt | -0.095 |
Beer | -0.091 |
coat | -0.082 |
andr | -0.082 |
ness | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
orem | +0.089 |
ril | +0.087 |
nerv | +0.083 |
riors | +0.081 |
wills | +0.080 |
Neg logit contributions | |
hatt | -0.090 |
Beer | -0.087 |
coat | -0.079 |
andr | -0.079 |
ness | -0.078 |
Token | Spe |
Token ID | 2531 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
orem | +0.085 |
ril | +0.083 |
nerv | +0.079 |
riors | +0.077 |
wills | +0.077 |
Neg logit contributions | |
hatt | -0.094 |
Beer | -0.090 |
coat | -0.082 |
andr | -0.082 |
ness | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
orem | +1.685 |
ril | +1.649 |
nerv | +1.597 |
riors | +1.558 |
wills | +1.553 |
Neg logit contributions | |
hatt | -1.263 |
Beer | -1.203 |
andr | -1.073 |
coat | -1.068 |
ness | -1.051 |
Token | P |
Token ID | 350 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
orem | +0.226 |
ril | +0.220 |
nerv | +0.212 |
riors | +0.206 |
wills | +0.205 |
Neg logit contributions | |
hatt | -0.215 |
Beer | -0.206 |
andr | -0.186 |
coat | -0.186 |
ness | -0.185 |
Token | ious |
Token ID | 699 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
orem | +0.170 |
ril | +0.167 |
nerv | +0.160 |
wills | +0.155 |
riors | +0.154 |
Neg logit contributions | |
hatt | -0.182 |
Beer | -0.174 |
coat | -0.159 |
andr | -0.159 |
ness | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
orem | +0.640 |
ril | +0.627 |
nerv | +0.604 |
riors | +0.590 |
wills | +0.588 |
Neg logit contributions | |
hatt | -0.485 |
Beer | -0.463 |
andr | -0.412 |
coat | -0.411 |
ness | -0.407 |
Token | Sanct |
Token ID | 43990 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
orem | +0.167 |
ril | +0.163 |
nerv | +0.156 |
riors | +0.152 |
wills | +0.152 |
Neg logit contributions | |
hatt | -0.158 |
Beer | -0.152 |
andr | -0.137 |
coat | -0.137 |
ness | -0.136 |
Token | imon |
Token ID | 20473 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
orem | +1.199 |
ril | +1.166 |
nerv | +1.077 |
riors | +1.035 |
wills | +1.027 |
Neg logit contributions | |
hatt | -2.179 |
Beer | -2.117 |
andr | -1.951 |
coat | -1.951 |
ness | -1.937 |
Token | ious |
Token ID | 699 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
orem | +4.188 |
ril | +4.013 |
nerv | +3.655 |
rior | +3.604 |
igation | +3.561 |
Neg logit contributions | |
hatt | -7.045 |
Beer | -6.933 |
andr | -6.371 |
Feel | -6.279 |
coat | -6.241 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
orem | +0.608 |
ril | +0.596 |
nerv | +0.571 |
riors | +0.557 |
wills | +0.555 |
Neg logit contributions | |
hatt | -0.539 |
Beer | -0.517 |
coat | -0.465 |
andr | -0.465 |
ness | -0.462 |
Token |
|
Token ID | 198 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
hatt | +0.177 |
Beer | +0.170 |
andr | +0.156 |
coat | +0.154 |
ness | +0.151 |
Neg logit contributions | |
orem | -0.155 |
ril | -0.152 |
nerv | -0.143 |
riors | -0.141 |
rior | -0.140 |
Token | Why |
Token ID | 5195 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
orem | +0.144 |
ril | +0.142 |
nerv | +0.137 |
riors | +0.134 |
wills | +0.134 |
Neg logit contributions | |
hatt | -0.078 |
Beer | -0.074 |
coat | -0.064 |
andr | -0.064 |
ness | -0.063 |
Token | 1939 |
Token ID | 24414 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
orem | +1.600 |
ril | +1.568 |
nerv | +1.503 |
riors | +1.451 |
wills | +1.449 |
Neg logit contributions | |
hatt | -2.063 |
Beer | -1.987 |
andr | -1.830 |
coat | -1.814 |
ness | -1.790 |
Token | ists |
Token ID | 1023 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
hatt | +1.522 |
Beer | +1.460 |
coat | +1.346 |
andr | +1.342 |
ness | +1.340 |
Neg logit contributions | |
orem | -1.236 |
ril | -1.199 |
nerv | -1.141 |
wills | -1.104 |
riors | -1.096 |
Token | , |
Token ID | 11 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
hatt | +0.731 |
Beer | +0.701 |
coat | +0.632 |
andr | +0.632 |
ness | +0.628 |
Neg logit contributions | |
orem | -0.792 |
ril | -0.775 |
nerv | -0.742 |
riors | -0.723 |
wills | -0.720 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
hatt | +0.437 |
Beer | +0.419 |
coat | +0.379 |
andr | +0.378 |
ness | +0.376 |
Neg logit contributions | |
orem | -0.470 |
ril | -0.459 |
nerv | -0.440 |
riors | -0.429 |
wills | -0.427 |
Token | more |
Token ID | 517 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
hatt | +0.394 |
Beer | +0.378 |
coat | +0.341 |
andr | +0.340 |
ness | +0.338 |
Neg logit contributions | |
orem | -0.431 |
ril | -0.422 |
nerv | -0.405 |
riors | -0.394 |
wills | -0.393 |
Token | successful |
Token ID | 4388 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
hatt | +0.390 |
Beer | +0.374 |
coat | +0.338 |
andr | +0.338 |
ness | +0.336 |
Neg logit contributions | |
orem | -0.413 |
ril | -0.404 |
nerv | -0.387 |
riors | -0.377 |
wills | -0.375 |
Token | fellow |
Token ID | 5891 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
orem | +0.496 |
ril | +0.486 |
nerv | +0.466 |
riors | +0.454 |
wills | +0.452 |
Neg logit contributions | |
hatt | -0.498 |
Beer | -0.481 |
andr | -0.434 |
coat | -0.433 |
ness | -0.428 |
Token | worship |
Token ID | 11892 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
hatt | +2.878 |
Beer | +2.714 |
ness | +2.489 |
coat | +2.478 |
andr | +2.461 |
Neg logit contributions | |
orem | -3.186 |
ril | -3.122 |
nerv | -2.992 |
igation | -2.892 |
wills | -2.889 |
Token | ers |
Token ID | 364 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
hatt | +1.976 |
Beer | +1.855 |
ness | +1.617 |
andr | +1.616 |
coat | +1.614 |
Neg logit contributions | |
orem | -3.565 |
ril | -3.487 |
nerv | -3.387 |
wills | -3.294 |
riors | -3.261 |
Token | of |
Token ID | 286 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
hatt | +0.260 |
Beer | +0.251 |
coat | +0.229 |
andr | +0.229 |
ness | +0.228 |
Neg logit contributions | |
orem | -0.223 |
ril | -0.218 |
nerv | -0.207 |
riors | -0.201 |
wills | -0.201 |
Token | the |
Token ID | 262 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
hatt | +0.625 |
Beer | +0.600 |
coat | +0.540 |
andr | +0.540 |
ness | +0.536 |
Neg logit contributions | |
orem | -0.685 |
ril | -0.670 |
nerv | -0.643 |
riors | -0.626 |
wills | -0.624 |
Token | Lenin |
Token ID | 22899 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
hatt | +0.627 |
Beer | +0.602 |
coat | +0.542 |
andr | +0.541 |
ness | +0.538 |
Neg logit contributions | |
orem | -0.690 |
ril | -0.675 |
nerv | -0.648 |
riors | -0.631 |
wills | -0.629 |
Token | with |
Token ID | 351 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
hatt | +0.283 |
Beer | +0.273 |
coat | +0.248 |
ness | +0.248 |
andr | +0.248 |
Neg logit contributions | |
orem | -0.267 |
ril | -0.260 |
nerv | -0.249 |
riors | -0.243 |
wills | -0.241 |
Token | a |
Token ID | 257 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
hatt | +0.657 |
Beer | +0.632 |
coat | +0.572 |
andr | +0.571 |
ness | +0.570 |
Neg logit contributions | |
orem | -0.659 |
ril | -0.643 |
nerv | -0.614 |
riors | -0.599 |
wills | -0.596 |
Token | football |
Token ID | 4346 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
orem | +0.185 |
ril | +0.182 |
nerv | +0.175 |
riors | +0.169 |
wills | +0.169 |
Neg logit contributions | |
hatt | -0.171 |
Beer | -0.165 |
andr | -0.148 |
coat | -0.148 |
ness | -0.147 |
Token | treatment |
Token ID | 3513 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
orem | +0.997 |
ril | +0.976 |
nerv | +0.941 |
riors | +0.919 |
rior | +0.906 |
Neg logit contributions | |
hatt | -0.919 |
Beer | -0.887 |
andr | -0.797 |
coat | -0.789 |
ness | -0.780 |
Token | !) |
Token ID | 8133 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
orem | +1.159 |
ril | +1.142 |
nerv | +1.100 |
riors | +1.069 |
wills | +1.058 |
Neg logit contributions | |
hatt | -0.987 |
Beer | -0.949 |
andr | -0.850 |
coat | -0.843 |
ness | -0.835 |
Token | HA |
