Token | and |
Token ID | 290 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Claud | +2.028 |
RANT | +1.935 |
handles | +1.890 |
cler | +1.830 |
fter | +1.790 |
Neg logit contributions | |
atis | -3.232 |
RAW | -3.218 |
olla | -2.660 |
oho | -2.657 |
edes | -2.577 |
Token | Malcolm |
Token ID | 20002 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
Claud | +1.394 |
RANT | +1.337 |
handles | +1.295 |
cler | +1.249 |
fter | +1.243 |
Neg logit contributions | |
RAW | -2.181 |
atis | -2.158 |
olla | -1.783 |
oho | -1.772 |
Flavoring | -1.733 |
Token | III |
Token ID | 6711 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
RANT | +0.052 |
Claud | +0.051 |
handles | +0.049 |
fter | +0.047 |
cler | +0.046 |
Neg logit contributions | |
RAW | -0.069 |
atis | -0.069 |
olla | -0.056 |
oho | -0.056 |
ande | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -9.05e-03 |
Pos logit contributions | |
Claud | +0.755 |
RANT | +0.751 |
handles | +0.713 |
fter | +0.690 |
cler | +0.679 |
Neg logit contributions | |
RAW | -1.089 |
atis | -1.084 |
olla | -0.882 |
oho | -0.880 |
edes | -0.860 |
Token | King |
Token ID | 2677 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
atis | +0.111 |
RAW | +0.111 |
olla | +0.090 |
oho | +0.090 |
edes | +0.088 |
Neg logit contributions | |
Claud | -0.074 |
RANT | -0.074 |
handles | -0.070 |
fter | -0.068 |
cler | -0.066 |
Token | of |
Token ID | 286 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Claud | +1.798 |
RANT | +1.791 |
handles | +1.694 |
fter | +1.642 |
cler | +1.594 |
Neg logit contributions | |
RAW | -2.757 |
atis | -2.753 |
oho | -2.243 |
olla | -2.235 |
ande | -2.194 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Claud | +9.686 |
Rou | +8.889 |
handles | +8.563 |
Lithuania | +8.486 |
ith | +8.229 |
Neg logit contributions | |
RAW | -12.950 |
atis | -12.412 |
ItemTracker | -10.268 |
edes | -10.233 |
oho | -10.203 |
Token | Scots |
Token ID | 33860 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Claud | +8.087 |
handles | +7.421 |
cler | +7.341 |
Rou | +7.208 |
fter | +7.017 |
Neg logit contributions | |
RAW | -11.095 |
atis | -11.044 |
olla | -9.157 |
edes | -9.119 |
ande | -8.940 |
Token | married |
Token ID | 6405 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Claud | +2.747 |
RANT | +2.693 |
handles | +2.582 |
cler | +2.474 |
fter | +2.438 |
Neg logit contributions | |
RAW | -4.624 |
atis | -4.616 |
olla | -3.890 |
oho | -3.877 |
ande | -3.793 |
Token | his |
Token ID | 465 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Claud | +3.126 |
RANT | +2.933 |
handles | +2.768 |
cler | +2.741 |
fter | +2.704 |
Neg logit contributions | |
RAW | -4.686 |
atis | -4.676 |
oho | -3.823 |
olla | -3.787 |
Flavoring | -3.765 |
Token | sister |
Token ID | 6621 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Claud | +2.320 |
RANT | +2.191 |
handles | +2.139 |
cler | +2.131 |
fter | +2.076 |
Neg logit contributions | |
atis | -3.310 |
RAW | -3.282 |
olla | -2.658 |
oho | -2.630 |
Flavoring | -2.621 |
Token | done |
Token ID | 1760 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
RAW | +2.401 |
atis | +2.396 |
oho | +1.929 |
olla | +1.925 |
ande | +1.889 |
Neg logit contributions | |
RANT | -1.764 |
Claud | -1.735 |
handles | -1.659 |
fter | -1.612 |
cler | -1.562 |
Token | any |
Token ID | 597 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Claud | +0.686 |
RANT | +0.678 |
handles | +0.658 |
fter | +0.623 |
cler | +0.610 |
Neg logit contributions | |
atis | -1.057 |
RAW | -1.041 |
oho | -0.857 |
olla | -0.855 |
ande | -0.841 |
Token | % |
Token ID | 4 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
atis | +0.134 |
RAW | +0.133 |
oho | +0.108 |
olla | +0.108 |
ande | +0.106 |
Neg logit contributions | |
RANT | -0.095 |
Claud | -0.094 |
handles | -0.090 |
fter | -0.087 |
cler | -0.084 |
Token | on |
Token ID | 319 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
RAW | +2.203 |
atis | +2.194 |
oho | +1.769 |
olla | +1.766 |
ande | +1.732 |
Neg logit contributions | |
RANT | -1.595 |
Claud | -1.571 |
handles | -1.498 |
fter | -1.457 |
cler | -1.414 |
Token | two |
Token ID | 734 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
RAW | +4.507 |
atis | +4.451 |
oho | +3.571 |
olla | +3.553 |
ande | +3.502 |
Neg logit contributions | |
RANT | -3.356 |
Claud | -3.245 |
handles | -3.089 |
fter | -3.051 |
cler | -2.948 |
Token | mar |
Token ID | 1667 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
RAW | +1.006 |
atis | +1.005 |
oho | +0.806 |
olla | +0.804 |
ande | +0.789 |
Neg logit contributions | |
RANT | -0.771 |
Claud | -0.760 |
handles | -0.729 |
fter | -0.707 |
cler | -0.686 |
Token | ath |
Token ID | 776 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
rent | +8.316 |
Claud | +8.228 |
handles | +8.198 |
RANT | +8.094 |
ith | +8.073 |
Neg logit contributions | |
RAW | -12.672 |
atis | -12.444 |
oho | -10.786 |
Flavoring | -10.523 |
Chaser | -10.291 |
Token | ons |
Token ID | 684 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
RANT | +0.795 |
Claud | +0.788 |
handles | +0.757 |
fter | +0.717 |
anski | +0.682 |
Neg logit contributions | |
RAW | -2.027 |
atis | -2.010 |
oho | -1.718 |
olla | -1.705 |
Flavoring | -1.669 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Claud | +1.919 |
RANT | +1.905 |
handles | +1.873 |
fter | +1.751 |
handle | +1.661 |
Neg logit contributions | |
atis | -3.376 |
RAW | -3.329 |
oho | -2.807 |
olla | -2.773 |
ande | -2.762 |
Token | it |
Token ID | 340 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
atis | +0.149 |
RAW | +0.148 |
oho | +0.122 |
olla | +0.122 |
ande | +0.120 |
Neg logit contributions | |
Claud | -0.088 |
RANT | -0.088 |
handles | -0.084 |
fter | -0.080 |
cler | -0.078 |
Token | 's |
Token ID | 338 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
RAW | +1.183 |
atis | +1.179 |
oho | +0.960 |
olla | +0.958 |
ande | +0.943 |
Neg logit contributions | |
RANT | -0.766 |
Claud | -0.757 |
handles | -0.726 |
fter | -0.697 |
cler | -0.676 |
Token | or |
Token ID | 393 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
RAW | +0.368 |
atis | +0.367 |
oho | +0.296 |
olla | +0.294 |
ande | +0.290 |
Neg logit contributions | |
RANT | -0.276 |
Claud | -0.272 |
handles | -0.261 |
fter | -0.253 |
cler | -0.245 |
Token | 100 |
Token ID | 1802 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
RANT | +2.629 |
Claud | +2.609 |
handles | +2.547 |
fter | +2.408 |
cler | +2.357 |
Neg logit contributions | |
RAW | -3.696 |
atis | -3.672 |
oho | -3.016 |
ande | -3.001 |
edes | -2.963 |
Token | mg |
Token ID | 11296 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
RANT | +2.248 |
Claud | +2.214 |
handles | +2.113 |
fter | +1.997 |
cler | +1.920 |
Neg logit contributions | |
atis | -4.412 |
RAW | -4.377 |
ande | -3.629 |
olla | -3.621 |
oho | -3.606 |
Token | / |
Token ID | 14 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
RANT | +4.135 |
Claud | +4.112 |
handles | +3.962 |
fter | +3.735 |
cler | +3.728 |
Neg logit contributions | |
atis | -6.648 |
RAW | -6.622 |
oho | -5.498 |
ande | -5.426 |
olla | -5.422 |
Token | kg |
Token ID | 10025 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
RANT | +2.997 |
Claud | +2.974 |
handles | +2.771 |
fter | +2.668 |
pent | +2.538 |
Neg logit contributions | |
atis | -7.619 |
RAW | -7.510 |
oho | -6.465 |
olla | -6.420 |
ande | -6.373 |
Token | ) |
Token ID | 8 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
RANT | +4.222 |
Claud | +4.213 |
handles | +4.075 |
fter | +3.838 |
cler | +3.835 |
Neg logit contributions | |
atis | -6.096 |
RAW | -5.978 |
oho | -4.969 |
olla | -4.901 |
edes | -4.869 |
Token | also |
Token ID | 635 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Claud | +7.427 |
handles | +7.334 |
RANT | +6.767 |
cler | +6.625 |
fter | +6.607 |
Neg logit contributions | |
atis | -13.777 |
RAW | -13.450 |
oho | -11.665 |
ItemTracker | -11.531 |
olla | -11.395 |
Token | showed |
Token ID | 3751 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Claud | +7.053 |
handles | +6.920 |
cler | +6.345 |
RANT | +6.282 |
fter | +6.238 |
Neg logit contributions | |
atis | -13.652 |
RAW | -13.235 |
Flavoring | -11.372 |
ItemTracker | -11.117 |
oho | -11.063 |
Token | an |
Token ID | 281 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Claud | +5.024 |
RANT | +4.942 |
handles | +4.783 |
cler | +4.649 |
fter | +4.542 |
Neg logit contributions | |
atis | -9.058 |
RAW | -8.703 |
olla | -7.381 |
oho | -7.316 |
ande | -7.229 |
Token | antidepressant |
Token ID | 41897 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
RANT | +4.629 |
Claud | +4.327 |
handles | +4.262 |
fter | +4.195 |
cler | +4.040 |
Neg logit contributions | |
RAW | -7.735 |
atis | -7.652 |
olla | -6.460 |
oho | -6.391 |
Flavoring | -6.262 |
Token | - |
Token ID | 12 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
RANT | +2.533 |
Claud | +2.520 |
handles | +2.372 |
fter | +2.281 |
cler | +2.261 |
Neg logit contributions | |
RAW | -4.240 |
atis | -4.202 |
olla | -3.491 |
oho | -3.448 |
edes | -3.419 |
Token | but |
Token ID | 475 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
RAW | +0.736 |
atis | +0.733 |
oho | +0.594 |
olla | +0.593 |
ande | +0.579 |
Neg logit contributions | |
RANT | -0.513 |
Claud | -0.510 |
handles | -0.489 |
fter | -0.472 |
cler | -0.461 |
Token | will |
Token ID | 481 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Claud | +3.298 |
handles | +3.256 |
RANT | +3.079 |
fter | +3.026 |
cler | +2.984 |
Neg logit contributions | |
RAW | -5.435 |
atis | -5.304 |
olla | -4.493 |
oho | -4.360 |
ande | -4.298 |
Token | at |
Token ID | 379 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Claud | +3.310 |
handles | +3.236 |
handle | +3.147 |
fter | +3.126 |
RANT | +3.118 |
Neg logit contributions | |
RAW | -5.730 |
atis | -5.572 |
olla | -4.605 |
ItemTracker | -4.572 |
oho | -4.532 |
Token | least |
Token ID | 1551 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Claud | +1.843 |
RANT | +1.818 |
handles | +1.763 |
fter | +1.635 |
cler | +1.629 |
Neg logit contributions | |
atis | -3.395 |
RAW | -3.394 |
oho | -2.756 |
olla | -2.747 |
edes | -2.744 |
Token | devote |
Token ID | 24103 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
Claud | +1.986 |
RANT | +1.934 |
handles | +1.912 |
fter | +1.869 |
handle | +1.825 |
Neg logit contributions | |
RAW | -3.200 |
atis | -3.125 |
olla | -2.556 |
oho | -2.538 |
edes | -2.512 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Claud | +0.343 |
RANT | +0.338 |
handles | +0.328 |
fter | +0.314 |
cler | +0.309 |
Neg logit contributions | |
RAW | -0.503 |
atis | -0.501 |
oho | -0.410 |
olla | -0.408 |
ande | -0.400 |
Token | little |
Token ID | 1310 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Claud | +7.114 |
cler | +6.938 |
fter | +6.874 |
handle | +6.853 |
handles | +6.681 |
Neg logit contributions | |
RAW | -13.549 |
atis | -13.041 |
olla | -11.270 |
ItemTracker | -11.249 |
oho | -10.935 |
Token | thought |
Token ID | 1807 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Claud | +4.472 |
handles | +4.324 |
cler | +4.176 |
RANT | +4.088 |
fter | +4.033 |
Neg logit contributions | |
RAW | -7.621 |
atis | -7.585 |
olla | -6.251 |
edes | -6.218 |
oho | -6.174 |
Token | to |
Token ID | 284 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
RANT | +3.732 |
Claud | +3.723 |
handles | +3.614 |
fter | +3.509 |
cler | +3.385 |
Neg logit contributions | |
RAW | -6.569 |
atis | -6.482 |
olla | -5.379 |
oho | -5.325 |
edes | -5.290 |
Token | the |
Token ID | 262 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
Claud | +0.701 |
RANT | +0.693 |
handles | +0.668 |
fter | +0.633 |
cler | +0.628 |
Neg logit contributions | |
RAW | -1.103 |
atis | -1.093 |
olla | -0.889 |
oho | -0.888 |
edes | -0.872 |
Token | wall |
Token ID | 3355 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Claud | +0.593 |
RANT | +0.587 |
handles | +0.571 |
fter | +0.542 |
cler | +0.537 |
Neg logit contributions | |
RAW | -0.799 |
atis | -0.793 |
oho | -0.635 |
olla | -0.634 |
edes | -0.625 |
Token | or |
Token ID | 393 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
RANT | +2.084 |
Claud | +2.056 |
handles | +1.973 |
fter | +1.898 |
cler | +1.822 |
Neg logit contributions | |
atis | -3.410 |
RAW | -3.400 |
oho | -2.780 |
olla | -2.773 |
ande | -2.736 |
Token | 20 |
Token ID | 1160 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Claud | +4.259 |
RANT | +4.208 |
handles | +4.114 |
Rou | +3.814 |
handle | +3.796 |
Neg logit contributions | |
atis | -6.828 |
RAW | -6.770 |
oho | -5.596 |
ande | -5.582 |
olla | -5.458 |
Token | mg |
Token ID | 11296 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
RANT | +3.779 |
Claud | +3.751 |
handles | +3.654 |
fter | +3.412 |
cler | +3.268 |
Neg logit contributions | |
atis | -7.895 |
RAW | -7.813 |
oho | -6.468 |
ande | -6.462 |
olla | -6.451 |
Token | / |
Token ID | 14 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
RANT | +4.286 |
Claud | +4.233 |
handles | +4.106 |
fter | +3.912 |
cler | +3.832 |
Neg logit contributions | |
atis | -6.558 |
RAW | -6.546 |
oho | -5.362 |
olla | -5.296 |
ande | -5.291 |
Token | kg |
Token ID | 10025 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
RANT | +2.044 |
Claud | +2.006 |
fter | +1.912 |
handles | +1.907 |
rent | +1.812 |
Neg logit contributions | |
atis | -6.369 |
RAW | -6.221 |
oho | -5.404 |
olla | -5.375 |
ande | -5.339 |
Token | ) |
Token ID | 8 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
RANT | +2.962 |
Claud | +2.928 |
handles | +2.826 |
fter | +2.724 |
cler | +2.658 |
Neg logit contributions | |
atis | -3.744 |
RAW | -3.719 |
oho | -2.994 |
olla | -2.966 |
edes | -2.924 |
Token | significantly |
Token ID | 5566 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
Claud | +7.190 |
handles | +7.152 |
RANT | +6.604 |
handle | +6.406 |
cler | +6.385 |
Neg logit contributions | |
atis | -13.623 |
RAW | -13.069 |
oho | -11.287 |
ItemTracker | -11.070 |
Flavoring | -10.984 |
Token | reduced |
Token ID | 5322 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Claud | +5.995 |
handles | +5.937 |
RANT | +5.507 |
cler | +5.355 |
handle | +5.215 |
Neg logit contributions | |
atis | -11.927 |
RAW | -11.682 |
oho | -9.726 |
Flavoring | -9.640 |
ItemTracker | -9.635 |
Token | anxiety |
Token ID | 9751 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Claud | +4.457 |
RANT | +4.446 |
handles | +4.214 |
cler | +4.138 |
fter | +3.918 |
Neg logit contributions | |
atis | -7.032 |
RAW | -6.891 |
oho | -5.860 |
olla | -5.682 |
ande | -5.609 |
Token | - |
Token ID | 12 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
RANT | +3.857 |
Claud | +3.848 |
handles | +3.756 |
fter | +3.437 |
cler | +3.353 |
Neg logit contributions | |
RAW | -6.880 |
atis | -6.792 |
oho | -5.777 |
olla | -5.708 |
edes | -5.681 |
Token | like |
Token ID | 2339 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
RANT | +3.216 |
Claud | +3.154 |
handles | +2.997 |
fter | +2.935 |
pent | +2.827 |
Neg logit contributions | |
RAW | -5.442 |
atis | -5.377 |
olla | -4.509 |
oho | -4.487 |
Flavoring | -4.484 |
Token | A |
Token ID | 317 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
RAW | +0.563 |
atis | +0.562 |
olla | +0.451 |
oho | +0.449 |
ande | +0.443 |
Neg logit contributions | |
RANT | -0.414 |
Claud | -0.411 |
handles | -0.392 |
fter | -0.380 |
cler | -0.369 |
Token | uk |
Token ID | 2724 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
atis | +0.219 |
RAW | +0.219 |
olla | +0.174 |
oho | +0.174 |
ande | +0.170 |
Neg logit contributions | |
RANT | -0.185 |
Claud | -0.182 |
handles | -0.175 |
fter | -0.171 |
cler | -0.165 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
atis | +2.749 |
RAW | +2.732 |
oho | +2.198 |
olla | +2.186 |
ande | +2.156 |
Neg logit contributions | |
RANT | -2.238 |
Claud | -2.185 |
handles | -2.091 |
fter | -2.045 |
cler | -1.986 |
Token | 51 |
Token ID | 6885 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Claud | +1.229 |
RANT | +1.196 |
handles | +1.149 |
fter | +1.101 |
Rou | +1.083 |
Neg logit contributions | |
atis | -1.588 |
RAW | -1.580 |
oho | -1.266 |
olla | -1.263 |
ande | -1.249 |
Token | ( |
Token ID | 7 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Claud | +4.612 |
RANT | +4.564 |
handles | +4.382 |
fter | +4.177 |
ith | +4.013 |
Neg logit contributions | |
atis | -8.195 |
RAW | -8.171 |
oho | -6.725 |
olla | -6.663 |
ande | -6.550 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
RANT | +5.299 |
Claud | +5.259 |
fter | +4.823 |
handles | +4.820 |
fa | +4.651 |
Neg logit contributions | |
atis | -7.712 |
RAW | -7.409 |
ande | -6.227 |
oho | -6.213 |
olla | -6.133 |
Token | ), |
Token ID | 828 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Claud | +5.492 |
RANT | +5.332 |
fter | +5.212 |
handles | +5.134 |
ith | +4.756 |
Neg logit contributions | |
atis | -15.151 |
RAW | -14.979 |
oho | -12.764 |
Flavoring | -12.642 |
ande | -12.617 |
Token | 306 |
Token ID | 37255 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
Claud | +3.412 |
RANT | +3.284 |
handles | +3.176 |
fter | +3.007 |
Rou | +2.986 |
Neg logit contributions | |
atis | -4.721 |
RAW | -4.640 |
oho | -3.816 |
ande | -3.791 |
olla | -3.788 |
Token | - |
Token ID | 532 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
RANT | +3.158 |
Claud | +3.132 |
handles | +2.932 |
fter | +2.745 |
cler | +2.638 |
Neg logit contributions | |
RAW | -7.360 |
atis | -7.312 |
oho | -6.205 |
olla | -6.147 |
edes | -6.105 |
Token | 327 |
Token ID | 36203 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Claud | +4.244 |
RANT | +4.027 |
handles | +3.909 |
Rou | +3.726 |
fter | +3.703 |
Neg logit contributions | |
atis | -5.948 |
RAW | -5.775 |
olla | -4.932 |
oho | -4.884 |
imir | -4.831 |
Token | . |
Token ID | 764 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
RANT | +3.113 |
Claud | +3.077 |
handles | +2.876 |
Rou | +2.805 |
fter | +2.731 |
Neg logit contributions | |
atis | -5.401 |
RAW | -5.309 |
oho | -4.515 |
ande | -4.437 |
olla | -4.388 |
Token | VEL |
Token ID | 18697 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
RAW | +1.055 |
atis | +1.043 |
olla | +0.843 |
oho | +0.842 |
edes | +0.826 |
Neg logit contributions | |
RANT | -0.756 |
Claud | -0.747 |
handles | -0.714 |
fter | -0.691 |
cler | -0.676 |
Token | ER |
Token ID | 1137 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
RAW | +2.092 |
atis | +2.066 |
olla | +1.632 |
oho | +1.631 |
edes | +1.602 |
Neg logit contributions | |
RANT | -1.782 |
Claud | -1.772 |
handles | -1.709 |
fter | -1.679 |
cler | -1.633 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
RAW | +3.008 |
atis | +2.950 |
olla | +2.272 |
oho | +2.237 |
ande | +2.203 |
Neg logit contributions | |
RANT | -3.067 |
Claud | -3.049 |
fter | -2.972 |
handles | -2.962 |
cler | -2.865 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
RAW | +1.747 |
atis | +1.746 |
oho | +1.372 |
olla | +1.367 |
ande | +1.340 |
Neg logit contributions | |
RANT | -1.584 |
Claud | -1.563 |
handles | -1.503 |
fter | -1.465 |
cler | -1.423 |
Token | + |
Token ID | 10 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
RAW | +1.000 |
atis | +0.972 |
olla | +0.708 |
oho | +0.705 |
ande | +0.679 |
Neg logit contributions | |
Claud | -1.426 |
RANT | -1.419 |
handles | -1.382 |
fter | -1.352 |
cler | -1.339 |
Token | Pun |
Token ID | 14944 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
RAW | +2.779 |
atis | +2.752 |
oho | +2.197 |
olla | +2.185 |
edes | +2.146 |
Neg logit contributions | |
RANT | -2.226 |
Claud | -2.161 |
handles | -2.091 |
fter | -2.035 |
cler | -1.980 |
Token | ct |
Token ID | 310 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
isher | +6.873 |
fter | +6.712 |
Claud | +6.696 |
RANT | +6.617 |
handles | +6.486 |
Neg logit contributions | |
RAW | -13.806 |
atis | -13.441 |
edes | -11.621 |
behavi | -11.401 |
oho | -11.254 |
Token | ual |
Token ID | 723 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
RANT | +4.720 |
Claud | +4.621 |
handles | +4.401 |
fter | +4.257 |
rent | +4.217 |
Neg logit contributions | |
RAW | -5.118 |
atis | -4.952 |
Flavoring | -3.987 |
olla | -3.912 |
oho | -3.910 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
RANT | +0.776 |
Claud | +0.768 |
handles | +0.732 |
fter | +0.709 |
cler | +0.684 |
Neg logit contributions | |
atis | -1.219 |
RAW | -1.218 |
oho | -0.995 |
olla | -0.993 |
ande | -0.975 |
Token | Per |
Token ID | 2448 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
RAW | +1.618 |
atis | +1.613 |
oho | +1.288 |
olla | +1.284 |
ande | +1.259 |
Neg logit contributions | |
RANT | -1.283 |
Claud | -1.260 |
handles | -1.209 |
fter | -1.176 |
cler | -1.142 |
Token | ceptive |
Token ID | 25867 |
Feature activation | +8.84e-03 |
Pos logit contributions | |
fter | +8.314 |
Claud | +8.262 |
RANT | +8.179 |
pent | +8.176 |
handles | +8.130 |
Neg logit contributions | |
RAW | -10.887 |
atis | -10.323 |
oho | -8.231 |
Flavoring | -8.130 |
olla | -8.104 |
Token | in |
Token ID | 287 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Claud | +3.718 |
handles | +3.626 |
RANT | +3.545 |
cler | +3.543 |
fter | +3.421 |
Neg logit contributions | |
RAW | -6.599 |
atis | -6.407 |
olla | -5.450 |
oho | -5.448 |
edes | -5.293 |
Token | such |
Token ID | 884 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Claud | +1.786 |
RANT | +1.761 |
handles | +1.719 |
cler | +1.634 |
fter | +1.615 |
Neg logit contributions | |
RAW | -2.864 |
atis | -2.806 |
oho | -2.337 |
olla | -2.316 |
edes | -2.296 |
Token | a |
Token ID | 257 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Claud | +2.229 |
handles | +2.202 |
RANT | +2.150 |
cler | +2.080 |
fter | +2.076 |
Neg logit contributions | |
RAW | -3.581 |
atis | -3.552 |
oho | -2.954 |
olla | -2.919 |
edes | -2.856 |
Token | way |
Token ID | 835 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Claud | +5.058 |
handles | +4.906 |
cler | +4.897 |
RANT | +4.725 |
handle | +4.715 |
Neg logit contributions | |
RAW | -7.254 |
atis | -7.053 |
oho | -5.803 |
olla | -5.767 |
Flavoring | -5.691 |
Token | as |
Token ID | 355 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
Claud | +3.177 |
RANT | +3.163 |
handles | +3.060 |
fter | +2.978 |
cler | +2.895 |
Neg logit contributions | |
RAW | -5.591 |
atis | -5.435 |
olla | -4.554 |
oho | -4.521 |
ande | -4.410 |
Token | may |
Token ID | 743 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Claud | +6.343 |
