Token |
|
Token ID | 198 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
ubes | +2.681 |
hib | +2.457 |
atri | +2.434 |
utenberg | +2.399 |
netflix | +2.392 |
Neg logit contributions | |
Sioux | -3.389 |
Red | -3.269 |
Pt | -3.250 |
RED | -3.198 |
Clarks | -3.149 |
Token |
|
Token ID | 198 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
ubes | +0.576 |
atri | +0.528 |
hib | +0.522 |
utenberg | +0.512 |
netflix | +0.510 |
Neg logit contributions | |
Sioux | -0.636 |
Red | -0.628 |
Pt | -0.619 |
RED | -0.608 |
Clarks | -0.585 |
Token | Thank |
Token ID | 10449 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
ubes | +0.643 |
atri | +0.591 |
hib | +0.583 |
utenberg | +0.573 |
netflix | +0.568 |
Neg logit contributions | |
Sioux | -0.831 |
Red | -0.828 |
Pt | -0.811 |
RED | -0.802 |
Clarks | -0.768 |
Token | you |
Token ID | 345 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
ubes | +2.249 |
atri | +2.022 |
hib | +2.015 |
netflix | +1.984 |
utenberg | +1.966 |
Neg logit contributions | |
Sioux | -2.278 |
Red | -2.202 |
Pt | -2.195 |
RED | -2.138 |
Clarks | -2.079 |
Token | for |
Token ID | 329 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ubes | +4.115 |
hib | +3.796 |
atri | +3.779 |
utenberg | +3.641 |
netflix | +3.634 |
Neg logit contributions | |
Sioux | -3.851 |
Pt | -3.766 |
Red | -3.716 |
RED | -3.647 |
Clarks | -3.603 |
Token | signing |
Token ID | 8415 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
ubes | +2.683 |
atri | +2.522 |
hib | +2.487 |
netflix | +2.417 |
utenberg | +2.411 |
Neg logit contributions | |
Sioux | -2.128 |
Red | -2.091 |
Pt | -2.073 |
RED | -2.020 |
Clarks | -1.929 |
Token | up |
Token ID | 510 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ubes | +5.246 |
hib | +4.728 |
netflix | +4.664 |
atri | +4.492 |
utenberg | +4.444 |
Neg logit contributions | |
Sioux | -7.961 |
Pt | -7.688 |
RED | -7.651 |
Clarks | -7.599 |
Red | -7.501 |
Token | . |
Token ID | 13 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
ubes | +1.799 |
atri | +1.652 |
hib | +1.635 |
netflix | +1.589 |
utenberg | +1.588 |
Neg logit contributions | |
Sioux | -1.805 |
Red | -1.767 |
Pt | -1.747 |
RED | -1.730 |
Clarks | -1.668 |
Token | For |
Token ID | 1114 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ubes | +2.467 |
atri | +2.241 |
hib | +2.234 |
netflix | +2.149 |
UTERS | +2.143 |
Neg logit contributions | |
Sioux | -3.334 |
Red | -3.230 |
Pt | -3.222 |
RED | -3.197 |
Clarks | -3.093 |
Token | more |
Token ID | 517 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ubes | +1.630 |
atri | +1.511 |
hib | +1.495 |
netflix | +1.489 |
utenberg | +1.470 |
Neg logit contributions | |
Sioux | -1.448 |
Pt | -1.404 |
Red | -1.398 |
RED | -1.366 |
Clarks | -1.316 |
Token | from |
Token ID | 422 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ubes | +1.594 |
atri | +1.483 |
netflix | +1.448 |
hib | +1.446 |
utenberg | +1.431 |
Neg logit contributions | |
Sioux | -1.013 |
Red | -0.981 |
Pt | -0.976 |
RED | -0.950 |
Clarks | -0.916 |
Token | MORE |
Token ID | 12011 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ubes | +2.025 |
atri | +1.888 |
netflix | +1.845 |
hib | +1.845 |
utenberg | +1.835 |
Neg logit contributions | |
Red | -1.614 |
Sioux | -1.568 |
Pt | -1.553 |
RED | -1.530 |
White | -1.437 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ubes | +0.156 |
atri | +0.146 |
hib | +0.144 |
utenberg | +0.143 |
netflix | +0.143 |
Neg logit contributions | |
Red | -0.084 |
Sioux | -0.082 |
Pt | -0.081 |
RED | -0.078 |
White | -0.073 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
ubes | +1.845 |
atri | +1.715 |
hib | +1.677 |
utenberg | +1.672 |
netflix | +1.658 |
Neg logit contributions | |
Red | -1.500 |
Sioux | -1.485 |
Pt | -1.465 |
RED | -1.431 |
Clarks | -1.323 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Red | +0.514 |
Sioux | +0.509 |
Pt | +0.502 |
RED | +0.490 |
Clarks | +0.454 |
Neg logit contributions | |
ubes | -0.628 |
atri | -0.583 |
hib | -0.571 |
utenberg | -0.569 |
netflix | -0.564 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +7.04e+00 |
Pos logit contributions | |
ubes | +0.791 |
atri | +0.737 |
hib | +0.723 |
utenberg | +0.721 |
netflix | +0.716 |
Neg logit contributions | |
Red | -0.607 |
Sioux | -0.599 |
Pt | -0.590 |
RED | -0.576 |
White | -0.533 |
Token | Diane |
Token ID | 26542 |
Feature activation | +9.30e+00 |
Pos logit contributions | |
ubes | +4.352 |
atri | +3.967 |
hib | +3.943 |
UTERS | +3.790 |
utenberg | +3.744 |
Neg logit contributions | |
Sioux | -5.644 |
Pt | -5.618 |
Red | -5.503 |
RED | -5.457 |
Lyme | -5.232 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
ubes | +5.190 |
atri | +4.822 |
UTERS | +4.732 |
netflix | +4.629 |
ictionary | +4.569 |
Neg logit contributions | |
Pt | -7.795 |
Sioux | -7.754 |
Red | -7.391 |
RED | -7.352 |
pt | -7.160 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ubes | +3.530 |
atri | +3.242 |
hib | +3.171 |
UTERS | +3.118 |
utenberg | +3.115 |
Neg logit contributions | |
Sioux | -3.296 |
Pt | -3.288 |
Red | -3.279 |
RED | -3.184 |
Clarks | -2.944 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
ubes | +1.651 |
atri | +1.503 |
utenberg | +1.476 |
hib | +1.460 |
netflix | +1.449 |
Neg logit contributions | |
Red | -2.023 |
Sioux | -1.995 |
Pt | -1.970 |
RED | -1.939 |
White | -1.835 |
Token | : |
Token ID | 25 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ubes | +2.528 |
atri | +2.316 |
hib | +2.283 |
netflix | +2.240 |
utenberg | +2.233 |
Neg logit contributions | |
Sioux | -2.642 |
Red | -2.642 |
Pt | -2.610 |
RED | -2.548 |
Clarks | -2.384 |
Token | ' |
Token ID | 705 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Red | +1.376 |
Sioux | +1.293 |
Pt | +1.245 |
RED | +1.241 |
White | +1.156 |
Neg logit contributions | |
ubes | -2.586 |
atri | -2.410 |
utenberg | -2.394 |
hib | -2.377 |
netflix | -2.377 |
Token | In |
Token ID | 818 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ubes | +2.317 |
atri | +2.104 |
hib | +2.034 |
utenberg | +2.020 |
netflix | +2.010 |
Neg logit contributions | |
Red | -3.188 |
Sioux | -3.166 |
Pt | -3.115 |
RED | -3.082 |
Clarks | -2.904 |
Token | Memory |
Token ID | 30871 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ubes | +1.029 |
atri | +0.932 |
hib | +0.929 |
UTERS | +0.891 |
utenberg | +0.887 |
Neg logit contributions | |
Sioux | -1.544 |
Red | -1.531 |
Pt | -1.508 |
RED | -1.495 |
Clarks | -1.436 |
Token | 4 |
Token ID | 604 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
Red | +0.754 |
Sioux | +0.736 |
Pt | +0.731 |
RED | +0.709 |
White | +0.647 |
Neg logit contributions | |
ubes | -1.218 |
atri | -1.141 |
utenberg | -1.122 |
hib | -1.119 |
netflix | -1.107 |
Token | 66 |
Token ID | 2791 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
ubes | +4.183 |
atri | +3.834 |
hib | +3.722 |
utenberg | +3.684 |
netflix | +3.659 |
Neg logit contributions | |
Sioux | -4.714 |
Red | -4.705 |
Pt | -4.646 |
RED | -4.560 |
Clarks | -4.290 |
Token | 284 |
Token ID | 30336 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ubes | +4.237 |
atri | +3.952 |
hib | +3.896 |
utenberg | +3.843 |
netflix | +3.805 |
Neg logit contributions | |
Sioux | -3.560 |
Red | -3.559 |
Pt | -3.500 |
RED | -3.409 |
Clarks | -3.184 |
Token | 4 |
Token ID | 604 |
Feature activation | +8.96e+00 |
Pos logit contributions | |
ubes | +1.887 |
atri | +1.777 |
hib | +1.726 |
utenberg | +1.713 |
netflix | +1.705 |
Neg logit contributions | |
Sioux | -1.271 |
Red | -1.260 |
Pt | -1.230 |
RED | -1.203 |
Clarks | -1.145 |
Token | 64 |
Token ID | 2414 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
ubes | +5.126 |
atri | +4.410 |
hib | +4.401 |
netflix | +4.280 |
UTERS | +4.210 |
Neg logit contributions | |
Sioux | -7.675 |
Pt | -7.443 |
Red | -7.338 |
RED | -7.329 |
Clarks | -7.258 |
Token | 406 |
Token ID | 29703 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ubes | +0.566 |
atri | +0.524 |
hib | +0.516 |
netflix | +0.510 |
utenberg | +0.510 |
Neg logit contributions | |
Red | -0.429 |
Sioux | -0.429 |
Pt | -0.415 |
RED | -0.412 |
Clarks | -0.380 |
Token | Mem |
Token ID | 4942 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
Red | +0.568 |
Sioux | +0.567 |
Pt | +0.550 |
RED | +0.529 |
Clarks | +0.471 |
Neg logit contributions | |
ubes | -1.425 |
atri | -1.346 |
hib | -1.327 |
utenberg | -1.317 |
netflix | -1.311 |
Token | c |
Token ID | 66 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
Red | +1.896 |
Sioux | +1.856 |
Pt | +1.831 |
RED | +1.772 |
White | +1.612 |
Neg logit contributions | |
ubes | -3.417 |
atri | -3.210 |
utenberg | -3.153 |
hib | -3.149 |
netflix | -3.123 |
Token | py |
Token ID | 9078 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Red | +1.344 |
Sioux | +1.327 |
Pt | +1.294 |
RED | +1.259 |
Clarks | +1.135 |
Neg logit contributions | |
ubes | -2.678 |
atri | -2.521 |
hib | -2.479 |
utenberg | -2.474 |
netflix | -2.458 |
Token | In |
Token ID | 818 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ubes | +2.123 |
atri | +1.926 |
hib | +1.864 |
utenberg | +1.847 |
netflix | +1.839 |
Neg logit contributions | |
Red | -2.957 |
Sioux | -2.933 |
Pt | -2.889 |
RED | -2.856 |
Clarks | -2.693 |
Token | Memory |
Token ID | 30871 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ubes | +0.983 |
atri | +0.892 |
hib | +0.891 |
UTERS | +0.853 |
utenberg | +0.849 |
Neg logit contributions | |
Sioux | -1.480 |
Red | -1.469 |
Pt | -1.446 |
RED | -1.435 |
Clarks | -1.377 |
Token | 4 |
Token ID | 604 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
Red | +1.028 |
Sioux | +0.997 |
Pt | +0.997 |
RED | +0.965 |
White | +0.869 |
Neg logit contributions | |
ubes | -1.888 |
atri | -1.768 |
hib | -1.740 |
utenberg | -1.740 |
netflix | -1.718 |
Token | 66 |
Token ID | 2791 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
ubes | +4.016 |
atri | +3.623 |
hib | +3.473 |
UTERS | +3.342 |
netflix | +3.337 |
Neg logit contributions | |
Sioux | -5.521 |
Pt | -5.370 |
Red | -5.355 |
RED | -5.280 |
Clarks | -5.146 |
Token | 284 |
Token ID | 30336 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ubes | +3.660 |
atri | +3.394 |
hib | +3.381 |
utenberg | +3.260 |
netflix | +3.219 |
Neg logit contributions | |
Sioux | -3.651 |
Red | -3.576 |
Pt | -3.572 |
RED | -3.452 |
Clarks | -3.351 |
Token | 4 |
Token ID | 604 |
Feature activation | +8.79e+00 |
Pos logit contributions | |
ubes | +1.636 |
atri | +1.539 |
hib | +1.497 |
utenberg | +1.486 |
netflix | +1.473 |
Neg logit contributions | |
Sioux | -1.152 |
Red | -1.133 |
Pt | -1.109 |
RED | -1.084 |
Clarks | -1.046 |
Token | 64 |
Token ID | 2414 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
ubes | +4.991 |
atri | +4.288 |
hib | +4.286 |
netflix | +4.130 |
UTERS | +4.066 |
Neg logit contributions | |
Sioux | -7.660 |
Pt | -7.408 |
Red | -7.311 |
RED | -7.306 |
Clarks | -7.291 |
Token | 406 |
Token ID | 29703 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
ubes | +0.075 |
atri | +0.069 |
hib | +0.068 |
utenberg | +0.067 |
netflix | +0.067 |
Neg logit contributions | |
Red | -0.055 |
Sioux | -0.055 |
Pt | -0.053 |
RED | -0.053 |
Clarks | -0.049 |
Token | Mem |
Token ID | 4942 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
Sioux | +0.332 |
Red | +0.327 |
Pt | +0.321 |
RED | +0.308 |
Clarks | +0.278 |
Neg logit contributions | |
ubes | -0.798 |
atri | -0.753 |
hib | -0.744 |
utenberg | -0.735 |
netflix | -0.731 |
Token | c |
Token ID | 66 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Red | +1.895 |
Sioux | +1.854 |
Pt | +1.829 |
RED | +1.768 |
White | +1.610 |
Neg logit contributions | |
ubes | -3.433 |
atri | -3.224 |
utenberg | -3.168 |
hib | -3.163 |
netflix | -3.137 |
Token | py |
Token ID | 9078 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Red | +1.342 |
Sioux | +1.322 |
Pt | +1.293 |
RED | +1.255 |
Clarks | +1.128 |
Neg logit contributions | |
ubes | -2.697 |
atri | -2.539 |
hib | -2.497 |
utenberg | -2.492 |
netflix | -2.476 |
Token | kindred |
Token ID | 46449 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ubes | +1.301 |
atri | +1.210 |
hib | +1.177 |
utenberg | +1.177 |
netflix | +1.153 |
Neg logit contributions | |
Red | -1.342 |
Sioux | -1.325 |
Pt | -1.320 |
RED | -1.287 |
Clarks | -1.221 |
Token | spirits |
Token ID | 13747 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ubes | +0.808 |
atri | +0.732 |
hib | +0.725 |
utenberg | +0.708 |
netflix | +0.707 |
Neg logit contributions | |
Red | -0.941 |
Sioux | -0.932 |
Pt | -0.925 |
RED | -0.911 |
Clarks | -0.861 |
Token | . |
Token ID | 13 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
ubes | +2.627 |
atri | +2.412 |
hib | +2.387 |
netflix | +2.318 |
utenberg | +2.309 |
Neg logit contributions | |
Sioux | -2.773 |
Red | -2.688 |
Pt | -2.658 |
RED | -2.633 |
Clarks | -2.546 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ubes | +3.058 |
atri | +2.798 |
hib | +2.785 |
netflix | +2.683 |
UTERS | +2.680 |
Neg logit contributions | |
Sioux | -3.950 |
Red | -3.814 |
Pt | -3.785 |
RED | -3.765 |
Clarks | -3.653 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ubes | +1.131 |
atri | +1.036 |
hib | +1.027 |
utenberg | +1.000 |
netflix | +0.997 |
Neg logit contributions | |
Sioux | -1.282 |
Red | -1.261 |
Pt | -1.244 |
RED | -1.228 |
Clarks | -1.182 |
Token | Sign |
Token ID | 11712 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
ubes | +0.824 |
atri | +0.775 |
hib | +0.760 |
utenberg | +0.738 |
UTERS | +0.735 |
Neg logit contributions | |
Sioux | -0.907 |
Red | -0.900 |
RED | -0.879 |
Pt | -0.877 |
Clarks | -0.824 |
Token | up |
Token ID | 510 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ubes | +5.369 |
hib | +4.826 |
atri | +4.789 |
netflix | +4.613 |
ictionary | +4.453 |
Neg logit contributions | |
Sioux | -7.077 |
RED | -6.831 |
Pt | -6.746 |
Red | -6.743 |
Clarks | -6.712 |
Token | for |
Token ID | 329 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
ubes | +2.196 |
atri | +2.000 |
hib | +1.977 |
utenberg | +1.924 |
netflix | +1.922 |
Neg logit contributions | |
Pt | -1.861 |
Sioux | -1.860 |
Red | -1.809 |
RED | -1.777 |
Clarks | -1.725 |
Token | our |
Token ID | 674 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ubes | +2.448 |
atri | +2.315 |
hib | +2.199 |
utenberg | +2.103 |
ictionary | +2.033 |
Neg logit contributions | |
Sioux | -4.887 |
Red | -4.798 |
Pt | -4.780 |
RED | -4.780 |
Clarks | -4.679 |
Token | Wine |
Token ID | 20447 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
ubes | +1.702 |
atri | +1.669 |
hib | +1.628 |
utenberg | +1.594 |
ictionary | +1.567 |
Neg logit contributions | |
Pt | -1.335 |
Sioux | -1.329 |
Red | -1.297 |
RED | -1.268 |
Clarks | -1.244 |
Token | Club |
Token ID | 6289 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
ubes | +3.105 |
atri | +3.045 |
hib | +2.963 |
ictionary | +2.751 |
utenberg | +2.733 |
Neg logit contributions | |
Sioux | -3.327 |
RED | -3.306 |
Pt | -3.304 |
Red | -3.174 |
Lyme | -3.080 |
Token | MORE |
Token ID | 12011 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ubes | +1.963 |
atri | +1.752 |
hib | +1.741 |
utenberg | +1.719 |
UTERS | +1.694 |
Neg logit contributions | |
Pt | -2.423 |
Red | -2.400 |
Sioux | -2.392 |
RED | -2.354 |
draft | -2.260 |
Token | and |
Token ID | 290 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ubes | +1.725 |
atri | +1.615 |
hib | +1.585 |
utenberg | +1.581 |
netflix | +1.569 |
Neg logit contributions | |
Red | -1.109 |
Sioux | -1.094 |
Pt | -1.076 |
RED | -1.049 |
Clarks | -0.959 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Red | +1.288 |
Sioux | +1.273 |
Pt | +1.236 |
RED | +1.213 |
White | +1.142 |
Neg logit contributions | |
ubes | -1.753 |
atri | -1.644 |
utenberg | -1.614 |
hib | -1.606 |
netflix | -1.590 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Red | +0.128 |
Sioux | +0.126 |
Pt | +0.123 |
RED | +0.120 |
White | +0.113 |
Neg logit contributions | |
ubes | -0.172 |
atri | -0.160 |
hib | -0.158 |
netflix | -0.157 |
utenberg | -0.157 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
ubes | +0.403 |
atri | +0.377 |
hib | +0.372 |
netflix | +0.370 |
utenberg | +0.369 |
Neg logit contributions | |
Red | -0.292 |
Sioux | -0.290 |
Pt | -0.282 |
RED | -0.276 |
White | -0.259 |
Token | Diane |
Token ID | 26542 |
Feature activation | +8.59e+00 |
Pos logit contributions | |
ubes | +3.627 |
atri | +3.317 |
hib | +3.301 |
UTERS | +3.175 |
utenberg | +3.173 |
Neg logit contributions | |
Sioux | -4.311 |
Pt | -4.279 |
Red | -4.227 |
RED | -4.168 |
Lyme | -3.990 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ubes | +4.857 |
atri | +4.489 |
UTERS | +4.397 |
netflix | +4.323 |
ictionary | +4.252 |
Neg logit contributions | |
Pt | -7.202 |
Sioux | -7.194 |
Red | -6.819 |
RED | -6.774 |
pt | -6.595 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ubes | +3.395 |
atri | +3.122 |
hib | +3.051 |
utenberg | +3.010 |
netflix | +2.997 |
Neg logit contributions | |
Sioux | -3.049 |
Red | -3.045 |
Pt | -3.032 |
RED | -2.945 |
Clarks | -2.723 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ubes | +1.080 |
atri | +0.986 |
utenberg | +0.976 |
netflix | +0.953 |
hib | +0.950 |
Neg logit contributions | |
Red | -1.258 |
Sioux | -1.234 |
Pt | -1.218 |
RED | -1.203 |
White | -1.141 |
Token | : |
Token ID | 25 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ubes | +2.377 |
atri | +2.169 |
hib | +2.143 |
netflix | +2.096 |
utenberg | +2.088 |
Neg logit contributions | |
Sioux | -2.531 |
Red | -2.528 |
Pt | -2.498 |
RED | -2.440 |
Clarks | -2.281 |
Token | ' |
Token ID | 705 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Red | +1.416 |
Sioux | +1.341 |
Pt | +1.291 |
RED | +1.281 |
White | +1.192 |
Neg logit contributions | |
ubes | -2.668 |
atri | -2.487 |
utenberg | -2.465 |
netflix | -2.451 |
hib | -2.436 |
Token |
|
Token ID | 198 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
ubes | +1.778 |
atri | +1.627 |
hib | +1.626 |
utenberg | +1.604 |
netflix | +1.577 |
Neg logit contributions | |
Sioux | -2.178 |
Red | -2.122 |
Pt | -2.106 |
RED | -2.084 |
Clarks | -2.031 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ubes | +0.464 |
atri | +0.425 |
hib | +0.420 |
utenberg | +0.413 |
netflix | +0.411 |
Neg logit contributions | |
Sioux | -0.511 |
Red | -0.505 |
Pt | -0.498 |
RED | -0.490 |
Clarks | -0.470 |
Token | Fight |
Token ID | 27365 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
ubes | +0.139 |
atri | +0.122 |
hib | +0.114 |
utenberg | +0.113 |
netflix | +0.109 |
Neg logit contributions | |
Sioux | -0.420 |
Red | -0.418 |
Pt | -0.414 |
RED | -0.411 |
Clarks | -0.396 |
Token | Back |
Token ID | 5157 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
ubes | +3.285 |
atri | +3.215 |
hib | +3.095 |
utenberg | +3.050 |
UTERS | +3.040 |
Neg logit contributions | |
Pt | -3.090 |
Sioux | -2.986 |
Red | -2.918 |
Clarks | -2.903 |
RED | -2.899 |
Token | ! |
Token ID | 0 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ubes | +3.310 |
atri | +3.126 |
hib | +2.966 |
utenberg | +2.936 |
UTERS | +2.890 |
Neg logit contributions | |
Red | -4.257 |
Sioux | -4.250 |
RED | -4.182 |
Pt | -4.164 |
Clarks | -3.988 |
Token | Sign |
Token ID | 5865 |
Feature activation | +8.48e+00 |
Pos logit contributions | |
ubes | +1.206 |
atri | +1.130 |
netflix | +1.111 |
hib | +1.108 |
utenberg | +1.099 |
Neg logit contributions | |
Red | -0.642 |
Sioux | -0.636 |
Pt | -0.629 |
RED | -0.612 |
Clarks | -0.575 |
Token | up |
Token ID | 510 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
ubes | +5.034 |
atri | +4.494 |
hib | +4.402 |
netflix | +4.382 |
utenberg | +4.240 |
Neg logit contributions | |
Sioux | -6.956 |
RED | -6.742 |
Pt | -6.699 |
Red | -6.539 |
Clarks | -6.520 |
Token | for |
Token ID | 329 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ubes | +3.907 |
atri | +3.542 |
hib | +3.487 |
netflix | +3.415 |
utenberg | +3.411 |
Neg logit contributions | |
Sioux | -3.625 |
Pt | -3.615 |
RED | -3.451 |
Red | -3.442 |
Clarks | -3.428 |
Token | Take |
Token ID | 7214 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
ubes | +2.571 |
atri | +2.441 |
utenberg | +2.347 |
hib | +2.298 |
ictionary | +2.249 |
Neg logit contributions | |
Sioux | -3.519 |
Pt | -3.452 |
RED | -3.403 |
Red | -3.394 |
Clarks | -3.365 |
Token | Action |
Token ID | 7561 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
ubes | +4.981 |
hib | +4.554 |
atri | +4.479 |
UTERS | +4.448 |
netflix | +4.277 |
Neg logit contributions | |
Sioux | -5.132 |
Pt | -4.885 |
Red | -4.807 |
hog | -4.776 |
Clarks | -4.717 |
Token | Now |
Token ID | 2735 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ubes | +3.196 |
atri | +2.981 |
utenberg | +2.953 |
netflix | +2.937 |
hib | +2.933 |
Neg logit contributions | |
Sioux | -2.126 |
Pt | -2.020 |
Red | -2.013 |
RED | -1.976 |
Clarks | -1.894 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Sioux | +0.327 |
Red | +0.327 |
Pt | +0.321 |
RED | +0.314 |
Clarks | +0.295 |
Neg logit contributions | |
ubes | -0.328 |
atri | -0.301 |
hib | -0.296 |
utenberg | -0.294 |
netflix | -0.292 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Red | +2.246 |
Sioux | +2.193 |
Pt | +2.176 |
RED | +2.129 |
White | +1.990 |
Neg logit contributions | |
ubes | -2.494 |
atri | -2.313 |
utenberg | -2.261 |
hib | -2.248 |
netflix | -2.238 |
Token | Thank |
Token ID | 10449 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Red | +1.478 |
Sioux | +1.449 |
Pt | +1.440 |
RED | +1.412 |
White | +1.323 |
Neg logit contributions | |
ubes | -1.447 |
atri | -1.322 |
utenberg | -1.305 |
hib | -1.288 |
netflix | -1.279 |
Token | you |
Token ID | 345 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ubes | +2.687 |
atri | +2.485 |
hib | +2.437 |
utenberg | +2.427 |
netflix | +2.407 |
Neg logit contributions | |
Red | -2.243 |
Sioux | -2.229 |
Pt | -2.198 |
RED | -2.142 |
Clarks | -1.993 |
Token | for |
Token ID | 329 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ubes | +4.089 |
atri | +3.817 |
hib | +3.746 |
utenberg | +3.738 |
netflix | +3.704 |
Neg logit contributions | |
Red | -2.998 |
Sioux | -2.972 |
Pt | -2.939 |
RED | -2.856 |
Clarks | -2.646 |
Token | signing |
Token ID | 8415 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
ubes | +2.916 |
atri | +2.717 |
hib | +2.704 |
utenberg | +2.666 |
netflix | +2.595 |
Neg logit contributions | |
Sioux | -2.061 |
Red | -2.058 |
Pt | -2.040 |
RED | -1.987 |
Clarks | -1.831 |
Token | up |
