Token | Jon |
Token ID | 5966 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
ities | +1.689 |
ctors | +1.339 |
ifax | +1.270 |
andro | +1.267 |
peria | +1.263 |
Neg logit contributions | |
picking | -1.255 |
ILLE | -1.115 |
Wester | -1.108 |
ECK | -1.100 |
rol | -1.061 |
Token | and |
Token ID | 290 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ities | +1.842 |
ctors | +1.447 |
andro | +1.377 |
ifax | +1.366 |
peria | +1.358 |
Neg logit contributions | |
picking | -1.487 |
ILLE | -1.316 |
Wester | -1.313 |
ECK | -1.311 |
SUP | -1.278 |
Token | others |
Token ID | 1854 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
picking | +0.599 |
Wester | +0.529 |
ECK | +0.520 |
ILLE | +0.520 |
rol | +0.506 |
Neg logit contributions | |
ities | -0.908 |
ctors | -0.733 |
ifax | -0.699 |
andro | -0.698 |
peria | -0.694 |
Token | bring |
Token ID | 2222 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
picking | +0.543 |
Wester | +0.488 |
ECK | +0.480 |
ILLE | +0.479 |
rol | +0.470 |
Neg logit contributions | |
ities | -0.659 |
ctors | -0.520 |
ifax | -0.493 |
andro | -0.491 |
peria | -0.489 |
Token | a |
Token ID | 257 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
picking | +2.087 |
Wester | +1.845 |
ECK | +1.796 |
ILLE | +1.783 |
SUP | +1.756 |
Neg logit contributions | |
ities | -3.638 |
ctors | -2.984 |
ifax | -2.854 |
andro | -2.838 |
peria | -2.824 |
Token | battery |
Token ID | 6555 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
ities | +0.437 |
ctors | +0.358 |
ifax | +0.342 |
andro | +0.341 |
peria | +0.341 |
Neg logit contributions | |
picking | -0.247 |
Wester | -0.213 |
ILLE | -0.211 |
ECK | -0.210 |
rol | -0.202 |
Token | pack |
Token ID | 2353 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
picking | +5.837 |
Wester | +5.182 |
SUP | +5.031 |
rol | +4.958 |
ECK | +4.931 |
Neg logit contributions | |
ities | -9.564 |
ctors | -8.167 |
ifax | -7.573 |
peria | -7.491 |
andro | -7.460 |
Token | for |
Token ID | 329 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
ities | +0.449 |
ctors | +0.347 |
andro | +0.331 |
ifax | +0.331 |
peria | +0.330 |
Neg logit contributions | |
picking | -0.377 |
Wester | -0.336 |
ILLE | -0.336 |
ECK | -0.335 |
rol | -0.324 |
Token | their |
Token ID | 511 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
picking | +1.422 |
Wester | +1.244 |
ECK | +1.230 |
ILLE | +1.228 |
rol | +1.191 |
Neg logit contributions | |
ities | -2.259 |
ctors | -1.823 |
ifax | -1.746 |
andro | -1.745 |
peria | -1.734 |
Token | phone |
Token ID | 3072 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
picking | +0.383 |
Wester | +0.326 |
ILLE | +0.325 |
ECK | +0.324 |
rol | +0.310 |
Neg logit contributions | |
ities | -0.737 |
ctors | -0.603 |
andro | -0.581 |
ifax | -0.579 |
peria | -0.578 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
picking | +0.921 |
Wester | +0.822 |
ECK | +0.811 |
ILLE | +0.809 |
rol | +0.789 |
Neg logit contributions | |
ities | -1.177 |
ctors | -0.928 |
ifax | -0.883 |
andro | -0.882 |
peria | -0.878 |
Token | just |
Token ID | 655 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
picking | +0.218 |
Wester | +0.194 |
ILLE | +0.192 |
ECK | +0.191 |
rol | +0.187 |
Neg logit contributions | |
ities | -0.298 |
ctors | -0.238 |
ifax | -0.226 |
andro | -0.226 |
peria | -0.225 |
Token | get |
Token ID | 651 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ities | +3.795 |
ctors | +2.977 |
ifax | +2.784 |
andro | +2.781 |
peria | +2.779 |
Neg logit contributions | |
picking | -3.234 |
ILLE | -2.919 |
Wester | -2.901 |
ECK | -2.877 |
rol | -2.795 |
Token | hold |
Token ID | 1745 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ities | +0.411 |
ctors | +0.327 |
ifax | +0.309 |
andro | +0.309 |
peria | +0.308 |
Neg logit contributions | |
picking | -0.309 |
Wester | -0.275 |
ECK | -0.273 |
ILLE | -0.273 |
rol | -0.265 |
Token | of |
Token ID | 286 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ities | +0.466 |
ctors | +0.379 |
ifax | +0.363 |
andro | +0.358 |
peria | +0.358 |
Neg logit contributions | |
picking | -0.307 |
Wester | -0.273 |
ECK | -0.264 |
ILLE | -0.263 |
rol | -0.260 |
Token | a |
Token ID | 257 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
picking | +0.029 |
Wester | +0.026 |
ECK | +0.026 |
ILLE | +0.026 |
rol | +0.025 |
Neg logit contributions | |
ities | -0.041 |
ctors | -0.032 |
ifax | -0.031 |
andro | -0.031 |
peria | -0.031 |
Token | battery |
Token ID | 6555 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
picking | +0.072 |
Wester | +0.064 |
ECK | +0.063 |
ILLE | +0.063 |
rol | +0.062 |
Neg logit contributions | |
ities | -0.101 |
ctors | -0.081 |
ifax | -0.077 |
andro | -0.077 |
peria | -0.076 |
Token | operated |
Token ID | 12228 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
picking | +6.182 |
Wester | +5.546 |
SUP | +5.353 |
rol | +5.303 |
ECK | +5.257 |
Neg logit contributions | |
ities | -8.795 |
ctors | -7.350 |
ifax | -6.894 |
peria | -6.855 |
andro | -6.797 |
Token | portable |
Token ID | 17726 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
picking | +1.436 |
Wester | +1.281 |
ECK | +1.252 |
ILLE | +1.247 |
rol | +1.224 |
Neg logit contributions | |
ities | -2.052 |
ctors | -1.651 |
ifax | -1.572 |
andro | -1.566 |
peria | -1.559 |
Token | AM |
Token ID | 3001 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
picking | +1.855 |
Wester | +1.656 |
ECK | +1.613 |
ILLE | +1.597 |
SUP | +1.583 |
Neg logit contributions | |
ities | -2.802 |
ctors | -2.287 |
ifax | -2.177 |
andro | -2.174 |
peria | -2.160 |
Token | / |
Token ID | 14 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
picking | +1.582 |
Wester | +1.408 |
ECK | +1.385 |
ILLE | +1.382 |
rol | +1.350 |
Neg logit contributions | |
ities | -2.191 |
ctors | -1.753 |
ifax | -1.668 |
andro | -1.664 |
peria | -1.655 |
Token | SW |
Token ID | 17887 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
picking | +0.896 |
Wester | +0.802 |
ECK | +0.788 |
ILLE | +0.787 |
rol | +0.769 |
Neg logit contributions | |
ities | -1.203 |
ctors | -0.956 |
andro | -0.910 |
ifax | -0.910 |
peria | -0.908 |
Token | [ |
Token ID | 685 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ities | +0.543 |
ctors | +0.435 |
andro | +0.416 |
peria | +0.413 |
ifax | +0.413 |
Neg logit contributions | |
picking | -0.370 |
Wester | -0.325 |
ECK | -0.322 |
ILLE | -0.322 |
rol | -0.313 |
Token | the |
Token ID | 1169 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
picking | +0.313 |
Wester | +0.283 |
ECK | +0.278 |
ILLE | +0.277 |
rol | +0.270 |
Neg logit contributions | |
ities | -0.382 |
ctors | -0.301 |
andro | -0.287 |
ifax | -0.285 |
peria | -0.284 |
Token | phone |
Token ID | 3072 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ities | +0.190 |
ctors | +0.151 |
andro | +0.144 |
ifax | +0.143 |
peria | +0.143 |
Neg logit contributions | |
picking | -0.145 |
Wester | -0.129 |
ECK | -0.128 |
ILLE | -0.128 |
rol | -0.124 |
Token | 's |
Token ID | 338 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ities | +0.818 |
ctors | +0.640 |
andro | +0.604 |
ifax | +0.603 |
peria | +0.600 |
Neg logit contributions | |
picking | -0.699 |
Wester | -0.628 |
ECK | -0.622 |
ILLE | -0.621 |
rol | -0.604 |
Token | ] |
Token ID | 60 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
picking | +0.901 |
Wester | +0.813 |
ECK | +0.801 |
ILLE | +0.799 |
rol | +0.783 |
Neg logit contributions | |
ities | -1.025 |
ctors | -0.802 |
ifax | -0.759 |
andro | -0.756 |
peria | -0.752 |
Token | battery |
Token ID | 6555 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ities | +1.843 |
ctors | +1.463 |
andro | +1.399 |
peria | +1.394 |
ifax | +1.387 |
Neg logit contributions | |
picking | -1.282 |
Wester | -1.129 |
ECK | -1.124 |
ILLE | -1.117 |
rol | -1.085 |
Token | life |
Token ID | 1204 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
picking | +5.719 |
Wester | +5.027 |
rol | +4.941 |
ECK | +4.815 |
SUP | +4.790 |
Neg logit contributions | |
ities | -8.681 |
ctors | -7.326 |
ifax | -7.005 |
peria | -6.985 |
andro | -6.907 |
Token | . |
Token ID | 13 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
picking | +2.059 |
Wester | +1.848 |
ECK | +1.809 |
ILLE | +1.804 |
rol | +1.781 |
Neg logit contributions | |
ities | -2.573 |
ctors | -2.053 |
ifax | -1.949 |
andro | -1.937 |
peria | -1.928 |
Token | Dillon |
Token ID | 40057 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ities | +0.117 |
ctors | +0.092 |
andro | +0.087 |
ifax | +0.087 |
peria | +0.087 |
Neg logit contributions | |
picking | -0.095 |
Wester | -0.085 |
ILLE | -0.084 |
ECK | -0.084 |
rol | -0.082 |
Token | says |
Token ID | 1139 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ities | +1.634 |
ctors | +1.277 |
andro | +1.215 |
ifax | +1.214 |
peria | +1.200 |
Neg logit contributions | |
picking | -1.344 |
Wester | -1.199 |
ILLE | -1.196 |
ECK | -1.189 |
rol | -1.158 |
Token | that |
Token ID | 326 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ities | +0.533 |
ctors | +0.425 |
andro | +0.404 |
ifax | +0.403 |
peria | +0.402 |
Neg logit contributions | |
picking | -0.388 |
Wester | -0.345 |
ILLE | -0.341 |
ECK | -0.340 |
rol | -0.331 |
Token | life |
Token ID | 1204 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
picking | +0.557 |
Wester | +0.491 |
ECK | +0.486 |
ILLE | +0.484 |
rol | +0.471 |
Neg logit contributions | |
ities | -0.821 |
ctors | -0.659 |
ifax | -0.629 |
andro | -0.627 |
peria | -0.624 |
Token | from |
Token ID | 422 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
picking | +2.695 |
Wester | +2.417 |
ECK | +2.359 |
ILLE | +2.331 |
SUP | +2.302 |
Neg logit contributions | |
ities | -3.618 |
ctors | -2.933 |
andro | -2.787 |
peria | -2.786 |
ifax | -2.784 |
Token | the |
Token ID | 262 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
picking | +0.534 |
Wester | +0.469 |
ECK | +0.466 |
ILLE | +0.463 |
rol | +0.454 |
Neg logit contributions | |
ities | -0.748 |
ctors | -0.597 |
andro | -0.569 |
ifax | -0.569 |
peria | -0.564 |
Token | polar |
Token ID | 13559 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
picking | +0.720 |
Wester | +0.630 |
ECK | +0.623 |
ILLE | +0.620 |
rol | +0.605 |
Neg logit contributions | |
ities | -1.126 |
ctors | -0.909 |
ifax | -0.869 |
andro | -0.866 |
peria | -0.860 |
Token | opposite |
Token ID | 6697 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
ities | +1.829 |
ctors | +1.419 |
ifax | +1.347 |
andro | +1.332 |
peria | +1.321 |
Neg logit contributions | |
picking | -1.356 |
ILLE | -1.206 |
Wester | -1.201 |
ECK | -1.200 |
rol | -1.166 |
Token | vantage |
Token ID | 47929 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ities | +1.966 |
ctors | +1.545 |
ifax | +1.470 |
peria | +1.464 |
andro | +1.463 |
Neg logit contributions | |
picking | -1.272 |
ILLE | -1.110 |
ECK | -1.102 |
Wester | -1.078 |
rol | -1.073 |
Token | point |
Token ID | 966 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
picking | +4.829 |
Wester | +4.249 |
ECK | +4.107 |
rol | +4.071 |
ILLE | +3.989 |
Neg logit contributions | |
ities | -9.299 |
ctors | -7.739 |
andro | -7.505 |
ifax | -7.459 |
peria | -7.356 |
Token | . |
Token ID | 13 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
picking | +0.245 |
Wester | +0.219 |
ILLE | +0.217 |
ECK | +0.217 |
rol | +0.211 |
Neg logit contributions | |
ities | -0.310 |
ctors | -0.243 |
ifax | -0.230 |
andro | -0.229 |
peria | -0.228 |
Token | For |
Token ID | 1114 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
ities | +1.078 |
ctors | +0.856 |
andro | +0.803 |
ifax | +0.802 |
peria | +0.795 |
Neg logit contributions | |
picking | -0.881 |
ILLE | -0.775 |
ECK | -0.772 |
Wester | -0.770 |
rol | -0.750 |
Token | Bob |
Token ID | 5811 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
picking | +1.623 |
Wester | +1.436 |
ECK | +1.412 |
ILLE | +1.410 |
rol | +1.374 |
Neg logit contributions | |
ities | -2.417 |
ctors | -1.949 |
ifax | -1.857 |
andro | -1.853 |
peria | -1.842 |
Token | , |
Token ID | 11 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
picking | +0.960 |
Wester | +0.851 |
ECK | +0.840 |
ILLE | +0.840 |
rol | +0.817 |
Neg logit contributions | |
ities | -1.274 |
ctors | -1.014 |
ifax | -0.964 |
andro | -0.963 |
peria | -0.954 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
ities | +0.177 |
ctors | +0.140 |
ifax | +0.134 |
andro | +0.133 |
peria | +0.133 |
Neg logit contributions | |
picking | -0.127 |
Wester | -0.113 |
ILLE | -0.113 |
ECK | -0.111 |
rol | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
picking | +1.060 |
Wester | +0.943 |
ECK | +0.927 |
ILLE | +0.926 |
rol | +0.904 |
Neg logit contributions | |
ities | -1.466 |
ctors | -1.172 |
ifax | -1.116 |
andro | -1.112 |
peria | -1.107 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
picking | +0.963 |
Wester | +0.853 |
ECK | +0.828 |
ILLE | +0.811 |
rol | +0.811 |
Neg logit contributions | |
ities | -1.596 |
ctors | -1.332 |
ifax | -1.299 |
peria | -1.279 |
andro | -1.277 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
picking | +0.506 |
Wester | +0.465 |
ILLE | +0.453 |
ECK | +0.452 |
SUP | +0.446 |
Neg logit contributions | |
ities | -0.503 |
ctors | -0.384 |
andro | -0.363 |
ifax | -0.360 |
peria | -0.360 |
Token | the |
Token ID | 262 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
picking | +0.382 |
Wester | +0.343 |
ILLE | +0.340 |
ECK | +0.339 |
SUP | +0.329 |
Neg logit contributions | |
ities | -0.476 |
ctors | -0.377 |
ifax | -0.356 |
andro | -0.354 |
peria | -0.352 |
Token | battery |
Token ID | 6555 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ities | +0.820 |
ctors | +0.651 |
andro | +0.620 |
ifax | +0.618 |
peria | +0.618 |
Neg logit contributions | |
picking | -0.595 |
Wester | -0.526 |
ILLE | -0.523 |
ECK | -0.518 |
rol | -0.503 |
Token | drain |
Token ID | 14782 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
picking | +5.859 |
Wester | +5.249 |
rol | +5.141 |
ECK | +5.082 |
SUP | +5.079 |
Neg logit contributions | |
ities | -7.932 |
ctors | -6.621 |
peria | -6.244 |
ifax | -6.176 |
andro | -6.166 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
picking | +2.884 |
Wester | +2.578 |
ECK | +2.536 |
ILLE | +2.498 |
rol | +2.487 |
Neg logit contributions | |
ities | -3.960 |
ctors | -3.209 |
ifax | -3.030 |
andro | -3.028 |
peria | -3.014 |
Token | so |
Token ID | 523 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ities | +0.400 |
ctors | +0.315 |
ifax | +0.301 |
andro | +0.299 |
peria | +0.298 |
Neg logit contributions | |
picking | -0.307 |
Wester | -0.274 |
ILLE | -0.273 |
ECK | -0.270 |
rol | -0.263 |
Token | the |
Token ID | 262 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
picking | +2.622 |
Wester | +2.322 |
ECK | +2.282 |
ILLE | +2.271 |
rol | +2.227 |
Neg logit contributions | |
ities | -3.929 |
ctors | -3.171 |
ifax | -3.022 |
andro | -3.021 |
peria | -2.997 |
Token | watch |
Token ID | 2342 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
ities | +0.191 |
ctors | +0.153 |
andro | +0.146 |
ifax | +0.146 |
peria | +0.145 |
Neg logit contributions | |
picking | -0.126 |
Wester | -0.110 |
ILLE | -0.109 |
ECK | -0.109 |
rol | -0.105 |
Token | came |
Token ID | 1625 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
ities | +1.048 |
ctors | +0.815 |
ifax | +0.777 |
andro | +0.773 |
peria | +0.760 |
Neg logit contributions | |
picking | -0.856 |
ILLE | -0.763 |
ECK | -0.759 |
Wester | -0.754 |
rol | -0.736 |
Token | from |
Token ID | 422 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
picking | +1.520 |
Wester | +1.369 |
ECK | +1.336 |
ILLE | +1.332 |
rol | +1.308 |
Neg logit contributions | |
ities | -1.976 |
ctors | -1.581 |
ifax | -1.496 |
andro | -1.490 |
peria | -1.486 |
Token | the |
Token ID | 262 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ities | +0.565 |
ctors | +0.452 |
andro | +0.430 |
ifax | +0.428 |
peria | +0.426 |
Neg logit contributions | |
picking | -0.414 |
Wester | -0.365 |
ECK | -0.362 |
ILLE | -0.362 |
rol | -0.352 |
Token | W |
Token ID | 370 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
picking | +0.517 |
Wester | +0.459 |
ECK | +0.454 |
ILLE | +0.454 |
rol | +0.443 |
Neg logit contributions | |
ities | -0.683 |
ctors | -0.543 |
ifax | -0.515 |
andro | -0.515 |
peria | -0.511 |
Token | BC |
Token ID | 2749 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
picking | +1.852 |
Wester | +1.603 |
ECK | +1.580 |
ILLE | +1.574 |
rol | +1.524 |
Neg logit contributions | |
ities | -3.667 |
ctors | -3.034 |
ifax | -2.906 |
andro | -2.895 |
peria | -2.884 |
Token | cruiser |
Token ID | 35239 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
picking | +2.698 |
Wester | +2.435 |
ECK | +2.378 |
ILLE | +2.377 |
SUP | +2.338 |
Neg logit contributions | |
ities | -3.604 |
ctors | -2.871 |
ifax | -2.750 |
peria | -2.727 |
andro | -2.727 |
Token | weight |
Token ID | 6551 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
picking | +5.237 |
Wester | +4.599 |
SUP | +4.428 |
ECK | +4.405 |
ILLE | +4.320 |
Neg logit contributions | |
ities | -8.684 |
ctors | -7.104 |
ifax | -7.000 |
andro | -6.787 |
peria | -6.777 |
Token | world |
Token ID | 995 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
picking | +0.774 |
Wester | +0.699 |
ECK | +0.688 |
ILLE | +0.686 |
rol | +0.673 |
Neg logit contributions | |
ities | -0.879 |
ctors | -0.687 |
ifax | -0.650 |
andro | -0.648 |
peria | -0.645 |
Token | champion |
Token ID | 8783 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
picking | +1.601 |
Wester | +1.439 |
ECK | +1.415 |
ILLE | +1.408 |
rol | +1.385 |
Neg logit contributions | |
ities | -1.923 |
ctors | -1.516 |
ifax | -1.440 |
andro | -1.432 |
peria | -1.431 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
picking | +0.407 |
Wester | +0.364 |
ILLE | +0.361 |
ECK | +0.360 |
rol | +0.351 |
Neg logit contributions | |
ities | -0.507 |
ctors | -0.401 |
ifax | -0.380 |
andro | -0.380 |
peria | -0.376 |
Token | Tony |
Token ID | 8832 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
ities | +0.595 |
ctors | +0.474 |
andro | +0.453 |
ifax | +0.451 |
peria | +0.447 |
Neg logit contributions | |
picking | -0.439 |
ILLE | -0.391 |
Wester | -0.389 |
ECK | -0.387 |
rol | -0.376 |
Token | chip |
Token ID | 11594 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ities | +1.190 |
ctors | +0.941 |
ifax | +0.890 |
andro | +0.887 |
peria | +0.882 |
Neg logit contributions | |
picking | -0.943 |
Wester | -0.843 |
ECK | -0.833 |
ILLE | -0.832 |
rol | -0.812 |
Token | away |
Token ID | 1497 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
picking | +0.459 |
Wester | +0.406 |
ILLE | +0.402 |
ECK | +0.400 |
rol | +0.389 |
Neg logit contributions | |
ities | -0.673 |
ctors | -0.540 |
ifax | -0.512 |
peria | -0.512 |
andro | -0.511 |
Token | at |
Token ID | 379 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
ities | +0.554 |
ctors | +0.425 |
ifax | +0.401 |
andro | +0.398 |
peria | +0.391 |
Neg logit contributions | |
picking | -0.478 |
ILLE | -0.428 |
Wester | -0.428 |
ECK | -0.424 |
SUP | -0.411 |
Token | Wisconsin |
Token ID | 9279 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
picking | +0.128 |
ILLE | +0.111 |
Wester | +0.111 |
ECK | +0.110 |
rol | +0.107 |
Neg logit contributions | |
ities | -0.203 |
ctors | -0.164 |
ifax | -0.156 |
andro | -0.155 |
peria | -0.154 |
Token | 's |
Token ID | 338 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
picking | +1.815 |
Wester | +1.618 |
ECK | +1.588 |
ILLE | +1.579 |
rol | +1.556 |
Neg logit contributions | |
ities | -2.479 |
ctors | -1.987 |
ifax | -1.897 |
andro | -1.892 |
peria | -1.890 |
Token | constitutionally |
Token ID | 40800 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
picking | +1.687 |
Wester | +1.499 |
ECK | +1.468 |
ILLE | +1.462 |
rol | +1.430 |
Neg logit contributions | |
ities | -2.518 |
ctors | -2.035 |
ifax | -1.940 |
andro | -1.938 |
peria | -1.931 |
Token | created |
Token ID | 2727 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
picking | +4.409 |
Wester | +3.907 |
ECK | +3.692 |
ILLE | +3.610 |
SUP | +3.598 |
Neg logit contributions | |
ities | -9.390 |
ctors | -7.895 |
peria | -7.653 |
ifax | -7.622 |
andro | -7.507 |
Token | system |
Token ID | 1080 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
picking | +0.245 |
Wester | +0.216 |
ILLE | +0.213 |
ECK | +0.213 |
rol | +0.207 |
Neg logit contributions | |
ities | -0.376 |
ctors | -0.304 |
ifax | -0.289 |
andro | -0.288 |
peria | -0.286 |
Token | of |
Token ID | 286 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
picking | +1.511 |
Wester | +1.350 |
ECK | +1.322 |
ILLE | +1.321 |
rol | +1.294 |
Neg logit contributions | |
ities | -1.993 |
ctors | -1.594 |
ifax | -1.512 |
andro | -1.509 |
peria | -1.503 |
Token | public |
Token ID | 1171 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
picking | +0.713 |
Wester | +0.615 |
ECK | +0.605 |
ILLE | +0.605 |
rol | +0.583 |
Neg logit contributions | |
ities | -1.386 |
ctors | -1.140 |
ifax | -1.090 |
andro | -1.088 |
peria | -1.081 |
Token | education |
Token ID | 3707 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
picking | +0.604 |
Wester | +0.539 |
ILLE | +0.531 |
ECK | +0.531 |
rol | +0.517 |
Neg logit contributions | |
ities | -0.797 |
ctors | -0.633 |
ifax | -0.601 |
andro | -0.600 |
peria | -0.595 |
Token | of |
Token ID | 286 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
ities | +0.747 |
ctors | +0.587 |
ifax | +0.559 |
andro | +0.554 |
peria | +0.550 |
Neg logit contributions | |
picking | -0.574 |
Wester | -0.513 |
ECK | -0.512 |
ILLE | -0.507 |
rol | -0.494 |
Token | exploiting |
Token ID | 29440 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ities | +1.258 |
ctors | +1.011 |
ifax | +0.963 |
andro | +0.961 |
peria | +0.953 |
Neg logit contributions | |
picking | -0.788 |
ECK | -0.699 |
Wester | -0.693 |
ILLE | -0.691 |
rol | -0.673 |
Token | it |
Token ID | 340 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
picking | +0.333 |
Wester | +0.292 |
ECK | +0.291 |
ILLE | +0.290 |
rol | +0.282 |
Neg logit contributions | |
ities | -0.499 |
ctors | -0.400 |
ifax | -0.382 |
andro | -0.380 |
peria | -0.378 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
picking | +0.955 |
Wester | +0.856 |
ECK | +0.843 |
ILLE | +0.842 |
rol | +0.823 |
Neg logit contributions | |
ities | -1.199 |
ctors | -0.948 |
ifax | -0.900 |
andro | -0.897 |
peria | -0.892 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ities | +0.244 |
ctors | +0.194 |
ifax | +0.184 |
andro | +0.184 |
peria | +0.182 |
Neg logit contributions | |
picking | -0.189 |
Wester | -0.169 |
ECK | -0.167 |
ILLE | -0.166 |
rol | -0.163 |
Token | Bed |
Token ID | 45896 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ities | +0.790 |
