Token | ison |
Token ID | 1653 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
theless | +1.526 |
ying | +1.365 |
ices | +1.268 |
zin | +1.259 |
lict | +1.232 |
Neg logit contributions | |
liking | -2.208 |
Awesome | -2.208 |
motto | -2.207 |
effectiveness | -2.148 |
worth | -2.140 |
Token | Rain |
Token ID | 10301 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
theless | +3.797 |
ying | +3.556 |
ices | +3.357 |
zin | +3.353 |
lict | +3.273 |
Neg logit contributions | |
liking | -3.349 |
Awesome | -3.343 |
motto | -3.340 |
effectiveness | -3.216 |
OUNT | -3.198 |
Token | ess |
Token ID | 408 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
theless | +2.396 |
ying | +2.190 |
ices | +2.053 |
zin | +2.041 |
lict | +1.999 |
Neg logit contributions | |
liking | -2.724 |
motto | -2.720 |
Awesome | -2.720 |
effectiveness | -2.636 |
worth | -2.620 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
theless | +2.820 |
ying | +2.618 |
ices | +2.478 |
zin | +2.470 |
lict | +2.424 |
Neg logit contributions | |
liking | -2.402 |
motto | -2.398 |
Awesome | -2.397 |
effectiveness | -2.312 |
worth | -2.295 |
Token |
|
Token ID | 198 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
theless | +0.959 |
ying | +0.908 |
ices | +0.861 |
zin | +0.854 |
lict | +0.836 |
Neg logit contributions | |
motto | -0.759 |
liking | -0.754 |
Awesome | -0.745 |
� | -0.728 |
olicy | -0.726 |
Token | Cross |
Token ID | 21544 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
theless | +0.771 |
ying | +0.714 |
ices | +0.679 |
zin | +0.677 |
lict | +0.666 |
Neg logit contributions | |
Awesome | -0.565 |
liking | -0.564 |
motto | -0.563 |
effectiveness | -0.542 |
worth | -0.539 |
Token | - |
Token ID | 12 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
theless | +9.181 |
ying | +8.892 |
ices | +8.129 |
lict | +8.028 |
zin | +7.753 |
Neg logit contributions | |
motto | -10.709 |
Awesome | -10.686 |
OUNT | -10.633 |
liking | -10.432 |
olicy | -10.300 |
Token | d |
Token ID | 67 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
theless | +2.151 |
ying | +1.980 |
ices | +1.868 |
zin | +1.853 |
lict | +1.825 |
Neg logit contributions | |
motto | -2.108 |
liking | -2.108 |
Awesome | -2.104 |
effectiveness | -2.039 |
worth | -2.026 |
Token | ressing |
Token ID | 11697 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
theless | +4.874 |
ying | +4.712 |
ices | +4.423 |
zin | +4.310 |
lict | +4.283 |
Neg logit contributions | |
motto | -4.310 |
Awesome | -4.300 |
liking | -4.286 |
effectiveness | -4.147 |
worth | -4.089 |
Token | : |
Token ID | 25 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
theless | +4.216 |
ying | +3.948 |
ices | +3.728 |
zin | +3.694 |
lict | +3.659 |
Neg logit contributions | |
Awesome | -3.582 |
liking | -3.533 |
motto | -3.528 |
OUNT | -3.423 |
olicy | -3.393 |
Token | Cross |
Token ID | 6372 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
liking | +1.573 |
motto | +1.561 |
Awesome | +1.544 |
effectiveness | +1.511 |
worth | +1.506 |
Neg logit contributions | |
theless | -1.625 |
ying | -1.474 |
zin | -1.399 |
ices | -1.396 |
lict | -1.377 |
Token | bill |
Token ID | 2855 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
theless | +0.290 |
ying | +0.271 |
ices | +0.261 |
zin | +0.260 |
lict | +0.256 |
Neg logit contributions | |
liking | -0.134 |
motto | -0.134 |
Awesome | -0.132 |
effectiveness | -0.127 |
worth | -0.126 |
Token | as |
Token ID | 355 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
motto | +1.154 |
liking | +1.153 |
Awesome | +1.139 |
worth | +1.115 |
effectiveness | +1.115 |
Neg logit contributions | |
theless | -1.376 |
ying | -1.261 |
ices | -1.196 |
zin | -1.189 |
lict | -1.174 |
Token | an |
Token ID | 281 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
liking | +1.894 |
motto | +1.881 |
Awesome | +1.828 |
worth | +1.822 |
effectiveness | +1.805 |
Neg logit contributions | |
theless | -3.734 |
ying | -3.468 |
ices | -3.359 |
zin | -3.333 |
lict | -3.299 |
Token | anti |
Token ID | 3098 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
theless | +1.692 |
ying | +1.598 |
ices | +1.513 |
zin | +1.508 |
lict | +1.488 |
Neg logit contributions | |
liking | -1.127 |
Awesome | -1.124 |
motto | -1.114 |
OUNT | -1.068 |
olicy | -1.066 |
Token | - |
Token ID | 12 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
theless | +1.493 |
ying | +1.430 |
ices | +1.320 |
zin | +1.320 |
lict | +1.282 |
Neg logit contributions | |
motto | -1.871 |
liking | -1.871 |
Awesome | -1.857 |
effectiveness | -1.810 |
� | -1.806 |
Token | trans |
Token ID | 7645 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
theless | +1.371 |
ying | +1.279 |
ices | +1.211 |
zin | +1.204 |
lict | +1.185 |
Neg logit contributions | |
motto | -1.169 |
liking | -1.168 |
Awesome | -1.160 |
effectiveness | -1.126 |
olicy | -1.115 |
Token | measure |
Token ID | 3953 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ying | +10.893 |
theless | +10.845 |
lict | +10.132 |
ices | +10.070 |
zin | +10.024 |
Neg logit contributions | |
Awesome | -7.854 |
liking | -7.762 |
motto | -7.562 |
OUNT | -7.440 |
srfAttach | -7.427 |
Token | intended |
Token ID | 5292 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
liking | +1.939 |
motto | +1.930 |
worth | +1.924 |
Awesome | +1.890 |
effectiveness | +1.862 |
Neg logit contributions | |
theless | -2.347 |
ying | -2.132 |
ices | -2.051 |
zin | -2.020 |
lict | -2.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
liking | +1.869 |
motto | +1.863 |
Awesome | +1.821 |
worth | +1.809 |
effectiveness | +1.808 |
Neg logit contributions | |
theless | -2.992 |
ying | -2.714 |
ices | -2.605 |
zin | -2.599 |
lict | -2.563 |
Token | discriminate |
Token ID | 28433 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
theless | +1.691 |
ying | +1.582 |
ices | +1.489 |
zin | +1.482 |
lict | +1.464 |
Neg logit contributions | |
Awesome | -1.333 |
liking | -1.325 |
motto | -1.321 |
effectiveness | -1.270 |
olicy | -1.263 |
Token | against |
Token ID | 1028 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
theless | +4.050 |
ying | +3.817 |
ices | +3.615 |
lict | +3.588 |
zin | +3.580 |
Neg logit contributions | |
Awesome | -3.254 |
motto | -3.213 |
liking | -3.155 |
olicy | -3.084 |
OUNT | -3.056 |
Token | has |
Token ID | 468 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
theless | +0.570 |
ying | +0.528 |
ices | +0.502 |
zin | +0.501 |
lict | +0.494 |
Neg logit contributions | |
motto | -0.418 |
liking | -0.416 |
Awesome | -0.414 |
effectiveness | -0.400 |
worth | -0.399 |
Token | claimed |
Token ID | 4752 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
theless | +3.956 |
ying | +3.688 |
ices | +3.472 |
zin | +3.448 |
lict | +3.394 |
Neg logit contributions | |
Awesome | -3.224 |
liking | -3.125 |
motto | -3.117 |
OUNT | -3.088 |
olicy | -3.082 |
Token | ? |
Token ID | 30 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
liking | +1.049 |
motto | +1.045 |
Awesome | +1.038 |
worth | +1.007 |
effectiveness | +1.006 |
Neg logit contributions | |
theless | -1.498 |
ying | -1.386 |
ices | -1.324 |
zin | -1.319 |
lict | -1.299 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Awesome | +0.602 |
motto | +0.600 |
liking | +0.599 |
effectiveness | +0.576 |
worth | +0.576 |
Neg logit contributions | |
theless | -0.914 |
ying | -0.845 |
ices | -0.806 |
zin | -0.804 |
lict | -0.796 |
Token |
|
Token ID | 198 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
theless | +1.091 |
ying | +1.040 |
ices | +0.987 |
zin | +0.974 |
meyer | +0.955 |
Neg logit contributions | |
motto | -0.899 |
liking | -0.890 |
� | -0.872 |
Awesome | -0.866 |
olicy | -0.860 |
Token | Trans |
Token ID | 8291 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
theless | +0.775 |
ying | +0.718 |
ices | +0.683 |
zin | +0.681 |
lict | +0.670 |
Neg logit contributions | |
Awesome | -0.549 |
liking | -0.547 |
motto | -0.546 |
effectiveness | -0.525 |
worth | -0.523 |
Token | gender |
Token ID | 8388 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
theless | +8.273 |
ying | +8.210 |
ices | +7.492 |
zin | +7.363 |
lict | +7.318 |
Neg logit contributions | |
liking | -10.506 |
motto | -10.429 |
Awesome | -10.417 |
EGA | -10.153 |
OUNT | -10.149 |
Token | people |
Token ID | 661 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
theless | +5.253 |
ying | +4.923 |
ices | +4.658 |
zin | +4.641 |
lict | +4.576 |
Neg logit contributions | |
Awesome | -3.914 |
liking | -3.904 |
motto | -3.856 |
olicy | -3.729 |
OUNT | -3.712 |
Token | can |
Token ID | 460 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
theless | +3.466 |
ying | +3.196 |
ices | +2.989 |
zin | +2.977 |
lict | +2.925 |
Neg logit contributions | |
Awesome | -3.562 |
liking | -3.514 |
motto | -3.510 |
olicy | -3.402 |
effectiveness | -3.395 |
Token | undergo |
Token ID | 17777 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
theless | +1.279 |
ying | +1.179 |
ices | +1.117 |
zin | +1.111 |
lict | +1.092 |
Neg logit contributions | |
liking | -1.110 |
motto | -1.108 |
Awesome | -1.106 |
effectiveness | -1.071 |
worth | -1.065 |
Token | medically |
Token ID | 35031 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
theless | +6.340 |
ying | +5.997 |
ices | +5.694 |
lict | +5.652 |
zin | +5.609 |
Neg logit contributions | |
Awesome | -4.063 |
motto | -3.918 |
liking | -3.904 |
OUNT | -3.819 |
olicy | -3.780 |
Token | for |
Token ID | 329 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
liking | +2.430 |
motto | +2.417 |
Awesome | +2.361 |
worth | +2.351 |
effectiveness | +2.342 |
Neg logit contributions | |
theless | -2.930 |
ying | -2.699 |
zin | -2.569 |
ices | -2.543 |
lict | -2.536 |
Token | ds |
Token ID | 9310 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
liking | +1.313 |
Awesome | +1.295 |
motto | +1.294 |
effectiveness | +1.256 |
worth | +1.252 |
Neg logit contributions | |
theless | -2.217 |
ying | -2.054 |
ices | -1.959 |
zin | -1.951 |
lict | -1.930 |
Token | � |
Token ID | 447 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
theless | +0.316 |
ying | +0.293 |
ices | +0.278 |
zin | +0.276 |
lict | +0.272 |
Neg logit contributions | |
liking | -0.249 |
motto | -0.249 |
Awesome | -0.248 |
effectiveness | -0.240 |
worth | -0.239 |
Token | � |
Token ID | 251 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
liking | +0.884 |
Awesome | +0.878 |
motto | +0.878 |
worth | +0.852 |
effectiveness | +0.852 |
Neg logit contributions | |
theless | -1.113 |
ying | -1.018 |
ices | -0.972 |
zin | -0.968 |
lict | -0.950 |
Token | — |
Token ID | 960 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
liking | +0.379 |
motto | +0.376 |
Awesome | +0.376 |
worth | +0.364 |
effectiveness | +0.363 |
Neg logit contributions | |
theless | -0.519 |
ying | -0.480 |
ices | -0.457 |
zin | -0.455 |
lict | -0.450 |
Token | cross |
Token ID | 19692 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
theless | +1.243 |
ying | +1.147 |
ices | +1.085 |
zin | +1.080 |
lict | +1.061 |
Neg logit contributions | |
liking | -1.097 |
motto | -1.096 |
Awesome | -1.095 |
effectiveness | -1.059 |
worth | -1.052 |
Token | ing |
Token ID | 278 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
theless | +10.068 |
ying | +9.727 |
ices | +8.946 |
zin | +8.696 |
meyer | +8.628 |
Neg logit contributions | |
Awesome | -9.033 |
motto | -8.972 |
liking | -8.937 |
EGA | -8.757 |
OUNT | -8.703 |
Token | highly |
Token ID | 4047 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
theless | +2.618 |
ying | +2.452 |
ices | +2.342 |
zin | +2.325 |
lict | +2.304 |
Neg logit contributions | |
Awesome | -1.504 |
liking | -1.497 |
motto | -1.492 |
effectiveness | -1.427 |
olicy | -1.409 |
Token | traff |
Token ID | 11878 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
liking | +4.538 |
motto | +4.517 |
worth | +4.473 |
Awesome | +4.377 |
effectiveness | +4.363 |
Neg logit contributions | |
theless | -6.423 |
ying | -5.994 |
zin | -5.691 |
ices | -5.685 |
meyer | -5.523 |
Token | icked |
Token ID | 9484 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
theless | +3.320 |
ying | +3.149 |
ices | +2.967 |
zin | +2.938 |
lict | +2.919 |
Neg logit contributions | |
motto | -2.803 |
liking | -2.779 |
Awesome | -2.770 |
effectiveness | -2.676 |
olicy | -2.657 |
Token | thorough |
Token ID | 9321 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
theless | +3.115 |
ying | +2.908 |
ices | +2.779 |
zin | +2.751 |
lict | +2.733 |
Neg logit contributions | |
Awesome | -2.004 |
liking | -1.976 |
motto | -1.974 |
olicy | -1.889 |
effectiveness | -1.888 |
Token | . |
Token ID | 13 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
theless | +0.593 |
ying | +0.548 |
ices | +0.520 |
zin | +0.517 |
lict | +0.509 |
Neg logit contributions | |
liking | -0.475 |
motto | -0.474 |
Awesome | -0.474 |
effectiveness | -0.457 |
worth | -0.455 |
Token | � |
Token ID | 447 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
theless | +0.780 |
ying | +0.725 |
ices | +0.690 |
zin | +0.687 |
lict | +0.676 |
Neg logit contributions | |
liking | -0.549 |
motto | -0.549 |
Awesome | -0.548 |
effectiveness | -0.528 |
worth | -0.524 |
Token | � |
Token ID | 251 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
liking | +0.121 |
Awesome | +0.121 |
motto | +0.121 |
effectiveness | +0.116 |
worth | +0.116 |
Neg logit contributions | |
theless | -0.132 |
ying | -0.121 |
ices | -0.115 |
zin | -0.114 |
lict | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Awesome | +0.436 |
liking | +0.435 |
motto | +0.432 |
worth | +0.416 |
effectiveness | +0.416 |
Neg logit contributions | |
theless | -0.630 |
ying | -0.586 |
ices | -0.557 |
zin | -0.555 |
lict | -0.550 |
Token |
|
Token ID | 198 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
theless | +1.067 |
ying | +1.021 |
ices | +0.968 |
zin | +0.957 |
meyer | +0.937 |
Neg logit contributions | |
motto | -0.895 |
liking | -0.884 |
� | -0.883 |
Awesome | -0.870 |
olicy | -0.858 |
Token | Trans |
Token ID | 8291 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
theless | +0.837 |
ying | +0.774 |
ices | +0.736 |
zin | +0.733 |
lict | +0.721 |
Neg logit contributions | |
Awesome | -0.626 |
liking | -0.624 |
motto | -0.623 |
effectiveness | -0.600 |
worth | -0.597 |
Token | gender |
Token ID | 8388 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
theless | +8.049 |
ying | +7.861 |
ices | +7.234 |
zin | +7.137 |
lict | +7.061 |
Neg logit contributions | |
liking | -9.896 |
Awesome | -9.882 |
motto | -9.841 |
OUNT | -9.602 |
olicy | -9.554 |
Token | identity |
Token ID | 5369 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
theless | +4.917 |
ying | +4.594 |
ices | +4.342 |
zin | +4.318 |
lict | +4.260 |
Neg logit contributions | |
Awesome | -4.209 |
liking | -4.178 |
motto | -4.155 |
olicy | -4.012 |
OUNT | -4.005 |
Token | may |
Token ID | 743 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
theless | +2.756 |
ying | +2.555 |
ices | +2.426 |
zin | +2.407 |
lict | +2.381 |
Neg logit contributions | |
Awesome | -2.148 |
liking | -2.137 |
motto | -2.120 |
olicy | -2.041 |
effectiveness | -2.038 |
Token | be |
Token ID | 307 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
theless | +1.002 |
ying | +0.929 |
ices | +0.878 |
zin | +0.875 |
lict | +0.861 |
Neg logit contributions | |
Awesome | -0.832 |
liking | -0.830 |
motto | -0.829 |
effectiveness | -0.800 |
worth | -0.794 |
Token | a |
Token ID | 257 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
motto | +0.782 |
liking | +0.781 |
Awesome | +0.776 |
worth | +0.749 |
effectiveness | +0.748 |
Neg logit contributions | |
theless | -1.284 |
ying | -1.195 |
ices | -1.144 |
zin | -1.141 |
lict | -1.122 |
Token | definitions |
Token ID | 17336 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
theless | +1.905 |
ying | +1.776 |
ices | +1.692 |
zin | +1.682 |
lict | +1.658 |
Neg logit contributions | |
Awesome | -1.276 |
liking | -1.274 |
motto | -1.271 |
effectiveness | -1.221 |
worth | -1.212 |
Token | below |
Token ID | 2174 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
theless | +0.882 |
ying | +0.822 |
ices | +0.782 |
zin | +0.778 |
lict | +0.766 |
Neg logit contributions | |
liking | -0.613 |
Awesome | -0.613 |
motto | -0.613 |
effectiveness | -0.588 |
worth | -0.584 |
Token | ). |
Token ID | 737 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
liking | +0.254 |
motto | +0.254 |
Awesome | +0.254 |
effectiveness | +0.244 |
worth | +0.242 |
Neg logit contributions | |
theless | -0.407 |
ying | -0.380 |
ices | -0.362 |
zin | -0.361 |
lict | -0.355 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Awesome | +0.187 |
liking | +0.187 |
motto | +0.187 |
effectiveness | +0.180 |
worth | +0.179 |
Neg logit contributions | |
theless | -0.268 |
ying | -0.249 |
ices | -0.237 |
zin | -0.237 |
lict | -0.233 |
Token |
|
Token ID | 198 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
theless | +1.268 |
ying | +1.200 |
ices | +1.143 |
zin | +1.128 |
meyer | +1.104 |
Neg logit contributions | |
motto | -1.032 |
liking | -1.022 |
Awesome | -0.997 |
� | -0.993 |
olicy | -0.984 |
Token | Trans |
Token ID | 8291 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
theless | +0.916 |
ying | +0.851 |
ices | +0.811 |
zin | +0.807 |
lict | +0.795 |
Neg logit contributions | |
liking | -0.636 |
motto | -0.635 |
Awesome | -0.635 |
effectiveness | -0.611 |
worth | -0.607 |
Token | sexual |
Token ID | 18338 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
theless | +8.940 |
ying | +8.737 |
ices | +8.063 |
zin | +7.903 |
lict | +7.841 |
Neg logit contributions | |
Awesome | -8.932 |
motto | -8.924 |
liking | -8.891 |
OUNT | -8.652 |
EGA | -8.496 |
Token | : |
Token ID | 25 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
theless | +5.442 |
ying | +5.069 |
ices | +4.791 |
zin | +4.722 |
lict | +4.624 |
Neg logit contributions | |
Awesome | -4.816 |
motto | -4.741 |
liking | -4.734 |
OUNT | -4.559 |
olicy | -4.557 |
Token | " |
Token ID | 366 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
liking | +1.226 |
motto | +1.213 |
Awesome | +1.204 |
effectiveness | +1.169 |
worth | +1.164 |
Neg logit contributions | |
theless | -1.897 |
ying | -1.764 |
zin | -1.689 |
ices | -1.688 |
lict | -1.662 |
Token | Trans |
Token ID | 8291 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Awesome | +1.389 |
liking | +1.377 |
motto | +1.359 |
effectiveness | +1.320 |
worth | +1.314 |
Neg logit contributions | |
theless | -2.025 |
ying | -1.871 |
zin | -1.794 |
ices | -1.785 |
lict | -1.755 |
Token | sexual |
Token ID | 18338 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
theless | +7.707 |
ying | +7.383 |
ices | +6.786 |
zin | +6.674 |
lict | +6.549 |
Neg logit contributions | |
Awesome | -8.212 |
motto | -8.203 |
liking | -8.074 |
OUNT | -7.975 |
olicy | -7.906 |
Token | who |
Token ID | 508 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
theless | +1.372 |
ying | +1.252 |
ices | +1.172 |
zin | +1.164 |
lict | +1.141 |
Neg logit contributions | |
Awesome | -1.596 |
motto | -1.591 |
liking | -1.588 |
effectiveness | -1.542 |
worth | -1.531 |
Token | desire |
Token ID | 6227 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
theless | +2.494 |
ying | +2.307 |
ices | +2.186 |
zin | +2.175 |
lict | +2.141 |
Neg logit contributions | |
Awesome | -2.035 |
liking | -2.033 |
motto | -2.031 |
effectiveness | -1.960 |
worth | -1.946 |
Token | physical |
Token ID | 3518 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
theless | +0.517 |
ying | +0.481 |
ices | +0.459 |
zin | +0.457 |
lict | +0.450 |
Neg logit contributions | |
liking | -0.337 |
Awesome | -0.337 |
motto | -0.336 |
effectiveness | -0.323 |
worth | -0.321 |
Token | transition |
Token ID | 6801 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
liking | +1.940 |
motto | +1.900 |
effectiveness | +1.867 |
Awesome | +1.852 |
worth | +1.848 |
Neg logit contributions | |
theless | -3.136 |
ying | -2.909 |
zin | -2.808 |
ices | -2.804 |
meyer | -2.750 |
Token | (" |
Token ID | 5855 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
theless | +3.613 |
ying | +3.361 |
ices | +3.172 |
zin | +3.148 |
lict | +3.110 |
Neg logit contributions | |
Awesome | -2.993 |
motto | -2.968 |
liking | -2.947 |
OUNT | -2.852 |
effectiveness | -2.822 |
Token | trans |
Token ID | 7645 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
Awesome | +2.894 |
liking | +2.876 |
motto | +2.836 |
effectiveness | +2.771 |
worth | +2.770 |
Neg logit contributions | |
theless | -3.115 |
ying | -2.818 |
ices | -2.664 |
zin | -2.664 |
lict | -2.622 |
Token | sexual |
Token ID | 18338 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
theless | +8.344 |
ying | +8.098 |
ices | +7.472 |
zin | +7.312 |
lict | +7.174 |
Neg logit contributions | |
Awesome | -9.517 |
motto | -9.512 |
liking | -9.326 |
OUNT | -9.157 |
EGA | -9.061 |
Token | " |
Token ID | 1 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
theless | +4.667 |
ying | +4.324 |
ices | +4.092 |
zin | +4.057 |
lict | +3.967 |
Neg logit contributions | |
Awesome | -4.273 |
motto | -4.226 |
liking | -4.207 |
olicy | -4.082 |
OUNT | -4.066 |
Token | people |
Token ID | 661 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
liking | +1.214 |
motto | +1.211 |
Awesome | +1.202 |
effectiveness | +1.163 |
worth | +1.157 |
Neg logit contributions | |
theless | -1.833 |
ying | -1.703 |
ices | -1.624 |
zin | -1.619 |
lict | -1.597 |
Token | ) |
Token ID | 8 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
theless | +3.250 |
ying | +3.015 |
ices | +2.826 |
zin | +2.809 |
lict | +2.756 |
Neg logit contributions | |
Awesome | -2.998 |
motto | -2.921 |
liking | -2.909 |
olicy | -2.841 |
OUNT | -2.838 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
liking | +0.427 |
motto | +0.425 |
Awesome | +0.424 |
effectiveness | +0.410 |
worth | +0.409 |
Neg logit contributions | |
theless | -0.593 |
ying | -0.550 |
ices | -0.523 |
zin | -0.522 |
lict | -0.514 |
Token | protection |
Token ID | 4800 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
motto | +0.763 |
liking | +0.763 |
Awesome | +0.748 |
effectiveness | +0.732 |
worth | +0.727 |
Neg logit contributions | |
theless | -1.628 |
ying | -1.521 |
zin | -1.461 |
ices | -1.460 |
lict | -1.436 |
Token | clause |
Token ID | 13444 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
theless | +0.101 |
ying | +0.094 |
ices | +0.090 |
zin | +0.089 |
lict | +0.088 |
Neg logit contributions | |
liking | -0.074 |
motto | -0.074 |
Awesome | -0.074 |
effectiveness | -0.071 |
worth | -0.071 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
theless | +0.369 |
ying | +0.341 |
ices | +0.323 |
zin | +0.321 |
lict | +0.316 |
Neg logit contributions | |
Awesome | -0.316 |
liking | -0.315 |
motto | -0.315 |
effectiveness | -0.304 |
worth | -0.302 |
Token | the |
Token ID | 262 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
theless | +1.119 |
ying | +1.047 |
ices | +1.002 |
zin | +0.998 |
lict | +0.985 |
Neg logit contributions | |
liking | -0.601 |
motto | -0.600 |
Awesome | -0.600 |
effectiveness | -0.573 |
worth | -0.568 |
Token | Four |
Token ID | 6675 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
theless | +0.632 |
ying | +0.590 |
ices | +0.562 |
zin | +0.559 |
lict | +0.551 |
Neg logit contributions | |
Awesome | -0.420 |
liking | -0.419 |
motto | -0.418 |
effectiveness | -0.402 |
worth | -0.399 |
Token | teenth |
Token ID | 20283 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
theless | +3.050 |
ying | +2.879 |
ices | +2.670 |
zin | +2.632 |
lict | +2.565 |
Neg logit contributions | |