handles | +6.095 |
fter | +5.675 |
cler | +5.661 |
RANT | +5.521 |
Neg logit contributions | |
RAW | -12.577 |
atis | -11.612 |
olla | -10.202 |
oho | -10.119 |
ande | -9.776 |
Token | tend |
Token ID | 4327 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Claud | +7.119 |
handle | +7.059 |
cler | +6.836 |
handles | +6.804 |
fter | +6.699 |
Neg logit contributions | |
RAW | -14.071 |
atis | -12.631 |
oho | -11.076 |
olla | -10.963 |
ItemTracker | -10.942 |
Token | to |
Token ID | 284 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
Claud | +3.849 |
RANT | +3.838 |
handles | +3.644 |
fter | +3.540 |
cler | +3.439 |
Neg logit contributions | |
RAW | -6.237 |
atis | -6.108 |
oho | -5.120 |
olla | -5.045 |
edes | -4.945 |
Token | the |
Token ID | 262 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
Claud | +5.225 |
handles | +5.038 |
RANT | +5.017 |
cler | +5.001 |
handle | +4.884 |
Neg logit contributions | |
RAW | -8.130 |
atis | -7.686 |
oho | -6.486 |
olla | -6.351 |
edes | -6.262 |
Token | instruction |
Token ID | 12064 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Claud | +5.721 |
cler | +5.671 |
handles | +5.549 |
RANT | +5.425 |
fter | +5.309 |
Neg logit contributions | |
RAW | -8.569 |
atis | -8.232 |
edes | -6.834 |
ande | -6.741 |
oho | -6.723 |
Token | of |
Token ID | 286 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Claud | +1.939 |
RANT | +1.934 |
handles | +1.852 |
fter | +1.790 |
cler | +1.750 |
Neg logit contributions | |
RAW | -3.152 |
atis | -3.101 |
oho | -2.561 |
olla | -2.558 |
edes | -2.511 |
Token | . |
Token ID | 13 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
RAW | +0.268 |
atis | +0.268 |
oho | +0.218 |
olla | +0.218 |
edes | +0.214 |
Neg logit contributions | |
RANT | -0.173 |
Claud | -0.171 |
handles | -0.163 |
fter | -0.158 |
cler | -0.152 |
Token | It |
Token ID | 632 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
Claud | +3.064 |
RANT | +2.915 |
handles | +2.758 |
Rou | +2.734 |
fter | +2.658 |
Neg logit contributions | |
RAW | -4.211 |
atis | -4.190 |
oho | -3.442 |
edes | -3.381 |
ande | -3.353 |
Token | was |
Token ID | 373 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
RAW | +0.462 |
atis | +0.459 |
oho | +0.371 |
olla | +0.370 |
edes | +0.363 |
Neg logit contributions | |
RANT | -0.317 |
Claud | -0.314 |
handles | -0.302 |
fter | -0.290 |
cler | -0.283 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Claud | +2.731 |
RANT | +2.628 |
handles | +2.583 |
fter | +2.437 |
cler | +2.436 |
Neg logit contributions | |
atis | -4.371 |
RAW | -4.345 |
Flavoring | -3.621 |
olla | -3.564 |
oho | -3.545 |
Token | jaw |
Token ID | 19218 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Claud | +1.201 |
RANT | +1.188 |
handles | +1.152 |
fter | +1.103 |
cler | +1.099 |
Neg logit contributions | |
RAW | -1.718 |
atis | -1.712 |
olla | -1.379 |
oho | -1.368 |
ande | -1.357 |
Token | - |
Token ID | 12 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Claud | +3.322 |
RANT | +3.292 |
handles | +3.245 |
fter | +3.077 |
rent | +2.963 |
Neg logit contributions | |
RAW | -5.723 |
atis | -5.652 |
Flavoring | -4.628 |
olla | -4.568 |
imir | -4.552 |
Token | dropping |
Token ID | 37554 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
RANT | +4.269 |
rent | +4.265 |
Claud | +4.206 |
fter | +3.952 |
handles | +3.872 |
Neg logit contributions | |
atis | -16.185 |
RAW | -16.165 |
Flavoring | -15.036 |
imir | -13.659 |
edes | -13.495 |
Token | play |
Token ID | 711 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
RAW | +0.207 |
atis | +0.205 |
olla | +0.165 |
oho | +0.165 |
ande | +0.163 |
Neg logit contributions | |
RANT | -0.149 |
Claud | -0.149 |
handles | -0.143 |
fter | -0.139 |
cler | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
RAW | +1.146 |
atis | +1.145 |
oho | +0.930 |
olla | +0.928 |
ande | +0.912 |
Neg logit contributions | |
RANT | -0.767 |
Claud | -0.755 |
handles | -0.720 |
fter | -0.698 |
cler | -0.675 |
Token | save |
Token ID | 3613 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
Claud | +1.184 |
RANT | +1.181 |
handles | +1.129 |
fter | +1.091 |
handle | +1.073 |
Neg logit contributions | |
atis | -1.632 |
RAW | -1.630 |
olla | -1.322 |
oho | -1.298 |
ande | -1.291 |
Token | a |
Token ID | 257 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
Claud | +0.012 |
RANT | +0.012 |
handles | +0.012 |
fter | +0.011 |
cler | +0.011 |
Neg logit contributions | |
atis | -0.019 |
RAW | -0.019 |
oho | -0.015 |
olla | -0.015 |
ande | -0.015 |
Token | ma |
Token ID | 17266 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
atis | +2.103 |
RAW | +2.098 |
oho | +1.699 |
olla | +1.696 |
ande | +1.666 |
Neg logit contributions | |
RANT | -1.521 |
Claud | -1.490 |
handles | -1.421 |
fter | -1.379 |
cler | -1.335 |
Token | l |
Token ID | 300 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
RANT | +0.081 |
Claud | +0.080 |
handles | +0.077 |
fter | +0.075 |
cler | +0.072 |
Neg logit contributions | |
RAW | -0.114 |
atis | -0.113 |
oho | -0.091 |
olla | -0.091 |
edes | -0.090 |
Token | una |
Token ID | 9613 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
RANT | +6.682 |
Claud | +6.561 |
handles | +6.510 |
fter | +6.463 |
ith | +6.428 |
Neg logit contributions | |
RAW | -4.296 |
atis | -4.019 |
Flavoring | -2.976 |
edes | -2.785 |
Chaser | -2.676 |
Token | o |
Token ID | 267 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Claud | +1.428 |
RANT | +1.418 |
handles | +1.373 |
fter | +1.337 |
cler | +1.292 |
Neg logit contributions | |
RAW | -2.211 |
atis | -2.172 |
oho | -1.755 |
olla | -1.744 |
edes | -1.743 |
Token | Kal |
Token ID | 12612 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Claud | +1.947 |
RANT | +1.937 |
handles | +1.873 |
fter | +1.838 |
cler | +1.759 |
Neg logit contributions | |
RAW | -3.082 |
atis | -3.013 |
oho | -2.446 |
olla | -2.427 |
edes | -2.420 |
Token | an |
Token ID | 272 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Claud | +5.256 |
RANT | +5.141 |
handles | +5.014 |
anski | +4.969 |
ith | +4.951 |
Neg logit contributions | |
RAW | -8.035 |
atis | -7.594 |
edes | -6.153 |
Flavoring | -6.104 |
olla | -6.037 |
Token | ial |
Token ID | 498 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ith | +3.189 |
Claud | +3.023 |
fa | +2.979 |
fter | +2.608 |
pent | +2.530 |
Neg logit contributions | |
RAW | -16.646 |
atis | -16.439 |
behavi | -14.993 |
Chaser | -14.967 |
edes | -14.122 |
Token | i |
Token ID | 72 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ith | +3.998 |
fter | +3.908 |
Claud | +3.867 |
RANT | +3.860 |
handles | +3.816 |
Neg logit contributions | |
RAW | -7.768 |
atis | -7.514 |
behavi | -6.377 |
oho | -6.155 |
edes | -6.093 |
Token | � |
Token ID | 134 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
RANT | +2.607 |
Claud | +2.564 |
handles | +2.485 |
fter | +2.452 |
ith | +2.409 |
Neg logit contributions | |
atis | -3.281 |
RAW | -3.249 |
ande | -2.571 |
oho | -2.541 |
edes | -2.538 |
Token | � |
Token ID | 119 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
RANT | +1.517 |
Claud | +1.476 |
fter | +1.400 |
handles | +1.384 |
ith | +1.269 |
Neg logit contributions | |
atis | -3.657 |
RAW | -3.650 |
oho | -3.083 |
olla | -3.078 |
ande | -3.065 |
Token | il |
Token ID | 346 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
RANT | +1.904 |
Claud | +1.877 |
handles | +1.812 |
fter | +1.757 |
cler | +1.686 |
Neg logit contributions | |
RAW | -2.901 |
atis | -2.889 |
oho | -2.335 |
olla | -2.321 |
ande | -2.292 |
Token | io |
Token ID | 952 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
RANT | +2.352 |
Claud | +2.331 |
handles | +2.259 |
fter | +2.226 |
ith | +2.163 |
Neg logit contributions | |
RAW | -2.910 |
atis | -2.856 |
edes | -2.250 |
olla | -2.237 |
ande | -2.230 |
Token | ly |
Token ID | 306 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
atis | +2.046 |
RAW | +2.024 |
oho | +1.531 |
olla | +1.500 |
ande | +1.480 |
Neg logit contributions | |
RANT | -2.478 |
Claud | -2.425 |
handles | -2.331 |
fter | -2.283 |
cler | -2.237 |
Token | tic |
Token ID | 13370 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
RAW | +3.972 |
atis | +3.965 |
oho | +3.206 |
olla | +3.160 |
ande | +3.124 |
Neg logit contributions | |
RANT | -2.685 |
Claud | -2.653 |
handles | -2.481 |
fter | -2.414 |
cler | -2.360 |
Token | agent |
Token ID | 5797 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Claud | +2.859 |
RANT | +2.859 |
handles | +2.745 |
fter | +2.547 |
cler | +2.543 |
Neg logit contributions | |
RAW | -5.334 |
atis | -5.315 |
oho | -4.434 |
edes | -4.369 |
olla | -4.366 |
Token | , |
Token ID | 11 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Claud | +2.360 |
RANT | +2.347 |
handles | +2.270 |
fter | +2.145 |
cler | +2.095 |
Neg logit contributions | |
atis | -4.132 |
RAW | -4.126 |
oho | -3.411 |
olla | -3.380 |
ande | -3.344 |
Token | also |
Token ID | 635 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Claud | +4.940 |
handles | +4.881 |
RANT | +4.690 |
cler | +4.390 |
fter | +4.324 |
Neg logit contributions | |
atis | -8.675 |
RAW | -8.492 |
oho | -7.089 |
olla | -7.087 |
Flavoring | -6.962 |
Token | showed |
Token ID | 3751 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
Claud | +7.289 |
handles | +7.217 |
cler | +6.608 |
RANT | +6.498 |
fter | +6.303 |
Neg logit contributions | |
atis | -13.526 |
RAW | -13.138 |
Flavoring | -11.156 |
ItemTracker | -10.927 |
olla | -10.861 |
Token | an |
Token ID | 281 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
Claud | +5.096 |
RANT | +4.981 |
handles | +4.880 |
cler | +4.716 |
handle | +4.396 |
Neg logit contributions | |
atis | -10.965 |
RAW | -10.504 |
olla | -9.065 |
oho | -8.822 |
ande | -8.820 |
Token | anx |
Token ID | 7296 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
RANT | +2.906 |
Claud | +2.644 |
handles | +2.517 |
fter | +2.251 |
cler | +2.238 |
Neg logit contributions | |
RAW | -12.005 |
atis | -11.978 |
olla | -10.535 |
Flavoring | -10.374 |
ande | -10.319 |
Token | io |
Token ID | 952 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
RANT | +1.938 |
Claud | +1.904 |
handles | +1.829 |
fter | +1.803 |
ith | +1.748 |
Neg logit contributions | |
RAW | -2.353 |
atis | -2.333 |
edes | -1.835 |
olla | -1.830 |
ande | -1.825 |
Token | ly |
Token ID | 306 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
atis | +2.440 |
RAW | +2.427 |
oho | +1.857 |
olla | +1.826 |
edes | +1.786 |
Neg logit contributions | |
RANT | -2.810 |
Claud | -2.766 |
handles | -2.670 |
fter | -2.595 |
cler | -2.548 |
Token | 100 |
Token ID | 1802 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
RANT | +2.629 |
Claud | +2.609 |
handles | +2.547 |
fter | +2.408 |
cler | +2.357 |
Neg logit contributions | |
RAW | -3.696 |
atis | -3.672 |
oho | -3.016 |
ande | -3.001 |
edes | -2.963 |
Token | mg |
Token ID | 11296 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
RANT | +2.248 |
Claud | +2.214 |
handles | +2.113 |
fter | +1.997 |
cler | +1.920 |
Neg logit contributions | |
atis | -4.412 |
RAW | -4.377 |
ande | -3.629 |
olla | -3.621 |
oho | -3.606 |
Token | / |
Token ID | 14 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
RANT | +4.135 |
Claud | +4.112 |
handles | +3.962 |
fter | +3.735 |
cler | +3.728 |
Neg logit contributions | |
atis | -6.648 |
RAW | -6.622 |
oho | -5.498 |
ande | -5.426 |
olla | -5.422 |
Token | kg |
Token ID | 10025 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
RANT | +2.997 |
Claud | +2.974 |
handles | +2.771 |
fter | +2.668 |
pent | +2.538 |
Neg logit contributions | |
atis | -7.619 |
RAW | -7.510 |
oho | -6.465 |
olla | -6.420 |
ande | -6.373 |
Token | ) |
Token ID | 8 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
RANT | +4.222 |
Claud | +4.213 |
handles | +4.075 |
fter | +3.838 |
cler | +3.835 |
Neg logit contributions | |
atis | -6.096 |
RAW | -5.978 |
oho | -4.969 |
olla | -4.901 |
edes | -4.869 |
Token | also |
Token ID | 635 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Claud | +7.427 |
handles | +7.334 |
RANT | +6.767 |
cler | +6.625 |
fter | +6.607 |
Neg logit contributions | |
atis | -13.777 |
RAW | -13.450 |
oho | -11.665 |
ItemTracker | -11.531 |
olla | -11.395 |
Token | showed |
Token ID | 3751 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Claud | +7.053 |
handles | +6.920 |
cler | +6.345 |
RANT | +6.282 |
fter | +6.238 |
Neg logit contributions | |
atis | -13.652 |
RAW | -13.235 |
Flavoring | -11.372 |
ItemTracker | -11.117 |
oho | -11.063 |
Token | an |
Token ID | 281 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Claud | +5.024 |
RANT | +4.942 |
handles | +4.783 |
cler | +4.649 |
fter | +4.542 |
Neg logit contributions | |
atis | -9.058 |
RAW | -8.703 |
olla | -7.381 |
oho | -7.316 |
ande | -7.229 |
Token | antidepressant |
Token ID | 41897 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
RANT | +4.629 |
Claud | +4.327 |
handles | +4.262 |
fter | +4.195 |
cler | +4.040 |
Neg logit contributions | |
RAW | -7.735 |
atis | -7.652 |
olla | -6.460 |
oho | -6.391 |
Flavoring | -6.262 |
Token | - |
Token ID | 12 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
RANT | +2.533 |
Claud | +2.520 |
handles | +2.372 |
fter | +2.281 |
cler | +2.261 |
Neg logit contributions | |
RAW | -4.240 |
atis | -4.202 |
olla | -3.491 |
oho | -3.448 |
edes | -3.419 |
Token | like |
Token ID | 2339 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
RANT | +4.293 |
Claud | +4.219 |
rent | +3.883 |
fter | +3.857 |
handles | +3.832 |
Neg logit contributions | |
atis | -7.936 |
RAW | -7.912 |
Flavoring | -6.706 |
olla | -6.706 |
oho | -6.587 |
Token | ( |
Token ID | 357 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Claud | +4.180 |
RANT | +4.038 |
handles | +4.031 |
cler | +3.698 |
fter | +3.667 |
Neg logit contributions | |
atis | -7.338 |
RAW | -7.178 |
oho | -6.024 |
edes | -6.001 |
olla | -5.930 |
Token | 30 |
Token ID | 1270 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
RANT | +3.024 |
Claud | +2.913 |
handles | +2.781 |
fter | +2.774 |
pent | +2.731 |
Neg logit contributions | |
atis | -3.997 |
RAW | -3.886 |
oho | -3.195 |
olla | -3.153 |
ande | -3.139 |
Token | mg |
Token ID | 11296 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
RANT | +3.194 |
Claud | +3.154 |
handles | +3.057 |
fter | +2.891 |
cler | +2.742 |
Neg logit contributions | |
atis | -6.749 |
RAW | -6.699 |
oho | -5.550 |
olla | -5.507 |
ande | -5.485 |
Token | / |
Token ID | 14 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
RANT | +3.444 |
Claud | +3.413 |
handles | +3.362 |
fter | +3.232 |
handle | +3.121 |
Neg logit contributions | |
atis | -7.130 |
RAW | -6.992 |
ande | -5.960 |
oho | -5.957 |
edes | -5.858 |
Token | kg |
Token ID | 10025 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
RANT | +1.870 |
Claud | +1.805 |
fter | +1.793 |
handles | +1.750 |
rent | +1.675 |
Neg logit contributions | |
atis | -5.642 |
RAW | -5.531 |
oho | -4.764 |
Flavoring | -4.737 |
olla | -4.721 |
Token | ) |
Token ID | 8 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
RANT | +3.294 |
Claud | +3.263 |
handles | +3.148 |
fter | +3.032 |
cler | +2.964 |
Neg logit contributions | |
atis | -4.269 |
RAW | -4.242 |
oho | -3.420 |
olla | -3.389 |
edes | -3.337 |
Token | administration |
Token ID | 3662 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Claud | +6.771 |
handles | +6.635 |
RANT | +6.226 |
cler | +5.990 |
handle | +5.924 |
Neg logit contributions | |
atis | -13.066 |
RAW | -12.500 |
ItemTracker | -10.870 |
oho | -10.834 |
edes | -10.709 |
Token | for |
Token ID | 329 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Claud | +3.912 |
handles | +3.768 |
RANT | +3.701 |
cler | +3.472 |
fter | +3.434 |
Neg logit contributions | |
atis | -7.183 |
RAW | -7.094 |
oho | -5.965 |
olla | -5.908 |
Flavoring | -5.856 |
Token | ≥ |
Token ID | 26870 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Claud | +2.486 |
RANT | +2.446 |
handles | +2.380 |
cler | +2.246 |
fter | +2.227 |
Neg logit contributions | |
atis | -3.526 |
RAW | -3.481 |
oho | -2.902 |
olla | -2.846 |
ande | -2.792 |
Token | 7 |
Token ID | 22 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
RANT | +3.963 |
Claud | +3.870 |
handles | +3.667 |
fter | +3.590 |
pent | +3.512 |
Neg logit contributions | |
atis | -5.589 |
RAW | -5.358 |
oho | -4.478 |
ande | -4.443 |
olla | -4.426 |
Token | consecutive |
Token ID | 12785 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
Claud | +4.892 |
RANT | +4.816 |
handles | +4.754 |
fter | +4.326 |
cler | +4.215 |
Neg logit contributions | |
atis | -9.721 |
RAW | -9.507 |
oho | -8.134 |
olla | -8.087 |
ande | -8.029 |
Token | variant |
Token ID | 15304 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Claud | +2.283 |
RANT | +2.261 |
handles | +2.161 |
fter | +2.072 |
cler | +2.001 |
Neg logit contributions | |
RAW | -3.463 |
atis | -3.455 |
oho | -2.846 |
olla | -2.781 |
edes | -2.750 |
Token | used |
Token ID | 973 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Claud | +3.631 |
handles | +3.569 |
RANT | +3.491 |
fter | +3.210 |
handle | +3.196 |
Neg logit contributions | |
RAW | -5.713 |
atis | -5.710 |
oho | -4.682 |
olla | -4.561 |
Flavoring | -4.552 |
Token | a |
Token ID | 257 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Claud | +4.109 |
handles | +4.026 |
RANT | +3.905 |
fter | +3.746 |
handle | +3.713 |
Neg logit contributions | |
atis | -6.610 |
RAW | -6.582 |
oho | -5.398 |
olla | -5.334 |
edes | -5.264 |
Token | " |
Token ID | 366 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Claud | +5.487 |
handles | +5.292 |
RANT | +5.114 |
handle | +5.111 |
fter | +5.025 |
Neg logit contributions | |
RAW | -7.782 |
atis | -7.763 |
oho | -6.295 |
Flavoring | -6.220 |
ItemTracker | -6.172 |
Token | pe |
Token ID | 431 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
RANT | +4.926 |
Claud | +4.729 |
fter | +4.622 |
handles | +4.612 |
rent | +4.470 |
Neg logit contributions | |
atis | -6.073 |
RAW | -5.914 |
Flavoring | -4.872 |
oho | -4.838 |
ande | -4.753 |
Token | ep |
Token ID | 538 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
fter | +5.964 |
RANT | +5.672 |
Claud | +5.615 |
handles | +5.497 |
ith | +5.484 |
Neg logit contributions | |
RAW | -8.576 |
atis | -8.407 |
Flavoring | -6.834 |
oho | -6.816 |
edes | -6.691 |
Token | " |
Token ID | 1 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
handles | +7.611 |
handle | +7.445 |
fter | +7.411 |
Claud | +7.318 |
RANT | +7.205 |
Neg logit contributions | |
RAW | -11.988 |
atis | -11.631 |
Flavoring | -10.321 |
ItemTracker | -9.858 |
edes | -9.546 |
Token | sight |
Token ID | 6504 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
Claud | +5.638 |
handles | +5.472 |
RANT | +5.441 |
handle | +5.309 |
fter | +5.109 |
Neg logit contributions | |
atis | -8.121 |
RAW | -8.034 |
oho | -6.743 |
Flavoring | -6.519 |
edes | -6.510 |
Token | located |
Token ID | 5140 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
RANT | +0.213 |
Claud | +0.211 |
handles | +0.202 |
fter | +0.195 |
cler | +0.190 |
Neg logit contributions | |
RAW | -0.314 |
atis | -0.313 |
oho | -0.255 |
olla | -0.253 |
ande | -0.249 |
Token | on |
Token ID | 319 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
RANT | +0.088 |
Claud | +0.087 |
handles | +0.083 |
fter | +0.080 |
cler | +0.078 |
Neg logit contributions | |
RAW | -0.127 |
atis | -0.127 |
oho | -0.103 |
olla | -0.102 |
ande | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
Claud | +3.945 |
RANT | +3.918 |
handles | +3.840 |
fter | +3.526 |
handle | +3.487 |
Neg logit contributions | |
RAW | -7.007 |
atis | -6.992 |
oho | -5.742 |
olla | -5.657 |
edes | -5.626 |
Token | Juda |
Token ID | 24771 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
RAW | +0.932 |
atis | +0.931 |
oho | +0.751 |
olla | +0.749 |
ande | +0.738 |
Neg logit contributions | |
RANT | -0.674 |
Claud | -0.666 |
handles | -0.636 |
fter | -0.616 |
cler | -0.601 |
Token | isation |
Token ID | 5612 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
atis | +0.440 |
RAW | +0.436 |
oho | +0.333 |
olla | +0.331 |
ande | +0.324 |
Neg logit contributions | |
RANT | -0.506 |
Claud | -0.497 |
handles | -0.479 |
fter | -0.468 |
cler | -0.456 |
Token | that |
Token ID | 326 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
atis | +2.690 |
RAW | +2.686 |
oho | +2.153 |
olla | +2.141 |
ande | +2.103 |
Neg logit contributions | |
RANT | -2.077 |
Claud | -2.030 |
handles | -1.935 |
fter | -1.912 |
cler | -1.829 |
Token | has |
Token ID | 468 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Claud | +1.805 |
RANT | +1.785 |
handles | +1.725 |
cler | +1.610 |
fter | +1.598 |
Neg logit contributions | |
RAW | -2.770 |
atis | -2.731 |
olla | -2.262 |
oho | -2.258 |
ande | -2.198 |
Token | be |
Token ID | 307 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Claud | +3.499 |
RANT | +3.499 |
handles | +3.388 |
cler | +3.278 |
fter | +3.167 |
Neg logit contributions | |
RAW | -5.566 |
atis | -5.443 |
olla | -4.493 |
oho | -4.425 |
ande | -4.413 |
Token | fall |
Token ID | 7207 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
RANT | +2.580 |
Claud | +2.561 |
handles | +2.475 |
fter | +2.444 |
ith | +2.361 |
Neg logit contributions | |
RAW | -2.303 |
atis | -2.257 |
olla | -1.727 |
oho | -1.672 |
ande | -1.669 |
Token | en |
Token ID | 268 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
ith | +4.958 |
Claud | +4.935 |
fter | +4.750 |
rent | +4.630 |
pent | +4.533 |
Neg logit contributions | |
RAW | -14.421 |
atis | -13.901 |
behavi | -12.269 |
Flavoring | -11.961 |
olla | -11.833 |
Token | Jerusalem |
Token ID | 10843 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
atis | +0.042 |
RAW | +0.042 |
oho | +0.034 |
olla | +0.034 |
ande | +0.033 |
Neg logit contributions | |
RANT | -0.028 |
Claud | -0.028 |
handles | -0.026 |
fter | -0.025 |
cler | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
RANT | +0.380 |
Claud | +0.376 |
handles | +0.361 |
fter | +0.345 |
cler | +0.337 |
Neg logit contributions | |
RAW | -0.592 |
atis | -0.590 |
olla | -0.481 |
oho | -0.480 |
ande | -0.472 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
atis | +0.383 |
RAW | +0.383 |
oho | +0.304 |
olla | +0.301 |
ande | +0.299 |
Neg logit contributions | |
RANT | -0.317 |
Claud | -0.316 |
handles | -0.298 |
fter | -0.291 |
cler | -0.282 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
Claud | +1.599 |
RANT | +1.586 |
handles | +1.521 |