Token ID | 14558 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
orem | +0.363 |
ril | +0.355 |
nerv | +0.341 |
riors | +0.331 |
wills | +0.329 |
Neg logit contributions | |
hatt | -0.359 |
Beer | -0.345 |
coat | -0.312 |
andr | -0.312 |
ness | -0.310 |
Token | IRD |
Token ID | 46833 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
hatt | +2.380 |
Beer | +2.268 |
ness | +1.989 |
coat | +1.987 |
andr | +1.960 |
Neg logit contributions | |
orem | -3.738 |
ril | -3.646 |
nerv | -3.528 |
riors | -3.482 |
wills | -3.466 |
Token | RI |
Token ID | 7112 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
hatt | +1.322 |
Beer | +1.270 |
ness | +1.145 |
coat | +1.141 |
andr | +1.140 |
Neg logit contributions | |
orem | -1.479 |
ril | -1.439 |
nerv | -1.388 |
wills | -1.350 |
riors | -1.349 |
Token | ER |
Token ID | 1137 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
hatt | +0.165 |
Beer | +0.158 |
coat | +0.140 |
andr | +0.140 |
ness | +0.140 |
Neg logit contributions | |
orem | -0.218 |
ril | -0.214 |
nerv | -0.206 |
riors | -0.201 |
wills | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
orem | +0.428 |
ril | +0.419 |
nerv | +0.401 |
riors | +0.390 |
wills | +0.388 |
Neg logit contributions | |
hatt | -0.427 |
Beer | -0.411 |
andr | -0.372 |
coat | -0.372 |
ness | -0.369 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
orem | +0.113 |
ril | +0.111 |
nerv | +0.104 |
riors | +0.103 |
rior | +0.102 |
Neg logit contributions | |
hatt | -0.131 |
Beer | -0.125 |
andr | -0.115 |
coat | -0.113 |
ness | -0.111 |
Token | day |
Token ID | 1110 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
orem | +0.461 |
ril | +0.451 |
nerv | +0.434 |
wills | +0.421 |
riors | +0.420 |
Neg logit contributions | |
hatt | -0.422 |
Beer | -0.404 |
andr | -0.366 |
coat | -0.363 |
ness | -0.358 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
hatt | +0.194 |
Beer | +0.187 |
coat | +0.168 |
andr | +0.168 |
ness | +0.167 |
Neg logit contributions | |
orem | -0.219 |
ril | -0.214 |
nerv | -0.205 |
riors | -0.200 |
wills | -0.199 |
Token | � |
Token ID | 447 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
orem | +0.377 |
ril | +0.370 |
nerv | +0.356 |
riors | +0.347 |
wills | +0.345 |
Neg logit contributions | |
hatt | -0.345 |
Beer | -0.332 |
coat | -0.299 |
andr | -0.299 |
ness | -0.296 |
Token | � |
Token ID | 251 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
orem | +0.910 |
ril | +0.897 |
nerv | +0.868 |
riors | +0.851 |
wills | +0.847 |
Neg logit contributions | |
hatt | -0.444 |
Beer | -0.417 |
coat | -0.357 |
andr | -0.356 |
ness | -0.351 |
Token | said |
Token ID | 531 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
hatt | +0.362 |
Beer | +0.349 |
andr | +0.318 |
coat | +0.318 |
ness | +0.317 |
Neg logit contributions | |
orem | -0.320 |
ril | -0.311 |
nerv | -0.297 |
riors | -0.288 |
wills | -0.287 |
Token | Brenda |
Token ID | 49495 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
orem | +0.511 |
ril | +0.501 |
nerv | +0.478 |
riors | +0.466 |
wills | +0.464 |
Neg logit contributions | |
hatt | -0.513 |
Beer | -0.493 |
coat | -0.447 |
andr | -0.447 |
ness | -0.443 |
Token | � |
Token ID | 447 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
hatt | +3.106 |
Beer | +2.993 |
ness | +2.731 |
coat | +2.712 |
andr | +2.690 |
Neg logit contributions | |
orem | -2.992 |
ril | -2.882 |
nerv | -2.786 |
wills | -2.702 |
riors | -2.692 |
Token | � |
Token ID | 247 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
orem | +0.437 |
ril | +0.428 |
nerv | +0.406 |
riors | +0.396 |
rior | +0.391 |
Neg logit contributions | |
hatt | -0.515 |
Beer | -0.495 |
coat | -0.454 |
andr | -0.453 |
ness | -0.449 |
Token | s |
Token ID | 82 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
hatt | +0.218 |
Beer | +0.205 |
coat | +0.175 |
andr | +0.175 |
ness | +0.174 |
Neg logit contributions | |
orem | -0.435 |
ril | -0.428 |
nerv | -0.414 |
riors | -0.406 |
wills | -0.405 |
Token | oldest |
Token ID | 13325 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
orem | +0.847 |
ril | +0.827 |
nerv | +0.793 |
riors | +0.770 |
wills | +0.767 |
Neg logit contributions | |
hatt | -0.899 |
Beer | -0.866 |
andr | -0.786 |
coat | -0.785 |
ness | -0.775 |
Token | daughter |
Token ID | 4957 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
orem | +0.271 |
ril | +0.264 |
nerv | +0.252 |
riors | +0.243 |
wills | +0.243 |
Neg logit contributions | |
hatt | -0.332 |
Beer | -0.321 |
andr | -0.293 |
coat | -0.293 |
ness | -0.289 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
hatt | +0.487 |
Beer | +0.466 |
coat | +0.418 |
andr | +0.418 |
ness | +0.415 |
Neg logit contributions | |
orem | -0.579 |
ril | -0.567 |
nerv | -0.544 |
riors | -0.531 |
wills | -0.528 |
Token | - |
Token ID | 12 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
hatt | +0.829 |
Beer | +0.790 |
coat | +0.705 |
andr | +0.704 |
ness | +0.702 |
Neg logit contributions | |
orem | -1.068 |
ril | -1.043 |
nerv | -1.004 |
riors | -0.986 |
wills | -0.978 |
Token | ethyl |
Token ID | 21610 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
hatt | +0.722 |
Beer | +0.690 |
coat | +0.619 |
andr | +0.618 |
ness | +0.615 |
Neg logit contributions | |
orem | -0.887 |
ril | -0.868 |
nerv | -0.835 |
riors | -0.817 |
wills | -0.813 |
Token | - |
Token ID | 12 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
hatt | +2.715 |
Beer | +2.576 |
coat | +2.341 |
ness | +2.329 |
andr | +2.322 |
Neg logit contributions | |
orem | -3.304 |
ril | -3.237 |
nerv | -3.135 |
riors | -3.083 |
wills | -3.064 |
Token | N |
Token ID | 45 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
hatt | +0.929 |
Beer | +0.887 |
coat | +0.795 |
andr | +0.795 |
ness | +0.791 |
Neg logit contributions | |
orem | -1.122 |
ril | -1.098 |
nerv | -1.056 |
riors | -1.032 |
wills | -1.029 |
Token | -( |
Token ID | 30420 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
hatt | +0.076 |
Beer | +0.072 |
coat | +0.065 |
andr | +0.065 |
ness | +0.064 |
Neg logit contributions | |
orem | -0.089 |
ril | -0.087 |
nerv | -0.084 |
riors | -0.082 |
wills | -0.082 |
Token | t |
Token ID | 83 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
hatt | +2.986 |
Beer | +2.835 |
coat | +2.557 |
ness | +2.549 |
andr | +2.546 |
Neg logit contributions | |
orem | -3.694 |
ril | -3.588 |
nerv | -3.464 |
riors | -3.419 |
wills | -3.414 |
Token | et |
Token ID | 316 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
hatt | +0.678 |
Beer | +0.636 |
coat | +0.555 |
andr | +0.551 |
ness | +0.550 |
Neg logit contributions | |
orem | -1.264 |
ril | -1.246 |
nerv | -1.209 |
riors | -1.183 |
wills | -1.181 |
Token | rah |
Token ID | 11392 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
hatt | +0.123 |
Beer | +0.118 |
coat | +0.107 |
andr | +0.107 |
ness | +0.106 |
Neg logit contributions | |
orem | -0.132 |
ril | -0.130 |
nerv | -0.124 |
riors | -0.121 |
wills | -0.121 |
Token | yd |
Token ID | 5173 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
hatt | +0.960 |
Beer | +0.904 |
andr | +0.779 |
coat | +0.778 |
ness | +0.772 |
Neg logit contributions | |
orem | -1.832 |
ril | -1.800 |
nerv | -1.744 |
riors | -1.707 |
wills | -1.704 |
Token | ro |
Token ID | 305 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
hatt | +1.014 |
Beer | +0.952 |
coat | +0.851 |
andr | +0.844 |
ness | +0.844 |
Neg logit contributions | |
orem | -1.449 |
ril | -1.412 |
nerv | -1.383 |
wills | -1.354 |
riors | -1.347 |
Token | icycle |
Token ID | 35298 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
hatt | +1.777 |
Beer | +1.698 |
coat | +1.557 |
andr | +1.555 |
ness | +1.550 |
Neg logit contributions | |
orem | -1.621 |
ril | -1.586 |
nerv | -1.527 |
wills | -1.481 |
riors | -1.477 |
Token | keeps |
Token ID | 7622 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
