Token | the |
Token ID | 262 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
emis | +0.091 |
Turing | +0.086 |
tar | +0.075 |
aver | +0.073 |
Starg | +0.073 |
Neg logit contributions | |
hered | -0.064 |
Bucc | -0.060 |
Revel | -0.057 |
Poly | -0.057 |
Pri | -0.054 |
Token | State |
Token ID | 1812 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
emis | +3.132 |
Turing | +2.964 |
tar | +2.410 |
Turk | +2.397 |
Starg | +2.345 |
Neg logit contributions | |
hered | -4.372 |
Bucc | -4.070 |
Revel | -3.972 |
Pri | -3.897 |
Poly | -3.895 |
Token | : |
Token ID | 25 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
emis | +4.269 |
Turing | +4.262 |
aver | +3.475 |
tar | +3.449 |
Turk | +3.385 |
Neg logit contributions | |
hered | -4.633 |
Bucc | -4.337 |
Revel | -4.162 |
Pri | -4.065 |
brim | -4.043 |
Token | The |
Token ID | 383 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
emis | +4.057 |
Turing | +3.820 |
tar | +3.209 |
aver | +3.121 |
Turk | +3.110 |
Neg logit contributions | |
hered | -4.230 |
Bucc | -3.973 |
Revel | -3.845 |
Poly | -3.796 |
Pri | -3.709 |
Token | Life |
Token ID | 5155 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
emis | +8.166 |
Turing | +7.894 |
Starg | +6.638 |
tar | +6.442 |
Turk | +6.338 |
Neg logit contributions | |
hered | -9.214 |
brim | -8.430 |
Bucc | -8.290 |
NRS | -8.235 |
merce | -8.199 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
emis | +6.917 |
Turing | +6.485 |
tar | +5.383 |
Alf | +5.373 |
Turk | +5.307 |
Neg logit contributions | |
hered | -7.417 |
merce | -6.888 |
Revel | -6.818 |
Bucc | -6.702 |
NRS | -6.698 |
Token | Murray |
Token ID | 12164 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
Turing | +5.273 |
emis | +4.975 |
Turk | +3.562 |
Alf | +3.551 |
tar | +3.551 |
Neg logit contributions | |
hered | -14.540 |
brim | -13.465 |
merce | -13.182 |
Bucc | -13.144 |
Revel | -13.120 |
Token | N |
Token ID | 399 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
emis | +4.212 |
Turing | +3.936 |
Turk | +3.592 |
Starg | +3.565 |
Alf | +3.555 |
Neg logit contributions | |
hered | -5.085 |
brim | -4.855 |
merce | -4.833 |
Revel | -4.567 |
Bucc | -4.483 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
emis | +1.531 |
Turing | +1.450 |
tar | +1.244 |
Turk | +1.226 |
aver | +1.206 |
Neg logit contributions | |
hered | -1.161 |
Bucc | -1.097 |
Revel | -1.047 |
brim | -1.028 |
Poly | -1.021 |
Token | Roth |
Token ID | 16131 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
emis | +3.864 |
Turing | +3.779 |
Alf | +3.103 |
Turk | +3.081 |
Starg | +3.023 |
Neg logit contributions | |
hered | -5.757 |
merce | -5.254 |
brim | -5.209 |
Revel | -5.096 |
Bucc | -4.971 |
Token | bard |
Token ID | 23024 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
emis | +2.357 |
Turing | +2.233 |
tar | +1.989 |
Turk | +1.919 |
aver | +1.910 |
Neg logit contributions | |
hered | -1.351 |
Bucc | -1.270 |
Revel | -1.176 |
brim | -1.153 |
Poly | -1.117 |
Token | Anti |
Token ID | 12297 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
emis | +2.109 |
Turing | +2.004 |
tar | +1.698 |
Turk | +1.685 |
aver | +1.670 |
Neg logit contributions | |
hered | -2.120 |
Bucc | -1.995 |
Revel | -1.929 |
Poly | -1.878 |
Pri | -1.864 |
Token | - |
Token ID | 12 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
hered | +0.800 |
Bucc | +0.754 |
Revel | +0.726 |
Poly | +0.713 |
brim | +0.702 |
Neg logit contributions | |
emis | -0.829 |
Turing | -0.786 |
tar | -0.666 |
Turk | -0.651 |
aver | -0.647 |
Token | Author |
Token ID | 13838 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
hered | +1.617 |
Bucc | +1.464 |
Revel | +1.388 |
Poly | +1.372 |
Pri | +1.332 |
Neg logit contributions | |
emis | -3.272 |
Turing | -3.125 |
tar | -2.751 |
aver | -2.721 |
Starg | -2.716 |
Token | itarian |
Token ID | 8353 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
hered | +1.953 |
Bucc | +1.773 |
Revel | +1.680 |
Poly | +1.647 |
Pri | +1.579 |
Neg logit contributions | |
emis | -4.063 |
Turing | -3.883 |
tar | -3.441 |
aver | -3.381 |
Turk | -3.373 |
Token | Movement |
Token ID | 15477 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
emis | +0.700 |
Turing | +0.661 |
tar | +0.554 |
Turk | +0.545 |
aver | +0.542 |
Neg logit contributions | |
hered | -0.715 |
Bucc | -0.674 |
Revel | -0.648 |
Poly | -0.638 |
Pri | -0.628 |
Token | ( |
Token ID | 357 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
emis | +2.866 |
Turing | +2.729 |
tar | +2.342 |
Turk | +2.312 |
agents | +2.286 |
Neg logit contributions | |
hered | -2.483 |
Bucc | -2.337 |
Revel | -2.245 |
Poly | -2.181 |
Pri | -2.147 |
Token | AK |
Token ID | 10206 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
emis | +7.318 |
Turing | +6.643 |
tar | +5.692 |
agents | +5.496 |
Turk | +5.138 |
Neg logit contributions | |
hered | -11.032 |
Bucc | -10.662 |
Revel | -10.416 |
brim | -10.187 |
Poly | -9.958 |
Token | ) |
Token ID | 8 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
emis | +6.779 |
Turing | +6.424 |
tar | +5.615 |
Turk | +5.512 |
agents | +5.421 |
Neg logit contributions | |
hered | -5.784 |
Bucc | -5.475 |
Revel | -5.262 |
brim | -5.000 |
Poly | -4.981 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
emis | +2.115 |
Turing | +1.990 |
tar | +1.720 |
Turk | +1.683 |
agents | +1.676 |
Neg logit contributions | |
hered | -1.856 |
Bucc | -1.749 |
Revel | -1.682 |
Poly | -1.639 |
Pri | -1.607 |
Token | what |
Token ID | 644 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
emis | +0.171 |
Turing | +0.162 |
tar | +0.139 |
Turk | +0.137 |
aver | +0.136 |
Neg logit contributions | |
hered | -0.141 |
Bucc | -0.131 |
Revel | -0.127 |
Poly | -0.123 |
Pri | -0.121 |
Token | type |
Token ID | 2099 |
Feature activation | -6.91e-03 |
Pos logit contributions | |
emis | +2.354 |
Turing | +2.218 |
tar | +1.910 |
aver | +1.872 |
Turk | +1.865 |
Neg logit contributions | |
hered | -2.110 |
Bucc | -1.994 |
Revel | -1.948 |
Poly | -1.876 |
Pri | -1.848 |
Token | attendance |
Token ID | 14858 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
hered | +0.072 |
Bucc | +0.066 |
Revel | +0.064 |
Poly | +0.062 |
Pri | +0.062 |
Neg logit contributions | |
emis | -0.079 |
Turing | -0.076 |
tar | -0.064 |
Turk | -0.064 |
aver | -0.063 |
Token | of |
Token ID | 286 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
emis | +1.353 |
Turing | +1.298 |
tar | +1.103 |
Turk | +1.084 |
aver | +1.080 |
Neg logit contributions | |
hered | -1.211 |
Bucc | -1.130 |
Revel | -1.088 |
Poly | -1.073 |
Pri | -1.049 |
Token | the |
Token ID | 262 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
emis | +1.390 |
Turing | +1.343 |
tar | +1.136 |
Turk | +1.115 |
aver | +1.112 |
Neg logit contributions | |
hered | -1.249 |
Bucc | -1.141 |
Revel | -1.106 |
Pri | -1.083 |
Poly | -1.082 |
Token | AL |
Token ID | 8355 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
emis | +0.750 |
Turing | +0.725 |
tar | +0.611 |
Turk | +0.602 |
aver | +0.596 |
Neg logit contributions | |
hered | -0.716 |
Bucc | -0.660 |
Revel | -0.635 |
Pri | -0.625 |
Poly | -0.621 |
Token | BA |
Token ID | 4339 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
emis | +1.985 |
Turing | +1.901 |
tar | +1.640 |
Turk | +1.594 |
aver | +1.570 |
Neg logit contributions | |
hered | -1.647 |
Bucc | -1.504 |
Revel | -1.453 |
Poly | -1.417 |
brim | -1.399 |
Token | ( |
Token ID | 357 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
emis | +3.502 |
Turing | +3.415 |
tar | +2.946 |
Turk | +2.886 |
aver | +2.793 |
Neg logit contributions | |
hered | -3.202 |
Bucc | -2.995 |
Revel | -2.836 |
brim | -2.780 |
Poly | -2.753 |
Token | B |
Token ID | 33 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
emis | +8.837 |
Turing | +8.347 |
tar | +7.674 |
agents | +7.430 |
Turk | +7.102 |
Neg logit contributions | |
hered | -8.146 |
Bucc | -8.136 |
brim | -7.837 |
Revel | -7.727 |
Poly | -7.486 |
Token | ol |
Token ID | 349 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
emis | +1.872 |
Turing | +1.711 |
tar | +1.472 |
Turk | +1.401 |
agents | +1.392 |
Neg logit contributions | |
hered | -1.974 |
Bucc | -1.888 |
Revel | -1.850 |
Poly | -1.787 |
brim | -1.754 |
Token | iv |
Token ID | 452 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
hered | +0.605 |
Bucc | +0.540 |
Revel | +0.507 |
Poly | +0.496 |
Pri | +0.471 |
Neg logit contributions | |
emis | -1.541 |
Turing | -1.477 |
tar | -1.319 |
aver | -1.298 |
Turk | -1.295 |
Token | arian |
Token ID | 3699 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
hered | +0.165 |
Bucc | +0.151 |
Revel | +0.143 |
Poly | +0.138 |
brim | +0.135 |
Neg logit contributions | |
emis | -0.335 |
Turing | -0.320 |
tar | -0.286 |
Turk | -0.278 |
aver | -0.278 |
Token | Alternative |
Token ID | 27182 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
hered | +0.343 |
Bucc | +0.321 |
Revel | +0.310 |
Poly | +0.305 |
Pri | +0.300 |
Neg logit contributions | |
emis | -0.356 |
Turing | -0.339 |
tar | -0.287 |
Turk | -0.280 |
aver | -0.279 |
Token | wing |
Token ID | 5469 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
emis | +1.325 |
Turing | +1.262 |
tar | +1.119 |
Turk | +1.087 |
agents | +1.086 |
Neg logit contributions | |
hered | -0.774 |
Bucc | -0.715 |
Revel | -0.685 |
Poly | -0.669 |
brim | -0.645 |
Token | populist |
Token ID | 26815 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
emis | +0.547 |
Turing | +0.528 |
Turk | +0.441 |
tar | +0.440 |
aver | +0.431 |
Neg logit contributions | |
hered | -0.544 |
Bucc | -0.507 |
Revel | -0.490 |
Pri | -0.479 |
Poly | -0.477 |
Token | Alternative |
Token ID | 27182 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
hered | +1.480 |
Bucc | +1.404 |
Revel | +1.361 |
Poly | +1.340 |
Pri | +1.328 |
Neg logit contributions | |
emis | -1.021 |
Turing | -0.959 |
tar | -0.772 |
Turk | -0.760 |
aver | -0.752 |
Token | for |
Token ID | 329 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
emis | +1.253 |
Turing | +1.189 |
tar | +1.031 |
Turk | +1.022 |
aver | +1.001 |
Neg logit contributions | |
hered | -1.073 |
Bucc | -1.002 |
Revel | -0.939 |
Poly | -0.923 |
brim | -0.916 |
Token | Germany |
Token ID | 4486 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
hered | +0.695 |
Bucc | +0.648 |
Revel | +0.624 |
Poly | +0.614 |
Pri | +0.604 |
Neg logit contributions | |
emis | -0.646 |
Turing | -0.615 |
tar | -0.513 |
Turk | -0.513 |
aver | -0.503 |
Token | ( |
Token ID | 357 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
emis | +2.329 |
Turing | +2.217 |
Turk | +1.895 |
tar | +1.885 |
aver | +1.877 |
Neg logit contributions | |
hered | -2.215 |
Bucc | -2.080 |
Revel | -1.987 |
Poly | -1.951 |
Pri | -1.918 |
Token | Af |
Token ID | 17584 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
emis | +1.094 |
Turing | +0.576 |
Af | +0.270 |
tar | -0.001 |
agents | -0.337 |
Neg logit contributions | |
hered | -15.888 |
Bucc | -15.796 |
Revel | -15.702 |
Poly | -15.244 |
brim | -15.126 |
Token | D |
Token ID | 35 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
emis | +4.194 |
Turing | +3.928 |
tar | +3.631 |
Turk | +3.504 |
agents | +3.341 |
Neg logit contributions | |
Bucc | -4.983 |
hered | -4.667 |
Revel | -4.640 |
Poly | -4.480 |
brim | -4.475 |
Token | ) |
Token ID | 8 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
emis | +3.703 |
Turing | +3.529 |
tar | +3.073 |
Turk | +3.020 |
aver | +3.007 |
Neg logit contributions | |
hered | -2.926 |
Bucc | -2.759 |
Revel | -2.627 |
Poly | -2.580 |
Pri | -2.496 |
Token | party |
Token ID | 2151 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
hered | +0.669 |
Bucc | +0.625 |
Revel | +0.600 |
Poly | +0.592 |
Pri | +0.576 |
Neg logit contributions | |
emis | -0.813 |
Turing | -0.775 |
tar | -0.662 |
aver | -0.656 |
Turk | -0.653 |
Token | | |
Token ID | 930 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
emis | +1.518 |
Turing | +1.475 |
aver | +1.246 |
tar | +1.243 |
Turk | +1.240 |
Neg logit contributions | |
hered | -1.354 |
Bucc | -1.257 |
Revel | -1.205 |
Poly | -1.192 |
Pri | -1.173 |
Token | a |
Token ID | 257 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
emis | +1.247 |
Turing | +1.207 |
aver | +1.025 |
tar | +1.016 |
Turk | +1.005 |
Neg logit contributions | |
hered | -1.131 |
Bucc | -1.078 |
Revel | -1.038 |
Pri | -0.994 |
merce | -0.987 |
Token | few |
Token ID | 1178 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
emis | +2.363 |
Turing | +2.328 |
tar | +1.930 |
Turk | +1.913 |
aver | +1.904 |
Neg logit contributions | |
hered | -2.504 |
Bucc | -2.412 |
Revel | -2.347 |
BuyableInstoreAndOnline | -2.276 |
merce | -2.204 |
Token | minutes |
Token ID | 2431 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
emis | +3.109 |
Turing | +2.910 |
aver | +2.464 |
Starg | +2.438 |
Turk | +2.368 |
Neg logit contributions | |
hered | -3.131 |
Bucc | -2.997 |
Revel | -2.820 |
Poly | -2.758 |
brim | -2.750 |
Token | until |
Token ID | 1566 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
emis | +4.628 |
Turing | +4.336 |
aver | +3.707 |
tar | +3.662 |
Starg | +3.523 |
Neg logit contributions | |
hered | -5.446 |
Bucc | -5.440 |
Revel | -5.179 |
Pri | -5.057 |
Poly | -4.967 |
Token | fork |
Token ID | 15563 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
Turing | +5.711 |
emis | +5.646 |
hash | +4.588 |
Turk | +4.512 |
tar | +4.343 |
Neg logit contributions | |
hered | -9.975 |
BuyableInstoreAndOnline | -9.718 |
Bucc | -9.696 |
Revel | -9.555 |
merce | -9.387 |
Token | - |
Token ID | 12 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Turing | +4.967 |
emis | +4.907 |
tar | +4.208 |
aver | +3.998 |
Turk | +3.936 |
Neg logit contributions | |
Bucc | -6.469 |
hered | -6.422 |
Revel | -6.251 |
merce | -6.189 |
BuyableInstoreAndOnline | -6.057 |
Token | t |
Token ID | 83 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
emis | +6.772 |
Turing | +6.565 |
tar | +6.129 |
agents | +5.008 |
agent | +4.795 |
Neg logit contributions | |
Bucc | -10.746 |
Revel | -10.200 |
hered | -9.867 |
BuyableInstoreAndOnline | -9.794 |
Poly | -9.599 |
Token | ender |
Token ID | 2194 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
emis | +4.881 |
Turing | +4.517 |
tar | +3.955 |
Starg | +3.805 |
aver | +3.801 |
Neg logit contributions | |
Bucc | -3.579 |
hered | -3.435 |
Revel | -3.350 |
Poly | -3.220 |
Pri | -3.136 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
emis | +3.345 |
Turing | +3.270 |
tar | +2.813 |
Starg | +2.736 |
Turk | +2.705 |
Neg logit contributions | |
hered | -2.890 |
Bucc | -2.855 |
Revel | -2.728 |
merce | -2.685 |
brim | -2.681 |
Token | Chop |
Token ID | 40159 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
emis | +2.658 |
Turing | +2.619 |
tar | +2.156 |
Turk | +2.107 |
Starg | +2.034 |
Neg logit contributions | |
hered | -3.406 |
Bucc | -3.151 |
Revel | -3.097 |
brim | -3.048 |
merce | -3.011 |
Token | fl |
Token ID | 781 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
emis | +0.845 |
Turing | +0.812 |
tar | +0.677 |
aver | +0.670 |
Starg | +0.660 |
Neg logit contributions | |
hered | -0.904 |
Bucc | -0.858 |
Revel | -0.836 |
Poly | -0.810 |
Pri | -0.809 |
Token | - |
Token ID | 532 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
emis | +0.748 |
Turing | +0.710 |
tar | +0.609 |
Turk | +0.594 |
aver | +0.592 |
Neg logit contributions | |
hered | -0.673 |
Bucc | -0.620 |
Revel | -0.606 |
Poly | -0.589 |
Pri | -0.580 |
Token | Quick |
Token ID | 12029 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
emis | +0.757 |
Turing | +0.727 |
tar | +0.625 |
Turk | +0.617 |
Starg | +0.615 |
Neg logit contributions | |
hered | -0.547 |
Bucc | -0.504 |
Revel | -0.474 |
Poly | -0.469 |
brim | -0.460 |
Token | step |
Token ID | 9662 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
hered | +0.011 |
Bucc | +0.010 |
Revel | +0.010 |
Poly | +0.010 |
Pri | +0.010 |
Neg logit contributions | |
emis | -0.012 |
Turing | -0.011 |
tar | -0.010 |
aver | -0.009 |
Starg | -0.009 |
Token | ) |
Token ID | 8 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
emis | +1.679 |
Turing | +1.603 |
tar | +1.385 |
Turk | +1.363 |
aver | +1.355 |
Neg logit contributions | |
hered | -1.213 |
Bucc | -1.112 |
Revel | -1.072 |
Poly | -1.043 |
Pri | -1.023 |
Token | s |
Token ID | 264 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
emis | +4.367 |
Turing | +4.099 |
tar | +3.524 |
Turk | +3.459 |
aver | +3.449 |
Neg logit contributions | |
hered | -3.768 |
Bucc | -3.472 |
Revel | -3.318 |
Poly | -3.254 |
Pri | -3.194 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
emis | +2.688 |
Turing | +2.584 |
tar | +2.255 |
Starg | +2.190 |
Turk | +2.168 |
Neg logit contributions | |
hered | -2.283 |
Bucc | -2.239 |
Revel | -2.133 |
merce | -2.104 |
brim | -2.085 |
Token | t |
Token ID | 83 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
emis | +6.241 |
Turing | +6.134 |
tar | +5.836 |
agents | +4.674 |
agent | +4.510 |
Neg logit contributions | |
Bucc | -10.604 |
hered | -10.195 |
BuyableInstoreAndOnline | -10.041 |
merce | -10.040 |
Revel | -10.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
hered | +0.176 |
Bucc | +0.167 |
Revel | +0.159 |
Poly | +0.155 |
brim | +0.154 |
Neg logit contributions | |
emis | -0.241 |
Turing | -0.231 |
tar | -0.200 |
Starg | -0.196 |
Turk | -0.195 |
Token | A |
Token ID | 317 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
hered | +3.119 |
Bucc | +2.995 |
Poly | +2.877 |
Revel | +2.877 |
Pri | +2.706 |
Neg logit contributions | |
emis | -4.470 |
Turing | -4.156 |
tar | -3.639 |
agents | -3.585 |
aver | -3.573 |
Token | US |
Token ID | 2937 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
hered | +1.844 |
Bucc | +1.704 |
Revel | +1.637 |
Poly | +1.621 |
Pri | +1.577 |
Neg logit contributions | |
emis | -2.515 |
Turing | -2.386 |
tar | -2.061 |
aver | -2.029 |
Turk | -2.012 |
Token | 12 |
Token ID | 1105 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
hered | +0.921 |
Bucc | +0.862 |
Revel | +0.844 |
Poly | +0.843 |
Pri | +0.804 |
Neg logit contributions | |
emis | -1.026 |
Turing | -0.949 |
tar | -0.808 |
aver | -0.796 |
agents | -0.793 |
Token | Enemy |
Token ID | 21785 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
emis | +1.004 |
Turing | +0.909 |
tar | +0.679 |
aver | +0.651 |
Turk | +0.646 |
Neg logit contributions | |
hered | -2.123 |
Bucc | -2.030 |
Revel | -1.984 |
Poly | -1.967 |
Pri | -1.930 |
Token | of |
Token ID | 286 |
Feature activation | +9.23e-03 |
Pos logit contributions | |
emis | +4.248 |
Turing | +3.918 |
Turk | +3.348 |
Starg | +3.306 |
aver | +3.262 |
Neg logit contributions | |
hered | -4.186 |
Bucc | -3.839 |
brim | -3.808 |
merce | -3.724 |
Pri | -3.667 |
Token | the |
Token ID | 262 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
emis | +0.091 |
Turing | +0.086 |
tar | +0.075 |
aver | +0.073 |
Starg | +0.073 |
Neg logit contributions | |
hered | -0.064 |
Bucc | -0.060 |
Revel | -0.057 |
Poly | -0.057 |
Pri | -0.054 |
Token | State |
Token ID | 1812 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
emis | +3.132 |
Turing | +2.964 |
tar | +2.410 |
Turk | +2.397 |
Starg | +2.345 |
Neg logit contributions | |
hered | -4.372 |
Bucc | -4.070 |
Revel | -3.972 |
Pri | -3.897 |
Poly | -3.895 |
Token | : |
Token ID | 25 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
emis | +4.269 |
Turing | +4.262 |
aver | +3.475 |
tar | +3.449 |
Turk | +3.385 |
Neg logit contributions | |
hered | -4.633 |
Bucc | -4.337 |
Revel | -4.162 |
Pri | -4.065 |
brim | -4.043 |
Token | The |
Token ID | 383 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
emis | +4.057 |
Turing | +3.820 |
tar | +3.209 |
aver | +3.121 |
Turk | +3.110 |
Neg logit contributions | |
hered | -4.230 |
Bucc | -3.973 |
Revel | -3.845 |
Poly | -3.796 |
Pri | -3.709 |
Token | Life |
Token ID | 5155 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
emis | +8.166 |
Turing | +7.894 |
Starg | +6.638 |
tar | +6.442 |
Turk | +6.338 |
Neg logit contributions | |
hered | -9.214 |
brim | -8.430 |
Bucc | -8.290 |
NRS | -8.235 |
merce | -8.199 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
emis | +6.917 |
Turing | +6.485 |
tar | +5.383 |
Alf | +5.373 |
Turk | +5.307 |
Neg logit contributions | |
hered | -7.417 |
merce | -6.888 |
Revel | -6.818 |
Bucc | -6.702 |
NRS | -6.698 |
Token | Murray |
Token ID | 12164 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
Turing | +5.273 |
emis | +4.975 |
Turk | +3.562 |
Alf | +3.551 |
tar | +3.551 |
Neg logit contributions | |
hered | -14.540 |
brim | -13.465 |
merce | -13.182 |
Bucc | -13.144 |
Revel | -13.120 |
Token | N |
Token ID | 399 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
emis | +4.212 |
Turing | +3.936 |
Turk | +3.592 |
Starg | +3.565 |
Alf | +3.555 |
Neg logit contributions | |
hered | -5.085 |
brim | -4.855 |
merce | -4.833 |
Revel | -4.567 |
Bucc | -4.483 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
emis | +1.531 |
Turing | +1.450 |
tar | +1.244 |
Turk | +1.226 |
aver | +1.206 |
Neg logit contributions | |
hered | -1.161 |
Bucc | -1.097 |
Revel | -1.047 |
brim | -1.028 |
Poly | -1.021 |
Token | old |
Token ID | 1468 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
hered | +1.702 |
Bucc | +1.612 |
Revel | +1.565 |
Poly | +1.555 |
Pri | +1.514 |
Neg logit contributions | |
emis | -1.261 |
Turing | -1.169 |
tar | -0.953 |
aver | -0.921 |
Turk | -0.916 |
Token | address |
Token ID | 2209 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
emis | +0.047 |
Turing | +0.044 |
tar | +0.035 |
aver | +0.035 |
Starg | +0.034 |
Neg logit contributions | |
hered | -0.068 |
Bucc | -0.065 |
Revel | -0.063 |
Poly | -0.062 |
Pri | -0.061 |
Token | https |
Token ID | 3740 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
hered | +0.658 |
Bucc | +0.616 |
Revel | +0.593 |
Poly | +0.587 |
Pri | +0.568 |
Neg logit contributions | |
emis | -0.803 |
Turing | -0.757 |
tar | -0.650 |
aver | -0.637 |
Turk | -0.634 |
Token | :// |
Token ID | 1378 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
emis | +1.577 |
Turing | +1.509 |
tar | +1.297 |
Starg | +1.269 |
Turk | +1.254 |
Neg logit contributions | |
hered | -1.323 |
Bucc | -1.250 |
Revel | -1.201 |
Poly | -1.166 |
brim | -1.157 |
Token | . |
Token ID | 764 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
hered | +1.145 |
Bucc | +1.070 |
Revel | +1.031 |
Poly | +1.019 |
Pri | +0.989 |
Neg logit contributions | |
emis | -1.369 |
Turing | -1.293 |
tar | -1.108 |
aver | -1.083 |
Turk | -1.080 |
Token | nice |
