Token | steps |
Token ID | 4831 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
esame | +1.122 |
(% | +1.048 |
atos | +0.984 |
ordan | +0.965 |
otal | +0.915 |
Neg logit contributions | |
miscar | -1.354 |
pard | -1.327 |
theless | -1.257 |
Ern | -1.234 |
\": | -1.207 |
Token | to |
Token ID | 284 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
miscar | +0.237 |
pard | +0.232 |
theless | +0.219 |
Ern | +0.214 |
\": | +0.210 |
Neg logit contributions | |
esame | -0.239 |
(% | -0.224 |
atos | -0.213 |
ordan | -0.209 |
otal | -0.199 |
Token | install |
Token ID | 2721 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
esame | +0.138 |
(% | +0.126 |
atos | +0.119 |
ordan | +0.116 |
otal | +0.108 |
Neg logit contributions | |
miscar | -0.217 |
pard | -0.213 |
theless | -0.204 |
Ern | -0.200 |
\": | -0.196 |
Token | Net |
Token ID | 3433 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
esame | +1.831 |
(% | +1.720 |
atos | +1.611 |
ordan | +1.576 |
otal | +1.500 |
Neg logit contributions | |
miscar | -2.128 |
pard | -2.074 |
theless | -1.959 |
Ern | -1.919 |
\": | -1.876 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
esame | +2.007 |
(% | +1.866 |
atos | +1.764 |
ordan | +1.726 |
otal | +1.654 |
Neg logit contributions | |
miscar | -2.234 |
pard | -2.175 |
theless | -2.048 |
Ern | -2.017 |
\": | -1.969 |
Token | i |
Token ID | 72 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
esame | +3.050 |
(% | +2.789 |
atos | +2.616 |
ordan | +2.542 |
otal | +2.438 |
Neg logit contributions | |
miscar | -4.282 |
pard | -4.186 |
theless | -4.036 |
Ern | -3.938 |
\": | -3.795 |
Token | X |
Token ID | 55 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
esame | +4.367 |
(% | +3.869 |
atos | +3.354 |
ordan | +3.264 |
otal | +3.026 |
Neg logit contributions | |
miscar | -10.740 |
pard | -10.369 |
theless | -10.020 |
Ern | -9.719 |
roe | -9.643 |
Token | B |
Token ID | 33 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
esame | +2.456 |
(% | +2.307 |
atos | +2.166 |
ordan | +2.107 |
otal | +2.008 |
Neg logit contributions | |
miscar | -2.851 |
pard | -2.758 |
theless | -2.650 |
Ern | -2.567 |
roe | -2.503 |
Token | MC |
Token ID | 9655 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
esame | +1.768 |
(% | +1.612 |
atos | +1.475 |
ordan | +1.441 |
otal | +1.341 |
Neg logit contributions | |
miscar | -3.293 |
pard | -3.233 |
theless | -3.106 |
Ern | -3.054 |
\": | -2.985 |
Token | around |
Token ID | 1088 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
esame | +2.642 |
(% | +2.501 |
atos | +2.333 |
ordan | +2.290 |
otal | +2.190 |
Neg logit contributions | |
miscar | -2.823 |
pard | -2.748 |
theless | -2.592 |
Ern | -2.538 |
\": | -2.478 |
Token | Kodi |
Token ID | 44129 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
esame | +1.050 |
(% | +0.983 |
atos | +0.926 |
ordan | +0.908 |
otal | +0.863 |
Neg logit contributions | |
miscar | -1.181 |
pard | -1.154 |
theless | -1.093 |
Ern | -1.071 |
\": | -1.047 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
esame | +0.392 |
(% | +0.367 |
atos | +0.348 |
ordan | +0.340 |
otal | +0.325 |
Neg logit contributions | |
miscar | -0.424 |
pard | -0.414 |
theless | -0.390 |
Ern | -0.384 |
\": | -0.375 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