hatt | +1.153 |
Beer | +1.106 |
coat | +0.999 |
ness | +0.996 |
andr | +0.995 |
Neg logit contributions | |
orem | -1.273 |
ril | -1.250 |
nerv | -1.189 |
riors | -1.164 |
wills | -1.154 |
Token | our |
Token ID | 674 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
hatt | +0.318 |
Beer | +0.306 |
andr | +0.277 |
coat | +0.276 |
ness | +0.274 |
Neg logit contributions | |
orem | -0.335 |
ril | -0.327 |
nerv | -0.315 |
riors | -0.306 |
wills | -0.305 |
Token | dreams |
Token ID | 10625 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
hatt | +0.198 |
Beer | +0.190 |
coat | +0.172 |
andr | +0.171 |
ness | +0.170 |
Neg logit contributions | |
orem | -0.210 |
ril | -0.205 |
nerv | -0.197 |
riors | -0.191 |
wills | -0.191 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
hatt | +0.246 |
Beer | +0.237 |
andr | +0.216 |
coat | +0.214 |
ness | +0.209 |
Neg logit contributions | |
orem | -0.241 |
ril | -0.238 |
nerv | -0.230 |
wills | -0.223 |
riors | -0.222 |
Token | speed |
Token ID | 2866 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
hatt | +0.286 |
Beer | +0.274 |
coat | +0.247 |
andr | +0.246 |
ness | +0.245 |
Neg logit contributions | |
orem | -0.320 |
ril | -0.313 |
nerv | -0.300 |
riors | -0.293 |
wills | -0.291 |
Token | er |
Token ID | 263 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
hatt | +2.830 |
Beer | +2.709 |
coat | +2.425 |
andr | +2.421 |
ness | +2.417 |
Neg logit contributions | |
orem | -3.435 |
ril | -3.358 |
nerv | -3.219 |
riors | -3.149 |
wills | -3.137 |
Token | bikes |
Token ID | 16715 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
orem | +0.642 |
ril | +0.631 |
nerv | +0.607 |
riors | +0.595 |
wills | +0.592 |
Neg logit contributions | |
hatt | -0.541 |
Beer | -0.520 |
andr | -0.467 |
coat | -0.466 |
ness | -0.454 |
Token | alive |
Token ID | 6776 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
hatt | +1.388 |
Beer | +1.335 |
andr | +1.201 |
coat | +1.198 |
ness | +1.183 |
Neg logit contributions | |
orem | -1.577 |
ril | -1.551 |
nerv | -1.492 |
riors | -1.449 |
wills | -1.448 |
Token | -- |
Token ID | 1377 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
orem | +0.323 |
ril | +0.316 |
nerv | +0.304 |
riors | +0.296 |
wills | +0.295 |
Neg logit contributions | |
hatt | -0.291 |
Beer | -0.280 |
andr | -0.252 |
coat | -0.251 |
ness | -0.249 |
Token | if |
Token ID | 611 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
orem | +0.123 |
ril | +0.120 |
nerv | +0.116 |
riors | +0.113 |
wills | +0.113 |
Neg logit contributions | |
hatt | -0.105 |
Beer | -0.101 |
coat | -0.091 |
andr | -0.090 |
ness | -0.089 |
Token | 14 |
Token ID | 1415 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
hatt | +0.113 |
Beer | +0.108 |
andr | +0.096 |
coat | +0.096 |
ness | +0.096 |
Neg logit contributions | |
orem | -0.143 |
ril | -0.140 |
nerv | -0.135 |
riors | -0.131 |
wills | -0.131 |
Token | dates |
Token ID | 9667 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
hatt | +0.650 |
Beer | +0.625 |
andr | +0.565 |
coat | +0.565 |
ness | +0.561 |
Neg logit contributions | |
orem | -0.665 |
ril | -0.650 |
nerv | -0.622 |
riors | -0.605 |
wills | -0.603 |
Token | in |
Token ID | 287 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
orem | +0.212 |
ril | +0.207 |
nerv | +0.200 |
riors | +0.194 |
wills | +0.194 |
Neg logit contributions | |
hatt | -0.183 |
Beer | -0.175 |
andr | -0.157 |
coat | -0.157 |
ness | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
hatt | +0.569 |
Beer | +0.548 |
andr | +0.496 |
coat | +0.495 |
ness | +0.491 |
Neg logit contributions | |
orem | -0.571 |
ril | -0.558 |
nerv | -0.535 |
riors | -0.520 |
wills | -0.518 |
Token | range |
Token ID | 2837 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
hatt | +0.192 |
Beer | +0.185 |
coat | +0.167 |
andr | +0.167 |
ness | +0.166 |
Neg logit contributions | |
orem | -0.189 |
ril | -0.185 |
nerv | -0.177 |
riors | -0.172 |
wills | -0.172 |
Token | of |
Token ID | 286 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
orem | +1.752 |
ril | +1.717 |
nerv | +1.644 |
riors | +1.582 |
wills | +1.575 |
Neg logit contributions | |
hatt | -2.152 |
Beer | -2.079 |
andr | -1.893 |
coat | -1.893 |
ness | -1.864 |
Token | 22 |
Token ID | 2534 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
orem | +0.087 |
ril | +0.085 |
nerv | +0.081 |
riors | +0.079 |
wills | +0.079 |
Neg logit contributions | |
hatt | -0.092 |
Beer | -0.089 |
coat | -0.081 |
andr | -0.081 |
ness | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
orem | +1.884 |
ril | +1.855 |
nerv | +1.778 |
riors | +1.732 |
wills | +1.726 |
Neg logit contributions | |
hatt | -1.614 |
Beer | -1.548 |
andr | -1.392 |
coat | -1.390 |
ness | -1.364 |
Token | 000 |
Token ID | 830 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
hatt | +0.187 |
Beer | +0.179 |
coat | +0.159 |
andr | +0.159 |
ness | +0.159 |
Neg logit contributions | |
orem | -0.240 |
ril | -0.235 |
nerv | -0.226 |
riors | -0.221 |
wills | -0.220 |
Token | to |
Token ID | 284 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
hatt | +1.335 |
Beer | +1.285 |
ness | +1.154 |
andr | +1.151 |
coat | +1.148 |
Neg logit contributions | |
orem | -1.581 |
ril | -1.536 |
nerv | -1.480 |
riors | -1.445 |
wills | -1.435 |
Token | 39 |
Token ID | 5014 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
hatt | +0.075 |
Beer | +0.072 |
coat | +0.065 |
andr | +0.065 |
ness | +0.064 |
Neg logit contributions | |
orem | -0.074 |
ril | -0.072 |
nerv | -0.069 |
riors | -0.067 |
wills | -0.067 |
Token | two |
Token ID | 734 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
hatt | +0.318 |
Beer | +0.305 |
andr | +0.274 |
coat | +0.274 |
ness | +0.271 |
Neg logit contributions | |
orem | -0.368 |
ril | -0.361 |
nerv | -0.348 |
wills | -0.337 |
riors | -0.337 |
Token | leads |
Token ID | 5983 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
orem | +0.581 |
ril | +0.571 |
nerv | +0.550 |
wills | +0.534 |
riors | +0.531 |
Neg logit contributions | |
hatt | -0.545 |
Beer | -0.526 |
andr | -0.475 |
coat | -0.471 |
ness | -0.466 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
hatt | +0.361 |
Beer | +0.348 |
andr | +0.313 |
coat | +0.311 |
ness | +0.307 |
Neg logit contributions | |
orem | -0.396 |
ril | -0.389 |
nerv | -0.373 |
wills | -0.363 |
riors | -0.362 |
Token | Hun |
Token ID | 5900 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
hatt | +0.163 |
Beer | +0.157 |
andr | +0.142 |
coat | +0.141 |
ness | +0.140 |
Neg logit contributions | |
orem | -0.172 |
ril | -0.168 |
nerv | -0.161 |
riors | -0.157 |
wills | -0.156 |
Token | nam |
Token ID | 7402 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
hatt | +1.834 |
Beer | +1.773 |
coat | +1.614 |
andr | +1.610 |
ness | +1.592 |
Neg logit contributions | |
orem | -1.636 |
ril | -1.603 |
nerv | -1.522 |
riors | -1.484 |
wills | -1.469 |
Token | joins |
Token ID | 15449 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
orem | +1.054 |
ril | +1.041 |
nerv | +0.997 |
wills | +0.967 |
riors | +0.965 |
Neg logit contributions | |
hatt | -1.132 |
Beer | -1.092 |
andr | -0.990 |
coat | -0.984 |
ness | -0.975 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
hatt | +2.227 |
Beer | +2.130 |
coat | +1.939 |
ness | +1.925 |
andr | +1.918 |
Neg logit contributions | |
orem | -2.461 |
ril | -2.395 |
nerv | -2.293 |
riors | -2.247 |
wills | -2.228 |
Token | list |
Token ID | 1351 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
hatt | +0.214 |
Beer | +0.205 |
coat | +0.185 |
andr | +0.185 |
ness | +0.184 |
Neg logit contributions | |
orem | -0.237 |
ril | -0.231 |
nerv | -0.221 |
riors | -0.216 |
wills | -0.215 |
Token | of |
Token ID | 286 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
orem | +0.360 |
ril | +0.351 |
nerv | +0.334 |
riors | +0.325 |
wills | +0.323 |
