Token | Gang |
Token ID | 19228 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
keys | +0.987 |
goats | +0.972 |
swers | +0.932 |
osher | +0.907 |
Edge | +0.878 |
Neg logit contributions | |
leys | -1.083 |
idad | -0.956 |
amina | -0.952 |
ici | -0.928 |
tru | -0.923 |
Token | etic |
Token ID | 5139 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
keys | +3.127 |
goats | +3.061 |
swers | +2.932 |
osher | +2.919 |
Edge | +2.763 |
Neg logit contributions | |
leys | -2.745 |
idad | -2.392 |
amina | -2.377 |
tru | -2.324 |
ici | -2.305 |
Token | dolphins |
Token ID | 36798 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
keys | +6.592 |
goats | +6.552 |
swers | +6.092 |
osher | +5.939 |
eer | +5.853 |
Neg logit contributions | |
leys | -6.211 |
amina | -5.300 |
idad | -5.284 |
tru | -5.247 |
ici | -5.135 |
Token | and |
Token ID | 290 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
keys | +0.356 |
goats | +0.351 |
swers | +0.337 |
osher | +0.328 |
Edge | +0.318 |
Neg logit contributions | |
leys | -0.381 |
idad | -0.336 |
amina | -0.335 |
ici | -0.326 |
tru | -0.324 |
Token | the |
Token ID | 262 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
keys | +2.250 |
goats | +2.244 |
swers | +2.111 |
osher | +2.041 |
Edge | +1.974 |
Neg logit contributions | |
leys | -2.620 |
idad | -2.322 |
amina | -2.297 |
ici | -2.260 |
tru | -2.230 |
Token | highly |
Token ID | 4047 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
keys | +1.918 |
goats | +1.902 |
swers | +1.803 |
osher | +1.750 |
Edge | +1.692 |
Neg logit contributions | |
leys | -2.230 |
idad | -1.970 |
amina | -1.957 |
ici | -1.919 |
tru | -1.896 |
Token | endangered |
Token ID | 22700 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
goats | +12.524 |
keys | +12.166 |
eer | +10.870 |
endangered | +10.650 |
Howe | +10.559 |
Neg logit contributions | |
leys | -16.530 |
idad | -14.371 |
ici | -13.782 |
ulk | -13.702 |
amina | -13.637 |
Token | Bengal |
Token ID | 28630 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
goats | +3.597 |
keys | +3.555 |
swers | +3.314 |
osher | +3.221 |
Khe | +3.139 |
Neg logit contributions | |
leys | -3.933 |
idad | -3.481 |
amina | -3.445 |
ici | -3.393 |
tru | -3.318 |
Token | tiger |
Token ID | 26241 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
goats | +4.915 |
keys | +4.870 |
swers | +4.477 |
osher | +4.421 |
eer | +4.284 |
Neg logit contributions | |
leys | -6.160 |
amina | -5.450 |
idad | -5.348 |
tru | -5.262 |
ici | -5.218 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
keys | +2.337 |
goats | +2.329 |
swers | +2.175 |
osher | +2.113 |
Edge | +2.066 |
Neg logit contributions | |
leys | -2.760 |
idad | -2.436 |
amina | -2.430 |
ici | -2.364 |
tru | -2.360 |
Token |
|
Token ID | 198 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
keys | +0.147 |
goats | +0.145 |
swers | +0.140 |
osher | +0.137 |
Edge | +0.132 |
Neg logit contributions | |
leys | -0.129 |
idad | -0.112 |
amina | -0.111 |
ici | -0.108 |
tru | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
keys | +4.914 |
goats | +4.838 |
swers | +4.558 |
osher | +4.377 |
Tips | +4.227 |
Neg logit contributions | |
leys | -7.613 |
idad | -6.877 |
amina | -6.748 |
tru | -6.555 |
ici | -6.555 |
Token | thrive |
Token ID | 22191 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
goats | +6.487 |
keys | +6.422 |
swers | +5.803 |
eer | +5.455 |
Edge | +5.451 |
Neg logit contributions | |
leys | -9.581 |
amina | -8.639 |
idad | -8.592 |
ici | -8.319 |
tru | -7.847 |
Token | in |
Token ID | 287 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
keys | +2.682 |
goats | +2.650 |
swers | +2.536 |
osher | +2.440 |
Tips | +2.379 |
Neg logit contributions | |
leys | -2.934 |
idad | -2.593 |
amina | -2.583 |
ici | -2.494 |
tru | -2.457 |
Token | many |
Token ID | 867 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
keys | +6.894 |
goats | +6.657 |
swers | +6.397 |
eer | +6.261 |
osher | +5.952 |
Neg logit contributions | |
leys | -10.007 |
amina | -9.029 |
idad | -8.738 |
ici | -8.680 |
ulk | -8.372 |
Token | different |
Token ID | 1180 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
keys | +7.161 |
goats | +7.062 |
swers | +6.586 |
eer | +6.406 |
osher | +6.115 |
Neg logit contributions | |
leys | -12.174 |
amina | -11.102 |
idad | -10.885 |
ici | -10.748 |
ulk | -10.334 |
Token | professional |
Token ID | 4708 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
goats | +8.001 |
keys | +7.910 |
swers | +7.232 |
eer | +7.097 |
osher | +7.065 |
Neg logit contributions | |
leys | -12.368 |
amina | -11.376 |
idad | -11.082 |
ici | -11.005 |
ulk | -10.790 |
Token | capacities |
Token ID | 32484 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
goats | +10.162 |
keys | +9.571 |
swers | +8.822 |
imaginable | +8.770 |
hands | +8.761 |
Neg logit contributions | |
leys | -17.547 |
amina | -15.711 |
idad | -15.628 |
ulk | -15.329 |
ici | -15.296 |
Token | , |
Token ID | 11 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
keys | +5.534 |
goats | +5.478 |
swers | +5.144 |
osher | +4.947 |
Tips | +4.731 |
Neg logit contributions | |
leys | -7.549 |
idad | -6.742 |
amina | -6.727 |
ici | -6.488 |
tru | -6.408 |
Token | including |
Token ID | 1390 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
keys | +2.846 |
goats | +2.823 |
swers | +2.697 |
osher | +2.612 |
Edge | +2.507 |
Neg logit contributions | |
leys | -3.705 |
amina | -3.299 |
idad | -3.289 |
ici | -3.200 |
tru | -3.156 |
Token | business |
Token ID | 1597 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
keys | +3.081 |
goats | +3.037 |
swers | +2.898 |
osher | +2.807 |
Tips | +2.713 |
Neg logit contributions | |
leys | -3.686 |
amina | -3.296 |
idad | -3.291 |
ici | -3.170 |
tru | -3.091 |
Token | roles |
Token ID | 9176 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
keys | +3.799 |
goats | +3.749 |
swers | +3.601 |
osher | +3.442 |
Edge | +3.372 |
Neg logit contributions | |
leys | -4.675 |
amina | -4.172 |
idad | -4.073 |
ici | -3.982 |
tru | -3.875 |
Token | says |
Token ID | 1139 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
goats | +3.437 |
keys | +3.426 |
swers | +3.168 |
osher | +3.030 |
eer | +3.007 |
Neg logit contributions | |
leys | -4.241 |
amina | -3.738 |
idad | -3.737 |
ici | -3.669 |
tru | -3.545 |
Token | it |
Token ID | 340 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
goats | +3.928 |
keys | +3.907 |
swers | +3.678 |
osher | +3.481 |
Tips | +3.419 |
Neg logit contributions | |
leys | -5.389 |
idad | -4.824 |
amina | -4.766 |
ici | -4.695 |
tru | -4.558 |
Token | has |
Token ID | 468 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
goats | +3.656 |
keys | +3.633 |
swers | +3.420 |
osher | +3.271 |
eer | +3.194 |
Neg logit contributions | |
leys | -4.365 |
idad | -3.848 |
amina | -3.821 |
ici | -3.779 |
tru | -3.660 |
Token | made |
Token ID | 925 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
goats | +4.486 |
keys | +4.433 |
swers | +4.193 |
osher | +3.895 |
Edge | +3.889 |
Neg logit contributions | |
leys | -5.954 |
idad | -5.194 |
amina | -5.187 |
ici | -5.136 |
tru | -4.937 |
Token | her |
Token ID | 607 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
keys | +2.035 |
goats | +2.004 |
swers | +1.925 |
osher | +1.875 |
Edge | +1.818 |
Neg logit contributions | |
leys | -2.091 |
idad | -1.837 |
amina | -1.829 |
ici | -1.781 |
tru | -1.773 |
Token | more |
Token ID | 517 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
goats | +6.131 |
keys | +5.952 |
swers | +5.644 |
eer | +5.363 |
Tips | +5.329 |
Neg logit contributions | |
leys | -7.046 |
idad | -6.165 |
ici | -6.148 |
amina | -6.080 |
tru | -5.525 |
Token | outgoing |
Token ID | 28181 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
goats | +10.991 |
keys | +10.099 |
eer | +10.015 |
kosher | +9.888 |
swers | +9.583 |
Neg logit contributions | |
leys | -16.745 |
ici | -15.038 |
idad | -14.627 |
amina | -14.455 |
ulk | -13.978 |
Token | and |
Token ID | 290 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
keys | +2.689 |
goats | +2.670 |
swers | +2.526 |
osher | +2.432 |
eer | +2.368 |
Neg logit contributions | |
leys | -3.207 |
idad | -2.839 |
amina | -2.810 |
ici | -2.766 |
tru | -2.706 |
Token | is |
Token ID | 318 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
goats | +4.484 |
keys | +4.400 |
swers | +4.163 |
eer | +3.966 |
Tips | +3.946 |
Neg logit contributions | |
leys | -5.680 |
idad | -5.054 |
ici | -5.036 |
amina | -5.023 |
ulk | -4.711 |
Token | a |
Token ID | 257 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
keys | +2.842 |
goats | +2.837 |
swers | +2.683 |
osher | +2.554 |
Edge | +2.499 |
Neg logit contributions | |
leys | -3.762 |
idad | -3.340 |
amina | -3.298 |
ici | -3.267 |
tru | -3.145 |
Token | good |
Token ID | 922 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
keys | +0.309 |
goats | +0.305 |
swers | +0.293 |
osher | +0.285 |
Edge | +0.277 |
Neg logit contributions | |
leys | -0.316 |
idad | -0.278 |
amina | -0.277 |
ici | -0.270 |
tru | -0.269 |
Token | how |
Token ID | 703 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
keys | +2.973 |
goats | +2.972 |
swers | +2.777 |
osher | +2.669 |
Edge | +2.603 |
Neg logit contributions | |
leys | -3.954 |
idad | -3.481 |
amina | -3.455 |
ici | -3.441 |
tru | -3.359 |
Token | this |
Token ID | 428 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
goats | +4.301 |
keys | +4.271 |
swers | +3.935 |
osher | +3.761 |
eer | +3.697 |
Neg logit contributions | |
leys | -5.422 |
idad | -4.702 |
ici | -4.702 |
amina | -4.657 |
tru | -4.543 |
Token | pr |
Token ID | 778 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
goats | +4.964 |
keys | +4.863 |
swers | +4.498 |
osher | +4.287 |
eer | +4.276 |
Neg logit contributions | |
leys | -7.053 |
ici | -6.192 |
idad | -6.159 |
amina | -6.116 |
tru | -5.864 |
Token | imate |
Token ID | 1920 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
keys | +2.558 |
goats | +2.495 |
swers | +2.424 |
osher | +2.405 |
Edge | +2.315 |
Neg logit contributions | |
leys | -1.891 |
idad | -1.587 |
tru | -1.555 |
ici | -1.528 |
amina | -1.525 |
Token | was |
Token ID | 373 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
goats | +4.744 |
keys | +4.645 |
swers | +4.342 |
eer | +4.180 |
osher | +4.108 |
Neg logit contributions | |
leys | -6.064 |
amina | -5.279 |
idad | -5.278 |
ici | -5.266 |
tru | -5.110 |
Token | uniquely |
Token ID | 24139 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
goats | +9.397 |
keys | +8.939 |
swers | +8.316 |
eer | +8.286 |
Khe | +7.851 |
Neg logit contributions | |
leys | -13.249 |
ici | -11.321 |
idad | -11.309 |
ulk | -10.741 |
amina | -10.738 |
Token | adapted |
Token ID | 16573 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
goats | +9.110 |
keys | +8.730 |
eer | +8.382 |
suited | +8.087 |
swers | +7.675 |
Neg logit contributions | |
leys | -18.186 |
ici | -16.661 |
idad | -15.544 |
ulk | -15.322 |
amina | -15.071 |
Token | to |
Token ID | 284 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
goats | +5.787 |
keys | +5.718 |
swers | +5.153 |
osher | +4.922 |
eer | +4.902 |
Neg logit contributions | |
leys | -8.914 |
idad | -7.906 |
ici | -7.782 |
tru | -7.723 |
amina | -7.717 |
Token | its |
Token ID | 663 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
goats | +7.348 |
keys | +7.280 |
swers | +6.682 |
eer | +6.535 |
Edge | +6.439 |
Neg logit contributions | |
leys | -9.834 |
ici | -8.388 |
idad | -8.329 |
amina | -8.209 |
tru | -8.111 |
Token | environment |
Token ID | 2858 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
goats | +7.319 |
keys | +7.186 |
swers | +6.369 |
osher | +6.214 |
Khe | +6.190 |
Neg logit contributions | |
leys | -10.486 |
ici | -9.219 |
amina | -8.864 |
idad | -8.858 |
ulk | -8.525 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
goats | +4.511 |
keys | +4.507 |
swers | +4.187 |
osher | +4.041 |
Edge | +3.945 |
Neg logit contributions | |
leys | -5.534 |
idad | -4.884 |
amina | -4.855 |
tru | -4.743 |
ici | -4.735 |
Token | leneck |
Token ID | 43163 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
leys | +3.089 |
amina | +2.606 |
idad | +2.562 |
ici | +2.457 |
tru | +2.430 |
Neg logit contributions | |
goats | -4.727 |
keys | -4.608 |
swers | -4.457 |
osher | -4.418 |
Tips | -4.247 |
Token | Buffer |
Token ID | 47017 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
keys | +3.858 |
goats | +3.828 |
swers | +3.644 |
Edge | +3.558 |
osher | +3.529 |
Neg logit contributions | |
leys | -4.211 |
amina | -3.654 |
idad | -3.640 |
ici | -3.600 |
tru | -3.525 |
Token | Size |
Token ID | 12849 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
leys | +0.852 |
idad | +0.753 |
amina | +0.747 |
tru | +0.727 |
ici | +0.726 |
Neg logit contributions | |
keys | -0.823 |
goats | -0.809 |
swers | -0.777 |
osher | -0.758 |
Tips | -0.728 |
Token | point |
Token ID | 966 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
leys | +2.370 |
idad | +2.101 |
amina | +2.066 |
tru | +2.042 |
ici | +2.027 |
Neg logit contributions | |
keys | -2.384 |
goats | -2.342 |
swers | -2.264 |
osher | -2.221 |
Tips | -2.114 |
Token | ( |
Token ID | 357 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
leys | +2.032 |
idad | +1.787 |
amina | +1.781 |
ici | +1.735 |
tru | +1.729 |
Neg logit contributions | |
keys | -1.999 |
goats | -1.955 |
swers | -1.883 |
osher | -1.844 |
Edge | -1.778 |
Token | green |
Token ID | 14809 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
keys | +7.158 |
goats | +6.434 |
swers | +6.348 |
Edge | +6.336 |
osher | +6.134 |
Neg logit contributions | |
leys | -9.210 |
tru | -8.253 |
idad | -8.172 |
amina | -8.154 |
ici | -7.995 |
Token | dot |
Token ID | 16605 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
goats | +11.249 |
keys | +10.683 |
Edge | +10.513 |
swers | +10.310 |
goat | +9.536 |
Neg logit contributions | |
leys | -14.367 |
idad | -13.208 |
amina | -13.148 |
tru | -12.802 |
ici | -12.652 |
Token | above |
Token ID | 2029 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
goats | +4.858 |
keys | +4.831 |
swers | +4.532 |
osher | +4.277 |
Edge | +4.224 |
Neg logit contributions | |
leys | -7.962 |
amina | -7.189 |
idad | -7.186 |
ici | -7.114 |
tru | -7.033 |
Token | ). |
Token ID | 737 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
keys | +4.222 |
goats | +4.203 |
swers | +3.963 |
osher | +3.658 |
Edge | +3.567 |
Neg logit contributions | |
leys | -9.388 |
idad | -8.555 |
amina | -8.524 |
ici | -8.406 |
tru | -8.265 |
Token |
|
Token ID | 198 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
leys | +1.497 |
idad | +1.290 |
amina | +1.286 |
tru | +1.272 |
ici | +1.257 |
Neg logit contributions | |
keys | -1.686 |
goats | -1.665 |
swers | -1.606 |
osher | -1.590 |
Edge | -1.503 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
leys | +0.625 |
idad | +0.544 |
amina | +0.541 |
ici | +0.524 |
tru | +0.519 |
Neg logit contributions | |
keys | -0.696 |
goats | -0.683 |
swers | -0.657 |
osher | -0.638 |
Edge | -0.628 |
Token | unemployment |
Token ID | 10681 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
keys | +1.939 |
goats | +1.919 |
swers | +1.829 |
osher | +1.778 |
Edge | +1.724 |
Neg logit contributions | |
leys | -2.119 |
amina | -1.862 |
idad | -1.862 |
ici | -1.821 |
tru | -1.788 |
Token | and |
Token ID | 290 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
goats | +4.215 |
keys | +4.171 |
swers | +3.884 |
Edge | +3.721 |
osher | +3.718 |
Neg logit contributions | |
leys | -5.435 |
amina | -4.796 |
idad | -4.722 |
ici | -4.692 |
tru | -4.544 |
Token | a |
Token ID | 257 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
goats | +5.339 |
keys | +5.213 |
swers | +4.869 |
osher | +4.708 |
eer | +4.658 |
Neg logit contributions | |
leys | -6.135 |
ici | -5.363 |
amina | -5.340 |
idad | -5.319 |
ulk | -4.975 |
Token | sovereign |
Token ID | 18901 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
goats | +3.757 |
keys | +3.757 |
swers | +3.525 |
osher | +3.490 |
eer | +3.327 |
Neg logit contributions | |
leys | -3.905 |
idad | -3.386 |
amina | -3.381 |
ici | -3.333 |
tru | -3.203 |
Token | debt |
Token ID | 5057 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
keys | +1.812 |
goats | +1.798 |
swers | +1.715 |
osher | +1.661 |
Edge | +1.605 |
Neg logit contributions | |
leys | -2.150 |
amina | -1.870 |
idad | -1.865 |
ici | -1.830 |
tru | -1.798 |
Token | default |
Token ID | 4277 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
leys | +4.144 |
tru | +3.763 |
idad | +3.754 |
amina | +3.737 |
ici | +3.615 |
Neg logit contributions | |
keys | -5.069 |
goats | -4.860 |
swers | -4.776 |
osher | -4.713 |
Tips | -4.591 |
Token | achieve |
Token ID | 4620 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
goats | +11.490 |
keys | +10.914 |
eer | +10.706 |
swers | +10.512 |
Khe | +9.815 |
Neg logit contributions | |
leys | -15.434 |
amina | -12.977 |
idad | -12.661 |
ici | -12.631 |
tru | -11.744 |
Token | such |
Token ID | 884 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
keys | +5.048 |
goats | +5.015 |
swers | +4.668 |
eer | +4.466 |
osher | +4.443 |
Neg logit contributions | |
leys | -7.334 |
amina | -6.432 |
idad | -6.361 |
ici | -6.332 |
tru | -6.137 |
Token | prosperity |
Token ID | 19519 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
keys | +2.183 |
goats | +2.148 |
swers | +2.043 |
osher | +1.978 |
Edge | +1.908 |
Neg logit contributions | |
leys | -2.820 |
idad | -2.497 |
amina | -2.494 |
ici | -2.448 |
tru | -2.413 |
Token | so |
Token ID | 523 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
goats | +6.628 |
keys | +6.469 |
swers | +6.005 |
eer | +5.720 |
Khe | +5.588 |
Neg logit contributions | |
leys | -10.759 |
amina | -9.635 |
idad | -9.463 |
ici | -9.306 |
tru | -9.097 |
Token | rapidly |
Token ID | 8902 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
goats | +4.885 |
keys | +4.881 |
swers | +4.507 |
osher | +4.326 |
eer | +4.278 |
Neg logit contributions | |
leys | -6.667 |
amina | -5.913 |
idad | -5.864 |
ici | -5.742 |
tru | -5.555 |
Token | , |
Token ID | 11 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
keys | +0.710 |
goats | +0.699 |
swers | +0.669 |
osher | +0.651 |
Edge | +0.630 |
Neg logit contributions | |
leys | -0.791 |
idad | -0.699 |
amina | -0.696 |
ici | -0.678 |
tru | -0.675 |
Token | who |
Token ID | 508 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
goats | +5.335 |
keys | +5.301 |
swers | +4.915 |
osher | +4.729 |
Edge | +4.693 |
Neg logit contributions | |
leys | -6.341 |
idad | -5.682 |
amina | -5.679 |
ici | -5.491 |
tru | -5.312 |
Token | had |
Token ID | 550 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
keys | +2.415 |
goats | +2.406 |
swers | +2.252 |
osher | +2.193 |
Edge | +2.130 |
Neg logit contributions | |
leys | -2.827 |
idad | -2.512 |
amina | -2.508 |
ici | -2.438 |
tru | -2.407 |
Token | started |
Token ID | 2067 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
keys | +2.891 |
goats | +2.878 |
swers | +2.711 |
osher | +2.613 |
Edge | +2.541 |
Neg logit contributions | |
leys | -3.489 |
amina | -3.086 |
idad | -3.072 |
ici | -2.984 |
tru | -2.960 |
Token | at |
Token ID | 379 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
goats | +5.782 |
keys | +5.737 |
swers | +5.351 |
Edge | +5.073 |
osher | +5.055 |
Neg logit contributions | |
leys | -6.717 |
amina | -6.024 |
idad | -5.998 |
ici | -5.758 |
tru | -5.568 |
Token | Goldman |
Token ID | 18740 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
goats | +4.823 |
keys | +4.798 |
swers | +4.569 |
osher | +4.297 |
Edge | +4.234 |
Neg logit contributions | |
leys | -6.049 |
idad | -5.399 |
amina | -5.395 |
ici | -5.164 |
tru | -5.037 |
Token | eight |
Token ID | 3624 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
goats | +10.002 |
keys | +9.436 |
Goodman | +8.967 |
swers | +8.878 |
Tips | +8.734 |
Neg logit contributions | |
leys | -15.500 |
amina | -14.030 |
idad | -13.702 |
fulness | -12.984 |
tru | -12.951 |
Token | years |
Token ID | 812 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
goats | +3.996 |
keys | +3.991 |
swers | +3.548 |
Tips | +3.342 |
osher | +3.312 |
Neg logit contributions | |
leys | -7.839 |
amina | -7.203 |
idad | -7.090 |
ici | -6.865 |
tru | -6.780 |
Token | before |
Token ID | 878 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
leys | +0.150 |
idad | +0.136 |
amina | +0.135 |
ici | +0.133 |
tru | +0.133 |
Neg logit contributions | |
keys | -0.082 |
goats | -0.080 |
swers | -0.076 |
osher | -0.073 |
Edge | -0.070 |
Token | Cohn |
Token ID | 45005 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
keys | +2.636 |
goats | +2.618 |
swers | +2.462 |
osher | +2.372 |
Edge | +2.314 |
Neg logit contributions | |
leys | -3.530 |
idad | -3.176 |
amina | -3.159 |
ici | -3.057 |
tru | -3.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
keys | +0.118 |
goats | +0.116 |
swers | +0.112 |
osher | +0.109 |
Edge | +0.106 |
Neg logit contributions | |
leys | -0.122 |
idad | -0.107 |
amina | -0.106 |
ici | -0.104 |
tru | -0.103 |
Token | that |
Token ID | 326 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
keys | +1.741 |
goats | +1.716 |
swers | +1.644 |
osher | +1.593 |
Edge | +1.547 |
Neg logit contributions | |
leys | -1.988 |
amina | -1.751 |
idad | -1.751 |
ici | -1.703 |
tru | -1.681 |
Token | American |
Token ID | 1605 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
leys | +0.107 |
idad | +0.095 |
amina | +0.094 |
tru | +0.093 |
ici | +0.092 |
Neg logit contributions | |
keys | -0.092 |
goats | -0.090 |
swers | -0.087 |
osher | -0.085 |
Edge | -0.082 |
Token | judicial |
Token ID | 13657 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
keys | +2.140 |
goats | +2.116 |
swers | +2.024 |
osher | +1.960 |
Edge | +1.902 |
Neg logit contributions | |
leys | -2.635 |
amina | -2.341 |
idad | -2.322 |
ici | -2.248 |
tru | -2.230 |
Token | system |
Token ID | 1080 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
keys | +2.272 |
goats | +2.260 |
swers | +2.154 |
osher | +2.083 |
Edge | +2.041 |
Neg logit contributions | |
leys | -2.330 |
amina | -2.051 |
idad | -2.040 |
ici | -1.988 |
tru | -1.947 |
Token | is |
Token ID | 318 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
leys | +0.268 |
idad | +0.239 |
amina | +0.236 |
tru | +0.233 |
ici | +0.232 |
Neg logit contributions | |
keys | -0.225 |
goats | -0.220 |
swers | -0.211 |
osher | -0.206 |
Edge | -0.199 |
Token | more |