Token ID | 44460 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
emis | +2.597 |
Turing | +2.429 |
tar | +1.998 |
aver | +1.898 |
Turk | +1.894 |
Neg logit contributions | |
hered | -3.752 |
Bucc | -3.591 |
Revel | -3.501 |
Poly | -3.382 |
Pri | -3.360 |
Token | hash |
Token ID | 17831 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
emis | +2.250 |
Turing | +1.801 |
tar | +1.036 |
hash | +0.915 |
agents | +0.335 |
Neg logit contributions | |
Bucc | -15.035 |
Revel | -14.590 |
hered | -14.374 |
BuyableInstoreAndOnline | -14.084 |
Poly | -14.076 |
Token | . |
Token ID | 13 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
emis | +1.142 |
Turing | +1.101 |
tar | +0.955 |
Starg | +0.931 |
Turk | +0.927 |
Neg logit contributions | |
hered | -0.893 |
Bucc | -0.848 |
Revel | -0.810 |
brim | -0.788 |
Poly | -0.778 |
Token | com |
Token ID | 785 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
hered | +3.400 |
Bucc | +3.063 |
Poly | +2.986 |
Revel | +2.949 |
Pri | +2.872 |
Neg logit contributions | |
emis | -4.698 |
Turing | -4.440 |
tar | -3.796 |
aver | -3.786 |
Turk | -3.773 |
Token | / |
Token ID | 14 |
Feature activation | +5.89e-04 |
Pos logit contributions | |
emis | +1.534 |
Turing | +1.470 |
tar | +1.257 |
Starg | +1.219 |
aver | +1.215 |
Neg logit contributions | |
hered | -1.449 |
Bucc | -1.358 |
Revel | -1.316 |
Poly | -1.268 |
brim | -1.266 |
Token | api |
Token ID | 15042 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
emis | +0.007 |
Turing | +0.006 |
tar | +0.006 |
aver | +0.006 |
Turk | +0.006 |
Neg logit contributions | |
hered | -0.003 |
Bucc | -0.003 |
Revel | -0.003 |
Poly | -0.003 |
Pri | -0.002 |
Token | Emmanuel |
Token ID | 32390 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
emis | +1.336 |
Turing | +1.252 |
tar | +1.015 |
aver | +1.003 |
agents | +0.993 |
Neg logit contributions | |
hered | -1.638 |
Bucc | -1.553 |
Revel | -1.493 |
Poly | -1.480 |
brim | -1.454 |
Token | College |
Token ID | 5535 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
hered | +3.134 |
Bucc | +2.945 |
Poly | +2.860 |
Revel | +2.825 |
Pri | +2.688 |
Neg logit contributions | |
emis | -4.889 |
Turing | -4.552 |
tar | -3.992 |
aver | -3.927 |
agents | -3.919 |
Token | in |
Token ID | 287 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
emis | +0.977 |
Turing | +0.946 |
tar | +0.814 |
Turk | +0.794 |
Starg | +0.793 |
Neg logit contributions | |
hered | -0.808 |
Bucc | -0.761 |
Revel | -0.734 |
brim | -0.711 |
merce | -0.705 |
Token | Boston |
Token ID | 6182 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
emis | +1.303 |
Turing | +1.216 |
tar | +1.001 |
aver | +0.973 |
Turk | +0.968 |
Neg logit contributions | |
hered | -1.615 |
Bucc | -1.528 |
Revel | -1.482 |
Poly | -1.466 |
Pri | -1.435 |
Token | ( |
Token ID | 357 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
emis | +2.267 |
Turing | +2.208 |
tar | +1.848 |
Turk | +1.825 |
Starg | +1.811 |
Neg logit contributions | |
hered | -2.516 |
Bucc | -2.318 |
Revel | -2.255 |
brim | -2.236 |
merce | -2.236 |
Token | pictured |
Token ID | 28852 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
emis | +4.647 |
Turing | +4.291 |
tar | +3.675 |
agents | +3.491 |
aver | +3.436 |
Neg logit contributions | |
hered | -5.101 |
Bucc | -4.884 |
Revel | -4.872 |
Poly | -4.707 |
brim | -4.647 |
Token | ), |
Token ID | 828 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
emis | +7.850 |
Turing | +7.558 |
tar | +6.457 |
Starg | +6.255 |
Turk | +6.159 |
Neg logit contributions | |
hered | -8.695 |
Revel | -8.451 |
merce | -8.432 |
BuyableInstoreAndOnline | -8.283 |
Bucc | -8.266 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
hered | +0.621 |
Bucc | +0.580 |
Revel | +0.557 |
Poly | +0.546 |
Pri | +0.534 |
Neg logit contributions | |
emis | -0.792 |
Turing | -0.755 |
tar | -0.649 |
Starg | -0.636 |
aver | -0.635 |
Token | Latin |
Token ID | 9133 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
emis | +0.329 |
Turing | +0.312 |
tar | +0.270 |
Turk | +0.264 |
aver | +0.264 |
Neg logit contributions | |
hered | -0.246 |
Bucc | -0.228 |
Revel | -0.219 |
Poly | -0.215 |
Pri | -0.210 |
Token | Academy |
Token ID | 8581 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
emis | +0.288 |
Turing | +0.275 |
tar | +0.235 |
Starg | +0.230 |
aver | +0.230 |
Neg logit contributions | |
hered | -0.226 |
Bucc | -0.209 |
Revel | -0.202 |
Poly | -0.198 |
brim | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
emis | +3.404 |
Turing | +3.348 |
tar | +2.824 |
Starg | +2.781 |
Turk | +2.741 |
Neg logit contributions | |
hered | -3.471 |
Bucc | -3.341 |
merce | -3.261 |
brim | -3.206 |
Revel | -3.184 |
Token | - |
Token ID | 532 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
hered | +0.762 |
Bucc | +0.716 |
Revel | +0.682 |
Poly | +0.680 |
Pri | +0.642 |
Neg logit contributions | |
emis | -1.171 |
Turing | -1.098 |
tar | -0.950 |
aver | -0.943 |
agents | -0.938 |
Token | Quick |
Token ID | 12029 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
hered | +0.885 |
Bucc | +0.815 |
Revel | +0.780 |
Poly | +0.767 |
Pri | +0.742 |
Neg logit contributions | |
emis | -1.382 |
Turing | -1.316 |
tar | -1.149 |
aver | -1.126 |
Turk | -1.124 |
Token | step |
Token ID | 9662 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
emis | +3.162 |
Turing | +2.962 |
tar | +2.605 |
agents | +2.451 |
Starg | +2.427 |
Neg logit contributions | |
hered | -3.264 |
Bucc | -3.217 |
Revel | -2.995 |
brim | -2.977 |
Poly | -2.952 |
Token | ) |
Token ID | 8 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
emis | +1.806 |
Turing | +1.747 |
tar | +1.511 |
Starg | +1.467 |
Turk | +1.466 |
Neg logit contributions | |
hered | -1.440 |
Bucc | -1.368 |
Revel | -1.309 |
brim | -1.282 |
Poly | -1.256 |
Token | s |
Token ID | 264 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
emis | +4.736 |
Turing | +4.451 |
tar | +3.816 |
Turk | +3.754 |
aver | +3.742 |
Neg logit contributions | |
hered | -4.073 |
Bucc | -3.765 |
Revel | -3.590 |
Poly | -3.531 |
Pri | -3.461 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
emis | +2.217 |
Turing | +2.128 |
tar | +1.854 |
Starg | +1.804 |
Turk | +1.788 |
Neg logit contributions | |
hered | -1.828 |
Bucc | -1.784 |
Revel | -1.698 |
merce | -1.658 |
brim | -1.655 |
Token | t |
Token ID | 83 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
emis | +6.161 |
Turing | +6.060 |
tar | +5.728 |
agents | +4.598 |
agent | +4.435 |
Neg logit contributions | |
Bucc | -10.393 |
hered | -10.027 |
merce | -9.825 |
BuyableInstoreAndOnline | -9.818 |
Revel | -9.814 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
emis | +0.210 |
Turing | +0.201 |
tar | +0.174 |
Starg | +0.170 |
Turk | +0.170 |
Neg logit contributions | |
hered | -0.156 |
Bucc | -0.147 |
Revel | -0.141 |
Poly | -0.137 |
brim | -0.137 |
Token | A |
Token ID | 317 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
hered | +2.460 |
Bucc | +2.321 |
Revel | +2.247 |
Poly | +2.227 |
Pri | +2.140 |
Neg logit contributions | |
emis | -2.784 |
Turing | -2.597 |
tar | -2.223 |
agents | -2.169 |
aver | -2.167 |
Token | US |
Token ID | 2937 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
hered | +1.863 |
Bucc | +1.719 |
Revel | +1.650 |
Poly | +1.636 |
Pri | +1.592 |
Neg logit contributions | |
emis | -2.560 |
Turing | -2.430 |
tar | -2.099 |
aver | -2.069 |
Turk | -2.050 |
Token | 16 |
Token ID | 1467 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
emis | +1.970 |
Turing | +1.855 |
tar | +1.572 |
aver | +1.534 |
Turk | +1.528 |
Neg logit contributions | |
hered | -1.874 |
Bucc | -1.758 |
Revel | -1.699 |
Poly | -1.679 |
Pri | -1.635 |
Token | where |
Token ID | 810 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
emis | +2.944 |
Turing | +2.829 |
tar | +2.472 |
aver | +2.445 |
Turk | +2.428 |
Neg logit contributions | |
hered | -1.755 |
Bucc | -1.646 |
Revel | -1.586 |
brim | -1.467 |
merce | -1.462 |
Token | some |
Token ID | 617 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
emis | +2.202 |
Turing | +2.113 |
tar | +1.740 |
Starg | +1.738 |
aver | +1.714 |
Neg logit contributions | |
hered | -2.523 |
Bucc | -2.397 |
Revel | -2.299 |
Poly | -2.215 |
brim | -2.205 |
Token | filming |
Token ID | 17691 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
emis | +5.351 |
Turing | +5.204 |
tar | +4.483 |
Starg | +4.407 |
aver | +4.332 |
Neg logit contributions | |
hered | -5.117 |
Bucc | -4.740 |
Revel | -4.657 |
brim | -4.527 |
BuyableInstoreAndOnline | -4.505 |
Token | took |
Token ID | 1718 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
emis | +1.672 |
Turing | +1.619 |
tar | +1.374 |
aver | +1.348 |
Turk | +1.326 |
Neg logit contributions | |
hered | -1.704 |
Bucc | -1.648 |
Revel | -1.593 |
merce | -1.553 |
BuyableInstoreAndOnline | -1.549 |
Token | place |
Token ID | 1295 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
emis | +0.826 |
Turing | +0.790 |
tar | +0.674 |
aver | +0.672 |
Starg | +0.664 |
Neg logit contributions | |
hered | -0.669 |
Bucc | -0.634 |
Revel | -0.610 |
Pri | -0.589 |
Poly | -0.580 |
Token | near |
Token ID | 1474 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
emis | +5.158 |
Turing | +4.940 |
aver | +4.178 |
tar | +4.145 |
Turk | +4.092 |
Neg logit contributions | |
hered | -4.950 |
Bucc | -4.871 |
Revel | -4.735 |
BuyableInstoreAndOnline | -4.605 |
merce | -4.600 |
Token | Alfred |
Token ID | 22044 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
emis | +5.798 |
Turing | +5.471 |
Alf | +4.370 |
agents | +4.178 |
tar | +3.987 |
Neg logit contributions | |
hered | -10.840 |
Bucc | -10.450 |
Revel | -10.101 |
Poly | -9.916 |
brim | -9.914 |
Token | Lerner |
Token ID | 49750 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
emis | +1.309 |
Turing | +1.244 |
tar | +1.037 |
Starg | +1.012 |
Turk | +1.008 |
Neg logit contributions | |
hered | -1.458 |
Bucc | -1.387 |
Revel | -1.337 |
Poly | -1.324 |
brim | -1.312 |
Token | Hall |
Token ID | 4789 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
emis | +0.954 |
Turing | +0.914 |
Starg | +0.744 |
tar | +0.742 |
Turk | +0.732 |
Neg logit contributions | |
hered | -1.114 |
Bucc | -1.070 |
Revel | -1.020 |
brim | -1.003 |
Poly | -0.999 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
emis | +2.199 |
Turing | +2.136 |
tar | +1.832 |
Starg | +1.799 |
Turk | +1.799 |
Neg logit contributions | |
hered | -1.804 |
Bucc | -1.715 |
Revel | -1.619 |
brim | -1.610 |
merce | -1.576 |
Token | Other |
Token ID | 3819 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
hered | +2.570 |
Bucc | +2.443 |
Revel | +2.370 |
Poly | +2.359 |
Pri | +2.294 |
Neg logit contributions | |
emis | -1.964 |
Turing | -1.818 |
tar | -1.490 |
aver | -1.446 |
Starg | -1.431 |
Token | - |
Token ID | 12 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
hered | +1.361 |
Bucc | +1.276 |
Revel | +1.232 |
Poly | +1.218 |
Pri | +1.184 |
Neg logit contributions | |
emis | -1.491 |
Turing | -1.405 |
tar | -1.197 |
aver | -1.168 |
Turk | -1.163 |
Token | DC |
Token ID | 9697 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
emis | +1.441 |
Turing | +1.366 |
tar | +1.177 |
Starg | +1.152 |
Turk | +1.148 |
Neg logit contributions | |
hered | -1.086 |
Bucc | -1.014 |
Revel | -0.979 |
Poly | -0.949 |
brim | -0.935 |
Token | M |
Token ID | 44 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
emis | +2.705 |
Turing | +2.536 |
Starg | +2.048 |
Turk | +2.042 |
Gadget | +2.034 |
Neg logit contributions | |
hered | -3.456 |
Bucc | -3.322 |
Revel | -3.150 |
Poly | -3.112 |
brim | -3.101 |
Token | ) |
Token ID | 8 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
emis | +0.827 |
Turing | +0.795 |
tar | +0.694 |
Starg | +0.681 |
Turk | +0.679 |
Neg logit contributions | |
hered | -0.533 |
Bucc | -0.493 |
Revel | -0.467 |
Poly | -0.451 |
Pri | -0.451 |
Token | s |
Token ID | 264 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
emis | +4.731 |
Turing | +4.441 |
tar | +3.822 |
aver | +3.748 |
Turk | +3.748 |
Neg logit contributions | |
hered | -4.093 |
Bucc | -3.767 |
Revel | -3.593 |
Poly | -3.532 |
Pri | -3.477 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
emis | +2.746 |
Turing | +2.637 |
tar | +2.305 |
Starg | +2.236 |
Turk | +2.213 |
Neg logit contributions | |
hered | -2.333 |
Bucc | -2.289 |
Revel | -2.179 |
merce | -2.150 |
brim | -2.132 |
Token | t |
Token ID | 83 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
emis | +6.157 |
Turing | +6.051 |
tar | +5.722 |
agents | +4.614 |
agent | +4.450 |
Neg logit contributions | |
Bucc | -10.240 |
hered | -9.926 |
merce | -9.706 |
BuyableInstoreAndOnline | -9.676 |
Revel | -9.644 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
hered | +0.308 |
Bucc | +0.290 |
Revel | +0.277 |
Poly | +0.270 |
brim | +0.268 |
Neg logit contributions | |
emis | -0.426 |
Turing | -0.408 |
tar | -0.353 |
Starg | -0.346 |
Turk | -0.345 |
Token | A |
Token ID | 317 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
hered | +3.038 |
Bucc | +2.901 |
Revel | +2.800 |
Poly | +2.780 |
Pri | +2.657 |
Neg logit contributions | |
emis | -3.370 |
Turing | -3.124 |
tar | -2.683 |
agents | -2.623 |
aver | -2.617 |
Token | US |
Token ID | 2937 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
hered | +1.845 |
Bucc | +1.706 |
Revel | +1.638 |
Poly | +1.621 |
Pri | +1.577 |
Neg logit contributions | |
emis | -2.509 |
Turing | -2.381 |
tar | -2.057 |
aver | -2.024 |
Turk | -2.008 |
Token | 14 |
Token ID | 1478 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
emis | +1.761 |
Turing | +1.630 |
tar | +1.369 |
aver | +1.338 |
Starg | +1.327 |
Neg logit contributions | |
hered | -1.883 |
Bucc | -1.774 |
Revel | -1.717 |
Poly | -1.717 |
Pri | -1.662 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
emis | +4.317 |
Turing | +4.214 |
tar | +3.584 |
Starg | +3.539 |
aver | +3.505 |
Neg logit contributions | |
hered | -3.755 |
Bucc | -3.653 |
Revel | -3.454 |
brim | -3.449 |
BuyableInstoreAndOnline | -3.442 |
Token | In |
Token ID | 554 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
hered | +1.016 |
Bucc | +0.953 |
Revel | +0.915 |
Poly | +0.913 |
Pri | +0.869 |
Neg logit contributions | |
emis | -1.409 |
Turing | -1.325 |
tar | -1.146 |
aver | -1.130 |
agents | -1.120 |
Token | this |
Token ID | 428 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
hered | +1.764 |
Bucc | +1.621 |
Revel | +1.545 |
Poly | +1.518 |
Pri | +1.465 |
Neg logit contributions | |
emis | -3.042 |
Turing | -2.900 |
tar | -2.546 |
aver | -2.499 |
Turk | -2.492 |
Token | post |
Token ID | 1281 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
hered | +0.604 |
Bucc | +0.565 |
Revel | +0.542 |
Poly | +0.525 |
brim | +0.522 |
Neg logit contributions | |
emis | -0.675 |
Turing | -0.647 |
tar | -0.550 |
aver | -0.541 |
Starg | -0.539 |
Token | I |
Token ID | 314 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
emis | +2.462 |
Turing | +2.385 |
tar | +2.005 |
aver | +1.956 |
Turk | +1.952 |
Neg logit contributions | |
hered | -2.548 |
Bucc | -2.442 |
Revel | -2.314 |
brim | -2.255 |
Pri | -2.251 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
emis | +2.815 |
Turing | +2.573 |
tar | +2.113 |
aver | +2.088 |
Starg | +1.997 |
Neg logit contributions | |
hered | -4.449 |
Bucc | -4.295 |
Revel | -4.187 |
Poly | -4.089 |
Pri | -4.050 |
Token | round |
Token ID | 2835 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
emis | +4.733 |
Turing | +4.285 |
tar | +3.302 |
aver | +3.242 |
Starg | +3.177 |
Neg logit contributions | |
hered | -11.966 |
BuyableInstoreAndOnline | -11.671 |
Bucc | -11.509 |
Revel | -11.126 |
Pri | -10.830 |
Token | up |
Token ID | 510 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
emis | +0.419 |
Turing | +0.392 |
tar | +0.328 |
aver | +0.322 |
Turk | +0.319 |
Neg logit contributions | |
hered | -0.498 |
Bucc | -0.475 |
Revel | -0.458 |
Poly | -0.447 |
Pri | -0.446 |
Token | some |
Token ID | 617 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
emis | +1.962 |
Turing | +1.876 |
tar | +1.577 |
aver | +1.548 |
Starg | +1.545 |
Neg logit contributions | |
hered | -2.177 |
Bucc | -2.081 |
Revel | -1.995 |
Pri | -1.933 |
brim | -1.933 |
Token | got |
Token ID | 1392 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
emis | +5.208 |
Turing | +5.114 |
tar | +4.341 |
aver | +4.321 |
Gadget | +4.228 |
Neg logit contributions | |
hered | -5.126 |
Bucc | -5.011 |
Revel | -4.901 |
merce | -4.676 |
Pri | -4.630 |
Token | cha |
Token ID | 11693 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
emis | +3.833 |
Turing | +3.387 |
tar | +2.937 |
aver | +2.768 |
agents | +2.748 |
Neg logit contributions | |
hered | -4.672 |
Bucc | -4.666 |
Revel | -4.518 |
brim | -4.323 |
Poly | -4.299 |
Token | the |
Token ID | 262 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
emis | +4.499 |
Turing | +4.327 |
Starg | +3.654 |
tar | +3.647 |
Turk | +3.619 |
Neg logit contributions | |
hered | -3.945 |
Bucc | -3.631 |
Revel | -3.530 |
brim | -3.452 |
Poly | -3.411 |
Token | American |
Token ID | 1605 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
emis | +4.455 |
Turing | +4.218 |
tar | +3.327 |
Starg | +3.326 |
Turk | +3.287 |
Neg logit contributions | |
hered | -6.150 |
Bucc | -5.789 |
Revel | -5.593 |
Poly | -5.536 |
brim | -5.511 |
Token | Right |
Token ID | 6498 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
emis | +5.293 |
Turing | +5.237 |
Starg | +4.099 |
Turk | +4.092 |
tar | +4.020 |
Neg logit contributions | |
hered | -7.306 |
Bucc | -7.240 |
brim | -7.218 |
Revel | -6.960 |
Poly | -6.850 |
Token | : |
Token ID | 25 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
emis | +4.036 |
Turing | +3.790 |
tar | +3.246 |
Starg | +3.168 |
aver | +3.168 |
Neg logit contributions | |
hered | -3.261 |
Bucc | -3.088 |
Revel | -2.932 |
Poly | -2.861 |
brim | -2.844 |
Token | The |
Token ID | 383 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
emis | +4.927 |
Turing | +4.662 |
tar | +3.883 |
Starg | +3.767 |
aver | +3.754 |
Neg logit contributions | |
hered | -5.344 |
Bucc | -5.029 |
Revel | -4.830 |
Poly | -4.769 |
brim | -4.756 |
Token | Lost |
Token ID | 9164 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
emis | +7.179 |
Turing | +6.701 |
tar | +5.383 |
Starg | +5.350 |
Turk | +5.152 |
Neg logit contributions | |
hered | -8.999 |
Bucc | -8.440 |
brim | -8.313 |
Revel | -8.010 |
Pri | -7.971 |
Token | Legacy |
Token ID | 14843 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
emis | +7.044 |
Turing | +6.869 |
Starg | +5.353 |
Turk | +5.220 |
tar | +5.201 |
Neg logit contributions | |
hered | -10.194 |
Bucc | -9.502 |
brim | -9.365 |
PB | -9.137 |
merce | -9.039 |
Token | of |
Token ID | 286 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
emis | +2.719 |
Turing | +2.583 |
tar | +2.219 |
aver | +2.155 |
Turk | +2.150 |
Neg logit contributions | |
hered | -2.123 |
Bucc | -1.989 |
Revel | -1.901 |
Poly | -1.849 |
brim | -1.841 |
Token | the |
Token ID | 262 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
emis | +5.078 |
Turing | +4.811 |
tar | +4.157 |
aver | +4.069 |
Turk | +4.057 |
Neg logit contributions | |
hered | -3.817 |
Bucc | -3.550 |
Revel | -3.413 |
Poly | -3.366 |
Pri | -3.264 |
Token | Conservative |
Token ID | 11132 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
emis | +3.714 |
Turing | +3.482 |
tar | +2.845 |
aver | +2.776 |
Turk | +2.775 |
Neg logit contributions | |
hered | -4.568 |
Bucc | -4.322 |
Revel | -4.188 |
Poly | -4.149 |
brim | -4.096 |
Token | Movement |
Token ID | 15477 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
emis | +1.522 |
Turing | +1.436 |
tar | +1.218 |
aver | +1.194 |
Turk | +1.181 |
Neg logit contributions | |
hered | -1.445 |
Bucc | -1.356 |
Revel | -1.311 |
Poly | -1.298 |
Pri | -1.262 |
Token | Action |
Token ID | 7561 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
emis | +0.372 |
Turing | +0.348 |
tar | +0.280 |
Turk | +0.271 |
aver | +0.271 |
Neg logit contributions | |
hered | -0.543 |
Bucc | -0.516 |
Revel | -0.491 |
Poly | -0.488 |
brim | -0.487 |
Token | for |
Token ID | 329 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
emis | +0.491 |
Turing | +0.473 |
tar | +0.403 |
Turk | +0.398 |
aver | +0.392 |
Neg logit contributions | |
hered | -0.428 |
Bucc | -0.401 |
Revel | -0.378 |
brim | -0.374 |
Pri | -0.370 |
Token | Childhood |
Token ID | 40992 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
emis | +4.113 |
Turing | +3.985 |
tar | +3.385 |
agents | +3.355 |
Turk | +3.323 |
Neg logit contributions | |
hered | -3.808 |
Bucc | -3.625 |
brim | -3.437 |
merce | -3.431 |
Revel | -3.298 |
Token | Arri |
Token ID | 27350 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
emis | +1.702 |
Turing | +1.637 |
tar | +1.403 |
aver | +1.378 |
Turk | +1.345 |
Neg logit contributions | |
hered | -1.669 |
Bucc | -1.539 |
brim | -1.493 |
Revel | -1.451 |
merce | -1.441 |
Token | vals |
Token ID | 12786 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
emis | +0.506 |
Turing | +0.456 |
tar | +0.340 |
aver | +0.319 |
Turk | +0.314 |
Neg logit contributions | |
hered | -1.145 |
Bucc | -1.101 |
Revel | -1.075 |
Poly | -1.062 |
brim | -1.052 |
Token | ( |
Token ID | 357 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
emis | +5.664 |
Turing | +5.489 |
aver | +4.769 |
tar | +4.689 |
Turk | +4.601 |
Neg logit contributions | |
hered | -5.144 |
Bucc | -4.801 |
Revel | -4.527 |
Poly | -4.404 |
Pri | -4.370 |
Token | D |
Token ID | 35 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
emis | +6.802 |
Turing | +6.588 |
tar | +6.137 |
aver | +5.488 |
Alf | +5.480 |
Neg logit contributions | |
hered | -9.158 |
Bucc | -9.080 |
brim | -8.967 |
Revel | -8.524 |
BuyableInstoreAndOnline | -8.345 |
Token | ACA |
Token ID | 26576 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
emis | +5.871 |
Turing | +5.207 |
tar | +4.730 |
aver | +4.384 |
uphem | +4.238 |
Neg logit contributions | |
Bucc | -6.998 |
hered | -6.993 |
Revel | -6.752 |
Poly | -6.576 |
merce | -6.418 |
Token | ) |
Token ID | 8 |
Feature activation | +9.11e-03 |
Pos logit contributions | |
emis | +4.313 |
Turing | +4.122 |
tar | +3.572 |
aver | +3.512 |
Turk | +3.469 |
Neg logit contributions | |
hered | -3.261 |
Bucc | -3.054 |
Revel | -2.905 |
Poly | -2.853 |
Pri | -2.809 |
Token | program |
Token ID | 1430 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
emis | +0.092 |
Turing | +0.087 |
tar | +0.077 |
aver | +0.076 |
Turk | +0.075 |
Neg logit contributions | |
