Token | Bill |
Token ID | 3941 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
oji | +0.604 |
anus | +0.584 |
ュ | +0.565 |
cair | +0.555 |
azor | +0.536 |
Neg logit contributions | |
lihood | -0.574 |
amounts | -0.563 |
ness | -0.552 |
lin | -0.523 |
entimes | -0.523 |
Token | proposes |
Token ID | 26017 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
lihood | +0.996 |
amounts | +0.974 |
ness | +0.952 |
lin | +0.896 |
entimes | +0.896 |
Neg logit contributions | |
oji | -1.310 |
anus | -1.270 |
ュ | -1.232 |
cair | -1.215 |
azor | -1.177 |
Token | offences |
Token ID | 20819 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
oji | +0.602 |
anus | +0.585 |
ュ | +0.568 |
cair | +0.559 |
azor | +0.543 |
Neg logit contributions | |
lihood | -0.428 |
amounts | -0.419 |
ness | -0.409 |
entimes | -0.384 |
lin | -0.383 |
Token | committed |
Token ID | 5364 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
lihood | +1.830 |
amounts | +1.818 |
ness | +1.753 |
lin | +1.649 |
entimes | +1.616 |
Neg logit contributions | |
oji | -2.693 |
anus | -2.634 |
ュ | -2.558 |
cair | -2.513 |
azor | -2.438 |
Token | by |
Token ID | 416 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
oji | +0.825 |
anus | +0.794 |
ュ | +0.776 |
cair | +0.765 |
uitous | +0.744 |
Neg logit contributions | |
lihood | -0.499 |
amounts | -0.480 |
ness | -0.471 |
entimes | -0.446 |
CENT | -0.440 |
Token | Juven |
Token ID | 48113 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
oji | +0.216 |
anus | +0.209 |
ュ | +0.203 |
cair | +0.199 |
azor | +0.193 |
Neg logit contributions | |
lihood | -0.178 |
amounts | -0.174 |
ness | -0.170 |
entimes | -0.163 |
lin | -0.161 |
Token | iles |
Token ID | 2915 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
lihood | +4.798 |
amounts | +4.754 |
ness | +4.622 |
dar | +4.379 |
incidentally | +4.224 |
Neg logit contributions | |
oji | -12.582 |
ュ | -12.535 |
anus | -12.352 |
cair | -12.115 |
Amazing | -11.825 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
amounts | +4.139 |
lihood | +4.101 |
ness | +3.973 |
lin | +3.706 |
incidentally | +3.635 |
Neg logit contributions | |
oji | -6.381 |
anus | -6.256 |
ュ | -6.083 |
cair | -5.927 |
hetics | -5.783 |
Token | The |
Token ID | 383 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
lihood | +1.322 |
amounts | +1.300 |
ness | +1.272 |
lin | +1.208 |
entimes | +1.205 |
Neg logit contributions | |
oji | -1.319 |
anus | -1.276 |
ュ | -1.233 |
cair | -1.211 |
azor | -1.169 |
Token | Guardian |
Token ID | 8283 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
oji | +0.793 |
anus | +0.764 |
ュ | +0.744 |
cair | +0.730 |
azor | +0.706 |
Neg logit contributions | |
lihood | -0.656 |
amounts | -0.635 |
ness | -0.629 |
entimes | -0.603 |
lin | -0.596 |
Token | / |
Token ID | 1220 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
lihood | +3.565 |
amounts | +3.560 |
ness | +3.486 |
lin | +3.246 |
entimes | +3.196 |
Neg logit contributions | |
oji | -4.625 |
anus | -4.517 |
ュ | -4.355 |
cair | -4.275 |
hetics | -4.132 |
Token | get |
Token ID | 651 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
lihood | +1.763 |
amounts | +1.732 |
ness | +1.688 |
lin | +1.579 |
entimes | +1.573 |
Neg logit contributions | |
oji | -2.619 |
anus | -2.548 |
ュ | -2.478 |
cair | -2.441 |
azor | -2.370 |
Token | our |
Token ID | 674 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
amounts | +3.248 |
lihood | +3.122 |
ness | +3.086 |
lin | +2.909 |
CENT | +2.811 |
Neg logit contributions | |
oji | -5.283 |
anus | -4.993 |
ュ | -4.809 |
cair | -4.780 |
uitous | -4.615 |
Token | Daily |
Token ID | 6714 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
amounts | +2.519 |
ness | +2.498 |
lihood | +2.418 |
lin | +2.345 |
entimes | +2.299 |
Neg logit contributions | |
oji | -3.098 |
anus | -3.057 |
ュ | -2.965 |
cair | -2.897 |
hesis | -2.791 |
Token | Dispatch |
Token ID | 35934 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ness | +3.311 |
amounts | +3.304 |
lihood | +3.205 |
lin | +2.925 |
entimes | +2.916 |
Neg logit contributions | |
oji | -5.769 |
anus | -5.523 |
ュ | -5.363 |
cair | -5.290 |
uitous | -5.128 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ness | +3.780 |
amounts | +3.723 |
lihood | +3.714 |
entimes | +3.382 |
lin | +3.380 |
Neg logit contributions | |
oji | -5.712 |
anus | -5.546 |
ュ | -5.408 |
cair | -5.353 |
ammy | -5.176 |
Token | Editor |
Token ID | 12058 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ness | +2.428 |
amounts | +2.420 |
lihood | +2.378 |
lin | +2.210 |
entimes | +2.193 |
Neg logit contributions | |
oji | -3.316 |
anus | -3.219 |
ュ | -3.143 |
cair | -3.052 |
uitous | -2.958 |
Token | 's |
Token ID | 338 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
amounts | +5.447 |
ness | +5.395 |
lihood | +4.998 |
lin | +4.825 |
LY | +4.653 |
Neg logit contributions | |
oji | -11.744 |
anus | -11.365 |
ュ | -11.061 |
cair | -10.747 |
uitous | -10.709 |
Token | Picks |
Token ID | 33957 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
lihood | +0.854 |
amounts | +0.835 |
ness | +0.814 |
entimes | +0.790 |
lin | +0.781 |
Neg logit contributions | |
oji | -0.559 |
anus | -0.531 |
ュ | -0.519 |
cair | -0.503 |
azor | -0.488 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
lihood | +2.739 |
ness | +2.704 |
amounts | +2.696 |
entimes | +2.445 |
lin | +2.438 |
Neg logit contributions | |
oji | -4.619 |
anus | -4.469 |
ュ | -4.373 |
cair | -4.278 |
uitous | -4.145 |
Token |
|
Token ID | 198 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
lihood | +0.866 |
amounts | +0.860 |
ness | +0.850 |
lin | +0.784 |
CENT | +0.782 |
Neg logit contributions | |
oji | -1.267 |
anus | -1.236 |
ュ | -1.198 |
cair | -1.167 |
uitous | -1.136 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
lihood | +0.640 |
amounts | +0.626 |
entimes | +0.602 |
ness | +0.600 |
lin | +0.588 |
Neg logit contributions | |
oji | -0.580 |
anus | -0.556 |
ュ | -0.543 |
cair | -0.525 |
azor | -0.510 |
Token | get |
Token ID | 651 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
lihood | +1.794 |
amounts | +1.762 |
ness | +1.717 |
lin | +1.606 |
entimes | +1.600 |
Neg logit contributions | |
oji | -2.661 |
anus | -2.589 |
ュ | -2.517 |
cair | -2.480 |
azor | -2.407 |
Token | our |
Token ID | 674 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
amounts | +3.156 |
lihood | +3.023 |
ness | +2.973 |
lin | +2.831 |
entitle | +2.712 |
Neg logit contributions | |
oji | -5.285 |
anus | -4.982 |
cair | -4.778 |
ュ | -4.771 |
isine | -4.622 |
Token | Daily |
Token ID | 6714 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
amounts | +2.380 |
ness | +2.360 |
lihood | +2.277 |
lin | +2.220 |
entimes | +2.160 |
Neg logit contributions | |
oji | -2.925 |
anus | -2.882 |
ュ | -2.776 |
cair | -2.741 |
hesis | -2.624 |
Token | Dispatch |
Token ID | 35934 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ness | +3.170 |
amounts | +3.159 |
lihood | +3.081 |
lin | +2.799 |
CENT | +2.798 |
Neg logit contributions | |
oji | -5.486 |
anus | -5.254 |
ュ | -5.097 |
cair | -5.032 |
uitous | -4.879 |
Token | and |
Token ID | 290 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
ness | +3.389 |
lihood | +3.366 |
amounts | +3.360 |
lin | +3.053 |
entimes | +3.049 |
Neg logit contributions | |
oji | -5.017 |
anus | -4.871 |
ュ | -4.755 |
cair | -4.701 |
ammy | -4.525 |
Token | Editor |
Token ID | 12058 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
amounts | +2.291 |
ness | +2.283 |
lihood | +2.277 |
lin | +2.098 |
entimes | +2.082 |
Neg logit contributions | |
oji | -2.974 |
anus | -2.880 |
ュ | -2.806 |
cair | -2.732 |
uitous | -2.642 |
Token | 's |
Token ID | 338 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
amounts | +5.304 |
ness | +5.293 |
lihood | +4.944 |
lin | +4.722 |
LY | +4.572 |
Neg logit contributions | |
oji | -11.224 |
anus | -10.884 |
ュ | -10.538 |
cair | -10.295 |
uitous | -10.236 |
Token | Picks |
Token ID | 33957 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
lihood | +0.629 |
amounts | +0.616 |
ness | +0.600 |
entimes | +0.583 |
lin | +0.576 |
Neg logit contributions | |
oji | -0.412 |
anus | -0.392 |
ュ | -0.383 |
cair | -0.371 |
azor | -0.360 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
lihood | +2.617 |
amounts | +2.566 |
ness | +2.565 |
entimes | +2.325 |
lin | +2.323 |
Neg logit contributions | |
oji | -4.328 |
anus | -4.189 |
ュ | -4.093 |
cair | -4.009 |
uitous | -3.893 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
lihood | +0.699 |
amounts | +0.695 |
ness | +0.689 |
CENT | +0.634 |
lin | +0.633 |
Neg logit contributions | |
oji | -1.049 |
anus | -1.022 |
ュ | -0.986 |
cair | -0.963 |
uitous | -0.940 |
Token |
|
Token ID | 198 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
lihood | +0.574 |
amounts | +0.561 |
entimes | +0.541 |
ness | +0.537 |
lin | +0.526 |
Neg logit contributions | |
oji | -0.514 |
anus | -0.491 |
ュ | -0.482 |
cair | -0.464 |
azor | -0.451 |
Token | will |
Token ID | 481 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
amounts | +2.485 |
lihood | +2.465 |
ness | +2.397 |
lin | +2.191 |
entimes | +2.158 |
Neg logit contributions | |
oji | -5.055 |
anus | -4.937 |
ュ | -4.868 |
cair | -4.762 |
azor | -4.623 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
amounts | +3.267 |
ness | +3.206 |
lihood | +3.196 |
lin | +2.875 |
LY | +2.788 |
Neg logit contributions | |
oji | -7.179 |
anus | -7.102 |
ュ | -6.897 |
cair | -6.850 |
azor | -6.603 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
amounts | +5.227 |
ness | +4.983 |
lihood | +4.905 |
lin | +4.803 |
LY | +4.639 |
Neg logit contributions | |
oji | -5.074 |
anus | -5.013 |
ュ | -4.822 |
cair | -4.650 |
itect | -4.425 |
Token | containing |
Token ID | 7268 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
amounts | +3.430 |
ness | +3.125 |
lihood | +2.998 |
lin | +2.920 |
entitle | +2.791 |
Neg logit contributions | |
oji | -9.361 |
anus | -9.320 |
ュ | -8.950 |
cair | -8.896 |
azor | -8.689 |
Token | news |
Token ID | 1705 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
amounts | +5.434 |
ness | +5.229 |
lihood | +4.937 |
lin | +4.746 |
LY | +4.595 |
Neg logit contributions | |
anus | -8.895 |
oji | -8.872 |
ュ | -8.485 |
cair | -8.340 |
hetics | -8.107 |
Token | content |
Token ID | 2695 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
amounts | +2.942 |
ness | +2.751 |
lihood | +2.585 |
lin | +2.235 |
LY | +2.112 |
Neg logit contributions | |
oji | -10.660 |
anus | -10.552 |
ュ | -10.298 |
cair | -10.099 |
azor | -9.829 |
Token | , |
Token ID | 837 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
amounts | +6.219 |
lihood | +6.047 |
ness | +6.022 |
LY | +5.456 |
entimes | +5.414 |
Neg logit contributions | |
oji | -9.625 |
anus | -9.324 |
ュ | -9.090 |
cair | -8.745 |
azor | -8.528 |
Token | updates |
Token ID | 5992 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
amounts | +1.959 |
lihood | +1.928 |
ness | +1.848 |
lin | +1.670 |
entimes | +1.630 |
Neg logit contributions | |
oji | -5.355 |
anus | -5.271 |
ュ | -5.131 |
cair | -5.052 |
azor | -4.952 |
Token | and |
Token ID | 290 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
amounts | +4.041 |
ness | +4.016 |
lihood | +3.877 |
lin | +3.622 |
dar | +3.572 |
Neg logit contributions | |
oji | -6.467 |
anus | -6.342 |
ュ | -6.152 |
cair | -6.042 |
azor | -5.879 |
Token | promotions |
Token ID | 20699 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
amounts | +7.435 |
ness | +7.097 |
lihood | +7.012 |
overfl | +6.642 |
lin | +6.630 |
Neg logit contributions | |
oji | -6.062 |
anus | -5.884 |
ュ | -5.699 |
cair | -5.622 |
azor | -5.388 |
Token | from |
Token ID | 422 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
lihood | +2.319 |
amounts | +2.318 |
ness | +2.228 |
lin | +2.013 |
entimes | +1.971 |
Neg logit contributions | |
oji | -5.759 |
anus | -5.655 |
ュ | -5.513 |
cair | -5.422 |
azor | -5.303 |
Token | will |
Token ID | 481 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
amounts | +2.647 |
lihood | +2.598 |
ness | +2.547 |
lin | +2.320 |
entimes | +2.276 |
Neg logit contributions | |
oji | -5.519 |
anus | -5.396 |
ュ | -5.341 |
cair | -5.207 |
azor | -5.058 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
amounts | +3.314 |
ness | +3.249 |
lihood | +3.245 |
lin | +2.909 |
LY | +2.828 |
Neg logit contributions | |
oji | -7.337 |
anus | -7.269 |
ュ | -7.052 |
cair | -6.996 |
azor | -6.753 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
amounts | +5.253 |
ness | +4.984 |
lihood | +4.909 |
lin | +4.806 |
LY | +4.645 |
Neg logit contributions | |
oji | -5.135 |
anus | -5.102 |
ュ | -4.892 |
cair | -4.706 |
itect | -4.502 |
Token | containing |
Token ID | 7268 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
amounts | +3.443 |
ness | +3.135 |
lihood | +3.047 |
lin | +2.921 |
entitle | +2.794 |
Neg logit contributions | |
oji | -9.248 |
anus | -9.229 |
ュ | -8.855 |
cair | -8.781 |
azor | -8.587 |
Token | news |
Token ID | 1705 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
amounts | +5.423 |
ness | +5.213 |
lihood | +4.985 |
lin | +4.730 |
LY | +4.603 |
Neg logit contributions | |
anus | -8.735 |
oji | -8.708 |
ュ | -8.336 |
cair | -8.154 |
hetics | -7.959 |
Token | content |
Token ID | 2695 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
amounts | +2.917 |
ness | +2.715 |
lihood | +2.588 |
lin | +2.222 |
LY | +2.101 |
Neg logit contributions | |
oji | -10.391 |
anus | -10.296 |
ュ | -10.050 |
cair | -9.843 |
azor | -9.599 |
Token | , |
Token ID | 837 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
amounts | +6.140 |
lihood | +5.980 |
ness | +5.946 |
LY | +5.393 |
entimes | +5.355 |
Neg logit contributions | |
oji | -9.602 |
anus | -9.301 |
ュ | -9.072 |
cair | -8.693 |
azor | -8.521 |
Token | updates |
Token ID | 5992 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
amounts | +1.927 |
lihood | +1.912 |
ness | +1.822 |
lin | +1.650 |
entimes | +1.614 |
Neg logit contributions | |
oji | -5.198 |
anus | -5.109 |
ュ | -4.980 |
cair | -4.901 |
azor | -4.805 |
Token | and |
Token ID | 290 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
amounts | +3.957 |
ness | +3.932 |
lihood | +3.815 |
lin | +3.552 |
dar | +3.516 |
Neg logit contributions | |
oji | -6.281 |
anus | -6.159 |
ュ | -5.980 |
cair | -5.853 |
azor | -5.708 |
Token | promotions |
Token ID | 20699 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
amounts | +7.392 |
ness | +7.065 |
lihood | +7.010 |
lin | +6.606 |
overfl | +6.604 |
Neg logit contributions | |
oji | -5.933 |
anus | -5.785 |
ュ | -5.589 |
cair | -5.479 |
azor | -5.273 |
Token | from |
Token ID | 422 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
amounts | +2.462 |
lihood | +2.447 |
ness | +2.360 |
lin | +2.123 |
entimes | +2.076 |
Neg logit contributions | |
oji | -6.234 |
anus | -6.137 |
ュ | -5.978 |
cair | -5.869 |
azor | -5.752 |
Token | management |
Token ID | 4542 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
lihood | +2.234 |
amounts | +2.201 |
ness | +2.145 |
lin | +2.017 |
entimes | +2.005 |
Neg logit contributions | |
oji | -3.038 |
anus | -2.954 |
ュ | -2.866 |
cair | -2.824 |
azor | -2.734 |
Token | correctly |
Token ID | 9380 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
lihood | +0.602 |
amounts | +0.584 |
ness | +0.569 |
entimes | +0.541 |
CENT | +0.537 |
Neg logit contributions | |
oji | -0.811 |
anus | -0.786 |
ュ | -0.763 |
cair | -0.751 |
azor | -0.733 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
oji | +0.995 |
anus | +0.961 |
ュ | +0.937 |
cair | +0.914 |
azor | +0.897 |
Neg logit contributions | |
lihood | -0.743 |
amounts | -0.719 |
ness | -0.696 |
CENT | -0.667 |
entimes | -0.661 |
Token |
|
Token ID | 198 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
lihood | +0.658 |
amounts | +0.647 |
ness | +0.633 |
lin | +0.600 |
entimes | +0.600 |
Neg logit contributions | |
oji | -0.679 |
anus | -0.657 |
ュ | -0.635 |
cair | -0.624 |
azor | -0.603 |
Token |
|
Token ID | 198 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
lihood | +1.521 |
amounts | +1.487 |
ness | +1.437 |
entimes | +1.404 |
lin | +1.385 |
Neg logit contributions | |
oji | -1.482 |
anus | -1.427 |
ュ | -1.382 |
cair | -1.352 |
azor | -1.311 |
Token | Guard |
Token ID | 24502 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
lihood | +0.821 |
amounts | +0.808 |
ness | +0.793 |
lin | +0.753 |
entimes | +0.751 |
Neg logit contributions | |
oji | -0.748 |
anus | -0.722 |
ュ | -0.697 |
cair | -0.684 |
azor | -0.658 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
amounts | +7.012 |
ness | +6.966 |
lihood | +6.722 |
lin | +6.543 |
dar | +6.348 |
Neg logit contributions | |
oji | -7.712 |
anus | -7.460 |
ュ | -7.398 |
cair | -7.270 |
hetics | -6.827 |
Token |
|
Token ID | 198 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
lihood | +3.180 |
amounts | +3.146 |
ness | +3.114 |
lin | +2.901 |
CENT | +2.868 |
Neg logit contributions | |
oji | -3.703 |
anus | -3.604 |
ュ | -3.485 |
cair | -3.437 |
azor | -3.307 |
Token | To |
Token ID | 2514 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
lihood | +2.470 |
ness | +2.423 |
amounts | +2.411 |
CENT | +2.277 |
lin | +2.269 |
Neg logit contributions | |
oji | -2.328 |
anus | -2.238 |
ュ | -2.195 |
cair | -2.144 |
hetics | -2.045 |
Token | operate |
Token ID | 8076 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
oji | +0.255 |
anus | +0.246 |
ュ | +0.239 |
cair | +0.236 |
azor | +0.229 |
Neg logit contributions | |
lihood | -0.179 |
amounts | -0.174 |
ness | -0.168 |
entimes | -0.160 |
CENT | -0.158 |
Token | on |
Token ID | 319 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
lihood | +0.376 |
amounts | +0.366 |
ness | +0.356 |
entimes | +0.337 |
CENT | +0.333 |
Neg logit contributions | |
oji | -0.479 |
anus | -0.464 |
ュ | -0.450 |
cair | -0.443 |
azor | -0.431 |
Token | will |
Token ID | 481 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
amounts | +2.542 |
lihood | +2.504 |
ness | +2.446 |
lin | +2.236 |
entimes | +2.197 |
Neg logit contributions | |
oji | -5.260 |
anus | -5.138 |
ュ | -5.081 |
cair | -4.959 |
azor | -4.821 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
amounts | +3.209 |
lihood | +3.151 |
ness | +3.129 |
lin | +2.820 |
LY | +2.734 |
Neg logit contributions | |
oji | -6.873 |
anus | -6.801 |
ュ | -6.602 |
cair | -6.533 |
azor | -6.319 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
amounts | +4.894 |
ness | +4.668 |
lihood | +4.631 |
lin | +4.497 |
LY | +4.340 |
Neg logit contributions | |
oji | -4.592 |
anus | -4.538 |
ュ | -4.379 |
cair | -4.197 |
azor | -4.011 |
Token | containing |
Token ID | 7268 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
amounts | +3.303 |
ness | +3.012 |
lihood | +2.916 |
lin | +2.801 |
entitle | +2.686 |
Neg logit contributions | |
oji | -8.714 |
anus | -8.680 |
ュ | -8.362 |
cair | -8.274 |
azor | -8.101 |
Token | news |
Token ID | 1705 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
amounts | +5.204 |
ness | +5.004 |
lihood | +4.780 |
lin | +4.547 |
LY | +4.424 |
Neg logit contributions | |
anus | -8.223 |
oji | -8.221 |
ュ | -7.883 |
cair | -7.706 |
hetics | -7.527 |
Token | content |
Token ID | 2695 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
amounts | +2.822 |
ness | +2.631 |
lihood | +2.527 |
lin | +2.159 |
entimes | +2.063 |
Neg logit contributions | |
oji | -9.932 |
anus | -9.823 |
ュ | -9.600 |
cair | -9.401 |
azor | -9.171 |
Token | , |
Token ID | 837 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
amounts | +5.989 |
lihood | +5.843 |
ness | +5.799 |
LY | +5.276 |
entimes | +5.263 |
Neg logit contributions | |
oji | -8.939 |
anus | -8.676 |
ュ | -8.489 |
cair | -8.120 |
azor | -7.955 |
Token | updates |
Token ID | 5992 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
amounts | +1.769 |
lihood | +1.758 |
ness | +1.674 |
lin | +1.517 |
entimes | +1.488 |
Neg logit contributions | |
oji | -4.729 |
anus | -4.644 |
ュ | -4.531 |
cair | -4.458 |
azor | -4.371 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
amounts | +3.771 |
ness | +3.746 |
lihood | +3.632 |
lin | +3.382 |
dar | +3.341 |
Neg logit contributions | |
oji | -5.929 |
anus | -5.804 |
ュ | -5.645 |
cair | -5.526 |
azor | -5.395 |
Token | promotions |
Token ID | 20699 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
amounts | +7.031 |
ness | +6.738 |
lihood | +6.675 |
lin | +6.319 |
overfl | +6.261 |
Neg logit contributions | |
oji | -5.539 |
anus | -5.391 |
ュ | -5.224 |
cair | -5.113 |
azor | -4.922 |
Token | from |
Token ID | 422 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
lihood | +2.198 |
amounts | +2.173 |
ness | +2.091 |
lin | +1.898 |
entimes | +1.875 |
Neg logit contributions | |
oji | -5.241 |
anus | -5.135 |
ュ | -5.011 |
cair | -4.934 |
azor | -4.822 |
Token | . |
Token ID | 13 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
oji | +2.653 |
anus | +2.598 |
ュ | +2.458 |
cair | +2.444 |
azor | +2.378 |
Neg logit contributions | |
lihood | -2.093 |
amounts | -1.994 |
ness | -1.950 |
entimes | -1.871 |
CENT | -1.857 |
Token |
|
Token ID | 198 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
lihood | +1.112 |
amounts | +1.094 |
ness | +1.071 |
lin | +1.015 |
entimes | +1.010 |
Neg logit contributions | |
oji | -1.128 |
anus | -1.091 |
ュ | -1.053 |
cair | -1.036 |
azor | -0.999 |
Token |
|
Token ID | 198 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
lihood | +1.353 |
amounts | +1.323 |
ness | +1.274 |
entimes | +1.251 |
lin | +1.235 |
Neg logit contributions | |
oji | -1.296 |
anus | -1.251 |
ュ | -1.214 |
cair | -1.183 |
azor | -1.149 |
Token | The |
Token ID | 464 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
lihood | +1.123 |
amounts | +1.102 |
ness | +1.088 |
CENT | +1.025 |
lin | +1.024 |
Neg logit contributions | |
oji | -1.105 |
anus | -1.066 |
ュ | -1.030 |
cair | -1.013 |
azor | -0.975 |
Token | City |
Token ID | 2254 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
lihood | +0.589 |
amounts | +0.577 |
ness | +0.565 |
lin | +0.534 |
entimes | +0.534 |
Neg logit contributions | |
oji | -0.667 |
anus | -0.646 |
ュ | -0.626 |
cair | -0.615 |
azor | -0.595 |
Token | Ord |
Token ID | 14230 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
lihood | +0.443 |
amounts | +0.436 |
ness | +0.427 |
lin | +0.404 |
entimes | +0.403 |
Neg logit contributions | |
oji | -0.462 |
anus | -0.447 |
ュ | -0.432 |
cair | -0.424 |