liking | -4.410 |
motto | -4.359 |
Awesome | -4.354 |
olicy | -4.251 |
OUNT | -4.246 |
Token | Amendment |
Token ID | 8441 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
theless | +7.213 |
ying | +6.936 |
zin | +6.316 |
ices | +6.306 |
meyer | +6.172 |
Neg logit contributions | |
liking | -10.036 |
Awesome | -9.973 |
olicy | -9.850 |
OUNT | -9.724 |
motto | -9.694 |
Token | as |
Token ID | 355 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
theless | +2.390 |
ying | +2.219 |
ices | +2.101 |
zin | +2.080 |
lict | +2.051 |
Neg logit contributions | |
Awesome | -2.169 |
liking | -2.133 |
motto | -2.125 |
olicy | -2.059 |
OUNT | -2.059 |
Token | it |
Token ID | 340 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
liking | +1.483 |
motto | +1.478 |
Awesome | +1.438 |
worth | +1.427 |
effectiveness | +1.414 |
Neg logit contributions | |
theless | -2.589 |
ying | -2.418 |
zin | -2.320 |
ices | -2.309 |
lict | -2.271 |
Token | applies |
Token ID | 8991 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
liking | +1.816 |
motto | +1.814 |
worth | +1.782 |
Awesome | +1.751 |
effectiveness | +1.743 |
Neg logit contributions | |
theless | -2.592 |
ying | -2.419 |
zin | -2.317 |
ices | -2.289 |
lict | -2.261 |
Token | to |
Token ID | 284 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
liking | +0.492 |
motto | +0.491 |
Awesome | +0.484 |
effectiveness | +0.473 |
worth | +0.472 |
Neg logit contributions | |
theless | -0.727 |
ying | -0.675 |
ices | -0.643 |
zin | -0.641 |
lict | -0.628 |
Token | , |
Token ID | 11 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
liking | +2.361 |
motto | +2.354 |
Awesome | +2.327 |
worth | +2.298 |
effectiveness | +2.236 |
Neg logit contributions | |
theless | -3.529 |
ying | -3.191 |
zin | -3.062 |
ices | -3.050 |
lict | -2.999 |
Token | which |
Token ID | 543 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
theless | +0.784 |
ying | +0.737 |
ices | +0.701 |
zin | +0.695 |
lict | +0.686 |
Neg logit contributions | |
Awesome | -0.510 |
motto | -0.507 |
liking | -0.507 |
effectiveness | -0.489 |
olicy | -0.485 |
Token | are |
Token ID | 389 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
theless | +1.340 |
ying | +1.234 |
ices | +1.164 |
zin | +1.155 |
lict | +1.138 |
Neg logit contributions | |
Awesome | -1.289 |
liking | -1.289 |
motto | -1.283 |
effectiveness | -1.245 |
worth | -1.234 |
Token | in |
Token ID | 287 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
liking | +0.041 |
Awesome | +0.041 |
motto | +0.041 |
effectiveness | +0.040 |
worth | +0.039 |
Neg logit contributions | |
theless | -0.062 |
ying | -0.057 |
ices | -0.055 |
zin | -0.054 |
lict | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
motto | +0.391 |
liking | +0.389 |
Awesome | +0.387 |
effectiveness | +0.372 |
worth | +0.372 |
Neg logit contributions | |
theless | -0.705 |
ying | -0.656 |
ices | -0.629 |
zin | -0.626 |
lict | -0.618 |
Token | nond |
Token ID | 30745 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
theless | +2.431 |
ying | +2.276 |
ices | +2.168 |
zin | +2.161 |
lict | +2.137 |
Neg logit contributions | |
Awesome | -1.473 |
liking | -1.465 |
motto | -1.463 |
effectiveness | -1.405 |
olicy | -1.391 |
Token | esc |
Token ID | 3798 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
ying | +6.256 |
theless | +6.121 |
ices | +5.493 |
zin | +5.290 |
lict | +5.258 |
Neg logit contributions | |
motto | -11.465 |
Awesome | -11.389 |
liking | -11.342 |
effectiveness | -10.981 |
adolesc | -10.932 |
Token | ript |
Token ID | 1968 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
theless | +3.244 |
ying | +3.056 |
ices | +2.916 |
zin | +2.901 |
lict | +2.880 |
Neg logit contributions | |
liking | -2.119 |
Awesome | -2.111 |
motto | -2.104 |
effectiveness | -2.023 |
worth | -1.999 |
Token | pre |
Token ID | 662 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
theless | +3.677 |
ying | +3.470 |
ices | +3.297 |
zin | +3.282 |
lict | +3.266 |
Neg logit contributions | |
Awesome | -2.071 |
liking | -2.036 |
motto | -2.029 |
olicy | -1.949 |
effectiveness | -1.946 |
Token | war |
Token ID | 5767 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
theless | +4.497 |
ying | +4.181 |
ices | +3.883 |
zin | +3.881 |
lict | +3.823 |
Neg logit contributions | |
liking | -5.070 |
motto | -5.051 |
Awesome | -5.048 |
effectiveness | -4.897 |
worth | -4.852 |
Token | building |
Token ID | 2615 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
theless | +1.938 |
ying | +1.822 |
ices | +1.735 |
zin | +1.730 |
lict | +1.710 |
Neg logit contributions | |
Awesome | -1.086 |
liking | -1.083 |
motto | -1.077 |
effectiveness | -1.032 |
olicy | -1.020 |
Token | touched |
Token ID | 12615 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
theless | +0.241 |
ying | +0.220 |
ices | +0.209 |
zin | +0.208 |
lict | +0.205 |
Neg logit contributions | |
liking | -0.233 |
motto | -0.233 |
Awesome | -0.231 |
worth | -0.226 |
effectiveness | -0.224 |
Token | on |
Token ID | 319 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
theless | +1.855 |
ying | +1.745 |
ices | +1.656 |
zin | +1.639 |
lict | +1.624 |
Neg logit contributions | |
Awesome | -1.122 |
motto | -1.117 |
liking | -1.116 |
effectiveness | -1.072 |
olicy | -1.061 |
Token | : |
Token ID | 25 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
liking | +1.518 |
motto | +1.511 |
Awesome | +1.504 |
worth | +1.470 |
effectiveness | +1.460 |
Neg logit contributions | |
theless | -1.716 |
ying | -1.579 |
ices | -1.500 |
zin | -1.500 |
lict | -1.475 |
Token |
|
Token ID | 198 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
liking | +1.155 |
motto | +1.149 |
Awesome | +1.148 |
effectiveness | +1.106 |
worth | +1.099 |
Neg logit contributions | |
theless | -1.815 |
ying | -1.688 |
ices | -1.611 |
zin | -1.607 |
lict | -1.586 |
Token |
|
Token ID | 198 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
motto | +0.421 |
liking | +0.420 |
Awesome | +0.417 |
effectiveness | +0.403 |
olicy | +0.400 |
Neg logit contributions | |
theless | -0.572 |
ying | -0.537 |
ices | -0.510 |
zin | -0.507 |
lict | -0.498 |
Token | Trans |
Token ID | 8291 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
Awesome | +0.541 |
liking | +0.533 |
motto | +0.530 |
effectiveness | +0.511 |
worth | +0.510 |
Neg logit contributions | |
theless | -0.798 |
ying | -0.736 |
ices | -0.702 |
zin | -0.700 |
lict | -0.689 |
Token | actions |
Token ID | 4658 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
theless | +7.919 |
ying | +7.824 |
ices | +7.044 |
zin | +6.953 |
lict | +6.866 |
Neg logit contributions | |
motto | -9.340 |
liking | -9.320 |
Awesome | -9.167 |
OUNT | -8.958 |
effectiveness | -8.909 |
Token | in |
Token ID | 287 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
theless | +4.813 |
ying | +4.514 |
ices | +4.280 |
zin | +4.238 |
meyer | +4.184 |
Neg logit contributions | |
motto | -3.655 |
Awesome | -3.643 |
liking | -3.630 |
OUNT | -3.494 |
olicy | -3.471 |
Token | database |
Token ID | 6831 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
liking | +0.024 |
motto | +0.024 |
Awesome | +0.024 |
effectiveness | +0.023 |
worth | +0.023 |
Neg logit contributions | |
theless | -0.041 |
ying | -0.039 |
ices | -0.037 |
zin | -0.037 |
lict | -0.036 |
Token | systems |
Token ID | 3341 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
theless | +0.825 |
ying | +0.768 |
ices | +0.732 |
zin | +0.730 |
lict | +0.718 |
Neg logit contributions | |
liking | -0.540 |
motto | -0.539 |
Awesome | -0.539 |
effectiveness | -0.518 |
worth | -0.515 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
liking | +1.246 |
Awesome | +1.241 |
motto | +1.241 |
worth | +1.210 |
effectiveness | +1.207 |
Neg logit contributions | |
theless | -1.541 |
ying | -1.410 |
ices | -1.341 |
zin | -1.337 |
lict | -1.317 |
Token | Berlin |
Token ID | 11307 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
liking | +0.414 |
motto | +0.413 |
Awesome | +0.412 |
effectiveness | +0.396 |
worth | +0.394 |
Neg logit contributions | |
theless | -0.676 |
ying | -0.630 |
ices | -0.601 |
zin | -0.598 |
lict | -0.590 |
Token | er |
Token ID | 263 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
theless | +2.948 |
ying | +2.740 |
zin | +2.593 |
ices | +2.590 |
meyer | +2.532 |
Neg logit contributions | |
Awesome | -2.536 |
motto | -2.516 |
liking | -2.509 |
effectiveness | -2.431 |
olicy | -2.416 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
theless | +1.885 |
ying | +1.752 |
ices | +1.666 |
zin | +1.662 |
lict | +1.628 |
Neg logit contributions | |
Awesome | -1.460 |
motto | -1.447 |
liking | -1.445 |
effectiveness | -1.397 |
olicy | -1.385 |
Token | 1994 |
Token ID | 9162 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
theless | +1.129 |
ying | +1.056 |
ices | +1.008 |
zin | +1.004 |
lict | +0.988 |
Neg logit contributions | |
Awesome | -0.693 |
motto | -0.692 |
liking | -0.692 |
effectiveness | -0.663 |
worth | -0.656 |
Token | ; |
Token ID | 26 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
liking | +1.171 |
motto | +1.164 |
Awesome | +1.160 |
worth | +1.130 |
effectiveness | +1.126 |
Neg logit contributions | |
theless | -1.558 |
ying | -1.435 |
ices | -1.367 |
zin | -1.356 |
lict | -1.339 |
Token | Cross |
Token ID | 6372 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
theless | +0.516 |
ying | +0.479 |
ices | +0.457 |
zin | +0.454 |
lict | +0.448 |
Neg logit contributions | |
liking | -0.353 |
motto | -0.352 |
Awesome | -0.352 |
effectiveness | -0.339 |
worth | -0.337 |
Token | an |
Token ID | 272 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
theless | +8.529 |
ying | +8.128 |
meyer | +7.752 |
zin | +7.717 |
ices | +7.548 |
Neg logit contributions | |
Awesome | -8.761 |
liking | -8.726 |
motto | -8.680 |
OUNT | -8.349 |
effectiveness | -8.297 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
theless | +3.129 |
ying | +2.893 |
zin | +2.734 |
ices | +2.729 |
lict | +2.670 |
Neg logit contributions | |
Awesome | -3.088 |
liking | -3.087 |
motto | -3.076 |
effectiveness | -2.968 |
worth | -2.944 |
Token | 1998 |
Token ID | 7795 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
theless | +1.385 |
ying | +1.296 |
ices | +1.237 |
zin | +1.229 |
lict | +1.209 |
Neg logit contributions | |
Awesome | -0.885 |
liking | -0.884 |
motto | -0.884 |
effectiveness | -0.847 |
worth | -0.838 |
Token | ; |
Token ID | 26 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
theless | +0.512 |
ying | +0.475 |
ices | +0.452 |
zin | +0.450 |
lict | +0.443 |
Neg logit contributions | |
liking | -0.370 |
motto | -0.370 |
Awesome | -0.369 |
effectiveness | -0.356 |
worth | -0.354 |
Token | We |
Token ID | 775 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
theless | +0.059 |
ying | +0.055 |
ices | +0.052 |
zin | +0.052 |
lict | +0.051 |
Neg logit contributions | |
liking | -0.041 |
motto | -0.041 |
Awesome | -0.040 |
effectiveness | -0.039 |
worth | -0.039 |
Token | gender |
Token ID | 5279 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
theless | +0.251 |
ying | +0.234 |
ices | +0.223 |
zin | +0.222 |
lict | +0.219 |
Neg logit contributions | |
liking | -0.163 |
motto | -0.162 |
Awesome | -0.162 |
effectiveness | -0.156 |
worth | -0.155 |
Token | que |
Token ID | 4188 |
Feature activation | +8.28e+00 |
Pos logit contributions | |
theless | +0.789 |
ying | +0.727 |
ices | +0.687 |
zin | +0.684 |
lict | +0.672 |
Neg logit contributions | |
liking | -0.715 |
motto | -0.714 |
Awesome | -0.714 |
effectiveness | -0.690 |
worth | -0.686 |
Token | er |
Token ID | 263 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
theless | +5.202 |
ying | +4.815 |
ices | +4.315 |
zin | +4.259 |
lict | +4.195 |
Neg logit contributions | |
motto | -8.043 |
liking | -8.036 |
Awesome | -8.019 |
olicy | -7.908 |
OUNT | -7.793 |
Token | people |
Token ID | 661 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
theless | +1.963 |
ying | +1.816 |
ices | +1.719 |
zin | +1.710 |
lict | +1.680 |
Neg logit contributions | |
Awesome | -1.664 |
motto | -1.663 |
liking | -1.663 |
effectiveness | -1.604 |
worth | -1.593 |
Token | or |
Token ID | 393 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
theless | +2.468 |
ying | +2.280 |
ices | +2.146 |
zin | +2.133 |
lict | +2.092 |
Neg logit contributions | |
Awesome | -2.391 |
motto | -2.385 |
liking | -2.377 |
effectiveness | -2.307 |
olicy | -2.284 |
Token | cross |
Token ID | 3272 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
theless | +0.555 |
ying | +0.514 |
ices | +0.490 |
zin | +0.488 |
lict | +0.480 |
Neg logit contributions | |
liking | -0.404 |
motto | -0.403 |
Awesome | -0.402 |
effectiveness | -0.388 |
worth | -0.386 |
Token | - |
Token ID | 12 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
theless | +7.925 |
ying | +7.599 |
ices | +6.934 |
lict | +6.737 |
zin | +6.703 |
Neg logit contributions | |
Awesome | -9.355 |
motto | -9.342 |
OUNT | -9.150 |
liking | -9.100 |
olicy | -9.078 |
Token | dress |
Token ID | 49380 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
theless | +2.219 |
ying | +2.014 |
ices | +1.877 |
zin | +1.862 |
lict | +1.823 |
Neg logit contributions | |
liking | -2.939 |
motto | -2.938 |
Awesome | -2.935 |
effectiveness | -2.856 |
worth | -2.839 |
Token | ers |
Token ID | 364 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
theless | +3.582 |
ying | +3.333 |
ices | +2.961 |
zin | +2.902 |
lict | +2.839 |
Neg logit contributions | |
motto | -7.467 |
Awesome | -7.454 |
liking | -7.350 |
OUNT | -7.263 |
olicy | -7.255 |
Token | ( |
Token ID | 357 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
theless | +3.461 |
ying | +3.219 |
ices | +3.027 |
zin | +2.998 |
lict | +2.944 |
Neg logit contributions | |
Awesome | -3.404 |
motto | -3.388 |
liking | -3.366 |
effectiveness | -3.273 |
olicy | -3.253 |
Token | see |
Token ID | 3826 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Awesome | +1.118 |
liking | +1.117 |
motto | +1.109 |
effectiveness | +1.074 |
worth | +1.072 |
Neg logit contributions | |
theless | -1.245 |
ying | -1.134 |
zin | -1.072 |
ices | -1.071 |
lict | -1.054 |
Token | expects |
Token ID | 13423 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
motto | +0.903 |
liking | +0.901 |
Awesome | +0.897 |
effectiveness | +0.868 |
worth | +0.864 |
Neg logit contributions | |
theless | -1.179 |
ying | -1.090 |
ices | -1.035 |
zin | -1.032 |
lict | -1.017 |
Token | clusters |
Token ID | 23163 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
liking | +1.790 |
motto | +1.780 |
Awesome | +1.752 |
effectiveness | +1.731 |
worth | +1.719 |
Neg logit contributions | |
theless | -3.083 |
ying | -2.869 |
ices | -2.748 |
zin | -2.743 |
lict | -2.703 |
Token | of |
Token ID | 286 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
liking | +0.815 |
motto | +0.808 |
Awesome | +0.805 |
worth | +0.795 |
effectiveness | +0.786 |
Neg logit contributions | |
theless | -0.985 |
ying | -0.900 |
ices | -0.857 |
zin | -0.854 |
lict | -0.841 |
Token | mosquito |
Token ID | 35446 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
theless | +2.186 |
ying | +2.049 |
ices | +1.953 |
zin | +1.941 |
lict | +1.915 |
Neg logit contributions | |
Awesome | -1.367 |
motto | -1.361 |
liking | -1.360 |
effectiveness | -1.298 |
olicy | -1.295 |
Token | - |
Token ID | 12 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
theless | +5.139 |
ying | +4.891 |
ices | +4.535 |
zin | +4.508 |
lict | +4.504 |
Neg logit contributions | |
Awesome | -4.456 |
motto | -4.385 |
liking | -4.349 |
olicy | -4.323 |
OUNT | -4.243 |
Token | trans |
Token ID | 7645 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
theless | +1.197 |
ying | +1.103 |
ices | +1.051 |
zin | +1.045 |
lict | +1.025 |
Neg logit contributions | |
liking | -0.902 |
Awesome | -0.899 |
motto | -0.898 |
effectiveness | -0.869 |
worth | -0.865 |
Token | mitted |
Token ID | 3291 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
ying | +6.457 |
theless | +6.281 |
zin | +5.465 |
lict | +5.386 |
ices | +5.367 |
Neg logit contributions | |
motto | -10.924 |
Awesome | -10.863 |
liking | -10.651 |
olicy | -10.631 |
EGA | -10.543 |
Token | cases |
Token ID | 2663 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
theless | +4.701 |
ying | +4.437 |
ices | +4.144 |
zin | +4.127 |
lict | +4.114 |
Neg logit contributions | |
Awesome | -4.548 |
olicy | -4.446 |
motto | -4.441 |
liking | -4.382 |
OUNT | -4.328 |
Token | in |
Token ID | 287 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
theless | +2.485 |
ying | +2.311 |
ices | +2.195 |
zin | +2.184 |
lict | +2.148 |
Neg logit contributions | |
Awesome | -1.832 |
motto | -1.831 |
liking | -1.829 |
effectiveness | -1.758 |
olicy | -1.741 |
Token | Florida |
Token ID | 4744 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
theless | +0.238 |
ying | +0.222 |
ices | +0.213 |
zin | +0.212 |
lict | +0.209 |
Neg logit contributions | |
liking | -0.134 |
motto | -0.134 |
Awesome | -0.133 |
effectiveness | -0.129 |
worth | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
liking | +1.611 |
motto | +1.590 |
Awesome | +1.588 |
worth | +1.577 |
effectiveness | +1.552 |
Neg logit contributions | |
theless | -2.366 |
ying | -2.174 |
zin | -2.087 |
ices | -2.080 |
lict | -2.042 |
Token | current |
Token ID | 1459 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
theless | +0.603 |
ying | +0.563 |
ices | +0.538 |
zin | +0.536 |
lict | +0.528 |
Neg logit contributions | |
liking | -0.361 |
motto | -0.360 |
Awesome | -0.358 |
effectiveness | -0.345 |
worth | -0.342 |
Token | climate |
Token ID | 4258 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
theless | +0.854 |
ying | +0.797 |
ices | +0.761 |
zin | +0.758 |
lict | +0.747 |
Neg logit contributions | |
liking | -0.511 |
motto | -0.511 |
Awesome | -0.510 |
effectiveness | -0.489 |
worth | -0.485 |
Token | of |
Token ID | 286 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
liking | +0.164 |
motto | +0.164 |
Awesome | +0.164 |
effectiveness | +0.158 |
worth | +0.157 |
Neg logit contributions | |
theless | -0.227 |
ying | -0.210 |
ices | -0.200 |
zin | -0.199 |
lict | -0.196 |
Token | misinformation |
Token ID | 32805 |
Feature activation | +7.55e+00 |
Pos logit contributions | |
theless | +1.707 |
ying | +1.600 |
ices | +1.521 |
zin | +1.517 |
lict | +1.496 |
Neg logit contributions | |
Awesome | -1.049 |
motto | -1.045 |
liking | -1.042 |
effectiveness | -0.994 |
olicy | -0.988 |
Token | around |
Token ID | 1088 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
theless | +6.450 |
ying | +6.282 |
ices | +5.864 |
zin | +5.820 |
lict | +5.785 |
Neg logit contributions | |
Awesome | -5.259 |
motto | -5.194 |
liking | -5.118 |
olicy | -5.069 |
OUNT | -5.002 |
Token | trans |
Token ID | 1007 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
liking | +2.364 |
motto | +2.325 |
Awesome | +2.293 |
effectiveness | +2.274 |
worth | +2.255 |
Neg logit contributions | |
theless | -3.104 |
ying | -2.831 |
ices | -2.719 |
zin | -2.702 |
meyer | -2.662 |
Token | identity |
Token ID | 5369 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
theless | +9.986 |
ying | +9.872 |
ices | +9.227 |
zin | +9.171 |
lict | +9.156 |
Neg logit contributions | |
Awesome | -6.837 |
motto | -6.752 |
liking | -6.672 |
EGA | -6.488 |
olicy | -6.425 |
Token | .) |
Token ID | 2014 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
theless | +4.520 |
ying | +4.291 |
ices | +4.051 |
zin | +4.011 |
lict | +3.982 |
Neg logit contributions | |
Awesome | -3.562 |
motto | -3.523 |
liking | -3.516 |
OUNT | -3.389 |
olicy | -3.364 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
theless | +0.051 |
ying | +0.048 |
ices | +0.045 |
zin | +0.045 |
lict | +0.045 |
Neg logit contributions | |
Awesome | -0.034 |
liking | -0.034 |
motto | -0.034 |
worth | -0.032 |
effectiveness | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
theless | +1.403 |
ying | +1.342 |
ices | +1.270 |
zin | +1.256 |
meyer | +1.230 |
Neg logit contributions | |
motto | -1.179 |
� | -1.167 |
liking | -1.164 |
Awesome | -1.145 |
olicy | -1.131 |
Token | So |
Token ID | 2396 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
theless | +1.294 |
ying | +1.200 |
ices | +1.141 |
zin | +1.136 |
lict | +1.119 |
Neg logit contributions | |
Awesome | -0.937 |
liking | -0.934 |
motto | -0.932 |
effectiveness | -0.897 |
worth | -0.893 |
Token | and |
Token ID | 290 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
motto | +2.376 |
liking | +2.365 |
Awesome | +2.345 |
effectiveness | +2.332 |
worth | +2.326 |
Neg logit contributions | |
theless | -3.103 |
ying | -2.799 |
ices | -2.681 |
zin | -2.674 |
lict | -2.624 |
Token | rare |
Token ID | 4071 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
theless | +0.517 |
ying | +0.489 |
ices | +0.469 |
zin | +0.465 |
lict | +0.460 |
Neg logit contributions | |
Awesome | -0.249 |
liking | -0.249 |
motto | -0.248 |
olicy | -0.234 |
effectiveness | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
theless | +2.956 |
ying | +2.741 |
ices | +2.582 |
zin | +2.564 |
lict | +2.534 |
Neg logit contributions | |
Awesome | -2.744 |
motto | -2.744 |
liking | -2.743 |
olicy | -2.621 |
effectiveness | -2.619 |
Token | � |
Token ID | 447 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
theless | +1.047 |
ying | +0.975 |
ices | +0.928 |
zin | +0.923 |
lict | +0.907 |
Neg logit contributions | |
liking | -0.745 |
motto | -0.744 |
Awesome | -0.741 |
effectiveness | -0.715 |
worth | -0.708 |
Token | � |
Token ID | 251 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
liking | +0.154 |
Awesome | +0.154 |
motto | +0.154 |
effectiveness | +0.150 |
worth | +0.149 |
Neg logit contributions | |
theless | -0.127 |
ying | -0.114 |
ices | -0.107 |
zin | -0.106 |
lict | -0.104 |
Token | Reprodu |
Token ID | 36551 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
Awesome | +0.732 |
liking | +0.731 |
motto | +0.727 |
worth | +0.703 |
effectiveness | +0.701 |
Neg logit contributions | |
theless | -1.053 |
ying | -0.977 |
ices | -0.932 |
zin | -0.927 |
lict | -0.916 |
Token | ctive |
Token ID | 14070 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
ying | +8.457 |
theless | +8.410 |
ices | +7.771 |
lict | +7.719 |
zin | +7.668 |
Neg logit contributions | |
liking | -8.665 |
motto | -8.636 |
Awesome | -8.523 |
OUNT | -8.282 |
� | -8.168 |
Token | rights |
Token ID | 2489 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
theless | +5.505 |
ying | +5.229 |
ices | +4.894 |
lict | +4.832 |
zin | +4.830 |
Neg logit contributions | |
Awesome | -3.926 |
liking | -3.862 |
motto | -3.838 |
OUNT | -3.798 |
EGA | -3.722 |
Token | advocates |
Token ID | 11009 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
theless | +4.939 |
ying | +4.625 |
ices | +4.334 |
zin | +4.312 |
lict | +4.246 |
Neg logit contributions | |
Awesome | -4.931 |
liking | -4.872 |
motto | -4.822 |
olicy | -4.712 |
OUNT | -4.656 |
Token | such |
Token ID | 884 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
liking | +0.170 |
motto | +0.170 |
Awesome | +0.167 |
worth | +0.165 |
effectiveness | +0.165 |
Neg logit contributions | |
theless | -0.171 |
ying | -0.155 |
ices | -0.148 |
zin | -0.146 |
lict | -0.144 |
Token | as |
Token ID | 355 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
theless | +1.330 |
ying | +1.268 |
ices | +1.209 |
zin | +1.201 |
lict | +1.178 |
Neg logit contributions | |
Awesome | -0.759 |
motto | -0.756 |
liking | -0.752 |
olicy | -0.723 |
effectiveness | -0.716 |
Token | to |
Token ID | 284 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