ctors | +0.608 |
andro | +0.576 |
peria | +0.570 |
ifax | +0.569 |
Neg logit contributions | |
picking | -0.756 |
Wester | -0.697 |
ECK | -0.675 |
ILLE | -0.673 |
SUP | -0.669 |
Token | side |
Token ID | 1589 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
picking | +6.335 |
Wester | +5.678 |
ECK | +5.587 |
rol | +5.534 |
ILLE | +5.498 |
Neg logit contributions | |
ities | -7.539 |
ctors | -5.990 |
peria | -5.722 |
andro | -5.689 |
ifax | -5.601 |
Token | is |
Token ID | 318 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
picking | +1.590 |
Wester | +1.411 |
ECK | +1.389 |
ILLE | +1.386 |
rol | +1.352 |
Neg logit contributions | |
ities | -2.261 |
ctors | -1.814 |
ifax | -1.727 |
andro | -1.721 |
peria | -1.712 |
Token | a |
Token ID | 257 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
picking | +1.641 |
Wester | +1.457 |
ECK | +1.433 |
ILLE | +1.431 |
rol | +1.396 |
Neg logit contributions | |
ities | -2.343 |
ctors | -1.882 |
ifax | -1.792 |
andro | -1.786 |
peria | -1.777 |
Token | series |
Token ID | 2168 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
picking | +0.376 |
Wester | +0.333 |
ECK | +0.328 |
ILLE | +0.328 |
rol | +0.320 |
Neg logit contributions | |
ities | -0.539 |
ctors | -0.434 |
ifax | -0.412 |
andro | -0.411 |
peria | -0.409 |
Token | about |
Token ID | 546 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
picking | +1.636 |
Wester | +1.457 |
ECK | +1.432 |
ILLE | +1.430 |
rol | +1.397 |
Neg logit contributions | |
ities | -2.247 |
ctors | -1.797 |
ifax | -1.709 |
andro | -1.704 |
peria | -1.695 |
Token | under |
Token ID | 739 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
picking | +0.330 |
Wester | +0.295 |
ECK | +0.291 |
ILLE | +0.290 |
rol | +0.283 |
Neg logit contributions | |
ities | -0.423 |
ctors | -0.335 |
ifax | -0.318 |
andro | -0.317 |
peria | -0.315 |
Token | the |
Token ID | 262 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
picking | +0.117 |
Wester | +0.104 |
ECK | +0.102 |
ILLE | +0.102 |
rol | +0.099 |
Neg logit contributions | |
ities | -0.164 |
ctors | -0.132 |
ifax | -0.125 |
andro | -0.124 |
peria | -0.123 |
Token | 9 |
Token ID | 860 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
ities | +1.581 |
ctors | +1.271 |
ifax | +1.204 |
andro | +1.199 |
peria | +1.186 |
Neg logit contributions | |
picking | -1.089 |
Wester | -0.957 |
ECK | -0.951 |
ILLE | -0.943 |
rol | -0.918 |
Token | / |
Token ID | 14 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ities | +1.689 |
ctors | +1.325 |
ifax | +1.253 |
peria | +1.247 |
andro | +1.242 |
Neg logit contributions | |
picking | -1.408 |
Wester | -1.276 |
ILLE | -1.251 |
ECK | -1.249 |
rol | -1.228 |
Token | 11 |
Token ID | 1157 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
picking | +1.134 |
Wester | +1.022 |
ECK | +1.013 |
ILLE | +1.009 |
rol | +0.990 |
Neg logit contributions | |
ities | -1.242 |
ctors | -0.969 |
ifax | -0.918 |
andro | -0.912 |
peria | -0.905 |
Token | GI |
Token ID | 30616 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
picking | +0.565 |
Wester | +0.501 |
ECK | +0.494 |
ILLE | +0.493 |
SUP | +0.481 |
Neg logit contributions | |
ities | -0.809 |
ctors | -0.653 |
ifax | -0.620 |
andro | -0.619 |
peria | -0.618 |
Token | Bill |
Token ID | 3941 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
picking | +6.261 |
Wester | +5.718 |
ECK | +5.707 |
ILLE | +5.655 |
rol | +5.504 |
Neg logit contributions | |
ities | -7.422 |
ctors | -5.763 |
ifax | -5.572 |
andro | -5.545 |
peria | -5.486 |
Token | ® |
Token ID | 38852 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
ities | +0.951 |
ctors | +0.747 |
ifax | +0.706 |
andro | +0.701 |
peria | +0.698 |
Neg logit contributions | |
picking | -0.782 |
Wester | -0.702 |
ILLE | -0.689 |
ECK | -0.687 |
rol | -0.669 |
Token | . |
Token ID | 764 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
ities | +1.156 |
ctors | +0.908 |
ifax | +0.854 |
peria | +0.847 |
andro | +0.846 |
Neg logit contributions | |
picking | -0.970 |
Wester | -0.874 |
ILLE | -0.852 |
ECK | -0.852 |
rol | -0.829 |
Token |
|
Token ID | 198 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
picking | +0.195 |
Wester | +0.174 |
ECK | +0.171 |
ILLE | +0.170 |
rol | +0.167 |
Neg logit contributions | |
ities | -0.249 |
ctors | -0.198 |
ifax | -0.187 |
andro | -0.186 |
peria | -0.185 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
picking | +0.123 |
Wester | +0.109 |
ECK | +0.109 |
ILLE | +0.108 |
rol | +0.105 |
Neg logit contributions | |
ities | -0.181 |
ctors | -0.146 |
ifax | -0.141 |
andro | -0.140 |
peria | -0.139 |
Token | influence |
Token ID | 4588 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
ities | +0.785 |
ctors | +0.620 |
ifax | +0.590 |
andro | +0.589 |
peria | +0.585 |
Neg logit contributions | |
picking | -0.620 |
Wester | -0.552 |
ECK | -0.546 |
ILLE | -0.545 |
rol | -0.530 |
Token | firm |
Token ID | 4081 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
picking | +2.186 |
Wester | +1.949 |
ECK | +1.910 |
ILLE | +1.903 |
rol | +1.876 |
Neg logit contributions | |
ities | -2.851 |
ctors | -2.273 |
ifax | -2.154 |
andro | -2.153 |
peria | -2.135 |
Token | with |
Token ID | 351 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
picking | +0.517 |
Wester | +0.461 |
ILLE | +0.456 |
ECK | +0.455 |
rol | +0.443 |
Neg logit contributions | |
ities | -0.680 |
ctors | -0.539 |
ifax | -0.512 |
andro | -0.510 |
peria | -0.508 |
Token | a |
Token ID | 257 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
picking | +0.066 |
ILLE | +0.057 |
Wester | +0.057 |
ECK | +0.057 |
rol | +0.055 |
Neg logit contributions | |
ities | -0.094 |
ctors | -0.074 |
ifax | -0.071 |
andro | -0.071 |
peria | -0.070 |
Token | long |
Token ID | 890 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
ities | +0.282 |
ctors | +0.228 |
ifax | +0.216 |
andro | +0.215 |
peria | +0.215 |
Neg logit contributions | |
picking | -0.187 |
Wester | -0.163 |
ILLE | -0.162 |
ECK | -0.162 |
rol | -0.156 |
Token | history |
Token ID | 2106 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
picking | +1.360 |
Wester | +1.225 |
ECK | +1.206 |
ILLE | +1.204 |
rol | +1.180 |
Neg logit contributions | |
ities | -1.571 |
ctors | -1.231 |
ifax | -1.166 |
andro | -1.162 |
peria | -1.155 |
Token | of |
Token ID | 286 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
picking | +5.202 |
Wester | +4.635 |
rol | +4.419 |
ECK | +4.371 |
SUP | +4.369 |
Neg logit contributions | |
ities | -8.292 |
ctors | -6.842 |
ifax | -6.566 |
peria | -6.522 |
andro | -6.498 |
Token | running |
Token ID | 2491 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
picking | +1.762 |
Wester | +1.568 |
ECK | +1.532 |
ILLE | +1.529 |
rol | +1.499 |
Neg logit contributions | |
ities | -2.545 |
ctors | -2.054 |
ifax | -1.955 |
andro | -1.950 |
peria | -1.940 |
Token | front |
Token ID | 2166 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
ities | +0.323 |
ctors | +0.258 |
ifax | +0.245 |
andro | +0.245 |
peria | +0.244 |
Neg logit contributions | |
picking | -0.223 |
Wester | -0.197 |
ILLE | -0.195 |
ECK | -0.195 |
rol | -0.189 |
Token | groups |
Token ID | 2628 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
picking | +1.723 |
Wester | +1.507 |
ILLE | +1.461 |
ECK | +1.460 |
rol | +1.445 |
Neg logit contributions | |
ities | -2.931 |
ctors | -2.408 |
ifax | -2.305 |
peria | -2.288 |
andro | -2.285 |
Token | for |
Token ID | 329 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
picking | +0.660 |
Wester | +0.589 |
ECK | +0.580 |
ILLE | +0.579 |
rol | +0.566 |
Neg logit contributions | |
ities | -0.872 |
ctors | -0.694 |
ifax | -0.659 |
andro | -0.657 |
peria | -0.654 |
Token | down |
Token ID | 866 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
picking | +0.528 |
Wester | +0.470 |
ILLE | +0.462 |
ECK | +0.462 |
rol | +0.449 |
Neg logit contributions | |
ities | -0.733 |
ctors | -0.585 |
ifax | -0.557 |
andro | -0.555 |
peria | -0.552 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
picking | +2.019 |
Wester | +1.805 |
ECK | +1.774 |
ILLE | +1.765 |
rol | +1.734 |
Neg logit contributions | |
ities | -2.708 |
ctors | -2.167 |
ifax | -2.060 |
andro | -2.054 |
peria | -2.042 |
Token | Depending |
Token ID | 23591 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
picking | +0.384 |
Wester | +0.340 |
ILLE | +0.336 |
ECK | +0.335 |
rol | +0.327 |
Neg logit contributions | |
ities | -0.525 |
ctors | -0.419 |
ifax | -0.398 |
andro | -0.397 |
peria | -0.395 |
Token | on |
Token ID | 319 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
picking | +0.665 |
Wester | +0.594 |
ILLE | +0.592 |
ECK | +0.584 |
rol | +0.564 |
Neg logit contributions | |
ities | -0.965 |
ctors | -0.768 |
ifax | -0.733 |
andro | -0.726 |
peria | -0.719 |
Token | the |
Token ID | 262 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
picking | +0.680 |
Wester | +0.598 |
ILLE | +0.590 |
ECK | +0.589 |
rol | +0.572 |
Neg logit contributions | |
ities | -1.049 |
ctors | -0.844 |
ifax | -0.807 |
andro | -0.805 |
peria | -0.803 |
Token | battery |
Token ID | 6555 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
picking | +1.343 |
Wester | +1.208 |
ECK | +1.187 |
ILLE | +1.185 |
rol | +1.162 |
Neg logit contributions | |
ities | -1.623 |
ctors | -1.282 |
ifax | -1.215 |
andro | -1.210 |
peria | -1.202 |
Token | you |
Token ID | 345 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
picking | +5.742 |
Wester | +5.170 |
rol | +5.020 |
SUP | +4.963 |
ECK | +4.939 |
Neg logit contributions | |
ities | -7.474 |
ctors | -6.236 |
ifax | -5.901 |
peria | -5.888 |
andro | -5.863 |
Token | had |
Token ID | 550 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
ities | +0.265 |
ctors | +0.201 |
ifax | +0.189 |
andro | +0.188 |
peria | +0.187 |
Neg logit contributions | |
picking | -0.281 |
Wester | -0.254 |
ILLE | -0.252 |
ECK | -0.252 |
rol | -0.246 |
Token | it |
Token ID | 340 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
ities | +1.091 |
ctors | +0.849 |
ifax | +0.818 |
peria | +0.810 |
andro | +0.810 |
Neg logit contributions | |
picking | -0.855 |
Wester | -0.759 |
ECK | -0.757 |
ILLE | -0.753 |
rol | -0.729 |
Token | might |
Token ID | 1244 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
picking | +1.247 |
Wester | +1.109 |
ECK | +1.089 |
ILLE | +1.088 |
rol | +1.062 |
Neg logit contributions | |
ities | -1.758 |
ctors | -1.410 |
ifax | -1.342 |
andro | -1.339 |
peria | -1.331 |
Token | get |
Token ID | 651 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
picking | +0.477 |
Wester | +0.427 |
ECK | +0.421 |
ILLE | +0.421 |
rol | +0.410 |
Neg logit contributions | |
ities | -0.591 |
ctors | -0.466 |
ifax | -0.441 |
andro | -0.440 |
peria | -0.438 |
Token | Under |
Token ID | 4698 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
ities | +1.247 |
ctors | +0.989 |
andro | +0.931 |
ifax | +0.930 |
peria | +0.922 |
Neg logit contributions | |
picking | -0.998 |
Wester | -0.883 |
ILLE | -0.880 |
ECK | -0.878 |
rol | -0.858 |
Token | NASA |
Token ID | 8884 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
picking | +0.954 |
Wester | +0.845 |
ILLE | +0.838 |
ECK | +0.836 |
rol | +0.813 |
Neg logit contributions | |
ities | -1.352 |
ctors | -1.085 |
ifax | -1.030 |
andro | -1.026 |
peria | -1.020 |
Token | � |
Token ID | 447 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ities | +0.411 |
ctors | +0.324 |
ifax | +0.304 |
andro | +0.303 |
peria | +0.301 |
Neg logit contributions | |
picking | -0.332 |
Wester | -0.298 |
ILLE | -0.293 |
ECK | -0.293 |
rol | -0.285 |
Token | � |
Token ID | 247 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ities | +0.846 |
ctors | +0.696 |
ifax | +0.665 |
peria | +0.658 |
andro | +0.657 |
Neg logit contributions | |
picking | -0.487 |
Wester | -0.427 |
ECK | -0.424 |
ILLE | -0.424 |
rol | -0.416 |
Token | s |
Token ID | 82 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ities | +0.305 |
ctors | +0.229 |
ifax | +0.214 |
andro | +0.213 |
peria | +0.210 |
Neg logit contributions | |
picking | -0.345 |
Wester | -0.315 |
ECK | -0.311 |
ILLE | -0.311 |
SUP | -0.305 |
Token | contingency |
Token ID | 38820 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ities | +1.795 |
ctors | +1.418 |
ifax | +1.343 |
andro | +1.341 |
peria | +1.328 |
Neg logit contributions | |
picking | -1.328 |
ILLE | -1.173 |
ECK | -1.171 |
Wester | -1.167 |
rol | -1.132 |
Token | plans |
Token ID | 3352 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
picking | +4.422 |
Wester | +3.859 |
ECK | +3.686 |
rol | +3.665 |
ILLE | +3.614 |
Neg logit contributions | |
ities | -8.723 |
ctors | -7.406 |
andro | -7.247 |
ifax | -7.182 |
peria | -7.135 |
Token | , |
Token ID | 11 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
picking | +0.299 |
Wester | +0.268 |
ECK | +0.265 |
ILLE | +0.265 |
rol | +0.259 |
Neg logit contributions | |
ities | -0.338 |
ctors | -0.264 |
ifax | -0.250 |
andro | -0.248 |
peria | -0.247 |
Token | operational |
Token ID | 13919 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
picking | +0.207 |
Wester | +0.184 |
ILLE | +0.182 |
ECK | +0.182 |
rol | +0.177 |
Neg logit contributions | |
ities | -0.288 |
ctors | -0.231 |
ifax | -0.219 |
andro | -0.218 |
peria | -0.217 |
Token | missions |
Token ID | 10566 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
ities | +0.076 |
ctors | +0.060 |
ifax | +0.057 |
andro | +0.056 |
peria | +0.056 |
Neg logit contributions | |
picking | -0.058 |
Wester | -0.052 |
ILLE | -0.051 |
ECK | -0.051 |
rol | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
ities | +1.594 |
ctors | +1.256 |
ifax | +1.181 |
andro | +1.176 |
peria | +1.175 |
Neg logit contributions | |
picking | -1.261 |
ILLE | -1.117 |
Wester | -1.115 |
ECK | -1.114 |
rol | -1.076 |
Token | style |
Token ID | 3918 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ities | +1.128 |
ctors | +0.891 |
ifax | +0.851 |
andro | +0.844 |
peria | +0.838 |
Neg logit contributions | |
picking | -0.793 |
Wester | -0.704 |
ILLE | -0.696 |
ECK | -0.696 |
rol | -0.674 |
Token | battles |
Token ID | 10181 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
picking | +1.202 |
Wester | +1.065 |
ECK | +1.045 |
ILLE | +1.043 |
rol | +1.018 |
Neg logit contributions | |
ities | -1.794 |
ctors | -1.449 |
ifax | -1.381 |
andro | -1.377 |
peria | -1.370 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
picking | +0.945 |
Wester | +0.846 |
ECK | +0.833 |
ILLE | +0.833 |
rol | +0.811 |
Neg logit contributions | |
ities | -1.216 |
ctors | -0.962 |
ifax | -0.911 |
andro | -0.910 |
peria | -0.906 |
Token |
|
Token ID | 198 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
picking | +0.336 |
Wester | +0.298 |
ECK | +0.294 |
ILLE | +0.294 |
rol | +0.287 |
Neg logit contributions | |
ities | -0.450 |
ctors | -0.358 |
ifax | -0.339 |
andro | -0.339 |
peria | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
picking | +0.854 |
Wester | +0.764 |
ECK | +0.731 |
rol | +0.723 |
SUP | +0.722 |
Neg logit contributions | |
ities | -1.401 |
ctors | -1.167 |
ifax | -1.139 |
peria | -1.122 |
andro | -1.119 |
Token | Weather |
Token ID | 41865 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
picking | +0.550 |
Wester | +0.501 |
ECK | +0.489 |
ILLE | +0.488 |
rol | +0.479 |
Neg logit contributions | |
ities | -0.592 |
ctors | -0.458 |
andro | -0.432 |
peria | -0.429 |
ifax | -0.429 |
Token | and |
Token ID | 290 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
picking | +5.931 |
Wester | +5.327 |
ECK | +5.154 |
rol | +5.149 |
ILLE | +5.146 |
Neg logit contributions | |
ities | -7.521 |
ctors | -6.078 |
peria | -5.743 |
andro | -5.741 |
ifax | -5.703 |
Token | time |
Token ID | 640 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
picking | +0.805 |
Wester | +0.705 |
ECK | +0.700 |
ILLE | +0.700 |
rol | +0.675 |
Neg logit contributions | |
ities | -1.223 |
ctors | -0.982 |
ifax | -0.934 |
andro | -0.930 |
peria | -0.929 |
Token | of |
Token ID | 286 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
picking | +1.649 |
Wester | +1.476 |
ILLE | +1.461 |
ECK | +1.456 |
rol | +1.420 |
Neg logit contributions | |
ities | -2.057 |
ctors | -1.623 |
ifax | -1.538 |
andro | -1.532 |
peria | -1.522 |
Token | day |
Token ID | 1110 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
picking | +0.594 |
Wester | +0.528 |
ECK | +0.524 |
ILLE | +0.522 |
rol | +0.510 |
Neg logit contributions | |
ities | -0.736 |
ctors | -0.580 |
ifax | -0.550 |
andro | -0.549 |
peria | -0.547 |
Token |
|
Token ID | 198 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
picking | +1.241 |
Wester | +1.114 |
ECK | +1.101 |
ILLE | +1.099 |
rol | +1.073 |
Neg logit contributions | |
ities | -1.454 |
ctors | -1.139 |
ifax | -1.077 |
andro | -1.073 |
peria | -1.066 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ities | +0.268 |
ctors | +0.210 |
ifax | +0.199 |
andro | +0.199 |
peria | +0.197 |
Neg logit contributions | |
picking | -0.218 |
Wester | -0.195 |
ECK | -0.194 |
ILLE | -0.194 |
rol | -0.188 |
Token | If |
Token ID | 1002 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
picking | +0.258 |
Wester | +0.228 |
ILLE | +0.226 |
ECK | +0.225 |
rol | +0.220 |
Neg logit contributions | |
ities | -0.350 |
ctors | -0.279 |
ifax | -0.265 |
andro | -0.265 |
peria | -0.263 |
Token | you |
Token ID | 345 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
picking | +0.378 |
Wester | +0.333 |
ILLE | +0.328 |
ECK | +0.328 |
rol | +0.318 |
Neg logit contributions | |
ities | -0.595 |
ctors | -0.479 |
ifax | -0.458 |
andro | -0.458 |
peria | -0.457 |
Token | see |
Token ID | 766 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
ities | +2.159 |
ctors | +1.655 |
ifax | +1.566 |
andro | +1.554 |
peria | +1.550 |
Neg logit contributions | |
picking | -2.020 |
Wester | -1.812 |
ILLE | -1.808 |
ECK | -1.795 |
rol | -1.745 |
Token | the |
Token ID | 262 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ities | +0.115 |
ctors | +0.092 |
andro | +0.087 |
ifax | +0.087 |
peria | +0.087 |
Neg logit contributions | |
picking | -0.082 |
Wester | -0.073 |
ILLE | -0.072 |
ECK | -0.072 |
rol | -0.070 |
Token | battery |
Token ID | 6555 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
picking | +0.685 |
Wester | +0.600 |
ECK | +0.589 |
ILLE | +0.589 |
rol | +0.573 |
Neg logit contributions | |
ities | -1.133 |
ctors | -0.921 |
ifax | -0.880 |
andro | -0.878 |
peria | -0.874 |
Token | logo |
Token ID | 11112 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
picking | +5.398 |
Wester | +4.781 |
rol | +4.621 |
ECK | +4.610 |
ILLE | +4.598 |
Neg logit contributions | |
ities | -7.854 |
ctors | -6.601 |
ifax | -6.226 |
peria | -6.226 |
andro | -6.179 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
ities | +0.342 |
ctors | +0.269 |
andro | +0.256 |
ifax | +0.256 |
peria | +0.255 |
Neg logit contributions | |
picking | -0.262 |
Wester | -0.233 |
ECK | -0.231 |
ILLE | -0.230 |
rol | -0.225 |
Token | you |
Token ID | 345 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ities | +0.116 |
ctors | +0.093 |
ifax | +0.088 |
andro | +0.088 |
peria | +0.088 |
Neg logit contributions | |
picking | -0.082 |
Wester | -0.073 |
ILLE | -0.072 |
ECK | -0.072 |
rol | -0.070 |
Token | 're |
Token ID | 821 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ities | +2.129 |
ctors | +1.637 |
andro | +1.547 |
ifax | +1.547 |
peria | +1.536 |
Neg logit contributions | |
picking | -1.946 |
Wester | -1.742 |
ILLE | -1.734 |
ECK | -1.724 |
rol | -1.684 |
Token | good |
Token ID | 922 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ities | +2.076 |
ctors | +1.654 |
andro | +1.591 |
ifax | +1.584 |
peria | +1.581 |
Neg logit contributions | |
picking | -1.448 |
Wester | -1.280 |
ILLE | -1.274 |
ECK | -1.271 |
rol | -1.238 |
Token | of |
Token ID | 286 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ities | +0.543 |
ctors | +0.426 |
ifax | +0.405 |
andro | +0.404 |
peria | +0.398 |
Neg logit contributions | |
picking | -0.448 |
Wester | -0.398 |
ILLE | -0.394 |
ECK | -0.394 |
rol | -0.384 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
picking | +0.853 |
Wester | +0.752 |
ECK | +0.742 |
ILLE | +0.741 |
rol | +0.721 |
Neg logit contributions | |
ities | -1.233 |
ctors | -0.989 |
ifax | -0.943 |
andro | -0.941 |
peria | -0.934 |
Token | dinosaur |
Token ID | 28257 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
picking | +0.219 |
Wester | +0.192 |
ECK | +0.190 |
ILLE | +0.189 |
rol | +0.184 |
Neg logit contributions | |
ities | -0.330 |
ctors | -0.267 |
ifax | -0.254 |
andro | -0.254 |
peria | -0.252 |
Token | - |
Token ID | 12 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
picking | +0.859 |
Wester | +0.766 |
ECK | +0.754 |
ILLE | +0.753 |
rol | +0.735 |
Neg logit contributions | |
ities | -1.134 |
ctors | -0.901 |
ifax | -0.857 |
andro | -0.854 |
peria | -0.849 |
Token | era |
Token ID | 8607 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
picking | +2.327 |
Wester | +2.089 |
ECK | +2.055 |
ILLE | +2.054 |
rol | +2.023 |
Neg logit contributions | |
ities | -2.547 |
ctors | -1.990 |
ifax | -1.876 |
andro | -1.861 |
peria | -1.858 |
Token | crocod |
Token ID | 37565 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
picking | +3.154 |
Wester | +2.852 |
ECK | +2.735 |
ILLE | +2.734 |
SUP | +2.698 |
Neg logit contributions | |
ities | -5.468 |
ctors | -4.516 |
ifax | -4.298 |
andro | -4.289 |
peria | -4.279 |
Token | ile |
Token ID | 576 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
picking | +5.961 |
ILLE | +5.311 |
Wester | +5.248 |
rol | +5.220 |
ECK | +5.172 |
Neg logit contributions | |
ities | -7.302 |
ctors | -5.988 |
andro | -5.554 |
ifax | -5.517 |
peria | -5.510 |
Token | found |
Token ID | 1043 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ities | +0.860 |
ctors | +0.674 |
ifax | +0.642 |
andro | +0.638 |
peria | +0.636 |
Neg logit contributions | |
picking | -0.675 |
Wester | -0.602 |
ECK | -0.595 |
ILLE | -0.593 |
rol | -0.578 |
Token | in |
Token ID | 287 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
picking | +0.975 |
Wester | +0.871 |
ECK | +0.855 |
ILLE | +0.854 |
rol | +0.835 |
Neg logit contributions | |
ities | -1.316 |
ctors | -1.051 |
ifax | -0.998 |
andro | -0.996 |
peria | -0.990 |
Token | the |
Token ID | 262 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
picking | +0.043 |
Wester | +0.038 |
ECK | +0.038 |
ILLE | +0.038 |
rol | +0.037 |
Neg logit contributions | |
ities | -0.059 |
ctors | -0.047 |
ifax | -0.045 |
andro | -0.045 |
peria | -0.045 |
Token | Sahara |
Token ID | 46882 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ities | +0.089 |
ctors | +0.071 |
ifax | +0.067 |
andro | +0.067 |
peria | +0.067 |