Neg logit contributions | |
hatt | -0.423 |
Beer | -0.408 |
coat | -0.373 |
andr | -0.372 |
ness | -0.371 |
Token | actors |
Token ID | 10544 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
hatt | +0.040 |
Beer | +0.039 |
andr | +0.035 |
coat | +0.035 |
ness | +0.035 |
Neg logit contributions | |
orem | -0.041 |
ril | -0.040 |
nerv | -0.038 |
riors | -0.037 |
wills | -0.037 |
Token | being |
Token ID | 852 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
orem | +1.176 |
ril | +1.160 |
nerv | +1.121 |
wills | +1.081 |
riors | +1.074 |
Neg logit contributions | |
hatt | -1.189 |
Beer | -1.148 |
andr | -1.045 |
coat | -1.037 |
ness | -1.012 |
Token | have |
Token ID | 423 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
hatt | +0.755 |
Beer | +0.724 |
coat | +0.649 |
andr | +0.649 |
ness | +0.644 |
Neg logit contributions | |
orem | -0.885 |
ril | -0.866 |
nerv | -0.832 |
riors | -0.811 |
wills | -0.808 |
Token | to |
Token ID | 284 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
orem | +0.858 |
ril | +0.840 |
nerv | +0.806 |
riors | +0.783 |
wills | +0.781 |
Neg logit contributions | |
hatt | -0.798 |
Beer | -0.768 |
andr | -0.691 |
coat | -0.690 |
ness | -0.684 |
Token | be |
Token ID | 307 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
orem | +0.045 |
ril | +0.044 |
nerv | +0.042 |
riors | +0.041 |
wills | +0.041 |
Neg logit contributions | |
hatt | -0.047 |
Beer | -0.045 |
andr | -0.041 |
coat | -0.041 |
ness | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
hatt | +0.419 |
Beer | +0.402 |
coat | +0.361 |
andr | +0.360 |
ness | +0.359 |
Neg logit contributions | |
orem | -0.487 |
ril | -0.477 |
nerv | -0.457 |
riors | -0.446 |
wills | -0.444 |
Token | practicing |
Token ID | 18207 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
orem | +0.342 |
ril | +0.334 |
nerv | +0.321 |
riors | +0.312 |
wills | +0.310 |
Neg logit contributions | |
hatt | -0.334 |
Beer | -0.321 |
andr | -0.290 |
coat | -0.290 |
ness | -0.288 |
Token | Lac |
Token ID | 23115 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
orem | +1.751 |
ril | +1.710 |
nerv | +1.656 |
wills | +1.596 |
riors | +1.588 |
Neg logit contributions | |
hatt | -1.895 |
Beer | -1.835 |
andr | -1.658 |
coat | -1.656 |
ness | -1.636 |
Token | anian |
Token ID | 38336 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
orem | +0.285 |
ril | +0.280 |
nerv | +0.270 |
riors | +0.264 |
wills | +0.263 |
Neg logit contributions | |
hatt | -0.173 |
Beer | -0.166 |
andr | -0.144 |
coat | -0.144 |
ness | -0.143 |
Token | psych |
Token ID | 3795 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
orem | +0.780 |
ril | +0.763 |
nerv | +0.735 |
riors | +0.714 |
wills | +0.710 |
Neg logit contributions | |
hatt | -0.725 |
Beer | -0.698 |
andr | -0.628 |
coat | -0.627 |
ness | -0.622 |
Token | oan |
Token ID | 24611 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
orem | +0.397 |
ril | +0.385 |
nerv | +0.362 |
riors | +0.349 |
wills | +0.347 |
Neg logit contributions | |
hatt | -0.679 |
Beer | -0.657 |
coat | -0.609 |
andr | -0.609 |
ness | -0.607 |
Token | alyst |
Token ID | 21470 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
orem | +2.234 |
ril | +2.178 |
nerv | +2.066 |
riors | +1.994 |
rior | +1.985 |
Neg logit contributions | |
hatt | -3.037 |
Beer | -2.980 |
andr | -2.706 |
coat | -2.705 |
ness | -2.689 |
Token | to |
Token ID | 284 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
orem | +1.192 |
ril | +1.171 |
nerv | +1.130 |
riors | +1.091 |
wills | +1.081 |
Neg logit contributions | |
hatt | -1.139 |
Beer | -1.111 |
andr | -0.998 |
coat | -0.989 |
ness | -0.975 |
Token | way |
Token ID | 835 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
orem | +1.327 |
ril | +1.300 |
nerv | +1.270 |
wills | +1.227 |
riors | +1.226 |
Neg logit contributions | |
hatt | -1.048 |
Beer | -1.003 |
andr | -0.896 |
coat | -0.890 |
ness | -0.870 |
Token | to |
Token ID | 284 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
hatt | +1.147 |
Beer | +1.094 |
ness | +0.991 |
coat | +0.985 |
andr | +0.980 |
Neg logit contributions | |
orem | -1.348 |
ril | -1.302 |
nerv | -1.252 |
wills | -1.226 |
riors | -1.219 |
Token | kick |
Token ID | 4829 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
orem | +0.292 |
ril | +0.287 |
nerv | +0.277 |
riors | +0.268 |
wills | +0.267 |
Neg logit contributions | |
hatt | -0.278 |
Beer | -0.268 |
andr | -0.241 |
coat | -0.240 |
ness | -0.238 |
Token | start |
Token ID | 923 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
orem | +0.416 |
ril | +0.410 |
nerv | +0.393 |
wills | +0.383 |
riors | +0.383 |
Neg logit contributions | |
hatt | -0.332 |
Beer | -0.319 |
andr | -0.285 |
coat | -0.282 |
ness | -0.280 |
Token | a |
Token ID | 257 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
orem | +0.737 |
ril | +0.729 |
nerv | +0.698 |
wills | +0.675 |
riors | +0.672 |
Neg logit contributions | |
hatt | -0.841 |
Beer | -0.813 |
andr | -0.744 |
coat | -0.734 |
ness | -0.725 |
Token | child |
Token ID | 1200 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
orem | +0.076 |
ril | +0.075 |
nerv | +0.073 |
wills | +0.071 |
riors | +0.071 |
Neg logit contributions | |
hatt | -0.056 |
Beer | -0.054 |
andr | -0.048 |
coat | -0.048 |
ness | -0.047 |
Token | � |
Token ID | 447 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
hatt | +0.986 |
Beer | +0.946 |
andr | +0.848 |
coat | +0.847 |
ness | +0.841 |
Neg logit contributions | |
orem | -1.168 |
ril | -1.147 |
nerv | -1.100 |
riors | -1.073 |
wills | -1.069 |
Token | � |
Token ID | 247 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
hatt | +0.016 |
Beer | +0.015 |
andr | +0.014 |
coat | +0.014 |
ness | +0.014 |
Neg logit contributions | |
orem | -0.014 |
ril | -0.014 |
nerv | -0.013 |
riors | -0.013 |
wills | -0.013 |
Token | s |
Token ID | 82 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
orem | +0.136 |
ril | +0.134 |
nerv | +0.128 |
riors | +0.125 |
wills | +0.124 |
Neg logit contributions | |
hatt | -0.118 |
Beer | -0.114 |
coat | -0.102 |
andr | -0.102 |
ness | -0.101 |
Token | play |
Token ID | 711 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
orem | +0.572 |
ril | +0.563 |
nerv | +0.544 |
wills | +0.526 |
riors | +0.526 |
Neg logit contributions | |
hatt | -0.495 |
Beer | -0.478 |
andr | -0.428 |
coat | -0.425 |
ness | -0.417 |
Token | and |
Token ID | 290 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
ril | +1.573 |
orem | +1.572 |
nerv | +1.502 |
riors | +1.473 |
wills | +1.463 |
Neg logit contributions | |
hatt | -1.330 |
Beer | -1.297 |
andr | -1.148 |
coat | -1.136 |
ness | -1.111 |
Token | need |
Token ID | 761 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
hatt | +1.413 |
Beer | +1.357 |
coat | +1.230 |
andr | +1.228 |
ness | +1.228 |
Neg logit contributions | |
orem | -1.416 |
ril | -1.386 |
nerv | -1.320 |
riors | -1.289 |
wills | -1.281 |
Token | to |
Token ID | 284 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
orem | +0.007 |
ril | +0.007 |
nerv | +0.006 |
riors | +0.006 |
wills | +0.006 |
Neg logit contributions | |
hatt | -0.006 |
Beer | -0.006 |
andr | -0.006 |
coat | -0.005 |
ness | -0.005 |
Token | be |
Token ID | 307 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
orem | +0.344 |
ril | +0.335 |
nerv | +0.320 |
riors | +0.311 |
wills | +0.309 |
Neg logit contributions | |
hatt | -0.393 |
Beer | -0.381 |
andr | -0.347 |
coat | -0.345 |
ness | -0.342 |
Token | studied |
Token ID | 9713 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
hatt | +0.677 |
Beer | +0.655 |
andr | +0.594 |
coat | +0.591 |
ness | +0.587 |
Neg logit contributions | |
orem | -0.659 |
ril | -0.644 |
nerv | -0.618 |
riors | -0.599 |
wills | -0.598 |
Token | further |
Token ID | 2252 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
hatt | +0.139 |
Beer | +0.133 |
andr | +0.120 |