liking | +0.540 |
motto | +0.540 |
Awesome | +0.530 |
effectiveness | +0.521 |
worth | +0.520 |
Neg logit contributions | |
theless | -0.792 |
ying | -0.733 |
ices | -0.695 |
zin | -0.692 |
lict | -0.685 |
Token | the |
Token ID | 262 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
theless | +0.824 |
ying | +0.772 |
ices | +0.737 |
zin | +0.735 |
lict | +0.726 |
Neg logit contributions | |
Awesome | -0.446 |
liking | -0.445 |
motto | -0.445 |
effectiveness | -0.424 |
worth | -0.421 |
Token | successes |
Token ID | 23682 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
theless | +0.972 |
ying | +0.908 |
ices | +0.868 |
zin | +0.865 |
lict | +0.853 |
Neg logit contributions | |
liking | -0.556 |
motto | -0.555 |
Awesome | -0.555 |
effectiveness | -0.531 |
worth | -0.527 |
Token | of |
Token ID | 286 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
theless | +1.193 |
ying | +1.099 |
ices | +1.041 |
zin | +1.036 |
lict | +1.018 |
Neg logit contributions | |
liking | -1.051 |
motto | -1.050 |
Awesome | -1.049 |
effectiveness | -1.015 |
worth | -1.010 |
Token | comparative |
Token ID | 29270 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
theless | +1.753 |
ying | +1.642 |
ices | +1.562 |
zin | +1.560 |
lict | +1.537 |
Neg logit contributions | |
Awesome | -1.092 |
motto | -1.086 |
liking | -1.085 |
effectiveness | -1.039 |
worth | -1.031 |
Token | lingu |
Token ID | 20280 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
liking | +0.186 |
motto | +0.186 |
Awesome | +0.184 |
effectiveness | +0.180 |
worth | +0.179 |
Neg logit contributions | |
theless | -0.244 |
ying | -0.225 |
ices | -0.215 |
zin | -0.213 |
lict | -0.210 |
Token | istics |
Token ID | 3969 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ying | +5.545 |
theless | +5.504 |
ices | +5.113 |
zin | +4.899 |
lict | +4.641 |
Neg logit contributions | |
motto | -11.329 |
liking | -11.269 |
Awesome | -11.178 |
OUNT | -10.885 |
olicy | -10.742 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
theless | +2.416 |
ying | +2.256 |
ices | +2.132 |
zin | +2.123 |
lict | +2.085 |
Neg logit contributions | |
Awesome | -2.031 |
motto | -2.023 |
liking | -2.016 |
effectiveness | -1.942 |
olicy | -1.931 |
Token | it |
Token ID | 340 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
theless | +1.681 |
ying | +1.569 |
ices | +1.493 |
zin | +1.489 |
lict | +1.466 |
Neg logit contributions | |
Awesome | -1.109 |
liking | -1.104 |
motto | -1.104 |
effectiveness | -1.059 |
worth | -1.051 |
Token | had |
Token ID | 550 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
liking | +1.725 |
motto | +1.715 |
worth | +1.683 |
Awesome | +1.672 |
effectiveness | +1.649 |
Neg logit contributions | |
theless | -1.812 |
ying | -1.657 |
ices | -1.570 |
zin | -1.566 |
lict | -1.546 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
theless | +2.502 |
ying | +2.281 |
ices | +2.138 |
zin | +2.126 |
lict | +2.082 |
Neg logit contributions | |
Awesome | -2.894 |
liking | -2.879 |
motto | -2.876 |
effectiveness | -2.790 |
olicy | -2.775 |
Token | recourse |
Token ID | 38424 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
theless | +0.475 |
ying | +0.444 |
ices | +0.425 |
zin | +0.423 |
lict | +0.417 |
Neg logit contributions | |
liking | -0.274 |
motto | -0.273 |
Awesome | -0.273 |
effectiveness | -0.261 |
worth | -0.259 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
theless | +2.263 |
ying | +2.107 |
ices | +1.999 |
zin | +1.988 |
lict | +1.948 |
Neg logit contributions | |
Awesome | -1.779 |
motto | -1.776 |
liking | -1.767 |
effectiveness | -1.699 |
olicy | -1.694 |
Token | without |
Token ID | 1231 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
theless | +1.216 |
ying | +1.134 |
ices | +1.079 |
zin | +1.073 |
lict | +1.057 |
Neg logit contributions | |
Awesome | -0.845 |
motto | -0.844 |
liking | -0.842 |
effectiveness | -0.809 |
worth | -0.802 |
Token | self |
Token ID | 2116 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
theless | +0.590 |
ying | +0.552 |
ices | +0.526 |
zin | +0.524 |
lict | +0.517 |
Neg logit contributions | |
Awesome | -0.353 |
motto | -0.352 |
liking | -0.351 |
effectiveness | -0.336 |
worth | -0.333 |
Token | - |
Token ID | 12 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
theless | +0.004 |
ying | +0.004 |
ices | +0.003 |
zin | +0.003 |
lict | +0.003 |
Neg logit contributions | |
liking | -0.004 |
motto | -0.004 |
Awesome | -0.004 |
effectiveness | -0.004 |
worth | -0.004 |
Token | ref |
Token ID | 5420 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
theless | +1.409 |
ying | +1.310 |
ices | +1.246 |
zin | +1.239 |
lict | +1.221 |
Neg logit contributions | |
motto | -1.026 |
Awesome | -1.026 |
liking | -1.024 |
effectiveness | -0.985 |
worth | -0.975 |
Token | lection |
Token ID | 1564 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
theless | +3.882 |
ying | +3.729 |
ices | +3.121 |
lict | +3.019 |
zin | +2.913 |
Neg logit contributions | |
Awesome | -13.198 |
motto | -13.155 |
liking | -12.854 |
� | -12.728 |
olicy | -12.654 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
theless | +5.761 |
ying | +5.394 |
ices | +5.019 |
zin | +4.974 |
lict | +4.887 |
Neg logit contributions | |
Awesome | -5.691 |
motto | -5.600 |
olicy | -5.518 |
liking | -5.504 |
OUNT | -5.450 |
Token | So |
Token ID | 1406 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
theless | +1.084 |
ying | +1.010 |
ices | +0.962 |
zin | +0.957 |
lict | +0.940 |
Neg logit contributions | |
motto | -0.746 |
liking | -0.746 |
Awesome | -0.742 |
effectiveness | -0.716 |
worth | -0.710 |
Token | through |
Token ID | 832 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
liking | +0.450 |
motto | +0.444 |
Awesome | +0.444 |
worth | +0.428 |
effectiveness | +0.426 |
Neg logit contributions | |
theless | -0.717 |
ying | -0.666 |
ices | -0.636 |
zin | -0.631 |
lict | -0.627 |
Token | that |
Token ID | 326 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
theless | +0.265 |
ying | +0.247 |
ices | +0.237 |
zin | +0.236 |
lict | +0.233 |
Neg logit contributions | |
liking | -0.151 |
motto | -0.150 |
Awesome | -0.150 |
effectiveness | -0.144 |
worth | -0.143 |
Token | it |
Token ID | 340 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
liking | +1.270 |
motto | +1.258 |
Awesome | +1.248 |
effectiveness | +1.213 |
worth | +1.208 |
Neg logit contributions | |
theless | -2.088 |
ying | -1.924 |
ices | -1.856 |
zin | -1.841 |
lict | -1.812 |
Token | seem |
Token ID | 1283 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
motto | +2.355 |
liking | +2.354 |
worth | +2.339 |
Awesome | +2.312 |
effectiveness | +2.275 |
Neg logit contributions | |
theless | -3.566 |
ying | -3.329 |
ices | -3.197 |
zin | -3.181 |
meyer | -3.106 |
Token | like |
Token ID | 588 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
liking | +0.816 |
motto | +0.812 |
Awesome | +0.810 |
worth | +0.785 |
effectiveness | +0.783 |
Neg logit contributions | |
theless | -1.172 |
ying | -1.086 |
ices | -1.038 |
zin | -1.030 |
lict | -1.017 |
Token | � |
Token ID | 564 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
liking | +2.907 |
motto | +2.837 |
Awesome | +2.786 |
worth | +2.760 |
effectiveness | +2.750 |
Neg logit contributions | |
theless | -4.589 |
ying | -4.240 |
ices | -4.088 |
zin | -4.032 |
lict | -4.011 |
Token | � |
Token ID | 250 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
theless | +1.754 |
ying | +1.651 |
ices | +1.556 |
zin | +1.548 |
lict | +1.517 |
Neg logit contributions | |
motto | -1.656 |
Awesome | -1.644 |
liking | -1.643 |
effectiveness | -1.594 |
olicy | -1.581 |
Token | trans |
Token ID | 7645 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
theless | +0.445 |
ying | +0.411 |
ices | +0.389 |
zin | +0.387 |
lict | +0.381 |
Neg logit contributions | |
Awesome | -0.372 |
liking | -0.372 |
motto | -0.370 |
effectiveness | -0.358 |
worth | -0.356 |
Token | gender |
Token ID | 8388 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
theless | +8.199 |
ying | +7.850 |
ices | +7.312 |
zin | +7.158 |
lict | +7.025 |
Neg logit contributions | |
Awesome | -8.669 |
motto | -8.603 |
liking | -8.531 |
EGA | -8.332 |
olicy | -8.327 |
Token | ism |
Token ID | 1042 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
theless | +3.548 |
ying | +3.293 |
ices | +3.116 |
zin | +3.097 |
lict | +3.044 |
Neg logit contributions | |
Awesome | -2.951 |
motto | -2.931 |
liking | -2.921 |
olicy | -2.818 |
effectiveness | -2.810 |
Token | � |
Token ID | 447 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
theless | +1.514 |
ying | +1.403 |
ices | +1.332 |
zin | +1.325 |
lict | +1.304 |
Neg logit contributions | |
liking | -1.180 |
Awesome | -1.180 |
motto | -1.179 |
effectiveness | -1.136 |
worth | -1.128 |
Token | � |
Token ID | 251 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
liking | +1.445 |
motto | +1.443 |
Awesome | +1.441 |
effectiveness | +1.402 |
worth | +1.398 |
Neg logit contributions | |
theless | -1.311 |
ying | -1.185 |
ices | -1.114 |
zin | -1.108 |
lict | -1.087 |
Token | is |
Token ID | 318 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
liking | +0.817 |
motto | +0.815 |
Awesome | +0.805 |
worth | +0.790 |
effectiveness | +0.786 |
Neg logit contributions | |
theless | -1.097 |
ying | -1.010 |
ices | -0.963 |
zin | -0.961 |
lict | -0.946 |
Token | za |
Token ID | 4496 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
liking | +1.109 |
Awesome | +1.108 |
motto | +1.106 |
effectiveness | +1.079 |
worth | +1.078 |
Neg logit contributions | |
theless | -0.881 |
ying | -0.790 |
ices | -0.738 |
zin | -0.728 |
lict | -0.718 |
Token | as |
Token ID | 355 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
theless | +0.535 |
ying | +0.501 |
ices | +0.480 |
zin | +0.478 |
lict | +0.471 |
Neg logit contributions | |
liking | -0.287 |
Awesome | -0.286 |
motto | -0.286 |
effectiveness | -0.273 |
worth | -0.271 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
motto | +1.699 |
liking | +1.687 |
worth | +1.650 |
Awesome | +1.641 |
effectiveness | +1.623 |
Neg logit contributions | |
theless | -4.061 |
ying | -3.752 |
ices | -3.628 |
zin | -3.626 |
meyer | -3.533 |
Token | � |
Token ID | 564 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
theless | +1.321 |
ying | +1.226 |
ices | +1.164 |
zin | +1.160 |
lict | +1.141 |
Neg logit contributions | |
Awesome | -1.014 |
liking | -1.013 |
motto | -1.012 |
effectiveness | -0.974 |
worth | -0.967 |
Token | � |
Token ID | 250 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
theless | +1.881 |
ying | +1.765 |
ices | +1.665 |
zin | +1.654 |
lict | +1.637 |
Neg logit contributions | |
motto | -1.787 |
Awesome | -1.774 |
liking | -1.773 |
effectiveness | -1.707 |
olicy | -1.699 |
Token | trans |
Token ID | 7645 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
theless | +0.522 |
ying | +0.481 |
ices | +0.457 |
zin | +0.455 |
lict | +0.446 |
Neg logit contributions | |
Awesome | -0.414 |
liking | -0.414 |
motto | -0.413 |
effectiveness | -0.399 |
worth | -0.398 |
Token | national |
Token ID | 14648 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
theless | +6.809 |
ying | +6.556 |
lict | +5.875 |
zin | +5.872 |
ices | +5.679 |
Neg logit contributions | |
liking | -9.956 |
Awesome | -9.874 |
motto | -9.827 |
olicy | -9.463 |
effectiveness | -9.420 |
Token | criminal |
Token ID | 4301 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
theless | +0.322 |
ying | +0.298 |
ices | +0.283 |
zin | +0.281 |
lict | +0.277 |
Neg logit contributions | |
liking | -0.254 |
motto | -0.253 |
Awesome | -0.253 |
effectiveness | -0.244 |
worth | -0.243 |
Token | organization |
Token ID | 4009 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
theless | +0.949 |
ying | +0.895 |
ices | +0.861 |
zin | +0.857 |
lict | +0.847 |
Neg logit contributions | |
liking | -0.365 |
motto | -0.363 |
Awesome | -0.362 |
effectiveness | -0.343 |
worth | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
liking | +0.923 |
motto | +0.919 |
Awesome | +0.913 |
worth | +0.900 |
effectiveness | +0.888 |
Neg logit contributions | |
theless | -1.196 |
ying | -1.103 |
ices | -1.051 |
zin | -1.043 |
lict | -1.025 |
Token | � |
Token ID | 447 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
theless | +0.660 |
ying | +0.614 |
ices | +0.585 |
zin | +0.582 |
lict | +0.573 |
Neg logit contributions | |
liking | -0.450 |
motto | -0.449 |
Awesome | -0.449 |
effectiveness | -0.431 |
worth | -0.428 |
Token | But |
Token ID | 1537 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
theless | +0.632 |
ying | +0.586 |
ices | +0.558 |
zin | +0.556 |
lict | +0.547 |
Neg logit contributions | |
Awesome | -0.453 |
liking | -0.452 |
motto | -0.451 |
effectiveness | -0.434 |
worth | -0.432 |
Token | a |
Token ID | 257 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
liking | +0.730 |
motto | +0.724 |
Awesome | +0.721 |
effectiveness | +0.700 |
worth | +0.698 |
Neg logit contributions | |
theless | -1.172 |
ying | -1.090 |
ices | -1.046 |
zin | -1.039 |
lict | -1.023 |
Token | few |
Token ID | 1178 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
theless | +2.742 |
ying | +2.561 |
ices | +2.435 |
zin | +2.430 |
lict | +2.393 |
Neg logit contributions | |
Awesome | -1.722 |
liking | -1.712 |
motto | -1.710 |
effectiveness | -1.641 |
olicy | -1.630 |
Token | non |
Token ID | 1729 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
theless | +2.742 |
ying | +2.557 |
ices | +2.433 |
zin | +2.427 |
lict | +2.387 |
Neg logit contributions | |
Awesome | -1.823 |
liking | -1.818 |
motto | -1.814 |
effectiveness | -1.737 |
olicy | -1.732 |
Token | - |
Token ID | 12 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
theless | +4.223 |
ying | +3.906 |
ices | +3.645 |
zin | +3.626 |
lict | +3.573 |
Neg logit contributions | |
Awesome | -4.769 |
motto | -4.760 |
liking | -4.754 |
OUNT | -4.612 |
olicy | -4.589 |
Token | ne |
Token ID | 710 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
theless | +1.833 |
ying | +1.707 |
ices | +1.626 |
zin | +1.619 |
lict | +1.595 |
Neg logit contributions | |
liking | -1.233 |
motto | -1.233 |
Awesome | -1.229 |
effectiveness | -1.183 |
worth | -1.174 |
Token | ur |
Token ID | 333 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
theless | +8.548 |
ying | +8.353 |
ices | +7.821 |
lict | +7.622 |
zin | +7.577 |
Neg logit contributions | |
liking | -8.302 |
motto | -8.261 |
Awesome | -8.207 |
� | -8.014 |
OUNT | -7.989 |
Token | om |
Token ID | 296 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
theless | +0.073 |
ying | +0.064 |
ices | +0.059 |
zin | +0.059 |
lict | +0.057 |
Neg logit contributions | |
liking | -0.124 |
Awesome | -0.124 |
motto | -0.124 |
effectiveness | -0.122 |
worth | -0.121 |
Token | od |
Token ID | 375 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
Awesome | +1.749 |
motto | +1.727 |
liking | +1.726 |
olicy | +1.702 |
worth | +1.702 |
Neg logit contributions | |
theless | -1.345 |
ying | -1.184 |
zin | -1.106 |
ices | -1.101 |
meyer | -1.081 |
Token | weapons |
Token ID | 3777 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
theless | +3.788 |
ying | +3.565 |
ices | +3.365 |
zin | +3.342 |
lict | +3.307 |
Neg logit contributions | |
motto | -2.461 |
Awesome | -2.459 |
liking | -2.449 |
olicy | -2.354 |
OUNT | -2.353 |
Token | are |
Token ID | 389 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
theless | +0.359 |
ying | +0.329 |
ices | +0.311 |
zin | +0.310 |
lict | +0.304 |
Neg logit contributions | |
liking | -0.342 |
motto | -0.341 |
Awesome | -0.340 |
effectiveness | -0.331 |
worth | -0.330 |
Token | The |
Token ID | 464 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Awesome | +0.173 |
liking | +0.171 |
motto | +0.171 |
effectiveness | +0.164 |
worth | +0.164 |
Neg logit contributions | |
theless | -0.239 |
ying | -0.220 |
ices | -0.209 |
zin | -0.209 |
lict | -0.206 |
Token | Android |
Token ID | 5565 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
theless | +1.015 |
ying | +0.944 |
ices | +0.899 |
zin | +0.895 |
lict | +0.882 |
Neg logit contributions | |
Awesome | -0.685 |
liking | -0.685 |
motto | -0.685 |
effectiveness | -0.658 |
worth | -0.653 |
Token | Market |
Token ID | 5991 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
motto | +1.247 |
liking | +1.246 |
Awesome | +1.245 |
effectiveness | +1.195 |
worth | +1.191 |
Neg logit contributions | |
theless | -1.760 |
ying | -1.632 |
ices | -1.549 |
zin | -1.544 |
lict | -1.530 |
Token | 's |
Token ID | 338 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Awesome | +3.484 |
motto | +3.467 |
liking | +3.464 |
worth | +3.399 |
effectiveness | +3.351 |
Neg logit contributions | |
theless | -5.367 |
ying | -4.963 |
zin | -4.694 |
lict | -4.676 |
ices | -4.658 |
Token | a |
Token ID | 257 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
liking | +1.924 |
motto | +1.918 |
Awesome | +1.911 |
worth | +1.855 |
effectiveness | +1.841 |
Neg logit contributions | |
theless | -2.784 |
ying | -2.573 |
ices | -2.458 |
zin | -2.450 |
lict | -2.426 |
Token | big |
Token ID | 1263 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
theless | +0.751 |
ying | +0.694 |
ices | +0.664 |
zin | +0.659 |
lict | +0.651 |
Neg logit contributions | |
Awesome | -0.517 |
liking | -0.516 |
motto | -0.514 |
worth | -0.495 |
effectiveness | -0.492 |
Token | place |
Token ID | 1295 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
liking | +7.478 |
investment | +7.416 |
worth | +7.284 |
motto | +7.196 |
Awesome | +7.107 |
Neg logit contributions | |
theless | -10.845 |
ying | -9.598 |
ices | -9.552 |
zin | -9.463 |
lict | -9.349 |
Token | , |
Token ID | 11 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
liking | +1.370 |
motto | +1.350 |
Awesome | +1.344 |
worth | +1.312 |
effectiveness | +1.290 |
Neg logit contributions | |
theless | -2.079 |
ying | -1.917 |
ices | -1.832 |
zin | -1.827 |
lict | -1.798 |
Token | and |
Token ID | 290 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
liking | +0.309 |
motto | +0.309 |
Awesome | +0.308 |
effectiveness | +0.297 |
worth | +0.296 |
Neg logit contributions | |
theless | -0.399 |
ying | -0.369 |
ices | -0.351 |
zin | -0.349 |
lict | -0.343 |
Token | we |
Token ID | 356 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
liking | +0.381 |
motto | +0.381 |
Awesome | +0.381 |
effectiveness | +0.365 |
worth | +0.362 |
Neg logit contributions | |
theless | -0.646 |
ying | -0.603 |
ices | -0.576 |
zin | -0.574 |
lict | -0.566 |
Token | 're |
Token ID | 821 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
theless | +0.835 |
ying | +0.766 |
ices | +0.728 |
zin | +0.724 |
lict | +0.714 |
Neg logit contributions | |
liking | -0.711 |
motto | -0.709 |
Awesome | -0.704 |
worth | -0.684 |
effectiveness | -0.683 |
Token | t |
Token ID | 83 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
liking | +1.010 |
Awesome | +1.005 |
motto | +1.000 |
worth | +0.959 |
effectiveness | +0.959 |
Neg logit contributions | |
theless | -1.874 |
ying | -1.741 |
zin | -1.668 |
ices | -1.665 |
lict | -1.643 |
Token | see |
Token ID | 766 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
theless | +0.789 |
ying | +0.720 |
ices | +0.683 |
zin | +0.679 |
lict | +0.667 |
Neg logit contributions | |
liking | -0.754 |
motto | -0.751 |
Awesome | -0.748 |
effectiveness | -0.726 |
worth | -0.725 |
Token | it |
Token ID | 340 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
theless | +0.721 |
ying | +0.674 |
ices | +0.644 |
zin | +0.642 |
lict | +0.633 |
Neg logit contributions | |
motto | -0.405 |
Awesome | -0.405 |
liking | -0.405 |
effectiveness | -0.387 |
worth | -0.384 |
Token | being |
Token ID | 852 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
liking | +2.077 |
Awesome | +1.989 |
motto | +1.981 |
worth | +1.965 |
effectiveness | +1.933 |
Neg logit contributions | |
theless | -3.811 |
ying | -3.531 |
ices | -3.408 |
zin | -3.388 |
meyer | -3.351 |
Token | a |
Token ID | 257 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
liking | +1.123 |
motto | +1.118 |
Awesome | +1.112 |
worth | +1.085 |
effectiveness | +1.077 |
Neg logit contributions | |
theless | -2.031 |
ying | -1.894 |
zin | -1.815 |
ices | -1.813 |
lict | -1.782 |
Token | big |
Token ID | 1263 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
theless | +0.778 |
ying | +0.725 |
ices | +0.692 |
zin | +0.688 |
lict | +0.678 |
Neg logit contributions | |
liking | -0.505 |
motto | -0.504 |
Awesome | -0.502 |
effectiveness | -0.483 |
worth | -0.481 |
Token | issue |
Token ID | 2071 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
liking | +6.761 |
investment | +6.634 |
motto | +6.469 |
worth | +6.369 |
effectiveness | +6.249 |
Neg logit contributions | |
theless | -10.777 |
ices | -9.843 |
ying | -9.743 |
zin | -9.700 |
meyer | -9.547 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
liking | +0.595 |
motto | +0.591 |
Awesome | +0.590 |
effectiveness | +0.569 |
worth | +0.568 |
Neg logit contributions | |
theless | -0.903 |
ying | -0.837 |
ices | -0.800 |
zin | -0.796 |
lict | -0.785 |
Token | The |
Token ID | 383 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
liking | +0.134 |
Awesome | +0.134 |
motto | +0.134 |
effectiveness | +0.128 |
worth | +0.128 |
Neg logit contributions | |
theless | -0.202 |
ying | -0.188 |
ices | -0.179 |
zin | -0.178 |
lict | -0.176 |
Token | power |
Token ID | 1176 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
theless | +0.628 |
ying | +0.589 |
ices | +0.564 |
zin | +0.560 |
lict | +0.553 |
Neg logit contributions | |
Awesome | -0.328 |
liking | -0.326 |
motto | -0.326 |
effectiveness | -0.310 |
olicy | -0.308 |
Token | delivery |
Token ID | 7585 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
liking | +3.035 |
motto | +3.035 |
Awesome | +2.990 |
effectiveness | +2.972 |
worth | +2.923 |
Neg logit contributions | |
theless | -4.487 |
ying | -4.060 |
zin | -3.915 |
ices | -3.895 |
lict | -3.827 |
Token | . |
Token ID | 13 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
liking | +4.485 |
worth | +4.418 |
Awesome | +4.402 |
motto | +4.388 |
effectiveness | +4.347 |
Neg logit contributions | |
theless | -5.652 |
ying | -5.099 |
ices | -4.826 |
zin | -4.789 |
lict | -4.783 |
Token | But |
Token ID | 887 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
theless | +0.549 |
ying | +0.512 |
ices | +0.488 |
zin | +0.484 |
lict | +0.475 |
Neg logit contributions | |
liking | -0.400 |
motto | -0.400 |
Awesome | -0.398 |
effectiveness | -0.384 |
worth | -0.380 |
Token | Trump |
Token ID | 1301 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
liking | +0.829 |
motto | +0.825 |
Awesome | +0.823 |
effectiveness | +0.793 |
worth | +0.790 |
Neg logit contributions | |
theless | -1.359 |
ying | -1.266 |
ices | -1.211 |
zin | -1.206 |
lict | -1.189 |
Token | is |
Token ID | 318 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
liking | +0.279 |
motto | +0.279 |
Awesome | +0.279 |
effectiveness | +0.269 |
worth | +0.268 |
Neg logit contributions | |
theless | -0.352 |
ying | -0.325 |
ices | -0.309 |
zin | -0.307 |
lict | -0.302 |
Token | also |
Token ID | 635 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
liking | +0.629 |
motto | +0.627 |
Awesome | +0.626 |
effectiveness | +0.600 |
worth | +0.599 |
Neg logit contributions | |
theless | -1.063 |
ying | -0.992 |
ices | -0.948 |
zin | -0.944 |
lict | -0.931 |
Token | big |
Token ID | 1263 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
Awesome | +0.173 |
motto | +0.172 |
liking | +0.172 |
effectiveness | +0.164 |
olicy | +0.162 |
Neg logit contributions | |