Token ID | 510 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
ubes | +4.888 |
atri | +4.448 |
utenberg | +4.414 |
hib | +4.329 |
netflix | +4.321 |
Neg logit contributions | |
Sioux | -6.811 |
RED | -6.737 |
Red | -6.665 |
Pt | -6.610 |
Clarks | -6.482 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ubes | +3.479 |
atri | +3.233 |
hib | +3.142 |
utenberg | +3.124 |
netflix | +3.080 |
Neg logit contributions | |
Sioux | -2.845 |
Red | -2.845 |
Pt | -2.829 |
RED | -2.744 |
Clarks | -2.564 |
Token | For |
Token ID | 1114 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ubes | +0.186 |
atri | +0.172 |
hib | +0.167 |
utenberg | +0.167 |
netflix | +0.166 |
Neg logit contributions | |
Red | -0.186 |
Sioux | -0.183 |
Pt | -0.181 |
RED | -0.177 |
White | -0.167 |
Token | more |
Token ID | 517 |
Feature activation | -8.80e-03 |
Pos logit contributions | |
ubes | +1.588 |
utenberg | +1.445 |
hib | +1.438 |
atri | +1.436 |
netflix | +1.430 |
Neg logit contributions | |
Sioux | -1.427 |
Red | -1.388 |
Pt | -1.378 |
RED | -1.364 |
Clarks | -1.298 |
Token | from |
Token ID | 422 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Sioux | +0.005 |
Red | +0.005 |
Pt | +0.005 |
RED | +0.004 |
Clarks | +0.004 |
Neg logit contributions | |
ubes | -0.008 |
atri | -0.008 |
hib | -0.008 |
utenberg | -0.008 |
netflix | -0.008 |
Token | presidential |
Token ID | 4787 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Red | +0.727 |
Sioux | +0.712 |
Pt | +0.702 |
RED | +0.682 |
White | +0.643 |
Neg logit contributions | |
ubes | -0.939 |
atri | -0.871 |
utenberg | -0.861 |
hib | -0.858 |
netflix | -0.857 |
Token | nominee |
Token ID | 10429 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Red | +0.375 |
Sioux | +0.368 |
Pt | +0.360 |
RED | +0.349 |
White | +0.327 |
Neg logit contributions | |
ubes | -0.591 |
atri | -0.553 |
utenberg | -0.545 |
hib | -0.544 |
netflix | -0.543 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ubes | +1.844 |
atri | +1.715 |
hib | +1.678 |
utenberg | +1.671 |
netflix | +1.658 |
Neg logit contributions | |
Red | -1.478 |
Sioux | -1.462 |
Pt | -1.441 |
RED | -1.409 |
Clarks | -1.305 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Red | +0.211 |
Sioux | +0.208 |
Pt | +0.205 |
RED | +0.200 |
White | +0.186 |
Neg logit contributions | |
ubes | -0.266 |
atri | -0.247 |
hib | -0.242 |
utenberg | -0.242 |
netflix | -0.240 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
Red | +0.830 |
Sioux | +0.814 |
Pt | +0.800 |
RED | +0.778 |
White | +0.730 |
Neg logit contributions | |
ubes | -1.208 |
atri | -1.129 |
hib | -1.114 |
netflix | -1.111 |
utenberg | -1.108 |
Token | Diane |
Token ID | 26542 |
Feature activation | +8.26e+00 |
Pos logit contributions | |
ubes | +3.864 |
atri | +3.507 |
hib | +3.457 |
UTERS | +3.383 |
utenberg | +3.341 |
Neg logit contributions | |
Sioux | -4.379 |
Pt | -4.327 |
Red | -4.298 |
RED | -4.216 |
Lyme | -4.010 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ubes | +4.899 |
atri | +4.525 |
UTERS | +4.470 |
netflix | +4.291 |
hib | +4.237 |
Neg logit contributions | |
Pt | -6.766 |
Sioux | -6.746 |
Red | -6.527 |
RED | -6.412 |
draft | -6.194 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ubes | +3.228 |
atri | +2.982 |
hib | +2.922 |
utenberg | +2.890 |
netflix | +2.884 |
Neg logit contributions | |
Red | -2.792 |
Sioux | -2.775 |
Pt | -2.756 |
RED | -2.679 |
Clarks | -2.476 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ubes | +0.869 |
atri | +0.795 |
utenberg | +0.784 |
hib | +0.769 |
netflix | +0.767 |
Neg logit contributions | |
Red | -1.018 |
Sioux | -1.003 |
Pt | -0.989 |
RED | -0.974 |
White | -0.923 |
Token | : |
Token ID | 25 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
ubes | +2.381 |
atri | +2.187 |
hib | +2.148 |
netflix | +2.113 |
utenberg | +2.106 |
Neg logit contributions | |
Red | -2.368 |
Sioux | -2.356 |
Pt | -2.331 |
RED | -2.275 |
Clarks | -2.121 |
Token | ' |
Token ID | 705 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
Red | +1.523 |
Sioux | +1.445 |
RED | +1.379 |
Pt | +1.377 |
White | +1.287 |
Neg logit contributions | |
ubes | -2.878 |
utenberg | -2.678 |
atri | -2.678 |
netflix | -2.646 |
hib | -2.640 |
Token | ing |
Token ID | 278 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ubes | +0.809 |
atri | +0.758 |
hib | +0.749 |
netflix | +0.733 |
utenberg | +0.733 |
Neg logit contributions | |
Sioux | -0.564 |
Red | -0.557 |
Pt | -0.542 |
RED | -0.539 |
Clarks | -0.508 |
Token | . |
Token ID | 13 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
Red | +1.530 |
Sioux | +1.508 |
Pt | +1.488 |
RED | +1.454 |
White | +1.347 |
Neg logit contributions | |
ubes | -1.892 |
atri | -1.759 |
hib | -1.722 |
utenberg | -1.719 |
netflix | -1.706 |
Token | Color |
Token ID | 10258 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ubes | +0.004 |
atri | +0.004 |
hib | +0.004 |
utenberg | +0.004 |
netflix | +0.004 |
Neg logit contributions | |
Red | -0.006 |
Sioux | -0.006 |
Pt | -0.006 |
RED | -0.006 |
White | -0.006 |
Token | ] |
Token ID | 60 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Red | +0.716 |
Sioux | +0.691 |
Pt | +0.676 |
RED | +0.660 |
White | +0.592 |
Neg logit contributions | |
ubes | -1.597 |
atri | -1.507 |
hib | -1.482 |
utenberg | -1.480 |
netflix | -1.473 |
Token | :: |
Token ID | 3712 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
ubes | +1.677 |
atri | +1.534 |
hib | +1.509 |
utenberg | +1.503 |
ictionary | +1.477 |
Neg logit contributions | |
Sioux | -1.663 |
Red | -1.630 |
Pt | -1.596 |
RED | -1.582 |
Clarks | -1.518 |
Token | From |
Token ID | 4863 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
ubes | +0.429 |
atri | +0.397 |
hib | +0.389 |
utenberg | +0.389 |
netflix | +0.384 |
Neg logit contributions | |
Red | -0.430 |
Sioux | -0.421 |
Pt | -0.417 |
RED | -0.410 |
White | -0.384 |
Token | Ar |
Token ID | 3163 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
ubes | +5.093 |
atri | +4.615 |
hib | +4.482 |
ictionary | +4.432 |
utenberg | +4.372 |
Neg logit contributions | |
Sioux | -6.823 |
Red | -6.771 |
Pt | -6.759 |
RED | -6.646 |
Clarks | -6.343 |
Token | gb |
Token ID | 22296 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ubes | +4.070 |
atri | +3.667 |
hib | +3.579 |
utenberg | +3.519 |
netflix | +3.510 |
Neg logit contributions | |
Sioux | -4.872 |
Red | -4.814 |
Pt | -4.777 |
RED | -4.680 |
Clarks | -4.662 |
Token | ($ |
Token ID | 16763 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Red | +0.399 |
Sioux | +0.392 |
Pt | +0.390 |
RED | +0.380 |
White | +0.356 |
Neg logit contributions | |
ubes | -0.414 |
atri | -0.381 |
hib | -0.372 |
utenberg | -0.372 |
netflix | -0.367 |
Token | FC |
Token ID | 4851 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
ubes | +0.953 |
atri | +0.883 |
hib | +0.865 |
utenberg | +0.862 |
netflix | +0.855 |
Neg logit contributions | |
Red | -0.866 |
Sioux | -0.851 |
Pt | -0.844 |
RED | -0.826 |
White | -0.768 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Red | +0.444 |
Sioux | +0.433 |
Pt | +0.429 |
RED | +0.420 |
White | +0.388 |
Neg logit contributions | |
ubes | -0.576 |
atri | -0.538 |
utenberg | -0.531 |
hib | -0.529 |
netflix | -0.528 |
Token | In |
Token ID | 818 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ubes | +3.018 |
atri | +2.748 |
hib | +2.644 |
netflix | +2.619 |
utenberg | +2.608 |
Neg logit contributions | |
Red | -4.106 |
Sioux | -4.092 |
Pt | -4.006 |
RED | -3.988 |
Clarks | -3.760 |
Token | Memory |
Token ID | 30871 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
ubes | +1.226 |
atri | +1.116 |
hib | +1.108 |
UTERS | +1.067 |
ictionary | +1.059 |
Neg logit contributions | |
Sioux | -1.850 |
Red | -1.833 |
Pt | -1.807 |
RED | -1.793 |
Clarks | -1.722 |
Token | 4 |
Token ID | 604 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
ubes | +0.741 |
atri | +0.693 |
hib | +0.680 |
utenberg | +0.679 |
netflix | +0.674 |
Neg logit contributions | |
Red | -0.488 |
Sioux | -0.481 |
Pt | -0.473 |
RED | -0.461 |
White | -0.422 |
Token | 66 |
Token ID | 2791 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ubes | +3.691 |
atri | +3.389 |
hib | +3.300 |
utenberg | +3.258 |
netflix | +3.248 |
Neg logit contributions | |
Red | -3.997 |
Sioux | -3.987 |
Pt | -3.936 |
RED | -3.862 |
Clarks | -3.626 |
Token | 284 |
Token ID | 30336 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ubes | +3.429 |
atri | +3.192 |
hib | +3.142 |
utenberg | +3.111 |
netflix | +3.090 |
Neg logit contributions | |
Red | -2.797 |
Sioux | -2.781 |
Pt | -2.737 |
RED | -2.670 |
Clarks | -2.482 |
Token | 4 |
Token ID | 604 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
ubes | +2.068 |
atri | +1.941 |
hib | +1.904 |
utenberg | +1.899 |
netflix | +1.886 |
Neg logit contributions | |
Red | -1.256 |
Sioux | -1.241 |
Pt | -1.217 |
RED | -1.186 |
Clarks | -1.082 |
Token | 64 |
Token ID | 2414 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
ubes | +5.536 |
atri | +4.989 |
hib | +4.867 |
netflix | +4.849 |
utenberg | +4.814 |
Neg logit contributions | |
Sioux | -6.429 |
Red | -6.392 |
Pt | -6.357 |
RED | -6.250 |
Clarks | -5.885 |
Token | 406 |
Token ID | 29703 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ubes | +0.424 |
atri | +0.398 |
utenberg | +0.390 |
hib | +0.389 |
netflix | +0.386 |
Neg logit contributions | |
Red | -0.274 |
Sioux | -0.268 |
Pt | -0.266 |
RED | -0.256 |
White | -0.236 |
Token | Mem |
Token ID | 4942 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
Red | +0.645 |
Sioux | +0.615 |
Pt | +0.606 |
RED | +0.586 |
White | +0.518 |
Neg logit contributions | |
ubes | -1.702 |
atri | -1.611 |
utenberg | -1.594 |
hib | -1.584 |
netflix | -1.581 |
Token | c |
Token ID | 66 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Red | +1.770 |
Sioux | +1.739 |
Pt | +1.711 |
RED | +1.659 |
White | +1.508 |
Neg logit contributions | |
ubes | -3.140 |
atri | -2.948 |
hib | -2.894 |
utenberg | -2.893 |
netflix | -2.870 |
Token | py |
Token ID | 9078 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Red | +1.077 |
Sioux | +1.071 |
Pt | +1.035 |
RED | +1.014 |
Clarks | +0.923 |
Neg logit contributions | |
ubes | -2.080 |
atri | -1.955 |
hib | -1.924 |
utenberg | -1.918 |
netflix | -1.906 |
Token | speeches |
Token ID | 18138 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Red | +0.985 |
Sioux | +0.960 |
Pt | +0.947 |
RED | +0.920 |
White | +0.868 |
Neg logit contributions | |
ubes | -1.408 |
atri | -1.313 |
utenberg | -1.306 |
netflix | -1.297 |
hib | -1.287 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
Red | +1.018 |
Sioux | +0.990 |
Pt | +0.983 |
RED | +0.956 |
White | +0.891 |
Neg logit contributions | |
ubes | -1.460 |
atri | -1.355 |
utenberg | -1.340 |
netflix | -1.331 |
hib | -1.326 |
Token |
|
Token ID | 198 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
Red | +0.467 |
Sioux | +0.453 |
Pt | +0.447 |
RED | +0.437 |
White | +0.415 |
Neg logit contributions | |
ubes | -0.551 |
atri | -0.508 |
utenberg | -0.500 |
hib | -0.494 |
netflix | -0.494 |
Token |
|
Token ID | 198 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
ubes | +0.046 |
atri | +0.042 |
hib | +0.041 |
utenberg | +0.041 |
netflix | +0.040 |
Neg logit contributions | |
Sioux | -0.047 |
Red | -0.047 |
Pt | -0.046 |
RED | -0.046 |
Clarks | -0.043 |
Token | Newsletter |
Token ID | 33031 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ubes | +0.036 |
atri | +0.032 |
utenberg | +0.032 |
hib | +0.031 |
netflix | +0.031 |
Neg logit contributions | |
Red | -0.048 |
Sioux | -0.047 |
Pt | -0.047 |
RED | -0.046 |
White | -0.044 |
Token | Sign |
Token ID | 5865 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
ubes | +1.271 |
atri | +1.180 |
hib | +1.167 |
netflix | +1.139 |
UTERS | +1.139 |
Neg logit contributions | |
Sioux | -0.684 |
Pt | -0.671 |
Red | -0.664 |
RED | -0.637 |
Clarks | -0.595 |
Token | Up |
Token ID | 3205 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
ubes | +4.734 |
atri | +4.202 |
hib | +4.079 |
netflix | +3.966 |
UTERS | +3.905 |
Neg logit contributions | |
Sioux | -6.725 |
hog | -6.599 |
Pt | -6.557 |
RED | -6.510 |
Red | -6.392 |
Token | Continue |
Token ID | 10054 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ubes | +2.744 |
atri | +2.455 |
hib | +2.382 |
UTERS | +2.381 |
ictionary | +2.337 |
Neg logit contributions | |
Sioux | -2.812 |
Pt | -2.806 |
Red | -2.747 |
RED | -2.716 |
hog | -2.581 |
Token | reading |
Token ID | 3555 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
ubes | +0.956 |
atri | +0.881 |
hib | +0.866 |
utenberg | +0.864 |
netflix | +0.855 |
Neg logit contributions | |
Red | -0.783 |
Sioux | -0.783 |
Pt | -0.774 |
RED | -0.751 |
Clarks | -0.703 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ubes | +2.289 |
atri | +2.118 |
hib | +2.082 |
UTERS | +2.074 |
netflix | +2.062 |
Neg logit contributions | |
Sioux | -1.740 |
Red | -1.693 |
Pt | -1.680 |
RED | -1.653 |
Clarks | -1.552 |
Token | main |
Token ID | 1388 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
Red | +1.132 |
Sioux | +1.119 |
Pt | +1.104 |
RED | +1.081 |
White | +1.006 |
Neg logit contributions | |
ubes | -1.247 |
atri | -1.155 |
hib | -1.129 |
utenberg | -1.126 |
netflix | -1.117 |
Token | visible |
Token ID | 7424 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
ubes | +1.308 |
atri | +1.189 |
hib | +1.172 |
netflix | +1.160 |
utenberg | +1.149 |
Neg logit contributions | |
Sioux | -1.205 |
Red | -1.189 |
Pt | -1.187 |
RED | -1.142 |
Clarks | -1.096 |
Token | since |
Token ID | 1201 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ubes | +1.758 |
atri | +1.621 |
hib | +1.593 |
netflix | +1.579 |
utenberg | +1.575 |
Neg logit contributions | |
Sioux | -1.802 |
Red | -1.794 |
Pt | -1.759 |
RED | -1.735 |
Clarks | -1.659 |
Token | at |
Token ID | 379 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ubes | +3.118 |
atri | +2.951 |
hib | +2.874 |
utenberg | +2.824 |
netflix | +2.778 |
Neg logit contributions | |
Sioux | -3.070 |
Red | -2.987 |
Pt | -2.949 |
RED | -2.909 |
Clarks | -2.806 |
Token | a |
Token ID | 257 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ubes | +1.242 |
atri | +1.168 |
hib | +1.147 |
utenberg | +1.123 |
netflix | +1.119 |
Neg logit contributions | |
Sioux | -0.819 |
Red | -0.796 |
Pt | -0.779 |
RED | -0.766 |
Clarks | -0.732 |
Token | 90 |
Token ID | 4101 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
ubes | +1.554 |
atri | +1.464 |
hib | +1.436 |
utenberg | +1.400 |
netflix | +1.392 |
Neg logit contributions | |
Sioux | -1.153 |
Red | -1.126 |
Pt | -1.117 |
RED | -1.073 |
Clarks | -1.021 |
Token | F |
Token ID | 376 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
ubes | +3.329 |
atri | +2.997 |
hib | +2.987 |
utenberg | +2.893 |
UTERS | +2.873 |
Neg logit contributions | |
Sioux | -5.126 |
Pt | -4.992 |
Red | -4.966 |
RED | -4.817 |
Clarks | -4.782 |
Token | OV |
Token ID | 8874 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ubes | +4.132 |
atri | +3.589 |
UTERS | +3.506 |
hib | +3.452 |
utenberg | +3.359 |
Neg logit contributions | |
Sioux | -7.667 |
Red | -7.427 |
Pt | -7.390 |
Clarks | -7.309 |
RED | -7.165 |
Token | even |
Token ID | 772 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ubes | +2.369 |
atri | +2.214 |
hib | +2.150 |
UTERS | +2.131 |
netflix | +2.120 |
Neg logit contributions | |
Sioux | -1.918 |
Red | -1.912 |
Pt | -1.900 |
RED | -1.833 |
Clarks | -1.756 |
Token | double |
Token ID | 4274 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ubes | +1.902 |
atri | +1.705 |
hib | +1.700 |
utenberg | +1.676 |
netflix | +1.670 |
Neg logit contributions | |
Sioux | -2.116 |
Pt | -2.065 |
Red | -2.050 |
RED | -1.983 |
Clarks | -1.941 |
Token | or |
Token ID | 393 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
ubes | +0.350 |
atri | +0.325 |
hib | +0.320 |
utenberg | +0.315 |
netflix | +0.314 |
Neg logit contributions | |
Sioux | -0.285 |
Red | -0.283 |
Pt | -0.279 |
RED | -0.271 |
Clarks | -0.256 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Red | +0.468 |
Sioux | +0.468 |
Pt | +0.457 |
RED | +0.443 |
Clarks | +0.413 |
Neg logit contributions | |
ubes | -0.751 |
atri | -0.704 |
hib | -0.689 |
utenberg | -0.688 |
netflix | -0.682 |
Token | our |
Token ID | 674 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ubes | +2.251 |
atri | +2.037 |
hib | +1.996 |
utenberg | +1.979 |
netflix | +1.919 |
Neg logit contributions | |
Sioux | -4.322 |
Red | -4.315 |
Pt | -4.268 |
RED | -4.261 |
Clarks | -4.077 |
Token | Privacy |
Token ID | 16777 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Sioux | +0.097 |
Red | +0.096 |
Pt | +0.095 |
RED | +0.094 |
Clarks | +0.089 |
Neg logit contributions | |
ubes | -0.068 |
atri | -0.063 |
hib | -0.061 |
utenberg | -0.061 |
netflix | -0.060 |
Token | Policy |
Token ID | 7820 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ubes | +1.457 |
atri | +1.374 |
hib | +1.355 |
utenberg | +1.336 |
netflix | +1.318 |
Neg logit contributions | |
Sioux | -1.211 |
Red | -1.190 |
RED | -1.172 |
Pt | -1.160 |
Clarks | -1.111 |
Token | here |
Token ID | 994 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
ubes | +0.291 |
atri | +0.271 |
hib | +0.267 |
utenberg | +0.265 |
netflix | +0.264 |
Neg logit contributions | |
Red | -0.199 |
Sioux | -0.198 |
Pt | -0.194 |
RED | -0.190 |
Clarks | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ubes | +3.026 |
atri | +2.776 |
hib | +2.759 |
netflix | +2.707 |
utenberg | +2.698 |
Neg logit contributions | |
Sioux | -3.315 |
Red | -3.201 |
Pt | -3.184 |
RED | -3.126 |
Clarks | -3.085 |
Token | Sign |
Token ID | 5865 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
ubes | +1.445 |
atri | +1.355 |
hib | +1.343 |
utenberg | +1.327 |
netflix | +1.322 |
Neg logit contributions | |
Sioux | -0.758 |
Red | -0.741 |
Pt | -0.724 |
RED | -0.709 |
Clarks | -0.651 |
Token | up |
Token ID | 510 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
ubes | +4.804 |
atri | +4.270 |
hib | +4.262 |
netflix | +4.126 |
utenberg | +4.067 |
Neg logit contributions | |
Sioux | -6.661 |
Pt | -6.413 |
RED | -6.346 |
Clarks | -6.289 |
Red | -6.267 |
Token | for |
Token ID | 329 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ubes | +3.581 |
atri | +3.264 |
hib | +3.250 |
netflix | +3.143 |
utenberg | +3.111 |
Neg logit contributions | |
Sioux | -3.335 |
Pt | -3.258 |
Red | -3.195 |
RED | -3.178 |
Clarks | -3.112 |
Token | Take |
Token ID | 7214 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
ubes | +2.412 |
atri | +2.236 |
hib | +2.158 |
utenberg | +2.120 |
netflix | +2.104 |
Neg logit contributions | |
Sioux | -2.857 |
Red | -2.822 |
Pt | -2.772 |
RED | -2.772 |
Clarks | -2.639 |
Token | Action |
Token ID | 7561 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ubes | +3.871 |
hib | +3.582 |
atri | +3.519 |
UTERS | +3.425 |
utenberg | +3.416 |
Neg logit contributions | |
Sioux | -3.573 |
Pt | -3.457 |
Red | -3.394 |
RED | -3.314 |
hog | -3.292 |
Token | Now |
Token ID | 2735 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
ubes | +3.217 |
hib | +2.968 |
atri | +2.961 |
netflix | +2.956 |
utenberg | +2.953 |
Neg logit contributions | |
Sioux | -2.217 |
Red | -2.071 |
Pt | -2.069 |
RED | -2.050 |
hog | -2.003 |
Token | :: |
Token ID | 3712 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ubes | +1.604 |
atri | +1.470 |
hib | +1.433 |
utenberg | +1.431 |
netflix | +1.414 |
Neg logit contributions | |
Red | -1.828 |
Sioux | -1.812 |
Pt | -1.787 |
RED | -1.756 |
White | -1.645 |
Token | Get |
Token ID | 3855 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ubes | +1.451 |
atri | +1.323 |
hib | +1.289 |
utenberg | +1.285 |
netflix | +1.271 |
Neg logit contributions | |
Red | -1.815 |
Sioux | -1.799 |
Pt | -1.777 |
RED | -1.745 |
White | -1.641 |
Token | Mass |
Token ID | 20273 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
ubes | +2.349 |
atri | +2.085 |
utenberg | +2.011 |
hib | +2.003 |
netflix | +1.969 |
Neg logit contributions | |
Sioux | -4.648 |
Red | -4.644 |
Pt | -4.566 |
RED | -4.523 |
Clarks | -4.304 |
Token | ( |
Token ID | 7 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ubes | +4.013 |
atri | +3.740 |
hib | +3.664 |
utenberg | +3.648 |
netflix | +3.598 |
Neg logit contributions | |
Red | -3.245 |
Sioux | -3.243 |
Pt | -3.161 |
RED | -3.123 |
Clarks | -2.889 |
Token | float |
Token ID | 12178 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ubes | +2.118 |
atri | +1.946 |
hib | +1.903 |
utenberg | +1.899 |
netflix | +1.876 |
Neg logit contributions | |
Red | -2.301 |
Sioux | -2.284 |
Pt | -2.249 |
RED | -2.210 |
Clarks | -2.070 |
Token | ambient |
Token ID | 25237 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
Red | +1.739 |
Pt | +1.688 |
Sioux | +1.671 |
RED | +1.636 |
White | +1.529 |
Neg logit contributions | |
ubes | -2.073 |
atri | -1.920 |
netflix | -1.895 |
hib | -1.883 |
utenberg | -1.861 |
Token | D |
Token ID | 35 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
ubes | +5.953 |
atri | +5.465 |
utenberg | +5.439 |
hib | +5.330 |
netflix | +5.309 |
Neg logit contributions | |
Sioux | -5.672 |
Red | -5.629 |
Pt | -5.507 |
RED | -5.470 |
Clarks | -5.177 |
Token | ensity |
Token ID | 6377 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
ubes | +3.650 |
utenberg | +3.359 |
atri | +3.356 |
ictionary | +3.317 |
hib | +3.292 |
Neg logit contributions | |
Sioux | -4.006 |
Red | -3.973 |
Pt | -3.961 |
RED | -3.880 |
Clarks | -3.729 |
Token | ) |
Token ID | 1267 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ubes | +2.384 |
atri | +2.206 |
hib | +2.160 |
utenberg | +2.156 |
netflix | +2.134 |
Neg logit contributions | |
Red | -2.178 |
Sioux | -2.159 |
Pt | -2.126 |
RED | -2.083 |
Clarks | -1.942 |
Token | const |
Token ID | 1500 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ubes | +2.571 |
atri | +2.399 |
hib | +2.354 |
utenberg | +2.345 |
netflix | +2.309 |
Neg logit contributions | |
Sioux | -1.994 |
Red | -1.993 |
Pt | -1.956 |
RED | -1.904 |
Clarks | -1.772 |
Token | { |
Token ID | 1391 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
Red | +1.452 |
Sioux | +1.404 |
Pt | +1.394 |
RED | +1.370 |
White | +1.261 |
Neg logit contributions | |
ubes | -1.826 |
atri | -1.704 |
utenberg | -1.671 |
netflix | -1.667 |
hib | -1.651 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Sioux | +0.300 |
Red | +0.300 |
Pt | +0.294 |
RED | +0.289 |
Clarks | +0.273 |
Neg logit contributions | |