Token ID | 517 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
keys | +3.559 |
goats | +3.556 |
swers | +3.358 |
osher | +3.225 |
Edge | +3.150 |
Neg logit contributions | |
leys | -4.872 |
amina | -4.317 |
idad | -4.313 |
ici | -4.231 |
tru | -4.071 |
Token | loyal |
Token ID | 9112 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
goats | +10.345 |
keys | +9.726 |
swers | +9.391 |
Khe | +9.380 |
kosher | +9.346 |
Neg logit contributions | |
leys | -15.236 |
ici | -13.613 |
amina | -13.556 |
idad | -13.298 |
ulk | -12.821 |
Token | when |
Token ID | 618 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
keys | +5.793 |
goats | +5.693 |
swers | +5.295 |
osher | +5.131 |
eer | +5.056 |
Neg logit contributions | |
leys | -8.765 |
amina | -7.895 |
idad | -7.796 |
ici | -7.500 |
tru | -7.459 |
Token | it |
Token ID | 340 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
goats | +4.482 |
keys | +4.474 |
swers | +4.206 |
osher | +3.957 |
Tips | +3.865 |
Neg logit contributions | |
leys | -6.673 |
idad | -5.948 |
amina | -5.943 |
ici | -5.788 |
tru | -5.633 |
Token | comes |
Token ID | 2058 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
keys | +2.273 |
goats | +2.245 |
swers | +2.128 |
osher | +2.051 |
Edge | +1.971 |
Neg logit contributions | |
leys | -3.168 |
idad | -2.825 |
amina | -2.818 |
ici | -2.758 |
tru | -2.721 |
Token | to |
Token ID | 284 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
keys | +2.756 |
goats | +2.716 |
swers | +2.582 |
osher | +2.497 |
Edge | +2.424 |
Neg logit contributions | |
leys | -3.637 |
idad | -3.233 |
amina | -3.218 |
ici | -3.147 |
tru | -3.103 |
Token | Robbie |
Token ID | 34855 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
keys | +2.887 |
goats | +2.858 |
swers | +2.691 |
osher | +2.600 |
Edge | +2.595 |
Neg logit contributions | |
leys | -3.153 |
idad | -2.780 |
amina | -2.759 |
ici | -2.684 |
tru | -2.646 |
Token | M |
Token ID | 337 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
keys | +1.009 |
goats | +0.996 |
swers | +0.956 |
osher | +0.935 |
Edge | +0.913 |
Neg logit contributions | |
leys | -0.798 |
idad | -0.695 |
amina | -0.690 |
ici | -0.664 |
tru | -0.663 |
Token | ce |
Token ID | 344 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
keys | +1.669 |
goats | +1.623 |
swers | +1.537 |
osher | +1.512 |
Edge | +1.456 |
Neg logit contributions | |
leys | -1.728 |
idad | -1.504 |
amina | -1.503 |
tru | -1.473 |
ici | -1.466 |
Token | wen |
Token ID | 21006 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
leys | +2.443 |
amina | +2.133 |
idad | +2.130 |
ici | +2.079 |
tru | +2.007 |
Neg logit contributions | |
keys | -2.391 |
goats | -2.379 |
swers | -2.310 |
osher | -2.239 |
Tips | -2.189 |
Token | ( |
Token ID | 357 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
keys | +0.419 |
goats | +0.413 |
swers | +0.397 |
osher | +0.386 |
Edge | +0.373 |
Neg logit contributions | |
leys | -0.452 |
idad | -0.398 |
amina | -0.396 |
ici | -0.387 |
tru | -0.384 |
Token | Green |
Token ID | 13719 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
keys | +4.787 |
goats | +4.461 |
Edge | +4.360 |
swers | +4.307 |
Tips | +4.238 |
Neg logit contributions | |
leys | -6.431 |
idad | -5.836 |
amina | -5.787 |
ici | -5.614 |
tru | -5.573 |
Token | Edge |
Token ID | 37021 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Edge | +7.712 |
keys | +5.037 |
swers | +4.323 |
goats | +4.305 |
Tips | +4.127 |
Neg logit contributions | |
leys | -19.955 |
tru | -18.169 |
ulk | -17.764 |
idad | -17.572 |
amina | -17.467 |
Token | Cycling |
Token ID | 25550 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
goats | +5.741 |
keys | +5.568 |
swers | +5.105 |
Edge | +5.100 |
osher | +4.952 |
Neg logit contributions | |
leys | -9.894 |
amina | -8.977 |
idad | -8.881 |
ici | -8.499 |
tru | -8.479 |
Token | Team |
Token ID | 4816 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
goats | +3.058 |
keys | +3.038 |
swers | +2.778 |
Tips | +2.764 |
Edge | +2.717 |
Neg logit contributions | |
leys | -5.435 |
amina | -4.950 |
idad | -4.880 |
ici | -4.824 |
tru | -4.748 |
Token | ) |
Token ID | 8 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
keys | +4.886 |
goats | +4.837 |
swers | +4.451 |
Edge | +4.424 |
Tips | +4.308 |
Neg logit contributions | |
leys | -11.491 |
idad | -10.466 |
amina | -10.306 |
ici | -10.267 |
tru | -9.763 |
Token | s |
Token ID | 264 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
keys | +0.694 |
goats | +0.680 |
swers | +0.656 |
osher | +0.640 |
Edge | +0.620 |
Neg logit contributions | |
leys | -0.684 |
idad | -0.600 |
amina | -0.597 |
ici | -0.582 |
tru | -0.581 |
Token | in |
Token ID | 287 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
keys | +1.941 |
goats | +1.919 |
swers | +1.828 |
osher | +1.781 |
Edge | +1.717 |
Neg logit contributions | |
leys | -2.117 |
idad | -1.860 |
amina | -1.853 |
tru | -1.799 |
ici | -1.795 |
Token | medi |
Token ID | 16957 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
keys | +0.460 |
goats | +0.451 |
swers | +0.432 |
osher | +0.420 |
Edge | +0.406 |
Neg logit contributions | |
leys | -0.554 |
idad | -0.492 |
amina | -0.490 |
ici | -0.478 |
tru | -0.477 |
Token | ating |
Token ID | 803 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
leys | +0.400 |
idad | +0.321 |
amina | +0.318 |
ici | +0.304 |
tru | +0.298 |
Neg logit contributions | |
keys | -0.912 |
goats | -0.903 |
swers | -0.879 |
osher | -0.863 |
Edge | -0.845 |
Token | in |
Token ID | 287 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
leys | +2.529 |
idad | +2.259 |
amina | +2.207 |
tru | +2.179 |
ici | +2.168 |
Neg logit contributions | |
keys | -2.277 |
goats | -2.222 |
swers | -2.123 |
osher | -2.104 |
Edge | -2.013 |
Token | a |
Token ID | 257 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
keys | +1.021 |
goats | +1.004 |
swers | +0.961 |
osher | +0.933 |
Edge | +0.902 |
Neg logit contributions | |
leys | -1.257 |
idad | -1.117 |
amina | -1.113 |
ici | -1.086 |
tru | -1.081 |
Token | highly |
Token ID | 4047 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
keys | +2.270 |
goats | +2.240 |
swers | +2.148 |
osher | +2.086 |
Edge | +2.010 |
Neg logit contributions | |
leys | -2.580 |
amina | -2.275 |
idad | -2.272 |
ici | -2.208 |
tru | -2.172 |
Token | heated |
Token ID | 16968 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
keys | +10.127 |
goats | +10.052 |
swers | +9.203 |
osher | +9.157 |
Khe | +9.094 |
Neg logit contributions | |
leys | -14.803 |
amina | -13.098 |
idad | -12.898 |
ici | -12.458 |
ulk | -12.118 |
Token | political |
Token ID | 1964 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
keys | +3.220 |
goats | +3.215 |
swers | +3.076 |
osher | +2.974 |
Edge | +2.891 |
Neg logit contributions | |
leys | -3.442 |
amina | -3.057 |
idad | -3.026 |
ici | -2.935 |
tru | -2.878 |
Token | conflict |
Token ID | 5358 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
goats | +4.483 |
keys | +4.395 |
swers | +4.226 |
osher | +4.102 |
Edge | +3.990 |
Neg logit contributions | |
leys | -4.995 |
amina | -4.425 |
idad | -4.406 |
ici | -4.252 |
ulk | -4.092 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
keys | +2.137 |
goats | +2.115 |
swers | +2.024 |
osher | +1.969 |
Edge | +1.903 |
Neg logit contributions | |
leys | -2.463 |
idad | -2.176 |
amina | -2.175 |
ici | -2.108 |
tru | -2.095 |
Token | Needless |
Token ID | 39114 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
leys | +3.846 |
idad | +3.393 |
ici | +3.324 |
tru | +3.311 |
amina | +3.302 |
Neg logit contributions | |
keys | -4.486 |
goats | -4.477 |
osher | -4.267 |
swers | -4.233 |
Edge | -3.967 |
Token | , |
Token ID | 11 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
keys | +3.864 |
goats | +3.859 |
swers | +3.591 |
osher | +3.508 |
Tips | +3.409 |
Neg logit contributions | |
leys | -4.956 |
idad | -4.414 |
amina | -4.372 |
ici | -4.259 |
tru | -4.159 |
Token | this |
Token ID | 428 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
keys | +1.910 |
goats | +1.894 |
swers | +1.797 |
osher | +1.725 |
Tips | +1.675 |
Neg logit contributions | |
leys | -2.477 |
idad | -2.218 |
amina | -2.198 |
ici | -2.145 |
tru | -2.124 |
Token | mourn |
Token ID | 25722 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
keys | +0.122 |
goats | +0.119 |
swers | +0.115 |
osher | +0.112 |
Edge | +0.108 |
Neg logit contributions | |
leys | -0.149 |
idad | -0.132 |
amina | -0.131 |
tru | -0.128 |
ici | -0.128 |
Token | ful |
Token ID | 913 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
leys | +1.726 |
idad | +1.456 |
amina | +1.434 |
tru | +1.424 |
fulness | +1.407 |
Neg logit contributions | |
keys | -2.487 |
goats | -2.443 |
swers | -2.375 |
osher | -2.320 |
Tips | -2.256 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
keys | +0.344 |
goats | +0.339 |
swers | +0.327 |
osher | +0.320 |
Edge | +0.311 |
Neg logit contributions | |
leys | -0.285 |
idad | -0.246 |
amina | -0.245 |
ici | -0.238 |
tru | -0.236 |
Token | highly |
Token ID | 4047 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
goats | +3.765 |
keys | +3.737 |
swers | +3.555 |
osher | +3.434 |
Tips | +3.300 |
Neg logit contributions | |
leys | -4.305 |
amina | -3.776 |
idad | -3.774 |
ici | -3.691 |
tru | -3.547 |
Token | distraught |
Token ID | 48629 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
goats | +10.940 |
keys | +10.559 |
swers | +9.813 |
eer | +9.430 |
Tips | +9.334 |
Neg logit contributions | |
leys | -14.626 |
idad | -12.757 |
amina | -12.571 |
ici | -12.160 |
ulk | -11.909 |
Token | dummy |
Token ID | 31548 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
leys | +1.281 |
idad | +1.119 |
amina | +1.106 |
tru | +1.091 |
ici | +1.068 |
Neg logit contributions | |
keys | -1.660 |
goats | -1.609 |
swers | -1.571 |
osher | -1.547 |
Edge | -1.506 |
Token | might |
Token ID | 1244 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
keys | +2.099 |
goats | +2.098 |
swers | +1.963 |
osher | +1.888 |
Edge | +1.825 |
Neg logit contributions | |
leys | -2.957 |
amina | -2.652 |
idad | -2.643 |
ici | -2.600 |
tru | -2.531 |
Token | be |
Token ID | 307 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
keys | +0.935 |
goats | +0.920 |
swers | +0.876 |
osher | +0.848 |
Edge | +0.817 |
Neg logit contributions | |
leys | -1.312 |
idad | -1.174 |
amina | -1.170 |
ici | -1.144 |
tru | -1.138 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
leys | +2.605 |
idad | +2.340 |
amina | +2.338 |
tru | +2.328 |
ici | +2.268 |
Neg logit contributions | |
keys | -2.306 |
goats | -2.212 |
swers | -2.164 |
osher | -2.161 |
Edge | -2.050 |
Token | the |
Token ID | 262 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
keys | +0.698 |
goats | +0.684 |
swers | +0.656 |
osher | +0.640 |
Edge | +0.619 |
Neg logit contributions | |
leys | -0.810 |
idad | -0.716 |
amina | -0.714 |
ici | -0.697 |
tru | -0.694 |
Token | FBI |
Token ID | 5349 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
leys | +0.503 |
idad | +0.444 |
amina | +0.441 |
tru | +0.432 |
ici | +0.431 |
Neg logit contributions | |
keys | -0.482 |
goats | -0.471 |
swers | -0.453 |
osher | -0.446 |
Edge | -0.431 |
Token | in |
Token ID | 287 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
leys | +2.008 |
idad | +1.798 |
amina | +1.777 |
tru | +1.763 |
ici | +1.756 |
Neg logit contributions | |
keys | -1.659 |
goats | -1.604 |
swers | -1.546 |
osher | -1.520 |
Edge | -1.462 |
Token | particular |
Token ID | 1948 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
leys | +0.567 |
idad | +0.504 |
amina | +0.501 |
ici | +0.491 |
tru | +0.490 |
Neg logit contributions | |
keys | -0.485 |
goats | -0.477 |
swers | -0.458 |
osher | -0.448 |
Edge | -0.432 |
Token | is |
Token ID | 318 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
keys | +0.021 |
goats | +0.020 |
swers | +0.020 |
osher | +0.019 |
Edge | +0.018 |
Neg logit contributions | |
leys | -0.025 |
idad | -0.023 |
amina | -0.022 |
ici | -0.022 |
tru | -0.022 |
Token | highly |
Token ID | 4047 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
keys | +2.726 |
goats | +2.697 |
swers | +2.545 |
osher | +2.463 |
Tips | +2.380 |
Neg logit contributions | |
leys | -3.875 |
idad | -3.468 |
amina | -3.428 |
ici | -3.349 |
tru | -3.304 |
Token | distrust |
Token ID | 30086 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
keys | +8.824 |
goats | +8.588 |
Tips | +8.011 |
kosher | +7.952 |
osher | +7.916 |
Neg logit contributions | |
leys | -16.337 |
idad | -14.111 |
amina | -14.068 |
ici | -13.578 |
ulk | -13.319 |
Token | ful |
Token ID | 913 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
keys | +2.035 |
goats | +2.012 |
swers | +1.954 |
osher | +1.921 |
Edge | +1.882 |
Neg logit contributions | |
leys | -0.918 |
idad | -0.740 |
amina | -0.735 |
ici | -0.694 |
tru | -0.692 |
Token | of |
Token ID | 286 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
keys | +2.644 |
goats | +2.635 |
swers | +2.479 |
osher | +2.412 |
Edge | +2.289 |
Neg logit contributions | |
leys | -4.178 |
idad | -3.778 |
amina | -3.767 |
tru | -3.648 |
ici | -3.629 |
Token | bio |
Token ID | 13401 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
leys | +0.734 |
amina | +0.643 |
idad | +0.642 |
tru | +0.632 |
ici | +0.628 |
Neg logit contributions | |
keys | -0.684 |
goats | -0.662 |
swers | -0.643 |
osher | -0.632 |
Edge | -0.610 |
Token | h |
Token ID | 71 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
leys | +4.249 |
idad | +3.671 |
ici | +3.564 |
amina | +3.525 |
tru | +3.468 |
Neg logit contributions | |
goats | -5.099 |
keys | -5.072 |
swers | -4.982 |
osher | -4.887 |
Edge | -4.773 |
Token | the |
Token ID | 262 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
leys | +2.250 |
amina | +1.978 |
idad | +1.975 |
tru | +1.933 |
ici | +1.929 |
Neg logit contributions | |
keys | -2.408 |
goats | -2.324 |
swers | -2.241 |
osher | -2.239 |
Edge | -2.148 |
Token | health |
Token ID | 1535 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
leys | +0.577 |
idad | +0.512 |
amina | +0.510 |
tru | +0.498 |
ici | +0.498 |
Neg logit contributions | |
keys | -0.519 |
goats | -0.506 |
swers | -0.489 |
osher | -0.480 |
Edge | -0.460 |
Token | care |
Token ID | 1337 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
leys | +0.484 |
idad | +0.433 |
amina | +0.430 |
tru | +0.420 |
ici | +0.420 |
Neg logit contributions | |
keys | -0.368 |
goats | -0.360 |
swers | -0.346 |
osher | -0.337 |
Edge | -0.323 |
Token | legislation |
Token ID | 5520 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
leys | +4.573 |
idad | +4.028 |
amina | +3.993 |
tru | +3.979 |
ici | +3.885 |
Neg logit contributions | |
keys | -4.803 |
osher | -4.588 |
goats | -4.578 |
swers | -4.535 |
Tips | -4.325 |
Token | was |
Token ID | 373 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
leys | +5.500 |
amina | +4.814 |
tru | +4.780 |
idad | +4.739 |
fulness | +4.672 |
Neg logit contributions | |
keys | -5.767 |
swers | -5.424 |
goats | -5.418 |
osher | -5.413 |
Edge | -5.281 |
Token | highly |
Token ID | 4047 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
keys | +1.964 |
goats | +1.938 |
swers | +1.847 |
osher | +1.789 |
Edge | +1.725 |
Neg logit contributions | |
leys | -2.492 |
idad | -2.217 |
amina | -2.214 |
ici | -2.147 |
tru | -2.119 |
Token | uncertain |
Token ID | 8627 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
keys | +9.888 |
goats | +9.415 |
uncertain | +8.769 |
osher | +8.663 |
kosher | +8.574 |
Neg logit contributions | |
leys | -15.346 |
amina | -14.090 |
idad | -13.843 |
ulk | -13.161 |
ici | -12.899 |
Token | as |
Token ID | 355 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
keys | +3.693 |
goats | +3.674 |
swers | +3.487 |
osher | +3.397 |
Edge | +3.256 |
Neg logit contributions | |
leys | -4.839 |
idad | -4.272 |
amina | -4.268 |
ici | -4.133 |
tru | -4.125 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
keys | +0.922 |
goats | +0.905 |
swers | +0.868 |
osher | +0.850 |
Edge | +0.822 |
Neg logit contributions | |
leys | -0.995 |
idad | -0.875 |
amina | -0.872 |
ici | -0.851 |
tru | -0.847 |
Token | leaders |
Token ID | 2766 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
keys | +1.254 |
goats | +1.237 |
swers | +1.184 |
osher | +1.147 |
Edge | +1.119 |
Neg logit contributions | |
leys | -1.316 |
idad | -1.159 |
amina | -1.157 |
ici | -1.124 |
tru | -1.119 |
Token | quickly |
Token ID | 2952 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
leys | +1.866 |
idad | +1.638 |
amina | +1.626 |
ici | +1.591 |
tru | +1.588 |
Neg logit contributions | |
keys | -1.857 |
goats | -1.815 |
swers | -1.762 |
osher | -1.742 |
Tips | -1.668 |
Token | � |
Token ID | 447 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
leys | +2.591 |
idad | +2.251 |
amina | +2.250 |
ici | +2.237 |
tru | +2.234 |
Neg logit contributions | |
keys | -2.731 |
goats | -2.671 |
swers | -2.555 |
osher | -2.513 |
Edge | -2.444 |
Token | � |
Token ID | 247 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
keys | +1.096 |
goats | +1.080 |
swers | +1.039 |
osher | +1.002 |
Edge | +0.974 |
Neg logit contributions | |
leys | -1.275 |
idad | -1.130 |
amina | -1.129 |
ici | -1.100 |
tru | -1.094 |
Token | s |
Token ID | 82 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
keys | +0.181 |
goats | +0.178 |
swers | +0.171 |
osher | +0.167 |
Edge | +0.161 |
Neg logit contributions | |
leys | -0.196 |
idad | -0.173 |
amina | -0.172 |
ici | -0.168 |
tru | -0.167 |
Token | environment |
Token ID | 2858 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
keys | +0.235 |
goats | +0.231 |
swers | +0.221 |
osher | +0.215 |
Edge | +0.207 |
Neg logit contributions | |
leys | -0.283 |
idad | -0.251 |
amina | -0.250 |
ici | -0.244 |
tru | -0.244 |
Token | is |
Token ID | 318 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
keys | +2.376 |
goats | +2.354 |
swers | +2.226 |
osher | +2.142 |
Tips | +2.081 |
Neg logit contributions | |
leys | -3.230 |
amina | -2.893 |
idad | -2.879 |
ici | -2.808 |
tru | -2.765 |
Token | very |
Token ID | 845 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
goats | +6.016 |
keys | +5.944 |
swers | +5.543 |
osher | +5.340 |
Edge | +5.262 |
Neg logit contributions | |
leys | -8.698 |
idad | -7.878 |
amina | -7.855 |
ici | -7.689 |
ulk | -7.320 |
Token | dynamic |
Token ID | 8925 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
goats | +10.074 |
keys | +9.192 |
swers | +8.804 |
eer | +8.710 |
hands | +8.569 |
Neg logit contributions | |
leys | -14.903 |
amina | -13.687 |
ici | -13.517 |
idad | -13.505 |
ppa | -12.746 |
Token | . |
Token ID | 13 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
keys | +3.428 |
goats | +3.416 |
swers | +3.238 |
osher | +3.137 |
Tips | +3.064 |
Neg logit contributions | |
leys | -4.255 |
amina | -3.784 |
idad | -3.761 |
ici | -3.626 |
tru | -3.626 |
Token | Lean |
Token ID | 45661 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
keys | +2.507 |
goats | +2.468 |
swers | +2.367 |
osher | +2.272 |
Edge | +2.254 |
Neg logit contributions | |
leys | -2.699 |
idad | -2.389 |
amina | -2.381 |
ici | -2.296 |
tru | -2.274 |
Token | or |
Token ID | 393 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
keys | +2.206 |
goats | +2.185 |
swers | +2.062 |
osher | +1.994 |
Edge | +1.928 |
Neg logit contributions | |
leys | -3.402 |
idad | -3.066 |
amina | -3.065 |
ici | -2.968 |
tru | -2.950 |
Token | six |
Token ID | 2237 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
leys | +1.566 |
amina | +1.397 |
idad | +1.396 |
tru | +1.386 |
ici | +1.381 |
Neg logit contributions | |
keys | -1.151 |
goats | -1.118 |
swers | -1.069 |
osher | -1.041 |
Edge | -0.994 |
Token | Donkey |
Token ID | 43823 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
goats | +4.402 |
keys | +4.369 |
swers | +3.906 |
eer | +3.745 |
osher | +3.709 |
Neg logit contributions | |
leys | -8.695 |
amina | -8.237 |
idad | -8.156 |
tru | -7.914 |
ici | -7.767 |
Token | Brewery |
Token ID | 31003 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
keys | +0.498 |
goats | +0.489 |
swers | +0.469 |
osher | +0.455 |
Edge | +0.440 |
Neg logit contributions | |
leys | -0.600 |
idad | -0.532 |
amina | -0.530 |
ici | -0.517 |
tru | -0.515 |
Token | is |
Token ID | 318 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
keys | +0.875 |
goats | +0.861 |
swers | +0.823 |
osher | +0.797 |
Edge | +0.771 |
Neg logit contributions | |
leys | -1.089 |
idad | -0.969 |
amina | -0.966 |
ici | -0.942 |
tru | -0.936 |
Token | definitely |
Token ID | 4753 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
keys | +2.165 |
goats | +2.135 |
swers | +2.003 |
osher | +1.942 |
Edge | +1.884 |
Neg logit contributions | |
leys | -3.026 |
idad | -2.722 |
amina | -2.711 |
ici | -2.627 |
tru | -2.594 |
Token | looking |
Token ID | 2045 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
goats | +5.555 |
keys | +5.511 |
swers | +4.980 |
osher | +4.866 |
Edge | +4.775 |
Neg logit contributions | |
leys | -8.298 |
amina | -7.612 |
idad | -7.482 |
ici | -7.180 |
ulk | -7.015 |
Token | very |
Token ID | 845 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
keys | +4.929 |
goats | +4.874 |
swers | +4.238 |
osher | +4.197 |
Edge | +4.123 |
Neg logit contributions | |
leys | -9.951 |
idad | -9.037 |
ici | -8.929 |
amina | -8.901 |
tru | -8.549 |
Token | bright |
Token ID | 6016 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
goats | +7.001 |
keys | +6.602 |
direction | +5.636 |
eer | +5.635 |
upside | +5.610 |
Neg logit contributions | |
leys | -17.764 |
idad | -16.094 |
amina | -16.072 |
ici | -16.002 |
ulner | -15.162 |
Token | . |
Token ID | 13 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
keys | +2.602 |
goats | +2.581 |
swers | +2.425 |
osher | +2.357 |
Tips | +2.282 |
Neg logit contributions | |
leys | -3.367 |
idad | -2.981 |
amina | -2.966 |
ici | -2.875 |
tru | -2.870 |
Token | I |
Token ID | 314 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
keys | +4.517 |
goats | +4.421 |
swers | +4.147 |
Edge | +4.014 |
Tips | +3.997 |
Neg logit contributions | |
leys | -5.165 |
idad | -4.626 |
amina | -4.593 |
ici | -4.406 |
tru | -4.291 |
Token | can |
Token ID | 460 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
keys | +1.832 |
goats | +1.803 |
swers | +1.718 |
osher | +1.656 |
Edge | +1.608 |
Neg logit contributions | |
leys | -2.335 |
idad | -2.074 |
amina | -2.074 |
ici | -2.008 |
tru | -2.001 |
Token | � |
Token ID | 447 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