theless | -0.332 |
ying | -0.312 |
ices | -0.298 |
zin | -0.297 |
lict | -0.293 |
Token | in |
Token ID | 287 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
liking | +6.623 |
worth | +6.564 |
investment | +6.549 |
motto | +6.390 |
Awesome | +6.211 |
Neg logit contributions | |
theless | -11.145 |
ices | -9.711 |
ying | -9.623 |
zin | -9.541 |
lict | -9.351 |
Token | golf |
Token ID | 13126 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
liking | +0.838 |
motto | +0.837 |
Awesome | +0.834 |
effectiveness | +0.798 |
worth | +0.793 |
Neg logit contributions | |
theless | -1.642 |
ying | -1.535 |
ices | -1.473 |
zin | -1.466 |
lict | -1.447 |
Token | courses |
Token ID | 10902 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
liking | +1.119 |
motto | +1.112 |
Awesome | +1.100 |
worth | +1.076 |
effectiveness | +1.072 |
Neg logit contributions | |
theless | -1.478 |
ying | -1.353 |
zin | -1.292 |
ices | -1.291 |
lict | -1.274 |
Token | , |
Token ID | 11 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
theless | +0.315 |
ying | +0.290 |
ices | +0.274 |
zin | +0.273 |
lict | +0.268 |
Neg logit contributions | |
liking | -0.284 |
motto | -0.284 |
Awesome | -0.284 |
effectiveness | -0.275 |
worth | -0.272 |
Token | where |
Token ID | 810 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
theless | +0.586 |
ying | +0.549 |
ices | +0.520 |
zin | +0.517 |
lict | +0.510 |
Neg logit contributions | |
Awesome | -0.412 |
motto | -0.408 |
liking | -0.407 |
effectiveness | -0.392 |
olicy | -0.390 |
Token | turned |
Token ID | 2900 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
liking | +1.774 |
motto | +1.761 |
worth | +1.731 |
Awesome | +1.719 |
effectiveness | +1.692 |
Neg logit contributions | |
theless | -2.393 |
ying | -2.213 |
zin | -2.119 |
ices | -2.107 |
lict | -2.079 |
Token | out |
Token ID | 503 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
liking | +1.264 |
Awesome | +1.262 |
motto | +1.261 |
effectiveness | +1.212 |
worth | +1.211 |
Neg logit contributions | |
theless | -2.031 |
ying | -1.882 |
ices | -1.801 |
zin | -1.792 |
lict | -1.769 |
Token | , |
Token ID | 11 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
liking | +1.299 |
motto | +1.297 |
Awesome | +1.290 |
effectiveness | +1.254 |
worth | +1.253 |
Neg logit contributions | |
theless | -1.478 |
ying | -1.350 |
ices | -1.278 |
zin | -1.272 |
lict | -1.255 |
Token | was |
Token ID | 373 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
liking | +0.072 |
motto | +0.072 |
Awesome | +0.071 |
worth | +0.069 |
effectiveness | +0.069 |
Neg logit contributions | |
theless | -0.088 |
ying | -0.081 |
zin | -0.077 |
ices | -0.077 |
lict | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
liking | +1.346 |
Awesome | +1.345 |
motto | +1.340 |
worth | +1.307 |
effectiveness | +1.286 |
Neg logit contributions | |
theless | -2.338 |
ying | -2.166 |
zin | -2.074 |
ices | -2.067 |
lict | -2.046 |
Token | big |
Token ID | 1263 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
theless | +1.626 |
ying | +1.522 |
ices | +1.451 |
zin | +1.445 |
lict | +1.424 |
Neg logit contributions | |
Awesome | -0.982 |
liking | -0.977 |
motto | -0.975 |
effectiveness | -0.937 |
olicy | -0.927 |
Token | mistake |
Token ID | 7457 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
liking | +6.653 |
investment | +6.646 |
motto | +6.602 |
worth | +6.476 |
Awesome | +6.230 |
Neg logit contributions | |
theless | -10.890 |
ying | -9.528 |
zin | -9.481 |
ices | -9.441 |
lict | -9.319 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
theless | +0.008 |
ying | +0.007 |
ices | +0.007 |
zin | +0.007 |
lict | +0.006 |
Neg logit contributions | |
liking | -0.007 |
motto | -0.007 |
Awesome | -0.007 |
effectiveness | -0.007 |
worth | -0.007 |
Token | Hitchcock |
Token ID | 49817 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
Awesome | +0.154 |
liking | +0.153 |
motto | +0.153 |
effectiveness | +0.147 |
worth | +0.147 |
Neg logit contributions | |
theless | -0.212 |
ying | -0.196 |
ices | -0.186 |
zin | -0.186 |
lict | -0.184 |
Token | shot |
Token ID | 2823 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
theless | +3.086 |
ying | +2.863 |
ices | +2.708 |
zin | +2.689 |
lict | +2.633 |
Neg logit contributions | |
Awesome | -2.626 |
motto | -2.613 |
liking | -2.602 |
effectiveness | -2.519 |
olicy | -2.493 |
Token | everything |
Token ID | 2279 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
liking | +1.257 |
Awesome | +1.257 |
motto | +1.234 |
worth | +1.201 |
effectiveness | +1.200 |
Neg logit contributions | |
theless | -2.644 |
ying | -2.463 |
ices | -2.369 |
zin | -2.365 |
lict | -2.334 |
Token | , |
Token ID | 11 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
theless | +2.660 |
ying | +2.466 |
zin | +2.323 |
ices | +2.321 |
lict | +2.259 |
Neg logit contributions | |
Awesome | -2.517 |
motto | -2.497 |
liking | -2.491 |
effectiveness | -2.423 |
olicy | -2.400 |
Token | New |
Token ID | 968 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
theless | +0.652 |
ying | +0.610 |
ices | +0.582 |
zin | +0.579 |
lict | +0.571 |
Neg logit contributions | |
Awesome | -0.397 |
motto | -0.396 |
liking | -0.395 |
effectiveness | -0.379 |
worth | -0.376 |
Token | Orleans |
Token ID | 12255 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
theless | +3.086 |
ying | +2.862 |
ices | +2.692 |
zin | +2.690 |
lict | +2.640 |
Neg logit contributions | |
Awesome | -2.970 |
liking | -2.959 |
motto | -2.942 |
effectiveness | -2.864 |
OUNT | -2.836 |
Token | is |
Token ID | 318 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
theless | +0.388 |
ying | +0.360 |
ices | +0.342 |
zin | +0.340 |
lict | +0.335 |
Neg logit contributions | |
liking | -0.291 |
motto | -0.291 |
Awesome | -0.291 |
effectiveness | -0.280 |
worth | -0.279 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
liking | +0.804 |
motto | +0.801 |
Awesome | +0.797 |
worth | +0.770 |
effectiveness | +0.760 |
Neg logit contributions | |
theless | -1.443 |
ying | -1.345 |
ices | -1.289 |
zin | -1.285 |
lict | -1.263 |
Token | big |
Token ID | 1263 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
theless | +1.426 |
ying | +1.330 |
ices | +1.271 |
zin | +1.265 |
lict | +1.246 |
Neg logit contributions | |
liking | -0.869 |
motto | -0.868 |
Awesome | -0.866 |
effectiveness | -0.830 |
worth | -0.826 |
Token | hub |
Token ID | 12575 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
liking | +6.227 |
motto | +6.184 |
investment | +6.144 |
worth | +5.985 |
Awesome | +5.651 |
Neg logit contributions | |
theless | -11.057 |
ices | -10.073 |
ying | -10.003 |
zin | -9.840 |
meyer | -9.551 |
Token | for |
Token ID | 329 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
liking | +2.902 |
motto | +2.879 |
worth | +2.872 |
Awesome | +2.848 |
effectiveness | +2.732 |
Neg logit contributions | |
theless | -5.281 |
ying | -4.860 |
ices | -4.672 |
zin | -4.633 |
lict | -4.527 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
liking | +1.437 |
motto | +1.421 |
Awesome | +1.400 |
effectiveness | +1.364 |
worth | +1.361 |
Neg logit contributions | |
theless | -2.537 |
ying | -2.355 |
ices | -2.271 |
zin | -2.246 |
lict | -2.217 |
Token | families |
Token ID | 4172 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
theless | +3.156 |
ying | +2.971 |
ices | +2.845 |
zin | +2.837 |
lict | +2.793 |
Neg logit contributions | |
Awesome | -1.610 |
liking | -1.595 |
motto | -1.593 |
effectiveness | -1.519 |
olicy | -1.516 |
Token | , |
Token ID | 11 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
theless | +2.605 |
ying | +2.442 |
ices | +2.303 |
zin | +2.302 |
lict | +2.256 |
Neg logit contributions | |
Awesome | -2.202 |
motto | -2.187 |
liking | -2.173 |
effectiveness | -2.120 |
olicy | -2.112 |
Token | He |
Token ID | 679 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Awesome | +0.781 |
liking | +0.771 |
motto | +0.770 |
worth | +0.740 |
effectiveness | +0.733 |
Neg logit contributions | |
theless | -1.250 |
ying | -1.157 |
zin | -1.099 |
ices | -1.097 |
lict | -1.094 |
Token | � |
Token ID | 447 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
liking | +0.170 |
motto | +0.169 |
Awesome | +0.169 |
worth | +0.163 |
effectiveness | +0.162 |
Neg logit contributions | |
theless | -0.230 |
ying | -0.212 |
ices | -0.201 |
zin | -0.201 |
lict | -0.199 |
Token | � |
Token ID | 247 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
motto | +0.425 |
liking | +0.425 |
Awesome | +0.425 |
effectiveness | +0.410 |
worth | +0.407 |
Neg logit contributions | |
theless | -0.526 |
ying | -0.488 |
ices | -0.462 |
zin | -0.460 |
lict | -0.453 |
Token | s |
Token ID | 82 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
liking | +0.939 |
Awesome | +0.937 |
motto | +0.934 |
worth | +0.904 |
effectiveness | +0.902 |
Neg logit contributions | |
theless | -1.022 |
ying | -0.935 |
zin | -0.882 |
ices | -0.877 |
lict | -0.873 |
Token | a |
Token ID | 257 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
liking | +2.175 |
Awesome | +2.145 |
motto | +2.138 |
worth | +2.093 |
effectiveness | +2.038 |
Neg logit contributions | |
theless | -3.357 |
ying | -3.079 |
ices | -2.960 |
zin | -2.945 |
lict | -2.926 |
Token | big |
Token ID | 1263 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
theless | +0.236 |
ying | +0.219 |
ices | +0.209 |
zin | +0.207 |
lict | +0.205 |
Neg logit contributions | |
liking | -0.169 |
motto | -0.168 |
Awesome | -0.168 |
effectiveness | -0.162 |
worth | -0.161 |
Token | theater |
Token ID | 13766 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
liking | +7.014 |
motto | +6.758 |
Awesome | +6.603 |
worth | +6.572 |
investment | +6.525 |
Neg logit contributions | |
theless | -10.191 |
ices | -9.194 |
ying | -9.142 |
lict | -8.965 |
zin | -8.838 |
Token | guy |
Token ID | 3516 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
theless | +0.592 |
ying | +0.548 |
ices | +0.526 |
zin | +0.521 |
lict | +0.514 |
Neg logit contributions | |
liking | -0.380 |
Awesome | -0.380 |
motto | -0.379 |
effectiveness | -0.364 |
worth | -0.362 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
liking | +2.235 |
motto | +2.187 |
Awesome | +2.187 |
worth | +2.160 |
effectiveness | +2.098 |
Neg logit contributions | |
theless | -2.629 |
ying | -2.366 |
ices | -2.266 |
zin | -2.236 |
lict | -2.230 |
Token | Patrick |
Token ID | 9925 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
Awesome | +0.837 |
liking | +0.827 |
motto | +0.823 |
worth | +0.791 |
effectiveness | +0.784 |
Neg logit contributions | |
theless | -1.372 |
ying | -1.270 |
ices | -1.207 |
zin | -1.207 |
lict | -1.202 |
Token | sings |
Token ID | 33041 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
liking | +0.056 |
motto | +0.056 |
Awesome | +0.056 |
worth | +0.054 |
effectiveness | +0.054 |
Neg logit contributions | |
theless | -0.079 |
ying | -0.073 |
ices | -0.069 |
zin | -0.069 |
lict | -0.068 |
Token | incidents |
Token ID | 10207 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
liking | +0.952 |
motto | +0.947 |
Awesome | +0.933 |
worth | +0.922 |
effectiveness | +0.920 |
Neg logit contributions | |
theless | -1.400 |
ying | -1.285 |
ices | -1.229 |
zin | -1.225 |
lict | -1.205 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
theless | +3.625 |
ying | +3.398 |
ices | +3.202 |
zin | +3.192 |
lict | +3.122 |
Neg logit contributions | |
Awesome | -2.997 |
motto | -2.962 |
liking | -2.932 |
olicy | -2.868 |
effectiveness | -2.845 |
Token | Fraud |
Token ID | 39826 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
Awesome | +0.059 |
liking | +0.059 |
motto | +0.059 |
effectiveness | +0.057 |
worth | +0.057 |
Neg logit contributions | |
theless | -0.088 |
ying | -0.081 |
ices | -0.078 |
zin | -0.077 |
lict | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
theless | +3.248 |
ying | +3.017 |
ices | +2.861 |
zin | +2.827 |
lict | +2.774 |
Neg logit contributions | |
motto | -2.863 |
Awesome | -2.861 |
liking | -2.859 |
effectiveness | -2.747 |
worth | -2.722 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
liking | +1.090 |
motto | +1.083 |
Awesome | +1.074 |
worth | +1.050 |
effectiveness | +1.037 |
Neg logit contributions | |
theless | -1.971 |
ying | -1.831 |
ices | -1.761 |
zin | -1.757 |
lict | -1.732 |
Token | big |
Token ID | 1263 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
theless | +1.334 |
ying | +1.240 |
ices | +1.181 |
zin | +1.176 |
lict | +1.158 |
Neg logit contributions | |
liking | -0.921 |
Awesome | -0.920 |
motto | -0.920 |
effectiveness | -0.884 |
worth | -0.878 |
Token | problem |
Token ID | 1917 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
investment | +6.453 |
motto | +6.371 |
worth | +6.274 |
liking | +6.216 |
effectiveness | +5.998 |
Neg logit contributions | |
theless | -10.638 |
ying | -9.699 |
zin | -9.593 |
ices | -9.542 |
meyer | -9.254 |
Token | . |
Token ID | 13 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
liking | +0.530 |
motto | +0.529 |
Awesome | +0.528 |
effectiveness | +0.510 |
worth | +0.508 |
Neg logit contributions | |
theless | -0.662 |
ying | -0.612 |
ices | -0.582 |
zin | -0.578 |
lict | -0.569 |
Token | People |
Token ID | 4380 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
Awesome | +0.316 |
liking | +0.315 |
motto | +0.315 |
effectiveness | +0.303 |
worth | +0.302 |
Neg logit contributions | |
theless | -0.478 |
ying | -0.443 |
ices | -0.422 |
zin | -0.421 |
lict | -0.417 |
Token | trying |
Token ID | 2111 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
theless | +3.466 |
ying | +3.219 |
ices | +3.012 |
zin | +2.995 |
lict | +2.920 |
Neg logit contributions | |
Awesome | -3.359 |
motto | -3.312 |
liking | -3.281 |
effectiveness | -3.211 |
olicy | -3.211 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
liking | +0.691 |
motto | +0.688 |
Awesome | +0.685 |
worth | +0.667 |
effectiveness | +0.665 |
Neg logit contributions | |
theless | -1.051 |
ying | -0.962 |
zin | -0.918 |
ices | -0.915 |
lict | -0.908 |
Token | talent |
Token ID | 7401 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
liking | +1.566 |
motto | +1.564 |
Awesome | +1.521 |
effectiveness | +1.499 |
worth | +1.480 |
Neg logit contributions | |
theless | -2.897 |
ying | -2.703 |
ices | -2.601 |
zin | -2.590 |
lict | -2.558 |
Token | for |
Token ID | 329 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
liking | +0.065 |
motto | +0.065 |
Awesome | +0.065 |
effectiveness | +0.062 |
worth | +0.062 |
Neg logit contributions | |
theless | -0.101 |
ying | -0.094 |
ices | -0.090 |
zin | -0.089 |
lict | -0.088 |
Token | disruption |
Token ID | 19911 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
liking | +1.279 |
motto | +1.268 |
Awesome | +1.256 |
effectiveness | +1.221 |
worth | +1.204 |
Neg logit contributions | |
theless | -2.383 |
ying | -2.218 |
ices | -2.139 |
zin | -2.123 |
lict | -2.098 |
Token | is |
Token ID | 318 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
theless | +1.961 |
ying | +1.821 |
ices | +1.725 |
zin | +1.715 |
lict | +1.688 |
Neg logit contributions | |
Awesome | -1.562 |
liking | -1.547 |
motto | -1.546 |
olicy | -1.484 |
effectiveness | -1.483 |
Token | a |
Token ID | 257 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
liking | +0.482 |
motto | +0.481 |
Awesome | +0.481 |
effectiveness | +0.461 |
worth | +0.458 |
Neg logit contributions | |
theless | -0.805 |
ying | -0.752 |
ices | -0.718 |
zin | -0.715 |
lict | -0.705 |
Token | big |
Token ID | 1263 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
theless | +2.097 |
ying | +1.957 |
ices | +1.864 |
zin | +1.860 |
lict | +1.831 |
Neg logit contributions | |
Awesome | -1.307 |
liking | -1.306 |
motto | -1.304 |
effectiveness | -1.251 |
worth | -1.240 |
Token | part |
Token ID | 636 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
liking | +6.436 |
investment | +6.288 |
worth | +6.251 |
motto | +6.250 |
effectiveness | +5.995 |
Neg logit contributions | |
theless | -10.806 |
ices | -9.655 |
ying | -9.541 |
zin | -9.383 |
meyer | -9.374 |
Token | of |
Token ID | 286 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
liking | +1.105 |
motto | +1.104 |
Awesome | +1.098 |
worth | +1.071 |
effectiveness | +1.069 |
Neg logit contributions | |
theless | -1.272 |
ying | -1.158 |
ices | -1.104 |
zin | -1.093 |
lict | -1.079 |
Token | his |
Token ID | 465 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
theless | +0.946 |
ying | +0.890 |
ices | +0.848 |
zin | +0.846 |
lict | +0.834 |
Neg logit contributions | |
Awesome | -0.502 |
motto | -0.501 |
liking | -0.499 |
effectiveness | -0.474 |
olicy | -0.472 |
Token | appeal |
Token ID | 5198 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
liking | +2.939 |
motto | +2.906 |
effectiveness | +2.851 |
Awesome | +2.813 |
worth | +2.801 |
Neg logit contributions | |
theless | -4.185 |
ying | -3.857 |
ices | -3.734 |
zin | -3.699 |
lict | -3.648 |
Token | . |
Token ID | 13 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
liking | +1.490 |
motto | +1.485 |
Awesome | +1.474 |
effectiveness | +1.443 |
worth | +1.440 |
Neg logit contributions | |
theless | -1.651 |
ying | -1.507 |
ices | -1.433 |
zin | -1.416 |
lict | -1.399 |
Token |
|
Token ID | 198 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
theless | +0.402 |
ying | +0.374 |
ices | +0.356 |
zin | +0.354 |
lict | +0.349 |
Neg logit contributions | |
liking | -0.277 |
Awesome | -0.277 |
motto | -0.277 |
effectiveness | -0.266 |
worth | -0.264 |
Token |
|
Token ID | 198 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
theless | +0.529 |
ying | +0.503 |
ices | +0.477 |
zin | +0.474 |
meyer | +0.463 |
Neg logit contributions | |
motto | -0.427 |
liking | -0.423 |
Awesome | -0.417 |
� | -0.412 |
olicy | -0.408 |
Token | Base |
Token ID | 14881 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
theless | +0.435 |
ying | +0.401 |
ices | +0.381 |
zin | +0.380 |
lict | +0.374 |
Neg logit contributions | |
Awesome | -0.326 |
liking | -0.324 |
motto | -0.323 |
effectiveness | -0.311 |
worth | -0.310 |
Token | ball |
Token ID | 1894 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
motto | +2.522 |
liking | +2.465 |
Awesome | +2.442 |
worth | +2.365 |
effectiveness | +2.338 |
Neg logit contributions | |
theless | -6.955 |
ying | -6.404 |
ices | -6.230 |
zin | -6.215 |
lict | -6.144 |
Token | was |
Token ID | 373 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
motto | +0.207 |
liking | +0.207 |
Awesome | +0.206 |
effectiveness | +0.199 |
worth | +0.198 |
Neg logit contributions | |
theless | -0.262 |
ying | -0.242 |
ices | -0.230 |
zin | -0.229 |
lict | -0.226 |
Token | hugely |
Token ID | 22641 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
liking | +1.072 |
motto | +1.068 |
Awesome | +1.064 |
effectiveness | +1.024 |
worth | +1.024 |
Neg logit contributions | |
theless | -1.589 |
ying | -1.474 |
ices | -1.406 |
zin | -1.402 |
lict | -1.381 |
Token | popular |
Token ID | 2968 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
liking | +4.522 |
worth | +4.263 |
motto | +4.037 |
investment | +3.939 |
Awesome | +3.904 |
Neg logit contributions | |
theless | -12.868 |
ying | -11.987 |
ices | -11.983 |
lict | -11.754 |
zin | -11.640 |
Token | . |
Token ID | 13 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
liking | +2.819 |
motto | +2.755 |
Awesome | +2.737 |
worth | +2.689 |
effectiveness | +2.657 |
Neg logit contributions | |
theless | -4.152 |
ying | -3.824 |
ices | -3.668 |
zin | -3.632 |
lict | -3.583 |
Token | Future |
Token ID | 10898 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Awesome | +0.164 |
liking | +0.164 |
motto | +0.164 |
effectiveness | +0.157 |
worth | +0.157 |
Neg logit contributions | |
theless | -0.244 |
ying | -0.226 |
ices | -0.215 |
zin | -0.215 |
lict | -0.212 |
Token | Hall |
Token ID | 4789 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
theless | +1.863 |
ying | +1.746 |
ices | +1.663 |
zin | +1.655 |
lict | +1.631 |
Neg logit contributions | |
Awesome | -1.172 |
liking | -1.164 |
motto | -1.163 |
effectiveness | -1.116 |
olicy | -1.110 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
theless | +0.898 |
ying | +0.823 |
ices | +0.779 |
zin | +0.776 |
lict | +0.762 |
Neg logit contributions | |
motto | -0.801 |
liking | -0.801 |
Awesome | -0.799 |
effectiveness | -0.774 |
worth | -0.770 |
Token | But |
Token ID | 1537 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
theless | +1.152 |
ying | +1.068 |
ices | +1.016 |
zin | +1.013 |
lict | +0.998 |
Neg logit contributions | |
Awesome | -0.801 |
liking | -0.797 |
motto | -0.795 |
effectiveness | -0.765 |
worth | -0.762 |
Token | whilst |
Token ID | 14590 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
liking | +0.353 |
motto | +0.351 |
Awesome | +0.349 |
effectiveness | +0.338 |
worth | +0.337 |
Neg logit contributions | |
theless | -0.598 |
ying | -0.557 |
ices | -0.534 |
zin | -0.532 |
lict | -0.524 |
Token | Brexit |
Token ID | 11435 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
liking | +1.506 |
motto | +1.493 |
Awesome | +1.463 |
effectiveness | +1.447 |
worth | +1.444 |
Neg logit contributions | |
theless | -2.712 |
ying | -2.515 |
ices | -2.433 |
zin | -2.417 |
lict | -2.383 |
Token | is |
Token ID | 318 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
theless | +2.990 |
ying | +2.773 |
ices | +2.603 |
zin | +2.578 |
lict | +2.534 |
Neg logit contributions | |
Awesome | -2.806 |
motto | -2.778 |
liking | -2.767 |
olicy | -2.676 |
OUNT | -2.658 |
Token | a |
Token ID | 257 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
liking | +0.292 |
motto | +0.291 |
Awesome | +0.291 |
effectiveness | +0.279 |
worth | +0.278 |
Neg logit contributions | |
theless | -0.501 |
ying | -0.468 |
ices | -0.448 |
zin | -0.446 |
lict | -0.439 |
Token | big |
Token ID | 1263 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
theless | +2.314 |
ying | +2.158 |
ices | +2.045 |
zin | +2.042 |
lict | +2.011 |
Neg logit contributions | |
Awesome | -1.561 |
liking | -1.550 |
motto | -1.549 |
effectiveness | -1.485 |
olicy | -1.482 |
Token | issue |
Token ID | 2071 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
investment | +6.615 |
worth | +6.416 |
liking | +6.409 |
motto | +6.326 |
effectiveness | +6.232 |
Neg logit contributions | |
theless | -10.509 |
ices | -9.482 |
zin | -9.396 |
ying | -9.313 |
lict | -9.093 |
Token | for |
Token ID | 329 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
theless | +0.461 |
ying | +0.432 |
ices | +0.410 |
zin | +0.409 |
lict | +0.403 |
Neg logit contributions | |
Awesome | -0.298 |
motto | -0.297 |
liking | -0.297 |
effectiveness | -0.285 |
olicy | -0.282 |
Token | the |
Token ID | 262 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
liking | +0.834 |
motto | +0.831 |
Awesome | +0.822 |
effectiveness | +0.800 |
worth | +0.795 |
Neg logit contributions | |
theless | -1.437 |
ying | -1.339 |
ices | -1.287 |
zin | -1.279 |
lict | -1.262 |
Token | UK |
Token ID | 3482 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
theless | +0.408 |
ying | +0.381 |
ices | +0.363 |
zin | +0.362 |
lict | +0.357 |
Neg logit contributions | |
Awesome | -0.247 |
liking | -0.247 |
motto | -0.247 |
effectiveness | -0.236 |
worth | -0.234 |
Token | and |
Token ID | 290 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
liking | +3.169 |
motto | +3.129 |
Awesome | +3.058 |
worth | +3.057 |
effectiveness | +3.021 |
Neg logit contributions | |
theless | -4.649 |
ying | -4.261 |
ices | -4.088 |
zin | -4.073 |
lict | -4.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