esame | +1.214 |
(% | +1.136 |
atos | +1.061 |
ordan | +1.038 |
otal | +0.979 |
Neg logit contributions | |
miscar | -1.580 |
pard | -1.550 |
theless | -1.477 |
Ern | -1.442 |
\": | -1.412 |
Token | email |
Token ID | 3053 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
esame | +2.685 |
(% | +2.553 |
atos | +2.335 |
ordan | +2.307 |
ateral | +2.171 |
Neg logit contributions | |
miscar | -3.596 |
pard | -3.465 |
theless | -3.454 |
Ern | -3.299 |
hower | -3.269 |
Token | address |
Token ID | 2209 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
esame | +4.288 |
(% | +4.073 |
ordan | +3.637 |
atos | +3.522 |
ateral | +3.165 |
Neg logit contributions | |
theless | -7.980 |
miscar | -7.943 |
pard | -7.757 |
Ern | -7.452 |
hower | -7.414 |
Token | . |
Token ID | 13 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
esame | +3.377 |
(% | +3.216 |
atos | +2.933 |
ordan | +2.916 |
otal | +2.704 |
Neg logit contributions | |
miscar | -4.228 |
pard | -4.146 |
theless | -4.061 |
Ern | -3.853 |
hower | -3.776 |
Token | Please |
Token ID | 4222 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
(% | +5.024 |
esame | +4.982 |
atos | +4.516 |
ordan | +4.487 |
otal | +4.226 |
Neg logit contributions | |
miscar | -4.395 |
pard | -4.374 |
theless | -4.164 |
ricanes | -4.055 |
roe | -4.012 |
Token | re |
Token ID | 302 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
(% | +5.249 |
esame | +5.147 |
atos | +4.622 |
ordan | +4.493 |
otal | +4.174 |
Neg logit contributions | |
miscar | -7.534 |
theless | -7.380 |
pard | -7.294 |
hower | -7.146 |
Ern | -7.070 |
Token | - |
Token ID | 12 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
esame | +3.084 |
(% | +2.926 |
atos | +2.723 |
ordan | +2.680 |
otal | +2.533 |
Neg logit contributions | |
miscar | -3.460 |
pard | -3.385 |
theless | -3.303 |
Ern | -3.183 |
hower | -3.118 |
Token | enter |
Token ID | 9255 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
esame | +1.532 |
(% | +1.362 |
atos | +1.152 |
ordan | +1.101 |
otal | +0.971 |
Neg logit contributions | |
miscar | -5.402 |
pard | -5.318 |
theless | -5.160 |
Ern | -5.075 |
hower | -5.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
esame | +3.492 |
(% | +3.346 |
atos | +3.059 |
ordan | +3.018 |
ateral | +2.792 |
Neg logit contributions | |
miscar | -4.829 |
pard | -4.796 |
theless | -4.758 |
Ern | -4.485 |
hower | -4.473 |
Token | You |
Token ID | 921 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
esame | +2.768 |
(% | +2.653 |
atos | +2.511 |
ordan | +2.451 |
otal | +2.331 |
Neg logit contributions | |
miscar | -2.294 |
pard | -2.246 |
theless | -2.149 |
Ern | -2.047 |
roe | -1.988 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
esame | +0.100 |
(% | +0.093 |
atos | +0.089 |
ordan | +0.087 |
otal | +0.083 |
Neg logit contributions | |
miscar | -0.105 |
pard | -0.103 |
theless | -0.096 |
Ern | -0.095 |
\": | -0.093 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
esame | +1.256 |
(% | +1.177 |
atos | +1.097 |
ordan | +1.073 |
otal | +1.012 |
Neg logit contributions | |
miscar | -1.654 |
pard | -1.622 |
theless | -1.549 |
Ern | -1.510 |
\": | -1.477 |
Token | email |
Token ID | 3053 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
esame | +2.283 |
(% | +2.164 |