Neg logit contributions | |
picking | -0.068 |
Wester | -0.061 |
ECK | -0.060 |
ILLE | -0.060 |
rol | -0.058 |
Token | wheels |
Token ID | 13666 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ities | +2.471 |
ctors | +1.941 |
andro | +1.845 |
ifax | +1.840 |
peria | +1.826 |
Neg logit contributions | |
picking | -1.842 |
Wester | -1.612 |
ECK | -1.603 |
ILLE | -1.593 |
rol | -1.548 |
Token | with |
Token ID | 351 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
picking | +1.739 |
Wester | +1.564 |
ECK | +1.540 |
ILLE | +1.537 |
rol | +1.506 |
Neg logit contributions | |
ities | -2.066 |
ctors | -1.626 |
ifax | -1.540 |
andro | -1.534 |
peria | -1.525 |
Token | next |
Token ID | 1306 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
picking | +0.437 |
Wester | +0.387 |
ECK | +0.381 |
ILLE | +0.380 |
rol | +0.371 |
Neg logit contributions | |
ities | -0.612 |
ctors | -0.489 |
ifax | -0.465 |
andro | -0.464 |
peria | -0.461 |
Token | - |
Token ID | 12 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
ities | +2.522 |
ctors | +1.992 |
andro | +1.876 |
peria | +1.859 |
ifax | +1.857 |
Neg logit contributions | |
picking | -1.956 |
Wester | -1.760 |
ECK | -1.744 |
ILLE | -1.741 |
SUP | -1.676 |
Token | generation |
Token ID | 20158 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ities | +1.773 |
ctors | +1.371 |
andro | +1.301 |
peria | +1.279 |
ifax | +1.270 |
Neg logit contributions | |
picking | -1.656 |
Wester | -1.514 |
ECK | -1.502 |
ILLE | -1.500 |
SUP | -1.457 |
Token | BF |
Token ID | 41646 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ities | +0.943 |
ctors | +0.752 |
andro | +0.715 |
ifax | +0.714 |
peria | +0.709 |
Neg logit contributions | |
picking | -0.660 |
Wester | -0.579 |
ECK | -0.574 |
ILLE | -0.570 |
rol | -0.555 |
Token | Good |
Token ID | 10248 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
picking | +6.118 |
ILLE | +5.722 |
Wester | +5.691 |
ECK | +5.605 |
rol | +5.412 |
Neg logit contributions | |
ities | -6.988 |
ctors | -5.647 |
andro | -5.485 |
ifax | -5.473 |
peria | -5.244 |
Token | rich |
Token ID | 7527 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
ities | +3.017 |
ctors | +2.436 |
ifax | +2.333 |
peria | +2.319 |
andro | +2.312 |
Neg logit contributions | |
picking | -2.047 |
Wester | -1.813 |
ILLE | -1.788 |
ECK | -1.777 |
rol | -1.760 |
Token | All |
Token ID | 1439 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
ities | +1.584 |
ctors | +1.255 |
andro | +1.190 |
ifax | +1.188 |
peria | +1.176 |
Neg logit contributions | |
picking | -1.149 |
Wester | -1.008 |
ECK | -0.998 |
ILLE | -0.987 |
rol | -0.964 |
Token | - |
Token ID | 12 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
picking | +0.189 |
Wester | +0.169 |
ILLE | +0.165 |
ECK | +0.165 |
rol | +0.162 |
Neg logit contributions | |
ities | -0.270 |
ctors | -0.218 |
ifax | -0.207 |
andro | -0.206 |
peria | -0.205 |
Token | Ter |
Token ID | 15156 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ities | +3.485 |
ctors | +2.670 |
andro | +2.575 |
peria | +2.536 |
ifax | +2.502 |
Neg logit contributions | |
picking | -3.082 |
Wester | -2.831 |
ECK | -2.782 |
SUP | -2.739 |
ILLE | -2.728 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
picking | +2.134 |
Wester | +1.909 |
ECK | +1.880 |
ILLE | +1.879 |
rol | +1.833 |
Neg logit contributions | |
ities | -2.698 |
ctors | -2.133 |
ifax | -2.021 |
andro | -2.021 |
peria | -2.011 |
Token | If |
Token ID | 1002 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
picking | +0.376 |
Wester | +0.333 |
ILLE | +0.329 |
ECK | +0.329 |
rol | +0.321 |
Neg logit contributions | |
ities | -0.507 |
ctors | -0.404 |
ifax | -0.383 |
andro | -0.382 |
peria | -0.381 |
Token | you |
Token ID | 345 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
picking | +0.161 |
Wester | +0.142 |
ILLE | +0.140 |
ECK | +0.140 |
rol | +0.136 |
Neg logit contributions | |
ities | -0.247 |
ctors | -0.198 |
ifax | -0.189 |
andro | -0.189 |
peria | -0.189 |
Token | see |
Token ID | 766 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ities | +2.725 |
ctors | +2.127 |
ifax | +2.008 |
andro | +1.991 |
peria | +1.987 |
Neg logit contributions | |
picking | -2.207 |
Wester | -1.961 |
ILLE | -1.957 |
ECK | -1.944 |
rol | -1.879 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ities | +0.811 |
ctors | +0.640 |
andro | +0.611 |
ifax | +0.609 |
peria | +0.609 |
Neg logit contributions | |
picking | -0.592 |
Wester | -0.522 |
ILLE | -0.517 |
ECK | -0.515 |
rol | -0.502 |
Token | battery |
Token ID | 6555 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
picking | +0.251 |
Wester | +0.215 |
ILLE | +0.213 |
ECK | +0.212 |
rol | +0.205 |
Neg logit contributions | |
ities | -0.489 |
ctors | -0.401 |
andro | -0.384 |
ifax | -0.384 |
peria | -0.383 |
Token | logo |
Token ID | 11112 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
picking | +4.291 |
Wester | +3.713 |
ECK | +3.615 |
ILLE | +3.552 |
rol | +3.546 |
Neg logit contributions | |
ities | -8.835 |
ctors | -7.522 |
ifax | -7.197 |
andro | -7.149 |
peria | -7.138 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ities | +1.089 |
ctors | +0.831 |
ifax | +0.788 |
peria | +0.787 |
andro | +0.787 |
Neg logit contributions | |
picking | -1.002 |
Wester | -0.905 |
ILLE | -0.894 |
ECK | -0.893 |
rol | -0.874 |
Token | you |
Token ID | 345 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
ities | +0.831 |
ctors | +0.662 |
ifax | +0.630 |
andro | +0.630 |
peria | +0.628 |
Neg logit contributions | |
picking | -0.571 |
Wester | -0.507 |
ILLE | -0.505 |
ECK | -0.498 |
rol | -0.487 |
Token | 're |
Token ID | 821 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
ities | +2.089 |
ctors | +1.468 |
ifax | +1.370 |
andro | +1.358 |
peria | +1.335 |
Neg logit contributions | |
picking | -3.097 |
Wester | -2.833 |
ILLE | -2.820 |
ECK | -2.799 |
rol | -2.753 |
Token | good |
Token ID | 922 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ities | +2.639 |
ctors | +2.093 |
andro | +2.007 |
ifax | +2.004 |
peria | +1.987 |
Neg logit contributions | |
picking | -1.925 |
Wester | -1.712 |
ILLE | -1.703 |
ECK | -1.694 |
rol | -1.644 |
Token | reported |
Token ID | 2098 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ities | +1.899 |
ctors | +1.501 |
ifax | +1.412 |
andro | +1.403 |
peria | +1.394 |
Neg logit contributions | |
picking | -1.547 |
Wester | -1.377 |
ILLE | -1.375 |
ECK | -1.374 |
rol | -1.322 |
Token | that |
Token ID | 326 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
ities | +1.459 |
ctors | +1.147 |
ifax | +1.102 |
andro | +1.091 |
peria | +1.086 |
Neg logit contributions | |
picking | -1.057 |
Wester | -0.936 |
ECK | -0.935 |
ILLE | -0.923 |
rol | -0.900 |
Token | they |
Token ID | 484 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ities | +2.434 |
ctors | +1.911 |
andro | +1.819 |
ifax | +1.819 |
peria | +1.799 |
Neg logit contributions | |
picking | -1.885 |
ECK | -1.666 |
Wester | -1.647 |
ILLE | -1.644 |
rol | -1.589 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ities | +0.800 |
ctors | +0.625 |
ifax | +0.587 |
andro | +0.584 |
peria | +0.578 |
Neg logit contributions | |
picking | -0.719 |
Wester | -0.646 |
ECK | -0.640 |
ILLE | -0.638 |
rol | -0.620 |
Token | a |
Token ID | 257 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
ities | +0.433 |
ctors | +0.342 |
andro | +0.327 |
ifax | +0.326 |
peria | +0.322 |
Neg logit contributions | |
picking | -0.320 |
Wester | -0.281 |
ECK | -0.280 |
ILLE | -0.278 |
rol | -0.271 |
Token | crocod |
Token ID | 37565 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ities | +0.265 |
ctors | +0.214 |
ifax | +0.204 |
andro | +0.204 |
peria | +0.203 |
Neg logit contributions | |
picking | -0.168 |
Wester | -0.147 |
ECK | -0.145 |
ILLE | -0.145 |
rol | -0.140 |
Token | ile |
Token ID | 576 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
picking | +5.935 |
ILLE | +5.304 |
rol | +5.248 |
Wester | +5.240 |
ECK | +5.175 |
Neg logit contributions | |
ities | -7.237 |
ctors | -5.945 |
peria | -5.491 |
andro | -5.489 |
ifax | -5.448 |
Token | kill |
Token ID | 1494 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ities | +0.703 |
ctors | +0.562 |
ifax | +0.538 |
andro | +0.536 |
peria | +0.533 |
Neg logit contributions | |
picking | -0.480 |
Wester | -0.425 |
ECK | -0.421 |
ILLE | -0.419 |
rol | -0.407 |
Token | a |
Token ID | 257 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
picking | +0.723 |
Wester | +0.646 |
ECK | +0.635 |
ILLE | +0.634 |
rol | +0.620 |
Neg logit contributions | |
ities | -0.961 |
ctors | -0.767 |
ifax | -0.729 |
andro | -0.726 |
peria | -0.723 |
Token | water |
Token ID | 1660 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ities | +1.411 |
ctors | +1.120 |
ifax | +1.062 |
andro | +1.058 |
peria | +1.055 |
Neg logit contributions | |
picking | -1.070 |
Wester | -0.944 |
ECK | -0.941 |
ILLE | -0.939 |
rol | -0.907 |
Token | buffalo |
Token ID | 45019 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
picking | +1.948 |
Wester | +1.698 |
ECK | +1.663 |
ILLE | +1.660 |
rol | +1.614 |
Neg logit contributions | |
ities | -3.488 |
ctors | -2.858 |
ifax | -2.734 |
andro | -2.728 |
peria | -2.715 |
Token | By |
Token ID | 2750 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
picking | +0.100 |
Wester | +0.089 |
ECK | +0.088 |
ILLE | +0.088 |
rol | +0.085 |
Neg logit contributions | |
ities | -0.126 |
ctors | -0.100 |
ifax | -0.094 |
andro | -0.094 |
peria | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ities | +0.577 |
ctors | +0.459 |
ifax | +0.438 |
andro | +0.437 |
peria | +0.433 |
Neg logit contributions | |
picking | -0.401 |
ILLE | -0.358 |
Wester | -0.357 |
ECK | -0.354 |
rol | -0.343 |
Token | start |
Token ID | 923 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
ities | +0.502 |
ctors | +0.400 |
ifax | +0.381 |
andro | +0.379 |
peria | +0.376 |
Neg logit contributions | |
picking | -0.348 |
Wester | -0.306 |
ECK | -0.304 |
ILLE | -0.303 |
rol | -0.296 |
Token | of |
Token ID | 286 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
picking | +1.743 |
Wester | +1.552 |
ECK | +1.526 |
ILLE | +1.524 |
rol | +1.487 |
Neg logit contributions | |
ities | -2.413 |
ctors | -1.931 |
ifax | -1.836 |
andro | -1.832 |
peria | -1.821 |
Token | the |
Token ID | 262 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
picking | +0.065 |
Wester | +0.058 |
ILLE | +0.057 |
ECK | +0.057 |
rol | +0.055 |
Neg logit contributions | |
ities | -0.089 |
ctors | -0.071 |
ifax | -0.068 |
andro | -0.068 |
peria | -0.067 |
Token | 1946 |
Token ID | 22717 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
picking | +0.136 |
Wester | +0.121 |
ILLE | +0.120 |
ECK | +0.120 |
rol | +0.117 |
Neg logit contributions | |
ities | -0.184 |
ctors | -0.146 |
ifax | -0.139 |
andro | -0.139 |
peria | -0.138 |
Token | season |
Token ID | 1622 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
picking | +5.410 |
Wester | +4.889 |
ECK | +4.700 |
SUP | +4.693 |
rol | +4.644 |
Neg logit contributions | |
ities | -7.676 |
ctors | -6.291 |
peria | -6.016 |
ifax | -6.006 |
andro | -5.992 |
Token | , |
Token ID | 11 |
Feature activation | +7.40e-05 |
Pos logit contributions | |
picking | +1.308 |
Wester | +1.176 |
ECK | +1.166 |
ILLE | +1.165 |
rol | +1.136 |
Neg logit contributions | |
ities | -1.453 |
ctors | -1.127 |
ifax | -1.068 |
andro | -1.065 |
peria | -1.053 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
picking | +0.000 |
ECK | +0.000 |
Wester | +0.000 |
ILLE | +0.000 |
rol | +0.000 |
Neg logit contributions | |
ities | -0.000 |
ctors | -0.000 |
andro | -0.000 |
ifax | -0.000 |
peria | -0.000 |
Token | defending |
Token ID | 11749 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
ities | +0.411 |
ctors | +0.326 |
ifax | +0.310 |
andro | +0.309 |
peria | +0.306 |
Neg logit contributions | |
picking | -0.305 |
Wester | -0.269 |
ECK | -0.269 |
ILLE | -0.268 |
rol | -0.260 |
Token | ch |
Token ID | 442 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ities | +0.764 |
ctors | +0.606 |
andro | +0.573 |
ifax | +0.572 |
peria | +0.566 |
Neg logit contributions | |
picking | -0.567 |
ILLE | -0.500 |
ECK | -0.497 |
Wester | -0.495 |
rol | -0.482 |
Token | # |
Token ID | 1303 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ities | +1.029 |
ctors | +0.818 |
andro | +0.776 |
ifax | +0.773 |
peria | +0.760 |
Neg logit contributions | |
picking | -0.819 |
Wester | -0.719 |
ECK | -0.715 |
ILLE | -0.713 |
rol | -0.699 |
Token | Bull |
Token ID | 39549 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ities | +0.325 |
ctors | +0.256 |
ifax | +0.243 |
andro | +0.243 |
peria | +0.241 |
Neg logit contributions | |
picking | -0.267 |
Wester | -0.240 |
ECK | -0.236 |
ILLE | -0.234 |
SUP | -0.230 |
Token | s |
Token ID | 82 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
ities | +1.629 |
ctors | +1.192 |
ifax | +1.125 |
andro | +1.104 |
peria | +1.092 |
Neg logit contributions | |
picking | -1.991 |
Wester | -1.838 |
ECK | -1.821 |
ILLE | -1.809 |
SUP | -1.778 |
Token | — |
Token ID | 851 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ities | +2.795 |
ctors | +2.209 |
andro | +2.112 |
ifax | +2.092 |
peria | +2.083 |
Neg logit contributions | |
picking | -2.190 |
Wester | -1.949 |
ECK | -1.911 |
ILLE | -1.903 |
rol | -1.851 |
Token | Cody |
Token ID | 27035 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
picking | +1.222 |
Wester | +1.087 |
ECK | +1.063 |
ILLE | +1.062 |
rol | +1.037 |
Neg logit contributions | |
ities | -1.810 |
ctors | -1.461 |
ifax | -1.391 |
andro | -1.388 |
peria | -1.383 |
Token | Wester |
Token ID | 32104 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
picking | +2.482 |
Wester | +2.250 |
ILLE | +2.179 |
ECK | +2.175 |
rol | +2.113 |
Neg logit contributions | |
ities | -3.640 |
ctors | -2.943 |
ifax | -2.804 |
andro | -2.787 |
peria | -2.782 |
Token | lund |
Token ID | 37525 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
picking | +6.149 |
Wester | +5.579 |
ECK | +5.480 |
ILLE | +5.408 |
rol | +5.276 |
Neg logit contributions | |
ities | -7.100 |
ctors | -5.707 |
ifax | -5.366 |
peria | -5.312 |
andro | -5.302 |
Token | (@ |
Token ID | 4275 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
picking | +1.402 |
Wester | +1.237 |
ECK | +1.213 |
ILLE | +1.211 |
rol | +1.179 |
Neg logit contributions | |
ities | -2.228 |
ctors | -1.808 |
ifax | -1.725 |
andro | -1.721 |
peria | -1.714 |
Token | C |
Token ID | 34 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
picking | +1.263 |
Wester | +1.148 |
ECK | +1.132 |
ILLE | +1.131 |
rol | +1.109 |
Neg logit contributions | |
ities | -1.235 |
ctors | -0.946 |
ifax | -0.889 |
andro | -0.886 |
peria | -0.880 |
Token | ody |
Token ID | 1118 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
picking | +0.431 |
Wester | +0.379 |
ECK | +0.372 |
ILLE | +0.371 |
rol | +0.362 |
Neg logit contributions | |
ities | -0.693 |
ctors | -0.563 |
ifax | -0.538 |
andro | -0.536 |
peria | -0.534 |
Token | W |
Token ID | 54 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
picking | +2.304 |
Wester | +2.090 |
ECK | +2.048 |
ILLE | +2.035 |
rol | +2.000 |
Neg logit contributions | |
ities | -2.660 |
ctors | -2.083 |
ifax | -1.976 |
andro | -1.965 |
peria | -1.957 |
Token | fiction |
Token ID | 24046 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
ities | +0.455 |
ctors | +0.346 |
andro | +0.325 |
ifax | +0.322 |
peria | +0.320 |
Neg logit contributions | |
picking | -0.469 |
Wester | -0.432 |
ECK | -0.429 |
ILLE | -0.425 |
SUP | -0.418 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ities | +2.422 |
ctors | +1.910 |
andro | +1.794 |
ifax | +1.793 |
peria | +1.758 |
Neg logit contributions | |
picking | -1.934 |
ECK | -1.711 |
ILLE | -1.709 |
Wester | -1.706 |
rol | -1.658 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
picking | +0.037 |
Wester | +0.033 |
ECK | +0.031 |
rol | +0.031 |
SUP | +0.031 |
Neg logit contributions | |
ities | -0.058 |
ctors | -0.048 |
ifax | -0.047 |
peria | -0.046 |
andro | -0.046 |
Token | In |
Token ID | 818 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
ities | +0.457 |
ctors | +0.349 |
andro | +0.327 |
ifax | +0.326 |
peria | +0.325 |
Neg logit contributions | |
picking | -0.465 |
Wester | -0.425 |
ECK | -0.417 |
ILLE | -0.416 |
SUP | -0.409 |
Token | Peter |
Token ID | 5613 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
picking | +0.181 |
Wester | +0.161 |
ILLE | +0.159 |
ECK | +0.159 |
rol | +0.155 |
Neg logit contributions | |
ities | -0.243 |
ctors | -0.193 |
ifax | -0.184 |
andro | -0.183 |
peria | -0.182 |
Token | Matth |
Token ID | 45524 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ities | +1.124 |
ctors | +0.897 |
andro | +0.853 |
ifax | +0.851 |
peria | +0.847 |
Neg logit contributions | |
picking | -0.816 |
ILLE | -0.718 |
Wester | -0.717 |
ECK | -0.713 |
SUP | -0.694 |
Token | i |
Token ID | 72 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
ities | +8.239 |
ctors | +6.026 |
andro | +5.816 |
ifax | +5.580 |
peria | +5.545 |
Neg logit contributions | |
picking | -9.848 |
SUP | -9.117 |
Wester | -9.117 |
ILLE | -9.090 |
ECK | -8.964 |
Token | essen |
Token ID | 44483 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ities | +1.020 |
ctors | +0.734 |
ifax | +0.678 |
andro | +0.677 |
peria | +0.668 |
Neg logit contributions | |
picking | -1.434 |
Wester | -1.321 |
ILLE | -1.306 |
ECK | -1.306 |
rol | -1.282 |
Token | 's |
Token ID | 338 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ities | +0.374 |
ctors | +0.294 |
andro | +0.278 |
ifax | +0.278 |
peria | +0.274 |
Neg logit contributions | |
picking | -0.300 |
Wester | -0.267 |
ILLE | -0.266 |
ECK | -0.265 |
SUP | -0.259 |
Token | 1978 |
Token ID | 15524 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
picking | +2.535 |
Wester | +2.313 |
ECK | +2.202 |
ILLE | +2.200 |
SUP | +2.172 |
Neg logit contributions | |
ities | -3.580 |
ctors | -2.887 |
ifax | -2.769 |
peria | -2.763 |
andro | -2.755 |
Token | travel |
Token ID | 3067 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
picking | +2.535 |
Wester | +2.319 |
ECK | +2.205 |
ILLE | +2.199 |
rol | +2.168 |
Neg logit contributions | |
ities | -3.716 |
ctors | -3.004 |
ifax | -2.883 |
peria | -2.881 |
andro | -2.864 |
Token | comment |
Token ID | 2912 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
picking | +1.968 |
Wester | +1.723 |
ILLE | +1.674 |
ECK | +1.670 |
rol | +1.630 |
Neg logit contributions | |
ities | -3.565 |
ctors | -2.931 |
peria | -2.794 |
ifax | -2.793 |
andro | -2.790 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
ities | +1.961 |
ctors | +1.527 |
ifax | +1.469 |
andro | +1.455 |
peria | +1.438 |
Neg logit contributions | |
picking | -1.595 |
ECK | -1.423 |
Wester | -1.422 |
ILLE | -1.417 |
rol | -1.378 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
picking | +0.170 |
Wester | +0.152 |
ECK | +0.150 |
ILLE | +0.150 |
rol | +0.147 |
Neg logit contributions | |
ities | -0.211 |
ctors | -0.167 |
ifax | -0.158 |
andro | -0.158 |
peria | -0.157 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
picking | +0.301 |
Wester | +0.268 |
ECK | +0.258 |
rol | +0.256 |
ILLE | +0.256 |
Neg logit contributions | |
ities | -0.482 |
ctors | -0.398 |
ifax | -0.386 |
peria | -0.382 |
andro | -0.382 |
Token | Though |
Token ID | 10915 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
picking | +0.080 |
Wester | +0.073 |
ECK | +0.072 |
ILLE | +0.072 |
rol | +0.071 |
Neg logit contributions | |
ities | -0.074 |
ctors | -0.056 |
andro | -0.052 |
ifax | -0.052 |
peria | -0.052 |
Token | deaf |
Token ID | 21815 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
ities | +1.057 |
ctors | +0.848 |
ifax | +0.810 |
andro | +0.801 |
peria | +0.801 |
Neg logit contributions | |
picking | -0.724 |
Wester | -0.632 |
ILLE | -0.625 |
ECK | -0.625 |
rol | -0.609 |
Token | and |
Token ID | 290 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
ities | +9.063 |
ctors | +6.779 |
ifax | +6.540 |
andro | +6.433 |
peria | +6.335 |
Neg logit contributions | |
picking | -8.480 |
Wester | -7.630 |
ECK | -7.603 |
ILLE | -7.493 |
rol | -7.480 |
Token | blind |
Token ID | 7770 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ities | +0.153 |
ctors | +0.120 |
ifax | +0.114 |
andro | +0.113 |
peria | +0.113 |
Neg logit contributions | |
picking | -0.136 |
Wester | -0.123 |
ILLE | -0.121 |
ECK | -0.121 |
rol | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
ities | +3.664 |
ctors | +2.788 |
ifax | +2.664 |
andro | +2.620 |
peria | +2.613 |
Neg logit contributions | |
picking | -3.322 |
Wester | -2.949 |
ECK | -2.940 |
ILLE | -2.922 |
rol | -2.893 |
Token | Helen |
Token ID | 22695 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
picking | +0.085 |
Wester | +0.073 |
ILLE | +0.072 |
ECK | +0.072 |
rol | +0.070 |
Neg logit contributions | |
ities | -0.157 |
ctors | -0.129 |
ifax | -0.124 |
andro | -0.123 |
peria | -0.123 |
Token | Keller |
Token ID | 35999 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
ities | +3.673 |
ctors | +2.981 |
ifax | +2.871 |
andro | +2.858 |
peria | +2.828 |
Neg logit contributions | |
picking | -2.095 |
ILLE | -1.767 |
Wester | -1.755 |
ECK | -1.736 |
rol | -1.709 |
Token | assassination |
Token ID | 18898 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
picking | +1.683 |
Wester | +1.484 |
ECK | +1.451 |
ILLE | +1.451 |
rol | +1.414 |
Neg logit contributions | |
ities | -2.637 |
ctors | -2.140 |
ifax | -2.046 |
andro | -2.038 |
peria | -2.028 |
Token | . |
Token ID | 13 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ities | +0.458 |
ctors | +0.359 |
ifax | +0.338 |
andro | +0.338 |
peria | +0.336 |
Neg logit contributions | |
picking | -0.368 |
Wester | -0.332 |
ECK | -0.331 |
ILLE | -0.330 |
rol | -0.319 |
Token | But |
Token ID | 887 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
ities | +0.916 |
ctors | +0.722 |
andro | +0.680 |
ifax | +0.680 |
peria | +0.674 |
Neg logit contributions | |
picking | -0.759 |
Wester | -0.677 |
ECK | -0.671 |
ILLE | -0.670 |
rol | -0.655 |
Token | he |
Token ID | 339 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
ities | +2.509 |
ctors | +1.978 |
ifax | +1.868 |
andro | +1.865 |
peria | +1.857 |
Neg logit contributions | |
picking | -1.907 |
ECK | -1.702 |
ILLE | -1.697 |
Wester | -1.695 |
rol | -1.639 |
Token | never |
Token ID | 1239 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
picking | +0.193 |
Wester | +0.173 |
ILLE | +0.171 |
ECK | +0.171 |
rol | +0.167 |
Neg logit contributions | |
ities | -0.232 |
ctors | -0.182 |
ifax | -0.172 |
andro | -0.172 |
peria | -0.170 |
Token | forgot |
Token ID | 16453 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