liking | +0.817 |
motto | +0.809 |
Awesome | +0.807 |
worth | +0.785 |
effectiveness | +0.782 |
Neg logit contributions | |
theless | -0.969 |
ying | -0.885 |
ices | -0.843 |
zin | -0.840 |
lict | -0.831 |
Token | They |
Token ID | 1119 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
liking | +0.172 |
Awesome | +0.172 |
motto | +0.172 |
effectiveness | +0.165 |
worth | +0.164 |
Neg logit contributions | |
theless | -0.254 |
ying | -0.236 |
ices | -0.225 |
zin | -0.224 |
lict | -0.221 |
Token | 've |
Token ID | 1053 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
liking | +0.306 |
motto | +0.304 |
Awesome | +0.300 |
worth | +0.296 |
effectiveness | +0.294 |
Neg logit contributions | |
theless | -0.337 |
ying | -0.305 |
ices | -0.291 |
zin | -0.291 |
lict | -0.285 |
Token | got |
Token ID | 1392 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
theless | +3.266 |
ying | +3.022 |
ices | +2.848 |
zin | +2.805 |
lict | +2.745 |
Neg logit contributions | |
Awesome | -3.352 |
liking | -3.304 |
motto | -3.295 |
olicy | -3.233 |
OUNT | -3.220 |
Token | a |
Token ID | 257 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
theless | +0.038 |
ying | +0.035 |
ices | +0.034 |
zin | +0.034 |
lict | +0.033 |
Neg logit contributions | |
liking | -0.021 |
motto | -0.021 |
Awesome | -0.020 |
effectiveness | -0.020 |
worth | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
theless | +1.586 |
ying | +1.478 |
ices | +1.407 |
zin | +1.402 |
lict | +1.380 |
Neg logit contributions | |
Awesome | -1.050 |
liking | -1.048 |
motto | -1.047 |
effectiveness | -1.007 |
worth | -0.999 |
Token | bath |
Token ID | 7837 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
liking | +6.887 |
motto | +6.757 |
investment | +6.478 |
worth | +6.433 |
effectiveness | +6.327 |
Neg logit contributions | |
theless | -10.552 |
ying | -9.431 |
ices | -9.309 |
zin | -9.173 |
lict | -9.062 |
Token | tub |
Token ID | 37995 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
theless | +1.564 |
ying | +1.464 |
ices | +1.389 |
zin | +1.387 |
lict | +1.361 |
Neg logit contributions | |
Awesome | -1.138 |
liking | -1.133 |
motto | -1.132 |
effectiveness | -1.091 |
olicy | -1.080 |
Token | full |
Token ID | 1336 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
theless | +2.221 |
ying | +2.081 |
ices | +1.967 |
zin | +1.954 |
lict | +1.928 |
Neg logit contributions | |
Awesome | -1.723 |
motto | -1.706 |
liking | -1.702 |
olicy | -1.652 |
effectiveness | -1.649 |
Token | of |
Token ID | 286 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
liking | +2.020 |
motto | +2.013 |
Awesome | +2.008 |
worth | +1.965 |
effectiveness | +1.952 |
Neg logit contributions | |
theless | -2.426 |
ying | -2.196 |
ices | -2.106 |
zin | -2.083 |
lict | -2.048 |
Token | liquids |
Token ID | 38236 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
theless | +0.927 |
ying | +0.867 |
ices | +0.826 |
zin | +0.823 |
lict | +0.810 |
Neg logit contributions | |
motto | -0.588 |
Awesome | -0.588 |
liking | -0.588 |
effectiveness | -0.562 |
worth | -0.558 |
Token |
|
Token ID | 198 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
theless | +0.515 |
ying | +0.489 |
ices | +0.464 |
zin | +0.461 |
lict | +0.450 |
Neg logit contributions | |
motto | -0.413 |
liking | -0.409 |
Awesome | -0.405 |
� | -0.398 |
olicy | -0.394 |
Token | " |
Token ID | 1 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
theless | +0.257 |
ying | +0.234 |
ices | +0.222 |
zin | +0.221 |
lict | +0.217 |
Neg logit contributions | |
Awesome | -0.232 |
liking | -0.229 |
motto | -0.228 |
effectiveness | -0.221 |
worth | -0.221 |
Token | It |
Token ID | 1026 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
Awesome | +1.233 |
liking | +1.193 |
motto | +1.187 |
worth | +1.142 |
effectiveness | +1.139 |
Neg logit contributions | |
theless | -1.987 |
ying | -1.829 |
zin | -1.749 |
ices | -1.742 |
lict | -1.729 |
Token | 's |
Token ID | 338 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
liking | +0.571 |
motto | +0.568 |
Awesome | +0.560 |
worth | +0.549 |
effectiveness | +0.547 |
Neg logit contributions | |
theless | -0.748 |
ying | -0.689 |
zin | -0.657 |
ices | -0.653 |
lict | -0.647 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
liking | +1.330 |
motto | +1.324 |
Awesome | +1.312 |
worth | +1.283 |
effectiveness | +1.273 |
Neg logit contributions | |
theless | -1.950 |
ying | -1.808 |
ices | -1.724 |
zin | -1.719 |
lict | -1.705 |
Token | big |
Token ID | 1263 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
theless | +1.116 |
ying | +1.038 |
ices | +0.993 |
zin | +0.985 |
lict | +0.973 |
Neg logit contributions | |
liking | -0.735 |
motto | -0.735 |
Awesome | -0.730 |
effectiveness | -0.704 |
worth | -0.701 |
Token | highlight |
Token ID | 7238 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
liking | +6.768 |
motto | +6.729 |
investment | +6.630 |
worth | +6.464 |
effectiveness | +6.296 |
Neg logit contributions | |
theless | -10.415 |
ices | -9.346 |
ying | -9.278 |
lict | -9.191 |
zin | -9.095 |
Token | for |
Token ID | 329 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
liking | +1.237 |
motto | +1.231 |
Awesome | +1.215 |
worth | +1.192 |
effectiveness | +1.185 |
Neg logit contributions | |
theless | -1.798 |
ying | -1.656 |
ices | -1.587 |
zin | -1.579 |
lict | -1.562 |
Token | us |
Token ID | 514 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
liking | +1.582 |
motto | +1.564 |
Awesome | +1.553 |
effectiveness | +1.516 |
worth | +1.500 |
Neg logit contributions | |
theless | -2.579 |
ying | -2.393 |
ices | -2.301 |
zin | -2.282 |
lict | -2.266 |
Token | in |
Token ID | 287 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
liking | +0.311 |
motto | +0.310 |
Awesome | +0.309 |
effectiveness | +0.298 |
worth | +0.297 |
Neg logit contributions | |
theless | -0.418 |
ying | -0.387 |
ices | -0.368 |
zin | -0.366 |
lict | -0.362 |
Token | our |
Token ID | 674 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
liking | +0.329 |
motto | +0.328 |
Awesome | +0.328 |
effectiveness | +0.312 |
worth | +0.309 |
Neg logit contributions | |
theless | -0.706 |
ying | -0.662 |
ices | -0.636 |
zin | -0.633 |
lict | -0.626 |
Token | man |
Token ID | 805 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
theless | +3.155 |
ying | +2.930 |
ices | +2.768 |
zin | +2.759 |
meyer | +2.687 |
Neg logit contributions | |
liking | -2.886 |
motto | -2.873 |
Awesome | -2.866 |
effectiveness | -2.794 |
olicy | -2.774 |
Token | and |
Token ID | 290 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
liking | +0.158 |
Awesome | +0.158 |
motto | +0.157 |
effectiveness | +0.151 |
worth | +0.150 |
Neg logit contributions | |
theless | -0.198 |
ying | -0.182 |
ices | -0.174 |
zin | -0.172 |
lict | -0.171 |
Token | Lair |
Token ID | 15067 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
theless | +0.713 |
ying | +0.663 |
ices | +0.633 |
zin | +0.630 |
lict | +0.621 |
Neg logit contributions | |
liking | -0.460 |
motto | -0.459 |
Awesome | -0.459 |
effectiveness | -0.440 |
worth | -0.438 |
Token | d |
Token ID | 67 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
theless | +0.912 |
ying | +0.845 |
ices | +0.806 |
zin | +0.802 |
lict | +0.791 |
Neg logit contributions | |
motto | -0.650 |
liking | -0.649 |
Awesome | -0.649 |
effectiveness | -0.625 |
worth | -0.622 |
Token | were |
Token ID | 547 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
theless | +3.208 |
ying | +2.956 |
ices | +2.778 |
zin | +2.765 |
lict | +2.705 |
Neg logit contributions | |
Awesome | -3.165 |
liking | -3.157 |
motto | -3.151 |
effectiveness | -3.062 |
olicy | -3.053 |
Token | big |
Token ID | 1263 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
liking | +0.636 |
motto | +0.635 |
Awesome | +0.631 |
effectiveness | +0.608 |
worth | +0.608 |
Neg logit contributions | |
theless | -0.982 |
ying | -0.911 |
ices | -0.870 |
zin | -0.868 |
lict | -0.855 |
Token | fans |
Token ID | 3296 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
liking | +6.055 |
motto | +5.791 |
worth | +5.599 |
Awesome | +5.538 |
investment | +5.534 |
Neg logit contributions | |
theless | -11.216 |
ying | -10.013 |
zin | -9.862 |
ices | -9.848 |
lict | -9.787 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
liking | +0.206 |
Awesome | +0.205 |
motto | +0.205 |
worth | +0.198 |
effectiveness | +0.198 |
Neg logit contributions | |
theless | -0.221 |
ying | -0.202 |
ices | -0.192 |
zin | -0.190 |
lict | -0.188 |
Token | The |
Token ID | 383 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
Awesome | +0.105 |
liking | +0.105 |
motto | +0.104 |
effectiveness | +0.100 |
worth | +0.100 |
Neg logit contributions | |
theless | -0.146 |
ying | -0.136 |
ices | -0.129 |
zin | -0.129 |
lict | -0.127 |
Token | success |
Token ID | 1943 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
theless | +0.899 |
ying | +0.838 |
ices | +0.800 |
zin | +0.796 |
lict | +0.785 |
Neg logit contributions | |
liking | -0.565 |
Awesome | -0.564 |
motto | -0.563 |
effectiveness | -0.540 |
worth | -0.537 |
Token | of |
Token ID | 286 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
motto | +2.105 |
liking | +2.091 |
Awesome | +2.041 |
effectiveness | +2.015 |
worth | +2.013 |
Neg logit contributions | |
theless | -2.590 |
ying | -2.356 |
zin | -2.254 |
ices | -2.248 |
lict | -2.227 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
motto | +3.483 |
liking | +3.464 |
Awesome | +3.375 |
worth | +3.356 |
effectiveness | +3.318 |
Neg logit contributions | |
theless | -4.653 |
ying | -4.261 |
zin | -4.052 |
ices | -4.044 |
lict | -3.999 |
Token | This |
Token ID | 770 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
liking | +0.172 |
motto | +0.172 |
Awesome | +0.172 |
effectiveness | +0.165 |
worth | +0.164 |
Neg logit contributions | |
theless | -0.253 |
ying | -0.235 |
ices | -0.224 |
zin | -0.223 |
lict | -0.220 |
Token | would |
Token ID | 561 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
theless | +4.571 |
ying | +4.267 |
ices | +4.036 |
zin | +3.996 |
lict | +3.956 |
Neg logit contributions | |
Awesome | -3.329 |
liking | -3.277 |
motto | -3.219 |
olicy | -3.168 |
OUNT | -3.158 |
Token | be |
Token ID | 307 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
theless | +0.050 |
ying | +0.046 |
ices | +0.044 |
zin | +0.044 |
lict | +0.043 |
Neg logit contributions | |
motto | -0.042 |
liking | -0.042 |
Awesome | -0.041 |
effectiveness | -0.040 |
worth | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
motto | +0.872 |
liking | +0.870 |
Awesome | +0.865 |
worth | +0.838 |
effectiveness | +0.829 |
Neg logit contributions | |
theless | -1.641 |
ying | -1.529 |
ices | -1.465 |
zin | -1.463 |
lict | -1.443 |
Token | big |
Token ID | 1263 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
theless | +1.917 |
ying | +1.788 |
ices | +1.700 |
zin | +1.696 |
lict | +1.670 |
Neg logit contributions | |
Awesome | -1.268 |
liking | -1.263 |
motto | -1.259 |
effectiveness | -1.213 |
olicy | -1.202 |
Token | team |
Token ID | 1074 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
liking | +6.236 |
motto | +6.231 |
investment | +6.184 |
worth | +6.026 |
effectiveness | +5.820 |
Neg logit contributions | |
theless | -10.923 |
ying | -9.672 |
ices | -9.671 |
zin | -9.566 |
lict | -9.381 |
Token | decision |
Token ID | 2551 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
motto | +1.558 |
liking | +1.554 |
Awesome | +1.523 |
worth | +1.492 |
effectiveness | +1.474 |
Neg logit contributions | |
theless | -2.397 |
ying | -2.181 |
ices | -2.114 |
zin | -2.097 |
lict | -2.059 |
Token | , |
Token ID | 11 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
liking | +0.490 |
motto | +0.489 |
Awesome | +0.487 |
worth | +0.470 |
effectiveness | +0.470 |
Neg logit contributions | |
theless | -0.699 |
ying | -0.649 |
ices | -0.619 |
zin | -0.616 |
lict | -0.606 |
Token | backed |
Token ID | 9763 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
theless | +0.252 |
ying | +0.234 |
ices | +0.223 |
zin | +0.221 |
lict | +0.218 |
Neg logit contributions | |
Awesome | -0.183 |
liking | -0.182 |
motto | -0.182 |
effectiveness | -0.175 |
worth | -0.174 |
Token | – |
Token ID | 784 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
motto | +2.845 |
liking | +2.841 |
Awesome | +2.813 |
worth | +2.774 |
effectiveness | +2.719 |
Neg logit contributions | |
theless | -5.326 |
ying | -4.857 |
ices | -4.691 |
zin | -4.598 |
meyer | -4.586 |
Token | . |
Token ID | 13 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
liking | +2.680 |
Awesome | +2.650 |
motto | +2.634 |
worth | +2.594 |
effectiveness | +2.548 |
Neg logit contributions | |
theless | -3.260 |
ying | -2.972 |
ices | -2.838 |
zin | -2.808 |
lict | -2.781 |
Token | It |
Token ID | 632 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
liking | +0.208 |
motto | +0.208 |
Awesome | +0.208 |
effectiveness | +0.200 |
worth | +0.199 |
Neg logit contributions | |
theless | -0.308 |
ying | -0.287 |
ices | -0.273 |
zin | -0.272 |
lict | -0.268 |
Token | was |
Token ID | 373 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
liking | +1.701 |
Awesome | +1.682 |
motto | +1.681 |
worth | +1.650 |
effectiveness | +1.625 |
Neg logit contributions | |
theless | -1.980 |
ying | -1.825 |
zin | -1.722 |
ices | -1.715 |
lict | -1.694 |
Token | quite |
Token ID | 2407 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
liking | +1.720 |
Awesome | +1.711 |
motto | +1.707 |
worth | +1.669 |
effectiveness | +1.634 |
Neg logit contributions | |
theless | -2.704 |
ying | -2.509 |
zin | -2.394 |
ices | -2.393 |
lict | -2.357 |
Token | a |
Token ID | 257 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
liking | +1.321 |
motto | +1.302 |
Awesome | +1.299 |
worth | +1.255 |
effectiveness | +1.245 |
Neg logit contributions | |
theless | -2.696 |
ying | -2.515 |
ices | -2.427 |
zin | -2.418 |
lict | -2.386 |
Token | big |
Token ID | 1263 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
theless | +0.448 |
ying | +0.418 |
ices | +0.399 |
zin | +0.397 |
lict | +0.392 |
Neg logit contributions | |
liking | -0.272 |
motto | -0.271 |
Awesome | -0.271 |
effectiveness | -0.260 |
worth | -0.258 |
Token | prototype |
Token ID | 14879 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
liking | +6.283 |
investment | +6.104 |
motto | +5.973 |
worth | +5.830 |
Awesome | +5.787 |
Neg logit contributions | |
theless | -11.011 |
ying | -9.920 |
ices | -9.901 |
zin | -9.756 |
meyer | -9.649 |
Token | , |
Token ID | 11 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
liking | +1.006 |
motto | +1.002 |
Awesome | +0.999 |
worth | +0.967 |
effectiveness | +0.966 |
Neg logit contributions | |
theless | -1.250 |
ying | -1.151 |
ices | -1.097 |
zin | -1.090 |
lict | -1.070 |
Token | here |
Token ID | 994 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
liking | +0.241 |
motto | +0.240 |
Awesome | +0.240 |
effectiveness | +0.231 |
worth | +0.230 |
Neg logit contributions | |
theless | -0.323 |
ying | -0.299 |
ices | -0.284 |
zin | -0.283 |
lict | -0.279 |
Token | � |
Token ID | 447 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
theless | +2.649 |
ying | +2.470 |
ices | +2.352 |
zin | +2.333 |
lict | +2.305 |
Neg logit contributions | |
Awesome | -2.074 |
motto | -2.073 |
liking | -2.072 |
olicy | -2.007 |
effectiveness | -2.005 |
Token | � |
Token ID | 247 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
liking | +0.169 |
Awesome | +0.169 |
motto | +0.169 |
effectiveness | +0.163 |
worth | +0.162 |
Neg logit contributions | |
theless | -0.216 |
ying | -0.200 |
ices | -0.190 |
zin | -0.189 |
lict | -0.186 |
Token | restaurant |
Token ID | 7072 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
theless | +2.143 |
ying | +1.999 |
ices | +1.894 |
zin | +1.889 |
lict | +1.861 |
Neg logit contributions | |
Awesome | -1.516 |
liking | -1.502 |
motto | -1.500 |
effectiveness | -1.447 |
olicy | -1.437 |
Token | - |
Token ID | 532 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
liking | +0.379 |
motto | +0.379 |
Awesome | +0.377 |
effectiveness | +0.364 |
worth | +0.364 |
Neg logit contributions | |
theless | -0.507 |
ying | -0.469 |
ices | -0.446 |
zin | -0.444 |
lict | -0.437 |
Token | cooking |
Token ID | 10801 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
liking | +1.354 |
motto | +1.351 |
Awesome | +1.338 |
worth | +1.299 |
effectiveness | +1.285 |
Neg logit contributions | |
theless | -2.206 |
ying | -2.052 |
ices | -1.960 |
zin | -1.958 |
lict | -1.928 |
Token | is |
Token ID | 318 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
theless | +1.045 |
ying | +0.971 |
ices | +0.924 |
zin | +0.921 |
lict | +0.905 |
Neg logit contributions | |
liking | -0.740 |
Awesome | -0.739 |
motto | -0.738 |
effectiveness | -0.710 |
worth | -0.704 |
Token | another |
Token ID | 1194 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
liking | +0.628 |
motto | +0.627 |
Awesome | +0.623 |
worth | +0.597 |
effectiveness | +0.596 |
Neg logit contributions | |
theless | -1.203 |
ying | -1.124 |
ices | -1.078 |
zin | -1.074 |
lict | -1.061 |
Token | big |
Token ID | 1263 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
theless | +4.038 |
ying | +3.830 |
zin | +3.623 |
ices | +3.587 |
lict | +3.531 |
Neg logit contributions | |
Awesome | -2.730 |
liking | -2.687 |
motto | -2.641 |
olicy | -2.639 |
OUNT | -2.591 |
Token | passion |
Token ID | 7506 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
motto | +6.256 |
liking | +6.150 |
investment | +6.077 |
worth | +5.924 |
effectiveness | +5.667 |
Neg logit contributions | |
theless | -11.070 |
ices | -9.792 |
ying | -9.720 |
zin | -9.612 |
meyer | -9.487 |
Token | of |
Token ID | 286 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
liking | +0.265 |
motto | +0.264 |
Awesome | +0.263 |
effectiveness | +0.254 |
worth | +0.253 |
Neg logit contributions | |
theless | -0.356 |
ying | -0.329 |
ices | -0.314 |
zin | -0.312 |
lict | -0.307 |
Token | mine |
Token ID | 6164 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
theless | +0.180 |
ying | +0.168 |
ices | +0.159 |
zin | +0.159 |
lict | +0.156 |
Neg logit contributions | |
Awesome | -0.128 |
liking | -0.128 |
motto | -0.128 |
effectiveness | -0.123 |
worth | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
liking | +2.358 |
motto | +2.338 |
Awesome | +2.318 |
worth | +2.282 |
effectiveness | +2.243 |
Neg logit contributions | |
theless | -2.841 |
ying | -2.592 |
ices | -2.481 |
zin | -2.460 |
lict | -2.430 |
Token | it |
Token ID | 340 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
theless | +0.543 |
ying | +0.504 |
ices | +0.478 |
zin | +0.475 |
lict | +0.467 |
Neg logit contributions | |
Awesome | -0.430 |
motto | -0.429 |
liking | -0.428 |
effectiveness | -0.414 |
olicy | -0.410 |
Token | is |
Token ID | 318 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
theless | +3.707 |
ying | +3.443 |
ices | +3.267 |
zin | +3.264 |
lict | +3.203 |
Neg logit contributions | |
Awesome | -2.644 |
motto | -2.637 |
liking | -2.634 |
olicy | -2.558 |
effectiveness | -2.533 |
Token | going |
Token ID | 1016 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
liking | +0.633 |
Awesome | +0.632 |
motto | +0.629 |
worth | +0.609 |
effectiveness | +0.602 |
Neg logit contributions | |
theless | -1.191 |
ying | -1.106 |
ices | -1.060 |
zin | -1.058 |
lict | -1.046 |
Token | to |
Token ID | 284 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
liking | +0.323 |
motto | +0.323 |
Awesome | +0.322 |
effectiveness | +0.311 |
worth | +0.310 |
Neg logit contributions | |
theless | -0.467 |
ying | -0.432 |
ices | -0.412 |
zin | -0.410 |
lict | -0.404 |
Token | be |
Token ID | 307 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
theless | +1.197 |
ying | +1.100 |
ices | +1.040 |
zin | +1.034 |
lict | +1.016 |
Neg logit contributions | |
liking | -1.111 |
motto | -1.110 |
Awesome | -1.109 |
effectiveness | -1.074 |
worth | -1.068 |
Token | a |
Token ID | 257 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
liking | +0.773 |
Awesome | +0.771 |
motto | +0.766 |
worth | +0.745 |
effectiveness | +0.734 |
Neg logit contributions | |
theless | -1.516 |
ying | -1.413 |
ices | -1.354 |
zin | -1.354 |
lict | -1.337 |
Token | big |
Token ID | 1263 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
theless | +1.756 |
ying | +1.636 |
ices | +1.559 |
zin | +1.554 |
lict | +1.529 |
Neg logit contributions | |
Awesome | -1.134 |
liking | -1.134 |
motto | -1.134 |
effectiveness | -1.088 |
worth | -1.078 |
Token | hit |
Token ID | 2277 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
liking | +6.912 |
investment | +6.722 |
motto | +6.687 |
worth | +6.624 |
Awesome | +6.537 |
Neg logit contributions | |
theless | -9.975 |
ices | -8.884 |
ying | -8.830 |
lict | -8.757 |
zin | -8.652 |
Token | for |
Token ID | 329 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
liking | +2.503 |
motto | +2.471 |
Awesome | +2.460 |
worth | +2.450 |
effectiveness | +2.401 |
Neg logit contributions | |
theless | -3.294 |
ying | -3.009 |
ices | -2.899 |
zin | -2.854 |
lict | -2.835 |
Token | the |
Token ID | 262 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
liking | +1.569 |
Awesome | +1.546 |
motto | +1.536 |
effectiveness | +1.489 |
worth | +1.487 |
Neg logit contributions | |
theless | -2.779 |
ying | -2.581 |
ices | -2.490 |
zin | -2.473 |
lict | -2.449 |
Token | franchise |
Token ID | 8663 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
liking | +0.059 |
motto | +0.059 |
Awesome | +0.059 |
effectiveness | +0.056 |
worth | +0.056 |
Neg logit contributions | |
theless | -0.103 |
ying | -0.096 |
ices | -0.092 |
zin | -0.091 |
lict | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
liking | +0.876 |
motto | +0.874 |
Awesome | +0.872 |
effectiveness | +0.844 |
worth | +0.843 |
Neg logit contributions | |
theless | -0.976 |
ying | -0.896 |
ices | -0.849 |
zin | -0.842 |
lict | -0.830 |
Token | at |
Token ID | 379 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
theless | +0.492 |
ying | +0.459 |
ices | +0.439 |
zin | +0.437 |
lict | +0.431 |
Neg logit contributions | |
liking | -0.297 |
motto | -0.296 |
Awesome | -0.296 |
effectiveness | -0.284 |
worth | -0.281 |
Token | onement |
Token ID | 49844 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
motto | +1.976 |
liking | +1.966 |
Awesome | +1.966 |
effectiveness | +1.917 |
worth | +1.908 |
Neg logit contributions | |
theless | -3.337 |
ying | -3.015 |
ices | -2.925 |
zin | -2.896 |
lict | -2.861 |
Token | has |
Token ID | 468 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
theless | +2.186 |
ying | +2.038 |
ices | +1.937 |
zin | +1.928 |
lict | +1.899 |
Neg logit contributions | |
Awesome | -1.570 |
liking | -1.555 |
motto | -1.547 |
olicy | -1.489 |
effectiveness | -1.489 |
Token | been |
Token ID | 587 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
theless | +3.184 |
ying | +2.916 |
ices | +2.750 |
zin | +2.731 |
lict | +2.677 |
Neg logit contributions | |
Awesome | -3.361 |
motto | -3.318 |
liking | -3.306 |
olicy | -3.230 |
effectiveness | -3.198 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
liking | +0.045 |
Awesome | +0.045 |
motto | +0.045 |
effectiveness | +0.043 |
worth | +0.042 |
Neg logit contributions | |
theless | -0.078 |
ying | -0.073 |
ices | -0.070 |
zin | -0.070 |
lict | -0.069 |
Token | big |
Token ID | 1263 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
theless | +1.427 |
ying | +1.340 |
ices | +1.275 |
zin | +1.273 |
lict | +1.255 |
Neg logit contributions | |
Awesome | -0.800 |