ubes | -0.291 |
atri | -0.267 |
hib | -0.263 |
utenberg | -0.260 |
netflix | -0.259 |
Token | J |
Token ID | 41 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Red | +0.947 |
Sioux | +0.924 |
Pt | +0.921 |
RED | +0.899 |
White | +0.835 |
Neg logit contributions | |
ubes | -1.025 |
atri | -0.942 |
utenberg | -0.929 |
hib | -0.914 |
netflix | -0.909 |
Token | aaaa |
Token ID | 24794 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Red | +0.935 |
Sioux | +0.914 |
Pt | +0.914 |
RED | +0.887 |
White | +0.832 |
Neg logit contributions | |
ubes | -0.991 |
atri | -0.918 |
hib | -0.898 |
utenberg | -0.898 |
netflix | -0.896 |
Token | asper |
Token ID | 32981 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Red | +1.276 |
Sioux | +1.243 |
Pt | +1.236 |
RED | +1.209 |
White | +1.137 |
Neg logit contributions | |
ubes | -1.422 |
atri | -1.320 |
utenberg | -1.305 |
hib | -1.305 |
netflix | -1.293 |
Token | Profile |
Token ID | 13118 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
Red | +0.243 |
Sioux | +0.240 |
Pt | +0.238 |
RED | +0.233 |
White | +0.219 |
Neg logit contributions | |
ubes | -0.219 |
atri | -0.200 |
utenberg | -0.196 |
hib | -0.196 |
netflix | -0.193 |
Token | Blog |
Token ID | 14001 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
ubes | +0.070 |
atri | +0.064 |
utenberg | +0.063 |
hib | +0.063 |
netflix | +0.062 |
Neg logit contributions | |
Red | -0.071 |
Sioux | -0.069 |
Pt | -0.069 |
RED | -0.067 |
White | -0.063 |
Token | Joined |
Token ID | 16709 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ubes | +3.686 |
atri | +3.169 |
hib | +3.089 |
UTERS | +2.980 |
netflix | +2.830 |
Neg logit contributions | |
Sioux | -7.587 |
Pt | -7.368 |
RED | -7.275 |
Red | -7.247 |
wolves | -7.091 |
Token | April |
Token ID | 3035 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
ubes | +3.911 |
atri | +3.656 |
hib | +3.622 |
netflix | +3.547 |
UTERS | +3.546 |
Neg logit contributions | |
Sioux | -2.459 |
Red | -2.420 |
Pt | -2.408 |
RED | -2.337 |
Clarks | -2.195 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ubes | +3.576 |
atri | +3.342 |
hib | +3.304 |
netflix | +3.208 |
utenberg | +3.163 |
Neg logit contributions | |
Sioux | -3.168 |
Pt | -3.057 |
Red | -3.057 |
RED | -2.987 |
Clarks | -2.896 |
Token | United |
Token ID | 1578 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
ubes | +2.343 |
atri | +2.197 |
hib | +2.152 |
netflix | +2.130 |
utenberg | +2.118 |
Neg logit contributions | |
Red | -1.729 |
Sioux | -1.722 |
Pt | -1.699 |
RED | -1.660 |
Clarks | -1.536 |
Token | States |
Token ID | 1829 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
ubes | +3.443 |
atri | +3.245 |
hib | +3.180 |
utenberg | +3.157 |
netflix | +3.149 |
Neg logit contributions | |
Red | -2.092 |
Sioux | -2.056 |
Pt | -2.029 |
RED | -1.983 |
Clarks | -1.811 |
Token | // |
Token ID | 3373 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
Red | +0.661 |
Sioux | +0.631 |
Pt | +0.628 |
RED | +0.619 |
White | +0.562 |
Neg logit contributions | |
ubes | -1.163 |
atri | -1.094 |
netflix | -1.079 |
hib | -1.075 |
utenberg | -1.069 |
Token | Time |
Token ID | 3862 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
Red | +0.567 |
Sioux | +0.553 |
Pt | +0.546 |
RED | +0.538 |
White | +0.499 |
Neg logit contributions | |
ubes | -0.702 |
atri | -0.652 |
utenberg | -0.641 |
hib | -0.640 |
netflix | -0.638 |
Token | component |
Token ID | 7515 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Red | +2.822 |
Pt | +2.693 |
Sioux | +2.666 |
RED | +2.652 |
White | +2.451 |
Neg logit contributions | |
ubes | -3.756 |
atri | -3.504 |
netflix | -3.486 |
hib | -3.457 |
utenberg | -3.426 |
Token | const |
Token ID | 1500 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ubes | +1.609 |
atri | +1.503 |
hib | +1.474 |
utenberg | +1.470 |
netflix | +1.459 |
Neg logit contributions | |
Red | -1.107 |
Sioux | -1.094 |
Pt | -1.076 |
RED | -1.049 |
White | -0.963 |
Token | float |
Token ID | 12178 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Red | +2.164 |
Pt | +2.087 |
Sioux | +2.079 |
RED | +2.049 |
White | +1.901 |
Neg logit contributions | |
ubes | -2.637 |
atri | -2.460 |
netflix | -2.436 |
utenberg | -2.430 |
hib | -2.426 |
Token | TA |
Token ID | 21664 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
Red | +1.032 |
Pt | +0.998 |
Sioux | +0.994 |
RED | +0.974 |
White | +0.908 |
Neg logit contributions | |
ubes | -1.300 |
atri | -1.212 |
netflix | -1.199 |
hib | -1.196 |
utenberg | -1.191 |
Token | U |
Token ID | 52 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
ubes | +5.812 |
atri | +5.279 |
hib | +5.147 |
utenberg | +5.113 |
netflix | +5.012 |
Neg logit contributions | |
Sioux | -5.872 |
Red | -5.769 |
Pt | -5.676 |
RED | -5.570 |
Clarks | -5.273 |
Token | = |
Token ID | 796 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ubes | +3.941 |
atri | +3.595 |
hib | +3.518 |
utenberg | +3.485 |
netflix | +3.453 |
Neg logit contributions | |
Sioux | -4.441 |
Red | -4.412 |
Pt | -4.349 |
RED | -4.230 |
Clarks | -4.022 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Red | +0.900 |
Pt | +0.870 |
Sioux | +0.866 |
RED | +0.851 |
White | +0.784 |
Neg logit contributions | |
ubes | -1.304 |
atri | -1.220 |
netflix | -1.204 |
hib | -1.203 |
utenberg | -1.196 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ubes | +1.321 |
atri | +1.230 |
hib | +1.206 |
utenberg | +1.203 |
netflix | +1.194 |
Neg logit contributions | |
Red | -1.016 |
Sioux | -1.002 |
Pt | -0.987 |
RED | -0.966 |
White | -0.891 |
Token | 283 |
Token ID | 30290 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ubes | +1.728 |
atri | +1.612 |
hib | +1.582 |
utenberg | +1.576 |
netflix | +1.564 |
Neg logit contributions | |
Red | -1.238 |
Sioux | -1.224 |
Pt | -1.205 |
RED | -1.174 |
White | -1.081 |
Token | McCain |
Token ID | 14264 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Red | +0.833 |
Sioux | +0.817 |
Pt | +0.802 |
RED | +0.777 |
White | +0.738 |
Neg logit contributions | |
ubes | -1.031 |
atri | -0.958 |
utenberg | -0.954 |
netflix | -0.953 |
hib | -0.938 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ubes | +0.450 |
atri | +0.418 |
hib | +0.412 |
utenberg | +0.411 |
netflix | +0.410 |
Neg logit contributions | |
Red | -0.301 |
Sioux | -0.295 |
Pt | -0.291 |
RED | -0.282 |
White | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
ubes | +0.233 |
atri | +0.216 |
hib | +0.212 |
utenberg | +0.211 |
netflix | +0.210 |
Neg logit contributions | |
Red | -0.198 |
Sioux | -0.195 |
Pt | -0.193 |
RED | -0.188 |
White | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
ubes | +0.408 |
atri | +0.373 |
hib | +0.369 |
utenberg | +0.363 |
netflix | +0.361 |
Neg logit contributions | |
Sioux | -0.440 |
Red | -0.437 |
Pt | -0.429 |
RED | -0.423 |
Clarks | -0.403 |
Token | Newsletter |
Token ID | 33031 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ubes | +0.036 |
atri | +0.033 |
utenberg | +0.032 |
hib | +0.032 |
netflix | +0.032 |
Neg logit contributions | |
Red | -0.031 |
Sioux | -0.031 |
Pt | -0.031 |
RED | -0.030 |
White | -0.028 |
Token | Sign |
Token ID | 5865 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
ubes | +0.498 |
atri | +0.465 |
hib | +0.459 |
netflix | +0.453 |
utenberg | +0.451 |
Neg logit contributions | |
Sioux | -0.260 |
Pt | -0.256 |
Red | -0.256 |
RED | -0.244 |
Clarks | -0.225 |
Token | Up |
Token ID | 3205 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ubes | +4.666 |
atri | +4.156 |
hib | +4.016 |
netflix | +3.951 |
utenberg | +3.874 |
Neg logit contributions | |
Sioux | -6.561 |
Pt | -6.396 |
RED | -6.371 |
hog | -6.330 |
Red | -6.269 |
Token | Continue |
Token ID | 10054 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ubes | +2.418 |
atri | +2.189 |
hib | +2.117 |
UTERS | +2.089 |
ictionary | +2.068 |
Neg logit contributions | |
Sioux | -2.411 |
Pt | -2.404 |
Red | -2.364 |
RED | -2.331 |
hog | -2.194 |
Token | reading |
Token ID | 3555 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ubes | +1.809 |
atri | +1.666 |
hib | +1.633 |
utenberg | +1.628 |
netflix | +1.613 |
Neg logit contributions | |
Sioux | -1.547 |
Red | -1.541 |
Pt | -1.531 |
RED | -1.481 |
Clarks | -1.398 |
Token | the |
Token ID | 262 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ubes | +2.753 |
atri | +2.568 |
netflix | +2.506 |
hib | +2.505 |
UTERS | +2.482 |
Neg logit contributions | |
Sioux | -2.097 |
Red | -2.046 |
Pt | -2.038 |
RED | -1.991 |
Clarks | -1.862 |
Token | main |
Token ID | 1388 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Red | +1.721 |
Sioux | +1.693 |
Pt | +1.670 |
RED | +1.638 |
White | +1.529 |
Neg logit contributions | |
ubes | -1.935 |
atri | -1.795 |
hib | -1.759 |
utenberg | -1.754 |
netflix | -1.741 |
Token | the |
Token ID | 1169 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
ubes | +0.069 |
atri | +0.064 |
utenberg | +0.062 |
hib | +0.062 |
netflix | +0.061 |
Neg logit contributions | |
Red | -0.075 |
Sioux | -0.074 |
Pt | -0.073 |
RED | -0.071 |
White | -0.067 |
Token | Bre |
Token ID | 3719 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
Red | +0.015 |
Sioux | +0.015 |
Pt | +0.014 |
RED | +0.014 |
White | +0.013 |
Neg logit contributions | |
ubes | -0.018 |
atri | -0.017 |
utenberg | -0.016 |
hib | -0.016 |
netflix | -0.016 |
Token | aux |
Token ID | 14644 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ubes | +0.594 |
atri | +0.557 |
hib | +0.545 |
netflix | +0.544 |
utenberg | +0.543 |
Neg logit contributions | |
Red | -0.419 |
Sioux | -0.411 |
Pt | -0.404 |
RED | -0.395 |
White | -0.367 |
Token | - |
Token ID | 12 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
ubes | +0.926 |
atri | +0.864 |
hib | +0.847 |
utenberg | +0.847 |
netflix | +0.841 |
Neg logit contributions | |
Red | -0.708 |
Sioux | -0.698 |
Pt | -0.686 |
RED | -0.670 |
White | -0.624 |
Token | L |
Token ID | 43 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Red | +0.398 |
Sioux | +0.387 |
Pt | +0.382 |
RED | +0.375 |
White | +0.355 |
Neg logit contributions | |
ubes | -0.500 |
atri | -0.464 |
utenberg | -0.458 |
hib | -0.456 |
netflix | -0.450 |
Token | ott |
Token ID | 1252 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
ubes | +2.178 |
atri | +2.007 |
hib | +1.960 |
utenberg | +1.954 |
netflix | +1.938 |
Neg logit contributions | |
Red | -2.238 |
Sioux | -2.213 |
Pt | -2.186 |
RED | -2.142 |
White | -2.004 |
Token | Leadership |
Token ID | 26935 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ubes | +6.575 |
atri | +6.067 |
hib | +5.970 |
utenberg | +5.900 |
netflix | +5.803 |
Neg logit contributions | |
Red | -4.771 |
Sioux | -4.769 |
Pt | -4.758 |
RED | -4.629 |
Clarks | -4.271 |
Token | Group |
Token ID | 4912 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ubes | +0.896 |
atri | +0.830 |
hib | +0.812 |
utenberg | +0.811 |
netflix | +0.806 |
Neg logit contributions | |
Red | -0.812 |
Sioux | -0.800 |
Pt | -0.790 |
RED | -0.773 |
White | -0.722 |
Token | ) |
Token ID | 8 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Red | +0.105 |
Sioux | +0.103 |
Pt | +0.102 |
RED | +0.100 |
White | +0.093 |
Neg logit contributions | |
ubes | -0.126 |
atri | -0.117 |
utenberg | -0.114 |
hib | -0.114 |
netflix | -0.113 |
Token | [ |
Token ID | 685 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Red | +0.922 |
Sioux | +0.898 |
Pt | +0.882 |
RED | +0.865 |
White | +0.803 |
Neg logit contributions | |
ubes | -1.427 |
atri | -1.332 |
hib | -1.304 |
utenberg | -1.300 |
netflix | -1.299 |
Token | L |
Token ID | 43 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Red | +0.156 |
Sioux | +0.153 |
Pt | +0.152 |
RED | +0.149 |
White | +0.139 |
Neg logit contributions | |
ubes | -0.175 |
atri | -0.162 |
utenberg | -0.158 |
hib | -0.157 |
netflix | -0.156 |
Token | spokeswoman |
Token ID | 12262 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
ubes | +0.267 |
atri | +0.248 |
hib | +0.243 |
utenberg | +0.243 |
netflix | +0.241 |
Neg logit contributions | |
Red | -0.202 |
Sioux | -0.198 |
Pt | -0.196 |
RED | -0.191 |
White | -0.177 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Red | +0.614 |
Sioux | +0.602 |
Pt | +0.587 |
RED | +0.573 |
White | +0.538 |
Neg logit contributions | |
ubes | -0.861 |
atri | -0.799 |
hib | -0.788 |
netflix | -0.787 |
utenberg | -0.786 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Red | +0.744 |
Sioux | +0.729 |
Pt | +0.718 |
RED | +0.702 |
White | +0.659 |
Neg logit contributions | |
ubes | -0.866 |
atri | -0.803 |
utenberg | -0.786 |
hib | -0.783 |
netflix | -0.774 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Red | +0.986 |
Sioux | +0.977 |
Pt | +0.963 |
RED | +0.944 |
Clarks | +0.882 |
Neg logit contributions | |
ubes | -1.010 |
atri | -0.932 |
hib | -0.912 |
utenberg | -0.908 |
netflix | -0.901 |
Token | Newsletter |
Token ID | 33031 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Red | +1.151 |
Pt | +1.125 |
Sioux | +1.125 |
RED | +1.088 |
White | +1.025 |
Neg logit contributions | |
ubes | -1.190 |
atri | -1.088 |
utenberg | -1.083 |
hib | -1.061 |
bably | -1.046 |
Token | Sign |
Token ID | 5865 |
Feature activation | +7.80e+00 |
Pos logit contributions | |
ubes | +1.761 |
atri | +1.639 |
hib | +1.615 |
netflix | +1.592 |
utenberg | +1.580 |
Neg logit contributions | |
Sioux | -0.955 |
Pt | -0.942 |
Red | -0.937 |
RED | -0.895 |
Clarks | -0.829 |
Token | Up |
Token ID | 3205 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
ubes | +4.618 |
atri | +4.137 |
hib | +3.977 |
netflix | +3.952 |
utenberg | +3.826 |
Neg logit contributions | |
Sioux | -6.486 |
Pt | -6.331 |
RED | -6.301 |
hog | -6.282 |
Red | -6.222 |
Token | Continue |
Token ID | 10054 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ubes | +2.483 |
atri | +2.240 |
hib | +2.168 |
UTERS | +2.153 |
ictionary | +2.116 |
Neg logit contributions | |
Sioux | -2.467 |
Pt | -2.460 |
Red | -2.430 |
RED | -2.390 |
hog | -2.261 |
Token | reading |
Token ID | 3555 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
ubes | +1.174 |
atri | +1.084 |
hib | +1.062 |
utenberg | +1.060 |
netflix | +1.053 |
Neg logit contributions | |
Red | -0.962 |
Sioux | -0.960 |
Pt | -0.949 |
RED | -0.921 |
Clarks | -0.864 |
Token | the |
Token ID | 262 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ubes | +2.623 |
atri | +2.436 |
netflix | +2.381 |
hib | +2.380 |
UTERS | +2.373 |
Neg logit contributions | |
Sioux | -2.012 |
Red | -1.966 |
Pt | -1.951 |
RED | -1.914 |
Clarks | -1.789 |
Token | main |
Token ID | 1388 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Red | +2.303 |
Sioux | +2.245 |
Pt | +2.216 |
RED | +2.179 |
White | +2.046 |
Neg logit contributions | |
ubes | -2.686 |
atri | -2.506 |
hib | -2.457 |
utenberg | -2.451 |
netflix | -2.434 |
Token | ; |
Token ID | 26 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Red | +0.336 |
Sioux | +0.326 |
Pt | +0.324 |
RED | +0.318 |
White | +0.291 |
Neg logit contributions | |
ubes | -0.463 |
atri | -0.430 |
hib | -0.422 |
utenberg | -0.422 |
netflix | -0.422 |
Token | } |
Token ID | 1782 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Red | +0.112 |
Sioux | +0.109 |
Pt | +0.108 |
RED | +0.105 |
White | +0.096 |
Neg logit contributions | |
ubes | -0.182 |
atri | -0.170 |
hib | -0.168 |
utenberg | -0.167 |
netflix | -0.167 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
Red | +1.191 |
Sioux | +1.158 |
Pt | +1.150 |
RED | +1.131 |
White | +1.058 |
Neg logit contributions | |
ubes | -1.301 |
atri | -1.200 |
netflix | -1.185 |
utenberg | -1.179 |
hib | -1.170 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
Red | +1.614 |
Pt | +1.565 |
Sioux | +1.556 |
RED | +1.525 |
White | +1.410 |
Neg logit contributions | |
ubes | -2.168 |
atri | -2.029 |
netflix | -2.010 |
hib | -1.972 |
utenberg | -1.965 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Red | +2.276 |
Pt | +2.206 |
Sioux | +2.205 |
RED | +2.155 |
White | +2.010 |
Neg logit contributions | |
ubes | -3.288 |
atri | -3.075 |
hib | -3.032 |
netflix | -3.032 |
utenberg | -2.980 |
Token | void |
Token ID | 7951 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
Red | +1.323 |
Sioux | +1.290 |
Pt | +1.282 |
RED | +1.242 |
White | +1.161 |
Neg logit contributions | |
ubes | -2.191 |
atri | -2.053 |
hib | -2.032 |
netflix | -2.025 |
utenberg | -1.995 |
Token | vert |
Token ID | 9421 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Red | +3.738 |
Pt | +3.539 |
RED | +3.440 |
Sioux | +3.415 |
pt | +3.285 |
Neg logit contributions | |
ubes | -11.646 |
atri | -11.430 |
netflix | -11.374 |
hib | -11.341 |
utenberg | -11.205 |
Token | ( |
Token ID | 357 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Red | +1.301 |
Sioux | +1.274 |
Pt | +1.259 |
RED | +1.227 |
White | +1.134 |
Neg logit contributions | |
ubes | -1.840 |
atri | -1.717 |
hib | -1.685 |
utenberg | -1.681 |
netflix | -1.660 |
Token | in |
Token ID | 287 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Red | +0.768 |
Sioux | +0.755 |
Pt | +0.746 |
RED | +0.718 |
White | +0.653 |
Neg logit contributions | |
ubes | -1.414 |
atri | -1.331 |
hib | -1.312 |
utenberg | -1.301 |
netflix | -1.301 |
Token | out |
Token ID | 448 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
ubes | +2.096 |
atri | +1.944 |
utenberg | +1.895 |
hib | +1.893 |
netflix | +1.873 |
Neg logit contributions | |
Red | -1.922 |
Sioux | -1.903 |
Pt | -1.873 |
RED | -1.836 |
Clarks | -1.728 |
Token | app |
Token ID | 598 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Red | +1.895 |
Pt | +1.779 |
Sioux | +1.767 |
RED | +1.744 |
hog | +1.560 |
Neg logit contributions | |
ubes | -4.770 |
atri | -4.552 |
utenberg | -4.476 |
hib | -4.454 |
UTERS | -4.432 |
Token | c |
Token ID | 66 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
ubes | +0.892 |
atri | +0.830 |
utenberg | +0.816 |
hib | +0.812 |
netflix | +0.805 |
Neg logit contributions | |
Red | -0.671 |
Sioux | -0.657 |
Pt | -0.649 |
RED | -0.632 |
White | -0.585 |
Token | ps |
Token ID | 862 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
Red | +0.350 |
Sioux | +0.341 |
Pt | +0.337 |
RED | +0.328 |
White | +0.297 |
Neg logit contributions | |
ubes | -0.570 |
atri | -0.536 |
utenberg | -0.528 |
hib | -0.524 |
netflix | -0.522 |
Token | j |
Token ID | 73 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
Red | +0.344 |
Sioux | +0.342 |
Pt | +0.334 |
RED | +0.323 |
Clarks | +0.295 |
Neg logit contributions | |
ubes | -0.725 |
atri | -0.686 |
hib | -0.676 |
utenberg | -0.671 |
netflix | -0.661 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ubes | +0.048 |
atri | +0.045 |
hib | +0.044 |
utenberg | +0.044 |
netflix | +0.043 |
Neg logit contributions | |
Red | -0.040 |
Sioux | -0.039 |
Pt | -0.039 |
RED | -0.038 |
White | -0.035 |
Token | com |
Token ID | 785 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
Red | +1.031 |
Sioux | +1.014 |
Pt | +1.000 |
RED | +0.976 |
White | +0.902 |
Neg logit contributions | |
ubes | -1.401 |
atri | -1.305 |
hib | -1.279 |
utenberg | -1.277 |
netflix | -1.267 |
Token | / |
Token ID | 14 |
Feature activation | -9.27e+00 |
Pos logit contributions | |
Red | +2.572 |
Sioux | +2.504 |
Pt | +2.489 |
RED | +2.437 |
White | +2.277 |
Neg logit contributions | |
ubes | -2.883 |
atri | -2.668 |
utenberg | -2.613 |
hib | -2.590 |
netflix | -2.580 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
Red | +5.096 |
Pt | +4.974 |
Sioux | +4.960 |
RED | +4.674 |
draft | +4.481 |
Neg logit contributions | |
ubes | -8.131 |
UTERS | -7.475 |
atri | -7.444 |
hib | -7.402 |
netflix | -7.394 |
Token | BP |
Token ID | 20866 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Red | +2.973 |
Pt | +2.931 |
Sioux | +2.878 |
RED | +2.788 |
White | +2.624 |
Neg logit contributions | |
ubes | -3.409 |
atri | -3.140 |
utenberg | -3.115 |
netflix | -3.112 |
hib | -3.047 |
Token | g |
Token ID | 70 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
Red | +1.678 |
Pt | +1.641 |
Sioux | +1.637 |
RED | +1.579 |
White | +1.479 |
Neg logit contributions | |
ubes | -2.015 |
atri | -1.865 |
utenberg | -1.839 |
netflix | -1.834 |
hib | -1.814 |
Token | 8 |
Token ID | 23 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
Red | +3.707 |
Pt | +3.635 |
Sioux | +3.578 |
RED | +3.490 |
White | +3.269 |
Neg logit contributions | |
ubes | -4.075 |
atri | -3.777 |
utenberg | -3.736 |
netflix | -3.731 |
hib | -3.628 |
Token | sm |
Token ID | 5796 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
Red | +2.772 |
Pt | +2.718 |
Sioux | +2.685 |
RED | +2.603 |
White | +2.444 |
Neg logit contributions | |
ubes | -3.290 |
atri | -3.039 |
utenberg | -3.010 |
netflix | -3.009 |
hib | -2.954 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Red | +1.150 |
Sioux | +1.118 |
Pt | +1.114 |
RED | +1.078 |
White | +1.006 |
Neg logit contributions | |
ubes | -1.857 |
atri | -1.735 |
hib | -1.723 |
netflix | -1.716 |
utenberg | -1.693 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Red | +1.024 |
Pt | +0.984 |
Sioux | +0.982 |
RED | +0.943 |
White | +0.860 |
Neg logit contributions | |
ubes | -2.435 |
atri | -2.318 |
hib | -2.292 |
utenberg | -2.271 |
netflix | -2.263 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Red | +1.050 |
Sioux | +1.018 |
Pt | +1.010 |
RED | +0.986 |
White | +0.919 |
Neg logit contributions | |
ubes | -1.617 |
atri | -1.529 |
utenberg | -1.513 |
hib | -1.505 |
netflix | -1.501 |
Token | 7 |
Token ID | 767 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
ubes | +1.133 |
atri | +1.061 |
utenberg | +1.038 |
hib | +1.033 |
netflix | +1.024 |
Neg logit contributions | |
Red | -1.006 |
Sioux | -0.986 |
Pt | -0.977 |
RED | -0.957 |
White | -0.895 |
Token | 8 |
Token ID | 807 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
ubes | +0.015 |
atri | +0.014 |
utenberg | +0.013 |
hib | +0.013 |
netflix | +0.013 |
Neg logit contributions | |
Red | -0.010 |
Sioux | -0.010 |
Pt | -0.010 |
RED | -0.010 |
White | -0.009 |
Token | void |
Token ID | 7951 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
Red | +1.505 |
Pt | +1.467 |
Sioux | +1.453 |
RED | +1.421 |
White | +1.350 |
Neg logit contributions | |
ubes | -2.221 |
atri | -2.066 |
utenberg | -2.045 |
hib | -2.041 |
netflix | -2.028 |
Token | vert |
Token ID | 9421 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Red | +3.132 |
Sioux | +2.966 |
Pt | +2.956 |
RED | +2.898 |
pt | +2.615 |
Neg logit contributions | |
ubes | -9.972 |
atri | -9.707 |
hib | -9.585 |