keys | +2.721 |
goats | +2.678 |
swers | +2.500 |
osher | +2.412 |
Edge | +2.320 |
Neg logit contributions | |
leys | -4.125 |
amina | -3.700 |
idad | -3.691 |
ici | -3.568 |
tru | -3.527 |
Token | stripes |
Token ID | 28806 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
goats | +6.527 |
keys | +6.479 |
swers | +5.821 |
Edge | +5.571 |
Tips | +5.518 |
Neg logit contributions | |
leys | -8.338 |
idad | -7.295 |
ici | -7.219 |
amina | -7.070 |
tru | -6.967 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
keys | +3.865 |
goats | +3.853 |
swers | +3.568 |
osher | +3.431 |
Edge | +3.402 |
Neg logit contributions | |
leys | -4.984 |
amina | -4.415 |
idad | -4.401 |
ici | -4.321 |
tru | -4.235 |
Token | as |
Token ID | 355 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
keys | +2.410 |
goats | +2.396 |
swers | +2.263 |
osher | +2.189 |
Edge | +2.133 |
Neg logit contributions | |
leys | -2.783 |
idad | -2.465 |
amina | -2.442 |
ici | -2.403 |
tru | -2.361 |
Token | well |
Token ID | 880 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
leys | +2.140 |
amina | +1.868 |
idad | +1.838 |
ici | +1.784 |
tru | +1.772 |
Neg logit contributions | |
keys | -2.429 |
goats | -2.384 |
swers | -2.339 |
osher | -2.307 |
Edge | -2.229 |
Token | as |
Token ID | 355 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
leys | +0.124 |
idad | +0.105 |
amina | +0.105 |
ici | +0.101 |
tru | +0.101 |
Neg logit contributions | |
keys | -0.180 |
goats | -0.177 |
swers | -0.172 |
osher | -0.168 |
Edge | -0.164 |
Token | brightly |
Token ID | 35254 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
goats | +3.471 |
keys | +3.453 |
swers | +3.211 |
osher | +3.086 |
Tips | +3.028 |
Neg logit contributions | |
leys | -4.388 |
idad | -3.888 |
amina | -3.830 |
ici | -3.826 |
tru | -3.697 |
Token | colored |
Token ID | 16396 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
goats | +9.422 |
keys | +8.651 |
goat | +7.798 |
Khe | +7.315 |
goose | +7.308 |
Neg logit contributions | |
leys | -16.194 |
idad | -14.343 |
ici | -13.968 |
amina | -13.682 |
ulk | -13.425 |
Token | limbs |
Token ID | 21755 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
goats | +4.785 |
keys | +4.667 |
swers | +4.214 |
eer | +4.056 |
Edge | +4.018 |
Neg logit contributions | |
leys | -6.462 |
idad | -5.740 |
ici | -5.711 |
amina | -5.656 |
tru | -5.406 |
Token | . |
Token ID | 13 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
goats | +4.068 |
keys | +4.061 |
swers | +3.752 |
osher | +3.585 |
Edge | +3.578 |
Neg logit contributions | |
leys | -5.289 |
amina | -4.662 |
idad | -4.646 |
ici | -4.548 |
tru | -4.483 |
Token |
|
Token ID | 198 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
leys | +0.548 |
amina | +0.475 |
idad | +0.473 |
ici | +0.459 |
tru | +0.455 |
Neg logit contributions | |
keys | -0.660 |
goats | -0.655 |
swers | -0.633 |
osher | -0.623 |
Edge | -0.597 |
Token |
|
Token ID | 198 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
keys | +3.522 |
goats | +3.278 |
Tips | +3.120 |
Edge | +3.120 |
eer | +3.110 |
Neg logit contributions | |
leys | -4.467 |
amina | -3.954 |
idad | -3.940 |
ici | -3.835 |
tru | -3.652 |
Token | hike |
Token ID | 18390 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
keys | +3.218 |
goats | +3.208 |
swers | +3.019 |
osher | +2.878 |
Tips | +2.779 |
Neg logit contributions | |
leys | -5.566 |
idad | -4.996 |
amina | -4.943 |
ici | -4.880 |
tru | -4.810 |
Token | this |
Token ID | 428 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
goats | +3.846 |
keys | +3.833 |
swers | +3.574 |
osher | +3.444 |
eer | +3.339 |
Neg logit contributions | |
leys | -5.076 |
idad | -4.483 |
amina | -4.425 |
ici | -4.355 |
tru | -4.298 |
Token | year |
Token ID | 614 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
goats | +3.741 |
keys | +3.722 |
swers | +3.441 |
osher | +3.292 |
Tips | +3.182 |
Neg logit contributions | |
leys | -6.315 |
idad | -5.699 |
amina | -5.674 |
ici | -5.505 |
tru | -5.428 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
keys | +3.920 |
goats | +3.879 |
swers | +3.690 |
osher | +3.556 |
Tips | +3.434 |
Neg logit contributions | |
leys | -5.055 |
idad | -4.524 |
amina | -4.493 |
tru | -4.350 |
ici | -4.327 |
Token | Senators |
Token ID | 22195 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
leys | +1.200 |
amina | +1.033 |
idad | +1.031 |
ici | +1.005 |
tru | +1.003 |
Neg logit contributions | |
keys | -1.451 |
goats | -1.429 |
swers | -1.377 |
osher | -1.356 |
Edge | -1.308 |
Token | got |
Token ID | 1392 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
leys | +1.431 |
idad | +1.260 |
amina | +1.253 |
ici | +1.219 |
tru | +1.215 |
Neg logit contributions | |
keys | -1.374 |
goats | -1.351 |
swers | -1.302 |
osher | -1.285 |
Edge | -1.228 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
goats | +10.452 |
keys | +10.039 |
swers | +9.366 |
eer | +8.832 |
Tips | +8.791 |
Neg logit contributions | |
leys | -14.204 |
idad | -13.044 |
amina | -12.805 |
ici | -12.737 |
ulk | -12.068 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
keys | +6.696 |
goats | +6.644 |
swers | +5.949 |
osher | +5.910 |
Tips | +5.861 |
Neg logit contributions | |
leys | -10.123 |
idad | -9.069 |
amina | -8.905 |
tru | -8.893 |
ici | -8.769 |
Token | 7 |
Token ID | 22 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
leys | +1.494 |
idad | +1.295 |
amina | +1.287 |
ici | +1.259 |
tru | +1.251 |
Neg logit contributions | |
keys | -1.627 |
goats | -1.609 |
swers | -1.553 |
osher | -1.517 |
Edge | -1.451 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
keys | +3.368 |
goats | +3.338 |
swers | +3.115 |
osher | +3.009 |
Tips | +2.949 |
Neg logit contributions | |
leys | -4.597 |
idad | -4.114 |
amina | -4.062 |
tru | -3.979 |
ici | -3.966 |
Token | 2 |
Token ID | 362 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
keys | +1.204 |
goats | +1.185 |
swers | +1.130 |
osher | +1.096 |
Edge | +1.058 |
Neg logit contributions | |
leys | -1.539 |
idad | -1.372 |
amina | -1.365 |
ici | -1.333 |
tru | -1.327 |
Token | the |
Token ID | 262 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
keys | +0.706 |
goats | +0.695 |
swers | +0.665 |
osher | +0.648 |
Edge | +0.627 |
Neg logit contributions | |
leys | -0.815 |
idad | -0.721 |
amina | -0.719 |
ici | -0.702 |
tru | -0.699 |
Token | broader |
Token ID | 11622 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
goats | +3.433 |
keys | +3.428 |
swers | +3.261 |
osher | +3.140 |
Edge | +3.048 |
Neg logit contributions | |
leys | -4.089 |
idad | -3.612 |
amina | -3.605 |
ici | -3.500 |
tru | -3.391 |
Token | context |
Token ID | 4732 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
leys | +3.717 |
tru | +3.324 |
amina | +3.312 |
idad | +3.298 |
ici | +3.195 |
Neg logit contributions | |
keys | -3.492 |
goats | -3.325 |
swers | -3.188 |
osher | -3.166 |
Tips | -3.080 |
Token | of |
Token ID | 286 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
keys | +2.837 |
goats | +2.829 |
swers | +2.695 |
osher | +2.608 |
Edge | +2.498 |
Neg logit contributions | |
leys | -4.309 |
idad | -3.879 |
amina | -3.859 |
tru | -3.753 |
ici | -3.751 |
Token | a |
Token ID | 257 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
leys | +1.992 |
idad | +1.773 |
amina | +1.766 |
tru | +1.755 |
ici | +1.733 |
Neg logit contributions | |
keys | -1.743 |
goats | -1.673 |
swers | -1.614 |
osher | -1.586 |
Edge | -1.531 |
Token | highly |
Token ID | 4047 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
keys | +1.559 |
goats | +1.540 |
swers | +1.472 |
osher | +1.433 |
Edge | +1.376 |
Neg logit contributions | |
leys | -1.866 |
idad | -1.653 |
amina | -1.645 |
ici | -1.607 |
tru | -1.590 |
Token | competitive |
Token ID | 7606 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
goats | +9.424 |
keys | +9.207 |
osher | +8.662 |
swers | +8.660 |
eer | +8.465 |
Neg logit contributions | |
leys | -14.731 |
idad | -13.555 |
amina | -13.005 |
ici | -12.827 |
ulk | -12.341 |
Token | industry |
Token ID | 2831 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
goats | +4.265 |
keys | +4.194 |
swers | +4.005 |
osher | +3.910 |
eer | +3.786 |
Neg logit contributions | |
leys | -5.709 |
idad | -5.066 |
amina | -5.030 |
ici | -4.948 |
ulk | -4.759 |
Token | , |
Token ID | 11 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
goats | +4.633 |
keys | +4.579 |
swers | +4.338 |
osher | +4.266 |
Edge | +4.171 |
Neg logit contributions | |
leys | -6.136 |
idad | -5.428 |
amina | -5.380 |
ici | -5.216 |
tru | -5.100 |
Token | many |
Token ID | 867 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
keys | +0.455 |
goats | +0.446 |
swers | +0.427 |
osher | +0.417 |
Edge | +0.402 |
Neg logit contributions | |
leys | -0.538 |
idad | -0.476 |
amina | -0.475 |
ici | -0.464 |
tru | -0.464 |
Token | of |
Token ID | 286 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
leys | +0.537 |
idad | +0.478 |
amina | +0.475 |
tru | +0.469 |
ici | +0.466 |
Neg logit contributions | |
keys | -0.418 |
goats | -0.407 |
swers | -0.391 |
osher | -0.383 |
Edge | -0.368 |
Token | of |
Token ID | 286 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
keys | +0.137 |
goats | +0.134 |
swers | +0.129 |
osher | +0.126 |
Edge | +0.121 |
Neg logit contributions | |
leys | -0.175 |
idad | -0.157 |
amina | -0.156 |
tru | -0.153 |
ici | -0.153 |
Token | privilege |
Token ID | 11941 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
keys | +2.620 |
goats | +2.603 |
swers | +2.455 |
osher | +2.376 |
Edge | +2.287 |
Neg logit contributions | |
leys | -3.319 |
amina | -2.956 |
idad | -2.945 |
ici | -2.871 |
tru | -2.827 |
Token | who |
Token ID | 508 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
leys | +2.809 |
idad | +2.528 |
tru | +2.492 |
amina | +2.440 |
ici | +2.432 |
Neg logit contributions | |
keys | -3.122 |
goats | -3.029 |
swers | -2.962 |
osher | -2.905 |
Edge | -2.831 |
Token | ve |
Token ID | 1569 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
leys | +0.888 |
idad | +0.787 |
amina | +0.779 |
tru | +0.770 |
ici | +0.760 |
Neg logit contributions | |
keys | -0.781 |
goats | -0.763 |
swers | -0.742 |
osher | -0.722 |
Edge | -0.701 |
Token | ered |
Token ID | 1068 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
leys | +4.861 |
amina | +4.415 |
idad | +4.404 |
ici | +4.310 |
tru | +4.270 |
Neg logit contributions | |
keys | -2.077 |
goats | -1.984 |
swers | -1.895 |
osher | -1.803 |
Edge | -1.744 |
Token | wildly |
Token ID | 20278 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
goats | +5.853 |
keys | +5.721 |
swers | +5.353 |
osher | +5.098 |
Tips | +5.079 |
Neg logit contributions | |
leys | -8.423 |
amina | -7.726 |
idad | -7.557 |
ici | -7.500 |
ulk | -7.150 |
Token | off |
Token ID | 572 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
goats | +8.739 |
keys | +8.274 |
swers | +7.784 |
osher | +7.276 |
Howe | +7.247 |
Neg logit contributions | |
leys | -15.015 |
amina | -14.333 |
idad | -13.912 |
ici | -13.657 |
ulk | -13.263 |
Token | the |
Token ID | 262 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
keys | +4.436 |
goats | +4.427 |
swers | +4.196 |
osher | +4.011 |
Edge | +3.984 |
Neg logit contributions | |
leys | -5.616 |
idad | -5.021 |
amina | -4.970 |
ici | -4.853 |
tru | -4.698 |
Token | expected |
Token ID | 2938 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
keys | +2.367 |
goats | +2.344 |
swers | +2.224 |
osher | +2.168 |
Edge | +2.107 |
Neg logit contributions | |
leys | -2.949 |
idad | -2.614 |
amina | -2.601 |
ici | -2.556 |
tru | -2.498 |
Token | course |
Token ID | 1781 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
leys | +0.787 |
idad | +0.709 |
amina | +0.703 |
tru | +0.696 |
ici | +0.682 |
Neg logit contributions | |
keys | -0.523 |
goats | -0.509 |
swers | -0.488 |
osher | -0.469 |
Tips | -0.452 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
leys | +2.661 |
idad | +2.368 |
tru | +2.362 |
amina | +2.357 |
ici | +2.323 |
Neg logit contributions | |
keys | -2.294 |
goats | -2.230 |
swers | -2.138 |
osher | -2.079 |
Edge | -2.017 |
Token | DOM |
Token ID | 24121 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
leys | +0.564 |
idad | +0.492 |
amina | +0.487 |
tru | +0.480 |
ici | +0.479 |
Neg logit contributions | |
keys | -0.622 |
goats | -0.613 |
swers | -0.586 |
osher | -0.579 |
Tips | -0.558 |
Token | A |
Token ID | 32 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
keys | +0.356 |
goats | +0.347 |
swers | +0.329 |
osher | +0.315 |
Edge | +0.314 |
Neg logit contributions | |
leys | -0.568 |
idad | -0.507 |
amina | -0.506 |
ici | -0.497 |
tru | -0.492 |
Token | in |
Token ID | 287 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
keys | +0.250 |
goats | +0.246 |
swers | +0.235 |
osher | +0.229 |
Edge | +0.221 |
Neg logit contributions | |
leys | -0.297 |
idad | -0.263 |
amina | -0.262 |
ici | -0.256 |
tru | -0.255 |
Token | court |
Token ID | 2184 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
keys | +2.196 |
goats | +2.156 |
swers | +2.026 |
osher | +1.959 |
Edge | +1.882 |
Neg logit contributions | |
leys | -3.522 |
idad | -3.160 |
amina | -3.150 |
ici | -3.063 |
tru | -3.041 |
Token | at |
Token ID | 379 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
keys | +2.637 |
goats | +2.613 |
swers | +2.463 |
osher | +2.375 |
Edge | +2.304 |
Neg logit contributions | |
leys | -3.501 |
idad | -3.137 |
amina | -3.126 |
ici | -3.053 |
tru | -3.019 |
Token | all |
Token ID | 477 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
goats | +5.318 |
keys | +5.231 |
swers | +4.777 |
Khe | +4.529 |
osher | +4.502 |
Neg logit contributions | |
leys | -9.764 |
idad | -8.782 |
amina | -8.584 |
ici | -8.382 |
tru | -8.362 |
Token | ? |
Token ID | 30 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
goats | +8.864 |
keys | +8.766 |
Khe | +7.571 |
swers | +7.428 |
osher | +7.322 |
Neg logit contributions | |
leys | -15.655 |
amina | -13.771 |
idad | -13.702 |
ici | -13.585 |
tru | -13.495 |
Token | What |
Token ID | 1867 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
keys | +3.507 |
goats | +3.437 |
swers | +3.297 |
Edge | +3.129 |
Tips | +3.108 |
Neg logit contributions | |
leys | -4.892 |
amina | -4.411 |
idad | -4.399 |
ici | -4.248 |
tru | -4.138 |
Token | will |
Token ID | 481 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
leys | +0.823 |
idad | +0.729 |
amina | +0.728 |
tru | +0.714 |
ici | +0.709 |
Neg logit contributions | |
keys | -0.666 |
goats | -0.649 |
swers | -0.626 |
osher | -0.612 |
Edge | -0.589 |
Token | that |
Token ID | 326 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
leys | +1.550 |
idad | +1.368 |
amina | +1.346 |
ici | +1.339 |
tru | +1.324 |
Neg logit contributions | |
keys | -1.477 |
goats | -1.441 |
swers | -1.393 |
osher | -1.364 |
Tips | -1.321 |
Token | eventually |
Token ID | 4191 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
keys | +1.706 |
goats | +1.684 |
swers | +1.608 |
osher | +1.553 |
Edge | +1.507 |
Neg logit contributions | |
leys | -2.086 |
idad | -1.850 |
amina | -1.840 |
ici | -1.793 |
tru | -1.778 |
Token | don |
Token ID | 836 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
leys | +4.034 |
tru | +3.477 |
idad | +3.475 |
amina | +3.440 |
ici | +3.409 |
Neg logit contributions | |
keys | -4.374 |
swers | -4.272 |
osher | -4.178 |
goats | -4.169 |
Tips | -4.061 |
Token | 't |
Token ID | 470 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
keys | +1.178 |
goats | +1.040 |
swers | +0.955 |
Edge | +0.890 |
Tips | +0.855 |
Neg logit contributions | |
leys | -3.834 |
amina | -3.528 |
idad | -3.507 |
ici | -3.422 |
tru | -3.397 |
Token | allow |
Token ID | 1249 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
leys | +3.029 |
idad | +2.623 |
amina | +2.609 |
tru | +2.596 |
ici | +2.544 |
Neg logit contributions | |
keys | -3.419 |
swers | -3.313 |
goats | -3.282 |
osher | -3.244 |
Tips | -3.166 |
Token | their |
Token ID | 511 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
leys | +5.883 |
tru | +5.265 |
amina | +5.227 |
idad | +5.198 |
ici | +5.035 |
Neg logit contributions | |
keys | -5.305 |
swers | -5.183 |
osher | -5.087 |
goats | -4.851 |
Edge | -4.848 |
Token | wives |
Token ID | 17743 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
leys | +4.502 |
tru | +3.936 |
idad | +3.742 |
amina | +3.702 |
ici | +3.484 |
Neg logit contributions | |
swers | -8.745 |
keys | -8.714 |
osher | -8.568 |
goats | -8.270 |
Edge | -8.262 |
Token | or |
Token ID | 393 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
leys | +7.631 |
idad | +6.629 |
tru | +6.455 |
ici | +6.411 |
amina | +6.404 |
Neg logit contributions | |
keys | -7.906 |
osher | -7.887 |
swers | -7.844 |
goats | -7.506 |
Edge | -7.467 |
Token | girlfriends |
Token ID | 47094 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
leys | +11.102 |
girlfriends | +10.854 |
tru | +10.299 |
nearest | +9.623 |
amina | +9.340 |
Neg logit contributions | |
osher | -16.235 |
swers | -16.185 |
Edge | -15.649 |
keys | -15.359 |
odus | -14.878 |
Token | on |
Token ID | 319 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
leys | +1.791 |
idad | +1.574 |
amina | +1.566 |
tru | +1.541 |
ici | +1.532 |
Neg logit contributions | |
keys | -1.653 |
goats | -1.600 |
swers | -1.585 |
osher | -1.548 |
Edge | -1.496 |
Token | tour |
Token ID | 4205 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
keys | +1.561 |
goats | +1.541 |
swers | +1.465 |
osher | +1.419 |
Edge | +1.378 |
Neg logit contributions | |
leys | -1.815 |
idad | -1.614 |
amina | -1.605 |
ici | -1.564 |
tru | -1.551 |
Token | then |
Token ID | 788 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
keys | +1.672 |
goats | +1.647 |
swers | +1.554 |
osher | +1.504 |
Edge | +1.457 |
Neg logit contributions | |
leys | -2.141 |
idad | -1.913 |
amina | -1.906 |
ici | -1.857 |
tru | -1.852 |
Token | that |
Token ID | 326 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
leys | +1.914 |
idad | +1.687 |
amina | +1.674 |
tru | +1.663 |
ici | +1.635 |
Neg logit contributions | |
keys | -1.645 |
goats | -1.574 |
swers | -1.553 |
osher | -1.527 |
Edge | -1.461 |
Token | with |
Token ID | 351 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
goats | +4.798 |
keys | +4.737 |
swers | +4.429 |
osher | +4.280 |
eer | +4.159 |
Neg logit contributions | |
leys | -8.101 |
amina | -7.363 |
idad | -7.280 |
ici | -7.041 |
tru | -6.959 |
Token | sanctioned |
Token ID | 30572 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
keys | +5.808 |
goats | +5.752 |
swers | +5.446 |
osher | +5.226 |
eer | +5.217 |
Neg logit contributions | |
leys | -7.350 |
amina | -6.524 |
idad | -6.495 |
ici | -6.226 |
tru | -6.179 |
Token | individuals |
Token ID | 3925 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
keys | +3.055 |
goats | +3.016 |
swers | +2.834 |
osher | +2.728 |
Edge | +2.664 |
Neg logit contributions | |
leys | -3.913 |
amina | -3.472 |
idad | -3.468 |
ici | -3.357 |
tru | -3.312 |
Token | , |
Token ID | 11 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
keys | +5.251 |
goats | +5.215 |
swers | +4.882 |
osher | +4.739 |
eer | +4.569 |
Neg logit contributions | |
leys | -7.411 |
amina | -6.611 |
idad | -6.587 |
tru | -6.359 |
ici | -6.358 |
Token | direct |
Token ID | 1277 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
keys | +1.846 |
goats | +1.824 |
swers | +1.739 |
osher | +1.678 |
Edge | +1.616 |
Neg logit contributions | |
leys | -2.368 |
idad | -2.111 |
amina | -2.108 |
ici | -2.048 |
tru | -2.031 |
Token | or |
Token ID | 393 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
leys | +1.834 |
idad | +1.623 |
amina | +1.604 |
ici | +1.586 |
tru | +1.569 |
Neg logit contributions | |
keys | -1.410 |
goats | -1.395 |
swers | -1.335 |
osher | -1.315 |
Edge | -1.261 |
Token | indirect |
Token ID | 12913 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
leys | +8.945 |
ici | +8.684 |
tru | +8.502 |
ional | +7.907 |
ifice | +7.305 |
Neg logit contributions | |
keys | -15.459 |
goats | -14.952 |
Edge | -14.857 |
osher | -14.508 |
swers | -14.381 |
Token | , |
Token ID | 11 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
keys | +1.077 |
goats | +1.061 |
swers | +1.019 |
osher | +0.992 |
Edge | +0.962 |
Neg logit contributions | |
leys | -1.136 |
idad | -1.001 |
amina | -0.995 |
ici | -0.971 |
tru | -0.966 |
Token | � |
Token ID | 447 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
keys | +3.986 |
goats | +3.960 |
swers | +3.741 |
osher | +3.639 |
Tips | +3.467 |
Neg logit contributions | |
leys | -5.165 |
amina | -4.632 |
idad | -4.610 |
ici | -4.429 |
tru | -4.388 |
Token | � |
Token ID | 251 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
leys | +0.773 |
idad | +0.677 |
amina | +0.674 |
ici | +0.656 |
tru | +0.653 |
Neg logit contributions | |
keys | -0.785 |
goats | -0.773 |
swers | -0.744 |
osher | -0.724 |
Edge | -0.703 |
Token | he |
Token ID | 339 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
keys | +3.022 |
goats | +2.965 |
swers | +2.856 |
osher | +2.750 |
Tips | +2.653 |
Neg logit contributions | |
leys | -3.733 |
amina | -3.336 |
idad | -3.327 |
ici | -3.217 |
tru | -3.191 |
Token | you |
Token ID | 345 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
leys | +1.644 |
idad | +1.455 |
amina | +1.454 |
tru | +1.439 |
ici | +1.422 |
Neg logit contributions | |
keys | -1.290 |
goats | -1.233 |
swers | -1.218 |
osher | -1.186 |
Edge | -1.135 |
Token | can |
Token ID | 460 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
goats | +3.557 |
keys | +3.527 |
swers | +3.175 |
osher | +3.065 |
eer | +2.999 |
Neg logit contributions | |
leys | -5.241 |
amina | -4.777 |
idad | -4.706 |
ici | -4.612 |
tru | -4.450 |
Token | start |
Token ID | 923 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
keys | +0.765 |
goats | +0.753 |
swers | +0.721 |
osher | +0.701 |
Edge | +0.679 |
Neg logit contributions | |
leys | -0.862 |
idad | -0.762 |
amina | -0.759 |
ici | -0.740 |
tru | -0.736 |
Token | blaming |
Token ID | 24630 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
keys | +2.393 |
goats | +2.388 |
swers | +2.229 |
osher | +2.153 |
Edge | +2.099 |
Neg logit contributions | |
leys | -3.082 |
idad | -2.748 |
amina | -2.737 |
ici | -2.682 |
tru | -2.625 |
Token | wives |
Token ID | 17743 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
leys | +1.976 |
idad | +1.735 |
amina | +1.726 |
tru | +1.713 |
ici | +1.686 |
Neg logit contributions | |
keys | -1.895 |
swers | -1.819 |