ities | +0.374 |
ctors | +0.296 |
ifax | +0.281 |
andro | +0.280 |
peria | +0.278 |
Neg logit contributions | |
picking | -0.283 |
Wester | -0.252 |
ECK | -0.251 |
ILLE | -0.251 |
rol | -0.243 |
Token | his |
Token ID | 465 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ities | +8.265 |
ctors | +6.154 |
andro | +5.807 |
ifax | +5.717 |
Discipline | +5.658 |
Neg logit contributions | |
picking | -7.191 |
ECK | -6.563 |
ILLE | -6.480 |
rol | -6.337 |
Wester | -6.233 |
Token | goal |
Token ID | 3061 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
picking | +0.814 |
Wester | +0.724 |
ECK | +0.715 |
ILLE | +0.713 |
rol | +0.696 |
Neg logit contributions | |
ities | -1.087 |
ctors | -0.863 |
ifax | -0.821 |
andro | -0.818 |
peria | -0.814 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ities | +0.500 |
ctors | +0.389 |
ifax | +0.368 |
andro | +0.368 |
peria | +0.366 |
Neg logit contributions | |
picking | -0.429 |
ILLE | -0.385 |
Wester | -0.384 |
ECK | -0.383 |
rol | -0.371 |
Token | and |
Token ID | 290 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ities | +0.614 |
ctors | +0.480 |
ifax | +0.456 |
andro | +0.454 |
peria | +0.450 |
Neg logit contributions | |
picking | -0.522 |
Wester | -0.471 |
ILLE | -0.470 |
ECK | -0.468 |
rol | -0.455 |
Token | after |
Token ID | 706 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
picking | +0.671 |
Wester | +0.598 |
ECK | +0.588 |
ILLE | +0.587 |
rol | +0.573 |
Neg logit contributions | |
ities | -0.915 |
ctors | -0.732 |
ifax | -0.696 |
andro | -0.694 |
peria | -0.690 |
Token | keeping |
Token ID | 5291 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
picking | +0.108 |
Wester | +0.096 |
ECK | +0.095 |
ILLE | +0.095 |
rol | +0.093 |
Neg logit contributions | |
ities | -0.142 |
ctors | -0.113 |
ifax | -0.107 |
andro | -0.107 |
peria | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ities | +4.660 |
ctors | +3.657 |
ifax | +3.516 |
peria | +3.457 |
andro | +3.435 |
Neg logit contributions | |
picking | -3.402 |
ECK | -3.018 |
ILLE | -2.985 |
Wester | -2.980 |
rol | -2.926 |
Token | Hair |
Token ID | 23102 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ities | +1.849 |
ctors | +1.456 |
ifax | +1.400 |
andro | +1.394 |
peria | +1.371 |
Neg logit contributions | |
picking | -1.330 |
Wester | -1.163 |
ECK | -1.152 |
ILLE | -1.150 |
rol | -1.126 |
Token | Club |
Token ID | 6289 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
ities | +3.935 |
ctors | +3.038 |
ifax | +2.878 |
andro | +2.860 |
peria | +2.830 |
Neg logit contributions | |
picking | -3.135 |
ILLE | -2.920 |
Wester | -2.893 |
ECK | -2.819 |
SUP | -2.748 |
Token | for |
Token ID | 329 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ities | +1.309 |
ctors | +1.036 |
andro | +0.977 |
ifax | +0.976 |
peria | +0.965 |
Neg logit contributions | |
picking | -1.033 |
Wester | -0.921 |
ILLE | -0.916 |
ECK | -0.915 |
rol | -0.885 |
Token | Growth |
Token ID | 19045 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
picking | +0.989 |
Wester | +0.880 |
ECK | +0.866 |
ILLE | +0.865 |
rol | +0.843 |
Neg logit contributions | |
ities | -1.380 |
ctors | -1.105 |
ifax | -1.051 |
andro | -1.049 |
peria | -1.041 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ities | +8.072 |
ctors | +6.233 |
andro | +5.813 |
ifax | +5.776 |
peria | +5.713 |
Neg logit contributions | |
picking | -6.871 |
Wester | -6.043 |
ILLE | -6.022 |
ECK | -5.972 |
rol | -5.837 |
Token | is |
Token ID | 318 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ities | +4.848 |
ctors | +3.781 |
ifax | +3.474 |
andro | +3.443 |
peria | +3.354 |
Neg logit contributions | |
picking | -4.348 |
ILLE | -3.933 |
Wester | -3.919 |
ECK | -3.897 |
SUP | -3.794 |
Token | more |
Token ID | 517 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
picking | +0.616 |
Wester | +0.546 |
ECK | +0.536 |
ILLE | +0.535 |
rol | +0.522 |
Neg logit contributions | |
ities | -0.916 |
ctors | -0.738 |
ifax | -0.703 |
andro | -0.702 |
peria | -0.698 |
Token | important |
Token ID | 1593 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
picking | +1.740 |
Wester | +1.527 |
ILLE | +1.472 |
ECK | +1.471 |
SUP | +1.445 |
Neg logit contributions | |
ities | -3.197 |
ctors | -2.653 |
ifax | -2.548 |
peria | -2.530 |
andro | -2.528 |
Token | to |
Token ID | 284 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ities | +0.809 |
ctors | +0.627 |
ifax | +0.591 |
andro | +0.590 |
peria | +0.585 |
Neg logit contributions | |
picking | -0.702 |
Wester | -0.629 |
ECK | -0.626 |
ILLE | -0.625 |
rol | -0.608 |
Token | Nuclear |
Token ID | 19229 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
picking | +0.053 |
Wester | +0.047 |
ILLE | +0.046 |
ECK | +0.046 |
rol | +0.045 |
Neg logit contributions | |
ities | -0.073 |
ctors | -0.059 |
ifax | -0.056 |
andro | -0.055 |
peria | -0.055 |
Token | Engineering |
Token ID | 14044 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
picking | +0.571 |
Wester | +0.512 |
ECK | +0.504 |
ILLE | +0.503 |
rol | +0.492 |
Neg logit contributions | |
ities | -0.710 |
ctors | -0.561 |
ifax | -0.532 |
andro | -0.530 |
peria | -0.527 |
Token | at |
Token ID | 379 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
ities | +1.501 |
ctors | +1.173 |
andro | +1.110 |
ifax | +1.106 |
peria | +1.101 |
Neg logit contributions | |
picking | -1.243 |
Wester | -1.108 |
ILLE | -1.104 |
ECK | -1.100 |
rol | -1.064 |
Token | the |
Token ID | 262 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ities | +1.429 |
ctors | +1.137 |
ifax | +1.082 |
andro | +1.081 |
peria | +1.073 |
Neg logit contributions | |
picking | -1.023 |
ILLE | -0.901 |
Wester | -0.895 |
ECK | -0.895 |
rol | -0.866 |
Token | Poly |
Token ID | 12280 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ities | +0.936 |
ctors | +0.742 |
andro | +0.704 |
ifax | +0.703 |
peria | +0.698 |
Neg logit contributions | |
picking | -0.716 |
Wester | -0.631 |
ILLE | -0.628 |
ECK | -0.628 |
rol | -0.610 |
Token | techn |
Token ID | 23873 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ities | +0.573 |
ctors | +0.396 |
andro | +0.362 |
peria | +0.359 |
ifax | +0.357 |
Neg logit contributions | |
picking | -0.954 |
Wester | -0.886 |
ILLE | -0.881 |
ECK | -0.879 |
SUP | -0.861 |
Token | ic |
Token ID | 291 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ities | +5.917 |
ctors | +3.807 |
andro | +3.689 |
ifax | +3.442 |
peria | +3.377 |
Neg logit contributions | |
picking | -9.127 |
ILLE | -8.506 |
ECK | -8.431 |
Wester | -8.429 |
SUP | -8.401 |
Token | University |
Token ID | 2059 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
ities | +0.781 |
ctors | +0.618 |
ifax | +0.585 |
andro | +0.585 |
peria | +0.581 |
Neg logit contributions | |
picking | -0.621 |
Wester | -0.555 |
ECK | -0.547 |
ILLE | -0.546 |
rol | -0.533 |
Token | of |
Token ID | 286 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
picking | +0.180 |
Wester | +0.159 |
ECK | +0.158 |
ILLE | +0.158 |
SUP | +0.153 |
Neg logit contributions | |
ities | -0.234 |
ctors | -0.185 |
ifax | -0.175 |
andro | -0.175 |
peria | -0.175 |
Token | Barcelona |
Token ID | 15142 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
ities | +0.343 |
ctors | +0.275 |
andro | +0.262 |
ifax | +0.261 |
peria | +0.260 |
Neg logit contributions | |
picking | -0.239 |
Wester | -0.209 |
ECK | -0.209 |
ILLE | -0.208 |
rol | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ities | +2.453 |
ctors | +1.903 |
andro | +1.806 |
peria | +1.801 |
ifax | +1.792 |
Neg logit contributions | |
picking | -2.131 |
ILLE | -1.894 |
ECK | -1.888 |
Wester | -1.887 |
SUP | -1.841 |
Token | � |
Token ID | 251 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
picking | +0.851 |
Wester | +0.774 |
ILLE | +0.762 |
ECK | +0.761 |
rol | +0.746 |
Neg logit contributions | |
ities | -0.823 |
ctors | -0.628 |
ifax | -0.590 |
andro | -0.589 |
peria | -0.583 |
Token | don |
Token ID | 836 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
picking | +0.698 |
Wester | +0.624 |
ILLE | +0.614 |
ECK | +0.613 |
rol | +0.599 |
Neg logit contributions | |
ities | -0.936 |
ctors | -0.746 |
ifax | -0.708 |
andro | -0.707 |
peria | -0.702 |
Token | � |
Token ID | 447 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
ities | +0.860 |
ctors | +0.659 |
ifax | +0.626 |
peria | +0.619 |
andro | +0.617 |
Neg logit contributions | |
picking | -0.920 |
Wester | -0.838 |
ECK | -0.829 |
ILLE | -0.822 |
rol | -0.816 |
Token | � |
Token ID | 247 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
picking | +1.279 |
Wester | +1.141 |
ECK | +1.140 |
ILLE | +1.133 |
rol | +1.115 |
Neg logit contributions | |
ities | -1.749 |
ctors | -1.407 |
ifax | -1.339 |
peria | -1.330 |
andro | -1.318 |
Token | t |
Token ID | 83 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
picking | +0.436 |
Wester | +0.388 |
ILLE | +0.381 |
ECK | +0.380 |
rol | +0.369 |
Neg logit contributions | |
ities | -0.647 |
ctors | -0.521 |
ifax | -0.496 |
andro | -0.495 |
peria | -0.490 |
Token | forget |
Token ID | 6044 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
picking | +2.359 |
Wester | +2.138 |
ECK | +2.059 |
SUP | +2.049 |
rol | +2.042 |
Neg logit contributions | |
ities | -3.012 |
ctors | -2.416 |
ifax | -2.317 |
andro | -2.313 |
peria | -2.309 |
Token | to |
Token ID | 284 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
ities | +7.603 |
ctors | +5.868 |
ifax | +5.541 |
peria | +5.385 |
andro | +5.361 |
Neg logit contributions | |
picking | -6.671 |
ILLE | -5.951 |
ECK | -5.883 |
Wester | -5.729 |
rol | -5.692 |
Token | ask |
Token ID | 1265 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
ities | +1.383 |
ctors | +1.087 |
ifax | +1.021 |
andro | +1.019 |
peria | +1.013 |
Neg logit contributions | |
picking | -1.161 |
Wester | -1.036 |
ILLE | -1.030 |
ECK | -1.022 |
rol | -0.997 |
Token | your |
Token ID | 534 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
ities | +2.833 |
ctors | +2.234 |
ifax | +2.144 |
andro | +2.125 |
peria | +2.094 |
Neg logit contributions | |
picking | -2.045 |
ILLE | -1.766 |
ECK | -1.759 |
Wester | -1.755 |
rol | -1.711 |
Token | husband |
Token ID | 5229 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ities | +0.277 |
ctors | +0.220 |
ifax | +0.209 |
andro | +0.209 |
peria | +0.206 |
Neg logit contributions | |
picking | -0.207 |
Wester | -0.183 |
ECK | -0.182 |
ILLE | -0.181 |
rol | -0.177 |
Token | before |
Token ID | 878 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
picking | +1.011 |
Wester | +0.903 |
ECK | +0.889 |
ILLE | +0.888 |
rol | +0.867 |
Neg logit contributions | |
ities | -1.314 |
ctors | -1.044 |
ifax | -0.991 |
andro | -0.988 |
peria | -0.982 |
Token | Trans |
Token ID | 3602 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ities | +0.706 |
ctors | +0.555 |
ifax | +0.526 |
andro | +0.523 |
peria | +0.519 |
Neg logit contributions | |
picking | -0.583 |
Wester | -0.521 |
ECK | -0.516 |
ILLE | -0.515 |
rol | -0.503 |
Token | atlantic |
Token ID | 43342 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ities | +2.620 |
ctors | +1.990 |
ifax | +1.841 |
peria | +1.822 |
andro | +1.818 |
Neg logit contributions | |
picking | -2.757 |
ILLE | -2.562 |
ECK | -2.527 |
Wester | -2.524 |
SUP | -2.435 |
Token | Trade |
Token ID | 9601 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ities | +2.623 |
ctors | +1.786 |
ifax | +1.589 |
andro | +1.571 |
peria | +1.500 |
Neg logit contributions | |
picking | -4.393 |
ECK | -4.054 |
Wester | -4.053 |
ILLE | -4.020 |
SUP | -3.935 |
Token | and |
Token ID | 290 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ities | +4.970 |
ctors | +3.794 |
andro | +3.624 |
ifax | +3.514 |
peria | +3.508 |
Neg logit contributions | |
picking | -4.733 |
ECK | -4.277 |
Wester | -4.263 |
ILLE | -4.239 |
SUP | -4.117 |
Token | Investment |
Token ID | 20877 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
ities | +1.330 |
ctors | +1.040 |
andro | +0.984 |
peria | +0.971 |
ifax | +0.970 |
Neg logit contributions | |
picking | -1.150 |
Wester | -1.032 |
ILLE | -1.029 |
ECK | -1.023 |
SUP | -0.988 |
Token | Partnership |
Token ID | 23270 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
ities | +1.358 |
ctors | +0.968 |
andro | +0.888 |
ifax | +0.886 |
peria | +0.876 |
Neg logit contributions | |
picking | -2.015 |
Wester | -1.856 |
ECK | -1.838 |
ILLE | -1.836 |
rol | -1.805 |
Token | is |
Token ID | 318 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ities | +7.239 |
ctors | +5.577 |
ifax | +5.143 |
andro | +5.137 |
peria | +4.978 |
Neg logit contributions | |
picking | -6.958 |
ECK | -6.219 |
Wester | -6.193 |
ILLE | -6.131 |
rol | -6.060 |
Token | a |
Token ID | 257 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
ities | +0.732 |
ctors | +0.586 |
ifax | +0.556 |
andro | +0.554 |
peria | +0.550 |
Neg logit contributions | |
picking | -0.523 |
Wester | -0.464 |
ECK | -0.459 |
ILLE | -0.458 |
rol | -0.448 |
Token | series |
Token ID | 2168 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ities | +1.777 |
ctors | +1.415 |
ifax | +1.338 |
andro | +1.332 |
peria | +1.323 |
Neg logit contributions | |
picking | -1.353 |
Wester | -1.199 |
ECK | -1.190 |
ILLE | -1.187 |
rol | -1.161 |
Token | of |
Token ID | 286 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
picking | +0.552 |
Wester | +0.493 |
ECK | +0.468 |
ILLE | +0.467 |
SUP | +0.466 |
Neg logit contributions | |
ities | -0.879 |
ctors | -0.719 |
ifax | -0.690 |
andro | -0.689 |
peria | -0.686 |
Token | trade |
Token ID | 3292 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ities | +0.236 |
ctors | +0.186 |
ifax | +0.176 |
andro | +0.175 |
peria | +0.174 |
Neg logit contributions | |
picking | -0.200 |
Wester | -0.180 |
ECK | -0.177 |
ILLE | -0.177 |
rol | -0.173 |
Token | gow |
Token ID | 21175 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
picking | +5.240 |
Wester | +4.862 |
rol | +4.782 |
rail | +4.746 |
bane | +4.646 |
Neg logit contributions | |
ities | -3.037 |
ctors | -2.299 |
ifax | -2.078 |
peria | -2.046 |
andro | -1.949 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ities | +1.182 |
ctors | +0.954 |
ifax | +0.917 |
peria | +0.909 |
andro | +0.909 |
Neg logit contributions | |
picking | -0.801 |
Wester | -0.722 |
ECK | -0.699 |
ILLE | -0.696 |
SUP | -0.690 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
picking | +0.456 |
Wester | +0.406 |
ECK | +0.388 |
rol | +0.385 |
SUP | +0.385 |
Neg logit contributions | |
ities | -0.746 |
ctors | -0.621 |
ifax | -0.605 |
peria | -0.599 |
andro | -0.594 |
Token | 2001 |
Token ID | 14585 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
picking | +0.074 |
Wester | +0.066 |
ECK | +0.065 |
ILLE | +0.065 |
rol | +0.063 |
Neg logit contributions | |
ities | -0.097 |
ctors | -0.078 |
ifax | -0.074 |
peria | -0.073 |
andro | -0.073 |
Token | Frankie |
Token ID | 48535 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
picking | +0.043 |
Wester | +0.038 |
ILLE | +0.037 |
ECK | +0.037 |
rol | +0.036 |
Neg logit contributions | |
ities | -0.059 |
ctors | -0.047 |
andro | -0.045 |
ifax | -0.045 |
peria | -0.045 |
Token | Mun |
Token ID | 12107 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
ities | +0.384 |
ctors | +0.310 |
andro | +0.294 |
ifax | +0.293 |
peria | +0.290 |
Neg logit contributions | |
picking | -0.267 |
ECK | -0.235 |
ILLE | -0.233 |
Wester | -0.232 |
rol | -0.227 |
Token | iz |
Token ID | 528 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ities | +5.446 |
ctors | +3.880 |
andro | +3.697 |
ifax | +3.532 |
peria | +3.285 |
Neg logit contributions | |
picking | -8.704 |
Wester | -8.166 |
ILLE | -8.156 |
ECK | -8.103 |
GOODMAN | -7.892 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
picking | +0.731 |
Wester | +0.650 |
ECK | +0.640 |
ILLE | +0.639 |
rol | +0.624 |
Neg logit contributions | |
ities | -0.993 |
ctors | -0.794 |
andro | -0.754 |
ifax | -0.754 |
peria | -0.746 |
Token |
|
Token ID | 198 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
picking | +0.456 |
Wester | +0.406 |
ECK | +0.388 |
rol | +0.385 |
SUP | +0.384 |
Neg logit contributions | |
ities | -0.743 |
ctors | -0.618 |
ifax | -0.600 |
peria | -0.593 |
andro | -0.590 |
Token | 2001 |
Token ID | 14585 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
picking | +0.060 |
Wester | +0.054 |
ECK | +0.053 |
ILLE | +0.053 |
rol | +0.052 |
Neg logit contributions | |
ities | -0.076 |
ctors | -0.060 |
ifax | -0.057 |
peria | -0.057 |
andro | -0.057 |
Token | Ray |
Token ID | 7760 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
picking | +0.043 |
Wester | +0.038 |
ILLE | +0.037 |
ECK | +0.037 |
rol | +0.036 |
Neg logit contributions | |
ities | -0.061 |
ctors | -0.048 |
andro | -0.046 |
ifax | -0.046 |
peria | -0.046 |
Token | ( |
Token ID | 357 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
picking | +1.376 |
Wester | +1.234 |
ECK | +1.215 |
ILLE | +1.213 |
rol | +1.186 |
Neg logit contributions | |
ities | -1.706 |
ctors | -1.349 |
ifax | -1.279 |
andro | -1.276 |
peria | -1.268 |
Token | don |
Token ID | 9099 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ities | +0.935 |
ctors | +0.700 |
andro | +0.654 |
peria | +0.641 |
ifax | +0.640 |
Neg logit contributions | |
picking | -1.112 |
Wester | -1.031 |
ILLE | -1.016 |
ECK | -1.016 |
rol | -0.991 |
Token | � |
Token ID | 447 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ities | +4.159 |
ctors | +3.319 |
andro | +3.089 |
ifax | +3.062 |
peria | +2.998 |
Neg logit contributions | |
picking | -3.167 |
Wester | -2.857 |
ILLE | -2.819 |
ECK | -2.754 |
SUP | -2.714 |
Token | � |
Token ID | 247 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ities | +0.359 |
ctors | +0.292 |
ifax | +0.279 |
peria | +0.277 |
andro | +0.276 |
Neg logit contributions | |
picking | -0.229 |
Wester | -0.203 |
ECK | -0.201 |
ILLE | -0.200 |
rol | -0.196 |
Token | t |
Token ID | 83 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
picking | +0.023 |
Wester | +0.020 |
ILLE | +0.020 |
ECK | +0.020 |
rol | +0.019 |
Neg logit contributions | |
ities | -0.033 |
ctors | -0.027 |
ifax | -0.025 |
andro | -0.025 |
peria | -0.025 |
Token | forget |
Token ID | 6044 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
picking | +1.644 |
Wester | +1.488 |
ECK | +1.453 |
ILLE | +1.452 |
SUP | +1.434 |
Neg logit contributions | |
ities | -1.957 |
ctors | -1.548 |
ifax | -1.481 |
andro | -1.477 |
peria | -1.463 |
Token | to |
Token ID | 284 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ities | +7.400 |
ctors | +5.771 |
ifax | +5.198 |
peria | +5.189 |
andro | +5.137 |
Neg logit contributions | |
picking | -6.842 |
ECK | -6.075 |
ILLE | -6.012 |
Wester | -5.979 |
rol | -5.820 |
Token | also |
Token ID | 635 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
ities | +1.633 |
ctors | +1.281 |
ifax | +1.203 |
andro | +1.202 |
peria | +1.197 |
Neg logit contributions | |
picking | -1.379 |
Wester | -1.228 |
ILLE | -1.219 |
ECK | -1.217 |
rol | -1.187 |
Token | add |
Token ID | 751 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ities | +1.960 |
ctors | +1.536 |
andro | +1.436 |
ifax | +1.433 |
peria | +1.429 |
Neg logit contributions | |
picking | -1.638 |
Wester | -1.454 |
ECK | -1.451 |
ILLE | -1.449 |
rol | -1.407 |
Token | their |
Token ID | 511 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
ities | +0.954 |
ctors | +0.759 |
peria | +0.712 |
ifax | +0.712 |
andro | +0.711 |
Neg logit contributions | |
picking | -0.717 |
Wester | -0.634 |
ECK | -0.628 |
ILLE | -0.628 |
rol | -0.610 |
Token | respective |
Token ID | 11756 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
ities | +0.009 |
ctors | +0.008 |
ifax | +0.007 |
andro | +0.007 |
peria | +0.007 |
Neg logit contributions | |
picking | -0.007 |
Wester | -0.006 |
ECK | -0.006 |
ILLE | -0.006 |
rol | -0.006 |
Token | let |
Token ID | 1309 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
picking | +0.330 |
Wester | +0.290 |
ILLE | +0.287 |
ECK | +0.287 |
rol | +0.277 |
Neg logit contributions | |
ities | -0.501 |
ctors | -0.404 |
ifax | -0.385 |
andro | -0.384 |
peria | -0.382 |
Token | � |
Token ID | 447 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
ities | +0.728 |
ctors | +0.575 |
ifax | +0.544 |
andro | +0.544 |
peria | +0.533 |
Neg logit contributions | |
picking | -0.572 |
ECK | -0.507 |
Wester | -0.506 |
ILLE | -0.503 |
SUP | -0.488 |
Token | � |
Token ID | 247 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
picking | +0.747 |
ECK | +0.664 |
Wester | +0.662 |
ILLE | +0.662 |
rol | +0.651 |
Neg logit contributions | |
ities | -1.162 |
ctors | -0.949 |
ifax | -0.902 |
peria | -0.896 |
andro | -0.891 |
Token | s |
Token ID | 82 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
picking | +0.146 |
Wester | +0.133 |
ECK | +0.131 |
ILLE | +0.130 |
SUP | +0.128 |
Neg logit contributions | |
ities | -0.146 |
ctors | -0.112 |
andro | -0.105 |
ifax | -0.105 |
peria | -0.104 |
Token | not |
Token ID | 407 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ities | +1.158 |
ctors | +0.926 |
andro | +0.869 |
peria | +0.863 |
ifax | +0.861 |
Neg logit contributions | |
picking | -0.890 |
Wester | -0.789 |
ECK | -0.784 |
ILLE | -0.781 |
rol | -0.755 |
Token | forget |
Token ID | 6044 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
picking | +0.702 |
Wester | +0.634 |
ECK | +0.623 |
ILLE | +0.622 |
rol | +0.611 |
Neg logit contributions | |
ities | -0.790 |
ctors | -0.618 |
ifax | -0.585 |
andro | -0.583 |
peria | -0.579 |
Token | …. |
Token ID | 11580 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
ities | +7.623 |
ctors | +5.969 |
ifax | +5.664 |
andro | +5.578 |
peria | +5.561 |
Neg logit contributions | |
picking | -6.335 |
ECK | -5.546 |
ILLE | -5.543 |
Wester | -5.460 |
rol | -5.255 |
Token | MY |
Token ID | 17615 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ities | +0.118 |
ctors | +0.093 |
andro | +0.088 |
ifax | +0.088 |
peria | +0.087 |
Neg logit contributions | |
picking | -0.098 |
Wester | -0.089 |
ECK | -0.087 |
ILLE | -0.087 |
rol | -0.085 |
Token | HA |
Token ID | 14558 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ities | +0.611 |
ctors | +0.484 |
ifax | +0.460 |
andro | +0.458 |
peria | +0.456 |
Neg logit contributions | |
picking | -0.468 |
Wester | -0.417 |
ECK | -0.407 |
ILLE | -0.406 |
rol | -0.400 |
Token | IR |
Token ID | 4663 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
picking | +0.211 |
Wester | +0.184 |
ILLE | +0.179 |
ECK | +0.179 |
rol | +0.177 |
Neg logit contributions | |
ities | -0.321 |
ctors | -0.259 |
ifax | -0.247 |
andro | -0.244 |
peria | -0.244 |
Token | . |
Token ID | 13 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ities | +1.676 |
ctors | +1.325 |
ifax | +1.256 |