fter | +1.490 |
ith | +1.425 |
Neg logit contributions | |
atis | -2.380 |
RAW | -2.344 |
oho | -1.930 |
ande | -1.899 |
olla | -1.888 |
Token | $ |
Token ID | 720 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
RANT | +0.752 |
Claud | +0.745 |
handles | +0.721 |
fter | +0.694 |
cler | +0.674 |
Neg logit contributions | |
atis | -0.958 |
RAW | -0.948 |
oho | -0.765 |
olla | -0.757 |
edes | -0.748 |
Token | rect |
Token ID | 2554 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
RAW | +1.391 |
atis | +1.386 |
oho | +1.110 |
olla | +1.108 |
ande | +1.086 |
Neg logit contributions | |
RANT | -1.073 |
Claud | -1.061 |
handles | -1.014 |
fter | -0.983 |
cler | -0.958 |
Token | 1 |
Token ID | 16 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
RAW | +5.171 |
atis | +5.064 |
olla | +4.003 |
oho | +3.958 |
ande | +3.856 |
Neg logit contributions | |
Claud | -5.252 |
RANT | -5.249 |
handles | -4.944 |
cler | -4.908 |
fter | -4.887 |
Token | = |
Token ID | 796 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
RAW | +3.427 |
atis | +3.350 |
olla | +2.573 |
oho | +2.547 |
ande | +2.463 |
Neg logit contributions | |
Claud | -4.220 |
RANT | -4.215 |
handles | -4.020 |
cler | -3.919 |
fter | -3.903 |
Token | New |
Token ID | 968 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
RAW | +0.734 |
atis | +0.732 |
oho | +0.569 |
olla | +0.567 |
ande | +0.554 |
Neg logit contributions | |
RANT | -0.722 |
Claud | -0.712 |
handles | -0.683 |
fter | -0.668 |
cler | -0.650 |
Token | - |
Token ID | 12 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
RANT | +1.101 |
Claud | +1.094 |
handles | +1.027 |
fter | +0.996 |
Rou | +0.962 |
Neg logit contributions | |
atis | -1.942 |
RAW | -1.896 |
olla | -1.584 |
oho | -1.575 |
ande | -1.574 |
Token | Object |
Token ID | 10267 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
RANT | +3.503 |
MON | +3.047 |
Catalog | +2.819 |
Claud | +2.642 |
Land | +2.507 |
Neg logit contributions | |
atis | -16.537 |
behavi | -14.629 |
metic | -14.055 |
imir | -14.039 |
RAW | -14.037 |
Token | System |
Token ID | 4482 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
RANT | +1.153 |
Claud | +1.149 |
handles | +1.102 |
fter | +1.062 |
cler | +1.029 |
Neg logit contributions | |
atis | -1.715 |
RAW | -1.703 |
olla | -1.387 |
oho | -1.380 |
ande | -1.365 |
Token | . |
Token ID | 13 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
RAW | +4.027 |
atis | +3.940 |
olla | +3.176 |
oho | +3.161 |
edes | +3.103 |
Neg logit contributions | |
RANT | -3.111 |
Claud | -3.061 |
handles | -2.925 |
fter | -2.834 |
cler | -2.804 |
Token | Draw |
Token ID | 25302 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
RANT | +2.910 |
Claud | +2.822 |
handles | +2.763 |
fter | +2.634 |
pent | +2.472 |
Neg logit contributions | |
atis | -5.121 |
RAW | -4.944 |
olla | -4.211 |
oho | -4.193 |
ande | -4.165 |
Token | ing |
Token ID | 278 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
RANT | +1.795 |
Claud | +1.745 |
fter | +1.707 |
handles | +1.701 |
ith | +1.623 |
Neg logit contributions | |
atis | -2.444 |
RAW | -2.367 |
olla | -1.915 |
oho | -1.902 |
ande | -1.874 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
RANT | +0.890 |
Claud | +0.889 |
handles | +0.846 |
fter | +0.816 |
cler | +0.792 |
Neg logit contributions | |
atis | -1.422 |
RAW | -1.420 |
olla | -1.168 |
oho | -1.168 |
ande | -1.137 |
Token | Article |
Token ID | 10172 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
RAW | +0.439 |
atis | +0.439 |
oho | +0.352 |
olla | +0.349 |
ande | +0.345 |
Neg logit contributions | |
Claud | -0.344 |
RANT | -0.341 |
handles | -0.320 |
fter | -0.312 |
cler | -0.304 |
Token | IV |
Token ID | 8363 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
Claud | +1.969 |
RANT | +1.917 |
handles | +1.898 |
fter | +1.791 |
cler | +1.755 |
Neg logit contributions | |
RAW | -2.957 |
atis | -2.902 |
oho | -2.382 |
olla | -2.368 |
ande | -2.365 |
Token | , |
Token ID | 11 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
Claud | +4.918 |
handles | +4.910 |
RANT | +4.738 |
fter | +4.481 |
cler | +4.292 |
Neg logit contributions | |
RAW | -9.487 |
atis | -9.285 |
olla | -7.849 |
oho | -7.823 |
ande | -7.674 |
Token | Section |
Token ID | 7275 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
Claud | +3.469 |
RANT | +3.402 |
handles | +3.305 |
fter | +3.232 |
cler | +3.080 |
Neg logit contributions | |
RAW | -3.931 |
atis | -3.878 |
oho | -3.118 |
olla | -3.098 |
ande | -3.064 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Claud | +5.910 |
handles | +5.590 |
RANT | +5.548 |
fter | +5.218 |
handle | +5.067 |
Neg logit contributions | |
RAW | -10.126 |
atis | -9.600 |
Flavoring | -8.385 |
ande | -8.106 |
edes | -8.071 |
Token | reads |
Token ID | 9743 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
handles | +6.709 |
Claud | +6.499 |
RANT | +6.390 |
fter | +6.217 |
cler | +5.740 |
Neg logit contributions | |
RAW | -12.684 |
atis | -12.381 |
olla | -10.474 |
oho | -10.260 |
Flavoring | -10.163 |
Token | , |
Token ID | 11 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
RANT | +3.472 |
Claud | +3.429 |
fter | +3.214 |
handles | +3.212 |
cler | +3.037 |
Neg logit contributions | |
atis | -6.424 |
RAW | -6.357 |
olla | -5.335 |
oho | -5.313 |
edes | -5.232 |
Token | in |
Token ID | 287 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
Claud | +4.792 |
RANT | +4.773 |
handles | +4.481 |
fter | +4.458 |
cler | +4.274 |
Neg logit contributions | |
RAW | -7.048 |
atis | -6.948 |
olla | -5.728 |
oho | -5.698 |
edes | -5.599 |
Token | full |
Token ID | 1336 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
RANT | +0.722 |
Claud | +0.718 |
handles | +0.686 |
fter | +0.669 |
cler | +0.652 |
Neg logit contributions | |
RAW | -1.003 |
atis | -0.994 |
oho | -0.810 |
olla | -0.804 |
edes | -0.795 |
Token | : |
Token ID | 25 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
RANT | +2.260 |
Claud | +2.235 |
handles | +2.109 |
fter | +2.064 |
cler | +1.981 |
Neg logit contributions | |
RAW | -3.941 |
atis | -3.936 |
oho | -3.262 |
olla | -3.246 |
ande | -3.194 |
Token | + |
Token ID | 10 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
RAW | +1.000 |
atis | +0.972 |
olla | +0.708 |
oho | +0.705 |
ande | +0.679 |
Neg logit contributions | |
Claud | -1.426 |
RANT | -1.419 |
handles | -1.382 |
fter | -1.352 |
cler | -1.339 |
Token | Pun |
Token ID | 14944 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
RAW | +2.779 |
atis | +2.752 |
oho | +2.197 |
olla | +2.185 |
edes | +2.146 |
Neg logit contributions | |
RANT | -2.226 |
Claud | -2.161 |
handles | -2.091 |
fter | -2.035 |
cler | -1.980 |
Token | ct |
Token ID | 310 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
isher | +6.873 |
fter | +6.712 |
Claud | +6.696 |
RANT | +6.617 |
handles | +6.486 |
Neg logit contributions | |
RAW | -13.806 |
atis | -13.441 |
edes | -11.621 |
behavi | -11.401 |
oho | -11.254 |
Token | ual |
Token ID | 723 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
RANT | +4.720 |
Claud | +4.621 |
handles | +4.401 |
fter | +4.257 |
rent | +4.217 |
Neg logit contributions | |
RAW | -5.118 |
atis | -4.952 |
Flavoring | -3.987 |
olla | -3.912 |
oho | -3.910 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
RANT | +0.776 |
Claud | +0.768 |
handles | +0.732 |
fter | +0.709 |
cler | +0.684 |
Neg logit contributions | |
atis | -1.219 |
RAW | -1.218 |
oho | -0.995 |
olla | -0.993 |
ande | -0.975 |
Token | Per |
Token ID | 2448 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
RAW | +1.618 |
atis | +1.613 |
oho | +1.288 |
olla | +1.284 |
ande | +1.259 |
Neg logit contributions | |
RANT | -1.283 |
Claud | -1.260 |
handles | -1.209 |
fter | -1.176 |
cler | -1.142 |
Token | ceptive |
Token ID | 25867 |
Feature activation | +8.84e-03 |
Pos logit contributions | |
fter | +8.314 |
Claud | +8.262 |
RANT | +8.179 |
pent | +8.176 |
handles | +8.130 |
Neg logit contributions | |
RAW | -10.887 |
atis | -10.323 |
oho | -8.231 |
Flavoring | -8.130 |
olla | -8.104 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
RANT | +0.076 |
Claud | +0.075 |
handles | +0.071 |
fter | +0.069 |
cler | +0.067 |
Neg logit contributions | |
RAW | -0.105 |
atis | -0.104 |
oho | -0.084 |
olla | -0.084 |
ande | -0.082 |
Token | Cos |
Token ID | 10437 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
RAW | +2.111 |
atis | +2.098 |
oho | +1.676 |
olla | +1.671 |
ande | +1.638 |
Neg logit contributions | |
RANT | -1.663 |
Claud | -1.623 |
handles | -1.560 |
fter | -1.519 |
cler | -1.476 |
Token | mopolitan |
Token ID | 44331 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
RANT | +1.826 |
Claud | +1.809 |
handles | +1.744 |
fter | +1.706 |
cler | +1.633 |
Neg logit contributions | |
RAW | -2.560 |
atis | -2.503 |
olla | -2.022 |
oho | -2.000 |
ande | -1.978 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
RANT | +1.821 |
Claud | +1.801 |
handles | +1.730 |
fter | +1.680 |
cler | +1.632 |
Neg logit contributions | |
RAW | -2.293 |
atis | -2.284 |
oho | -1.823 |
olla | -1.820 |
ande | -1.785 |
Token | times |
Token ID | 1661 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Claud | +2.245 |
RANT | +2.194 |
handles | +2.148 |
cler | +2.065 |
fter | +2.058 |
Neg logit contributions | |
atis | -3.110 |
RAW | -3.067 |
olla | -2.527 |
oho | -2.455 |
ande | -2.433 |
Token | it |
Token ID | 340 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Claud | +2.126 |
RANT | +2.125 |
handles | +2.028 |
fter | +1.945 |
cler | +1.906 |
Neg logit contributions | |
atis | -3.672 |
RAW | -3.671 |
olla | -3.030 |
oho | -3.009 |
edes | -2.947 |
Token | was |
Token ID | 373 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
handles | +3.205 |
Claud | +3.124 |
RANT | +3.011 |
cler | +2.883 |
handle | +2.787 |
Neg logit contributions | |
RAW | -5.390 |
atis | -5.286 |
olla | -4.400 |
Flavoring | -4.341 |
oho | -4.291 |
Token | made |
Token ID | 925 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Claud | +2.484 |
RANT | +2.423 |
handles | +2.403 |
cler | +2.269 |
fter | +2.238 |
Neg logit contributions | |
atis | -4.059 |
RAW | -3.978 |
olla | -3.317 |
oho | -3.253 |
Flavoring | -3.226 |
Token | in |
Token ID | 287 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
RANT | +3.831 |
Claud | +3.784 |
handles | +3.610 |
fter | +3.449 |
handle | +3.341 |
Neg logit contributions | |
atis | -6.875 |
RAW | -6.715 |
Flavoring | -5.605 |
olla | -5.601 |
edes | -5.569 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Claud | +2.873 |
RANT | +2.846 |
handles | +2.755 |
fter | +2.591 |
cler | +2.577 |
Neg logit contributions | |
atis | -4.424 |
RAW | -4.346 |
olla | -3.580 |
oho | -3.494 |
imir | -3.490 |
Token | - |
Token ID | 532 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Claud | +7.957 |
RANT | +7.335 |
handles | +7.255 |
Rou | +6.997 |
cler | +6.797 |
Neg logit contributions | |
atis | -11.205 |
RAW | -11.164 |
olla | -9.354 |
oho | -9.307 |
ande | -9.101 |
Token | December |
Token ID | 3426 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
RANT | +0.906 |
Claud | +0.894 |
handles | +0.818 |
fter | +0.792 |
cler | +0.741 |
Neg logit contributions | |
atis | -2.136 |
RAW | -2.101 |
oho | -1.795 |
olla | -1.790 |
ande | -1.759 |
Token | 13 |
Token ID | 1511 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
atis | +1.693 |
RAW | +1.691 |
oho | +1.317 |
olla | +1.311 |
ande | +1.285 |
Neg logit contributions | |
RANT | -1.660 |
Claud | -1.643 |
handles | -1.581 |
fter | -1.541 |
cler | -1.500 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
RAW | +3.095 |
atis | +3.061 |
olla | +2.495 |
oho | +2.488 |
edes | +2.444 |
Neg logit contributions | |
RANT | -2.084 |
Claud | -2.046 |
handles | -1.947 |
fter | -1.882 |
cler | -1.845 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Claud | +0.914 |
RANT | +0.900 |
handles | +0.871 |
fter | +0.828 |
Rou | +0.792 |
Neg logit contributions | |
atis | -1.680 |
RAW | -1.656 |
oho | -1.390 |
olla | -1.377 |
ande | -1.360 |
Token | largest |
Token ID | 4387 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
Claud | +1.422 |
RANT | +1.398 |
handles | +1.369 |
fter | +1.289 |
cler | +1.266 |
Neg logit contributions | |
atis | -2.403 |
RAW | -2.402 |
olla | -1.952 |
ande | -1.943 |
oho | -1.942 |
Token | and |
Token ID | 290 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Claud | +0.526 |
RANT | +0.525 |
handles | +0.507 |
fter | +0.485 |
cler | +0.478 |
Neg logit contributions | |
RAW | -0.740 |
atis | -0.738 |
olla | -0.601 |
ande | -0.592 |
oho | -0.592 |
Token | busiest |
Token ID | 42745 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
RAW | +2.710 |
atis | +2.699 |
oho | +2.181 |
olla | +2.159 |
ande | +2.118 |
Neg logit contributions | |
RANT | -2.069 |
Claud | -2.006 |
handles | -1.909 |
fter | -1.864 |
cler | -1.803 |
Token | p |
Token ID | 279 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Claud | +2.317 |
RANT | +2.269 |
handles | +2.263 |
cler | +2.123 |
fter | +2.114 |
Neg logit contributions | |
atis | -3.337 |
RAW | -3.324 |
olla | -2.730 |
ande | -2.716 |
edes | -2.647 |
Token | iers |
Token ID | 3183 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
RANT | +1.067 |
Claud | +1.049 |
handles | +1.009 |
fter | +0.981 |
ith | +0.931 |
Neg logit contributions | |
RAW | -2.506 |
atis | -2.501 |
olla | -2.080 |
oho | -2.074 |
ande | -2.059 |
Token | on |
Token ID | 319 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Claud | +2.049 |
RANT | +1.997 |
handles | +1.945 |
fter | +1.847 |
cler | +1.815 |
Neg logit contributions | |
RAW | -3.461 |
atis | -3.433 |
olla | -2.841 |
oho | -2.818 |
ande | -2.791 |
Token | New |
Token ID | 968 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
Claud | +7.333 |
handles | +6.884 |
Rou | +6.533 |
RANT | +6.477 |
handle | +6.409 |
Neg logit contributions | |
atis | -12.254 |
RAW | -12.237 |
olla | -10.334 |
ItemTracker | -9.978 |
ande | -9.948 |
Token | York |
Token ID | 1971 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Claud | +2.607 |
RANT | +2.406 |
handles | +2.352 |
fter | +2.266 |
Rou | +2.145 |
Neg logit contributions | |
RAW | -6.785 |
atis | -6.559 |
olla | -5.621 |
ande | -5.596 |
edes | -5.551 |
Token | � |
Token ID | 447 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
Claud | +3.521 |
handles | +3.399 |
RANT | +3.371 |
fter | +3.162 |
cler | +3.117 |
Neg logit contributions | |
atis | -6.776 |
RAW | -6.681 |
olla | -5.628 |
ande | -5.563 |
edes | -5.552 |
Token | � |
Token ID | 247 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
RANT | +0.048 |
Claud | +0.047 |
handles | +0.045 |
fter | +0.045 |
cler | +0.044 |
Neg logit contributions | |
atis | -0.043 |
RAW | -0.042 |
oho | -0.032 |
olla | -0.032 |
edes | -0.032 |
Token | s |
Token ID | 82 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
RANT | +1.369 |
Claud | +1.347 |
handles | +1.299 |
fter | +1.280 |
cler | +1.213 |
Neg logit contributions | |
RAW | -1.791 |
atis | -1.789 |
olla | -1.435 |
oho | -1.429 |
ande | -1.400 |
Token | receive |
Token ID | 3328 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
atis | +2.610 |
RAW | +2.609 |
oho | +2.051 |
olla | +2.047 |
ande | +2.008 |
Neg logit contributions | |
RANT | -2.328 |
Claud | -2.300 |
handles | -2.215 |
fter | -2.164 |
cler | -2.110 |
Token | emails |
Token ID | 7237 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
RAW | +3.549 |
atis | +3.545 |
oho | +2.912 |
olla | +2.906 |
ande | +2.859 |
Neg logit contributions | |
RANT | -2.088 |
Claud | -2.052 |
handles | -1.950 |
fter | -1.884 |
cler | -1.816 |
Token | containing |
Token ID | 7268 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
RAW | +5.783 |
atis | +5.669 |
olla | +4.116 |
edes | +3.988 |
oho | +3.971 |
Neg logit contributions | |
RANT | -8.557 |
Claud | -8.386 |
handles | -7.827 |
fter | -7.806 |
anski | -7.801 |
Token | news |
Token ID | 1705 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
RAW | +3.714 |
atis | +3.620 |
oho | +2.695 |
olla | +2.664 |
edes | +2.620 |
Neg logit contributions | |
RANT | -4.869 |
Claud | -4.792 |
handles | -4.619 |
fter | -4.540 |
anski | -4.445 |
Token | content |
Token ID | 2695 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
RAW | +2.038 |
atis | +2.036 |
oho | +1.611 |
olla | +1.606 |
ande | +1.579 |
Neg logit contributions | |
RANT | -1.711 |
Claud | -1.687 |
handles | -1.609 |
fter | -1.576 |
cler | -1.528 |
Token | , |
Token ID | 837 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
RAW | +7.736 |
atis | +7.579 |
oho | +5.859 |
olla | +5.830 |
edes | +5.795 |
Neg logit contributions | |
Claud | -6.607 |
RANT | -6.570 |
fter | -6.197 |
handles | -6.083 |
anski | -6.068 |
Token | updates |
Token ID | 5992 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
RAW | +11.517 |
atis | +11.371 |
edes | +9.210 |
phrine | +8.216 |
olla | +8.204 |
Neg logit contributions | |
Claud | -11.420 |
RANT | -11.383 |
fter | -11.135 |
merce | -10.943 |
pent | -10.626 |
Token | and |
Token ID | 290 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
atis | +2.646 |
RAW | +2.646 |
olla | +2.127 |
oho | +2.126 |
ande | +2.095 |
Neg logit contributions | |
RANT | -1.938 |
Claud | -1.903 |
handles | -1.806 |
fter | -1.769 |
cler | -1.709 |
Token | promotions |
Token ID | 20699 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
RAW | +5.120 |
atis | +4.999 |
oho | +3.437 |
olla | +3.421 |
edes | +3.330 |
Neg logit contributions | |
RANT | -7.911 |
Claud | -7.741 |
fter | -7.410 |
handles | -7.365 |
anski | -7.277 |
Token | from |
Token ID | 422 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
RAW | +3.241 |
atis | +3.235 |
oho | +2.614 |
olla | +2.613 |
ande | +2.571 |
Neg logit contributions | |
RANT | -2.232 |
Claud | -2.194 |
handles | -2.092 |
fter | -2.031 |
cler | -1.966 |
Token | The |
Token ID | 383 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
RAW | +1.802 |
atis | +1.799 |
oho | +1.429 |
olla | +1.425 |
ande | +1.397 |
Neg logit contributions | |
RANT | -1.506 |
Claud | -1.484 |
handles | -1.424 |
fter | -1.386 |
cler | -1.345 |
Token | piece |
Token ID | 3704 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Claud | +1.491 |
RANT | +1.476 |
handles | +1.413 |
fter | +1.370 |
cler | +1.343 |
Neg logit contributions | |
RAW | -2.014 |
atis | -2.000 |
oho | -1.601 |
olla | -1.598 |
Flavoring | -1.568 |
Token | that |
Token ID | 326 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Claud | +1.340 |
RANT | +1.338 |
handles | +1.279 |
fter | +1.231 |
cler | +1.191 |
Neg logit contributions | |
RAW | -2.130 |
atis | -2.114 |
oho | -1.733 |
olla | -1.718 |
ande | -1.692 |
Token | — |
Token ID | 851 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Claud | +1.093 |
RANT | +1.081 |
handles | +1.070 |
fter | +1.000 |
cler | +0.980 |
Neg logit contributions | |
RAW | -1.601 |
atis | -1.586 |
oho | -1.298 |
olla | -1.290 |
ande | -1.265 |
Token | by |
Token ID | 416 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Claud | +3.752 |
RANT | +3.636 |
handles | +3.622 |
fter | +3.569 |
cler | +3.501 |
Neg logit contributions | |
RAW | -5.845 |
atis | -5.845 |
ande | -4.749 |
edes | -4.748 |
olla | -4.743 |
Token | his |
Token ID | 465 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Claud | +1.811 |
RANT | +1.776 |
handles | +1.753 |
fter | +1.650 |
cler | +1.646 |
Neg logit contributions | |
atis | -2.823 |
RAW | -2.820 |
olla | -2.264 |
oho | -2.237 |
ande | -2.222 |
Token | own |
Token ID | 898 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
RAW | +6.512 |
atis | +6.436 |
oho | +5.337 |
olla | +5.334 |
ande | +5.184 |
Neg logit contributions | |
RANT | -4.452 |
Claud | -4.240 |
handles | -3.984 |
fter | -3.913 |
anski | -3.844 |
Token | admission |
Token ID | 13938 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
RAW | +10.628 |
atis | +10.194 |
olla | +8.382 |
edes | +7.977 |
oho | +7.972 |
Neg logit contributions | |
RANT | -11.558 |
Claud | -10.713 |
anski | -10.322 |
pent | -10.233 |
rent | -10.223 |
Token | — |
Token ID | 851 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
RANT | +0.857 |
Claud | +0.840 |
handles | +0.793 |
fter | +0.763 |
cler | +0.732 |
Neg logit contributions | |
RAW | -1.738 |
atis | -1.735 |
oho | -1.444 |
olla | -1.441 |
ande | -1.419 |
Token | has |
Token ID | 468 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
Claud | +0.393 |
RANT | +0.390 |
handles | +0.382 |
fter | +0.360 |
cler | +0.355 |
Neg logit contributions | |
RAW | -0.579 |
atis | -0.574 |
oho | -0.468 |
olla | -0.466 |
ande | -0.459 |
Token | inspired |
Token ID | 7867 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Claud | +0.652 |
RANT | +0.652 |
handles | +0.631 |
fter | +0.597 |
cler | +0.590 |
Neg logit contributions | |
atis | -0.971 |
RAW | -0.967 |
olla | -0.791 |
oho | -0.790 |
ande | -0.780 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
Claud | +1.138 |
RANT | +1.120 |
handles | +1.083 |
fter | +1.028 |
cler | +1.006 |
Neg logit contributions | |
atis | -1.852 |
RAW | -1.843 |
oho | -1.512 |
olla | -1.511 |
ande | -1.490 |
Token | States |
Token ID | 1829 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Claud | +3.898 |
RANT | +3.890 |
handles | +3.714 |
fter | +3.612 |
cler | +3.514 |
Neg logit contributions | |
RAW | -3.943 |
atis | -3.904 |
oho | -3.040 |
olla | -3.023 |
ande | -2.955 |
Token | often |
Token ID | 1690 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Claud | +2.096 |
RANT | +2.085 |
handles | +2.020 |
fter | +1.907 |
cler | +1.878 |
Neg logit contributions | |
RAW | -2.957 |
atis | -2.930 |
oho | -2.402 |
olla | -2.363 |
imir | -2.330 |
Token | carry |
Token ID | 3283 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Claud | +2.955 |
handles | +2.940 |
RANT | +2.805 |
handle | +2.746 |
fter | +2.727 |
Neg logit contributions | |
RAW | -4.688 |
atis | -4.613 |
oho | -3.761 |
olla | -3.661 |
Flavoring | -3.656 |
Token | My |
Token ID | 2011 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
RAW | +2.867 |
atis | +2.862 |
olla | +2.287 |
oho | +2.285 |
edes | +2.249 |
Neg logit contributions | |
RANT | -2.255 |
Claud | -2.205 |
handles | -2.108 |
fter | -2.069 |
anski | -1.998 |
Token | c |
Token ID | 66 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
atis | +4.482 |
RAW | +4.481 |
oho | +3.600 |
olla | +3.587 |
edes | +3.534 |
Neg logit contributions | |
RANT | -3.464 |
Claud | -3.395 |
handles | -3.283 |
fter | -3.153 |
cler | -3.104 |
Token | ob |