coat | +0.120 |
ness | +0.119 |
Neg logit contributions | |
orem | -0.145 |
ril | -0.142 |
nerv | -0.136 |
riors | -0.132 |
wills | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
hatt | +1.310 |
Beer | +1.255 |
coat | +1.130 |
andr | +1.127 |
ness | +1.125 |
Neg logit contributions | |
orem | -1.515 |
ril | -1.483 |
nerv | -1.420 |
riors | -1.387 |
wills | -1.382 |
Token | my |
Token ID | 616 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
hatt | +0.174 |
Beer | +0.167 |
coat | +0.150 |
andr | +0.150 |
ness | +0.149 |
Neg logit contributions | |
orem | -0.192 |
ril | -0.188 |
nerv | -0.180 |
riors | -0.176 |
wills | -0.175 |
Token | advice |
Token ID | 5608 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
hatt | +1.205 |
Beer | +1.157 |
coat | +1.047 |
andr | +1.045 |
ness | +1.042 |
Neg logit contributions | |
orem | -1.245 |
ril | -1.219 |
nerv | -1.165 |
riors | -1.137 |
wills | -1.131 |
Token | for |
Token ID | 329 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
hatt | +0.257 |
Beer | +0.247 |
andr | +0.223 |
coat | +0.222 |
ness | +0.220 |
Neg logit contributions | |
orem | -0.262 |
ril | -0.256 |
nerv | -0.245 |
riors | -0.239 |
wills | -0.238 |
Token | policy |
Token ID | 2450 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
hatt | +0.257 |
Beer | +0.247 |
coat | +0.224 |
andr | +0.224 |
ness | +0.223 |
Neg logit contributions | |
orem | -0.256 |
ril | -0.251 |
nerv | -0.239 |
riors | -0.233 |
wills | -0.232 |
Token | makers |
Token ID | 14429 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
orem | +0.792 |
ril | +0.776 |
nerv | +0.743 |
riors | +0.724 |
wills | +0.719 |
Neg logit contributions | |
hatt | -0.881 |
Beer | -0.847 |
andr | -0.772 |
coat | -0.769 |
ness | -0.763 |
Token | another |
Token ID | 1194 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
orem | +1.156 |
ril | +1.131 |
nerv | +1.089 |
wills | +1.054 |
riors | +1.047 |
Neg logit contributions | |
hatt | -1.109 |
Beer | -1.078 |
andr | -0.971 |
coat | -0.964 |
ness | -0.945 |
Token | drawing |
Token ID | 8263 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
hatt | +0.800 |
Beer | +0.769 |
coat | +0.694 |
andr | +0.693 |
ness | +0.689 |
Neg logit contributions | |
orem | -0.854 |
ril | -0.835 |
nerv | -0.800 |
riors | -0.780 |
wills | -0.776 |
Token | or |
Token ID | 393 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
orem | +0.773 |
ril | +0.759 |
nerv | +0.730 |
riors | +0.705 |
wills | +0.704 |
Neg logit contributions | |
hatt | -0.700 |
Beer | -0.675 |
andr | -0.607 |
coat | -0.603 |
ness | -0.596 |
Token | poem |
Token ID | 21247 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
orem | +0.063 |
ril | +0.062 |
nerv | +0.059 |
riors | +0.057 |
wills | +0.056 |
Neg logit contributions | |
hatt | -0.083 |
Beer | -0.081 |
andr | -0.074 |
coat | -0.074 |
ness | -0.073 |
Token | shortly |
Token ID | 8972 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
orem | +1.830 |
ril | +1.793 |
nerv | +1.741 |
wills | +1.669 |
riors | +1.667 |
Neg logit contributions | |
hatt | -1.735 |
Beer | -1.684 |
andr | -1.512 |
coat | -1.493 |
ness | -1.465 |
Token | after |
Token ID | 706 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
hatt | +0.218 |
Beer | +0.211 |
coat | +0.194 |
andr | +0.194 |
ness | +0.193 |
Neg logit contributions | |
orem | -0.156 |
ril | -0.152 |
nerv | -0.144 |
riors | -0.139 |
wills | -0.139 |
Token | finishing |
Token ID | 12848 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
orem | +0.677 |
ril | +0.662 |
nerv | +0.635 |
wills | +0.615 |
riors | +0.614 |
Neg logit contributions | |
hatt | -0.697 |
Beer | -0.672 |
andr | -0.610 |
coat | -0.607 |
ness | -0.600 |
Token | the |
Token ID | 262 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
orem | +0.487 |
ril | +0.475 |
nerv | +0.457 |
riors | +0.443 |
wills | +0.443 |
Neg logit contributions | |
hatt | -0.459 |
Beer | -0.441 |
andr | -0.399 |
coat | -0.396 |
ness | -0.392 |
Token | first |
Token ID | 717 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
orem | +0.059 |
ril | +0.057 |
nerv | +0.055 |
wills | +0.053 |
riors | +0.053 |
Neg logit contributions | |
hatt | -0.057 |
Beer | -0.055 |
andr | -0.050 |
coat | -0.050 |
ness | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
hatt | +0.892 |
Beer | +0.853 |
coat | +0.765 |
andr | +0.762 |
ness | +0.761 |
Neg logit contributions | |
orem | -1.095 |
ril | -1.073 |
nerv | -1.029 |
riors | -1.007 |
wills | -1.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
hatt | +0.111 |
Beer | +0.106 |
coat | +0.096 |
andr | +0.096 |
ness | +0.096 |
Neg logit contributions | |
orem | -0.114 |
ril | -0.111 |
nerv | -0.106 |
riors | -0.104 |
wills | -0.103 |
Token | ov |
Token ID | 709 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
hatt | +1.025 |
Beer | +0.991 |
coat | +0.914 |
andr | +0.913 |
ness | +0.911 |
Neg logit contributions | |
orem | -0.706 |
ril | -0.686 |
nerv | -0.653 |
riors | -0.629 |
wills | -0.627 |
Token | , |
Token ID | 11 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
orem | +2.439 |
ril | +2.418 |
nerv | +2.308 |
riors | +2.258 |
wills | +2.238 |
Neg logit contributions | |
hatt | -2.292 |
Beer | -2.216 |
coat | -1.998 |
andr | -1.991 |
ness | -1.953 |
Token | now |
Token ID | 783 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
hatt | +0.579 |
Beer | +0.556 |
andr | +0.505 |
coat | +0.505 |
ness | +0.504 |
Neg logit contributions | |
orem | -0.570 |
ril | -0.555 |
nerv | -0.530 |
riors | -0.518 |
wills | -0.514 |
Token | 88 |
Token ID | 9193 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
hatt | +0.108 |
Beer | +0.104 |
coat | +0.094 |
andr | +0.094 |
ness | +0.093 |
Neg logit contributions | |
orem | -0.110 |
ril | -0.108 |
nerv | -0.103 |
riors | -0.100 |
wills | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
orem | +0.733 |
ril | +0.718 |
nerv | +0.690 |
riors | +0.673 |
wills | +0.671 |
Neg logit contributions | |
hatt | -0.607 |
Beer | -0.580 |
coat | -0.520 |
andr | -0.520 |
ness | -0.512 |
Token | Philadelphia |
Token ID | 8857 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
hatt | +0.235 |
Beer | +0.226 |
andr | +0.204 |
coat | +0.204 |
ness | +0.203 |
Neg logit contributions | |
orem | -0.240 |
ril | -0.234 |
nerv | -0.224 |
riors | -0.218 |
wills | -0.217 |
Token | � |
Token ID | 447 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
orem | +1.338 |
ril | +1.308 |
nerv | +1.252 |
riors | +1.215 |
wills | +1.214 |
Neg logit contributions | |
hatt | -1.410 |
Beer | -1.352 |
andr | -1.233 |
coat | -1.228 |
ness | -1.209 |
Token | � |
Token ID | 247 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
hatt | +0.124 |
Beer | +0.118 |
coat | +0.103 |
andr | +0.103 |
ness | +0.103 |
Neg logit contributions | |
orem | -0.193 |
ril | -0.189 |
nerv | -0.182 |
riors | -0.178 |
wills | -0.178 |
Token | s |
Token ID | 82 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
hatt | +0.043 |
Beer | +0.041 |
andr | +0.036 |
coat | +0.036 |
ness | +0.036 |
Neg logit contributions | |
orem | -0.063 |
ril | -0.062 |
nerv | -0.060 |
riors | -0.059 |
wills | -0.058 |
Token | accents |
Token ID | 39271 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
orem | +0.329 |
ril | +0.323 |
nerv | +0.310 |
riors | +0.301 |
wills | +0.300 |
Neg logit contributions | |
hatt | -0.307 |
Beer | -0.295 |
coat | -0.266 |
andr | -0.265 |
ness | -0.262 |
Token | are |
Token ID | 389 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
hatt | +1.007 |
Beer | +0.967 |
coat | +0.876 |
andr | +0.875 |
ness | +0.872 |
Neg logit contributions | |
orem | -1.033 |
ril | -1.011 |
nerv | -0.967 |
riors | -0.942 |
wills | -0.938 |
Token | � |
Token ID | 447 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
orem | +1.303 |
ril | +1.278 |
nerv | +1.230 |
riors | +1.200 |
wills | +1.195 |
Neg logit contributions | |