andro | +1.252 |
peria | +1.241 |
Neg logit contributions | |
picking | -1.315 |
Wester | -1.180 |
ILLE | -1.142 |
ECK | -1.139 |
rol | -1.129 |
Token | . |
Token ID | 13 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
ities | +0.661 |
ctors | +0.522 |
andro | +0.493 |
ifax | +0.492 |
peria | +0.487 |
Neg logit contributions | |
picking | -0.536 |
Wester | -0.478 |
ECK | -0.474 |
ILLE | -0.474 |
rol | -0.460 |
Token | Don |
Token ID | 2094 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
picking | +0.010 |
Wester | +0.009 |
ECK | +0.008 |
ILLE | +0.008 |
rol | +0.008 |
Neg logit contributions | |
ities | -0.012 |
ctors | -0.010 |
ifax | -0.009 |
andro | -0.009 |
peria | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ities | +1.453 |
ctors | +1.026 |
andro | +0.926 |
ifax | +0.925 |
peria | +0.907 |
Neg logit contributions | |
picking | -2.204 |
Wester | -2.023 |
ILLE | -2.022 |
ECK | -2.009 |
SUP | -1.982 |
Token | � |
Token ID | 247 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
picking | +0.806 |
Wester | +0.729 |
ECK | +0.722 |
ILLE | +0.721 |
rol | +0.709 |
Neg logit contributions | |
ities | -0.873 |
ctors | -0.680 |
ifax | -0.642 |
andro | -0.637 |
peria | -0.636 |
Token | t |
Token ID | 83 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
picking | +0.793 |
Wester | +0.717 |
ECK | +0.707 |
ILLE | +0.705 |
rol | +0.693 |
Neg logit contributions | |
ities | -0.846 |
ctors | -0.657 |
ifax | -0.621 |
andro | -0.619 |
peria | -0.616 |
Token | forget |
Token ID | 6044 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
picking | +2.591 |
Wester | +2.358 |
ECK | +2.282 |
ILLE | +2.270 |
rol | +2.253 |
Neg logit contributions | |
ities | -3.149 |
ctors | -2.490 |
ifax | -2.397 |
andro | -2.396 |
peria | -2.373 |
Token | that |
Token ID | 326 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
ities | +7.232 |
ctors | +5.611 |
ifax | +5.190 |
peria | +5.177 |
andro | +5.025 |
Neg logit contributions | |
picking | -6.805 |
ILLE | -6.001 |
ECK | -5.951 |
Wester | -5.810 |
rol | -5.758 |
Token | we |
Token ID | 356 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
ities | +1.151 |
ctors | +0.916 |
ifax | +0.867 |
andro | +0.859 |
peria | +0.858 |
Neg logit contributions | |
picking | -0.816 |
ECK | -0.715 |
ILLE | -0.715 |
Wester | -0.713 |
rol | -0.692 |
Token | do |
Token ID | 466 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ities | +0.107 |
ctors | +0.084 |
ifax | +0.079 |
andro | +0.078 |
peria | +0.078 |
Neg logit contributions | |
picking | -0.092 |
Wester | -0.081 |
ILLE | -0.081 |
ECK | -0.081 |
rol | -0.078 |
Token | not |
Token ID | 407 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
picking | +0.561 |
Wester | +0.495 |
ECK | +0.492 |
ILLE | +0.491 |
rol | +0.477 |
Neg logit contributions | |
ities | -0.747 |
ctors | -0.599 |
andro | -0.563 |
ifax | -0.562 |
peria | -0.558 |
Token | even |
Token ID | 772 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
picking | +1.108 |
Wester | +0.998 |
ECK | +0.974 |
ILLE | +0.969 |
SUP | +0.957 |
Neg logit contributions | |
ities | -1.439 |
ctors | -1.144 |
ifax | -1.096 |
andro | -1.094 |
peria | -1.089 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
picking | +0.489 |
Wester | +0.434 |
ECK | +0.419 |
ILLE | +0.414 |
rol | +0.413 |
Neg logit contributions | |
ities | -0.785 |
ctors | -0.650 |
ifax | -0.633 |
peria | -0.627 |
andro | -0.624 |
Token | Ven |
Token ID | 37522 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
picking | +0.065 |
Wester | +0.059 |
ECK | +0.058 |
ILLE | +0.058 |
SUP | +0.057 |
Neg logit contributions | |
ities | -0.066 |
ctors | -0.050 |
andro | -0.047 |
peria | -0.047 |
ifax | -0.047 |
Token | ue |
Token ID | 518 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
picking | +2.793 |
Wester | +2.559 |
ILLE | +2.510 |
ECK | +2.509 |
rol | +2.491 |
Neg logit contributions | |
ities | -2.418 |
ctors | -1.833 |
ifax | -1.721 |
andro | -1.706 |
peria | -1.689 |
Token | : |
Token ID | 25 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
picking | +1.264 |
Wester | +1.137 |
ECK | +1.121 |
ILLE | +1.119 |
rol | +1.096 |
Neg logit contributions | |
ities | -1.466 |
ctors | -1.149 |
ifax | -1.087 |
andro | -1.083 |
peria | -1.077 |
Token | Poly |
Token ID | 12280 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
ities | +0.445 |
ctors | +0.355 |
andro | +0.338 |
ifax | +0.338 |
peria | +0.335 |
Neg logit contributions | |
picking | -0.309 |
Wester | -0.269 |
ILLE | -0.268 |
ECK | -0.267 |
rol | -0.261 |
Token | techn |
Token ID | 23873 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ities | +2.865 |
ctors | +2.279 |
andro | +2.205 |
ifax | +2.186 |
peria | +2.175 |
Neg logit contributions | |
picking | -1.780 |
Wester | -1.559 |
ILLE | -1.543 |
ECK | -1.530 |
rol | -1.492 |
Token | ic |
Token ID | 291 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ities | +6.005 |
ctors | +4.014 |
andro | +3.848 |
ifax | +3.747 |
peria | +3.594 |
Neg logit contributions | |
picking | -8.251 |
ECK | -7.506 |
ILLE | -7.501 |
Wester | -7.444 |
SUP | -7.382 |
Token | University |
Token ID | 2059 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
ities | +0.626 |
ctors | +0.496 |
ifax | +0.471 |
andro | +0.471 |
peria | +0.467 |
Neg logit contributions | |
picking | -0.468 |
Wester | -0.415 |
ILLE | -0.409 |
ECK | -0.409 |
rol | -0.398 |
Token | , |
Token ID | 11 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
ities | +1.414 |
ctors | +1.104 |
andro | +1.039 |
ifax | +1.039 |
peria | +1.033 |
Neg logit contributions | |
picking | -1.149 |
Wester | -1.005 |
ECK | -1.004 |
ILLE | -1.001 |
rol | -0.972 |
Token | Hung |
Token ID | 12149 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ities | +0.236 |
ctors | +0.188 |
ifax | +0.179 |
andro | +0.179 |
peria | +0.177 |
Neg logit contributions | |
picking | -0.170 |
Wester | -0.149 |
ILLE | -0.149 |
ECK | -0.149 |
rol | -0.144 |
Token | Hom |
Token ID | 8074 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ities | +3.876 |
ctors | +3.005 |
ifax | +2.918 |
andro | +2.855 |
peria | +2.791 |
Neg logit contributions | |
picking | -3.290 |
ECK | -2.967 |
ILLE | -2.948 |
Wester | -2.911 |
rol | -2.870 |
Token | competitors |
Token ID | 13861 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ities | +0.006 |
ctors | +0.005 |
ifax | +0.004 |
andro | +0.004 |
peria | +0.004 |
Neg logit contributions | |
picking | -0.004 |
Wester | -0.003 |
ECK | -0.003 |
ILLE | -0.003 |
rol | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
ities | +1.557 |
ctors | +1.220 |
ifax | +1.170 |
peria | +1.163 |
andro | +1.163 |
Neg logit contributions | |
picking | -1.143 |
ILLE | -1.026 |
Wester | -1.013 |
ECK | -1.012 |
rol | -0.978 |
Token | Even |
Token ID | 3412 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
ities | +0.091 |
ctors | +0.072 |
ifax | +0.068 |
andro | +0.068 |
peria | +0.068 |
Neg logit contributions | |
picking | -0.077 |
Wester | -0.070 |
ECK | -0.069 |
ILLE | -0.068 |
SUP | -0.067 |
Token | Chairman |
Token ID | 12787 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ities | +2.820 |
ctors | +2.237 |
andro | +2.114 |
ifax | +2.113 |
peria | +2.095 |
Neg logit contributions | |
picking | -2.076 |
ILLE | -1.847 |
ECK | -1.840 |
Wester | -1.824 |
rol | -1.771 |
Token | Bill |
Token ID | 3941 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
ities | +0.358 |
ctors | +0.290 |
ifax | +0.277 |
andro | +0.276 |
peria | +0.275 |
Neg logit contributions | |
picking | -0.228 |
Wester | -0.201 |
ECK | -0.197 |
ILLE | -0.196 |
rol | -0.192 |
Token | Gates |
Token ID | 15953 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
ities | +1.315 |
ctors | +1.001 |
ifax | +0.938 |
andro | +0.934 |
peria | +0.929 |
Neg logit contributions | |
picking | -1.410 |
Wester | -1.287 |
ECK | -1.267 |
ILLE | -1.264 |
rol | -1.244 |
Token | said |
Token ID | 531 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
ities | +7.308 |
ctors | +5.529 |
andro | +5.369 |
ifax | +5.266 |
peria | +5.054 |
Neg logit contributions | |
picking | -6.396 |
ILLE | -5.885 |
Wester | -5.784 |
ECK | -5.746 |
amera | -5.530 |
Token | this |
Token ID | 428 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
ities | +0.160 |
ctors | +0.127 |
ifax | +0.121 |
andro | +0.120 |
peria | +0.120 |
Neg logit contributions | |
picking | -0.121 |
Wester | -0.108 |
ECK | -0.107 |
ILLE | -0.107 |
rol | -0.104 |
Token | week |
Token ID | 1285 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ities | +0.146 |
ctors | +0.113 |
ifax | +0.106 |
andro | +0.106 |
peria | +0.105 |
Neg logit contributions | |
picking | -0.139 |
Wester | -0.126 |
ECK | -0.124 |
ILLE | -0.124 |
rol | -0.121 |
Token | that |
Token ID | 326 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ities | +1.010 |
ctors | +0.797 |
ifax | +0.757 |
andro | +0.756 |
peria | +0.749 |
Neg logit contributions | |
picking | -0.781 |
Wester | -0.693 |
ILLE | -0.691 |
ECK | -0.688 |
rol | -0.670 |
Token | he |
Token ID | 339 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ities | +0.892 |
ctors | +0.708 |
ifax | +0.673 |
andro | +0.672 |
peria | +0.667 |
Neg logit contributions | |
picking | -0.669 |
Wester | -0.595 |
ILLE | -0.589 |
ECK | -0.589 |
rol | -0.574 |
Token | and |
Token ID | 290 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ities | +0.981 |
ctors | +0.762 |
andro | +0.723 |
ifax | +0.720 |
peria | +0.710 |
Neg logit contributions | |
picking | -0.860 |
Wester | -0.772 |
ECK | -0.766 |
ILLE | -0.766 |
rol | -0.747 |
Token | other |
Token ID | 584 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ities | +0.788 |
ctors | +0.630 |
andro | +0.599 |
ifax | +0.595 |
peria | +0.590 |
Neg logit contributions | |
picking | -0.558 |
Wester | -0.494 |
ECK | -0.489 |
ILLE | -0.487 |
rol | -0.475 |
Token | gender |
Token ID | 5279 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
picking | +1.055 |
Wester | +0.942 |
ECK | +0.924 |
ILLE | +0.924 |
rol | +0.902 |
Neg logit contributions | |
ities | -1.430 |
ctors | -1.146 |
ifax | -1.091 |
andro | -1.086 |
peria | -1.084 |
Token | non |
Token ID | 1729 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ities | +2.333 |
ctors | +1.832 |
andro | +1.750 |
ifax | +1.729 |
peria | +1.702 |
Neg logit contributions | |
picking | -1.702 |
Wester | -1.511 |
ECK | -1.500 |
ILLE | -1.492 |
rol | -1.445 |
Token | con |
Token ID | 1102 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
picking | +0.345 |
Wester | +0.311 |
ECK | +0.307 |
ILLE | +0.307 |
SUP | +0.299 |
Neg logit contributions | |
ities | -0.403 |
ctors | -0.316 |
andro | -0.299 |
ifax | -0.298 |
peria | -0.294 |
Token | forming |
Token ID | 15464 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
ities | +4.530 |
ctors | +3.556 |
andro | +3.349 |
ifax | +3.311 |
fen | +3.172 |
Neg logit contributions | |
picking | -3.537 |
ILLE | -3.355 |
Wester | -3.266 |
ECK | -3.255 |
SUP | -3.120 |
Token | ( |
Token ID | 357 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ities | +7.872 |
ctors | +5.790 |
andro | +5.473 |
ifax | +5.354 |
peria | +5.112 |
Neg logit contributions | |
picking | -6.447 |
ECK | -5.666 |
ILLE | -5.632 |
Wester | -5.531 |
rail | -5.422 |
Token | G |
Token ID | 38 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ities | +0.991 |
ctors | +0.753 |
andro | +0.721 |
ifax | +0.705 |
peria | +0.697 |
Neg logit contributions | |
picking | -1.007 |
Wester | -0.927 |
ECK | -0.905 |
ILLE | -0.905 |
rol | -0.888 |
Token | NC |
Token ID | 7792 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ities | +1.326 |
ctors | +1.032 |
andro | +0.987 |
ifax | +0.977 |
peria | +0.973 |
Neg logit contributions | |
picking | -1.101 |
Wester | -0.987 |
ECK | -0.963 |
ILLE | -0.959 |
SUP | -0.945 |
Token | ) |
Token ID | 8 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
picking | +1.273 |
Wester | +1.160 |
ILLE | +1.144 |
ECK | +1.144 |
rol | +1.122 |
Neg logit contributions | |
ities | -1.181 |
ctors | -0.899 |
ifax | -0.844 |
andro | -0.841 |
peria | -0.839 |
Token | people |
Token ID | 661 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
picking | +0.233 |
Wester | +0.207 |
ECK | +0.203 |
ILLE | +0.203 |
rol | +0.198 |
Neg logit contributions | |
ities | -0.331 |
ctors | -0.266 |
ifax | -0.253 |
andro | -0.252 |
peria | -0.251 |
Token | ; |
Token ID | 26 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
picking | +1.244 |
Wester | +1.117 |
ECK | +1.099 |
ILLE | +1.097 |
rol | +1.074 |
Neg logit contributions | |
ities | -1.507 |
ctors | -1.188 |
ifax | -1.126 |
andro | -1.123 |
peria | -1.117 |
Token | not |
Token ID | 407 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
picking | +0.562 |
Wester | +0.495 |
ECK | +0.487 |
ILLE | +0.487 |
rol | +0.474 |
Neg logit contributions | |
ities | -0.892 |
ctors | -0.723 |
ifax | -0.689 |
andro | -0.689 |
peria | -0.684 |
Token | � |
Token ID | 564 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
ities | +0.980 |
ctors | +0.786 |
ifax | +0.750 |
andro | +0.748 |
peria | +0.740 |
Neg logit contributions | |
picking | -0.662 |
Wester | -0.586 |
ECK | -0.580 |
ILLE | -0.578 |
rol | -0.563 |
Token | � |
Token ID | 250 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
picking | +1.765 |
Wester | +1.607 |
ECK | +1.585 |
ILLE | +1.583 |
rol | +1.553 |
Neg logit contributions | |
ities | -1.666 |
ctors | -1.268 |
ifax | -1.192 |
andro | -1.188 |
peria | -1.178 |
Token | diff |
Token ID | 26069 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
picking | +1.278 |
Wester | +1.158 |
ECK | +1.140 |
ILLE | +1.137 |
rol | +1.113 |
Neg logit contributions | |
ities | -1.403 |
ctors | -1.094 |
andro | -1.031 |
ifax | -1.030 |
peria | -1.021 |
Token | icult |
Token ID | 2249 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ities | +4.324 |
ctors | +3.104 |
ifax | +2.929 |
andro | +2.922 |
peria | +2.822 |
Neg logit contributions | |
picking | -5.309 |
ECK | -4.915 |
Wester | -4.898 |
ILLE | -4.892 |
SUP | -4.794 |
Token | , |
Token ID | 11 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
ities | +7.201 |
ctors | +5.483 |
ifax | +5.120 |
andro | +5.074 |
peria | +4.889 |
Neg logit contributions | |
picking | -6.450 |
ECK | -5.914 |
ILLE | -5.869 |
Wester | -5.819 |
SUP | -5.666 |
Token | � |
Token ID | 447 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
picking | +0.200 |
Wester | +0.181 |
ECK | +0.180 |
ILLE | +0.179 |
rol | +0.175 |
Neg logit contributions | |
ities | -0.204 |
ctors | -0.157 |
andro | -0.148 |
ifax | -0.147 |
peria | -0.145 |
Token | � |
Token ID | 251 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ities | +0.456 |
ctors | +0.370 |
ifax | +0.352 |
peria | +0.349 |
andro | +0.348 |
Neg logit contributions | |
picking | -0.303 |
Wester | -0.268 |
ECK | -0.264 |
ILLE | -0.262 |
rol | -0.257 |
Token | but |
Token ID | 475 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
picking | +1.010 |
Wester | +0.925 |
ILLE | +0.912 |
ECK | +0.912 |
rol | +0.895 |
Neg logit contributions | |
ities | -0.899 |
ctors | -0.677 |
andro | -0.634 |
ifax | -0.631 |
peria | -0.626 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ities | +3.612 |
ctors | +2.880 |
andro | +2.766 |
ifax | +2.718 |
peria | +2.696 |
Neg logit contributions | |
picking | -2.434 |
Wester | -2.153 |
ILLE | -2.141 |
ECK | -2.134 |
rol | -2.073 |
Token | е |
Token ID | 16843 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ities | +2.122 |
ctors | +1.547 |
ifax | +1.458 |
andro | +1.448 |
peria | +1.425 |
Neg logit contributions | |
picking | -2.552 |
Wester | -2.339 |
ILLE | -2.324 |
ECK | -2.288 |
rol | -2.248 |
Token | л |
Token ID | 30143 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ities | +0.896 |
ctors | +0.711 |
ifax | +0.673 |
andro | +0.671 |
peria | +0.664 |
Neg logit contributions | |
picking | -0.722 |
Wester | -0.645 |
ILLE | -0.638 |
ECK | -0.630 |
SUP | -0.618 |
Token | и |
Token ID | 18849 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
picking | +0.364 |
Wester | +0.330 |
ECK | +0.326 |
ILLE | +0.325 |
rol | +0.319 |
Neg logit contributions | |
ities | -0.384 |
ctors | -0.298 |
ifax | -0.281 |
andro | -0.280 |
peria | -0.278 |
Token | |
Token ID | 220 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
ities | +1.739 |
ctors | +1.340 |
andro | +1.271 |
ifax | +1.267 |
peria | +1.253 |
Neg logit contributions | |
picking | -1.642 |
Wester | -1.473 |
ECK | -1.455 |
ILLE | -1.451 |
rol | -1.418 |
Token | р |
Token ID | 21169 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ities | +1.798 |
ctors | +1.361 |
andro | +1.294 |
ifax | +1.294 |
peria | +1.258 |
Neg logit contributions | |
picking | -1.884 |
Wester | -1.710 |
ECK | -1.682 |
ILLE | -1.676 |
SUP | -1.647 |
Token | а |
Token ID | 16142 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
ities | +2.602 |
ctors | +1.994 |
andro | +1.890 |
ifax | +1.889 |
peria | +1.863 |
Neg logit contributions | |
picking | -2.523 |
Wester | -2.289 |
ILLE | -2.231 |
ECK | -2.228 |
rol | -2.189 |
Token | н |
Token ID | 22177 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ities | +5.755 |
ctors | +4.168 |
ifax | +3.918 |
andro | +3.904 |
peria | +3.746 |
Neg logit contributions | |
picking | -7.803 |
Wester | -7.128 |
ECK | -7.062 |
ILLE | -7.036 |
rol | -6.897 |
Token | е |
Token ID | 16843 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ities | +2.862 |
ctors | +2.092 |
andro | +1.985 |
ifax | +1.974 |
peria | +1.918 |
Neg logit contributions | |
picking | -3.344 |
Wester | -3.073 |
ILLE | -3.013 |
ECK | -3.002 |
rol | -2.939 |
Token | н |
Token ID | 22177 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ities | +2.989 |
ctors | +2.243 |
andro | +2.129 |
ifax | +2.102 |
peria | +2.082 |
Neg logit contributions | |
picking | -3.210 |
Wester | -2.914 |
ILLE | -2.871 |
ECK | -2.845 |
rol | -2.799 |
Token | и |
Token ID | 18849 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ities | +2.804 |
ctors | +2.129 |
andro | +2.048 |
ifax | +2.026 |
peria | +1.990 |
Neg logit contributions | |
picking | -2.696 |
Wester | -2.440 |
ILLE | -2.407 |
ECK | -2.398 |
rol | -2.341 |
Token | я |
Token ID | 40623 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ities | +3.044 |
ctors | +2.220 |
andro | +2.079 |
ifax | +2.072 |
peria | +2.045 |
Neg logit contributions | |
picking | -3.929 |
Wester | -3.572 |
ILLE | -3.555 |
ECK | -3.537 |
rol | -3.478 |
Token | as |
Token ID | 355 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ities | +1.247 |
ctors | +0.975 |
andro | +0.923 |
ifax | +0.921 |
peria | +0.915 |
Neg logit contributions | |
picking | -1.073 |
Wester | -0.973 |
ILLE | -0.960 |
ECK | -0.959 |
SUP | -0.933 |
Token | � |
Token ID | 564 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ities | +1.523 |
ctors | +1.201 |
ifax | +1.146 |
andro | +1.143 |
peria | +1.131 |
Neg logit contributions | |
picking | -1.153 |
ILLE | -1.031 |
Wester | -1.030 |
ECK | -1.027 |
rol | -1.009 |
Token | � |
Token ID | 250 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ities | +1.340 |
ctors | +1.046 |
ifax | +0.998 |
andro | +0.995 |
peria | +0.967 |
Neg logit contributions | |
picking | -1.228 |
Wester | -1.117 |
ECK | -1.096 |
ILLE | -1.093 |
SUP | -1.069 |
Token | more |
Token ID | 3549 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
picking | +0.561 |
Wester | +0.509 |
ECK | +0.502 |
ILLE | +0.501 |
rol | +0.491 |
Neg logit contributions | |
ities | -0.584 |
ctors | -0.451 |
ifax | -0.425 |
andro | -0.424 |
peria | -0.421 |
Token | Nancy |
Token ID | 18496 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
picking | +0.920 |
Wester | +0.818 |
ECK | +0.805 |
ILLE | +0.804 |
rol | +0.785 |
Neg logit contributions | |
ities | -1.282 |
ctors | -1.027 |
ifax | -0.977 |
andro | -0.975 |
peria | -0.969 |
Token | Pelosi |
Token ID | 29611 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
picking | +1.111 |
Wester | +1.014 |
ECK | +0.999 |
ILLE | +0.996 |
rol | +0.979 |
Neg logit contributions | |
ities | -1.047 |
ctors | -0.798 |
ifax | -0.750 |
andro | -0.747 |
peria | -0.743 |
Token | than |
Token ID | 621 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ities | +7.198 |
ctors | +5.502 |
ifax | +5.273 |
andro | +5.256 |
peria | +5.071 |
Neg logit contributions | |
picking | -6.194 |
ILLE | -5.576 |
ECK | -5.540 |
Wester | -5.475 |
rol | -5.344 |
Token | Montana |
Token ID | 18311 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ities | +1.265 |
ctors | +1.010 |
andro | +0.962 |
ifax | +0.962 |
peria | +0.951 |
Neg logit contributions | |
picking | -0.915 |
Wester | -0.807 |
ILLE | -0.800 |
ECK | -0.799 |
rol | -0.780 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ities | +0.645 |
ctors | +0.511 |
ifax | +0.486 |
andro | +0.485 |
peria | +0.481 |
Neg logit contributions | |
picking | -0.497 |
Wester | -0.442 |
ECK | -0.439 |
ILLE | -0.438 |
rol | -0.425 |
Token | � |
Token ID | 447 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ities | +0.886 |
ctors | +0.701 |
ifax | +0.660 |
andro | +0.659 |
peria | +0.653 |
Neg logit contributions | |
picking | -0.721 |
Wester | -0.640 |
ILLE | -0.634 |
ECK | -0.634 |
rol | -0.619 |
Token | � |
Token ID | 251 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ities | +1.115 |
ctors | +0.859 |
ifax | +0.816 |
andro | +0.814 |
peria | +0.801 |
Neg logit contributions | |
picking | -1.058 |
Wester | -0.956 |
ILLE | -0.939 |
ECK | -0.934 |
SUP | -0.920 |
Token | , |
Token ID | 11 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ities | +2.185 |
ctors | +1.686 |
ifax | +1.596 |
andro | +1.593 |
peria | +1.575 |
Neg logit contributions | |
picking | -1.915 |
ILLE | -1.726 |
Wester | -1.720 |
ECK | -1.714 |
rol | -1.668 |
Token | so |
Token ID | 523 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ities | +0.210 |
ctors | +0.167 |
andro | +0.159 |
ifax | +0.158 |
peria | +0.156 |
Neg logit contributions | |
picking | -0.158 |
Wester | -0.141 |
ILLE | -0.141 |
ECK | -0.140 |
rol | -0.137 |
Token | please |
Token ID | 3387 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
picking | +2.324 |
Wester | +2.058 |
ECK | +2.012 |
ILLE | +1.993 |
SUP | +1.955 |
Neg logit contributions | |
ities | -3.703 |
ctors | -3.004 |
ifax | -2.888 |
andro | -2.875 |
peria | -2.864 |
Token | don |
Token ID | 836 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
ities | +0.729 |
ctors | +0.575 |
ifax | +0.541 |
andro | +0.541 |
peria | +0.538 |
Neg logit contributions | |
picking | -0.597 |
Wester | -0.533 |
ILLE | -0.529 |
ECK | -0.528 |
rol | -0.514 |
Token | 't |
Token ID | 470 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
ities | +1.823 |
ctors | +1.325 |
ifax | +1.239 |
andro | +1.222 |
peria | +1.221 |
Neg logit contributions | |
picking | -2.569 |