hered | -0.061 |
Bucc | -0.057 |
Revel | -0.053 |
Poly | -0.052 |
Pri | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
emis | +2.318 |
Turing | +2.245 |
aver | +1.933 |
tar | +1.912 |
Turk | +1.887 |
Neg logit contributions | |
hered | -1.878 |
Bucc | -1.789 |
Revel | -1.691 |
Poly | -1.676 |
Pri | -1.643 |
Token | Mond |
Token ID | 27328 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
hered | +1.397 |
Bucc | +1.322 |
Revel | +1.307 |
Poly | +1.301 |
Pri | +1.261 |
Neg logit contributions | |
emis | -1.506 |
Turing | -1.407 |
tar | -1.232 |
aver | -1.180 |
uphem | -1.158 |
Token | ial |
Token ID | 498 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
hered | +2.187 |
Bucc | +1.999 |
Revel | +1.935 |
Poly | +1.900 |
Pri | +1.838 |
Neg logit contributions | |
emis | -3.565 |
Turing | -3.422 |
tar | -2.997 |
aver | -2.948 |
Starg | -2.932 |
Token | e |
Token ID | 68 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
emis | +1.783 |
Turing | +1.703 |
Turk | +1.444 |
tar | +1.435 |
Starg | +1.427 |
Neg logit contributions | |
hered | -1.545 |
Bucc | -1.403 |
Revel | -1.334 |
merce | -1.305 |
Poly | -1.295 |
Token | ) |
Token ID | 8 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
hered | +0.900 |
Bucc | +0.834 |
Revel | +0.799 |
Poly | +0.790 |
Pri | +0.762 |
Neg logit contributions | |
emis | -1.340 |
Turing | -1.271 |
tar | -1.108 |
aver | -1.084 |
Starg | -1.081 |
Token | s |
Token ID | 264 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
emis | +4.543 |
Turing | +4.268 |
tar | +3.673 |
Turk | +3.619 |
aver | +3.603 |
Neg logit contributions | |
hered | -3.961 |
Bucc | -3.643 |
Revel | -3.479 |
Poly | -3.408 |
Pri | -3.358 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
emis | +3.343 |
Turing | +3.220 |
tar | +2.811 |
Starg | +2.727 |
Turk | +2.700 |
Neg logit contributions | |
hered | -2.937 |
Bucc | -2.901 |
Revel | -2.761 |
merce | -2.760 |
brim | -2.716 |
Token | t |
Token ID | 83 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
emis | +6.098 |
Turing | +5.992 |
tar | +5.673 |
agents | +4.578 |
agent | +4.411 |
Neg logit contributions | |
Bucc | -10.134 |
hered | -9.820 |
merce | -9.593 |
BuyableInstoreAndOnline | -9.550 |
Revel | -9.546 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
hered | +0.319 |
Bucc | +0.301 |
Revel | +0.287 |
Poly | +0.280 |
brim | +0.278 |
Neg logit contributions | |
emis | -0.440 |
Turing | -0.421 |
tar | -0.364 |
Starg | -0.357 |
Turk | -0.356 |
Token | A |
Token ID | 317 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
hered | +3.337 |
Bucc | +3.173 |
Revel | +3.066 |
Poly | +3.042 |
Pri | +2.902 |
Neg logit contributions | |
emis | -4.235 |
Turing | -3.930 |
tar | -3.407 |
aver | -3.336 |
agents | -3.334 |
Token | US |
Token ID | 2937 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
hered | +1.651 |
Bucc | +1.534 |
Revel | +1.474 |
Poly | +1.455 |
Pri | +1.413 |
Neg logit contributions | |
emis | -2.205 |
Turing | -2.091 |
tar | -1.806 |
aver | -1.771 |
Turk | -1.762 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
hered | +1.433 |
Bucc | +1.323 |
Poly | +1.309 |
Revel | +1.285 |
Pri | +1.227 |
Neg logit contributions | |
emis | -2.365 |
Turing | -2.215 |
tar | -1.926 |
agents | -1.911 |
Starg | -1.905 |
Token | - |
Token ID | 532 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
hered | +1.027 |
Bucc | +0.954 |
Revel | +0.916 |
Poly | +0.903 |
Pri | +0.876 |
Neg logit contributions | |
emis | -1.414 |
Turing | -1.342 |
tar | -1.163 |
aver | -1.138 |
Turk | -1.135 |
Token | Quick |
Token ID | 12029 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
hered | +0.864 |
Bucc | +0.791 |
Revel | +0.752 |
Poly | +0.740 |
brim | +0.729 |
Neg logit contributions | |
emis | -1.271 |
Turing | -1.221 |
tar | -1.058 |
Starg | -1.042 |
Turk | -1.041 |
Token | step |
Token ID | 9662 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
emis | +3.398 |
Turing | +3.162 |
tar | +2.815 |
agents | +2.619 |
Starg | +2.582 |
Neg logit contributions | |
Bucc | -3.571 |
hered | -3.543 |
Revel | -3.309 |
Poly | -3.277 |
brim | -3.272 |
Token | ) |
Token ID | 8 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
emis | +2.043 |
Turing | +1.978 |
tar | +1.713 |
Starg | +1.660 |
Turk | +1.658 |
Neg logit contributions | |
hered | -1.663 |
Bucc | -1.589 |
Revel | -1.518 |
brim | -1.492 |
merce | -1.470 |
Token | s |
Token ID | 264 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
emis | +4.656 |
Turing | +4.366 |
tar | +3.733 |
Turk | +3.678 |
aver | +3.676 |
Neg logit contributions | |
hered | -4.040 |
Bucc | -3.731 |
Revel | -3.539 |
Poly | -3.492 |
Pri | -3.439 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
emis | +2.340 |
Turing | +2.248 |
tar | +1.955 |
Starg | +1.905 |
Turk | +1.885 |
Neg logit contributions | |
hered | -1.950 |
Bucc | -1.909 |
Revel | -1.814 |
merce | -1.781 |
brim | -1.773 |
Token | t |
Token ID | 83 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
emis | +6.068 |
Turing | +5.998 |
tar | +5.633 |
agents | +4.531 |
Starg | +4.394 |
Neg logit contributions | |
Bucc | -10.173 |
hered | -9.802 |
merce | -9.634 |
BuyableInstoreAndOnline | -9.593 |
Revel | -9.593 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
hered | +0.171 |
Bucc | +0.162 |
Revel | +0.154 |
Poly | +0.150 |
brim | +0.149 |
Neg logit contributions | |
emis | -0.233 |
Turing | -0.223 |
tar | -0.193 |
Starg | -0.189 |
Turk | -0.189 |
Token | BEL |
Token ID | 29991 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
hered | +3.150 |
Bucc | +2.955 |
Revel | +2.861 |
Poly | +2.818 |
Pri | +2.688 |
Neg logit contributions | |
emis | -4.456 |
Turing | -4.172 |
tar | -3.640 |
agents | -3.563 |
aver | -3.554 |
Token | 22 |
Token ID | 2534 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
hered | +3.064 |
Bucc | +2.756 |
Poly | +2.747 |
Revel | +2.739 |
brim | +2.606 |
Neg logit contributions | |
emis | -5.328 |
Turing | -4.965 |
tar | -4.361 |
agents | -4.337 |
Starg | -4.271 |
Token | Krist |
Token ID | 14912 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
emis | +2.745 |
Turing | +2.644 |
tar | +2.215 |
Turk | +2.209 |
Starg | +2.187 |
Neg logit contributions | |
hered | -2.694 |
Bucc | -2.468 |
Revel | -2.375 |
brim | -2.358 |
Poly | -2.322 |
Token | u |
Token ID | 84 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
hered | +1.065 |
Bucc | +1.000 |
Revel | +0.966 |
Poly | +0.950 |
brim | +0.923 |
Neg logit contributions | |
emis | -1.186 |
Turing | -1.116 |
tar | -0.957 |
aver | -0.930 |
Turk | -0.927 |
Token | — |
Token ID | 851 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
emis | +4.948 |
Turing | +4.635 |
tar | +4.069 |
Turk | +3.931 |
Starg | +3.895 |
Neg logit contributions | |
hered | -4.533 |
Bucc | -4.237 |
Revel | -4.110 |
brim | -3.929 |
Poly | -3.922 |
Token | Dan |
Token ID | 6035 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
emis | +0.473 |
Turing | +0.448 |
tar | +0.378 |
Turk | +0.372 |
Starg | +0.371 |
Neg logit contributions | |
hered | -0.455 |
Bucc | -0.423 |
Revel | -0.408 |
Poly | -0.401 |
Pri | -0.395 |
Token | Mer |
Token ID | 4638 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
emis | +0.094 |
Turing | +0.084 |
tar | +0.057 |
Starg | +0.054 |
Turk | +0.054 |
Neg logit contributions | |
hered | -0.262 |
Bucc | -0.251 |
Revel | -0.245 |
Poly | -0.243 |
brim | -0.240 |
Token | ica |
Token ID | 3970 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
hered | +1.102 |
Bucc | +1.025 |
Revel | +0.984 |
Poly | +0.967 |
Pri | +0.937 |
Neg logit contributions | |
emis | -1.535 |
Turing | -1.454 |
tar | -1.261 |
aver | -1.233 |
Starg | -1.230 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
emis | +3.434 |
Turing | +3.376 |
Turk | +2.809 |
tar | +2.796 |
Starg | +2.794 |
Neg logit contributions | |
hered | -3.759 |
Bucc | -3.571 |
merce | -3.546 |
brim | -3.483 |
Revel | -3.436 |
Token | dan |
Token ID | 25604 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
emis | +6.187 |
Turing | +5.282 |
tar | +5.109 |
agents | +4.614 |
agent | +4.367 |
Neg logit contributions | |
Bucc | -10.460 |
Revel | -9.977 |
hered | -9.963 |
Poly | -9.807 |
brim | -9.788 |
Token | meric |
Token ID | 946 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
emis | +2.204 |
Turing | +1.595 |
tar | +1.086 |
agents | +0.991 |
uphem | +0.896 |
Neg logit contributions | |
Bucc | -7.549 |
hered | -7.471 |
Revel | -7.447 |
brim | -7.238 |
Poly | -7.205 |
Token | a |
Token ID | 64 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
emis | +1.798 |
Turing | +1.695 |
tar | +1.511 |
agents | +1.446 |
aver | +1.443 |
Neg logit contributions | |
hered | -1.253 |
Bucc | -1.206 |
Revel | -1.163 |
brim | -1.125 |
Poly | -1.109 |
Token | CNN |
Token ID | 18474 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
emis | +0.779 |
Turing | +0.744 |
tar | +0.658 |
agents | +0.643 |
Starg | +0.643 |
Neg logit contributions | |
hered | -0.467 |
Bucc | -0.435 |
Revel | -0.415 |
Poly | -0.409 |
brim | -0.406 |
Token | ) |
Token ID | 8 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
emis | +2.355 |
Turing | +2.287 |
tar | +1.980 |
Turk | +1.919 |
Starg | +1.915 |
Neg logit contributions | |
hered | -1.966 |
Bucc | -1.914 |
Revel | -1.840 |
brim | -1.791 |
merce | -1.763 |
Token | On |
Token ID | 2202 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
emis | +4.137 |
Turing | +4.020 |
tar | +3.369 |
Starg | +3.130 |
Turk | +3.092 |
Neg logit contributions | |
hered | -5.768 |
Bucc | -5.540 |
Revel | -5.418 |
Poly | -5.308 |
brim | -5.259 |
Token | September |
Token ID | 2693 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
emis | +5.154 |
Turing | +5.067 |
Starg | +4.379 |
tar | +4.248 |
aver | +4.193 |
Neg logit contributions | |
Bucc | -4.595 |
hered | -4.595 |
Revel | -4.328 |
merce | -4.269 |
NRS | -4.163 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
emis | +1.276 |
Turing | +1.221 |
tar | +1.020 |
Turk | +1.003 |
Starg | +0.996 |
Neg logit contributions | |
hered | -1.309 |
Bucc | -1.235 |
Revel | -1.189 |
Poly | -1.162 |
brim | -1.156 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
hered | +1.140 |
Bucc | +1.068 |
Revel | +1.021 |
Poly | +1.005 |
brim | +0.980 |
Neg logit contributions | |
emis | -1.494 |
Turing | -1.424 |
tar | -1.228 |
Turk | -1.202 |
Starg | -1.201 |
Token | 07 |
Token ID | 8753 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Turing | +4.797 |
emis | +4.690 |
Turk | +3.898 |
tar | +3.759 |
Gadget | +3.731 |
Neg logit contributions | |
hered | -7.026 |
merce | -6.622 |
Bucc | -6.606 |
brim | -6.357 |
Revel | -6.343 |
Token | : |
Token ID | 25 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
emis | +3.329 |
Turing | +3.236 |
tar | +2.754 |
Starg | +2.704 |
Turk | +2.658 |
Neg logit contributions | |
hered | -3.207 |
Bucc | -3.197 |
merce | -3.039 |
Revel | -3.035 |
brim | -3.027 |
Token | 44 |
Token ID | 2598 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
emis | +6.758 |
Turing | +6.529 |
tar | +5.792 |
Starg | +5.182 |
Turk | +5.031 |
Neg logit contributions | |
hered | -9.114 |
merce | -8.922 |
brim | -8.872 |
Revel | -8.768 |
Bucc | -8.760 |
Token | Se |
Token ID | 1001 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
emis | +3.848 |
Turing | +3.765 |
Starg | +3.293 |
tar | +3.193 |
Turk | +3.183 |
Neg logit contributions | |
hered | -2.342 |
Bucc | -2.097 |
Revel | -1.954 |
Poly | -1.941 |
Pri | -1.918 |
Token | eker |
Token ID | 28233 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
hered | +0.315 |
Bucc | +0.309 |
Poly | +0.296 |
Revel | +0.294 |
brim | +0.286 |
Neg logit contributions | |
emis | -0.268 |
Turing | -0.248 |
tar | -0.209 |
Starg | -0.203 |
agents | -0.199 |
Token | wrote |
Token ID | 2630 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
emis | +3.582 |
Turing | +3.423 |
tar | +3.014 |
aver | +2.981 |
Starg | +2.945 |
Neg logit contributions | |
hered | -2.737 |
Bucc | -2.641 |
Revel | -2.559 |
Poly | -2.452 |
merce | -2.432 |
Token | : |
Token ID | 25 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
Turing | +6.433 |
emis | +6.354 |
Starg | +5.354 |
tar | +5.336 |
Turk | +5.008 |
Neg logit contributions | |
merce | -8.383 |
Bucc | -8.351 |
BuyableInstoreAndOnline | -8.275 |
hered | -8.030 |
brim | -8.005 |
Token | ank |
Token ID | 962 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
hered | +0.733 |
Bucc | +0.687 |
Revel | +0.655 |
Poly | +0.637 |
brim | +0.621 |
Neg logit contributions | |
emis | -1.161 |
Turing | -1.103 |
tar | -0.970 |
Starg | -0.945 |
Turk | -0.942 |
Token | Cycling |
Token ID | 25550 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
hered | +2.603 |
Bucc | +2.481 |
Revel | +2.412 |
Poly | +2.393 |
Pri | +2.336 |
Neg logit contributions | |
emis | -1.799 |
Turing | -1.658 |
tar | -1.335 |
aver | -1.294 |
Starg | -1.284 |
Token | Team |
Token ID | 4816 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
emis | +0.452 |
Turing | +0.429 |
tar | +0.348 |
Turk | +0.341 |
Starg | +0.338 |
Neg logit contributions | |
hered | -0.622 |
Bucc | -0.587 |
Revel | -0.570 |
Poly | -0.558 |
brim | -0.555 |
Token | ) |
Token ID | 8 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
hered | +0.527 |
Bucc | +0.493 |
Revel | +0.471 |
Poly | +0.460 |
brim | +0.450 |
Neg logit contributions | |
emis | -0.751 |
Turing | -0.716 |
tar | -0.623 |
Turk | -0.608 |
Starg | -0.607 |
Token | s |
Token ID | 264 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
emis | +4.380 |
Turing | +4.117 |
tar | +3.532 |
aver | +3.472 |
Turk | +3.469 |
Neg logit contributions | |
hered | -3.745 |
Bucc | -3.457 |
Revel | -3.301 |
Poly | -3.246 |
Pri | -3.186 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
emis | +2.691 |
Turing | +2.587 |
tar | +2.257 |
Starg | +2.195 |
Turk | +2.168 |
Neg logit contributions | |
hered | -2.280 |
Bucc | -2.236 |
Revel | -2.127 |
merce | -2.100 |
brim | -2.081 |
Token | t |
Token ID | 83 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
emis | +6.049 |
Turing | +5.924 |
tar | +5.571 |
agents | +4.550 |
agent | +4.378 |
Neg logit contributions | |
Bucc | -9.965 |
hered | -9.631 |
merce | -9.419 |
Revel | -9.392 |
BuyableInstoreAndOnline | -9.390 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
hered | +0.580 |
Bucc | +0.545 |
Revel | +0.520 |
Poly | +0.509 |
brim | +0.501 |
Neg logit contributions | |
emis | -0.816 |
Turing | -0.779 |
tar | -0.675 |
Starg | -0.661 |
Turk | -0.660 |
Token | F |
Token ID | 376 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
hered | +2.977 |
Bucc | +2.860 |
Revel | +2.752 |
Poly | +2.751 |
Pri | +2.584 |
Neg logit contributions | |
emis | -4.351 |
Turing | -4.042 |
tar | -3.548 |
agents | -3.496 |
aver | -3.483 |
Token | RA |
Token ID | 3861 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
hered | +1.117 |
Bucc | +1.040 |
Revel | +1.000 |
Poly | +0.985 |
Pri | +0.955 |
Neg logit contributions | |
emis | -1.476 |
Turing | -1.397 |
tar | -1.208 |
aver | -1.181 |
Turk | -1.178 |
Token | 13 |
Token ID | 1511 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
emis | +1.701 |
Turing | +1.602 |
tar | +1.354 |
aver | +1.325 |
Turk | +1.316 |
Neg logit contributions | |
hered | -1.631 |
Bucc | -1.527 |
Revel | -1.479 |
Poly | -1.464 |
Pri | -1.424 |
Token | 16 |
Token ID | 1467 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
hered | +3.342 |
Bucc | +3.110 |
Revel | +3.028 |
Poly | +3.011 |
brim | +2.886 |
Neg logit contributions | |
emis | -3.919 |
Turing | -3.676 |
tar | -3.143 |
agents | -3.074 |
Starg | -3.070 |
Token | 17 |
Token ID | 1596 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
hered | +5.323 |
Bucc | +4.892 |
Poly | +4.837 |
Revel | +4.832 |
brim | +4.570 |
Neg logit contributions | |
emis | -5.473 |
Turing | -5.211 |
tar | -4.397 |
Turk | -4.299 |
Starg | -4.273 |
Token | 18 |
Token ID | 1248 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
hered | +2.444 |
Bucc | +2.296 |
Revel | +2.221 |
Poly | +2.215 |
Pri | +2.137 |
Neg logit contributions | |
emis | -2.545 |
Turing | -2.374 |
tar | -2.026 |
Starg | -1.995 |
Turk | -1.993 |
Token | 19 |
Token ID | 678 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
hered | +3.172 |
Bucc | +2.964 |
Poly | +2.876 |
Revel | +2.868 |
brim | +2.754 |
Neg logit contributions | |
emis | -4.046 |
Turing | -3.828 |
tar | -3.303 |
Turk | -3.236 |
agents | -3.236 |
Token | 20 |
Token ID | 1160 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
hered | +6.106 |
Poly | +5.757 |
Bucc | +5.601 |
Revel | +5.537 |
brim | +5.274 |
Neg logit contributions | |
emis | -8.912 |
Turing | -8.257 |
tar | -7.129 |
agents | -7.100 |
Starg | -7.003 |
Token | 21 |
Token ID | 2310 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
hered | +4.181 |
Bucc | +3.825 |
Poly | +3.796 |
Revel | +3.741 |
brim | +3.599 |
Neg logit contributions | |
emis | -5.042 |
Turing | -4.737 |
tar | -4.038 |
agents | -3.978 |
aver | -3.948 |
Token | 22 |
Token ID | 2534 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
hered | +6.976 |
Poly | +6.243 |
Revel | +6.002 |
Bucc | +5.757 |
brim | +5.718 |
Neg logit contributions | |
emis | -12.269 |
Turing | -11.198 |
tar | -9.881 |
agents | -9.744 |
Starg | -9.697 |
Token | 23 |
Token ID | 2242 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
hered | +4.897 |
Revel | +4.393 |
Poly | +4.317 |
Bucc | +4.310 |
brim | +4.088 |
Neg logit contributions | |
emis | -8.583 |
Turing | -8.116 |
tar | -7.043 |
agents | -6.947 |
Starg | -6.925 |
Token | 24 |
Token ID | 1987 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
hered | +4.213 |
Bucc | +3.812 |
Poly | +3.810 |
Revel | +3.795 |
brim | +3.611 |
Neg logit contributions | |
emis | -6.756 |
Turing | -6.190 |
tar | -5.366 |
Turk | -5.363 |
Starg | -5.357 |
Token | SELECT |
Token ID | 33493 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
hered | +4.262 |
Poly | +3.901 |
Revel | +3.866 |
Bucc | +3.851 |
brim | +3.688 |
Neg logit contributions | |
emis | -6.625 |
Turing | -6.210 |
tar | -5.352 |
Turk | -5.292 |
Starg | -5.283 |
Token | REG |
Token ID | 23337 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
emis | +1.971 |
Turing | +1.888 |
tar | +1.613 |
Turk | +1.588 |
aver | +1.584 |
Neg logit contributions | |
hered | -1.776 |
Bucc | -1.630 |
Revel | -1.566 |
Pri | -1.524 |
Poly | -1.517 |
Token | 16 |
Token ID | 1467 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
hered | +3.748 |
Bucc | +3.467 |
Poly | +3.382 |
Revel | +3.360 |
Pri | +3.186 |
Neg logit contributions | |
emis | -4.645 |
Turing | -4.344 |
tar | -3.789 |
agents | -3.688 |
Starg | -3.679 |
Token | 17 |
Token ID | 1596 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
hered | +3.735 |
Bucc | +3.465 |
Revel | +3.393 |
Poly | +3.386 |
Pri | +3.233 |
Neg logit contributions | |
emis | -3.567 |
Turing | -3.364 |
tar | -2.863 |
Turk | -2.790 |
aver | -2.755 |
Token | 18 |
Token ID | 1248 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
hered | +1.928 |
Bucc | +1.817 |
Revel | +1.751 |
Poly | +1.748 |
Pri | +1.685 |
Neg logit contributions | |
emis | -1.975 |
Turing | -1.838 |
tar | -1.577 |
Turk | -1.546 |
Starg | -1.543 |
Token | 19 |
Token ID | 678 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
hered | +2.962 |
Bucc | +2.773 |
Poly | +2.684 |
Revel | +2.670 |
Pri | +2.557 |
Neg logit contributions | |
emis | -3.818 |
Turing | -3.600 |
tar | -3.140 |
aver | -3.059 |
Turk | -3.059 |
Token | 20 |
Token ID | 1160 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
hered | +5.449 |
Poly | +5.111 |
Bucc | +5.024 |
Revel | +4.908 |
brim | +4.671 |
Neg logit contributions | |
emis | -7.814 |
Turing | -7.213 |
tar | -6.347 |
agents | -6.234 |
aver | -6.174 |
Token | 21 |
Token ID | 2310 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
hered | +5.189 |
Poly | +4.706 |
Bucc | +4.675 |
Revel | +4.588 |
Pri | +4.409 |
Neg logit contributions | |
emis | -6.675 |
Turing | -6.264 |
tar | -5.438 |
agents | -5.321 |
aver | -5.288 |
Token | 22 |
Token ID | 2534 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
hered | +6.605 |
Poly | +5.832 |
Revel | +5.612 |
Bucc | +5.538 |
brim | +5.262 |
Neg logit contributions | |
emis | -11.936 |
Turing | -10.988 |
tar | -9.831 |
agents | -9.652 |
Starg | -9.556 |
Token | 23 |
Token ID | 2242 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
hered | +4.165 |
Bucc | +3.704 |
Revel | +3.703 |
Poly | +3.635 |
Pri | +3.419 |
Neg logit contributions | |
emis | -7.890 |
Turing | -7.417 |
tar | -6.594 |
Turk | -6.463 |
agents | -6.430 |
Token | 24 |
Token ID | 1987 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
hered | +3.379 |
Bucc | +3.099 |
Poly | +3.052 |
Revel | +3.033 |
Pri | +2.886 |
Neg logit contributions | |
emis | -5.513 |
Turing | -5.064 |
tar | -4.457 |
Turk | -4.428 |
Starg | -4.390 |
Token | 25 |
Token ID | 1679 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
hered | +4.089 |
Bucc | +3.754 |
Poly | +3.733 |
Revel | +3.707 |
brim | +3.523 |
Neg logit contributions | |
emis | -6.489 |
Turing | -6.071 |
tar | -5.307 |
Turk | -5.211 |
agents | -5.206 |
Token | 26 |
Token ID | 2608 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
hered | +3.467 |
Bucc | +3.151 |
Poly | +3.093 |
Revel | +3.069 |
brim | +2.907 |
Neg logit contributions | |
emis | -6.973 |
Turing | -6.517 |
tar | -5.811 |
agents | -5.718 |
Starg | -5.710 |
Token | buf |
Token ID | 29325 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
hered | +5.172 |
Bucc | +4.765 |
Revel | +4.544 |
Poly | +4.498 |
brim | +4.434 |
Neg logit contributions | |
emis | -5.661 |
Turing | -5.420 |
Turk | -4.554 |
Starg | -4.522 |
aver | -4.451 |
Token | | |
Token ID | 930 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
hered | +1.697 |
Bucc | +1.470 |
Revel | +1.382 |
Poly | +1.364 |
Pri | +1.280 |
Neg logit contributions | |
emis | -4.898 |
Turing | -4.671 |
tar | -4.191 |
aver | -4.133 |
Turk | -4.129 |
Token | + |
Token ID | 1343 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
hered | +2.333 |
Bucc | +2.190 |
Revel | +2.117 |
Poly | +2.093 |
Pri | +2.037 |
Neg logit contributions | |
emis | -2.447 |
Turing | -2.300 |
tar | -1.950 |
aver | -1.903 |
Turk | -1.896 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
emis | +1.434 |
Turing | +1.362 |
tar | +1.176 |
Starg | +1.145 |
agents | +1.136 |
Neg logit contributions | |
hered | -1.050 |
Bucc | -1.015 |
Revel | -0.966 |
Poly | -0.935 |
brim | -0.929 |
Token | --+ |
Token ID | 44785 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
emis | +3.518 |