azor | -0.410 |
Token | inance |
Token ID | 14149 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ness | +4.726 |
amounts | +4.582 |
lihood | +4.529 |
lin | +4.031 |
inarily | +4.028 |
Neg logit contributions | |
ュ | -9.295 |
anus | -9.052 |
oji | -9.050 |
cair | -8.880 |
Amazing | -8.538 |
Token |
|
Token ID | 198 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
amounts | +3.079 |
lihood | +3.059 |
ness | +2.959 |
lin | +2.757 |
entimes | +2.716 |
Neg logit contributions | |
oji | -4.173 |
anus | -4.072 |
ュ | -3.971 |
cair | -3.889 |
azor | -3.765 |
Token |
|
Token ID | 198 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
lihood | +1.493 |
amounts | +1.459 |
ness | +1.409 |
entimes | +1.383 |
lin | +1.362 |
Neg logit contributions | |
oji | -1.428 |
anus | -1.373 |
ュ | -1.333 |
cair | -1.302 |
azor | -1.262 |
Token | According |
Token ID | 4821 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
lihood | +0.733 |
amounts | +0.722 |
ness | +0.706 |
lin | +0.672 |
entimes | +0.671 |
Neg logit contributions | |
oji | -0.701 |
anus | -0.678 |
ュ | -0.654 |
cair | -0.643 |
azor | -0.619 |
Token | to |
Token ID | 284 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
lihood | +1.016 |
amounts | +0.970 |
ness | +0.939 |
entimes | +0.904 |
lin | +0.889 |
Neg logit contributions | |
oji | -1.685 |
anus | -1.625 |
ュ | -1.586 |
cair | -1.569 |
azor | -1.526 |
Token | even |
Token ID | 772 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
lihood | +0.710 |
amounts | +0.695 |
ness | +0.678 |
entimes | +0.639 |
lin | +0.638 |
Neg logit contributions | |
oji | -0.905 |
anus | -0.878 |
ュ | -0.852 |
cair | -0.838 |
azor | -0.812 |
Token | though |
Token ID | 996 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
lihood | +1.858 |
amounts | +1.827 |
ness | +1.790 |
lin | +1.614 |
entimes | +1.593 |
Neg logit contributions | |
oji | -4.189 |
anus | -4.129 |
ュ | -4.014 |
cair | -3.985 |
azor | -3.862 |
Token | he |
Token ID | 339 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
oji | +1.287 |
anus | +1.258 |
ュ | +1.212 |
cair | +1.197 |
azor | +1.158 |
Neg logit contributions | |
lihood | -1.047 |
amounts | -1.014 |
ness | -0.999 |
entimes | -0.952 |
lin | -0.944 |
Token | 's |
Token ID | 338 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
oji | +1.184 |
anus | +1.155 |
ュ | +1.119 |
cair | +1.097 |
azor | +1.069 |
Neg logit contributions | |
lihood | -0.841 |
amounts | -0.806 |
ness | -0.788 |
CENT | -0.757 |
entimes | -0.752 |
Token | a |
Token ID | 257 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
lihood | +0.400 |
amounts | +0.389 |
ness | +0.380 |
entimes | +0.363 |
CENT | +0.359 |
Neg logit contributions | |
oji | -0.474 |
anus | -0.461 |
ュ | -0.445 |
cair | -0.436 |
azor | -0.425 |
Token | juvenile |
Token ID | 21904 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
oji | +0.865 |
anus | +0.841 |
ュ | +0.813 |
cair | +0.793 |
azor | +0.766 |
Neg logit contributions | |
lihood | -0.791 |
amounts | -0.771 |
ness | -0.748 |
entimes | -0.722 |
CENT | -0.714 |
Token | because |
Token ID | 780 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
amounts | +5.247 |
ness | +4.963 |
lihood | +4.733 |
lin | +4.636 |
incidentally | +4.632 |
Neg logit contributions | |
oji | -9.151 |
anus | -8.841 |
ュ | -8.688 |
cair | -8.480 |
azor | -8.184 |
Token | " |
Token ID | 366 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
oji | +0.722 |
anus | +0.704 |
ュ | +0.680 |
cair | +0.673 |
azor | +0.650 |
Neg logit contributions | |
lihood | -0.588 |
amounts | -0.573 |
ness | -0.562 |
entimes | -0.533 |
lin | -0.530 |
Token | he |
Token ID | 258 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
oji | +1.355 |
anus | +1.330 |
cair | +1.266 |
ュ | +1.265 |
azor | +1.200 |
Neg logit contributions | |
lihood | -1.348 |
amounts | -1.316 |
ness | -1.265 |
lin | -1.230 |
entimes | -1.225 |
Token | represents |
Token ID | 6870 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
oji | +2.033 |
anus | +1.952 |
ュ | +1.895 |
cair | +1.865 |
azor | +1.817 |
Neg logit contributions | |
lihood | -1.538 |
amounts | -1.450 |
ness | -1.433 |
CENT | -1.400 |
entimes | -1.358 |
Token | ... |
Token ID | 2644 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
oji | +1.762 |
anus | +1.714 |
ュ | +1.662 |
cair | +1.638 |
azor | +1.587 |
Neg logit contributions | |
lihood | -1.828 |
amounts | -1.765 |
ness | -1.742 |
entimes | -1.689 |
CENT | -1.682 |
Token | of |
Token ID | 286 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
lihood | +0.078 |
amounts | +0.076 |
ness | +0.075 |
entimes | +0.071 |
lin | +0.071 |
Neg logit contributions | |
oji | -0.078 |
anus | -0.076 |
ュ | -0.074 |
cair | -0.072 |
azor | -0.070 |
Token | concepts |
Token ID | 10838 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
oji | +0.874 |
anus | +0.846 |
ュ | +0.819 |
cair | +0.803 |
azor | +0.776 |
Neg logit contributions | |
lihood | -0.853 |
amounts | -0.834 |
ness | -0.818 |
entimes | -0.779 |
lin | -0.774 |
Token | that |
Token ID | 326 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
oji | +0.058 |
anus | +0.056 |
ュ | +0.054 |
cair | +0.053 |
azor | +0.052 |
Neg logit contributions | |
lihood | -0.046 |
amounts | -0.044 |
ness | -0.044 |
entimes | -0.041 |
CENT | -0.041 |
Token | accept |
Token ID | 2453 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
lihood | +1.947 |
amounts | +1.913 |
ness | +1.856 |
lin | +1.730 |
entimes | +1.717 |
Neg logit contributions | |
oji | -3.239 |
anus | -3.161 |
ュ | -3.076 |
cair | -3.031 |
azor | -2.947 |
Token | Bitcoin |
Token ID | 6185 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
amounts | +2.999 |
lihood | +2.964 |
ness | +2.904 |
lin | +2.728 |
entimes | +2.650 |
Neg logit contributions | |
oji | -3.748 |
anus | -3.663 |
ュ | -3.512 |
cair | -3.501 |
azor | -3.342 |
Token | micro |
Token ID | 4580 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
amounts | +2.870 |
ness | +2.774 |
lihood | +2.760 |
lin | +2.567 |
entimes | +2.483 |
Neg logit contributions | |
oji | -4.679 |
anus | -4.581 |
ュ | -4.444 |
cair | -4.377 |
azor | -4.243 |
Token | - |
Token ID | 12 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
amounts | +6.102 |
ness | +5.681 |
lihood | +5.584 |
lin | +5.446 |
dar | +5.138 |
Neg logit contributions | |
oji | -8.296 |
anus | -8.086 |
cair | -7.692 |
ュ | -7.673 |
uitous | -7.637 |
Token | trans |
Token ID | 7645 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
lihood | +1.271 |
amounts | +1.252 |
ness | +1.224 |
lin | +1.158 |
entimes | +1.154 |
Neg logit contributions | |
oji | -1.393 |
anus | -1.349 |
ュ | -1.306 |
cair | -1.284 |
azor | -1.241 |
Token | actions |
Token ID | 4658 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
oji | +0.272 |
anus | +0.262 |
ュ | +0.254 |
cair | +0.249 |
azor | +0.242 |
Neg logit contributions | |
lihood | -0.243 |
amounts | -0.237 |
ness | -0.231 |
entimes | -0.220 |
lin | -0.219 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
lihood | +0.657 |
amounts | +0.642 |
ness | +0.626 |
lin | +0.587 |
entimes | +0.586 |
Neg logit contributions | |
oji | -0.948 |
anus | -0.920 |
ュ | -0.895 |
cair | -0.881 |
azor | -0.856 |
Token | We |
Token ID | 775 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
lihood | +1.601 |
amounts | +1.575 |
ness | +1.541 |
lin | +1.464 |
entimes | +1.462 |
Neg logit contributions | |
oji | -1.581 |
anus | -1.527 |
ュ | -1.477 |
cair | -1.450 |
azor | -1.399 |
Token | child |
Token ID | 1200 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
oji | +0.254 |
anus | +0.248 |
ュ | +0.238 |
cair | +0.235 |
azor | +0.228 |
Neg logit contributions | |
lihood | -0.193 |
amounts | -0.188 |
ness | -0.184 |
entimes | -0.175 |
lin | -0.174 |
Token | welfare |
Token ID | 9490 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
lihood | +1.319 |
amounts | +1.294 |
ness | +1.262 |
lin | +1.184 |
entimes | +1.180 |
Neg logit contributions | |
oji | -1.823 |
anus | -1.771 |
ュ | -1.720 |
cair | -1.694 |
azor | -1.643 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
oji | +1.330 |
anus | +1.290 |
ュ | +1.261 |
cair | +1.247 |
azor | +1.204 |
Neg logit contributions | |
lihood | -0.718 |
amounts | -0.713 |
ness | -0.699 |
lin | -0.642 |
entimes | -0.636 |
Token | education |
Token ID | 3707 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
oji | +1.362 |
anus | +1.333 |
ュ | +1.281 |
cair | +1.261 |
azor | +1.226 |
Neg logit contributions | |
lihood | -1.075 |
amounts | -1.042 |
ness | -1.017 |
entimes | -0.978 |
CENT | -0.968 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
amounts | +0.349 |
lihood | +0.348 |
ness | +0.343 |
lin | +0.311 |
entimes | +0.308 |
Neg logit contributions | |
oji | -0.667 |
anus | -0.645 |
ュ | -0.629 |
cair | -0.623 |
azor | -0.601 |
Token | juvenile |
Token ID | 21904 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
oji | +1.210 |
anus | +1.180 |
ュ | +1.136 |
cair | +1.118 |
azor | +1.087 |
Neg logit contributions | |
lihood | -0.973 |
amounts | -0.947 |
ness | -0.922 |
entimes | -0.882 |
CENT | -0.877 |
Token | justice |
Token ID | 5316 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ness | +4.821 |
amounts | +4.776 |
lihood | +4.706 |
lin | +4.384 |
entitle | +4.255 |
Neg logit contributions | |
oji | -9.568 |
anus | -9.073 |
ュ | -9.048 |
cair | -8.999 |
Amazing | -8.584 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ness | +2.367 |
amounts | +2.348 |
lihood | +2.308 |
lin | +2.102 |
dar | +2.047 |
Neg logit contributions | |
oji | -4.965 |
anus | -4.744 |
ュ | -4.708 |
cair | -4.672 |
uitous | -4.472 |
Token | and |
Token ID | 290 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
oji | +1.214 |
anus | +1.188 |
ュ | +1.144 |
cair | +1.124 |
azor | +1.095 |
Neg logit contributions | |
lihood | -0.916 |
amounts | -0.887 |
ness | -0.865 |
entimes | -0.828 |
CENT | -0.819 |
Token | homelessness |
Token ID | 28822 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
lihood | +0.974 |
amounts | +0.955 |
ness | +0.932 |
lin | +0.878 |
entimes | +0.877 |
Neg logit contributions | |
oji | -1.235 |
anus | -1.199 |
ュ | -1.162 |
cair | -1.144 |
azor | -1.109 |
Token | ." |
Token ID | 526 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
lihood | +0.750 |
amounts | +0.738 |
ness | +0.720 |
lin | +0.673 |
entimes | +0.670 |
Neg logit contributions | |
oji | -1.118 |
anus | -1.085 |
ュ | -1.056 |
cair | -1.040 |
azor | -1.008 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
lihood | +2.912 |
amounts | +2.863 |
ness | +2.797 |
lin | +2.650 |
entimes | +2.644 |
Neg logit contributions | |
oji | -3.175 |
anus | -3.073 |
ュ | -2.976 |
cair | -2.926 |
azor | -2.827 |
Token | You |
Token ID | 921 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
lihood | +4.414 |
amounts | +4.403 |
ness | +4.338 |
CENT | +4.055 |
lin | +4.051 |
Neg logit contributions | |
oji | -4.415 |
anus | -4.268 |
ュ | -4.083 |
cair | -4.029 |
azor | -3.895 |
Token | will |
Token ID | 481 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
amounts | +2.485 |
lihood | +2.465 |
ness | +2.397 |
lin | +2.191 |
entimes | +2.158 |
Neg logit contributions | |
oji | -5.055 |
anus | -4.937 |
ュ | -4.868 |
cair | -4.762 |
azor | -4.623 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
amounts | +3.267 |
ness | +3.206 |
lihood | +3.196 |
lin | +2.875 |
LY | +2.788 |
Neg logit contributions | |
oji | -7.179 |
anus | -7.102 |
ュ | -6.897 |
cair | -6.850 |
azor | -6.603 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
amounts | +5.227 |
ness | +4.983 |
lihood | +4.905 |
lin | +4.803 |
LY | +4.639 |
Neg logit contributions | |
oji | -5.074 |
anus | -5.013 |
ュ | -4.822 |
cair | -4.650 |
itect | -4.425 |
Token | containing |
Token ID | 7268 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
amounts | +3.430 |
ness | +3.125 |
lihood | +2.998 |
lin | +2.920 |
entitle | +2.791 |
Neg logit contributions | |
oji | -9.361 |
anus | -9.320 |
ュ | -8.950 |
cair | -8.896 |
azor | -8.689 |
Token | news |
Token ID | 1705 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
amounts | +5.434 |
ness | +5.229 |
lihood | +4.937 |
lin | +4.746 |
LY | +4.595 |
Neg logit contributions | |
anus | -8.895 |
oji | -8.872 |
ュ | -8.485 |
cair | -8.340 |
hetics | -8.107 |
Token | content |
Token ID | 2695 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
amounts | +2.942 |
ness | +2.751 |
lihood | +2.585 |
lin | +2.235 |
LY | +2.112 |
Neg logit contributions | |
oji | -10.660 |
anus | -10.552 |
ュ | -10.298 |
cair | -10.099 |
azor | -9.829 |
Token | , |
Token ID | 837 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
amounts | +6.219 |
lihood | +6.047 |
ness | +6.022 |
LY | +5.456 |
entimes | +5.414 |
Neg logit contributions | |
oji | -9.625 |
anus | -9.324 |
ュ | -9.090 |
cair | -8.745 |
azor | -8.528 |
Token | updates |
Token ID | 5992 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
amounts | +1.959 |
lihood | +1.928 |
ness | +1.848 |
lin | +1.670 |
entimes | +1.630 |
Neg logit contributions | |
oji | -5.355 |
anus | -5.271 |
ュ | -5.131 |
cair | -5.052 |
azor | -4.952 |
Token | and |
Token ID | 290 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
amounts | +4.041 |
ness | +4.016 |
lihood | +3.877 |
lin | +3.622 |
dar | +3.572 |
Neg logit contributions | |
oji | -6.467 |
anus | -6.342 |
ュ | -6.152 |
cair | -6.042 |
azor | -5.879 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
lihood | +3.071 |
amounts | +3.020 |
ness | +2.956 |
lin | +2.790 |
entimes | +2.782 |
Neg logit contributions | |
oji | -3.410 |
anus | -3.309 |
ュ | -3.196 |
cair | -3.145 |
azor | -3.042 |
Token | You |
Token ID | 921 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
amounts | +4.732 |
lihood | +4.729 |
ness | +4.670 |
CENT | +4.358 |
lin | +4.337 |
Neg logit contributions | |
oji | -4.891 |
anus | -4.738 |
ュ | -4.519 |
cair | -4.470 |
azor | -4.329 |
Token | will |
Token ID | 481 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
amounts | +2.647 |
lihood | +2.598 |
ness | +2.547 |
lin | +2.320 |
entimes | +2.276 |
Neg logit contributions | |
oji | -5.519 |
anus | -5.396 |
ュ | -5.341 |
cair | -5.207 |
azor | -5.058 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
amounts | +3.314 |
ness | +3.249 |
lihood | +3.245 |
lin | +2.909 |
LY | +2.828 |
Neg logit contributions | |
oji | -7.337 |
anus | -7.269 |
ュ | -7.052 |
cair | -6.996 |
azor | -6.753 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
amounts | +5.253 |
ness | +4.984 |
lihood | +4.909 |
lin | +4.806 |
LY | +4.645 |
Neg logit contributions | |
oji | -5.135 |
anus | -5.102 |
ュ | -4.892 |
cair | -4.706 |
itect | -4.502 |
Token | containing |
Token ID | 7268 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
amounts | +3.443 |
ness | +3.135 |
lihood | +3.047 |
lin | +2.921 |
entitle | +2.794 |
Neg logit contributions | |
oji | -9.248 |
anus | -9.229 |
ュ | -8.855 |
cair | -8.781 |
azor | -8.587 |
Token | news |
Token ID | 1705 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
amounts | +5.423 |
ness | +5.213 |
lihood | +4.985 |
lin | +4.730 |
LY | +4.603 |
Neg logit contributions | |
anus | -8.735 |
oji | -8.708 |
ュ | -8.336 |
cair | -8.154 |
hetics | -7.959 |
Token | content |
Token ID | 2695 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
amounts | +2.917 |
ness | +2.715 |
lihood | +2.588 |
lin | +2.222 |
LY | +2.101 |
Neg logit contributions | |
oji | -10.391 |
anus | -10.296 |
ュ | -10.050 |
cair | -9.843 |
azor | -9.599 |
Token | , |
Token ID | 837 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
amounts | +6.140 |
lihood | +5.980 |
ness | +5.946 |
LY | +5.393 |
entimes | +5.355 |
Neg logit contributions | |
oji | -9.602 |
anus | -9.301 |
ュ | -9.072 |
cair | -8.693 |
azor | -8.521 |
Token | updates |
Token ID | 5992 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
amounts | +1.927 |
lihood | +1.912 |
ness | +1.822 |
lin | +1.650 |
entimes | +1.614 |
Neg logit contributions | |
oji | -5.198 |
anus | -5.109 |
ュ | -4.980 |
cair | -4.901 |
azor | -4.805 |
Token | and |
Token ID | 290 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
amounts | +3.957 |
ness | +3.932 |
lihood | +3.815 |
lin | +3.552 |
dar | +3.516 |
Neg logit contributions | |
oji | -6.281 |
anus | -6.159 |
ュ | -5.980 |
cair | -5.853 |
azor | -5.708 |
Token | -- |
Token ID | 1377 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
amounts | +1.392 |
lihood | +1.391 |
ness | +1.352 |
CENT | +1.248 |
lin | +1.239 |
Neg logit contributions | |
oji | -2.594 |
anus | -2.529 |
ュ | -2.456 |
cair | -2.444 |
azor | -2.362 |
Token | Boston |
Token ID | 6182 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
lihood | +0.219 |
amounts | +0.216 |
ness | +0.211 |
lin | +0.201 |
entimes | +0.201 |
Neg logit contributions | |
oji | -0.204 |
anus | -0.197 |
ュ | -0.190 |
cair | -0.186 |
azor | -0.180 |
Token | Celtics |
Token ID | 24116 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
oji | +0.360 |
anus | +0.348 |
ュ | +0.336 |
cair | +0.330 |
azor | +0.318 |
Neg logit contributions | |
lihood | -0.378 |
amounts | -0.372 |
ness | -0.364 |
lin | -0.346 |
entimes | -0.346 |
Token | swing |
Token ID | 9628 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
lihood | +2.289 |
amounts | +2.274 |
ness | +2.270 |
lin | +2.130 |
CENT | +2.059 |
Neg logit contributions | |
oji | -2.739 |
anus | -2.672 |
ュ | -2.601 |
cair | -2.562 |
azor | -2.473 |
Token | man |
Token ID | 805 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
oji | +0.470 |
anus | +0.449 |
ュ | +0.427 |
cair | +0.422 |
azor | +0.405 |
Neg logit contributions | |
lihood | -0.720 |
amounts | -0.704 |
ness | -0.688 |
entimes | -0.666 |
CENT | -0.657 |
Token | Jae |
Token ID | 34521 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ness | +3.353 |
lihood | +3.352 |
amounts | +3.345 |
lin | +3.153 |
dar | +3.051 |
Neg logit contributions | |
anus | -3.953 |
oji | -3.946 |
ュ | -3.826 |
cair | -3.790 |
uitous | -3.607 |
Token | Crow |
Token ID | 15502 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ness | +4.863 |
amounts | +4.857 |
lin | +4.529 |
lihood | +4.360 |
dar | +4.177 |
Neg logit contributions | |
oji | -8.724 |
anus | -8.678 |
ュ | -8.577 |
cair | -8.571 |
Haunted | -8.202 |
Token | der |
Token ID | 1082 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
lihood | +2.061 |
amounts | +2.024 |
ness | +1.989 |
entimes | +1.909 |
lin | +1.905 |
Neg logit contributions | |
oji | -1.352 |
anus | -1.298 |
ュ | -1.237 |
cair | -1.209 |
azor | -1.150 |
Token | , |
Token ID | 11 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
lihood | +1.079 |
amounts | +1.068 |
ness | +1.038 |
lin | +0.971 |
entimes | +0.961 |
Neg logit contributions | |
oji | -1.600 |
anus | -1.561 |
ュ | -1.517 |
cair | -1.495 |
azor | -1.450 |
Token | whose |
Token ID | 3025 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
lihood | +0.745 |
amounts | +0.730 |
ness | +0.714 |
entimes | +0.674 |
lin | +0.673 |
Neg logit contributions | |
oji | -0.885 |
anus | -0.859 |
ュ | -0.831 |
cair | -0.818 |
azor | -0.792 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
amounts | +3.345 |
lihood | +3.339 |
ness | +3.275 |
lin | +3.118 |
incidentally | +2.992 |
Neg logit contributions | |
oji | -3.485 |
anus | -3.370 |
ュ | -3.283 |
cair | -3.274 |
azor | -3.137 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
lihood | +0.617 |
amounts | +0.603 |
ness | +0.588 |
entimes | +0.551 |
lin | +0.550 |
Neg logit contributions | |
oji | -0.860 |
anus | -0.834 |
ュ | -0.812 |
cair | -0.798 |
azor | -0.775 |
Token |
|
Token ID | 198 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
oji | +0.841 |
anus | +0.806 |
ュ | +0.788 |
cair | +0.758 |
azor | +0.742 |
Neg logit contributions | |
lihood | -0.940 |
amounts | -0.923 |
ness | -0.903 |
entimes | -0.877 |
lin | -0.864 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
oji | +0.906 |
anus | +0.858 |
ュ | +0.836 |
cair | +0.804 |
Amazing | +0.796 |
Neg logit contributions | |
lihood | -1.196 |
amounts | -1.155 |
entimes | -1.140 |
lin | -1.089 |
ness | -1.084 |
Token | On |
Token ID | 2202 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
oji | +0.975 |
anus | +0.941 |
ュ | +0.907 |
cair | +0.879 |
Amazing | +0.861 |
Neg logit contributions | |
lihood | -1.038 |
amounts | -1.028 |
ness | -0.983 |
entimes | -0.962 |
lin | -0.958 |
Token | the |
Token ID | 262 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
oji | +0.512 |
anus | +0.494 |
ュ | +0.478 |
cair | +0.465 |
azor | +0.451 |
Neg logit contributions | |
lihood | -0.521 |
amounts | -0.509 |
ness | -0.498 |
entimes | -0.474 |
lin | -0.473 |
Token | surface |
Token ID | 4417 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
lihood | +0.250 |
amounts | +0.244 |
ness | +0.240 |
entimes | +0.227 |
lin | +0.226 |
Neg logit contributions | |
oji | -0.270 |
anus | -0.260 |
ュ | -0.252 |
cair | -0.247 |
azor | -0.239 |
Token | it |
Token ID | 340 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
amounts | +4.668 |
lihood | +4.576 |
ness | +4.475 |
lin | +4.093 |
LY | +3.803 |
Neg logit contributions | |
anus | -8.955 |
oji | -8.931 |
cair | -8.667 |
ュ | -8.428 |
azor | -8.305 |
Token | � |
Token ID | 447 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
lihood | +1.086 |
amounts | +1.078 |
ness | +1.042 |
lin | +0.979 |
entimes | +0.973 |
Neg logit contributions | |
oji | -1.497 |
anus | -1.456 |
ュ | -1.411 |
cair | -1.394 |
azor | -1.352 |
Token | � |
Token ID | 247 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
lihood | +0.523 |
amounts | +0.501 |
ness | +0.493 |
entimes | +0.474 |
lin | +0.466 |
Neg logit contributions | |
oji | -0.522 |
anus | -0.515 |
ュ | -0.497 |
cair | -0.477 |
azor | -0.473 |
Token | s |
Token ID | 82 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
lihood | +0.526 |
amounts | +0.503 |
ness | +0.487 |
entimes | +0.447 |
lin | +0.446 |
Neg logit contributions | |
oji | -1.268 |
anus | -1.236 |
ュ | -1.207 |
cair | -1.190 |
azor | -1.163 |
Token | a |
Token ID | 257 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
oji | +0.365 |
anus | +0.353 |
ュ | +0.341 |
cair | +0.334 |
azor | +0.324 |
Neg logit contributions | |
lihood | -0.372 |
amounts | -0.363 |
ness | -0.357 |
entimes | -0.340 |
CENT | -0.338 |
Token | with |
Token ID | 351 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
lihood | +0.741 |
amounts | +0.704 |
ness | +0.670 |
entimes | +0.664 |
CENT | +0.649 |
Neg logit contributions | |