netflix | -9.558 |
utenberg | -9.506 |
Token | ( |
Token ID | 357 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Red | +0.299 |
Sioux | +0.296 |
Pt | +0.291 |
RED | +0.285 |
Clarks | +0.264 |
Neg logit contributions | |
ubes | -0.381 |
atri | -0.354 |
hib | -0.347 |
utenberg | -0.346 |
netflix | -0.344 |
Token | in |
Token ID | 287 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
ubes | +1.052 |
atri | +0.982 |
utenberg | +0.963 |
hib | +0.962 |
netflix | +0.953 |
Neg logit contributions | |
Red | -0.689 |
Sioux | -0.681 |
Pt | -0.666 |
RED | -0.654 |
Clarks | -0.609 |
Token | out |
Token ID | 448 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ubes | +3.843 |
atri | +3.567 |
hib | +3.432 |
utenberg | +3.413 |
netflix | +3.366 |
Neg logit contributions | |
Red | -4.351 |
Sioux | -4.350 |
Pt | -4.238 |
RED | -4.193 |
Clarks | -4.091 |
Token | app |
Token ID | 598 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Red | +1.220 |
Sioux | +1.170 |
Pt | +1.163 |
RED | +1.133 |
White | +1.011 |
Neg logit contributions | |
ubes | -2.743 |
atri | -2.605 |
utenberg | -2.558 |
hib | -2.549 |
netflix | -2.526 |
Token | |
Token ID | 220 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ubes | +1.278 |
atri | +1.201 |
hib | +1.180 |
utenberg | +1.177 |
netflix | +1.169 |
Neg logit contributions | |
Red | -0.714 |
Sioux | -0.704 |
Pt | -0.691 |
RED | -0.671 |
White | -0.608 |
Token | р |
Token ID | 21169 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ubes | +2.287 |
atri | +2.137 |
hib | +2.096 |
utenberg | +2.085 |
netflix | +2.074 |
Neg logit contributions | |
Red | -1.570 |
Sioux | -1.556 |
Pt | -1.527 |
RED | -1.490 |
Clarks | -1.367 |
Token | о |
Token ID | 15166 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ubes | +0.023 |
atri | +0.022 |
utenberg | +0.021 |
hib | +0.021 |
netflix | +0.021 |
Neg logit contributions | |
Red | -0.010 |
Sioux | -0.010 |
Pt | -0.010 |
RED | -0.009 |
White | -0.008 |
Token | с |
Token ID | 21727 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Red | +1.986 |
Sioux | +1.910 |
Pt | +1.908 |
RED | +1.880 |
White | +1.722 |
Neg logit contributions | |
ubes | -2.778 |
atri | -2.608 |
utenberg | -2.569 |
hib | -2.553 |
netflix | -2.543 |
Token | с |
Token ID | 21727 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
Red | +0.589 |
Sioux | +0.573 |
Pt | +0.569 |
RED | +0.559 |
White | +0.511 |
Neg logit contributions | |
ubes | -0.854 |
atri | -0.798 |
utenberg | -0.782 |
hib | -0.782 |
netflix | -0.776 |
Token | и |
Token ID | 18849 |
Feature activation | -9.09e+00 |
Pos logit contributions | |
Red | +1.374 |
Pt | +1.275 |
Sioux | +1.254 |
RED | +1.245 |
White | +1.044 |
Neg logit contributions | |
ubes | -4.958 |
atri | -4.725 |
hib | -4.674 |
utenberg | -4.663 |
netflix | -4.616 |
Token | � |
Token ID | 140 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
Red | +3.548 |
Pt | +3.368 |
RED | +3.265 |
Sioux | +3.144 |
White | +2.830 |
Neg logit contributions | |
ubes | -9.622 |
utenberg | -9.027 |
hib | -8.990 |
atri | -8.981 |
netflix | -8.867 |
Token | � |
Token ID | 117 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Red | +2.718 |
Sioux | +2.642 |
Pt | +2.570 |
RED | +2.485 |
White | +2.295 |
Neg logit contributions | |
ubes | -6.364 |
atri | -6.000 |
hib | -5.992 |
utenberg | -5.989 |
netflix | -5.880 |
Token | с |
Token ID | 21727 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ubes | +1.046 |
atri | +0.979 |
hib | +0.960 |
utenberg | +0.959 |
netflix | +0.951 |
Neg logit contributions | |
Red | -0.695 |
Sioux | -0.682 |
Pt | -0.674 |
RED | -0.658 |
White | -0.602 |
Token | к |
Token ID | 31583 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
Red | +0.948 |
Sioux | +0.927 |
Pt | +0.919 |
RED | +0.900 |
White | +0.829 |
Neg logit contributions | |
ubes | -1.315 |
atri | -1.229 |
hib | -1.213 |
utenberg | -1.211 |
netflix | -1.192 |
Token | о |
Token ID | 15166 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Red | +1.136 |
Pt | +1.064 |
Sioux | +1.007 |
RED | +0.987 |
White | +0.792 |
Neg logit contributions | |
ubes | -5.374 |
utenberg | -5.169 |
atri | -5.155 |
hib | -5.089 |
netflix | -5.011 |
Token | http |
Token ID | 2638 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Red | +0.327 |
Sioux | +0.322 |
Pt | +0.318 |
RED | +0.312 |
White | +0.292 |
Neg logit contributions | |
ubes | -0.333 |
atri | -0.308 |
hib | -0.300 |
utenberg | -0.299 |
netflix | -0.297 |
Token | :// |
Token ID | 1378 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
ubes | +0.059 |
atri | +0.052 |
hib | +0.051 |
utenberg | +0.051 |
netflix | +0.050 |
Neg logit contributions | |
Red | -0.107 |
Sioux | -0.107 |
Pt | -0.105 |
RED | -0.104 |
Clarks | -0.099 |
Token | cin |
Token ID | 17879 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
Red | +1.892 |
Pt | +1.820 |
Sioux | +1.786 |
RED | +1.773 |
White | +1.580 |
Neg logit contributions | |
ubes | -3.487 |
atri | -3.306 |
netflix | -3.252 |
UTERS | -3.230 |
utenberg | -3.229 |
Token | . |
Token ID | 13 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ubes | +3.076 |
hib | +2.812 |
atri | +2.800 |
utenberg | +2.674 |
netflix | +2.670 |
Neg logit contributions | |
Sioux | -2.993 |
Red | -2.989 |
Pt | -2.969 |
RED | -2.880 |
Clarks | -2.804 |
Token | ci |
Token ID | 979 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Red | +0.487 |
Sioux | +0.485 |
Pt | +0.476 |
RED | +0.466 |
Clarks | +0.434 |
Neg logit contributions | |
ubes | -0.594 |
atri | -0.556 |
hib | -0.543 |
utenberg | -0.538 |
netflix | -0.534 |
Token | / |
Token ID | 14 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
ubes | +1.018 |
atri | +0.928 |
hib | +0.919 |
utenberg | +0.887 |
netflix | +0.880 |
Neg logit contributions | |
Sioux | -1.206 |
Red | -1.183 |
Pt | -1.163 |
RED | -1.147 |
Clarks | -1.115 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
Red | +5.032 |
Pt | +4.904 |
Sioux | +4.825 |
RED | +4.569 |
draft | +4.476 |
Neg logit contributions | |
ubes | -7.851 |
UTERS | -7.209 |
utenberg | -7.195 |
atri | -7.190 |
netflix | -7.132 |
Token | yp |
Token ID | 4464 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Red | +2.006 |
Pt | +1.972 |
Sioux | +1.951 |
RED | +1.883 |
White | +1.757 |
Neg logit contributions | |
ubes | -2.572 |
atri | -2.382 |
utenberg | -2.351 |
netflix | -2.347 |
hib | -2.317 |
Token | d |
Token ID | 67 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Red | +1.212 |
Pt | +1.185 |
Sioux | +1.184 |
RED | +1.145 |
White | +1.072 |
Neg logit contributions | |
ubes | -1.423 |
atri | -1.314 |
utenberg | -1.296 |
netflix | -1.289 |
hib | -1.281 |
Token | G |
Token ID | 38 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Red | +1.878 |
Pt | +1.839 |
Sioux | +1.829 |
RED | +1.777 |
White | +1.664 |
Neg logit contributions | |
ubes | -2.120 |
atri | -1.962 |
utenberg | -1.935 |
netflix | -1.919 |
hib | -1.902 |
Token | uf |
Token ID | 3046 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Red | +1.948 |
Pt | +1.903 |
Sioux | +1.894 |
RED | +1.830 |
White | +1.716 |
Neg logit contributions | |
ubes | -2.352 |
atri | -2.177 |
utenberg | -2.146 |
netflix | -2.144 |
hib | -2.110 |
Token | =" |
Token ID | 2625 |
Feature activation | -7.62e+00 |
Pos logit contributions | |
Red | +0.569 |
Sioux | +0.566 |
Pt | +0.559 |
RED | +0.550 |
Clarks | +0.524 |
Neg logit contributions | |
ubes | -0.348 |
atri | -0.312 |
hib | -0.303 |
utenberg | -0.301 |
netflix | -0.298 |
Token | phone |
Token ID | 4862 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Red | +4.025 |
Pt | +3.894 |
Sioux | +3.887 |
RED | +3.696 |
draft | +3.634 |
Neg logit contributions | |
ubes | -6.925 |
utenberg | -6.479 |
atri | -6.467 |
UTERS | -6.321 |
bably | -6.220 |
Token | in |
Token ID | 287 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ubes | +1.842 |
atri | +1.726 |
hib | +1.695 |
utenberg | +1.691 |
netflix | +1.679 |
Neg logit contributions | |
Red | -1.116 |
Sioux | -1.099 |
Pt | -1.080 |
RED | -1.051 |
White | -0.958 |
Token | phones |
Token ID | 9512 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Red | +0.374 |
Sioux | +0.368 |
Pt | +0.363 |
RED | +0.354 |
White | +0.330 |
Neg logit contributions | |
ubes | -0.465 |
atri | -0.433 |
utenberg | -0.427 |
hib | -0.421 |
netflix | -0.418 |
Token | "> |
Token ID | 5320 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Red | +1.377 |
Pt | +1.349 |
Sioux | +1.331 |
RED | +1.297 |
White | +1.205 |
Neg logit contributions | |
ubes | -1.819 |
atri | -1.700 |
hib | -1.648 |
utenberg | -1.646 |
netflix | -1.616 |
Token | < |
Token ID | 1279 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
Red | +1.032 |
Sioux | +1.004 |
Pt | +0.992 |
RED | +0.977 |
White | +0.915 |
Neg logit contributions | |
ubes | -1.129 |
atri | -1.043 |
hib | -1.014 |
utenberg | -1.013 |
UTERS | -0.990 |
Token | span |
Token ID | 12626 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
Red | +4.584 |
Pt | +4.413 |
Sioux | +4.215 |
RED | +4.197 |
draft | +3.867 |
Neg logit contributions | |
ubes | -8.597 |
utenberg | -7.929 |
atri | -7.862 |
UTERS | -7.752 |
hib | -7.713 |
Token | ng |
Token ID | 23370 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
Red | +2.274 |
Sioux | +2.112 |
Pt | +2.108 |
RED | +2.099 |
White | +1.860 |
Neg logit contributions | |
ubes | -5.109 |
atri | -4.832 |
utenberg | -4.773 |
hib | -4.720 |
netflix | -4.712 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Red | +2.124 |
Sioux | +2.059 |
Pt | +2.017 |
RED | +1.960 |
White | +1.767 |
Neg logit contributions | |
ubes | -3.993 |
atri | -3.778 |
utenberg | -3.731 |
netflix | -3.683 |
hib | -3.676 |
Token | bind |
Token ID | 21653 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
Red | +0.747 |
Sioux | +0.728 |
Pt | +0.722 |
RED | +0.709 |
White | +0.659 |
Neg logit contributions | |
ubes | -0.828 |
atri | -0.768 |
utenberg | -0.756 |
hib | -0.749 |
netflix | -0.741 |
Token | =" |
Token ID | 2625 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
Red | +2.492 |
Sioux | +2.420 |
Pt | +2.413 |
RED | +2.377 |
White | +2.251 |
Neg logit contributions | |
ubes | -1.836 |
atri | -1.680 |
utenberg | -1.646 |
hib | -1.614 |
netflix | -1.592 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ubes | +1.485 |
atri | +1.379 |
hib | +1.357 |
utenberg | +1.346 |
netflix | +1.336 |
Neg logit contributions | |
Red | -1.139 |
Sioux | -1.130 |
Pt | -1.111 |
RED | -1.085 |
Clarks | -1.006 |
Token | - |
Token ID | 532 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Red | +1.026 |
Sioux | +1.006 |
Pt | +0.992 |
RED | +0.970 |
White | +0.898 |
Neg logit contributions | |
ubes | -1.366 |
atri | -1.274 |
utenberg | -1.247 |
hib | -1.244 |
netflix | -1.235 |
Token | January |
Token ID | 3269 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
Red | +0.808 |
Sioux | +0.797 |
Pt | +0.781 |
RED | +0.761 |
Clarks | +0.694 |
Neg logit contributions | |
ubes | -1.401 |
atri | -1.316 |
hib | -1.294 |
utenberg | -1.291 |
netflix | -1.279 |
Token | 4 |
Token ID | 604 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
Red | +3.412 |
Pt | +3.235 |
Sioux | +3.228 |
RED | +3.075 |
White | +2.880 |
Neg logit contributions | |
ubes | -7.185 |
atri | -6.823 |
hib | -6.738 |
netflix | -6.724 |
bably | -6.714 |
Token | , |
Token ID | 11 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
Red | +3.041 |
Pt | +2.889 |
Sioux | +2.888 |
RED | +2.772 |
White | +2.572 |
Neg logit contributions | |
ubes | -5.734 |
atri | -5.429 |
utenberg | -5.358 |
bably | -5.314 |
netflix | -5.278 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
Red | +2.375 |
Sioux | +2.288 |
Pt | +2.257 |
RED | +2.188 |
White | +2.013 |
Neg logit contributions | |
ubes | -5.012 |
atri | -4.758 |
hib | -4.634 |
utenberg | -4.623 |
netflix | -4.601 |
Token | User |
Token ID | 12982 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
Red | +7.191 |
Pt | +6.868 |
Sioux | +6.834 |
RED | +6.722 |
White | +6.551 |
Neg logit contributions | |
ubes | -5.937 |
netflix | -5.371 |
atri | -5.364 |
bably | -5.335 |
utenberg | -5.234 |
Token | reviews |
Token ID | 8088 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
Red | +2.832 |
Sioux | +2.643 |
Pt | +2.616 |
RED | +2.527 |
White | +2.211 |
Neg logit contributions | |
ubes | -8.242 |
atri | -7.875 |
utenberg | -7.818 |
netflix | -7.719 |
hib | -7.699 |
Token | are |
Token ID | 389 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
Red | +3.144 |
Sioux | +3.030 |
Pt | +2.993 |
RED | +2.924 |
White | +2.701 |
Neg logit contributions | |
ubes | -4.845 |
atri | -4.556 |
hib | -4.487 |
utenberg | -4.451 |
netflix | -4.450 |
Token | a |
Token ID | 257 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Red | +2.273 |
Sioux | +2.223 |
Pt | +2.193 |
RED | +2.121 |
White | +1.919 |
Neg logit contributions | |
ubes | -4.374 |
atri | -4.117 |
utenberg | -4.043 |
hib | -4.043 |
netflix | -4.019 |
Token | bad |
Token ID | 2089 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Sioux | +1.025 |
Red | +1.013 |
Pt | +0.992 |
RED | +0.960 |
Clarks | +0.892 |
Neg logit contributions | |
ubes | -1.825 |
atri | -1.709 |
hib | -1.690 |
utenberg | -1.659 |
netflix | -1.654 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Red | +1.595 |
Sioux | +1.550 |
Pt | +1.525 |
RED | +1.502 |
White | +1.382 |
Neg logit contributions | |
ubes | -2.326 |
atri | -2.179 |
utenberg | -2.146 |
hib | -2.133 |
netflix | -2.113 |
Token | - |
Token ID | 532 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Red | +0.162 |
Sioux | +0.160 |
Pt | +0.158 |
RED | +0.154 |
White | +0.143 |
Neg logit contributions | |
ubes | -0.198 |
atri | -0.184 |
hib | -0.180 |
utenberg | -0.180 |
netflix | -0.178 |
Token | December |
Token ID | 3426 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
Red | +0.656 |
Sioux | +0.648 |
Pt | +0.637 |
RED | +0.619 |
Clarks | +0.564 |
Neg logit contributions | |
ubes | -1.088 |
atri | -1.019 |
hib | -1.001 |
utenberg | -0.999 |
netflix | -0.990 |
Token | 5 |
Token ID | 642 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
Red | +3.237 |
Sioux | +3.082 |
Pt | +3.052 |
RED | +2.806 |
White | +2.631 |
Neg logit contributions | |
ubes | -9.184 |
atri | -8.810 |
bably | -8.624 |
utenberg | -8.623 |
hib | -8.609 |
Token | , |
Token ID | 11 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
Red | +3.366 |
Sioux | +3.197 |
Pt | +3.189 |
RED | +3.065 |
White | +2.836 |
Neg logit contributions | |
ubes | -6.525 |
atri | -6.157 |
utenberg | -6.090 |
bably | -6.069 |
netflix | -6.008 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -8.99e+00 |
Pos logit contributions | |
Red | +2.896 |
Sioux | +2.820 |
Pt | +2.755 |
RED | +2.687 |
White | +2.522 |
Neg logit contributions | |
ubes | -5.147 |
atri | -4.855 |
utenberg | -4.700 |
ictionary | -4.692 |
hib | -4.686 |
Token | Que |
Token ID | 15681 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
Red | +5.813 |
Sioux | +5.583 |
Pt | +5.495 |
RED | +5.351 |
draft | +5.144 |
Neg logit contributions | |
ubes | -7.053 |
utenberg | -6.679 |
bably | -6.636 |
ailability | -6.583 |
atri | -6.520 |
Token | ers |
Token ID | 364 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
Red | +4.030 |
Sioux | +3.760 |
Pt | +3.734 |
RED | +3.661 |
White | +3.342 |
Neg logit contributions | |
ubes | -7.083 |
utenberg | -6.821 |
atri | -6.764 |
netflix | -6.656 |
ictionary | -6.634 |
Token | are |
Token ID | 389 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
Red | +3.452 |
Sioux | +3.212 |
Pt | +3.186 |
RED | +3.124 |
White | +2.865 |
Neg logit contributions | |
ubes | -6.080 |
atri | -5.786 |
utenberg | -5.720 |
UTERS | -5.712 |
netflix | -5.705 |
Token | Here |
Token ID | 3423 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
Red | +4.740 |
Pt | +4.527 |
Sioux | +4.436 |
RED | +4.345 |
White | +4.137 |
Neg logit contributions | |
ubes | -6.266 |
atri | -5.773 |
utenberg | -5.745 |
ictionary | -5.664 |
netflix | -5.657 |
Token | .... |
Token ID | 1106 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Red | +2.133 |
Sioux | +2.052 |
Pt | +2.051 |
RED | +2.027 |
White | +1.849 |
Neg logit contributions | |
ubes | -2.925 |
atri | -2.735 |
utenberg | -2.715 |
ictionary | -2.672 |
netflix | -2.672 |
Token | OT |
Token ID | 2394 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
ubes | +1.126 |
atri | +1.036 |
hib | +1.012 |
utenberg | +1.010 |
netflix | +0.999 |
Neg logit contributions | |
Red | -1.162 |
Sioux | -1.149 |
Pt | -1.135 |
RED | -1.112 |
White | -1.040 |
Token | TA |
Token ID | 5603 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Red | +1.792 |
Sioux | +1.763 |
Pt | +1.719 |
RED | +1.704 |
White | +1.566 |
Neg logit contributions | |
ubes | -2.385 |
atri | -2.254 |
utenberg | -2.211 |
netflix | -2.203 |
hib | -2.198 |
Token | WA |
Token ID | 15543 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Red | +2.682 |
Sioux | +2.547 |
RED | +2.528 |
Pt | +2.459 |
White | +2.255 |
Neg logit contributions | |
ubes | -4.241 |
utenberg | -4.058 |
atri | -4.007 |
netflix | -3.992 |
bably | -3.845 |
Token | ( |
Token ID | 357 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
Red | +1.413 |
Sioux | +1.366 |
Pt | +1.360 |
RED | +1.349 |
White | +1.232 |
Neg logit contributions | |
ubes | -2.081 |
atri | -1.959 |
utenberg | -1.926 |
netflix | -1.909 |
hib | -1.908 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
Red | +2.684 |
Sioux | +2.623 |
Pt | +2.605 |
RED | +2.559 |
White | +2.397 |
Neg logit contributions | |
ubes | -2.574 |
atri | -2.363 |
hib | -2.308 |
netflix | -2.298 |
utenberg | -2.278 |
Token | ) |
Token ID | 8 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
ubes | +0.004 |
atri | +0.003 |
hib | +0.003 |
UTERS | +0.003 |
utenberg | +0.003 |
Neg logit contributions | |
Red | -0.004 |
Sioux | -0.004 |
Pt | -0.004 |
RED | -0.004 |
Clarks | -0.004 |
Token | - |
Token ID | 532 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
Red | +3.412 |
Sioux | +3.201 |
Pt | +3.098 |
RED | +3.058 |
White | +2.751 |
Neg logit contributions | |
ubes | -9.928 |
atri | -9.515 |
utenberg | -9.361 |
bably | -9.297 |
netflix | -9.288 |
Token | Canada |
Token ID | 3340 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Red | +3.445 |
Sioux | +3.274 |
Pt | +3.213 |
RED | +3.186 |
White | +3.046 |
Neg logit contributions | |
ubes | -4.969 |
atri | -4.675 |
utenberg | -4.653 |
hib | -4.575 |
bably | -4.558 |
Token | � |
Token ID | 447 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ubes | +0.220 |
atri | +0.205 |
hib | +0.202 |
utenberg | +0.201 |
netflix | +0.200 |
Neg logit contributions | |
Red | -0.161 |
Sioux | -0.158 |
Pt | -0.156 |
RED | -0.152 |
White | -0.141 |
Token | � |
Token ID | 247 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
Red | +0.577 |
Sioux | +0.571 |
Pt | +0.559 |
RED | +0.543 |
Clarks | +0.491 |
Neg logit contributions | |
ubes | -1.086 |
atri | -1.021 |
hib | -1.002 |
utenberg | -0.998 |
netflix | -0.991 |
Token | s |
Token ID | 82 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ubes | +0.298 |
atri | +0.276 |
utenberg | +0.271 |
hib | +0.271 |
netflix | +0.269 |
Neg logit contributions | |
Red | -0.227 |
Sioux | -0.223 |
Pt | -0.220 |
RED | -0.215 |
White | -0.199 |
Token |
|
Token ID | 198 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
ubes | +0.118 |
atri | +0.110 |
hib | +0.108 |
utenberg | +0.108 |
netflix | +0.107 |
Neg logit contributions | |
Red | -0.082 |
Sioux | -0.080 |
Pt | -0.079 |
RED | -0.077 |
White | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Red | +0.347 |
Sioux | +0.340 |
Pt | +0.336 |
RED | +0.328 |
White | +0.308 |
Neg logit contributions | |
ubes | -0.402 |
atri | -0.371 |
utenberg | -0.364 |
hib | -0.361 |
netflix | -0.357 |
Token | 2017 |
Token ID | 5539 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
Red | +0.895 |
Sioux | +0.880 |
Pt | +0.871 |
RED | +0.851 |
White | +0.800 |
Neg logit contributions | |
ubes | -0.861 |
atri | -0.787 |
utenberg | -0.777 |
hib | -0.769 |
netflix | -0.758 |
Token | - |
Token ID | 12 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
Red | +0.003 |
Sioux | +0.003 |
Pt | +0.003 |
RED | +0.003 |
White | +0.003 |
Neg logit contributions | |
ubes | -0.004 |
atri | -0.004 |
hib | -0.004 |
utenberg | -0.004 |
netflix | -0.004 |
Token | 09 |
Token ID | 2931 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Red | +3.085 |
Pt | +2.978 |
Sioux | +2.977 |
RED | +2.912 |
White | +2.731 |
Neg logit contributions | |
ubes | -3.676 |
atri | -3.413 |
utenberg | -3.374 |
hib | -3.315 |
bably | -3.291 |
Token | - |
Token ID | 12 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
Red | +1.773 |
Sioux | +1.704 |
Pt | +1.688 |
RED | +1.636 |
White | +1.490 |
Neg logit contributions | |
ubes | -3.391 |
atri | -3.178 |
utenberg | -3.161 |
netflix | -3.112 |
bably | -3.098 |
Token | 05 |
Token ID | 2713 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Red | +5.132 |
Pt | +4.892 |
Sioux | +4.788 |
RED | +4.773 |
draft | +4.499 |
Neg logit contributions | |
ubes | -7.590 |
utenberg | -7.152 |
atri | -7.146 |
bably | -7.027 |
ailability | -7.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Red | +1.504 |
Sioux | +1.462 |
Pt | +1.441 |
RED | +1.415 |
White | +1.325 |
Neg logit contributions | |
ubes | -1.721 |
atri | -1.597 |
utenberg | -1.576 |
netflix | -1.566 |
hib | -1.564 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Red | +0.994 |
Sioux | +0.989 |
Pt | +0.972 |
RED | +0.954 |
Clarks | +0.895 |
Neg logit contributions | |
ubes | -0.997 |
atri | -0.918 |
hib | -0.901 |
utenberg | -0.894 |
netflix | -0.888 |
Token | Dear |
Token ID | 20266 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Red | +1.001 |
Sioux | +0.985 |
Pt | +0.975 |
RED | +0.951 |
White | +0.893 |
Neg logit contributions | |
ubes | -0.985 |
atri | -0.898 |
utenberg | -0.891 |
hib | -0.877 |
netflix | -0.867 |
Token | users |
Token ID | 2985 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Red | +1.576 |
Sioux | +1.537 |
Pt | +1.497 |
RED | +1.482 |
White | +1.380 |
Neg logit contributions | |
ubes | -2.022 |
atri | -1.877 |
utenberg | -1.845 |
hib | -1.845 |
netflix | -1.831 |
Token | com |
Token ID | 785 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Red | +0.979 |
Sioux | +0.971 |
Pt | +0.954 |
RED | +0.932 |
Clarks | +0.866 |
Neg logit contributions | |
ubes | -1.259 |
atri | -1.171 |
hib | -1.148 |
utenberg | -1.145 |
netflix | -1.137 |
Token | / |
Token ID | 14 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