Turing | +3.349 |
tar | +2.822 |
aver | +2.697 |
Turk | +2.678 |
Neg logit contributions | |
hered | -4.229 |
Bucc | -4.105 |
Revel | -4.067 |
brim | -3.885 |
Poly | -3.846 |
Token | | |
Token ID | 930 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hered | +2.241 |
Bucc | +1.934 |
Poly | +1.841 |
Revel | +1.822 |
Pri | +1.678 |
Neg logit contributions | |
emis | -6.992 |
Turing | -6.622 |
tar | -5.966 |
aver | -5.895 |
agents | -5.883 |
Token | int |
Token ID | 493 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
hered | +6.667 |
Bucc | +6.382 |
Poly | +6.279 |
Revel | +6.068 |
brim | +5.907 |
Neg logit contributions | |
emis | -10.817 |
Turing | -9.921 |
agents | -9.092 |
tar | -8.887 |
uphem | -8.799 |
Token | f |
Token ID | 277 |
Feature activation | +3.84e-03 |
Pos logit contributions | |
emis | +0.284 |
Turing | +0.264 |
tar | +0.216 |
aver | +0.208 |
Turk | +0.208 |
Neg logit contributions | |
hered | -0.380 |
Bucc | -0.360 |
Revel | -0.349 |
Poly | -0.346 |
Pri | -0.339 |
Token | d |
Token ID | 67 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
emis | +0.033 |
Turing | +0.031 |
tar | +0.027 |
aver | +0.025 |
Starg | +0.025 |
Neg logit contributions | |
hered | -0.031 |
Bucc | -0.030 |
Revel | -0.029 |
Poly | -0.028 |
brim | -0.028 |
Token | | |
Token ID | 930 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
hered | +1.302 |
Bucc | +1.156 |
Revel | +1.083 |
Poly | +1.058 |
Pri | +1.003 |
Neg logit contributions | |
emis | -3.512 |
Turing | -3.365 |
tar | -3.011 |
aver | -2.964 |
Turk | -2.958 |
Token | < |
Token ID | 1279 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
hered | +1.678 |
Bucc | +1.575 |
Revel | +1.523 |
Poly | +1.521 |
brim | +1.464 |
Neg logit contributions | |
emis | -1.915 |
Turing | -1.787 |
tar | -1.529 |
agents | -1.497 |
aver | -1.497 |
Token | 65 |
Token ID | 6135 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
hered | +0.570 |
Bucc | +0.529 |
Revel | +0.512 |
Poly | +0.501 |
brim | +0.495 |
Neg logit contributions | |
emis | -0.623 |
Turing | -0.594 |
tar | -0.503 |
Turk | -0.496 |
Starg | -0.493 |
Token | . |
Token ID | 13 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
emis | +1.051 |
Turing | +0.998 |
tar | +0.865 |
aver | +0.847 |
Turk | +0.845 |
Neg logit contributions | |
hered | -0.750 |
Bucc | -0.696 |
Revel | -0.668 |
Poly | -0.657 |
Pri | -0.638 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
hered | +0.039 |
Bucc | +0.037 |
Revel | +0.036 |
Poly | +0.035 |
Pri | +0.034 |
Neg logit contributions | |
emis | -0.044 |
Turing | -0.042 |
tar | -0.036 |
aver | -0.035 |
Turk | -0.034 |
Token | grams |
Token ID | 16379 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
hered | +0.844 |
Bucc | +0.787 |
Revel | +0.758 |
Poly | +0.746 |
Pri | +0.727 |
Neg logit contributions | |
emis | -1.047 |
Turing | -0.991 |
tar | -0.852 |
aver | -0.833 |
Turk | -0.830 |
Token |
|
Token ID | 198 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
hered | +3.130 |
Bucc | +2.927 |
Poly | +2.854 |
Revel | +2.814 |
brim | +2.692 |
Neg logit contributions | |
emis | -4.252 |
Turing | -3.983 |
tar | -3.446 |
agents | -3.394 |
Turk | -3.391 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hered | +3.752 |
Bucc | +3.426 |
Poly | +3.340 |
Revel | +3.307 |
Pri | +3.216 |
Neg logit contributions | |
emis | -4.869 |
Turing | -4.528 |
tar | -3.897 |
aver | -3.851 |
Turk | -3.828 |
Token | B |
Token ID | 33 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
hered | +6.003 |
Bucc | +5.321 |
Pri | +5.228 |
Poly | +5.016 |
Revel | +4.916 |
Neg logit contributions | |
emis | -11.787 |
Turing | -11.066 |
Turk | -9.839 |
Starg | -9.646 |
aver | -9.549 |
Token | earing |
Token ID | 6648 |
Feature activation | +5.66e-03 |
Pos logit contributions | |
hered | +1.556 |
Bucc | +1.415 |
Revel | +1.367 |
Poly | +1.351 |
Pri | +1.319 |
Neg logit contributions | |
emis | -2.084 |
Turing | -1.985 |
tar | -1.706 |
Turk | -1.692 |
Starg | -1.681 |
Token | : |
Token ID | 25 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
emis | +0.052 |
Turing | +0.050 |
tar | +0.043 |
Starg | +0.042 |
aver | +0.042 |
Neg logit contributions | |
hered | -0.042 |
Bucc | -0.040 |
Revel | -0.038 |
Poly | -0.037 |
brim | -0.037 |
Token | Size |
Token ID | 12849 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
hered | +3.895 |
Bucc | +3.781 |
Poly | +3.653 |
Revel | +3.593 |
brim | +3.416 |
Neg logit contributions | |
emis | -4.350 |
Turing | -4.055 |
tar | -3.468 |
agents | -3.412 |
aver | -3.375 |
Token | C |
Token ID | 327 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
hered | +3.862 |
Bucc | +3.643 |
Poly | +3.494 |
Revel | +3.465 |
brim | +3.332 |
Neg logit contributions | |
emis | -4.991 |
Turing | -4.703 |
tar | -4.080 |
agents | -3.993 |
aver | -3.967 |
Token | need |
Token ID | 761 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
emis | +0.873 |
Turing | +0.818 |
tar | +0.691 |
aver | +0.678 |
Turk | +0.661 |
Neg logit contributions | |
hered | -0.987 |
Bucc | -0.942 |
Revel | -0.907 |
Poly | -0.901 |
Pri | -0.880 |
Token | to |
Token ID | 284 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
hered | +0.146 |
Bucc | +0.136 |
Revel | +0.130 |
Poly | +0.128 |
Pri | +0.125 |
Neg logit contributions | |
emis | -0.184 |
Turing | -0.174 |
tar | -0.151 |
Turk | -0.147 |
aver | -0.147 |
Token | be |
Token ID | 307 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
hered | +1.314 |
Bucc | +1.229 |
Revel | +1.180 |
Poly | +1.164 |
Pri | +1.138 |
Neg logit contributions | |
emis | -1.530 |
Turing | -1.451 |
tar | -1.242 |
aver | -1.216 |
Starg | -1.211 |
Token | in |
Token ID | 287 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
hered | +0.631 |
Bucc | +0.593 |
Revel | +0.568 |
Poly | +0.559 |
Pri | +0.551 |
Neg logit contributions | |
emis | -0.733 |
Turing | -0.698 |
tar | -0.595 |
aver | -0.585 |
Starg | -0.582 |
Token | fifth |
Token ID | 8150 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
hered | +1.183 |
Bucc | +1.104 |
Revel | +1.057 |
Poly | +1.038 |
Pri | +1.019 |
Neg logit contributions | |
emis | -1.457 |
Turing | -1.383 |
tar | -1.189 |
Turk | -1.169 |
Starg | -1.167 |
Token | or |
Token ID | 393 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hered | +1.185 |
Bucc | +1.107 |
Revel | +1.059 |
Poly | +1.039 |
Pri | +1.010 |
Neg logit contributions | |
emis | -1.577 |
Turing | -1.490 |
tar | -1.298 |
aver | -1.267 |
Turk | -1.263 |
Token | sixth |
Token ID | 11695 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
hered | +6.351 |
Bucc | +6.040 |
Revel | +5.800 |
Poly | +5.670 |
brim | +5.508 |
Neg logit contributions | |
emis | -11.015 |
Turing | -10.376 |
agents | -9.163 |
tar | -9.075 |
uphem | -8.949 |
Token | position |
Token ID | 2292 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
hered | +1.375 |
Bucc | +1.281 |
Revel | +1.228 |
Poly | +1.206 |
Pri | +1.173 |
Neg logit contributions | |
emis | -1.807 |
Turing | -1.711 |
tar | -1.485 |
aver | -1.451 |
Turk | -1.447 |
Token | at |
Token ID | 379 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
hered | +1.979 |
Bucc | +1.841 |
Revel | +1.768 |
Poly | +1.743 |
Pri | +1.691 |
Neg logit contributions | |
emis | -2.645 |
Turing | -2.507 |
tar | -2.167 |
aver | -2.122 |
Turk | -2.115 |
Token | that |
Token ID | 326 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
hered | +1.512 |
Bucc | +1.405 |
Revel | +1.351 |
Poly | +1.332 |
Pri | +1.295 |
Neg logit contributions | |
emis | -1.956 |
Turing | -1.854 |
tar | -1.598 |
aver | -1.564 |
Turk | -1.562 |
Token | point |
Token ID | 966 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
hered | +0.323 |
Bucc | +0.303 |
Revel | +0.291 |
Poly | +0.286 |
Pri | +0.280 |
Neg logit contributions | |
emis | -0.366 |
Turing | -0.350 |
tar | -0.299 |
aver | -0.292 |
Turk | -0.292 |
Token | journalism |
Token ID | 14033 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
hered | +0.337 |
Bucc | +0.317 |
Revel | +0.308 |
Poly | +0.301 |
brim | +0.294 |
Neg logit contributions | |
emis | -0.378 |
Turing | -0.356 |
tar | -0.306 |
aver | -0.299 |
Starg | -0.298 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
emis | +1.414 |
Turing | +1.351 |
tar | +1.172 |
Starg | +1.144 |
Turk | +1.141 |
Neg logit contributions | |
hered | -1.127 |
Bucc | -1.082 |
Revel | -1.045 |
brim | -1.018 |
merce | -1.004 |
Token | You |
Token ID | 921 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
hered | +2.523 |
Bucc | +2.366 |
Revel | +2.289 |
Poly | +2.265 |
Pri | +2.203 |
Neg logit contributions | |
emis | -2.637 |
Turing | -2.477 |
tar | -2.095 |
aver | -2.051 |
Turk | -2.037 |
Token | can |
Token ID | 460 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
emis | +0.037 |
Turing | +0.035 |
tar | +0.030 |
aver | +0.029 |
Starg | +0.029 |
Neg logit contributions | |
hered | -0.036 |
Bucc | -0.034 |
Revel | -0.033 |
Poly | -0.032 |
brim | -0.032 |
Token | read |
Token ID | 1100 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
hered | +4.130 |
Bucc | +3.598 |
Revel | +3.484 |
Poly | +3.448 |
Pri | +3.269 |
Neg logit contributions | |
emis | -9.078 |
Turing | -8.723 |
tar | -7.659 |
agents | -7.577 |
Turk | -7.554 |
Token | our |
Token ID | 674 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
hered | +4.050 |
Bucc | +3.695 |
Poly | +3.594 |
Revel | +3.579 |
Pri | +3.401 |
Neg logit contributions | |
emis | -6.214 |
Turing | -5.842 |
tar | -5.096 |
aver | -4.992 |
agents | -4.970 |
Token | Privacy |
Token ID | 16777 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
hered | +4.113 |
Bucc | +3.858 |
Poly | +3.562 |
Revel | +3.475 |
Pri | +3.362 |
Neg logit contributions | |
emis | -13.314 |
Turing | -12.761 |
tar | -11.499 |
aver | -11.324 |
Turk | -11.270 |
Token | Policy |
Token ID | 7820 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
hered | +1.796 |
Bucc | +1.669 |
Revel | +1.602 |
Poly | +1.583 |
Pri | +1.536 |
Neg logit contributions | |
emis | -2.474 |
Turing | -2.342 |
tar | -2.031 |
aver | -1.993 |
Turk | -1.982 |
Token | here |
Token ID | 994 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
hered | +2.222 |
Bucc | +2.026 |
Revel | +1.946 |
Poly | +1.920 |
Pri | +1.847 |
Neg logit contributions | |
emis | -3.728 |
Turing | -3.550 |
tar | -3.106 |
aver | -3.054 |
Turk | -3.052 |
Token | . |
Token ID | 13 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
emis | +0.875 |
Turing | +0.840 |
tar | +0.726 |
Starg | +0.714 |
Turk | +0.707 |
Neg logit contributions | |
hered | -0.670 |
Bucc | -0.636 |
Revel | -0.607 |
brim | -0.594 |
Poly | -0.588 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
hered | +0.596 |
Bucc | +0.564 |
Revel | +0.545 |
Poly | +0.540 |
brim | +0.529 |
Neg logit contributions | |
emis | -0.484 |
Turing | -0.455 |
tar | -0.376 |
Starg | -0.365 |
aver | -0.363 |
Token | ) |
Token ID | 8 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
hered | +1.047 |
Bucc | +0.974 |
Revel | +0.935 |
Poly | +0.920 |
Pri | +0.891 |
Neg logit contributions | |
emis | -1.463 |
Turing | -1.387 |
tar | -1.203 |
aver | -1.179 |
Turk | -1.175 |
Token | 17 |
Token ID | 1596 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
emis | +0.348 |
Turing | +0.327 |
tar | +0.276 |
aver | +0.273 |
Turk | +0.270 |
Neg logit contributions | |
hered | -0.329 |
Bucc | -0.309 |
Revel | -0.297 |
Poly | -0.291 |
Pri | -0.289 |
Token | 18 |
Token ID | 1248 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
hered | +2.037 |
Bucc | +1.902 |
Revel | +1.833 |
Poly | +1.811 |
Pri | +1.759 |
Neg logit contributions | |
emis | -2.416 |
Turing | -2.284 |
tar | -1.954 |
aver | -1.910 |
Turk | -1.905 |
Token | 19 |
Token ID | 678 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
hered | +2.659 |
Bucc | +2.495 |
Revel | +2.410 |
Poly | +2.388 |
Pri | +2.306 |
Neg logit contributions | |
emis | -3.014 |
Turing | -2.840 |
tar | -2.429 |
aver | -2.367 |
Starg | -2.364 |
Token | 20 |
Token ID | 1160 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
hered | +5.600 |
Bucc | +5.235 |
Poly | +5.146 |
Revel | +5.111 |
brim | +4.855 |
Neg logit contributions | |
emis | -7.030 |
Turing | -6.515 |
tar | -5.622 |
agents | -5.558 |
Starg | -5.546 |
Token | 21 |
Token ID | 2310 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
hered | +3.481 |
Bucc | +3.217 |
Poly | +3.149 |
Revel | +3.117 |
brim | +3.005 |
Neg logit contributions | |
emis | -4.165 |
Turing | -3.915 |
tar | -3.361 |
Starg | -3.297 |
agents | -3.291 |
Token | 22 |
Token ID | 2534 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
hered | +6.076 |
Poly | +5.420 |
Revel | +5.240 |
Bucc | +5.226 |
brim | +5.022 |
Neg logit contributions | |
emis | -11.023 |
Turing | -10.072 |
Starg | -8.966 |
tar | -8.940 |
agents | -8.793 |
Token | 23 |
Token ID | 2242 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
hered | +3.342 |
Bucc | +3.015 |
Revel | +2.992 |
Poly | +2.933 |
brim | +2.775 |
Neg logit contributions | |
emis | -6.106 |
Turing | -5.814 |
tar | -5.116 |
Starg | -5.033 |
Turk | -5.026 |
Token | 24 |
Token ID | 1987 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
hered | +2.383 |
Bucc | +2.212 |
Revel | +2.138 |
Poly | +2.131 |
brim | +2.041 |
Neg logit contributions | |
emis | -3.524 |
Turing | -3.288 |
tar | -2.865 |
Starg | -2.826 |
Turk | -2.820 |
Token | 25 |
Token ID | 1679 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
hered | +2.751 |
Bucc | +2.550 |
Revel | +2.460 |
Poly | +2.431 |
Pri | +2.344 |
Neg logit contributions | |
emis | -3.848 |
Turing | -3.644 |
tar | -3.160 |
aver | -3.088 |
Turk | -3.086 |
Token | 26 |
Token ID | 2608 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
hered | +2.554 |
Bucc | +2.346 |
Revel | +2.246 |
Poly | +2.228 |
brim | +2.131 |
Neg logit contributions | |
emis | -4.691 |
Turing | -4.442 |
tar | -3.932 |
Starg | -3.853 |
agents | -3.837 |
Token | x |
Token ID | 2124 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
emis | +0.276 |
Turing | +0.263 |
tar | +0.219 |
aver | +0.214 |
Turk | +0.213 |
Neg logit contributions | |
hered | -0.307 |
Bucc | -0.288 |
Revel | -0.279 |
Poly | -0.272 |
Pri | -0.270 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
hered | +1.497 |
Bucc | +1.386 |
Revel | +1.328 |
Poly | +1.307 |
Pri | +1.265 |
Neg logit contributions | |
emis | -2.231 |
Turing | -2.121 |
tar | -1.847 |
aver | -1.809 |
Turk | -1.804 |
Token | x |
Token ID | 87 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
emis | +2.377 |
Turing | +2.237 |
tar | +1.951 |
agents | +1.809 |
Starg | +1.802 |
Neg logit contributions | |
hered | -2.623 |
Bucc | -2.598 |
Revel | -2.498 |
brim | -2.434 |
Poly | -2.397 |
Token | . |
Token ID | 13 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
hered | +0.365 |
Bucc | +0.344 |
Revel | +0.330 |
Poly | +0.320 |
brim | +0.317 |
Neg logit contributions | |
emis | -0.508 |
Turing | -0.486 |
tar | -0.423 |
Starg | -0.412 |
Turk | -0.411 |
Token | x |
Token ID | 87 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
emis | +0.804 |
Turing | +0.756 |
tar | +0.651 |
Starg | +0.616 |
aver | +0.616 |
Neg logit contributions | |
hered | -0.811 |
Bucc | -0.781 |
Revel | -0.753 |
Poly | -0.733 |
brim | -0.727 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
hered | +3.338 |
Bucc | +2.968 |
Poly | +2.870 |
Revel | +2.856 |
Pri | +2.791 |
Neg logit contributions | |
emis | -5.571 |
Turing | -5.237 |
aver | -4.549 |
tar | -4.547 |
Turk | -4.511 |
Token | 122 |
Token ID | 18376 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
hered | +6.925 |
Bucc | +5.819 |
Pri | +5.790 |
Poly | +5.766 |
Revel | +5.578 |
Neg logit contributions | |
emis | -10.734 |
Turing | -9.979 |
Gadget | -8.898 |
Turk | -8.754 |
aver | -8.743 |
Token | 110 |
Token ID | 9796 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
hered | +1.976 |
Bucc | +1.843 |
Revel | +1.776 |
Poly | +1.745 |
brim | +1.706 |
Neg logit contributions | |
emis | -2.360 |
Turing | -2.245 |
tar | -1.920 |
Turk | -1.873 |
Starg | -1.873 |
Token | 75 |
Token ID | 2425 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
hered | +0.393 |
Bucc | +0.370 |
Revel | +0.358 |
brim | +0.350 |
Poly | +0.347 |
Neg logit contributions | |
emis | -0.447 |
Turing | -0.429 |
tar | -0.369 |
Starg | -0.357 |
Turk | -0.355 |
Token | 46 |
Token ID | 3510 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
emis | +3.440 |
Turing | +3.408 |
tar | +2.923 |
Starg | +2.806 |
Turk | +2.790 |
Neg logit contributions | |
hered | -3.687 |
Bucc | -3.515 |
merce | -3.479 |
Revel | -3.427 |
brim | -3.395 |
Token | x |
Token ID | 2124 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
hered | +0.165 |
Bucc | +0.155 |
Revel | +0.150 |
Poly | +0.146 |
Pri | +0.145 |
Neg logit contributions | |
emis | -0.150 |
Turing | -0.142 |
tar | -0.118 |
aver | -0.116 |
Starg | -0.115 |
Token | ulse |
Token ID | 9615 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
hered | +1.171 |
Bucc | +1.119 |
Revel | +1.084 |
Poly | +1.070 |
brim | +1.046 |
Neg logit contributions | |
emis | -0.858 |
Turing | -0.794 |
tar | -0.650 |
aver | -0.626 |
Starg | -0.623 |
Token | Per |
Token ID | 5990 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
hered | +3.010 |
Bucc | +2.770 |
Poly | +2.646 |
Revel | +2.642 |
Pri | +2.543 |
Neg logit contributions | |
emis | -5.138 |
Turing | -4.864 |
tar | -4.254 |
Starg | -4.189 |
Turk | -4.172 |
Token | iod |
Token ID | 2101 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
hered | +4.051 |
Bucc | +3.733 |
Poly | +3.614 |
Revel | +3.612 |
Pri | +3.539 |
Neg logit contributions | |
emis | -4.242 |
Turing | -3.998 |
tar | -3.342 |
Turk | -3.305 |
aver | -3.300 |
Token | (" |
Token ID | 5855 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
hered | +1.160 |
Bucc | +1.087 |
Revel | +1.049 |
Poly | +1.036 |
Pri | +1.008 |
Neg logit contributions | |
emis | -1.284 |
Turing | -1.211 |
tar | -1.031 |
aver | -1.007 |
Turk | -1.004 |
Token | P |
Token ID | 47 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
hered | +2.302 |
Bucc | +2.135 |
Revel | +2.053 |
Poly | +2.039 |
Pri | +1.988 |
Neg logit contributions | |
emis | -2.955 |
Turing | -2.795 |
tar | -2.401 |
Turk | -2.361 |
aver | -2.354 |
Token | ulse |
Token ID | 9615 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
hered | +2.446 |
Bucc | +2.324 |
Revel | +2.257 |
Poly | +2.230 |
Pri | +2.181 |
Neg logit contributions | |
emis | -1.831 |
Turing | -1.702 |
tar | -1.390 |
aver | -1.346 |
Turk | -1.339 |
Token | period |
Token ID | 2278 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
hered | +6.826 |
Bucc | +6.219 |
Poly | +6.084 |
Revel | +5.924 |
brim | +5.821 |
Neg logit contributions | |
emis | -10.407 |
Turing | -9.753 |
tar | -8.630 |
agents | -8.534 |
Starg | -8.320 |
Token | ", |
Token ID | 1600 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
hered | +1.737 |
Bucc | +1.590 |
Revel | +1.526 |
Poly | +1.517 |
brim | +1.457 |
Neg logit contributions | |
emis | -2.699 |
Turing | -2.558 |
tar | -2.235 |
agents | -2.199 |
Turk | -2.193 |
Token | Float |
Token ID | 48436 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
emis | +1.825 |
Turing | +1.754 |
tar | +1.533 |
aver | +1.520 |
Starg | +1.512 |
Neg logit contributions | |
hered | -0.981 |
Bucc | -0.896 |
Revel | -0.846 |
Poly | -0.817 |
Pri | -0.806 |
Token | ) |
Token ID | 8 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
hered | +0.644 |
Bucc | +0.602 |
Revel | +0.580 |
Poly | +0.569 |
Pri | +0.554 |
Neg logit contributions | |
emis | -0.783 |
Turing | -0.742 |
tar | -0.636 |
aver | -0.623 |
Turk | -0.621 |
Token | = |
Token ID | 796 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
hered | +2.217 |
Bucc | +2.070 |
Revel | +2.010 |
Poly | +2.004 |
Pri | +1.921 |
Neg logit contributions | |
emis | -2.526 |
Turing | -2.358 |
tar | -2.025 |
agents | -1.967 |
Turk | -1.966 |
Token | + |
Token ID | 10 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
hered | +2.205 |
Bucc | +2.044 |
Revel | +1.959 |
Poly | +1.944 |
Pri | +1.874 |
Neg logit contributions | |
emis | -3.289 |
Turing | -3.114 |
tar | -2.709 |
aver | -2.657 |
Turk | -2.650 |
Token | " |
Token ID | 1 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
hered | +1.301 |
Bucc | +1.218 |
Revel | +1.174 |
Poly | +1.152 |
Pri | +1.122 |
Neg logit contributions | |
emis | -1.506 |
Turing | -1.424 |
tar | -1.224 |
aver | -1.192 |
Turk | -1.186 |
Token | \ |
Token ID | 59 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
hered | +3.757 |
Bucc | +3.510 |
Revel | +3.398 |
Poly | +3.381 |
Pri | +3.266 |
Neg logit contributions | |
emis | -4.352 |
Turing | -4.100 |
tar | -3.473 |
aver | -3.418 |
Starg | -3.413 |
Token | S |
Token ID | 50 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
hered | +0.155 |
Bucc | +0.146 |
Revel | +0.140 |
Poly | +0.136 |
brim | +0.133 |
Neg logit contributions | |
emis | -0.210 |
Turing | -0.199 |
tar | -0.175 |
aver | -0.169 |
Starg | -0.169 |
Token | + |
Token ID | 10 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
hered | +2.519 |
Bucc | +2.337 |
Revel | +2.243 |
Poly | +2.231 |
Pri | +2.150 |
Neg logit contributions | |
emis | -3.559 |
Turing | -3.364 |
tar | -2.907 |
aver | -2.857 |
Turk | -2.849 |
Token | "] |
Token ID | 8973 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
hered | +1.372 |
Bucc | +1.277 |
Revel | +1.227 |
Poly | +1.207 |
Pri | +1.172 |
Neg logit contributions | |
emis | -1.820 |
Turing | -1.727 |
tar | -1.495 |
aver | -1.461 |
Turk | -1.456 |
Token | ' |
Token ID | 6 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
hered | +7.175 |
Poly | +6.676 |
Bucc | +6.637 |
Revel | +6.504 |
Pri | +6.272 |
Neg logit contributions | |
emis | -9.763 |
Turing | -9.068 |
agents | -7.744 |
Starg | -7.722 |
aver | -7.714 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
hered | +2.502 |
Bucc | +2.337 |
Revel | +2.262 |
Poly | +2.238 |
Pri | +2.167 |
Neg logit contributions | |
emis | -2.913 |
Turing | -2.747 |
tar | -2.340 |
aver | -2.291 |
Starg | -2.291 |
Token | AS |
Token ID | 7054 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
hered | +1.241 |
Bucc | +1.156 |
Revel | +1.111 |
Poly | +1.096 |
Pri | +1.066 |
Neg logit contributions | |
emis | -1.569 |
Turing | -1.487 |
tar | -1.281 |
aver | -1.252 |
Turk | -1.248 |
Token | library |
Token ID | 5888 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
emis | +2.497 |
Turing | +2.401 |
tar | +2.043 |
Turk | +2.005 |
aver | +2.004 |
Neg logit contributions | |
hered | -2.200 |
Bucc | -2.037 |
Revel | -1.952 |
Poly | -1.895 |