oji | -1.312 |
anus | -1.251 |
ュ | -1.240 |
cair | -1.225 |
azor | -1.201 |
Token | the |
Token ID | 262 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
oji | +0.465 |
anus | +0.450 |
ュ | +0.437 |
cair | +0.431 |
azor | +0.415 |
Neg logit contributions | |
lihood | -0.410 |
amounts | -0.400 |
ness | -0.392 |
entimes | -0.374 |
CENT | -0.370 |
Token | requests |
Token ID | 7007 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
lihood | +1.466 |
amounts | +1.440 |
ness | +1.406 |
lin | +1.326 |
entimes | +1.323 |
Neg logit contributions | |
oji | -1.782 |
anus | -1.728 |
ュ | -1.676 |
cair | -1.649 |
azor | -1.596 |
Token | of |
Token ID | 286 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
oji | +0.589 |
anus | +0.568 |
ュ | +0.549 |
cair | +0.540 |
azor | +0.520 |
Neg logit contributions | |
lihood | -0.598 |
amounts | -0.586 |
ness | -0.573 |
entimes | -0.547 |
lin | -0.545 |
Token | other |
Token ID | 584 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
lihood | +0.537 |
amounts | +0.530 |
ness | +0.519 |
lin | +0.493 |
entimes | +0.491 |
Neg logit contributions | |
oji | -0.507 |
anus | -0.490 |
ュ | -0.473 |
cair | -0.464 |
azor | -0.447 |
Token | autonomous |
Token ID | 18284 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
oji | +2.558 |
anus | +2.471 |
ュ | +2.422 |
cair | +2.412 |
azor | +2.278 |
Neg logit contributions | |
lihood | -2.437 |
amounts | -2.297 |
ness | -2.211 |
entimes | -2.188 |
CENT | -2.172 |
Token | communities |
Token ID | 5348 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
ness | +5.869 |
amounts | +5.826 |
lihood | +5.351 |
lin | +5.344 |
dar | +5.123 |
Neg logit contributions | |
oji | -8.066 |
anus | -7.751 |
ュ | -7.389 |
cair | -7.217 |
Haunted | -7.176 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
lihood | +1.000 |
amounts | +0.987 |
ness | +0.960 |
lin | +0.898 |
entimes | +0.890 |
Neg logit contributions | |
oji | -1.466 |
anus | -1.428 |
ュ | -1.386 |
cair | -1.363 |
azor | -1.325 |
Token | � |
Token ID | 447 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
lihood | +0.624 |
amounts | +0.611 |
ness | +0.596 |
lin | +0.552 |
entimes | +0.545 |
Neg logit contributions | |
oji | -1.042 |
anus | -1.018 |
ュ | -0.985 |
cair | -0.975 |
azor | -0.948 |
Token | � |
Token ID | 251 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
oji | +1.230 |
anus | +1.193 |
cair | +1.145 |
ュ | +1.142 |
azor | +1.093 |
Neg logit contributions | |
lihood | -1.118 |
amounts | -1.107 |
ness | -1.090 |
lin | -1.022 |
entimes | -1.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
oji | +0.333 |
anus | +0.325 |
ュ | +0.312 |
cair | +0.309 |
azor | +0.300 |
Neg logit contributions | |
lihood | -0.281 |
amounts | -0.275 |
ness | -0.274 |
lin | -0.255 |
CENT | -0.252 |
Token | said |
Token ID | 531 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
oji | +1.155 |
anus | +1.115 |
ュ | +1.080 |
cair | +1.060 |
azor | +1.026 |
Neg logit contributions | |
lihood | -0.976 |
amounts | -0.950 |
ness | -0.925 |
lin | -0.876 |
entimes | -0.872 |
Token | that |
Token ID | 326 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
lihood | +0.147 |
amounts | +0.143 |
ness | +0.139 |
lin | +0.129 |
entimes | +0.129 |
Neg logit contributions | |
oji | -0.251 |
anus | -0.245 |
ュ | -0.238 |
cair | -0.235 |
azor | -0.229 |
Token | they |
Token ID | 484 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
lihood | +0.689 |
amounts | +0.674 |
ness | +0.656 |
lin | +0.615 |
entimes | +0.613 |
Neg logit contributions | |
oji | -1.011 |
anus | -0.983 |
ュ | -0.955 |
cair | -0.941 |
azor | -0.914 |
Token | did |
Token ID | 750 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
oji | +0.621 |
anus | +0.601 |
ュ | +0.579 |
cair | +0.570 |
azor | +0.551 |
Neg logit contributions | |
lihood | -0.502 |
amounts | -0.488 |
ness | -0.473 |
lin | -0.445 |
CENT | -0.444 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
lihood | +0.761 |
amounts | +0.749 |
ness | +0.732 |
lin | +0.686 |
entimes | +0.684 |
Neg logit contributions | |
oji | -1.039 |
anus | -1.010 |
ュ | -0.982 |
cair | -0.968 |
azor | -0.938 |
Token | Lomb |
Token ID | 28503 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
oji | +0.503 |
anus | +0.484 |
ュ | +0.471 |
cair | +0.458 |
azor | +0.445 |
Neg logit contributions | |
lihood | -0.501 |
amounts | -0.492 |
ness | -0.480 |
entimes | -0.461 |
lin | -0.458 |
Token | ardi |
Token ID | 22490 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
ness | +5.353 |
lihood | +5.346 |
amounts | +5.117 |
lin | +4.922 |
entimes | +4.900 |
Neg logit contributions | |
oji | -7.958 |
ュ | -7.620 |
anus | -7.513 |
cair | -7.409 |
Haunted | -7.255 |
Token | explains |
Token ID | 6688 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
lihood | +1.486 |
amounts | +1.472 |
ness | +1.438 |
lin | +1.355 |
entimes | +1.341 |
Neg logit contributions | |
oji | -1.894 |
anus | -1.835 |
ュ | -1.777 |
cair | -1.752 |
azor | -1.699 |
Token | that |
Token ID | 326 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
oji | +1.601 |
anus | +1.548 |
ュ | +1.501 |
cair | +1.471 |
azor | +1.427 |
Neg logit contributions | |
lihood | -1.435 |
amounts | -1.399 |
ness | -1.361 |
entimes | -1.299 |
CENT | -1.291 |
Token | people |
Token ID | 661 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
lihood | +0.544 |
amounts | +0.534 |
ness | +0.521 |
lin | +0.491 |
entimes | +0.490 |
Neg logit contributions | |
oji | -0.677 |
anus | -0.656 |
ュ | -0.636 |
cair | -0.626 |
azor | -0.607 |
Token | in |
Token ID | 287 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
oji | +0.115 |
anus | +0.111 |
ュ | +0.108 |
cair | +0.107 |
azor | +0.104 |
Neg logit contributions | |
lihood | -0.079 |
amounts | -0.077 |
ness | -0.075 |
lin | -0.070 |
CENT | -0.070 |
Token | seized |
Token ID | 12000 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
lihood | +1.164 |
amounts | +1.134 |
ness | +1.109 |
entimes | +1.045 |
lin | +1.038 |
Neg logit contributions | |
oji | -1.555 |
anus | -1.506 |
ュ | -1.464 |
cair | -1.437 |
azor | -1.400 |
Token | two |
Token ID | 734 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
amounts | +3.982 |
lihood | +3.901 |
ness | +3.828 |
lin | +3.656 |
entimes | +3.566 |
Neg logit contributions | |
oji | -3.677 |
anus | -3.552 |
ュ | -3.432 |
cair | -3.351 |
azor | -3.228 |
Token | dump |
Token ID | 10285 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
oji | +2.049 |
anus | +1.985 |
ュ | +1.940 |
cair | +1.911 |
azor | +1.857 |
Neg logit contributions | |
lihood | -1.392 |
amounts | -1.338 |
ness | -1.314 |
entimes | -1.232 |
CENT | -1.227 |
Token | ers |
Token ID | 364 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
lihood | +0.491 |
amounts | +0.462 |
ness | +0.454 |
entimes | +0.443 |
CENT | +0.438 |
Neg logit contributions | |
oji | -0.525 |
anus | -0.501 |
cair | -0.484 |
ュ | -0.482 |
azor | -0.466 |
Token | and |
Token ID | 290 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
amounts | +1.822 |
lihood | +1.786 |
ness | +1.755 |
lin | +1.659 |
dar | +1.606 |
Neg logit contributions | |
oji | -2.705 |
anus | -2.646 |
ュ | -2.559 |
cair | -2.542 |
azor | -2.457 |
Token | arrested |
Token ID | 5169 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
lihood | +0.707 |
amounts | +0.693 |
ness | +0.659 |
lin | +0.598 |
entimes | +0.586 |
Neg logit contributions | |
oji | -1.962 |
anus | -1.926 |
ュ | -1.880 |
cair | -1.860 |
azor | -1.814 |
Token | drivers |
Token ID | 6643 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
amounts | +5.632 |
ness | +5.373 |
lihood | +5.311 |
dar | +5.149 |
lin | +5.074 |
Neg logit contributions | |
oji | -7.687 |
anus | -7.581 |
ュ | -7.488 |
cair | -7.304 |
Haunted | -7.158 |
Token | from |
Token ID | 422 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
amounts | +0.425 |
lihood | +0.415 |
ness | +0.405 |
lin | +0.368 |
dar | +0.360 |
Neg logit contributions | |
oji | -0.961 |
anus | -0.950 |
ュ | -0.918 |
cair | -0.912 |
azor | -0.886 |
Token | this |
Token ID | 428 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
lihood | +1.959 |
amounts | +1.955 |
ness | +1.916 |
lin | +1.799 |
incidentally | +1.774 |
Neg logit contributions | |
oji | -2.285 |
anus | -2.218 |
ュ | -2.180 |
cair | -2.099 |
azor | -2.056 |
Token | place |
Token ID | 1295 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
lihood | +0.791 |
amounts | +0.771 |
ness | +0.753 |
entimes | +0.711 |
lin | +0.708 |
Neg logit contributions | |
oji | -1.049 |
anus | -1.019 |
ュ | -0.988 |
cair | -0.973 |
azor | -0.944 |
Token | . |
Token ID | 13 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
lihood | +0.939 |
amounts | +0.925 |
ness | +0.899 |
lin | +0.843 |
entimes | +0.834 |
Neg logit contributions | |
oji | -1.374 |
anus | -1.338 |
ュ | -1.299 |
cair | -1.278 |
azor | -1.243 |
Token | � |
Token ID | 250 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
oji | +1.282 |
anus | +1.246 |
ュ | +1.213 |
cair | +1.193 |
azor | +1.160 |
Neg logit contributions | |
lihood | -0.847 |
amounts | -0.829 |
ness | -0.806 |
lin | -0.754 |
entimes | -0.753 |
Token | Obviously |
Token ID | 20670 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
oji | +0.387 |
anus | +0.372 |
ュ | +0.364 |
cair | +0.356 |
azor | +0.344 |
Neg logit contributions | |
lihood | -0.370 |
amounts | -0.366 |
ness | -0.353 |
entimes | -0.341 |
lin | -0.340 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
oji | +1.359 |
anus | +1.307 |
ュ | +1.278 |
cair | +1.265 |
uitous | +1.219 |
Neg logit contributions | |
lihood | -0.897 |
amounts | -0.872 |
ness | -0.850 |
entimes | -0.804 |
lin | -0.804 |
Token | we |
Token ID | 356 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
lihood | +0.938 |
amounts | +0.922 |
ness | +0.898 |
lin | +0.843 |
entimes | +0.840 |
Neg logit contributions | |
oji | -1.280 |
anus | -1.245 |
ュ | -1.208 |
cair | -1.189 |
azor | -1.154 |
Token | condemn |
Token ID | 15402 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
lihood | +0.518 |
amounts | +0.506 |
ness | +0.489 |
lin | +0.458 |
entimes | +0.457 |
Neg logit contributions | |
oji | -0.823 |
anus | -0.797 |
ュ | -0.774 |
cair | -0.767 |
azor | -0.741 |
Token | what |
Token ID | 644 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
amounts | +3.729 |
lihood | +3.680 |
ness | +3.572 |
lin | +3.364 |
entimes | +3.257 |
Neg logit contributions | |
oji | -5.067 |
anus | -4.970 |
ュ | -4.770 |
cair | -4.611 |
azor | -4.558 |
Token | he |
Token ID | 339 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
amounts | +5.463 |
lihood | +5.156 |
ness | +5.002 |
lin | +4.642 |
amounted | +4.618 |
Neg logit contributions | |
anus | -8.236 |
oji | -8.216 |
ュ | -7.789 |
azor | -7.534 |
cair | -7.530 |
Token | said |
Token ID | 531 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
lihood | +1.852 |
amounts | +1.841 |
ness | +1.782 |
lin | +1.669 |
entimes | +1.663 |
Neg logit contributions | |
oji | -2.726 |
anus | -2.662 |
ュ | -2.578 |
cair | -2.541 |
azor | -2.471 |
Token | . |
Token ID | 13 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
lihood | +1.190 |
amounts | +1.171 |
ness | +1.137 |
lin | +1.061 |
entimes | +1.055 |
Neg logit contributions | |
oji | -1.809 |
anus | -1.763 |
ュ | -1.710 |
cair | -1.690 |
azor | -1.639 |
Token | � |
Token ID | 447 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
lihood | +1.696 |
amounts | +1.664 |
ness | +1.631 |
lin | +1.532 |
entimes | +1.523 |
Neg logit contributions | |
oji | -1.976 |
anus | -1.924 |
ュ | -1.853 |
cair | -1.828 |
azor | -1.767 |
Token | � |
Token ID | 251 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
lihood | +1.069 |
amounts | +1.060 |
ness | +1.035 |
lin | +0.966 |
entimes | +0.960 |
Neg logit contributions | |
oji | -1.421 |
anus | -1.379 |
ュ | -1.331 |
cair | -1.325 |
azor | -1.271 |
Token | lives |
Token ID | 3160 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
oji | +3.609 |
anus | +3.464 |
ュ | +3.324 |
cair | +3.299 |
azor | +3.182 |
Neg logit contributions | |
lihood | -3.654 |
amounts | -3.489 |
ness | -3.418 |
entimes | -3.386 |
dar | -3.332 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
lihood | +0.847 |
amounts | +0.833 |
ness | +0.812 |
lin | +0.766 |
entimes | +0.763 |
Neg logit contributions | |
oji | -1.079 |
anus | -1.049 |
ュ | -1.018 |
cair | -1.003 |
azor | -0.969 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
oji | +3.571 |
anus | +3.439 |
ュ | +3.325 |
cair | +3.275 |
uitous | +3.199 |
Neg logit contributions | |
lihood | -2.776 |
amounts | -2.654 |
ness | -2.604 |
entimes | -2.483 |
CENT | -2.476 |
Token | while |
Token ID | 981 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
oji | +0.387 |
anus | +0.377 |
ュ | +0.364 |
cair | +0.359 |
azor | +0.347 |
Neg logit contributions | |
lihood | -0.339 |
amounts | -0.330 |
ness | -0.325 |
entimes | -0.307 |
lin | -0.306 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
oji | +1.363 |
anus | +1.332 |
ュ | +1.291 |
cair | +1.275 |
azor | +1.231 |
Neg logit contributions | |
lihood | -0.996 |
amounts | -0.974 |
ness | -0.954 |
lin | -0.894 |
entimes | -0.892 |
Token | Post |
Token ID | 2947 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
lihood | +0.356 |
amounts | +0.349 |
ness | +0.341 |
lin | +0.322 |
entimes | +0.322 |
Neg logit contributions | |
oji | -0.414 |
anus | -0.402 |
ュ | -0.389 |
cair | -0.383 |
azor | -0.370 |
Token | has |
Token ID | 468 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
amounts | +5.456 |
ness | +5.278 |
lihood | +5.140 |
lin | +4.815 |
entimes | +4.724 |
Neg logit contributions | |
oji | -8.143 |
anus | -7.740 |
ュ | -7.396 |
cair | -7.270 |
azor | -7.242 |
Token | relayed |
Token ID | 47968 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
lihood | +1.767 |
amounts | +1.752 |
ness | +1.703 |
lin | +1.608 |
entimes | +1.589 |
Neg logit contributions | |
oji | -2.292 |
anus | -2.216 |
ュ | -2.145 |
cair | -2.117 |
azor | -2.051 |
Token | 12 |
Token ID | 1105 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
amounts | +2.561 |
lihood | +2.559 |
ness | +2.497 |
lin | +2.380 |
entimes | +2.323 |
Neg logit contributions | |
oji | -2.284 |
anus | -2.182 |
ュ | -2.125 |
cair | -2.084 |
azor | -2.005 |
Token | dead |
Token ID | 2636 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
oji | +0.372 |
anus | +0.361 |
ュ | +0.350 |
cair | +0.344 |
azor | +0.333 |
Neg logit contributions | |
lihood | -0.326 |
amounts | -0.319 |
ness | -0.311 |
entimes | -0.295 |
lin | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
oji | +1.388 |
anus | +1.345 |
ュ | +1.299 |
cair | +1.281 |
azor | +1.246 |
Neg logit contributions | |
lihood | -1.039 |
amounts | -1.005 |
ness | -0.980 |
entimes | -0.935 |
lin | -0.923 |
Token | News |
Token ID | 3000 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
oji | +2.192 |
anus | +2.139 |
ュ | +2.064 |
cair | +2.014 |
uitous | +1.953 |
Neg logit contributions | |
lihood | -2.049 |
amounts | -2.001 |
ness | -1.933 |
entimes | -1.866 |
lin | -1.846 |
Token | analysis |
Token ID | 3781 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
oji | +1.038 |
anus | +1.013 |
ュ | +0.985 |
cair | +0.966 |
azor | +0.945 |
Neg logit contributions | |
lihood | -0.714 |
amounts | -0.693 |
ness | -0.670 |
entimes | -0.636 |
lin | -0.635 |
Token | pointed |
Token ID | 6235 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
oji | +1.004 |
anus | +0.967 |
ュ | +0.939 |
cair | +0.930 |
azor | +0.896 |
Neg logit contributions | |
lihood | -1.028 |
amounts | -0.986 |
ness | -0.972 |
entimes | -0.932 |
CENT | -0.929 |
Token | to |
Token ID | 284 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
oji | +0.479 |
anus | +0.468 |
ュ | +0.453 |
cair | +0.450 |
azor | +0.436 |
Neg logit contributions | |
lihood | -0.276 |
amounts | -0.272 |
ness | -0.268 |
lin | -0.247 |
entimes | -0.245 |
Token | five |
Token ID | 1936 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
oji | +0.939 |
anus | +0.911 |
ュ | +0.883 |
cair | +0.864 |
azor | +0.838 |
Neg logit contributions | |
lihood | -0.892 |
amounts | -0.864 |
ness | -0.849 |
entimes | -0.813 |
lin | -0.807 |
Token | reasons |
Token ID | 3840 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
oji | +4.477 |
anus | +4.218 |
ュ | +4.206 |
cair | +4.051 |
azor | +4.021 |
Neg logit contributions | |
lihood | -4.853 |
amounts | -4.435 |
ness | -4.380 |
entimes | -4.342 |
CENT | -4.328 |
Token | why |
Token ID | 1521 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
oji | +6.902 |
anus | +6.374 |
ュ | +6.350 |
Curse | +6.189 |
cair | +6.188 |
Neg logit contributions | |
lihood | -7.392 |
entimes | -7.076 |
dar | -6.937 |
amounts | -6.895 |
CENT | -6.741 |
Token | the |
Token ID | 262 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
oji | +3.853 |
anus | +3.691 |
ュ | +3.593 |
cair | +3.575 |
uitous | +3.475 |
Neg logit contributions | |
lihood | -3.152 |
amounts | -3.003 |
ness | -2.954 |
entimes | -2.904 |
dar | -2.869 |
Token | Russians |
Token ID | 13234 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
oji | +1.462 |
anus | +1.422 |
ュ | +1.383 |
cair | +1.362 |
azor | +1.320 |
Neg logit contributions | |
lihood | -1.135 |
amounts | -1.081 |
ness | -1.072 |
entimes | -1.036 |
dar | -1.013 |
Token | are |
Token ID | 389 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
lihood | +0.220 |
amounts | +0.213 |
ness | +0.208 |
entimes | +0.195 |
lin | +0.195 |
Neg logit contributions | |
oji | -0.334 |
anus | -0.324 |
ュ | -0.314 |
cair | -0.311 |
azor | -0.302 |
Token | likely |
Token ID | 1884 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
oji | +1.355 |
anus | +1.298 |
ュ | +1.271 |
cair | +1.248 |
azor | +1.231 |
Neg logit contributions | |
lihood | -1.103 |
amounts | -1.063 |
ness | -1.045 |
entimes | -1.000 |
dar | -0.987 |
Token | ighton |
Token ID | 42993 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
oji | +2.776 |
anus | +2.644 |
cair | +2.464 |
ュ | +2.431 |
uitous | +2.366 |
Neg logit contributions | |
lihood | -3.258 |
amounts | -3.205 |
ness | -3.094 |
lin | -2.992 |
entimes | -2.948 |
Token | University |
Token ID | 2059 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
oji | +0.671 |
anus | +0.644 |
ュ | +0.610 |
cair | +0.595 |
azor | +0.564 |
Neg logit contributions | |
lihood | -1.217 |
amounts | -1.195 |
ness | -1.177 |
lin | -1.135 |
entimes | -1.131 |
Token | in |
Token ID | 287 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
oji | +2.161 |
anus | +2.106 |
ュ | +2.032 |
cair | +2.010 |
azor | +1.942 |
Neg logit contributions | |
lihood | -1.748 |
amounts | -1.676 |
ness | -1.642 |
lin | -1.568 |
entimes | -1.560 |
Token | Omaha |
Token ID | 37053 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
lihood | +0.910 |
amounts | +0.894 |
ness | +0.876 |
lin | +0.835 |
entimes | +0.835 |
Neg logit contributions | |
oji | -0.798 |
anus | -0.771 |
ュ | -0.743 |
cair | -0.729 |
azor | -0.701 |
Token | , |
Token ID | 11 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
oji | +2.479 |
anus | +2.412 |
ュ | +2.334 |
cair | +2.309 |
azor | +2.242 |
Neg logit contributions | |
lihood | -1.771 |
amounts | -1.686 |
ness | -1.658 |
lin | -1.574 |
entimes | -1.565 |
Token | Nebraska |
Token ID | 18329 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
oji | +1.688 |
anus | +1.639 |
ュ | +1.562 |
cair | +1.540 |
azor | +1.502 |
Neg logit contributions | |
lihood | -1.645 |
amounts | -1.571 |
ness | -1.553 |
lin | -1.477 |
entimes | -1.477 |
Token | became |
Token ID | 2627 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
oji | +7.962 |
anus | +7.691 |
ュ | +7.385 |
cair | +7.291 |
azor | +7.211 |
Neg logit contributions | |
lihood | -6.858 |
amounts | -6.097 |
CENT | -6.071 |
ness | -6.045 |
lin | -5.985 |
Token | the |
Token ID | 262 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
oji | +1.660 |
anus | +1.624 |
ュ | +1.548 |
cair | +1.538 |
azor | +1.479 |
Neg logit contributions | |
lihood | -1.858 |
amounts | -1.791 |
ness | -1.768 |
entimes | -1.689 |
lin | -1.662 |
Token | latest |
Token ID | 3452 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
oji | +1.978 |
anus | +1.940 |
ュ | +1.855 |
cair | +1.825 |
azor | +1.769 |
Neg logit contributions | |
lihood | -1.854 |
amounts | -1.782 |
ness | -1.750 |
entimes | -1.697 |
CENT | -1.654 |
Token | Jesuit |
Token ID | 50190 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
oji | +1.869 |
anus | +1.798 |
ュ | +1.727 |
cair | +1.710 |
azor | +1.641 |
Neg logit contributions | |
lihood | -2.124 |
amounts | -2.059 |
ness | -2.002 |
lin | -1.928 |
entimes | -1.927 |
Token | institution |
Token ID | 9901 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
amounts | +3.332 |
lihood | +3.326 |
ness | +3.303 |
lin | +3.121 |
entimes | +3.113 |
Neg logit contributions | |
oji | -2.810 |
anus | -2.698 |
ュ | -2.654 |
cair | -2.566 |
azor | -2.481 |
Token | omy |
Token ID | 9145 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
oji | +4.252 |
anus | +4.047 |
cair | +3.782 |
ュ | +3.765 |
azor | +3.743 |
Neg logit contributions | |
lihood | -4.758 |
amounts | -4.742 |
ness | -4.554 |
CENT | -4.390 |
lin | -4.384 |
Token | Observatory |
Token ID | 25758 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
oji | +2.647 |
anus | +2.590 |
ュ | +2.508 |
cair | +2.460 |
azor | +2.423 |
Neg logit contributions | |
lihood | -1.843 |
amounts | -1.813 |
ness | -1.773 |
lin | -1.669 |
entimes | -1.665 |
Token | in |
Token ID | 287 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
oji | +1.650 |
anus | +1.610 |
ュ | +1.562 |
cair | +1.531 |
azor | +1.487 |
Neg logit contributions | |
lihood | -1.191 |
amounts | -1.149 |
ness | -1.136 |
entimes | -1.076 |
lin | -1.059 |
Token | Charlottesville |
Token ID | 24756 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
oji | +0.110 |
anus | +0.106 |
ュ | +0.102 |
cair | +0.101 |
azor | +0.097 |
Neg logit contributions | |
lihood | -0.105 |
amounts | -0.103 |
ness | -0.101 |
entimes | -0.096 |
lin | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
oji | +4.409 |
anus | +4.306 |
ュ | +4.156 |
cair | +4.095 |
azor | +3.946 |
Neg logit contributions | |
lihood | -3.093 |
ness | -2.908 |
amounts | -2.878 |
entimes | -2.760 |
CENT | -2.700 |
Token | Virginia |
Token ID | 6025 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
oji | +1.094 |
anus | +1.064 |
ュ | +1.029 |
cair | +1.007 |
azor | +0.975 |
Neg logit contributions | |
lihood | -1.049 |
amounts | -1.012 |