hatt | -0.996 |
Beer | -0.952 |
coat | -0.847 |
andr | -0.847 |
ness | -0.839 |
Token | � |
Token ID | 247 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
orem | +0.232 |
ril | +0.227 |
nerv | +0.215 |
riors | +0.209 |
rior | +0.206 |
Neg logit contributions | |
hatt | -0.305 |
Beer | -0.293 |
coat | -0.269 |
andr | -0.269 |
ness | -0.267 |
Token | s |
Token ID | 82 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
hatt | +0.018 |
Beer | +0.017 |
coat | +0.014 |
andr | +0.014 |
ness | +0.014 |
Neg logit contributions | |
orem | -0.051 |
ril | -0.050 |
nerv | -0.048 |
riors | -0.048 |
wills | -0.047 |
Token | sake |
Token ID | 11060 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
orem | +0.648 |
ril | +0.635 |
nerv | +0.611 |
riors | +0.595 |
wills | +0.592 |
Neg logit contributions | |
hatt | -0.522 |
Beer | -0.501 |
coat | -0.447 |
andr | -0.446 |
ness | -0.441 |
Token | , |
Token ID | 11 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
orem | +1.331 |
ril | +1.305 |
nerv | +1.257 |
riors | +1.228 |
wills | +1.221 |
Neg logit contributions | |
hatt | -0.969 |
Beer | -0.926 |
coat | -0.822 |
andr | -0.821 |
ness | -0.814 |
Token | American |
Token ID | 1605 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
orem | +0.110 |
ril | +0.108 |
nerv | +0.103 |
riors | +0.100 |
wills | +0.100 |
Neg logit contributions | |
hatt | -0.109 |
Beer | -0.105 |
coat | -0.095 |
andr | -0.095 |
ness | -0.094 |
Token | Horror |
Token ID | 22732 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
orem | +0.558 |
ril | +0.538 |
nerv | +0.508 |
riors | +0.482 |
wills | +0.481 |
Neg logit contributions | |
hatt | -1.038 |
Beer | -1.005 |
andr | -0.935 |
coat | -0.934 |
ness | -0.925 |
Token | Story |
Token ID | 8362 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
orem | +1.577 |
ril | +1.556 |
nerv | +1.404 |
riors | +1.389 |
rior | +1.360 |
Neg logit contributions | |
hatt | -3.152 |
Beer | -3.076 |
andr | -2.871 |
coat | -2.844 |
ness | -2.795 |
Token | : |
Token ID | 25 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
orem | +1.092 |
ril | +1.067 |
nerv | +1.026 |
riors | +0.993 |
wills | +0.990 |
Neg logit contributions | |
hatt | -1.097 |
Beer | -1.054 |
andr | -0.956 |
coat | -0.954 |
ness | -0.944 |
Token | Murder |
Token ID | 23375 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
orem | +0.204 |
ril | +0.199 |
nerv | +0.191 |
riors | +0.186 |
wills | +0.184 |
Neg logit contributions | |
hatt | -0.194 |
Beer | -0.186 |
coat | -0.169 |
andr | -0.168 |
ness | -0.167 |
Token | House |
Token ID | 2097 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
hatt | +0.613 |
Beer | +0.589 |
andr | +0.535 |
coat | +0.533 |
ness | +0.529 |
Neg logit contributions | |
orem | -0.611 |
ril | -0.597 |
nerv | -0.571 |
riors | -0.557 |
wills | -0.554 |
Token | That |
Token ID | 1320 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
orem | +0.371 |
ril | +0.365 |
nerv | +0.348 |
riors | +0.340 |
wills | +0.337 |
Neg logit contributions | |
hatt | -0.355 |
Beer | -0.340 |
andr | -0.308 |
coat | -0.308 |
ness | -0.304 |
Token | is |
Token ID | 318 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
hatt | +0.603 |
Beer | +0.579 |
andr | +0.521 |
coat | +0.520 |
ness | +0.514 |
Neg logit contributions | |
orem | -0.665 |
ril | -0.653 |
nerv | -0.626 |
riors | -0.609 |
wills | -0.607 |
Token | not |
Token ID | 407 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
hatt | +0.782 |
Beer | +0.750 |
andr | +0.673 |
coat | +0.673 |
ness | +0.667 |
Neg logit contributions | |
orem | -0.902 |
ril | -0.884 |
nerv | -0.850 |
riors | -0.826 |
wills | -0.824 |
Token | even |
Token ID | 772 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
orem | +0.395 |
ril | +0.388 |
nerv | +0.376 |
wills | +0.362 |
riors | +0.359 |
Neg logit contributions | |
hatt | -0.376 |
Beer | -0.363 |
andr | -0.326 |
coat | -0.326 |
ness | -0.318 |
Token | the |
Token ID | 262 |
Feature activation | +9.11e-05 |
Pos logit contributions | |
hatt | +0.759 |
Beer | +0.730 |
andr | +0.658 |
coat | +0.658 |
ness | +0.652 |
Neg logit contributions | |
orem | -0.820 |
ril | -0.803 |
nerv | -0.771 |
riors | -0.748 |
wills | -0.746 |
Token | worst |
Token ID | 5290 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
hatt | +0.000 |
Beer | +0.000 |
andr | +0.000 |
coat | +0.000 |
ness | +0.000 |
Neg logit contributions | |
orem | -0.000 |
ril | -0.000 |
nerv | -0.000 |
riors | -0.000 |
wills | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
orem | +0.601 |
ril | +0.588 |
nerv | +0.563 |
riors | +0.547 |
wills | +0.545 |
Neg logit contributions | |
hatt | -0.586 |
Beer | -0.563 |
andr | -0.510 |
coat | -0.508 |
ness | -0.503 |
Token | it |
Token ID | 340 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
hatt | +0.261 |
Beer | +0.252 |
coat | +0.230 |
ness | +0.230 |
andr | +0.229 |
Neg logit contributions | |
orem | -0.219 |
ril | -0.214 |
nerv | -0.202 |
riors | -0.198 |
wills | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
orem | +0.142 |
ril | +0.139 |
nerv | +0.134 |
riors | +0.130 |
wills | +0.129 |
Neg logit contributions | |
hatt | -0.125 |
Beer | -0.120 |
andr | -0.108 |
coat | -0.108 |
ness | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
orem | +0.203 |
ril | +0.199 |
nerv | +0.190 |
riors | +0.185 |
wills | +0.183 |
Neg logit contributions | |
hatt | -0.199 |
Beer | -0.191 |
andr | -0.173 |
coat | -0.173 |
ness | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
hatt | +0.134 |
Beer | +0.128 |
andr | +0.118 |
coat | +0.116 |
ness | +0.114 |
Neg logit contributions | |
orem | -0.118 |
ril | -0.116 |
nerv | -0.108 |
riors | -0.107 |
rior | -0.106 |
Token | our |
Token ID | 674 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
orem | +0.873 |
ril | +0.863 |
nerv | +0.835 |
wills | +0.811 |
riors | +0.803 |
Neg logit contributions | |
hatt | -0.794 |
Beer | -0.765 |
andr | -0.689 |
coat | -0.677 |
ness | -0.666 |
Token | legs |
Token ID | 7405 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
orem | +0.226 |
ril | +0.222 |
nerv | +0.214 |
wills | +0.210 |
riors | +0.207 |
Neg logit contributions | |
hatt | -0.219 |
Beer | -0.213 |
andr | -0.192 |
coat | -0.190 |
ness | -0.187 |
Token | open |
Token ID | 1280 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
orem | +0.800 |
ril | +0.788 |
nerv | +0.766 |
wills | +0.751 |
riors | +0.733 |
Neg logit contributions | |
hatt | -0.734 |
Beer | -0.719 |
andr | -0.638 |
coat | -0.628 |
ness | -0.617 |
Token | . |
Token ID | 13 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
orem | +1.384 |
ril | +1.371 |
nerv | +1.333 |
wills | +1.294 |
riors | +1.274 |
Neg logit contributions | |
hatt | -1.243 |
Beer | -1.206 |
andr | -1.083 |
coat | -1.062 |
ness | -1.032 |
Token | I |
Token ID | 314 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
orem | +0.455 |
ril | +0.447 |
nerv | +0.428 |
riors | +0.417 |
wills | +0.414 |
Neg logit contributions | |
hatt | -0.430 |
Beer | -0.412 |
andr | -0.373 |
coat | -0.372 |
ness | -0.368 |
Token | found |
Token ID | 1043 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
orem | +0.786 |
ril | +0.782 |
nerv | +0.754 |
wills | +0.728 |
riors | +0.723 |
Neg logit contributions | |
hatt | -0.736 |
Beer | -0.720 |
andr | -0.642 |
coat | -0.639 |
ness | -0.624 |
Token | it |
Token ID | 340 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
orem | +0.884 |
ril | +0.870 |
nerv | +0.841 |
wills | +0.816 |
riors | +0.809 |
Neg logit contributions | |
hatt | -0.877 |
Beer | -0.847 |
andr | -0.765 |
coat | -0.760 |
ness | -0.745 |
Token | painful |
Token ID | 12132 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
orem | +0.859 |
ril | +0.848 |
nerv | +0.837 |
wills | +0.805 |
riors | +0.791 |
Neg logit contributions | |
hatt | -0.681 |
Beer | -0.654 |
andr | -0.585 |
coat | -0.579 |