Pri | -1.893 |
Token | , |
Token ID | 837 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
hered | +0.442 |
Bucc | +0.413 |
Revel | +0.396 |
Poly | +0.390 |
brim | +0.378 |
Neg logit contributions | |
emis | -0.525 |
Turing | -0.498 |
tar | -0.431 |
aver | -0.418 |
Turk | -0.417 |
Token | buf |
Token ID | 29325 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
hered | +5.090 |
Bucc | +4.676 |
Revel | +4.460 |
Poly | +4.433 |
brim | +4.349 |
Neg logit contributions | |
emis | -5.635 |
Turing | -5.374 |
Turk | -4.550 |
Starg | -4.483 |
aver | -4.451 |
Token | | |
Token ID | 930 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
hered | +1.599 |
Bucc | +1.391 |
Revel | +1.307 |
Poly | +1.289 |
Pri | +1.212 |
Neg logit contributions | |
emis | -4.562 |
Turing | -4.352 |
tar | -3.903 |
aver | -3.849 |
Turk | -3.845 |
Token | + |
Token ID | 1343 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
hered | +2.864 |
Bucc | +2.686 |
Poly | +2.619 |
Revel | +2.598 |
brim | +2.512 |
Neg logit contributions | |
emis | -3.518 |
Turing | -3.257 |
tar | -2.815 |
agents | -2.778 |
Turk | -2.755 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
emis | +0.919 |
Turing | +0.874 |
tar | +0.756 |
Starg | +0.736 |
agents | +0.731 |
Neg logit contributions | |
hered | -0.663 |
Bucc | -0.637 |
Revel | -0.607 |
Poly | -0.589 |
brim | -0.582 |
Token | --+ |
Token ID | 44785 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
emis | +3.029 |
Turing | +2.892 |
tar | +2.432 |
aver | +2.333 |
Turk | +2.317 |
Neg logit contributions | |
hered | -3.583 |
Bucc | -3.470 |
Revel | -3.429 |
brim | -3.273 |
Poly | -3.250 |
Token | | |
Token ID | 930 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
hered | +2.192 |
Bucc | +1.892 |
Poly | +1.799 |
Revel | +1.781 |
Pri | +1.646 |
Neg logit contributions | |
emis | -6.703 |
Turing | -6.347 |
tar | -5.717 |
aver | -5.648 |
agents | -5.635 |
Token | int |
Token ID | 493 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
hered | +6.246 |
Bucc | +5.957 |
Poly | +5.886 |
Revel | +5.632 |
brim | +5.557 |
Neg logit contributions | |
emis | -10.074 |
Turing | -9.254 |
agents | -8.488 |
tar | -8.267 |
Turk | -8.234 |
Token | f |
Token ID | 277 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
hered | +0.278 |
Bucc | +0.265 |
Revel | +0.258 |
Poly | +0.253 |
Pri | +0.250 |
Neg logit contributions | |
emis | -0.185 |
Turing | -0.173 |
tar | -0.138 |
aver | -0.136 |
Starg | -0.134 |
Token | d |
Token ID | 67 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
hered | +0.496 |
Bucc | +0.476 |
Revel | +0.459 |
Poly | +0.447 |
brim | +0.441 |
Neg logit contributions | |
emis | -0.527 |
Turing | -0.496 |
tar | -0.431 |
aver | -0.412 |
agents | -0.409 |
Token | | |
Token ID | 930 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
hered | +1.696 |
Bucc | +1.477 |
Revel | +1.390 |
Poly | +1.372 |
Pri | +1.289 |
Neg logit contributions | |
emis | -4.885 |
Turing | -4.659 |
tar | -4.178 |
aver | -4.122 |
Turk | -4.116 |
Token | < |
Token ID | 1279 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
hered | +3.891 |
Bucc | +3.569 |
Poly | +3.492 |
Revel | +3.481 |
brim | +3.262 |
Neg logit contributions | |
emis | -7.560 |
Turing | -7.078 |
tar | -6.299 |
agents | -6.240 |
Turk | -6.205 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
emis | +0.410 |
Turing | +0.391 |
tar | +0.331 |
Starg | +0.321 |
Turk | +0.320 |
Neg logit contributions | |
hered | -0.406 |
Bucc | -0.387 |
Revel | -0.373 |
brim | -0.364 |
Poly | -0.363 |
Token | See |
Token ID | 6214 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
emis | +1.732 |
Turing | +1.616 |
tar | +1.357 |
Starg | +1.296 |
aver | +1.292 |
Neg logit contributions | |
hered | -2.046 |
Bucc | -1.955 |
Revel | -1.891 |
Poly | -1.866 |
brim | -1.833 |
Token | the |
Token ID | 262 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
hered | +4.447 |
Bucc | +4.105 |
Poly | +3.998 |
Revel | +3.966 |
Pri | +3.785 |
Neg logit contributions | |
emis | -6.873 |
Turing | -6.459 |
tar | -5.688 |
aver | -5.562 |
agents | -5.533 |
Token | full |
Token ID | 1336 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
hered | +0.513 |
Bucc | +0.470 |
Revel | +0.447 |
Poly | +0.435 |
brim | +0.425 |
Neg logit contributions | |
emis | -0.822 |
Turing | -0.794 |
tar | -0.685 |
Starg | -0.682 |
aver | -0.676 |
Token | list |
Token ID | 1351 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
hered | +0.972 |
Bucc | +0.910 |
Revel | +0.872 |
Poly | +0.855 |
Pri | +0.836 |
Neg logit contributions | |
emis | -1.139 |
Turing | -1.088 |
tar | -0.923 |
Starg | -0.910 |
Turk | -0.907 |
Token | of |
Token ID | 286 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
hered | +0.446 |
Bucc | +0.420 |
Revel | +0.402 |
Poly | +0.392 |
brim | +0.386 |
Neg logit contributions | |
emis | -0.588 |
Turing | -0.561 |
tar | -0.485 |
Starg | -0.473 |
Turk | -0.473 |
Token | previous |
Token ID | 2180 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
hered | +7.027 |
Bucc | +6.537 |
Revel | +6.295 |
Poly | +6.282 |
Pri | +5.974 |
Neg logit contributions | |
emis | -9.970 |
Turing | -9.357 |
tar | -8.343 |
agents | -8.066 |
Turk | -7.931 |
Token | award |
Token ID | 5764 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
hered | +2.487 |
Bucc | +2.301 |
Revel | +2.221 |
Poly | +2.197 |
Pri | +2.131 |
Neg logit contributions | |
emis | -3.538 |
Turing | -3.313 |
tar | -2.897 |
aver | -2.827 |
agents | -2.818 |
Token | winners |
Token ID | 14591 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
hered | +3.177 |
Bucc | +2.970 |
Revel | +2.862 |
Poly | +2.824 |
Pri | +2.746 |
Neg logit contributions | |
emis | -3.757 |
Turing | -3.550 |
tar | -3.040 |
aver | -2.972 |
Turk | -2.962 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
emis | +0.217 |
Turing | +0.208 |
tar | +0.179 |
Starg | +0.176 |
Turk | +0.175 |
Neg logit contributions | |
hered | -0.161 |
Bucc | -0.152 |
Revel | -0.145 |
Poly | -0.141 |
brim | -0.140 |
Token |
|
Token ID | 198 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
hered | +1.183 |
Bucc | +1.107 |
Revel | +1.071 |
Poly | +1.066 |
Pri | +1.029 |
Neg logit contributions | |
emis | -1.434 |
Turing | -1.347 |
tar | -1.160 |
aver | -1.144 |
agents | -1.132 |
Token | + |
Token ID | 10 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
hered | +1.083 |
Bucc | +1.005 |
Revel | +0.963 |
Poly | +0.952 |
Pri | +0.921 |
Neg logit contributions | |
emis | -1.556 |
Turing | -1.477 |
tar | -1.281 |
aver | -1.256 |
Turk | -1.253 |
Token | "( |
Token ID | 18109 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
hered | +1.546 |
Bucc | +1.439 |
Revel | +1.384 |
Poly | +1.365 |
Pri | +1.325 |
Neg logit contributions | |
emis | -2.013 |
Turing | -1.907 |
tar | -1.645 |
aver | -1.610 |
Turk | -1.605 |
Token | \ |
Token ID | 59 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
hered | +2.719 |
Bucc | +2.533 |
Revel | +2.440 |
Poly | +2.422 |
Pri | +2.351 |
Neg logit contributions | |
emis | -3.298 |
Turing | -3.116 |
tar | -2.658 |
aver | -2.612 |
Turk | -2.607 |
Token | S |
Token ID | 50 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
hered | +0.588 |
Bucc | +0.544 |
Revel | +0.522 |
Poly | +0.511 |
brim | +0.494 |
Neg logit contributions | |
emis | -0.892 |
Turing | -0.847 |
tar | -0.742 |
aver | -0.724 |
Starg | -0.722 |
Token | +) |
Token ID | 28988 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
hered | +3.130 |
Bucc | +2.881 |
Poly | +2.779 |
Revel | +2.725 |
Pri | +2.646 |
Neg logit contributions | |
emis | -5.287 |
Turing | -5.004 |
tar | -4.333 |
aver | -4.292 |
Turk | -4.284 |
Token | "] |
Token ID | 8973 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
hered | +4.875 |
Bucc | +4.473 |
Poly | +4.358 |
Revel | +4.351 |
Pri | +4.184 |
Neg logit contributions | |
emis | -6.630 |
Turing | -6.240 |
Turk | -5.296 |
tar | -5.289 |
aver | -5.283 |
Token | ' |
Token ID | 6 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
hered | +5.473 |
Poly | +5.087 |
Bucc | +4.968 |
Revel | +4.868 |
Pri | +4.663 |
Neg logit contributions | |
emis | -10.832 |
Turing | -10.134 |
agents | -8.959 |
Starg | -8.868 |
Turk | -8.837 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
hered | +4.522 |
Bucc | +4.148 |
Poly | +4.016 |
Revel | +4.005 |
brim | +3.799 |
Neg logit contributions | |
emis | -7.012 |
Turing | -6.638 |
Starg | -5.798 |
tar | -5.712 |
agents | -5.694 |
Token | AS |
Token ID | 7054 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
hered | +2.539 |
Bucc | +2.357 |
Revel | +2.272 |
Poly | +2.258 |
Pri | +2.145 |
Neg logit contributions | |
emis | -4.048 |
Turing | -3.819 |
tar | -3.328 |
aver | -3.269 |
agents | -3.265 |
Token | version |
Token ID | 2196 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
emis | +0.706 |
Turing | +0.672 |
tar | +0.570 |
aver | +0.560 |
Turk | +0.558 |
Neg logit contributions | |
hered | -0.636 |
Bucc | -0.594 |
Revel | -0.574 |
Poly | -0.561 |
Pri | -0.556 |
Token | , |
Token ID | 837 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
hered | +0.217 |
Bucc | +0.204 |
Revel | +0.196 |
Poly | +0.193 |
Pri | +0.188 |
Neg logit contributions | |
emis | -0.235 |
Turing | -0.222 |
tar | -0.190 |
aver | -0.184 |
Turk | -0.184 |
Token | x |
Token ID | 2124 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
emis | +0.781 |
Turing | +0.744 |
tar | +0.618 |
aver | +0.605 |
Turk | +0.604 |
Neg logit contributions | |
hered | -0.906 |
Bucc | -0.853 |
Revel | -0.826 |
brim | -0.801 |
Poly | -0.800 |
Token | . |
Token ID | 13 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
hered | +1.702 |
Bucc | +1.568 |
Revel | +1.503 |
Poly | +1.484 |
Pri | +1.436 |
Neg logit contributions | |
emis | -2.577 |
Turing | -2.445 |
tar | -2.130 |
aver | -2.091 |
Turk | -2.084 |
Token | x |
Token ID | 87 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
emis | +2.856 |
Turing | +2.690 |
tar | +2.349 |
Starg | +2.166 |
agents | +2.162 |
Neg logit contributions | |
hered | -3.265 |
Bucc | -3.254 |
Revel | -3.129 |
brim | -3.062 |
Poly | -2.981 |
Token | . |
Token ID | 13 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
emis | +0.277 |
Turing | +0.266 |
tar | +0.231 |
Starg | +0.225 |
Turk | +0.223 |
Neg logit contributions | |
hered | -0.207 |
Bucc | -0.197 |
Revel | -0.188 |
brim | -0.182 |
Poly | -0.181 |
Token | x |
Token ID | 87 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
emis | +1.830 |
Turing | +1.718 |
tar | +1.492 |
Starg | +1.391 |
agents | +1.389 |
Neg logit contributions | |
hered | -1.956 |
Bucc | -1.913 |
Revel | -1.844 |
brim | -1.794 |
Poly | -1.776 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
hered | +2.817 |
Bucc | +2.549 |
Revel | +2.442 |
Poly | +2.439 |
Pri | +2.378 |
Neg logit contributions | |
emis | -4.517 |
Turing | -4.283 |
tar | -3.719 |
aver | -3.696 |
Turk | -3.681 |
Token | 117 |
Token ID | 17657 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
hered | +3.378 |
Bucc | +2.579 |
Pri | +2.422 |
Revel | +2.403 |
Poly | +2.370 |
Neg logit contributions | |
emis | -13.468 |
Turing | -13.158 |
Turk | -11.866 |
Gadget | -11.761 |
aver | -11.732 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
hered | +0.250 |
Bucc | +0.232 |
Revel | +0.224 |
Poly | +0.219 |
brim | +0.218 |
Neg logit contributions | |
emis | -0.287 |
Turing | -0.277 |
tar | -0.235 |
Turk | -0.231 |
Starg | -0.230 |
Token | 0000 |
Token ID | 2388 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
hered | +1.168 |
Bucc | +1.088 |
Revel | +1.052 |
Poly | +1.029 |
brim | +1.020 |
Neg logit contributions | |
emis | -1.394 |
Turing | -1.334 |
tar | -1.142 |
Starg | -1.110 |
Turk | -1.108 |
Token | 8 |
Token ID | 23 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
emis | +4.238 |
Turing | +4.142 |
tar | +3.516 |
aver | +3.405 |
Turk | +3.398 |
Neg logit contributions | |
hered | -4.735 |
Bucc | -4.403 |
Revel | -4.251 |
merce | -4.113 |
Pri | -4.099 |
Token | x |
Token ID | 2124 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
emis | +0.491 |
Turing | +0.465 |
tar | +0.388 |
aver | +0.378 |
Turk | +0.378 |
Neg logit contributions | |
hered | -0.558 |
Bucc | -0.522 |
Revel | -0.506 |
Poly | -0.492 |
Pri | -0.491 |
Token | : |
Token ID | 25 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
hered | +0.217 |
Bucc | +0.203 |
Revel | +0.194 |
Poly | +0.190 |
brim | +0.187 |
Neg logit contributions | |
emis | -0.276 |
Turing | -0.264 |
tar | -0.227 |
Starg | -0.222 |
aver | -0.222 |
Token | US |
Token ID | 1294 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
hered | +4.131 |
Bucc | +3.910 |
Revel | +3.781 |
Poly | +3.763 |
brim | +3.573 |
Neg logit contributions | |
emis | -5.018 |
Turing | -4.657 |
tar | -4.056 |
agents | -3.931 |
aver | -3.899 |
Token | Department |
Token ID | 2732 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
hered | +2.713 |
Bucc | +2.495 |
Revel | +2.392 |
Poly | +2.370 |
Pri | +2.250 |
Neg logit contributions | |
emis | -4.353 |
Turing | -4.058 |
tar | -3.567 |
aver | -3.490 |
Starg | -3.487 |
Token | of |
Token ID | 286 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
hered | +1.495 |
Bucc | +1.386 |
Revel | +1.331 |
Poly | +1.312 |
Pri | +1.271 |
Neg logit contributions | |
emis | -2.111 |
Turing | -2.002 |
tar | -1.736 |
aver | -1.702 |
Turk | -1.696 |
Token | Transportation |
Token ID | 15198 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
hered | +1.940 |
Bucc | +1.840 |
Revel | +1.789 |
Poly | +1.773 |
Pri | +1.731 |
Neg logit contributions | |
emis | -1.402 |
Turing | -1.299 |
tar | -1.054 |
aver | -1.022 |
Turk | -1.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
hered | +2.274 |
Bucc | +2.109 |
Revel | +2.039 |
Poly | +2.027 |
Pri | +1.909 |
Neg logit contributions | |
emis | -3.476 |
Turing | -3.250 |
tar | -2.866 |
aver | -2.796 |
agents | -2.772 |
Token | National |
Token ID | 2351 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
hered | +5.894 |
Bucc | +5.472 |
Revel | +5.313 |
Poly | +5.300 |
brim | +4.846 |
Neg logit contributions | |
emis | -10.668 |
Turing | -9.776 |
tar | -8.743 |
agents | -8.710 |
Starg | -8.507 |
Token | Highway |
Token ID | 14914 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
hered | +1.159 |
Bucc | +1.080 |
Revel | +1.042 |
Poly | +1.024 |
Pri | +1.005 |
Neg logit contributions | |
emis | -1.297 |
Turing | -1.239 |
tar | -1.049 |
Turk | -1.028 |
aver | -1.027 |
Token | Traffic |
Token ID | 23624 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
emis | +1.112 |
Turing | +1.050 |
tar | +0.777 |
Turk | +0.760 |
Starg | +0.750 |
Neg logit contributions | |
hered | -2.266 |
Bucc | -2.147 |
Revel | -2.091 |
Poly | -2.066 |
brim | -2.053 |
Token | Safety |
Token ID | 11233 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
emis | +1.859 |
Turing | +1.751 |
aver | +1.333 |
tar | +1.332 |
Turk | +1.327 |
Neg logit contributions | |
hered | -3.065 |
Bucc | -2.888 |
Revel | -2.809 |
brim | -2.784 |
Poly | -2.778 |
Token | Administration |
Token ID | 8694 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
hered | +0.726 |
Bucc | +0.673 |
Revel | +0.647 |
Poly | +0.638 |
brim | +0.625 |
Neg logit contributions | |
emis | -0.893 |
Turing | -0.850 |
tar | -0.730 |
aver | -0.716 |
Turk | -0.714 |
Token | P |
Token ID | 47 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
hered | +0.793 |
Bucc | +0.724 |
Revel | +0.688 |
Poly | +0.675 |
Pri | +0.649 |
Neg logit contributions | |
emis | -1.527 |
Turing | -1.458 |
tar | -1.287 |
aver | -1.264 |
Turk | -1.261 |
Token | ORTS |
Token ID | 33002 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
hered | +1.402 |
Bucc | +1.298 |
Revel | +1.246 |
Poly | +1.227 |
Pri | +1.185 |
Neg logit contributions | |
emis | -2.053 |
Turing | -1.948 |
tar | -1.695 |
aver | -1.659 |
Turk | -1.655 |
Token | 100 |
Token ID | 1802 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
emis | +2.026 |
Turing | +1.956 |
Turk | +1.650 |
tar | +1.645 |
Starg | +1.624 |
Neg logit contributions | |
hered | -1.830 |
Bucc | -1.674 |
Revel | -1.618 |
Poly | -1.585 |
Pri | -1.584 |
Token | % |
Token ID | 4 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
emis | +2.118 |
Turing | +2.078 |
tar | +1.773 |
Starg | +1.760 |
Turk | +1.747 |
Neg logit contributions | |
hered | -1.803 |
Bucc | -1.666 |
Revel | -1.609 |
brim | -1.586 |
Poly | -1.559 |
Token | ON |
Token ID | 6177 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
hered | +0.773 |
Bucc | +0.715 |
Revel | +0.685 |
Poly | +0.674 |
Pri | +0.655 |
Neg logit contributions | |
emis | -1.113 |
Turing | -1.060 |
tar | -0.920 |
aver | -0.901 |
Turk | -0.901 |
Token | ALL |
Token ID | 11096 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hered | +0.655 |
Bucc | +0.606 |
Revel | +0.586 |
Poly | +0.573 |
Pri | +0.565 |
Neg logit contributions | |
emis | -0.748 |
Turing | -0.713 |
tar | -0.608 |
Turk | -0.598 |
Starg | -0.592 |
Token | PERSON |
Token ID | 46740 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
hered | +3.395 |
Bucc | +3.153 |
Poly | +3.013 |
Revel | +2.919 |
Pri | +2.537 |
Neg logit contributions | |
emis | -12.948 |
Turing | -12.013 |
agents | -10.928 |
uphem | -10.924 |
aver | -10.917 |
Token | EL |
Token ID | 3698 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
emis | +2.057 |
Turing | +1.964 |
tar | +1.690 |
Starg | +1.676 |
Turk | +1.673 |
Neg logit contributions | |
hered | -1.407 |
Bucc | -1.341 |
Revel | -1.264 |
brim | -1.249 |
Poly | -1.246 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
emis | +0.721 |
Turing | +0.689 |
tar | +0.595 |
aver | +0.582 |
Turk | +0.582 |
Neg logit contributions | |
hered | -0.533 |
Bucc | -0.491 |
Revel | -0.471 |
Poly | -0.463 |
Pri | -0.453 |
Token | : |
Token ID | 25 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
emis | +4.681 |
Turing | +4.474 |
tar | +3.807 |
Turk | +3.768 |
aver | +3.748 |
Neg logit contributions | |
hered | -4.217 |
Bucc | -3.903 |
Revel | -3.752 |
Poly | -3.670 |
brim | -3.636 |
Token | 0 |
Token ID | 657 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
emis | +1.487 |
Turing | +1.421 |
tar | +1.157 |
Turk | +1.136 |
aver | +1.131 |
Neg logit contributions | |
hered | -1.849 |
Bucc | -1.721 |
Revel | -1.665 |
Poly | -1.655 |
brim | -1.635 |
Token | ve |
Token ID | 303 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
emis | +1.941 |
Turing | +1.809 |
tar | +1.492 |
aver | +1.439 |
Starg | +1.401 |
Neg logit contributions | |
hered | -2.629 |
Bucc | -2.550 |
Revel | -2.456 |
Poly | -2.445 |
Pri | -2.367 |
Token | made |
Token ID | 925 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
emis | +1.650 |
Turing | +1.568 |
aver | +1.345 |
tar | +1.341 |
Turk | +1.299 |
Neg logit contributions | |
hered | -1.451 |
Bucc | -1.379 |
Revel | -1.341 |
Poly | -1.309 |
Pri | -1.280 |
Token | , |
Token ID | 11 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
emis | +2.474 |
Turing | +2.354 |
tar | +2.038 |
aver | +2.019 |
Turk | +1.996 |
Neg logit contributions | |
hered | -2.074 |
Bucc | -1.945 |
Revel | -1.865 |
Poly | -1.817 |
Pri | -1.793 |
Token | we |
Token ID | 356 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
emis | +0.664 |
Turing | +0.637 |
tar | +0.551 |
aver | +0.544 |
Turk | +0.539 |
Neg logit contributions | |
hered | -0.551 |
Bucc | -0.504 |
Revel | -0.486 |
Poly | -0.477 |
Pri | -0.469 |
Token | more |
Token ID | 517 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
emis | +2.084 |
Turing | +1.970 |
tar | +1.719 |
aver | +1.710 |
Turk | +1.675 |
Neg logit contributions | |
hered | -1.556 |
Bucc | -1.470 |
Revel | -1.409 |
Poly | -1.389 |
Pri | -1.324 |
Token | or |
Token ID | 393 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
emis | +0.671 |
Turing | +0.633 |
tar | +0.550 |
aver | +0.540 |
Turk | +0.534 |
Neg logit contributions | |
hered | -0.552 |
Bucc | -0.516 |
Revel | -0.494 |
Poly | -0.489 |
Pri | -0.478 |
Token | less |
Token ID | 1342 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
hered | +5.891 |
Bucc | +5.076 |
Poly | +5.061 |
Pri | +4.877 |
Revel | +4.872 |
Neg logit contributions | |
emis | -10.643 |
Turing | -9.981 |
agents | -8.661 |
Starg | -8.552 |
tar | -8.532 |
Token | know |
Token ID | 760 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
emis | +0.418 |
Turing | +0.396 |
aver | +0.340 |
tar | +0.336 |
Turk | +0.327 |
Neg logit contributions | |
hered | -0.404 |
Bucc | -0.383 |
Revel | -0.368 |
Poly | -0.364 |
Pri | -0.355 |
Token | where |
Token ID | 810 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
hered | +0.640 |
Bucc | +0.597 |
Revel | +0.575 |
Poly | +0.564 |
Pri | +0.552 |
Neg logit contributions | |
emis | -0.784 |
Turing | -0.749 |
tar | -0.644 |
aver | -0.631 |
Turk | -0.631 |
Token | we |
Token ID | 356 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
emis | +0.794 |
Turing | +0.764 |
tar | +0.660 |
aver | +0.650 |
Turk | +0.648 |
Neg logit contributions | |
hered | -0.656 |
Bucc | -0.604 |
Revel | -0.584 |
Poly | -0.570 |
Pri | -0.561 |
Token | are |
Token ID | 389 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
hered | +3.847 |
Bucc | +3.531 |
Revel | +3.392 |
Poly | +3.359 |
brim | +3.305 |
Neg logit contributions | |
emis | -5.016 |
Turing | -4.737 |
tar | -4.077 |
Starg | -3.982 |
aver | -3.961 |
Token | x |
Token ID | 2124 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
emis | +0.491 |
Turing | +0.465 |
tar | +0.388 |
aver | +0.378 |
Turk | +0.378 |
Neg logit contributions | |
hered | -0.558 |
Bucc | -0.522 |
Revel | -0.506 |
Poly | -0.492 |
Pri | -0.491 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
hered | +0.657 |
Bucc | +0.618 |
Revel | +0.592 |
Poly | +0.576 |
brim | +0.567 |
Neg logit contributions | |
emis | -0.927 |
Turing | -0.886 |
tar | -0.771 |
Starg | -0.751 |
aver | -0.749 |
Token | x |
Token ID | 87 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
emis | +3.493 |
Turing | +3.281 |
tar | +2.890 |
agents | +2.639 |
Starg | +2.622 |
Neg logit contributions | |
Bucc | -4.103 |
hered | -4.091 |
Revel | -3.949 |
brim | -3.859 |
merce | -3.760 |
Token | . |
Token ID | 13 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
emis | +0.652 |
Turing | +0.627 |
tar | +0.545 |
Starg | +0.529 |
Turk | +0.525 |
Neg logit contributions | |
hered | -0.496 |
Bucc | -0.474 |
Revel | -0.454 |
brim | -0.440 |
Poly | -0.436 |
Token | x |
Token ID | 87 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
hered | +2.275 |
Bucc | +2.115 |
Revel | +2.042 |
Poly | +2.026 |
Pri | +1.980 |