Token ID | 672 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
atis | +1.707 |
RAW | +1.706 |
oho | +1.332 |
olla | +1.325 |
ande | +1.298 |
Neg logit contributions | |
RANT | -1.685 |
Claud | -1.661 |
handles | -1.602 |
fter | -1.564 |
cler | -1.524 |
Token | acter |
Token ID | 7321 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
atis | +9.972 |
RAW | +8.272 |
olla | +7.565 |
edes | +7.382 |
oho | +7.128 |
Neg logit contributions | |
RANT | -12.860 |
Claud | -12.365 |
handles | -12.122 |
cler | -11.757 |
fter | -11.629 |
Token | ium |
Token ID | 1505 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
atis | +4.609 |
RAW | +4.428 |
oho | +3.245 |
edes | +3.219 |
olla | +3.195 |
Neg logit contributions | |
RANT | -7.316 |
Claud | -7.105 |
fter | -6.845 |
handles | -6.787 |
anski | -6.572 |
Token | le |
Token ID | 443 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
atis | +4.118 |
RAW | +4.058 |
olla | +3.108 |
edes | +3.096 |
oho | +3.089 |
Neg logit contributions | |
RANT | -4.315 |
Claud | -4.149 |
handles | -4.017 |
fter | -3.948 |
anski | -3.881 |
Token | p |
Token ID | 79 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
RANT | +0.705 |
Claud | +0.697 |
handles | +0.654 |
fter | +0.637 |
cler | +0.599 |
Neg logit contributions | |
RAW | -1.676 |
atis | -1.664 |
oho | -1.391 |
olla | -1.383 |
ande | -1.374 |
Token | ra |
Token ID | 430 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
RANT | +1.028 |
Claud | +0.999 |
fter | +0.922 |
handles | +0.917 |
anski | +0.860 |
Neg logit contributions | |
RAW | -2.391 |
atis | -2.350 |
oho | -1.989 |
Flavoring | -1.970 |
olla | -1.964 |
Token | receive |
Token ID | 3328 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
atis | +2.547 |
RAW | +2.546 |
oho | +2.004 |
olla | +1.998 |
ande | +1.960 |
Neg logit contributions | |
RANT | -2.258 |
Claud | -2.232 |
handles | -2.149 |
fter | -2.100 |
cler | -2.049 |
Token | emails |
Token ID | 7237 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
atis | +3.193 |
RAW | +3.192 |
oho | +2.622 |
olla | +2.617 |
ande | +2.578 |
Neg logit contributions | |
RANT | -1.858 |
Claud | -1.824 |
handles | -1.736 |
fter | -1.673 |
cler | -1.614 |
Token | containing |
Token ID | 7268 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
RAW | +5.633 |
atis | +5.518 |
olla | +4.013 |
oho | +3.890 |
edes | +3.887 |
Neg logit contributions | |
RANT | -8.221 |
Claud | -8.051 |
handles | -7.520 |
anski | -7.499 |
fter | -7.498 |
Token | news |
Token ID | 1705 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
RAW | +3.201 |
atis | +3.152 |
oho | +2.357 |
olla | +2.339 |
ande | +2.289 |
Neg logit contributions | |
RANT | -4.044 |
Claud | -3.987 |
handles | -3.845 |
fter | -3.769 |
anski | -3.673 |
Token | content |
Token ID | 2695 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
RAW | +1.866 |
atis | +1.863 |
oho | +1.478 |
olla | +1.474 |
ande | +1.448 |
Neg logit contributions | |
RANT | -1.546 |
Claud | -1.524 |
handles | -1.457 |
fter | -1.423 |
cler | -1.380 |
Token | , |
Token ID | 837 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
RAW | +7.371 |
atis | +7.251 |
oho | +5.620 |
olla | +5.589 |
ande | +5.567 |
Neg logit contributions | |
Claud | -6.213 |
RANT | -6.182 |
fter | -5.798 |
handles | -5.729 |
anski | -5.674 |
Token | updates |
Token ID | 5992 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
RAW | +11.120 |
atis | +11.110 |
edes | +8.992 |
olla | +8.086 |
ande | +8.054 |
Neg logit contributions | |
RANT | -10.625 |
Claud | -10.597 |
fter | -10.263 |
merce | -10.066 |
pent | -9.789 |
Token | and |
Token ID | 290 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
RAW | +1.953 |
atis | +1.952 |
oho | +1.577 |
olla | +1.575 |
ande | +1.549 |
Neg logit contributions | |
RANT | -1.372 |
Claud | -1.349 |
handles | -1.285 |
fter | -1.251 |
cler | -1.209 |
Token | promotions |
Token ID | 20699 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
RAW | +4.890 |
atis | +4.797 |
oho | +3.346 |
olla | +3.315 |
edes | +3.243 |
Neg logit contributions | |
RANT | -7.353 |
Claud | -7.194 |
fter | -6.872 |
handles | -6.860 |
anski | -6.731 |
Token | from |
Token ID | 422 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
RAW | +2.702 |
atis | +2.698 |
oho | +2.192 |
olla | +2.187 |
ande | +2.148 |
Neg logit contributions | |
RANT | -1.810 |
Claud | -1.781 |
handles | -1.699 |
fter | -1.647 |
cler | -1.592 |
Token | The |
Token ID | 383 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
RAW | +1.231 |
atis | +1.231 |
oho | +0.985 |
olla | +0.981 |
ande | +0.961 |
Neg logit contributions | |
RANT | -1.003 |
Claud | -0.988 |
handles | -0.947 |
fter | -0.920 |
cler | -0.892 |
Token | int |
Token ID | 493 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
RAW | +0.940 |
atis | +0.932 |
olla | +0.730 |
oho | +0.722 |
ande | +0.704 |
Neg logit contributions | |
RANT | -0.927 |
Claud | -0.902 |
handles | -0.855 |
fter | -0.849 |
anski | -0.827 |
Token | f |
Token ID | 277 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
atis | +4.957 |
RAW | +4.880 |
olla | +4.036 |
oho | +4.028 |
ande | +3.928 |
Neg logit contributions | |
RANT | -3.132 |
Claud | -2.955 |
anski | -2.709 |
fter | -2.680 |
handles | -2.647 |
Token | d |
Token ID | 67 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
RAW | +0.527 |
atis | +0.526 |
olla | +0.428 |
oho | +0.426 |
ande | +0.420 |
Neg logit contributions | |
RANT | -0.338 |
Claud | -0.334 |
handles | -0.320 |
fter | -0.312 |
cler | -0.297 |
Token | | |
Token ID | 930 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Claud | +0.564 |
RANT | +0.564 |
handles | +0.546 |
fter | +0.527 |
cler | +0.516 |
Neg logit contributions | |
atis | -0.560 |
RAW | -0.552 |
oho | -0.427 |
olla | -0.423 |
ande | -0.416 |
Token | < |
Token ID | 1279 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
RAW | +1.522 |
atis | +1.509 |
olla | +1.173 |
oho | +1.152 |
ande | +1.131 |
Neg logit contributions | |
RANT | -1.622 |
Claud | -1.597 |
handles | -1.523 |
fter | -1.515 |
anski | -1.468 |
Token | -- |
Token ID | 438 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
RAW | +3.479 |
atis | +3.299 |
oho | +2.524 |
olla | +2.522 |
ande | +2.429 |
Neg logit contributions | |
RANT | -3.833 |
Claud | -3.760 |
fter | -3.523 |
handles | -3.508 |
anski | -3.494 |
Token | Stack |
Token ID | 23881 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
RAW | +11.290 |
atis | +10.933 |
oho | +8.767 |
Flavoring | +8.733 |
olla | +8.712 |
Neg logit contributions | |
RANT | -10.502 |
anski | -9.253 |
Claud | -9.235 |
fter | -8.925 |
rent | -8.920 |
Token | pointer |
Token ID | 17562 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Claud | +3.078 |
RANT | +3.050 |
handles | +3.036 |
fter | +2.761 |
handle | +2.742 |
Neg logit contributions | |
atis | -6.482 |
RAW | -6.423 |
oho | -5.376 |
olla | -5.311 |
edes | -5.300 |
Token | + |
Token ID | 1343 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
RAW | +4.176 |
atis | +4.104 |
olla | +3.149 |
oho | +3.079 |
ande | +3.064 |
Neg logit contributions | |
RANT | -4.694 |
Claud | -4.581 |
fter | -4.355 |
anski | -4.284 |
handles | -4.235 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
RANT | +0.136 |
Claud | +0.131 |
handles | +0.126 |
fter | +0.124 |
ith | +0.116 |
Neg logit contributions | |
atis | -0.206 |
RAW | -0.203 |
oho | -0.167 |
olla | -0.166 |
ande | -0.164 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
RAW | +1.519 |
atis | +1.514 |
oho | +1.175 |
olla | +1.173 |
ande | +1.147 |
Neg logit contributions | |
RANT | -1.534 |
Claud | -1.516 |
handles | -1.462 |
fter | -1.430 |
cler | -1.387 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
RAW | +1.726 |
atis | +1.724 |
oho | +1.408 |
olla | +1.405 |
ande | +1.381 |
Neg logit contributions | |
RANT | -1.083 |
Claud | -1.065 |
handles | -1.015 |
fter | -0.982 |
cler | -0.948 |
Token | content |
Token ID | 2695 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
RAW | +2.238 |
atis | +2.229 |
oho | +1.789 |
olla | +1.782 |
ande | +1.752 |
Neg logit contributions | |
RANT | -1.721 |
Claud | -1.696 |
handles | -1.615 |
fter | -1.573 |
cler | -1.524 |
Token | so |
Token ID | 523 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
RAW | +6.879 |
atis | +6.879 |
oho | +5.510 |
olla | +5.389 |
edes | +5.375 |
Neg logit contributions | |
RANT | -5.782 |
Claud | -5.687 |
handles | -5.209 |
anski | -5.134 |
fter | -5.133 |
Token | provided |
Token ID | 2810 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
RAW | +2.803 |
atis | +2.803 |
oho | +2.296 |
olla | +2.275 |
edes | +2.238 |
Neg logit contributions | |
RANT | -1.817 |
Claud | -1.793 |
handles | -1.685 |
fter | -1.623 |
cler | -1.583 |
Token | is |
Token ID | 318 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
atis | +3.488 |
RAW | +3.481 |
oho | +2.802 |
olla | +2.784 |
edes | +2.735 |
Neg logit contributions | |
RANT | -2.574 |
Claud | -2.537 |
handles | -2.394 |
fter | -2.337 |
cler | -2.267 |
Token | either |
Token ID | 2035 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
atis | +8.577 |
RAW | +8.451 |
oho | +6.648 |
edes | +6.557 |
ande | +6.501 |
Neg logit contributions | |
RANT | -7.376 |
Claud | -7.301 |
handles | -6.973 |
fter | -6.638 |
anski | -6.583 |
Token | expressed |
Token ID | 6241 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
atis | +11.048 |
RAW | +10.641 |
ande | +8.505 |
olla | +8.333 |
oho | +8.331 |
Neg logit contributions | |
RANT | -10.562 |
Claud | -10.281 |
handles | -9.884 |
swick | -9.439 |
anski | -9.426 |
Token | or |
Token ID | 393 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
atis | +5.688 |
RAW | +5.605 |
oho | +4.478 |
olla | +4.415 |
ande | +4.367 |
Neg logit contributions | |
Claud | -4.845 |
RANT | -4.833 |
handles | -4.606 |
anski | -4.445 |
fter | -4.406 |
Token | implied |
Token ID | 17142 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
atis | +4.924 |
RAW | +4.834 |
olla | +3.737 |
oho | +3.732 |
edes | +3.652 |
Neg logit contributions | |
RANT | -5.049 |
Claud | -5.044 |
handles | -4.739 |
fter | -4.617 |
anski | -4.538 |
Token | by |
Token ID | 416 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
atis | +6.127 |
RAW | +6.039 |
olla | +4.800 |
oho | +4.763 |
ande | +4.641 |
Neg logit contributions | |
Claud | -4.926 |
RANT | -4.871 |
handles | -4.655 |
fter | -4.495 |
anski | -4.456 |
Token | our |
Token ID | 674 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
RAW | +2.637 |
atis | +2.631 |
oho | +2.143 |
olla | +2.137 |
ande | +2.096 |
Neg logit contributions | |
RANT | -1.788 |
Claud | -1.760 |
handles | -1.671 |
fter | -1.625 |
cler | -1.573 |
Token | receive |
Token ID | 3328 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
RAW | +3.025 |
atis | +3.022 |
oho | +2.367 |
olla | +2.361 |
ande | +2.312 |
Neg logit contributions | |
RANT | -2.796 |
Claud | -2.760 |
handles | -2.657 |
fter | -2.592 |
cler | -2.524 |
Token | emails |
Token ID | 7237 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
RAW | +3.747 |
atis | +3.733 |
oho | +3.065 |
olla | +3.059 |
ande | +3.002 |
Neg logit contributions | |
RANT | -2.251 |
Claud | -2.216 |
handles | -2.101 |
fter | -2.039 |
cler | -1.963 |
Token | containing |
Token ID | 7268 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
RAW | +5.814 |
atis | +5.672 |
olla | +4.108 |
oho | +3.988 |
edes | +3.983 |
Neg logit contributions | |
RANT | -8.757 |
Claud | -8.612 |
anski | -8.030 |
handles | -8.008 |
fter | -8.000 |
Token | news |
Token ID | 1705 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
RAW | +3.702 |
atis | +3.604 |
oho | +2.687 |
olla | +2.655 |
edes | +2.614 |
Neg logit contributions | |
RANT | -4.872 |
Claud | -4.801 |
handles | -4.626 |
fter | -4.545 |
anski | -4.451 |
Token | content |
Token ID | 2695 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
RAW | +2.189 |
atis | +2.185 |
oho | +1.725 |
olla | +1.719 |
ande | +1.693 |
Neg logit contributions | |
RANT | -1.866 |
Claud | -1.841 |
handles | -1.753 |
fter | -1.720 |
cler | -1.667 |
Token | , |
Token ID | 837 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
RAW | +7.746 |
atis | +7.575 |
oho | +5.841 |
olla | +5.839 |
edes | +5.823 |
Neg logit contributions | |
Claud | -6.628 |
RANT | -6.540 |
fter | -6.211 |
handles | -6.100 |
anski | -6.027 |
Token | updates |
Token ID | 5992 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
RAW | +10.838 |
atis | +10.810 |
edes | +8.788 |
ande | +7.904 |
olla | +7.887 |
Neg logit contributions | |
Claud | -10.410 |
RANT | -10.378 |
fter | -10.184 |
merce | -10.022 |
pent | -9.608 |
Token | and |
Token ID | 290 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
RAW | +2.035 |
atis | +2.035 |
oho | +1.641 |
olla | +1.640 |
ande | +1.614 |
Neg logit contributions | |
RANT | -1.451 |
Claud | -1.427 |
handles | -1.358 |
fter | -1.324 |
cler | -1.280 |
Token | promotions |
Token ID | 20699 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
RAW | +4.839 |
atis | +4.725 |
oho | +3.280 |
olla | +3.248 |
edes | +3.184 |
Neg logit contributions | |
RANT | -7.404 |
Claud | -7.255 |
fter | -6.921 |
handles | -6.901 |
anski | -6.814 |
Token | from |
Token ID | 422 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
RAW | +3.043 |
atis | +3.037 |
oho | +2.452 |
olla | +2.450 |
ande | +2.414 |
Neg logit contributions | |
RANT | -2.105 |
Claud | -2.071 |
handles | -1.975 |
fter | -1.917 |
cler | -1.857 |
Token | The |
Token ID | 383 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
RAW | +2.021 |
atis | +2.017 |
oho | +1.596 |
olla | +1.592 |
ande | +1.561 |
Neg logit contributions | |
RANT | -1.712 |
Claud | -1.689 |
handles | -1.621 |
fter | -1.579 |
cler | -1.535 |
Token | or |
Token ID | 393 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
RANT | +0.112 |
Claud | +0.111 |
handles | +0.107 |
fter | +0.102 |
cler | +0.100 |
Neg logit contributions | |
RAW | -0.165 |
atis | -0.165 |
oho | -0.134 |
olla | -0.134 |
ande | -0.131 |
Token | called |
Token ID | 1444 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
RAW | +0.125 |
atis | +0.124 |
oho | +0.102 |
olla | +0.101 |
edes | +0.099 |
Neg logit contributions | |
RANT | -0.080 |
Claud | -0.080 |
handles | -0.076 |
fter | -0.073 |
cler | -0.071 |
Token | female |
Token ID | 4048 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
RANT | +1.220 |
Claud | +1.220 |
handles | +1.158 |
fter | +1.094 |
cler | +1.086 |
Neg logit contributions | |
atis | -1.848 |
RAW | -1.827 |
oho | -1.498 |
olla | -1.480 |
edes | -1.461 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
atis | +1.050 |
RAW | +1.049 |
oho | +0.842 |
olla | +0.840 |
ande | +0.822 |
Neg logit contributions | |
RANT | -0.787 |
Claud | -0.775 |
handles | -0.745 |
fter | -0.719 |
cler | -0.702 |
Token | supporters |
Token ID | 5941 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
RANT | +3.372 |
Claud | +3.327 |
handles | +3.291 |
fter | +3.167 |
cler | +3.100 |
Neg logit contributions | |
RAW | -3.283 |
atis | -3.276 |
olla | -2.524 |
oho | -2.462 |
ande | -2.442 |
Token | sl |
Token ID | 1017 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Claud | +2.629 |
RANT | +2.606 |
handles | +2.547 |
fter | +2.415 |
cler | +2.399 |
Neg logit contributions | |
atis | -3.594 |
RAW | -3.592 |
olla | -2.895 |
oho | -2.872 |
Flavoring | -2.824 |
Token | uts |
Token ID | 5500 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
atis | +8.843 |
RAW | +7.754 |
oho | +7.033 |
olla | +6.334 |
ande | +6.148 |
Neg logit contributions | |
Claud | -12.826 |
RANT | -12.504 |
cler | -11.836 |
handles | -11.739 |
handle | -11.369 |
Token | and |
Token ID | 290 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
RAW | +0.691 |
atis | +0.690 |
oho | +0.564 |
olla | +0.563 |
ande | +0.554 |
Neg logit contributions | |
RANT | -0.430 |
Claud | -0.423 |
handles | -0.403 |
fter | -0.390 |
cler | -0.376 |
Token | wh |
Token ID | 348 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
RAW | +0.688 |
atis | +0.687 |
olla | +0.553 |
oho | +0.553 |
ande | +0.543 |
Neg logit contributions | |
RANT | -0.503 |
Claud | -0.497 |
handles | -0.477 |
fter | -0.461 |
cler | -0.449 |
Token | ores |
Token ID | 2850 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
RAW | +1.225 |
atis | +1.224 |
oho | +0.945 |
olla | +0.942 |
ande | +0.920 |
Neg logit contributions | |
RANT | -1.263 |
Claud | -1.247 |
handles | -1.201 |
fter | -1.172 |
cler | -1.142 |
Token | ? |
Token ID | 30 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
RAW | +1.125 |
atis | +1.124 |
oho | +0.919 |
olla | +0.916 |
ande | +0.901 |
Neg logit contributions | |
RANT | -0.704 |
Claud | -0.692 |
handles | -0.658 |
fter | -0.637 |
cler | -0.615 |
Token | to |
Token ID | 284 |
Feature activation | -1.75e-04 |
Pos logit contributions | |
atis | +2.900 |
RAW | +2.893 |
oho | +2.323 |
olla | +2.302 |
ande | +2.272 |
Neg logit contributions | |
RANT | -2.302 |
Claud | -2.247 |
handles | -2.157 |
fter | -2.101 |
cler | -2.033 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
RAW | +0.002 |
atis | +0.002 |
olla | +0.002 |
oho | +0.002 |
edes | +0.002 |
Neg logit contributions | |
RANT | -0.001 |
Claud | -0.001 |
handles | -0.001 |
fter | -0.001 |
cler | -0.001 |
Token | great |
Token ID | 1049 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
RAW | +1.172 |
atis | +1.171 |
olla | +0.936 |
oho | +0.936 |
ande | +0.918 |
Neg logit contributions | |
RANT | -0.891 |
Claud | -0.883 |
handles | -0.848 |
fter | -0.822 |
cler | -0.800 |
Token | spider |
Token ID | 19230 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
RAW | +0.221 |
atis | +0.221 |
olla | +0.175 |
oho | +0.174 |
edes | +0.172 |
Neg logit contributions | |
RANT | -0.182 |
Claud | -0.181 |
handles | -0.174 |
fter | -0.169 |
cler | -0.165 |
Token | Shel |
Token ID | 15325 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
RAW | +1.072 |
atis | +1.071 |
oho | +0.864 |
olla | +0.862 |
ande | +0.846 |
Neg logit contributions | |
RANT | -0.769 |
Claud | -0.757 |
handles | -0.725 |
fter | -0.703 |
cler | -0.681 |
Token | ob |
Token ID | 672 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
atis | +5.462 |
RAW | +5.443 |
oho | +4.518 |
olla | +4.441 |
imir | +4.359 |
Neg logit contributions | |
RANT | -4.273 |
Claud | -4.136 |
handles | -3.967 |
fter | -3.809 |
cler | -3.783 |
Token | in |
Token ID | 287 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
atis | +11.859 |
RAW | +11.244 |
oho | +9.457 |
ande | +9.176 |
olla | +9.138 |
Neg logit contributions | |
RANT | -8.872 |
Claud | -8.752 |
handles | -8.395 |
fter | -8.229 |
cler | -8.080 |
Token | the |
Token ID | 262 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
Claud | +1.310 |
RANT | +1.297 |
handles | +1.238 |
fter | +1.188 |
cler | +1.173 |
Neg logit contributions | |
RAW | -1.896 |
atis | -1.890 |
oho | -1.526 |
olla | -1.526 |
edes | -1.495 |
Token | tunnels |
Token ID | 22642 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
RAW | +0.458 |
atis | +0.458 |
olla | +0.365 |
oho | +0.364 |
ande | +0.358 |
Neg logit contributions | |
RANT | -0.352 |
Claud | -0.350 |
handles | -0.337 |
fter | -0.326 |
cler | -0.317 |
Token | of |
Token ID | 286 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
RAW | +1.849 |
atis | +1.846 |
oho | +1.484 |
olla | +1.479 |
ande | +1.454 |
Neg logit contributions | |
RANT | -1.377 |
Claud | -1.353 |
handles | -1.294 |
fter | -1.258 |
cler | -1.219 |
Token | Cir |
Token ID | 21239 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
RANT | +0.050 |
Claud | +0.050 |
handles | +0.048 |
fter | +0.046 |
cler | +0.045 |
Neg logit contributions | |
RAW | -0.070 |
atis | -0.069 |
olla | -0.056 |
oho | -0.056 |
edes | -0.055 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
RANT | +0.532 |
Claud | +0.529 |
handles | +0.509 |
fter | +0.503 |
cler | +0.478 |
Neg logit contributions | |
RAW | -0.599 |
atis | -0.595 |
oho | -0.476 |
olla | -0.475 |
ande | -0.467 |
Token | + |
Token ID | 1343 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
RAW | +2.588 |
atis | +2.579 |
olla | +2.018 |
oho | +2.016 |
ande | +1.969 |
Neg logit contributions | |
RANT | -2.421 |
Claud | -2.381 |
handles | -2.288 |
fter | -2.237 |
cler | -2.173 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
RANT | +1.123 |
Claud | +1.061 |
fter | +1.026 |
handles | +1.020 |
ith | +0.960 |
Neg logit contributions | |
atis | -1.850 |
RAW | -1.802 |
oho | -1.510 |
olla | -1.490 |
ande | -1.485 |
Token | --+ |
Token ID | 44785 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
RAW | +0.543 |
atis | +0.539 |
oho | +0.425 |
olla | +0.424 |
ande | +0.416 |
Neg logit contributions | |
RANT | -0.513 |
Claud | -0.509 |
handles | -0.491 |
fter | -0.482 |
cler | -0.464 |
Token | < |
Token ID | 1279 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
RAW | +5.755 |
atis | +5.642 |
olla | +4.702 |
oho | +4.547 |
edes | +4.494 |
Neg logit contributions | |
RANT | -3.719 |
Claud | -3.475 |
fter | -3.346 |
handles | -3.234 |
anski | -3.230 |
Token | -- |
Token ID | 438 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
RAW | +3.250 |
atis | +3.191 |
oho | +2.447 |
olla | +2.442 |
edes | +2.391 |
Neg logit contributions | |
RANT | -3.409 |
Claud | -3.383 |
handles | -3.237 |
fter | -3.138 |
cler | -3.113 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
RAW | +9.997 |
atis | +9.732 |
olla | +7.792 |
oho | +7.737 |
Flavoring | +7.698 |
Neg logit contributions | |
RANT | -10.123 |
Claud | -8.989 |
anski | -8.948 |
rent | -8.646 |
cler | -8.595 |
Token | of |
Token ID | 286 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
atis | +0.371 |
RAW | +0.368 |
oho | +0.302 |
olla | +0.299 |
ande | +0.296 |
Neg logit contributions | |
RANT | -0.244 |
Claud | -0.241 |
handles | -0.232 |
fter | -0.224 |
cler | -0.215 |
Token | read |
Token ID | 1100 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
RAW | +4.908 |
atis | +4.843 |
oho | +3.821 |
olla | +3.809 |
imir | +3.690 |
Neg logit contributions | |
RANT | -4.311 |
Claud | -4.156 |
fter | -3.826 |
anski | -3.790 |
handles | -3.781 |
Token | () |
Token ID | 3419 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
RAW | +4.500 |
atis | +4.424 |
olla | +3.221 |
oho | +3.196 |
edes | +3.150 |
Neg logit contributions | |
RANT | -6.365 |
Claud | -6.289 |
handles | -5.935 |
cler | -5.867 |
fter | -5.836 |
Token | ' |
Token ID | 6 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
RAW | +4.933 |
atis | +4.797 |
olla | +3.785 |