Wester | -2.361 |
ECK | -2.334 |
ILLE | -2.326 |
rol | -2.302 |
Token | forget |
Token ID | 6044 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
picking | +1.229 |
Wester | +1.102 |
ECK | +1.072 |
ILLE | +1.068 |
SUP | +1.055 |
Neg logit contributions | |
ities | -1.614 |
ctors | -1.291 |
ifax | -1.234 |
andro | -1.229 |
peria | -1.223 |
Token | to |
Token ID | 284 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
ities | +6.900 |
ctors | +5.353 |
ifax | +4.895 |
peria | +4.824 |
andro | +4.775 |
Neg logit contributions | |
picking | -6.447 |
ECK | -5.775 |
ILLE | -5.724 |
Wester | -5.622 |
rol | -5.546 |
Token | dry |
Token ID | 5894 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ities | +1.596 |
ctors | +1.256 |
ifax | +1.182 |
andro | +1.180 |
peria | +1.174 |
Neg logit contributions | |
picking | -1.311 |
ILLE | -1.170 |
Wester | -1.170 |
ECK | -1.161 |
rol | -1.127 |
Token | off |
Token ID | 572 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
picking | +2.145 |
Wester | +1.882 |
ECK | +1.854 |
ILLE | +1.827 |
rol | +1.797 |
Neg logit contributions | |
ities | -3.598 |
ctors | -2.949 |
ifax | -2.819 |
andro | -2.805 |
peria | -2.800 |
Token | ." |
Token ID | 526 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
picking | +1.026 |
Wester | +0.907 |
ECK | +0.891 |
ILLE | +0.888 |
rol | +0.867 |
Neg logit contributions | |
ities | -1.587 |
ctors | -1.288 |
ifax | -1.227 |
andro | -1.224 |
peria | -1.219 |
Token |
|
Token ID | 198 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
picking | +0.995 |
Wester | +0.895 |
ECK | +0.860 |
SUP | +0.849 |
ILLE | +0.844 |
Neg logit contributions | |
ities | -1.577 |
ctors | -1.288 |
ifax | -1.252 |
andro | -1.237 |
peria | -1.225 |
Token | . |
Token ID | 13 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
picking | +2.134 |
Wester | +1.910 |
ECK | +1.846 |
ILLE | +1.845 |
rol | +1.818 |
Neg logit contributions | |
ities | -3.256 |
ctors | -2.656 |
ifax | -2.535 |
andro | -2.525 |
peria | -2.519 |
Token | The |
Token ID | 383 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ities | +0.216 |
ctors | +0.171 |
ifax | +0.162 |
andro | +0.162 |
peria | +0.161 |
Neg logit contributions | |
picking | -0.169 |
Wester | -0.151 |
ECK | -0.149 |
ILLE | -0.148 |
rol | -0.145 |
Token | Libyan |
Token ID | 28661 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ities | +0.590 |
ctors | +0.466 |
ifax | +0.443 |
andro | +0.440 |
peria | +0.437 |
Neg logit contributions | |
picking | -0.451 |
Wester | -0.400 |
ECK | -0.397 |
ILLE | -0.396 |
rol | -0.386 |
Token | leader |
Token ID | 3554 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
picking | +0.285 |
Wester | +0.253 |
ECK | +0.249 |
ILLE | +0.249 |
rol | +0.242 |
Neg logit contributions | |
ities | -0.405 |
ctors | -0.325 |
ifax | -0.308 |
andro | -0.307 |
peria | -0.305 |
Token | demanded |
Token ID | 12284 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ities | +2.162 |
ctors | +1.683 |
ifax | +1.593 |
andro | +1.586 |
peria | +1.557 |
Neg logit contributions | |
picking | -1.823 |
ILLE | -1.628 |
ECK | -1.627 |
Wester | -1.625 |
rol | -1.570 |
Token | tough |
Token ID | 5802 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
picking | +1.149 |
Wester | +1.028 |
ECK | +1.002 |
ILLE | +1.000 |
SUP | +0.979 |
Neg logit contributions | |
ities | -1.609 |
ctors | -1.295 |
ifax | -1.232 |
andro | -1.230 |
peria | -1.225 |
Token | contract |
Token ID | 2775 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
ities | +7.192 |
ctors | +5.321 |
ifax | +4.969 |
andro | +4.967 |
peria | +4.812 |
Neg logit contributions | |
picking | -6.382 |
ILLE | -5.694 |
ECK | -5.660 |
rail | -5.620 |
Wester | -5.617 |
Token | terms |
Token ID | 2846 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ities | +2.629 |
ctors | +2.016 |
ifax | +1.902 |
andro | +1.892 |
peria | +1.867 |
Neg logit contributions | |
picking | -2.400 |
Wester | -2.169 |
ECK | -2.150 |
ILLE | -2.146 |
SUP | -2.090 |
Token | . |
Token ID | 13 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ities | +4.510 |
ctors | +3.393 |
ifax | +3.258 |
andro | +3.222 |
peria | +3.197 |
Neg logit contributions | |
picking | -4.003 |
ECK | -3.626 |
Wester | -3.572 |
ILLE | -3.571 |
rol | -3.459 |
Token | He |
Token ID | 679 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ities | +0.918 |
ctors | +0.725 |
ifax | +0.684 |
andro | +0.683 |
peria | +0.677 |
Neg logit contributions | |
picking | -0.747 |
Wester | -0.665 |
ECK | -0.659 |
ILLE | -0.657 |
rol | -0.643 |
Token | sought |
Token ID | 7194 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ities | +0.504 |
ctors | +0.399 |
ifax | +0.378 |
andro | +0.377 |
peria | +0.373 |
Neg logit contributions | |
picking | -0.396 |
Wester | -0.353 |
ILLE | -0.350 |
ECK | -0.350 |
rol | -0.340 |
Token | is |
Token ID | 318 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
picking | +0.383 |
Wester | +0.345 |
ECK | +0.340 |
ILLE | +0.339 |
rol | +0.332 |
Neg logit contributions | |
ities | -0.453 |
ctors | -0.356 |
ifax | -0.337 |
andro | -0.336 |
peria | -0.333 |
Token | older |
Token ID | 4697 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
picking | +0.012 |
Wester | +0.010 |
ECK | +0.010 |
ILLE | +0.010 |
rol | +0.010 |
Neg logit contributions | |
ities | -0.018 |
ctors | -0.014 |
ifax | -0.013 |
andro | -0.013 |
peria | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
picking | +1.340 |
Wester | +1.203 |
ECK | +1.184 |
ILLE | +1.183 |
rol | +1.157 |
Neg logit contributions | |
ities | -1.638 |
ctors | -1.292 |
ifax | -1.224 |
andro | -1.221 |
peria | -1.213 |
Token | should |
Token ID | 815 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
picking | +0.466 |
Wester | +0.419 |
ECK | +0.413 |
ILLE | +0.413 |
rol | +0.403 |
Neg logit contributions | |
ities | -0.561 |
ctors | -0.441 |
ifax | -0.417 |
andro | -0.416 |
peria | -0.413 |
Token | be |
Token ID | 307 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
ities | +1.812 |
ctors | +1.427 |
ifax | +1.335 |
andro | +1.334 |
peria | +1.322 |
Neg logit contributions | |
picking | -1.523 |
Wester | -1.362 |
ILLE | -1.361 |
ECK | -1.352 |
rol | -1.317 |
Token | able |
Token ID | 1498 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ities | +2.341 |
ctors | +1.797 |
andro | +1.683 |
ifax | +1.676 |
peria | +1.664 |
Neg logit contributions | |
picking | -2.277 |
ILLE | -2.055 |
Wester | -2.054 |
ECK | -2.040 |
rol | -2.009 |
Token | to |
Token ID | 284 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ities | +6.970 |
ctors | +5.275 |
andro | +4.858 |
ifax | +4.806 |
peria | +4.710 |
Neg logit contributions | |
picking | -6.568 |
ILLE | -6.105 |
ECK | -6.033 |
Wester | -5.914 |
rol | -5.810 |
Token | master |
Token ID | 4958 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ities | +1.724 |
ctors | +1.372 |
andro | +1.284 |
ifax | +1.282 |
peria | +1.265 |
Neg logit contributions | |
picking | -1.315 |
ILLE | -1.171 |
Wester | -1.169 |
ECK | -1.167 |
rol | -1.138 |
Token | sticking |
Token ID | 17274 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ities | +0.795 |
ctors | +0.640 |
andro | +0.604 |
ifax | +0.603 |
peria | +0.597 |
Neg logit contributions | |
picking | -0.518 |
Wester | -0.459 |
ILLE | -0.455 |
ECK | -0.454 |
rol | -0.445 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ities | +3.459 |
ctors | +2.663 |
andro | +2.458 |
ifax | +2.447 |
peria | +2.420 |
Neg logit contributions | |
picking | -2.716 |
ILLE | -2.403 |
Wester | -2.389 |
ECK | -2.387 |
rol | -2.351 |
Token | thread |
Token ID | 4704 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ities | +0.402 |
ctors | +0.308 |
ifax | +0.291 |
andro | +0.289 |
peria | +0.286 |
Neg logit contributions | |
picking | -0.385 |
Wester | -0.347 |
ECK | -0.344 |
ILLE | -0.343 |
rol | -0.337 |
Token | am |
Token ID | 716 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ities | +0.075 |
ctors | +0.061 |
ifax | +0.058 |
andro | +0.058 |
peria | +0.058 |
Neg logit contributions | |
picking | -0.049 |
Wester | -0.043 |
ECK | -0.043 |
ILLE | -0.043 |
rol | -0.041 |
Token | assing |
Token ID | 19696 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
picking | +0.800 |
Wester | +0.724 |
ECK | +0.714 |
ILLE | +0.711 |
rol | +0.702 |
Neg logit contributions | |
ities | -0.782 |
ctors | -0.598 |
ifax | -0.566 |
andro | -0.562 |
peria | -0.559 |
Token | as |
Token ID | 355 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
picking | +0.110 |
Wester | +0.098 |
ECK | +0.098 |
ILLE | +0.097 |
rol | +0.095 |
Neg logit contributions | |
ities | -0.138 |
ctors | -0.108 |
ifax | -0.103 |
andro | -0.102 |
peria | -0.102 |
Token | they |
Token ID | 484 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ities | +1.757 |
ctors | +1.381 |
ifax | +1.304 |
andro | +1.299 |
peria | +1.295 |
Neg logit contributions | |
picking | -1.361 |
Wester | -1.206 |
ECK | -1.203 |
ILLE | -1.192 |
rol | -1.179 |
Token | held |
Token ID | 2714 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
picking | +0.637 |
Wester | +0.568 |
ECK | +0.557 |
ILLE | +0.556 |
rol | +0.544 |
Neg logit contributions | |
ities | -0.890 |
ctors | -0.714 |
ifax | -0.679 |
andro | -0.679 |
peria | -0.676 |
Token | up |
Token ID | 510 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
picking | +0.802 |
Wester | +0.712 |
ECK | +0.703 |
ILLE | +0.700 |
rol | +0.683 |
Neg logit contributions | |
ities | -1.144 |
ctors | -0.916 |
ifax | -0.873 |
andro | -0.869 |
peria | -0.865 |
Token | hundreds |
Token ID | 5179 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
picking | +3.266 |
Wester | +2.915 |
ECK | +2.821 |
ILLE | +2.815 |
SUP | +2.769 |
Neg logit contributions | |
ities | -4.707 |
ctors | -3.848 |
andro | -3.684 |
ifax | -3.655 |
peria | -3.634 |
Token | of |
Token ID | 286 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
picking | +2.746 |
Wester | +2.438 |
ECK | +2.395 |
ILLE | +2.388 |
rol | +2.336 |
Neg logit contributions | |
ities | -3.941 |
ctors | -3.170 |
ifax | -3.019 |
andro | -3.018 |
peria | -3.000 |
Token | tea |
Token ID | 8887 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
picking | +1.708 |
Wester | +1.492 |
ECK | +1.456 |
ILLE | +1.453 |
rol | +1.414 |
Neg logit contributions | |
ities | -3.071 |
ctors | -2.525 |
andro | -2.419 |
ifax | -2.413 |
peria | -2.409 |
Token | party |
Token ID | 2151 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
picking | +2.578 |
Wester | +2.265 |
ECK | +2.216 |
ILLE | +2.192 |
rol | +2.164 |
Neg logit contributions | |
ities | -4.123 |
ctors | -3.313 |
ifax | -3.200 |
andro | -3.198 |
peria | -3.171 |
Token | and |
Token ID | 290 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
picking | +0.662 |
Wester | +0.588 |
ECK | +0.578 |
ILLE | +0.577 |
rol | +0.562 |
Neg logit contributions | |
ities | -0.956 |
ctors | -0.768 |
ifax | -0.730 |
andro | -0.727 |
peria | -0.723 |
Token | they |
Token ID | 484 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
picking | +0.110 |
Wester | +0.097 |
ILLE | +0.096 |
ECK | +0.096 |
rol | +0.093 |
Neg logit contributions | |
ities | -0.166 |
ctors | -0.134 |
ifax | -0.127 |
andro | -0.127 |
peria | -0.126 |
Token | barely |
Token ID | 8523 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ities | +0.237 |
ctors | +0.187 |
ifax | +0.177 |
andro | +0.177 |
peria | +0.175 |
Neg logit contributions | |
picking | -0.188 |
Wester | -0.168 |
ILLE | -0.167 |
ECK | -0.166 |
rol | -0.161 |
Token | ripple |
Token ID | 42462 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ities | +1.160 |
ctors | +0.919 |
ifax | +0.864 |
andro | +0.864 |
peria | +0.851 |
Neg logit contributions | |
picking | -0.877 |
ILLE | -0.786 |
Wester | -0.780 |
ECK | -0.778 |
rol | -0.744 |
Token | in |
Token ID | 287 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
picking | +2.746 |
Wester | +2.494 |
ECK | +2.389 |
rol | +2.371 |
SUP | +2.354 |
Neg logit contributions | |
ities | -3.984 |
ctors | -3.255 |
ifax | -3.109 |
peria | -3.109 |
andro | -3.093 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
picking | +0.603 |
ILLE | +0.534 |
Wester | +0.532 |
ECK | +0.525 |
rol | +0.514 |
Neg logit contributions | |
ities | -0.839 |
ctors | -0.667 |
ifax | -0.632 |
andro | -0.632 |
peria | -0.626 |
Token | breeze |
Token ID | 28633 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
picking | +0.489 |
Wester | +0.421 |
ILLE | +0.416 |
ECK | +0.415 |
rol | +0.402 |
Neg logit contributions | |
ities | -0.922 |
ctors | -0.755 |
ifax | -0.723 |
andro | -0.721 |
peria | -0.716 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
picking | +3.879 |
Wester | +3.484 |
ECK | +3.358 |
rol | +3.355 |
ILLE | +3.344 |
Neg logit contributions | |
ities | -5.274 |
ctors | -4.262 |
ifax | -4.080 |
andro | -4.056 |
peria | -4.050 |
Token | In |
Token ID | 554 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ities | +0.608 |
ctors | +0.482 |
andro | +0.453 |
ifax | +0.452 |
peria | +0.448 |
Neg logit contributions | |
picking | -0.490 |
Wester | -0.433 |
ECK | -0.431 |
ILLE | -0.431 |
rol | -0.419 |
Token | Shang |
Token ID | 45797 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ities | +0.682 |
ctors | +0.544 |
ifax | +0.515 |
andro | +0.514 |
peria | +0.510 |
Neg logit contributions | |
picking | -0.491 |
ILLE | -0.436 |
ECK | -0.431 |
Wester | -0.431 |
rol | -0.417 |
Token | ba |
Token ID | 7012 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
ities | +1.503 |
ctors | +1.258 |
ifax | +1.210 |
andro | +1.207 |
peria | +1.202 |
Neg logit contributions | |
picking | -0.600 |
Wester | -0.502 |
ECK | -0.486 |
ILLE | -0.486 |
rol | -0.472 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
picking | +0.113 |
Wester | +0.101 |
ECK | +0.100 |
ILLE | +0.100 |
SUP | +0.097 |
Neg logit contributions | |
ities | -0.131 |
ctors | -0.103 |
ifax | -0.097 |
andro | -0.097 |
peria | -0.096 |
Token | abolic |
Token ID | 29304 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
ities | +0.878 |
ctors | +0.617 |
andro | +0.574 |
ifax | +0.573 |
peria | +0.553 |
Neg logit contributions | |
picking | -1.324 |
Wester | -1.224 |
ILLE | -1.220 |
ECK | -1.214 |
SUP | -1.184 |
Token | exercise |
Token ID | 5517 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
ities | +1.478 |
ctors | +1.164 |
ifax | +1.113 |
andro | +1.107 |
peria | +1.089 |
Neg logit contributions | |
picking | -1.069 |
ILLE | -0.952 |
ECK | -0.945 |
Wester | -0.943 |
SUP | -0.905 |
Token |
|
Token ID | 198 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
ities | +0.917 |
ctors | +0.728 |
ifax | +0.684 |
andro | +0.682 |
peria | +0.676 |
Neg logit contributions | |
picking | -0.741 |
Wester | -0.661 |
ILLE | -0.658 |
ECK | -0.655 |
rol | -0.635 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
picking | +0.101 |
Wester | +0.090 |
ECK | +0.087 |
ILLE | +0.086 |
rol | +0.086 |
Neg logit contributions | |
ities | -0.157 |
ctors | -0.129 |
ifax | -0.126 |
peria | -0.124 |
andro | -0.123 |
Token | The |
Token ID | 464 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ities | +0.435 |
ctors | +0.332 |
andro | +0.313 |
ifax | +0.310 |
peria | +0.309 |
Neg logit contributions | |
picking | -0.440 |
Wester | -0.403 |
ECK | -0.394 |
ILLE | -0.393 |
SUP | -0.387 |
Token | purpose |
Token ID | 4007 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
picking | +0.335 |
Wester | +0.299 |
ECK | +0.295 |
ILLE | +0.294 |
rol | +0.287 |
Neg logit contributions | |
ities | -0.436 |
ctors | -0.346 |
ifax | -0.329 |
andro | -0.328 |
peria | -0.325 |
Token | of |
Token ID | 286 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
picking | +2.868 |
Wester | +2.548 |
ECK | +2.503 |
ILLE | +2.479 |
rol | +2.456 |
Neg logit contributions | |
ities | -4.254 |
ctors | -3.432 |
ifax | -3.280 |
andro | -3.279 |
peria | -3.277 |
Token | this |
Token ID | 428 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
picking | +0.824 |
Wester | +0.730 |
ECK | +0.717 |
ILLE | +0.716 |
rol | +0.698 |
Neg logit contributions | |
ities | -1.220 |
ctors | -0.983 |
ifax | -0.937 |
andro | -0.934 |
peria | -0.930 |
Token | is |
Token ID | 318 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ities | +0.165 |
ctors | +0.128 |
ifax | +0.121 |
andro | +0.121 |
peria | +0.120 |
Neg logit contributions | |
picking | -0.152 |
Wester | -0.137 |
ECK | -0.136 |
ILLE | -0.136 |
rol | -0.133 |
Token | to |
Token ID | 284 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
picking | +0.531 |
Wester | +0.475 |
ECK | +0.468 |
ILLE | +0.468 |
rol | +0.456 |
Neg logit contributions | |
ities | -0.665 |
ctors | -0.526 |
ifax | -0.498 |
andro | -0.498 |
peria | -0.494 |
Token | highlight |
Token ID | 7238 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ities | +1.223 |
ctors | +0.948 |
ifax | +0.889 |
andro | +0.889 |
peria | +0.880 |
Neg logit contributions | |
picking | -1.155 |
Wester | -1.040 |
ILLE | -1.033 |
ECK | -1.031 |
rol | -1.005 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
picking | +0.162 |
Wester | +0.145 |
ECK | +0.143 |
ILLE | +0.143 |
rol | +0.140 |
Neg logit contributions | |
ities | -0.198 |
ctors | -0.156 |
ifax | -0.148 |
andro | -0.148 |
peria | -0.147 |
Token | which |
Token ID | 543 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
ities | +0.702 |
ctors | +0.539 |
ifax | +0.508 |
andro | +0.506 |
peria | +0.502 |
Neg logit contributions | |
picking | -0.679 |
Wester | -0.615 |
ILLE | -0.612 |
ECK | -0.611 |
rol | -0.595 |
Token | , |
Token ID | 11 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ities | +1.511 |
ctors | +1.178 |
ifax | +1.115 |
andro | +1.110 |
peria | +1.102 |
Neg logit contributions | |
picking | -1.248 |
Wester | -1.104 |
ILLE | -1.104 |
ECK | -1.102 |
rol | -1.073 |
Token | in |
Token ID | 287 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
picking | +0.705 |
Wester | +0.632 |
ECK | +0.620 |
ILLE | +0.618 |
rol | +0.606 |
Neg logit contributions | |
ities | -0.907 |
ctors | -0.721 |
ifax | -0.684 |
andro | -0.683 |
peria | -0.680 |
Token | their |
Token ID | 511 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
picking | +1.120 |
Wester | +0.989 |
ILLE | +0.974 |
ECK | +0.974 |
rol | +0.949 |
Neg logit contributions | |
ities | -1.656 |
ctors | -1.333 |
ifax | -1.271 |
andro | -1.267 |
peria | -1.259 |
Token | turn |
Token ID | 1210 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
picking | +1.172 |
Wester | +1.044 |
ECK | +1.025 |
ILLE | +1.023 |
rol | +0.998 |
Neg logit contributions | |
ities | -1.647 |
ctors | -1.325 |
ifax | -1.258 |
andro | -1.256 |
peria | -1.249 |
Token | , |
Token ID | 11 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
picking | +3.613 |
Wester | +3.267 |
ILLE | +3.191 |
ECK | +3.179 |
rol | +3.136 |
Neg logit contributions | |
ities | -4.430 |
ctors | -3.519 |
andro | -3.345 |
ifax | -3.331 |
peria | -3.330 |
Token | threatened |
Token ID | 8556 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
picking | +0.138 |
Wester | +0.123 |
ECK | +0.122 |
ILLE | +0.122 |
rol | +0.119 |
Neg logit contributions | |
ities | -0.181 |
ctors | -0.144 |
ifax | -0.137 |
andro | -0.136 |
peria | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
picking | +0.167 |
Wester | +0.147 |
ECK | +0.147 |
ILLE | +0.147 |
rol | +0.143 |
Neg logit contributions | |
ities | -0.220 |
ctors | -0.174 |
ifax | -0.166 |
andro | -0.165 |
peria | -0.164 |
Token | surround |
Token ID | 4573 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
picking | +0.111 |
Wester | +0.099 |
ECK | +0.097 |
ILLE | +0.097 |
rol | +0.095 |
Neg logit contributions | |
ities | -0.151 |
ctors | -0.121 |
ifax | -0.115 |
andro | -0.114 |
peria | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
picking | +1.726 |
Wester | +1.555 |
ECK | +1.512 |
ILLE | +1.509 |
rol | +1.481 |
Neg logit contributions | |
ities | -2.309 |
ctors | -1.850 |
ifax | -1.756 |
andro | -1.751 |
peria | -1.746 |
Token | as |
Token ID | 355 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
ities | +0.051 |
ctors | +0.040 |
ifax | +0.038 |
andro | +0.038 |
peria | +0.037 |
Neg logit contributions | |
picking | -0.041 |
Wester | -0.037 |
ECK | -0.036 |
ILLE | -0.036 |
rol | -0.035 |
Token | non |
Token ID | 1729 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
ities | +1.402 |
ctors | +1.138 |
andro | +1.080 |
ifax | +1.076 |
peria | +1.068 |
Neg logit contributions | |
picking | -0.881 |
Wester | -0.762 |
ECK | -0.758 |
ILLE | -0.753 |
rol | -0.736 |
Token | combat |
Token ID | 39969 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ities | +0.274 |
ctors | +0.219 |
andro | +0.206 |
ifax | +0.204 |
peria | +0.202 |
Neg logit contributions | |
picking | -0.209 |
Wester | -0.189 |
ECK | -0.188 |
ILLE | -0.187 |
SUP | -0.180 |
Token | ants |
Token ID | 1187 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
picking | +0.500 |
Wester | +0.453 |
ECK | +0.447 |
ILLE | +0.446 |
rol | +0.437 |
Neg logit contributions | |
ities | -0.510 |
ctors | -0.394 |
ifax | -0.370 |
andro | -0.369 |
peria | -0.365 |
Token | in |
Token ID | 287 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ities | +0.355 |
ctors | +0.279 |
ifax | +0.265 |
andro | +0.265 |
peria | +0.263 |
Neg logit contributions | |
picking | -0.284 |
Wester | -0.254 |
ECK | -0.252 |
ILLE | -0.251 |
rol | -0.244 |
Token | paramilitary |
Token ID | 43542 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ities | +0.662 |
ctors | +0.523 |
andro | +0.494 |
ifax | +0.494 |
peria | +0.486 |
Neg logit contributions | |
picking | -0.491 |
ECK | -0.432 |
ILLE | -0.429 |
Wester | -0.423 |
rol | -0.414 |
Token | units |
Token ID | 4991 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
picking | +3.517 |
Wester | +3.190 |
ECK | +3.047 |
ILLE | +3.034 |
SUP | +3.018 |
Neg logit contributions | |
ities | -5.823 |
ctors | -4.826 |
ifax | -4.657 |
peria | -4.637 |
andro | -4.612 |
Token | and |
Token ID | 290 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
picking | +1.334 |
Wester | +1.195 |
ECK | +1.170 |
ILLE | +1.167 |
rol | +1.145 |
Neg logit contributions | |
ities | -1.802 |
ctors | -1.443 |
ifax | -1.372 |
andro | -1.368 |
peria | -1.360 |
Token | police |
Token ID | 1644 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
ities | +0.897 |
ctors | +0.717 |
andro | +0.678 |
ifax | +0.674 |
peria | +0.672 |
Neg logit contributions | |
picking | -0.630 |
Wester | -0.550 |
ECK | -0.546 |
ILLE | -0.545 |
rol | -0.529 |
Token | formations |
Token ID | 30648 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
picking | +1.424 |
Wester | +1.265 |
ECK | +1.243 |
ILLE | +1.241 |
rol | +1.211 |
Neg logit contributions | |
ities | -2.029 |
ctors | -1.629 |
ifax | -1.550 |
andro | -1.546 |
peria | -1.538 |
Token | ( |