Red | +2.941 |
Sioux | +2.851 |
Pt | +2.840 |
RED | +2.801 |
White | +2.596 |
Neg logit contributions | |
ubes | -3.342 |
atri | -3.108 |
utenberg | -3.028 |
hib | -3.019 |
netflix | -2.992 |
Token | watch |
Token ID | 8340 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
Red | +2.419 |
Sioux | +2.310 |
Pt | +2.297 |
RED | +2.247 |
draft | +2.080 |
Neg logit contributions | |
ubes | -4.592 |
atri | -4.299 |
hib | -4.183 |
ictionary | -4.146 |
utenberg | -4.132 |
Token | ? |
Token ID | 30 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ubes | +0.040 |
atri | +0.036 |
hib | +0.036 |
utenberg | +0.035 |
netflix | +0.035 |
Neg logit contributions | |
Red | -0.049 |
Sioux | -0.049 |
Pt | -0.048 |
RED | -0.048 |
Clarks | -0.045 |
Token | v |
Token ID | 85 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Red | +2.842 |
Sioux | +2.748 |
Pt | +2.741 |
RED | +2.675 |
White | +2.495 |
Neg logit contributions | |
ubes | -3.341 |
atri | -3.124 |
utenberg | -3.033 |
hib | -3.014 |
netflix | -3.002 |
Token | = |
Token ID | 28 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
Red | +1.019 |
Sioux | +1.007 |
Pt | +1.001 |
RED | +0.986 |
White | +0.935 |
Neg logit contributions | |
ubes | -0.533 |
atri | -0.479 |
utenberg | -0.459 |
hib | -0.457 |
netflix | -0.450 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Red | +5.691 |
Pt | +5.641 |
Sioux | +5.417 |
RED | +5.282 |
cz | +5.121 |
Neg logit contributions | |
ubes | -6.528 |
utenberg | -6.025 |
atri | -6.016 |
netflix | -5.972 |
UTERS | -5.836 |
Token | g |
Token ID | 70 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Red | +2.649 |
Pt | +2.612 |
Sioux | +2.573 |
RED | +2.490 |
White | +2.334 |
Neg logit contributions | |
ubes | -3.112 |
atri | -2.880 |
utenberg | -2.849 |
netflix | -2.840 |
hib | -2.796 |
Token | 7 |
Token ID | 22 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Red | +2.150 |
Pt | +2.112 |
Sioux | +2.095 |
RED | +2.032 |
White | +1.900 |
Neg logit contributions | |
ubes | -2.428 |
atri | -2.252 |
utenberg | -2.220 |
netflix | -2.206 |
hib | -2.173 |
Token | p |
Token ID | 79 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Red | +2.319 |
Pt | +2.281 |
Sioux | +2.253 |
RED | +2.182 |
White | +2.047 |
Neg logit contributions | |
ubes | -2.728 |
atri | -2.523 |
utenberg | -2.496 |
netflix | -2.483 |
hib | -2.455 |
Token | k |
Token ID | 74 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Red | +1.606 |
Pt | +1.574 |
Sioux | +1.569 |
RED | +1.522 |
White | +1.422 |
Neg logit contributions | |
ubes | -1.803 |
atri | -1.670 |
utenberg | -1.648 |
netflix | -1.634 |
hib | -1.624 |
Token | full |
Token ID | 1336 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
Red | +0.888 |
Pt | +0.866 |
Sioux | +0.864 |
RED | +0.837 |
White | +0.770 |
Neg logit contributions | |
ubes | -1.404 |
atri | -1.318 |
hib | -1.296 |
utenberg | -1.283 |
netflix | -1.278 |
Token | v |
Token ID | 410 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Red | +0.027 |
Sioux | +0.026 |
Pt | +0.026 |
RED | +0.025 |
Clarks | +0.023 |
Neg logit contributions | |
ubes | -0.043 |
atri | -0.040 |
utenberg | -0.040 |
hib | -0.040 |
netflix | -0.039 |
Token | ) |
Token ID | 1267 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Red | +0.590 |
Sioux | +0.585 |
Pt | +0.578 |
RED | +0.568 |
Clarks | +0.537 |
Neg logit contributions | |
ubes | -0.414 |
atri | -0.375 |
hib | -0.364 |
utenberg | -0.362 |
netflix | -0.359 |
Token | { |
Token ID | 1391 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
Red | +1.602 |
Sioux | +1.581 |
Pt | +1.559 |
RED | +1.526 |
White | +1.415 |
Neg logit contributions | |
ubes | -1.893 |
atri | -1.758 |
hib | -1.720 |
utenberg | -1.716 |
netflix | -1.702 |
Token | // |
Token ID | 3373 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
Red | +2.697 |
Sioux | +2.523 |
Pt | +2.522 |
RED | +2.470 |
White | +2.267 |
Neg logit contributions | |
ubes | -5.285 |
atri | -4.960 |
netflix | -4.870 |
utenberg | -4.868 |
bably | -4.859 |
Token | Time |
Token ID | 3862 |
Feature activation | -8.56e+00 |
Pos logit contributions | |
Red | +4.178 |
Pt | +3.969 |
RED | +3.832 |
Sioux | +3.827 |
White | +3.747 |
Neg logit contributions | |
ubes | -3.919 |
atri | -3.700 |
netflix | -3.612 |
utenberg | -3.611 |
hib | -3.590 |
Token | component |
Token ID | 7515 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Red | +4.593 |
Pt | +4.345 |
Sioux | +4.260 |
RED | +4.154 |
White | +3.853 |
Neg logit contributions | |
ubes | -8.206 |
atri | -7.661 |
bably | -7.558 |
netflix | -7.543 |
utenberg | -7.508 |
Token | const |
Token ID | 1500 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
Red | +0.637 |
Sioux | +0.626 |
Pt | +0.611 |
RED | +0.590 |
White | +0.521 |
Neg logit contributions | |
ubes | -1.547 |
atri | -1.462 |
hib | -1.439 |
utenberg | -1.436 |
netflix | -1.427 |
Token | float |
Token ID | 12178 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
Red | +2.424 |
Sioux | +2.352 |
Pt | +2.328 |
RED | +2.299 |
White | +2.127 |
Neg logit contributions | |
ubes | -3.160 |
atri | -2.971 |
utenberg | -2.913 |
netflix | -2.913 |
hib | -2.904 |
Token | TA |
Token ID | 21664 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
Red | +5.563 |
Sioux | +5.510 |
RED | +5.485 |
Pt | +5.476 |
White | +5.167 |
Neg logit contributions | |
ubes | -2.790 |
hib | -2.487 |
utenberg | -2.457 |
atri | -2.455 |
netflix | -2.405 |
Token | U |
Token ID | 52 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ubes | +4.558 |
atri | +4.094 |
UTERS | +4.028 |
hib | +3.934 |
utenberg | +3.881 |
Neg logit contributions | |
Sioux | -5.664 |
Red | -5.510 |
Pt | -5.493 |
Clarks | -5.397 |
RED | -5.339 |
Token | ? |
Token ID | 30 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Red | +1.479 |
Sioux | +1.450 |
Pt | +1.423 |
RED | +1.396 |
White | +1.299 |
Neg logit contributions | |
ubes | -1.890 |
atri | -1.758 |
utenberg | -1.737 |
hib | -1.714 |
netflix | -1.709 |
Token | - |
Token ID | 532 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ubes | +0.123 |
atri | +0.114 |
hib | +0.112 |
utenberg | +0.111 |
netflix | +0.110 |
Neg logit contributions | |
Red | -0.104 |
Sioux | -0.102 |
Pt | -0.101 |
RED | -0.099 |
White | -0.091 |
Token | January |
Token ID | 3269 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
Red | +0.195 |
Sioux | +0.193 |
Pt | +0.189 |
RED | +0.185 |
Clarks | +0.170 |
Neg logit contributions | |
ubes | -0.326 |
atri | -0.306 |
hib | -0.301 |
utenberg | -0.300 |
netflix | -0.296 |
Token | 15 |
Token ID | 1315 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
Red | +2.921 |
Sioux | +2.843 |
Pt | +2.789 |
RED | +2.690 |
White | +2.525 |
Neg logit contributions | |
ubes | -4.852 |
atri | -4.584 |
utenberg | -4.495 |
hib | -4.490 |
netflix | -4.477 |
Token | , |
Token ID | 11 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
Red | +3.750 |
Pt | +3.538 |
Sioux | +3.524 |
RED | +3.379 |
White | +3.145 |
Neg logit contributions | |
ubes | -7.523 |
atri | -7.148 |
utenberg | -7.068 |
bably | -7.048 |
ailability | -6.964 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -8.51e+00 |
Pos logit contributions | |
Red | +2.477 |
Sioux | +2.386 |
Pt | +2.339 |
RED | +2.278 |
White | +2.098 |
Neg logit contributions | |
ubes | -5.260 |
atri | -4.998 |
hib | -4.865 |
utenberg | -4.859 |
netflix | -4.828 |
Token | Que |
Token ID | 15681 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
Red | +5.762 |
Sioux | +5.545 |
Pt | +5.429 |
RED | +5.330 |
draft | +5.072 |
Neg logit contributions | |
ubes | -6.619 |
utenberg | -6.203 |
bably | -6.151 |
ailability | -6.136 |
atri | -6.130 |
Token | er |
Token ID | 263 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
Red | +4.375 |
Sioux | +4.112 |
Pt | +4.104 |
RED | +4.027 |
White | +3.726 |
Neg logit contributions | |
ubes | -6.481 |
atri | -6.014 |
utenberg | -6.001 |
netflix | -5.948 |
UTERS | -5.939 |
Token | magnet |
Token ID | 19972 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Red | +4.859 |
Pt | +4.721 |
Sioux | +4.684 |
RED | +4.599 |
White | +4.364 |
Neg logit contributions | |
ubes | -3.913 |
netflix | -3.547 |
atri | -3.544 |
utenberg | -3.516 |
hib | -3.479 |
Token | ? |
Token ID | 30 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Red | +3.995 |
Pt | +3.875 |
Sioux | +3.867 |
RED | +3.747 |
White | +3.578 |
Neg logit contributions | |
ubes | -4.353 |
atri | -4.093 |
utenberg | -3.998 |
netflix | -3.979 |
hib | -3.976 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ubes | +0.297 |
atri | +0.276 |
utenberg | +0.269 |
hib | +0.269 |
netflix | +0.266 |
Neg logit contributions | |
Red | -0.251 |
Sioux | -0.247 |
Pt | -0.244 |
RED | -0.239 |
White | -0.223 |
Token | + |
Token ID | 1343 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
ubes | +3.088 |
atri | +2.898 |
hib | +2.850 |
utenberg | +2.840 |
netflix | +2.818 |
Neg logit contributions | |
Red | -1.821 |
Sioux | -1.805 |
Pt | -1.772 |
RED | -1.721 |
Clarks | -1.572 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ubes | +0.600 |
atri | +0.560 |
hib | +0.548 |
utenberg | +0.547 |
netflix | +0.544 |
Neg logit contributions | |
Red | -0.437 |
Sioux | -0.431 |
Pt | -0.424 |
RED | -0.415 |
White | -0.382 |
Token | --+ |
Token ID | 44785 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Red | +0.877 |
Sioux | +0.870 |
Pt | +0.859 |
RED | +0.844 |
Clarks | +0.794 |
Neg logit contributions | |
ubes | -0.706 |
atri | -0.644 |
hib | -0.628 |
utenberg | -0.625 |
netflix | -0.617 |
Token | | |
Token ID | 930 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
ubes | +0.099 |
atri | +0.092 |
utenberg | +0.090 |
hib | +0.090 |
netflix | +0.090 |
Neg logit contributions | |
Red | -0.077 |
Sioux | -0.075 |
Pt | -0.074 |
RED | -0.073 |
White | -0.068 |
Token | [ |
Token ID | 685 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Red | +2.182 |
Sioux | +2.098 |
Pt | +2.066 |
RED | +2.053 |
White | +1.910 |
Neg logit contributions | |
ubes | -2.823 |
atri | -2.623 |
utenberg | -2.573 |
netflix | -2.571 |
hib | -2.560 |
Token | return |
Token ID | 7783 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
Red | +3.228 |
Sioux | +3.129 |
Pt | +3.072 |
RED | +3.066 |
White | +2.852 |
Neg logit contributions | |
ubes | -3.252 |
atri | -2.951 |
utenberg | -2.931 |
netflix | -2.859 |
hib | -2.840 |
Token | address |
Token ID | 2209 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
Red | +3.583 |
Sioux | +3.303 |
Pt | +3.256 |
RED | +3.241 |
White | +2.960 |
Neg logit contributions | |
ubes | -8.978 |
utenberg | -8.354 |
netflix | -8.340 |
atri | -8.332 |
hib | -8.166 |
Token | ] |
Token ID | 60 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Red | +2.093 |
Sioux | +1.945 |
Pt | +1.905 |
RED | +1.902 |
White | +1.669 |
Neg logit contributions | |
ubes | -5.344 |
atri | -5.029 |
utenberg | -4.978 |
hib | -4.932 |
netflix | -4.918 |
Token | | |
Token ID | 930 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Red | +1.756 |
Sioux | +1.668 |
Pt | +1.659 |
RED | +1.648 |
White | +1.510 |
Neg logit contributions | |
ubes | -2.543 |
atri | -2.371 |
utenberg | -2.320 |
netflix | -2.317 |
hib | -2.304 |
Token | + |
Token ID | 1343 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ubes | +0.228 |
atri | +0.211 |
utenberg | +0.207 |
hib | +0.206 |
netflix | +0.205 |
Neg logit contributions | |
Red | -0.188 |
Sioux | -0.183 |
Pt | -0.181 |
RED | -0.178 |
White | -0.165 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Red | +0.316 |
Sioux | +0.313 |
Pt | +0.307 |
RED | +0.298 |
Clarks | +0.274 |
Neg logit contributions | |
ubes | -0.535 |
atri | -0.501 |
hib | -0.494 |
utenberg | -0.491 |
netflix | -0.486 |
Token | http |
Token ID | 2638 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Red | +0.911 |
Sioux | +0.900 |
Pt | +0.885 |
RED | +0.868 |
White | +0.811 |
Neg logit contributions | |
ubes | -0.983 |
atri | -0.910 |
hib | -0.888 |
utenberg | -0.885 |
netflix | -0.876 |
Token | :// |
Token ID | 1378 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
Red | +0.178 |
Sioux | +0.178 |
Pt | +0.175 |
RED | +0.173 |
Clarks | +0.165 |
Neg logit contributions | |
ubes | -0.100 |
atri | -0.089 |
hib | -0.087 |
utenberg | -0.086 |
netflix | -0.085 |
Token | usat |
Token ID | 37937 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Red | +3.068 |
Sioux | +3.017 |
Pt | +2.993 |
RED | +2.953 |
White | +2.772 |
Neg logit contributions | |
ubes | -2.427 |
atri | -2.175 |
utenberg | -2.128 |
hib | -2.117 |
UTERS | -2.102 |
Token | . |
Token ID | 13 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
Red | +1.485 |
Sioux | +1.466 |
Pt | +1.445 |
RED | +1.413 |
White | +1.309 |
Neg logit contributions | |
ubes | -1.835 |
atri | -1.706 |
hib | -1.671 |
utenberg | -1.668 |
netflix | -1.654 |
Token | ly |
Token ID | 306 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Red | +1.934 |
Sioux | +1.876 |
Pt | +1.867 |
RED | +1.791 |
White | +1.630 |
Neg logit contributions | |
ubes | -3.929 |
atri | -3.700 |
hib | -3.640 |
utenberg | -3.635 |
netflix | -3.620 |
Token | / |
Token ID | 14 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
Red | +0.893 |
Sioux | +0.885 |
Pt | +0.872 |
RED | +0.855 |
Clarks | +0.800 |
Neg logit contributions | |
ubes | -0.894 |
atri | -0.824 |
hib | -0.807 |
utenberg | -0.802 |
netflix | -0.796 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Red | +4.895 |
Sioux | +4.738 |
Pt | +4.717 |
RED | +4.506 |
draft | +4.338 |
Neg logit contributions | |
ubes | -7.257 |
utenberg | -6.674 |
atri | -6.646 |
hib | -6.550 |
UTERS | -6.507 |
Token | G |
Token ID | 38 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Red | +1.967 |
Pt | +1.934 |
Sioux | +1.911 |
RED | +1.853 |
White | +1.735 |
Neg logit contributions | |
ubes | -2.306 |
atri | -2.130 |
utenberg | -2.102 |
netflix | -2.097 |
hib | -2.073 |
Token | q |
Token ID | 80 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
Red | +1.994 |
Pt | +1.954 |
Sioux | +1.940 |
RED | +1.874 |
White | +1.758 |
Neg logit contributions | |
ubes | -2.373 |
atri | -2.198 |
netflix | -2.159 |
utenberg | -2.158 |
hib | -2.127 |
Token | FP |
Token ID | 5837 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Red | +3.349 |
Pt | +3.292 |
Sioux | +3.228 |
RED | +3.147 |
White | +2.960 |
Neg logit contributions | |
ubes | -3.812 |
atri | -3.514 |
utenberg | -3.505 |
netflix | -3.480 |
hib | -3.398 |
Token | P |
Token ID | 47 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Red | +1.330 |
Pt | +1.302 |
Sioux | +1.297 |
RED | +1.253 |
White | +1.172 |
Neg logit contributions | |
ubes | -1.601 |
atri | -1.479 |
utenberg | -1.461 |
netflix | -1.453 |
hib | -1.441 |
Token | org |
Token ID | 2398 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Red | +0.401 |
Sioux | +0.394 |
Pt | +0.390 |
RED | +0.380 |
White | +0.353 |
Neg logit contributions | |
ubes | -0.521 |
atri | -0.485 |
hib | -0.476 |
utenberg | -0.473 |
netflix | -0.469 |
Token | / |
Token ID | 14 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
Red | +2.249 |
Sioux | +2.194 |
Pt | +2.159 |
RED | +2.126 |
White | +1.998 |
Neg logit contributions | |
ubes | -2.509 |
atri | -2.288 |
utenberg | -2.247 |
netflix | -2.233 |
hib | -2.220 |
Token | 2015 |
Token ID | 4626 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Red | +3.911 |
Sioux | +3.815 |
Pt | +3.760 |
RED | +3.692 |
White | +3.493 |
Neg logit contributions | |
ubes | -3.827 |
atri | -3.490 |
utenberg | -3.447 |
UTERS | -3.408 |
netflix | -3.397 |
Token | / |
Token ID | 14 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
Red | +0.100 |
Sioux | +0.098 |
Pt | +0.097 |
RED | +0.095 |
White | +0.089 |
Neg logit contributions | |
ubes | -0.109 |
atri | -0.100 |
utenberg | -0.099 |
hib | -0.098 |
netflix | -0.097 |
Token | 08 |
Token ID | 2919 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
Red | +4.764 |
Sioux | +4.620 |
Pt | +4.581 |
RED | +4.491 |
draft | +4.229 |
Neg logit contributions | |
ubes | -5.727 |
utenberg | -5.245 |
atri | -5.208 |
UTERS | -5.166 |
CLUD | -5.084 |
Token | / |
Token ID | 14 |
Feature activation | -8.44e+00 |
Pos logit contributions | |
Red | +2.866 |
Pt | +2.784 |
Sioux | +2.776 |
RED | +2.713 |
White | +2.528 |
Neg logit contributions | |
ubes | -3.244 |
atri | -3.017 |
utenberg | -2.978 |
netflix | -2.919 |
hib | -2.905 |
Token | 11 |
Token ID | 1157 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
Red | +5.292 |
Sioux | +5.080 |
Pt | +4.988 |
RED | +4.976 |
draft | +4.760 |
Neg logit contributions | |
ubes | -6.941 |
utenberg | -6.429 |
UTERS | -6.381 |
atri | -6.350 |
CLUD | -6.229 |
Token | / |
Token ID | 14 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
Red | +0.438 |
Sioux | +0.434 |
Pt | +0.428 |
RED | +0.420 |
Clarks | +0.392 |
Neg logit contributions | |
ubes | -0.440 |
atri | -0.406 |
hib | -0.397 |
utenberg | -0.394 |
netflix | -0.391 |
Token | e |
Token ID | 68 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Red | +2.674 |
Sioux | +2.617 |
Pt | +2.577 |
RED | +2.546 |
White | +2.379 |
Neg logit contributions | |
ubes | -3.027 |
atri | -2.780 |
utenberg | -2.757 |
UTERS | -2.700 |
netflix | -2.682 |
Token | uth |
Token ID | 1071 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Red | +1.426 |
Sioux | +1.375 |
Pt | +1.352 |
RED | +1.307 |
White | +1.184 |
Neg logit contributions | |
ubes | -2.891 |
atri | -2.699 |
netflix | -2.674 |
utenberg | -2.672 |
hib | -2.665 |
Token | an |
Token ID | 272 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
ubes | +0.341 |
atri | +0.308 |
utenberg | +0.302 |
hib | +0.301 |
netflix | +0.298 |
Neg logit contributions | |
Red | -0.471 |
Sioux | -0.465 |
Pt | -0.460 |
RED | -0.453 |
White | -0.428 |
Token | free |
Token ID | 1479 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Red | +0.061 |
Sioux | +0.061 |
Pt | +0.060 |
RED | +0.059 |
White | +0.054 |
Neg logit contributions | |
ubes | -0.071 |
atri | -0.066 |
hib | -0.064 |
utenberg | -0.064 |
netflix | -0.064 |
Token | up |
Token ID | 510 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Red | +0.952 |
Sioux | +0.935 |
Pt | +0.915 |
RED | +0.903 |
White | +0.842 |
Neg logit contributions | |
ubes | -1.205 |
atri | -1.113 |
utenberg | -1.099 |
hib | -1.094 |
netflix | -1.088 |
Token | cash |
Token ID | 5003 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ubes | +0.612 |
atri | +0.571 |
hib | +0.560 |
utenberg | +0.559 |
netflix | +0.555 |
Neg logit contributions | |
Red | -0.432 |
Sioux | -0.426 |
Pt | -0.419 |
RED | -0.409 |
White | -0.376 |
Token | flow |
Token ID | 5202 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Red | +1.192 |
Sioux | +1.161 |
Pt | +1.138 |
RED | +1.129 |
White | +1.044 |
Neg logit contributions | |
ubes | -1.682 |
atri | -1.563 |
utenberg | -1.539 |
netflix | -1.537 |
hib | -1.530 |
Token |
|
Token ID | 198 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
ubes | +0.523 |
atri | +0.488 |
hib | +0.478 |
utenberg | +0.477 |
netflix | +0.474 |
Neg logit contributions | |
Red | -0.375 |
Sioux | -0.370 |
Pt | -0.364 |
RED | -0.355 |
White | -0.327 |
Token |
|
Token ID | 198 |
Feature activation | -8.40e+00 |
Pos logit contributions | |
Red | +3.809 |
Pt | +3.652 |
Sioux | +3.649 |
RED | +3.583 |
White | +3.347 |
Neg logit contributions | |
ubes | -4.834 |
atri | -4.540 |
utenberg | -4.445 |
bably | -4.410 |
netflix | -4.363 |
Token | WASHINGTON |
Token ID | 21793 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Red | +6.165 |
RED | +5.975 |
Sioux | +5.960 |
Pt | +5.931 |
White | +5.625 |
Neg logit contributions | |
ubes | -6.145 |
utenberg | -5.700 |
atri | -5.538 |
bably | -5.445 |
hib | -5.360 |
Token | -- |
Token ID | 1377 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Red | +2.457 |
Sioux | +2.355 |
RED | +2.339 |
Pt | +2.328 |
White | +2.089 |
Neg logit contributions | |
ubes | -4.387 |
atri | -4.113 |
utenberg | -4.083 |
hib | -4.025 |
netflix | -4.010 |
Token | Treasury |
Token ID | 13419 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Red | +2.899 |
Sioux | +2.761 |
Pt | +2.703 |
RED | +2.693 |
White | +2.573 |
Neg logit contributions | |
ubes | -4.195 |
utenberg | -3.898 |
atri | -3.886 |
netflix | -3.821 |
hib | -3.816 |
Token | Secretary |
Token ID | 4986 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Red | +1.969 |
Sioux | +1.915 |
Pt | +1.863 |
RED | +1.844 |
White | +1.725 |
Neg logit contributions | |
ubes | -3.113 |
atri | -2.918 |
netflix | -2.882 |
hib | -2.873 |
utenberg | -2.859 |
Token | Jacob |
Token ID | 12806 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Red | +0.946 |
Sioux | +0.915 |
Pt | +0.888 |
RED | +0.877 |
White | +0.835 |
Neg logit contributions | |
ubes | -1.302 |
atri | -1.223 |
netflix | -1.214 |
utenberg | -1.212 |
hib | -1.194 |
Token | - |
Token ID | 532 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Red | +2.427 |
Sioux | +2.363 |
Pt | +2.337 |
RED | +2.278 |
White | +2.128 |
Neg logit contributions | |
ubes | -2.954 |
atri | -2.734 |
utenberg | -2.731 |
netflix | -2.692 |
ictionary | -2.667 |
Token | 1100 |
Token ID | 36566 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Red | +1.062 |
Sioux | +1.031 |
Pt | +1.018 |
RED | +0.998 |
White | +0.925 |
Neg logit contributions | |
ubes | -1.439 |
atri | -1.342 |
utenberg | -1.325 |
hib | -1.314 |
netflix | -1.306 |
Token | MHz |
Token ID | 19805 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Red | +0.665 |
Sioux | +0.646 |
Pt | +0.644 |
RED | +0.623 |
White | +0.578 |
Neg logit contributions | |
ubes | -0.994 |
atri | -0.929 |
utenberg | -0.916 |
netflix | -0.913 |
hib | -0.908 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ubes | +0.369 |
atri | +0.343 |
hib | +0.335 |
utenberg | +0.335 |
netflix | +0.333 |
Neg logit contributions | |
Red | -0.310 |
Sioux | -0.306 |
Pt | -0.302 |
RED | -0.295 |
White | -0.274 |
Token |
|
Token ID | 198 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Sioux | +0.087 |
Red | +0.087 |
Pt | +0.085 |
RED | +0.084 |
Clarks | +0.079 |
Neg logit contributions | |
ubes | -0.083 |
atri | -0.076 |
hib | -0.075 |
utenberg | -0.074 |
netflix | -0.073 |
Token | Memory |
Token ID | 30871 |
Feature activation | -8.37e+00 |
Pos logit contributions | |
Red | +0.329 |
Sioux | +0.322 |
Pt | +0.320 |
RED | +0.312 |
White | +0.294 |
Neg logit contributions | |
ubes | -0.307 |
atri | -0.282 |
utenberg | -0.279 |
hib | -0.275 |
netflix | -0.273 |
Token | : |
Token ID | 25 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Red | +4.942 |