oho | +3.752 |
edes | +3.688 |
Neg logit contributions | |
RANT | -4.741 |
Claud | -4.612 |
handles | -4.345 |
fter | -4.299 |
anski | -4.249 |
Token | pop |
Token ID | 12924 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
RANT | +0.822 |
Claud | +0.776 |
fter | +0.760 |
handles | +0.758 |
rent | +0.716 |
Neg logit contributions | |
RAW | -1.863 |
atis | -1.858 |
oho | -1.541 |
Flavoring | -1.535 |
olla | -1.530 |
Token | / |
Token ID | 14 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
RAW | +0.643 |
atis | +0.643 |
oho | +0.522 |
olla | +0.517 |
ande | +0.511 |
Neg logit contributions | |
RANT | -0.449 |
Claud | -0.443 |
handles | -0.429 |
fter | -0.415 |
cler | -0.399 |
Token | pop |
Token ID | 12924 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
RANT | +0.396 |
Claud | +0.378 |
handles | +0.365 |
fter | +0.363 |
rent | +0.343 |
Neg logit contributions | |
RAW | -0.788 |
atis | -0.787 |
oho | -0.653 |
olla | -0.647 |
Flavoring | -0.644 |
Token | / |
Token ID | 14 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
RAW | +0.308 |
atis | +0.308 |
oho | +0.251 |
olla | +0.248 |
ande | +0.245 |
Neg logit contributions | |
RANT | -0.213 |
Claud | -0.210 |
handles | -0.205 |
fter | -0.197 |
cler | -0.189 |
Token | ret |
Token ID | 1186 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
RAW | +0.111 |
atis | +0.111 |
oho | +0.090 |
olla | +0.089 |
ande | +0.088 |
Neg logit contributions | |
RANT | -0.076 |
Claud | -0.073 |
handles | -0.071 |
fter | -0.070 |
rent | -0.066 |
Token | 's |
Token ID | 338 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
RAW | +2.168 |
atis | +2.150 |
oho | +1.719 |
olla | +1.716 |
edes | +1.695 |
Neg logit contributions | |
RANT | -1.612 |
Claud | -1.591 |
fter | -1.471 |
handles | -1.466 |
cler | -1.422 |
Token | frame |
Token ID | 5739 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
RAW | +8.506 |
atis | +8.277 |
oho | +6.182 |
ande | +5.935 |
>[ | +5.852 |
Neg logit contributions | |
RANT | -11.911 |
Claud | -11.279 |
fter | -10.748 |
swick | -10.576 |
anski | -10.554 |
Token | | |
Token ID | 930 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
RAW | +3.417 |
atis | +3.350 |
olla | +2.482 |
oho | +2.463 |
edes | +2.415 |
Neg logit contributions | |
RANT | -4.568 |
Claud | -4.460 |
handles | -4.315 |
fter | -4.274 |
cler | -4.169 |
Token | [ |
Token ID | 685 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
RAW | +3.766 |
atis | +3.629 |
olla | +2.438 |
oho | +2.365 |
>[ | +2.363 |
Neg logit contributions | |
RANT | -7.510 |
Claud | -7.249 |
fter | -7.047 |
anski | -6.860 |
cler | -6.713 |
Token | address |
Token ID | 21975 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
atis | +1.530 |
RAW | +1.529 |
oho | +1.235 |
olla | +1.230 |
ande | +1.205 |
Neg logit contributions | |
RANT | -1.100 |
Claud | -1.084 |
handles | -1.044 |
fter | -1.013 |
cler | -0.971 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
atis | +0.981 |
RAW | +0.977 |
oho | +0.797 |
olla | +0.790 |
ande | +0.781 |
Neg logit contributions | |
RANT | -0.661 |
Claud | -0.653 |
handles | -0.625 |
fter | -0.604 |
cler | -0.583 |
Token | becoming |
Token ID | 5033 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
Claud | +2.002 |
handles | +1.974 |
RANT | +1.973 |
cler | +1.876 |
fter | +1.826 |
Neg logit contributions | |
RAW | -3.062 |
atis | -3.050 |
olla | -2.502 |
oho | -2.492 |
ande | -2.491 |
Token | excessively |
Token ID | 40437 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
atis | +0.523 |
RAW | +0.523 |
oho | +0.422 |
olla | +0.421 |
ande | +0.414 |
Neg logit contributions | |
RANT | -0.393 |
Claud | -0.389 |
handles | -0.376 |
fter | -0.362 |
cler | -0.354 |
Token | sensitive |
Token ID | 8564 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
RAW | +0.289 |
atis | +0.289 |
olla | +0.232 |
oho | +0.232 |
ande | +0.228 |
Neg logit contributions | |
RANT | -0.218 |
Claud | -0.216 |
handles | -0.208 |
fter | -0.201 |
cler | -0.197 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
atis | +2.155 |
RAW | +2.153 |
oho | +1.731 |
olla | +1.726 |
ande | +1.701 |
Neg logit contributions | |
RANT | -1.597 |
Claud | -1.572 |
handles | -1.493 |
fter | -1.458 |
cler | -1.404 |
Token | perceived |
Token ID | 11067 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
atis | +0.261 |
RAW | +0.261 |
oho | +0.210 |
olla | +0.210 |
ande | +0.207 |
Neg logit contributions | |
RANT | -0.180 |
Claud | -0.178 |
handles | -0.172 |
fter | -0.164 |
cler | -0.162 |
Token | sl |
Token ID | 1017 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
RANT | +0.974 |
Claud | +0.967 |
handles | +0.948 |
fter | +0.903 |
cler | +0.897 |
Neg logit contributions | |
atis | -1.335 |
RAW | -1.335 |
olla | -1.076 |
oho | -1.074 |
ande | -1.068 |
Token | ights |
Token ID | 2337 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
atis | +9.988 |
RAW | +8.820 |
oho | +7.997 |
olla | +7.706 |
ande | +7.589 |
Neg logit contributions | |
RANT | -10.772 |
Claud | -10.689 |
handles | -9.792 |
MON | -9.682 |
cler | -9.680 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
RANT | +1.500 |
Claud | +1.478 |
handles | +1.437 |
fter | +1.358 |
cler | +1.346 |
Neg logit contributions | |
RAW | -2.482 |
atis | -2.466 |
oho | -2.030 |
olla | -2.020 |
edes | -1.985 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Claud | +1.452 |
RANT | +1.438 |
handles | +1.354 |
fter | +1.310 |
cler | +1.282 |
Neg logit contributions | |
atis | -1.846 |
RAW | -1.844 |
oho | -1.478 |
olla | -1.447 |
edes | -1.444 |
Token |
|
Token ID | 198 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
RANT | +0.964 |
Claud | +0.962 |
handles | +0.918 |
fter | +0.898 |
Rou | +0.854 |
Neg logit contributions | |
atis | -1.317 |
RAW | -1.303 |
oho | -1.064 |
olla | -1.042 |
ande | -1.042 |
Token | Three |
Token ID | 12510 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
RANT | +2.160 |
Claud | +2.039 |
fter | +1.941 |
handles | +1.940 |
ith | +1.847 |
Neg logit contributions | |
atis | -3.315 |
RAW | -3.204 |
oho | -2.716 |
olla | -2.657 |
edes | -2.644 |
Token | int |
Token ID | 493 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
RAW | +0.352 |
atis | +0.349 |
olla | +0.272 |
oho | +0.270 |
ande | +0.264 |
Neg logit contributions | |
RANT | -0.348 |
Claud | -0.341 |
handles | -0.324 |
fter | -0.321 |
anski | -0.311 |
Token | f |
Token ID | 277 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
RAW | +2.045 |
atis | +2.037 |
oho | +1.710 |
olla | +1.707 |
ande | +1.683 |
Neg logit contributions | |
RANT | -0.881 |
Claud | -0.870 |
handles | -0.824 |
fter | -0.786 |
cler | -0.755 |
Token | d |
Token ID | 67 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
RANT | +0.569 |
Claud | +0.563 |
handles | +0.543 |
fter | +0.533 |
rent | +0.508 |
Neg logit contributions | |
RAW | -0.968 |
atis | -0.966 |
olla | -0.791 |
oho | -0.791 |
ande | -0.776 |
Token | | |
Token ID | 930 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
RANT | +0.462 |
Claud | +0.460 |
handles | +0.443 |
fter | +0.431 |
cler | +0.418 |
Neg logit contributions | |
atis | -0.461 |
RAW | -0.453 |
oho | -0.354 |
olla | -0.348 |
ande | -0.346 |
Token | < |
Token ID | 1279 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
RAW | +2.268 |
atis | +2.243 |
olla | +1.863 |
oho | +1.840 |
ande | +1.816 |
Neg logit contributions | |
RANT | -1.316 |
Claud | -1.278 |
fter | -1.194 |
handles | -1.188 |
anski | -1.133 |
Token | -- |
Token ID | 438 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
RAW | +2.847 |
atis | +2.825 |
oho | +2.192 |
olla | +2.186 |
ande | +2.136 |
Neg logit contributions | |
RANT | -2.821 |
Claud | -2.789 |
handles | -2.677 |
fter | -2.607 |
cler | -2.556 |
Token | Stack |
Token ID | 23881 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
RAW | +7.463 |
atis | +7.108 |
Flavoring | +5.490 |
oho | +5.413 |
olla | +5.175 |
Neg logit contributions | |
RANT | -12.109 |
Claud | -11.105 |
anski | -10.901 |
rent | -10.756 |
fter | -10.733 |
Token | pointer |
Token ID | 17562 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
handles | +2.252 |
Claud | +2.244 |
handle | +2.132 |
RANT | +2.094 |
cler | +2.040 |
Neg logit contributions | |
atis | -5.982 |
RAW | -5.823 |
oho | -4.990 |
edes | -4.926 |
olla | -4.901 |
Token | + |
Token ID | 1343 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
RAW | +3.340 |
atis | +3.321 |
olla | +2.585 |
oho | +2.583 |
ande | +2.531 |
Neg logit contributions | |
RANT | -3.238 |
Claud | -3.179 |
handles | -3.051 |
fter | -2.994 |
cler | -2.909 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
RANT | +0.454 |
Claud | +0.435 |
handles | +0.416 |
fter | +0.414 |
rent | +0.388 |
Neg logit contributions | |
atis | -0.713 |
RAW | -0.699 |
oho | -0.580 |
olla | -0.575 |
ande | -0.571 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
RAW | +0.987 |
atis | +0.983 |
oho | +0.770 |
olla | +0.770 |
ande | +0.752 |
Neg logit contributions | |
RANT | -0.957 |
Claud | -0.947 |
handles | -0.913 |
fter | -0.895 |
cler | -0.864 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
atis | +1.166 |
RAW | +1.157 |
oho | +0.910 |
olla | +0.901 |
ande | +0.875 |
Neg logit contributions | |
RANT | -1.192 |
Claud | -1.158 |
handles | -1.129 |
fter | -1.100 |
cler | -1.084 |
Token |
|
Token ID | 198 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
RAW | +2.079 |
atis | +2.073 |
oho | +1.621 |
olla | +1.620 |
ande | +1.583 |
Neg logit contributions | |
RANT | -1.943 |
Claud | -1.916 |
handles | -1.843 |
fter | -1.795 |
cler | -1.751 |
Token | " |
Token ID | 1 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
RAW | +2.557 |
atis | +2.473 |
oho | +1.967 |
olla | +1.961 |
ande | +1.910 |
Neg logit contributions | |
Claud | -2.222 |
RANT | -2.147 |
handles | -2.123 |
cler | -2.050 |
fter | -1.994 |
Token | Opening |
Token ID | 43093 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
RANT | +0.455 |
Claud | +0.439 |
handles | +0.414 |
fter | +0.410 |
ith | +0.388 |
Neg logit contributions | |
atis | -0.687 |
RAW | -0.673 |
olla | -0.556 |
oho | -0.556 |
ande | -0.551 |
Token | our |
Token ID | 674 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
RAW | +2.549 |
atis | +2.546 |
oho | +2.059 |
olla | +2.050 |
ande | +2.016 |
Neg logit contributions | |
RANT | -1.801 |
Claud | -1.767 |
handles | -1.683 |
fter | -1.638 |
cler | -1.586 |
Token | Aberdeen |
Token ID | 44985 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
RAW | +4.339 |
atis | +4.333 |
oho | +3.521 |
olla | +3.458 |
ande | +3.376 |
Neg logit contributions | |
RANT | -3.480 |
Claud | -3.384 |
handles | -3.214 |
fter | -3.160 |
cler | -3.057 |
Token | garden |
Token ID | 11376 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
atis | +9.126 |
RAW | +8.921 |
oho | +7.408 |
olla | +7.057 |
Fountain | +6.912 |
Neg logit contributions | |
RANT | -10.436 |
Claud | -9.728 |
fter | -9.175 |
anski | -9.136 |
handles | -9.035 |
Token | centre |
Token ID | 7372 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
atis | +5.341 |
RAW | +5.248 |
oho | +4.286 |
olla | +4.238 |
edes | +4.151 |
Neg logit contributions | |
RANT | -4.284 |
Claud | -4.181 |
handles | -3.843 |
fter | -3.825 |
anski | -3.767 |
Token | is |
Token ID | 318 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
RAW | +1.020 |
atis | +1.013 |
oho | +0.824 |
olla | +0.824 |
ande | +0.809 |
Neg logit contributions | |
Claud | -0.688 |
RANT | -0.687 |
handles | -0.661 |
fter | -0.634 |
cler | -0.616 |
Token | a |
Token ID | 257 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
RAW | +3.455 |
atis | +3.452 |
oho | +2.806 |
olla | +2.792 |
ande | +2.743 |
Neg logit contributions | |
RANT | -2.362 |
Claud | -2.310 |
handles | -2.201 |
fter | -2.136 |
cler | -2.060 |
Token | step |
Token ID | 2239 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
RAW | +2.090 |
atis | +2.086 |
oho | +1.672 |
olla | +1.670 |
ande | +1.640 |
Neg logit contributions | |
RANT | -1.559 |
Claud | -1.539 |
handles | -1.474 |
fter | -1.432 |
cler | -1.391 |
Token | labor |
Token ID | 4827 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
atis | +1.174 |
RAW | +1.169 |
oho | +0.909 |
olla | +0.905 |
ande | +0.885 |
Neg logit contributions | |
RANT | -1.175 |
Claud | -1.156 |
handles | -1.107 |
fter | -1.088 |
cler | -1.051 |
Token | in |
Token ID | 287 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
atis | +4.498 |
RAW | +4.471 |
oho | +3.573 |
olla | +3.568 |
ande | +3.512 |
Neg logit contributions | |
RANT | -3.256 |
Claud | -3.154 |
handles | -2.999 |
fter | -2.950 |
anski | -2.810 |
Token | East |
Token ID | 3687 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
atis | +4.516 |
RAW | +4.510 |
olla | +3.527 |
oho | +3.502 |
ande | +3.465 |
Neg logit contributions | |
RANT | -4.160 |
Claud | -4.018 |
handles | -3.878 |
fter | -3.851 |
anski | -3.691 |
Token | Germany |
Token ID | 4486 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
RAW | +5.093 |
atis | +5.076 |
oho | +4.161 |
olla | +4.138 |
edes | +4.096 |
Neg logit contributions | |
RANT | -3.108 |
Claud | -2.997 |
handles | -2.851 |
fter | -2.765 |
cler | -2.695 |
Token | from |
Token ID | 422 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
atis | +3.657 |
RAW | +3.643 |
oho | +2.928 |
olla | +2.924 |
edes | +2.879 |
Neg logit contributions | |
RANT | -2.558 |
Claud | -2.494 |
handles | -2.371 |
fter | -2.314 |
cler | -2.209 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
atis | +5.985 |
RAW | +5.970 |
olla | +4.673 |
oho | +4.648 |
edes | +4.633 |
Neg logit contributions | |
RANT | -5.294 |
Claud | -4.995 |
handles | -4.812 |
fter | -4.787 |
anski | -4.568 |
Token | 1960 |
Token ID | 9507 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
RAW | +10.152 |
atis | +10.145 |
oho | +8.214 |
olla | +8.092 |
edes | +7.931 |
Neg logit contributions | |
RANT | -9.405 |
Claud | -8.211 |
fter | -8.108 |
handles | -8.072 |
ocry | -8.023 |
Token | s |
Token ID | 82 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
RAW | +2.653 |
atis | +2.645 |
oho | +2.022 |
edes | +2.007 |
olla | +1.993 |
Neg logit contributions | |
RANT | -2.699 |
Claud | -2.617 |
handles | -2.543 |
fter | -2.508 |
cler | -2.388 |
Token | to |
Token ID | 284 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
atis | +1.629 |
RAW | +1.627 |
oho | +1.308 |
olla | +1.307 |
ande | +1.287 |
Neg logit contributions | |
RANT | -1.168 |
Claud | -1.136 |
handles | -1.092 |
fter | -1.065 |
cler | -1.019 |
Token | 1980 |
Token ID | 7169 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
atis | +5.549 |
RAW | +5.529 |
oho | +4.387 |
olla | +4.383 |
edes | +4.304 |
Neg logit contributions | |
RANT | -4.883 |
Claud | -4.668 |
handles | -4.548 |
fter | -4.428 |
cler | -4.246 |
Token | s |
Token ID | 82 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
RAW | +1.218 |
atis | +1.216 |
oho | +0.966 |
olla | +0.964 |
ande | +0.945 |
Neg logit contributions | |
RANT | -1.012 |
Claud | -1.001 |
handles | -0.959 |
fter | -0.933 |
cler | -0.908 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
RAW | +2.238 |
atis | +2.234 |
oho | +1.790 |
olla | +1.786 |
ande | +1.753 |
Neg logit contributions | |
RANT | -1.716 |
Claud | -1.690 |
handles | -1.618 |
fter | -1.573 |
cler | -1.525 |
Token | pain |
Token ID | 2356 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Claud | +0.150 |
RANT | +0.148 |
handles | +0.144 |
fter | +0.136 |
cler | +0.136 |
Neg logit contributions | |
RAW | -0.200 |
atis | -0.199 |
oho | -0.162 |
olla | -0.161 |
ande | -0.157 |
Token | of |
Token ID | 286 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
RANT | +3.305 |
handles | +3.281 |
Claud | +3.267 |
fter | +2.980 |
handle | +2.929 |
Neg logit contributions | |
RAW | -5.383 |
atis | -5.230 |
oho | -4.446 |
olla | -4.400 |
ande | -4.300 |
Token | her |
Token ID | 607 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Claud | +3.090 |
RANT | +2.965 |
handles | +2.941 |
cler | +2.803 |
Rou | +2.710 |
Neg logit contributions | |
atis | -4.510 |
RAW | -4.412 |
oho | -3.686 |
olla | -3.626 |
edes | -3.622 |
Token | r |
Token ID | 374 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Claud | +1.930 |
handles | +1.862 |
RANT | +1.861 |
cler | +1.771 |
fter | +1.730 |
Neg logit contributions | |
atis | -2.623 |
RAW | -2.616 |
olla | -2.098 |
oho | -2.089 |
edes | -2.072 |
Token | he |
Token ID | 258 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
RANT | +2.782 |
Claud | +2.767 |
handles | +2.709 |
fter | +2.672 |
ith | +2.584 |
Neg logit contributions | |
RAW | -3.162 |
atis | -3.072 |
Flavoring | -2.504 |
oho | -2.451 |
olla | -2.439 |
Token | umat |
Token ID | 27798 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
atis | +6.497 |
RAW | +5.641 |
olla | +4.171 |
ande | +4.151 |
oho | +4.144 |
Neg logit contributions | |
RANT | -12.975 |
Claud | -12.503 |
handles | -12.228 |
swick | -11.917 |
fter | -11.858 |
Token | oid |
Token ID | 1868 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
atis | +2.020 |
RAW | +1.998 |
oho | +1.550 |
olla | +1.544 |
ande | +1.507 |
Neg logit contributions | |
RANT | -2.131 |
Claud | -2.097 |
handles | -2.018 |
fter | -1.984 |
cler | -1.933 |
Token | arthritis |
Token ID | 37954 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Claud | +0.882 |
RANT | +0.879 |
handles | +0.853 |
fter | +0.819 |
cler | +0.808 |
Neg logit contributions | |
RAW | -0.889 |
atis | -0.879 |
oho | -0.689 |
olla | -0.681 |
edes | -0.668 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
RANT | +1.463 |
Claud | +1.463 |
handles | +1.410 |
fter | +1.330 |
cler | +1.308 |
Neg logit contributions | |
RAW | -2.351 |
atis | -2.344 |
oho | -1.937 |
olla | -1.909 |
ande | -1.881 |
Token | Trying |
Token ID | 31165 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Claud | +1.637 |
RANT | +1.633 |
handles | +1.535 |
Rou | +1.467 |
fter | +1.464 |
Neg logit contributions | |
atis | -2.176 |
RAW | -2.155 |
oho | -1.744 |
olla | -1.712 |
edes | -1.707 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
atis | +3.359 |
RAW | +3.351 |
oho | +2.723 |
olla | +2.715 |
ande | +2.609 |
Neg logit contributions | |
RANT | -2.603 |
Claud | -2.544 |
handles | -2.397 |
fter | -2.350 |
cler | -2.286 |
Token | said |
Token ID | 531 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Claud | +0.860 |
RANT | +0.855 |
handles | +0.831 |
fter | +0.792 |
cler | +0.773 |
Neg logit contributions | |
RAW | -1.190 |
atis | -1.181 |
olla | -0.949 |
oho | -0.945 |
ande | -0.936 |
Token | : |
Token ID | 25 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
RANT | +0.217 |
Claud | +0.214 |
handles | +0.204 |
fter | +0.197 |
cler | +0.191 |
Neg logit contributions | |
RAW | -0.334 |
atis | -0.333 |
oho | -0.271 |
olla | -0.271 |
ande | -0.266 |
Token | " |
Token ID | 366 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
RANT | +0.371 |
Claud | +0.367 |
handles | +0.345 |
fter | +0.335 |
cler | +0.321 |
Neg logit contributions | |
atis | -0.657 |
RAW | -0.655 |
oho | -0.539 |
olla | -0.538 |
ande | -0.531 |
Token | The |
Token ID | 464 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
RANT | +0.636 |
Claud | +0.622 |
handles | +0.585 |
fter | +0.578 |
ith | +0.546 |
Neg logit contributions | |
atis | -0.964 |
RAW | -0.949 |
olla | -0.785 |
oho | -0.780 |
ande | -0.775 |
Token | Aberdeen |
Token ID | 44985 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
RAW | +2.695 |
atis | +2.690 |
oho | +2.153 |
olla | +2.148 |
ande | +2.107 |
Neg logit contributions | |
RANT | -2.094 |
Claud | -2.064 |
handles | -1.977 |
fter | -1.921 |
cler | -1.863 |
Token | store |
Token ID | 3650 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
atis | +9.739 |
RAW | +9.626 |
oho | +7.923 |
olla | +7.695 |
Fountain | +7.540 |
Neg logit contributions | |
RANT | -9.473 |
Claud | -8.881 |
fter | -8.377 |
handles | -8.341 |
anski | -8.194 |
Token | is |
Token ID | 318 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
atis | +4.413 |
RAW | +4.389 |
oho | +3.524 |
olla | +3.500 |
ande | +3.428 |
Neg logit contributions | |
RANT | -3.505 |
Claud | -3.398 |
handles | -3.192 |
fter | -3.186 |
anski | -3.072 |
Token | a |
Token ID | 257 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
RAW | +3.862 |
atis | +3.855 |
oho | +3.135 |
olla | +3.109 |
ande | +3.044 |
Neg logit contributions | |
RANT | -2.726 |
Claud | -2.652 |
handles | -2.521 |
fter | -2.464 |
anski | -2.367 |
Token | concept |
Token ID | 3721 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
atis | +4.973 |
RAW | +4.964 |
oho | +4.054 |
olla | +3.986 |
edes | +3.918 |
Neg logit contributions | |
RANT | -3.980 |
Claud | -3.857 |
handles | -3.678 |
fter | -3.578 |
anski | -3.494 |
Token | for |
Token ID | 329 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
RANT | +0.527 |
Claud | +0.524 |
handles | +0.503 |
fter | +0.486 |
cler | +0.475 |
Neg logit contributions | |
RAW | -0.827 |
atis | -0.824 |
olla | -0.673 |
oho | -0.671 |
edes | -0.662 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
RANT | +1.199 |
Claud | +1.193 |
handles | +1.152 |
fter | +1.135 |
cler | +1.074 |
Neg logit contributions | |
RAW | -1.429 |
atis | -1.416 |
olla | -1.144 |
oho | -1.141 |
ande | -1.125 |
Token | + |
Token ID | 1343 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
RAW | +1.043 |
atis | +1.038 |
olla | +0.807 |
oho | +0.805 |
ande | +0.785 |
Neg logit contributions | |
RANT | -1.053 |
Claud | -1.035 |
handles | -0.992 |
fter | -0.976 |
cler | -0.946 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
RANT | +1.809 |
Claud | +1.686 |
fter | +1.648 |
handles | +1.628 |
ith | +1.549 |
Neg logit contributions | |
atis | -3.207 |
RAW | -3.105 |
oho | -2.609 |
ande | -2.587 |
olla | -2.575 |
Token | --+ |
Token ID | 44785 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
RANT | +0.830 |
Claud | +0.829 |
handles | +0.799 |
fter | +0.788 |
cler | +0.747 |
Neg logit contributions | |
RAW | -0.973 |
atis | -0.960 |
oho | -0.771 |
olla | -0.770 |
ande | -0.761 |
Token | < |
Token ID | 1279 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
RAW | +0.841 |
atis | +0.827 |
olla | +0.634 |
oho | +0.626 |
ande | +0.609 |
Neg logit contributions | |
RANT | -0.998 |
Claud | -0.969 |
handles | -0.930 |
fter | -0.927 |
anski | -0.899 |
Token | -- |
Token ID | 438 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
RAW | +2.223 |
atis | +2.219 |
oho | +1.730 |
olla | +1.725 |
ande | +1.688 |
Neg logit contributions | |
RANT | -2.134 |