ness | -1.002 |
entimes | -0.956 |
lin | -0.945 |
Token | , |
Token ID | 11 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
oji | +8.249 |
anus | +8.009 |
ュ | +7.757 |
cair | +7.482 |
uitous | +7.395 |
Neg logit contributions | |
lihood | -6.645 |
ness | -6.078 |
entimes | -5.929 |
amounts | -5.911 |
CENT | -5.818 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
oji | +1.969 |
anus | +1.914 |
ュ | +1.848 |
cair | +1.821 |
azor | +1.774 |
Neg logit contributions | |
lihood | -1.692 |
ness | -1.614 |
amounts | -1.613 |
entimes | -1.530 |
dar | -1.512 |
Token | facility |
Token ID | 6841 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
oji | +0.699 |
anus | +0.677 |
ュ | +0.656 |
cair | +0.642 |
azor | +0.622 |
Neg logit contributions | |
lihood | -0.643 |
amounts | -0.619 |
ness | -0.615 |
entimes | -0.585 |
lin | -0.579 |
Token | would |
Token ID | 561 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
oji | +0.239 |
anus | +0.233 |
ュ | +0.226 |
cair | +0.222 |
azor | +0.216 |
Neg logit contributions | |
lihood | -0.157 |
amounts | -0.151 |
ness | -0.148 |
entimes | -0.140 |
CENT | -0.138 |
Token | be |
Token ID | 307 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
lihood | +0.279 |
amounts | +0.268 |
ness | +0.262 |
CENT | +0.245 |
entimes | +0.245 |
Neg logit contributions | |
oji | -0.427 |
anus | -0.415 |
ュ | -0.404 |
cair | -0.399 |
uitous | -0.385 |
Token |
|
Token ID | 198 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
oji | +0.123 |
anus | +0.119 |
ュ | +0.116 |
cair | +0.113 |
azor | +0.110 |
Neg logit contributions | |
lihood | -0.124 |
amounts | -0.122 |
ness | -0.119 |
entimes | -0.115 |
lin | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
lihood | +2.719 |
amounts | +2.677 |
ness | +2.624 |
lin | +2.477 |
entimes | +2.462 |
Neg logit contributions | |
oji | -2.952 |
anus | -2.860 |
ュ | -2.764 |
cair | -2.721 |
azor | -2.627 |
Token | Among |
Token ID | 14311 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
lihood | +1.756 |
amounts | +1.726 |
ness | +1.702 |
CENT | +1.608 |
lin | +1.595 |
Neg logit contributions | |
oji | -1.730 |
anus | -1.674 |
ュ | -1.611 |
cair | -1.589 |
azor | -1.528 |
Token | those |
Token ID | 883 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
oji | +2.354 |
anus | +2.275 |
ュ | +2.204 |
cair | +2.169 |
azor | +2.105 |
Neg logit contributions | |
lihood | -2.028 |
amounts | -1.991 |
ness | -1.942 |
entimes | -1.844 |
lin | -1.842 |
Token | ens |
Token ID | 3140 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
oji | +2.049 |
anus | +1.945 |
ュ | +1.890 |
cair | +1.865 |
azor | +1.846 |
Neg logit contributions | |
lihood | -1.407 |
amounts | -1.344 |
ness | -1.320 |
entimes | -1.279 |
CENT | -1.262 |
Token | n |
Token ID | 77 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
lihood | +2.184 |
amounts | +2.149 |
ness | +2.128 |
lin | +2.031 |
dar | +2.001 |
Neg logit contributions | |
oji | -1.662 |
anus | -1.592 |
ュ | -1.559 |
cair | -1.524 |
azor | -1.445 |
Token | ared |
Token ID | 1144 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
oji | +6.831 |
azor | +6.230 |
anus | +6.182 |
ammy | +6.057 |
isance | +5.963 |
Neg logit contributions | |
lin | -8.083 |
Adin | -8.051 |
CENT | -7.664 |
amounts | -7.633 |
incidentally | -7.616 |
Token | by |
Token ID | 416 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
lihood | +1.231 |
amounts | +1.215 |
ness | +1.172 |
lin | +1.092 |
entimes | +1.082 |
Neg logit contributions | |
oji | -2.039 |
anus | -1.988 |
ュ | -1.940 |
cair | -1.915 |
azor | -1.852 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
lihood | +0.674 |
amounts | +0.668 |
ness | +0.650 |
lin | +0.615 |
entimes | +0.608 |
Neg logit contributions | |
oji | -0.743 |
anus | -0.719 |
ュ | -0.696 |
cair | -0.686 |
azor | -0.659 |
Token | wide |
Token ID | 3094 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
lihood | +0.274 |
amounts | +0.264 |
ness | +0.260 |
entimes | +0.247 |
CENT | +0.244 |
Neg logit contributions | |
oji | -0.372 |
anus | -0.363 |
ュ | -0.351 |
cair | -0.345 |
azor | -0.336 |
Token | - |
Token ID | 12 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
oji | +1.826 |
anus | +1.789 |
ュ | +1.738 |
cair | +1.682 |
azor | +1.657 |
Neg logit contributions | |
lihood | -1.447 |
amounts | -1.348 |
CENT | -1.334 |
ness | -1.318 |
entimes | -1.276 |
Token | Force |
Token ID | 5221 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ness | +0.796 |
lihood | +0.796 |
amounts | +0.790 |
lin | +0.725 |
dar | +0.696 |
Neg logit contributions | |
oji | -1.650 |
anus | -1.627 |
cair | -1.565 |
ュ | -1.562 |
hetics | -1.522 |
Token | One |
Token ID | 1881 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
oji | +1.120 |
anus | +1.072 |
ュ | +1.020 |
cair | +0.988 |
azor | +0.950 |
Neg logit contributions | |
lihood | -1.808 |
amounts | -1.758 |
ness | -1.729 |
entimes | -1.664 |
lin | -1.653 |
Token | in |
Token ID | 287 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
lihood | +0.295 |
amounts | +0.288 |
ness | +0.281 |
entimes | +0.264 |
lin | +0.264 |
Neg logit contributions | |
oji | -0.389 |
anus | -0.378 |
ュ | -0.366 |
cair | -0.360 |
azor | -0.349 |
Token | Reno |
Token ID | 33817 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
lihood | +0.912 |
amounts | +0.900 |
ness | +0.880 |
lin | +0.830 |
entimes | +0.824 |
Neg logit contributions | |
oji | -1.061 |
anus | -1.028 |
ュ | -0.996 |
cair | -0.981 |
azor | -0.948 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
oji | +3.645 |
anus | +3.472 |
ュ | +3.384 |
cair | +3.333 |
azor | +3.248 |
Neg logit contributions | |
lihood | -2.562 |
amounts | -2.397 |
ness | -2.303 |
entimes | -2.266 |
lin | -2.218 |
Token | Nevada |
Token ID | 12087 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
lihood | +0.704 |
amounts | +0.689 |
ness | +0.675 |
lin | +0.643 |
entimes | +0.642 |
Neg logit contributions | |
oji | -0.697 |
anus | -0.669 |
ュ | -0.647 |
cair | -0.636 |
azor | -0.614 |
Token | , |
Token ID | 11 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
oji | +8.007 |
anus | +7.489 |
ュ | +7.263 |
cair | +7.128 |
hetics | +6.915 |
Neg logit contributions | |
lihood | -6.892 |
amounts | -6.361 |
entimes | -6.233 |
ritical | -6.128 |
ness | -6.014 |
Token | U |
Token ID | 471 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
oji | +1.461 |
anus | +1.406 |
ュ | +1.361 |
cair | +1.343 |
azor | +1.298 |
Neg logit contributions | |
lihood | -1.293 |
amounts | -1.245 |
ness | -1.222 |
entimes | -1.189 |
lin | -1.155 |
Token | . |
Token ID | 13 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
lihood | +0.474 |
amounts | +0.465 |
entimes | +0.437 |
ness | +0.437 |
lin | +0.428 |
Neg logit contributions | |
oji | -0.553 |
anus | -0.524 |
ュ | -0.517 |
cair | -0.504 |
azor | -0.491 |
Token | S |
Token ID | 50 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
oji | +2.002 |
ュ | +1.986 |
anus | +1.920 |
Amazing | +1.900 |
Haunted | +1.885 |
Neg logit contributions | |
lihood | -1.694 |
amounts | -1.671 |
entimes | -1.626 |
ritical | -1.548 |
lin | -1.533 |
Token | ., |
Token ID | 1539 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
lihood | +0.265 |
amounts | +0.264 |
ness | +0.262 |
lin | +0.236 |
entimes | +0.233 |
Neg logit contributions | |
oji | -0.560 |
anus | -0.550 |
ュ | -0.535 |
cair | -0.531 |
azor | -0.515 |
Token | ev |
Token ID | 1990 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
oji | +3.190 |
anus | +3.093 |
cair | +2.888 |
ュ | +2.851 |
azor | +2.829 |
Neg logit contributions | |
lihood | -2.701 |
amounts | -2.629 |
ness | -2.472 |
CENT | -2.458 |
entimes | -2.457 |
Token | ic |
Token ID | 291 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
oji | +3.114 |
anus | +3.036 |
cair | +2.765 |
ュ | +2.743 |
azor | +2.706 |
Neg logit contributions | |
lihood | -3.357 |
amounts | -3.252 |
ness | -3.107 |
entimes | -3.080 |
CENT | -3.048 |
Token | " |
Token ID | 1 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
oji | +0.401 |
anus | +0.391 |
ュ | +0.377 |
cair | +0.374 |
azor | +0.362 |
Neg logit contributions | |
lihood | -0.298 |
amounts | -0.292 |
ness | -0.284 |
entimes | -0.268 |
lin | -0.267 |
Token | ( |
Token ID | 357 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
lihood | +0.835 |
amounts | +0.822 |
ness | +0.800 |
lin | +0.751 |
entimes | +0.748 |
Neg logit contributions | |
oji | -1.168 |
anus | -1.134 |
ュ | -1.103 |
cair | -1.086 |
azor | -1.053 |
Token | m |
Token ID | 76 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
oji | +0.745 |
anus | +0.726 |
ュ | +0.701 |
cair | +0.689 |
azor | +0.664 |
Neg logit contributions | |
lihood | -0.688 |
amounts | -0.678 |
ness | -0.655 |
lin | -0.628 |
entimes | -0.627 |
Token | att |
Token ID | 1078 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
oji | +2.652 |
anus | +2.538 |
ュ | +2.454 |
cair | +2.372 |
azor | +2.357 |
Neg logit contributions | |
lihood | -2.812 |
amounts | -2.755 |
ness | -2.638 |
entimes | -2.572 |
lin | -2.552 |
Token | - |
Token ID | 12 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
oji | +7.795 |
anus | +7.319 |
cair | +7.070 |
hetics | +6.795 |
ュ | +6.742 |
Neg logit contributions | |
lihood | -7.110 |
amounts | -6.982 |
CENT | -6.552 |
lin | -6.497 |
ness | -6.469 |
Token | EE |
Token ID | 6500 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
oji | +3.559 |
anus | +3.398 |
cair | +3.271 |
ュ | +3.244 |
azor | +3.125 |
Neg logit contributions | |
lihood | -2.731 |
amounts | -2.681 |
ness | -2.517 |
lin | -2.472 |
entimes | -2.452 |
Token | - |
Token ID | 12 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
oji | +1.937 |
anus | +1.869 |
ュ | +1.809 |
cair | +1.779 |
azor | +1.735 |
Neg logit contributions | |
lihood | -1.411 |
amounts | -1.366 |
ness | -1.321 |
entimes | -1.263 |
lin | -1.249 |
Token | oh |
Token ID | 1219 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
lihood | +1.120 |
amounts | +1.099 |
ness | +1.076 |
lin | +1.009 |
entimes | +1.006 |
Neg logit contributions | |
oji | -1.460 |
anus | -1.417 |
ュ | -1.377 |
cair | -1.354 |
azor | -1.313 |
Token | - |
Token ID | 12 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
oji | +2.060 |
anus | +1.998 |
ュ | +1.923 |
cair | +1.894 |
azor | +1.834 |
Neg logit contributions | |
lihood | -1.436 |
amounts | -1.410 |
ness | -1.348 |
lin | -1.283 |
entimes | -1.281 |
Token | professor |
Token ID | 6240 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
oji | +0.717 |
anus | +0.694 |
ュ | +0.671 |
cair | +0.665 |
azor | +0.638 |
Neg logit contributions | |
lihood | -0.720 |
amounts | -0.704 |
ness | -0.690 |
entimes | -0.665 |
CENT | -0.657 |
Token | at |
Token ID | 379 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
lihood | +0.099 |
amounts | +0.098 |
ness | +0.097 |
lin | +0.091 |
entimes | +0.090 |
Neg logit contributions | |
oji | -0.112 |
anus | -0.108 |
ュ | -0.104 |
cair | -0.102 |
azor | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
oji | +3.391 |
anus | +3.271 |
cair | +3.153 |
ュ | +3.151 |
azor | +3.003 |
Neg logit contributions | |
lihood | -3.646 |
amounts | -3.517 |
ness | -3.445 |
entimes | -3.379 |
CENT | -3.363 |
Token | University |
Token ID | 2059 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
oji | +1.269 |
anus | +1.206 |
ュ | +1.149 |
cair | +1.130 |
azor | +1.061 |
Neg logit contributions | |
lihood | -2.229 |
amounts | -2.172 |
ness | -2.140 |
entimes | -2.092 |
CENT | -2.091 |
Token | of |
Token ID | 286 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
oji | +2.080 |
anus | +1.966 |
ュ | +1.958 |
cair | +1.933 |
itect | +1.787 |
Neg logit contributions | |
lihood | -3.263 |
amounts | -3.152 |
entimes | -3.137 |
ness | -3.037 |
CENT | -3.011 |
Token | Calgary |
Token ID | 17842 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
oji | +2.577 |
anus | +2.485 |
ュ | +2.430 |
cair | +2.358 |
uitous | +2.305 |
Neg logit contributions | |
lihood | -2.464 |
amounts | -2.390 |
entimes | -2.313 |
ness | -2.296 |
CENT | -2.274 |
Token | , |
Token ID | 11 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
anus | +7.105 |
oji | +7.074 |
cair | +6.924 |
ュ | +6.524 |
azor | +6.441 |
Neg logit contributions | |
lihood | -7.237 |
amounts | -6.829 |
CENT | -6.761 |
entimes | -6.706 |
ness | -6.595 |
Token | as |
Token ID | 355 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
oji | +2.153 |
anus | +2.096 |
ュ | +2.019 |
cair | +2.008 |
azor | +1.940 |
Neg logit contributions | |
lihood | -1.876 |
amounts | -1.816 |
ness | -1.793 |
entimes | -1.700 |
lin | -1.687 |
Token | both |
Token ID | 1111 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
lihood | +1.602 |
amounts | +1.583 |
ness | +1.534 |
lin | +1.431 |
entimes | +1.421 |
Neg logit contributions | |
oji | -2.447 |
anus | -2.379 |
ュ | -2.306 |
cair | -2.270 |
azor | -2.205 |
Token | cases |
Token ID | 2663 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
oji | +3.324 |
anus | +3.236 |
cair | +3.148 |
ュ | +3.094 |
azor | +3.000 |
Neg logit contributions | |
lihood | -2.846 |
ness | -2.719 |
amounts | -2.703 |
entimes | -2.650 |
CENT | -2.643 |
Token | involved |
Token ID | 2950 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
oji | +3.018 |
anus | +2.893 |
ュ | +2.744 |
azor | +2.734 |
cair | +2.728 |
Neg logit contributions | |
lihood | -2.211 |
amounts | -2.101 |
ness | -2.047 |
LY | -1.988 |
entimes | -1.986 |
Token | etry |
Token ID | 11973 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
oji | +2.725 |
anus | +2.596 |
cair | +2.417 |
ュ | +2.388 |
hetics | +2.340 |
Neg logit contributions | |
lihood | -3.582 |
amounts | -3.520 |
ness | -3.380 |
lin | -3.315 |
entimes | -3.286 |
Token | Arts |
Token ID | 11536 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
oji | +2.822 |
anus | +2.750 |
ュ | +2.640 |
cair | +2.605 |
azor | +2.521 |
Neg logit contributions | |
lihood | -2.373 |
amounts | -2.321 |
ness | -2.247 |
entimes | -2.158 |
lin | -2.146 |
Token | in |
Token ID | 287 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
oji | +1.768 |
anus | +1.726 |
ュ | +1.665 |
cair | +1.640 |
azor | +1.595 |
Neg logit contributions | |
lihood | -1.373 |
amounts | -1.348 |
ness | -1.311 |
entimes | -1.245 |
lin | -1.239 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
oji | +1.289 |
anus | +1.246 |
ュ | +1.200 |
cair | +1.183 |
azor | +1.136 |
Neg logit contributions | |
lihood | -1.327 |
amounts | -1.290 |
ness | -1.266 |
entimes | -1.223 |
lin | -1.198 |
Token | , |
Token ID | 11 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
oji | +3.579 |
anus | +3.502 |
ュ | +3.372 |
cair | +3.320 |
azor | +3.227 |
Neg logit contributions | |
lihood | -2.636 |
amounts | -2.538 |
ness | -2.466 |
entimes | -2.364 |
lin | -2.346 |
Token | Georgia |
Token ID | 7859 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
oji | +1.158 |
anus | +1.125 |
ュ | +1.084 |
cair | +1.053 |
azor | +1.025 |
Neg logit contributions | |
lihood | -1.303 |
amounts | -1.258 |
ness | -1.239 |
entimes | -1.193 |
lin | -1.176 |
Token | .[ |
Token ID | 3693 |
Feature activation | -9.75e-02 |
Pos logit contributions | |
oji | +7.388 |
anus | +7.199 |
ュ | +6.915 |
cair | +6.777 |
azor | +6.653 |
Neg logit contributions | |
lihood | -6.945 |
amounts | -6.477 |
ness | -6.227 |
entimes | -6.130 |
CENT | -6.106 |
Token | 7 |
Token ID | 22 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
oji | +0.323 |
anus | +0.313 |
ュ | +0.305 |
cair | +0.301 |
azor | +0.290 |
Neg logit contributions | |
lihood | -0.232 |
amounts | -0.227 |
ness | -0.220 |
lin | -0.208 |
entimes | -0.207 |
Token | ] |
Token ID | 60 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
amounts | +0.715 |
lihood | +0.711 |
ness | +0.702 |
lin | +0.642 |
entimes | +0.634 |
Neg logit contributions | |
oji | -1.385 |
anus | -1.384 |
cair | -1.320 |
ュ | -1.304 |
azor | -1.290 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
lihood | +0.436 |
amounts | +0.430 |
ness | +0.421 |
lin | +0.399 |
entimes | +0.397 |
Neg logit contributions | |
oji | -0.426 |
anus | -0.412 |
ュ | -0.397 |
cair | -0.391 |
azor | -0.377 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
oji | +0.317 |
anus | +0.301 |
ュ | +0.293 |
cair | +0.284 |
azor | +0.276 |
Neg logit contributions | |
lihood | -0.386 |
amounts | -0.375 |
entimes | -0.369 |
ness | -0.355 |
lin | -0.353 |
Token | map |
Token ID | 3975 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
oji | +1.233 |
anus | +1.201 |
ュ | +1.163 |
cair | +1.145 |
azor | +1.112 |
Neg logit contributions | |
lihood | -0.918 |
amounts | -0.893 |
ness | -0.868 |
entimes | -0.829 |
CENT | -0.821 |
Token | of |
Token ID | 286 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
lihood | +0.289 |
amounts | +0.283 |
ness | +0.276 |
entimes | +0.261 |
lin | +0.260 |
Neg logit contributions | |
oji | -0.363 |
anus | -0.353 |
ュ | -0.342 |
cair | -0.337 |
azor | -0.327 |
Token | Brigham |
Token ID | 37434 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
lihood | +0.089 |
amounts | +0.087 |
ness | +0.085 |
lin | +0.081 |
entimes | +0.080 |
Neg logit contributions | |
oji | -0.099 |
anus | -0.095 |
ュ | -0.092 |
cair | -0.091 |
azor | -0.088 |
Token | City |
Token ID | 2254 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
oji | +1.337 |
anus | +1.304 |
ュ | +1.238 |
cair | +1.209 |
azor | +1.156 |
Neg logit contributions | |
lihood | -1.734 |
amounts | -1.674 |
ness | -1.643 |
entimes | -1.605 |
CENT | -1.576 |
Token | , |
Token ID | 11 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
oji | +2.675 |
anus | +2.624 |
ュ | +2.514 |
cair | +2.496 |
azor | +2.395 |
Neg logit contributions | |
lihood | -1.995 |
amounts | -1.868 |
ness | -1.859 |
entimes | -1.806 |
CENT | -1.755 |
Token | Utah |
Token ID | 10202 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
oji | +2.557 |
anus | +2.527 |
ュ | +2.389 |
cair | +2.373 |
uitous | +2.294 |
Neg logit contributions | |
lihood | -2.065 |
amounts | -1.974 |
ness | -1.949 |
entimes | -1.871 |
dar | -1.848 |
Token | in |
Token ID | 287 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
oji | +7.575 |
anus | +7.356 |
cair | +7.011 |
ュ | +6.840 |
Curse | +6.710 |
Neg logit contributions | |
lihood | -6.787 |
entimes | -6.117 |
CENT | -5.913 |
ness | -5.897 |
amounts | -5.873 |
Token | 18 |
Token ID | 1248 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
oji | +2.452 |
anus | +2.390 |
ュ | +2.291 |
cair | +2.289 |
uitous | +2.168 |
Neg logit contributions | |
lihood | -2.341 |
amounts | -2.226 |
ness | -2.218 |
entimes | -2.143 |
CENT | -2.099 |
Token | 75 |
Token ID | 2425 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
lihood | +0.048 |
amounts | +0.047 |
ness | +0.045 |
entimes | +0.044 |
lin | +0.043 |
Neg logit contributions | |
oji | -0.061 |
anus | -0.060 |
ュ | -0.058 |
cair | -0.057 |
azor | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
amounts | +1.513 |
lihood | +1.512 |
ness | +1.467 |
lin | +1.375 |
entimes | +1.351 |
Neg logit contributions | |
oji | -2.169 |
anus | -2.105 |
ュ | -2.049 |
cair | -2.014 |
azor | -1.962 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
oji | +0.229 |
anus | +0.220 |
ュ | +0.214 |
cair | +0.210 |
azor | +0.202 |
Neg logit contributions | |
lihood | -0.231 |
amounts | -0.226 |
ness | -0.221 |
entimes | -0.213 |
lin | -0.210 |
Token | , |
Token ID | 11 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
oji | +0.292 |
anus | +0.283 |
ュ | +0.276 |
cair | +0.273 |
azor | +0.264 |
Neg logit contributions | |
lihood | -0.195 |
amounts | -0.189 |
ness | -0.182 |
entimes | -0.173 |
lin | -0.171 |
Token | � |
Token ID | 447 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
oji | +0.270 |
anus | +0.261 |
ュ | +0.254 |
cair | +0.250 |
azor | +0.243 |
Neg logit contributions | |
lihood | -0.199 |
amounts | -0.193 |
ness | -0.189 |
entimes | -0.178 |
lin | -0.177 |
Token | � |
Token ID | 251 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
lihood | +0.492 |
amounts | +0.481 |
ness | +0.471 |
entimes | +0.447 |
lin | +0.447 |
Neg logit contributions | |
oji | -0.528 |
anus | -0.513 |
ュ | -0.496 |
cair | -0.484 |
azor | -0.470 |
Token | said |
Token ID | 531 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
lihood | +0.028 |
amounts | +0.028 |
ness | +0.027 |
lin | +0.026 |
entimes | +0.026 |
Neg logit contributions | |
oji | -0.032 |
anus | -0.031 |
ュ | -0.030 |
cair | -0.030 |
azor | -0.029 |
Token | Mer |
Token ID | 4638 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
lihood | +0.704 |
amounts | +0.697 |
ness | +0.681 |
lin | +0.645 |
entimes | +0.637 |
Neg logit contributions | |
oji | -0.701 |
anus | -0.678 |
ュ | -0.656 |
cair | -0.643 |
azor | -0.621 |
Token | r |
Token ID | 81 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
lihood | +0.789 |
amounts | +0.777 |
ness | +0.763 |
lin | +0.722 |
entimes | +0.719 |
Neg logit contributions | |
oji | -0.821 |
anus | -0.794 |
ュ | -0.770 |
cair | -0.755 |
azor | -0.729 |
Token | ion |
Token ID | 295 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
anus | +6.448 |
oji | +6.231 |
cair | +5.864 |
ife | +5.841 |
azor | +5.722 |
Neg logit contributions | |
lihood | -8.084 |
amounts | -7.438 |
CENT | -7.279 |
entimes | -7.122 |
incidentally | -7.075 |
Token | Stock |
Token ID | 10500 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
oji | +0.824 |
anus | +0.798 |
ュ | +0.770 |
cair | +0.760 |
azor | +0.731 |
Neg logit contributions | |
lihood | -0.813 |
amounts | -0.798 |
ness | -0.780 |
entimes | -0.742 |
lin | -0.742 |
Token | bro |
Token ID | 7957 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
oji | +0.299 |
anus | +0.289 |
ュ | +0.281 |
cair | +0.275 |
azor | +0.266 |
Neg logit contributions | |
lihood | -0.272 |
amounts | -0.269 |
ness | -0.263 |
lin | -0.248 |
entimes | -0.246 |
Token | kers |
Token ID | 15949 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
oji | +0.795 |
anus | +0.769 |
ュ | +0.738 |
cair | +0.720 |
azor | +0.697 |
Neg logit contributions | |
lihood | -0.996 |
amounts | -0.975 |
ness | -0.956 |
entimes | -0.916 |
lin | -0.915 |
Token | chief |
Token ID | 4039 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
oji | +2.578 |
anus | +2.518 |
ュ | +2.423 |
cair | +2.399 |
azor | +2.326 |
Neg logit contributions | |
lihood | -2.257 |
amounts | -2.177 |
ness | -2.106 |
entimes | -2.077 |
lin | -2.022 |
Token | , |
Token ID | 11 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
oji | +1.576 |
anus | +1.533 |
ュ | +1.491 |