Neg logit contributions | |
emis | -2.506 |
Turing | -2.367 |
tar | -1.999 |
aver | -1.973 |
Turk | -1.972 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hered | +3.716 |
Bucc | +3.336 |
Poly | +3.193 |
Revel | +3.176 |
Pri | +3.155 |
Neg logit contributions | |
emis | -6.160 |
Turing | -5.842 |
Turk | -5.066 |
tar | -5.064 |
aver | -5.063 |
Token | 118 |
Token ID | 16817 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
hered | +5.466 |
Bucc | +4.940 |
Pri | +4.694 |
Poly | +4.571 |
Revel | +4.492 |
Neg logit contributions | |
emis | -10.858 |
Turing | -10.330 |
Gadget | -9.388 |
Turk | -9.224 |
Starg | -9.097 |
Token | 10 |
Token ID | 838 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
hered | +2.149 |
Bucc | +2.006 |
Revel | +1.932 |
Poly | +1.906 |
Pri | +1.852 |
Neg logit contributions | |
emis | -2.627 |
Turing | -2.484 |
tar | -2.132 |
aver | -2.085 |
Turk | -2.079 |
Token | 95 |
Token ID | 3865 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
hered | +0.388 |
Bucc | +0.364 |
Revel | +0.353 |
brim | +0.344 |
Poly | +0.342 |
Neg logit contributions | |
emis | -0.447 |
Turing | -0.431 |
tar | -0.369 |
Starg | -0.357 |
Turk | -0.355 |
Token | 607 |
Token ID | 31980 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
emis | +2.587 |
Turing | +2.504 |
tar | +2.162 |
Starg | +2.091 |
Turk | +2.082 |
Neg logit contributions | |
hered | -2.020 |
Bucc | -1.898 |
Revel | -1.860 |
brim | -1.786 |
Poly | -1.758 |
Token | x |
Token ID | 2124 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
emis | +1.144 |
Turing | +1.092 |
tar | +0.904 |
aver | +0.883 |
Turk | +0.880 |
Neg logit contributions | |
hered | -1.350 |
Bucc | -1.268 |
Revel | -1.229 |
Pri | -1.192 |
brim | -1.192 |
Token | government |
Token ID | 1230 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
hered | +2.099 |
Bucc | +1.958 |
Revel | +1.886 |
Poly | +1.860 |
Pri | +1.806 |
Neg logit contributions | |
emis | -2.619 |
Turing | -2.475 |
tar | -2.129 |
aver | -2.083 |
Turk | -2.074 |
Token | and |
Token ID | 290 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
hered | +1.747 |
Bucc | +1.625 |
Revel | +1.563 |
Poly | +1.541 |
Pri | +1.495 |
Neg logit contributions | |
emis | -2.307 |
Turing | -2.185 |
tar | -1.887 |
aver | -1.847 |
Turk | -1.841 |
Token | both |
Token ID | 1111 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
hered | +2.600 |
Bucc | +2.427 |
Revel | +2.343 |
Poly | +2.312 |
Pri | +2.244 |
Neg logit contributions | |
emis | -3.054 |
Turing | -2.863 |
tar | -2.452 |
aver | -2.388 |
Starg | -2.384 |
Token | an |
Token ID | 281 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
emis | +0.765 |
Turing | +0.733 |
tar | +0.625 |
Turk | +0.617 |
aver | +0.615 |
Neg logit contributions | |
hered | -0.713 |
Bucc | -0.677 |
Revel | -0.649 |
Poly | -0.639 |
Pri | -0.631 |
Token | upper |
Token ID | 6727 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
hered | +0.477 |
Bucc | +0.452 |
Revel | +0.437 |
Poly | +0.432 |
Pri | +0.424 |
Neg logit contributions | |
emis | -0.393 |
Turing | -0.369 |
tar | -0.304 |
aver | -0.297 |
Turk | -0.296 |
Token | and |
Token ID | 290 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
emis | +0.443 |
Turing | +0.421 |
tar | +0.359 |
Turk | +0.351 |
aver | +0.351 |
Neg logit contributions | |
hered | -0.404 |
Bucc | -0.377 |
Revel | -0.365 |
Poly | -0.358 |
Pri | -0.349 |
Token | lower |
Token ID | 2793 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
hered | +5.421 |
Bucc | +5.043 |
Revel | +4.701 |
Poly | +4.649 |
Pri | +4.479 |
Neg logit contributions | |
emis | -10.906 |
Turing | -10.346 |
Starg | -9.013 |
agents | -8.999 |
tar | -8.959 |
Token | house |
Token ID | 2156 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
emis | +0.623 |
Turing | +0.596 |
tar | +0.505 |
Turk | +0.498 |
aver | +0.495 |
Neg logit contributions | |
hered | -0.592 |
Bucc | -0.551 |
Revel | -0.533 |
Poly | -0.520 |
Pri | -0.511 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
hered | +0.398 |
Bucc | +0.370 |
Revel | +0.355 |
Poly | +0.350 |
Pri | +0.339 |
Neg logit contributions | |
emis | -0.542 |
Turing | -0.515 |
tar | -0.446 |
aver | -0.437 |
Turk | -0.436 |
Token | It |
Token ID | 632 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
hered | +0.261 |
Bucc | +0.244 |
Revel | +0.236 |
Poly | +0.232 |
brim | +0.231 |
Neg logit contributions | |
emis | -0.261 |
Turing | -0.250 |
tar | -0.212 |
Turk | -0.206 |
Starg | -0.206 |
Token | was |
Token ID | 373 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
emis | +1.446 |
Turing | +1.389 |
tar | +1.187 |
aver | +1.185 |
Turk | +1.149 |
Neg logit contributions | |
hered | -1.258 |
Bucc | -1.202 |
Revel | -1.148 |
Poly | -1.132 |
Pri | -1.110 |
Token | buf |
Token ID | 29325 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
hered | +4.670 |
Bucc | +4.314 |
Revel | +4.129 |
Poly | +4.086 |
brim | +4.025 |
Neg logit contributions | |
emis | -5.049 |
Turing | -4.816 |
Turk | -4.058 |
Starg | -4.009 |
aver | -3.974 |
Token | | |
Token ID | 930 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
hered | +1.618 |
Bucc | +1.417 |
Revel | +1.330 |
Poly | +1.308 |
Pri | +1.229 |
Neg logit contributions | |
emis | -4.529 |
Turing | -4.323 |
tar | -3.875 |
aver | -3.817 |
Turk | -3.815 |
Token | + |
Token ID | 1343 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
hered | +3.370 |
Bucc | +3.139 |
Poly | +3.070 |
Revel | +3.046 |
brim | +2.942 |
Neg logit contributions | |
emis | -4.566 |
Turing | -4.248 |
tar | -3.706 |
agents | -3.673 |
Turk | -3.636 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
emis | +0.485 |
Turing | +0.461 |
tar | +0.400 |
Starg | +0.389 |
aver | +0.386 |
Neg logit contributions | |
hered | -0.347 |
Bucc | -0.333 |
Revel | -0.318 |
Poly | -0.308 |
brim | -0.304 |
Token | --+ |
Token ID | 44785 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
emis | +3.420 |
Turing | +3.271 |
tar | +2.748 |
aver | +2.632 |
Turk | +2.608 |
Neg logit contributions | |
hered | -4.182 |
Bucc | -4.066 |
Revel | -4.022 |
brim | -3.845 |
Poly | -3.800 |
Token | | |
Token ID | 930 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
hered | +2.106 |
Bucc | +1.847 |
Poly | +1.737 |
Revel | +1.737 |
Pri | +1.599 |
Neg logit contributions | |
emis | -6.144 |
Turing | -5.830 |
tar | -5.244 |
aver | -5.171 |
agents | -5.161 |
Token | int |
Token ID | 493 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
hered | +6.363 |
Bucc | +6.020 |
Poly | +5.931 |
Revel | +5.722 |
brim | +5.612 |
Neg logit contributions | |
emis | -9.542 |
Turing | -8.809 |
agents | -7.963 |
tar | -7.786 |
Turk | -7.737 |
Token | f |
Token ID | 277 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
hered | +0.547 |
Bucc | +0.518 |
Revel | +0.502 |
Poly | +0.499 |
Pri | +0.487 |
Neg logit contributions | |
emis | -0.407 |
Turing | -0.378 |
tar | -0.309 |
Turk | -0.298 |
aver | -0.297 |
Token | d |
Token ID | 67 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
hered | +0.441 |
Bucc | +0.424 |
Revel | +0.409 |
Poly | +0.398 |
brim | +0.393 |
Neg logit contributions | |
emis | -0.470 |
Turing | -0.442 |
tar | -0.383 |
aver | -0.367 |
agents | -0.364 |
Token | | |
Token ID | 930 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
hered | +1.383 |
Bucc | +1.222 |
Revel | +1.146 |
Poly | +1.122 |
Pri | +1.061 |
Neg logit contributions | |
emis | -3.787 |
Turing | -3.626 |
tar | -3.246 |
aver | -3.197 |
Turk | -3.191 |
Token | + |
Token ID | 1343 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
hered | +3.859 |
Bucc | +3.525 |
Poly | +3.454 |
Revel | +3.441 |
brim | +3.209 |
Neg logit contributions | |
emis | -8.081 |
Turing | -7.593 |
tar | -6.783 |
agents | -6.735 |
Turk | -6.682 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Turing | +2.948 |
emis | +2.916 |
Turk | +2.462 |
Starg | +2.440 |
tar | +2.387 |
Neg logit contributions | |
hered | -2.966 |
Bucc | -2.724 |
merce | -2.647 |
brim | -2.638 |
Revel | -2.610 |
Token | United |
Token ID | 1578 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
emis | +1.700 |
Turing | +1.672 |
Turk | +1.411 |
tar | +1.387 |
Starg | +1.387 |
Neg logit contributions | |
hered | -1.543 |
Bucc | -1.422 |
Revel | -1.370 |
brim | -1.346 |
Pri | -1.338 |
Token | States |
Token ID | 1829 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
emis | +5.399 |
Turing | +5.184 |
Turk | +4.418 |
tar | +4.406 |
Starg | +4.403 |
Neg logit contributions | |
hered | -4.307 |
Bucc | -4.000 |
Revel | -3.845 |
brim | -3.726 |
Poly | -3.726 |
Token | 228 |
Token ID | 29041 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
Turing | +3.883 |
emis | +3.844 |
Turk | +3.254 |
Starg | +3.240 |
tar | +3.156 |
Neg logit contributions | |
hered | -3.615 |
Bucc | -3.356 |
merce | -3.283 |
brim | -3.205 |
Revel | -3.183 |
Token | 65 |
Token ID | 2996 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
Turing | +4.398 |
emis | +4.378 |
Turk | +3.691 |
Starg | +3.688 |
tar | +3.671 |
Neg logit contributions | |
hered | -4.632 |
Bucc | -4.280 |
merce | -4.181 |
brim | -4.163 |
Revel | -4.125 |
Token | Posts |
Token ID | 12043 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
Turing | +4.803 |
emis | +4.600 |
Starg | +3.960 |
Turk | +3.921 |
Alf | +3.744 |
Neg logit contributions | |
hered | -7.085 |
merce | -6.857 |
Bucc | -6.627 |
brim | -6.625 |
Revel | -6.266 |
Token | # |
Token ID | 1303 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
emis | +5.667 |
Turing | +5.469 |
tar | +4.477 |
Starg | +4.451 |
Turk | +4.384 |
Neg logit contributions | |
hered | -6.761 |
Bucc | -6.334 |
Revel | -6.118 |
Pri | -5.979 |
Poly | -5.968 |
Token | 13 |
Token ID | 1485 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
emis | +4.471 |
Turing | +4.242 |
tar | +3.742 |
Starg | +3.387 |
agents | +3.336 |
Neg logit contributions | |
Bucc | -6.342 |
hered | -6.116 |
Revel | -6.021 |
brim | -5.923 |
merce | -5.827 |
Token | On |
Token ID | 1550 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
emis | +1.472 |
Turing | +1.413 |
Starg | +1.171 |
tar | +1.169 |
Turk | +1.155 |
Neg logit contributions | |
hered | -1.570 |
Bucc | -1.456 |
Revel | -1.408 |
Poly | -1.385 |
Pri | -1.379 |
Token | September |
Token ID | 2693 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
emis | +2.442 |
Turing | +2.383 |
Starg | +2.036 |
tar | +2.010 |
Turk | +1.990 |
Neg logit contributions | |
hered | -1.926 |
Bucc | -1.858 |
Revel | -1.755 |
Pri | -1.693 |
Poly | -1.687 |
Token | 20 |
Token ID | 1160 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
emis | +3.654 |
Turing | +3.565 |
Turk | +2.916 |
tar | +2.891 |
Starg | +2.871 |
Neg logit contributions | |
hered | -4.213 |
Bucc | -4.025 |
Revel | -3.832 |
brim | -3.792 |
Pri | -3.753 |
Token | create |
Token ID | 2251 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
emis | +0.628 |
Turing | +0.594 |
tar | +0.506 |
aver | +0.503 |
Starg | +0.494 |
Neg logit contributions | |
hered | -0.588 |
Bucc | -0.553 |
Revel | -0.533 |
Poly | -0.524 |
Pri | -0.516 |
Token | nuclear |
Token ID | 4523 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
hered | +0.049 |
Bucc | +0.046 |
Revel | +0.044 |
Poly | +0.043 |
Pri | +0.042 |
Neg logit contributions | |
emis | -0.058 |
Turing | -0.055 |
tar | -0.047 |
aver | -0.046 |
Starg | -0.046 |
Token | - |
Token ID | 12 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
hered | +1.473 |
Bucc | +1.371 |
Revel | +1.318 |
Poly | +1.298 |
Pri | +1.261 |
Neg logit contributions | |
emis | -1.946 |
Turing | -1.845 |
tar | -1.593 |
aver | -1.560 |
Turk | -1.555 |
Token | free |
Token ID | 5787 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
emis | +0.970 |
Turing | +0.900 |
tar | +0.752 |
aver | +0.717 |
agents | +0.716 |
Neg logit contributions | |
hered | -1.266 |
Bucc | -1.219 |
Revel | -1.178 |
Poly | -1.161 |
brim | -1.131 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
emis | +3.595 |
Turing | +3.511 |
Turk | +3.010 |
Starg | +3.002 |
tar | +2.965 |
Neg logit contributions | |
hered | -3.381 |
Bucc | -3.189 |
Revel | -3.044 |
Pri | -2.995 |
Poly | -2.892 |
Token | peace |
Token ID | 4167 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
emis | +2.031 |
Turing | +1.953 |
tar | +1.628 |
aver | +1.624 |
Turk | +1.619 |
Neg logit contributions | |
hered | -2.138 |
Bucc | -2.023 |
Revel | -1.951 |
Pri | -1.896 |
Poly | -1.873 |
Token | zones |
Token ID | 14123 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
emis | +4.703 |
Turing | +4.471 |
tar | +3.762 |
aver | +3.682 |
Starg | +3.676 |
Neg logit contributions | |
hered | -5.099 |
Bucc | -4.963 |
Revel | -4.739 |
Poly | -4.637 |
brim | -4.593 |
Token | in |
Token ID | 287 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
emis | +2.679 |
Turing | +2.546 |
aver | +2.186 |
tar | +2.177 |
Turk | +2.144 |
Neg logit contributions | |
hered | -2.212 |
Bucc | -2.148 |
Revel | -2.050 |
Poly | -1.981 |
Pri | -1.977 |
Token | many |
Token ID | 867 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
emis | +1.197 |
Turing | +1.143 |
tar | +0.976 |
Turk | +0.974 |
aver | +0.973 |
Neg logit contributions | |
hered | -1.004 |
Bucc | -0.946 |
Revel | -0.906 |
Pri | -0.877 |
Poly | -0.873 |
Token | regions |
Token ID | 7652 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
hered | +0.768 |
Bucc | +0.718 |
Revel | +0.690 |
Poly | +0.671 |
Pri | +0.663 |
Neg logit contributions | |
emis | -0.998 |
Turing | -0.952 |
tar | -0.819 |
aver | -0.807 |
Turk | -0.806 |
Token | of |
Token ID | 286 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
emis | +2.074 |
Turing | +1.968 |
tar | +1.692 |
aver | +1.679 |
Turk | +1.669 |
Neg logit contributions | |
hered | -1.652 |
Bucc | -1.582 |
Revel | -1.518 |
Poly | -1.468 |
Pri | -1.457 |
Token | other |
Token ID | 584 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
emis | +0.208 |
Turing | +0.198 |
tar | +0.166 |
Turk | +0.163 |
aver | +0.163 |
Neg logit contributions | |
hered | -0.206 |
Bucc | -0.193 |
Revel | -0.187 |
Poly | -0.185 |
Pri | -0.182 |
Token | locker |
Token ID | 17355 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
hered | +2.707 |
Bucc | +2.554 |
Revel | +2.469 |
Poly | +2.444 |
brim | +2.376 |
Neg logit contributions | |
emis | -2.582 |
Turing | -2.401 |
tar | -2.022 |
aver | -1.964 |
agents | -1.955 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
emis | +1.810 |
Turing | +1.744 |
tar | +1.493 |
aver | +1.478 |
Turk | +1.467 |
Neg logit contributions | |
hered | -1.436 |
Bucc | -1.342 |
Revel | -1.287 |
Poly | -1.264 |
Pri | -1.249 |
Token | every |
Token ID | 790 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
hered | +0.113 |
Bucc | +0.105 |
Revel | +0.101 |
Poly | +0.099 |
Pri | +0.098 |
Neg logit contributions | |
emis | -0.133 |
Turing | -0.127 |
tar | -0.109 |
aver | -0.108 |
Turk | -0.107 |
Token | second |
Token ID | 1218 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
emis | +1.568 |
Turing | +1.521 |
tar | +1.261 |
Turk | +1.257 |
aver | +1.251 |
Neg logit contributions | |
hered | -1.574 |
Bucc | -1.463 |
Revel | -1.422 |
Poly | -1.392 |
Pri | -1.386 |
Token | locker |
Token ID | 17355 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
emis | +1.774 |
Turing | +1.718 |
tar | +1.440 |
Turk | +1.434 |
aver | +1.420 |
Neg logit contributions | |
hered | -1.830 |
Bucc | -1.709 |
Revel | -1.670 |
Poly | -1.634 |
Pri | -1.627 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
emis | +5.260 |
Turing | +5.156 |
aver | +4.395 |
tar | +4.344 |
Turk | +4.312 |
Neg logit contributions | |
hered | -4.806 |
Bucc | -4.478 |
Revel | -4.299 |
Pri | -4.277 |
Poly | -4.237 |
Token | Third |
Token ID | 10467 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
emis | +1.195 |
Turing | +1.177 |
Turk | +0.966 |
tar | +0.963 |
Starg | +0.958 |
Neg logit contributions | |
hered | -1.347 |
Bucc | -1.236 |
brim | -1.203 |
Revel | -1.197 |
Pri | -1.171 |
Token | kid |
Token ID | 5141 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
hered | +0.780 |
Bucc | +0.714 |
Revel | +0.683 |
Poly | +0.670 |
Pri | +0.649 |
Neg logit contributions | |
emis | -1.368 |
Turing | -1.308 |
tar | -1.151 |
Turk | -1.129 |
aver | -1.129 |
Token | comes |
Token ID | 2058 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
emis | +0.648 |
Turing | +0.620 |
aver | +0.543 |
tar | +0.540 |
Turk | +0.539 |
Neg logit contributions | |
hered | -0.440 |
Bucc | -0.402 |
Revel | -0.385 |
Poly | -0.376 |
Pri | -0.374 |
Token | by |
Token ID | 416 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
emis | +1.527 |
Turing | +1.475 |
tar | +1.281 |
aver | +1.255 |
Turk | +1.254 |
Neg logit contributions | |
hered | -1.321 |
Bucc | -1.231 |
Revel | -1.193 |
Pri | -1.163 |
Poly | -1.160 |
Token | the |
Token ID | 262 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
emis | +2.942 |
Turing | +2.869 |
Turk | +2.397 |
aver | +2.390 |
tar | +2.374 |
Neg logit contributions | |
hered | -2.562 |
Bucc | -2.428 |
Revel | -2.334 |
Poly | -2.283 |
Pri | -2.281 |
Token | patient |
Token ID | 5827 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
emis | +3.172 |
Turing | +3.105 |
Turk | +2.572 |
aver | +2.553 |
Starg | +2.532 |
Neg logit contributions | |
hered | -3.127 |
Bucc | -2.939 |
Revel | -2.901 |
Poly | -2.820 |
Pri | -2.811 |
Token | � |
Token ID | 447 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
emis | +2.816 |
Turing | +2.717 |
Turk | +2.339 |
tar | +2.338 |
aver | +2.327 |
Neg logit contributions | |
hered | -2.108 |
Bucc | -1.951 |
Revel | -1.892 |
Poly | -1.839 |
Pri | -1.824 |
Token | � |
Token ID | 247 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
hered | +0.252 |
Bucc | +0.241 |
Revel | +0.231 |
Poly | +0.228 |
Pri | +0.224 |
Neg logit contributions | |
emis | -0.244 |
Turing | -0.228 |
tar | -0.192 |
Turk | -0.189 |
aver | -0.188 |
Token | s |
Token ID | 82 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
emis | +3.535 |
Turing | +3.395 |
tar | +2.947 |
Turk | +2.828 |
aver | +2.814 |
Neg logit contributions | |
hered | -2.873 |
Bucc | -2.726 |
Revel | -2.655 |
Poly | -2.567 |
Pri | -2.541 |
Token | brain |
Token ID | 3632 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
emis | +2.925 |
Turing | +2.859 |
Turk | +2.371 |
aver | +2.363 |
Starg | +2.342 |
Neg logit contributions | |
hered | -2.903 |
Bucc | -2.717 |
Revel | -2.676 |
Pri | -2.592 |
Poly | -2.578 |
Token | causing |
Token ID | 6666 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
emis | +5.634 |
Turing | +5.510 |
tar | +4.631 |
Turk | +4.605 |
aver | +4.544 |
Neg logit contributions | |
hered | -4.896 |
Bucc | -4.518 |
Revel | -4.390 |
Pri | -4.338 |
Poly | -4.297 |
Token | them |
Token ID | 606 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
hered | +1.851 |
Bucc | +1.729 |
Revel | +1.667 |
Poly | +1.646 |
Pri | +1.598 |
Neg logit contributions | |
emis | -2.192 |
Turing | -2.068 |
tar | -1.775 |
aver | -1.731 |
Turk | -1.726 |
Token | , |
Token ID | 11 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
hered | +0.111 |
Bucc | +0.103 |
Revel | +0.099 |
Poly | +0.097 |
Pri | +0.095 |
Neg logit contributions | |
emis | -0.153 |
Turing | -0.145 |
tar | -0.126 |
aver | -0.123 |
Turk | -0.123 |
Token | Chang |
Token ID | 22597 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
hered | +0.459 |
Bucc | +0.427 |
Revel | +0.412 |
Poly | +0.405 |
Pri | +0.396 |
Neg logit contributions | |
emis | -0.561 |
Turing | -0.533 |
tar | -0.457 |
Turk | -0.448 |
aver | -0.446 |
Token | removes |
Token ID | 20694 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
hered | +1.639 |
Bucc | +1.531 |
Revel | +1.479 |
Poly | +1.456 |
Pri | +1.416 |
Neg logit contributions | |
emis | -1.964 |
Turing | -1.853 |
tar | -1.592 |
aver | -1.559 |
Turk | -1.553 |
Token | ini |
Token ID | 5362 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
emis | +0.985 |
Turing | +0.925 |
tar | +0.803 |
aver | +0.770 |
agents | +0.761 |
Neg logit contributions | |
hered | -0.982 |
Bucc | -0.943 |
Revel | -0.915 |
Poly | -0.890 |
brim | -0.877 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
hered | +2.719 |
Bucc | +2.512 |
Revel | +2.412 |
Poly | +2.410 |
Pri | +2.317 |
Neg logit contributions | |
emis | -3.912 |
Turing | -3.676 |
tar | -3.194 |
aver | -3.129 |
agents | -3.114 |
Token | A |
Token ID | 317 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
emis | +1.053 |
Turing | +1.028 |
tar | +0.868 |
Turk | +0.862 |
Starg | +0.859 |
Neg logit contributions | |
hered | -0.905 |
Bucc | -0.828 |
Revel | -0.801 |
brim | -0.792 |
Pri | -0.777 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
emis | +2.751 |
Turing | +2.606 |
tar | +2.253 |
aver | +2.207 |
Turk | +2.205 |
Neg logit contributions | |
hered | -2.015 |
Bucc | -1.876 |
Revel | -1.804 |
Poly | -1.774 |
Pri | -1.721 |
Token | D |
Token ID | 360 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
emis | +1.669 |
Turing | +1.584 |
tar | +1.369 |
aver | +1.341 |
Turk | +1.337 |
Neg logit contributions | |
hered | -1.234 |
Bucc | -1.146 |
Revel | -1.102 |
Poly | -1.085 |
Pri | -1.054 |
Token | ., |
Token ID | 1539 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
emis | +1.601 |
Turing | +1.510 |
tar | +1.285 |
aver | +1.255 |
Turk | +1.251 |
Neg logit contributions | |
hered | -1.449 |
Bucc | -1.358 |
Revel | -1.310 |
Poly | -1.294 |
Pri | -1.260 |
Token | Long |
Token ID | 5882 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
emis | +5.648 |
Turing | +5.511 |
Turk | +4.736 |
Starg | +4.600 |
tar | +4.565 |
Neg logit contributions | |
hered | -5.052 |
Bucc | -4.390 |
brim | -4.382 |
merce | -4.374 |
Pri | -4.300 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
hered | +1.295 |
Bucc | +1.218 |
Revel | +1.178 |
Poly | +1.165 |
Pri | +1.136 |
Neg logit contributions | |
emis | -1.253 |
Turing | -1.178 |
tar | -0.988 |
aver | -0.966 |
Turk | -0.962 |
Token | J |
Token ID | 449 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Turing | +2.217 |
emis | +2.185 |
Turk | +1.863 |
Starg | +1.861 |
tar | +1.820 |
Neg logit contributions | |
hered | -2.017 |
Bucc | -1.810 |
merce | -1.796 |
brim | -1.775 |
Revel | -1.744 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
emis | +1.022 |
Turing | +0.973 |
tar | +0.843 |
aver | +0.826 |
Starg | +0.823 |
Neg logit contributions | |
hered | -0.738 |
Bucc | -0.685 |
Revel | -0.657 |
Poly | -0.649 |
Pri | -0.629 |
Token | D |
Token ID | 360 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
hered | +0.853 |
Bucc | +0.786 |
Revel | +0.758 |
Poly | +0.743 |