Claud | -2.106 |
handles | -2.027 |
fter | -1.977 |
cler | -1.924 |
Token | Start |
Token ID | 7253 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
RAW | +9.556 |
atis | +9.299 |
oho | +7.478 |
olla | +7.390 |
Flavoring | +7.267 |
Neg logit contributions | |
RANT | -9.426 |
Claud | -8.594 |
anski | -8.277 |
fter | -8.201 |
ocry | -8.177 |
Token | of |
Token ID | 286 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
RANT | +0.256 |
Claud | +0.255 |
handles | +0.247 |
fter | +0.236 |
cler | +0.228 |
Neg logit contributions | |
atis | -0.415 |
RAW | -0.410 |
oho | -0.339 |
olla | -0.336 |
ande | -0.333 |
Token | read |
Token ID | 1100 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
RAW | +5.924 |
atis | +5.709 |
oho | +4.449 |
olla | +4.426 |
imir | +4.336 |
Neg logit contributions | |
RANT | -5.980 |
Claud | -5.832 |
fter | -5.386 |
anski | -5.323 |
swick | -5.242 |
Token | () |
Token ID | 3419 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
RAW | +3.825 |
atis | +3.767 |
olla | +2.786 |
oho | +2.765 |
edes | +2.724 |
Neg logit contributions | |
RANT | -5.067 |
Claud | -5.010 |
handles | -4.773 |
fter | -4.677 |
cler | -4.652 |
Token | ' |
Token ID | 6 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
RAW | +4.040 |
atis | +3.973 |
olla | +3.146 |
oho | +3.135 |
edes | +3.068 |
Neg logit contributions | |
RANT | -3.589 |
Claud | -3.503 |
handles | -3.328 |
fter | -3.271 |
cler | -3.190 |
Token | Experimental |
Token ID | 32286 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
RAW | +4.731 |
atis | +4.717 |
oho | +3.747 |
olla | +3.705 |
edes | +3.686 |
Neg logit contributions | |
RANT | -3.826 |
Claud | -3.638 |
handles | -3.533 |
fter | -3.480 |
cler | -3.373 |
Token | subjects |
Token ID | 7481 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
RAW | +0.270 |
atis | +0.269 |
oho | +0.215 |
olla | +0.214 |
edes | +0.210 |
Neg logit contributions | |
RANT | -0.219 |
Claud | -0.217 |
handles | -0.208 |
fter | -0.202 |
cler | -0.196 |
Token | Three |
Token ID | 7683 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
RAW | +0.861 |
atis | +0.859 |
oho | +0.694 |
olla | +0.694 |
ande | +0.679 |
Neg logit contributions | |
RANT | -0.622 |
Claud | -0.615 |
handles | -0.587 |
fter | -0.569 |
cler | -0.552 |
Token | female |
Token ID | 4048 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Claud | +2.380 |
RANT | +2.330 |
handles | +2.274 |
cler | +2.153 |
Rou | +2.109 |
Neg logit contributions | |
RAW | -3.950 |
atis | -3.938 |
olla | -3.283 |
oho | -3.267 |
ande | -3.188 |
Token | r |
Token ID | 374 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
RAW | +1.536 |
atis | +1.534 |
oho | +1.241 |
olla | +1.239 |
ande | +1.216 |
Neg logit contributions | |
RANT | -1.071 |
Claud | -1.057 |
handles | -1.010 |
fter | -0.976 |
cler | -0.948 |
Token | hes |
Token ID | 956 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
RANT | +2.248 |
Claud | +2.200 |
handles | +2.123 |
fter | +2.032 |
ith | +1.961 |
Neg logit contributions | |
atis | -3.818 |
RAW | -3.805 |
oho | -3.106 |
olla | -3.094 |
ande | -3.070 |
Token | us |
Token ID | 385 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
atis | +7.650 |
RAW | +6.707 |
olla | +5.786 |
ande | +5.406 |
edes | +5.347 |
Neg logit contributions | |
RANT | -11.776 |
Claud | -11.276 |
handles | -11.189 |
cler | -10.679 |
MON | -10.514 |
Token | monkeys |
Token ID | 26697 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
atis | +4.972 |
RAW | +4.897 |
oho | +3.896 |
olla | +3.861 |
ande | +3.850 |
Neg logit contributions | |
RANT | -4.226 |
Claud | -4.109 |
handles | -3.961 |
fter | -3.914 |
cler | -3.707 |
Token | ( |
Token ID | 357 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
atis | +2.330 |
RAW | +2.321 |
oho | +1.859 |
olla | +1.856 |
ande | +1.828 |
Neg logit contributions | |
RANT | -1.776 |
Claud | -1.732 |
handles | -1.654 |
fter | -1.620 |
cler | -1.555 |
Token | Mac |
Token ID | 14155 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
RAW | +2.012 |
atis | +2.002 |
oho | +1.607 |
olla | +1.604 |
ande | +1.576 |
Neg logit contributions | |
RANT | -1.512 |
Claud | -1.490 |
handles | -1.429 |
fter | -1.388 |
cler | -1.346 |
Token | aca |
Token ID | 22260 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
atis | +4.410 |
RAW | +4.338 |
olla | +3.377 |
ande | +3.255 |
oho | +3.230 |
Neg logit contributions | |
RANT | -6.091 |
Claud | -5.874 |
handles | -5.717 |
fter | -5.651 |
cler | -5.540 |
Token | as |
Token ID | 355 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
RAW | +1.864 |
atis | +1.863 |
oho | +1.503 |
olla | +1.499 |
edes | +1.473 |
Neg logit contributions | |
RANT | -1.321 |
Claud | -1.290 |
handles | -1.231 |
fter | -1.196 |
cler | -1.161 |
Token | to |
Token ID | 284 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
RANT | +2.817 |
Claud | +2.804 |
handles | +2.676 |
fter | +2.587 |
cler | +2.487 |
Neg logit contributions | |
RAW | -4.466 |
atis | -4.447 |
oho | -3.635 |
olla | -3.621 |
ande | -3.550 |
Token | facilitate |
Token ID | 15570 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
RAW | +0.989 |
atis | +0.987 |
oho | +0.795 |
olla | +0.794 |
ande | +0.778 |
Neg logit contributions | |
RANT | -0.723 |
Claud | -0.716 |
handles | -0.686 |
fter | -0.666 |
cler | -0.643 |
Token | construction |
Token ID | 5103 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
RAW | +3.668 |
atis | +3.634 |
olla | +2.928 |
oho | +2.917 |
edes | +2.871 |
Neg logit contributions | |
RANT | -2.780 |
Claud | -2.689 |
handles | -2.566 |
fter | -2.520 |
anski | -2.411 |
Token | of |
Token ID | 286 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
RAW | +4.743 |
atis | +4.706 |
olla | +3.721 |
oho | +3.683 |
edes | +3.625 |
Neg logit contributions | |
RANT | -4.077 |
Claud | -3.980 |
handles | -3.715 |
fter | -3.689 |
anski | -3.664 |
Token | multi |
Token ID | 5021 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
RAW | +1.306 |
atis | +1.304 |
oho | +1.051 |
olla | +1.049 |
ande | +1.030 |
Neg logit contributions | |
RANT | -0.941 |
Claud | -0.927 |
handles | -0.887 |
fter | -0.860 |
cler | -0.834 |
Token | - |
Token ID | 12 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
atis | +8.810 |
RAW | +8.554 |
oho | +6.944 |
olla | +6.476 |
ande | +6.387 |
Neg logit contributions | |
RANT | -9.612 |
Claud | -9.465 |
fter | -8.890 |
anski | -8.832 |
handles | -8.726 |
Token | store |
Token ID | 8095 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
atis | +6.428 |
RAW | +6.399 |
oho | +5.061 |
olla | +4.944 |
ande | +4.842 |
Neg logit contributions | |
RANT | -6.384 |
Claud | -6.290 |
handles | -6.011 |
fter | -5.822 |
cler | -5.722 |
Token | y |
Token ID | 88 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
RANT | +1.278 |
Claud | +1.266 |
handles | +1.229 |
fter | +1.193 |
ith | +1.160 |
Neg logit contributions | |
RAW | -2.134 |
atis | -2.075 |
oho | -1.701 |
edes | -1.694 |
olla | -1.687 |
Token | residential |
Token ID | 12420 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
RAW | +2.288 |
atis | +2.285 |
oho | +1.854 |
olla | +1.850 |
ande | +1.817 |
Neg logit contributions | |
RANT | -1.553 |
Claud | -1.529 |
handles | -1.459 |
fter | -1.415 |
cler | -1.368 |
Token | and |
Token ID | 290 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
atis | +5.671 |
RAW | +5.631 |
oho | +4.690 |
olla | +4.610 |
ande | +4.532 |
Neg logit contributions | |
RANT | -3.459 |
Claud | -3.341 |
handles | -3.114 |
fter | -3.111 |
anski | -2.983 |
Token | Cal |
Token ID | 9771 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
RANT | +1.518 |
Claud | +1.451 |
handles | +1.380 |
fter | +1.368 |
rent | +1.292 |
Neg logit contributions | |
atis | -2.309 |
RAW | -2.206 |
oho | -1.886 |
olla | -1.854 |
ande | -1.845 |
Token | oric |
Token ID | 8146 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Claud | +2.033 |
RANT | +2.017 |
handles | +1.943 |
fter | +1.908 |
cler | +1.842 |
Neg logit contributions | |
atis | -2.089 |
RAW | -2.077 |
oho | -1.617 |
olla | -1.604 |
edes | -1.550 |
Token | restriction |
Token ID | 17504 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Claud | +3.389 |
RANT | +3.319 |
handles | +3.261 |
fter | +3.093 |
Rou | +3.030 |
Neg logit contributions | |
atis | -4.026 |
RAW | -3.985 |
oho | -3.231 |
olla | -3.191 |
edes | -3.133 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
RANT | +1.408 |
Claud | +1.392 |
handles | +1.333 |
fter | +1.282 |
cler | +1.241 |
Neg logit contributions | |
atis | -2.139 |
RAW | -2.138 |
oho | -1.745 |
olla | -1.738 |
ande | -1.701 |
Token | Eating |
Token ID | 37537 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Claud | +2.143 |
RANT | +2.069 |
handles | +1.956 |
Rou | +1.913 |
fter | +1.891 |
Neg logit contributions | |
atis | -2.846 |
RAW | -2.780 |
oho | -2.315 |
olla | -2.273 |
ande | -2.256 |
Token | fewer |
Token ID | 7380 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
atis | +0.363 |
RAW | +0.361 |
oho | +0.293 |
olla | +0.291 |
ande | +0.286 |
Neg logit contributions | |
RANT | -0.263 |
Claud | -0.261 |
handles | -0.250 |
fter | -0.241 |
cler | -0.236 |
Token | calories |
Token ID | 14653 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
Claud | +5.895 |
handles | +5.757 |
RANT | +5.664 |
cler | +5.299 |
handle | +5.158 |
Neg logit contributions | |
atis | -8.424 |
RAW | -8.105 |
ande | -7.059 |
oho | -6.909 |
imir | -6.742 |
Token | also |
Token ID | 635 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
handles | +3.706 |
Claud | +3.696 |
RANT | +3.488 |
fter | +3.340 |
cler | +3.256 |
Neg logit contributions | |
atis | -6.669 |
RAW | -6.653 |
oho | -5.653 |
olla | -5.557 |
ande | -5.472 |
Token | equals |
Token ID | 21767 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
handles | +4.450 |
Claud | +4.156 |
RANT | +3.800 |
handle | +3.740 |
fter | +3.739 |
Neg logit contributions | |
RAW | -8.417 |
atis | -8.370 |
oho | -6.990 |
olla | -6.974 |
ande | -6.817 |
Token | less |
Token ID | 1342 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
RANT | +0.668 |
Claud | +0.666 |
handles | +0.643 |
fter | +0.618 |
cler | +0.601 |
Neg logit contributions | |
atis | -1.053 |
RAW | -1.043 |
oho | -0.861 |
olla | -0.852 |
ande | -0.844 |
Token | glucose |
Token ID | 15701 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Claud | +0.305 |
RANT | +0.305 |
handles | +0.294 |
fter | +0.279 |
cler | +0.278 |
Neg logit contributions | |
atis | -0.428 |
RAW | -0.422 |
oho | -0.346 |
olla | -0.341 |
ande | -0.340 |
Token | begun |
Token ID | 9258 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
RANT | +0.496 |
Claud | +0.496 |
handles | +0.479 |
fter | +0.462 |
cler | +0.456 |
Neg logit contributions | |
RAW | -0.676 |
atis | -0.670 |
oho | -0.535 |
olla | -0.533 |
edes | -0.523 |
Token | to |
Token ID | 284 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
RANT | +0.360 |
Claud | +0.358 |
handles | +0.344 |
fter | +0.330 |
cler | +0.325 |
Neg logit contributions | |
RAW | -0.547 |
atis | -0.547 |
oho | -0.443 |
olla | -0.442 |
edes | -0.432 |
Token | raise |
Token ID | 5298 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
Claud | +0.499 |
RANT | +0.498 |
handles | +0.485 |
fter | +0.470 |
cler | +0.462 |
Neg logit contributions | |
RAW | -0.737 |
atis | -0.733 |
oho | -0.583 |
olla | -0.582 |
edes | -0.578 |
Token | their |
Token ID | 511 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
RANT | +0.700 |
Claud | +0.693 |
handles | +0.669 |
fter | +0.641 |
cler | +0.625 |
Neg logit contributions | |
atis | -1.165 |
RAW | -1.160 |
oho | -0.952 |
olla | -0.945 |
edes | -0.927 |
Token | voices |
Token ID | 10839 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
RANT | +1.098 |
Claud | +1.078 |
handles | +1.067 |
fter | +1.015 |
cler | +0.973 |
Neg logit contributions | |
atis | -1.953 |
RAW | -1.944 |
olla | -1.602 |
oho | -1.599 |
edes | -1.555 |
Token | in |
Token ID | 287 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
RANT | +2.944 |
Claud | +2.922 |
handles | +2.842 |
fter | +2.688 |
cler | +2.673 |
Neg logit contributions | |
atis | -5.435 |
RAW | -5.404 |
oho | -4.477 |
olla | -4.468 |
edes | -4.378 |
Token | opposition |
Token ID | 5471 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
Claud | +4.266 |
RANT | +4.174 |
handles | +4.024 |
cler | +3.963 |
fter | +3.870 |
Neg logit contributions | |
atis | -8.410 |
RAW | -8.208 |
edes | -6.849 |
oho | -6.799 |
olla | -6.782 |
Token | to |
Token ID | 284 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
RANT | +0.795 |
Claud | +0.780 |
handles | +0.743 |
fter | +0.722 |
cler | +0.696 |
Neg logit contributions | |
RAW | -1.092 |
atis | -1.088 |
olla | -0.877 |
oho | -0.877 |
ande | -0.864 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
RANT | +4.046 |
Claud | +4.016 |
handles | +3.867 |
cler | +3.746 |
fter | +3.684 |
Neg logit contributions | |
atis | -7.131 |
RAW | -7.088 |
olla | -5.896 |
oho | -5.862 |
edes | -5.737 |
Token | idea |
Token ID | 2126 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
Claud | +1.248 |
RANT | +1.247 |
handles | +1.206 |
fter | +1.167 |
cler | +1.162 |
Neg logit contributions | |
atis | -1.546 |
RAW | -1.535 |
olla | -1.235 |
oho | -1.224 |
edes | -1.193 |
Token | . |
Token ID | 13 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
RANT | +0.472 |
Claud | +0.464 |
handles | +0.442 |
fter | +0.430 |
cler | +0.415 |
Neg logit contributions | |
atis | -0.652 |
RAW | -0.652 |
oho | -0.524 |
olla | -0.522 |
ande | -0.515 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Claud | +1.666 |
handles | +1.646 |
RANT | +1.644 |
fter | +1.498 |
cler | +1.482 |
Neg logit contributions | |
RAW | -2.838 |
atis | -2.803 |
oho | -2.317 |
olla | -2.298 |
ande | -2.286 |
Token | features |
Token ID | 3033 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
RAW | +1.420 |
atis | +1.418 |
oho | +1.144 |
olla | +1.141 |
ande | +1.120 |
Neg logit contributions | |
RANT | -1.024 |
Claud | -1.009 |
handles | -0.966 |
fter | -0.936 |
cler | -0.907 |
Token | a |
Token ID | 257 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Claud | +4.035 |
handles | +4.007 |
RANT | +3.908 |
handle | +3.617 |
fter | +3.596 |
Neg logit contributions | |
atis | -6.549 |
RAW | -6.542 |
olla | -5.371 |
oho | -5.300 |
Flavoring | -5.253 |
Token | full |
Token ID | 1336 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
Claud | +2.543 |
RANT | +2.470 |
handles | +2.465 |
fter | +2.313 |
handle | +2.304 |
Neg logit contributions | |
RAW | -3.433 |
atis | -3.396 |
oho | -2.727 |
olla | -2.721 |
Flavoring | -2.703 |
Token | Shim |
Token ID | 31698 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
RANT | +0.044 |
Claud | +0.044 |
handles | +0.042 |
fter | +0.041 |
cler | +0.040 |
Neg logit contributions | |
RAW | -0.062 |
atis | -0.062 |
oho | -0.050 |
olla | -0.050 |
ande | -0.049 |
Token | ano |
Token ID | 5733 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
RAW | +0.522 |
atis | +0.522 |
oho | +0.412 |
olla | +0.410 |
ande | +0.402 |
Neg logit contributions | |
RANT | -0.456 |
Claud | -0.450 |
handles | -0.432 |
fter | -0.420 |
cler | -0.409 |
Token | 600 |
Token ID | 10053 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
Claud | +5.212 |
handles | +5.122 |
RANT | +5.003 |
handle | +4.904 |
Rou | +4.791 |
Neg logit contributions | |
RAW | -7.415 |
atis | -7.089 |
olla | -5.971 |
Flavoring | -5.890 |
edes | -5.861 |
Token | tri |
Token ID | 1333 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
Claud | +4.207 |
RANT | +4.201 |
handles | +4.093 |
handle | +3.877 |
fter | +3.822 |
Neg logit contributions | |
RAW | -5.816 |
atis | -5.773 |
Flavoring | -4.877 |
olla | -4.832 |
oho | -4.739 |
Token | - |
Token ID | 12 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
RAW | +1.143 |
atis | +1.138 |
oho | +0.919 |
olla | +0.916 |
ande | +0.901 |
Neg logit contributions | |
RANT | -0.808 |
Claud | -0.797 |
handles | -0.766 |
fter | -0.743 |
cler | -0.715 |
Token | color |
Token ID | 8043 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
RANT | +4.585 |
handles | +4.493 |
Claud | +4.448 |
fter | +4.259 |
handle | +4.215 |
Neg logit contributions | |
RAW | -5.761 |
atis | -5.668 |
Flavoring | -4.775 |
olla | -4.505 |
oho | -4.478 |
Token | group |
Token ID | 1448 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Claud | +2.916 |
handles | +2.905 |
RANT | +2.867 |
handle | +2.721 |
fter | +2.628 |
Neg logit contributions | |
RAW | -4.414 |
atis | -4.322 |
olla | -3.565 |
oho | -3.526 |
edes | -3.477 |
Token | thought |
Token ID | 1807 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
RAW | +2.513 |
atis | +2.512 |
oho | +1.990 |
olla | +1.984 |
ande | +1.946 |
Neg logit contributions | |
RANT | -2.233 |
Claud | -2.186 |
handles | -2.085 |
fter | -2.051 |
anski | -1.955 |
Token | focused |
Token ID | 5670 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
handles | +3.051 |
Claud | +3.000 |
RANT | +2.937 |
cler | +2.813 |
fter | +2.711 |
Neg logit contributions | |
RAW | -4.786 |
atis | -4.704 |
oho | -3.871 |
olla | -3.870 |
Flavoring | -3.823 |
Token | on |
Token ID | 319 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
RANT | +1.102 |
Claud | +1.089 |
handles | +1.041 |
fter | +1.004 |
cler | +0.979 |
Neg logit contributions | |
RAW | -1.610 |
atis | -1.607 |
oho | -1.306 |
olla | -1.298 |
ande | -1.277 |
Token | literally |
Token ID | 7360 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
RAW | +2.214 |
atis | +2.209 |
oho | +1.786 |
olla | +1.782 |
ande | +1.751 |
Neg logit contributions | |
RANT | -1.584 |
Claud | -1.548 |
handles | -1.478 |
fter | -1.443 |
cler | -1.383 |
Token | removing |
Token ID | 10829 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
Claud | +1.536 |
RANT | +1.521 |
handles | +1.488 |
cler | +1.415 |
fter | +1.393 |
Neg logit contributions | |
atis | -2.252 |
RAW | -2.238 |
oho | -1.804 |
olla | -1.802 |
ande | -1.784 |
Token | a |
Token ID | 257 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
Claud | +0.584 |
RANT | +0.580 |
handles | +0.562 |
cler | +0.533 |
fter | +0.528 |
Neg logit contributions | |
atis | -0.857 |
RAW | -0.852 |
oho | -0.697 |
olla | -0.687 |
ande | -0.676 |
Token | disease |
Token ID | 4369 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Claud | +5.594 |
RANT | +5.338 |
cler | +5.262 |
handles | +5.229 |
handle | +5.106 |
Neg logit contributions | |
atis | -8.896 |
RAW | -8.836 |
oho | -7.468 |
Flavoring | -7.423 |
imir | -7.204 |
Token | from |
Token ID | 422 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
Claud | +2.690 |
RANT | +2.641 |
handles | +2.554 |
fter | +2.412 |
cler | +2.383 |
Neg logit contributions | |
RAW | -4.585 |
atis | -4.527 |
oho | -3.830 |
olla | -3.704 |
Flavoring | -3.647 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
atis | +0.026 |
RAW | +0.026 |
oho | +0.021 |
olla | +0.021 |
ande | +0.021 |
Neg logit contributions | |
RANT | -0.017 |
Claud | -0.017 |
handles | -0.016 |
fter | -0.015 |
cler | -0.015 |
Token | body |
Token ID | 1767 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Claud | +1.516 |
RANT | +1.466 |
handles | +1.465 |
cler | +1.393 |
fter | +1.375 |
Neg logit contributions | |
atis | -1.884 |
RAW | -1.863 |
oho | -1.496 |
olla | -1.486 |
ande | -1.457 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
RANT | +0.130 |
Claud | +0.129 |
handles | +0.123 |
fter | +0.119 |
cler | +0.116 |
Neg logit contributions | |
RAW | -0.198 |
atis | -0.197 |
oho | -0.161 |
olla | -0.160 |
ande | -0.157 |
Token | origin |
Token ID | 47103 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
atis | +3.081 |
RAW | +3.074 |
olla | +2.408 |
oho | +2.402 |
ande | +2.356 |
Neg logit contributions | |
RANT | -2.935 |
Claud | -2.908 |
handles | -2.786 |
fter | -2.702 |
cler | -2.653 |
Token | will |
Token ID | 481 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
Claud | +1.372 |
RANT | +1.363 |
handles | +1.355 |
fter | +1.255 |
cler | +1.225 |
Neg logit contributions | |
RAW | -2.157 |
atis | -2.151 |
oho | -1.766 |
olla | -1.761 |
ande | -1.732 |
Token | shine |
Token ID | 18340 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
RANT | +0.486 |
Claud | +0.484 |
handles | +0.468 |
fter | +0.449 |
cler | +0.436 |
Neg logit contributions | |
RAW | -0.740 |
atis | -0.739 |
olla | -0.599 |
oho | -0.598 |
ande | -0.588 |
Token | in |
Token ID | 287 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
RAW | +3.049 |
atis | +3.041 |
oho | +2.463 |
olla | +2.454 |
ande | +2.414 |
Neg logit contributions | |
RANT | -2.124 |
Claud | -2.079 |
handles | -1.983 |
fter | -1.922 |
cler | -1.860 |
Token | a |
Token ID | 257 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Claud | +3.127 |
RANT | +3.065 |
handles | +3.024 |
fter | +2.874 |
cler | +2.845 |
Neg logit contributions | |
atis | -5.394 |
RAW | -5.331 |
oho | -4.361 |
olla | -4.354 |
edes | -4.345 |
Token | Vend |
Token ID | 44220 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Claud | +1.687 |
RANT | +1.666 |
handles | +1.605 |
fter | +1.570 |
cler | +1.542 |
Neg logit contributions | |
atis | -2.203 |
RAW | -2.190 |
olla | -1.733 |
oho | -1.733 |
ande | -1.712 |
Token | read |
Token ID | 961 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
fter | +3.776 |
ith | +3.678 |
RANT | +3.623 |
rent | +3.329 |
ocry | +3.307 |
Neg logit contributions | |
atis | -10.047 |
RAW | -9.820 |
behavi | -9.206 |
Flavoring | -8.496 |
Chaser | -8.363 |
Token | Deck |
Token ID | 20961 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
Claud | +3.586 |
RANT | +3.573 |
fter | +3.436 |
handles | +3.432 |
Rou | +3.299 |
Neg logit contributions | |
atis | -5.748 |
RAW | -5.683 |
oho | -4.585 |
ande | -4.553 |
edes | -4.548 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
RANT | +0.597 |
Claud | +0.592 |
handles | +0.565 |
fter | +0.551 |
cler | +0.532 |
Neg logit contributions | |
atis | -0.965 |
RAW | -0.961 |
oho | -0.785 |
olla | -0.784 |
ande | -0.770 |
Token | but |
Token ID | 475 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Claud | +1.782 |
RANT | +1.740 |
handles | +1.721 |
fter | +1.646 |
cler | +1.616 |
Neg logit contributions | |
RAW | -2.894 |
atis | -2.876 |
oho | -2.355 |
olla | -2.340 |
ande | -2.317 |
Token | that |
Token ID | 326 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
Claud | +0.769 |
RANT | +0.760 |
handles | +0.745 |
fter | +0.719 |
cler | +0.687 |
Neg logit contributions | |
RAW | -1.304 |
atis | -1.287 |