atos | +2.001 |
ordan | +1.969 |
otal | +1.850 |
Neg logit contributions | |
miscar | -2.929 |
pard | -2.826 |
theless | -2.793 |
Ern | -2.680 |
hower | -2.635 |
Token | address |
Token ID | 2209 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
esame | +4.136 |
(% | +3.949 |
ordan | +3.537 |
atos | +3.421 |
ateral | +3.078 |
Neg logit contributions | |
theless | -7.651 |
miscar | -7.627 |
pard | -7.446 |
Ern | -7.145 |
hower | -7.077 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
esame | +3.176 |
(% | +3.025 |
atos | +2.771 |
ordan | +2.751 |
otal | +2.555 |
Neg logit contributions | |
miscar | -3.930 |
pard | -3.851 |
theless | -3.756 |
Ern | -3.575 |
hower | -3.496 |
Token | Please |
Token ID | 4222 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
(% | +4.939 |
esame | +4.912 |
atos | +4.474 |
ordan | +4.446 |
otal | +4.203 |
Neg logit contributions | |
miscar | -4.222 |
pard | -4.190 |
theless | -3.994 |
ricanes | -3.841 |
roe | -3.809 |
Token | re |
Token ID | 302 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
(% | +5.206 |
esame | +5.034 |
atos | +4.569 |
ordan | +4.431 |
otal | +4.105 |
Neg logit contributions | |
miscar | -7.516 |
theless | -7.332 |
pard | -7.247 |
hower | -7.082 |
Ern | -6.992 |
Token | - |
Token ID | 12 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
esame | +2.854 |
(% | +2.705 |
atos | +2.525 |
ordan | +2.483 |
otal | +2.352 |
Neg logit contributions | |
miscar | -3.137 |
pard | -3.069 |
theless | -2.979 |
Ern | -2.875 |
hower | -2.811 |
Token | enter |
Token ID | 9255 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
esame | +1.512 |
(% | +1.348 |
atos | +1.150 |
ordan | +1.093 |
otal | +0.963 |
Neg logit contributions | |
miscar | -5.236 |
pard | -5.153 |
theless | -5.002 |
Ern | -4.919 |
hower | -4.850 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
esame | +3.399 |
(% | +3.261 |
atos | +2.984 |
ordan | +2.942 |
ateral | +2.720 |
Neg logit contributions | |
miscar | -4.660 |
pard | -4.622 |
theless | -4.572 |
Ern | -4.321 |
hower | -4.296 |
Token | You |
Token ID | 921 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
esame | +2.637 |
(% | +2.532 |
atos | +2.396 |
ordan | +2.337 |
otal | +2.225 |
Neg logit contributions | |
miscar | -2.182 |
pard | -2.135 |
theless | -2.042 |
Ern | -1.945 |
roe | -1.888 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
esame | +0.233 |
(% | +0.218 |
atos | +0.207 |
ordan | +0.202 |
otal | +0.194 |
Neg logit contributions | |
miscar | -0.247 |
pard | -0.241 |
theless | -0.226 |
Ern | -0.224 |
\": | -0.219 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
esame | +1.151 |
(% | +1.079 |
atos | +1.006 |
ordan | +0.984 |
otal | +0.928 |
Neg logit contributions | |
miscar | -1.508 |
pard | -1.481 |
theless | -1.412 |
Ern | -1.378 |
\": | -1.347 |
Token | email |
Token ID | 3053 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
esame | +2.434 |
(% | +2.314 |
atos | +2.123 |
ordan | +2.102 |
ateral | +1.968 |
Neg logit contributions | |
miscar | -3.198 |
pard | -3.085 |
theless | -3.066 |
Ern | -2.937 |
hower | -2.900 |
Token | address |
Token ID | 2209 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
esame | +3.778 |
(% | +3.575 |
ordan | +3.224 |
atos | +3.138 |
ateral | +2.817 |