ness | -0.560 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
orem | +1.106 |
ril | +1.095 |
nerv | +1.070 |
wills | +1.022 |
riors | +1.020 |
Neg logit contributions | |
hatt | -1.031 |
Beer | -0.999 |
andr | -0.900 |
coat | -0.887 |
ness | -0.853 |
Token | When |
Token ID | 1649 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
orem | +0.478 |
ril | +0.470 |
nerv | +0.450 |
riors | +0.439 |
wills | +0.435 |
Neg logit contributions | |
hatt | -0.450 |
Beer | -0.430 |
andr | -0.390 |
coat | -0.389 |
ness | -0.384 |
Token | he |
Token ID | 339 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
orem | +2.371 |
ril | +2.348 |
nerv | +2.269 |
wills | +2.196 |
riors | +2.172 |
Neg logit contributions | |
hatt | -2.731 |
Beer | -2.656 |
andr | -2.418 |
coat | -2.398 |
ness | -2.346 |
Token | d |
Token ID | 67 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
orem | +0.411 |
ril | +0.408 |
nerv | +0.392 |
riors | +0.383 |
rior | +0.380 |
Neg logit contributions | |
hatt | -0.244 |
Beer | -0.232 |
andr | -0.205 |
coat | -0.201 |
ness | -0.198 |
Token | recounted |
Token ID | 34187 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
orem | +0.159 |
ril | +0.156 |
nerv | +0.149 |
riors | +0.145 |
wills | +0.144 |
Neg logit contributions | |
hatt | -0.171 |
Beer | -0.165 |
andr | -0.150 |
coat | -0.150 |
ness | -0.149 |
Token | in |
Token ID | 287 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
hatt | +0.114 |
Beer | +0.110 |
andr | +0.099 |
coat | +0.099 |
ness | +0.098 |
Neg logit contributions | |
orem | -0.122 |
ril | -0.119 |
nerv | -0.115 |
riors | -0.111 |
wills | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
hatt | +0.243 |
Beer | +0.234 |
coat | +0.212 |
andr | +0.212 |
ness | +0.211 |
Neg logit contributions | |
orem | -0.241 |
ril | -0.236 |
nerv | -0.226 |
riors | -0.220 |
wills | -0.219 |
Token | New |
Token ID | 968 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
orem | +0.192 |
ril | +0.188 |
nerv | +0.179 |
riors | +0.174 |
wills | +0.173 |
Neg logit contributions | |
hatt | -0.214 |
Beer | -0.206 |
coat | -0.188 |
andr | -0.188 |
ness | -0.187 |
Token | York |
Token ID | 1971 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
orem | +1.025 |
ril | +1.003 |
nerv | +0.934 |
riors | +0.898 |
wills | +0.888 |
Neg logit contributions | |
hatt | -1.995 |
Beer | -1.932 |
andr | -1.800 |
coat | -1.793 |
ness | -1.775 |
Token | Times |
Token ID | 3782 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
orem | +2.214 |
ril | +2.150 |
nerv | +2.020 |
wills | +1.882 |
riors | +1.873 |
Neg logit contributions | |
hatt | -5.829 |
Beer | -5.652 |
andr | -5.317 |
coat | -5.293 |
ness | -5.234 |
Token | recently |
Token ID | 2904 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
orem | +2.424 |
ril | +2.390 |
nerv | +2.300 |
riors | +2.209 |
igation | +2.206 |
Neg logit contributions | |
hatt | -2.233 |
Beer | -2.151 |
andr | -1.956 |
coat | -1.937 |
ness | -1.915 |
Token | , |
Token ID | 11 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
hatt | +0.258 |
Beer | +0.247 |
andr | +0.220 |
coat | +0.220 |
ness | +0.217 |
Neg logit contributions | |
orem | -0.338 |
ril | -0.332 |
nerv | -0.319 |
riors | -0.311 |
wills | -0.310 |
Token | edible |
Token ID | 35988 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
hatt | +0.075 |
Beer | +0.072 |
coat | +0.066 |
andr | +0.066 |
ness | +0.065 |
Neg logit contributions | |
orem | -0.077 |
ril | -0.075 |
nerv | -0.072 |
riors | -0.070 |
wills | -0.070 |
Token | tet |
Token ID | 28408 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
hatt | +2.290 |
Beer | +2.208 |
ness | +2.044 |
coat | +2.001 |
andr | +1.996 |
Neg logit contributions | |
orem | -2.244 |
ril | -2.180 |
nerv | -2.059 |
riors | -2.037 |
wills | -1.999 |
Token |
|
Token ID | 198 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
hatt | +0.442 |
Beer | +0.422 |
andr | +0.389 |
coat | +0.384 |
ness | +0.375 |
Neg logit contributions | |
orem | -0.389 |
ril | -0.384 |
nerv | -0.359 |
riors | -0.354 |
rior | -0.352 |
Token | That |
Token ID | 2504 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
hatt | +0.051 |
Beer | +0.048 |
coat | +0.043 |
andr | +0.043 |
ness | +0.042 |
Neg logit contributions | |
orem | -0.077 |
ril | -0.076 |
nerv | -0.072 |
riors | -0.071 |
rior | -0.071 |
Token | being |
Token ID | 852 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
hatt | +0.677 |
Beer | +0.650 |
coat | +0.586 |
andr | +0.585 |
ness | +0.582 |
Neg logit contributions | |
orem | -0.738 |
ril | -0.723 |
nerv | -0.693 |
riors | -0.675 |
wills | -0.672 |
Token | said |
Token ID | 531 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
hatt | +0.113 |
Beer | +0.108 |
coat | +0.098 |
andr | +0.098 |
ness | +0.097 |
Neg logit contributions | |
orem | -0.126 |
ril | -0.123 |
nerv | -0.118 |
riors | -0.115 |
wills | -0.114 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
orem | +0.479 |
ril | +0.470 |
nerv | +0.452 |
riors | +0.442 |
wills | +0.440 |
Neg logit contributions | |
hatt | -0.338 |
Beer | -0.323 |
coat | -0.286 |
andr | -0.286 |
ness | -0.284 |
Token | Vil |
Token ID | 34037 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
hatt | +0.043 |
Beer | +0.041 |
coat | +0.038 |
andr | +0.038 |
ness | +0.037 |
Neg logit contributions | |
orem | -0.043 |
ril | -0.042 |
nerv | -0.040 |
riors | -0.039 |
wills | -0.039 |
Token | ma |
Token ID | 2611 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
orem | +1.949 |
ril | +1.833 |
igation | +1.539 |
riors | +1.519 |
rior | +1.513 |
Neg logit contributions | |
hatt | -6.120 |
Beer | -5.995 |
coat | -5.594 |
andr | -5.583 |
Feel | -5.505 |
Token | and |
Token ID | 290 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
hatt | +0.463 |
Beer | +0.445 |
coat | +0.403 |
andr | +0.403 |
ness | +0.401 |
Neg logit contributions | |
orem | -0.462 |
ril | -0.451 |
nerv | -0.431 |
riors | -0.420 |
wills | -0.417 |
Token | the |
Token ID | 262 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
orem | +0.304 |
ril | +0.297 |
nerv | +0.284 |
riors | +0.276 |
wills | +0.275 |
Neg logit contributions | |
hatt | -0.327 |
Beer | -0.315 |
coat | -0.287 |
andr | -0.287 |
ness | -0.285 |
Token | NFL |
Token ID | 5134 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
orem | +0.414 |
ril | +0.403 |
nerv | +0.384 |
riors | +0.372 |
wills | +0.370 |
Neg logit contributions | |
hatt | -0.521 |
Beer | -0.503 |
andr | -0.460 |
coat | -0.460 |
ness | -0.457 |
Token | PA |
Token ID | 4537 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
orem | +2.554 |
ril | +2.502 |
nerv | +2.409 |
riors | +2.380 |
wills | +2.354 |
Neg logit contributions | |
hatt | -2.543 |
Beer | -2.418 |
andr | -2.205 |
coat | -2.173 |
ness | -2.147 |
Token | by |
Token ID | 416 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
orem | +1.422 |
ril | +1.404 |
nerv | +1.342 |
riors | +1.305 |
wills | +1.296 |
Neg logit contributions | |
hatt | -1.499 |
Beer | -1.441 |
andr | -1.306 |
coat | -1.301 |
ness | -1.272 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
hatt | +0.807 |
Beer | +0.776 |
coat | +0.705 |
andr | +0.704 |
ness | +0.702 |
Neg logit contributions | |
orem | -0.792 |
ril | -0.774 |
nerv | -0.739 |
riors | -0.720 |
wills | -0.715 |
Token | majority |
Token ID | 3741 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
hatt | +0.159 |
Beer | +0.152 |
coat | +0.138 |
andr | +0.138 |
ness | +0.137 |
Neg logit contributions | |
orem | -0.165 |
ril | -0.162 |
nerv | -0.155 |
riors | -0.151 |
wills | -0.150 |
Token | of |
Token ID | 286 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
orem | +1.699 |
ril | +1.656 |
nerv | +1.578 |
riors | +1.528 |
wills | +1.523 |
Neg logit contributions | |
hatt | -2.102 |
Beer | -2.030 |
andr | -1.855 |
coat | -1.854 |
ness | -1.843 |
Token | feminist |