cair | +1.469 |
azor | +1.427 |
Neg logit contributions | |
lihood | -1.032 |
amounts | -1.011 |
ness | -0.983 |
lin | -0.920 |
entimes | -0.917 |
Token | in |
Token ID | 287 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
oji | +2.173 |
anus | +2.116 |
ュ | +2.036 |
cair | +2.013 |
uitous | +1.936 |
Neg logit contributions | |
lihood | -1.930 |
amounts | -1.850 |
ness | -1.824 |
entimes | -1.759 |
CENT | -1.722 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
oji | +0.737 |
anus | +0.713 |
ュ | +0.689 |
cair | +0.679 |
azor | +0.653 |
Neg logit contributions | |
lihood | -0.739 |
amounts | -0.711 |
ness | -0.704 |
entimes | -0.681 |
CENT | -0.669 |
Token | Lafayette |
Token ID | 41388 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
lihood | +0.537 |
amounts | +0.527 |
ness | +0.514 |
entimes | +0.488 |
lin | +0.485 |
Neg logit contributions | |
oji | -0.601 |
anus | -0.581 |
ュ | -0.564 |
cair | -0.553 |
azor | -0.535 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
oji | +2.064 |
anus | +2.002 |
ュ | +1.940 |
cair | +1.920 |
azor | +1.863 |
Neg logit contributions | |
lihood | -1.441 |
amounts | -1.385 |
ness | -1.340 |
entimes | -1.287 |
dar | -1.265 |
Token | Louisiana |
Token ID | 13340 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
oji | +0.484 |
anus | +0.466 |
ュ | +0.449 |
cair | +0.441 |
azor | +0.424 |
Neg logit contributions | |
lihood | -0.536 |
amounts | -0.525 |
ness | -0.514 |
entimes | -0.493 |
lin | -0.490 |
Token | theater |
Token ID | 13766 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
oji | +7.163 |
anus | +6.744 |
ュ | +6.597 |
Showdown | +6.408 |
azor | +6.371 |
Neg logit contributions | |
lihood | -6.863 |
amounts | -6.305 |
entimes | -6.192 |
dar | -6.091 |
CENT | -6.061 |
Token | in |
Token ID | 287 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
oji | +4.869 |
anus | +4.809 |
ュ | +4.641 |
cair | +4.583 |
azor | +4.439 |
Neg logit contributions | |
lihood | -4.805 |
amounts | -4.544 |
ness | -4.424 |
entimes | -4.331 |
CENT | -4.238 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
oji | +1.117 |
anus | +1.074 |
ュ | +1.044 |
cair | +1.027 |
azor | +0.989 |
Neg logit contributions | |
lihood | -1.100 |
amounts | -1.043 |
ness | -1.035 |
entimes | -1.015 |
CENT | -1.000 |
Token | . |
Token ID | 13 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
amounts | +0.674 |
lihood | +0.665 |
ness | +0.654 |
lin | +0.604 |
entimes | +0.599 |
Neg logit contributions | |
oji | -1.142 |
anus | -1.113 |
ュ | -1.081 |
cair | -1.067 |
azor | -1.035 |
Token | Though |
Token ID | 7486 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
oji | +0.188 |
anus | +0.182 |
ュ | +0.177 |
cair | +0.172 |
azor | +0.167 |
Neg logit contributions | |
lihood | -0.198 |
amounts | -0.195 |
ness | -0.190 |
entimes | -0.182 |
lin | -0.182 |
Token | trading |
Token ID | 7313 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
lihood | +0.554 |
amounts | +0.537 |
ness | +0.525 |
entimes | +0.499 |
lin | +0.494 |
Neg logit contributions | |
oji | -0.741 |
anus | -0.723 |
ュ | -0.701 |
cair | -0.688 |
azor | -0.671 |
Token | provision |
Token ID | 8287 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
oji | +1.467 |
anus | +1.432 |
ュ | +1.378 |
cair | +1.350 |
azor | +1.326 |
Neg logit contributions | |
lihood | -1.234 |
amounts | -1.193 |
ness | -1.161 |
entimes | -1.141 |
CENT | -1.113 |
Token | they |
Token ID | 484 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
lihood | +0.774 |
amounts | +0.761 |
ness | +0.743 |
lin | +0.701 |
entimes | +0.698 |
Neg logit contributions | |
oji | -0.925 |
anus | -0.897 |
ュ | -0.870 |
cair | -0.856 |
azor | -0.828 |
Token | thought |
Token ID | 1807 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
lihood | +1.349 |
amounts | +1.320 |
ness | +1.288 |
lin | +1.211 |
entimes | +1.210 |
Neg logit contributions | |
oji | -1.778 |
anus | -1.724 |
ュ | -1.671 |
cair | -1.652 |
azor | -1.597 |
Token | was |
Token ID | 373 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
lihood | +2.054 |
amounts | +2.043 |
ness | +1.976 |
lin | +1.835 |
entimes | +1.810 |
Neg logit contributions | |
oji | -3.334 |
anus | -3.255 |
ュ | -3.172 |
cair | -3.124 |
azor | -3.026 |
Token | too |
Token ID | 1165 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
lihood | +0.148 |
amounts | +0.145 |
ness | +0.142 |
entimes | +0.134 |
lin | +0.134 |
Neg logit contributions | |
oji | -0.171 |
anus | -0.165 |
ュ | -0.159 |
cair | -0.157 |
azor | -0.153 |
Token | harsh |
Token ID | 11859 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
oji | +7.241 |
anus | +6.497 |
ammy | +6.298 |
Curse | +6.281 |
uitous | +6.280 |
Neg logit contributions | |
lihood | -6.685 |
dar | -6.238 |
CENT | -6.222 |
entimes | -6.138 |
amounts | -6.081 |
Token | on |
Token ID | 319 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
oji | +0.940 |
anus | +0.909 |
ュ | +0.885 |
cair | +0.871 |
azor | +0.846 |
Neg logit contributions | |
lihood | -0.688 |
amounts | -0.668 |
ness | -0.648 |
entimes | -0.617 |
lin | -0.613 |
Token | banks |
Token ID | 6341 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
lihood | +0.581 |
amounts | +0.565 |
ness | +0.554 |
entimes | +0.523 |
lin | +0.521 |
Neg logit contributions | |
oji | -0.764 |
anus | -0.741 |
ュ | -0.720 |
cair | -0.708 |
azor | -0.689 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
amounts | +1.510 |
lihood | +1.502 |
ness | +1.461 |
lin | +1.362 |
entimes | +1.348 |
Neg logit contributions | |
oji | -2.262 |
anus | -2.211 |
ュ | -2.146 |
cair | -2.115 |
azor | -2.044 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
oji | +0.585 |
anus | +0.565 |
ュ | +0.549 |
cair | +0.536 |
azor | +0.520 |
Neg logit contributions | |
lihood | -0.595 |
amounts | -0.586 |
ness | -0.572 |
entimes | -0.548 |
lin | -0.547 |
Token | California |
Token ID | 3442 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
lihood | +0.058 |
amounts | +0.056 |
ness | +0.055 |
entimes | +0.053 |
lin | +0.052 |
Neg logit contributions | |
oji | -0.060 |
anus | -0.059 |
ュ | -0.056 |
cair | -0.056 |
azor | -0.054 |
Token | � |
Token ID | 447 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
oji | +3.932 |
anus | +3.846 |
ュ | +3.691 |
cair | +3.647 |
hetics | +3.518 |
Neg logit contributions | |
lihood | -3.199 |
amounts | -3.002 |
ness | -2.957 |
entimes | -2.895 |
CENT | -2.818 |
Token | � |
Token ID | 247 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
oji | +2.590 |
anus | +2.518 |
ュ | +2.435 |
cair | +2.388 |
azor | +2.319 |
Neg logit contributions | |
lihood | -2.310 |
amounts | -2.260 |
ness | -2.209 |
lin | -2.090 |
entimes | -2.085 |
Token | s |
Token ID | 82 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
lihood | +0.020 |
amounts | +0.020 |
ness | +0.019 |
entimes | +0.018 |
lin | +0.018 |
Neg logit contributions | |
oji | -0.035 |
anus | -0.034 |
ュ | -0.033 |
cair | -0.033 |
azor | -0.032 |
Token | Sierra |
Token ID | 17559 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
lihood | +0.668 |
amounts | +0.656 |
ness | +0.643 |
entimes | +0.611 |
lin | +0.610 |
Neg logit contributions | |
oji | -0.630 |
anus | -0.609 |
ュ | -0.588 |
cair | -0.578 |
azor | -0.557 |
Token | Nevada |
Token ID | 12087 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
oji | +0.999 |
anus | +0.971 |
ュ | +0.937 |
cair | +0.921 |
azor | +0.887 |
Neg logit contributions | |
lihood | -0.963 |
amounts | -0.945 |
ness | -0.923 |
entimes | -0.890 |
lin | -0.875 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
oji | +7.029 |
anus | +6.918 |
cair | +6.405 |
ュ | +6.397 |
hetics | +6.208 |
Neg logit contributions | |
lihood | -6.947 |
entimes | -6.560 |
amounts | -6.534 |
ritical | -6.321 |
CENT | -6.315 |
Token | Dan |
Token ID | 6035 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
oji | +1.476 |
anus | +1.421 |
ュ | +1.382 |
cair | +1.349 |
azor | +1.300 |
Neg logit contributions | |
lihood | -1.632 |
amounts | -1.622 |
ness | -1.570 |
entimes | -1.556 |
lin | -1.508 |
Token | K |
Token ID | 509 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
lihood | +0.788 |
amounts | +0.776 |
ness | +0.762 |
lin | +0.721 |
entimes | +0.716 |
Neg logit contributions | |
oji | -0.807 |
anus | -0.780 |
ュ | -0.756 |
cair | -0.742 |
azor | -0.715 |
Token | oe |
Token ID | 2577 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
lihood | +2.807 |
ness | +2.772 |
amounts | +2.761 |
lin | +2.603 |
dar | +2.566 |
Neg logit contributions | |
oji | -2.455 |
anus | -2.376 |
ュ | -2.349 |
cair | -2.267 |
hetics | -2.153 |
Token | ppel |
Token ID | 46357 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
oji | +0.236 |
anus | +0.226 |
ュ | +0.215 |
cair | +0.212 |
azor | +0.201 |
Neg logit contributions | |
lihood | -0.376 |
amounts | -0.372 |
ness | -0.364 |
entimes | -0.350 |
lin | -0.349 |
Token | S |
Token ID | 311 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
lihood | +0.065 |
amounts | +0.064 |
ness | +0.063 |
entimes | +0.059 |
lin | +0.059 |
Neg logit contributions | |
oji | -0.072 |
anus | -0.070 |
ュ | -0.067 |
cair | -0.066 |
azor | -0.064 |
Token | art |
Token ID | 433 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
lihood | +3.896 |
ness | +3.862 |
amounts | +3.845 |
dar | +3.654 |
lin | +3.608 |
Neg logit contributions | |
oji | -3.134 |
anus | -3.047 |
ュ | -3.018 |
cair | -2.925 |
uitous | -2.759 |
Token | aq |
Token ID | 30188 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
oji | +1.731 |
anus | +1.667 |
ュ | +1.544 |
cair | +1.540 |
azor | +1.492 |
Neg logit contributions | |
lihood | -2.077 |
amounts | -2.053 |
ness | -1.987 |
CENT | -1.920 |
lin | -1.919 |
Token | ( |
Token ID | 357 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
oji | +1.202 |
anus | +1.163 |
ュ | +1.112 |
cair | +1.099 |
azor | +1.068 |
Neg logit contributions | |
lihood | -1.081 |
amounts | -1.050 |
ness | -1.023 |
entimes | -0.972 |
CENT | -0.971 |
Token | mer |
Token ID | 647 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
lihood | +0.492 |
amounts | +0.483 |
ness | +0.472 |
lin | +0.447 |
entimes | +0.446 |
Neg logit contributions | |
oji | -0.539 |
anus | -0.522 |
ュ | -0.505 |
cair | -0.497 |
azor | -0.480 |
Token | ch |
Token ID | 354 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
lihood | +1.285 |
amounts | +1.263 |
ness | +1.237 |
lin | +1.171 |
entimes | +1.166 |
Neg logit contributions | |
oji | -1.376 |
anus | -1.332 |
ュ | -1.289 |
cair | -1.266 |
azor | -1.223 |
Token | ants |
Token ID | 1187 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
oji | +6.866 |
anus | +6.634 |
ュ | +6.415 |
uitous | +6.171 |
itect | +6.131 |
Neg logit contributions | |
lihood | -7.104 |
amounts | -6.538 |
CENT | -6.393 |
ness | -6.290 |
entimes | -6.276 |
Token | of |
Token ID | 286 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
oji | +0.692 |
anus | +0.673 |
ュ | +0.654 |
cair | +0.644 |
azor | +0.625 |
Neg logit contributions | |
lihood | -0.492 |
amounts | -0.480 |
ness | -0.465 |
entimes | -0.440 |
lin | -0.439 |
Token | western |
Token ID | 8830 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
oji | +0.874 |
anus | +0.845 |
ュ | +0.817 |
cair | +0.802 |
azor | +0.774 |
Neg logit contributions | |
lihood | -0.852 |
amounts | -0.829 |
ness | -0.811 |
entimes | -0.778 |
CENT | -0.773 |
Token | Asian |
Token ID | 7740 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
oji | +1.020 |
anus | +0.979 |
ュ | +0.955 |
cair | +0.942 |
azor | +0.906 |
Neg logit contributions | |
lihood | -0.876 |
amounts | -0.847 |
ness | -0.816 |
entimes | -0.793 |
CENT | -0.790 |
Token | or |
Token ID | 393 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
lihood | +1.134 |
amounts | +1.116 |
ness | +1.091 |
lin | +1.031 |
entimes | +1.027 |
Neg logit contributions | |
oji | -1.294 |
anus | -1.254 |
ュ | -1.215 |
cair | -1.195 |
azor | -1.155 |
Token | for |
Token ID | 329 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
lihood | +0.839 |
amounts | +0.825 |
ness | +0.805 |
lin | +0.759 |
entimes | +0.756 |
Neg logit contributions | |
oji | -1.041 |
anus | -1.010 |
ュ | -0.979 |
cair | -0.964 |
azor | -0.933 |
Token | whom |
Token ID | 4150 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
lihood | +1.300 |
amounts | +1.280 |
ness | +1.251 |
lin | +1.177 |
entimes | +1.166 |
Neg logit contributions | |
oji | -1.637 |
anus | -1.588 |
ュ | -1.543 |
cair | -1.519 |
azor | -1.469 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
lihood | +4.829 |
amounts | +4.795 |
ness | +4.706 |
lin | +4.534 |
entimes | +4.252 |
Neg logit contributions | |
oji | -5.404 |
anus | -5.282 |
ュ | -5.106 |
cair | -5.033 |
azor | -4.807 |
Token | world |
Token ID | 995 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
oji | +1.148 |
anus | +1.111 |
ュ | +1.078 |
cair | +1.055 |
azor | +1.029 |
Neg logit contributions | |
lihood | -0.933 |
amounts | -0.902 |
ness | -0.882 |
entimes | -0.851 |
CENT | -0.846 |
Token | was |
Token ID | 373 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
lihood | +1.043 |
amounts | +1.022 |
ness | +0.994 |
lin | +0.929 |
entimes | +0.925 |
Neg logit contributions | |
oji | -1.620 |
anus | -1.576 |
ュ | -1.532 |
cair | -1.511 |
azor | -1.467 |
Token | too |
Token ID | 1165 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
oji | +2.061 |
anus | +2.017 |
ュ | +1.953 |
cair | +1.914 |
azor | +1.866 |
Neg logit contributions | |
lihood | -1.718 |
amounts | -1.659 |
ness | -1.601 |
entimes | -1.557 |
CENT | -1.544 |
Token | full |
Token ID | 1336 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
oji | +7.425 |
anus | +6.959 |
ュ | +6.621 |
cair | +6.555 |
azor | +6.527 |
Neg logit contributions | |
lihood | -5.732 |
amounts | -5.441 |
dar | -5.337 |
CENT | -5.331 |
entimes | -5.195 |
Token | , |
Token ID | 11 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
oji | +1.543 |
anus | +1.495 |
ュ | +1.451 |
cair | +1.420 |
azor | +1.373 |
Neg logit contributions | |
lihood | -1.514 |
amounts | -1.483 |
ness | -1.440 |
entimes | -1.379 |
lin | -1.376 |
Token | and |
Token ID | 290 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
oji | +1.018 |
anus | +0.988 |
ュ | +0.958 |
cair | +0.938 |
azor | +0.913 |
Neg logit contributions | |
lihood | -0.827 |
amounts | -0.799 |
ness | -0.779 |
entimes | -0.743 |
CENT | -0.735 |
Token | Gl |
Token ID | 2671 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
lihood | +1.161 |
amounts | +1.139 |
ness | +1.112 |
lin | +1.049 |
entimes | +1.048 |
Neg logit contributions | |
oji | -1.427 |
anus | -1.382 |
ュ | -1.340 |
cair | -1.320 |
azor | -1.278 |
Token | ü |
Token ID | 9116 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
oji | +0.601 |
anus | +0.568 |
cair | +0.539 |
azor | +0.521 |
hetics | +0.520 |
Neg logit contributions | |
lihood | -0.861 |
amounts | -0.844 |
ness | -0.806 |
CENT | -0.801 |
lin | -0.794 |
Token | liberal |
Token ID | 7270 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
oji | +0.824 |
anus | +0.801 |
ュ | +0.775 |
cair | +0.764 |
azor | +0.740 |
Neg logit contributions | |
lihood | -0.655 |
amounts | -0.637 |
ness | -0.623 |
entimes | -0.588 |
lin | -0.586 |
Token | towns |
Token ID | 11684 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
amounts | +1.659 |
lihood | +1.655 |
ness | +1.618 |
lin | +1.524 |
entimes | +1.511 |
Neg logit contributions | |
oji | -1.891 |
anus | -1.834 |
ュ | -1.773 |
cair | -1.738 |
azor | -1.686 |
Token | like |
Token ID | 588 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
lihood | +0.226 |
amounts | +0.222 |
ness | +0.217 |
lin | +0.203 |
entimes | +0.203 |
Neg logit contributions | |
oji | -0.313 |
anus | -0.304 |
ュ | -0.296 |
cair | -0.291 |
azor | -0.282 |
Token | Madison |
Token ID | 14909 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
lihood | +1.849 |
amounts | +1.832 |
ness | +1.788 |
lin | +1.698 |
entimes | +1.664 |
Neg logit contributions | |
oji | -1.839 |
anus | -1.774 |
ュ | -1.717 |
cair | -1.676 |
azor | -1.625 |
Token | , |
Token ID | 11 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
oji | +3.625 |
anus | +3.536 |
ュ | +3.428 |
cair | +3.391 |
azor | +3.281 |
Neg logit contributions | |
lihood | -2.616 |
amounts | -2.515 |
ness | -2.462 |
entimes | -2.350 |
lin | -2.332 |
Token | Wisconsin |
Token ID | 9279 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
oji | +1.574 |
anus | +1.515 |
ュ | +1.470 |
cair | +1.429 |
azor | +1.390 |
Neg logit contributions | |
lihood | -1.593 |
amounts | -1.540 |
ness | -1.514 |
entimes | -1.490 |
CENT | -1.450 |
Token | , |
Token ID | 11 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
oji | +7.555 |
anus | +7.321 |
ュ | +7.083 |
cair | +7.068 |
azor | +6.887 |
Neg logit contributions | |
lihood | -6.296 |
amounts | -5.882 |
ness | -5.721 |
CENT | -5.626 |
entimes | -5.549 |
Token | and |
Token ID | 290 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
oji | +2.374 |
anus | +2.309 |
ュ | +2.222 |
cair | +2.211 |
azor | +2.138 |
Neg logit contributions | |
lihood | -2.110 |
amounts | -2.019 |
ness | -1.997 |
entimes | -1.922 |
CENT | -1.879 |
Token | Iowa |
Token ID | 9406 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
lihood | +0.306 |
amounts | +0.301 |
ness | +0.294 |
lin | +0.279 |
entimes | +0.279 |
Neg logit contributions | |
oji | -0.306 |
anus | -0.296 |
ュ | -0.286 |
cair | -0.281 |
azor | -0.271 |
Token | City |
Token ID | 2254 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
oji | +3.539 |
anus | +3.443 |
ュ | +3.329 |
cair | +3.315 |
azor | +3.187 |
Neg logit contributions | |
lihood | -2.717 |
amounts | -2.612 |
ness | -2.556 |
lin | -2.428 |
entimes | -2.419 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
amounts | +0.492 |
lihood | +0.492 |
ness | +0.474 |
lin | +0.436 |
entimes | +0.431 |
Neg logit contributions | |
oji | -0.878 |
anus | -0.855 |
ュ | -0.832 |
cair | -0.813 |
azor | -0.797 |
Token | year |
Token ID | 1941 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
lihood | +1.581 |
amounts | +1.537 |
ness | +1.467 |
lin | +1.403 |
entimes | +1.398 |
Neg logit contributions | |
oji | -2.446 |
anus | -2.376 |
ュ | -2.296 |
cair | -2.279 |
azor | -2.209 |
Token | - |
Token ID | 12 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
lihood | +1.600 |
amounts | +1.586 |
ness | +1.578 |
lin | +1.471 |
entimes | +1.425 |
Neg logit contributions | |
oji | -3.078 |
anus | -3.044 |
cair | -2.912 |
ュ | -2.887 |
azor | -2.838 |
Token | old |
Token ID | 727 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
lihood | +1.100 |
amounts | +1.077 |
ness | +1.021 |
entimes | +1.012 |
lin | +1.007 |
Neg logit contributions | |
oji | -0.982 |
anus | -0.950 |
ュ | -0.901 |
cair | -0.898 |
azor | -0.869 |
Token | University |
Token ID | 2059 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
lihood | +3.928 |
amounts | +3.928 |
ness | +3.886 |
lin | +3.708 |
incidentally | +3.583 |
Neg logit contributions | |
oji | -4.039 |
anus | -3.935 |
ュ | -3.831 |
cair | -3.766 |
azor | -3.633 |
Token | of |
Token ID | 286 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
oji | +3.088 |
anus | +2.972 |
ュ | +2.858 |
cair | +2.823 |
azor | +2.717 |
Neg logit contributions | |
lihood | -3.076 |
amounts | -3.048 |
ness | -2.998 |
lin | -2.819 |
entimes | -2.791 |
Token | Virginia |
Token ID | 6025 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
oji | +3.058 |
anus | +2.927 |
ュ | +2.871 |
cair | +2.748 |
hetics | +2.702 |
Neg logit contributions | |
lihood | -3.264 |
amounts | -3.188 |
entimes | -3.104 |
ness | -3.051 |
CENT | -3.007 |
Token | undergrad |
Token ID | 43485 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
oji | +5.082 |
anus | +4.969 |
ュ | +4.532 |
cair | +4.462 |
azor | +4.333 |
Neg logit contributions | |
lihood | -8.376 |
amounts | -7.971 |
entimes | -7.918 |
CENT | -7.723 |
ness | -7.718 |
Token | who |
Token ID | 508 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
lihood | +0.127 |
amounts | +0.126 |
ness | +0.124 |
lin | +0.115 |
entimes | +0.114 |
Neg logit contributions | |
oji | -0.205 |
anus | -0.200 |
ュ | -0.196 |
cair | -0.192 |
azor | -0.186 |
Token | served |
Token ID | 4983 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
amounts | +1.756 |
lihood | +1.748 |
ness | +1.691 |
lin | +1.586 |
entimes | +1.540 |
Neg logit contributions | |
oji | -2.869 |
anus | -2.814 |
ュ | -2.743 |
cair | -2.697 |
azor | -2.633 |
Token | 18 |
Token ID | 1248 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
oji | +1.331 |
anus | +1.287 |
ュ | +1.245 |
cair | +1.228 |
azor | +1.182 |
Neg logit contributions | |
lihood | -1.167 |
amounts | -1.136 |
ness | -1.117 |
entimes | -1.059 |
lin | -1.052 |
Token | months |
Token ID | 1933 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
oji | +1.200 |
anus | +1.151 |
ュ | +1.112 |
cair | +1.097 |
azor | +1.048 |
Neg logit contributions | |
lihood | -1.277 |
amounts | -1.240 |
ness | -1.221 |
entimes | -1.161 |
lin | -1.160 |
Token | ). |
Token ID | 737 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
oji | +0.041 |
anus | +0.040 |
ュ | +0.038 |
cair | +0.038 |
azor | +0.037 |
Neg logit contributions | |
lihood | -0.034 |
amounts | -0.033 |
ness | -0.032 |
entimes | -0.031 |
lin | -0.031 |
Token | New |
Token ID | 968 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
oji | +0.837 |
anus | +0.809 |
ュ | +0.781 |
cair | +0.767 |
azor | +0.740 |
Neg logit contributions | |
lihood | -0.842 |
amounts | -0.824 |
ness | -0.807 |
entimes | -0.779 |
lin | -0.766 |
Token | York |
Token ID | 1971 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
oji | +1.450 |
anus | +1.412 |
ュ | +1.374 |
cair | +1.362 |
azor | +1.311 |
Neg logit contributions | |
lihood | -1.043 |
amounts | -1.010 |
ness | -0.976 |
entimes | -0.934 |
lin | -0.921 |
Token | , |
Token ID | 11 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
oji | +3.211 |
anus | +3.130 |
ュ | +3.018 |
cair | +2.959 |
azor | +2.866 |
Neg logit contributions | |
lihood | -2.827 |
amounts | -2.721 |
ness | -2.668 |
entimes | -2.604 |
lin | -2.550 |
Token | NY |
Token ID | 6645 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
oji | +2.340 |
anus | +2.261 |
ュ | +2.182 |
cair | +2.143 |
azor | +2.087 |
Neg logit contributions | |
lihood | -1.924 |
amounts | -1.843 |
ness | -1.823 |
entimes | -1.767 |
lin | -1.709 |
Token | : |
Token ID | 1058 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
oji | +3.523 |
anus | +3.424 |
ュ | +3.319 |