goats | -1.813 |
osher | -1.770 |
Edge | -1.698 |
Token | or |
Token ID | 393 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
leys | +3.558 |
idad | +3.108 |
amina | +3.070 |
tru | +3.032 |
ici | +3.020 |
Neg logit contributions | |
keys | -3.310 |
goats | -3.211 |
swers | -3.207 |
osher | -3.140 |
Edge | -3.018 |
Token | girlfriends |
Token ID | 47094 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
leys | +9.697 |
tru | +9.005 |
girlfriends | +8.826 |
amina | +7.989 |
nearest | +7.971 |
Neg logit contributions | |
osher | -14.438 |
swers | -14.415 |
keys | -14.067 |
Edge | -14.042 |
eer | -13.562 |
Token | for |
Token ID | 329 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
goats | +2.850 |
keys | +2.844 |
swers | +2.619 |
osher | +2.531 |
Tips | +2.463 |
Neg logit contributions | |
leys | -3.667 |
amina | -3.278 |
idad | -3.273 |
ici | -3.198 |
tru | -3.132 |
Token | performance |
Token ID | 2854 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
leys | +3.824 |
tru | +3.412 |
idad | +3.408 |
amina | +3.367 |
ici | +3.247 |
Neg logit contributions | |
keys | -3.276 |
swers | -3.138 |
osher | -3.073 |
goats | -3.051 |
Edge | -2.898 |
Token | ," |
Token ID | 553 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
goats | +2.721 |
keys | +2.716 |
swers | +2.526 |
osher | +2.421 |
Tips | +2.394 |
Neg logit contributions | |
leys | -3.339 |
amina | -2.971 |
idad | -2.946 |
ici | -2.895 |
tru | -2.812 |
Token | he |
Token ID | 339 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
keys | +1.176 |
goats | +1.159 |
swers | +1.111 |
osher | +1.079 |
Edge | +1.047 |
Neg logit contributions | |
leys | -1.299 |
idad | -1.148 |
amina | -1.143 |
ici | -1.114 |
tru | -1.107 |
Token | the |
Token ID | 262 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
leys | +1.697 |
idad | +1.485 |
amina | +1.479 |
tru | +1.451 |
ici | +1.436 |
Neg logit contributions | |
keys | -1.708 |
goats | -1.666 |
swers | -1.598 |
osher | -1.587 |
Tips | -1.520 |
Token | film |
Token ID | 2646 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
leys | +0.714 |
idad | +0.621 |
amina | +0.619 |
tru | +0.605 |
ici | +0.600 |
Neg logit contributions | |
keys | -0.761 |
goats | -0.746 |
swers | -0.719 |
osher | -0.705 |
Edge | -0.680 |
Token | ? |
Token ID | 30 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
leys | +3.003 |
idad | +2.643 |
amina | +2.635 |
ici | +2.597 |
tru | +2.595 |
Neg logit contributions | |
keys | -2.501 |
goats | -2.437 |
swers | -2.347 |
osher | -2.302 |
Edge | -2.217 |
Token | Let |
Token ID | 3914 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
leys | +3.421 |
tru | +2.973 |
idad | +2.938 |
amina | +2.906 |
ici | +2.898 |
Neg logit contributions | |
keys | -3.657 |
goats | -3.646 |
osher | -3.478 |
swers | -3.464 |
Edge | -3.235 |
Token | us |
Token ID | 514 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
leys | +5.590 |
idad | +4.894 |
tru | +4.867 |
ici | +4.867 |
amina | +4.739 |
Neg logit contributions | |
keys | -5.841 |
goats | -5.716 |
osher | -5.564 |
swers | -5.307 |
Edge | -5.225 |
Token | know |
Token ID | 760 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
leys | +3.476 |
tru | +2.893 |
idad | +2.884 |
amina | +2.810 |
ici | +2.797 |
Neg logit contributions | |
keys | -4.581 |
goats | -4.482 |
osher | -4.366 |
swers | -4.327 |
Edge | -4.180 |
Token | in |
Token ID | 287 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
leys | +9.602 |
tru | +8.766 |
idad | +7.949 |
nearest | +7.894 |
ici | +7.861 |
Neg logit contributions | |
keys | -14.545 |
osher | -14.207 |
swers | -13.673 |
goats | -13.623 |
odus | -13.325 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
leys | +7.102 |
tru | +6.294 |
amina | +6.060 |
ici | +5.923 |
idad | +5.903 |
Neg logit contributions | |
keys | -11.618 |
goats | -11.569 |
osher | -11.223 |
swers | -11.056 |
Edge | -10.986 |
Token | comments |
Token ID | 3651 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
leys | +5.162 |
tru | +4.353 |
idad | +3.613 |
ici | +3.534 |
nearest | +3.353 |
Neg logit contributions | |
keys | -15.098 |
goats | -15.076 |
osher | -14.713 |
swers | -14.193 |
ertodd | -14.006 |
Token | below |
Token ID | 2174 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
leys | +5.491 |
idad | +4.623 |
tru | +4.562 |
ici | +4.534 |
amina | +4.457 |
Neg logit contributions | |
keys | -6.446 |
goats | -6.288 |
swers | -6.091 |
osher | -6.016 |
Edge | -5.861 |
Token | . |
Token ID | 13 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
leys | +5.592 |
idad | +4.818 |
tru | +4.759 |
ici | +4.754 |
amina | +4.608 |
Neg logit contributions | |
keys | -6.637 |
goats | -6.491 |
osher | -6.269 |
swers | -6.210 |
Edge | -6.104 |
Token | to |
Token ID | 284 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
leys | +4.224 |
idad | +3.663 |
tru | +3.641 |
amina | +3.635 |
ici | +3.577 |
Neg logit contributions | |
keys | -4.102 |
goats | -3.987 |
swers | -3.886 |
osher | -3.793 |
Edge | -3.682 |
Token | fr |
Token ID | 1216 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
leys | +5.913 |
tru | +5.331 |
amina | +5.235 |
idad | +5.229 |
ici | +5.093 |
Neg logit contributions | |
keys | -5.528 |
goats | -5.253 |
swers | -5.252 |
osher | -5.171 |
Tips | -4.961 |
Token | atern |
Token ID | 9205 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
leys | +3.764 |
amina | +2.928 |
idad | +2.826 |
ici | +2.775 |
tru | +2.761 |
Neg logit contributions | |
goats | -8.177 |
keys | -8.127 |
eer | -7.893 |
swers | -7.867 |
osher | -7.706 |
Token | ities |
Token ID | 871 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
leys | +1.761 |
idad | +1.293 |
ici | +1.062 |
amina | +1.034 |
tru | +0.880 |
Neg logit contributions | |
goats | -7.610 |
keys | -7.516 |
swers | -7.375 |
osher | -7.351 |
Edge | -7.196 |
Token | or |
Token ID | 393 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
leys | +1.734 |
idad | +1.528 |
amina | +1.512 |
ici | +1.488 |
tru | +1.486 |
Neg logit contributions | |
keys | -1.669 |
goats | -1.632 |
swers | -1.573 |
osher | -1.540 |
Edge | -1.495 |
Token | just |
Token ID | 655 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
leys | +7.317 |
tru | +6.606 |
amina | +6.259 |
ici | +6.146 |
idad | +6.117 |
Neg logit contributions | |
keys | -9.941 |
swers | -9.645 |
osher | -9.469 |
goats | -9.406 |
Edge | -9.169 |
Token | sor |
Token ID | 25655 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
leys | +12.345 |
tru | +11.454 |
ici | +10.880 |
amina | +10.681 |
ional | +10.460 |
Neg logit contributions | |
keys | -11.376 |
swers | -11.095 |
goats | -10.680 |
osher | -10.590 |
eer | -10.356 |
Token | or |
Token ID | 273 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
leys | +4.729 |
amina | +3.978 |
idad | +3.955 |
ici | +3.866 |
tru | +3.743 |
Neg logit contributions | |
goats | -5.045 |
keys | -4.871 |
swers | -4.853 |
Khe | -4.723 |
osher | -4.717 |
Token | ities |
Token ID | 871 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
leys | +1.687 |
idad | +1.209 |
amina | +1.089 |
ici | +1.009 |
tru | +0.899 |
Neg logit contributions | |
goats | -6.615 |
keys | -6.610 |
swers | -6.457 |
osher | -6.430 |
Edge | -6.371 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
keys | +0.730 |
goats | +0.718 |
swers | +0.688 |
osher | +0.669 |
Edge | +0.647 |
Neg logit contributions | |
leys | -0.842 |
idad | -0.745 |
amina | -0.743 |
ici | -0.724 |
tru | -0.720 |
Token | This |
Token ID | 770 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
leys | +2.041 |
idad | +1.793 |
amina | +1.788 |
tru | +1.758 |
ici | +1.753 |
Neg logit contributions | |
keys | -2.144 |
goats | -2.119 |
swers | -2.014 |
osher | -1.992 |
Edge | -1.917 |
Token | end |
Token ID | 886 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
leys | +0.960 |
idad | +0.843 |
amina | +0.835 |
tru | +0.826 |
ici | +0.821 |
Neg logit contributions | |
keys | -0.914 |
goats | -0.885 |
swers | -0.874 |
osher | -0.853 |
Edge | -0.823 |
Token | until |
Token ID | 1566 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
leys | +0.799 |
idad | +0.712 |
amina | +0.708 |
ici | +0.694 |
tru | +0.691 |
Neg logit contributions | |
keys | -0.685 |
goats | -0.669 |
swers | -0.645 |
osher | -0.630 |
Edge | -0.609 |
Token | the |
Token ID | 262 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
leys | +4.674 |
idad | +4.175 |
tru | +4.158 |
amina | +4.123 |
ici | +3.960 |
Neg logit contributions | |
keys | -4.422 |
osher | -4.224 |
goats | -4.222 |
swers | -4.180 |
Edge | -4.023 |
Token | accumulated |
Token ID | 22425 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
leys | +1.710 |
idad | +1.520 |
amina | +1.503 |
tru | +1.497 |
ici | +1.462 |
Neg logit contributions | |
keys | -1.680 |
goats | -1.633 |
swers | -1.596 |
osher | -1.577 |
Edge | -1.513 |
Token | debt |
Token ID | 5057 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
leys | +8.713 |
tru | +8.160 |
amina | +7.884 |
idad | +7.825 |
fallacy | +7.453 |
Neg logit contributions | |
swers | -8.715 |
keys | -8.711 |
osher | -8.501 |
goats | -8.201 |
Edge | -8.187 |
Token | becomes |
Token ID | 4329 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
leys | +11.469 |
tru | +10.487 |
fulness | +10.185 |
idad | +10.102 |
amina | +10.012 |
Neg logit contributions | |
osher | -11.788 |
swers | -11.730 |
keys | -11.721 |
Edge | -11.158 |
goats | -10.993 |
Token | unsustainable |
Token ID | 39554 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
leys | +10.875 |
tru | +10.627 |
amina | +10.007 |
ional | +9.739 |
lodged | +9.235 |
Neg logit contributions | |
swers | -12.845 |
keys | -12.832 |
Edge | -12.245 |
osher | -12.185 |
odus | -11.916 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
leys | +7.057 |
idad | +6.201 |
tru | +6.092 |
amina | +6.079 |
ici | +5.957 |
Neg logit contributions | |
keys | -8.738 |
swers | -8.327 |
goats | -8.314 |
osher | -8.183 |
Edge | -7.818 |
Token | the |
Token ID | 262 |
Feature activation | +3.76e-03 |
Pos logit contributions | |
leys | +1.338 |
idad | +1.178 |
amina | +1.177 |
tru | +1.165 |
ici | +1.141 |
Neg logit contributions | |
keys | -1.180 |
goats | -1.143 |
swers | -1.112 |
osher | -1.094 |
Edge | -1.053 |
Token | government |
Token ID | 1230 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
keys | +0.028 |
goats | +0.027 |
swers | +0.026 |
osher | +0.026 |
Edge | +0.025 |
Neg logit contributions | |
leys | -0.033 |
idad | -0.029 |
amina | -0.029 |
ici | -0.028 |
tru | -0.028 |
Token | � |
Token ID | 447 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
leys | +1.065 |
idad | +0.944 |
amina | +0.936 |
tru | +0.922 |
ici | +0.913 |
Neg logit contributions | |
keys | -0.907 |
goats | -0.886 |
swers | -0.858 |
osher | -0.841 |
Edge | -0.809 |
Token | in |
Token ID | 287 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
keys | +1.643 |
goats | +1.617 |
swers | +1.538 |
osher | +1.489 |
Edge | +1.438 |
Neg logit contributions | |
leys | -2.251 |
idad | -2.011 |
amina | -2.002 |
ici | -1.955 |
tru | -1.946 |
Token | the |
Token ID | 262 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
keys | +1.950 |
goats | +1.942 |
swers | +1.831 |
osher | +1.769 |
Edge | +1.719 |
Neg logit contributions | |
leys | -2.348 |
idad | -2.085 |
amina | -2.070 |
ici | -2.023 |
tru | -2.005 |
Token | country |
Token ID | 1499 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
goats | +2.368 |
keys | +2.351 |
swers | +2.203 |
osher | +2.107 |
Edge | +2.037 |
Neg logit contributions | |
leys | -3.618 |
idad | -3.241 |
amina | -3.238 |
ici | -3.161 |
tru | -3.112 |
Token | 's |
Token ID | 338 |
Feature activation | +9.74e-03 |
Pos logit contributions | |
keys | +2.985 |
goats | +2.949 |
swers | +2.790 |
osher | +2.723 |
Edge | +2.619 |
Neg logit contributions | |
leys | -3.651 |
idad | -3.214 |
amina | -3.208 |
ici | -3.119 |
tru | -3.111 |
Token | central |
Token ID | 4318 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
keys | +0.076 |
goats | +0.074 |
swers | +0.071 |
osher | +0.070 |
Edge | +0.067 |
Neg logit contributions | |
leys | -0.082 |
idad | -0.073 |
amina | -0.072 |
tru | -0.070 |
ici | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
leys | +6.260 |
idad | +5.725 |
amina | +5.407 |
ici | +5.385 |
tru | +5.384 |
Neg logit contributions | |
keys | -7.294 |
swers | -7.065 |
osher | -7.000 |
goats | -6.875 |
odus | -6.541 |
Token | southern |
Token ID | 8372 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
leys | +9.066 |
idad | +8.188 |
amina | +8.164 |
tru | +8.069 |
nearest | +7.646 |
Neg logit contributions | |
keys | -15.586 |
osher | -14.603 |
goats | -14.555 |
swers | -14.380 |
Edge | -13.779 |
Token | areas |
Token ID | 3006 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
leys | +2.335 |
idad | +2.069 |
amina | +2.015 |
tru | +1.991 |
ici | +1.983 |
Neg logit contributions | |
keys | -2.526 |
goats | -2.470 |
swers | -2.423 |
osher | -2.370 |
Edge | -2.268 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
keys | +1.746 |
goats | +1.722 |
swers | +1.643 |
osher | +1.597 |
Edge | +1.548 |
Neg logit contributions | |
leys | -2.022 |
idad | -1.786 |
amina | -1.779 |
ici | -1.735 |
tru | -1.728 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
leys | +0.873 |
idad | +0.756 |
amina | +0.753 |
ici | +0.732 |
tru | +0.726 |
Neg logit contributions | |
keys | -1.015 |
goats | -0.999 |
swers | -0.967 |
osher | -0.946 |
Edge | -0.913 |
Token | The |
Token ID | 464 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
leys | +2.459 |
idad | +2.184 |
amina | +2.159 |
ici | +2.125 |
tru | +2.112 |
Neg logit contributions | |
goats | -1.992 |
keys | -1.956 |
swers | -1.891 |
osher | -1.838 |
Khe | -1.719 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
keys | +2.345 |
goats | +2.342 |
swers | +2.183 |
osher | +2.113 |
Edge | +2.047 |
Neg logit contributions | |
leys | -2.981 |
idad | -2.656 |
amina | -2.649 |
ici | -2.577 |
tru | -2.537 |
Token | end |
Token ID | 886 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
leys | +0.960 |
idad | +0.843 |
amina | +0.835 |
tru | +0.826 |
ici | +0.821 |
Neg logit contributions | |
keys | -0.914 |
goats | -0.885 |
swers | -0.874 |
osher | -0.853 |
Edge | -0.823 |
Token | until |
Token ID | 1566 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
leys | +0.799 |
idad | +0.712 |
amina | +0.708 |
ici | +0.694 |
tru | +0.691 |
Neg logit contributions | |
keys | -0.685 |
goats | -0.669 |
swers | -0.645 |
osher | -0.630 |
Edge | -0.609 |
Token | the |
Token ID | 262 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
leys | +4.674 |
idad | +4.175 |
tru | +4.158 |
amina | +4.123 |
ici | +3.960 |
Neg logit contributions | |
keys | -4.422 |
osher | -4.224 |
goats | -4.222 |
swers | -4.180 |
Edge | -4.023 |
Token | accumulated |
Token ID | 22425 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
leys | +1.710 |
idad | +1.520 |
amina | +1.503 |
tru | +1.497 |
ici | +1.462 |
Neg logit contributions | |
keys | -1.680 |
goats | -1.633 |
swers | -1.596 |
osher | -1.577 |
Edge | -1.513 |
Token | debt |
Token ID | 5057 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
leys | +8.713 |
tru | +8.160 |
amina | +7.884 |
idad | +7.825 |
fallacy | +7.453 |
Neg logit contributions | |
swers | -8.715 |
keys | -8.711 |
osher | -8.501 |
goats | -8.201 |
Edge | -8.187 |
Token | becomes |
Token ID | 4329 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
leys | +11.469 |
tru | +10.487 |
fulness | +10.185 |
idad | +10.102 |
amina | +10.012 |
Neg logit contributions | |
osher | -11.788 |
swers | -11.730 |
keys | -11.721 |
Edge | -11.158 |
goats | -10.993 |
Token | unsustainable |
Token ID | 39554 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
leys | +10.875 |
tru | +10.627 |
amina | +10.007 |
ional | +9.739 |
lodged | +9.235 |
Neg logit contributions | |
swers | -12.845 |
keys | -12.832 |
Edge | -12.245 |
osher | -12.185 |
odus | -11.916 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
leys | +7.057 |
idad | +6.201 |
tru | +6.092 |
amina | +6.079 |
ici | +5.957 |
Neg logit contributions | |
keys | -8.738 |
swers | -8.327 |
goats | -8.314 |
osher | -8.183 |
Edge | -7.818 |
Token | the |
Token ID | 262 |
Feature activation | +3.76e-03 |
Pos logit contributions | |
leys | +1.338 |
idad | +1.178 |
amina | +1.177 |
tru | +1.165 |
ici | +1.141 |
Neg logit contributions | |
keys | -1.180 |
goats | -1.143 |
swers | -1.112 |
osher | -1.094 |
Edge | -1.053 |
Token | government |
Token ID | 1230 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
keys | +0.028 |
goats | +0.027 |
swers | +0.026 |
osher | +0.026 |
Edge | +0.025 |
Neg logit contributions | |
leys | -0.033 |
idad | -0.029 |
amina | -0.029 |
ici | -0.028 |
tru | -0.028 |
Token | Christian |
Token ID | 4302 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
keys | +2.624 |
goats | +2.572 |
swers | +2.442 |
osher | +2.332 |
Edge | +2.294 |
Neg logit contributions | |
leys | -3.590 |
idad | -3.256 |
amina | -3.219 |
ici | -3.145 |
tru | -3.096 |
Token | Grey |
Token ID | 13980 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
keys | +2.879 |
goats | +2.832 |
swers | +2.714 |
osher | +2.605 |
Edge | +2.558 |
Neg logit contributions | |
leys | -3.327 |
amina | -2.967 |
idad | -2.964 |
ici | -2.864 |
tru | -2.847 |
Token | ? |
Token ID | 30 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
keys | +4.141 |
goats | +4.090 |
swers | +3.870 |
osher | +3.656 |
Edge | +3.609 |
Neg logit contributions | |
leys | -5.565 |
idad | -5.038 |
amina | -4.985 |
ici | -4.836 |
tru | -4.757 |
Token | Let |
Token ID | 3914 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
leys | +2.472 |
idad | +2.136 |
tru | +2.131 |
amina | +2.127 |
ici | +2.106 |
Neg logit contributions | |
keys | -2.585 |
goats | -2.569 |
swers | -2.452 |
osher | -2.436 |
Edge | -2.299 |
Token | us |
Token ID | 514 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
leys | +5.346 |
idad | +4.705 |
ici | +4.660 |
tru | +4.622 |
amina | +4.585 |
Neg logit contributions | |
keys | -5.441 |
goats | -5.399 |
osher | -5.219 |
swers | -5.022 |
eer | -4.872 |
Token | know |
Token ID | 760 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
leys | +3.666 |
tru | +3.053 |
idad | +3.050 |
amina | +2.960 |
ici | +2.953 |
Neg logit contributions | |
keys | -5.022 |
goats | -4.918 |
osher | -4.806 |
swers | -4.756 |
Edge | -4.609 |
Token | in |
Token ID | 287 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
leys | +9.359 |
tru | +8.556 |
idad | +7.900 |
ici | +7.740 |
nearest | +7.517 |
Neg logit contributions | |
keys | -13.882 |
osher | -13.663 |
goats | -13.233 |
swers | -13.109 |
ertodd | -12.783 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
leys | +6.718 |
tru | +5.940 |
amina | +5.871 |
ici | +5.641 |
idad | +5.630 |
Neg logit contributions | |
goats | -10.367 |
keys | -10.307 |
osher | -10.121 |
swers | -10.030 |
Edge | -9.828 |
Token | comments |
Token ID | 3651 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
leys | +5.492 |
tru | +4.617 |
idad | +3.955 |
ici | +3.947 |
amina | +3.773 |
Neg logit contributions | |
goats | -14.487 |
keys | -14.339 |
osher | -14.248 |
swers | -13.776 |
ertodd | -13.559 |
Token | below |
Token ID | 2174 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
leys | +5.294 |
idad | +4.445 |
tru | +4.394 |
ici | +4.350 |
amina | +4.305 |
Neg logit contributions | |
keys | -6.096 |
goats | -6.003 |
swers | -5.798 |
osher | -5.751 |
Edge | -5.528 |
Token | …. |
Token ID | 11580 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
leys | +4.432 |
idad | +3.839 |
tru | +3.786 |
ici | +3.768 |
amina | +3.704 |
Neg logit contributions | |
keys | -4.894 |
goats | -4.832 |
osher | -4.649 |
swers | -4.616 |
Edge | -4.437 |
Token | thought |
Token ID | 1807 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
leys | +1.839 |
amina | +1.638 |
idad | +1.634 |
tru | +1.617 |
ici | +1.598 |
Neg logit contributions | |
keys | -1.574 |
goats | -1.534 |
swers | -1.486 |
osher | -1.455 |
Edge | -1.396 |
Token | he |
Token ID | 339 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
leys | +2.743 |
amina | +2.396 |
idad | +2.394 |
tru | +2.369 |
ici | +2.346 |
Neg logit contributions | |
keys | -2.711 |
goats | -2.626 |
osher | -2.539 |
swers | -2.536 |
Tips | -2.423 |
Token | will |
Token ID | 481 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
leys | +1.451 |
idad | +1.299 |
amina | +1.290 |
tru | +1.263 |
ici | +1.259 |
Neg logit contributions | |
keys | -1.092 |
goats | -1.070 |
swers | -1.038 |
osher | -1.009 |
Edge | -0.967 |
Token | make |
Token ID | 787 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
leys | +3.910 |
idad | +3.456 |
tru | +3.419 |
amina | +3.402 |
ici | +3.346 |
Neg logit contributions | |
keys | -3.706 |
swers | -3.645 |
goats | -3.595 |
osher | -3.591 |
Tips | -3.476 |
Token | the |
Token ID | 262 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
leys | +7.067 |
tru | +6.475 |
idad | +6.475 |
amina | +6.423 |
ici | +6.191 |
Neg logit contributions | |
keys | -6.916 |
goats | -6.541 |
osher | -6.432 |
swers | -6.368 |
Edge | -6.349 |
Token | announcement |
Token ID | 8009 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
leys | +6.366 |
tru | +5.895 |
idad | +5.849 |
amina | +5.595 |
ici | +5.543 |
Neg logit contributions | |
keys | -6.436 |
goats | -6.223 |
swers | -6.193 |
osher | -6.172 |
Tips | -5.950 |
Token | in |
Token ID | 287 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
leys | +10.714 |
fulness | +9.549 |
tru | +9.493 |
nearest | +9.306 |
idad | +9.245 |
Neg logit contributions | |
keys | -12.484 |
osher | -12.392 |
swers | -12.363 |
goats | -11.596 |
Tips | -11.470 |
Token | a |
Token ID | 257 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
leys | +6.961 |
idad | +6.221 |
tru | +6.173 |
amina | +6.062 |
ici | +6.010 |
Neg logit contributions | |
keys | -7.134 |
swers | -7.074 |
goats | -6.859 |
osher | -6.821 |
Edge | -6.602 |
Token | speech |
Token ID | 4046 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
leys | +4.641 |
tru | +4.123 |
idad | +4.111 |
amina | +4.033 |
ici | +3.998 |
Neg logit contributions | |
keys | -4.245 |
goats | -4.113 |
swers | -4.051 |
osher | -3.978 |
Tips | -3.875 |
Token | on |
Token ID | 319 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
leys | +4.540 |
idad | +3.980 |
tru | +3.915 |
amina | +3.908 |
ici | +3.889 |
Neg logit contributions | |
keys | -4.901 |
goats | -4.780 |
swers | -4.698 |
osher | -4.645 |
Tips | -4.432 |
Token | the |