Neg logit contributions | |
miscar | -6.701 |
theless | -6.672 |
pard | -6.546 |
Ern | -6.240 |
hower | -6.215 |
Token | . |
Token ID | 13 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
esame | +3.145 |
(% | +2.994 |
atos | +2.747 |
ordan | +2.724 |
otal | +2.529 |
Neg logit contributions | |
miscar | -3.885 |
pard | -3.811 |
theless | -3.720 |
Ern | -3.535 |
hower | -3.467 |
Token | Please |
Token ID | 4222 |
Feature activation | +8.48e+00 |
Pos logit contributions | |
(% | +4.683 |
esame | +4.666 |
atos | +4.251 |
ordan | +4.194 |
otal | +3.987 |
Neg logit contributions | |
miscar | -4.001 |
pard | -3.980 |
theless | -3.789 |
ricanes | -3.636 |
roe | -3.619 |
Token | re |
Token ID | 302 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
(% | +5.092 |
esame | +5.013 |
atos | +4.489 |
ordan | +4.339 |
otal | +4.065 |
Neg logit contributions | |
miscar | -7.180 |
theless | -6.994 |
pard | -6.962 |
hower | -6.794 |
Ern | -6.725 |
Token | - |
Token ID | 12 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
esame | +3.012 |
(% | +2.854 |
atos | +2.657 |
ordan | +2.621 |
otal | +2.470 |
Neg logit contributions | |
miscar | -3.374 |
pard | -3.300 |
theless | -3.219 |
Ern | -3.100 |
hower | -3.043 |
Token | enter |
Token ID | 9255 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
esame | +1.399 |
(% | +1.242 |
atos | +1.063 |
ordan | +1.020 |
otal | +0.896 |
Neg logit contributions | |
miscar | -4.731 |
pard | -4.657 |
theless | -4.517 |
Ern | -4.444 |
hower | -4.380 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
esame | +3.062 |
(% | +2.926 |
atos | +2.692 |
ordan | +2.654 |
ateral | +2.456 |
Neg logit contributions | |
miscar | -4.067 |
pard | -4.030 |
theless | -3.969 |
Ern | -3.768 |
hower | -3.734 |
Token | You |
Token ID | 921 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
esame | +2.330 |
(% | +2.235 |
atos | +2.118 |
ordan | +2.066 |
otal | +1.964 |
Neg logit contributions | |
miscar | -1.925 |
pard | -1.882 |
theless | -1.800 |
Ern | -1.715 |
roe | -1.666 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
esame | +0.405 |
(% | +0.378 |
atos | +0.359 |
ordan | +0.351 |
otal | +0.336 |
Neg logit contributions | |
miscar | -0.434 |
pard | -0.425 |
theless | -0.399 |
Ern | -0.393 |
\": | -0.385 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
esame | +1.253 |
(% | +1.176 |
atos | +1.094 |
ordan | +1.071 |
otal | +1.008 |
Neg logit contributions | |
miscar | -1.657 |
pard | -1.627 |
theless | -1.554 |
Ern | -1.513 |
roe | -1.482 |
Token | email |
Token ID | 3053 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
esame | +2.502 |
(% | +2.377 |
atos | +2.184 |
ordan | +2.158 |
otal | +2.029 |
Neg logit contributions | |
miscar | -3.258 |
pard | -3.141 |
theless | -3.111 |
Ern | -2.983 |
hower | -2.943 |
Token | address |
Token ID | 2209 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
esame | +4.094 |
(% | +3.899 |
ordan | +3.491 |
atos | +3.371 |
ateral | +3.034 |
Neg logit contributions | |
theless | -7.550 |
miscar | -7.534 |
pard | -7.349 |
Ern | -7.050 |
hower | -7.009 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
esame | +3.208 |
(% | +3.049 |
atos | +2.789 |
ordan | +2.775 |
otal | +2.577 |
Neg logit contributions | |
miscar | -3.979 |
pard | -3.899 |
theless | -3.809 |