oho | -1.062 |
olla | -1.060 |
ande | -1.041 |
Token | affecting |
Token ID | 13891 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
handles | +3.362 |
RANT | +3.152 |
Claud | +3.140 |
cler | +3.129 |
handle | +3.071 |
Neg logit contributions | |
RAW | -5.965 |
atis | -5.956 |
olla | -4.994 |
Flavoring | -4.924 |
oho | -4.916 |
Token | its |
Token ID | 663 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
RAW | +0.917 |
atis | +0.916 |
oho | +0.740 |
olla | +0.738 |
ande | +0.727 |
Neg logit contributions | |
RANT | -0.633 |
Claud | -0.626 |
handles | -0.599 |
fter | -0.576 |
cler | -0.563 |
Token | 500 |
Token ID | 5323 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
RANT | +0.435 |
Claud | +0.433 |
handles | +0.423 |
cler | +0.399 |
fter | +0.397 |
Neg logit contributions | |
atis | -0.592 |
RAW | -0.591 |
oho | -0.475 |
olla | -0.474 |
ande | -0.469 |
Token | content |
Token ID | 2695 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
RAW | +1.297 |
atis | +1.295 |
oho | +1.046 |
olla | +1.041 |
ande | +1.019 |
Neg logit contributions | |
RANT | -0.961 |
Claud | -0.945 |
handles | -0.899 |
fter | -0.880 |
cler | -0.846 |
Token | moderators |
Token ID | 37265 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
RAW | +1.425 |
atis | +1.423 |
oho | +1.136 |
olla | +1.134 |
ande | +1.112 |
Neg logit contributions | |
RANT | -1.125 |
Claud | -1.109 |
handles | -1.064 |
fter | -1.033 |
cler | -1.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
RANT | +1.771 |
Claud | +1.762 |
handles | +1.701 |
fter | +1.606 |
cler | +1.580 |
Neg logit contributions | |
RAW | -2.912 |
atis | -2.884 |
oho | -2.392 |
olla | -2.380 |
ande | -2.326 |
Token | The |
Token ID | 383 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
RAW | +0.028 |
atis | +0.028 |
oho | +0.022 |
olla | +0.022 |
ande | +0.022 |
Neg logit contributions | |
RANT | -0.023 |
Claud | -0.023 |
handles | -0.021 |
fter | -0.021 |
cler | -0.020 |
Token | psychologist |
Token ID | 23540 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
RANT | +0.370 |
Claud | +0.368 |
handles | +0.358 |
fter | +0.342 |
cler | +0.337 |
Neg logit contributions | |
RAW | -0.481 |
atis | -0.480 |
olla | -0.384 |
oho | -0.382 |
ande | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
atis | +3.048 |
RAW | +3.027 |
oho | +2.421 |
olla | +2.416 |
ande | +2.379 |
Neg logit contributions | |
RANT | -2.346 |
Claud | -2.268 |
handles | -2.152 |
fter | -2.126 |
anski | -2.035 |
Token | Patricia |
Token ID | 30223 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
RAW | +0.803 |
atis | +0.803 |
oho | +0.648 |
olla | +0.646 |
ande | +0.632 |
Neg logit contributions | |
RANT | -0.584 |
Claud | -0.582 |
handles | -0.554 |
fter | -0.535 |
cler | -0.522 |
Token | M |
Token ID | 337 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
atis | +1.833 |
RAW | +1.832 |
olla | +1.470 |
oho | +1.467 |
ande | +1.438 |
Neg logit contributions | |
RANT | -1.440 |
Claud | -1.397 |
handles | -1.351 |
fter | -1.313 |
cler | -1.276 |
Token | We |
Token ID | 775 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Claud | +1.889 |
RANT | +1.886 |
handles | +1.787 |
fter | +1.716 |
Rou | +1.682 |
Neg logit contributions | |
atis | -2.171 |
RAW | -2.135 |
oho | -1.714 |
olla | -1.669 |
ande | -1.662 |
Token | know |
Token ID | 760 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
RANT | +1.261 |
Claud | +1.239 |
handles | +1.198 |
fter | +1.145 |
cler | +1.124 |
Neg logit contributions | |
atis | -1.900 |
RAW | -1.899 |
oho | -1.538 |
olla | -1.534 |
edes | -1.523 |
Token | what |
Token ID | 644 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Claud | +2.410 |
RANT | +2.366 |
handles | +2.331 |
fter | +2.171 |
cler | +2.171 |
Neg logit contributions | |
atis | -4.286 |
RAW | -4.246 |
oho | -3.499 |
olla | -3.496 |
edes | -3.459 |
Token | miracles |
Token ID | 32904 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Claud | +1.000 |
RANT | +0.993 |
handles | +0.971 |
fter | +0.907 |
cler | +0.893 |
Neg logit contributions | |
atis | -1.619 |
RAW | -1.617 |
olla | -1.314 |
oho | -1.314 |
ande | -1.284 |
Token | are |
Token ID | 389 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
RAW | +1.614 |
atis | +1.612 |
oho | +1.304 |
olla | +1.301 |
ande | +1.278 |
Neg logit contributions | |
RANT | -1.118 |
Claud | -1.103 |
handles | -1.054 |
fter | -1.020 |
cler | -0.988 |
Token | ! |
Token ID | 0 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
RANT | +1.599 |
Claud | +1.590 |
handles | +1.542 |
fter | +1.464 |
cler | +1.420 |
Neg logit contributions | |
atis | -2.770 |
RAW | -2.764 |
oho | -2.251 |
olla | -2.251 |
ande | -2.230 |
Token | And |
Token ID | 843 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Claud | +1.795 |
RANT | +1.792 |
handles | +1.711 |
fter | +1.639 |
cler | +1.605 |
Neg logit contributions | |
atis | -2.020 |
RAW | -2.005 |
oho | -1.585 |
olla | -1.557 |
edes | -1.547 |
Token | we |
Token ID | 356 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Claud | +1.344 |
RANT | +1.335 |
handles | +1.285 |
fter | +1.227 |
cler | +1.196 |
Neg logit contributions | |
atis | -2.237 |
RAW | -2.237 |
oho | -1.823 |
olla | -1.822 |
ande | -1.799 |
Token | know |
Token ID | 760 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
RANT | +1.438 |
Claud | +1.414 |
handles | +1.368 |
fter | +1.298 |
cler | +1.278 |
Neg logit contributions | |
RAW | -2.430 |
atis | -2.425 |
oho | -1.981 |
edes | -1.979 |
olla | -1.977 |
Token | those |
Token ID | 883 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Claud | +1.848 |
RANT | +1.821 |
handles | +1.769 |
fter | +1.662 |
cler | +1.649 |
Neg logit contributions | |
atis | -3.454 |
RAW | -3.419 |
olla | -2.828 |
oho | -2.816 |
edes | -2.805 |
Token | aren |
Token ID | 3588 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Claud | +1.760 |
RANT | +1.744 |
handles | +1.710 |
fter | +1.618 |
cler | +1.598 |
Neg logit contributions | |
RAW | -2.808 |
atis | -2.793 |
olla | -2.280 |
oho | -2.272 |
ande | -2.262 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
RANT | +0.345 |
Claud | +0.340 |
handles | +0.324 |
fter | +0.313 |
cler | +0.303 |
Neg logit contributions | |
RAW | -0.553 |
atis | -0.552 |
oho | -0.451 |
olla | -0.450 |
ande | -0.443 |
Token | the |
Token ID | 262 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
Claud | +1.847 |
RANT | +1.776 |
handles | +1.769 |
fter | +1.660 |
cler | +1.652 |
Neg logit contributions | |
RAW | -3.223 |
atis | -3.202 |
oho | -2.647 |
olla | -2.641 |
ande | -2.598 |
Token | smart |
Token ID | 4451 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Claud | +0.034 |
RANT | +0.034 |
handles | +0.033 |
fter | +0.031 |
cler | +0.031 |
Neg logit contributions | |
RAW | -0.047 |
atis | -0.047 |
olla | -0.038 |
oho | -0.038 |
ande | -0.037 |
Token | cities |
Token ID | 4736 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
atis | +4.307 |
RAW | +4.258 |
oho | +3.474 |
olla | +3.446 |
ande | +3.394 |
Neg logit contributions | |
RANT | -2.916 |
Claud | -2.856 |
fter | -2.677 |
handles | -2.666 |
anski | -2.543 |
Token | movement |
Token ID | 3356 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
RAW | +0.839 |
atis | +0.837 |
oho | +0.678 |
olla | +0.675 |
ande | +0.662 |
Neg logit contributions | |
RANT | -0.593 |
Claud | -0.586 |
handles | -0.563 |
fter | -0.541 |
cler | -0.527 |
Token | with |
Token ID | 351 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
RAW | +0.272 |
atis | +0.272 |
oho | +0.221 |
olla | +0.220 |
ande | +0.215 |
Neg logit contributions | |
RANT | -0.187 |
Claud | -0.186 |
handles | -0.180 |
fter | -0.171 |
cler | -0.168 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
RANT | +1.628 |
Claud | +1.625 |
handles | +1.568 |
fter | +1.448 |
cler | +1.437 |
Neg logit contributions | |
RAW | -2.633 |
atis | -2.623 |
oho | -2.141 |
olla | -2.125 |
ande | -2.111 |
Token | strong |
Token ID | 1913 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
RANT | +0.889 |
Claud | +0.885 |
handles | +0.858 |
fter | +0.820 |
cler | +0.813 |
Neg logit contributions | |
RAW | -1.217 |
atis | -1.217 |
oho | -0.978 |
ande | -0.977 |
olla | -0.973 |
Token | focus |
Token ID | 2962 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
RANT | +1.170 |
Claud | +1.149 |
handles | +1.131 |
cler | +1.068 |
fter | +1.059 |
Neg logit contributions | |
RAW | -1.674 |
atis | -1.662 |
oho | -1.347 |
olla | -1.341 |
ande | -1.330 |
Token | on |
Token ID | 319 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
RANT | +1.232 |
Claud | +1.212 |
handles | +1.159 |
fter | +1.121 |
cler | +1.087 |
Neg logit contributions | |
RAW | -1.820 |
atis | -1.816 |
oho | -1.476 |
olla | -1.471 |
ande | -1.446 |
Token | the |
Token ID | 262 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
Claud | +2.973 |
RANT | +2.947 |
handles | +2.909 |
cler | +2.752 |
fter | +2.707 |
Neg logit contributions | |
RAW | -4.417 |
atis | -4.367 |
olla | -3.556 |
oho | -3.533 |
ande | -3.482 |
Token | have |
Token ID | 423 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
Claud | +0.287 |
RANT | +0.285 |
handles | +0.277 |
fter | +0.267 |
cler | +0.259 |
Neg logit contributions | |
RAW | -0.436 |
atis | -0.432 |
oho | -0.352 |
olla | -0.350 |
edes | -0.346 |
Token | fought |
Token ID | 8350 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Claud | +0.163 |
RANT | +0.162 |
handles | +0.157 |
fter | +0.150 |
cler | +0.148 |
Neg logit contributions | |
RAW | -0.229 |
atis | -0.228 |
oho | -0.185 |
olla | -0.183 |
edes | -0.181 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Claud | +1.548 |
RANT | +1.515 |
handles | +1.473 |
fter | +1.388 |
cler | +1.372 |
Neg logit contributions | |
RAW | -2.486 |
atis | -2.456 |
oho | -2.058 |
olla | -2.004 |
edes | -2.001 |
Token | NFL |
Token ID | 5134 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
RAW | +1.772 |
atis | +1.769 |
oho | +1.432 |
olla | +1.429 |
ande | +1.402 |
Neg logit contributions | |
RANT | -1.242 |
Claud | -1.226 |
handles | -1.173 |
fter | -1.136 |
cler | -1.101 |
Token | harder |
Token ID | 7069 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
RANT | +1.155 |
Claud | +1.137 |
handles | +1.098 |
fter | +1.058 |
cler | +1.027 |
Neg logit contributions | |
RAW | -1.596 |
atis | -1.594 |
oho | -1.303 |
olla | -1.284 |
edes | -1.264 |
Token | to |
Token ID | 284 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
atis | +2.934 |
RAW | +2.931 |
olla | +2.369 |
oho | +2.364 |
ande | +2.312 |
Neg logit contributions | |
RANT | -2.147 |
Claud | -2.101 |
handles | -1.989 |
fter | -1.955 |
cler | -1.879 |
Token | make |
Token ID | 787 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
Claud | +2.473 |
handles | +2.445 |
RANT | +2.435 |
handle | +2.364 |
fter | +2.322 |
Neg logit contributions | |
RAW | -3.627 |
atis | -3.566 |
edes | -2.894 |
oho | -2.881 |
olla | -2.879 |
Token | employee |
Token ID | 6538 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Claud | +0.448 |
RANT | +0.442 |
handles | +0.426 |
fter | +0.404 |
cler | +0.394 |
Neg logit contributions | |
RAW | -0.756 |
atis | -0.753 |
oho | -0.623 |
olla | -0.615 |
ande | -0.609 |
Token | protections |
Token ID | 15018 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
RAW | +1.514 |
atis | +1.510 |
oho | +1.200 |
olla | +1.193 |
ande | +1.173 |
Neg logit contributions | |
RANT | -1.275 |
Claud | -1.261 |
handles | -1.213 |
fter | -1.176 |
cler | -1.145 |
Token | more |
Token ID | 517 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
RAW | +0.748 |
atis | +0.745 |
olla | +0.604 |
oho | +0.604 |
ande | +0.592 |
Neg logit contributions | |
RANT | -0.501 |
Claud | -0.494 |
handles | -0.475 |
fter | -0.460 |
cler | -0.446 |
Token | explicit |
Token ID | 7952 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
RANT | +0.252 |
Claud | +0.249 |
handles | +0.239 |
fter | +0.231 |
cler | +0.224 |
Neg logit contributions | |
RAW | -0.412 |
atis | -0.412 |
olla | -0.339 |
oho | -0.336 |
ande | -0.331 |
Token | – |
Token ID | 784 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
RAW | +0.922 |
atis | +0.920 |
oho | +0.743 |
olla | +0.741 |
ande | +0.728 |
Neg logit contributions | |
RANT | -0.659 |
Claud | -0.648 |
handles | -0.618 |
fter | -0.601 |
cler | -0.582 |
Token | but |
Token ID | 475 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
RAW | +1.383 |
atis | +1.381 |
oho | +1.118 |
olla | +1.115 |
ande | +1.095 |
Neg logit contributions | |
RANT | -0.964 |
Claud | -0.949 |
handles | -0.907 |
fter | -0.879 |
cler | -0.851 |
Token | Vox |
Token ID | 28035 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
RAW | +0.511 |
atis | +0.508 |
oho | +0.414 |
olla | +0.414 |
ande | +0.407 |
Neg logit contributions | |
RANT | -0.330 |
Claud | -0.328 |
handles | -0.313 |
fter | -0.302 |
cler | -0.292 |
Token | this |
Token ID | 428 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
RAW | +0.255 |
atis | +0.253 |
oho | +0.205 |
olla | +0.204 |
edes | +0.200 |
Neg logit contributions | |
RANT | -0.186 |
Claud | -0.183 |
handles | -0.176 |
fter | -0.170 |
cler | -0.165 |
Token | morning |
Token ID | 3329 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
RANT | +0.860 |
Claud | +0.858 |
handles | +0.831 |
fter | +0.793 |
cler | +0.778 |
Neg logit contributions | |
RAW | -1.303 |
atis | -1.300 |
oho | -1.056 |
olla | -1.054 |
ande | -1.032 |
Token | highlighted |
Token ID | 14537 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
RAW | +0.452 |
atis | +0.450 |
oho | +0.362 |
olla | +0.360 |
ande | +0.354 |
Neg logit contributions | |
RANT | -0.330 |
Claud | -0.328 |
handles | -0.317 |
fter | -0.305 |
cler | -0.298 |
Token | what |
Token ID | 644 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
RANT | +0.573 |
Claud | +0.569 |
handles | +0.541 |
fter | +0.522 |
cler | +0.506 |
Neg logit contributions | |
atis | -0.907 |
RAW | -0.906 |
oho | -0.739 |
olla | -0.737 |
edes | -0.726 |
Token | I |
Token ID | 314 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
RAW | +1.814 |
atis | +1.812 |
oho | +1.473 |
olla | +1.471 |
ande | +1.445 |
Neg logit contributions | |
RANT | -1.201 |
Claud | -1.180 |
handles | -1.124 |
fter | -1.093 |
cler | -1.054 |
Token | believe |
Token ID | 1975 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
atis | +4.653 |
RAW | +4.622 |
oho | +3.784 |
olla | +3.775 |
ande | +3.673 |
Neg logit contributions | |
RANT | -3.349 |
Claud | -3.258 |
handles | -3.121 |
fter | -3.010 |
cler | -2.882 |
Token | is |
Token ID | 318 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
RAW | +0.037 |
atis | +0.037 |
oho | +0.030 |
olla | +0.030 |
ande | +0.029 |
Neg logit contributions | |
RANT | -0.025 |
Claud | -0.025 |
handles | -0.024 |
fter | -0.023 |
cler | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
RANT | +0.787 |
Claud | +0.784 |
handles | +0.740 |
fter | +0.717 |
cler | +0.698 |
Neg logit contributions | |
atis | -1.262 |
RAW | -1.262 |
oho | -1.037 |
olla | -1.030 |
ande | -1.016 |
Token | _ |
Token ID | 62 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
RANT | +0.032 |
Claud | +0.031 |
handles | +0.030 |
fter | +0.029 |
cler | +0.028 |
Neg logit contributions | |
atis | -0.049 |
RAW | -0.048 |
oho | -0.040 |
olla | -0.039 |
ande | -0.039 |
Token | state |
Token ID | 5219 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
RANT | +4.205 |
Claud | +4.157 |
handles | +4.039 |
fter | +3.958 |
pent | +3.778 |
Neg logit contributions | |
atis | -4.907 |
RAW | -4.815 |
oho | -3.878 |
Flavoring | -3.825 |
olla | -3.821 |
Token | inside |
Token ID | 2641 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
RAW | +1.748 |
atis | +1.746 |
oho | +1.416 |
olla | +1.412 |
ande | +1.388 |
Neg logit contributions | |
RANT | -1.192 |
Claud | -1.173 |
handles | -1.120 |
fter | -1.086 |
cler | -1.050 |
Token | an |
Token ID | 281 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
RAW | +1.223 |
atis | +1.223 |
oho | +0.988 |
olla | +0.987 |
ande | +0.968 |
Neg logit contributions | |
RANT | -0.857 |
Claud | -0.841 |
handles | -0.800 |
fter | -0.779 |
cler | -0.753 |
Token | Arc |
Token ID | 10173 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
RANT | +1.396 |
Claud | +1.388 |
handles | +1.365 |
fter | +1.309 |
cler | +1.255 |
Neg logit contributions | |
RAW | -1.955 |
atis | -1.932 |
oho | -1.577 |
olla | -1.568 |
edes | -1.562 |
Token | , |
Token ID | 837 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
RANT | +1.883 |
Claud | +1.865 |
handles | +1.819 |
fter | +1.749 |
cler | +1.667 |
Neg logit contributions | |
atis | -2.683 |
RAW | -2.673 |
oho | -2.180 |
olla | -2.177 |
ande | -2.125 |
Token | an |
Token ID | 281 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
RAW | +1.581 |
atis | +1.578 |
oho | +1.283 |
olla | +1.278 |
ande | +1.256 |
Neg logit contributions | |
RANT | -1.072 |
Claud | -1.064 |
handles | -1.022 |
fter | -0.986 |
cler | -0.956 |
Token | As |
Token ID | 1081 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
RANT | +0.792 |
Claud | +0.786 |
handles | +0.768 |
fter | +0.736 |
cler | +0.710 |
Neg logit contributions | |
RAW | -1.138 |
atis | -1.127 |
oho | -0.921 |
olla | -0.919 |
edes | -0.909 |
Token | ynchronous |
Token ID | 31301 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
RAW | +1.668 |
atis | +1.662 |
oho | +1.322 |
olla | +1.321 |
ande | +1.297 |
Neg logit contributions | |
RANT | -1.323 |
Claud | -1.300 |
handles | -1.239 |
fter | -1.203 |
cler | -1.173 |
Token | Reference |
Token ID | 20984 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Claud | +3.093 |
RANT | +3.082 |
handles | +2.992 |
fter | +2.832 |
Rou | +2.774 |
Neg logit contributions | |
atis | -4.083 |
RAW | -4.038 |
olla | -3.303 |
oho | -3.283 |
ande | -3.245 |
Token | Counter |
Token ID | 15034 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Claud | +1.711 |
RANT | +1.703 |
handles | +1.641 |
fter | +1.555 |
cler | +1.509 |
Neg logit contributions | |
atis | -2.681 |
RAW | -2.665 |
oho | -2.214 |
olla | -2.181 |
ande | -2.134 |
Token | increments |
Token ID | 41867 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
RAW | +3.036 |
atis | +3.023 |
oho | +2.400 |
olla | +2.391 |
ande | +2.350 |
Neg logit contributions | |
RANT | -2.490 |
Claud | -2.437 |
handles | -2.318 |
fter | -2.282 |
cler | -2.201 |
Token | of |
Token ID | 286 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
RANT | +0.476 |
Claud | +0.471 |
handles | +0.457 |
fter | +0.434 |
cler | +0.425 |
Neg logit contributions | |
RAW | -0.733 |
atis | -0.726 |
oho | -0.595 |
olla | -0.593 |
ande | -0.584 |
Token | 50 |
Token ID | 2026 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
atis | +0.156 |
RAW | +0.156 |
oho | +0.126 |
olla | +0.126 |
ande | +0.123 |
Neg logit contributions | |
RANT | -0.117 |
Claud | -0.116 |
handles | -0.112 |
fter | -0.107 |
cler | -0.105 |
Token | gig |
Token ID | 12526 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
atis | +2.374 |
RAW | +2.374 |
oho | +1.824 |
olla | +1.805 |
edes | +1.782 |
Neg logit contributions | |
RANT | -2.448 |
Claud | -2.404 |
handles | -2.300 |
fter | -2.261 |
cler | -2.208 |
Token | abytes |
Token ID | 38346 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
atis | +2.647 |
RAW | +2.550 |
oho | +1.846 |
ande | +1.814 |
olla | +1.811 |
Neg logit contributions | |
RANT | -3.970 |
Claud | -3.895 |
handles | -3.676 |
fter | -3.657 |
cler | -3.637 |
Token | would |
Token ID | 561 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
atis | +2.385 |
RAW | +2.381 |
oho | +1.919 |
olla | +1.916 |
edes | +1.881 |
Neg logit contributions | |
RANT | -1.699 |
Claud | -1.658 |
handles | -1.566 |
fter | -1.542 |
cler | -1.481 |
Token | cost |
Token ID | 1575 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
atis | +3.494 |
RAW | +3.455 |
olla | +2.768 |
oho | +2.764 |
ande | +2.704 |
Neg logit contributions | |
RANT | -2.847 |
Claud | -2.788 |
handles | -2.643 |
fter | -2.570 |
cler | -2.486 |
Token | $ |
Token ID | 720 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
atis | +3.514 |
RAW | +3.512 |
olla | +2.775 |
oho | +2.765 |
edes | +2.714 |
Neg logit contributions | |
RANT | -2.947 |
Claud | -2.885 |
handles | -2.756 |
fter | -2.721 |
anski | -2.602 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
atis | +1.169 |
RAW | +1.164 |
oho | +0.922 |
olla | +0.913 |
ande | +0.905 |
Neg logit contributions | |
RANT | -1.034 |
Claud | -1.016 |
handles | -0.972 |
fter | -0.949 |
cler | -0.916 |
Token | more |
Token ID | 517 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
RAW | +3.369 |
atis | +3.366 |
olla | +2.712 |
oho | +2.702 |
ande | +2.646 |
Neg logit contributions | |
RANT | -2.496 |
Claud | -2.443 |
handles | -2.313 |
fter | -2.269 |
cler | -2.174 |
Token | under |
Token ID | 739 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
RAW | +3.574 |
atis | +3.572 |
olla | +2.890 |
oho | +2.872 |
ande | +2.801 |
Neg logit contributions | |
RANT | -2.557 |
Claud | -2.487 |
handles | -2.348 |
fter | -2.308 |
anski | -2.204 |
Token | as |
Token ID | 355 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
RANT | +2.162 |
Claud | +2.133 |
handles | +2.028 |
fter | +1.933 |
cler | +1.876 |
Neg logit contributions | |
RAW | -3.973 |
atis | -3.934 |
oho | -3.244 |
olla | -3.232 |
edes | -3.198 |
Token | an |
Token ID | 281 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
RAW | +6.543 |
atis | +6.464 |
oho | +5.348 |
olla | +5.299 |
ande | +5.285 |
Neg logit contributions | |
RANT | -4.930 |
Claud | -4.828 |
handles | -4.554 |
fter | -4.485 |
anski | -4.402 |
Token | independent |
Token ID | 4795 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
atis | +4.648 |
RAW | +4.647 |
oho | +3.812 |
olla | +3.790 |
ande | +3.762 |
Neg logit contributions | |
RANT | -2.782 |
Claud | -2.769 |
handles | -2.595 |
fter | -2.515 |
cler | -2.439 |
Token | voice |
Token ID | 3809 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
atis | +2.526 |
RAW | +2.524 |
olla | +2.020 |
oho | +2.016 |
ande | +1.997 |
Neg logit contributions | |
RANT | -1.873 |
Claud | -1.844 |
handles | -1.762 |
fter | -1.708 |
cler | -1.652 |
Token | who |
Token ID | 508 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
RAW | +1.891 |
atis | +1.885 |
oho | +1.520 |
olla | +1.517 |
ande | +1.499 |
Neg logit contributions | |
RANT | -1.360 |
Claud | -1.341 |
handles | -1.275 |
fter | -1.242 |
cler | -1.198 |
Token | will |
Token ID | 481 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