Token ID | 262 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
leys | +5.060 |
tru | +4.619 |
idad | +4.571 |
amina | +4.444 |
ici | +4.379 |
Neg logit contributions | |
keys | -5.013 |
osher | -4.733 |
goats | -4.728 |
swers | -4.608 |
Edge | -4.450 |
Token | few |
Token ID | 1178 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
keys | +2.308 |
goats | +2.278 |
swers | +2.181 |
osher | +2.129 |
Edge | +2.071 |
Neg logit contributions | |
leys | -2.333 |
idad | -2.053 |
amina | -2.048 |
ici | -1.982 |
tru | -1.960 |
Token | bites |
Token ID | 26081 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
leys | +0.139 |
idad | +0.120 |
amina | +0.119 |
tru | +0.116 |
ici | +0.116 |
Neg logit contributions | |
keys | -0.167 |
goats | -0.165 |
swers | -0.160 |
osher | -0.156 |
Edge | -0.152 |
Token | it |
Token ID | 340 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
keys | +2.081 |
goats | +2.065 |
swers | +1.946 |
osher | +1.883 |
Edge | +1.826 |
Neg logit contributions | |
leys | -2.560 |
idad | -2.295 |
amina | -2.289 |
ici | -2.222 |
tru | -2.186 |
Token | makes |
Token ID | 1838 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
keys | +1.098 |
goats | +1.084 |
swers | +1.031 |
osher | +1.001 |
Edge | +0.969 |
Neg logit contributions | |
leys | -1.263 |
idad | -1.120 |
amina | -1.115 |
ici | -1.089 |
tru | -1.076 |
Token | its |
Token ID | 663 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
leys | +5.288 |
tru | +4.833 |
amina | +4.801 |
idad | +4.779 |
fulness | +4.610 |
Neg logit contributions | |
keys | -4.527 |
swers | -4.341 |
goats | -4.334 |
osher | -4.232 |
Edge | -4.169 |
Token | presence |
Token ID | 4931 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
leys | +8.617 |
tru | +8.085 |
idad | +7.759 |
amina | +7.734 |
fulness | +7.546 |
Neg logit contributions | |
keys | -5.219 |
swers | -5.101 |
goats | -5.043 |
osher | -4.881 |
Edge | -4.680 |
Token | known |
Token ID | 1900 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
leys | +7.989 |
tru | +7.036 |
idad | +6.299 |
fulness | +6.120 |
ional | +6.082 |
Neg logit contributions | |
keys | -15.874 |
swers | -15.696 |
goats | -15.204 |
osher | -15.071 |
Tips | -14.769 |
Token | with |
Token ID | 351 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
leys | +3.884 |
tru | +3.391 |
idad | +3.387 |
amina | +3.311 |
fulness | +3.295 |
Neg logit contributions | |
keys | -4.259 |
goats | -4.124 |
swers | -4.099 |
osher | -3.941 |
Edge | -3.831 |
Token | a |
Token ID | 257 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
keys | +1.665 |
goats | +1.643 |
swers | +1.556 |
osher | +1.512 |
Edge | +1.453 |
Neg logit contributions | |
leys | -2.268 |
idad | -2.023 |
amina | -2.018 |
ici | -1.974 |
tru | -1.951 |
Token | pleasant |
Token ID | 15497 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
leys | +0.405 |
idad | +0.356 |
amina | +0.354 |
tru | +0.348 |
ici | +0.345 |
Neg logit contributions | |
keys | -0.377 |
goats | -0.369 |
swers | -0.357 |
osher | -0.345 |
Edge | -0.337 |
Token | , |
Token ID | 11 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
keys | +0.855 |
goats | +0.842 |
swers | +0.809 |
osher | +0.787 |
Edge | +0.763 |
Neg logit contributions | |
leys | -0.901 |
idad | -0.793 |
amina | -0.790 |
ici | -0.769 |
tru | -0.765 |
Token | , |
Token ID | 11 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
leys | +3.867 |
idad | +3.478 |
amina | +3.403 |
tru | +3.403 |
fulness | +3.376 |
Neg logit contributions | |
keys | -3.813 |
goats | -3.667 |
swers | -3.645 |
osher | -3.556 |
Edge | -3.461 |
Token | but |
Token ID | 475 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
leys | +4.064 |
idad | +3.575 |
tru | +3.574 |
amina | +3.512 |
ici | +3.446 |
Neg logit contributions | |
keys | -4.067 |
goats | -3.871 |
swers | -3.861 |
osher | -3.794 |
Tips | -3.626 |
Token | it |
Token ID | 340 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
leys | +1.656 |
idad | +1.464 |
amina | +1.446 |
tru | +1.441 |
ici | +1.417 |
Neg logit contributions | |
keys | -1.467 |
goats | -1.435 |
swers | -1.395 |
osher | -1.373 |
Edge | -1.307 |
Token | would |
Token ID | 561 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
keys | +1.532 |
goats | +1.512 |
swers | +1.438 |
osher | +1.393 |
Edge | +1.345 |
Neg logit contributions | |
leys | -1.930 |
idad | -1.715 |
amina | -1.710 |
ici | -1.669 |
tru | -1.656 |
Token | soon |
Token ID | 2582 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
leys | +1.978 |
idad | +1.703 |
amina | +1.696 |
tru | +1.679 |
ici | +1.643 |
Neg logit contributions | |
keys | -2.287 |
goats | -2.205 |
swers | -2.169 |
osher | -2.132 |
Tips | -2.088 |
Token | become |
Token ID | 1716 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
leys | +5.182 |
tru | +4.625 |
idad | +4.532 |
ici | +4.425 |
amina | +4.423 |
Neg logit contributions | |
keys | -5.509 |
swers | -5.257 |
Tips | -5.185 |
goats | -5.176 |
osher | -5.169 |
Token | Carter |
Token ID | 10831 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
tru | +10.035 |
leys | +9.841 |
idad | +8.629 |
fallacy | +8.403 |
amina | +8.320 |
Neg logit contributions | |
keys | -12.607 |
swers | -12.188 |
goats | -12.003 |
osher | -11.685 |
Tips | -11.579 |
Token | 's |
Token ID | 338 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
leys | +6.880 |
tru | +6.102 |
idad | +5.983 |
ici | +5.730 |
amina | +5.581 |
Neg logit contributions | |
keys | -9.735 |
goats | -9.698 |
swers | -9.437 |
osher | -9.045 |
Edge | -8.960 |
Token | calling |
Token ID | 4585 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
leys | +8.995 |
tru | +8.901 |
idad | +8.231 |
amina | +8.037 |
fallacy | +7.948 |
Neg logit contributions | |
keys | -8.731 |
swers | -8.494 |
osher | -8.201 |
goats | -8.183 |
Edge | -7.994 |
Token | card |
Token ID | 2657 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
leys | +3.324 |
tru | +2.990 |
idad | +2.899 |
amina | +2.830 |
ici | +2.774 |
Neg logit contributions | |
keys | -4.916 |
swers | -4.805 |
goats | -4.763 |
osher | -4.667 |
Tips | -4.531 |
Token | ." |
Token ID | 526 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
leys | +3.901 |
idad | +3.486 |
tru | +3.478 |
amina | +3.406 |
ici | +3.339 |
Neg logit contributions | |
keys | -3.894 |
goats | -3.756 |
swers | -3.756 |
osher | -3.673 |
Edge | -3.531 |
Token | 're |
Token ID | 821 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
keys | +1.084 |
goats | +1.068 |
swers | +1.009 |
osher | +0.975 |
Edge | +0.946 |
Neg logit contributions | |
leys | -1.555 |
amina | -1.395 |
idad | -1.393 |
ici | -1.356 |
tru | -1.348 |
Token | all |
Token ID | 477 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
keys | +2.509 |
goats | +2.508 |
swers | +2.326 |
osher | +2.216 |
Edge | +2.203 |
Neg logit contributions | |
leys | -3.894 |
idad | -3.505 |
amina | -3.489 |
ici | -3.407 |
tru | -3.339 |
Token | really |
Token ID | 1107 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
goats | +2.597 |
keys | +2.592 |
swers | +2.399 |
osher | +2.324 |
Edge | +2.281 |
Neg logit contributions | |
leys | -3.693 |
idad | -3.325 |
amina | -3.295 |
ici | -3.223 |
tru | -3.162 |
Token | close |
Token ID | 1969 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
goats | +4.189 |
keys | +4.131 |
swers | +3.770 |
Edge | +3.633 |
osher | +3.624 |
Neg logit contributions | |
leys | -6.259 |
idad | -5.616 |
amina | -5.566 |
ici | -5.473 |
tru | -5.276 |
Token | on |
Token ID | 319 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
leys | +0.250 |
idad | +0.221 |
amina | +0.220 |
ici | +0.215 |
tru | +0.215 |
Neg logit contributions | |
keys | -0.217 |
goats | -0.213 |
swers | -0.206 |
osher | -0.200 |
Edge | -0.192 |
Token | becoming |
Token ID | 5033 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
keys | +0.781 |
goats | +0.768 |
swers | +0.735 |
osher | +0.714 |
Edge | +0.691 |
Neg logit contributions | |
leys | -0.932 |
idad | -0.826 |
amina | -0.823 |
ici | -0.803 |
tru | -0.799 |
Token | a |
Token ID | 257 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
leys | +11.454 |
tru | +10.401 |
amina | +9.915 |
idad | +9.788 |
ici | +9.687 |
Neg logit contributions | |
keys | -11.194 |
swers | -10.528 |
osher | -10.475 |
odus | -10.454 |
goats | -10.426 |
Token | community |
Token ID | 2055 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
leys | +10.334 |
tru | +9.545 |
amina | +9.193 |
idad | +8.863 |
ici | +8.818 |
Neg logit contributions | |
keys | -11.087 |
goats | -10.606 |
swers | -10.552 |
Tips | -10.164 |
odus | -10.007 |
Token | ." |
Token ID | 526 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
keys | +0.671 |
goats | +0.659 |
swers | +0.632 |
osher | +0.614 |
Edge | +0.593 |
Neg logit contributions | |
leys | -0.798 |
idad | -0.708 |
amina | -0.705 |
ici | -0.688 |
tru | -0.686 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
keys | +0.655 |
goats | +0.645 |
swers | +0.622 |
osher | +0.606 |
Edge | +0.589 |
Neg logit contributions | |
leys | -0.596 |
idad | -0.519 |
amina | -0.517 |
ici | -0.502 |
tru | -0.499 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
leys | +0.173 |
idad | +0.151 |
amina | +0.150 |
ici | +0.146 |
tru | +0.143 |
Neg logit contributions | |
keys | -0.186 |
goats | -0.181 |
swers | -0.174 |
osher | -0.168 |
Edge | -0.167 |
Token | require |
Token ID | 2421 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
keys | +2.305 |
goats | +2.303 |
swers | +2.139 |
osher | +2.058 |
Edge | +1.986 |
Neg logit contributions | |
leys | -3.306 |
amina | -2.980 |
idad | -2.969 |
ici | -2.899 |
tru | -2.840 |
Token | dismantling |
Token ID | 41928 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
leys | +1.443 |
idad | +1.275 |
amina | +1.269 |
tru | +1.260 |
ici | +1.234 |
Neg logit contributions | |
keys | -1.325 |
goats | -1.275 |
swers | -1.244 |
osher | -1.223 |
Edge | -1.189 |
Token | a |
Token ID | 257 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
leys | +3.776 |
tru | +3.388 |
idad | +3.362 |
amina | +3.275 |
ici | +3.252 |
Neg logit contributions | |
keys | -3.681 |
goats | -3.543 |
swers | -3.462 |
osher | -3.453 |
Edge | -3.295 |
Token | long |
Token ID | 890 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
leys | +4.602 |
tru | +4.187 |
idad | +4.070 |
amina | +4.025 |
ici | +3.887 |
Neg logit contributions | |
keys | -4.841 |
goats | -4.629 |
swers | -4.585 |
osher | -4.414 |
Edge | -4.392 |
Token | - |
Token ID | 12 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
leys | +5.046 |
tru | +4.260 |
idad | +4.228 |
amina | +4.202 |
ici | +4.086 |
Neg logit contributions | |
keys | -6.114 |
goats | -5.979 |
swers | -5.675 |
osher | -5.633 |
Edge | -5.604 |
Token | standing |
Token ID | 5646 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
leys | +3.210 |
idad | +2.697 |
amina | +2.653 |
ici | +2.619 |
tru | +2.581 |
Neg logit contributions | |
goats | -4.876 |
keys | -4.743 |
swers | -4.678 |
osher | -4.584 |
Tips | -4.496 |
Token | and |
Token ID | 290 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
tru | +10.950 |
leys | +10.772 |
fallacy | +9.489 |
idad | +9.323 |
amina | +9.041 |
Neg logit contributions | |
keys | -12.419 |
ertodd | -11.511 |
goats | -11.442 |
osher | -11.222 |
swers | -11.189 |
Token | successful |
Token ID | 4388 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
leys | +3.482 |
tru | +3.167 |
idad | +3.043 |
amina | +3.028 |
ici | +2.940 |
Neg logit contributions | |
keys | -3.344 |
goats | -3.227 |
swers | -3.166 |
osher | -3.081 |
Edge | -3.032 |
Token | public |
Token ID | 1171 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
leys | +8.081 |
tru | +7.715 |
idad | +7.213 |
amina | +6.962 |
ici | +6.820 |
Neg logit contributions | |
keys | -8.018 |
goats | -7.299 |
swers | -7.190 |
osher | -7.015 |
ertodd | -6.857 |
Token | health |
Token ID | 1535 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
leys | +4.394 |
tru | +3.980 |
idad | +3.961 |
amina | +3.832 |
ici | +3.727 |
Neg logit contributions | |
keys | -4.813 |
goats | -4.622 |
swers | -4.440 |
osher | -4.361 |
Tips | -4.271 |
Token | initiative |
Token ID | 10219 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
leys | +4.049 |
tru | +3.691 |
idad | +3.656 |
amina | +3.583 |
ici | +3.501 |
Neg logit contributions | |
keys | -3.184 |
goats | -3.029 |
swers | -2.922 |
osher | -2.858 |
Edge | -2.707 |
Token | � |
Token ID | 247 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
leys | +2.487 |
idad | +2.199 |
amina | +2.189 |
ici | +2.135 |
tru | +2.125 |
Neg logit contributions | |
keys | -2.208 |
goats | -2.172 |
swers | -2.083 |
osher | -2.025 |
Edge | -1.961 |
Token | m |
Token ID | 76 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
leys | +2.072 |
amina | +1.627 |
idad | +1.625 |
ici | +1.554 |
tru | +1.533 |
Neg logit contributions | |
keys | -5.293 |
goats | -5.237 |
osher | -5.083 |
swers | -5.073 |
Edge | -4.941 |
Token | sick |
Token ID | 6639 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
keys | +1.530 |
goats | +1.515 |
swers | +1.441 |
osher | +1.385 |
Edge | +1.339 |
Neg logit contributions | |
leys | -2.061 |
idad | -1.839 |
amina | -1.836 |
ici | -1.787 |
tru | -1.768 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
keys | +2.549 |
goats | +2.540 |
swers | +2.394 |
osher | +2.301 |
Edge | +2.193 |
Neg logit contributions | |
leys | -4.153 |
amina | -3.759 |
idad | -3.732 |
tru | -3.626 |
ici | -3.612 |
Token | This |
Token ID | 770 |
Feature activation | -9.79e-04 |
Pos logit contributions | |
keys | +1.562 |
goats | +1.540 |
swers | +1.478 |
osher | +1.431 |
Edge | +1.390 |
Neg logit contributions | |
leys | -1.759 |
idad | -1.553 |
amina | -1.547 |
ici | -1.505 |
tru | -1.496 |
Token | just |
Token ID | 655 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
leys | +0.009 |
idad | +0.008 |
amina | +0.008 |
tru | +0.007 |
ici | +0.007 |
Neg logit contributions | |
keys | -0.007 |
goats | -0.007 |
swers | -0.007 |
osher | -0.007 |
Edge | -0.006 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
leys | +11.088 |
tru | +10.301 |
idad | +9.813 |
ici | +9.483 |
fulness | +9.353 |
Neg logit contributions | |
keys | -11.915 |
swers | -11.054 |
osher | -10.923 |
Edge | -10.710 |
Tips | -10.629 |
Token | me |
Token ID | 502 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
leys | +2.442 |
idad | +2.193 |
tru | +2.187 |
amina | +2.173 |
ici | +2.132 |
Neg logit contributions | |
keys | -2.165 |
goats | -2.053 |
swers | -1.999 |
osher | -1.975 |
Edge | -1.931 |
Token | sick |
Token ID | 6639 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
goats | +2.609 |
keys | +2.607 |
swers | +2.452 |
osher | +2.340 |
Edge | +2.285 |
Neg logit contributions | |
leys | -3.411 |
amina | -3.043 |
idad | -3.026 |
ici | -2.956 |
tru | -2.874 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
keys | +0.394 |
goats | +0.387 |
swers | +0.372 |
osher | +0.362 |
Edge | +0.351 |
Neg logit contributions | |
leys | -0.436 |
idad | -0.384 |
amina | -0.383 |
ici | -0.374 |
tru | -0.372 |
Token | � |
Token ID | 447 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
keys | +1.139 |
goats | +1.122 |
swers | +1.077 |
osher | +1.046 |
Edge | +1.014 |
Neg logit contributions | |
leys | -1.243 |
idad | -1.097 |
amina | -1.092 |
ici | -1.064 |
tru | -1.058 |
Token | consulting |
Token ID | 18158 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
keys | +0.219 |
goats | +0.216 |
swers | +0.208 |
osher | +0.203 |
Edge | +0.197 |
Neg logit contributions | |
leys | -0.206 |
idad | -0.180 |
amina | -0.179 |
tru | -0.174 |
ici | -0.174 |
Token | room |
Token ID | 2119 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
goats | +5.116 |
keys | +5.050 |
swers | +4.604 |
osher | +4.526 |
eer | +4.516 |
Neg logit contributions | |
leys | -6.408 |
amina | -5.559 |
idad | -5.552 |
ici | -5.519 |
tru | -5.271 |
Token |
|
Token ID | 198 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
leys | +2.709 |
idad | +2.407 |
amina | +2.357 |
tru | +2.326 |
ici | +2.324 |
Neg logit contributions | |
keys | -2.805 |
goats | -2.736 |
swers | -2.667 |
osher | -2.601 |
Edge | -2.514 |
Token |
|
Token ID | 198 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
leys | +2.938 |
idad | +2.528 |
amina | +2.496 |
tru | +2.467 |
ici | +2.440 |
Neg logit contributions | |
keys | -4.011 |
goats | -4.007 |
swers | -3.891 |
osher | -3.846 |
Edge | -3.638 |
Token | – |
Token ID | 1906 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
leys | +3.499 |
idad | +3.075 |
amina | +3.016 |
ici | +2.946 |
tru | +2.890 |
Neg logit contributions | |
goats | -3.905 |
keys | -3.839 |
swers | -3.747 |
osher | -3.662 |
Khe | -3.471 |
Token | Come |
Token ID | 7911 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
leys | +0.790 |
idad | +0.698 |
amina | +0.695 |
ici | +0.679 |
tru | +0.679 |
Neg logit contributions | |
keys | -0.723 |
goats | -0.709 |
swers | -0.682 |
osher | -0.668 |
Edge | -0.646 |
Token | along |
Token ID | 1863 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
leys | +11.242 |
tru | +10.218 |
fulness | +9.729 |
idad | +9.716 |
amina | +9.676 |
Neg logit contributions | |
osher | -11.633 |
keys | -11.471 |
Edge | -11.197 |
swers | -10.834 |
goats | -10.816 |
Token | , |
Token ID | 11 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
leys | +9.130 |
tru | +7.867 |
amina | +7.830 |
idad | +7.706 |
ici | +7.597 |
Neg logit contributions | |
keys | -10.003 |
swers | -9.745 |
osher | -9.724 |
goats | -9.314 |
Edge | -9.260 |
Token | my |
Token ID | 616 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
leys | +7.323 |
tru | +6.682 |
idad | +6.472 |
amina | +6.457 |
ici | +6.444 |
Neg logit contributions | |
keys | -7.158 |
osher | -6.848 |
swers | -6.821 |
goats | -6.634 |
Edge | -6.545 |
Token | dear |
Token ID | 13674 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
keys | +2.387 |
goats | +2.370 |
swers | +2.256 |
osher | +2.192 |
Tips | +2.134 |
Neg logit contributions | |
leys | -2.097 |
idad | -1.800 |
amina | -1.793 |
ici | -1.751 |
tru | -1.711 |
Token | , |
Token ID | 11 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
leys | +2.949 |
idad | +2.623 |
amina | +2.585 |
tru | +2.559 |
ici | +2.537 |
Neg logit contributions | |
keys | -3.167 |
goats | -3.081 |
swers | -3.029 |
osher | -2.979 |
Edge | -2.879 |
Token | oat |
Token ID | 15073 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
leys | +1.020 |
idad | +0.926 |
amina | +0.920 |
ici | +0.903 |
tru | +0.893 |
Neg logit contributions | |
keys | -0.537 |
goats | -0.537 |
swers | -0.509 |
osher | -0.484 |
Edge | -0.466 |
Token | . |
Token ID | 13 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
leys | +2.220 |
idad | +1.959 |
amina | +1.932 |
tru | +1.896 |
ici | +1.876 |
Neg logit contributions | |
keys | -2.208 |
goats | -2.154 |
swers | -2.087 |
osher | -2.058 |
Edge | -1.976 |
Token | When |
Token ID | 1649 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
leys | +4.485 |
tru | +3.911 |
idad | +3.809 |
amina | +3.788 |
ici | +3.773 |
Neg logit contributions | |
keys | -5.157 |
goats | -5.104 |
osher | -5.013 |
swers | -5.004 |
odus | -4.602 |
Token | bottleneck |
Token ID | 49936 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
leys | +5.113 |
amina | +4.475 |
tru | +4.434 |
idad | +4.408 |
ici | +4.284 |
Neg logit contributions | |
keys | -4.864 |
goats | -4.656 |
osher | -4.599 |
swers | -4.578 |
Edge | -4.298 |
Token | buffers |
Token ID | 39334 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
leys | +1.590 |
amina | +1.323 |
idad | +1.315 |
tru | +1.275 |
ici | +1.249 |
Neg logit contributions | |
keys | -2.511 |
goats | -2.473 |
swers | -2.419 |
osher | -2.393 |
Edge | -2.316 |
Token | are |
Token ID | 389 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
leys | +7.170 |
tru | +5.973 |
amina | +5.870 |
idad | +5.820 |
ional | +5.661 |
Neg logit contributions | |
keys | -10.476 |
osher | -10.060 |
swers | -10.049 |
goats | -9.925 |
Edge | -9.543 |
Token | small |
Token ID | 1402 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
leys | +9.761 |
tru | +8.877 |
amina | +8.536 |
nearest | +8.388 |
ional | +8.337 |
Neg logit contributions | |
keys | -12.802 |
osher | -12.375 |
swers | -12.185 |
goats | -11.752 |
Edge | -11.652 |
Token | , |
Token ID | 11 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
leys | +3.855 |
amina | +3.374 |
idad | +3.298 |
ici | +3.255 |
tru | +3.225 |
Neg logit contributions | |
keys | -4.408 |
goats | -4.289 |
swers | -4.202 |
osher | -4.154 |
Edge | -4.003 |
Token | loss |
Token ID | 2994 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
leys | +2.729 |
amina | +2.400 |
tru | +2.395 |
idad | +2.390 |
ici | +2.328 |
Neg logit contributions | |
keys | -2.445 |
goats | -2.350 |
osher | -2.285 |
swers | -2.278 |
Edge | -2.133 |
Token | - |
Token ID | 12 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
leys | +2.722 |
idad | +2.351 |
amina | +2.296 |
tru | +2.284 |
ici | +2.275 |
Neg logit contributions | |
keys | -3.211 |
goats | -3.141 |
swers | -3.072 |
osher | -3.040 |
Edge | -2.889 |
Token | based |
Token ID | 3106 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
leys | +0.839 |
idad | +0.741 |
amina | +0.737 |
ici | +0.722 |
tru | +0.716 |
Neg logit contributions | |
keys | -0.771 |
goats | -0.768 |
swers | -0.737 |
osher | -0.718 |
Edge | -0.690 |
Token | with |
Token ID | 351 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
leys | +0.771 |
idad | +0.688 |
amina | +0.683 |
ici | +0.669 |
tru | +0.667 |
Neg logit contributions | |
keys | -0.655 |
goats | -0.640 |
swers | -0.617 |
osher | -0.602 |
Edge | -0.585 |
Token | a |
Token ID | 257 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
leys | +6.523 |
tru | +6.076 |
idad | +5.991 |
amina | +5.843 |
ici | +5.746 |
Neg logit contributions | |
keys | -5.673 |
osher | -5.335 |
swers | -5.283 |
goats | -5.252 |
Edge | -4.970 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
leys | +3.859 |
tru | +3.475 |
idad | +3.470 |
amina | +3.399 |
ici | +3.308 |
Neg logit contributions | |
keys | -3.991 |
goats | -3.844 |
swers | -3.719 |
osher | -3.667 |
Edge | -3.625 |
Token | of |
Token ID | 286 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
keys | +0.943 |
goats | +0.927 |
swers | +0.885 |
osher | +0.858 |
Edge | +0.828 |
Neg logit contributions | |
leys | -1.235 |
idad | -1.101 |
amina | -1.097 |
ici | -1.072 |
tru | -1.067 |
Token | his |
Token ID | 465 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
leys | +4.049 |
idad | +3.733 |
tru | +3.696 |