Pt | +4.650 |
Sioux | +4.575 |
RED | +4.424 |
White | +4.167 |
Neg logit contributions | |
ubes | -7.420 |
utenberg | -7.232 |
atri | -7.110 |
hib | -7.034 |
bably | -7.008 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Red | +1.970 |
Sioux | +1.908 |
Pt | +1.882 |
RED | +1.823 |
White | +1.702 |
Neg logit contributions | |
ubes | -2.866 |
atri | -2.685 |
utenberg | -2.670 |
hib | -2.648 |
netflix | -2.628 |
Token | GB |
Token ID | 4579 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
Red | +3.014 |
Pt | +2.946 |
Sioux | +2.940 |
RED | +2.872 |
White | +2.723 |
Neg logit contributions | |
ubes | -2.185 |
atri | -2.034 |
netflix | -2.007 |
hib | -1.987 |
utenberg | -1.976 |
Token | GDDR |
Token ID | 50092 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
Red | +2.387 |
Sioux | +2.249 |
Pt | +2.229 |
RED | +2.185 |
White | +1.981 |
Neg logit contributions | |
ubes | -4.593 |
hib | -4.314 |
atri | -4.307 |
utenberg | -4.269 |
netflix | -4.266 |
Token | 5 |
Token ID | 20 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Red | +2.643 |
Pt | +2.542 |
Sioux | +2.488 |
RED | +2.420 |
White | +2.230 |
Neg logit contributions | |
ubes | -5.520 |
atri | -5.200 |
utenberg | -5.177 |
netflix | -5.098 |
hib | -5.094 |
Token | index |
Token ID | 9630 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
Red | +3.697 |
Sioux | +3.586 |
Pt | +3.504 |
RED | +3.439 |
draft | +3.312 |
Neg logit contributions | |
ubes | -3.334 |
UTERS | -3.051 |
atri | -3.051 |
utenberg | -3.021 |
hib | -2.955 |
Token | . |
Token ID | 13 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ubes | +3.528 |
atri | +3.244 |
hib | +3.131 |
ictionary | +3.096 |
utenberg | +3.069 |
Neg logit contributions | |
Sioux | -3.517 |
Red | -3.439 |
Pt | -3.397 |
RED | -3.331 |
Clarks | -3.223 |
Token | php |
Token ID | 10121 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Red | +0.177 |
Sioux | +0.173 |
Pt | +0.171 |
RED | +0.166 |
White | +0.153 |
Neg logit contributions | |
ubes | -0.254 |
atri | -0.236 |
utenberg | -0.234 |
hib | -0.231 |
UTERS | -0.231 |
Token | ? |
Token ID | 30 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Red | +2.340 |
Pt | +2.246 |
Sioux | +2.245 |
RED | +2.224 |
White | +2.068 |
Neg logit contributions | |
ubes | -2.407 |
atri | -2.252 |
utenberg | -2.236 |
netflix | -2.201 |
hib | -2.167 |
Token | topic |
Token ID | 26652 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
Red | +1.775 |
Pt | +1.713 |
Sioux | +1.693 |
RED | +1.670 |
draft | +1.608 |
Neg logit contributions | |
ubes | -1.792 |
utenberg | -1.657 |
atri | -1.648 |
netflix | -1.603 |
UTERS | -1.596 |
Token | = |
Token ID | 28 |
Feature activation | -8.36e+00 |
Pos logit contributions | |
ubes | +0.412 |
atri | +0.365 |
hib | +0.352 |
utenberg | +0.350 |
netflix | +0.345 |
Neg logit contributions | |
Red | -0.810 |
Sioux | -0.803 |
Pt | -0.796 |
RED | -0.784 |
White | -0.745 |
Token | 28 |
Token ID | 2078 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
Red | +5.285 |
Pt | +5.083 |
Sioux | +5.046 |
RED | +4.938 |
draft | +4.617 |
Neg logit contributions | |
ubes | -6.853 |
utenberg | -6.466 |
atri | -6.375 |
bably | -6.239 |
UTERS | -6.195 |
Token | 18 |
Token ID | 1507 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Red | +2.783 |
Sioux | +2.687 |
Pt | +2.676 |
RED | +2.610 |
White | +2.429 |
Neg logit contributions | |
ubes | -3.469 |
utenberg | -3.233 |
atri | -3.225 |
bably | -3.136 |
netflix | -3.135 |
Token | 48 |
Token ID | 2780 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Red | +1.152 |
Sioux | +1.117 |
Pt | +1.111 |
RED | +1.085 |
White | +1.010 |
Neg logit contributions | |
ubes | -1.407 |
atri | -1.309 |
utenberg | -1.296 |
hib | -1.278 |
netflix | -1.268 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Red | +0.332 |
Sioux | +0.322 |
Pt | +0.319 |
RED | +0.313 |
White | +0.289 |
Neg logit contributions | |
ubes | -0.437 |
atri | -0.407 |
utenberg | -0.402 |
hib | -0.397 |
netflix | -0.396 |
Token | 0 |
Token ID | 15 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Red | +1.439 |
Sioux | +1.386 |
Pt | +1.377 |
RED | +1.334 |
White | +1.230 |
Neg logit contributions | |
ubes | -2.488 |
atri | -2.335 |
utenberg | -2.303 |
UTERS | -2.288 |
hib | -2.283 |
Token | + |
Token ID | 1343 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ubes | +2.280 |
atri | +2.100 |
hib | +2.051 |
utenberg | +2.046 |
netflix | +2.024 |
Neg logit contributions | |
Red | -2.503 |
Sioux | -2.488 |
Pt | -2.455 |
RED | -2.404 |
Clarks | -2.261 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
ubes | +0.127 |
atri | +0.119 |
hib | +0.118 |
utenberg | +0.117 |
netflix | +0.116 |
Neg logit contributions | |
Red | -0.078 |
Sioux | -0.078 |
Pt | -0.076 |
RED | -0.074 |
Clarks | -0.069 |
Token | --+ |
Token ID | 44785 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
Red | +0.446 |
Sioux | +0.444 |
Pt | +0.437 |
RED | +0.430 |
Clarks | +0.405 |
Neg logit contributions | |
ubes | -0.350 |
atri | -0.320 |
hib | -0.312 |
utenberg | -0.310 |
netflix | -0.304 |
Token | | |
Token ID | 930 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Sioux | +0.608 |
Red | +0.608 |
Pt | +0.598 |
RED | +0.581 |
Clarks | +0.544 |
Neg logit contributions | |
ubes | -0.760 |
atri | -0.704 |
hib | -0.695 |
utenberg | -0.688 |
netflix | -0.684 |
Token | [ |
Token ID | 685 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
Red | +1.707 |
Sioux | +1.643 |
Pt | +1.633 |
RED | +1.608 |
White | +1.493 |
Neg logit contributions | |
ubes | -2.162 |
atri | -1.998 |
hib | -1.958 |
netflix | -1.947 |
utenberg | -1.946 |
Token | return |
Token ID | 7783 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
Red | +2.324 |
Sioux | +2.272 |
Pt | +2.237 |
RED | +2.206 |
White | +2.068 |
Neg logit contributions | |
ubes | -2.278 |
atri | -2.060 |
utenberg | -2.042 |
netflix | -2.000 |
hib | -1.997 |
Token | address |
Token ID | 2209 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
Red | +3.707 |
Sioux | +3.453 |
Pt | +3.451 |
RED | +3.346 |
White | +3.060 |
Neg logit contributions | |
ubes | -8.715 |
atri | -8.155 |
utenberg | -8.130 |
netflix | -8.116 |
hib | -7.986 |
Token | ] |
Token ID | 60 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Red | +1.912 |
Sioux | +1.858 |
Pt | +1.826 |
RED | +1.772 |
White | +1.580 |
Neg logit contributions | |
ubes | -4.268 |
atri | -4.030 |
hib | -3.959 |
utenberg | -3.959 |
netflix | -3.930 |
Token | | |
Token ID | 930 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
Red | +1.439 |
Sioux | +1.417 |
Pt | +1.397 |
RED | +1.366 |
White | +1.260 |
Neg logit contributions | |
ubes | -1.908 |
atri | -1.778 |
hib | -1.742 |
utenberg | -1.739 |
netflix | -1.726 |
Token | + |
Token ID | 1343 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ubes | +0.562 |
atri | +0.512 |
hib | +0.500 |
utenberg | +0.499 |
netflix | +0.494 |
Neg logit contributions | |
Red | -0.623 |
Sioux | -0.612 |
Pt | -0.604 |
RED | -0.595 |
White | -0.559 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Red | +0.289 |
Sioux | +0.287 |
Pt | +0.280 |
RED | +0.273 |
Clarks | +0.253 |
Neg logit contributions | |
ubes | -0.480 |
atri | -0.450 |
hib | -0.443 |
utenberg | -0.440 |
netflix | -0.437 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Red | +3.290 |
Sioux | +3.207 |
Pt | +3.143 |
RED | +3.089 |
White | +2.890 |
Neg logit contributions | |
ubes | -4.490 |
atri | -4.142 |
utenberg | -4.083 |
hib | -4.031 |
bably | -4.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Red | +0.752 |
Sioux | +0.748 |
Pt | +0.735 |
RED | +0.721 |
Clarks | +0.677 |
Neg logit contributions | |
ubes | -0.756 |
atri | -0.696 |
hib | -0.683 |
utenberg | -0.678 |
netflix | -0.673 |
Token | " |
Token ID | 1 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
Red | +0.820 |
Sioux | +0.807 |
Pt | +0.802 |
RED | +0.779 |
White | +0.733 |
Neg logit contributions | |
ubes | -0.806 |
atri | -0.740 |
utenberg | -0.735 |
hib | -0.722 |
netflix | -0.714 |
Token | Crystal |
Token ID | 43752 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Red | +0.472 |
Sioux | +0.465 |
Pt | +0.461 |
RED | +0.449 |
White | +0.424 |
Neg logit contributions | |
ubes | -0.435 |
atri | -0.397 |
utenberg | -0.391 |
hib | -0.387 |
netflix | -0.384 |
Token | Emb |
Token ID | 13302 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ubes | +0.276 |
atri | +0.257 |
hib | +0.252 |
utenberg | +0.251 |
netflix | +0.250 |
Neg logit contributions | |
Red | -0.221 |
Sioux | -0.218 |
Pt | -0.215 |
RED | -0.208 |
White | -0.195 |
Token | ry |
Token ID | 563 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
Red | +1.750 |
Sioux | +1.713 |
Pt | +1.690 |
RED | +1.640 |
White | +1.500 |
Neg logit contributions | |
ubes | -2.902 |
atri | -2.717 |
utenberg | -2.679 |
hib | -2.673 |
netflix | -2.653 |
Token | o |
Token ID | 78 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ubes | +4.269 |
atri | +3.915 |
netflix | +3.792 |
hib | +3.760 |
utenberg | +3.760 |
Neg logit contributions | |
Sioux | -3.845 |
Red | -3.766 |
RED | -3.672 |
Pt | -3.656 |
Clarks | -3.580 |
Token | lives |
Token ID | 3160 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Red | +0.982 |
Sioux | +0.963 |
Pt | +0.953 |
RED | +0.922 |
White | +0.849 |
Neg logit contributions | |
ubes | -1.529 |
atri | -1.425 |
utenberg | -1.400 |
hib | -1.398 |
netflix | -1.392 |
Token | in |
Token ID | 287 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ubes | +2.918 |
atri | +2.719 |
hib | +2.667 |
utenberg | +2.644 |
netflix | +2.626 |
Neg logit contributions | |
Red | -2.336 |
Sioux | -2.328 |
Pt | -2.303 |
RED | -2.242 |
Clarks | -2.098 |
Token | a |
Token ID | 257 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ubes | +1.841 |
atri | +1.728 |
hib | +1.693 |
utenberg | +1.689 |
netflix | +1.675 |
Neg logit contributions | |
Red | -1.185 |
Sioux | -1.169 |
Pt | -1.153 |
RED | -1.123 |
White | -1.024 |
Token | plane |
Token ID | 6614 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
ubes | +0.610 |
atri | +0.568 |
hib | +0.557 |
utenberg | +0.557 |
netflix | +0.551 |
Neg logit contributions | |
Red | -0.458 |
Sioux | -0.452 |
Pt | -0.444 |
RED | -0.435 |
White | -0.402 |
Token | according |
Token ID | 1864 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Red | +0.100 |
Sioux | +0.098 |
Pt | +0.097 |
RED | +0.095 |
White | +0.087 |
Neg logit contributions | |
ubes | -0.154 |
atri | -0.143 |
hib | -0.141 |
utenberg | -0.141 |
netflix | -0.140 |
Token | to |
Token ID | 284 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
Red | +0.695 |
Sioux | +0.688 |
Pt | +0.677 |
RED | +0.656 |
Clarks | +0.602 |
Neg logit contributions | |
ubes | -1.181 |
atri | -1.110 |
hib | -1.093 |
utenberg | -1.084 |
netflix | -1.080 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Red | +0.371 |
Sioux | +0.364 |
Pt | +0.358 |
RED | +0.349 |
White | +0.321 |
Neg logit contributions | |
ubes | -0.594 |
atri | -0.554 |
utenberg | -0.545 |
hib | -0.544 |
netflix | -0.541 |
Token | University |
Token ID | 2059 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Red | +1.070 |
Sioux | +1.054 |
Pt | +1.028 |
RED | +1.012 |
White | +0.945 |
Neg logit contributions | |
ubes | -1.470 |
atri | -1.369 |
utenberg | -1.353 |
hib | -1.342 |
netflix | -1.341 |
Token | of |
Token ID | 286 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ubes | +0.095 |
atri | +0.088 |
utenberg | +0.087 |
netflix | +0.087 |
hib | +0.087 |
Neg logit contributions | |
Red | -0.057 |
Sioux | -0.056 |
Pt | -0.055 |
RED | -0.053 |
White | -0.049 |
Token | Hawai |
Token ID | 10847 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
ubes | +1.875 |
atri | +1.740 |
hib | +1.704 |
utenberg | +1.693 |
netflix | +1.674 |
Neg logit contributions | |
Red | -1.672 |
Sioux | -1.653 |
Pt | -1.635 |
RED | -1.609 |
Clarks | -1.492 |
Token | � |
Token ID | 447 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ubes | +5.180 |
atri | +4.924 |
hib | +4.876 |
utenberg | +4.807 |
netflix | +4.740 |
Neg logit contributions | |
Red | -1.894 |
Sioux | -1.868 |
Pt | -1.821 |
RED | -1.781 |
Clarks | -1.591 |
Token | � |
Token ID | 247 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ubes | +0.303 |
atri | +0.285 |
hib | +0.280 |
utenberg | +0.280 |
netflix | +0.278 |
Neg logit contributions | |
Red | -0.163 |
Sioux | -0.160 |
Pt | -0.157 |
RED | -0.153 |
White | -0.138 |
Token | i |
Token ID | 72 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Red | +0.012 |
Sioux | +0.012 |
Pt | +0.012 |
RED | +0.012 |
White | +0.011 |
Neg logit contributions | |
ubes | -0.016 |
atri | -0.015 |
netflix | -0.015 |
utenberg | -0.015 |
hib | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
ubes | +1.933 |
atri | +1.807 |
hib | +1.773 |
utenberg | +1.769 |
netflix | +1.756 |
Neg logit contributions | |
Red | -1.298 |
Sioux | -1.280 |
Pt | -1.259 |
RED | -1.228 |
White | -1.126 |
Token | there |
Token ID | 612 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
ubes | +0.882 |
atri | +0.825 |
hib | +0.809 |
utenberg | +0.806 |
netflix | +0.801 |
Neg logit contributions | |
Red | -0.607 |
Sioux | -0.600 |
Pt | -0.590 |
RED | -0.575 |
White | -0.528 |
Token | vehicle |
Token ID | 4038 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ubes | +0.496 |
atri | +0.459 |
utenberg | +0.451 |
hib | +0.448 |
netflix | +0.445 |
Neg logit contributions | |
Red | -0.445 |
Sioux | -0.437 |
Pt | -0.430 |
RED | -0.423 |
White | -0.394 |
Token | , |
Token ID | 11 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ubes | +1.467 |
atri | +1.366 |
hib | +1.339 |
utenberg | +1.336 |
netflix | +1.325 |
Neg logit contributions | |
Red | -1.126 |
Sioux | -1.111 |
Pt | -1.095 |
RED | -1.069 |
White | -0.988 |
Token | Har |
Token ID | 13587 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
Red | +0.331 |
Sioux | +0.324 |
Pt | +0.319 |
RED | +0.311 |
White | +0.290 |
Neg logit contributions | |
ubes | -0.432 |
atri | -0.400 |
utenberg | -0.394 |
hib | -0.393 |
netflix | -0.388 |
Token | vey |
Token ID | 3304 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Red | +0.038 |
Sioux | +0.037 |
Pt | +0.037 |
RED | +0.036 |
White | +0.034 |
Neg logit contributions | |
ubes | -0.035 |
atri | -0.032 |
hib | -0.032 |
utenberg | -0.032 |
netflix | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
ubes | +2.304 |
atri | +2.149 |
hib | +2.107 |
utenberg | +2.102 |
netflix | +2.086 |
Neg logit contributions | |
Red | -1.663 |
Sioux | -1.642 |
Pt | -1.616 |
RED | -1.578 |
White | -1.452 |
Token | 1950 |
Token ID | 11445 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ubes | +2.425 |
atri | +2.281 |
hib | +2.230 |
utenberg | +2.222 |
netflix | +2.212 |
Neg logit contributions | |
Red | -1.734 |
Sioux | -1.729 |
Pt | -1.691 |
RED | -1.662 |
Clarks | -1.525 |
Token | .) |
Token ID | 2014 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
ubes | +3.535 |
atri | +3.247 |
hib | +3.214 |
utenberg | +3.162 |
netflix | +3.150 |
Neg logit contributions | |
Red | -3.452 |
Sioux | -3.442 |
Pt | -3.373 |
RED | -3.322 |
Clarks | -3.095 |
Token | Hitchcock |
Token ID | 49817 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
ubes | +0.500 |
atri | +0.463 |
hib | +0.454 |
utenberg | +0.451 |
netflix | +0.448 |
Neg logit contributions | |
Red | -0.457 |
Sioux | -0.453 |
Pt | -0.447 |
RED | -0.437 |
White | -0.406 |
Token | 's |
Token ID | 338 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
Red | +0.022 |
Sioux | +0.022 |
Pt | +0.021 |
RED | +0.021 |
White | +0.019 |
Neg logit contributions | |
ubes | -0.030 |
atri | -0.028 |
hib | -0.027 |
utenberg | -0.027 |
netflix | -0.027 |
Token | unw |
Token ID | 7379 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ubes | +0.596 |
atri | +0.554 |
hib | +0.543 |
utenberg | +0.542 |
netflix | +0.538 |
Neg logit contributions | |
Red | -0.470 |
Sioux | -0.463 |
Pt | -0.456 |
RED | -0.446 |
White | -0.413 |
Token | avering |
Token ID | 42610 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Red | +1.590 |
Sioux | +1.538 |
Pt | +1.534 |
RED | +1.485 |
White | +1.407 |
Neg logit contributions | |
ubes | -1.768 |
netflix | -1.645 |
atri | -1.628 |
UTERS | -1.621 |
utenberg | -1.611 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Red | +1.702 |
Sioux | +1.644 |
Pt | +1.627 |
RED | +1.595 |
White | +1.479 |
Neg logit contributions | |
ubes | -2.450 |
atri | -2.286 |
utenberg | -2.234 |
hib | -2.227 |
netflix | -2.221 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ubes | +1.461 |
atri | +1.326 |
hib | +1.324 |
netflix | +1.281 |
utenberg | +1.279 |
Neg logit contributions | |
Sioux | -1.719 |
Red | -1.689 |
Pt | -1.684 |
RED | -1.643 |
Clarks | -1.591 |
Token | Jo |
Token ID | 9908 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ubes | +0.960 |
atri | +0.883 |
hib | +0.863 |
utenberg | +0.860 |
netflix | +0.852 |
Neg logit contributions | |
Red | -1.003 |
Sioux | -0.992 |
Pt | -0.979 |
RED | -0.960 |
White | -0.898 |
Token | ong |
Token ID | 506 |
Feature activation | +6.62e+00 |
Pos logit contributions | |
ubes | +0.832 |
atri | +0.771 |
hib | +0.745 |
utenberg | +0.740 |
netflix | +0.738 |
Neg logit contributions | |
Red | -0.869 |
Sioux | -0.864 |
Pt | -0.852 |
RED | -0.840 |
Clarks | -0.788 |
Token | Ang |
Token ID | 13450 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
ubes | +3.193 |
atri | +2.860 |
utenberg | +2.715 |
hib | +2.708 |
netflix | +2.664 |
Neg logit contributions | |
Red | -6.575 |
Sioux | -6.526 |
Pt | -6.504 |
RED | -6.417 |
Clarks | -6.127 |
Token | Il |
Token ID | 13778 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
ubes | +2.947 |
atri | +2.746 |
hib | +2.684 |
utenberg | +2.673 |
netflix | +2.646 |
Neg logit contributions | |
Red | -2.464 |
Sioux | -2.446 |
Pt | -2.425 |
RED | -2.364 |
Clarks | -2.193 |
Token | bo |
Token ID | 2127 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ubes | +4.474 |
hib | +4.138 |
atri | +4.119 |
netflix | +4.027 |
utenberg | +3.931 |
Neg logit contributions | |
Sioux | -3.995 |
Red | -3.915 |
RED | -3.854 |
Pt | -3.790 |
Clarks | -3.679 |
Token | reported |
Token ID | 2098 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ubes | +1.638 |
atri | +1.529 |
hib | +1.497 |
utenberg | +1.486 |
netflix | +1.468 |
Neg logit contributions | |
Red | -1.244 |
Sioux | -1.238 |
Pt | -1.228 |
RED | -1.192 |
Clarks | -1.109 |
Token | that |
Token ID | 326 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ubes | +1.743 |
atri | +1.627 |
hib | +1.597 |
utenberg | +1.592 |
netflix | +1.580 |
Neg logit contributions | |
Red | -1.218 |
Sioux | -1.205 |
Pt | -1.186 |
RED | -1.156 |
Clarks | -1.061 |
Token | in |
Token ID | 287 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Red | +0.246 |
Sioux | +0.241 |
Pt | +0.237 |
RED | +0.231 |
White | +0.213 |
Neg logit contributions | |
ubes | -0.369 |
atri | -0.346 |
hib | -0.339 |
utenberg | -0.339 |
netflix | -0.336 |
Token | W |
Token ID | 370 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Red | +0.139 |
Sioux | +0.136 |
Pt | +0.134 |
RED | +0.131 |
White | +0.121 |
Neg logit contributions | |
ubes | -0.195 |
atri | -0.182 |
utenberg | -0.178 |
hib | -0.178 |
netflix | -0.177 |
Token | for |
Token ID | 329 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ubes | +1.470 |
atri | +1.374 |
hib | +1.346 |
utenberg | +1.339 |
netflix | +1.325 |
Neg logit contributions | |
Red | -1.072 |
Sioux | -1.062 |
Pt | -1.046 |
RED | -1.022 |
Clarks | -0.945 |
Token | us |
Token ID | 514 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Red | +0.809 |
Sioux | +0.786 |
Pt | +0.766 |
RED | +0.756 |
White | +0.701 |
Neg logit contributions | |
ubes | -1.193 |
atri | -1.111 |
utenberg | -1.101 |
hib | -1.091 |
netflix | -1.082 |
Token | , |
Token ID | 11 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
ubes | +0.238 |
atri | +0.222 |
utenberg | +0.218 |
hib | +0.218 |
netflix | +0.216 |
Neg logit contributions | |
Red | -0.168 |
Sioux | -0.165 |
Pt | -0.162 |
RED | -0.159 |
White | -0.146 |
Token | � |
Token ID | 447 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
Red | +0.298 |
Sioux | +0.292 |
Pt | +0.287 |
RED | +0.281 |
White | +0.259 |
Neg logit contributions | |
ubes | -0.442 |
atri | -0.411 |
utenberg | -0.404 |
hib | -0.404 |
netflix | -0.400 |
Token | � |
Token ID | 251 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ubes | +0.548 |
atri | +0.514 |
hib | +0.506 |
utenberg | +0.502 |
netflix | +0.499 |
Neg logit contributions | |
Sioux | -0.324 |
Red | -0.324 |
Pt | -0.315 |
RED | -0.306 |
Clarks | -0.281 |
Token | team |
Token ID | 1074 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
ubes | +1.391 |
atri | +1.297 |
hib | +1.272 |
utenberg | +1.269 |
netflix | +1.259 |
Neg logit contributions | |
Red | -1.011 |
Sioux | -0.998 |
Pt | -0.983 |
RED | -0.959 |
White | -0.883 |
Token | chairman |
Token ID | 8900 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
ubes | +3.794 |
atri | +3.561 |
hib | +3.461 |
netflix | +3.400 |
utenberg | +3.399 |
Neg logit contributions | |
Sioux | -2.997 |
Red | -2.984 |
Pt | -2.965 |
RED | -2.866 |
Clarks | -2.694 |
Token | Bill |
Token ID | 3941 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ubes | +0.775 |
atri | +0.721 |
utenberg | +0.708 |
hib | +0.708 |
netflix | +0.700 |
Neg logit contributions | |
Red | -0.578 |
Sioux | -0.567 |
Pt | -0.559 |
RED | -0.546 |
White | -0.506 |
Token | De |
Token ID | 1024 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Red | +1.506 |
Sioux | +1.460 |
Pt | +1.443 |
RED | +1.395 |
White | +1.332 |
Neg logit contributions | |
ubes | -1.876 |
atri | -1.744 |
utenberg | -1.737 |
netflix | -1.731 |
hib | -1.719 |
Token | W |
Token ID | 54 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Red | +1.387 |
Sioux | +1.366 |
Pt | +1.346 |
RED | +1.305 |
White | +1.241 |
Neg logit contributions | |
ubes | -1.514 |
atri | -1.400 |
utenberg | -1.382 |
hib | -1.369 |
netflix | -1.367 |
Token | itt |
Token ID | 715 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ubes | +2.095 |
atri | +1.956 |
hib | +1.915 |
utenberg | +1.904 |
netflix | +1.861 |
Neg logit contributions | |
Red | -1.794 |
Sioux | -1.780 |
Pt | -1.747 |
RED | -1.722 |
Clarks | -1.598 |
Token | is |
Token ID | 318 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Red | +0.556 |
Sioux | +0.546 |
Pt | +0.537 |
RED | +0.524 |
White | +0.480 |
Neg logit contributions | |
ubes | -0.877 |
atri | -0.819 |
hib | -0.806 |