brim | +0.737 |
Neg logit contributions | |
emis | -1.049 |
Turing | -1.007 |
tar | -0.859 |
Turk | -0.846 |
Starg | -0.845 |
Token | % |
Token ID | 4 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
emis | +1.063 |
Turing | +1.009 |
tar | +0.873 |
aver | +0.863 |
Turk | +0.859 |
Neg logit contributions | |
hered | -0.755 |
Bucc | -0.699 |
Revel | -0.675 |
Poly | -0.658 |
Pri | -0.648 |
Token | of |
Token ID | 286 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
hered | +0.871 |
Bucc | +0.806 |
Revel | +0.773 |
Poly | +0.765 |
Pri | +0.725 |
Neg logit contributions | |
emis | -1.324 |
Turing | -1.250 |
tar | -1.096 |
Starg | -1.071 |
Turk | -1.068 |
Token | the |
Token ID | 262 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
hered | +1.484 |
Bucc | +1.383 |
Revel | +1.331 |
Poly | +1.311 |
Pri | +1.279 |
Neg logit contributions | |
emis | -1.834 |
Turing | -1.740 |
tar | -1.491 |
aver | -1.463 |
Turk | -1.458 |
Token | company |
Token ID | 1664 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
hered | +1.625 |
Bucc | +1.514 |
Revel | +1.459 |
Poly | +1.434 |
Pri | +1.405 |
Neg logit contributions | |
emis | -1.942 |
Turing | -1.846 |
tar | -1.575 |
aver | -1.552 |
Turk | -1.544 |
Token | 's |
Token ID | 338 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
emis | +0.175 |
Turing | +0.166 |
tar | +0.144 |
aver | +0.142 |
Turk | +0.141 |
Neg logit contributions | |
hered | -0.124 |
Bucc | -0.114 |
Revel | -0.110 |
Poly | -0.108 |
Pri | -0.105 |
Token | enroll |
Token ID | 14627 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
hered | +0.587 |
Bucc | +0.546 |
Revel | +0.526 |
Poly | +0.516 |
Pri | +0.512 |
Neg logit contributions | |
emis | -0.652 |
Turing | -0.624 |
tar | -0.524 |
aver | -0.523 |
Turk | -0.520 |
Token | ments |
Token ID | 902 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
emis | +3.096 |
Turing | +2.916 |
tar | +2.443 |
agents | +2.398 |
Turk | +2.377 |
Neg logit contributions | |
hered | -3.236 |
Bucc | -3.094 |
Revel | -2.986 |
brim | -2.916 |
Poly | -2.906 |
Token | allegedly |
Token ID | 7910 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
hered | +0.042 |
Bucc | +0.039 |
Revel | +0.038 |
Poly | +0.037 |
Pri | +0.037 |
Neg logit contributions | |
emis | -0.053 |
Turing | -0.050 |
tar | -0.043 |
aver | -0.043 |
Turk | -0.042 |
Token | involved |
Token ID | 2950 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
hered | +1.149 |
Bucc | +1.077 |
Revel | +1.039 |
Poly | +1.024 |
Pri | +1.000 |
Neg logit contributions | |
emis | -1.293 |
Turing | -1.224 |
tar | -1.042 |
aver | -1.025 |
Turk | -1.015 |
Token | overriding |
Token ID | 44987 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
hered | +0.763 |
Bucc | +0.710 |
Revel | +0.681 |
Poly | +0.668 |
Pri | +0.662 |
Neg logit contributions | |
emis | -0.904 |
Turing | -0.867 |
tar | -0.733 |
aver | -0.729 |
Turk | -0.725 |
Token | a |
Token ID | 257 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
hered | +1.027 |
Bucc | +0.960 |
Revel | +0.922 |
Poly | +0.904 |
Pri | +0.894 |
Neg logit contributions | |
emis | -1.214 |
Turing | -1.167 |
tar | -0.991 |
aver | -0.977 |
Turk | -0.976 |
Token | of |
Token ID | 286 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
hered | +0.817 |
Bucc | +0.759 |
Revel | +0.731 |
Poly | +0.721 |
Pri | +0.707 |
Neg logit contributions | |
emis | -0.988 |
Turing | -0.936 |
tar | -0.802 |
Turk | -0.788 |
aver | -0.786 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
emis | +1.279 |
Turing | +1.224 |
tar | +1.045 |
Turk | +1.031 |
aver | +1.023 |
Neg logit contributions | |
hered | -1.081 |
Bucc | -1.013 |
Revel | -0.971 |
Poly | -0.953 |
Pri | -0.942 |
Token | defensive |
Token ID | 6110 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
emis | +0.926 |
Turing | +0.886 |
tar | +0.750 |
Turk | +0.742 |
Starg | +0.737 |
Neg logit contributions | |
hered | -0.813 |
Bucc | -0.765 |
Revel | -0.734 |
Poly | -0.723 |
Pri | -0.721 |
Token | facet |
Token ID | 39144 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
emis | +0.240 |
Turing | +0.232 |
tar | +0.196 |
Turk | +0.193 |
aver | +0.193 |
Neg logit contributions | |
hered | -0.222 |
Bucc | -0.207 |
Revel | -0.197 |
Pri | -0.195 |
Poly | -0.194 |
Token | to |
Token ID | 284 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
hered | +0.050 |
Bucc | +0.047 |
Revel | +0.045 |
Poly | +0.044 |
Pri | +0.044 |
Neg logit contributions | |
emis | -0.063 |
Turing | -0.059 |
tar | -0.051 |
Turk | -0.050 |
aver | -0.050 |
Token | his |
Token ID | 465 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
emis | +1.651 |
Turing | +1.576 |
Turk | +1.331 |
aver | +1.325 |
tar | +1.322 |
Neg logit contributions | |
hered | -1.516 |
Bucc | -1.403 |
Revel | -1.353 |
Poly | -1.321 |
Pri | -1.314 |
Token | game |
Token ID | 983 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
emis | +0.943 |
Turing | +0.904 |
Turk | +0.763 |
tar | +0.759 |
aver | +0.753 |
Neg logit contributions | |
hered | -0.830 |
Bucc | -0.770 |
Revel | -0.749 |
Poly | -0.731 |
Pri | -0.729 |
Token | to |
Token ID | 284 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
emis | +3.992 |
Turing | +3.857 |
tar | +3.286 |
Turk | +3.237 |
aver | +3.193 |
Neg logit contributions | |
hered | -3.644 |
Bucc | -3.418 |
Revel | -3.318 |
Poly | -3.224 |
Pri | -3.215 |
Token | truly |
Token ID | 4988 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
emis | +2.727 |
Turing | +2.585 |
aver | +2.188 |
tar | +2.158 |
Turk | +2.153 |
Neg logit contributions | |
hered | -2.688 |
Bucc | -2.494 |
Revel | -2.403 |
Poly | -2.344 |
Pri | -2.341 |
Token | be |
Token ID | 307 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
emis | +2.010 |
Turing | +1.901 |
aver | +1.606 |
tar | +1.604 |
Turk | +1.572 |
Neg logit contributions | |
hered | -1.883 |
Bucc | -1.765 |
Revel | -1.697 |
Poly | -1.661 |
Pri | -1.655 |
Token | considered |
Token ID | 3177 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
emis | +1.517 |
Turing | +1.458 |
aver | +1.216 |
Turk | +1.214 |
tar | +1.211 |
Neg logit contributions | |
hered | -1.387 |
Bucc | -1.304 |
Revel | -1.253 |
Poly | -1.233 |
Pri | -1.216 |
Token | � |
Token ID | 251 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
hered | +0.023 |
Bucc | +0.022 |
Revel | +0.021 |
Poly | +0.021 |
Pri | +0.020 |
Neg logit contributions | |
emis | -0.024 |
Turing | -0.022 |
tar | -0.019 |
aver | -0.018 |
Turk | -0.018 |
Token | Cl |
Token ID | 2601 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
emis | +1.225 |
Turing | +1.162 |
tar | +0.994 |
Turk | +0.973 |
Starg | +0.964 |
Neg logit contributions | |
hered | -1.122 |
Bucc | -1.053 |
Revel | -1.008 |
Poly | -1.000 |
brim | -0.982 |
Token | arks |
Token ID | 5558 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
emis | +0.497 |
Turing | +0.448 |
tar | +0.347 |
aver | +0.331 |
Turk | +0.329 |
Neg logit contributions | |
hered | -0.929 |
Bucc | -0.893 |
Revel | -0.868 |
Poly | -0.858 |
brim | -0.841 |
Token | on |
Token ID | 261 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
emis | +0.957 |
Turing | +0.899 |
tar | +0.787 |
aver | +0.767 |
Turk | +0.755 |
Neg logit contributions | |
hered | -0.773 |
Bucc | -0.727 |
Revel | -0.690 |
Poly | -0.661 |
brim | -0.652 |
Token | added |
Token ID | 2087 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
emis | +1.926 |
Turing | +1.820 |
tar | +1.590 |
aver | +1.587 |
Turk | +1.561 |
Neg logit contributions | |
hered | -1.328 |
Bucc | -1.235 |
Revel | -1.182 |
Poly | -1.164 |
Pri | -1.125 |
Token | : |
Token ID | 25 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
emis | +2.088 |
Turing | +1.984 |
tar | +1.698 |
Turk | +1.680 |
aver | +1.671 |
Neg logit contributions | |
hered | -1.729 |
Bucc | -1.622 |
Revel | -1.543 |
Poly | -1.537 |
Pri | -1.503 |
Token | � |
Token ID | 564 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
emis | +1.036 |
Turing | +0.983 |
tar | +0.847 |
Turk | +0.828 |
aver | +0.824 |
Neg logit contributions | |
hered | -0.826 |
Bucc | -0.772 |
Revel | -0.741 |
Poly | -0.731 |
brim | -0.710 |
Token | � |
Token ID | 250 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
hered | +0.965 |
Bucc | +0.913 |
Revel | +0.879 |
Poly | +0.866 |
Pri | +0.849 |
Neg logit contributions | |
emis | -0.919 |
Turing | -0.865 |
tar | -0.728 |
aver | -0.709 |
Turk | -0.708 |
Token | He |
Token ID | 1544 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
hered | +0.970 |
Bucc | +0.915 |
Revel | +0.882 |
Poly | +0.870 |
brim | +0.847 |
Neg logit contributions | |
emis | -1.082 |
Turing | -1.020 |
tar | -0.875 |
Turk | -0.846 |
aver | -0.845 |
Token | will |
Token ID | 481 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
hered | +0.296 |
Bucc | +0.278 |
Revel | +0.267 |
Poly | +0.263 |
Pri | +0.255 |
Neg logit contributions | |
emis | -0.380 |
Turing | -0.358 |
tar | -0.312 |
aver | -0.306 |
Turk | -0.303 |
Token | be |
Token ID | 307 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
emis | +0.351 |
Turing | +0.334 |
tar | +0.284 |
aver | +0.278 |
Turk | +0.276 |
Neg logit contributions | |
hered | -0.333 |
Bucc | -0.311 |
Revel | -0.298 |
Poly | -0.295 |
Pri | -0.290 |
Token | � |
Token ID | 251 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
emis | +1.750 |
Turing | +1.641 |
tar | +1.356 |
Turk | +1.333 |
aver | +1.328 |
Neg logit contributions | |
hered | -2.018 |
Bucc | -1.919 |
Revel | -1.837 |
Poly | -1.820 |
Pri | -1.790 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
hered | +0.175 |
Bucc | +0.163 |
Revel | +0.156 |
Poly | +0.153 |
Pri | +0.150 |
Neg logit contributions | |
emis | -0.214 |
Turing | -0.204 |
tar | -0.177 |
aver | -0.172 |
Turk | -0.171 |
Token | the |
Token ID | 262 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
emis | +1.214 |
Turing | +1.158 |
tar | +0.990 |
aver | +0.985 |
Turk | +0.973 |
Neg logit contributions | |
hered | -1.107 |
Bucc | -1.027 |
Revel | -0.979 |
Poly | -0.964 |
Pri | -0.952 |
Token | price |
Token ID | 2756 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
hered | +0.184 |
Bucc | +0.171 |
Revel | +0.162 |
Pri | +0.160 |
Poly | +0.159 |
Neg logit contributions | |
emis | -0.213 |
Turing | -0.204 |
tar | -0.174 |
aver | -0.172 |
Turk | -0.171 |
Token | of |
Token ID | 286 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
emis | +2.789 |
Turing | +2.690 |
tar | +2.317 |
aver | +2.315 |
Turk | +2.270 |
Neg logit contributions | |
hered | -2.354 |
Bucc | -2.223 |
Revel | -2.091 |
Poly | -2.056 |
Pri | -2.047 |
Token | established |
Token ID | 4920 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
emis | +1.486 |
Turing | +1.419 |
tar | +1.174 |
aver | +1.159 |
Turk | +1.145 |
Neg logit contributions | |
hered | -1.722 |
Bucc | -1.631 |
Revel | -1.570 |
Pri | -1.550 |
Poly | -1.548 |
Token | dwellings |
Token ID | 50078 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
emis | +0.854 |
Turing | +0.817 |
tar | +0.715 |
aver | +0.702 |
Turk | +0.699 |
Neg logit contributions | |
hered | -0.537 |
Bucc | -0.498 |
Revel | -0.475 |
Poly | -0.464 |
Pri | -0.455 |
Token | gets |
Token ID | 3011 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
emis | +4.493 |
Turing | +4.296 |
aver | +3.782 |
tar | +3.708 |
Turk | +3.648 |
Neg logit contributions | |
hered | -3.732 |
Bucc | -3.548 |
Revel | -3.346 |
Poly | -3.308 |
Pri | -3.286 |
Token | a |
Token ID | 257 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
emis | +2.385 |
Turing | +2.294 |
aver | +1.933 |
Turk | +1.930 |
tar | +1.916 |
Neg logit contributions | |
hered | -2.107 |
Bucc | -2.028 |
Revel | -1.926 |
Pri | -1.889 |
Poly | -1.883 |
Token | boost |
Token ID | 5750 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
emis | +0.383 |
Turing | +0.366 |
tar | +0.311 |
Turk | +0.306 |
Starg | +0.305 |
Neg logit contributions | |
hered | -0.322 |
Bucc | -0.305 |
Revel | -0.294 |
Poly | -0.287 |
Pri | -0.285 |
Token | , |
Token ID | 11 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
hered | +0.132 |
Bucc | +0.123 |
Revel | +0.118 |
Poly | +0.116 |
Pri | +0.113 |
Neg logit contributions | |
emis | -0.172 |
Turing | -0.163 |
tar | -0.141 |
aver | -0.138 |
Turk | -0.138 |
Token | enough |
Token ID | 1576 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
hered | +1.181 |
Bucc | +1.104 |
Revel | +1.059 |
Poly | +1.042 |
Pri | +1.027 |
Neg logit contributions | |
emis | -1.437 |
Turing | -1.372 |
tar | -1.182 |
aver | -1.161 |
Turk | -1.155 |
Token | to |
Token ID | 284 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
hered | +0.555 |
Bucc | +0.522 |
Revel | +0.499 |
Poly | +0.490 |
Pri | +0.482 |
Neg logit contributions | |
emis | -0.673 |
Turing | -0.639 |
tar | -0.553 |
aver | -0.543 |
Turk | -0.538 |
Token | accommodate |
Token ID | 15550 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
hered | +0.881 |
Bucc | +0.824 |
Revel | +0.792 |
Poly | +0.786 |
Pri | +0.771 |
Neg logit contributions | |
emis | -0.907 |
Turing | -0.860 |
tar | -0.726 |
aver | -0.716 |
Starg | -0.709 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
emis | +0.552 |
Turing | +0.531 |
Turk | +0.447 |
tar | +0.446 |
Starg | +0.445 |
Neg logit contributions | |
hered | -0.470 |
Bucc | -0.439 |
Revel | -0.415 |
Poly | -0.409 |
Pri | -0.409 |
Token | first |
Token ID | 717 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
emis | +0.115 |
Turing | +0.111 |
tar | +0.093 |
Turk | +0.093 |
Starg | +0.093 |
Neg logit contributions | |
hered | -0.099 |
Bucc | -0.092 |
Revel | -0.087 |
Poly | -0.085 |
Pri | -0.085 |
Token | Falling |
Token ID | 42914 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
hered | +0.746 |
Bucc | +0.698 |
Revel | +0.670 |
Poly | +0.659 |
Pri | +0.649 |
Neg logit contributions | |
emis | -0.847 |
Turing | -0.807 |
tar | -0.686 |
Turk | -0.673 |
aver | -0.672 |
Token | water |
Token ID | 7050 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
emis | +1.709 |
Turing | +1.655 |
tar | +1.426 |
agents | +1.376 |
Starg | +1.372 |
Neg logit contributions | |
hered | -1.368 |
Bucc | -1.300 |
Revel | -1.228 |
Pri | -1.205 |
Poly | -1.189 |
Token | tour |
Token ID | 4205 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
emis | +3.358 |
Turing | +3.280 |
Turk | +2.811 |
tar | +2.796 |
aver | +2.747 |
Neg logit contributions | |
hered | -2.976 |
Bucc | -2.708 |
Revel | -2.547 |
Pri | -2.533 |
Poly | -2.495 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
hered | +0.348 |
Bucc | +0.326 |
Revel | +0.313 |
Poly | +0.307 |
Pri | +0.300 |
Neg logit contributions | |
emis | -0.416 |
Turing | -0.393 |
tar | -0.338 |
aver | -0.331 |
Turk | -0.330 |
Token | is |
Token ID | 318 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
hered | +1.500 |
Bucc | +1.401 |
Revel | +1.344 |
Poly | +1.328 |
Pri | +1.296 |
Neg logit contributions | |
emis | -1.815 |
Turing | -1.719 |
tar | -1.477 |
aver | -1.450 |
Turk | -1.439 |
Token | superb |
Token ID | 21840 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
hered | +0.154 |
Bucc | +0.145 |
Revel | +0.138 |
Poly | +0.136 |
Pri | +0.134 |
Neg logit contributions | |
emis | -0.176 |
Turing | -0.168 |
tar | -0.142 |
aver | -0.140 |
Turk | -0.140 |
Token | ). |
Token ID | 737 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
hered | +1.606 |
Bucc | +1.501 |
Revel | +1.444 |
Poly | +1.421 |
Pri | +1.383 |
Neg logit contributions | |
emis | -2.035 |
Turing | -1.929 |
tar | -1.660 |
aver | -1.628 |
Turk | -1.618 |
Token | In |
Token ID | 554 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
hered | +2.037 |
Bucc | +1.910 |
Revel | +1.845 |
Poly | +1.821 |
Pri | +1.777 |
Neg logit contributions | |
emis | -2.127 |
Turing | -2.008 |
tar | -1.699 |
aver | -1.657 |
Turk | -1.654 |
Token | the |
Token ID | 262 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
hered | +1.496 |
Bucc | +1.401 |
Revel | +1.348 |
Poly | +1.331 |
Pri | +1.298 |
Neg logit contributions | |
emis | -1.705 |
Turing | -1.613 |
tar | -1.374 |
aver | -1.346 |
Turk | -1.341 |
Token | end |
Token ID | 886 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
hered | +2.058 |
Bucc | +1.935 |
Revel | +1.870 |
Poly | +1.847 |
Pri | +1.798 |
Neg logit contributions | |
emis | -2.141 |
Turing | -2.014 |
tar | -1.706 |
aver | -1.663 |
Turk | -1.658 |
Token | , |
Token ID | 11 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
hered | +0.390 |
Bucc | +0.363 |
Revel | +0.349 |
Poly | +0.344 |
Pri | +0.334 |
Neg logit contributions | |
emis | -0.518 |
Turing | -0.490 |
tar | -0.423 |
aver | -0.415 |
Turk | -0.414 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
hered | +0.543 |
Bucc | +0.502 |
Revel | +0.483 |
Poly | +0.475 |
Pri | +0.466 |
Neg logit contributions | |
emis | -0.657 |
Turing | -0.624 |
tar | -0.535 |
aver | -0.523 |
Starg | -0.521 |
Token | Premiere |
Token ID | 44151 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
hered | +0.972 |
Bucc | +0.903 |
Revel | +0.873 |
Poly | +0.861 |
Pri | +0.844 |
Neg logit contributions | |
emis | -1.022 |
Turing | -0.967 |
tar | -0.819 |
Starg | -0.800 |
aver | -0.800 |
Token | won |
Token ID | 1839 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
emis | +1.237 |
Turing | +1.180 |
tar | +1.008 |
aver | +1.001 |
Turk | +0.989 |
Neg logit contributions | |
hered | -1.069 |
Bucc | -0.990 |
Revel | -0.948 |
Poly | -0.927 |
Pri | -0.917 |
Token | out |
Token ID | 503 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
emis | +1.740 |
Turing | +1.668 |
tar | +1.439 |
aver | +1.419 |
Turk | +1.411 |
Neg logit contributions | |
hered | -1.276 |
Bucc | -1.207 |
Revel | -1.150 |
Poly | -1.126 |
brim | -1.106 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
emis | +1.419 |
Turing | +1.369 |
tar | +1.170 |
aver | +1.152 |
Starg | +1.131 |
Neg logit contributions | |
hered | -1.232 |
Bucc | -1.166 |
Revel | -1.115 |
Poly | -1.090 |
brim | -1.072 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
hered | +0.193 |
Bucc | +0.179 |
Revel | +0.173 |
Poly | +0.170 |
brim | +0.170 |
Neg logit contributions | |
emis | -0.195 |
Turing | -0.187 |
tar | -0.157 |
Starg | -0.154 |
Turk | -0.154 |
Token | � |
Token ID | 247 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
hered | +0.453 |
Bucc | +0.428 |
Revel | +0.413 |
Poly | +0.407 |
Pri | +0.398 |
Neg logit contributions | |
emis | -0.453 |
Turing | -0.425 |
tar | -0.360 |
aver | -0.353 |
Turk | -0.352 |
Token | s |
Token ID | 82 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
emis | +0.330 |
Turing | +0.315 |
tar | +0.275 |
Turk | +0.266 |
aver | +0.265 |
Neg logit contributions | |
hered | -0.249 |
Bucc | -0.232 |
Revel | -0.223 |
Poly | -0.218 |
brim | -0.212 |
Token | deputy |
Token ID | 10636 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
hered | +2.885 |
Bucc | +2.704 |
Revel | +2.602 |
Poly | +2.578 |
Pri | +2.488 |
Neg logit contributions | |
emis | -3.564 |
Turing | -3.350 |
tar | -2.884 |
aver | -2.811 |
Starg | -2.806 |
Token | critic |
Token ID | 4014 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
emis | +1.773 |
Turing | +1.689 |
tar | +1.478 |
Turk | +1.460 |
aver | +1.457 |
Neg logit contributions | |
hered | -1.294 |
Bucc | -1.197 |
Revel | -1.142 |
Poly | -1.120 |
Pri | -1.096 |
Token | for |
Token ID | 329 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
hered | +0.967 |
Bucc | +0.898 |
Revel | +0.862 |
Poly | +0.850 |
Pri | +0.824 |
Neg logit contributions | |
emis | -1.335 |
Turing | -1.266 |
tar | -1.097 |
aver | -1.075 |
Turk | -1.071 |
Token | democratic |
Token ID | 10518 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
hered | +1.267 |
Bucc | +1.180 |
Revel | +1.136 |
Poly | +1.116 |
Pri | +1.090 |
Neg logit contributions | |
emis | -1.573 |
Turing | -1.493 |
tar | -1.283 |
aver | -1.258 |
Turk | -1.256 |
Token | reform |
Token ID | 4975 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
hered | +2.149 |
Bucc | +1.970 |
Revel | +1.878 |
Poly | +1.846 |
Pri | +1.778 |
Neg logit contributions | |
emis | -3.830 |
Turing | -3.651 |
tar | -3.210 |
aver | -3.151 |
Turk | -3.141 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
hered | +1.676 |
Bucc | +1.554 |
Revel | +1.490 |
Poly | +1.468 |
Pri | +1.422 |
Neg logit contributions | |
emis | -2.412 |
Turing | -2.290 |
tar | -1.990 |
aver | -1.949 |
Turk | -1.944 |
Token | who |
Token ID | 508 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
emis | +1.085 |
Turing | +1.038 |
tar | +0.902 |
Turk | +0.885 |
aver | +0.881 |
Neg logit contributions | |
hered | -0.840 |
Bucc | -0.780 |
Revel | -0.744 |
Poly | -0.727 |
Pri | -0.714 |
Token | t |
Token ID | 256 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
hered | +0.718 |
Bucc | +0.673 |
Revel | +0.651 |
Poly | +0.639 |
Pri | +0.625 |
Neg logit contributions | |
emis | -0.843 |
Turing | -0.798 |
tar | -0.685 |
aver | -0.679 |
Turk | -0.667 |
Token | abled |
Token ID | 4510 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
emis | +0.138 |
Turing | +0.128 |
tar | +0.106 |
aver | +0.102 |
Starg | +0.101 |
Neg logit contributions | |
hered | -0.179 |
Bucc | -0.172 |
Revel | -0.168 |
Poly | -0.165 |
Pri | -0.161 |
Token | the |
Token ID | 262 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
emis | +1.209 |
Turing | +1.151 |
tar | +0.978 |
aver | +0.961 |
Turk | +0.960 |
Neg logit contributions | |
hered | -1.062 |
Bucc | -0.997 |
Revel | -0.965 |
Poly | -0.934 |
Pri | -0.928 |
Token | black |
Token ID | 2042 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
emis | +0.720 |
Turing | +0.685 |
tar | +0.579 |
aver | +0.569 |
Turk | +0.568 |
Neg logit contributions | |
hered | -0.659 |
Bucc | -0.620 |
Revel | -0.600 |
Poly | -0.581 |
Pri | -0.578 |
Token | hats |
Token ID | 23910 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
emis | +0.410 |
Turing | +0.393 |
tar | +0.334 |
Turk | +0.328 |
aver | +0.326 |
Neg logit contributions | |
hered | -0.350 |
Bucc | -0.326 |
Revel | -0.314 |
Poly | -0.308 |
Pri | -0.302 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
emis | +2.359 |
Turing | +2.274 |
tar | +1.942 |
aver | +1.915 |
Turk | +1.889 |
Neg logit contributions | |
hered | -1.873 |
Bucc | -1.780 |
Revel | -1.698 |
Poly | -1.670 |
Pri | -1.631 |
Token | � |
Token ID | 447 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
emis | +2.464 |
Turing | +2.373 |
tar | +2.040 |
aver | +2.029 |
Turk | +2.006 |
Neg logit contributions | |
hered | -2.019 |
Bucc | -1.861 |
Revel | -1.797 |
Poly | -1.728 |
Pri | -1.718 |
Token | � |
Token ID | 251 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