amina | +3.665 |
ici | +3.548 |
Neg logit contributions | |
keys | -3.097 |
swers | -2.913 |
goats | -2.910 |
osher | -2.857 |
Edge | -2.746 |
Token | past |
Token ID | 1613 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
leys | +3.125 |
idad | +2.798 |
tru | +2.787 |
amina | +2.780 |
ici | +2.662 |
Neg logit contributions | |
keys | -2.984 |
goats | -2.868 |
swers | -2.833 |
osher | -2.779 |
Edge | -2.693 |
Token | , |
Token ID | 11 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
leys | +11.595 |
tru | +10.993 |
idad | +10.623 |
amina | +10.505 |
fulness | +10.351 |
Neg logit contributions | |
keys | -10.697 |
goats | -10.362 |
swers | -9.919 |
osher | -9.844 |
Tips | -9.716 |
Token | but |
Token ID | 475 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
leys | +7.407 |
tru | +6.746 |
idad | +6.552 |
amina | +6.445 |
ici | +6.361 |
Neg logit contributions | |
keys | -6.419 |
goats | -6.209 |
swers | -5.908 |
osher | -5.869 |
Edge | -5.717 |
Token | a |
Token ID | 257 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
leys | +3.526 |
idad | +3.104 |
tru | +3.096 |
amina | +3.063 |
ici | +3.001 |
Neg logit contributions | |
keys | -3.111 |
goats | -2.984 |
swers | -2.897 |
osher | -2.872 |
Edge | -2.748 |
Token | fe |
Token ID | 730 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
leys | +2.667 |
idad | +2.369 |
amina | +2.345 |
tru | +2.345 |
ici | +2.271 |
Neg logit contributions | |
keys | -2.645 |
goats | -2.560 |
swers | -2.458 |
osher | -2.407 |
Edge | -2.379 |
Token | ist |
Token ID | 396 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
leys | +2.650 |
idad | +2.378 |
amina | +2.331 |
ici | +2.295 |
tru | +2.244 |
Neg logit contributions | |
keys | -2.528 |
goats | -2.528 |
swers | -2.392 |
osher | -2.325 |
Edge | -2.288 |
Token | passive |
Token ID | 14513 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
leys | +5.160 |
tru | +4.639 |
idad | +4.615 |
amina | +4.563 |
ici | +4.442 |
Neg logit contributions | |
keys | -4.823 |
goats | -4.613 |
osher | -4.560 |
swers | -4.508 |
Edge | -4.266 |
Token | defense |
Token ID | 3761 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
leys | +2.631 |
idad | +2.314 |
amina | +2.301 |
tru | +2.269 |
ici | +2.243 |
Neg logit contributions | |
keys | -2.359 |
goats | -2.302 |
swers | -2.228 |
osher | -2.188 |
Edge | -2.089 |
Token | and |
Token ID | 290 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
leys | +4.958 |
idad | +4.383 |
tru | +4.372 |
fulness | +4.336 |
amina | +4.315 |
Neg logit contributions | |
keys | -5.204 |
goats | -5.000 |
swers | -4.902 |
osher | -4.898 |
odus | -4.597 |
Token | un |
Token ID | 555 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
leys | +3.058 |
tru | +2.689 |
amina | +2.676 |
idad | +2.664 |
ici | +2.596 |
Neg logit contributions | |
keys | -2.863 |
goats | -2.756 |
swers | -2.668 |
osher | -2.628 |
Edge | -2.555 |
Token | en |
Token ID | 268 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
leys | +3.969 |
idad | +3.653 |
ici | +3.530 |
amina | +3.439 |
fulness | +3.369 |
Neg logit contributions | |
goats | -3.117 |
keys | -2.999 |
swers | -2.967 |
osher | -2.856 |
Edge | -2.747 |
Token | force |
Token ID | 3174 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
leys | +1.745 |
idad | +1.502 |
amina | +1.491 |
ici | +1.437 |
tru | +1.415 |
Neg logit contributions | |
keys | -2.407 |
goats | -2.397 |
swers | -2.316 |
osher | -2.246 |
Tips | -2.200 |
Token | able |
Token ID | 540 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
leys | +8.262 |
fulness | +7.746 |
idad | +7.118 |
tru | +6.829 |
ional | +6.827 |
Neg logit contributions | |
goats | -14.628 |
keys | -14.304 |
swers | -14.291 |
osher | -13.884 |
Tips | -13.313 |
Token | indict |
Token ID | 16056 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
leys | +7.289 |
tru | +6.530 |
idad | +6.405 |
fulness | +6.209 |
amina | +6.155 |
Neg logit contributions | |
keys | -7.519 |
goats | -7.256 |
swers | -7.233 |
osher | -7.144 |
odus | -6.705 |
Token | ments |
Token ID | 902 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
leys | +2.522 |
amina | +1.873 |
ici | +1.842 |
idad | +1.837 |
tru | +1.815 |
Neg logit contributions | |
keys | -6.589 |
goats | -6.579 |
swers | -6.378 |
osher | -6.261 |
Edge | -6.161 |
Token | — |
Token ID | 851 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
leys | +3.593 |
idad | +3.133 |
amina | +3.088 |
tru | +3.081 |
ici | +3.069 |
Neg logit contributions | |
keys | -3.592 |
goats | -3.493 |
swers | -3.371 |
osher | -3.292 |
Tips | -3.183 |
Token | but |
Token ID | 475 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
leys | +1.051 |
idad | +0.925 |
amina | +0.919 |
tru | +0.909 |
ici | +0.901 |
Neg logit contributions | |
keys | -0.934 |
goats | -0.917 |
swers | -0.877 |
osher | -0.862 |
Tips | -0.824 |
Token | power |
Token ID | 1176 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
leys | +0.067 |
idad | +0.059 |
amina | +0.059 |
ici | +0.058 |
tru | +0.058 |
Neg logit contributions | |
keys | -0.064 |
goats | -0.063 |
swers | -0.061 |
osher | -0.059 |
Edge | -0.057 |
Token | modules |
Token ID | 13103 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
leys | +1.414 |
amina | +1.196 |
idad | +1.195 |
ici | +1.140 |
tru | +1.132 |
Neg logit contributions | |
keys | -2.188 |
goats | -2.147 |
swers | -2.114 |
osher | -2.062 |
Edge | -1.993 |
Token | , |
Token ID | 11 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
leys | +5.143 |
idad | +4.495 |
amina | +4.480 |
tru | +4.403 |
ici | +4.277 |
Neg logit contributions | |
keys | -5.296 |
swers | -5.085 |
goats | -5.047 |
osher | -4.914 |
odus | -4.720 |
Token | ensure |
Token ID | 4155 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
leys | +0.373 |
idad | +0.329 |
amina | +0.328 |
tru | +0.322 |
ici | +0.321 |
Neg logit contributions | |
keys | -0.319 |
goats | -0.312 |
swers | -0.301 |
osher | -0.292 |
Edge | -0.282 |
Token | the |
Token ID | 262 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
leys | +3.406 |
amina | +3.003 |
idad | +2.981 |
tru | +2.955 |
ici | +2.869 |
Neg logit contributions | |
keys | -3.679 |
goats | -3.577 |
swers | -3.470 |
osher | -3.407 |
Edge | -3.326 |
Token | structural |
Token ID | 13204 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
leys | +4.230 |
tru | +3.756 |
idad | +3.730 |
amina | +3.701 |
ici | +3.555 |
Neg logit contributions | |
keys | -4.462 |
goats | -4.276 |
swers | -4.240 |
osher | -4.163 |
Edge | -3.992 |
Token | integrity |
Token ID | 11540 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
leys | +6.505 |
amina | +5.842 |
tru | +5.798 |
idad | +5.668 |
fulness | +5.332 |
Neg logit contributions | |
keys | -15.617 |
swers | -15.186 |
osher | -14.878 |
goats | -14.782 |
odus | -14.452 |
Token | and |
Token ID | 290 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
leys | +4.914 |
idad | +4.372 |
amina | +4.329 |
fulness | +4.263 |
tru | +4.214 |
Neg logit contributions | |
keys | -5.061 |
goats | -4.883 |
swers | -4.830 |
osher | -4.659 |
Tips | -4.488 |
Token | card |
Token ID | 2657 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
keys | +0.260 |
goats | +0.255 |
swers | +0.246 |
osher | +0.240 |
Edge | +0.232 |
Neg logit contributions | |
leys | -0.274 |
idad | -0.241 |
amina | -0.241 |
tru | -0.234 |
ici | -0.234 |
Token | is |
Token ID | 318 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
leys | +5.909 |
amina | +5.373 |
idad | +5.308 |
tru | +5.217 |
fulness | +5.126 |
Neg logit contributions | |
keys | -6.041 |
goats | -5.990 |
osher | -5.778 |
swers | -5.776 |
odus | -5.510 |
Token | protected |
Token ID | 6861 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
leys | +0.825 |
amina | +0.737 |
idad | +0.734 |
tru | +0.717 |
ici | +0.712 |
Neg logit contributions | |
keys | -0.724 |
goats | -0.709 |
swers | -0.681 |
osher | -0.665 |
Edge | -0.642 |
Token | up |
Token ID | 510 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
keys | +1.672 |
goats | +1.640 |
swers | +1.535 |
osher | +1.477 |
Edge | +1.424 |
Neg logit contributions | |
leys | -3.068 |
idad | -2.774 |
amina | -2.769 |
ici | -2.711 |
tru | -2.681 |
Token | Netflix |
Token ID | 12074 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
leys | +2.622 |
tru | +2.263 |
idad | +2.255 |
amina | +2.233 |
ici | +2.200 |
Neg logit contributions | |
keys | -3.207 |
goats | -3.142 |
swers | -3.085 |
osher | -3.028 |
Tips | -2.874 |
Token | on |
Token ID | 319 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
leys | +4.039 |
tru | +3.445 |
idad | +3.422 |
amina | +3.328 |
ici | +3.295 |
Neg logit contributions | |
keys | -5.148 |
goats | -5.143 |
swers | -5.007 |
osher | -4.875 |
Edge | -4.590 |
Token | Kodi |
Token ID | 44129 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
keys | +1.307 |
goats | +1.289 |
swers | +1.243 |
osher | +1.215 |
Edge | +1.185 |
Neg logit contributions | |
leys | -1.018 |
idad | -0.876 |
amina | -0.873 |
ici | -0.843 |
tru | -0.837 |
Token | 17 |
Token ID | 1596 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
keys | +2.266 |
goats | +2.217 |
swers | +2.083 |
osher | +2.011 |
Edge | +1.958 |
Neg logit contributions | |
leys | -3.706 |
amina | -3.384 |
idad | -3.373 |
ici | -3.306 |
tru | -3.238 |
Token | Krypt |
Token ID | 44679 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
keys | +2.014 |
goats | +1.970 |
swers | +1.874 |
osher | +1.828 |
Edge | +1.773 |
Neg logit contributions | |
leys | -2.501 |
amina | -2.239 |
idad | -2.231 |
ici | -2.174 |
tru | -2.144 |
Token | on |
Token ID | 261 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
keys | +5.346 |
goats | +4.542 |
osher | +4.255 |
eer | +4.251 |
swers | +4.054 |
Neg logit contributions | |
leys | -14.581 |
tru | -13.280 |
idad | -13.265 |
amina | -13.124 |
fallacy | -13.044 |
Token | differs |
Token ID | 24242 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
keys | +4.438 |
goats | +4.380 |
swers | +4.096 |
osher | +3.963 |
Tips | +3.929 |
Neg logit contributions | |
leys | -5.722 |
amina | -5.203 |
idad | -5.124 |
ici | -4.974 |
tru | -4.831 |
Token | a |
Token ID | 257 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
keys | +1.219 |
goats | +1.196 |
swers | +1.142 |
osher | +1.105 |
Edge | +1.065 |
Neg logit contributions | |
leys | -1.679 |
idad | -1.502 |
amina | -1.497 |
ici | -1.462 |
tru | -1.455 |
Token | little |
Token ID | 1310 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
keys | +0.250 |
goats | +0.246 |
swers | +0.237 |
osher | +0.231 |
Edge | +0.225 |
Neg logit contributions | |
leys | -0.223 |
idad | -0.193 |
amina | -0.193 |
ici | -0.187 |
tru | -0.186 |
Token | bit |
Token ID | 1643 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
keys | +2.808 |
goats | +2.778 |
swers | +2.634 |
osher | +2.560 |
Tips | +2.477 |
Neg logit contributions | |
leys | -3.676 |
idad | -3.283 |
amina | -3.269 |
ici | -3.212 |
tru | -3.162 |
Token | hunting |
Token ID | 10988 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
leys | +0.300 |
idad | +0.265 |
amina | +0.262 |
tru | +0.256 |
ici | +0.255 |
Neg logit contributions | |
keys | -0.272 |
goats | -0.265 |
swers | -0.257 |
osher | -0.251 |
Edge | -0.242 |
Token | for |
Token ID | 329 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
goats | +5.639 |
keys | +5.466 |
swers | +4.997 |
Tips | +4.806 |
eer | +4.742 |
Neg logit contributions | |
leys | -7.570 |
idad | -6.870 |
ici | -6.792 |
amina | -6.790 |
tru | -6.352 |
Token | digital |
Token ID | 4875 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
goats | +3.154 |
keys | +3.152 |
swers | +2.978 |
osher | +2.843 |
Tips | +2.776 |
Neg logit contributions | |
leys | -3.559 |
idad | -3.169 |
amina | -3.105 |
ici | -3.079 |
tru | -2.983 |
Token | characters |
Token ID | 3435 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
keys | +1.411 |
goats | +1.394 |
swers | +1.312 |
osher | +1.253 |
Edge | +1.214 |
Neg logit contributions | |
leys | -2.058 |
idad | -1.841 |
amina | -1.838 |
ici | -1.799 |
tru | -1.774 |
Token | that |
Token ID | 326 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
goats | +3.574 |
keys | +3.568 |
swers | +3.350 |
osher | +3.214 |
Edge | +3.147 |
Neg logit contributions | |
leys | -4.493 |
amina | -3.997 |
idad | -3.975 |
ici | -3.883 |
tru | -3.785 |
Token | show |
Token ID | 905 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
goats | +5.215 |
keys | +5.071 |
swers | +4.787 |
osher | +4.542 |
Edge | +4.430 |
Neg logit contributions | |
leys | -6.486 |
idad | -5.960 |
amina | -5.872 |
ici | -5.768 |
tru | -5.397 |
Token | up |
Token ID | 510 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
goats | +6.517 |
keys | +6.204 |
swers | +5.569 |
eer | +5.299 |
Tips | +5.166 |
Neg logit contributions | |
leys | -12.589 |
ici | -11.265 |
idad | -11.216 |
amina | -11.035 |
ulk | -10.773 |
Token | on |
Token ID | 319 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
leys | +0.045 |
idad | +0.039 |
amina | +0.039 |
tru | +0.038 |
ici | +0.038 |
Neg logit contributions | |
keys | -0.041 |
goats | -0.041 |
swers | -0.039 |
osher | -0.038 |
Edge | -0.037 |
Token | their |
Token ID | 511 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
goats | +4.765 |
keys | +4.709 |
swers | +4.418 |
osher | +4.197 |
Edge | +4.113 |
Neg logit contributions | |
leys | -5.930 |
idad | -5.413 |
amina | -5.329 |
ici | -5.115 |
ulk | -4.999 |
Token | smartphone |
Token ID | 11745 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
goats | +2.473 |
keys | +2.469 |
swers | +2.316 |
osher | +2.228 |
Edge | +2.169 |
Neg logit contributions | |
leys | -2.987 |
idad | -2.680 |
amina | -2.670 |
ici | -2.580 |
tru | -2.510 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
leys | +1.196 |
idad | +1.055 |
amina | +1.043 |
tru | +1.032 |
ici | +1.024 |
Neg logit contributions | |
keys | -1.039 |
goats | -1.017 |
swers | -0.985 |
osher | -0.966 |
Edge | -0.925 |
Token | tattoo |
Token ID | 18785 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
keys | +1.052 |
goats | +1.034 |
swers | +0.981 |
osher | +0.946 |
Edge | +0.912 |
Neg logit contributions | |
leys | -1.589 |
idad | -1.426 |
amina | -1.422 |
ici | -1.388 |
tru | -1.380 |
Token | � |
Token ID | 564 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
keys | +2.515 |
goats | +2.509 |
swers | +2.360 |
osher | +2.282 |
Edge | +2.209 |
Neg logit contributions | |
leys | -2.968 |
amina | -2.633 |
idad | -2.625 |
ici | -2.548 |
tru | -2.515 |
Token | � |
Token ID | 246 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
leys | +1.119 |
idad | +0.967 |
amina | +0.960 |
ici | +0.929 |
tru | +0.929 |
Neg logit contributions | |
keys | -1.418 |
goats | -1.398 |
swers | -1.345 |
osher | -1.324 |
Edge | -1.280 |
Token | it |
Token ID | 270 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
keys | +1.798 |
goats | +1.771 |
swers | +1.696 |
osher | +1.647 |
Edge | +1.599 |
Neg logit contributions | |
leys | -1.940 |
idad | -1.713 |
amina | -1.706 |
ici | -1.657 |
tru | -1.647 |
Token | was |
Token ID | 373 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
leys | +0.992 |
idad | +0.875 |
amina | +0.874 |
tru | +0.857 |
ici | +0.852 |
Neg logit contributions | |
keys | -0.881 |
goats | -0.861 |
swers | -0.828 |
osher | -0.807 |
Edge | -0.787 |
Token | satire |
Token ID | 35704 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
keys | +1.241 |
goats | +1.222 |
swers | +1.169 |
osher | +1.134 |
Edge | +1.096 |
Neg logit contributions | |
leys | -1.525 |
idad | -1.353 |
amina | -1.349 |
ici | -1.315 |
tru | -1.308 |
Token | ! |
Token ID | 0 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
goats | +7.095 |
keys | +6.917 |
swers | +6.705 |
osher | +6.356 |
Tips | +6.287 |
Neg logit contributions | |
leys | -9.732 |
amina | -8.776 |
idad | -8.595 |
ici | -8.267 |
tru | -8.078 |
Token | � |
Token ID | 447 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
keys | +2.147 |
goats | +2.124 |
swers | +2.038 |
osher | +1.970 |
Edge | +1.913 |
Neg logit contributions | |
leys | -2.392 |
idad | -2.113 |
amina | -2.108 |
ici | -2.040 |
tru | -2.019 |
Token | � |
Token ID | 247 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
keys | +1.377 |
goats | +1.358 |
swers | +1.312 |
osher | +1.271 |
Edge | +1.242 |
Neg logit contributions | |
leys | -1.263 |
idad | -1.099 |
amina | -1.096 |
ici | -1.065 |
tru | -1.056 |
Token | on |
Token ID | 319 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
keys | +2.147 |
goats | +2.119 |
swers | +2.037 |
osher | +1.971 |
Edge | +1.918 |
Neg logit contributions | |
leys | -2.267 |
idad | -1.998 |
amina | -1.988 |
ici | -1.935 |
tru | -1.914 |
Token | my |
Token ID | 616 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
keys | +2.838 |
goats | +2.824 |
swers | +2.666 |
osher | +2.572 |
Edge | +2.514 |
Neg logit contributions | |
leys | -3.233 |
amina | -2.869 |
idad | -2.867 |
ici | -2.766 |
tru | -2.735 |
Token | of |
Token ID | 286 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
leys | +3.600 |
idad | +3.159 |
amina | +3.106 |
ici | +3.077 |
tru | +3.044 |
Neg logit contributions | |
keys | -3.711 |
goats | -3.621 |
swers | -3.541 |
osher | -3.414 |
Edge | -3.292 |
Token | the |
Token ID | 262 |
Feature activation | +8.16e-03 |
Pos logit contributions | |
keys | +1.293 |
goats | +1.273 |
swers | +1.220 |
osher | +1.186 |
Edge | +1.149 |
Neg logit contributions | |
leys | -1.457 |
idad | -1.288 |
amina | -1.282 |
ici | -1.251 |
tru | -1.245 |
Token | movie |
Token ID | 3807 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
keys | +0.066 |
goats | +0.065 |
swers | +0.063 |
osher | +0.061 |
Edge | +0.059 |
Neg logit contributions | |
leys | -0.065 |
idad | -0.057 |
amina | -0.057 |
tru | -0.056 |
ici | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
leys | +3.580 |
idad | +3.136 |
amina | +3.085 |
ici | +3.050 |
tru | +3.035 |
Neg logit contributions | |
keys | -4.148 |
goats | -4.060 |
swers | -3.968 |
osher | -3.840 |
Edge | -3.733 |
Token | and |
Token ID | 290 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
keys | +1.060 |
goats | +1.045 |
swers | +1.005 |
osher | +0.979 |
Edge | +0.950 |
Neg logit contributions | |
leys | -1.029 |
idad | -0.901 |
amina | -0.897 |
ici | -0.872 |
tru | -0.868 |
Token | shows |
Token ID | 2523 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
goats | +5.158 |
keys | +5.087 |
swers | +4.799 |
osher | +4.600 |
Edge | +4.511 |
Neg logit contributions | |
leys | -7.085 |
idad | -6.437 |
amina | -6.366 |
ici | -6.139 |
tru | -6.037 |
Token | Cycl |
Token ID | 28007 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
goats | +7.844 |
keys | +7.749 |
swers | +7.109 |
Edge | +6.889 |
eer | +6.878 |
Neg logit contributions | |
leys | -9.479 |
idad | -8.429 |
amina | -8.329 |
ici | -8.083 |
tru | -8.019 |
Token | ops |
Token ID | 2840 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
leys | +2.392 |
amina | +2.144 |
idad | +2.133 |
tru | +2.090 |
ici | +2.079 |
Neg logit contributions | |
keys | -2.595 |
goats | -2.520 |
swers | -2.508 |
osher | -2.390 |
Edge | -2.336 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
keys | +3.174 |
goats | +3.165 |
swers | +2.978 |
osher | +2.875 |
Edge | +2.823 |
Neg logit contributions | |
leys | -3.765 |
idad | -3.369 |
amina | -3.336 |
ici | -3.233 |
tru | -3.191 |
Token | Jean |
Token ID | 11320 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
keys | +2.165 |
goats | +2.144 |
swers | +2.044 |
osher | +1.970 |
Edge | +1.932 |
Neg logit contributions | |
leys | -2.480 |
idad | -2.207 |
amina | -2.190 |
ici | -2.143 |
tru | -2.115 |
Token | Grey |
Token ID | 13980 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
keys | +1.865 |
goats | +1.838 |
swers | +1.771 |
osher | +1.726 |
Edge | +1.671 |
Neg logit contributions | |
leys | -1.841 |
amina | -1.606 |
idad | -1.606 |
ici | -1.563 |
tru | -1.557 |
Token | Brian |
Token ID | 8403 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
keys | +1.973 |
goats | +1.925 |
swers | +1.831 |
osher | +1.770 |
Edge | +1.719 |
Neg logit contributions | |
leys | -2.792 |
amina | -2.517 |
idad | -2.504 |
ici | -2.445 |
tru | -2.429 |
Token | King |
Token ID | 2677 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
keys | +4.729 |
goats | +4.534 |
swers | +4.084 |
Khe | +3.837 |
Howe | +3.622 |
Neg logit contributions | |
leys | -13.904 |
amina | -13.304 |
idad | -13.136 |
ici | -12.873 |
tru | -12.499 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
keys | +4.474 |
goats | +4.332 |
swers | +4.208 |
osher | +3.989 |
Edge | +3.927 |
Neg logit contributions | |
leys | -5.395 |
amina | -4.842 |
idad | -4.768 |
ici | -4.633 |
tru | -4.608 |
Token |
|
Token ID | 198 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
leys | +0.808 |
idad | +0.701 |
amina | +0.698 |
ici | +0.677 |
tru | +0.672 |
Neg logit contributions | |
keys | -0.927 |
goats | -0.911 |
swers | -0.880 |
osher | -0.856 |
Edge | -0.838 |
Token | John |
Token ID | 7554 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
leys | +4.362 |
idad | +3.912 |
amina | +3.786 |
tru | +3.735 |
ici | +3.728 |
Neg logit contributions | |
goats | -3.699 |
keys | -3.512 |
swers | -3.448 |
osher | -3.415 |
Khe | -3.197 |
Token | Brian |
Token ID | 8403 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
keys | +3.852 |
goats | +3.763 |
swers | +3.572 |
osher | +3.440 |
Edge | +3.339 |
Neg logit contributions | |
leys | -5.166 |
amina | -4.695 |
idad | -4.634 |
ici | -4.527 |
tru | -4.471 |
Token | King |
Token ID | 2677 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
keys | +4.055 |
goats | +3.983 |
swers | +3.517 |
Khe | +3.260 |
Goodman | +3.215 |
Neg logit contributions | |
leys | -12.105 |
amina | -11.498 |
idad | -11.370 |
ici | -11.170 |
tru | -10.756 |
Token | was |
Token ID | 373 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
keys | +2.711 |
goats | +2.651 |
swers | +2.540 |
osher | +2.454 |
Edge | +2.382 |
Neg logit contributions | |
leys | -3.211 |
amina | -2.849 |
idad | -2.843 |
ici | -2.757 |
tru | -2.734 |
Token | 18 |
Token ID | 1248 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
keys | +3.424 |
goats | +3.364 |
swers | +3.162 |
osher | +2.984 |
Edge | +2.891 |
Neg logit contributions | |
leys | -6.015 |
idad | -5.418 |
amina | -5.390 |
ici | -5.287 |
tru | -5.170 |
Token | when |
Token ID | 618 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
leys | +4.052 |
idad | +3.562 |
amina | +3.514 |
ici | +3.501 |
tru | +3.500 |
Neg logit contributions | |