cair | +3.238 |
azor | +3.154 |
Neg logit contributions | |
lihood | -3.458 |
amounts | -3.340 |
ness | -3.276 |
entimes | -3.153 |
lin | -3.109 |
Token | Worth |
Token ID | 22301 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
oji | +5.719 |
ュ | +5.431 |
anus | +5.418 |
Curse | +5.316 |
Knife | +5.291 |
Neg logit contributions | |
lihood | -7.392 |
entimes | -7.336 |
ness | -7.056 |
ritical | -7.046 |
amounts | -6.914 |
Token | Publishers |
Token ID | 43403 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
oji | +0.759 |
anus | +0.734 |
ュ | +0.708 |
cair | +0.695 |
azor | +0.671 |
Neg logit contributions | |
lihood | -0.797 |
amounts | -0.784 |
ness | -0.766 |
entimes | -0.731 |
lin | -0.731 |
Token | . |
Token ID | 764 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
oji | +2.909 |
anus | +2.799 |
ュ | +2.714 |
cair | +2.655 |
azor | +2.580 |
Neg logit contributions | |
lihood | -2.998 |
amounts | -2.936 |
ness | -2.855 |
entimes | -2.767 |
lin | -2.739 |
Token |
|
Token ID | 198 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
oji | +1.846 |
anus | +1.796 |
ュ | +1.725 |
cair | +1.720 |
azor | +1.643 |
Neg logit contributions | |
lihood | -1.545 |
amounts | -1.539 |
ness | -1.501 |
lin | -1.415 |
dar | -1.385 |
Token |
|
Token ID | 198 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
oji | +1.565 |
anus | +1.455 |
ュ | +1.420 |
cair | +1.367 |
Amazing | +1.352 |
Neg logit contributions | |
lihood | -2.188 |
entimes | -2.131 |
amounts | -2.111 |
lin | -2.003 |
ritical | -1.999 |
Token | laid |
Token ID | 8104 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
lihood | +1.154 |
amounts | +1.152 |
ness | +1.121 |
lin | +1.048 |
entimes | +1.042 |
Neg logit contributions | |
oji | -1.590 |
anus | -1.549 |
ュ | -1.496 |
cair | -1.473 |
azor | -1.430 |
Token | out |
Token ID | 503 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
oji | +0.381 |
anus | +0.371 |
ュ | +0.360 |
cair | +0.355 |
azor | +0.345 |
Neg logit contributions | |
lihood | -0.271 |
amounts | -0.264 |
ness | -0.258 |
lin | -0.242 |
entimes | -0.242 |
Token | a |
Token ID | 257 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
lihood | +0.094 |
amounts | +0.093 |
ness | +0.091 |
lin | +0.086 |
entimes | +0.085 |
Neg logit contributions | |
oji | -0.094 |
anus | -0.091 |
ュ | -0.087 |
cair | -0.086 |
azor | -0.083 |
Token | number |
Token ID | 1271 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
lihood | +0.744 |
amounts | +0.731 |
ness | +0.714 |
lin | +0.673 |
entimes | +0.673 |
Neg logit contributions | |
oji | -0.882 |
anus | -0.856 |
ュ | -0.829 |
cair | -0.816 |
azor | -0.790 |
Token | of |
Token ID | 286 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
oji | +0.835 |
anus | +0.805 |
ュ | +0.765 |
cair | +0.759 |
azor | +0.733 |
Neg logit contributions | |
amounts | -0.749 |
lihood | -0.738 |
ness | -0.727 |
lin | -0.689 |
entimes | -0.668 |
Token | reasons |
Token ID | 3840 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
oji | +2.293 |
anus | +2.209 |
ュ | +2.153 |
cair | +2.108 |
azor | +2.040 |
Neg logit contributions | |
lihood | -2.452 |
amounts | -2.343 |
ness | -2.321 |
entimes | -2.242 |
CENT | -2.220 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
oji | +5.702 |
ュ | +5.290 |
anus | +5.258 |
Curse | +4.959 |
cair | +4.958 |
Neg logit contributions | |
lihood | -7.423 |
entimes | -7.091 |
amounts | -6.973 |
dar | -6.852 |
ness | -6.837 |
Token | distrust |
Token ID | 30086 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
oji | +3.691 |
anus | +3.530 |
ュ | +3.468 |
cair | +3.424 |
uitous | +3.294 |
Neg logit contributions | |
lihood | -2.779 |
amounts | -2.664 |
ness | -2.568 |
entimes | -2.513 |
CENT | -2.477 |
Token | the |
Token ID | 262 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
oji | +2.100 |
anus | +2.035 |
ュ | +1.981 |
cair | +1.945 |
azor | +1.874 |
Neg logit contributions | |
lihood | -1.927 |
amounts | -1.869 |
ness | -1.828 |
entimes | -1.754 |
lin | -1.743 |
Token | Federal |
Token ID | 5618 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
oji | +1.113 |
anus | +1.082 |
ュ | +1.049 |
cair | +1.030 |
azor | +0.991 |
Neg logit contributions | |
lihood | -0.877 |
amounts | -0.843 |
ness | -0.830 |
entimes | -0.790 |
lin | -0.780 |
Token | Bureau |
Token ID | 9840 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
lihood | +0.587 |
amounts | +0.583 |
ness | +0.573 |
lin | +0.546 |
entimes | +0.543 |
Neg logit contributions | |
oji | -0.450 |
anus | -0.432 |
ュ | -0.413 |
cair | -0.407 |
azor | -0.391 |
Token | mentioned |
Token ID | 4750 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
lihood | +0.065 |
amounts | +0.063 |
ness | +0.061 |
CENT | +0.058 |
entimes | +0.058 |
Neg logit contributions | |
oji | -0.077 |
anus | -0.074 |
ュ | -0.072 |
cair | -0.071 |
azor | -0.068 |
Token | other |
Token ID | 584 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
oji | +2.493 |
anus | +2.421 |
ュ | +2.354 |
cair | +2.288 |
azor | +2.227 |
Neg logit contributions | |
lihood | -2.542 |
amounts | -2.481 |
ness | -2.437 |
entimes | -2.345 |
CENT | -2.336 |
Token | examples |
Token ID | 6096 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
oji | +4.764 |
anus | +4.528 |
ュ | +4.469 |
cair | +4.304 |
azor | +4.250 |
Neg logit contributions | |
lihood | -4.787 |
amounts | -4.447 |
ness | -4.343 |
CENT | -4.331 |
entimes | -4.294 |
Token | of |
Token ID | 286 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
oji | +3.643 |
anus | +3.519 |
ュ | +3.450 |
cair | +3.306 |
uitous | +3.279 |
Neg logit contributions | |
lihood | -3.945 |
amounts | -3.777 |
ness | -3.732 |
entimes | -3.639 |
dar | -3.524 |
Token | FBI |
Token ID | 5349 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
oji | +2.342 |
anus | +2.261 |
ュ | +2.187 |
cair | +2.139 |
uitous | +2.096 |
Neg logit contributions | |
lihood | -2.120 |
amounts | -2.043 |
ness | -2.007 |
entimes | -1.919 |
CENT | -1.900 |
Token | incompetence |
Token ID | 39674 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
lihood | +0.533 |
amounts | +0.523 |
ness | +0.510 |
entimes | +0.485 |
lin | +0.485 |
Neg logit contributions | |
oji | -0.540 |
anus | -0.522 |
ュ | -0.504 |
cair | -0.495 |
azor | -0.479 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
oji | +6.875 |
anus | +6.661 |
ュ | +6.396 |
uitous | +6.251 |
azor | +6.203 |
Neg logit contributions | |
lihood | -6.216 |
amounts | -5.698 |
CENT | -5.538 |
entimes | -5.533 |
dar | -5.503 |
Token | including |
Token ID | 1390 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
oji | +0.863 |
anus | +0.836 |
ュ | +0.807 |
cair | +0.791 |
azor | +0.769 |
Neg logit contributions | |
lihood | -0.832 |
amounts | -0.810 |
ness | -0.796 |
entimes | -0.757 |
lin | -0.752 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
oji | +0.222 |
anus | +0.215 |
ュ | +0.209 |
cair | +0.205 |
azor | +0.198 |
Neg logit contributions | |
lihood | -0.199 |
amounts | -0.195 |
ness | -0.191 |
lin | -0.181 |
entimes | -0.180 |
Token | investigation |
Token ID | 3645 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
oji | +0.049 |
anus | +0.048 |
ュ | +0.046 |
cair | +0.046 |
azor | +0.044 |
Neg logit contributions | |
lihood | -0.039 |
amounts | -0.038 |
ness | -0.037 |
entimes | -0.035 |
lin | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
lihood | +0.792 |
amounts | +0.783 |
ness | +0.762 |
lin | +0.708 |
entimes | +0.699 |
Neg logit contributions | |
oji | -1.307 |
anus | -1.270 |
ュ | -1.237 |
cair | -1.223 |
azor | -1.184 |
Token | after |
Token ID | 706 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
lihood | +0.557 |
amounts | +0.548 |
ness | +0.534 |
lin | +0.502 |
entimes | +0.500 |
Neg logit contributions | |
oji | -0.742 |
anus | -0.721 |
ュ | -0.700 |
cair | -0.690 |
azor | -0.668 |
Token | being |
Token ID | 852 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
oji | +0.890 |
anus | +0.867 |
ュ | +0.836 |
cair | +0.825 |
azor | +0.803 |
Neg logit contributions | |
lihood | -0.633 |
amounts | -0.617 |
ness | -0.604 |
entimes | -0.573 |
CENT | -0.568 |
Token | shot |
Token ID | 2823 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
lihood | +0.025 |
amounts | +0.025 |
ness | +0.024 |
entimes | +0.023 |
CENT | +0.022 |
Neg logit contributions | |
oji | -0.035 |
anus | -0.034 |
ュ | -0.033 |
cair | -0.033 |
azor | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
oji | +0.378 |
anus | +0.367 |
ュ | +0.356 |
cair | +0.350 |
azor | +0.341 |
Neg logit contributions | |
lihood | -0.303 |
amounts | -0.295 |
ness | -0.288 |
entimes | -0.272 |
lin | -0.272 |
Token | were |
Token ID | 547 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
lihood | +0.152 |
amounts | +0.148 |
ness | +0.144 |
entimes | +0.134 |
lin | +0.134 |
Neg logit contributions | |
oji | -0.237 |
anus | -0.231 |
ュ | -0.224 |
cair | -0.220 |
azor | -0.214 |
Token | expected |
Token ID | 2938 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
lihood | +0.742 |
amounts | +0.725 |
ness | +0.707 |
entimes | +0.663 |
lin | +0.661 |
Neg logit contributions | |
oji | -1.067 |
anus | -1.038 |
ュ | -1.008 |
cair | -0.991 |
azor | -0.963 |
Token | to |
Token ID | 284 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
amounts | +2.937 |
ness | +2.884 |
lihood | +2.779 |
lin | +2.483 |
incidentally | +2.433 |
Neg logit contributions | |
oji | -7.571 |
anus | -7.488 |
cair | -7.354 |
ュ | -7.200 |
itect | -7.049 |
Token | survive |
Token ID | 7866 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
lihood | +1.881 |
amounts | +1.862 |
ness | +1.813 |
lin | +1.680 |
entimes | +1.660 |
Neg logit contributions | |
oji | -3.195 |
anus | -3.121 |
ュ | -3.043 |
cair | -3.004 |
azor | -2.918 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
lihood | +0.605 |
amounts | +0.593 |
ness | +0.578 |
lin | +0.541 |
entimes | +0.539 |
Neg logit contributions | |
oji | -0.882 |
anus | -0.858 |
ュ | -0.834 |
cair | -0.821 |
azor | -0.797 |
Token | Chief |
Token ID | 5953 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
oji | +0.357 |
anus | +0.347 |
ュ | +0.334 |
cair | +0.330 |
azor | +0.319 |
Neg logit contributions | |
lihood | -0.301 |
amounts | -0.291 |
ness | -0.285 |
entimes | -0.271 |
lin | -0.269 |
Token | Deputy |
Token ID | 15110 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
lihood | +2.126 |
amounts | +2.121 |
ness | +2.099 |
lin | +1.955 |
dar | +1.927 |
Neg logit contributions | |
oji | -2.296 |
anus | -2.212 |
ュ | -2.138 |
cair | -2.102 |
azor | -2.022 |
Token | attack |
Token ID | 1368 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
oji | +1.521 |
anus | +1.474 |
ュ | +1.428 |
cair | +1.412 |
azor | +1.372 |
Neg logit contributions | |
lihood | -1.324 |
amounts | -1.275 |
ness | -1.252 |
entimes | -1.201 |
CENT | -1.189 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
oji | +1.814 |
anus | +1.739 |
ュ | +1.685 |
cair | +1.659 |
azor | +1.632 |
Neg logit contributions | |
lihood | -1.325 |
amounts | -1.279 |
ness | -1.240 |
entimes | -1.192 |
CENT | -1.180 |
Token | meaning |
Token ID | 3616 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
oji | +0.682 |
anus | +0.663 |
ュ | +0.642 |
cair | +0.630 |
azor | +0.614 |
Neg logit contributions | |
lihood | -0.527 |
amounts | -0.511 |
ness | -0.501 |
entimes | -0.472 |
lin | -0.469 |
Token | he |
Token ID | 339 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
oji | +0.291 |
anus | +0.282 |
ュ | +0.274 |
cair | +0.268 |
azor | +0.261 |
Neg logit contributions | |
lihood | -0.232 |
amounts | -0.227 |
ness | -0.221 |
lin | -0.209 |
entimes | -0.209 |
Token | can |
Token ID | 460 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
oji | +1.702 |
anus | +1.648 |
ュ | +1.617 |
cair | +1.577 |
azor | +1.545 |
Neg logit contributions | |
lihood | -1.163 |
amounts | -1.101 |
ness | -1.086 |
CENT | -1.023 |
entimes | -1.015 |
Token | lock |
Token ID | 5793 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
lihood | +0.921 |
amounts | +0.900 |
ness | +0.875 |
entimes | +0.817 |
lin | +0.817 |
Neg logit contributions | |
oji | -1.348 |
anus | -1.309 |
ュ | -1.277 |
cair | -1.254 |
azor | -1.218 |
Token | the |
Token ID | 262 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
amounts | +4.522 |
ness | +4.402 |
lihood | +4.345 |
lin | +4.101 |
entimes | +4.028 |
Neg logit contributions | |
oji | -7.133 |
anus | -6.936 |
ュ | -6.792 |
cair | -6.707 |
hesis | -6.488 |
Token | Quin |
Token ID | 29338 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
lihood | +2.062 |
amounts | +2.034 |
ness | +1.992 |
lin | +1.890 |
entimes | +1.882 |
Neg logit contributions | |
oji | -2.064 |
anus | -1.998 |
ュ | -1.932 |
cair | -1.897 |
azor | -1.827 |
Token | jet |
Token ID | 31173 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
oji | +1.132 |
anus | +1.059 |
ュ | +1.046 |
cair | +1.040 |
azor | +1.021 |
Neg logit contributions | |
lihood | -1.375 |
amounts | -1.365 |
ness | -1.289 |
entimes | -1.282 |
lin | -1.257 |
Token | or |
Token ID | 393 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
lihood | +1.307 |
amounts | +1.280 |
ness | +1.245 |
lin | +1.164 |
entimes | +1.161 |
Neg logit contributions | |
oji | -2.010 |
anus | -1.955 |
ュ | -1.901 |
cair | -1.874 |
azor | -1.821 |
Token | Kr |
Token ID | 13685 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
lihood | +1.219 |
amounts | +1.198 |
ness | +1.170 |
lin | +1.105 |
entimes | +1.101 |
Neg logit contributions | |
oji | -1.481 |
anus | -1.437 |
ュ | -1.393 |
cair | -1.371 |
azor | -1.327 |
Token | And |
Token ID | 1870 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
oji | +0.151 |
anus | +0.146 |
ュ | +0.141 |
cair | +0.138 |
azor | +0.133 |
Neg logit contributions | |
lihood | -0.157 |
amounts | -0.155 |
ness | -0.150 |
entimes | -0.144 |
lin | -0.144 |
Token | life |
Token ID | 1204 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
lihood | +0.266 |
amounts | +0.261 |
ness | +0.254 |
entimes | +0.240 |
lin | +0.239 |
Neg logit contributions | |
oji | -0.334 |
anus | -0.323 |
ュ | -0.314 |
cair | -0.309 |
azor | -0.299 |
Token | is |
Token ID | 318 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
lihood | +0.861 |
amounts | +0.842 |
ness | +0.819 |
lin | +0.766 |
entimes | +0.765 |
Neg logit contributions | |
oji | -1.304 |
anus | -1.268 |
ュ | -1.233 |
cair | -1.214 |
azor | -1.181 |
Token | returning |
Token ID | 8024 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
oji | +0.673 |
anus | +0.657 |
ュ | +0.636 |
cair | +0.626 |
azor | +0.602 |
Neg logit contributions | |
lihood | -0.647 |
amounts | -0.631 |
ness | -0.617 |
entimes | -0.592 |
CENT | -0.582 |
Token | to |
Token ID | 284 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
oji | +1.012 |
anus | +0.978 |
ュ | +0.964 |
cair | +0.940 |
azor | +0.920 |
Neg logit contributions | |
lihood | -0.604 |
amounts | -0.583 |
ness | -0.561 |
entimes | -0.531 |
CENT | -0.522 |
Token | Jar |
Token ID | 15374 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
oji | +0.027 |
anus | +0.026 |
ュ | +0.026 |
cair | +0.025 |
azor | +0.024 |
Neg logit contributions | |
lihood | -0.020 |
amounts | -0.019 |
ness | -0.019 |
entimes | -0.018 |
lin | -0.018 |
Token | abl |
Token ID | 23117 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ness | +5.948 |
amounts | +5.904 |
lihood | +5.833 |
dar | +5.547 |
lin | +5.460 |
Neg logit contributions | |
oji | -4.644 |
ュ | -4.390 |
anus | -4.330 |
cair | -4.207 |
uitous | -4.124 |
Token | us |
Token ID | 385 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
oji | +0.760 |
anus | +0.751 |
ュ | +0.710 |
cair | +0.700 |
azor | +0.682 |
Neg logit contributions | |
lihood | -0.646 |
amounts | -0.631 |
ness | -0.609 |
entimes | -0.581 |
CENT | -0.581 |
Token | after |
Token ID | 706 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
oji | +1.363 |
anus | +1.312 |
ュ | +1.283 |
cair | +1.261 |
azor | +1.217 |
Neg logit contributions | |
lihood | -0.957 |
amounts | -0.915 |
ness | -0.887 |
entimes | -0.849 |
lin | -0.835 |
Token | ISIS |
Token ID | 7768 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
oji | +0.737 |
anus | +0.712 |
ュ | +0.690 |
cair | +0.676 |
azor | +0.656 |
Neg logit contributions | |
lihood | -0.697 |
amounts | -0.681 |
ness | -0.669 |
entimes | -0.637 |
lin | -0.635 |
Token | was |
Token ID | 373 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
lihood | +0.487 |
amounts | +0.472 |
ness | +0.460 |
lin | +0.432 |
entimes | +0.432 |
Neg logit contributions | |
oji | -0.738 |
anus | -0.718 |
ュ | -0.697 |
cair | -0.685 |
azor | -0.668 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
lihood | +0.736 |
amounts | +0.721 |
ness | +0.702 |
lin | +0.657 |
entimes | +0.654 |
Neg logit contributions | |
oji | -1.116 |
anus | -1.086 |
ュ | -1.056 |
cair | -1.040 |
azor | -1.010 |
Token | through |
Token ID | 832 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
lihood | +0.426 |
amounts | +0.413 |
ness | +0.404 |
entimes | +0.379 |
lin | +0.377 |
Neg logit contributions | |
oji | -0.597 |
anus | -0.578 |
ュ | -0.560 |
cair | -0.553 |
azor | -0.539 |
Token | its |
Token ID | 663 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
lihood | +0.899 |
amounts | +0.883 |
ness | +0.863 |
lin | +0.816 |
entimes | +0.814 |
Neg logit contributions | |
oji | -1.027 |
anus | -0.995 |
ュ | -0.964 |
cair | -0.948 |
azor | -0.917 |
Token | deals |
Token ID | 7529 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
lihood | +1.906 |
amounts | +1.886 |
ness | +1.840 |
lin | +1.731 |
entimes | +1.716 |
Neg logit contributions | |
oji | -2.309 |
anus | -2.247 |
ュ | -2.177 |
cair | -2.142 |
azor | -2.066 |
Token | with |
Token ID | 351 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
lihood | +0.687 |
amounts | +0.675 |
ness | +0.651 |
lin | +0.601 |
entimes | +0.590 |
Neg logit contributions | |
oji | -1.398 |
anus | -1.367 |
ュ | -1.332 |
cair | -1.318 |
azor | -1.278 |
Token | Gaz |
Token ID | 21347 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
lihood | +0.286 |
amounts | +0.281 |
ness | +0.274 |
lin | +0.259 |
entimes | +0.259 |
Neg logit contributions | |
oji | -0.344 |
anus | -0.333 |
ュ | -0.323 |
cair | -0.318 |
azor | -0.308 |
Token | prom |
Token ID | 16963 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
ness | +4.825 |
amounts | +4.800 |
lihood | +4.728 |
dar | +4.503 |
lin | +4.382 |
Neg logit contributions | |
oji | -5.708 |
ュ | -5.580 |
anus | -5.541 |
cair | -5.374 |
hetics | -5.212 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
oji | +0.260 |
anus | +0.252 |
ュ | +0.245 |
cair | +0.242 |
azor | +0.235 |
Neg logit contributions | |
lihood | -0.175 |
amounts | -0.171 |
ness | -0.166 |
lin | -0.156 |
entimes | -0.156 |
Token | allow |
Token ID | 1249 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
lihood | +0.648 |
amounts | +0.631 |
ness | +0.616 |
entimes | +0.580 |
lin | +0.577 |
Neg logit contributions | |
oji | -0.911 |
anus | -0.880 |
ュ | -0.857 |
cair | -0.846 |
azor | -0.824 |
Token | the |
Token ID | 262 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
lihood | +1.145 |
amounts | +1.124 |
ness | +1.097 |
lin | +1.034 |
entimes | +1.032 |
Neg logit contributions | |
oji | -1.424 |
anus | -1.381 |
ュ | -1.340 |
cair | -1.319 |
azor | -1.277 |
Token | Russians |
Token ID | 13234 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
lihood | +1.468 |
amounts | +1.455 |
ness | +1.412 |
lin | +1.334 |
entimes | +1.318 |
Neg logit contributions | |
oji | -1.868 |
anus | -1.819 |
ュ | -1.761 |
cair | -1.734 |
azor | -1.675 |
Token | Sign |
Token ID | 5865 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
lihood | +3.088 |
amounts | +3.042 |
ness | +2.990 |
lin | +2.832 |
entimes | +2.817 |
Neg logit contributions | |
oji | -2.783 |
anus | -2.690 |
ュ | -2.585 |
cair | -2.535 |
azor | -2.446 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
lihood | +2.663 |
amounts | +2.618 |
ness | +2.554 |
lin | +2.429 |
entimes | +2.426 |
Neg logit contributions | |
oji | -2.851 |
anus | -2.753 |
ュ | -2.675 |
cair | -2.626 |
azor | -2.533 |
Token | You |
Token ID | 921 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
lihood | +3.811 |
amounts | +3.782 |
ness | +3.718 |
lin | +3.497 |
CENT | +3.489 |
Neg logit contributions | |
oji | -3.597 |
anus | -3.472 |
ュ | -3.334 |
cair | -3.283 |
azor | -3.168 |
Token | will |
Token ID | 481 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
amounts | +2.269 |
lihood | +2.250 |
ness | +2.184 |
lin | +2.000 |
entimes | +1.972 |
Neg logit contributions | |
oji | -4.592 |
anus | -4.480 |
ュ | -4.419 |
cair | -4.323 |
azor | -4.201 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
amounts | +3.125 |
lihood | +3.060 |
ness | +3.048 |
lin | +2.744 |
LY | +2.658 |
Neg logit contributions | |
oji | -6.815 |
anus | -6.721 |
ュ | -6.537 |
cair | -6.480 |
azor | -6.247 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
amounts | +4.920 |
ness | +4.684 |
lihood | +4.653 |
lin | +4.513 |
LY | +4.376 |
Neg logit contributions | |
oji | -4.643 |
anus | -4.577 |
ュ | -4.402 |
cair | -4.223 |
azor | -4.042 |
Token | containing |
Token ID | 7268 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
amounts | +3.184 |
ness | +2.903 |
lihood | +2.809 |
lin | +2.715 |
entitle | +2.597 |
Neg logit contributions | |
oji | -8.480 |
anus | -8.425 |
ュ | -8.110 |
cair | -8.017 |
azor | -7.863 |
Token | news |
Token ID | 1705 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
amounts | +5.117 |
ness | +4.897 |
lihood | +4.708 |
lin | +4.471 |
LY | +4.348 |
Neg logit contributions | |
anus | -8.158 |
oji | -8.143 |
ュ | -7.810 |
cair | -7.633 |
hetics | -7.457 |
Token | content |
Token ID | 2695 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
amounts | +2.720 |
ness | +2.532 |
lihood | +2.445 |
lin | +2.084 |
CENT | +1.993 |
Neg logit contributions | |
oji | -9.604 |
anus | -9.502 |
ュ | -9.277 |
cair | -9.101 |
azor | -8.872 |
Token | , |
Token ID | 837 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
amounts | +5.711 |
lihood | +5.554 |
ness | +5.507 |
LY | +5.015 |
CENT | +4.963 |
Neg logit contributions | |
oji | -8.997 |
anus | -8.703 |
ュ | -8.468 |
cair | -8.138 |
hetics | -7.959 |
Token | updates |
Token ID | 5992 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
amounts | +1.712 |
lihood | +1.694 |
ness | +1.617 |
lin | +1.465 |
entimes | +1.430 |
Neg logit contributions | |
oji | -4.622 |
anus | -4.542 |
ュ | -4.423 |
cair | -4.353 |