liking | -0.796 |
motto | -0.793 |
effectiveness | -0.760 |
olicy | -0.756 |
Token | blessing |
Token ID | 20027 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
motto | +5.393 |
liking | +5.321 |
investment | +5.249 |
worth | +5.228 |
effectiveness | +4.928 |
Neg logit contributions | |
theless | -11.812 |
ices | -10.562 |
ying | -10.459 |
zin | -10.420 |
lict | -10.290 |
Token | in |
Token ID | 287 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
liking | +2.142 |
motto | +2.128 |
Awesome | +2.096 |
worth | +2.093 |
effectiveness | +2.049 |
Neg logit contributions | |
theless | -2.965 |
ying | -2.724 |
ices | -2.617 |
zin | -2.593 |
lict | -2.558 |
Token | helping |
Token ID | 5742 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
liking | +0.405 |
motto | +0.405 |
Awesome | +0.405 |
effectiveness | +0.386 |
worth | +0.382 |
Neg logit contributions | |
theless | -0.808 |
ying | -0.757 |
ices | -0.725 |
zin | -0.723 |
lict | -0.713 |
Token | me |
Token ID | 502 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
liking | +0.544 |
motto | +0.541 |
Awesome | +0.533 |
effectiveness | +0.522 |
worth | +0.520 |
Neg logit contributions | |
theless | -0.990 |
ying | -0.921 |
ices | -0.881 |
zin | -0.880 |
meyer | -0.863 |
Token | repent |
Token ID | 28787 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
liking | +1.051 |
motto | +1.048 |
Awesome | +1.030 |
worth | +1.014 |
effectiveness | +1.012 |
Neg logit contributions | |
theless | -1.336 |
ying | -1.228 |
ices | -1.172 |
zin | -1.166 |
lict | -1.140 |
Token | coating |
Token ID | 26749 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
theless | +3.204 |
ying | +3.029 |
ices | +2.900 |
zin | +2.886 |
lict | +2.843 |
Neg logit contributions | |
Awesome | -1.861 |
liking | -1.850 |
motto | -1.844 |
effectiveness | -1.775 |
olicy | -1.762 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
liking | +1.851 |
motto | +1.849 |
Awesome | +1.808 |
worth | +1.791 |
effectiveness | +1.781 |
Neg logit contributions | |
theless | -2.691 |
ying | -2.463 |
zin | -2.350 |
ices | -2.349 |
lict | -2.323 |
Token | I |
Token ID | 314 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
liking | +0.001 |
Awesome | +0.001 |
motto | +0.001 |
effectiveness | +0.001 |
worth | +0.001 |
Neg logit contributions | |
theless | -0.002 |
ying | -0.002 |
ices | -0.002 |
zin | -0.002 |
lict | -0.002 |
Token | am |
Token ID | 716 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
theless | +0.314 |
ying | +0.286 |
ices | +0.273 |
zin | +0.272 |
lict | +0.268 |
Neg logit contributions | |
liking | -0.265 |
motto | -0.265 |
Awesome | -0.260 |
worth | -0.256 |
effectiveness | -0.254 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
liking | +0.411 |
motto | +0.406 |
Awesome | +0.403 |
worth | +0.389 |
effectiveness | +0.386 |
Neg logit contributions | |
theless | -0.682 |
ying | -0.632 |
ices | -0.605 |
zin | -0.604 |
lict | -0.598 |
Token | big |
Token ID | 1263 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
theless | +1.238 |
ying | +1.153 |
ices | +1.100 |
zin | +1.095 |
lict | +1.079 |
Neg logit contributions | |
liking | -0.792 |
Awesome | -0.791 |
motto | -0.791 |
effectiveness | -0.759 |
worth | -0.753 |
Token | fan |
Token ID | 4336 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
liking | +6.006 |
motto | +5.623 |
worth | +5.434 |
investment | +5.348 |
Awesome | +5.307 |
Neg logit contributions | |
theless | -10.973 |
ying | -9.989 |
ices | -9.865 |
lict | -9.768 |
zin | -9.728 |
Token | of |
Token ID | 286 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
liking | +1.970 |
motto | +1.952 |
Awesome | +1.941 |
worth | +1.891 |
effectiveness | +1.870 |
Neg logit contributions | |
theless | -2.396 |
ying | -2.188 |
ices | -2.100 |
zin | -2.074 |
lict | -2.050 |
Token | this |
Token ID | 428 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
liking | +0.137 |
motto | +0.136 |
Awesome | +0.135 |
effectiveness | +0.130 |
worth | +0.129 |
Neg logit contributions | |
theless | -0.244 |
ying | -0.228 |
ices | -0.218 |
zin | -0.218 |
lict | -0.215 |
Token | stuff |
Token ID | 3404 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
theless | +3.243 |
ying | +3.051 |
ices | +2.911 |
zin | +2.903 |
lict | +2.858 |
Neg logit contributions | |
Awesome | -1.849 |
liking | -1.827 |
motto | -1.815 |
olicy | -1.770 |
effectiveness | -1.746 |
Token | ; |
Token ID | 26 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
theless | +0.040 |
ying | +0.037 |
ices | +0.035 |
zin | +0.035 |
lict | +0.034 |
Neg logit contributions | |
liking | -0.033 |
motto | -0.033 |
Awesome | -0.033 |
effectiveness | -0.032 |
worth | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
liking | +0.115 |
motto | +0.115 |
Awesome | +0.114 |
worth | +0.111 |
effectiveness | +0.111 |
Neg logit contributions | |
theless | -0.151 |
ying | -0.139 |
ices | -0.132 |
zin | -0.131 |
lict | -0.129 |
Token | Ol |
Token ID | 6544 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Awesome | +0.479 |
liking | +0.474 |
motto | +0.474 |
worth | +0.455 |
effectiveness | +0.453 |
Neg logit contributions | |
theless | -0.762 |
ying | -0.708 |
ices | -0.673 |
zin | -0.673 |
lict | -0.667 |
Token | af |
Token ID | 1878 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Awesome | +1.302 |
liking | +1.301 |
motto | +1.298 |
effectiveness | +1.252 |
worth | +1.248 |
Neg logit contributions | |
theless | -1.698 |
ying | -1.567 |
ices | -1.489 |
zin | -1.484 |
lict | -1.458 |
Token | sings |
Token ID | 33041 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
motto | +0.893 |
liking | +0.893 |
Awesome | +0.885 |
worth | +0.856 |
effectiveness | +0.853 |
Neg logit contributions | |
theless | -1.231 |
ying | -1.134 |
ices | -1.080 |
zin | -1.077 |
lict | -1.064 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
theless | +2.223 |
ying | +2.079 |
ices | +1.980 |
zin | +1.969 |
lict | +1.937 |
Neg logit contributions | |
Awesome | -1.443 |
liking | -1.440 |
motto | -1.439 |
effectiveness | -1.384 |
olicy | -1.371 |
Token | big |
Token ID | 1263 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
theless | +1.518 |
ying | +1.409 |
ices | +1.342 |
zin | +1.335 |
lict | +1.316 |
Neg logit contributions | |
liking | -1.087 |
motto | -1.086 |
Awesome | -1.084 |
effectiveness | -1.042 |
worth | -1.037 |
Token | random |
Token ID | 4738 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
motto | +6.742 |
liking | +6.700 |
worth | +6.428 |
Awesome | +6.397 |
investment | +6.218 |
Neg logit contributions | |
theless | -10.037 |
ying | -9.066 |
ices | -8.942 |
zin | -8.770 |
lict | -8.638 |
Token | musical |
Token ID | 10530 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
theless | +2.465 |
ying | +2.308 |
ices | +2.191 |
zin | +2.183 |
lict | +2.150 |
Neg logit contributions | |
Awesome | -1.651 |
liking | -1.639 |
motto | -1.632 |
olicy | -1.581 |
effectiveness | -1.579 |
Token | number |
Token ID | 1271 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
motto | +0.587 |
liking | +0.584 |
Awesome | +0.577 |
worth | +0.552 |
effectiveness | +0.548 |
Neg logit contributions | |
theless | -1.336 |
ying | -1.250 |
ices | -1.203 |
zin | -1.198 |
lict | -1.185 |
Token | called |
Token ID | 1444 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
liking | +0.336 |
motto | +0.336 |
Awesome | +0.334 |
worth | +0.323 |
effectiveness | +0.322 |
Neg logit contributions | |
theless | -0.438 |
ying | -0.405 |
ices | -0.385 |
zin | -0.383 |
lict | -0.377 |
Token | � |
Token ID | 564 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
motto | +2.717 |
Awesome | +2.705 |
liking | +2.703 |
worth | +2.616 |
effectiveness | +2.562 |
Neg logit contributions | |
theless | -4.297 |
ying | -3.961 |
zin | -3.795 |
ices | -3.792 |
lict | -3.744 |
Token | if |
Token ID | 611 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
theless | +0.557 |
ying | +0.516 |
ices | +0.490 |
zin | +0.487 |
lict | +0.479 |
Neg logit contributions | |
Awesome | -0.446 |
liking | -0.446 |
motto | -0.445 |
effectiveness | -0.429 |
worth | -0.426 |
Token | you |
Token ID | 345 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
liking | +1.209 |
motto | +1.204 |
Awesome | +1.197 |
effectiveness | +1.159 |
worth | +1.154 |
Neg logit contributions | |
theless | -1.994 |
ying | -1.859 |
ices | -1.781 |
zin | -1.774 |
lict | -1.748 |
Token | were |
Token ID | 547 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
liking | +0.396 |
motto | +0.396 |
Awesome | +0.392 |
worth | +0.383 |
effectiveness | +0.382 |
Neg logit contributions | |
theless | -0.403 |
ying | -0.366 |
ices | -0.348 |
zin | -0.346 |
lict | -0.338 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
liking | +0.317 |
motto | +0.316 |
Awesome | +0.316 |
effectiveness | +0.303 |
worth | +0.301 |
Neg logit contributions | |
theless | -0.513 |
ying | -0.478 |
ices | -0.457 |
zin | -0.455 |
lict | -0.448 |
Token | believe |
Token ID | 1975 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
theless | +1.421 |
ying | +1.335 |
ices | +1.252 |
zin | +1.242 |
lict | +1.231 |
Neg logit contributions | |
Awesome | -1.155 |
liking | -1.140 |
motto | -1.138 |
effectiveness | -1.100 |
olicy | -1.094 |
Token | ze |
Token ID | 41271 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
liking | +1.197 |
motto | +1.195 |
Awesome | +1.184 |
effectiveness | +1.142 |
worth | +1.139 |
Neg logit contributions | |
theless | -2.146 |
ying | -1.999 |
ices | -1.919 |
zin | -1.912 |
lict | -1.887 |
Token | ves |
Token ID | 1158 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
theless | +7.105 |
ying | +6.759 |
ices | +6.462 |
zin | +6.406 |
lict | +6.250 |
Neg logit contributions | |
liking | -4.548 |
motto | -4.455 |
Awesome | -4.422 |
effectiveness | -4.371 |
olicy | -4.319 |
Token | and |
Token ID | 290 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
theless | +4.243 |
ying | +3.947 |
ices | +3.722 |
zin | +3.717 |
meyer | +3.632 |
Neg logit contributions | |
liking | -3.469 |
Awesome | -3.459 |
motto | -3.440 |
effectiveness | -3.350 |
olicy | -3.328 |
Token | his |
Token ID | 465 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
theless | +0.439 |
ying | +0.409 |
ices | +0.390 |
zin | +0.388 |
lict | +0.383 |
Neg logit contributions | |
liking | -0.283 |
motto | -0.283 |
Awesome | -0.283 |
effectiveness | -0.271 |
worth | -0.270 |
Token | logic |
Token ID | 9156 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
motto | +2.248 |
liking | +2.226 |
Awesome | +2.189 |
effectiveness | +2.121 |
worth | +2.109 |
Neg logit contributions | |
theless | -3.854 |
ying | -3.578 |
ices | -3.424 |
zin | -3.413 |
lict | -3.408 |
Token | in |
Token ID | 287 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
motto | +1.158 |
liking | +1.157 |
Awesome | +1.151 |
worth | +1.116 |
effectiveness | +1.115 |
Neg logit contributions | |
theless | -1.400 |
ying | -1.288 |
ices | -1.218 |
zin | -1.218 |
lict | -1.198 |
Token | Photo |
Token ID | 6191 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
theless | +1.463 |
ying | +1.356 |
ices | +1.290 |
zin | +1.284 |
lict | +1.264 |
Neg logit contributions | |
Awesome | -1.071 |
liking | -1.070 |
motto | -1.069 |
effectiveness | -1.029 |
worth | -1.023 |
Token | of |
Token ID | 286 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
theless | +3.821 |
ying | +3.590 |
ices | +3.427 |
zin | +3.403 |
lict | +3.361 |
Neg logit contributions | |
liking | -2.348 |
Awesome | -2.342 |
motto | -2.337 |
effectiveness | -2.236 |
olicy | -2.227 |
Token | a |
Token ID | 257 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
theless | +1.769 |
ying | +1.656 |
ices | +1.577 |
zin | +1.571 |
lict | +1.551 |
Neg logit contributions | |
Awesome | -1.083 |
liking | -1.083 |
motto | -1.081 |
effectiveness | -1.035 |
olicy | -1.026 |
Token | juvenile |
Token ID | 21904 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
theless | +3.117 |
ying | +2.925 |
zin | +2.774 |
ices | +2.774 |
lict | +2.732 |
Neg logit contributions | |
Awesome | -1.971 |
motto | -1.958 |
liking | -1.958 |
olicy | -1.884 |
effectiveness | -1.879 |
Token | C |
Token ID | 327 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
theless | +0.944 |
ying | +0.880 |
ices | +0.838 |
zin | +0.835 |
lict | +0.822 |
Neg logit contributions | |
liking | -0.615 |
Awesome | -0.615 |
motto | -0.615 |
effectiveness | -0.590 |
worth | -0.585 |
Token | ract |
Token ID | 974 |
Feature activation | +9.41e+00 |
Pos logit contributions | |
theless | +1.374 |
ying | +1.274 |
ices | +1.202 |
zin | +1.201 |
lict | +1.175 |
Neg logit contributions | |
liking | -1.340 |
Awesome | -1.332 |
motto | -1.330 |
effectiveness | -1.289 |
worth | -1.277 |
Token | icus |
Token ID | 24552 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
theless | +7.886 |
ying | +7.596 |
ices | +7.191 |
zin | +7.108 |
lict | +6.995 |
Neg logit contributions | |
motto | -6.639 |
liking | -6.565 |
Awesome | -6.529 |
effectiveness | -6.420 |
olicy | -6.365 |
Token | nig |
Token ID | 44873 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
theless | +2.842 |
ying | +2.661 |
ices | +2.532 |
zin | +2.519 |
lict | +2.498 |
Neg logit contributions | |
Awesome | -1.816 |
liking | -1.802 |
motto | -1.794 |
effectiveness | -1.737 |
olicy | -1.725 |
Token | rog |
Token ID | 3828 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
theless | +0.226 |
ying | +0.209 |
ices | +0.198 |
zin | +0.197 |
lict | +0.194 |
Neg logit contributions | |
liking | -0.183 |
motto | -0.183 |
Awesome | -0.183 |
effectiveness | -0.176 |
worth | -0.176 |
Token | ular |
Token ID | 934 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
theless | +2.255 |
ying | +2.083 |
ices | +1.954 |
zin | +1.938 |
lict | +1.905 |
Neg logit contributions | |
Awesome | -2.368 |
liking | -2.368 |
motto | -2.363 |
effectiveness | -2.295 |
worth | -2.267 |
Token | is |
Token ID | 271 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
liking | +0.198 |
motto | +0.198 |
Awesome | +0.197 |
worth | +0.192 |
effectiveness | +0.192 |
Neg logit contributions | |
theless | -0.144 |
ying | -0.129 |
ices | -0.120 |
zin | -0.119 |
lict | -0.117 |
Token | needs |
Token ID | 2476 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
liking | +1.627 |
motto | +1.616 |
Awesome | +1.589 |
effectiveness | +1.577 |
worth | +1.563 |
Neg logit contributions | |
theless | -2.446 |
ying | -2.256 |
ices | -2.160 |
zin | -2.155 |
lict | -2.115 |
Token | . |
Token ID | 13 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
theless | +0.872 |
ying | +0.808 |
ices | +0.766 |
zin | +0.763 |
lict | +0.750 |
Neg logit contributions | |
liking | -0.704 |
Awesome | -0.703 |
motto | -0.703 |
effectiveness | -0.678 |
worth | -0.673 |
Token |
|
Token ID | 198 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
theless | +0.512 |
ying | +0.475 |
ices | +0.451 |
zin | +0.450 |
lict | +0.445 |
Neg logit contributions | |
Awesome | -0.354 |
liking | -0.353 |
motto | -0.353 |
effectiveness | -0.340 |
worth | -0.338 |
Token |
|
Token ID | 198 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
theless | +0.539 |
ying | +0.513 |
ices | +0.486 |
zin | +0.482 |
lict | +0.471 |
Neg logit contributions | |
motto | -0.432 |
liking | -0.428 |
Awesome | -0.424 |
� | -0.416 |
olicy | -0.413 |
Token | " |
Token ID | 1 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
theless | +0.390 |
ying | +0.356 |
ices | +0.338 |
zin | +0.337 |
lict | +0.332 |
Neg logit contributions | |
Awesome | -0.319 |
liking | -0.314 |
motto | -0.313 |
effectiveness | -0.303 |
worth | -0.303 |
Token | These |
Token ID | 4711 |
Feature activation | +7.04e+00 |
Pos logit contributions | |
Awesome | +1.381 |
liking | +1.328 |
motto | +1.321 |
OUNT | +1.283 |
worth | +1.281 |
Neg logit contributions | |
theless | -2.150 |
ying | -1.969 |
zin | -1.880 |
ices | -1.871 |
lict | -1.859 |
Token | programs |
Token ID | 4056 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
theless | +6.743 |
ying | +6.283 |
ices | +6.001 |
zin | +5.923 |
lict | +5.860 |
Neg logit contributions | |
Awesome | -4.502 |
motto | -4.409 |
liking | -4.409 |
olicy | -4.323 |
OUNT | -4.247 |
Token | can |
Token ID | 460 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
theless | +0.497 |
ying | +0.452 |
ices | +0.427 |
zin | +0.426 |
lict | +0.416 |
Neg logit contributions | |
motto | -0.509 |
liking | -0.509 |
Awesome | -0.504 |
effectiveness | -0.495 |
worth | -0.495 |
Token | protect |
Token ID | 1805 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
theless | +1.202 |
ying | +1.107 |
ices | +1.055 |
zin | +1.050 |
lict | +1.030 |
Neg logit contributions | |
motto | -0.909 |
liking | -0.909 |
Awesome | -0.903 |
effectiveness | -0.878 |
worth | -0.874 |
Token | consumers |
Token ID | 7008 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
liking | +1.433 |
motto | +1.421 |
Awesome | +1.403 |
effectiveness | +1.381 |
worth | +1.374 |
Neg logit contributions | |
theless | -2.407 |
ying | -2.236 |
ices | -2.134 |
zin | -2.132 |
lict | -2.090 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
theless | +2.352 |
ying | +2.190 |
ices | +2.065 |
zin | +2.057 |
lict | +2.017 |
Neg logit contributions | |
Awesome | -2.101 |
motto | -2.082 |
liking | -2.057 |
olicy | -2.000 |
OUNT | -1.992 |
Token | in |
Token ID | 287 |
Feature activation | +8.65e-05 |
Pos logit contributions | |
theless | +1.764 |
ying | +1.644 |
ices | +1.560 |
zin | +1.553 |
lict | +1.530 |
Neg logit contributions | |
Awesome | -1.262 |
motto | -1.257 |
liking | -1.256 |
effectiveness | -1.208 |
worth | -1.199 |
Token | lock |
Token ID | 5793 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
theless | +0.000 |
ying | +0.000 |
ices | +0.000 |
zin | +0.000 |
lict | +0.000 |
Neg logit contributions | |
liking | -0.000 |
motto | -0.000 |
Awesome | -0.000 |
effectiveness | -0.000 |
worth | -0.000 |
Token | step |
Token ID | 9662 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
liking | +0.023 |
motto | +0.023 |
Awesome | +0.023 |
effectiveness | +0.022 |
worth | +0.022 |
Neg logit contributions | |
theless | -0.049 |
ying | -0.046 |
zin | -0.044 |
ices | -0.044 |
lict | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
theless | +1.532 |
ying | +1.431 |
ices | +1.350 |
zin | +1.338 |
lict | +1.319 |
Neg logit contributions | |
Awesome | -1.303 |
motto | -1.292 |
liking | -1.289 |
olicy | -1.249 |
OUNT | -1.244 |
Token | Civil |
Token ID | 7511 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
theless | +0.445 |
ying | +0.411 |
ices | +0.390 |
zin | +0.388 |
lict | +0.382 |
Neg logit contributions | |
liking | -0.370 |
Awesome | -0.369 |
motto | -0.369 |
effectiveness | -0.356 |
worth | -0.354 |
Token | rights |
Token ID | 2489 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
theless | +2.724 |
ying | +2.537 |
ices | +2.392 |
zin | +2.364 |
lict | +2.335 |
Neg logit contributions | |
Awesome | -2.440 |
liking | -2.430 |
motto | -2.422 |
effectiveness | -2.339 |
olicy | -2.324 |
Token | and |
Token ID | 290 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
theless | +6.685 |
ying | +6.422 |
ices | +6.023 |
zin | +5.985 |
lict | +5.878 |
Neg logit contributions | |
Awesome | -5.096 |
liking | -5.057 |
motto | -5.020 |
olicy | -4.854 |
OUNT | -4.838 |
Token | civil |
Token ID | 3026 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
theless | +1.230 |
ying | +1.151 |
ices | +1.097 |
zin | +1.091 |
lict | +1.073 |
Neg logit contributions | |
Awesome | -0.803 |
liking | -0.798 |
motto | -0.798 |
effectiveness | -0.763 |
olicy | -0.757 |
Token | liberties |
Token ID | 22008 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
theless | +1.318 |
ying | +1.217 |
ices | +1.149 |
zin | +1.137 |
lict | +1.119 |
Neg logit contributions | |
Awesome | -1.289 |
liking | -1.282 |
motto | -1.279 |
effectiveness | -1.235 |
olicy | -1.231 |
Token | cross |
Token ID | 3272 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
theless | +5.857 |
ying | +5.534 |
ices | +5.174 |
zin | +5.100 |
lict | +5.063 |
Neg logit contributions | |
Awesome | -5.831 |
liking | -5.727 |
motto | -5.695 |
olicy | -5.601 |
OUNT | -5.539 |
Token | precon |
Token ID | 49394 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
theless | +9.369 |
ying | +9.208 |
ices | +8.690 |
zin | +8.423 |
lict | +8.421 |
Neg logit contributions | |
Awesome | -6.169 |
liking | -6.074 |
motto | -6.065 |
OUNT | -5.957 |
olicy | -5.908 |
Token | " |
Token ID | 1 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
theless | +1.060 |
ying | +0.971 |
ices | +0.918 |
zin | +0.914 |
lict | +0.898 |
Neg logit contributions | |
Awesome | -0.984 |
liking | -0.979 |
motto | -0.976 |
effectiveness | -0.946 |
worth | -0.942 |
Token | But |
Token ID | 1537 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
Awesome | +1.167 |
liking | +1.110 |
motto | +1.106 |
OUNT | +1.081 |
worth | +1.072 |
Neg logit contributions | |
theless | -1.886 |
ying | -1.734 |
zin | -1.663 |
ices | -1.652 |
lict | -1.648 |
Token | then |
Token ID | 788 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
liking | +0.558 |
motto | +0.555 |
Awesome | +0.554 |
effectiveness | +0.535 |
worth | +0.533 |
Neg logit contributions | |
theless | -0.894 |
ying | -0.833 |
ices | -0.797 |
zin | -0.794 |
lict | -0.783 |
Token | we |
Token ID | 356 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
theless | +0.318 |
ying | +0.296 |
ices | +0.282 |
zin | +0.281 |
lict | +0.277 |
Neg logit contributions | |
liking | -0.219 |
motto | -0.219 |
Awesome | -0.218 |
effectiveness | -0.210 |
worth | -0.209 |
Token | find |
Token ID | 1064 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
theless | +1.123 |
ying | +1.022 |
ices | +0.968 |
zin | +0.966 |
lict | +0.946 |
Neg logit contributions | |
motto | -1.120 |
liking | -1.117 |
Awesome | -1.108 |
worth | -1.083 |
effectiveness | -1.083 |
Token | other |
Token ID | 584 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
theless | +4.258 |
ying | +4.002 |
ices | +3.777 |
zin | +3.772 |
lict | +3.711 |
Neg logit contributions | |
Awesome | -2.887 |
motto | -2.860 |
liking | -2.859 |
olicy | -2.761 |
OUNT | -2.716 |
Token | turtles |
Token ID | 36288 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
theless | +6.515 |
ying | +6.151 |
zin | +5.777 |
ices | +5.775 |
lict | +5.688 |
Neg logit contributions | |
Awesome | -4.815 |
motto | -4.710 |
liking | -4.692 |
olicy | -4.659 |
� | -4.570 |
Token | that |
Token ID | 326 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
theless | +2.874 |
ying | +2.691 |
ices | +2.554 |
zin | +2.546 |
lict | +2.505 |
Neg logit contributions | |
Awesome | -1.876 |
motto | -1.866 |
liking | -1.858 |
effectiveness | -1.787 |
olicy | -1.781 |
Token | have |
Token ID | 423 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
liking | +0.016 |
motto | +0.016 |
Awesome | +0.015 |
worth | +0.015 |
effectiveness | +0.015 |
Neg logit contributions | |
theless | -0.012 |
ying | -0.011 |
ices | -0.010 |
zin | -0.010 |
lict | -0.010 |
Token | one |
Token ID | 530 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
theless | +3.573 |
ying | +3.250 |
ices | +3.046 |
zin | +3.033 |
lict | +2.954 |
Neg logit contributions | |
Awesome | -4.249 |
motto | -4.200 |
liking | -4.185 |
olicy | -4.095 |
OUNT | -4.069 |
Token | piece |
Token ID | 3704 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
theless | +2.425 |
ying | +2.260 |
zin | +2.134 |
ices | +2.132 |
lict | +2.096 |
Neg logit contributions | |
Awesome | -1.896 |
liking | -1.885 |
motto | -1.880 |
effectiveness | -1.811 |
olicy | -1.805 |
Token | Elder |