keys | -3.940 |
swers | -3.847 |
goats | -3.828 |
osher | -3.694 |
Edge | -3.603 |
Token | he |
Token ID | 339 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
keys | +1.990 |
goats | +1.960 |
swers | +1.874 |
osher | +1.820 |
Edge | +1.763 |
Neg logit contributions | |
leys | -2.226 |
idad | -1.967 |
amina | -1.962 |
ici | -1.911 |
tru | -1.897 |
Token | contributing |
Token ID | 14329 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
keys | +4.025 |
goats | +3.932 |
swers | +3.709 |
Edge | +3.475 |
osher | +3.462 |
Neg logit contributions | |
leys | -5.485 |
amina | -4.883 |
idad | -4.880 |
ici | -4.718 |
tru | -4.678 |
Token | right |
Token ID | 826 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
leys | +3.441 |
idad | +3.018 |
amina | +2.985 |
tru | +2.956 |
ici | +2.931 |
Neg logit contributions | |
keys | -3.581 |
goats | -3.502 |
swers | -3.487 |
osher | -3.408 |
Edge | -3.262 |
Token | away |
Token ID | 1497 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
keys | +3.090 |
goats | +3.031 |
swers | +2.841 |
osher | +2.663 |
Edge | +2.621 |
Neg logit contributions | |
leys | -5.118 |
idad | -4.662 |
amina | -4.633 |
ici | -4.525 |
tru | -4.501 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
leys | +0.471 |
idad | +0.415 |
amina | +0.412 |
ici | +0.404 |
tru | +0.402 |
Neg logit contributions | |
keys | -0.456 |
goats | -0.449 |
swers | -0.432 |
osher | -0.423 |
Edge | -0.409 |
Token | but |
Token ID | 475 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
keys | +0.982 |
goats | +0.967 |
swers | +0.926 |
osher | +0.898 |
Edge | +0.869 |
Neg logit contributions | |
leys | -1.157 |
idad | -1.027 |
amina | -1.022 |
ici | -0.996 |
tru | -0.991 |
Token | that |
Token ID | 326 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
goats | +3.629 |
keys | +3.619 |
swers | +3.406 |
osher | +3.179 |
Edge | +3.142 |
Neg logit contributions | |
leys | -5.082 |
idad | -4.598 |
amina | -4.530 |
ici | -4.395 |
tru | -4.312 |
Token | is |
Token ID | 318 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
keys | +0.967 |
goats | +0.952 |
swers | +0.910 |
osher | +0.882 |
Edge | +0.852 |
Neg logit contributions | |
leys | -1.214 |
idad | -1.079 |
amina | -1.075 |
ici | -1.049 |
tru | -1.044 |
Token | not |
Token ID | 407 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
leys | +1.398 |
idad | +1.255 |
amina | +1.248 |
tru | +1.239 |
ici | +1.223 |
Neg logit contributions | |
keys | -1.107 |
goats | -1.078 |
swers | -1.030 |
osher | -1.017 |
Tips | -0.959 |
Token | how |
Token ID | 703 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
leys | +1.307 |
idad | +1.168 |
amina | +1.159 |
tru | +1.149 |
ici | +1.132 |
Neg logit contributions | |
keys | -1.173 |
goats | -1.144 |
swers | -1.106 |
osher | -1.088 |
Edge | -1.043 |
Token | it |
Token ID | 340 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
keys | +0.527 |
goats | +0.516 |
swers | +0.491 |
osher | +0.477 |
Edge | +0.456 |
Neg logit contributions | |
leys | -0.832 |
idad | -0.749 |
amina | -0.746 |
ici | -0.731 |
tru | -0.729 |
Token | works |
Token ID | 2499 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
keys | +2.073 |
goats | +2.041 |
swers | +1.946 |
osher | +1.878 |
Tips | +1.822 |
Neg logit contributions | |
leys | -2.289 |
idad | -2.012 |
amina | -2.007 |
ici | -1.957 |
tru | -1.949 |
Token | be |
Token ID | 307 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
keys | +3.641 |
goats | +3.638 |
swers | +3.417 |
osher | +3.285 |
Edge | +3.197 |
Neg logit contributions | |
leys | -4.742 |
idad | -4.285 |
amina | -4.248 |
ici | -4.118 |
tru | -4.031 |
Token | hosted |
Token ID | 12007 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
leys | +2.324 |
idad | +2.059 |
amina | +2.058 |
tru | +2.046 |
ici | +1.990 |
Neg logit contributions | |
keys | -2.159 |
goats | -2.080 |
swers | -2.013 |
osher | -2.004 |
Tips | -1.917 |
Token | by |
Token ID | 416 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
keys | +2.687 |
goats | +2.660 |
swers | +2.529 |
osher | +2.443 |
Tips | +2.373 |
Neg logit contributions | |
leys | -3.317 |
idad | -2.965 |
amina | -2.948 |
ici | -2.867 |
tru | -2.837 |
Token | Warriors |
Token ID | 12090 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
leys | +0.298 |
idad | +0.263 |
amina | +0.263 |
tru | +0.258 |
ici | +0.256 |
Neg logit contributions | |
keys | -0.260 |
goats | -0.255 |
swers | -0.246 |
osher | -0.240 |
Tips | -0.230 |
Token | TV |
Token ID | 3195 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
keys | +0.861 |
goats | +0.847 |
swers | +0.812 |
osher | +0.790 |
Edge | +0.763 |
Neg logit contributions | |
leys | -0.985 |
idad | -0.872 |
amina | -0.868 |
ici | -0.846 |
tru | -0.843 |
Token | � |
Token ID | 447 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
keys | +1.084 |
goats | +1.067 |
swers | +1.021 |
osher | +0.995 |
Edge | +0.963 |
Neg logit contributions | |
leys | -1.226 |
idad | -1.084 |
amina | -1.080 |
ici | -1.053 |
tru | -1.047 |
Token | � |
Token ID | 247 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
keys | +1.180 |
goats | +1.162 |
swers | +1.131 |
osher | +1.070 |
Edge | +1.055 |
Neg logit contributions | |
leys | -1.499 |
amina | -1.334 |
idad | -1.329 |
ici | -1.294 |
tru | -1.279 |
Token | s |
Token ID | 82 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
keys | +0.962 |
goats | +0.946 |
swers | +0.909 |
osher | +0.883 |
Edge | +0.856 |
Neg logit contributions | |
leys | -1.081 |
idad | -0.955 |
amina | -0.953 |
ici | -0.929 |
tru | -0.924 |
Token | Laure |
Token ID | 13826 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
leys | +2.518 |
idad | +2.224 |
amina | +2.213 |
tru | +2.205 |
ici | +2.152 |
Neg logit contributions | |
keys | -2.176 |
goats | -2.112 |
swers | -2.052 |
osher | -2.000 |
Tips | -1.915 |
Token | nce |
Token ID | 1198 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
keys | +3.664 |
goats | +3.611 |
swers | +3.502 |
osher | +3.455 |
Edge | +3.368 |
Neg logit contributions | |
leys | -1.891 |
idad | -1.546 |
amina | -1.540 |
tru | -1.486 |
ici | -1.481 |
Token | Scott |
Token ID | 4746 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
keys | +1.557 |
goats | +1.537 |
swers | +1.467 |
osher | +1.428 |
Edge | +1.386 |
Neg logit contributions | |
leys | -1.751 |
idad | -1.550 |
amina | -1.545 |
ici | -1.506 |
tru | -1.494 |
Token |
|
Token ID | 198 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
leys | +3.354 |
idad | +2.866 |
amina | +2.828 |
tru | +2.820 |
ici | +2.769 |
Neg logit contributions | |
goats | -4.776 |
keys | -4.773 |
swers | -4.625 |
osher | -4.603 |
Edge | -4.309 |
Token | When |
Token ID | 2215 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
leys | +4.386 |
idad | +3.911 |
amina | +3.858 |
tru | +3.840 |
ici | +3.773 |
Neg logit contributions | |
goats | -4.143 |
keys | -4.021 |
osher | -3.939 |
swers | -3.863 |
Khe | -3.663 |
Token | a |
Token ID | 257 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
keys | +2.186 |
goats | +2.160 |
swers | +2.050 |
osher | +1.937 |
Edge | +1.886 |
Neg logit contributions | |
leys | -3.406 |
idad | -3.062 |
amina | -3.046 |
ici | -2.977 |
tru | -2.950 |
Token | government |
Token ID | 1230 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
leys | +1.376 |
idad | +1.229 |
amina | +1.217 |
tru | +1.207 |
ici | +1.186 |
Neg logit contributions | |
keys | -1.271 |
goats | -1.236 |
swers | -1.193 |
osher | -1.175 |
Edge | -1.134 |
Token | spends |
Token ID | 16887 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
leys | +1.737 |
idad | +1.537 |
tru | +1.509 |
amina | +1.509 |
ici | +1.470 |
Neg logit contributions | |
keys | -1.734 |
goats | -1.689 |
swers | -1.635 |
osher | -1.626 |
Edge | -1.552 |
Token | more |
Token ID | 517 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
keys | +1.298 |
goats | +1.281 |
swers | +1.218 |
osher | +1.179 |
Edge | +1.137 |
Neg logit contributions | |
leys | -1.703 |
idad | -1.520 |
amina | -1.510 |
ici | -1.479 |
tru | -1.465 |
Token | than |
Token ID | 621 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
goats | +3.291 |
keys | +3.283 |
swers | +3.000 |
osher | +2.854 |
Tips | +2.833 |
Neg logit contributions | |
leys | -5.756 |
idad | -5.184 |
amina | -5.116 |
ici | -5.082 |
tru | -4.949 |
Token | its |
Token ID | 663 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
keys | +1.406 |
goats | +1.389 |
swers | +1.305 |
osher | +1.255 |
Tips | +1.203 |
Neg logit contributions | |
leys | -2.370 |
idad | -2.137 |
amina | -2.123 |
ici | -2.088 |
tru | -2.066 |
Token | revenue |
Token ID | 6426 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
leys | +4.587 |
tru | +4.133 |
amina | +4.100 |
idad | +4.088 |
ici | +3.882 |
Neg logit contributions | |
keys | -5.092 |
goats | -4.956 |
swers | -4.951 |
osher | -4.820 |
Edge | -4.654 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
keys | +0.351 |
goats | +0.346 |
swers | +0.331 |
osher | +0.322 |
Edge | +0.312 |
Neg logit contributions | |
leys | -0.389 |
idad | -0.343 |
amina | -0.342 |
ici | -0.333 |
tru | -0.331 |
Token | it |
Token ID | 340 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
keys | +1.290 |
goats | +1.273 |
swers | +1.209 |
osher | +1.158 |
Edge | +1.121 |
Neg logit contributions | |
leys | -1.907 |
idad | -1.713 |
amina | -1.706 |
ici | -1.666 |
tru | -1.653 |
Token | pale |
Token ID | 14005 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
leys | +0.518 |
idad | +0.458 |
amina | +0.457 |
tru | +0.450 |
ici | +0.447 |
Neg logit contributions | |
keys | -0.430 |
goats | -0.418 |
swers | -0.408 |
osher | -0.396 |
Edge | -0.382 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
keys | +3.407 |
goats | +3.375 |
swers | +3.061 |
osher | +3.051 |
Edge | +2.892 |
Neg logit contributions | |
leys | -5.315 |
idad | -4.794 |
amina | -4.748 |
ici | -4.691 |
tru | -4.568 |
Token | lightly |
Token ID | 15376 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
goats | +4.390 |
keys | +4.304 |
swers | +3.960 |
osher | +3.931 |
Edge | +3.792 |
Neg logit contributions | |
leys | -5.246 |
idad | -4.657 |
amina | -4.648 |
ici | -4.477 |
tru | -4.274 |
Token | a |
Token ID | 257 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
goats | +9.210 |
keys | +8.553 |
osher | +7.860 |
goat | +7.779 |
kosher | +7.731 |
Neg logit contributions | |
leys | -10.874 |
amina | -9.967 |
idad | -9.693 |
ici | -9.247 |
uality | -8.921 |
Token | lder |
Token ID | 6499 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
leys | +0.793 |
idad | +0.648 |
amina | +0.647 |
ici | +0.625 |
tru | +0.611 |
Neg logit contributions | |
keys | -1.505 |
goats | -1.492 |
swers | -1.463 |
osher | -1.411 |
Edge | -1.392 |
Token | smoked |
Token ID | 21603 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
keys | +3.730 |
goats | +3.730 |
osher | +3.423 |
swers | +3.414 |
Edge | +3.277 |
Neg logit contributions | |
leys | -4.574 |
amina | -4.100 |
idad | -4.060 |
ici | -3.921 |
tru | -3.886 |
Token | mal |
Token ID | 6428 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
goats | +4.021 |
keys | +4.011 |
osher | +3.607 |
swers | +3.596 |
Edge | +3.470 |
Neg logit contributions | |
leys | -5.266 |
idad | -4.744 |
amina | -4.722 |
ici | -4.607 |
tru | -4.509 |
Token | ts |
Token ID | 912 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
keys | +3.444 |
goats | +3.352 |
swers | +3.220 |
osher | +3.167 |
Edge | +3.071 |
Neg logit contributions | |
leys | -2.454 |
idad | -2.137 |
amina | -2.114 |
tru | -2.059 |
ici | -2.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
keys | +1.443 |
goats | +1.425 |
swers | +1.348 |
osher | +1.314 |
Edge | +1.267 |
Neg logit contributions | |
leys | -1.833 |
idad | -1.632 |
amina | -1.631 |
ici | -1.588 |
tru | -1.578 |
Token | probably |
Token ID | 2192 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
keys | +1.383 |
goats | +1.367 |
swers | +1.298 |
osher | +1.264 |
Edge | +1.223 |
Neg logit contributions | |
leys | -1.643 |
idad | -1.460 |
amina | -1.454 |
ici | -1.415 |
tru | -1.404 |
Token | of |
Token ID | 286 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
goats | +2.647 |
keys | +2.644 |
swers | +2.437 |
osher | +2.412 |
Edge | +2.326 |
Neg logit contributions | |
leys | -3.214 |
idad | -2.861 |
amina | -2.851 |
ici | -2.768 |
tru | -2.725 |
Token | anything |
Token ID | 1997 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
leys | +0.778 |
idad | +0.696 |
amina | +0.695 |
tru | +0.684 |
ici | +0.680 |
Neg logit contributions | |
keys | -0.570 |
goats | -0.552 |
swers | -0.536 |
osher | -0.523 |
Edge | -0.503 |
Token | like |
Token ID | 588 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
leys | +2.556 |
idad | +2.267 |
amina | +2.260 |
tru | +2.215 |
ici | +2.202 |
Neg logit contributions | |
keys | -2.649 |
goats | -2.561 |
swers | -2.518 |
osher | -2.442 |
Edge | -2.397 |
Token | that |
Token ID | 326 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
leys | +3.200 |
idad | +2.852 |
ici | +2.798 |
amina | +2.770 |
tru | +2.755 |
Neg logit contributions | |
keys | -3.149 |
goats | -3.061 |
swers | -2.992 |
osher | -2.914 |
Edge | -2.830 |
Token | … |
Token ID | 1399 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
keys | +0.572 |
goats | +0.563 |
swers | +0.540 |
osher | +0.525 |
Edge | +0.508 |
Neg logit contributions | |
leys | -0.648 |
idad | -0.573 |
amina | -0.571 |
ici | -0.557 |
tru | -0.554 |
Token | � |
Token ID | 447 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
keys | +1.190 |
goats | +1.172 |
swers | +1.127 |
osher | +1.098 |
Edge | +1.067 |
Neg logit contributions | |
leys | -1.157 |
idad | -1.013 |
amina | -1.008 |
ici | -0.980 |
tru | -0.975 |
Token | � |
Token ID | 251 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
keys | +0.440 |
goats | +0.434 |
swers | +0.419 |
osher | +0.408 |
Edge | +0.397 |
Neg logit contributions | |
leys | -0.387 |
idad | -0.336 |
amina | -0.335 |
ici | -0.325 |
tru | -0.323 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
keys | +0.822 |
goats | +0.810 |
swers | +0.780 |
osher | +0.760 |
Edge | +0.738 |
Neg logit contributions | |
leys | -0.782 |
idad | -0.683 |
amina | -0.680 |
ici | -0.662 |
tru | -0.658 |
Token |
|
Token ID | 198 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
keys | +0.908 |
goats | +0.878 |
swers | +0.841 |
Edge | +0.816 |
Tips | +0.811 |
Neg logit contributions | |
leys | -0.914 |
idad | -0.801 |
amina | -0.799 |
ici | -0.772 |
tru | -0.753 |
Token | Game |
Token ID | 8777 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
keys | +1.653 |
goats | +1.616 |
swers | +1.546 |
osher | +1.497 |
Edge | +1.462 |
Neg logit contributions | |
leys | -2.121 |
idad | -1.892 |
amina | -1.885 |
ici | -1.840 |
tru | -1.832 |
Token | 74 |
Token ID | 8915 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
keys | +1.385 |
goats | +1.363 |
swers | +1.291 |
osher | +1.241 |
Edge | +1.192 |
Neg logit contributions | |
leys | -2.348 |
idad | -2.114 |
amina | -2.113 |
ici | -2.063 |
tru | -2.054 |
Token | v |
Token ID | 410 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
goats | +4.017 |
keys | +4.012 |
swers | +3.682 |
osher | +3.502 |
Edge | +3.454 |
Neg logit contributions | |
leys | -7.425 |
amina | -6.767 |
idad | -6.656 |
ici | -6.518 |
tru | -6.412 |
Token | the |
Token ID | 262 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
keys | +2.556 |
goats | +2.523 |
swers | +2.400 |
osher | +2.315 |
Edge | +2.267 |
Neg logit contributions | |
leys | -2.819 |
idad | -2.479 |
amina | -2.456 |
ici | -2.405 |
tru | -2.394 |
Token | Dominican |
Token ID | 32022 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
leys | +0.381 |
idad | +0.336 |
amina | +0.335 |
tru | +0.326 |
ici | +0.325 |
Neg logit contributions | |
keys | -0.364 |
goats | -0.358 |
swers | -0.344 |
osher | -0.337 |
Edge | -0.325 |
Token | Republic |
Token ID | 2066 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
keys | +0.824 |
goats | +0.812 |
swers | +0.781 |
osher | +0.760 |
Edge | +0.744 |
Neg logit contributions | |
leys | -0.696 |
amina | -0.596 |
idad | -0.596 |
ici | -0.580 |
tru | -0.576 |
Token | since |
Token ID | 1201 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
keys | +2.900 |
goats | +2.848 |
swers | +2.683 |
osher | +2.584 |
Edge | +2.494 |
Neg logit contributions | |
leys | -4.399 |
idad | -3.893 |
amina | -3.868 |
tru | -3.825 |
ici | -3.812 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
leys | +1.177 |
idad | +1.050 |
amina | +1.036 |
tru | +1.025 |
ici | +1.016 |
Neg logit contributions | |
keys | -1.023 |
goats | -0.997 |
swers | -0.966 |
osher | -0.953 |
Edge | -0.914 |
Token | , |
Token ID | 11 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
leys | +0.470 |
amina | +0.413 |
idad | +0.413 |
ici | +0.402 |
tru | +0.399 |
Neg logit contributions | |
keys | -0.443 |
goats | -0.437 |
swers | -0.422 |
osher | -0.411 |
Edge | -0.397 |
Token | searching |
Token ID | 10342 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
leys | +0.413 |
idad | +0.366 |
amina | +0.366 |
ici | +0.357 |
tru | +0.355 |
Neg logit contributions | |
keys | -0.339 |
goats | -0.332 |
swers | -0.321 |
osher | -0.313 |
Edge | -0.301 |
Token | for |
Token ID | 329 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
keys | +1.349 |
goats | +1.328 |
swers | +1.255 |
osher | +1.207 |
Edge | +1.159 |
Neg logit contributions | |
leys | -2.199 |
idad | -1.977 |
amina | -1.967 |
ici | -1.939 |
tru | -1.923 |
Token | rare |
Token ID | 4071 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
keys | +3.181 |
goats | +3.173 |
swers | +3.000 |
osher | +2.842 |
Edge | +2.764 |
Neg logit contributions | |
leys | -4.164 |
idad | -3.678 |
ici | -3.637 |
amina | -3.615 |
tru | -3.518 |
Token | fossil |
Token ID | 12584 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
keys | +4.105 |
goats | +4.015 |
swers | +3.795 |
osher | +3.606 |
Edge | +3.487 |
Neg logit contributions | |
leys | -5.121 |
idad | -4.527 |
ici | -4.479 |
amina | -4.468 |
tru | -4.377 |
Token | remains |
Token ID | 3793 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
leys | +0.722 |
idad | +0.640 |
amina | +0.637 |
tru | +0.619 |
ici | +0.616 |
Neg logit contributions | |
keys | -0.656 |
goats | -0.643 |
swers | -0.621 |
osher | -0.612 |
Edge | -0.591 |
Token | depending |
Token ID | 6906 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
leys | +0.727 |
idad | +0.640 |
amina | +0.635 |
tru | +0.623 |
ici | +0.622 |
Neg logit contributions | |
keys | -0.646 |
goats | -0.635 |
swers | -0.611 |
osher | -0.597 |
Edge | -0.575 |
Token | on |
Token ID | 319 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
keys | +2.002 |
goats | +1.975 |
swers | +1.875 |
osher | +1.812 |
Edge | +1.765 |
Neg logit contributions | |
leys | -2.592 |
idad | -2.314 |
amina | -2.307 |
ici | -2.248 |
tru | -2.230 |
Token | the |
Token ID | 262 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
leys | +1.110 |
idad | +0.981 |
amina | +0.979 |
tru | +0.956 |
ici | +0.951 |
Neg logit contributions | |
keys | -1.031 |
goats | -1.004 |
swers | -0.975 |
osher | -0.950 |
Edge | -0.916 |
Token | environment |
Token ID | 2858 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
keys | +0.452 |
goats | +0.444 |
swers | +0.427 |
osher | +0.415 |
Edge | +0.401 |
Neg logit contributions | |
leys | -0.528 |
idad | -0.468 |
amina | -0.466 |
ici | -0.455 |
tru | -0.454 |
Token | 's |
Token ID | 338 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
keys | +0.216 |
goats | +0.212 |
swers | +0.205 |
osher | +0.199 |
Edge | +0.192 |
Neg logit contributions | |
leys | -0.240 |
idad | -0.212 |
amina | -0.211 |
ici | -0.206 |
tru | -0.205 |
Token | context |
Token ID | 4732 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
leys | +0.232 |
idad | +0.206 |
amina | +0.205 |
tru | +0.200 |
ici | +0.200 |
Neg logit contributions | |
keys | -0.198 |
goats | -0.194 |
swers | -0.187 |
osher | -0.182 |
Edge | -0.175 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
leys | +1.504 |
idad | +1.328 |
amina | +1.309 |
ici | +1.285 |
tru | +1.275 |
Neg logit contributions | |
keys | -1.483 |
goats | -1.477 |
swers | -1.429 |
osher | -1.398 |
Edge | -1.338 |
Token | dist |
Token ID | 1233 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
keys | +1.064 |
goats | +1.048 |
swers | +1.000 |
osher | +0.970 |
Edge | +0.941 |
Neg logit contributions | |
leys | -1.277 |
idad | -1.133 |
amina | -1.127 |
ici | -1.101 |
tru | -1.092 |
Token | al |
Token ID | 282 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
keys | +0.347 |
goats | +0.344 |
swers | +0.331 |
osher | +0.322 |
Edge | +0.313 |
Neg logit contributions | |
leys | -0.331 |
idad | -0.289 |
amina | -0.289 |
ici | -0.281 |
tru | -0.278 |
Token | cues |
Token ID | 25288 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
leys | +1.184 |
idad | +1.060 |
amina | +1.053 |
tru | +1.023 |
ici | +1.019 |
Neg logit contributions | |
keys | -0.966 |
goats | -0.952 |
swers | -0.929 |
osher | -0.900 |
Tips | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
leys | +1.493 |
idad | +1.315 |
amina | +1.301 |
ici | +1.273 |
tru | +1.269 |
Neg logit contributions | |
keys | -1.425 |
goats | -1.409 |
swers | -1.357 |
osher | -1.326 |
Edge | -1.276 |
Token | , |
Token ID | 11 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
leys | +3.251 |
amina | +2.867 |
idad | +2.843 |
tru | +2.793 |
ici | +2.790 |
Neg logit contributions | |
keys | -3.333 |
goats | -3.250 |
swers | -3.209 |
osher | -3.153 |
Edge | -3.032 |
Token | but |
Token ID | 475 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
leys | +0.454 |
amina | +0.400 |
idad | +0.399 |
tru | +0.393 |
ici | +0.390 |
Neg logit contributions | |
keys | -0.410 |
goats | -0.400 |
swers | -0.386 |
osher | -0.378 |
Edge | -0.365 |
Token | you |
Token ID | 345 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
leys | +2.538 |
amina | +2.243 |
tru | +2.239 |
idad | +2.215 |
ici | +2.191 |
Neg logit contributions | |
keys | -2.021 |
goats | -1.946 |
swers | -1.903 |
osher | -1.872 |
Edge | -1.789 |
Token | will |
Token ID | 481 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
goats | +4.198 |
keys | +4.099 |
swers | +3.671 |
eer | +3.523 |
Edge | +3.488 |
Neg logit contributions | |
leys | -7.181 |
amina | -6.531 |
idad | -6.458 |
ici | -6.282 |
tru | -6.041 |
Token | be |
Token ID | 307 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
keys | +0.753 |
goats | +0.741 |
swers | +0.706 |
osher | +0.684 |
Edge | +0.662 |
Neg logit contributions | |