Token ID | 357 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
picking | +0.921 |
Wester | +0.825 |
ECK | +0.809 |
ILLE | +0.808 |
rol | +0.792 |
Neg logit contributions | |
ities | -1.216 |
ctors | -0.971 |
ifax | -0.923 |
andro | -0.920 |
peria | -0.915 |
Token | wielding |
Token ID | 33949 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
picking | +1.860 |
Wester | +1.652 |
ECK | +1.619 |
ILLE | +1.612 |
rol | +1.593 |
Neg logit contributions | |
ities | -2.558 |
ctors | -2.049 |
ifax | -1.953 |
andro | -1.949 |
peria | -1.944 |
Token | a |
Token ID | 257 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
picking | +0.377 |
Wester | +0.335 |
ILLE | +0.332 |
ECK | +0.331 |
rol | +0.321 |
Neg logit contributions | |
ities | -0.491 |
ctors | -0.386 |
ifax | -0.369 |
andro | -0.369 |
peria | -0.365 |
Token | gun |
Token ID | 2485 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
picking | +0.173 |
Wester | +0.153 |
ECK | +0.151 |
ILLE | +0.151 |
rol | +0.147 |
Neg logit contributions | |
ities | -0.245 |
ctors | -0.196 |
ifax | -0.187 |
andro | -0.187 |
peria | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
picking | +2.256 |
Wester | +2.018 |
ECK | +1.983 |
ILLE | +1.980 |
rol | +1.938 |
Neg logit contributions | |
ities | -2.914 |
ctors | -2.320 |
ifax | -2.198 |
andro | -2.194 |
peria | -2.181 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
picking | +0.050 |
Wester | +0.044 |
ECK | +0.044 |
ILLE | +0.044 |
rol | +0.043 |
Neg logit contributions | |
ities | -0.063 |
ctors | -0.049 |
ifax | -0.047 |
andro | -0.047 |
peria | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ities | +0.375 |
ctors | +0.307 |
ifax | +0.297 |
peria | +0.294 |
andro | +0.294 |
Neg logit contributions | |
picking | -0.246 |
Wester | -0.219 |
ECK | -0.213 |
ILLE | -0.211 |
rol | -0.209 |
Token | On |
Token ID | 2202 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ities | +0.374 |
ctors | +0.284 |
andro | +0.267 |
ifax | +0.265 |
peria | +0.264 |
Neg logit contributions | |
picking | -0.393 |
Wester | -0.360 |
ECK | -0.352 |
ILLE | -0.351 |
rol | -0.346 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
picking | +0.797 |
Wester | +0.713 |
ECK | +0.701 |
ILLE | +0.699 |
rol | +0.684 |
Neg logit contributions | |
ities | -1.039 |
ctors | -0.827 |
ifax | -0.785 |
andro | -0.783 |
peria | -0.780 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ities | +0.506 |
ctors | +0.393 |
ifax | +0.371 |
andro | +0.371 |
peria | +0.367 |
Neg logit contributions | |
picking | -0.454 |
Wester | -0.407 |
ECK | -0.403 |
ILLE | -0.403 |
rol | -0.394 |
Token | a |
Token ID | 257 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ities | +0.089 |
ctors | +0.071 |
ifax | +0.067 |
andro | +0.067 |
peria | +0.067 |
Neg logit contributions | |
picking | -0.068 |
Wester | -0.061 |
ECK | -0.060 |
ILLE | -0.060 |
rol | -0.058 |
Token | second |
Token ID | 1218 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
ities | +0.081 |
ctors | +0.065 |
ifax | +0.062 |
andro | +0.061 |
peria | +0.061 |
Neg logit contributions | |
picking | -0.058 |
Wester | -0.051 |
ECK | -0.051 |
ILLE | -0.051 |
rol | -0.049 |
Token | professional |
Token ID | 4708 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
picking | +0.430 |
Wester | +0.382 |
ECK | +0.377 |
ILLE | +0.376 |
rol | +0.367 |
Neg logit contributions | |
ities | -0.580 |
ctors | -0.462 |
ifax | -0.439 |
andro | -0.438 |
peria | -0.436 |
Token | reputation |
Token ID | 8507 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
picking | +0.172 |
Wester | +0.153 |
ECK | +0.151 |
ILLE | +0.151 |
rol | +0.147 |
Neg logit contributions | |
ities | -0.220 |
ctors | -0.174 |
ifax | -0.164 |
andro | -0.164 |
peria | -0.163 |
Token | . |
Token ID | 13 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ities | +1.453 |
ctors | +1.102 |
ifax | +1.052 |
andro | +1.037 |
peria | +1.030 |
Neg logit contributions | |
picking | -1.321 |
Wester | -1.200 |
ECK | -1.197 |
ILLE | -1.191 |
rol | -1.155 |
Token |
|
Token ID | 198 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
ities | +0.803 |
ctors | +0.638 |
ifax | +0.602 |
andro | +0.599 |
peria | +0.594 |
Neg logit contributions | |
picking | -0.636 |
Wester | -0.564 |
ECK | -0.560 |
ILLE | -0.559 |
rol | -0.549 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
picking | +0.194 |
Wester | +0.172 |
ECK | +0.166 |
SUP | +0.164 |
rol | +0.164 |
Neg logit contributions | |
ities | -0.309 |
ctors | -0.256 |
ifax | -0.248 |
peria | -0.246 |
andro | -0.245 |
Token | What |
Token ID | 2061 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
ities | +0.281 |
ctors | +0.213 |
andro | +0.200 |
ifax | +0.199 |
peria | +0.198 |
Neg logit contributions | |
picking | -0.301 |
Wester | -0.276 |
ECK | -0.271 |
ILLE | -0.270 |
rol | -0.267 |
Token | are |
Token ID | 389 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
picking | +2.077 |
Wester | +1.864 |
ECK | +1.817 |
ILLE | +1.817 |
SUP | +1.783 |
Neg logit contributions | |
ities | -2.713 |
ctors | -2.167 |
andro | -2.062 |
ifax | -2.059 |
peria | -2.048 |
Token | the |
Token ID | 262 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ities | +0.205 |
ctors | +0.164 |
ifax | +0.156 |
andro | +0.155 |
peria | +0.154 |
Neg logit contributions | |
picking | -0.145 |
Wester | -0.128 |
ECK | -0.127 |
ILLE | -0.126 |
rol | -0.124 |
Token | odds |
Token ID | 10402 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
picking | +0.684 |
Wester | +0.608 |
ECK | +0.598 |
ILLE | +0.596 |
rol | +0.582 |
Neg logit contributions | |
ities | -0.960 |
ctors | -0.769 |
ifax | -0.732 |
andro | -0.730 |
peria | -0.726 |
Token | of |
Token ID | 286 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
picking | +0.933 |
Wester | +0.830 |
ECK | +0.817 |
ILLE | +0.815 |
rol | +0.796 |
Neg logit contributions | |
ities | -1.300 |
ctors | -1.040 |
ifax | -0.990 |
andro | -0.986 |
peria | -0.981 |
Token | Jonathan |
Token ID | 11232 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
picking | +0.800 |
Wester | +0.709 |
ILLE | +0.695 |
ECK | +0.694 |
rol | +0.677 |
Neg logit contributions | |
ities | -1.179 |
ctors | -0.951 |
ifax | -0.905 |
andro | -0.904 |
peria | -0.899 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ities | +0.095 |
ctors | +0.076 |
andro | +0.072 |
ifax | +0.072 |
peria | +0.071 |
Neg logit contributions | |
picking | -0.070 |
Wester | -0.062 |
ILLE | -0.062 |
ECK | -0.062 |
rol | -0.060 |
Token | M |
Token ID | 337 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ities | +0.409 |
ctors | +0.322 |
andro | +0.306 |
ifax | +0.306 |
peria | +0.301 |
Neg logit contributions | |
picking | -0.325 |
Wester | -0.287 |
ILLE | -0.286 |
ECK | -0.286 |
rol | -0.279 |
Token | oom |
Token ID | 4207 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
ities | +0.908 |
ctors | +0.738 |
ifax | +0.701 |
peria | +0.696 |
andro | +0.695 |
Neg logit contributions | |
picking | -0.615 |
Wester | -0.546 |
ECK | -0.539 |
ILLE | -0.535 |
rol | -0.525 |
Token | in |
Token ID | 259 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
picking | +0.230 |
Wester | +0.212 |
rol | +0.207 |
ILLE | +0.207 |
ECK | +0.207 |
Neg logit contributions | |
ities | -0.145 |
ctors | -0.103 |
ifax | -0.095 |
peria | -0.093 |
andro | -0.092 |
Token | books |
Token ID | 3835 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
picking | +0.187 |
Wester | +0.166 |
ECK | +0.164 |
ILLE | +0.164 |
rol | +0.159 |
Neg logit contributions | |
ities | -0.249 |
ctors | -0.198 |
ifax | -0.188 |
andro | -0.188 |
peria | -0.187 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
picking | +0.598 |
Wester | +0.535 |
ECK | +0.528 |
ILLE | +0.528 |
rol | +0.515 |
Neg logit contributions | |
ities | -0.740 |
ctors | -0.584 |
ifax | -0.554 |
andro | -0.554 |
peria | -0.549 |
Token | has |
Token ID | 468 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ities | +0.457 |
ctors | +0.362 |
andro | +0.344 |
ifax | +0.343 |
peria | +0.338 |
Neg logit contributions | |
picking | -0.343 |
ILLE | -0.302 |
Wester | -0.301 |
ECK | -0.301 |
rol | -0.291 |
Token | many |
Token ID | 867 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
ities | +0.653 |
ctors | +0.521 |
ifax | +0.495 |
andro | +0.494 |
peria | +0.488 |
Neg logit contributions | |
picking | -0.476 |
Wester | -0.421 |
ECK | -0.417 |
ILLE | -0.417 |
rol | -0.404 |
Token | original |
Token ID | 2656 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
picking | +1.812 |
Wester | +1.624 |
ECK | +1.582 |
ILLE | +1.580 |
rol | +1.549 |
Neg logit contributions | |
ities | -2.609 |
ctors | -2.104 |
ifax | -2.009 |
peria | -2.000 |
andro | -1.997 |
Token | M |
Token ID | 337 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
picking | +1.119 |
Wester | +1.001 |
ECK | +0.980 |
ILLE | +0.979 |
rol | +0.958 |
Neg logit contributions | |
ities | -1.544 |
ctors | -1.240 |
ifax | -1.180 |
andro | -1.175 |
peria | -1.174 |
Token | oom |
Token ID | 4207 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
ities | +0.730 |
ctors | +0.598 |
ifax | +0.569 |
peria | +0.565 |
andro | +0.561 |
Neg logit contributions | |
picking | -0.483 |
Wester | -0.428 |
ECK | -0.424 |
ILLE | -0.419 |
rol | -0.413 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ities | +3.166 |
ctors | +2.478 |
andro | +2.331 |
ifax | +2.331 |
peria | +2.294 |
Neg logit contributions | |
picking | -2.582 |
ECK | -2.323 |
Wester | -2.310 |
ILLE | -2.276 |
rol | -2.238 |
Token | falls |
Token ID | 8953 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
ities | +0.879 |
ctors | +0.699 |
ifax | +0.664 |
andro | +0.662 |
peria | +0.657 |
Neg logit contributions | |
picking | -0.652 |
Wester | -0.578 |
ECK | -0.576 |
ILLE | -0.571 |
rol | -0.558 |
Token | into |
Token ID | 656 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ities | +0.287 |
ctors | +0.229 |
andro | +0.218 |
ifax | +0.218 |
peria | +0.216 |
Neg logit contributions | |
picking | -0.210 |
Wester | -0.187 |
ILLE | -0.184 |
ECK | -0.184 |
rol | -0.180 |
Token | this |
Token ID | 428 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
picking | +0.813 |
Wester | +0.725 |
ECK | +0.712 |
ILLE | +0.711 |
rol | +0.694 |
Neg logit contributions | |
ities | -1.113 |
ctors | -0.890 |
ifax | -0.846 |
andro | -0.844 |
peria | -0.839 |
Token | same |
Token ID | 976 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
picking | +0.119 |
Wester | +0.109 |
ECK | +0.109 |
ILLE | +0.109 |
rol | +0.107 |
Neg logit contributions | |
ities | -0.087 |
ctors | -0.063 |
ifax | -0.058 |
andro | -0.058 |
peria | -0.058 |
Token | category |
Token ID | 6536 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
ities | +2.559 |
ctors | +1.867 |
ifax | +1.751 |
andro | +1.747 |
peria | +1.735 |
Neg logit contributions | |
picking | -3.010 |
ILLE | -2.717 |
ECK | -2.714 |
Wester | -2.687 |
rol | -2.681 |
Token | : |
Token ID | 25 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ities | +0.238 |
ctors | +0.185 |
ifax | +0.175 |
andro | +0.175 |
peria | +0.173 |
Neg logit contributions | |
picking | -0.205 |
Wester | -0.184 |
ILLE | -0.183 |
ECK | -0.182 |
rol | -0.177 |
Token | while |
Token ID | 981 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ities | +1.607 |
ctors | +1.282 |
ifax | +1.222 |
andro | +1.212 |
peria | +1.200 |
Neg logit contributions | |
picking | -1.168 |
ECK | -1.038 |
Wester | -1.032 |
ILLE | -1.028 |
rol | -1.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
picking | +0.819 |
Wester | +0.721 |
ECK | +0.710 |
ILLE | +0.708 |
rol | +0.690 |
Neg logit contributions | |
ities | -1.280 |
ctors | -1.037 |
ifax | -0.989 |
andro | -0.986 |
peria | -0.981 |
Token | truly |
Token ID | 4988 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ities | +0.389 |
ctors | +0.311 |
ifax | +0.295 |
andro | +0.294 |
peria | +0.293 |
Neg logit contributions | |
picking | -0.287 |
Wester | -0.256 |
ECK | -0.252 |
ILLE | -0.251 |
rol | -0.246 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
picking | +2.440 |
Wester | +2.163 |
ILLE | +2.105 |
ECK | +2.089 |
rol | +2.044 |
Neg logit contributions | |
ities | -3.910 |
ctors | -3.187 |
andro | -3.040 |
ifax | -3.035 |
peria | -3.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
picking | +0.011 |
Wester | +0.009 |
ECK | +0.009 |
ILLE | +0.009 |
rol | +0.009 |
Neg logit contributions | |
ities | -0.016 |
ctors | -0.013 |
ifax | -0.013 |
peria | -0.013 |
andro | -0.013 |
Token | A |
Token ID | 32 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ities | +0.304 |
ctors | +0.231 |
andro | +0.216 |
ifax | +0.216 |
peria | +0.215 |
Neg logit contributions | |
picking | -0.315 |
Wester | -0.289 |
ECK | -0.282 |
ILLE | -0.280 |
SUP | -0.276 |
Token | message |
Token ID | 3275 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
ities | +0.541 |
ctors | +0.436 |
ifax | +0.410 |
peria | +0.406 |
andro | +0.404 |
Neg logit contributions | |
picking | -0.396 |
Wester | -0.351 |
ECK | -0.349 |
ILLE | -0.347 |
rol | -0.335 |
Token | from |
Token ID | 422 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
ities | +2.141 |
ctors | +1.671 |
ifax | +1.615 |
andro | +1.576 |
peria | +1.567 |
Neg logit contributions | |
picking | -1.815 |
ECK | -1.613 |
ILLE | -1.606 |
Wester | -1.595 |
rol | -1.553 |
Token | Hydro |
Token ID | 32116 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ities | +0.251 |
ctors | +0.205 |
ifax | +0.198 |
andro | +0.196 |
peria | +0.195 |
Neg logit contributions | |
picking | -0.139 |
ECK | -0.119 |
Wester | -0.119 |
ILLE | -0.119 |
rol | -0.114 |
Token | president |
Token ID | 1893 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
picking | +3.088 |
Wester | +2.801 |
ECK | +2.716 |
ILLE | +2.710 |
SUP | +2.687 |
Neg logit contributions | |
ities | -4.021 |
ctors | -3.215 |
andro | -3.064 |
peria | -3.028 |
ifax | -3.003 |
Token | and |
Token ID | 290 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
picking | +1.061 |
Wester | +0.943 |
ECK | +0.926 |
ILLE | +0.925 |
rol | +0.903 |
Neg logit contributions | |
ities | -1.505 |
ctors | -1.208 |
ifax | -1.150 |
andro | -1.147 |
peria | -1.141 |
Token | CEO |
Token ID | 6123 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
ities | +1.516 |
ctors | +1.173 |
ifax | +1.087 |
andro | +1.079 |
peria | +1.068 |
Neg logit contributions | |
picking | -1.542 |
ILLE | -1.397 |
Wester | -1.384 |
ECK | -1.383 |
rol | -1.334 |
Token | Kelvin |
Token ID | 46577 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
ities | +2.420 |
ctors | +1.916 |
andro | +1.834 |
ifax | +1.828 |
peria | +1.804 |
Neg logit contributions | |
picking | -1.706 |
ILLE | -1.501 |
ECK | -1.493 |
Wester | -1.475 |
rol | -1.428 |
Token | Shepherd |
Token ID | 30890 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
picking | +0.172 |
Wester | +0.151 |
ILLE | +0.150 |
ECK | +0.150 |
rol | +0.146 |
Neg logit contributions | |
ities | -0.247 |
ctors | -0.198 |
ifax | -0.189 |
andro | -0.188 |
peria | -0.187 |
Token | to |
Token ID | 284 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ities | +2.450 |
ctors | +1.888 |
ifax | +1.833 |
andro | +1.802 |
peria | +1.788 |
Neg logit contributions | |
picking | -2.062 |
ILLE | -1.838 |
ECK | -1.829 |
Wester | -1.817 |
rol | -1.771 |
Token | Def |
Token ID | 2896 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
picking | +0.280 |
Wester | +0.250 |
ECK | +0.247 |
ILLE | +0.246 |
rol | +0.241 |
Neg logit contributions | |
ities | -0.365 |
ctors | -0.290 |
ifax | -0.275 |
andro | -0.275 |
peria | -0.273 |
Token | ending |
Token ID | 1571 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
picking | +0.416 |
Wester | +0.378 |
ECK | +0.372 |
ILLE | +0.371 |
rol | +0.365 |
Neg logit contributions | |
ities | -0.422 |
ctors | -0.325 |
ifax | -0.306 |
andro | -0.305 |
peria | -0.304 |
Token | battered |
Token ID | 33613 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
picking | +0.987 |
Wester | +0.890 |
ECK | +0.863 |
ILLE | +0.862 |
SUP | +0.847 |
Neg logit contributions | |
ities | -1.367 |
ctors | -1.099 |
ifax | -1.046 |
andro | -1.041 |
peria | -1.039 |
Token | Women |
Token ID | 6926 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
picking | +1.200 |
Wester | +1.050 |
ECK | +1.016 |
ILLE | +1.011 |
SUP | +0.982 |
Neg logit contributions | |
ities | -2.397 |
ctors | -1.980 |
ifax | -1.904 |
peria | -1.897 |
andro | -1.896 |
Token | on |
Token ID | 319 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
picking | +3.197 |
Wester | +2.899 |
ECK | +2.819 |
ILLE | +2.814 |
rol | +2.773 |
Neg logit contributions | |
ities | -3.919 |
ctors | -3.093 |
ifax | -2.967 |
peria | -2.948 |
andro | -2.942 |
Token | Trial |
Token ID | 21960 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
picking | +0.233 |
Wester | +0.204 |
ILLE | +0.203 |
ECK | +0.203 |
rol | +0.197 |
Neg logit contributions | |
ities | -0.350 |
ctors | -0.282 |
ifax | -0.269 |
andro | -0.268 |
peria | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
ities | +0.948 |
ctors | +0.732 |
ifax | +0.686 |
andro | +0.681 |
peria | +0.677 |
Neg logit contributions | |
picking | -0.895 |
ECK | -0.801 |
Wester | -0.801 |
ILLE | -0.795 |
rol | -0.778 |
Token | will |
Token ID | 481 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ities | +0.242 |
ctors | +0.191 |
ifax | +0.180 |
andro | +0.180 |
peria | +0.178 |
Neg logit contributions | |
picking | -0.199 |
Wester | -0.177 |
ECK | -0.176 |
ILLE | -0.176 |
rol | -0.171 |
Token | be |
Token ID | 307 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
picking | +1.153 |
Wester | +1.043 |
ECK | +1.025 |
ILLE | +1.021 |
rol | +1.004 |
Neg logit contributions | |
ities | -1.314 |
ctors | -1.028 |
ifax | -0.975 |
andro | -0.973 |
peria | -0.968 |
Token | released |
Token ID | 2716 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
picking | +0.309 |
Wester | +0.269 |
ILLE | +0.265 |
ECK | +0.263 |
rol | +0.256 |
Neg logit contributions | |
ities | -0.556 |
ctors | -0.454 |
ifax | -0.435 |
andro | -0.432 |
peria | -0.428 |
Token | Dec |
Token ID | 4280 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ities | +0.752 |
ctors | +0.595 |
ifax | +0.569 |
andro | +0.565 |
peria | +0.560 |
Neg logit contributions | |
picking | -0.543 |
Wester | -0.479 |
ECK | -0.478 |
ILLE | -0.477 |
rol | -0.463 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
picking | +0.052 |
ILLE | +0.046 |
ECK | +0.046 |
Wester | +0.046 |
rol | +0.045 |
Neg logit contributions | |
ities | -0.072 |
ctors | -0.058 |
ifax | -0.055 |
andro | -0.055 |
peria | -0.054 |
Token | 21 |
Token ID | 2310 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ities | +0.516 |
ctors | +0.409 |
ifax | +0.389 |
andro | +0.387 |
peria | +0.384 |
Neg logit contributions | |
picking | -0.389 |
Wester | -0.343 |
ECK | -0.341 |
ILLE | -0.340 |
rol | -0.334 |
Token | st |
Token ID | 301 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
picking | +0.472 |
Wester | +0.406 |
ILLE | +0.398 |
ECK | +0.398 |
rol | +0.386 |
Neg logit contributions | |
ities | -0.958 |
ctors | -0.792 |
ifax | -0.758 |
andro | -0.756 |
peria | -0.752 |
Token | century |
Token ID | 4289 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ities | +0.474 |
ctors | +0.378 |
andro | +0.354 |
ifax | +0.353 |
peria | +0.350 |
Neg logit contributions | |
picking | -0.370 |
Wester | -0.329 |
ECK | -0.326 |
ILLE | -0.326 |
rol | -0.317 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
picking | +2.959 |
Wester | +2.681 |
ECK | +2.597 |
ILLE | +2.588 |
SUP | +2.539 |
Neg logit contributions | |
ities | -4.042 |
ctors | -3.259 |
ifax | -3.110 |
peria | -3.107 |
andro | -3.095 |
Token | Hope |
Token ID | 13408 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
ities | +1.070 |
ctors | +0.846 |
ifax | +0.799 |
andro | +0.797 |
peria | +0.792 |
Neg logit contributions | |
picking | -0.869 |
Wester | -0.774 |
ECK | -0.766 |
ILLE | -0.766 |
rol | -0.749 |
Token | springs |
Token ID | 24747 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ities | +1.991 |
ctors | +1.555 |
ifax | +1.478 |
andro | +1.464 |
peria | +1.452 |
Neg logit contributions | |
picking | -1.671 |
ILLE | -1.486 |
ECK | -1.479 |
Wester | -1.459 |
SUP | -1.432 |
Token | eternal |
Token ID | 15851 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
picking | +2.006 |
Wester | +1.757 |
ECK | +1.715 |
ILLE | +1.707 |
rol | +1.666 |
Neg logit contributions | |
ities | -3.610 |
ctors | -2.963 |
ifax | -2.836 |
andro | -2.828 |
peria | -2.812 |
Token | among |
Token ID | 1871 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
ities | +3.027 |
ctors | +2.316 |
andro | +2.205 |
ifax | +2.200 |
peria | +2.185 |
Neg logit contributions | |
picking | -2.572 |
ILLE | -2.301 |
ECK | -2.283 |
Wester | -2.271 |
SUP | -2.217 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ities | +1.828 |
ctors | +1.445 |
ifax | +1.378 |
andro | +1.375 |
peria | +1.359 |
Neg logit contributions | |
picking | -1.323 |
ILLE | -1.159 |
ECK | -1.155 |
Wester | -1.146 |
rol | -1.127 |
Token | " |
Token ID | 366 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ities | +0.444 |
ctors | +0.351 |
ifax | +0.335 |
andro | +0.334 |
peria | +0.330 |
Neg logit contributions | |
picking | -0.327 |
Wester | -0.288 |
ECK | -0.287 |
ILLE | -0.287 |
rol | -0.280 |
Token | the |
Token ID | 262 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
picking | +0.076 |
Wester | +0.068 |
ECK | +0.066 |
ILLE | +0.066 |
rol | +0.065 |
Neg logit contributions | |
ities | -0.104 |
ctors | -0.083 |
ifax | -0.079 |
andro | -0.078 |
peria | -0.078 |
Token | serial |
Token ID | 11389 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ities | +0.219 |
ctors | +0.177 |
ifax | +0.168 |
andro | +0.168 |
peria | +0.167 |
Neg logit contributions | |
picking | -0.141 |
Wester | -0.124 |
ECK | -0.122 |
ILLE | -0.122 |
rol | -0.118 |
Token | cable |
Token ID | 7862 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ities | +1.069 |
ctors | +0.850 |
ifax | +0.806 |
andro | +0.804 |
peria | +0.798 |
Neg logit contributions | |
picking | -0.766 |
Wester | -0.680 |
ECK | -0.670 |
ILLE | -0.664 |
rol | -0.650 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
picking | +0.429 |
Wester | +0.386 |
ECK | +0.381 |
ILLE | +0.379 |
rol | +0.372 |
Neg logit contributions | |
ities | -0.517 |
ctors | -0.406 |
ifax | -0.384 |
andro | -0.382 |
peria | -0.381 |
Token | the |
Token ID | 262 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ities | +0.377 |
ctors | +0.302 |
ifax | +0.285 |
andro | +0.285 |
peria | +0.283 |
Neg logit contributions | |
picking | -0.277 |
Wester | -0.247 |
ECK | -0.243 |
ILLE | -0.243 |
rol | -0.237 |
Token | parallel |
Token ID | 10730 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
picking | +0.061 |
Wester | +0.053 |
ECK | +0.053 |