utenberg | -0.805 |
netflix | -0.798 |
Token | and |
Token ID | 290 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ubes | +1.189 |
atri | +1.109 |
hib | +1.087 |
utenberg | +1.084 |
netflix | +1.076 |
Neg logit contributions | |
Red | -0.871 |
Sioux | -0.860 |
Pt | -0.846 |
RED | -0.826 |
White | -0.761 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Red | +0.305 |
Sioux | +0.301 |
Pt | +0.296 |
RED | +0.289 |
White | +0.266 |
Neg logit contributions | |
ubes | -0.429 |
atri | -0.400 |
hib | -0.392 |
utenberg | -0.392 |
netflix | -0.389 |
Token | coaches |
Token ID | 11070 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Red | +1.088 |
Sioux | +1.067 |
Pt | +1.047 |
RED | +1.027 |
White | +0.953 |
Neg logit contributions | |
ubes | -1.402 |
atri | -1.306 |
utenberg | -1.277 |
hib | -1.276 |
netflix | -1.270 |
Token | are |
Token ID | 389 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Red | +1.109 |
Sioux | +1.084 |
Pt | +1.060 |
RED | +1.044 |
White | +0.964 |
Neg logit contributions | |
ubes | -1.593 |
atri | -1.478 |
utenberg | -1.464 |
hib | -1.451 |
netflix | -1.445 |
Token | . |
Token ID | 13 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
Red | +1.301 |
Sioux | +1.264 |
Pt | +1.247 |
RED | +1.222 |
White | +1.132 |
Neg logit contributions | |
ubes | -1.840 |
atri | -1.690 |
utenberg | -1.676 |
netflix | -1.663 |
hib | -1.663 |
Token | He |
Token ID | 679 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Red | +0.022 |
Sioux | +0.022 |
Pt | +0.021 |
RED | +0.021 |
White | +0.019 |
Neg logit contributions | |
ubes | -0.027 |
atri | -0.025 |
hib | -0.024 |
utenberg | -0.024 |
netflix | -0.024 |
Token | said |
Token ID | 531 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Red | +1.219 |
Sioux | +1.198 |
Pt | +1.175 |
RED | +1.154 |
White | +1.063 |
Neg logit contributions | |
ubes | -1.758 |
atri | -1.630 |
utenberg | -1.610 |
hib | -1.610 |
netflix | -1.599 |
Token | [ |
Token ID | 685 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Red | +0.228 |
Sioux | +0.224 |
Pt | +0.220 |
RED | +0.215 |
White | +0.197 |
Neg logit contributions | |
ubes | -0.358 |
atri | -0.334 |
hib | -0.328 |
utenberg | -0.327 |
netflix | -0.325 |
Token | ass |
Token ID | 562 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ubes | +0.424 |
atri | +0.392 |
hib | +0.383 |
utenberg | +0.383 |
netflix | +0.379 |
Neg logit contributions | |
Red | -0.377 |
Sioux | -0.372 |
Pt | -0.367 |
RED | -0.359 |
White | -0.334 |
Token | istant |
Token ID | 10167 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ubes | +0.746 |
atri | +0.681 |
hib | +0.664 |
utenberg | +0.663 |
netflix | +0.658 |
Neg logit contributions | |
Red | -0.891 |
Sioux | -0.881 |
Pt | -0.870 |
RED | -0.855 |
White | -0.804 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Red | +0.191 |
Sioux | +0.187 |
Pt | +0.185 |
RED | +0.179 |
White | +0.167 |
Neg logit contributions | |
ubes | -0.255 |
atri | -0.235 |
hib | -0.231 |
netflix | -0.230 |
utenberg | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ubes | +0.127 |
atri | +0.116 |
hib | +0.115 |
utenberg | +0.113 |
netflix | +0.112 |
Neg logit contributions | |
Sioux | -0.134 |
Red | -0.134 |
Pt | -0.131 |
RED | -0.129 |
Clarks | -0.122 |
Token | - |
Token ID | 12 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
ubes | +0.960 |
atri | +0.896 |
utenberg | +0.884 |
hib | +0.878 |
netflix | +0.870 |
Neg logit contributions | |
Red | -0.631 |
Sioux | -0.618 |
Pt | -0.614 |
RED | -0.596 |
White | -0.546 |
Token | Rest |
Token ID | 8324 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ubes | +0.820 |
atri | +0.761 |
utenberg | +0.746 |
hib | +0.745 |
netflix | +0.741 |
Neg logit contributions | |
Red | -0.642 |
Sioux | -0.630 |
Pt | -0.623 |
RED | -0.607 |
White | -0.564 |
Token | less |
Token ID | 1203 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Red | +0.099 |
Sioux | +0.097 |
Pt | +0.096 |
RED | +0.094 |
White | +0.087 |
Neg logit contributions | |
ubes | -0.122 |
atri | -0.112 |
utenberg | -0.111 |
netflix | -0.111 |
hib | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Red | +0.891 |
Sioux | +0.859 |
Pt | +0.856 |
RED | +0.816 |
White | +0.759 |
Neg logit contributions | |
ubes | -1.590 |
atri | -1.476 |
hib | -1.453 |
netflix | -1.450 |
utenberg | -1.449 |
Token | Quick |
Token ID | 12029 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ubes | +1.714 |
atri | +1.592 |
hib | +1.561 |
utenberg | +1.559 |
netflix | +1.547 |
Neg logit contributions | |
Red | -1.334 |
Sioux | -1.314 |
Pt | -1.297 |
RED | -1.265 |
White | -1.172 |
Token | to |
Token ID | 284 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ubes | +2.668 |
atri | +2.489 |
hib | +2.441 |
utenberg | +2.435 |
netflix | +2.415 |
Neg logit contributions | |
Red | -1.921 |
Sioux | -1.897 |
Pt | -1.867 |
RED | -1.824 |
White | -1.677 |
Token | anger |
Token ID | 8993 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Red | +1.482 |
Sioux | +1.434 |
Pt | +1.426 |
RED | +1.383 |
White | +1.308 |
Neg logit contributions | |
ubes | -1.693 |
atri | -1.571 |
utenberg | -1.553 |
hib | -1.553 |
netflix | -1.553 |
Token | , |
Token ID | 11 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Red | +1.459 |
Pt | +1.399 |
Sioux | +1.399 |
RED | +1.349 |
White | +1.259 |
Neg logit contributions | |
ubes | -2.289 |
atri | -2.139 |
hib | -2.096 |
utenberg | -2.094 |
netflix | -2.080 |
Token | Unt |
Token ID | 26970 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ubes | +0.361 |
atri | +0.334 |
utenberg | +0.329 |
hib | +0.327 |
netflix | +0.326 |
Neg logit contributions | |
Red | -0.296 |
Sioux | -0.288 |
Pt | -0.287 |
RED | -0.278 |
White | -0.260 |
Token | be |
Token ID | 307 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Red | +2.074 |
Sioux | +2.004 |
Pt | +1.954 |
RED | +1.946 |
White | +1.814 |
Neg logit contributions | |
ubes | -2.795 |
atri | -2.605 |
hib | -2.603 |
utenberg | -2.560 |
netflix | -2.544 |
Token | a |
Token ID | 257 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Red | +1.568 |
Sioux | +1.504 |
Pt | +1.477 |
RED | +1.462 |
White | +1.338 |
Neg logit contributions | |
ubes | -2.542 |
atri | -2.380 |
utenberg | -2.345 |
hib | -2.338 |
netflix | -2.335 |
Token | break |
Token ID | 2270 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
ubes | +0.456 |
atri | +0.424 |
hib | +0.416 |
utenberg | +0.415 |
netflix | +0.412 |
Neg logit contributions | |
Red | -0.354 |
Sioux | -0.349 |
Pt | -0.344 |
RED | -0.336 |
White | -0.311 |
Token | away |
Token ID | 8272 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
ubes | +0.440 |
atri | +0.411 |
utenberg | +0.404 |
hib | +0.403 |
netflix | +0.402 |
Neg logit contributions | |
Red | -0.295 |
Sioux | -0.289 |
Pt | -0.285 |
RED | -0.278 |
White | -0.255 |
Token | , |
Token ID | 11 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
ubes | +0.337 |
atri | +0.315 |
hib | +0.309 |
utenberg | +0.307 |
netflix | +0.305 |
Neg logit contributions | |
Red | -0.243 |
Sioux | -0.240 |
Pt | -0.237 |
RED | -0.231 |
White | -0.212 |
Token | but |
Token ID | 475 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ubes | +0.886 |
atri | +0.829 |
hib | +0.813 |
utenberg | +0.811 |
netflix | +0.805 |
Neg logit contributions | |
Red | -0.591 |
Sioux | -0.583 |
Pt | -0.574 |
RED | -0.559 |
White | -0.512 |
Token | with |
Token ID | 351 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
ubes | +2.098 |
atri | +1.964 |
hib | +1.925 |
utenberg | +1.907 |
netflix | +1.899 |
Neg logit contributions | |
Red | -1.371 |
Sioux | -1.369 |
Pt | -1.344 |
RED | -1.307 |
Clarks | -1.202 |
Token | no |
Token ID | 645 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
Red | +0.492 |
Sioux | +0.475 |
Pt | +0.470 |
RED | +0.460 |
White | +0.423 |
Neg logit contributions | |
ubes | -0.741 |
atri | -0.691 |
utenberg | -0.684 |
hib | -0.678 |
netflix | -0.678 |
Token | construct |
Token ID | 5678 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Red | +0.036 |
Sioux | +0.035 |
Pt | +0.034 |
RED | +0.034 |
White | +0.031 |
Neg logit contributions | |
ubes | -0.044 |
atri | -0.041 |
utenberg | -0.040 |
hib | -0.040 |
netflix | -0.040 |
Token | ors |
Token ID | 669 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ubes | +1.161 |
atri | +1.093 |
hib | +1.075 |
utenberg | +1.072 |
netflix | +1.065 |
Neg logit contributions | |
Red | -0.560 |
Sioux | -0.552 |
Pt | -0.540 |
RED | -0.524 |
White | -0.469 |
Token | left |
Token ID | 1364 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Red | +0.162 |
Sioux | +0.159 |
Pt | +0.156 |
RED | +0.153 |
White | +0.140 |
Neg logit contributions | |
ubes | -0.247 |
atri | -0.231 |
utenberg | -0.227 |
hib | -0.227 |
netflix | -0.225 |
Token | downfall |
Token ID | 38041 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ubes | +0.076 |
atri | +0.071 |
hib | +0.069 |
utenberg | +0.069 |
netflix | +0.068 |
Neg logit contributions | |
Red | -0.067 |
Sioux | -0.066 |
Pt | -0.065 |
RED | -0.064 |
White | -0.059 |
Token | of |
Token ID | 286 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ubes | +1.650 |
atri | +1.547 |
hib | +1.518 |
utenberg | +1.514 |
netflix | +1.504 |
Neg logit contributions | |
Red | -1.004 |
Sioux | -0.989 |
Pt | -0.972 |
RED | -0.946 |
White | -0.864 |
Token | that |
Token ID | 326 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
ubes | +2.174 |
atri | +2.032 |
hib | +1.997 |
utenberg | +1.985 |
netflix | +1.970 |
Neg logit contributions | |
Red | -1.501 |
Sioux | -1.488 |
Pt | -1.465 |
RED | -1.431 |
Clarks | -1.314 |
Token | which |
Token ID | 543 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ubes | +0.746 |
atri | +0.694 |
hib | +0.679 |
utenberg | +0.678 |
netflix | +0.672 |
Neg logit contributions | |
Red | -0.604 |
Sioux | -0.597 |
Pt | -0.588 |
RED | -0.575 |
White | -0.532 |
Token | it |
Token ID | 340 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ubes | +0.908 |
atri | +0.847 |
hib | +0.830 |
utenberg | +0.824 |
netflix | +0.821 |
Neg logit contributions | |
Red | -0.661 |
Sioux | -0.655 |
Pt | -0.648 |
RED | -0.631 |
Clarks | -0.584 |
Token | spoke |
Token ID | 5158 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
Red | +0.155 |
Sioux | +0.153 |
Pt | +0.151 |
RED | +0.147 |
White | +0.135 |
Neg logit contributions | |
ubes | -0.230 |
atri | -0.215 |
hib | -0.211 |
utenberg | -0.210 |
netflix | -0.209 |
Token | against |
Token ID | 1028 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
ubes | +0.712 |
atri | +0.665 |
hib | +0.653 |
utenberg | +0.651 |
netflix | +0.646 |
Neg logit contributions | |
Red | -0.485 |
Sioux | -0.478 |
Pt | -0.471 |
RED | -0.459 |
White | -0.422 |
Token | . |
Token ID | 13 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
ubes | +2.841 |
atri | +2.640 |
hib | +2.595 |
utenberg | +2.572 |
netflix | +2.556 |
Neg logit contributions | |
Red | -2.260 |
Sioux | -2.248 |
Pt | -2.208 |
RED | -2.158 |
Clarks | -2.015 |
Token | To |
Token ID | 1675 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ubes | +0.443 |
atri | +0.411 |
hib | +0.404 |
utenberg | +0.400 |
netflix | +0.398 |
Neg logit contributions | |
Red | -0.362 |
Sioux | -0.359 |
Pt | -0.354 |
RED | -0.347 |
Clarks | -0.321 |
Token | say |
Token ID | 910 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
Red | +0.680 |
Sioux | +0.670 |
Pt | +0.659 |
RED | +0.645 |
White | +0.596 |
Neg logit contributions | |
ubes | -0.891 |
atri | -0.830 |
hib | -0.813 |
utenberg | -0.812 |
netflix | -0.805 |
Token | that |
Token ID | 326 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
Red | +0.307 |
Sioux | +0.301 |
Pt | +0.296 |
RED | +0.289 |
White | +0.267 |
Neg logit contributions | |
ubes | -0.442 |
atri | -0.413 |
utenberg | -0.406 |
hib | -0.405 |
netflix | -0.402 |
Token | wish |
Token ID | 4601 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Red | +0.629 |
Sioux | +0.615 |
Pt | +0.609 |
RED | +0.599 |
White | +0.553 |
Neg logit contributions | |
ubes | -0.771 |
atri | -0.717 |
utenberg | -0.705 |
hib | -0.704 |
netflix | -0.697 |
Token | I |
Token ID | 314 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ubes | +0.978 |
atri | +0.915 |
hib | +0.897 |
utenberg | +0.896 |
netflix | +0.889 |
Neg logit contributions | |
Red | -0.644 |
Sioux | -0.634 |
Pt | -0.624 |
RED | -0.608 |
White | -0.557 |
Token | could |
Token ID | 714 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ubes | +0.313 |
atri | +0.292 |
utenberg | +0.286 |
hib | +0.285 |
netflix | +0.283 |
Neg logit contributions | |
Red | -0.254 |
Sioux | -0.250 |
Pt | -0.247 |
RED | -0.242 |
White | -0.224 |
Token | do |
Token ID | 466 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ubes | +0.631 |
atri | +0.585 |
hib | +0.572 |
utenberg | +0.570 |
netflix | +0.567 |
Neg logit contributions | |
Red | -0.579 |
Sioux | -0.569 |
Pt | -0.563 |
RED | -0.552 |
White | -0.513 |
Token | more |
Token ID | 517 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Red | +0.009 |
Sioux | +0.009 |
Pt | +0.009 |
RED | +0.009 |
White | +0.008 |
Neg logit contributions | |
ubes | -0.016 |
atri | -0.015 |
hib | -0.014 |
utenberg | -0.014 |
netflix | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ubes | +1.719 |
atri | +1.606 |
hib | +1.574 |
utenberg | +1.569 |
netflix | +1.556 |
Neg logit contributions | |
Red | -1.207 |
Sioux | -1.196 |
Pt | -1.175 |
RED | -1.146 |
Clarks | -1.055 |
Token | more |
Token ID | 517 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
ubes | +0.913 |
atri | +0.849 |
hib | +0.831 |
utenberg | +0.831 |
netflix | +0.823 |
Neg logit contributions | |
Red | -0.739 |
Sioux | -0.726 |
Pt | -0.717 |
RED | -0.700 |
White | -0.650 |
Token | helpless |
Token ID | 21144 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ubes | +2.270 |
atri | +2.106 |
hib | +2.062 |
utenberg | +2.055 |
netflix | +2.036 |
Neg logit contributions | |
Red | -1.923 |
Sioux | -1.902 |
Pt | -1.876 |
RED | -1.835 |
White | -1.700 |
Token | k |
Token ID | 479 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ubes | +1.330 |
atri | +1.235 |
hib | +1.209 |
utenberg | +1.208 |
netflix | +1.198 |
Neg logit contributions | |
Red | -1.124 |
Sioux | -1.110 |
Pt | -1.094 |
RED | -1.069 |
White | -0.994 |
Token | itt |
Token ID | 715 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ubes | +1.100 |
atri | +1.012 |
hib | +0.990 |
utenberg | +0.988 |
netflix | +0.980 |
Neg logit contributions | |
Red | -1.136 |
Sioux | -1.123 |
Pt | -1.109 |
RED | -1.087 |
White | -1.018 |
Token | ies |
Token ID | 444 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ubes | +0.184 |
atri | +0.172 |
hib | +0.170 |
utenberg | +0.169 |
netflix | +0.169 |
Neg logit contributions | |
Red | -0.113 |
Sioux | -0.111 |
Pt | -0.109 |
RED | -0.106 |
White | -0.098 |
Token | mol |
Token ID | 18605 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
ubes | +1.491 |
atri | +1.378 |
hib | +1.346 |
utenberg | +1.345 |
netflix | +1.331 |
Neg logit contributions | |
Red | -1.445 |
Sioux | -1.427 |
Pt | -1.407 |
RED | -1.380 |
White | -1.289 |
Token | esting |
Token ID | 37761 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Red | +0.680 |
Sioux | +0.674 |
Pt | +0.666 |
RED | +0.653 |
White | +0.612 |
Neg logit contributions | |
ubes | -0.605 |
atri | -0.555 |
hib | -0.543 |
utenberg | -0.539 |
netflix | -0.535 |
Token | kids |
Token ID | 3988 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Red | +1.182 |
Sioux | +1.159 |
Pt | +1.149 |
RED | +1.126 |
Clarks | +1.072 |
Neg logit contributions | |
ubes | -0.920 |
atri | -0.869 |
utenberg | -0.845 |
hib | -0.822 |
netflix | -0.811 |
Token | attract |
Token ID | 4729 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ubes | +0.910 |
atri | +0.842 |
utenberg | +0.825 |
hib | +0.823 |
netflix | +0.814 |
Neg logit contributions | |
Red | -0.822 |
Sioux | -0.808 |
Pt | -0.799 |
RED | -0.784 |
White | -0.729 |
Token | so |
Token ID | 523 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Red | +0.863 |
Sioux | +0.832 |
Pt | +0.815 |
RED | +0.799 |
White | +0.733 |
Neg logit contributions | |
ubes | -1.558 |
atri | -1.474 |
utenberg | -1.459 |
hib | -1.428 |
netflix | -1.424 |
Token | many |
Token ID | 867 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
Red | +0.977 |
Sioux | +0.969 |
Pt | +0.956 |
RED | +0.935 |
Clarks | +0.867 |
Neg logit contributions | |
ubes | -1.144 |
atri | -1.060 |
hib | -1.042 |
utenberg | -1.032 |
netflix | -1.028 |
Token | gays |
Token ID | 28067 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Red | +3.863 |
Sioux | +3.740 |
RED | +3.628 |
Pt | +3.622 |
White | +3.493 |
Neg logit contributions | |
ubes | -3.522 |
atri | -3.306 |
utenberg | -3.260 |
UTERS | -3.158 |
hib | -3.158 |
Token | ? |
Token ID | 30 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Red | +2.456 |
Sioux | +2.367 |
Pt | +2.363 |
RED | +2.308 |
White | +2.183 |
Neg logit contributions | |
ubes | -2.539 |
atri | -2.337 |
utenberg | -2.300 |
netflix | -2.274 |
UTERS | -2.268 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ubes | +0.394 |
atri | +0.367 |
hib | +0.359 |
utenberg | +0.359 |
netflix | +0.355 |
Neg logit contributions | |
Red | -0.312 |
Sioux | -0.308 |
Pt | -0.304 |
RED | -0.297 |
White | -0.275 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ubes | +0.769 |
atri | +0.700 |
hib | +0.696 |
netflix | +0.680 |
utenberg | +0.677 |
Neg logit contributions | |
Sioux | -0.875 |
Red | -0.864 |
Pt | -0.852 |
RED | -0.839 |
Clarks | -0.808 |
Token | Think |
Token ID | 22073 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ubes | +0.147 |
atri | +0.135 |
utenberg | +0.132 |
hib | +0.131 |
netflix | +0.130 |
Neg logit contributions | |
Red | -0.158 |
Sioux | -0.156 |
Pt | -0.155 |
RED | -0.151 |
White | -0.142 |
Token | � |
Token ID | 250 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Red | +0.412 |
Sioux | +0.392 |
Pt | +0.391 |
RED | +0.381 |
White | +0.341 |
Neg logit contributions | |
ubes | -0.835 |
atri | -0.787 |
utenberg | -0.776 |
hib | -0.771 |
netflix | -0.766 |
Token | The |
Token ID | 464 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
ubes | +0.817 |
atri | +0.751 |
hib | +0.734 |
utenberg | +0.733 |
netflix | +0.725 |
Neg logit contributions | |
Red | -0.849 |
Sioux | -0.839 |
Pt | -0.828 |
RED | -0.812 |
White | -0.760 |
Token | culture |
Token ID | 3968 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
ubes | +0.079 |
atri | +0.073 |
utenberg | +0.072 |
hib | +0.072 |
netflix | +0.072 |
Neg logit contributions | |
Red | -0.062 |
Sioux | -0.061 |
Pt | -0.060 |
RED | -0.059 |
White | -0.055 |
Token | is |
Token ID | 318 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ubes | +0.690 |
atri | +0.646 |
hib | +0.634 |
utenberg | +0.633 |
netflix | +0.629 |
Neg logit contributions | |
Red | -0.443 |
Sioux | -0.436 |
Pt | -0.429 |
RED | -0.418 |
White | -0.383 |
Token | fantastic |
Token ID | 9623 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Red | +0.147 |
Sioux | +0.145 |
Pt | +0.142 |
RED | +0.139 |
White | +0.128 |
Neg logit contributions | |
ubes | -0.212 |
atri | -0.198 |
hib | -0.194 |
utenberg | -0.194 |
netflix | -0.193 |
Token | here |
Token ID | 994 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Red | +0.773 |
Sioux | +0.749 |
Pt | +0.738 |
RED | +0.722 |
White | +0.664 |
Neg logit contributions | |
ubes | -1.230 |
atri | -1.144 |
utenberg | -1.135 |
netflix | -1.126 |
hib | -1.124 |
Token | . |
Token ID | 13 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
Red | +0.615 |
Sioux | +0.593 |
Pt | +0.590 |
RED | +0.574 |
White | +0.528 |
Neg logit contributions | |
ubes | -0.969 |
atri | -0.898 |
utenberg | -0.889 |
hib | -0.884 |
netflix | -0.883 |
Token | It |
Token ID | 632 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Red | +0.626 |
Sioux | +0.611 |
Pt | +0.603 |
RED | +0.590 |
White | +0.548 |
Neg logit contributions | |
ubes | -0.834 |
atri | -0.773 |
utenberg | -0.762 |
hib | -0.756 |
netflix | -0.754 |
Token | � |
Token ID | 447 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Red | +1.013 |
Sioux | +0.986 |
Pt | +0.972 |
RED | +0.953 |
White | +0.876 |
Neg logit contributions | |
ubes | -1.541 |
atri | -1.435 |
utenberg | -1.421 |
netflix | -1.410 |
hib | -1.409 |
Token | � |
Token ID | 247 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ubes | +0.409 |
atri | +0.386 |
hib | +0.380 |
utenberg | +0.380 |
netflix | +0.377 |
Neg logit contributions | |
Red | -0.199 |
Sioux | -0.194 |
Pt | -0.191 |
RED | -0.185 |
White | -0.166 |
Token | s |
Token ID | 82 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Red | +0.205 |
Sioux | +0.202 |
Pt | +0.199 |
RED | +0.194 |
White | +0.179 |
Neg logit contributions | |
ubes | -0.278 |
atri | -0.259 |
hib | -0.254 |
utenberg | -0.254 |
netflix | -0.252 |
Token | crunch |
Token ID | 23527 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
Red | +0.021 |
Sioux | +0.021 |
Pt | +0.020 |
RED | +0.020 |
White | +0.018 |
Neg logit contributions | |
ubes | -0.027 |
atri | -0.025 |
utenberg | -0.025 |
hib | -0.025 |
netflix | -0.024 |
Token | y |
Token ID | 88 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
ubes | +0.078 |
atri | +0.073 |
hib | +0.071 |
utenberg | +0.071 |
netflix | +0.071 |
Neg logit contributions | |
Red | -0.059 |
Sioux | -0.058 |
Pt | -0.057 |
RED | -0.056 |
White | -0.052 |
Token | gran |
Token ID | 19468 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Red | +0.551 |
Sioux | +0.539 |
Pt | +0.530 |
RED | +0.520 |
White | +0.481 |
Neg logit contributions | |
ubes | -0.761 |
atri | -0.712 |
hib | -0.697 |
utenberg | -0.697 |
netflix | -0.692 |
Token | ola |
Token ID | 5708 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ubes | +1.592 |
atri | +1.507 |
hib | +1.484 |
utenberg | +1.481 |
netflix | +1.472 |
Neg logit contributions | |
Red | -0.582 |
Sioux | -0.570 |
Pt | -0.556 |
RED | -0.535 |
White | -0.466 |
Token | mentality |
Token ID | 21332 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
Red | +1.721 |
Sioux | +1.682 |
Pt | +1.662 |
RED | +1.617 |
White | +1.512 |
Neg logit contributions | |
ubes | -2.207 |
atri | -2.071 |
utenberg | -2.028 |
hib | -2.022 |
netflix | -2.003 |
Token | running |
Token ID | 2491 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ubes | +0.340 |
atri | +0.318 |
utenberg | +0.312 |
hib | +0.311 |
netflix | +0.309 |
Neg logit contributions | |
Red | -0.228 |
Sioux | -0.224 |
Pt | -0.221 |
RED | -0.215 |
White | -0.198 |
Token | things |