RAW | +1.592 |
atis | +1.589 |
oho | +1.284 |
olla | +1.283 |
ande | +1.258 |
Neg logit contributions | |
RANT | -1.113 |
Claud | -1.097 |
handles | -1.052 |
fter | -1.016 |
cler | -0.987 |
Token | protect |
Token ID | 1805 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
RAW | +2.683 |
atis | +2.680 |
oho | +2.171 |
olla | +2.162 |
ande | +2.128 |
Neg logit contributions | |
RANT | -1.899 |
Claud | -1.868 |
handles | -1.779 |
fter | -1.729 |
cler | -1.670 |
Token | Montana |
Token ID | 18311 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
RANT | +1.002 |
Claud | +0.985 |
handles | +0.952 |
fter | +0.907 |
cler | +0.895 |
Neg logit contributions | |
atis | -1.507 |
RAW | -1.498 |
olla | -1.208 |
oho | -1.202 |
edes | -1.200 |
Token | � |
Token ID | 447 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
RANT | +0.445 |
Claud | +0.437 |
handles | +0.422 |
fter | +0.403 |
cler | +0.393 |
Neg logit contributions | |
RAW | -0.700 |
atis | -0.699 |
oho | -0.570 |
olla | -0.569 |
edes | -0.560 |
Token | � |
Token ID | 247 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
RAW | +1.342 |
atis | +1.337 |
oho | +1.030 |
olla | +1.026 |
ande | +1.000 |
Neg logit contributions | |
RANT | -1.414 |
Claud | -1.396 |
handles | -1.344 |
fter | -1.309 |
cler | -1.279 |
Token | s |
Token ID | 82 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
RANT | +2.374 |
Claud | +2.280 |
handles | +2.261 |
fter | +2.200 |
ith | +2.095 |
Neg logit contributions | |
RAW | -3.131 |
atis | -3.109 |
oho | -2.510 |
olla | -2.494 |
Flavoring | -2.442 |
Token | times |
Token ID | 1661 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
RAW | +5.925 |
atis | +5.887 |
olla | +4.709 |
edes | +4.690 |
ande | +4.617 |
Neg logit contributions | |
RANT | -4.982 |
Claud | -4.764 |
handles | -4.443 |
fter | -4.421 |
anski | -4.375 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
atis | +2.577 |
RAW | +2.577 |
oho | +2.078 |
olla | +2.072 |
ande | +2.040 |
Neg logit contributions | |
RANT | -1.875 |
Claud | -1.840 |
handles | -1.749 |
fter | -1.704 |
cler | -1.644 |
Token | I |
Token ID | 314 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Claud | +2.698 |
RANT | +2.611 |
handles | +2.430 |
Rou | +2.365 |
fter | +2.358 |
Neg logit contributions | |
atis | -3.804 |
RAW | -3.743 |
oho | -3.061 |
olla | -2.999 |
ande | -2.989 |
Token | know |
Token ID | 760 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
RAW | +2.199 |
atis | +2.189 |
oho | +1.771 |
olla | +1.768 |
ande | +1.738 |
Neg logit contributions | |
RANT | -1.495 |
Claud | -1.479 |
handles | -1.408 |
fter | -1.365 |
cler | -1.328 |
Token | that |
Token ID | 326 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
Claud | +1.906 |
RANT | +1.844 |
handles | +1.788 |
cler | +1.702 |
fter | +1.679 |
Neg logit contributions | |
atis | -3.504 |
RAW | -3.463 |
olla | -2.835 |
oho | -2.828 |
Flavoring | -2.798 |
Token | science |
Token ID | 3783 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Claud | +0.135 |
RANT | +0.135 |
handles | +0.129 |
fter | +0.123 |
cler | +0.121 |
Neg logit contributions | |
RAW | -0.223 |
atis | -0.223 |
oho | -0.182 |
olla | -0.181 |
ande | -0.178 |
Token | doesn |
Token ID | 1595 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
RAW | +3.125 |
atis | +3.118 |
oho | +2.516 |
olla | +2.509 |
ande | +2.467 |
Neg logit contributions | |
RANT | -2.314 |
Claud | -2.268 |
handles | -2.158 |
fter | -2.113 |
cler | -2.036 |
Token | 't |
Token ID | 470 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
atis | +1.579 |
RAW | +1.579 |
oho | +1.305 |
olla | +1.302 |
ande | +1.282 |
Neg logit contributions | |
RANT | -0.852 |
Claud | -0.837 |
handles | -0.793 |
fter | -0.766 |
cler | -0.734 |
Token | necessarily |
Token ID | 6646 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
atis | +6.459 |
RAW | +6.334 |
oho | +5.199 |
ande | +5.142 |
olla | +5.131 |
Neg logit contributions | |
RANT | -5.613 |
Claud | -5.279 |
handles | -4.967 |
fter | -4.931 |
swick | -4.794 |
Token | sway |
Token ID | 20009 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
atis | +3.664 |
RAW | +3.646 |
oho | +2.916 |
olla | +2.903 |
ande | +2.863 |
Neg logit contributions | |
RANT | -3.199 |
Claud | -3.114 |
handles | -2.981 |
fter | -2.912 |
cler | -2.812 |
Token | policy |
Token ID | 2450 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
atis | +1.379 |
RAW | +1.378 |
olla | +1.105 |
oho | +1.104 |
ande | +1.081 |
Neg logit contributions | |
RANT | -1.023 |
Claud | -1.010 |
handles | -0.969 |
fter | -0.938 |
cler | -0.913 |
Token | very |
Token ID | 845 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
RAW | +1.938 |
atis | +1.935 |
oho | +1.549 |
olla | +1.545 |
ande | +1.516 |
Neg logit contributions | |
RANT | -1.504 |
Claud | -1.482 |
handles | -1.419 |
fter | -1.379 |
cler | -1.338 |
Token | strong |
Token ID | 1913 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
atis | +0.511 |
RAW | +0.507 |
olla | +0.414 |
oho | +0.412 |
ande | +0.407 |
Neg logit contributions | |
RANT | -0.347 |
Claud | -0.342 |
handles | -0.329 |
fter | -0.318 |
cler | -0.307 |
Token | performance |
Token ID | 2854 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
RAW | +2.003 |
atis | +1.999 |
oho | +1.588 |
olla | +1.586 |
ande | +1.560 |
Neg logit contributions | |
RANT | -1.647 |
Claud | -1.621 |
handles | -1.549 |
fter | -1.513 |
cler | -1.467 |
Token | versus |
Token ID | 9051 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
RAW | +0.549 |
atis | +0.547 |
oho | +0.445 |
olla | +0.444 |
ande | +0.436 |
Neg logit contributions | |
RANT | -0.365 |
Claud | -0.360 |
handles | -0.344 |
fter | -0.333 |
cler | -0.322 |
Token | m |
Token ID | 285 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
RANT | +0.515 |
Claud | +0.514 |
handles | +0.489 |
fter | +0.474 |
cler | +0.461 |
Neg logit contributions | |
RAW | -0.662 |
atis | -0.659 |
oho | -0.527 |
olla | -0.526 |
edes | -0.515 |
Token | ouses |
Token ID | 11370 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
RANT | +2.602 |
Claud | +2.408 |
ith | +2.312 |
handles | +2.306 |
fter | +2.262 |
Neg logit contributions | |
atis | -4.395 |
RAW | -4.289 |
oho | -3.542 |
olla | -3.529 |
Flavoring | -3.515 |
Token | ports |
Token ID | 3742 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
atis | +1.245 |
RAW | +1.245 |
olla | +1.061 |
oho | +1.059 |
ande | +1.039 |
Neg logit contributions | |
RANT | -0.406 |
Claud | -0.394 |
handles | -0.366 |
fter | -0.348 |
cler | -0.327 |
Token | in |
Token ID | 287 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
RANT | +0.412 |
Claud | +0.408 |
handles | +0.390 |
fter | +0.376 |
cler | +0.364 |
Neg logit contributions | |
RAW | -0.643 |
atis | -0.641 |
oho | -0.525 |
olla | -0.522 |
ande | -0.512 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
RAW | +0.266 |
atis | +0.265 |
oho | +0.213 |
olla | +0.213 |
ande | +0.209 |
Neg logit contributions | |
RANT | -0.195 |
Claud | -0.193 |
handles | -0.185 |
fter | -0.179 |
cler | -0.173 |
Token | deciding |
Token ID | 14615 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
Claud | +1.341 |
RANT | +1.328 |
handles | +1.295 |
fter | +1.227 |
Rou | +1.190 |
Neg logit contributions | |
atis | -2.092 |
RAW | -2.090 |
oho | -1.703 |
olla | -1.697 |
edes | -1.667 |
Token | game |
Token ID | 983 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
RANT | +0.593 |
Claud | +0.593 |
handles | +0.571 |
fter | +0.551 |
cler | +0.532 |
Neg logit contributions | |
RAW | -0.782 |
atis | -0.781 |
oho | -0.632 |
olla | -0.628 |
edes | -0.614 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
RAW | +2.147 |
atis | +2.131 |
oho | +1.697 |
olla | +1.691 |
ande | +1.667 |
Neg logit contributions | |
RANT | -1.762 |
Claud | -1.738 |
handles | -1.667 |
fter | -1.628 |
cler | -1.573 |
Token | # |
Token ID | 1303 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
RAW | +1.398 |
atis | +1.396 |
oho | +1.112 |
olla | +1.109 |
ande | +1.088 |
Neg logit contributions | |
RANT | -1.130 |
Claud | -1.114 |
handles | -1.068 |
fter | -1.039 |
cler | -1.008 |
Token | deb |
Token ID | 11275 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
atis | +0.188 |
RAW | +0.187 |
oho | +0.150 |
olla | +0.150 |
ande | +0.147 |
Neg logit contributions | |
RANT | -0.147 |
Claud | -0.144 |
handles | -0.139 |
fter | -0.135 |
cler | -0.130 |
Token | ates |
Token ID | 689 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
RAW | +0.663 |
atis | +0.662 |
oho | +0.514 |
olla | +0.512 |
ande | +0.501 |
Neg logit contributions | |
RANT | -0.660 |
Claud | -0.651 |
handles | -0.627 |
fter | -0.611 |
cler | -0.596 |
Token | # |
Token ID | 1303 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
RANT | +1.559 |
Claud | +1.530 |
handles | +1.467 |
fter | +1.431 |
cler | +1.361 |
Neg logit contributions | |
atis | -2.250 |
RAW | -2.233 |
olla | -1.830 |
oho | -1.827 |
edes | -1.785 |
Token | Occup |
Token ID | 47658 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
RANT | +1.686 |
Claud | +1.617 |
handles | +1.565 |
fter | +1.541 |
pent | +1.463 |
Neg logit contributions | |
atis | -2.148 |
RAW | -2.121 |
olla | -1.727 |
oho | -1.723 |
Flavoring | -1.678 |
Token | y |
Token ID | 88 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
RAW | +6.993 |
atis | +6.946 |
oho | +5.587 |
olla | +5.432 |
edes | +5.390 |
Neg logit contributions | |
RANT | -7.611 |
Claud | -7.301 |
handles | -7.004 |
cler | -6.817 |
fter | -6.598 |
Token | The |
Token ID | 464 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
RAW | +3.351 |
atis | +3.307 |
oho | +2.652 |
olla | +2.650 |
ande | +2.622 |
Neg logit contributions | |
RANT | -2.457 |
Claud | -2.451 |
handles | -2.332 |
fter | -2.268 |
cler | -2.222 |
Token | Deb |
Token ID | 16587 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
RANT | +0.151 |
Claud | +0.148 |
handles | +0.142 |
fter | +0.138 |
cler | +0.132 |
Neg logit contributions | |
atis | -0.205 |
RAW | -0.205 |
oho | -0.165 |
olla | -0.165 |
ande | -0.162 |
Token | ates |
Token ID | 689 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
RAW | +0.152 |
atis | +0.152 |
oho | +0.118 |
olla | +0.118 |
ande | +0.115 |
Neg logit contributions | |
RANT | -0.147 |
Claud | -0.146 |
handles | -0.140 |
fter | -0.137 |
cler | -0.133 |
Token | pic |
Token ID | 8301 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
RANT | +2.995 |
Claud | +2.905 |
handles | +2.768 |
fter | +2.677 |
cler | +2.567 |
Neg logit contributions | |
atis | -4.813 |
RAW | -4.758 |
oho | -3.951 |
olla | -3.951 |
edes | -3.855 |
Token | had |
Token ID | 550 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
RANT | +1.389 |
Claud | +1.382 |
handles | +1.356 |
fter | +1.289 |
cler | +1.270 |
Neg logit contributions | |
RAW | -2.192 |
atis | -2.174 |
olla | -1.782 |
oho | -1.764 |
Flavoring | -1.751 |
Token | to |
Token ID | 284 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
RAW | +1.267 |
atis | +1.265 |
oho | +1.022 |
olla | +1.020 |
ande | +1.003 |
Neg logit contributions | |
RANT | -0.898 |
Claud | -0.883 |
handles | -0.844 |
fter | -0.820 |
cler | -0.793 |
Token | take |
Token ID | 1011 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
Claud | +1.774 |
handles | +1.764 |
RANT | +1.739 |
handle | +1.697 |
fter | +1.693 |
Neg logit contributions | |
RAW | -2.855 |
atis | -2.825 |
olla | -2.315 |
oho | -2.296 |
edes | -2.261 |
Token | matters |
Token ID | 6067 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
RANT | +0.276 |
Claud | +0.275 |
handles | +0.264 |
fter | +0.252 |
cler | +0.247 |
Neg logit contributions | |
atis | -0.413 |
RAW | -0.412 |
oho | -0.335 |
olla | -0.334 |
ande | -0.329 |
Token | into |
Token ID | 656 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Claud | +2.180 |
RANT | +2.165 |
handles | +2.154 |
fter | +2.054 |
cler | +2.011 |
Neg logit contributions | |
RAW | -3.061 |
atis | -3.021 |
oho | -2.460 |
olla | -2.428 |
ande | -2.413 |
Token | our |
Token ID | 674 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
atis | +2.073 |
RAW | +2.062 |
olla | +1.580 |
oho | +1.565 |
ande | +1.536 |
Neg logit contributions | |
RANT | -2.276 |
Claud | -2.213 |
handles | -2.105 |
fter | -2.074 |
cler | -2.026 |
Token | own |
Token ID | 898 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
RAW | +7.828 |
atis | +7.794 |
oho | +6.343 |
olla | +6.318 |
ande | +6.205 |
Neg logit contributions | |
RANT | -5.848 |
Claud | -5.512 |
fter | -4.967 |
handles | -4.925 |
Rou | -4.780 |
Token | hands |
Token ID | 2832 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
atis | +6.815 |
RAW | +6.810 |
olla | +4.960 |
oho | +4.929 |
ande | +4.752 |
Neg logit contributions | |
RANT | -10.888 |
Claud | -10.355 |
fter | -9.613 |
rent | -9.316 |
cler | -9.288 |
Token | . |
Token ID | 13 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
RANT | +1.531 |
Claud | +1.517 |
handles | +1.471 |
fter | +1.409 |
cler | +1.370 |
Neg logit contributions | |
atis | -2.410 |
RAW | -2.401 |
olla | -1.962 |
oho | -1.962 |
ande | -1.918 |
Token | Long |
Token ID | 5882 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
atis | +0.470 |
RAW | +0.468 |
oho | +0.371 |
olla | +0.368 |
ande | +0.362 |
Neg logit contributions | |
RANT | -0.403 |
Claud | -0.401 |
handles | -0.381 |
fter | -0.370 |
cler | -0.359 |
Token | story |
Token ID | 1621 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
RANT | +2.035 |
Claud | +2.018 |
handles | +1.980 |
fter | +1.889 |
cler | +1.838 |
Neg logit contributions | |
atis | -2.694 |
RAW | -2.668 |
oho | -2.144 |
olla | -2.143 |
ande | -2.098 |
Token | that |
Token ID | 326 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
RAW | +2.744 |
atis | +2.738 |
oho | +2.206 |
olla | +2.198 |
ande | +2.164 |
Neg logit contributions | |
RANT | -2.008 |
Claud | -1.972 |
handles | -1.878 |
fter | -1.833 |
cler | -1.762 |
Token | do |
Token ID | 466 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
RAW | +0.507 |
atis | +0.506 |
olla | +0.408 |
oho | +0.406 |
edes | +0.399 |
Neg logit contributions | |
Claud | -0.354 |
RANT | -0.353 |
handles | -0.341 |
fter | -0.326 |
cler | -0.323 |
Token | practice |
Token ID | 3357 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
RANT | +0.036 |
Claud | +0.036 |
handles | +0.034 |
fter | +0.033 |
cler | +0.032 |
Neg logit contributions | |
RAW | -0.057 |
atis | -0.057 |
oho | -0.047 |
olla | -0.046 |
ande | -0.046 |
Token | Lac |
Token ID | 23115 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
RAW | +2.897 |
atis | +2.878 |
oho | +2.320 |
olla | +2.313 |
ande | +2.272 |
Neg logit contributions | |
RANT | -2.228 |
Claud | -2.167 |
handles | -2.066 |
fter | -2.032 |
anski | -1.937 |
Token | anian |
Token ID | 38336 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
RAW | +1.607 |
atis | +1.600 |
olla | +1.116 |
oho | +1.113 |
ande | +1.098 |
Neg logit contributions | |
RANT | -2.750 |
Claud | -2.730 |
handles | -2.639 |
fter | -2.589 |
cler | -2.532 |
Token | psycho |
Token ID | 30731 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
RAW | +1.828 |
atis | +1.821 |
oho | +1.450 |
olla | +1.443 |
ande | +1.414 |
Neg logit contributions | |
RANT | -1.543 |
Claud | -1.519 |
handles | -1.449 |
fter | -1.419 |
cler | -1.366 |
Token | analysis |
Token ID | 20930 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
atis | +7.849 |
RAW | +7.696 |
oho | +6.146 |
ande | +6.063 |
olla | +6.016 |
Neg logit contributions | |
RANT | -6.627 |
Claud | -6.488 |
handles | -5.948 |
fter | -5.919 |
Rou | -5.640 |
Token | in |
Token ID | 287 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
RAW | +1.584 |
atis | +1.582 |
oho | +1.280 |
olla | +1.278 |
ande | +1.254 |
Neg logit contributions | |
RANT | -1.082 |
Claud | -1.068 |
handles | -1.023 |
fter | -0.989 |
cler | -0.961 |
Token | such |
Token ID | 884 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
RANT | +0.128 |
Claud | +0.126 |
handles | +0.121 |
fter | +0.117 |
cler | +0.114 |
Neg logit contributions | |
atis | -0.179 |
RAW | -0.179 |
oho | -0.145 |
olla | -0.144 |
ande | -0.142 |
Token | settings |
Token ID | 6460 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
RAW | +2.418 |
atis | +2.407 |
oho | +1.945 |
olla | +1.937 |
ande | +1.904 |
Neg logit contributions | |
RANT | -1.771 |
Claud | -1.739 |
handles | -1.657 |
fter | -1.612 |
cler | -1.556 |
Token | practice |
Token ID | 3357 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
RAW | +0.931 |
atis | +0.929 |
olla | +0.751 |
oho | +0.751 |
ande | +0.735 |
Neg logit contributions | |
RANT | -0.636 |
Claud | -0.628 |
handles | -0.602 |
fter | -0.582 |
cler | -0.566 |
Token | you |
Token ID | 345 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Claud | +1.282 |
RANT | +1.277 |
handles | +1.229 |
cler | +1.154 |
fter | +1.153 |
Neg logit contributions | |
atis | -2.008 |
RAW | -2.003 |
oho | -1.651 |
olla | -1.630 |
ande | -1.616 |
Token | have |
Token ID | 423 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
RAW | +2.649 |
atis | +2.645 |
oho | +2.136 |
olla | +2.131 |
ande | +2.093 |
Neg logit contributions | |
RANT | -1.882 |
Claud | -1.853 |
handles | -1.770 |
fter | -1.718 |
cler | -1.663 |
Token | all |
Token ID | 477 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
RAW | +0.991 |
atis | +0.989 |
oho | +0.805 |
olla | +0.800 |
ande | +0.787 |
Neg logit contributions | |
RANT | -0.672 |
Claud | -0.666 |
handles | -0.638 |
fter | -0.610 |
cler | -0.598 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
RANT | +1.027 |
Claud | +1.020 |
handles | +0.984 |
fter | +0.931 |
cler | +0.920 |
Neg logit contributions | |
RAW | -1.656 |
atis | -1.653 |
oho | -1.362 |
olla | -1.352 |
ande | -1.340 |
Token | time |
Token ID | 640 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
Claud | +1.198 |
RANT | +1.187 |
handles | +1.174 |
cler | +1.103 |
fter | +1.089 |
Neg logit contributions | |
atis | -1.716 |
RAW | -1.715 |
oho | -1.381 |
olla | -1.380 |
ande | -1.372 |
Token | in |
Token ID | 287 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
atis | +5.788 |
RAW | +5.782 |
oho | +4.589 |
olla | +4.564 |
edes | +4.500 |
Neg logit contributions | |
RANT | -4.663 |
Claud | -4.526 |
fter | -4.298 |
handles | -4.245 |
anski | -4.106 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
RAW | +7.226 |
atis | +7.170 |
oho | +5.613 |
olla | +5.574 |
ande | +5.552 |
Neg logit contributions | |
RANT | -7.186 |
Claud | -6.764 |
fter | -6.666 |
handles | -6.387 |
swick | -6.291 |
Token | world |
Token ID | 995 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
RAW | +2.098 |
atis | +2.094 |
oho | +1.650 |
olla | +1.641 |
ande | +1.610 |
Neg logit contributions | |
RANT | -1.883 |
Claud | -1.849 |
handles | -1.772 |
fter | -1.730 |
cler | -1.679 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
RAW | +6.510 |
atis | +6.487 |
olla | +5.110 |
oho | +5.104 |
edes | +5.029 |
Neg logit contributions | |
RANT | -5.558 |
Claud | -5.299 |
fter | -5.085 |
handles | -4.984 |
anski | -4.870 |
Token | which |
Token ID | 543 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
RAW | +3.294 |
atis | +3.288 |
oho | +2.652 |
olla | +2.651 |
ande | +2.602 |
Neg logit contributions | |
RANT | -2.330 |
Claud | -2.284 |
handles | -2.175 |
fter | -2.122 |
cler | -2.043 |
Token | is |
Token ID | 318 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
RAW | +2.880 |
atis | +2.875 |
olla | +2.305 |
oho | +2.302 |
edes | +2.264 |
Neg logit contributions | |
RANT | -2.132 |
Claud | -2.088 |
handles | -1.984 |
fter | -1.942 |
cler | -1.878 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
RAW | +0.267 |
atis | +0.267 |
oho | +0.213 |
olla | +0.212 |
ande | +0.208 |
Neg logit contributions | |
RANT | -0.214 |
Claud | -0.211 |
handles | -0.203 |
fter | -0.197 |
cler | -0.191 |
Token | airline |
Token ID | 18091 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
RAW | +2.139 |
atis | +2.136 |
oho | +1.715 |
olla | +1.709 |
ande | +1.681 |
Neg logit contributions | |
RANT | -1.625 |
Claud | -1.602 |
handles | -1.529 |
fter | -1.491 |
cler | -1.441 |
Token | takes |
Token ID | 2753 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
RAW | +2.454 |
atis | +2.451 |
olla | +1.941 |
oho | +1.939 |
ande | +1.930 |
Neg logit contributions | |
RANT | -1.980 |
Claud | -1.925 |
handles | -1.838 |
fter | -1.809 |
cler | -1.758 |
Token | steps |
Token ID | 4831 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
atis | +3.747 |
RAW | +3.734 |
olla | +3.018 |
edes | +2.995 |
oho | +2.918 |
Neg logit contributions | |
RANT | -3.217 |
Claud | -3.140 |
fter | -3.055 |
swick | -3.019 |
handles | -3.017 |
Token | to |
Token ID | 284 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
atis | +3.381 |
RAW | +3.380 |
edes | +2.716 |
imir | +2.588 |
olla | +2.574 |
Neg logit contributions | |
RANT | -3.154 |
Claud | -3.109 |
handles | -2.970 |
swick | -2.913 |
fter | -2.864 |
Token | open |
Token ID | 1280 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
RAW | +3.716 |
atis | +3.603 |
oho | +2.863 |
olla | +2.800 |
ande | +2.793 |
Neg logit contributions | |
RANT | -3.605 |
Claud | -3.593 |
fter | -3.459 |
handles | -3.328 |
ocry | -3.317 |
Token | flights |
Token ID | 13956 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
RAW | +7.140 |
atis | +7.037 |
olla | +5.841 |
oho | +5.550 |
edes | +5.532 |
Neg logit contributions | |
RANT | -5.794 |
Claud | -5.595 |
handles | -5.353 |
fter | -5.348 |
swick | -5.272 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
atis | +3.051 |
RAW | +3.016 |
olla | +2.387 |
edes | +2.359 |
oho | +2.333 |
Neg logit contributions | |
RANT | -2.637 |
Claud | -2.561 |
handles | -2.480 |
fter | -2.461 |
cler | -2.378 |
Token | US |
Token ID | 1294 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
RAW | +1.717 |
atis | +1.706 |
edes | +1.368 |
olla | +1.358 |
oho | +1.343 |
Neg logit contributions | |
Claud | -1.333 |
RANT | -1.327 |
fter | -1.264 |
handles | -1.242 |
cler | -1.188 |
Token | on |
Token ID | 319 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
RAW | +4.242 |
atis | +4.226 |
olla | +3.545 |
oho | +3.543 |
>[ | +3.429 |
Neg logit contributions | |
RANT | -2.795 |
Claud | -2.784 |
handles | -2.640 |
fter | -2.589 |
cler | -2.501 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
atis | +0.232 |
RAW | +0.231 |
oho | +0.188 |
olla | +0.184 |
ande | +0.182 |
Neg logit contributions | |
RANT | -0.164 |
Claud | -0.162 |
handles | -0.157 |
fter | -0.150 |
cler | -0.147 |