azor | -4.268 |
Token | he |
Token ID | 339 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
lihood | +1.945 |
amounts | +1.913 |
ness | +1.868 |
lin | +1.762 |
entimes | +1.754 |
Neg logit contributions | |
oji | -2.396 |
anus | -2.323 |
ュ | -2.254 |
cair | -2.218 |
azor | -2.147 |
Token | thought |
Token ID | 1807 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
lihood | +0.600 |
amounts | +0.580 |
ness | +0.568 |
lin | +0.535 |
entimes | +0.534 |
Neg logit contributions | |
oji | -0.792 |
anus | -0.767 |
ュ | -0.744 |
cair | -0.735 |
azor | -0.710 |
Token | was |
Token ID | 373 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
lihood | +0.941 |
amounts | +0.911 |
ness | +0.889 |
entimes | +0.843 |
lin | +0.835 |
Neg logit contributions | |
oji | -1.346 |
anus | -1.308 |
ュ | -1.269 |
cair | -1.248 |
azor | -1.214 |
Token | rational |
Token ID | 9377 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
oji | +0.817 |
anus | +0.792 |
ュ | +0.760 |
cair | +0.748 |
azor | +0.730 |
Neg logit contributions | |
lihood | -0.766 |
amounts | -0.735 |
ness | -0.719 |
entimes | -0.694 |
CENT | -0.689 |
Token | over |
Token ID | 625 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
oji | +4.633 |
anus | +4.520 |
ュ | +4.346 |
cair | +4.231 |
hetics | +4.174 |
Neg logit contributions | |
lihood | -3.569 |
amounts | -3.234 |
entimes | -3.125 |
ness | -3.107 |
CENT | -3.076 |
Token | the |
Token ID | 262 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
oji | +1.839 |
anus | +1.805 |
ュ | +1.737 |
cair | +1.705 |
azor | +1.652 |
Neg logit contributions | |
lihood | -1.613 |
amounts | -1.536 |
ness | -1.508 |
entimes | -1.454 |
lin | -1.432 |
Token | objections |
Token ID | 21954 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
lihood | +1.037 |
amounts | +1.021 |
ness | +0.994 |
lin | +0.934 |
entimes | +0.927 |
Neg logit contributions | |
oji | -1.426 |
anus | -1.385 |
ュ | -1.345 |
cair | -1.326 |
azor | -1.285 |
Token | of |
Token ID | 286 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
oji | +1.841 |
anus | +1.777 |
ュ | +1.711 |
cair | +1.691 |
azor | +1.624 |
Neg logit contributions | |
lihood | -1.818 |
amounts | -1.807 |
ness | -1.767 |
lin | -1.667 |
entimes | -1.649 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
oji | +0.841 |
anus | +0.818 |
ュ | +0.791 |
cair | +0.775 |
azor | +0.753 |
Neg logit contributions | |
lihood | -0.823 |
amounts | -0.799 |
ness | -0.785 |
entimes | -0.751 |
lin | -0.745 |
Token | Democratic |
Token ID | 4390 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
oji | +0.629 |
anus | +0.612 |
ュ | +0.592 |
cair | +0.578 |
azor | +0.562 |
Neg logit contributions | |
lihood | -0.582 |
amounts | -0.557 |
ness | -0.547 |
entimes | -0.526 |
dar | -0.518 |
Token | congressional |
Token ID | 11702 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
oji | +2.156 |
anus | +2.065 |
ュ | +1.995 |
cair | +1.961 |
hetics | +1.873 |
Neg logit contributions | |
lihood | -2.721 |
amounts | -2.593 |
ness | -2.529 |
entimes | -2.481 |
dar | -2.455 |
Token | J |
Token ID | 41 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
oji | +3.241 |
anus | +3.149 |
cair | +3.014 |
ュ | +3.012 |
azor | +2.929 |
Neg logit contributions | |
lihood | -2.210 |
amounts | -2.183 |
ness | -2.077 |
entimes | -1.980 |
lin | -1.964 |
Token | edi |
Token ID | 13740 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
lihood | +1.675 |
amounts | +1.653 |
ness | +1.646 |
lin | +1.539 |
entimes | +1.532 |
Neg logit contributions | |
oji | -1.687 |
anus | -1.626 |
ュ | -1.600 |
cair | -1.559 |
azor | -1.492 |
Token | You |
Token ID | 1639 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
lihood | +1.111 |
amounts | +1.093 |
ness | +1.071 |
lin | +1.017 |
entimes | +1.014 |
Neg logit contributions | |
oji | -1.072 |
anus | -1.036 |
ュ | -1.001 |
cair | -0.983 |
azor | -0.947 |
Token | Are |
Token ID | 8491 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
oji | +0.115 |
anus | +0.112 |
ュ | +0.108 |
cair | +0.106 |
azor | +0.103 |
Neg logit contributions | |
lihood | -0.108 |
amounts | -0.107 |
ness | -0.104 |
entimes | -0.100 |
lin | -0.099 |
Token | Not |
Token ID | 3673 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
lihood | +0.492 |
amounts | +0.485 |
ness | +0.474 |
lin | +0.453 |
entimes | +0.452 |
Neg logit contributions | |
oji | -0.436 |
anus | -0.421 |
ュ | -0.405 |
cair | -0.398 |
azor | -0.384 |
Token | . |
Token ID | 13 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
lihood | +0.559 |
amounts | +0.551 |
ness | +0.538 |
lin | +0.513 |
entimes | +0.513 |
Neg logit contributions | |
oji | -0.504 |
anus | -0.487 |
ュ | -0.469 |
cair | -0.460 |
azor | -0.444 |
Token | � |
Token ID | 447 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
lihood | +1.455 |
amounts | +1.434 |
ness | +1.407 |
lin | +1.332 |
entimes | +1.322 |
Neg logit contributions | |
oji | -1.465 |
anus | -1.419 |
ュ | -1.371 |
cair | -1.350 |
azor | -1.297 |
Token | � |
Token ID | 251 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
oji | +0.873 |
anus | +0.845 |
ュ | +0.816 |
cair | +0.813 |
azor | +0.779 |
Neg logit contributions | |
lihood | -0.751 |
amounts | -0.741 |
ness | -0.725 |
lin | -0.685 |
entimes | -0.679 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
oji | +0.389 |
anus | +0.376 |
ュ | +0.362 |
cair | +0.356 |
azor | +0.345 |
Neg logit contributions | |
lihood | -0.382 |
amounts | -0.375 |
ness | -0.366 |
entimes | -0.349 |
lin | -0.348 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
oji | +0.572 |
anus | +0.542 |
ュ | +0.531 |
cair | +0.510 |
Amazing | +0.501 |
Neg logit contributions | |
lihood | -0.713 |
amounts | -0.695 |
entimes | -0.681 |
ness | -0.655 |
lin | -0.652 |
Token | The |
Token ID | 464 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
oji | +0.877 |
anus | +0.848 |
ュ | +0.818 |
cair | +0.799 |
azor | +0.778 |
Neg logit contributions | |
lihood | -0.944 |
amounts | -0.934 |
ness | -0.897 |
entimes | -0.876 |
lin | -0.871 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
lihood | +0.597 |
amounts | +0.582 |
ness | +0.571 |
entimes | +0.544 |
lin | +0.540 |
Neg logit contributions | |
oji | -0.715 |
anus | -0.692 |
ュ | -0.673 |
cair | -0.661 |
azor | -0.641 |
Token | doctrine |
Token ID | 13115 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
oji | +0.740 |
anus | +0.719 |
ュ | +0.705 |
cair | +0.687 |
azor | +0.665 |
Neg logit contributions | |
lihood | -0.590 |
amounts | -0.568 |
ness | -0.562 |
entimes | -0.544 |
CENT | -0.536 |
Token | of |
Token ID | 286 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
oji | +0.586 |
anus | +0.568 |
ュ | +0.550 |
cair | +0.538 |
azor | +0.518 |
Neg logit contributions | |
lihood | -0.616 |
amounts | -0.599 |
ness | -0.588 |
entimes | -0.566 |
lin | -0.561 |
Token | acquired |
Token ID | 9477 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
lihood | +0.816 |
amounts | +0.803 |
ness | +0.783 |
lin | +0.739 |
entimes | +0.735 |
Neg logit contributions | |
oji | -1.001 |
anus | -0.970 |
ュ | -0.940 |
cair | -0.926 |
azor | -0.897 |
Token | rights |
Token ID | 2489 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
lihood | +0.830 |
amounts | +0.812 |
ness | +0.789 |
entimes | +0.739 |
lin | +0.739 |
Neg logit contributions | |
oji | -1.253 |
anus | -1.220 |
ュ | -1.186 |
cair | -1.168 |
azor | -1.135 |
Token | under |
Token ID | 739 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
lihood | +1.793 |
amounts | +1.783 |
ness | +1.730 |
lin | +1.603 |
entimes | +1.584 |
Neg logit contributions | |
oji | -2.946 |
anus | -2.857 |
ュ | -2.787 |
cair | -2.751 |
azor | -2.671 |
Token | public |
Token ID | 1171 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
lihood | +1.967 |
amounts | +1.960 |
ness | +1.913 |
lin | +1.803 |
entimes | +1.751 |
Neg logit contributions | |
oji | -2.468 |
anus | -2.393 |
ュ | -2.314 |
cair | -2.287 |
azor | -2.219 |
Token | international |
Token ID | 3230 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
oji | +0.704 |
anus | +0.685 |
ュ | +0.664 |
cair | +0.648 |
azor | +0.627 |
Neg logit contributions | |
lihood | -0.616 |
amounts | -0.599 |
ness | -0.581 |
entimes | -0.564 |
CENT | -0.559 |
Token | law |
Token ID | 1099 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
oji | +0.105 |
anus | +0.101 |
ュ | +0.098 |
cair | +0.094 |
azor | +0.092 |
Neg logit contributions | |
lihood | -0.120 |
amounts | -0.117 |
ness | -0.114 |
CENT | -0.112 |
entimes | -0.112 |
Token | will |
Token ID | 481 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
oji | +0.359 |
anus | +0.351 |
ュ | +0.340 |
cair | +0.334 |
azor | +0.327 |
Neg logit contributions | |
lihood | -0.236 |
amounts | -0.224 |
ness | -0.220 |
entimes | -0.209 |
CENT | -0.208 |
Token | provide |
Token ID | 2148 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
lihood | +0.321 |
amounts | +0.310 |
ness | +0.302 |
entimes | +0.287 |
CENT | +0.286 |
Neg logit contributions | |
oji | -0.423 |
anus | -0.409 |
ュ | -0.400 |
cair | -0.392 |
azor | -0.379 |
Token | AS |
Token ID | 1921 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
oji | +1.342 |
anus | +1.304 |
ュ | +1.264 |
cair | +1.244 |
azor | +1.208 |
Neg logit contributions | |
lihood | -1.042 |
amounts | -1.022 |
ness | -0.996 |
lin | -0.938 |
entimes | -0.936 |
Token | Insurance |
Token ID | 17541 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
lihood | +0.970 |
amounts | +0.954 |
ness | +0.929 |
lin | +0.875 |
entimes | +0.872 |
Neg logit contributions | |
oji | -1.248 |
anus | -1.211 |
ュ | -1.175 |
cair | -1.157 |
azor | -1.121 |
Token | Partner |
Token ID | 35532 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
oji | +3.365 |
anus | +3.165 |
cair | +3.073 |
ュ | +3.060 |
azor | +2.999 |
Neg logit contributions | |
lihood | -3.597 |
amounts | -3.344 |
ness | -3.312 |
entimes | -3.246 |
dar | -3.230 |
Token | � |
Token ID | 447 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
lihood | +1.139 |
amounts | +1.121 |
ness | +1.098 |
lin | +1.039 |
entimes | +1.034 |
Neg logit contributions | |
oji | -1.184 |
anus | -1.147 |
ュ | -1.109 |
cair | -1.088 |
azor | -1.050 |
Token | � |
Token ID | 247 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
oji | +0.785 |
anus | +0.757 |
ュ | +0.731 |
cair | +0.716 |
azor | +0.691 |
Neg logit contributions | |
lihood | -0.868 |
amounts | -0.854 |
ness | -0.837 |
lin | -0.796 |
entimes | -0.795 |
Token | s |
Token ID | 82 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
lihood | +0.013 |
amounts | +0.013 |
ness | +0.013 |
entimes | +0.012 |
lin | +0.012 |
Neg logit contributions | |
oji | -0.015 |
anus | -0.015 |
ュ | -0.014 |
cair | -0.014 |
azor | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
lihood | +0.954 |
amounts | +0.939 |
ness | +0.917 |
lin | +0.868 |
entimes | +0.867 |
Neg logit contributions | |
oji | -1.036 |
anus | -1.002 |
ュ | -0.970 |
cair | -0.954 |
azor | -0.922 |
Token |
|
Token ID | 198 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
lihood | +0.165 |
amounts | +0.160 |
entimes | +0.156 |
ness | +0.152 |
lin | +0.150 |
Neg logit contributions | |
oji | -0.141 |
anus | -0.134 |
ュ | -0.131 |
cair | -0.127 |
azor | -0.124 |
Token | V |
Token ID | 53 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
lihood | +0.137 |
amounts | +0.135 |
ness | +0.131 |
lin | +0.125 |
entimes | +0.125 |
Neg logit contributions | |
oji | -0.132 |
anus | -0.128 |
ュ | -0.123 |
cair | -0.121 |
azor | -0.117 |
Token | AS |
Token ID | 1921 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
oji | +1.137 |
anus | +1.103 |
ュ | +1.073 |
cair | +1.057 |
azor | +1.020 |
Neg logit contributions | |
lihood | -0.856 |
amounts | -0.841 |
ness | -0.821 |
lin | -0.771 |
entimes | -0.770 |
Token | has |
Token ID | 468 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
lihood | +0.089 |
amounts | +0.087 |
ness | +0.085 |
lin | +0.080 |
entimes | +0.080 |
Neg logit contributions | |
oji | -0.118 |
anus | -0.115 |
ュ | -0.111 |
cair | -0.110 |
azor | -0.107 |
Token | know |
Token ID | 760 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
oji | +0.433 |
anus | +0.412 |
cair | +0.401 |
ュ | +0.401 |
hetics | +0.389 |
Neg logit contributions | |
lihood | -0.295 |
amounts | -0.283 |
ness | -0.272 |
entimes | -0.268 |
CENT | -0.265 |
Token | - |
Token ID | 532 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
oji | +1.351 |
anus | +1.286 |
ュ | +1.262 |
cair | +1.249 |
azor | +1.211 |
Neg logit contributions | |
lihood | -1.232 |
amounts | -1.194 |
ness | -1.161 |
entimes | -1.160 |
CENT | -1.147 |
Token | and |
Token ID | 290 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
oji | +1.775 |
anus | +1.725 |
ュ | +1.652 |
cair | +1.641 |
azor | +1.604 |
Neg logit contributions | |
lihood | -1.335 |
amounts | -1.278 |
ness | -1.255 |
entimes | -1.206 |
lin | -1.184 |
Token | they |
Token ID | 484 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
lihood | +0.196 |
amounts | +0.191 |
ness | +0.186 |
entimes | +0.177 |
lin | +0.176 |
Neg logit contributions | |
oji | -0.255 |
anus | -0.246 |
ュ | -0.238 |
cair | -0.236 |
azor | -0.228 |
Token | can |
Token ID | 460 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
oji | +1.146 |
anus | +1.100 |
cair | +1.073 |
ュ | +1.061 |
hetics | +1.026 |
Neg logit contributions | |
lihood | -0.853 |
amounts | -0.824 |
ness | -0.798 |
CENT | -0.764 |
lin | -0.759 |
Token | 't |
Token ID | 470 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
lihood | +1.186 |
amounts | +1.159 |
ness | +1.127 |
entimes | +1.062 |
lin | +1.060 |
Neg logit contributions | |
oji | -1.560 |
anus | -1.513 |
ュ | -1.467 |
cair | -1.449 |
azor | -1.400 |
Token | tell |
Token ID | 1560 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
lihood | +1.614 |
amounts | +1.575 |
ness | +1.531 |
entimes | +1.443 |
lin | +1.436 |
Neg logit contributions | |
oji | -2.225 |
anus | -2.158 |
ュ | -2.090 |
cair | -2.068 |
azor | -2.001 |
Token | you |
Token ID | 345 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
lihood | +1.539 |
amounts | +1.521 |
ness | +1.484 |
lin | +1.381 |
entimes | +1.366 |
Neg logit contributions | |
oji | -2.370 |
anus | -2.313 |
ュ | -2.250 |
cair | -2.216 |
azor | -2.148 |
Token | - |
Token ID | 532 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
lihood | +1.114 |
amounts | +1.092 |
ness | +1.066 |
entimes | +1.005 |
lin | +1.005 |
Neg logit contributions | |
oji | -1.372 |
anus | -1.330 |
ュ | -1.289 |
cair | -1.270 |
azor | -1.230 |
Token | the |
Token ID | 262 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
lihood | +0.343 |
amounts | +0.335 |
ness | +0.328 |
entimes | +0.310 |
lin | +0.309 |
Neg logit contributions | |
oji | -0.431 |
anus | -0.417 |
ュ | -0.404 |
cair | -0.399 |
azor | -0.387 |
Token | terms |
Token ID | 2846 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
oji | +0.855 |
anus | +0.823 |
ュ | +0.805 |
cair | +0.790 |
azor | +0.764 |
Neg logit contributions | |
lihood | -0.688 |
amounts | -0.659 |
ness | -0.651 |
entimes | -0.632 |
CENT | -0.619 |
Token | chilling |
Token ID | 28010 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
lihood | +1.017 |
amounts | +1.001 |
ness | +0.980 |
lin | +0.931 |
entimes | +0.928 |
Neg logit contributions | |
oji | -0.992 |
anus | -0.959 |
ュ | -0.926 |
cair | -0.910 |
azor | -0.877 |
Token | precedent |
Token ID | 19719 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
lihood | +0.557 |
amounts | +0.548 |
ness | +0.535 |
entimes | +0.508 |
lin | +0.507 |
Neg logit contributions | |
oji | -0.580 |
anus | -0.562 |
ュ | -0.543 |
cair | -0.534 |
azor | -0.516 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
lihood | +0.448 |
amounts | +0.441 |
ness | +0.430 |
lin | +0.405 |
entimes | +0.399 |
Neg logit contributions | |
oji | -0.621 |
anus | -0.603 |
ュ | -0.584 |
cair | -0.577 |
azor | -0.559 |
Token | Once |
Token ID | 4874 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
oji | +0.304 |
anus | +0.292 |
ュ | +0.287 |
cair | +0.278 |
azor | +0.268 |
Neg logit contributions | |
lihood | -0.332 |
amounts | -0.327 |
ness | -0.320 |
entimes | -0.311 |
lin | -0.306 |
Token | one |
Token ID | 530 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
lihood | +0.714 |
amounts | +0.696 |
ness | +0.681 |
entimes | +0.645 |
lin | +0.643 |
Neg logit contributions | |
oji | -0.803 |
anus | -0.780 |
ュ | -0.754 |
cair | -0.743 |
azor | -0.717 |
Token | of |
Token ID | 286 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
oji | +1.884 |
anus | +1.833 |
ュ | +1.775 |
cair | +1.739 |
uitous | +1.681 |
Neg logit contributions | |
lihood | -1.831 |
amounts | -1.768 |
ness | -1.733 |
entimes | -1.682 |
CENT | -1.679 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
oji | +1.423 |
anus | +1.378 |
ュ | +1.334 |
cair | +1.311 |
azor | +1.267 |
Neg logit contributions | |
lihood | -1.332 |
amounts | -1.309 |
ness | -1.279 |
lin | -1.211 |
entimes | -1.210 |
Token | world |
Token ID | 995 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
oji | +0.004 |
anus | +0.004 |
ュ | +0.004 |
cair | +0.004 |
azor | +0.004 |
Neg logit contributions | |
lihood | -0.004 |
amounts | -0.004 |
ness | -0.003 |
entimes | -0.003 |
lin | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
lihood | +1.744 |
amounts | +1.704 |
ness | +1.660 |
entimes | +1.562 |
lin | +1.554 |
Neg logit contributions | |
oji | -2.413 |
anus | -2.346 |
ュ | -2.281 |
cair | -2.247 |
azor | -2.179 |
Token | � |
Token ID | 247 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
oji | +1.536 |
anus | +1.528 |
ュ | +1.462 |
azor | +1.391 |
cair | +1.390 |
Neg logit contributions | |
lihood | -1.666 |
amounts | -1.586 |
ness | -1.553 |
entimes | -1.526 |
lin | -1.494 |
Token | s |
Token ID | 82 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
oji | +1.190 |
anus | +1.159 |
ュ | +1.135 |
cair | +1.119 |
azor | +1.092 |
Neg logit contributions | |
lihood | -0.522 |
amounts | -0.502 |
ness | -0.482 |
entimes | -0.454 |
lin | -0.447 |
Token | and |
Token ID | 290 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
lihood | +1.606 |
amounts | +1.602 |
ness | +1.548 |
lin | +1.447 |
entimes | +1.423 |
Neg logit contributions | |
oji | -2.485 |
anus | -2.429 |
ュ | -2.364 |
cair | -2.334 |
azor | -2.263 |
Token | major |
Token ID | 1688 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
lihood | +0.131 |
amounts | +0.126 |
ness | +0.125 |
entimes | +0.119 |
lin | +0.117 |
Neg logit contributions | |
oji | -0.162 |
anus | -0.157 |
ュ | -0.153 |
cair | -0.149 |
azor | -0.145 |
Token | dem |
Token ID | 1357 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
amounts | +2.823 |
lihood | +2.811 |
ness | +2.700 |
lin | +2.517 |
entimes | +2.478 |
Neg logit contributions | |
oji | -4.148 |
anus | -4.064 |
ュ | -3.921 |
cair | -3.899 |
azor | -3.754 |
Token | otions |
Token ID | 36083 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
lihood | +1.074 |
amounts | +1.065 |
ness | +1.050 |
lin | +1.012 |
entimes | +1.005 |
Neg logit contributions | |
oji | -0.344 |
anus | -0.325 |
ュ | -0.306 |
cair | -0.290 |
azor | -0.264 |
Token | � |
Token ID | 447 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
lihood | +1.378 |
amounts | +1.357 |
ness | +1.317 |
lin | +1.235 |
entimes | +1.227 |
Neg logit contributions | |
oji | -2.015 |
anus | -1.963 |
ュ | -1.908 |
cair | -1.879 |
azor | -1.823 |
Token | � |
Token ID | 251 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
oji | +0.507 |
anus | +0.491 |
ュ | +0.472 |
cair | +0.470 |
azor | +0.450 |
Neg logit contributions | |
lihood | -0.469 |
amounts | -0.465 |
ness | -0.454 |
lin | -0.428 |
entimes | -0.427 |
Token | . |
Token ID | 13 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
lihood | +0.213 |
amounts | +0.207 |
ness | +0.203 |
lin | +0.190 |
entimes | +0.190 |
Neg logit contributions | |
oji | -0.292 |
anus | -0.283 |
ュ | -0.275 |
cair | -0.271 |
azor | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
oji | +0.024 |
anus | +0.023 |
ュ | +0.022 |
cair | +0.022 |
azor | +0.021 |
Neg logit contributions | |
lihood | -0.023 |
amounts | -0.023 |
ness | -0.022 |
lin | -0.021 |
entimes | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
lihood | +1.177 |
amounts | +1.150 |
ness | +1.106 |
entimes | +1.092 |
lin | +1.072 |
Neg logit contributions | |
oji | -1.111 |
anus | -1.068 |
ュ | -1.039 |
cair | -1.011 |
azor | -0.982 |
Token | Ten |
Token ID | 24893 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
lihood | +0.482 |
amounts | +0.474 |
ness | +0.463 |
lin | +0.442 |
entimes | +0.441 |
Neg logit contributions | |
oji | -0.468 |
anus | -0.452 |
ュ | -0.438 |
cair | -0.429 |
azor | -0.414 |
Token | � |
Token ID | 564 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
oji | +1.449 |
anus | +1.381 |
ュ | +1.352 |
cair | +1.322 |
azor | +1.281 |
Neg logit contributions | |
lihood | -1.384 |
amounts | -1.344 |
ness | -1.308 |
lin | -1.251 |
entimes | -1.241 |
Token | of |
Token ID | 286 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
oji | +1.496 |
anus | +1.440 |
ュ | +1.384 |
cair | +1.362 |
azor | +1.309 |
Neg logit contributions | |
amounts | -1.435 |
lihood | -1.431 |
ness | -1.403 |
entimes | -1.319 |
lin | -1.313 |
Token | information |
Token ID | 1321 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
oji | +2.473 |
anus | +2.380 |
ュ | +2.313 |
cair | +2.265 |
azor | +2.205 |
Neg logit contributions | |
lihood | -2.244 |
ness | -2.093 |
amounts | -2.089 |
CENT | -2.056 |
entimes | -2.051 |
Token | from |
Token ID | 422 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
oji | +2.444 |
anus | +2.369 |
ュ | +2.334 |
cair | +2.239 |
azor | +2.207 |
Neg logit contributions | |
lihood | -1.945 |
amounts | -1.800 |
ness | -1.790 |
entimes | -1.775 |
dar | -1.713 |
Token | the |
Token ID | 262 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
oji | +0.884 |
anus | +0.857 |
ュ | +0.831 |
cair | +0.816 |
azor | +0.790 |
Neg logit contributions | |
lihood | -0.774 |
amounts | -0.757 |
ness | -0.742 |
entimes | -0.701 |
lin | -0.701 |
Token | two |
Token ID | 734 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
lihood | +0.078 |
amounts | +0.075 |
ness | +0.074 |
entimes | +0.070 |
lin | +0.070 |
Neg logit contributions | |
oji | -0.086 |
anus | -0.084 |
ュ | -0.081 |
cair | -0.079 |
azor | -0.077 |
Token | instruments |
Token ID | 12834 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
oji | +3.630 |
anus | +3.481 |