Token ID | 15624 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
theless | +3.242 |
ying | +3.040 |
ices | +2.896 |
zin | +2.882 |
lict | +2.827 |
Neg logit contributions | |
liking | -2.247 |
Awesome | -2.237 |
motto | -2.233 |
effectiveness | -2.149 |
worth | -2.124 |
Token | , |
Token ID | 11 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
theless | +4.251 |
ying | +3.929 |
zin | +3.731 |
ices | +3.687 |
meyer | +3.651 |
Neg logit contributions | |
Awesome | -4.072 |
motto | -4.057 |
liking | -4.040 |
effectiveness | -3.939 |
olicy | -3.916 |
Token | who |
Token ID | 508 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
theless | +0.820 |
ying | +0.763 |
ices | +0.720 |
zin | +0.716 |
lict | +0.701 |
Neg logit contributions | |
Awesome | -0.710 |
motto | -0.702 |
liking | -0.700 |
effectiveness | -0.679 |
olicy | -0.672 |
Token | is |
Token ID | 318 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
theless | +1.493 |
ying | +1.386 |
ices | +1.314 |
zin | +1.300 |
lict | +1.275 |
Neg logit contributions | |
Awesome | -1.289 |
liking | -1.275 |
motto | -1.274 |
effectiveness | -1.234 |
olicy | -1.227 |
Token | also |
Token ID | 635 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
liking | +1.031 |
motto | +1.026 |
Awesome | +1.018 |
worth | +0.982 |
effectiveness | +0.979 |
Neg logit contributions | |
theless | -1.643 |
ying | -1.524 |
ices | -1.455 |
zin | -1.451 |
lict | -1.429 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
theless | +0.212 |
ying | +0.200 |
ices | +0.191 |
zin | +0.190 |
lict | +0.188 |
Neg logit contributions | |
Awesome | -0.117 |
motto | -0.116 |
liking | -0.116 |
effectiveness | -0.111 |
olicy | -0.110 |
Token | former |
Token ID | 1966 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
theless | +1.492 |
ying | +1.391 |
ices | +1.322 |
zin | +1.319 |
lict | +1.297 |
Neg logit contributions | |
Awesome | -1.035 |
liking | -1.030 |
motto | -1.028 |
effectiveness | -0.991 |
worth | -0.982 |
Token | officer |
Token ID | 3818 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
theless | +0.148 |
ying | +0.138 |
ices | +0.132 |
zin | +0.131 |
lict | +0.129 |
Neg logit contributions | |
liking | -0.100 |
motto | -0.100 |
Awesome | -0.100 |
effectiveness | -0.096 |
worth | -0.095 |
Token | with |
Token ID | 351 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
theless | +1.033 |
ying | +0.952 |
ices | +0.902 |
zin | +0.897 |
lict | +0.882 |
Neg logit contributions | |
liking | -0.895 |
motto | -0.894 |
Awesome | -0.893 |
effectiveness | -0.863 |
worth | -0.859 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
motto | +0.961 |
liking | +0.959 |
Awesome | +0.952 |
effectiveness | +0.928 |
worth | +0.915 |
Neg logit contributions | |
theless | -1.867 |
ying | -1.730 |
ices | -1.655 |
zin | -1.652 |
lict | -1.632 |
Token | Minneapolis |
Token ID | 20455 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
theless | +0.266 |
ying | +0.248 |
ices | +0.236 |
zin | +0.236 |
lict | +0.232 |
Neg logit contributions | |
Awesome | -0.167 |
liking | -0.167 |
motto | -0.167 |
effectiveness | -0.160 |
worth | -0.159 |
Token | between |
Token ID | 1022 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
liking | +0.622 |
motto | +0.617 |
Awesome | +0.610 |
effectiveness | +0.595 |
worth | +0.593 |
Neg logit contributions | |
theless | -0.987 |
ying | -0.920 |
ices | -0.880 |
zin | -0.877 |
lict | -0.861 |
Token | the |
Token ID | 262 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
theless | +0.468 |
ying | +0.438 |
ices | +0.420 |
zin | +0.419 |
lict | +0.413 |
Neg logit contributions | |
liking | -0.253 |
motto | -0.251 |
Awesome | -0.248 |
effectiveness | -0.240 |
worth | -0.239 |
Token | frank |
Token ID | 14346 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
theless | +0.597 |
ying | +0.553 |
ices | +0.525 |
zin | +0.523 |
lict | +0.514 |
Neg logit contributions | |
liking | -0.474 |
motto | -0.473 |
Awesome | -0.469 |
effectiveness | -0.456 |
worth | -0.452 |
Token | practical |
Token ID | 8472 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
theless | +0.096 |
ying | +0.089 |
ices | +0.085 |
zin | +0.084 |
lict | +0.083 |
Neg logit contributions | |
liking | -0.068 |
motto | -0.068 |
Awesome | -0.067 |
effectiveness | -0.065 |
worth | -0.065 |
Token | ' |
Token ID | 705 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
liking | +0.263 |
motto | +0.262 |
Awesome | +0.259 |
effectiveness | +0.253 |
worth | +0.250 |
Neg logit contributions | |
theless | -0.400 |
ying | -0.371 |
ices | -0.355 |
zin | -0.353 |
lict | -0.350 |
Token | mid |
Token ID | 13602 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Awesome | +0.747 |
liking | +0.743 |
motto | +0.738 |
effectiveness | +0.711 |
worth | +0.708 |
Neg logit contributions | |
theless | -1.123 |
ying | -1.034 |
ices | -0.988 |
zin | -0.983 |
lict | -0.972 |
Token | - |
Token ID | 12 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
theless | +2.064 |
ying | +1.893 |
ices | +1.778 |
zin | +1.766 |
lict | +1.725 |
Neg logit contributions | |
Awesome | -2.260 |
liking | -2.257 |
motto | -2.254 |
effectiveness | -2.183 |
worth | -2.170 |
Token | western |
Token ID | 14197 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
theless | +0.596 |
ying | +0.540 |
ices | +0.508 |
zin | +0.506 |
lict | +0.497 |
Neg logit contributions | |
liking | -0.676 |
Awesome | -0.673 |
motto | -0.673 |
effectiveness | -0.655 |
worth | -0.652 |
Token | ' |
Token ID | 6 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
theless | +1.614 |
ying | +1.483 |
ices | +1.398 |
zin | +1.389 |
lict | +1.363 |
Neg logit contributions | |
Awesome | -1.604 |
liking | -1.602 |
motto | -1.601 |
effectiveness | -1.550 |
worth | -1.542 |
Token | type |
Token ID | 2099 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
liking | +0.559 |
motto | +0.559 |
Awesome | +0.548 |
effectiveness | +0.537 |
worth | +0.534 |
Neg logit contributions | |
theless | -0.687 |
ying | -0.632 |
ices | -0.600 |
zin | -0.600 |
lict | -0.590 |
Token | of |
Token ID | 286 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
liking | +0.422 |
motto | +0.421 |
Awesome | +0.414 |
effectiveness | +0.405 |
worth | +0.405 |
Neg logit contributions | |
theless | -0.528 |
ying | -0.486 |
ices | -0.461 |
zin | -0.460 |
lict | -0.454 |
Token | public |
Token ID | 1171 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
liking | +0.305 |
motto | +0.303 |
Awesome | +0.302 |
effectiveness | +0.291 |
worth | +0.288 |
Neg logit contributions | |
theless | -0.602 |
ying | -0.564 |
ices | -0.541 |
zin | -0.541 |
lict | -0.531 |
Token | view |
Token ID | 1570 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
theless | +2.115 |
ying | +1.987 |
ices | +1.907 |
zin | +1.904 |
lict | +1.874 |
Neg logit contributions | |
liking | -0.947 |
motto | -0.942 |
Awesome | -0.939 |
effectiveness | -0.896 |
worth | -0.888 |
Token | without |
Token ID | 1231 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
theless | +0.262 |
ying | +0.242 |
ices | +0.229 |
zin | +0.228 |
lict | +0.224 |
Neg logit contributions | |
liking | -0.224 |
motto | -0.223 |
Awesome | -0.223 |
effectiveness | -0.216 |
worth | -0.215 |
Token | a |
Token ID | 257 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
theless | +0.486 |
ying | +0.453 |
ices | +0.432 |
zin | +0.431 |
lict | +0.424 |
Neg logit contributions | |
liking | -0.299 |
motto | -0.298 |
Awesome | -0.298 |
effectiveness | -0.286 |
worth | -0.284 |
Token | word |
Token ID | 1573 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
theless | +4.127 |
ying | +3.911 |
ices | +3.710 |
zin | +3.687 |
lict | +3.632 |
Neg logit contributions | |
Awesome | -2.646 |
liking | -2.571 |
motto | -2.568 |
effectiveness | -2.483 |
olicy | -2.473 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
theless | +0.944 |
ying | +0.870 |
ices | +0.823 |
zin | +0.819 |
lict | +0.805 |
Neg logit contributions | |
liking | -0.842 |
motto | -0.841 |
Awesome | -0.841 |
effectiveness | -0.813 |
worth | -0.808 |
Token | the |
Token ID | 262 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
theless | +1.614 |
ying | +1.508 |
ices | +1.440 |
zin | +1.434 |
lict | +1.414 |
Neg logit contributions | |
liking | -0.959 |
motto | -0.957 |
Awesome | -0.957 |
effectiveness | -0.916 |
worth | -0.910 |
Token | authors |
Token ID | 7035 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
theless | +0.718 |
ying | +0.669 |
ices | +0.639 |
zin | +0.636 |
lict | +0.628 |
Neg logit contributions | |
liking | -0.454 |
motto | -0.451 |
Awesome | -0.449 |
effectiveness | -0.435 |
worth | -0.431 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
theless | +2.938 |
ying | +2.714 |
ices | +2.549 |
zin | +2.535 |
lict | +2.485 |
Neg logit contributions | |
Awesome | -2.852 |
motto | -2.839 |
liking | -2.834 |
effectiveness | -2.742 |
olicy | -2.717 |
Token | When |
Token ID | 1649 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
theless | +0.947 |
ying | +0.881 |
ices | +0.839 |
zin | +0.835 |
lict | +0.822 |
Neg logit contributions | |
liking | -0.658 |
motto | -0.657 |
Awesome | -0.656 |
effectiveness | -0.631 |
worth | -0.627 |
Token | the |
Token ID | 262 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
theless | +0.767 |
ying | +0.713 |
ices | +0.679 |
zin | +0.676 |
lict | +0.666 |
Neg logit contributions | |
liking | -0.541 |
motto | -0.539 |
Awesome | -0.538 |
effectiveness | -0.518 |
worth | -0.516 |
Token | have |
Token ID | 423 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
theless | +1.375 |
ying | +1.266 |
ices | +1.187 |
zin | +1.181 |
lict | +1.161 |
Neg logit contributions | |
Awesome | -1.435 |
liking | -1.432 |
motto | -1.429 |
effectiveness | -1.384 |
worth | -1.374 |
Token | broken |
Token ID | 5445 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
theless | +3.462 |
ying | +3.198 |
ices | +3.010 |
zin | +2.978 |
lict | +2.932 |
Neg logit contributions | |
Awesome | -3.358 |
liking | -3.291 |
motto | -3.255 |
olicy | -3.212 |
OUNT | -3.180 |
Token | off |
Token ID | 572 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
theless | +2.652 |
ying | +2.493 |
ices | +2.378 |
zin | +2.367 |
lict | +2.336 |
Neg logit contributions | |
Awesome | -1.421 |
liking | -1.416 |
motto | -1.414 |
effectiveness | -1.347 |
worth | -1.331 |
Token | to |
Token ID | 284 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
liking | +0.206 |
motto | +0.205 |
Awesome | +0.204 |
effectiveness | +0.198 |
worth | +0.198 |
Neg logit contributions | |
theless | -0.267 |
ying | -0.246 |
ices | -0.234 |
zin | -0.233 |
lict | -0.228 |
Token | form |
Token ID | 1296 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
theless | +0.998 |
ying | +0.925 |
ices | +0.877 |
zin | +0.873 |
lict | +0.858 |
Neg logit contributions | |
liking | -0.796 |
Awesome | -0.796 |
motto | -0.795 |
effectiveness | -0.766 |
worth | -0.761 |
Token | a |
Token ID | 257 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
liking | +0.243 |
motto | +0.242 |
Awesome | +0.240 |
effectiveness | +0.231 |
worth | +0.231 |
Neg logit contributions | |
theless | -0.450 |
ying | -0.420 |
ices | -0.402 |
zin | -0.401 |
lict | -0.396 |
Token | rival |
Token ID | 8976 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
theless | +2.907 |
ying | +2.729 |
zin | +2.587 |
ices | +2.583 |
lict | +2.537 |
Neg logit contributions | |
Awesome | -1.839 |
motto | -1.811 |
liking | -1.806 |
effectiveness | -1.739 |
olicy | -1.731 |
Token | organization |
Token ID | 4009 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
liking | +1.161 |
motto | +1.152 |
Awesome | +1.132 |
worth | +1.119 |
effectiveness | +1.114 |
Neg logit contributions | |
theless | -1.657 |
ying | -1.527 |
ices | -1.469 |
zin | -1.450 |
lict | -1.446 |
Token | , |
Token ID | 11 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
liking | +1.543 |
motto | +1.537 |
worth | +1.519 |
Awesome | +1.512 |
effectiveness | +1.485 |
Neg logit contributions | |
theless | -1.843 |
ying | -1.678 |
ices | -1.594 |
zin | -1.583 |
lict | -1.563 |
Token | called |
Token ID | 1444 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
theless | +0.605 |
ying | +0.564 |
ices | +0.537 |
zin | +0.535 |
lict | +0.527 |
Neg logit contributions | |
Awesome | -0.401 |
liking | -0.400 |
motto | -0.400 |
effectiveness | -0.384 |
worth | -0.380 |
Token | the |
Token ID | 262 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
motto | +1.924 |
liking | +1.922 |
Awesome | +1.885 |
worth | +1.854 |
effectiveness | +1.833 |
Neg logit contributions | |
theless | -3.724 |
ying | -3.449 |
ices | -3.335 |
zin | -3.309 |
lict | -3.289 |
Token | action |
Token ID | 2223 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
liking | +0.347 |
motto | +0.345 |
Awesome | +0.342 |
effectiveness | +0.332 |
worth | +0.330 |
Neg logit contributions | |
theless | -0.652 |
ying | -0.607 |
zin | -0.583 |
ices | -0.582 |
lict | -0.573 |
Token | against |
Token ID | 1028 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
theless | +0.833 |
ying | +0.776 |
ices | +0.739 |
zin | +0.735 |
lict | +0.724 |
Neg logit contributions | |
liking | -0.565 |
Awesome | -0.565 |
motto | -0.565 |
effectiveness | -0.543 |
worth | -0.538 |
Token | Vin |
Token ID | 11820 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
liking | +0.990 |
motto | +0.984 |
Awesome | +0.972 |
worth | +0.949 |
effectiveness | +0.948 |
Neg logit contributions | |
theless | -1.710 |
ying | -1.590 |
ices | -1.526 |
zin | -1.524 |
lict | -1.495 |
Token | od |
Token ID | 375 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
liking | +1.511 |
Awesome | +1.510 |
motto | +1.502 |
worth | +1.480 |
effectiveness | +1.478 |
Neg logit contributions | |
theless | -0.735 |
ying | -0.619 |
ices | -0.561 |
zin | -0.557 |
lict | -0.541 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
theless | +3.678 |
ying | +3.446 |
ices | +3.275 |
zin | +3.263 |
lict | +3.190 |
Neg logit contributions | |
Awesome | -2.802 |
motto | -2.778 |
liking | -2.762 |
effectiveness | -2.670 |
olicy | -2.650 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
theless | +0.203 |
ying | +0.189 |
ices | +0.180 |
zin | +0.179 |
lict | +0.177 |
Neg logit contributions | |
Awesome | -0.137 |
motto | -0.137 |
liking | -0.137 |
effectiveness | -0.131 |
worth | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
theless | +1.061 |
ying | +1.007 |
ices | +0.954 |
zin | +0.943 |
meyer | +0.924 |
Neg logit contributions | |
motto | -0.866 |
liking | -0.858 |
� | -0.847 |
Awesome | -0.847 |
olicy | -0.832 |
Token | J |
Token ID | 41 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
theless | +0.930 |
ying | +0.862 |
ices | +0.819 |
zin | +0.816 |
lict | +0.803 |
Neg logit contributions | |
Awesome | -0.690 |
liking | -0.689 |
motto | -0.688 |
effectiveness | -0.663 |
worth | -0.660 |
Token | ag |
Token ID | 363 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
liking | +0.205 |
Awesome | +0.205 |
motto | +0.205 |
effectiveness | +0.198 |
worth | +0.197 |
Neg logit contributions | |
theless | -0.213 |
ying | -0.196 |
ices | -0.185 |
zin | -0.184 |
lict | -0.181 |
Token | d |
Token ID | 67 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
motto | +2.493 |
liking | +2.467 |
Awesome | +2.461 |
effectiveness | +2.404 |
worth | +2.401 |
Neg logit contributions | |
theless | -2.818 |
ying | -2.504 |
ices | -2.376 |
zin | -2.372 |
lict | -2.340 |
Token | ish |
Token ID | 680 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
theless | +2.647 |
ying | +2.480 |
ices | +2.333 |
zin | +2.320 |
lict | +2.253 |
Neg logit contributions | |
liking | -2.764 |
Awesome | -2.757 |
motto | -2.746 |
effectiveness | -2.669 |
OUNT | -2.646 |
Token | a |
Token ID | 64 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
theless | +1.250 |
ying | +1.159 |
ices | +1.102 |
zin | +1.098 |
lict | +1.080 |
Neg logit contributions | |
Awesome | -0.917 |
motto | -0.917 |
liking | -0.916 |
effectiveness | -0.881 |
worth | -0.877 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
theless | +0.275 |
ying | +0.259 |
ices | +0.249 |
zin | +0.249 |
lict | +0.246 |
Neg logit contributions | |
liking | -0.092 |
motto | -0.092 |
Awesome | -0.092 |
effectiveness | -0.086 |
worth | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
theless | +0.326 |
ying | +0.297 |
ices | +0.280 |
zin | +0.279 |
lict | +0.274 |
Neg logit contributions | |
Awesome | -0.316 |
liking | -0.316 |
motto | -0.315 |
effectiveness | -0.305 |
worth | -0.305 |
Token | Sw |
Token ID | 2451 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
motto | +1.009 |
Awesome | +1.007 |
liking | +1.007 |
worth | +0.964 |
effectiveness | +0.963 |
Neg logit contributions | |
theless | -1.455 |
ying | -1.343 |
ices | -1.282 |
zin | -1.278 |
lict | -1.263 |
Token | immer |
Token ID | 10957 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
theless | +1.329 |
ying | +1.235 |
ices | +1.169 |
zin | +1.162 |
lict | +1.144 |
Neg logit contributions | |
liking | -1.126 |
motto | -1.125 |
Awesome | -1.125 |
effectiveness | -1.087 |
worth | -1.077 |
Token | means |
Token ID | 1724 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
theless | +0.785 |
ying | +0.731 |
ices | +0.696 |
zin | +0.693 |
lict | +0.683 |
Neg logit contributions | |
Awesome | -0.531 |
liking | -0.530 |
motto | -0.530 |
effectiveness | -0.509 |
worth | -0.505 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
liking | +2.152 |
motto | +2.145 |
Awesome | +2.101 |
worth | +2.066 |
effectiveness | +2.049 |
Neg logit contributions | |
theless | -3.409 |
ying | -3.137 |
ices | -3.028 |
zin | -3.019 |
lict | -2.967 |
Token | keep |
Token ID | 1394 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
theless | +1.044 |
ying | +0.970 |
ices | +0.918 |
zin | +0.913 |
lict | +0.900 |
Neg logit contributions | |
Awesome | -0.834 |
liking | -0.833 |
motto | -0.832 |
effectiveness | -0.802 |
worth | -0.797 |
Token | fit |
Token ID | 4197 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
liking | +0.125 |
motto | +0.125 |
Awesome | +0.125 |
effectiveness | +0.120 |
worth | +0.119 |
Neg logit contributions | |
theless | -0.213 |
ying | -0.199 |
ices | -0.190 |
zin | -0.189 |
lict | -0.186 |
Token | moving |
Token ID | 3867 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
liking | +2.617 |
motto | +2.583 |
Awesome | +2.566 |
worth | +2.517 |
effectiveness | +2.495 |
Neg logit contributions | |
theless | -3.757 |
ying | -3.480 |
ices | -3.326 |
zin | -3.294 |
lict | -3.243 |
Token | about |
Token ID | 546 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
liking | +0.579 |
motto | +0.578 |
Awesome | +0.575 |
effectiveness | +0.553 |
worth | +0.551 |
Neg logit contributions | |
theless | -1.007 |
ying | -0.940 |
ices | -0.899 |
zin | -0.897 |
lict | -0.883 |
Token | a |
Token ID | 257 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
liking | +0.323 |
motto | +0.322 |
Awesome | +0.321 |
effectiveness | +0.310 |
worth | +0.309 |
Neg logit contributions | |
theless | -0.478 |
ying | -0.443 |
ices | -0.423 |
zin | -0.420 |
lict | -0.416 |
Token | beer |
Token ID | 6099 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
theless | +2.440 |
ying | +2.287 |
ices | +2.173 |
zin | +2.172 |
lict | +2.130 |
Neg logit contributions | |
Awesome | -1.553 |
liking | -1.541 |
motto | -1.540 |
effectiveness | -1.481 |
worth | -1.468 |
Token | would |
Token ID | 561 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
theless | +0.976 |
ying | +0.904 |
ices | +0.859 |
zin | +0.855 |
lict | +0.842 |
Neg logit contributions | |
liking | -0.740 |
motto | -0.740 |
Awesome | -0.739 |
effectiveness | -0.712 |
worth | -0.708 |
Token | be |
Token ID | 307 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
theless | +0.518 |
ying | +0.476 |
ices | +0.453 |
zin | +0.451 |
lict | +0.443 |
Neg logit contributions | |
liking | -0.423 |
motto | -0.422 |
Awesome | -0.421 |
effectiveness | -0.408 |
worth | -0.407 |
Token | better |
Token ID | 1365 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
motto | +0.421 |
liking | +0.421 |
Awesome | +0.420 |
worth | +0.403 |
effectiveness | +0.401 |
Neg logit contributions | |
theless | -0.836 |
ying | -0.780 |
ices | -0.746 |
zin | -0.745 |
lict | -0.737 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
motto | +2.579 |
liking | +2.566 |
Awesome | +2.525 |
worth | +2.504 |
effectiveness | +2.475 |
Neg logit contributions | |
theless | -3.363 |
ying | -3.069 |
zin | -2.928 |
ices | -2.915 |
lict | -2.873 |
Token | His |
Token ID | 2399 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
theless | +0.053 |
ying | +0.049 |
ices | +0.047 |
zin | +0.046 |
lict | +0.046 |
Neg logit contributions | |
liking | -0.034 |
motto | -0.034 |
Awesome | -0.034 |
effectiveness | -0.033 |
worth | -0.033 |
Token | supporters |
Token ID | 5941 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
motto | +1.972 |
liking | +1.958 |
Awesome | +1.891 |
effectiveness | +1.871 |
worth | +1.848 |
Neg logit contributions | |
theless | -3.418 |
ying | -3.164 |
zin | -3.050 |
ices | -3.046 |
lict | -3.006 |
Token | will |
Token ID | 481 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
theless | +0.216 |
ying | +0.198 |
ices | +0.188 |
zin | +0.187 |
lict | +0.184 |
Neg logit contributions | |
liking | -0.211 |
motto | -0.210 |
Awesome | -0.207 |
worth | -0.203 |
effectiveness | -0.203 |
Token | stick |
Token ID | 4859 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
theless | +1.414 |
ying | +1.315 |
ices | +1.249 |
zin | +1.244 |
lict | +1.225 |
Neg logit contributions | |
Awesome | -1.017 |
liking | -1.015 |
motto | -1.015 |
effectiveness | -0.976 |
worth | -0.969 |
Token | with |
Token ID | 351 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
theless | +0.075 |
ying | +0.070 |
ices | +0.067 |
zin | +0.066 |
lict | +0.065 |
Neg logit contributions | |
liking | -0.051 |
motto | -0.051 |
Awesome | -0.051 |
effectiveness | -0.049 |
worth | -0.049 |
Token | appreciate |
Token ID | 9144 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
liking | +2.764 |
worth | +2.736 |
motto | +2.711 |
effectiveness | +2.625 |
investment | +2.619 |
Neg logit contributions | |
theless | -3.257 |
ying | -2.896 |
ices | -2.801 |
zin | -2.796 |
meyer | -2.736 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
liking | +0.803 |
motto | +0.796 |
Awesome | +0.790 |
effectiveness | +0.766 |
worth | +0.763 |
Neg logit contributions | |
theless | -1.473 |
ying | -1.375 |
ices | -1.321 |
zin | -1.316 |
lict | -1.299 |
Token | conditions |
Token ID | 3403 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
theless | +0.139 |
ying | +0.130 |
ices | +0.124 |
zin | +0.124 |
lict | +0.122 |
Neg logit contributions | |
Awesome | -0.075 |
liking | -0.074 |
motto | -0.074 |
effectiveness | -0.071 |
olicy | -0.070 |
Token | that |
Token ID | 326 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
theless | +1.577 |
ying | +1.474 |
ices | +1.397 |
zin | +1.391 |
lict | +1.371 |
Neg logit contributions | |
Awesome | -1.138 |
motto | -1.127 |
liking | -1.123 |
olicy | -1.080 |
effectiveness | -1.080 |
Token | they |
Token ID | 484 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
theless | +0.014 |
ying | +0.013 |
ices | +0.012 |
zin | +0.012 |
lict | +0.012 |
Neg logit contributions | |
liking | -0.011 |
motto | -0.011 |
Awesome | -0.010 |
effectiveness | -0.010 |
worth | -0.010 |
Token | 're |
Token ID | 821 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
motto | +0.996 |
liking | +0.993 |
worth | +0.973 |
effectiveness | +0.962 |
Awesome | +0.956 |
Neg logit contributions | |