Token ID | 14314 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
orem | +0.537 |
ril | +0.524 |
nerv | +0.502 |
riors | +0.487 |
wills | +0.486 |
Neg logit contributions | |
hatt | -0.584 |
Beer | -0.564 |
andr | -0.512 |
coat | -0.512 |
ness | -0.508 |
Token | philosophers |
Token ID | 24858 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
orem | +2.736 |
ril | +2.689 |
nerv | +2.645 |
wills | +2.554 |
riors | +2.511 |
Neg logit contributions | |
hatt | -3.694 |
Beer | -3.592 |
coat | -3.267 |
andr | -3.261 |
ness | -3.151 |
Token | . |
Token ID | 13 |
Feature activation | +4.45e-03 |
Pos logit contributions | |
orem | +3.914 |
ril | +3.851 |
nerv | +3.824 |
wills | +3.609 |
riors | +3.605 |
Neg logit contributions | |
hatt | -4.104 |
Beer | -3.984 |
andr | -3.618 |
coat | -3.547 |
Feel | -3.444 |
Token | I |
Token ID | 314 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
hatt | +0.007 |
Beer | +0.006 |
coat | +0.006 |
andr | +0.006 |
ness | +0.006 |
Neg logit contributions | |
orem | -0.007 |
ril | -0.007 |
nerv | -0.007 |
riors | -0.006 |
wills | -0.006 |
Token | do |
Token ID | 466 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
orem | +0.116 |
ril | +0.114 |
nerv | +0.109 |
riors | +0.105 |
wills | +0.105 |
Neg logit contributions | |
hatt | -0.116 |
Beer | -0.112 |
andr | -0.101 |
coat | -0.101 |
ness | -0.099 |
Token | not |
Token ID | 407 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
orem | +0.448 |
ril | +0.441 |
nerv | +0.425 |
riors | +0.413 |
wills | +0.413 |
Neg logit contributions | |
hatt | -0.358 |
Beer | -0.344 |
andr | -0.306 |
coat | -0.305 |
ness | -0.299 |
Token | see |
Token ID | 766 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
orem | +0.056 |
ril | +0.054 |
nerv | +0.052 |
wills | +0.051 |
riors | +0.050 |
Neg logit contributions | |
hatt | -0.056 |
Beer | -0.054 |
andr | -0.049 |
coat | -0.049 |
ness | -0.048 |
Token | slider |
Token ID | 28982 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
orem | +1.191 |
ril | +1.164 |
nerv | +1.142 |
wills | +1.108 |
rior | +1.100 |
Neg logit contributions | |
hatt | -0.916 |
Beer | -0.871 |
andr | -0.783 |
coat | -0.768 |
ness | -0.737 |
Token | after |
Token ID | 706 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
hatt | +0.022 |
Beer | +0.021 |
andr | +0.019 |
coat | +0.019 |
ness | +0.018 |
Neg logit contributions | |
orem | -0.024 |
ril | -0.024 |
nerv | -0.023 |
riors | -0.023 |
wills | -0.022 |
Token | shifting |
Token ID | 15852 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
orem | +0.926 |
ril | +0.915 |
nerv | +0.883 |
wills | +0.847 |
riors | +0.844 |
Neg logit contributions | |
hatt | -0.962 |
Beer | -0.930 |
andr | -0.841 |
coat | -0.837 |
ness | -0.830 |
Token | to |
Token ID | 284 |
Feature activation | -6.77e-04 |
Pos logit contributions | |
hatt | +0.382 |
Beer | +0.368 |
andr | +0.330 |
coat | +0.329 |
ness | +0.326 |
Neg logit contributions | |
orem | -0.408 |
ril | -0.401 |
nerv | -0.385 |
wills | -0.374 |
riors | -0.373 |
Token | the |
Token ID | 262 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
orem | +0.001 |
ril | +0.001 |
nerv | +0.001 |
riors | +0.001 |
wills | +0.001 |
Neg logit contributions | |
hatt | -0.001 |
Beer | -0.001 |
coat | -0.001 |
andr | -0.001 |
ness | -0.001 |
Token | pen |
Token ID | 3112 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
orem | +0.104 |
ril | +0.101 |
nerv | +0.096 |
riors | +0.093 |
wills | +0.092 |
Neg logit contributions | |
hatt | -0.140 |
Beer | -0.136 |
andr | -0.125 |
coat | -0.125 |
ness | -0.124 |
Token | last |
Token ID | 938 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ril | +4.101 |
orem | +4.063 |
nerv | +3.897 |
riors | +3.777 |
rior | +3.771 |
Neg logit contributions | |
hatt | -4.071 |
Beer | -4.011 |
andr | -3.543 |
coat | -3.495 |
Feel | -3.432 |
Token | year |
Token ID | 614 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
orem | +0.217 |
ril | +0.213 |
nerv | +0.207 |
wills | +0.201 |
riors | +0.201 |
Neg logit contributions | |
hatt | -0.135 |
Beer | -0.128 |
andr | -0.112 |
coat | -0.112 |
ness | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
hatt | +0.478 |
Beer | +0.459 |
andr | +0.411 |
coat | +0.411 |
ness | +0.407 |
Neg logit contributions | |
orem | -0.560 |
ril | -0.550 |
nerv | -0.529 |
riors | -0.515 |
wills | -0.512 |
Token | am |
Token ID | 716 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
orem | +0.095 |
ril | +0.093 |
nerv | +0.090 |
wills | +0.087 |
riors | +0.087 |
Neg logit contributions | |
hatt | -0.076 |
Beer | -0.073 |
coat | -0.065 |
andr | -0.065 |
ness | -0.065 |
Token | assing |
Token ID | 19696 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
hatt | +0.145 |
Beer | +0.140 |
coat | +0.128 |
andr | +0.128 |
ness | +0.127 |
Neg logit contributions | |
orem | -0.126 |
ril | -0.123 |
nerv | -0.118 |
riors | -0.114 |
wills | -0.114 |
Token | ( |
Token ID | 357 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
orem | +0.488 |
ril | +0.477 |
nerv | +0.456 |
riors | +0.444 |
wills | +0.442 |
Neg logit contributions | |
hatt | -0.479 |
Beer | -0.461 |
coat | -0.417 |
andr | -0.417 |
ness | -0.415 |
Token | t |
Token ID | 83 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
hatt | +1.743 |
Beer | +1.673 |
coat | +1.509 |
andr | +1.505 |
ness | +1.500 |
Neg logit contributions | |
orem | -1.945 |
ril | -1.893 |
nerv | -1.831 |
wills | -1.785 |
riors | -1.783 |
Token | � |
Token ID | 447 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
hatt | +0.046 |
Beer | +0.044 |
coat | +0.040 |
andr | +0.040 |
ness | +0.040 |
Neg logit contributions | |
orem | -0.054 |
ril | -0.053 |
nerv | -0.051 |
riors | -0.049 |
wills | -0.049 |
Token | � |
Token ID | 247 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
orem | +0.323 |
ril | +0.315 |
nerv | +0.301 |
riors | +0.292 |
wills | +0.291 |
Neg logit contributions | |
hatt | -0.380 |
Beer | -0.366 |
coat | -0.335 |
andr | -0.334 |
ness | -0.333 |
Token | ) |
Token ID | 8 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
orem | +0.098 |
ril | +0.096 |
nerv | +0.093 |
riors | +0.091 |
wills | +0.090 |
Neg logit contributions | |
hatt | -0.078 |
Beer | -0.074 |
coat | -0.066 |
andr | -0.066 |
ness | -0.066 |
Token | exp |
Token ID | 1033 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
orem | +0.618 |
ril | +0.603 |
nerv | +0.577 |
riors | +0.560 |
wills | +0.558 |
Neg logit contributions | |
hatt | -0.659 |
Beer | -0.635 |
coat | -0.577 |
andr | -0.577 |
ness | -0.573 |
Token | ( |
Token ID | 7 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
orem | +3.911 |
ril | +3.827 |
nerv | +3.674 |
riors | +3.501 |
rior | +3.497 |
Neg logit contributions | |
hatt | -5.245 |
Beer | -5.049 |
coat | -4.621 |
andr | -4.609 |
Feel | -4.525 |
Token | -( |
Token ID | 30420 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
hatt | +1.450 |
Beer | +1.397 |
coat | +1.259 |
andr | +1.257 |
ness | +1.252 |
Neg logit contributions | |
orem | -1.581 |
ril | -1.542 |
nerv | -1.485 |
riors | -1.447 |
wills | -1.445 |
Token | t |
Token ID | 83 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
hatt | +1.347 |
Beer | +1.293 |
coat | +1.168 |
andr | +1.164 |
ness | +1.161 |
Neg logit contributions | |
orem | -1.483 |
ril | -1.441 |
nerv | -1.395 |
wills | -1.358 |
riors | -1.356 |
Token | - |
Token ID | 12 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
hatt | +0.222 |
Beer | +0.213 |
coat | +0.192 |
andr | +0.191 |
ness | +0.191 |
Neg logit contributions | |
orem | -0.246 |
ril | -0.240 |
nerv | -0.231 |
riors | -0.225 |
wills | -0.224 |
Token | t |
Token ID | 83 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
orem | +0.034 |
ril | +0.033 |
nerv | +0.031 |
riors | +0.031 |
wills | +0.030 |
Neg logit contributions | |
hatt | -0.034 |
Beer | -0.032 |
andr | -0.029 |
coat | -0.029 |
ness | -0.029 |