ュ | +3.435 |
cair | +3.316 |
azor | +3.260 |
Neg logit contributions | |
lihood | -3.288 |
ness | -3.067 |
amounts | -3.052 |
CENT | -3.024 |
entimes | -3.013 |
Token | checking |
Token ID | 10627 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
oji | +0.324 |
anus | +0.315 |
ュ | +0.305 |
cair | +0.300 |
azor | +0.293 |
Neg logit contributions | |
lihood | -0.220 |
amounts | -0.209 |
ness | -0.206 |
entimes | -0.196 |
CENT | -0.194 |
Token | chemical |
Token ID | 5931 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
oji | +1.107 |
anus | +1.071 |
ュ | +1.044 |
cair | +1.027 |
azor | +0.992 |
Neg logit contributions | |
lihood | -0.964 |
amounts | -0.921 |
ness | -0.906 |
entimes | -0.874 |
CENT | -0.870 |
Token | elements |
Token ID | 4847 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
oji | +1.138 |
anus | +1.103 |
ュ | +1.067 |
cair | +1.048 |
azor | +1.015 |
Neg logit contributions | |
lihood | -1.088 |
amounts | -1.042 |
ness | -1.023 |
entimes | -0.983 |
CENT | -0.982 |
Token | in |
Token ID | 287 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
oji | +1.914 |
anus | +1.858 |
ュ | +1.789 |
cair | +1.763 |
uitous | +1.720 |
Neg logit contributions | |
lihood | -1.517 |
amounts | -1.432 |
ness | -1.425 |
entimes | -1.379 |
CENT | -1.376 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
oji | +0.768 |
anus | +0.743 |
ュ | +0.723 |
cair | +0.710 |
azor | +0.688 |
Neg logit contributions | |
lihood | -0.625 |
amounts | -0.607 |
ness | -0.596 |
entimes | -0.564 |
lin | -0.562 |
Token | he |
Token ID | 339 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
oji | +0.279 |
anus | +0.271 |
ュ | +0.263 |
cair | +0.259 |
azor | +0.251 |
Neg logit contributions | |
lihood | -0.222 |
amounts | -0.217 |
ness | -0.213 |
entimes | -0.201 |
lin | -0.200 |
Token | advises |
Token ID | 34138 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
lihood | +0.241 |
amounts | +0.237 |
ness | +0.231 |
lin | +0.217 |
entimes | +0.216 |
Neg logit contributions | |
oji | -0.333 |
anus | -0.324 |
ュ | -0.315 |
cair | -0.310 |
azor | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
lihood | +0.192 |
amounts | +0.189 |
ness | +0.185 |
lin | +0.173 |
entimes | +0.170 |
Neg logit contributions | |
oji | -0.292 |
anus | -0.284 |
ュ | -0.276 |
cair | -0.273 |
azor | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
oji | +0.841 |
anus | +0.809 |
ュ | +0.789 |
cair | +0.764 |
azor | +0.746 |
Neg logit contributions | |
lihood | -0.885 |
amounts | -0.872 |
ness | -0.850 |
entimes | -0.824 |
lin | -0.817 |
Token |
|
Token ID | 198 |
Feature activation | +6.64e-04 |
Pos logit contributions | |
lihood | +0.439 |
amounts | +0.426 |
entimes | +0.411 |
ness | +0.406 |
lin | +0.399 |
Neg logit contributions | |
oji | -0.383 |
anus | -0.366 |
ュ | -0.355 |
cair | -0.346 |
azor | -0.337 |
Token | � |
Token ID | 447 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
lihood | +0.002 |
amounts | +0.002 |
ness | +0.002 |
lin | +0.002 |
entimes | +0.002 |
Neg logit contributions | |
oji | -0.002 |
anus | -0.002 |
ュ | -0.002 |
cair | -0.002 |
azor | -0.002 |
Token | � |
Token ID | 250 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
oji | +2.560 |
anus | +2.484 |
ュ | +2.409 |
cair | +2.374 |
azor | +2.297 |
Neg logit contributions | |
lihood | -2.020 |
amounts | -1.984 |
ness | -1.937 |
lin | -1.824 |
entimes | -1.818 |
Token | Let |
Token ID | 5756 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
oji | +0.670 |
anus | +0.648 |
ュ | +0.626 |
cair | +0.608 |
azor | +0.593 |
Neg logit contributions | |
lihood | -0.709 |
amounts | -0.705 |
ness | -0.677 |
entimes | -0.660 |
lin | -0.659 |
Token | me |
Token ID | 502 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
lihood | +2.177 |
amounts | +2.170 |
ness | +2.145 |
lin | +1.993 |
entimes | +1.962 |
Neg logit contributions | |
oji | -2.422 |
anus | -2.312 |
cair | -2.241 |
ュ | -2.240 |
azor | -2.148 |
Token | give |
Token ID | 1577 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
oji | +1.253 |
anus | +1.193 |
ュ | +1.163 |
cair | +1.131 |
hetics | +1.104 |
Neg logit contributions | |
lihood | -1.050 |
amounts | -1.038 |
ness | -0.986 |
CENT | -0.954 |
dar | -0.945 |
Token | you |
Token ID | 345 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
oji | +2.634 |
anus | +2.548 |
ュ | +2.482 |
cair | +2.411 |
azor | +2.357 |
Neg logit contributions | |
lihood | -1.856 |
amounts | -1.783 |
ness | -1.745 |
entimes | -1.667 |
CENT | -1.648 |
Token | may |
Token ID | 743 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
lihood | +1.136 |
amounts | +1.111 |
ness | +1.080 |
lin | +1.014 |
entimes | +1.011 |
Neg logit contributions | |
oji | -1.627 |
anus | -1.579 |
ュ | -1.534 |
cair | -1.511 |
azor | -1.467 |
Token | be |
Token ID | 307 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
lihood | +1.839 |
amounts | +1.808 |
ness | +1.761 |
lin | +1.649 |
entimes | +1.643 |
Neg logit contributions | |
oji | -2.762 |
anus | -2.690 |
ュ | -2.614 |
cair | -2.579 |
azor | -2.503 |
Token | the |
Token ID | 262 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
lihood | +2.216 |
amounts | +2.199 |
ness | +2.151 |
lin | +2.036 |
entimes | +2.011 |
Neg logit contributions | |
oji | -2.756 |
anus | -2.677 |
ュ | -2.598 |
cair | -2.569 |
azor | -2.459 |
Token | gateway |
Token ID | 24308 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
oji | +0.978 |
anus | +0.946 |
ュ | +0.920 |
cair | +0.898 |
azor | +0.876 |
Neg logit contributions | |
lihood | -0.863 |
amounts | -0.835 |
ness | -0.816 |
entimes | -0.778 |
CENT | -0.772 |
Token | drug |
Token ID | 2563 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
oji | +0.824 |
anus | +0.806 |
ュ | +0.782 |
cair | +0.765 |
azor | +0.751 |
Neg logit contributions | |
lihood | -0.557 |
amounts | -0.534 |
ness | -0.517 |
entimes | -0.491 |
CENT | -0.486 |
Token | to |
Token ID | 284 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
lihood | +1.464 |
amounts | +1.446 |
ness | +1.410 |
lin | +1.310 |
entimes | +1.300 |
Neg logit contributions | |
oji | -2.311 |
anus | -2.250 |
ュ | -2.184 |
cair | -2.164 |
azor | -2.090 |
Token | opportunities |
Token ID | 6443 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
lihood | +0.125 |
amounts | +0.122 |
ness | +0.119 |
entimes | +0.113 |
lin | +0.112 |
Neg logit contributions | |
oji | -0.146 |
anus | -0.142 |
ュ | -0.138 |
cair | -0.134 |
azor | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
oji | +0.537 |
anus | +0.520 |
ュ | +0.506 |
cair | +0.496 |
azor | +0.485 |
Neg logit contributions | |
lihood | -0.409 |
amounts | -0.398 |
ness | -0.386 |
entimes | -0.365 |
lin | -0.364 |
Token | but |
Token ID | 475 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
lihood | +0.799 |
amounts | +0.794 |
ness | +0.769 |
lin | +0.713 |
entimes | +0.706 |
Neg logit contributions | |
oji | -1.492 |
anus | -1.459 |
ュ | -1.417 |
cair | -1.407 |
azor | -1.359 |
Token | we |
Token ID | 356 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
oji | +3.761 |
anus | +3.555 |
ュ | +3.503 |
cair | +3.381 |
azor | +3.374 |
Neg logit contributions | |
lihood | -3.093 |
amounts | -2.948 |
ness | -2.883 |
CENT | -2.828 |
entimes | -2.784 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
oji | +1.418 |
anus | +1.365 |
ュ | +1.335 |
cair | +1.308 |
hetics | +1.273 |
Neg logit contributions | |
lihood | -0.963 |
amounts | -0.931 |
ness | -0.903 |
entimes | -0.847 |
lin | -0.842 |
Token | book |
Token ID | 1492 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
lihood | +1.079 |
amounts | +1.055 |
ness | +1.031 |
entimes | +0.979 |
lin | +0.972 |
Neg logit contributions | |
oji | -1.252 |
anus | -1.208 |
ュ | -1.171 |
cair | -1.153 |
azor | -1.114 |
Token | , |
Token ID | 11 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
lihood | +2.718 |
amounts | +2.683 |
ness | +2.644 |
lin | +2.471 |
entimes | +2.419 |
Neg logit contributions | |
oji | -3.955 |
anus | -3.884 |
ュ | -3.758 |
cair | -3.716 |
azor | -3.586 |
Token | somewhat |
Token ID | 6454 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
lihood | +0.908 |
amounts | +0.896 |
ness | +0.871 |
lin | +0.815 |
entimes | +0.809 |
Neg logit contributions | |
oji | -1.419 |
anus | -1.382 |
ュ | -1.346 |
cair | -1.328 |
azor | -1.286 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
lihood | +2.508 |
amounts | +2.496 |
ness | +2.484 |
lin | +2.299 |
entimes | +2.250 |
Neg logit contributions | |
oji | -4.438 |
anus | -4.372 |
cair | -4.252 |
ュ | -4.250 |
azor | -4.048 |
Token | but |
Token ID | 475 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
lihood | +0.485 |
amounts | +0.473 |
ness | +0.459 |
entimes | +0.427 |
lin | +0.426 |
Neg logit contributions | |
oji | -0.830 |
anus | -0.808 |
ュ | -0.786 |
cair | -0.775 |
azor | -0.755 |
Token | at |
Token ID | 379 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
oji | +4.284 |
anus | +3.994 |
ュ | +3.889 |
cair | +3.835 |
hetics | +3.805 |
Neg logit contributions | |
lihood | -3.817 |
amounts | -3.611 |
ness | -3.523 |
CENT | -3.416 |
entimes | -3.412 |
Token | the |
Token ID | 262 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
oji | +3.731 |
anus | +3.645 |
ュ | +3.531 |
cair | +3.470 |
uitous | +3.356 |
Neg logit contributions | |
lihood | -3.848 |
amounts | -3.731 |
ness | -3.677 |
CENT | -3.489 |
entimes | -3.479 |
Token | same |
Token ID | 976 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
oji | +1.867 |
anus | +1.809 |
ュ | +1.758 |
cair | +1.734 |
azor | +1.690 |
Neg logit contributions | |
lihood | -1.319 |
amounts | -1.280 |
ness | -1.254 |
entimes | -1.172 |
CENT | -1.171 |
Token | time |
Token ID | 640 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
oji | +0.769 |
anus | +0.740 |
ュ | +0.710 |
cair | +0.695 |
azor | +0.665 |
Neg logit contributions | |
lihood | -1.052 |
amounts | -1.038 |
ness | -1.020 |
lin | -0.974 |
entimes | -0.971 |
Token | it |
Token ID | 340 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
oji | +3.078 |
anus | +2.908 |
ュ | +2.847 |
cair | +2.777 |
hetics | +2.750 |
Neg logit contributions | |
lihood | -2.308 |
amounts | -2.202 |
ness | -2.132 |
CENT | -2.054 |
entimes | -2.050 |
Token | � |
Token ID | 447 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
oji | +0.879 |
anus | +0.855 |
ュ | +0.833 |
cair | +0.820 |
azor | +0.800 |
Neg logit contributions | |
lihood | -0.512 |
amounts | -0.493 |
ness | -0.481 |
entimes | -0.447 |
lin | -0.447 |
Token | game |
Token ID | 983 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
oji | +0.474 |
anus | +0.458 |
ュ | +0.445 |
cair | +0.429 |
azor | +0.422 |
Neg logit contributions | |
lihood | -0.517 |
amounts | -0.497 |
ness | -0.488 |
entimes | -0.474 |
CENT | -0.468 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
oji | +2.330 |
anus | +2.268 |
ュ | +2.199 |
cair | +2.167 |
azor | +2.114 |
Neg logit contributions | |
lihood | -1.790 |
amounts | -1.733 |
ness | -1.673 |
entimes | -1.632 |
CENT | -1.595 |
Token | despite |
Token ID | 3805 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
oji | +0.565 |
anus | +0.549 |
ュ | +0.532 |
cair | +0.523 |
azor | +0.509 |
Neg logit contributions | |
lihood | -0.427 |
amounts | -0.415 |
ness | -0.405 |
entimes | -0.382 |
lin | -0.380 |
Token | having |
Token ID | 1719 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
oji | +1.945 |
anus | +1.886 |
ュ | +1.828 |
cair | +1.789 |
azor | +1.744 |
Neg logit contributions | |
lihood | -1.807 |
amounts | -1.760 |
ness | -1.732 |
entimes | -1.653 |
CENT | -1.652 |
Token | good |
Token ID | 922 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
lihood | +0.141 |
amounts | +0.137 |
ness | +0.134 |
entimes | +0.127 |
lin | +0.126 |
Neg logit contributions | |
oji | -0.181 |
anus | -0.176 |
ュ | -0.170 |
cair | -0.167 |
azor | -0.163 |
Token | insurance |
Token ID | 5096 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
lihood | +0.307 |
amounts | +0.300 |
ness | +0.294 |
entimes | +0.278 |
lin | +0.277 |
Neg logit contributions | |
oji | -0.356 |
anus | -0.345 |
ュ | -0.334 |
cair | -0.328 |
azor | -0.318 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
oji | +4.773 |
anus | +4.672 |
ュ | +4.487 |
azor | +4.431 |
cair | +4.405 |
Neg logit contributions | |
lihood | -3.992 |
amounts | -3.590 |
entimes | -3.589 |
ness | -3.583 |
CENT | -3.554 |
Token | He |
Token ID | 679 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
oji | +0.534 |
anus | +0.514 |
ュ | +0.499 |
cair | +0.483 |
azor | +0.472 |
Neg logit contributions | |
lihood | -0.597 |
amounts | -0.589 |
ness | -0.573 |
entimes | -0.556 |
lin | -0.549 |
Token | had |
Token ID | 550 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
oji | +0.767 |
anus | +0.743 |
ュ | +0.720 |
cair | +0.708 |
azor | +0.689 |
Neg logit contributions | |
lihood | -0.587 |
amounts | -0.566 |
ness | -0.554 |
CENT | -0.522 |
lin | -0.521 |
Token | been |
Token ID | 587 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
lihood | +1.073 |
amounts | +1.059 |
ness | +1.031 |
lin | +0.975 |
entimes | +0.965 |
Neg logit contributions | |
oji | -1.331 |
anus | -1.286 |
ュ | -1.249 |
cair | -1.231 |
azor | -1.189 |
Token | off |
Token ID | 572 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
lihood | +0.810 |
amounts | +0.792 |
ness | +0.773 |
entimes | +0.726 |
lin | +0.726 |
Neg logit contributions | |
oji | -1.052 |
anus | -1.022 |
ュ | -0.990 |
cair | -0.975 |
azor | -0.946 |
Token | Government |
Token ID | 5070 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
oji | +0.298 |
anus | +0.288 |
ュ | +0.277 |
cair | +0.275 |
azor | +0.264 |
Neg logit contributions | |
lihood | -0.222 |
amounts | -0.218 |
ness | -0.212 |
entimes | -0.202 |
lin | -0.200 |
Token | came |
Token ID | 1625 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
oji | +1.203 |
anus | +1.160 |
ュ | +1.116 |
cair | +1.105 |
azor | +1.071 |
Neg logit contributions | |
lihood | -0.924 |
amounts | -0.901 |
ness | -0.878 |
entimes | -0.846 |
lin | -0.837 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
oji | +1.880 |
anus | +1.813 |
ュ | +1.760 |
cair | +1.729 |
azor | +1.690 |
Neg logit contributions | |
lihood | -1.077 |
amounts | -1.047 |
ness | -1.012 |
entimes | -0.966 |
CENT | -0.953 |
Token | power |
Token ID | 1176 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
oji | +2.917 |
anus | +2.810 |
ュ | +2.663 |
cair | +2.620 |
hetics | +2.539 |
Neg logit contributions | |
lihood | -2.796 |
amounts | -2.709 |
ness | -2.678 |
entimes | -2.594 |
CENT | -2.556 |
Token | . |
Token ID | 13 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
oji | +1.207 |
anus | +1.157 |
ュ | +1.119 |
cair | +1.110 |
azor | +1.074 |
Neg logit contributions | |
lihood | -0.943 |
amounts | -0.921 |
ness | -0.898 |
entimes | -0.868 |
lin | -0.857 |
Token | However |
Token ID | 2102 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
oji | +1.775 |
anus | +1.659 |
ュ | +1.647 |
cair | +1.589 |
License | +1.538 |
Neg logit contributions | |
lihood | -2.036 |
amounts | -2.017 |
ness | -1.960 |
entimes | -1.953 |
lin | -1.911 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
oji | +5.739 |
anus | +5.458 |
ュ | +5.342 |
cair | +5.288 |
uitous | +5.170 |
Neg logit contributions | |
lihood | -3.863 |
amounts | -3.746 |
ness | -3.655 |
lin | -3.535 |
entimes | -3.528 |
Token | most |
Token ID | 749 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
oji | +3.237 |
anus | +3.051 |
ュ | +2.957 |
cair | +2.943 |
uitous | +2.849 |
Neg logit contributions | |
lihood | -2.818 |
amounts | -2.716 |
ness | -2.687 |
entimes | -2.628 |
CENT | -2.598 |
Token | of |
Token ID | 286 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
oji | +2.154 |
anus | +2.031 |
ュ | +1.988 |
cair | +1.953 |
hetics | +1.867 |
Neg logit contributions | |
lihood | -2.215 |
amounts | -2.159 |
ness | -2.123 |
lin | -2.049 |
entimes | -2.045 |
Token | the |
Token ID | 262 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
oji | +0.698 |
anus | +0.676 |
ュ | +0.654 |
cair | +0.643 |
azor | +0.622 |
Neg logit contributions | |
lihood | -0.642 |
amounts | -0.631 |
ness | -0.617 |
lin | -0.584 |
entimes | -0.582 |
Token | States |
Token ID | 1829 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
oji | +1.431 |
anus | +1.373 |
ュ | +1.333 |
cair | +1.309 |
azor | +1.261 |
Neg logit contributions | |
lihood | -1.338 |
amounts | -1.296 |
ness | -1.277 |
entimes | -1.232 |
lin | -1.218 |
Token | and |
Token ID | 290 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
lihood | +0.356 |
amounts | +0.351 |
ness | +0.345 |
lin | +0.322 |
entimes | +0.318 |
Neg logit contributions | |
oji | -0.493 |
anus | -0.479 |
ュ | -0.465 |
cair | -0.459 |
azor | -0.442 |
Token | dem |
Token ID | 1357 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
oji | +1.112 |
anus | +1.078 |
ュ | +1.035 |
cair | +1.012 |
azor | +0.981 |
Neg logit contributions | |
lihood | -1.184 |
amounts | -1.153 |
ness | -1.130 |
entimes | -1.085 |
lin | -1.074 |
Token | ographer |
Token ID | 18539 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
lihood | +0.115 |
amounts | +0.113 |
ness | +0.109 |
entimes | +0.105 |
lin | +0.105 |
Neg logit contributions | |
oji | -0.124 |
anus | -0.119 |
ュ | -0.114 |
cair | -0.112 |
azor | -0.110 |
Token | at |
Token ID | 379 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
lihood | +0.633 |
amounts | +0.624 |
ness | +0.613 |
lin | +0.571 |
entimes | +0.563 |
Neg logit contributions | |
oji | -0.895 |
anus | -0.869 |
ュ | -0.843 |
cair | -0.834 |
azor | -0.802 |
Token | Pennsylvania |
Token ID | 9589 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
oji | +2.628 |
anus | +2.545 |
ュ | +2.453 |
cair | +2.413 |
azor | +2.335 |
Neg logit contributions | |
lihood | -2.780 |
amounts | -2.726 |
ness | -2.661 |
entimes | -2.574 |
lin | -2.535 |
Token | State |
Token ID | 1812 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
oji | +3.679 |
anus | +3.621 |
ュ | +3.414 |
cair | +3.333 |
azor | +3.166 |
Neg logit contributions | |
lihood | -5.616 |
amounts | -5.467 |
ness | -5.361 |
entimes | -5.245 |
CENT | -5.157 |
Token | University |
Token ID | 2059 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
oji | +2.497 |
anus | +2.302 |
ュ | +2.245 |
cair | +2.075 |
azor | +2.018 |
Neg logit contributions | |
lihood | -5.972 |
amounts | -5.873 |
ness | -5.752 |
entimes | -5.707 |
lin | -5.602 |
Token | . |
Token ID | 13 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
oji | +5.679 |
anus | +5.518 |
ュ | +5.375 |
cair | +5.284 |
azor | +5.182 |
Neg logit contributions | |
lihood | -4.380 |
amounts | -4.237 |
ness | -4.118 |
entimes | -4.051 |
lin | -3.958 |
Token | It |
Token ID | 632 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
oji | +1.410 |
anus | +1.352 |
ュ | +1.331 |
cair | +1.281 |
azor | +1.248 |
Neg logit contributions | |
lihood | -1.713 |
amounts | -1.677 |
ness | -1.640 |
entimes | -1.602 |
lin | -1.578 |
Token | adds |
Token ID | 6673 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
oji | +0.968 |
anus | +0.933 |
ュ | +0.913 |
cair | +0.897 |
azor | +0.874 |
Neg logit contributions | |
lihood | -0.744 |
amounts | -0.711 |
ness | -0.703 |
entimes | -0.668 |
CENT | -0.667 |
Token | to |
Token ID | 284 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
oji | +1.386 |
anus | +1.344 |
ュ | +1.308 |
cair | +1.282 |
azor | +1.244 |
Neg logit contributions | |
lihood | -1.125 |
amounts | -1.099 |
ness | -1.072 |
entimes | -1.022 |
lin | -1.012 |
Token | know |
Token ID | 760 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
lihood | +2.386 |
amounts | +2.342 |
ness | +2.284 |
lin | +2.151 |
entimes | +2.146 |
Neg logit contributions | |
oji | -3.046 |
anus | -2.956 |
ュ | -2.867 |
cair | -2.823 |
azor | -2.735 |
Token | how |
Token ID | 703 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
lihood | +0.925 |
amounts | +0.905 |
ness | +0.879 |
entimes | +0.830 |
CENT | +0.829 |
Neg logit contributions | |
oji | -1.331 |
anus | -1.286 |
ュ | -1.253 |
cair | -1.233 |
azor | -1.201 |
Token | guys |
Token ID | 3730 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
lihood | +2.091 |
amounts | +2.049 |
ness | +1.997 |
lin | +1.872 |
entimes | +1.859 |
Neg logit contributions | |
oji | -3.023 |
anus | -2.944 |
ュ | -2.860 |
cair | -2.820 |
azor | -2.734 |
Token | on |
Token ID | 319 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
lihood | +0.609 |
amounts | +0.590 |
ness | +0.572 |
CENT | +0.541 |
lin | +0.539 |
Neg logit contributions | |
oji | -0.873 |
anus | -0.843 |
ュ | -0.809 |
cair | -0.806 |
azor | -0.784 |
Token | either |
Token ID | 2035 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
lihood | +1.070 |
amounts | +1.056 |
ness | +1.035 |
lin | +0.980 |
entimes | +0.974 |
Neg logit contributions | |
oji | -1.157 |
anus | -1.121 |
ュ | -1.084 |
cair | -1.069 |
azor | -1.030 |
Token | side |
Token ID | 1735 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
oji | +2.158 |
anus | +1.999 |
ュ | +1.887 |
cair | +1.858 |
azor | +1.815 |
Neg logit contributions | |
lihood | -3.827 |
amounts | -3.732 |
ness | -3.643 |
CENT | -3.587 |
entimes | -3.578 |
Token | feel |
Token ID | 1254 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
oji | +3.517 |
anus | +3.252 |
cair | +3.149 |
ュ | +3.114 |
hetics | +3.086 |
Neg logit contributions | |
lihood | -3.359 |
amounts | -3.232 |
ness | -3.154 |
CENT | -3.076 |
LY | -3.067 |
Token | about |
Token ID | 546 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
oji | +0.007 |
anus | +0.007 |
ュ | +0.006 |
cair | +0.006 |
azor | +0.006 |
Neg logit contributions | |
lihood | -0.005 |
amounts | -0.005 |
ness | -0.005 |
CENT | -0.005 |
entimes | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
lihood | +1.276 |
amounts | +1.255 |
ness | +1.225 |
lin | +1.155 |
entimes | +1.146 |
Neg logit contributions | |
oji | -1.552 |
anus | -1.507 |
ュ | -1.459 |
cair | -1.438 |
azor | -1.390 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
lihood | +0.526 |
amounts | +0.514 |
ness | +0.500 |
lin | +0.468 |
entimes | +0.467 |
Neg logit contributions | |
oji | -0.802 |
anus | -0.780 |
ュ | -0.758 |
cair | -0.747 |
azor | -0.726 |
Token | I |
Token ID | 314 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
lihood | +0.811 |
amounts | +0.805 |
ness | +0.778 |
entimes | +0.753 |
lin | +0.748 |
Neg logit contributions | |
oji | -0.826 |
anus | -0.790 |
ュ | -0.771 |
cair | -0.751 |
azor | -0.729 |