Token ID | 1243 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Red | +0.872 |
Sioux | +0.855 |
Pt | +0.841 |
RED | +0.826 |
White | +0.766 |
Neg logit contributions | |
ubes | -1.074 |
atri | -1.003 |
utenberg | -0.982 |
hib | -0.974 |
netflix | -0.969 |
Token | as |
Token ID | 355 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ubes | +0.032 |
atri | +0.030 |
hib | +0.029 |
utenberg | +0.029 |
netflix | +0.029 |
Neg logit contributions | |
Red | -0.021 |
Sioux | -0.021 |
Pt | -0.021 |
RED | -0.020 |
White | -0.019 |
Token | if |
Token ID | 611 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
ubes | +0.276 |
atri | +0.256 |
hib | +0.250 |
utenberg | +0.250 |
netflix | +0.248 |
Neg logit contributions | |
Red | -0.234 |
Sioux | -0.231 |
Pt | -0.228 |
RED | -0.223 |
White | -0.207 |
Token | we |
Token ID | 356 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Red | +0.020 |
Sioux | +0.020 |
Pt | +0.019 |
RED | +0.019 |
White | +0.018 |
Neg logit contributions | |
ubes | -0.025 |
atri | -0.023 |
hib | -0.023 |
utenberg | -0.023 |
netflix | -0.023 |
Token | cannot |
Token ID | 2314 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ubes | +0.191 |
atri | +0.178 |
hib | +0.175 |
utenberg | +0.175 |
netflix | +0.173 |
Neg logit contributions | |
Red | -0.138 |
Sioux | -0.137 |
Pt | -0.134 |
RED | -0.131 |
White | -0.121 |
Token | just |
Token ID | 655 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Red | +0.981 |
Sioux | +0.953 |
Pt | +0.946 |
RED | +0.928 |
White | +0.848 |
Neg logit contributions | |
ubes | -1.427 |
atri | -1.334 |
utenberg | -1.310 |
hib | -1.301 |
netflix | -1.295 |
Token | as |
Token ID | 355 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Red | +0.311 |
Sioux | +0.306 |
Pt | +0.301 |
RED | +0.293 |
White | +0.266 |
Neg logit contributions | |
ubes | -0.528 |
atri | -0.495 |
hib | -0.486 |
utenberg | -0.486 |
netflix | -0.482 |
Token | fast |
Token ID | 3049 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Red | +1.965 |
Sioux | +1.915 |
Pt | +1.885 |
RED | +1.860 |
White | +1.710 |
Neg logit contributions | |
ubes | -2.573 |
atri | -2.411 |
utenberg | -2.368 |
hib | -2.351 |
netflix | -2.336 |
Token | as |
Token ID | 355 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Red | +1.289 |
Sioux | +1.252 |
Pt | +1.237 |
RED | +1.206 |
White | +1.095 |
Neg logit contributions | |
ubes | -2.221 |
atri | -2.090 |
utenberg | -2.052 |
hib | -2.047 |
netflix | -2.038 |
Token | it |
Token ID | 340 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Red | +0.214 |
Sioux | +0.210 |
Pt | +0.207 |
RED | +0.203 |
White | +0.186 |
Neg logit contributions | |
ubes | -0.300 |
atri | -0.281 |
hib | -0.275 |
utenberg | -0.275 |
netflix | -0.272 |
Token | can |
Token ID | 460 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Red | +1.175 |
Sioux | +1.155 |
Pt | +1.135 |
RED | +1.117 |
White | +1.029 |
Neg logit contributions | |
ubes | -1.527 |
atri | -1.428 |
hib | -1.400 |
utenberg | -1.396 |
netflix | -1.386 |
Token | go |
Token ID | 467 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Red | +0.921 |
Sioux | +0.903 |
Pt | +0.889 |
RED | +0.872 |
White | +0.802 |
Neg logit contributions | |
ubes | -1.259 |
atri | -1.180 |
hib | -1.159 |
utenberg | -1.154 |
netflix | -1.145 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ubes | +0.105 |
atri | +0.098 |
hib | +0.096 |
utenberg | +0.095 |
netflix | +0.095 |
Neg logit contributions | |
Red | -0.076 |
Sioux | -0.075 |
Pt | -0.074 |
RED | -0.072 |
White | -0.066 |
Token | The |
Token ID | 383 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
ubes | +0.145 |
atri | +0.134 |
hib | +0.132 |
utenberg | +0.131 |
netflix | +0.130 |
Neg logit contributions | |
Red | -0.129 |
Sioux | -0.127 |
Pt | -0.126 |
RED | -0.123 |
White | -0.114 |
Token | buffer |
Token ID | 11876 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
Red | +0.562 |
Sioux | +0.552 |
Pt | +0.544 |
RED | +0.533 |
White | +0.491 |
Neg logit contributions | |
ubes | -0.749 |
atri | -0.700 |
hib | -0.685 |
utenberg | -0.685 |
netflix | -0.680 |
Token | will |
Token ID | 481 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ubes | +0.476 |
atri | +0.444 |
hib | +0.435 |
utenberg | +0.434 |
netflix | +0.431 |
Neg logit contributions | |
Red | -0.353 |
Sioux | -0.348 |
Pt | -0.343 |
RED | -0.335 |
White | -0.309 |
Token | games |
Token ID | 1830 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ubes | +0.838 |
atri | +0.767 |
utenberg | +0.747 |
hib | +0.744 |
netflix | +0.738 |
Neg logit contributions | |
Red | -1.035 |
Sioux | -1.020 |
Pt | -1.009 |
RED | -0.993 |
White | -0.934 |
Token | from |
Token ID | 422 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
Red | +0.467 |
Sioux | +0.452 |
Pt | +0.447 |
RED | +0.439 |
White | +0.404 |
Neg logit contributions | |
ubes | -0.706 |
atri | -0.660 |
utenberg | -0.650 |
hib | -0.647 |
netflix | -0.642 |
Token | 1988 |
Token ID | 12122 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Red | +0.432 |
Sioux | +0.419 |
Pt | +0.413 |
RED | +0.406 |
White | +0.377 |
Neg logit contributions | |
ubes | -0.611 |
atri | -0.567 |
utenberg | -0.560 |
netflix | -0.555 |
hib | -0.553 |
Token | to |
Token ID | 284 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Red | +1.101 |
Sioux | +1.064 |
Pt | +1.052 |
RED | +1.032 |
White | +0.951 |
Neg logit contributions | |
ubes | -1.636 |
atri | -1.528 |
utenberg | -1.501 |
hib | -1.485 |
netflix | -1.479 |
Token | 1992 |
Token ID | 9768 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
ubes | +0.221 |
atri | +0.206 |
hib | +0.202 |
utenberg | +0.202 |
netflix | +0.200 |
Neg logit contributions | |
Red | -0.159 |
Sioux | -0.157 |
Pt | -0.154 |
RED | -0.151 |
White | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Red | +0.042 |
Sioux | +0.041 |
Pt | +0.040 |
RED | +0.040 |
White | +0.037 |
Neg logit contributions | |
ubes | -0.056 |
atri | -0.052 |
utenberg | -0.051 |
hib | -0.051 |
netflix | -0.051 |
Token | adds |
Token ID | 6673 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Red | +0.422 |
Sioux | +0.413 |
Pt | +0.406 |
RED | +0.397 |
White | +0.364 |
Neg logit contributions | |
ubes | -0.671 |
atri | -0.629 |
hib | -0.617 |
utenberg | -0.616 |
netflix | -0.613 |
Token | modern |
Token ID | 3660 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Red | +0.984 |
Sioux | +0.954 |
Pt | +0.935 |
RED | +0.925 |
White | +0.847 |
Neg logit contributions | |
ubes | -1.465 |
atri | -1.373 |
utenberg | -1.341 |
netflix | -1.339 |
hib | -1.325 |
Token | gameplay |
Token ID | 11327 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Red | +1.514 |
Sioux | +1.471 |
Pt | +1.447 |
RED | +1.425 |
White | +1.333 |
Neg logit contributions | |
ubes | -1.735 |
atri | -1.626 |
utenberg | -1.589 |
netflix | -1.585 |
hib | -1.557 |
Token | elements |
Token ID | 4847 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Red | +2.120 |
Sioux | +2.055 |
Pt | +2.034 |
RED | +1.967 |
White | +1.806 |
Neg logit contributions | |
ubes | -3.440 |
atri | -3.242 |
netflix | -3.186 |
utenberg | -3.177 |
hib | -3.162 |
Token | of |
Token ID | 286 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Red | +1.261 |
Sioux | +1.210 |
Pt | +1.202 |
RED | +1.175 |
White | +1.076 |
Neg logit contributions | |
ubes | -2.151 |
atri | -2.013 |
utenberg | -1.986 |
hib | -1.969 |
netflix | -1.965 |
Token | road |
Token ID | 6344 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Red | +0.755 |
Sioux | +0.736 |
Pt | +0.731 |
RED | +0.721 |
White | +0.681 |
Neg logit contributions | |
ubes | -0.676 |
atri | -0.620 |
utenberg | -0.611 |
netflix | -0.604 |
hib | -0.602 |
Token | and |
Token ID | 290 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ubes | +0.169 |
atri | +0.158 |
hib | +0.155 |
utenberg | +0.155 |
netflix | +0.154 |
Neg logit contributions | |
Red | -0.109 |
Sioux | -0.107 |
Pt | -0.106 |
RED | -0.103 |
White | -0.094 |
Token | he |
Token ID | 339 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
ubes | +0.172 |
atri | +0.161 |
hib | +0.157 |
utenberg | +0.157 |
netflix | +0.156 |
Neg logit contributions | |
Red | -0.128 |
Sioux | -0.127 |
Pt | -0.125 |
RED | -0.122 |
White | -0.112 |
Token | still |
Token ID | 991 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
Red | +0.300 |
Sioux | +0.295 |
Pt | +0.290 |
RED | +0.284 |
White | +0.264 |
Neg logit contributions | |
ubes | -0.397 |
atri | -0.369 |
hib | -0.362 |
utenberg | -0.362 |
netflix | -0.360 |
Token | pulled |
Token ID | 5954 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
Red | +0.449 |
Sioux | +0.441 |
Pt | +0.433 |
RED | +0.425 |
White | +0.395 |
Neg logit contributions | |
ubes | -0.592 |
atri | -0.552 |
utenberg | -0.541 |
hib | -0.540 |
netflix | -0.537 |
Token | off |
Token ID | 572 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
Red | +2.068 |
Sioux | +2.017 |
Pt | +1.966 |
RED | +1.925 |
White | +1.797 |
Neg logit contributions | |
ubes | -3.340 |
atri | -3.161 |
hib | -3.091 |
netflix | -3.084 |
utenberg | -3.079 |
Token | one |
Token ID | 530 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Red | +3.572 |
Sioux | +3.496 |
Pt | +3.407 |
RED | +3.334 |
White | +3.169 |
Neg logit contributions | |
ubes | -5.246 |
atri | -4.882 |
utenberg | -4.815 |
netflix | -4.785 |
UTERS | -4.740 |
Token | of |
Token ID | 286 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Red | +2.021 |
Sioux | +1.970 |
Pt | +1.938 |
RED | +1.892 |
White | +1.776 |
Neg logit contributions | |
ubes | -3.091 |
atri | -2.885 |
utenberg | -2.842 |
hib | -2.826 |
netflix | -2.811 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Red | +1.169 |
Sioux | +1.128 |
Pt | +1.121 |
RED | +1.081 |
White | +1.032 |
Neg logit contributions | |
ubes | -1.888 |
atri | -1.765 |
utenberg | -1.735 |
hib | -1.733 |
netflix | -1.725 |
Token | great |
Token ID | 1049 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
Red | +0.640 |
Sioux | +0.626 |
Pt | +0.617 |
RED | +0.602 |
White | +0.566 |
Neg logit contributions | |
ubes | -0.870 |
atri | -0.815 |
utenberg | -0.797 |
hib | -0.794 |
netflix | -0.792 |
Token | political |
Token ID | 1964 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ubes | +0.686 |
atri | +0.639 |
hib | +0.627 |
utenberg | +0.625 |
netflix | +0.620 |
Neg logit contributions | |
Red | -0.520 |
Sioux | -0.513 |
Pt | -0.505 |
RED | -0.494 |
White | -0.456 |
Token | ' |
Token ID | 6 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ubes | +0.509 |
atri | +0.472 |
hib | +0.463 |
utenberg | +0.462 |
netflix | +0.458 |
Neg logit contributions | |
Red | -0.427 |
Sioux | -0.420 |
Pt | -0.414 |
RED | -0.406 |
White | -0.376 |
Token | s |
Token ID | 82 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ubes | +1.971 |
atri | +1.831 |
hib | +1.786 |
utenberg | +1.778 |
netflix | +1.769 |
Neg logit contributions | |
Red | -1.689 |
Sioux | -1.677 |
Pt | -1.651 |
RED | -1.613 |
Clarks | -1.501 |
Token | stack |
Token ID | 8931 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
ubes | +1.239 |
atri | +1.152 |
hib | +1.128 |
utenberg | +1.124 |
netflix | +1.115 |
Neg logit contributions | |
Red | -0.995 |
Sioux | -0.985 |
Pt | -0.970 |
RED | -0.947 |
Clarks | -0.877 |
Token | frame |
Token ID | 5739 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ubes | +0.083 |
atri | +0.078 |
utenberg | +0.076 |
hib | +0.076 |
netflix | +0.075 |
Neg logit contributions | |
Red | -0.065 |
Sioux | -0.064 |
Pt | -0.064 |
RED | -0.062 |
White | -0.058 |
Token | | |
Token ID | 930 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Red | +0.373 |
Sioux | +0.363 |
Pt | +0.360 |
RED | +0.354 |
White | +0.328 |
Neg logit contributions | |
ubes | -0.441 |
atri | -0.409 |
utenberg | -0.402 |
hib | -0.401 |
netflix | -0.398 |
Token | void |
Token ID | 7951 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
ubes | +0.049 |
atri | +0.045 |
hib | +0.044 |
utenberg | +0.044 |
netflix | +0.044 |
Neg logit contributions | |
Red | -0.044 |
Sioux | -0.043 |
Pt | -0.042 |
RED | -0.041 |
White | -0.039 |
Token | * |
Token ID | 1635 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
Red | +4.342 |
RED | +4.118 |
Sioux | +4.114 |
Pt | +4.100 |
White | +3.792 |
Neg logit contributions | |
ubes | -5.620 |
atri | -5.282 |
utenberg | -5.240 |
hib | -5.186 |
netflix | -5.154 |
Token | arg |
Token ID | 853 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Red | +0.503 |
Sioux | +0.493 |
Pt | +0.488 |
RED | +0.477 |
White | +0.441 |
Neg logit contributions | |
ubes | -0.668 |
atri | -0.622 |
hib | -0.610 |
utenberg | -0.609 |
netflix | -0.605 |
Token | | |
Token ID | 930 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
Red | +0.110 |
Sioux | +0.108 |
Pt | +0.107 |
RED | +0.105 |
White | +0.097 |
Neg logit contributions | |
ubes | -0.129 |
atri | -0.120 |
hib | -0.117 |
utenberg | -0.117 |
netflix | -0.116 |
Token | - |
Token ID | 532 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ubes | +0.669 |
atri | +0.620 |
hib | +0.607 |
utenberg | +0.606 |
netflix | +0.602 |
Neg logit contributions | |
Red | -0.574 |
Sioux | -0.566 |
Pt | -0.558 |
RED | -0.546 |
White | -0.508 |
Token | our |
Token ID | 674 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
Red | +1.701 |
Sioux | +1.657 |
Pt | +1.637 |
RED | +1.602 |
White | +1.488 |
Neg logit contributions | |
ubes | -2.195 |
atri | -2.032 |
utenberg | -2.003 |
netflix | -1.990 |
hib | -1.975 |
Token | ipe |
Token ID | 3757 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
Red | +4.687 |
Pt | +4.567 |
Sioux | +4.557 |
RED | +4.448 |
White | +4.249 |
Neg logit contributions | |
ubes | -3.597 |
atri | -3.252 |
netflix | -3.212 |
utenberg | -3.185 |
hib | -3.180 |
Token | for |
Token ID | 329 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Red | +3.333 |
Sioux | +3.184 |
Pt | +3.146 |
RED | +3.055 |
White | +2.858 |
Neg logit contributions | |
ubes | -5.644 |
atri | -5.281 |
utenberg | -5.259 |
netflix | -5.151 |
hib | -5.136 |
Token | M |
Token ID | 337 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Red | +2.126 |
Sioux | +2.029 |
Pt | +2.024 |
RED | +1.996 |
White | +1.852 |
Neg logit contributions | |
ubes | -3.152 |
atri | -2.954 |
utenberg | -2.876 |
hib | -2.869 |
ictionary | -2.862 |
Token | ST |
Token ID | 2257 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
Red | +0.789 |
Sioux | +0.781 |
Pt | +0.768 |
RED | +0.752 |
Clarks | +0.698 |
Neg logit contributions | |
ubes | -0.958 |
atri | -0.888 |
hib | -0.871 |
utenberg | -0.867 |
netflix | -0.862 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Red | +1.764 |
Sioux | +1.732 |
Pt | +1.713 |
RED | +1.672 |
White | +1.546 |
Neg logit contributions | |
ubes | -2.337 |
atri | -2.178 |
utenberg | -2.132 |
hib | -2.129 |
netflix | -2.110 |
Token | K |
Token ID | 42 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
Red | +1.025 |
Sioux | +1.015 |
Pt | +1.005 |
RED | +0.987 |
White | +0.933 |
Neg logit contributions | |
ubes | -0.689 |
atri | -0.623 |
hib | -0.604 |
utenberg | -0.603 |
netflix | -0.596 |
Token | , |
Token ID | 11 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
Red | +3.143 |
Sioux | +3.039 |
Pt | +3.022 |
RED | +2.918 |
White | +2.688 |
Neg logit contributions | |
ubes | -5.624 |
atri | -5.280 |
utenberg | -5.211 |
bably | -5.132 |
hib | -5.132 |
Token | I |
Token ID | 314 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Red | +1.872 |
Sioux | +1.835 |
Pt | +1.824 |
RED | +1.758 |
White | +1.656 |
Neg logit contributions | |
ubes | -2.411 |
atri | -2.251 |
hib | -2.183 |
utenberg | -2.182 |
netflix | -2.150 |
Token | think |
Token ID | 892 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Red | +1.735 |
Sioux | +1.712 |
Pt | +1.691 |
RED | +1.656 |
White | +1.543 |
Neg logit contributions | |
ubes | -1.863 |
atri | -1.723 |
hib | -1.684 |
utenberg | -1.682 |
netflix | -1.667 |
Token |
|
Token ID | 198 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Red | +0.082 |
Sioux | +0.080 |
Pt | +0.080 |
RED | +0.078 |
White | +0.073 |
Neg logit contributions | |
ubes | -0.093 |
atri | -0.086 |
hib | -0.084 |
utenberg | -0.084 |
netflix | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ubes | +0.575 |
atri | +0.522 |
hib | +0.519 |
netflix | +0.509 |
utenberg | +0.506 |
Neg logit contributions | |
Sioux | -0.643 |
Red | -0.635 |
Pt | -0.626 |
RED | -0.616 |
Clarks | -0.593 |
Token | the |
Token ID | 262 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Red | +0.380 |
Sioux | +0.371 |
Pt | +0.364 |
RED | +0.357 |
White | +0.331 |
Neg logit contributions | |
ubes | -0.557 |
atri | -0.513 |
utenberg | -0.508 |
hib | -0.504 |
netflix | -0.501 |
Token | acquired |
Token ID | 9477 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Red | +0.386 |
Sioux | +0.379 |
Pt | +0.372 |
RED | +0.365 |
White | +0.341 |
Neg logit contributions | |
ubes | -0.488 |
atri | -0.451 |
utenberg | -0.445 |
hib | -0.443 |
netflix | -0.438 |
Token | series |
Token ID | 2168 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ubes | +1.676 |
atri | +1.560 |
hib | +1.528 |
utenberg | +1.514 |
netflix | +1.509 |
Neg logit contributions | |
Red | -1.435 |
Sioux | -1.421 |
Pt | -1.403 |
RED | -1.370 |
Clarks | -1.273 |
Token | � |
Token ID | 564 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
Red | +0.085 |
Sioux | +0.083 |
Pt | +0.082 |
RED | +0.080 |
White | +0.074 |
Neg logit contributions | |
ubes | -0.126 |
atri | -0.116 |
utenberg | -0.115 |
hib | -0.114 |
netflix | -0.113 |
Token | � |
Token ID | 246 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Red | +0.509 |
Sioux | +0.489 |
Pt | +0.487 |
RED | +0.474 |
White | +0.427 |
Neg logit contributions | |
ubes | -0.963 |
atri | -0.909 |
utenberg | -0.893 |
hib | -0.890 |
netflix | -0.884 |
Token | Bel |
Token ID | 12193 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
Red | +0.269 |
Sioux | +0.263 |
Pt | +0.260 |
RED | +0.254 |
White | +0.237 |
Neg logit contributions | |
ubes | -0.321 |
atri | -0.294 |
utenberg | -0.290 |
hib | -0.288 |
netflix | -0.286 |
Token | iever |
Token ID | 47818 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Red | +4.084 |
Pt | +3.973 |
Sioux | +3.945 |
RED | +3.872 |
White | +3.618 |
Neg logit contributions | |
ubes | -4.617 |
atri | -4.186 |
utenberg | -4.167 |
hib | -4.140 |
netflix | -4.110 |
Token | with |
Token ID | 351 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
Red | +0.710 |
Sioux | +0.686 |
Pt | +0.686 |
RED | +0.662 |
White | +0.608 |
Neg logit contributions | |
ubes | -1.235 |
atri | -1.148 |
utenberg | -1.133 |
hib | -1.131 |
netflix | -1.117 |
Token | Re |
Token ID | 797 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Red | +0.452 |
Sioux | +0.440 |
Pt | +0.435 |
RED | +0.426 |
White | +0.402 |
Neg logit contributions | |
ubes | -0.498 |
atri | -0.451 |
utenberg | -0.448 |
hib | -0.445 |
netflix | -0.442 |
Token | za |
Token ID | 4496 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
Red | +0.981 |
Sioux | +0.962 |
Pt | +0.947 |
RED | +0.919 |
White | +0.858 |
Neg logit contributions | |
ubes | -1.442 |
atri | -1.351 |
netflix | -1.322 |
utenberg | -1.320 |
hib | -1.314 |
Token | As |
Token ID | 1081 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
ubes | +0.650 |
atri | +0.597 |
utenberg | +0.583 |
hib | +0.583 |
netflix | +0.578 |
Neg logit contributions | |
Red | -0.672 |
Sioux | -0.663 |
Pt | -0.656 |
RED | -0.640 |
White | -0.603 |
Token | free |
Token ID | 1479 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Red | +0.061 |
Sioux | +0.061 |
Pt | +0.060 |
RED | +0.059 |
White | +0.054 |
Neg logit contributions | |
ubes | -0.071 |
atri | -0.066 |
hib | -0.064 |
utenberg | -0.064 |
netflix | -0.064 |
Token | up |
Token ID | 510 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Red | +0.952 |
Sioux | +0.935 |
Pt | +0.915 |
RED | +0.903 |
White | +0.842 |
Neg logit contributions | |
ubes | -1.205 |
atri | -1.113 |
utenberg | -1.099 |
hib | -1.094 |
netflix | -1.088 |
Token | cash |
Token ID | 5003 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ubes | +0.612 |
atri | +0.571 |
hib | +0.560 |
utenberg | +0.559 |
netflix | +0.555 |
Neg logit contributions | |
Red | -0.432 |
Sioux | -0.426 |
Pt | -0.419 |
RED | -0.409 |
White | -0.376 |
Token | flow |
Token ID | 5202 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Red | +1.192 |
Sioux | +1.161 |
Pt | +1.138 |
RED | +1.129 |
White | +1.044 |
Neg logit contributions | |
ubes | -1.682 |
atri | -1.563 |
utenberg | -1.539 |
netflix | -1.537 |
hib | -1.530 |
Token |
|
Token ID | 198 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
ubes | +0.523 |
atri | +0.488 |
hib | +0.478 |
utenberg | +0.477 |
netflix | +0.474 |
Neg logit contributions | |
Red | -0.375 |
Sioux | -0.370 |
Pt | -0.364 |
RED | -0.355 |
White | -0.327 |
Token |
|
Token ID | 198 |
Feature activation | -8.40e+00 |
Pos logit contributions | |
Red | +3.809 |
Pt | +3.652 |
Sioux | +3.649 |
RED | +3.583 |
White | +3.347 |
Neg logit contributions | |
ubes | -4.834 |
atri | -4.540 |
utenberg | -4.445 |
bably | -4.410 |
netflix | -4.363 |
Token | WASHINGTON |
Token ID | 21793 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Red | +6.165 |
RED | +5.975 |
Sioux | +5.960 |
Pt | +5.931 |
White | +5.625 |
Neg logit contributions | |
ubes | -6.145 |
utenberg | -5.700 |
atri | -5.538 |
bably | -5.445 |
hib | -5.360 |
Token | -- |
Token ID | 1377 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Red | +2.457 |
Sioux | +2.355 |
RED | +2.339 |
Pt | +2.328 |
White | +2.089 |
Neg logit contributions | |
ubes | -4.387 |
atri | -4.113 |
utenberg | -4.083 |
hib | -4.025 |
netflix | -4.010 |
Token | Treasury |
Token ID | 13419 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Red | +2.899 |
Sioux | +2.761 |
Pt | +2.703 |
RED | +2.693 |
White | +2.573 |
Neg logit contributions | |
ubes | -4.195 |
utenberg | -3.898 |
atri | -3.886 |
netflix | -3.821 |
hib | -3.816 |
Token | Secretary |
Token ID | 4986 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Red | +1.969 |
Sioux | +1.915 |
Pt | +1.863 |
RED | +1.844 |
White | +1.725 |
Neg logit contributions | |
ubes | -3.113 |
atri | -2.918 |
netflix | -2.882 |
hib | -2.873 |
utenberg | -2.859 |
Token | Jacob |
Token ID | 12806 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Red | +0.946 |
Sioux | +0.915 |
Pt | +0.888 |
RED | +0.877 |
White | +0.835 |
Neg logit contributions | |
ubes | -1.302 |
atri | -1.223 |
netflix | -1.214 |
utenberg | -1.212 |
hib | -1.194 |