ILLE | +0.053 |
rol | +0.051 |
Neg logit contributions | |
ities | -0.097 |
ctors | -0.079 |
ifax | -0.075 |
andro | -0.075 |
peria | -0.075 |
Token | cable |
Token ID | 7862 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ities | +1.470 |
ctors | +1.170 |
ifax | +1.110 |
andro | +1.104 |
peria | +1.102 |
Neg logit contributions | |
picking | -1.022 |
Wester | -0.901 |
ECK | -0.894 |
ILLE | -0.890 |
rol | -0.870 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
picking | +0.782 |
Wester | +0.704 |
ECK | +0.694 |
ILLE | +0.693 |
rol | +0.678 |
Neg logit contributions | |
ities | -0.917 |
ctors | -0.718 |
ifax | -0.679 |
andro | -0.676 |
peria | -0.672 |
Token | the |
Token ID | 262 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
picking | +0.048 |
Wester | +0.043 |
ECK | +0.043 |
ILLE | +0.043 |
rol | +0.042 |
Neg logit contributions | |
ities | -0.064 |
ctors | -0.051 |
ifax | -0.048 |
andro | -0.048 |
peria | -0.048 |
Token | video |
Token ID | 2008 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
picking | +0.169 |
Wester | +0.149 |
ECK | +0.147 |
ILLE | +0.146 |
rol | +0.143 |
Neg logit contributions | |
ities | -0.248 |
ctors | -0.199 |
ifax | -0.190 |
andro | -0.189 |
peria | -0.188 |
Token | cable |
Token ID | 7862 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ities | +0.113 |
ctors | +0.091 |
andro | +0.086 |
ifax | +0.086 |
peria | +0.086 |
Neg logit contributions | |
picking | -0.074 |
Wester | -0.065 |
ECK | -0.064 |
ILLE | -0.064 |
rol | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
picking | +0.217 |
Wester | +0.193 |
ECK | +0.187 |
ILLE | +0.185 |
rol | +0.184 |
Neg logit contributions | |
ities | -0.343 |
ctors | -0.282 |
ifax | -0.275 |
peria | -0.271 |
andro | -0.271 |
Token | Of |
Token ID | 5189 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
ities | +0.192 |
ctors | +0.144 |
andro | +0.135 |
peria | +0.134 |
ifax | +0.134 |
Neg logit contributions | |
picking | -0.216 |
Wester | -0.199 |
ECK | -0.194 |
ILLE | -0.194 |
SUP | -0.192 |
Token | course |
Token ID | 1781 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
picking | +1.065 |
Wester | +0.952 |
ECK | +0.939 |
ILLE | +0.936 |
rol | +0.916 |
Neg logit contributions | |
ities | -1.372 |
ctors | -1.090 |
ifax | -1.036 |
andro | -1.031 |
peria | -1.027 |
Token | , |
Token ID | 11 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
picking | +0.326 |
Wester | +0.292 |
ECK | +0.292 |
ILLE | +0.290 |
SUP | +0.284 |
Neg logit contributions | |
ities | -0.366 |
ctors | -0.284 |
ifax | -0.269 |
andro | -0.267 |
peria | -0.266 |
Token | that |
Token ID | 326 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
picking | +0.595 |
Wester | +0.523 |
ECK | +0.517 |
ILLE | +0.516 |
rol | +0.502 |
Neg logit contributions | |
ities | -0.938 |
ctors | -0.758 |
ifax | -0.723 |
andro | -0.721 |
peria | -0.717 |
Token | doesn |
Token ID | 1595 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
picking | +0.381 |
Wester | +0.342 |
ECK | +0.338 |
ILLE | +0.338 |
rol | +0.330 |
Neg logit contributions | |
ities | -0.454 |
ctors | -0.357 |
ifax | -0.338 |
andro | -0.336 |
peria | -0.335 |
Token | 't |
Token ID | 470 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
ities | +0.872 |
ctors | +0.656 |
ifax | +0.632 |
peria | +0.620 |
andro | +0.610 |
Neg logit contributions | |
picking | -1.131 |
Wester | -1.040 |
ECK | -1.022 |
ILLE | -1.014 |
rol | -1.011 |
Token | always |
Token ID | 1464 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
picking | +1.852 |
Wester | +1.690 |
SUP | +1.607 |
ECK | +1.593 |
rol | +1.593 |
Neg logit contributions | |
ities | -2.541 |
ctors | -2.039 |
peria | -1.983 |
ifax | -1.982 |
andro | -1.967 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
picking | +2.126 |
Wester | +1.945 |
SUP | +1.857 |
ECK | +1.854 |
rol | +1.843 |
Neg logit contributions | |
ities | -2.772 |
ctors | -2.222 |
ifax | -2.148 |
peria | -2.135 |
andro | -2.112 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
picking | +0.449 |
Wester | +0.401 |
ECK | +0.396 |
ILLE | +0.395 |
rol | +0.386 |
Neg logit contributions | |
ities | -0.574 |
ctors | -0.455 |
ifax | -0.431 |
andro | -0.430 |
peria | -0.427 |
Token | Mer |
Token ID | 4638 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
picking | +0.842 |
Wester | +0.758 |
ECK | +0.740 |
ILLE | +0.738 |
SUP | +0.722 |
Neg logit contributions | |
ities | -1.134 |
ctors | -0.904 |
ifax | -0.864 |
andro | -0.859 |
peria | -0.857 |
Token | but |
Token ID | 475 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ities | +0.903 |
ctors | +0.703 |
andro | +0.664 |
ifax | +0.662 |
peria | +0.655 |
Neg logit contributions | |
picking | -0.782 |
Wester | -0.702 |
ILLE | -0.695 |
ECK | -0.693 |
rol | -0.677 |
Token | know |
Token ID | 760 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
ities | +4.791 |
ctors | +3.703 |
andro | +3.555 |
ifax | +3.466 |
peria | +3.347 |
Neg logit contributions | |
picking | -4.012 |
ILLE | -3.578 |
ECK | -3.534 |
Wester | -3.524 |
AKING | -3.426 |
Token | themselves |
Token ID | 2405 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ities | +2.969 |
ctors | +2.351 |
andro | +2.262 |
ifax | +2.224 |
peria | +2.171 |
Neg logit contributions | |
picking | -2.204 |
ECK | -1.944 |
ILLE | -1.931 |
Wester | -1.929 |
rol | -1.879 |
Token | to |
Token ID | 284 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
picking | +1.209 |
Wester | +1.087 |
ILLE | +1.065 |
ECK | +1.064 |
rol | +1.043 |
Neg logit contributions | |
ities | -1.523 |
ctors | -1.209 |
ifax | -1.148 |
peria | -1.143 |
andro | -1.140 |
Token | be |
Token ID | 307 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ities | +0.269 |
ctors | +0.207 |
andro | +0.195 |
ifax | +0.194 |
peria | +0.192 |
Neg logit contributions | |
picking | -0.260 |
Wester | -0.234 |
ECK | -0.232 |
ILLE | -0.232 |
rol | -0.227 |
Token | male |
Token ID | 4257 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ities | +1.927 |
ctors | +1.549 |
andro | +1.504 |
ifax | +1.479 |
peria | +1.450 |
Neg logit contributions | |
picking | -1.194 |
ECK | -1.029 |
ILLE | -1.026 |
Wester | -1.019 |
rol | -1.000 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ities | +3.305 |
ctors | +2.531 |
andro | +2.430 |
ifax | +2.409 |
peria | +2.315 |
Neg logit contributions | |
picking | -2.856 |
ECK | -2.567 |
Wester | -2.549 |
ILLE | -2.541 |
rol | -2.461 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ities | +0.448 |
ctors | +0.352 |
andro | +0.335 |
ifax | +0.334 |
peria | +0.330 |
Neg logit contributions | |
picking | -0.372 |
Wester | -0.333 |
ECK | -0.329 |
ILLE | -0.329 |
rol | -0.322 |
Token | wish |
Token ID | 4601 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
picking | +0.257 |
Wester | +0.230 |
ECK | +0.226 |
ILLE | +0.226 |
rol | +0.221 |
Neg logit contributions | |
ities | -0.324 |
ctors | -0.257 |
ifax | -0.244 |
andro | -0.243 |
peria | -0.242 |
Token | to |
Token ID | 284 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
picking | +0.467 |
Wester | +0.418 |
ECK | +0.413 |
ILLE | +0.411 |
rol | +0.401 |
Neg logit contributions | |
ities | -0.572 |
ctors | -0.452 |
andro | -0.427 |
ifax | -0.425 |
peria | -0.420 |
Token | be |
Token ID | 307 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
ities | +0.711 |
ctors | +0.561 |
ifax | +0.532 |
andro | +0.530 |
peria | +0.527 |
Neg logit contributions | |
picking | -0.579 |
Wester | -0.519 |
ECK | -0.511 |
ILLE | -0.511 |
rol | -0.499 |
Token | Sw |
Token ID | 2451 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ities | +0.018 |
ctors | +0.015 |
ifax | +0.014 |
andro | +0.014 |
peria | +0.014 |
Neg logit contributions | |
picking | -0.012 |
Wester | -0.011 |
ECK | -0.010 |
ILLE | -0.010 |
rol | -0.010 |
Token | immer |
Token ID | 10957 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
picking | +0.929 |
Wester | +0.846 |
ECK | +0.835 |
ILLE | +0.834 |
rol | +0.816 |
Neg logit contributions | |
ities | -0.893 |
ctors | -0.682 |
ifax | -0.641 |
andro | -0.638 |
peria | -0.634 |
Token | means |
Token ID | 1724 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
picking | +2.001 |
Wester | +1.793 |
ECK | +1.762 |
ILLE | +1.760 |
rol | +1.724 |
Neg logit contributions | |
ities | -2.480 |
ctors | -1.967 |
ifax | -1.865 |
andro | -1.862 |
peria | -1.851 |
Token | to |
Token ID | 284 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
picking | +0.135 |
Wester | +0.122 |
ECK | +0.120 |
ILLE | +0.120 |
rol | +0.117 |
Neg logit contributions | |
ities | -0.165 |
ctors | -0.129 |
ifax | -0.122 |
andro | -0.122 |
peria | -0.121 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ities | +1.535 |
ctors | +1.187 |
ifax | +1.113 |
andro | +1.112 |
peria | +1.105 |
Neg logit contributions | |
picking | -1.414 |
Wester | -1.272 |
ILLE | -1.265 |
ECK | -1.262 |
rol | -1.225 |
Token | fit |
Token ID | 4197 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ities | +4.520 |
ctors | +3.548 |
andro | +3.404 |
ifax | +3.389 |
peria | +3.361 |
Neg logit contributions | |
picking | -3.220 |
ILLE | -2.881 |
Wester | -2.880 |
ECK | -2.848 |
rol | -2.736 |
Token | moving |
Token ID | 3867 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
ities | +6.969 |
ctors | +5.406 |
andro | +5.149 |
ifax | +5.057 |
peria | +4.988 |
Neg logit contributions | |
picking | -5.170 |
ILLE | -4.739 |
ECK | -4.716 |
Wester | -4.690 |
rol | -4.534 |
Token | about |
Token ID | 546 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
ities | +2.486 |
ctors | +1.877 |
andro | +1.743 |
ifax | +1.739 |
peria | +1.713 |
Neg logit contributions | |
picking | -2.521 |
ILLE | -2.292 |
Wester | -2.285 |
ECK | -2.283 |
rol | -2.211 |
Token | ( |
Token ID | 357 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
picking | +0.009 |
Wester | +0.008 |
ECK | +0.008 |
ILLE | +0.008 |
rol | +0.007 |
Neg logit contributions | |
ities | -0.010 |
ctors | -0.008 |
ifax | -0.008 |
andro | -0.008 |
peria | -0.008 |
Token | 7 |
Token ID | 22 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
ities | +0.807 |
ctors | +0.630 |
andro | +0.599 |
peria | +0.590 |
ifax | +0.590 |
Neg logit contributions | |
picking | -0.722 |
Wester | -0.662 |
ILLE | -0.647 |
ECK | -0.645 |
SUP | -0.634 |
Token | ) |
Token ID | 8 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ities | +2.023 |
ctors | +1.482 |
ifax | +1.358 |
andro | +1.356 |
peria | +1.318 |
Neg logit contributions | |
picking | -2.629 |
Wester | -2.412 |
ILLE | -2.393 |
ECK | -2.379 |
rol | -2.326 |
Token | ian |
Token ID | 666 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
picking | +1.563 |
rol | +1.454 |
Wester | +1.445 |
ECK | +1.425 |
rail | +1.423 |
Neg logit contributions | |
ities | -0.787 |
ctors | -0.543 |
peria | -0.473 |
ifax | -0.471 |
andro | -0.452 |
Token | said |
Token ID | 531 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
picking | +0.441 |
Wester | +0.397 |
ECK | +0.391 |
ILLE | +0.390 |
rol | +0.382 |
Neg logit contributions | |
ities | -0.513 |
ctors | -0.403 |
ifax | -0.381 |
andro | -0.380 |
peria | -0.378 |
Token | he |
Token ID | 339 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
picking | +0.531 |
Wester | +0.472 |
ECK | +0.464 |
ILLE | +0.464 |
rol | +0.453 |
Neg logit contributions | |
ities | -0.745 |
ctors | -0.597 |
ifax | -0.568 |
andro | -0.566 |
peria | -0.563 |
Token | found |
Token ID | 1043 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
picking | +0.003 |
Wester | +0.003 |
ILLE | +0.003 |
ECK | +0.003 |
rol | +0.003 |
Neg logit contributions | |
ities | -0.004 |
ctors | -0.003 |
ifax | -0.003 |
andro | -0.003 |
peria | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ities | +0.484 |
ctors | +0.386 |
ifax | +0.368 |
andro | +0.367 |
peria | +0.364 |
Neg logit contributions | |
picking | -0.329 |
Wester | -0.290 |
ECK | -0.288 |
ILLE | -0.286 |
rol | -0.280 |
Token | hard |
Token ID | 1327 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
picking | +0.477 |
Wester | +0.418 |
ECK | +0.410 |
ILLE | +0.410 |
rol | +0.399 |
Neg logit contributions | |
ities | -0.787 |
ctors | -0.641 |
ifax | -0.612 |
andro | -0.611 |
peria | -0.608 |
Token | to |
Token ID | 284 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ities | +5.499 |
ctors | +4.173 |
ifax | +3.899 |
andro | +3.842 |
peria | +3.739 |
Neg logit contributions | |
picking | -5.112 |
Wester | -4.727 |
ECK | -4.700 |
ILLE | -4.661 |
SUP | -4.538 |
Token | believe |
Token ID | 1975 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
ities | +1.334 |
ctors | +1.058 |
ifax | +0.987 |
andro | +0.987 |
peria | +0.979 |
Neg logit contributions | |
picking | -1.068 |
Wester | -0.954 |
ILLE | -0.948 |
ECK | -0.947 |
rol | -0.922 |
Token | that |
Token ID | 326 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ities | +2.806 |
ctors | +2.205 |
ifax | +2.103 |
andro | +2.085 |
peria | +2.079 |
Neg logit contributions | |
picking | -2.062 |
ECK | -1.816 |
ILLE | -1.811 |
Wester | -1.798 |
rol | -1.760 |
Token | Jack |
Token ID | 3619 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
picking | +0.824 |
Wester | +0.728 |
ECK | +0.715 |
ILLE | +0.713 |
rol | +0.695 |
Neg logit contributions | |
ities | -1.274 |
ctors | -1.031 |
ifax | -0.984 |
andro | -0.981 |
peria | -0.976 |
Token | now |
Token ID | 2197 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ities | +2.683 |
ctors | +2.116 |
ifax | +2.068 |
andro | +2.050 |
peria | +2.009 |
Neg logit contributions | |
picking | -1.971 |
ILLE | -1.741 |
ECK | -1.734 |
Wester | -1.705 |
SUP | -1.655 |
Token | . |
Token ID | 13 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
picking | +1.792 |
Wester | +1.604 |
ECK | +1.568 |
ILLE | +1.564 |
rol | +1.535 |
Neg logit contributions | |
ities | -2.326 |
ctors | -1.856 |
ifax | -1.763 |
andro | -1.759 |
peria | -1.752 |
Token | While |
Token ID | 2893 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ities | +0.175 |
ctors | +0.138 |
ifax | +0.129 |
andro | +0.129 |
peria | +0.128 |
Neg logit contributions | |
picking | -0.154 |
Wester | -0.137 |
ECK | -0.136 |
ILLE | -0.136 |
rol | -0.133 |
Token | he |
Token ID | 339 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
picking | +0.432 |
Wester | +0.382 |
ECK | +0.379 |
ILLE | +0.377 |
rol | +0.368 |
Neg logit contributions | |
ities | -0.618 |
ctors | -0.494 |
ifax | -0.471 |
andro | -0.470 |
peria | -0.466 |
Token | should |
Token ID | 815 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
picking | +1.017 |
Wester | +0.913 |
ECK | +0.900 |
ILLE | +0.899 |
rol | +0.878 |
Neg logit contributions | |
ities | -1.245 |
ctors | -0.982 |
ifax | -0.930 |
andro | -0.928 |
peria | -0.921 |
Token | be |
Token ID | 307 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ities | +2.720 |
ctors | +2.127 |
ifax | +1.955 |
andro | +1.954 |
peria | +1.925 |
Neg logit contributions | |
picking | -2.489 |
ILLE | -2.282 |
ECK | -2.250 |
Wester | -2.229 |
SUP | -2.150 |
Token | able |
Token ID | 1498 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ities | +1.894 |
ctors | +1.495 |
ifax | +1.428 |
andro | +1.416 |
peria | +1.410 |
Neg logit contributions | |
picking | -1.446 |
Wester | -1.281 |
ILLE | -1.278 |
ECK | -1.275 |
rol | -1.235 |
Token | to |
Token ID | 284 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ities | +6.029 |
ctors | +4.638 |
ifax | +4.385 |
andro | +4.363 |
peria | +4.307 |
Neg logit contributions | |
picking | -5.313 |
ECK | -4.798 |
ILLE | -4.796 |
Wester | -4.751 |
SUP | -4.608 |
Token | return |
Token ID | 1441 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ities | +0.576 |
ctors | +0.457 |
ifax | +0.432 |
andro | +0.430 |
peria | +0.428 |
Neg logit contributions | |
picking | -0.450 |
Wester | -0.400 |
ECK | -0.397 |
ILLE | -0.397 |
rol | -0.386 |
Token | fairly |
Token ID | 6547 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ities | +0.091 |
ctors | +0.071 |
ifax | +0.068 |
andro | +0.068 |
peria | +0.067 |
Neg logit contributions | |
picking | -0.070 |
Wester | -0.062 |
ECK | -0.062 |
ILLE | -0.062 |
rol | -0.060 |
Token | early |
Token ID | 1903 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
picking | +0.074 |
Wester | +0.064 |
ECK | +0.063 |
ILLE | +0.063 |
rol | +0.061 |
Neg logit contributions | |
ities | -0.149 |
ctors | -0.122 |
ifax | -0.117 |
andro | -0.117 |
peria | -0.116 |
Token | in |
Token ID | 287 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
picking | +1.481 |
Wester | +1.321 |
ECK | +1.292 |
ILLE | +1.288 |
rol | +1.264 |
Neg logit contributions | |
ities | -1.996 |
ctors | -1.604 |
andro | -1.521 |
ifax | -1.519 |
peria | -1.512 |
Token | vs |
Token ID | 3691 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
picking | +1.768 |
Wester | +1.586 |
ECK | +1.559 |
ILLE | +1.553 |
rol | +1.524 |
Neg logit contributions | |
ities | -2.231 |
ctors | -1.770 |
ifax | -1.679 |
andro | -1.675 |
peria | -1.665 |
Token | Sak |
Token ID | 13231 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
picking | +1.181 |
Wester | +1.047 |
ECK | +1.027 |
ILLE | +1.025 |
rol | +1.001 |
Neg logit contributions | |
ities | -1.751 |
ctors | -1.412 |
ifax | -1.346 |
andro | -1.342 |
peria | -1.335 |
Token | ash |
Token ID | 1077 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ities | +0.351 |
ctors | +0.274 |
andro | +0.259 |
ifax | +0.258 |
peria | +0.258 |
Neg logit contributions | |
picking | -0.315 |
Wester | -0.284 |
ILLE | -0.281 |
ECK | -0.281 |
SUP | -0.273 |
Token | ima |
Token ID | 8083 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
picking | +1.561 |
Wester | +1.416 |
ECK | +1.392 |
ILLE | +1.390 |
rol | +1.370 |
Neg logit contributions | |
ities | -1.627 |
ctors | -1.261 |
ifax | -1.189 |
andro | -1.185 |
peria | -1.177 |
Token | the |
Token ID | 262 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ities | +0.259 |
ctors | +0.206 |
ifax | +0.196 |
andro | +0.196 |
peria | +0.195 |
Neg logit contributions | |
picking | -0.190 |
Wester | -0.167 |
ILLE | -0.167 |
ECK | -0.166 |
rol | -0.161 |
Token | Im |
Token ID | 1846 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
picking | +0.697 |
Wester | +0.617 |
ECK | +0.607 |
ILLE | +0.606 |
rol | +0.591 |
Neg logit contributions | |
ities | -1.037 |
ctors | -0.836 |
ifax | -0.796 |
andro | -0.794 |
peria | -0.790 |
Token | post |
Token ID | 7353 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ities | +5.704 |
peria | +4.195 |
ctors | +4.161 |
andro | +4.052 |
ifax | +4.021 |
Neg logit contributions | |
picking | -6.106 |
ILLE | -5.992 |
ECK | -5.804 |
Wester | -5.754 |
SUP | -5.537 |
Token | or |
Token ID | 273 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
ities | +2.049 |
ctors | +1.400 |
ifax | +1.306 |
andro | +1.302 |
peria | +1.269 |
Neg logit contributions | |
picking | -3.232 |
ILLE | -3.020 |
Wester | -3.007 |
ECK | -2.968 |
SUP | -2.916 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
ities | +1.304 |
ctors | +1.024 |
ifax | +0.968 |
andro | +0.966 |
peria | +0.959 |
Neg logit contributions | |
picking | -1.060 |
ILLE | -0.946 |
Wester | -0.945 |
ECK | -0.936 |
rol | -0.901 |
Token |
|
Token ID | 198 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
picking | +0.790 |
Wester | +0.705 |
ECK | +0.671 |
rol | +0.667 |
SUP | +0.664 |
Neg logit contributions | |
ities | -1.319 |
ctors | -1.103 |
ifax | -1.075 |
peria | -1.064 |
andro | -1.058 |
Token | H |
Token ID | 39 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
picking | +0.675 |
Wester | +0.612 |
ECK | +0.600 |
ILLE | +0.600 |
rol | +0.588 |
Neg logit contributions | |
ities | -0.738 |
ctors | -0.573 |
andro | -0.541 |
ifax | -0.539 |
peria | -0.538 |
Token |
|
Token ID | 198 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ities | +1.202 |
ctors | +0.978 |
ifax | +0.940 |
andro | +0.932 |
peria | +0.932 |
Neg logit contributions | |
picking | -0.815 |
Wester | -0.731 |
ECK | -0.708 |
ILLE | -0.708 |
SUP | -0.698 |
Token | Russia |
Token ID | 16347 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
ities | +1.406 |
ctors | +1.085 |
andro | +1.020 |
ifax | +1.008 |
peria | +1.008 |
Neg logit contributions | |
picking | -1.347 |
Wester | -1.232 |
ECK | -1.197 |
ILLE | -1.190 |
SUP | -1.175 |
Token | 's |
Token ID | 338 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
picking | +0.185 |
Wester | +0.166 |
ECK | +0.164 |
ILLE | +0.163 |
rol | +0.159 |
Neg logit contributions | |
ities | -0.229 |
ctors | -0.181 |
ifax | -0.172 |
andro | -0.171 |
peria | -0.170 |
Token | President |
Token ID | 1992 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
picking | +0.639 |
Wester | +0.575 |
ECK | +0.573 |
ILLE | +0.572 |
rol | +0.559 |
Neg logit contributions | |
ities | -0.642 |
ctors | -0.492 |
andro | -0.461 |
ifax | -0.461 |
peria | -0.458 |
Token | Vladimir |
Token ID | 14840 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
picking | +0.077 |
Wester | +0.068 |
ECK | +0.067 |
ILLE | +0.067 |
rol | +0.065 |
Neg logit contributions | |
ities | -0.096 |
ctors | -0.076 |
andro | -0.072 |
ifax | -0.071 |
peria | -0.071 |
Token | Putin |
Token ID | 8144 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ities | +3.771 |
ctors | +2.925 |
andro | +2.757 |
ifax | +2.743 |
peria | +2.717 |
Neg logit contributions | |
picking | -3.259 |
ECK | -2.908 |
ILLE | -2.884 |
Wester | -2.866 |
rol | -2.773 |
Token | chairs |
Token ID | 18791 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
ities | +5.649 |
ctors | +4.356 |
andro | +4.048 |
ifax | +4.025 |
fen | +3.863 |
Neg logit contributions | |
picking | -5.351 |
ILLE | -4.823 |
ECK | -4.771 |
Wester | -4.689 |
rol | -4.604 |
Token | a |
Token ID | 257 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
picking | +1.789 |
Wester | +1.611 |
ECK | +1.565 |
ILLE | +1.554 |
SUP | +1.544 |
Neg logit contributions | |
ities | -2.609 |
ctors | -2.118 |
ifax | -2.019 |
andro | -2.012 |
peria | -2.002 |
Token | meeting |
Token ID | 3249 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
ities | +0.886 |
ctors | +0.689 |
ifax | +0.649 |
andro | +0.647 |
peria | +0.644 |
Neg logit contributions | |
picking | -0.812 |
Wester | -0.732 |
ECK | -0.724 |
ILLE | -0.723 |
rol | -0.708 |
Token | with |
Token ID | 351 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
ities | +0.183 |
ctors | +0.144 |
ifax | +0.137 |
andro | +0.136 |
peria | +0.136 |
Neg logit contributions | |
picking | -0.143 |
Wester | -0.128 |
ECK | -0.127 |
ILLE | -0.126 |
rol | -0.123 |
Token | government |
Token ID | 1230 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
picking | +0.140 |
Wester | +0.126 |
ECK | +0.123 |
ILLE | +0.123 |
rol | +0.120 |
Neg logit contributions | |
ities | -0.183 |
ctors | -0.146 |
ifax | -0.138 |
andro | -0.138 |
peria | -0.137 |