emis | +0.470 |
Turing | +0.444 |
tar | +0.380 |
aver | +0.372 |
Turk | +0.372 |
Neg logit contributions | |
hered | -0.401 |
Bucc | -0.375 |
Revel | -0.361 |
Poly | -0.356 |
Pri | -0.347 |
Token | or |
Token ID | 393 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
hered | +0.109 |
Bucc | +0.102 |
Revel | +0.097 |
Poly | +0.095 |
Pri | +0.094 |
Neg logit contributions | |
emis | -0.122 |
Turing | -0.117 |
tar | -0.100 |
aver | -0.099 |
Turk | -0.098 |
Token | those |
Token ID | 883 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
emis | +1.046 |
Turing | +1.007 |
tar | +0.854 |
aver | +0.849 |
Turk | +0.846 |
Neg logit contributions | |
hered | -0.916 |
Bucc | -0.842 |
Revel | -0.812 |
Poly | -0.787 |
Pri | -0.783 |
Token | who |
Token ID | 508 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
emis | +1.994 |
Turing | +1.924 |
tar | +1.663 |
aver | +1.651 |
Turk | +1.641 |
Neg logit contributions | |
hered | -1.345 |
Bucc | -1.226 |
Revel | -1.193 |
Poly | -1.141 |
Pri | -1.137 |
Token | use |
Token ID | 779 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
emis | +0.250 |
Turing | +0.239 |
tar | +0.202 |
aver | +0.200 |
Turk | +0.197 |
Neg logit contributions | |
hered | -0.230 |
Bucc | -0.214 |
Revel | -0.207 |
Poly | -0.202 |
Pri | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
hered | +0.064 |
Bucc | +0.060 |
Revel | +0.058 |
Poly | +0.057 |
Pri | +0.056 |
Neg logit contributions | |
emis | -0.070 |
Turing | -0.067 |
tar | -0.056 |
aver | -0.056 |
Turk | -0.055 |
Token | H |
Token ID | 367 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
hered | +1.109 |
Bucc | +1.029 |
Revel | +0.987 |
Poly | +0.973 |
Pri | +0.957 |
Neg logit contributions | |
emis | -1.363 |
Turing | -1.303 |
tar | -1.103 |
aver | -1.094 |
Turk | -1.088 |
Token | SP |
Token ID | 4303 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
emis | +1.205 |
Turing | +1.132 |
tar | +0.993 |
agents | +0.973 |
aver | +0.968 |
Neg logit contributions | |
hered | -0.786 |
Bucc | -0.751 |
Revel | -0.706 |
Poly | -0.689 |
brim | -0.670 |
Token | program |
Token ID | 1430 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
emis | +1.116 |
Turing | +1.066 |
tar | +0.925 |
aver | +0.918 |
Turk | +0.909 |
Neg logit contributions | |
hered | -0.788 |
Bucc | -0.737 |
Revel | -0.695 |
Poly | -0.691 |
Pri | -0.672 |
Token | quickly |
Token ID | 2952 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
hered | +1.512 |
Bucc | +1.417 |
Revel | +1.360 |
Poly | +1.343 |
Pri | +1.307 |
Neg logit contributions | |
emis | -1.852 |
Turing | -1.755 |
tar | -1.505 |
aver | -1.479 |
Turk | -1.469 |
Token | back |
Token ID | 736 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
hered | +1.563 |
Bucc | +1.467 |
Revel | +1.415 |
Poly | +1.396 |
Pri | +1.360 |
Neg logit contributions | |
emis | -1.760 |
Turing | -1.663 |
tar | -1.417 |
aver | -1.390 |
Turk | -1.380 |
Token | fired |
Token ID | 26803 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
hered | +2.627 |
Bucc | +2.491 |
Revel | +2.428 |
Poly | +2.405 |
Pri | +2.357 |
Neg logit contributions | |
emis | -1.569 |
Turing | -1.448 |
tar | -1.133 |
aver | -1.097 |
Turk | -1.090 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
hered | +2.201 |
Bucc | +2.030 |
Revel | +1.955 |
Poly | +1.925 |
Pri | +1.863 |
Neg logit contributions | |
emis | -3.155 |
Turing | -2.988 |
tar | -2.590 |
Starg | -2.538 |
Turk | -2.531 |
Token | The |
Token ID | 383 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
hered | +0.250 |
Bucc | +0.231 |
Revel | +0.222 |
brim | +0.220 |
Poly | +0.219 |
Neg logit contributions | |
emis | -0.253 |
Turing | -0.245 |
tar | -0.205 |
Turk | -0.203 |
Starg | -0.200 |
Token | city |
Token ID | 1748 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
hered | +0.130 |
Bucc | +0.120 |
Revel | +0.115 |
Poly | +0.114 |
Pri | +0.113 |
Neg logit contributions | |
emis | -0.159 |
Turing | -0.153 |
tar | -0.129 |
aver | -0.129 |
Turk | -0.128 |
Token | funded |
Token ID | 10588 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
emis | +0.017 |
Turing | +0.016 |
tar | +0.014 |
aver | +0.014 |
Turk | +0.014 |
Neg logit contributions | |
hered | -0.015 |
Bucc | -0.014 |
Revel | -0.014 |
Poly | -0.013 |
Pri | -0.013 |
Token | 10 |
Token ID | 838 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
emis | +0.088 |
Turing | +0.084 |
tar | +0.070 |
aver | +0.070 |
Turk | +0.070 |
Neg logit contributions | |
hered | -0.079 |
Bucc | -0.074 |
Revel | -0.071 |
Poly | -0.070 |
Pri | -0.069 |
Token | nail |
Token ID | 17864 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
hered | +0.519 |
Bucc | +0.488 |
Revel | +0.466 |
Poly | +0.459 |
Pri | +0.453 |
Neg logit contributions | |
emis | -0.590 |
Turing | -0.559 |
tar | -0.476 |
aver | -0.470 |
Turk | -0.466 |
Token | some |
Token ID | 617 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
hered | +1.660 |
Bucc | +1.548 |
Revel | +1.491 |
Poly | +1.469 |
Pri | +1.431 |
Neg logit contributions | |
emis | -2.032 |
Turing | -1.924 |
tar | -1.651 |
aver | -1.616 |
Turk | -1.610 |
Token | amazing |
Token ID | 4998 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
emis | +0.294 |
Turing | +0.280 |
tar | +0.239 |
aver | +0.235 |
Starg | +0.235 |
Neg logit contributions | |
hered | -0.241 |
Bucc | -0.223 |
Revel | -0.214 |
Pri | -0.209 |
Poly | -0.208 |
Token | set |
Token ID | 900 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
emis | +0.915 |
Turing | +0.879 |
tar | +0.750 |
aver | +0.742 |
Starg | +0.740 |
Neg logit contributions | |
hered | -0.731 |
Bucc | -0.670 |
Revel | -0.638 |
Pri | -0.627 |
Poly | -0.621 |
Token | ups |
Token ID | 19649 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
hered | +2.104 |
Bucc | +1.954 |
Revel | +1.878 |
Poly | +1.862 |
brim | +1.792 |
Neg logit contributions | |
emis | -2.829 |
Turing | -2.680 |
tar | -2.308 |
aver | -2.267 |
Starg | -2.258 |
Token | in |
Token ID | 287 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
emis | +2.016 |
Turing | +1.900 |
tar | +1.638 |
aver | +1.622 |
Turk | +1.594 |
Neg logit contributions | |
hered | -1.721 |
Bucc | -1.632 |
Revel | -1.553 |
Poly | -1.519 |
Pri | -1.513 |
Token | the |
Token ID | 262 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
hered | +0.588 |
Bucc | +0.548 |
Revel | +0.520 |
Poly | +0.511 |
Pri | +0.504 |
Neg logit contributions | |
emis | -0.713 |
Turing | -0.682 |
tar | -0.582 |
aver | -0.575 |
Turk | -0.573 |
Token | past |
Token ID | 1613 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
hered | +0.608 |
Bucc | +0.567 |
Revel | +0.541 |
Poly | +0.531 |
Pri | +0.525 |
Neg logit contributions | |
emis | -0.703 |
Turing | -0.667 |
tar | -0.568 |
Starg | -0.559 |
aver | -0.558 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
hered | +0.304 |
Bucc | +0.285 |
Revel | +0.271 |
Poly | +0.266 |
Pri | +0.262 |
Neg logit contributions | |
emis | -0.383 |
Turing | -0.364 |
tar | -0.315 |
aver | -0.309 |
Turk | -0.308 |
Token | but |
Token ID | 475 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
hered | +0.988 |
Bucc | +0.924 |
Revel | +0.887 |
Poly | +0.873 |
Pri | +0.857 |
Neg logit contributions | |
emis | -1.101 |
Turing | -1.040 |
tar | -0.889 |
aver | -0.871 |
Turk | -0.867 |
Token | then |
Token ID | 788 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
emis | +0.834 |
Turing | +0.796 |
tar | +0.679 |
aver | +0.673 |
Starg | +0.669 |
Neg logit contributions | |
hered | -0.726 |
Bucc | -0.672 |
Revel | -0.635 |
Pri | -0.623 |
Poly | -0.622 |
Token | will |
Token ID | 481 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
emis | +0.121 |
Turing | +0.115 |
tar | +0.098 |
aver | +0.096 |
Turk | +0.096 |
Neg logit contributions | |
hered | -0.103 |
Bucc | -0.096 |
Revel | -0.093 |
Poly | -0.091 |
Pri | -0.089 |
Token | still |
Token ID | 991 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
hered | +0.746 |
Bucc | +0.697 |
Revel | +0.672 |
Poly | +0.661 |
Pri | +0.646 |
Neg logit contributions | |
emis | -0.881 |
Turing | -0.836 |
tar | -0.716 |
aver | -0.700 |
Starg | -0.698 |
Token | be |
Token ID | 307 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
emis | +0.215 |
Turing | +0.204 |
tar | +0.171 |
aver | +0.166 |
Starg | +0.166 |
Neg logit contributions | |
hered | -0.228 |
Bucc | -0.216 |
Revel | -0.208 |
Poly | -0.205 |
Pri | -0.202 |
Token | available |
Token ID | 1695 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
hered | +0.862 |
Bucc | +0.810 |
Revel | +0.781 |
Poly | +0.770 |
Pri | +0.754 |
Neg logit contributions | |
emis | -0.953 |
Turing | -0.904 |
tar | -0.767 |
aver | -0.751 |
Turk | -0.749 |
Token | for |
Token ID | 329 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
hered | +2.523 |
Bucc | +2.341 |
Revel | +2.253 |
Poly | +2.233 |
Pri | +2.155 |
Neg logit contributions | |
emis | -3.306 |
Turing | -3.119 |
tar | -2.694 |
aver | -2.631 |
Turk | -2.627 |
Token | a |
Token ID | 257 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
hered | +3.235 |
Bucc | +3.032 |
Revel | +2.917 |
Poly | +2.899 |
Pri | +2.793 |
Neg logit contributions | |
emis | -3.951 |
Turing | -3.701 |
tar | -3.195 |
aver | -3.120 |
Starg | -3.100 |
Token | limited |
Token ID | 3614 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
hered | +4.914 |
Bucc | +4.546 |
Poly | +4.379 |
Revel | +4.375 |
Pri | +4.232 |
Neg logit contributions | |
emis | -5.998 |
Turing | -5.528 |
tar | -4.773 |
agents | -4.728 |
aver | -4.655 |
Token | period |
Token ID | 2278 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
hered | +3.113 |
Bucc | +2.855 |
Poly | +2.749 |
Revel | +2.732 |
brim | +2.638 |
Neg logit contributions | |
emis | -4.505 |
Turing | -4.175 |
tar | -3.632 |
agents | -3.581 |
Turk | -3.523 |
Token | of |
Token ID | 286 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
hered | +1.152 |
Bucc | +1.055 |
Revel | +1.014 |
Poly | +1.012 |
Pri | +0.967 |
Neg logit contributions | |
emis | -1.784 |
Turing | -1.685 |
tar | -1.470 |
agents | -1.441 |
Starg | -1.435 |
Token | time |
Token ID | 640 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
hered | +0.631 |
Bucc | +0.593 |
Revel | +0.575 |
Poly | +0.570 |
brim | +0.551 |
Neg logit contributions | |
emis | -0.624 |
Turing | -0.580 |
tar | -0.490 |
aver | -0.475 |
Starg | -0.473 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
emis | +0.896 |
Turing | +0.854 |
tar | +0.736 |
aver | +0.721 |
Turk | +0.717 |
Neg logit contributions | |
hered | -0.740 |
Bucc | -0.696 |
Revel | -0.667 |
Poly | -0.653 |
Pri | -0.640 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
emis | +2.295 |
Turing | +2.213 |
tar | +1.886 |
aver | +1.851 |
Turk | +1.846 |
Neg logit contributions | |
hered | -2.067 |
Bucc | -1.933 |
Revel | -1.853 |
Poly | -1.792 |
Pri | -1.792 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
hered | +1.898 |
Bucc | +1.757 |
Revel | +1.678 |
Poly | +1.659 |
Pri | +1.601 |
Neg logit contributions | |
emis | -2.883 |
Turing | -2.734 |
tar | -2.379 |
aver | -2.334 |
Starg | -2.326 |
Token | 1 |
Token ID | 16 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
hered | +1.824 |
Bucc | +1.707 |
Revel | +1.648 |
Poly | +1.622 |
Pri | +1.577 |
Neg logit contributions | |
emis | -2.126 |
Turing | -2.010 |
tar | -1.724 |
aver | -1.680 |
Turk | -1.674 |
Token | MB |
Token ID | 10744 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
hered | +3.034 |
Bucc | +2.839 |
Revel | +2.726 |
Poly | +2.724 |
brim | +2.651 |
Neg logit contributions | |
emis | -3.304 |
Turing | -3.099 |
tar | -2.609 |
Starg | -2.562 |
aver | -2.557 |
Token | , |
Token ID | 11 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
hered | +3.428 |
Bucc | +3.137 |
Revel | +3.015 |
Poly | +3.012 |
Pri | +2.888 |
Neg logit contributions | |
emis | -5.241 |
Turing | -4.912 |
tar | -4.258 |
aver | -4.196 |
agents | -4.180 |
Token | resolution |
Token ID | 6323 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
hered | +2.260 |
Bucc | +2.121 |
Revel | +2.026 |
Poly | +1.997 |
Pri | +1.952 |
Neg logit contributions | |
emis | -2.632 |
Turing | -2.512 |
tar | -2.142 |
aver | -2.098 |
Turk | -2.091 |
Token | : |
Token ID | 25 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
hered | +4.133 |
Bucc | +3.700 |
Revel | +3.611 |
Poly | +3.590 |
Pri | +3.462 |
Neg logit contributions | |
emis | -6.376 |
Turing | -5.993 |
tar | -5.250 |
agents | -5.118 |
Turk | -5.110 |
Token | 1600 |
Token ID | 26143 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
emis | +0.331 |
Turing | +0.313 |
tar | +0.262 |
aver | +0.258 |
Turk | +0.255 |
Neg logit contributions | |
hered | -0.362 |
Bucc | -0.342 |
Revel | -0.328 |
Poly | -0.321 |
Pri | -0.319 |
Token | x |
Token ID | 87 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
hered | +2.508 |
Bucc | +2.353 |
Revel | +2.272 |
Poly | +2.242 |
Pri | +2.184 |
Neg logit contributions | |
emis | -2.702 |
Turing | -2.546 |
tar | -2.163 |
aver | -2.112 |
Turk | -2.104 |
Token | 900 |
Token ID | 12865 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
hered | +3.377 |
Bucc | +3.120 |
Revel | +3.014 |
Poly | +2.997 |
Pri | +2.906 |
Neg logit contributions | |
emis | -4.199 |
Turing | -3.936 |
tar | -3.363 |
aver | -3.308 |
Turk | -3.302 |
Token | pixels |
Token ID | 17848 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
hered | +4.741 |
Bucc | +4.349 |
Revel | +4.211 |
Poly | +4.200 |
brim | +3.988 |
Neg logit contributions | |
emis | -7.839 |
Turing | -7.300 |
tar | -6.401 |
aver | -6.356 |
Starg | -6.287 |
Token | bi |
Token ID | 3182 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
hered | +1.582 |
Bucc | +1.484 |
Revel | +1.433 |
Poly | +1.415 |
Pri | +1.379 |
Neg logit contributions | |
emis | -1.679 |
Turing | -1.584 |
tar | -1.342 |
aver | -1.311 |
Turk | -1.307 |
Token | otechnology |
Token ID | 31201 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
hered | +1.112 |
Bucc | +1.055 |
Revel | +1.025 |
Poly | +1.014 |
Pri | +0.993 |
Neg logit contributions | |
emis | -0.798 |
Turing | -0.741 |
tar | -0.601 |
aver | -0.581 |
Turk | -0.579 |
Token | critic |
Token ID | 4014 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
hered | +0.398 |
Bucc | +0.371 |
Revel | +0.356 |
Poly | +0.350 |
Pri | +0.343 |
Neg logit contributions | |
emis | -0.444 |
Turing | -0.424 |
tar | -0.359 |
aver | -0.353 |
Turk | -0.352 |
Token | Jeremy |
Token ID | 11753 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
hered | +3.428 |
Bucc | +3.223 |
Revel | +3.135 |
Poly | +3.108 |
Pri | +3.003 |
Neg logit contributions | |
emis | -3.282 |
Turing | -3.049 |
tar | -2.582 |
aver | -2.514 |
agents | -2.499 |
Token | R |
Token ID | 371 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
hered | +2.201 |
Bucc | +2.077 |
Revel | +2.007 |
Poly | +1.985 |
Pri | +1.927 |
Neg logit contributions | |
emis | -2.194 |
Turing | -2.052 |
tar | -1.737 |
aver | -1.692 |
Starg | -1.677 |
Token | if |
Token ID | 361 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
hered | +0.232 |
Bucc | +0.218 |
Revel | +0.211 |
Poly | +0.207 |
brim | +0.202 |
Neg logit contributions | |
emis | -0.244 |
Turing | -0.230 |
tar | -0.195 |
Turk | -0.189 |
aver | -0.189 |
Token | kin |
Token ID | 5116 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
hered | +6.465 |
Bucc | +5.735 |
Poly | +5.613 |
Revel | +5.574 |
Pri | +5.413 |
Neg logit contributions | |
emis | -8.064 |
Turing | -7.775 |
Turk | -6.602 |
Starg | -6.537 |
Gadget | -6.508 |
Token | , |
Token ID | 11 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
hered | +2.116 |
Bucc | +1.968 |
Revel | +1.897 |
Poly | +1.873 |
brim | +1.812 |
Neg logit contributions | |
emis | -2.905 |
Turing | -2.743 |
tar | -2.376 |
agents | -2.324 |
Starg | -2.324 |
Token | protest |
Token ID | 5402 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
hered | +3.504 |
Bucc | +3.287 |
Revel | +3.168 |
Poly | +3.132 |
brim | +3.039 |
Neg logit contributions | |
emis | -4.159 |
Turing | -3.909 |
tar | -3.353 |
Starg | -3.266 |
aver | -3.265 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
hered | +1.009 |
Bucc | +0.939 |
Revel | +0.905 |
Poly | +0.887 |
Pri | +0.870 |
Neg logit contributions | |
emis | -1.203 |
Turing | -1.151 |
tar | -0.982 |
aver | -0.958 |
Turk | -0.958 |
Token | patent |
Token ID | 12701 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
emis | +1.364 |
Turing | +1.333 |
Starg | +1.110 |
tar | +1.109 |
Turk | +1.108 |
Neg logit contributions | |
hered | -1.217 |
Bucc | -1.118 |
Revel | -1.075 |
Poly | -1.044 |
Pri | -1.044 |
Token | - |
Token ID | 12 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
hered | +2.273 |
Bucc | +2.134 |
Poly | +2.058 |
Revel | +2.048 |
Pri | +1.971 |
Neg logit contributions | |
emis | -2.630 |
Turing | -2.454 |
tar | -2.089 |
Turk | -2.048 |
aver | -2.040 |
Token | Object |
Token ID | 10267 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
hered | +1.968 |
Bucc | +1.801 |
Poly | +1.718 |
Revel | +1.712 |
Pri | +1.680 |
Neg logit contributions | |
emis | -3.422 |
Turing | -3.246 |
tar | -2.849 |
Turk | -2.807 |
aver | -2.788 |
Token | Drawing |
Token ID | 40027 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
hered | +0.421 |
Bucc | +0.393 |
Revel | +0.380 |
Poly | +0.373 |
Pri | +0.365 |
Neg logit contributions | |
emis | -0.465 |
Turing | -0.441 |
tar | -0.374 |
aver | -0.365 |
Starg | -0.365 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
hered | +0.918 |
Bucc | +0.858 |
Revel | +0.828 |
Poly | +0.816 |
Pri | +0.794 |
Neg logit contributions | |
emis | -1.075 |
Turing | -1.015 |
tar | -0.869 |
aver | -0.849 |
Turk | -0.846 |
Token | Solid |
Token ID | 46933 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
hered | +0.925 |
Bucc | +0.873 |
Revel | +0.847 |
Poly | +0.834 |
Pri | +0.815 |
Neg logit contributions | |
emis | -0.824 |
Turing | -0.773 |
tar | -0.645 |
aver | -0.625 |
Starg | -0.622 |
Token | Br |
Token ID | 9414 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
hered | +2.476 |
Bucc | +2.327 |
Revel | +2.248 |
Poly | +2.230 |
Pri | +2.172 |
Neg logit contributions | |
emis | -2.448 |
Turing | -2.297 |
tar | -1.932 |
aver | -1.890 |
Turk | -1.880 |
Token | ush |
Token ID | 1530 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
hered | +4.429 |
Bucc | +4.075 |
Poly | +3.972 |
Revel | +3.942 |
Pri | +3.830 |
Neg logit contributions | |
emis | -5.872 |
Turing | -5.625 |
tar | -4.825 |
aver | -4.708 |
agents | -4.700 |
Token | ( |
Token ID | 357 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
hered | +3.344 |
Bucc | +3.088 |
Poly | +2.995 |
Revel | +2.979 |
Pri | +2.881 |
Neg logit contributions | |
emis | -4.258 |
Turing | -4.001 |
tar | -3.440 |
aver | -3.375 |
Turk | -3.367 |
Token | [ |
Token ID | 685 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
hered | +1.419 |
Bucc | +1.333 |
Revel | +1.287 |
Poly | +1.269 |
Pri | +1.237 |
Neg logit contributions | |
emis | -1.495 |
Turing | -1.409 |
tar | -1.197 |
aver | -1.166 |
Starg | -1.160 |
Token | System |
Token ID | 11964 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
hered | +0.703 |
Bucc | +0.662 |
Revel | +0.640 |
Poly | +0.629 |
Pri | +0.615 |
Neg logit contributions | |
emis | -0.710 |
Turing | -0.669 |
tar | -0.568 |
aver | -0.550 |
Starg | -0.548 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
hered | +1.273 |
Bucc | +1.170 |
Revel | +1.116 |
Poly | +1.116 |
Pri | +1.080 |
Neg logit contributions | |
emis | -2.068 |
Turing | -1.950 |
tar | -1.706 |
Turk | -1.678 |
aver | -1.677 |
Token | s |
Token ID | 82 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
emis | +0.871 |
Turing | +0.829 |
tar | +0.733 |
agents | +0.707 |
Starg | +0.705 |
Neg logit contributions | |
hered | -0.720 |
Bucc | -0.707 |
Revel | -0.674 |
brim | -0.652 |
Poly | -0.644 |
Token | journalism |
Token ID | 14033 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
hered | +0.337 |
Bucc | +0.317 |
Revel | +0.308 |
Poly | +0.301 |
brim | +0.294 |
Neg logit contributions | |
emis | -0.378 |
Turing | -0.356 |
tar | -0.306 |
aver | -0.299 |
Starg | -0.298 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
emis | +1.414 |
Turing | +1.351 |
tar | +1.172 |
Starg | +1.144 |
Turk | +1.141 |
Neg logit contributions | |
hered | -1.127 |
Bucc | -1.082 |
Revel | -1.045 |
brim | -1.018 |
merce | -1.004 |
Token | You |
Token ID | 921 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
hered | +2.523 |
Bucc | +2.366 |
Revel | +2.289 |
Poly | +2.265 |
Pri | +2.203 |
Neg logit contributions | |
emis | -2.637 |
Turing | -2.477 |
tar | -2.095 |
aver | -2.051 |
Turk | -2.037 |
Token | can |
Token ID | 460 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
emis | +0.037 |
Turing | +0.035 |
tar | +0.030 |
aver | +0.029 |
Starg | +0.029 |
Neg logit contributions | |
hered | -0.036 |
Bucc | -0.034 |
Revel | -0.033 |
Poly | -0.032 |
brim | -0.032 |
Token | read |
Token ID | 1100 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
hered | +4.130 |
Bucc | +3.598 |
Revel | +3.484 |
Poly | +3.448 |
Pri | +3.269 |
Neg logit contributions | |
emis | -9.078 |
Turing | -8.723 |
tar | -7.659 |
agents | -7.577 |
Turk | -7.554 |
Token | our |
Token ID | 674 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
hered | +4.050 |
Bucc | +3.695 |
Poly | +3.594 |
Revel | +3.579 |
Pri | +3.401 |
Neg logit contributions | |
emis | -6.214 |
Turing | -5.842 |
tar | -5.096 |
aver | -4.992 |
agents | -4.970 |
Token | Privacy |
Token ID | 16777 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
hered | +4.113 |
Bucc | +3.858 |
Poly | +3.562 |
Revel | +3.475 |
Pri | +3.362 |
Neg logit contributions | |
emis | -13.314 |
Turing | -12.761 |
tar | -11.499 |
aver | -11.324 |
Turk | -11.270 |
Token | Policy |
Token ID | 7820 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
hered | +1.796 |
Bucc | +1.669 |
Revel | +1.602 |
Poly | +1.583 |
Pri | +1.536 |
Neg logit contributions | |
emis | -2.474 |
Turing | -2.342 |
tar | -2.031 |
aver | -1.993 |
Turk | -1.982 |
Token | here |
Token ID | 994 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
hered | +2.222 |
Bucc | +2.026 |
Revel | +1.946 |
Poly | +1.920 |
Pri | +1.847 |
Neg logit contributions | |
emis | -3.728 |
Turing | -3.550 |
tar | -3.106 |
aver | -3.054 |
Turk | -3.052 |
Token | . |
Token ID | 13 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
emis | +0.875 |
Turing | +0.840 |
tar | +0.726 |
Starg | +0.714 |
Turk | +0.707 |
Neg logit contributions | |
hered | -0.670 |
Bucc | -0.636 |
Revel | -0.607 |
brim | -0.594 |
Poly | -0.588 |