theless | -1.065 |
ying | -0.965 |
ices | -0.924 |
zin | -0.923 |
meyer | -0.895 |
Token | working |
Token ID | 1762 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
liking | +1.385 |
motto | +1.364 |
Awesome | +1.338 |
worth | +1.331 |
effectiveness | +1.309 |
Neg logit contributions | |
theless | -2.172 |
ying | -2.007 |
zin | -1.928 |
ices | -1.925 |
lict | -1.885 |
Token | in |
Token ID | 287 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
theless | +1.464 |
ying | +1.372 |
ices | +1.309 |
zin | +1.305 |
lict | +1.286 |
Neg logit contributions | |
Awesome | -0.883 |
liking | -0.880 |
motto | -0.879 |
effectiveness | -0.840 |
olicy | -0.833 |
Token | ." |
Token ID | 526 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
liking | +0.064 |
motto | +0.063 |
Awesome | +0.063 |
effectiveness | +0.061 |
worth | +0.061 |
Neg logit contributions | |
theless | -0.074 |
ying | -0.068 |
ices | -0.064 |
zin | -0.064 |
lict | -0.063 |
Token | Vel |
Token ID | 17378 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
liking | +0.731 |
motto | +0.730 |
Awesome | +0.730 |
effectiveness | +0.704 |
worth | +0.699 |
Neg logit contributions | |
theless | -1.096 |
ying | -1.016 |
ices | -0.969 |
zin | -0.964 |
lict | -0.954 |
Token | ie |
Token ID | 494 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
theless | +0.013 |
ying | +0.012 |
ices | +0.011 |
zin | +0.011 |
lict | +0.011 |
Neg logit contributions | |
motto | -0.011 |
liking | -0.011 |
Awesome | -0.011 |
effectiveness | -0.010 |
olicy | -0.010 |
Token | informed |
Token ID | 35698 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
theless | +0.212 |
ying | +0.197 |
ices | +0.187 |
zin | +0.187 |
lict | +0.184 |
Neg logit contributions | |
motto | -0.148 |
liking | -0.148 |
Awesome | -0.148 |
effectiveness | -0.143 |
worth | -0.141 |
Token | non |
Token ID | 1729 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
theless | +2.241 |
ying | +2.104 |
ices | +1.999 |
zin | +1.993 |
lict | +1.952 |
Neg logit contributions | |
Awesome | -1.628 |
liking | -1.623 |
motto | -1.610 |
effectiveness | -1.553 |
olicy | -1.550 |
Token | |
Token ID | 3907 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
theless | +4.728 |
ying | +4.488 |
zin | +4.203 |
ices | +4.154 |
lict | +4.063 |
Neg logit contributions | |
Awesome | -4.938 |
liking | -4.921 |
motto | -4.904 |
OUNT | -4.748 |
effectiveness | -4.745 |
Token | int |
Token ID | 600 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
theless | +3.604 |
ying | +3.342 |
ices | +3.157 |
zin | +3.149 |
lict | +3.091 |
Neg logit contributions | |
liking | -2.962 |
motto | -2.958 |
Awesome | -2.956 |
effectiveness | -2.854 |
worth | -2.831 |
Token | ellectual |
Token ID | 29706 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
theless | +1.974 |
ying | +1.833 |
ices | +1.734 |
zin | +1.727 |
lict | +1.692 |
Neg logit contributions | |
motto | -1.777 |
liking | -1.773 |
Awesome | -1.773 |
effectiveness | -1.713 |
worth | -1.697 |
Token | I |
Token ID | 314 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
theless | +2.342 |
ying | +2.189 |
ices | +2.081 |
zin | +2.064 |
lict | +2.029 |
Neg logit contributions | |
Awesome | -1.788 |
liking | -1.784 |
motto | -1.777 |
effectiveness | -1.715 |
olicy | -1.706 |
Token | � |
Token ID | 447 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
motto | +0.174 |
liking | +0.174 |
Awesome | +0.172 |
worth | +0.169 |
effectiveness | +0.168 |
Neg logit contributions | |
theless | -0.165 |
ying | -0.148 |
ices | -0.141 |
zin | -0.139 |
lict | -0.137 |
Token | � |
Token ID | 247 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
liking | +0.337 |
motto | +0.336 |
Awesome | +0.335 |
effectiveness | +0.325 |
worth | +0.324 |
Neg logit contributions | |
theless | -0.389 |
ying | -0.357 |
ices | -0.339 |
zin | -0.338 |
lict | -0.330 |
Token | ve |
Token ID | 303 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
liking | +0.423 |
motto | +0.422 |
Awesome | +0.418 |
worth | +0.411 |
effectiveness | +0.406 |
Neg logit contributions | |
theless | -0.473 |
ying | -0.433 |
ices | -0.411 |
zin | -0.409 |
lict | -0.400 |
Token | ever |
Token ID | 1683 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
theless | +5.432 |
ying | +5.099 |
ices | +4.836 |
zin | +4.806 |
lict | +4.735 |
Neg logit contributions | |
Awesome | -4.187 |
motto | -4.098 |
liking | -4.098 |
olicy | -3.994 |
effectiveness | -3.968 |
Token | met |
Token ID | 1138 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
theless | +2.800 |
ying | +2.580 |
ices | +2.433 |
zin | +2.420 |
lict | +2.377 |
Neg logit contributions | |
Awesome | -2.663 |
liking | -2.659 |
motto | -2.657 |
effectiveness | -2.572 |
worth | -2.551 |
Token | running |
Token ID | 2491 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
liking | +1.201 |
motto | +1.200 |
Awesome | +1.182 |
effectiveness | +1.149 |
worth | +1.144 |
Neg logit contributions | |
theless | -2.082 |
ying | -1.916 |
ices | -1.850 |
zin | -1.844 |
lict | -1.821 |
Token | , |
Token ID | 11 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
motto | +3.099 |
liking | +3.061 |
Awesome | +3.020 |
worth | +2.990 |
effectiveness | +2.958 |
Neg logit contributions | |
theless | -4.472 |
ying | -4.062 |
zin | -3.902 |
ices | -3.890 |
lict | -3.873 |
Token | plan |
Token ID | 1410 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
theless | +0.696 |
ying | +0.653 |
ices | +0.623 |
zin | +0.621 |
lict | +0.612 |
Neg logit contributions | |
Awesome | -0.385 |
liking | -0.385 |
motto | -0.385 |
effectiveness | -0.368 |
worth | -0.365 |
Token | ks |
Token ID | 591 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
liking | +2.021 |
motto | +2.001 |
Awesome | +1.986 |
effectiveness | +1.957 |
worth | +1.936 |
Neg logit contributions | |
theless | -3.025 |
ying | -2.671 |
lict | -2.571 |
ices | -2.569 |
zin | -2.562 |
Token | , |
Token ID | 11 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
theless | +0.024 |
ying | +0.022 |
ices | +0.021 |
zin | +0.021 |
lict | +0.020 |
Neg logit contributions | |
liking | -0.021 |
Awesome | -0.021 |
motto | -0.021 |
effectiveness | -0.020 |
worth | -0.020 |
Token | lung |
Token ID | 12317 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
theless | +0.636 |
ying | +0.595 |
ices | +0.568 |
zin | +0.565 |
lict | +0.557 |
Neg logit contributions | |
liking | -0.376 |
Awesome | -0.376 |
motto | -0.375 |
effectiveness | -0.359 |
worth | -0.357 |
Token | es |
Token ID | 274 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
liking | +0.477 |
Awesome | +0.476 |
motto | +0.476 |
effectiveness | +0.464 |
worth | +0.462 |
Neg logit contributions | |
theless | -0.364 |
ying | -0.325 |
ices | -0.305 |
zin | -0.305 |
lict | -0.299 |
Token | , |
Token ID | 11 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
theless | +0.394 |
ying | +0.361 |
ices | +0.343 |
zin | +0.342 |
lict | +0.337 |
Neg logit contributions | |
liking | -0.329 |
Awesome | -0.329 |
motto | -0.329 |
effectiveness | -0.318 |
worth | -0.317 |
Token | bur |
Token ID | 4356 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
theless | +0.615 |
ying | +0.576 |
ices | +0.549 |
zin | +0.546 |
lict | +0.538 |
Neg logit contributions | |
Awesome | -0.365 |
liking | -0.365 |
motto | -0.364 |
effectiveness | -0.349 |
worth | -0.346 |
Token | pees |
Token ID | 42623 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
theless | +2.195 |
ying | +2.017 |
ices | +1.872 |
zin | +1.864 |
lict | +1.800 |
Neg logit contributions | |
liking | -2.759 |
motto | -2.755 |
Awesome | -2.753 |
effectiveness | -2.674 |
worth | -2.651 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
theless | +0.906 |
ying | +0.835 |
ices | +0.791 |
zin | +0.787 |
lict | +0.774 |
Neg logit contributions | |
liking | -0.780 |
motto | -0.779 |
Awesome | -0.779 |
effectiveness | -0.752 |
worth | -0.748 |
Token | oll |
Token ID | 692 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
Awesome | +1.983 |
motto | +1.957 |
liking | +1.950 |
worth | +1.908 |
effectiveness | +1.899 |
Neg logit contributions | |
theless | -3.086 |
ying | -2.802 |
ices | -2.672 |
zin | -2.662 |
lict | -2.622 |
Token | are |
Token ID | 389 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
theless | +4.044 |
ying | +3.808 |
ices | +3.619 |
zin | +3.575 |
meyer | +3.515 |
Neg logit contributions | |
liking | -3.357 |
Awesome | -3.355 |
motto | -3.294 |
olicy | -3.211 |
effectiveness | -3.178 |
Token | displayed |
Token ID | 9066 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
liking | +0.046 |
Awesome | +0.046 |
motto | +0.046 |
effectiveness | +0.044 |
worth | +0.043 |
Neg logit contributions | |
theless | -0.074 |
ying | -0.069 |
ices | -0.066 |
zin | -0.065 |
lict | -0.064 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
theless | +0.430 |
ying | +0.403 |
ices | +0.384 |
zin | +0.382 |
lict | +0.376 |
Neg logit contributions | |
Awesome | -0.273 |
liking | -0.272 |
motto | -0.272 |
effectiveness | -0.261 |
olicy | -0.258 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
motto | +0.757 |
liking | +0.753 |
Awesome | +0.750 |
effectiveness | +0.726 |
worth | +0.723 |
Neg logit contributions | |
theless | -1.397 |
ying | -1.300 |
ices | -1.250 |
zin | -1.250 |
lict | -1.225 |
Token | Maj |
Token ID | 12390 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
theless | +0.176 |
ying | +0.164 |
ices | +0.157 |
zin | +0.156 |
lict | +0.154 |
Neg logit contributions | |
liking | -0.107 |
motto | -0.107 |
Awesome | -0.107 |
effectiveness | -0.102 |
worth | -0.101 |
Token | uro |
Token ID | 1434 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Awesome | +3.964 |
liking | +3.922 |
motto | +3.883 |
olicy | +3.842 |
worth | +3.829 |
Neg logit contributions | |
theless | -5.395 |
ying | -4.721 |
zin | -4.557 |
ices | -4.528 |
lict | -4.456 |
Token | Water |
Token ID | 5638 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
theless | +0.201 |
ying | +0.187 |
ices | +0.179 |
zin | +0.178 |
lict | +0.176 |
Neg logit contributions | |
motto | -0.116 |
liking | -0.116 |
Awesome | -0.116 |
effectiveness | -0.111 |
worth | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
theless | +2.360 |
ying | +2.191 |
ices | +2.072 |
zin | +2.061 |
lict | +2.024 |
Neg logit contributions | |
liking | -2.033 |
motto | -2.033 |
Awesome | -2.031 |
effectiveness | -1.959 |
worth | -1.946 |
Token | Sew |
Token ID | 27347 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
theless | +0.550 |
ying | +0.509 |
ices | +0.485 |
zin | +0.484 |
lict | +0.477 |
Neg logit contributions | |
liking | -0.387 |
Awesome | -0.385 |
motto | -0.385 |
effectiveness | -0.372 |
worth | -0.370 |
Token | er |
Token ID | 263 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
theless | +3.149 |
ying | +2.968 |
ices | +2.710 |
zin | +2.677 |
lict | +2.612 |
Neg logit contributions | |
motto | -4.641 |
liking | -4.610 |
Awesome | -4.597 |
effectiveness | -4.477 |
olicy | -4.463 |
Token | YD |
Token ID | 35755 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
motto | +3.001 |
Awesome | +2.994 |
liking | +2.973 |
OUNT | +2.898 |
EGA | +2.870 |
Neg logit contributions | |
theless | -4.251 |
ying | -3.740 |
zin | -3.580 |
ices | -3.574 |
lict | -3.545 |
Token | has |
Token ID | 468 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
theless | +2.071 |
ying | +1.925 |
zin | +1.811 |
ices | +1.810 |
lict | +1.776 |
Neg logit contributions | |
Awesome | -1.683 |
liking | -1.671 |
motto | -1.647 |
olicy | -1.600 |
effectiveness | -1.595 |
Token | made |
Token ID | 925 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
theless | +3.190 |
ying | +2.937 |
ices | +2.745 |
zin | +2.730 |
lict | +2.695 |
Neg logit contributions | |
Awesome | -3.137 |
liking | -3.086 |
motto | -3.049 |
olicy | -2.985 |
OUNT | -2.974 |
Token | calculations |
Token ID | 16765 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
motto | +1.048 |
liking | +1.046 |
Awesome | +1.034 |
effectiveness | +1.003 |
worth | +0.995 |
Neg logit contributions | |
theless | -1.946 |
ying | -1.810 |
ices | -1.745 |
zin | -1.737 |
lict | -1.705 |
Token | in |
Token ID | 287 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
liking | +1.353 |
motto | +1.340 |
Awesome | +1.319 |
worth | +1.312 |
effectiveness | +1.296 |
Neg logit contributions | |
theless | -2.137 |
ying | -1.974 |
ices | -1.902 |
zin | -1.897 |
lict | -1.873 |
Token | its |
Token ID | 663 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
motto | +0.403 |
liking | +0.402 |
Awesome | +0.397 |
effectiveness | +0.386 |
worth | +0.383 |
Neg logit contributions | |
theless | -0.710 |
ying | -0.659 |
ices | -0.635 |
zin | -0.630 |
lict | -0.623 |
Token | own |
Token ID | 898 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
motto | +3.452 |
liking | +3.392 |
effectiveness | +3.312 |
worth | +3.242 |
Awesome | +3.208 |
Neg logit contributions | |
theless | -5.806 |
ying | -5.325 |
ices | -5.164 |
zin | -5.103 |
lict | -5.011 |
Token | long |
Token ID | 890 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
motto | +1.507 |
liking | +1.490 |
Awesome | +1.455 |
effectiveness | +1.436 |
worth | +1.423 |
Neg logit contributions | |
theless | -2.814 |
ying | -2.611 |
ices | -2.518 |
zin | -2.503 |
lict | -2.468 |
Token | - |
Token ID | 12 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
motto | +1.657 |
liking | +1.644 |
Awesome | +1.616 |
effectiveness | +1.600 |
worth | +1.598 |
Neg logit contributions | |
theless | -1.919 |
ying | -1.739 |
ices | -1.656 |
zin | -1.656 |
lict | -1.620 |
Token | term |
Token ID | 4354 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
theless | +0.541 |
ying | +0.502 |
ices | +0.478 |
zin | +0.476 |
lict | +0.468 |
Neg logit contributions | |
liking | -0.378 |
Awesome | -0.377 |
motto | -0.377 |
effectiveness | -0.363 |
worth | -0.361 |
Token | interest |
Token ID | 1393 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
motto | +1.647 |
liking | +1.641 |
effectiveness | +1.571 |
Awesome | +1.549 |
worth | +1.547 |
Neg logit contributions | |
theless | -4.359 |
ying | -4.081 |
ices | -3.964 |
zin | -3.944 |
lict | -3.870 |
Token | � |
Token ID | 447 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
theless | +0.550 |
ying | +0.513 |
ices | +0.488 |
zin | +0.486 |
lict | +0.478 |
Neg logit contributions | |
liking | -0.379 |
motto | -0.378 |
Awesome | -0.378 |
effectiveness | -0.364 |
worth | -0.361 |
Token | � |
Token ID | 251 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
liking | +0.189 |
motto | +0.189 |
Awesome | +0.188 |
effectiveness | +0.182 |
olicy | +0.180 |
Neg logit contributions | |
theless | -0.224 |
ying | -0.209 |
ices | -0.197 |
zin | -0.196 |
lict | -0.193 |
Token | There |
Token ID | 1318 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
Awesome | +0.595 |
liking | +0.593 |
motto | +0.593 |
worth | +0.570 |
effectiveness | +0.569 |
Neg logit contributions | |
theless | -0.871 |
ying | -0.808 |
ices | -0.769 |
zin | -0.765 |
lict | -0.758 |
Token | would |
Token ID | 561 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
theless | +3.129 |
ying | +2.872 |
ices | +2.710 |
zin | +2.697 |
lict | +2.655 |
Neg logit contributions | |
Awesome | -3.029 |
liking | -3.021 |
motto | -3.021 |
effectiveness | -2.915 |
olicy | -2.896 |
Token | be |
Token ID | 307 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
theless | +0.791 |
ying | +0.725 |
ices | +0.689 |
zin | +0.683 |
lict | +0.671 |
Neg logit contributions | |
liking | -0.715 |
motto | -0.713 |
Awesome | -0.712 |
effectiveness | -0.691 |
worth | -0.690 |
Token | massive |
Token ID | 4858 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
liking | +0.195 |
motto | +0.194 |
Awesome | +0.192 |
effectiveness | +0.186 |
worth | +0.186 |
Neg logit contributions | |
theless | -0.360 |
ying | -0.335 |
ices | -0.322 |
zin | -0.320 |
lict | -0.316 |
Token | outrage |
Token ID | 11616 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
liking | +4.783 |
investment | +4.642 |
effectiveness | +4.622 |
worth | +4.622 |
motto | +4.548 |
Neg logit contributions | |
theless | -8.032 |
ying | -7.244 |
ices | -7.205 |
zin | -7.020 |
lict | -7.017 |
Token | — |
Token ID | 851 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
theless | +1.279 |
ying | +1.191 |
ices | +1.130 |
zin | +1.127 |
lict | +1.107 |
Neg logit contributions | |
Awesome | -0.972 |
motto | -0.971 |
liking | -0.969 |
effectiveness | -0.933 |
olicy | -0.924 |
Token | and |
Token ID | 290 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
theless | +0.851 |
ying | +0.793 |
ices | +0.755 |
zin | +0.752 |
lict | +0.741 |
Neg logit contributions | |
liking | -0.568 |
motto | -0.567 |
Awesome | -0.567 |
effectiveness | -0.544 |
worth | -0.541 |
Token | rightly |
Token ID | 22956 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
theless | +0.831 |
ying | +0.775 |
ices | +0.741 |
zin | +0.737 |
lict | +0.727 |
Neg logit contributions | |
liking | -0.503 |
motto | -0.502 |
Awesome | -0.501 |
effectiveness | -0.482 |
worth | -0.479 |
Token | so |
Token ID | 523 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
liking | +0.894 |
motto | +0.889 |
Awesome | +0.889 |
worth | +0.870 |
effectiveness | +0.863 |
Neg logit contributions | |
theless | -0.978 |
ying | -0.899 |
ices | -0.855 |
zin | -0.843 |
lict | -0.839 |
Token | uffle |
Token ID | 18137 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
liking | +0.282 |
Awesome | +0.281 |
motto | +0.281 |
effectiveness | +0.274 |
worth | +0.272 |
Neg logit contributions | |
theless | -0.296 |
ying | -0.268 |
ices | -0.253 |
zin | -0.253 |
lict | -0.248 |
Token | appears |
Token ID | 3568 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
theless | +1.148 |
ying | +1.059 |
ices | +1.000 |
zin | +0.995 |
lict | +0.980 |
Neg logit contributions | |
Awesome | -1.014 |
liking | -1.010 |
motto | -1.008 |
effectiveness | -0.973 |
olicy | -0.966 |
Token | to |
Token ID | 284 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
theless | +1.841 |
ying | +1.720 |
ices | +1.630 |
zin | +1.622 |
lict | +1.600 |
Neg logit contributions | |
Awesome | -1.326 |
liking | -1.317 |
motto | -1.313 |
effectiveness | -1.262 |
OUNT | -1.252 |
Token | have |
Token ID | 423 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
theless | +1.040 |
ying | +0.941 |
ices | +0.881 |
zin | +0.875 |
lict | +0.856 |
Neg logit contributions | |
liking | -1.310 |
motto | -1.308 |
Awesome | -1.307 |
effectiveness | -1.271 |
worth | -1.265 |
Token | strengthened |
Token ID | 27324 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
theless | +3.430 |
ying | +3.173 |
ices | +2.977 |
zin | +2.973 |
lict | +2.917 |
Neg logit contributions | |
Awesome | -3.197 |
motto | -3.152 |
liking | -3.152 |
olicy | -3.050 |
OUNT | -3.032 |
Token | Mr |
Token ID | 1770 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
liking | +1.877 |
motto | +1.855 |
effectiveness | +1.821 |
Awesome | +1.804 |
worth | +1.792 |
Neg logit contributions | |
theless | -3.606 |
ying | -3.341 |
ices | -3.260 |
zin | -3.231 |
lict | -3.166 |
Token | . |
Token ID | 13 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
Awesome | +5.165 |
worth | +5.055 |
liking | +5.042 |
motto | +4.908 |
effectiveness | +4.831 |
Neg logit contributions | |
theless | -7.100 |
ying | -5.973 |
lict | -5.801 |
zin | -5.789 |
ices | -5.763 |
Token | Maduro |
Token ID | 33007 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
liking | +1.170 |
motto | +1.168 |
Awesome | +1.151 |
effectiveness | +1.112 |
worth | +1.106 |
Neg logit contributions | |
theless | -2.735 |
ying | -2.548 |
ices | -2.456 |
zin | -2.440 |
lict | -2.421 |
Token | � |
Token ID | 447 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
liking | +2.378 |
motto | +2.352 |
Awesome | +2.340 |
effectiveness | +2.297 |
worth | +2.289 |
Neg logit contributions | |
theless | -3.050 |
ying | -2.795 |
ices | -2.669 |
zin | -2.642 |
lict | -2.599 |
Token | � |
Token ID | 247 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
liking | +0.557 |
Awesome | +0.556 |
motto | +0.556 |
effectiveness | +0.539 |
worth | +0.536 |
Neg logit contributions | |
theless | -0.597 |
ying | -0.548 |
ices | -0.518 |
zin | -0.515 |
lict | -0.505 |
Token | s |
Token ID | 82 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
liking | +0.654 |
motto | +0.652 |
Awesome | +0.649 |
effectiveness | +0.632 |
worth | +0.630 |
Neg logit contributions | |
theless | -0.680 |
ying | -0.624 |
ices | -0.588 |
zin | -0.586 |
lict | -0.576 |
Token | SR |
Token ID | 12562 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
Awesome | +5.024 |
liking | +4.814 |
worth | +4.736 |
motto | +4.729 |
OUNT | +4.664 |
Neg logit contributions | |
theless | -6.727 |
ying | -5.938 |
ices | -5.727 |
zin | -5.680 |
lict | -5.647 |
Token | . |
Token ID | 13 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
Awesome | +4.627 |
liking | +4.539 |
motto | +4.509 |
worth | +4.492 |
olicy | +4.423 |
Neg logit contributions | |
theless | -6.366 |
ying | -5.683 |
zin | -5.386 |
lict | -5.351 |
ices | -5.331 |
Token | Width |
Token ID | 30916 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
Awesome | +2.058 |
liking | +1.974 |
motto | +1.946 |
worth | +1.910 |
OUNT | +1.876 |
Neg logit contributions | |
theless | -4.061 |
ying | -3.712 |
zin | -3.563 |
lict | -3.543 |
ices | -3.534 |
Token | , |
Token ID | 11 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
liking | +0.021 |
motto | +0.021 |
Awesome | +0.021 |
effectiveness | +0.021 |
worth | +0.020 |
Neg logit contributions | |
theless | -0.027 |
ying | -0.025 |
ices | -0.023 |
zin | -0.023 |
lict | -0.023 |
Token | $ |
Token ID | 3 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
Awesome | +0.378 |
liking | +0.377 |
motto | +0.376 |
effectiveness | +0.356 |
worth | +0.355 |
Neg logit contributions | |
theless | -0.957 |
ying | -0.898 |
ices | -0.862 |
zin | -0.861 |
lict | -0.852 |
Token | SR |
Token ID | 12562 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
Awesome | +3.499 |
liking | +3.352 |
worth | +3.227 |
OUNT | +3.217 |
motto | +3.212 |
Neg logit contributions | |
theless | -8.005 |
ying | -7.250 |
zin | -7.007 |
ices | -6.973 |
lict | -6.924 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
Awesome | +4.406 |
liking | +4.279 |
worth | +4.263 |
OUNT | +4.175 |
motto | +4.163 |
Neg logit contributions | |
theless | -5.495 |
ying | -4.781 |
lict | -4.572 |
zin | -4.552 |
ices | -4.510 |
Token | Height |
Token ID | 23106 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Awesome | +1.215 |
liking | +1.102 |
motto | +1.082 |
worth | +1.044 |
OUNT | +1.039 |
Neg logit contributions | |
theless | -4.414 |
ying | -4.091 |
zin | -3.971 |
lict | -3.956 |
ices | -3.926 |
Token | ) |
Token ID | 8 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Awesome | +1.335 |
liking | +1.327 |
motto | +1.326 |
worth | +1.278 |
effectiveness | +1.277 |
Neg logit contributions | |
theless | -2.046 |
ying | -1.888 |
zin | -1.794 |
ices | -1.793 |
lict | -1.773 |
Token | $ |
Token ID | 720 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
liking | +0.986 |
Awesome | +0.986 |
motto | +0.985 |
effectiveness | +0.944 |
worth | +0.941 |
Neg logit contributions | |
theless | -1.743 |
ying | -1.623 |
ices | -1.552 |
zin | -1.549 |
lict | -1.527 |
Token | image |
Token ID | 9060 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Awesome | +5.085 |
liking | +4.862 |
motto | +4.807 |
worth | +4.778 |
OUNT | +4.759 |
Neg logit contributions | |
theless | -6.213 |
ying | -5.513 |
zin | -5.241 |
ices | -5.223 |
lict | -5.171 |