leys | -0.965 |
idad | -0.860 |
amina | -0.856 |
ici | -0.836 |
tru | -0.831 |
Token | in |
Token ID | 287 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
leys | +2.338 |
idad | +2.063 |
tru | +2.060 |
amina | +2.060 |
ici | +2.018 |
Neg logit contributions | |
keys | -2.039 |
goats | -1.979 |
swers | -1.930 |
osher | -1.921 |
Edge | -1.803 |
Token | complete |
Token ID | 1844 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
leys | +2.997 |
amina | +2.738 |
idad | +2.699 |
tru | +2.666 |
ici | +2.634 |
Neg logit contributions | |
keys | -2.455 |
goats | -2.412 |
swers | -2.353 |
osher | -2.297 |
Edge | -2.206 |
Token | control |
Token ID | 1630 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
keys | +3.192 |
goats | +3.181 |
swers | +3.007 |
osher | +2.836 |
Tips | +2.808 |
Neg logit contributions | |
leys | -3.681 |
idad | -3.233 |
amina | -3.211 |
ici | -3.170 |
tru | -3.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
keys | +2.537 |
goats | +2.499 |
swers | +2.368 |
osher | +2.291 |
Edge | +2.219 |
Neg logit contributions | |
leys | -3.520 |
idad | -3.143 |
amina | -3.138 |
ici | -3.059 |
tru | -3.032 |
Token | At |
Token ID | 1629 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
leys | +1.852 |
amina | +1.624 |
idad | +1.613 |
tru | +1.611 |
ici | +1.593 |
Neg logit contributions | |
keys | -1.796 |
goats | -1.779 |
swers | -1.718 |
osher | -1.691 |
Edge | -1.591 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
keys | +0.297 |
goats | +0.292 |
swers | +0.280 |
osher | +0.273 |
Edge | +0.264 |
Neg logit contributions | |
leys | -0.351 |
idad | -0.311 |
amina | -0.310 |
ici | -0.303 |
tru | -0.302 |
Token | ART |
Token ID | 24278 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
goats | +5.482 |
keys | +5.420 |
swers | +5.076 |
Edge | +4.964 |
Khe | +4.904 |
Neg logit contributions | |
leys | -7.261 |
idad | -6.340 |
amina | -6.275 |
ici | -6.079 |
ulk | -5.902 |
Token | IS |
Token ID | 1797 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
leys | +0.897 |
idad | +0.819 |
amina | +0.812 |
ici | +0.804 |
tru | +0.792 |
Neg logit contributions | |
keys | -0.566 |
goats | -0.556 |
swers | -0.527 |
osher | -0.511 |
Tips | -0.482 |
Token | . |
Token ID | 764 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
leys | +0.601 |
idad | +0.528 |
amina | +0.526 |
ici | +0.515 |
tru | +0.513 |
Neg logit contributions | |
keys | -0.626 |
goats | -0.615 |
swers | -0.594 |
osher | -0.579 |
Edge | -0.558 |
Token |
|
Token ID | 198 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
keys | +0.352 |
goats | +0.347 |
swers | +0.334 |
osher | +0.326 |
Edge | +0.317 |
Neg logit contributions | |
leys | -0.303 |
idad | -0.263 |
amina | -0.262 |
ici | -0.254 |
tru | -0.253 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
leys | +2.634 |
idad | +2.263 |
amina | +2.242 |
tru | +2.212 |
ici | +2.190 |
Neg logit contributions | |
keys | -3.537 |
goats | -3.525 |
swers | -3.420 |
osher | -3.376 |
Edge | -3.197 |
Token | Faith |
Token ID | 45536 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
keys | +1.986 |
goats | +1.937 |
swers | +1.856 |
osher | +1.791 |
Edge | +1.760 |
Neg logit contributions | |
leys | -2.703 |
idad | -2.407 |
amina | -2.403 |
ici | -2.344 |
tru | -2.337 |
Token | . |
Token ID | 13 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
leys | +0.235 |
idad | +0.204 |
amina | +0.202 |
ici | +0.198 |
tru | +0.197 |
Neg logit contributions | |
keys | -0.264 |
goats | -0.260 |
swers | -0.249 |
osher | -0.244 |
Edge | -0.237 |
Token | Hope |
Token ID | 13408 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
leys | +0.788 |
idad | +0.697 |
amina | +0.694 |
tru | +0.680 |
ici | +0.679 |
Neg logit contributions | |
keys | -0.738 |
goats | -0.723 |
swers | -0.691 |
osher | -0.681 |
Edge | -0.653 |
Token | . |
Token ID | 13 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
leys | +1.700 |
idad | +1.504 |
amina | +1.479 |
ici | +1.464 |
tru | +1.452 |
Neg logit contributions | |
keys | -1.696 |
goats | -1.661 |
swers | -1.591 |
osher | -1.564 |
Edge | -1.510 |
Token | Charity |
Token ID | 37575 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
leys | +0.425 |
idad | +0.378 |
amina | +0.376 |
tru | +0.368 |
ici | +0.367 |
Neg logit contributions | |
keys | -0.374 |
goats | -0.367 |
swers | -0.350 |
osher | -0.345 |
Edge | -0.330 |
Token | . |
Token ID | 13 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
keys | +0.296 |
goats | +0.291 |
swers | +0.280 |
osher | +0.272 |
Edge | +0.264 |
Neg logit contributions | |
leys | -0.319 |
idad | -0.282 |
amina | -0.280 |
ici | -0.273 |
tru | -0.272 |
Token | bul |
Token ID | 4807 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
leys | +5.649 |
tru | +5.130 |
amina | +5.042 |
idad | +4.947 |
nearest | +4.656 |
Neg logit contributions | |
keys | -6.048 |
swers | -5.996 |
goats | -5.938 |
osher | -5.813 |
Edge | -5.592 |
Token | wark |
Token ID | 48542 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
leys | +5.062 |
idad | +4.458 |
amina | +4.349 |
tru | +4.216 |
ici | +4.201 |
Neg logit contributions | |
goats | -5.600 |
swers | -5.559 |
keys | -5.425 |
osher | -5.241 |
eer | -5.188 |
Token | of |
Token ID | 286 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
leys | +3.459 |
idad | +3.075 |
amina | +3.068 |
tru | +2.974 |
ici | +2.970 |
Neg logit contributions | |
keys | -2.982 |
goats | -2.903 |
swers | -2.814 |
osher | -2.772 |
Tips | -2.661 |
Token | Western |
Token ID | 4885 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
leys | +4.154 |
amina | +3.770 |
idad | +3.756 |
tru | +3.714 |
ici | +3.539 |
Neg logit contributions | |
keys | -4.032 |
goats | -3.826 |
swers | -3.783 |
osher | -3.758 |
Edge | -3.576 |
Token | defence |
Token ID | 9366 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
leys | +2.453 |
idad | +2.205 |
amina | +2.191 |
tru | +2.150 |
ici | +2.131 |
Neg logit contributions | |
keys | -1.825 |
goats | -1.766 |
swers | -1.706 |
osher | -1.682 |
Edge | -1.585 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
leys | +2.861 |
idad | +2.527 |
amina | +2.518 |
tru | +2.478 |
ici | +2.446 |
Neg logit contributions | |
keys | -3.000 |
goats | -2.924 |
swers | -2.845 |
osher | -2.826 |
Edge | -2.644 |
Token |
|
Token ID | 198 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
leys | +3.063 |
idad | +2.650 |
amina | +2.612 |
ici | +2.548 |
tru | +2.477 |
Neg logit contributions | |
keys | -4.280 |
goats | -4.258 |
swers | -4.099 |
osher | -4.016 |
Edge | -3.864 |
Token |
|
Token ID | 198 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
keys | +2.214 |
goats | +2.116 |
swers | +2.001 |
Edge | +1.973 |
Tips | +1.967 |
Neg logit contributions | |
leys | -2.513 |
amina | -2.220 |
idad | -2.201 |
ici | -2.146 |
tru | -2.063 |
Token | Syria |
Token ID | 40029 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
leys | +0.819 |
idad | +0.731 |
amina | +0.725 |
ici | +0.707 |
tru | +0.703 |
Neg logit contributions | |
goats | -0.682 |
keys | -0.677 |
swers | -0.648 |
osher | -0.632 |
Edge | -0.585 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
leys | +3.949 |
idad | +3.490 |
amina | +3.398 |
tru | +3.375 |
ici | +3.365 |
Neg logit contributions | |
keys | -3.975 |
goats | -3.870 |
swers | -3.795 |
osher | -3.787 |
Tips | -3.538 |
Token | terrorism |
Token ID | 8649 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
keys | +1.003 |
goats | +0.989 |
swers | +0.947 |
osher | +0.920 |
Edge | +0.891 |
Neg logit contributions | |
leys | -1.133 |
idad | -1.001 |
amina | -0.997 |
ici | -0.973 |
tru | -0.967 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
leys | +3.523 |
idad | +3.062 |
tru | +3.055 |
amina | +3.054 |
ici | +2.971 |
Neg logit contributions | |
keys | -3.453 |
goats | -3.338 |
osher | -3.269 |
swers | -3.264 |
Edge | -3.139 |
Token | learn |
Token ID | 2193 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
keys | +0.978 |
goats | +0.962 |
swers | +0.921 |
osher | +0.895 |
Edge | +0.865 |
Neg logit contributions | |
leys | -1.173 |
idad | -1.041 |
amina | -1.037 |
ici | -1.012 |
tru | -1.008 |
Token | things |
Token ID | 1243 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
keys | +1.223 |
goats | +1.204 |
swers | +1.137 |
osher | +1.097 |
Edge | +1.060 |
Neg logit contributions | |
leys | -1.862 |
idad | -1.672 |
amina | -1.667 |
ici | -1.631 |
tru | -1.618 |
Token | piece |
Token ID | 3704 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
leys | +0.921 |
idad | +0.813 |
amina | +0.810 |
tru | +0.799 |
ici | +0.793 |
Neg logit contributions | |
keys | -0.779 |
goats | -0.760 |
swers | -0.737 |
osher | -0.721 |
Edge | -0.694 |
Token | - |
Token ID | 12 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
keys | +0.670 |
goats | +0.660 |
swers | +0.636 |
osher | +0.620 |
Edge | +0.603 |
Neg logit contributions | |
leys | -0.612 |
idad | -0.534 |
amina | -0.531 |
ici | -0.516 |
tru | -0.514 |
Token | by |
Token ID | 1525 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
keys | +1.601 |
goats | +1.572 |
swers | +1.513 |
osher | +1.481 |
Edge | +1.449 |
Neg logit contributions | |
leys | -1.163 |
idad | -1.006 |
amina | -0.994 |
ici | -0.957 |
tru | -0.956 |
Token | - |
Token ID | 12 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
leys | +6.370 |
tru | +5.458 |
fulness | +5.171 |
ici | +5.083 |
idad | +5.025 |
Neg logit contributions | |
keys | -10.339 |
swers | -10.285 |
goats | -10.207 |
osher | -10.110 |
Palestin | -9.777 |
Token | piece |
Token ID | 12239 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
leys | +6.186 |
amina | +5.182 |
ici | +5.122 |
idad | +5.113 |
fulness | +4.969 |
Neg logit contributions | |
goats | -7.277 |
swers | -6.994 |
keys | -6.744 |
Khe | -6.736 |
osher | -6.576 |
Token | , |
Token ID | 11 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
keys | +1.916 |
goats | +1.897 |
swers | +1.796 |
osher | +1.747 |
Edge | +1.686 |
Neg logit contributions | |
leys | -2.350 |
idad | -2.097 |
amina | -2.090 |
ici | -2.037 |
tru | -2.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
leys | +0.382 |
amina | +0.335 |
idad | +0.334 |
tru | +0.330 |
ici | +0.327 |
Neg logit contributions | |
keys | -0.338 |
goats | -0.329 |
swers | -0.319 |
osher | -0.312 |
Edge | -0.300 |
Token | that |
Token ID | 326 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
keys | +0.887 |
goats | +0.872 |
swers | +0.831 |
osher | +0.805 |
Edge | +0.776 |
Neg logit contributions | |
leys | -1.232 |
idad | -1.102 |
amina | -1.097 |
ici | -1.073 |
tru | -1.068 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
leys | +5.776 |
tru | +5.171 |
idad | +5.099 |
ici | +5.003 |
amina | +4.953 |
Neg logit contributions | |
keys | -4.736 |
swers | -4.574 |
osher | -4.572 |
goats | -4.452 |
Edge | -4.256 |
Token | Lead |
Token ID | 20116 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
leys | +1.961 |
idad | +1.735 |
amina | +1.718 |
tru | +1.705 |
ici | +1.682 |
Neg logit contributions | |
keys | -1.600 |
goats | -1.552 |
swers | -1.531 |
osher | -1.503 |
Edge | -1.440 |
Token | b |
Token ID | 65 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
keys | +4.201 |
goats | +4.124 |
swers | +3.914 |
osher | +3.774 |
Edge | +3.728 |
Neg logit contributions | |
leys | -4.877 |
idad | -4.414 |
amina | -4.373 |
tru | -4.247 |
ici | -4.230 |
Token | elly |
Token ID | 6148 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
keys | +1.700 |
goats | +1.675 |
swers | +1.622 |
osher | +1.591 |
Edge | +1.550 |
Neg logit contributions | |
leys | -1.095 |
idad | -0.923 |
amina | -0.917 |
ici | -0.887 |
tru | -0.882 |
Token | records |
Token ID | 4406 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
keys | +1.594 |
goats | +1.569 |
swers | +1.495 |
osher | +1.450 |
Edge | +1.405 |
Neg logit contributions | |
leys | -1.899 |
idad | -1.689 |
amina | -1.683 |
ici | -1.639 |
tru | -1.630 |
Token | out |
Token ID | 503 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
leys | +3.954 |
idad | +3.508 |
ici | +3.458 |
tru | +3.453 |
amina | +3.424 |
Neg logit contributions | |
keys | -3.278 |
goats | -3.177 |
swers | -3.160 |
osher | -3.064 |
Edge | -2.967 |
Token | . |
Token ID | 13 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
leys | +8.065 |
ici | +7.043 |
amina | +6.752 |
idad | +6.683 |
tru | +6.566 |
Neg logit contributions | |
keys | -8.627 |
osher | -8.356 |
goats | -8.272 |
swers | -8.256 |
Edge | -7.896 |
Token | � |
Token ID | 447 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
leys | +0.410 |
idad | +0.360 |
amina | +0.359 |
tru | +0.351 |
ici | +0.351 |
Neg logit contributions | |
keys | -0.395 |
goats | -0.391 |
swers | -0.374 |
osher | -0.368 |
Edge | -0.353 |
Token | � |
Token ID | 251 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
leys | +2.692 |
idad | +2.345 |
amina | +2.318 |
tru | +2.245 |
ici | +2.237 |
Neg logit contributions | |
keys | -3.215 |
goats | -3.182 |
swers | -3.044 |
osher | -3.020 |
Edge | -2.902 |
Token | Cob |
Token ID | 14828 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
leys | +0.357 |
idad | +0.310 |
amina | +0.310 |
tru | +0.302 |
ici | +0.302 |
Neg logit contributions | |
keys | -0.368 |
goats | -0.364 |
swers | -0.350 |
osher | -0.345 |
Edge | -0.330 |
Token | ain |
Token ID | 391 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
keys | +0.816 |
goats | +0.796 |
swers | +0.766 |
osher | +0.739 |
Edge | +0.724 |
Neg logit contributions | |
leys | -0.898 |
idad | -0.794 |
amina | -0.790 |
tru | -0.775 |
ici | -0.773 |
Token | expansion |
Token ID | 7118 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
leys | +5.769 |
tru | +5.154 |
amina | +4.905 |
idad | +4.895 |
ici | +4.835 |
Neg logit contributions | |
keys | -6.087 |
swers | -6.049 |
goats | -5.904 |
osher | -5.742 |
Tips | -5.589 |
Token | pack |
Token ID | 2353 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
leys | +4.896 |
tru | +4.246 |
amina | +4.217 |
ici | +4.154 |
idad | +4.141 |
Neg logit contributions | |
keys | -4.685 |
swers | -4.614 |
goats | -4.596 |
osher | -4.381 |
Edge | -4.265 |
Token | " |
Token ID | 1 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
leys | +2.649 |
amina | +2.310 |
tru | +2.277 |
idad | +2.265 |
ici | +2.247 |
Neg logit contributions | |
keys | -2.554 |
goats | -2.522 |
swers | -2.483 |
osher | -2.368 |
Edge | -2.310 |
Token | will |
Token ID | 481 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
leys | +2.648 |
amina | +2.316 |
tru | +2.291 |
idad | +2.284 |
ici | +2.281 |
Neg logit contributions | |
keys | -2.340 |
goats | -2.300 |
swers | -2.246 |
osher | -2.169 |
Edge | -2.100 |
Token | be |
Token ID | 307 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
leys | +1.978 |
amina | +1.728 |
tru | +1.721 |
idad | +1.712 |
ici | +1.700 |
Neg logit contributions | |
keys | -1.905 |
goats | -1.869 |
swers | -1.841 |
osher | -1.777 |
Tips | -1.747 |
Token | made |
Token ID | 925 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
leys | +8.711 |
amina | +8.145 |
tru | +7.996 |
ici | +7.419 |
idad | +7.402 |
Neg logit contributions | |
keys | -8.630 |
goats | -8.565 |
swers | -8.394 |
osher | -8.360 |
Tips | -8.092 |
Token | for |
Token ID | 329 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
leys | +7.187 |
tru | +6.395 |
amina | +6.123 |
ici | +5.790 |
fulness | +5.785 |
Neg logit contributions | |
keys | -9.874 |
goats | -9.637 |
swers | -9.607 |
Edge | -9.279 |
osher | -9.243 |
Token | the |
Token ID | 262 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
leys | +7.787 |
amina | +7.275 |
tru | +7.066 |
ici | +6.903 |
ulk | +6.487 |
Neg logit contributions | |
goats | -8.329 |
keys | -8.295 |
swers | -8.143 |
osher | -8.073 |
Tips | -7.785 |
Token | Xbox |
Token ID | 9445 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
leys | +5.262 |
tru | +4.671 |
amina | +4.603 |
ici | +4.431 |
idad | +4.380 |
Neg logit contributions | |
keys | -7.151 |
goats | -7.137 |
swers | -6.968 |
osher | -6.815 |
Tips | -6.676 |
Token | 360 |
Token ID | 11470 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
leys | +1.261 |
idad | +1.103 |
amina | +1.103 |
tru | +1.085 |
ici | +1.084 |
Neg logit contributions | |
keys | -1.200 |
goats | -1.187 |
swers | -1.150 |
osher | -1.107 |
Tips | -1.075 |
Token | and |
Token ID | 290 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
leys | +5.833 |
tru | +5.122 |
amina | +5.037 |
idad | +5.027 |
ici | +5.012 |
Neg logit contributions | |
goats | -6.843 |
keys | -6.830 |
swers | -6.693 |
osher | -6.494 |
Tips | -6.281 |
Token | att |
Token ID | 1078 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
leys | +5.926 |
idad | +5.003 |
amina | +4.971 |
tru | +4.851 |
ici | +4.800 |
Neg logit contributions | |
goats | -8.103 |
keys | -8.031 |
osher | -8.024 |
swers | -8.003 |
Tips | -7.456 |
Token | acked |
Token ID | 6021 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
leys | +4.784 |
amina | +4.306 |
idad | +4.259 |
ici | +4.258 |
tru | +4.039 |
Neg logit contributions | |
goats | -3.770 |
keys | -3.687 |
swers | -3.503 |
osher | -3.379 |
Edge | -3.269 |
Token | and |
Token ID | 290 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
leys | +4.274 |
amina | +3.738 |
idad | +3.716 |
tru | +3.687 |
ici | +3.584 |
Neg logit contributions | |
keys | -3.859 |
goats | -3.727 |
swers | -3.700 |
osher | -3.660 |
Edge | -3.439 |
Token | by |
Token ID | 416 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
leys | +3.622 |
amina | +3.197 |
idad | +3.152 |
tru | +3.124 |
ici | +3.097 |
Neg logit contributions | |
keys | -3.383 |
goats | -3.263 |
swers | -3.216 |
osher | -3.172 |
Edge | -3.001 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
leys | +3.932 |
amina | +3.447 |
idad | +3.424 |
tru | +3.416 |
ici | +3.369 |
Neg logit contributions | |
keys | -3.381 |
goats | -3.280 |
swers | -3.219 |
osher | -3.146 |
Edge | -3.046 |
Token | August |
Token ID | 2932 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
leys | +3.961 |
amina | +3.506 |
idad | +3.443 |
ici | +3.306 |
tru | +3.305 |
Neg logit contributions | |
keys | -5.329 |
goats | -5.235 |
swers | -5.111 |
osher | -4.995 |
Edge | -4.865 |
Token | reached |
Token ID | 4251 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
leys | +8.563 |
amina | +7.464 |
tru | +7.418 |
ulk | +7.406 |
idad | +7.245 |
Neg logit contributions | |
keys | -8.840 |
osher | -8.741 |
swers | -8.668 |
goats | -8.540 |
Tips | -8.065 |
Token | the |
Token ID | 262 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
leys | +4.571 |
amina | +4.076 |
idad | +4.015 |
tru | +3.979 |
ici | +3.890 |
Neg logit contributions | |
keys | -4.336 |
goats | -4.229 |
swers | -4.159 |
osher | -4.076 |
Edge | -3.895 |
Token | original |
Token ID | 2656 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
leys | +3.373 |
idad | +3.017 |
amina | +3.004 |
tru | +2.986 |
ici | +2.905 |
Neg logit contributions | |
keys | -3.399 |
swers | -3.282 |
goats | -3.280 |
osher | -3.205 |
Tips | -3.049 |
Token | border |
Token ID | 4865 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
leys | +5.330 |
idad | +4.821 |
amina | +4.737 |
tru | +4.700 |
ici | +4.547 |
Neg logit contributions | |
keys | -5.155 |
goats | -4.998 |
swers | -4.975 |
osher | -4.914 |
Tips | -4.661 |
Token | .[ |
Token ID | 3693 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
leys | +4.326 |
idad | +3.826 |
amina | +3.772 |
tru | +3.737 |
ici | +3.679 |
Neg logit contributions | |
keys | -4.126 |
goats | -4.013 |
swers | -4.010 |
osher | -3.911 |
Tips | -3.731 |
Token | title |
Token ID | 3670 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
leys | +5.487 |
idad | +4.973 |
tru | +4.956 |
ici | +4.703 |
amina | +4.693 |
Neg logit contributions | |
keys | -5.804 |
swers | -5.649 |
goats | -5.593 |
osher | -5.563 |
Tips | -5.174 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
leys | +5.322 |
tru | +4.693 |
idad | +4.654 |
amina | +4.571 |
ici | +4.534 |
Neg logit contributions | |
keys | -5.926 |
osher | -5.718 |
goats | -5.718 |
swers | -5.671 |
Tips | -5.364 |
Token | and |
Token ID | 290 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
leys | +1.410 |
idad | +1.242 |
amina | +1.229 |
tru | +1.221 |
ici | +1.211 |
Neg logit contributions | |
keys | -1.295 |
goats | -1.264 |
swers | -1.223 |
osher | -1.196 |
Edge | -1.145 |
Token | the |
Token ID | 262 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
leys | +1.811 |
idad | +1.583 |
tru | +1.570 |
amina | +1.568 |
ici | +1.552 |
Neg logit contributions | |
keys | -1.575 |
goats | -1.535 |
swers | -1.487 |
osher | -1.455 |
Edge | -1.389 |
Token | sport |
Token ID | 6332 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
leys | +2.524 |
idad | +2.226 |
tru | +2.196 |
amina | +2.183 |
ici | +2.147 |
Neg logit contributions | |
keys | -2.471 |
goats | -2.417 |
swers | -2.349 |
osher | -2.326 |
Edge | -2.198 |
Token | of |
Token ID | 286 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
leys | +2.505 |
idad | +2.211 |
tru | +2.178 |
amina | +2.165 |
ici | +2.159 |
Neg logit contributions | |
keys | -2.277 |
goats | -2.238 |
swers | -2.171 |
osher | -2.104 |
Edge | -2.026 |
Token | MMA |
Token ID | 19055 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
leys | +6.749 |
tru | +6.081 |
idad | +5.910 |
amina | +5.695 |
fulness | +5.536 |
Neg logit contributions | |
keys | -9.692 |
osher | -9.467 |
swers | -9.371 |
goats | -9.356 |
odus | -8.864 |
Token | . |
Token ID | 13 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
leys | +1.338 |
idad | +1.185 |
amina | +1.166 |
tru | +1.166 |
ici | +1.151 |
Neg logit contributions | |
keys | -1.238 |
goats | -1.210 |
swers | -1.169 |
osher | -1.142 |
Edge | -1.098 |
Token |
|
Token ID | 198 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
leys | +3.999 |
tru | +3.340 |
idad | +3.301 |
ici | +3.265 |
amina | +3.227 |
Neg logit contributions | |
goats | -5.729 |
keys | -5.668 |
osher | -5.451 |
swers | -5.427 |
eer | -5.095 |
Token |
|
Token ID | 198 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
keys | +2.270 |
goats | +2.162 |
swers | +2.061 |
Edge | +2.036 |
Tips | +2.022 |
Neg logit contributions | |
leys | -2.560 |
amina | -2.260 |
idad | -2.238 |
ici | -2.174 |
tru | -2.100 |
Token | � |
Token ID | 447 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
keys | +0.279 |
goats | +0.277 |
swers | +0.265 |
osher | +0.258 |
Edge | +0.246 |
Neg logit contributions | |
leys | -0.317 |
idad | -0.281 |
amina | -0.279 |
ici | -0.272 |
tru | -0.272 |