Ern | -3.622 |
\": | -3.542 |
Token | Please |
Token ID | 4222 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
(% | +4.880 |
esame | +4.853 |
atos | +4.429 |
ordan | +4.376 |
Matrix | +4.136 |
Neg logit contributions | |
miscar | -4.231 |
pard | -4.216 |
theless | -4.020 |
ricanes | -3.875 |
roe | -3.844 |
Token | re |
Token ID | 302 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
(% | +5.048 |
esame | +4.954 |
atos | +4.465 |
ordan | +4.318 |
otal | +4.030 |
Neg logit contributions | |
miscar | -7.110 |
theless | -6.914 |
pard | -6.892 |
hower | -6.700 |
Ern | -6.652 |
Token | - |
Token ID | 12 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
esame | +2.930 |
(% | +2.775 |
atos | +2.590 |
ordan | +2.548 |
otal | +2.409 |
Neg logit contributions | |
miscar | -3.243 |
pard | -3.173 |
theless | -3.086 |
Ern | -2.978 |
hower | -2.912 |
Token | enter |
Token ID | 9255 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
esame | +1.458 |
(% | +1.298 |
atos | +1.104 |
ordan | +1.053 |
otal | +0.932 |
Neg logit contributions | |
miscar | -5.062 |
pard | -4.982 |
theless | -4.836 |
Ern | -4.759 |
hower | -4.692 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
esame | +3.292 |
(% | +3.150 |
atos | +2.888 |
ordan | +2.850 |
ateral | +2.636 |
Neg logit contributions | |
miscar | -4.453 |
pard | -4.413 |
theless | -4.359 |
Ern | -4.128 |
hower | -4.099 |
Token | You |
Token ID | 921 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
esame | +2.671 |
(% | +2.562 |
atos | +2.426 |
ordan | +2.365 |
otal | +2.248 |
Neg logit contributions | |
miscar | -2.231 |
pard | -2.186 |
theless | -2.095 |
Ern | -1.991 |
hower | -1.934 |
Token | clicking |
Token ID | 12264 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
esame | +1.084 |
(% | +0.989 |
atos | +0.899 |
ordan | +0.870 |
otal | +0.805 |
Neg logit contributions | |
miscar | -2.251 |
pard | -2.211 |
theless | -2.129 |
Ern | -2.090 |
\": | -2.057 |
Token | the |
Token ID | 262 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
esame | +1.906 |
(% | +1.790 |
atos | +1.682 |
ordan | +1.650 |
otal | +1.565 |
Neg logit contributions | |
miscar | -2.124 |
pard | -2.078 |
theless | -1.997 |
Ern | -1.941 |
\": | -1.896 |
Token | box |
Token ID | 3091 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
esame | +1.537 |
(% | +1.406 |
atos | +1.266 |
ordan | +1.229 |
otal | +1.138 |
Neg logit contributions | |
miscar | -3.198 |
pard | -3.137 |
theless | -3.027 |
Ern | -2.979 |
\": | -2.919 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
esame | +0.392 |
(% | +0.367 |
atos | +0.348 |
ordan | +0.340 |
otal | +0.325 |
Neg logit contributions | |
miscar | -0.424 |
pard | -0.414 |
theless | -0.390 |
Ern | -0.384 |
\": | -0.375 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
esame | +1.214 |
(% | +1.136 |
atos | +1.061 |
ordan | +1.038 |
otal | +0.979 |
Neg logit contributions | |
miscar | -1.580 |
pard | -1.550 |
theless | -1.477 |
Ern | -1.442 |
\": | -1.412 |
Token | email |
Token ID | 3053 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
esame | +2.685 |
(% | +2.553 |
atos | +2.335 |
ordan | +2.307 |
ateral | +2.171 |
Neg logit contributions | |
miscar | -3.596 |
pard | -3.465 |
theless | -3.454 |
Ern | -3.299 |
hower | -3.269 |
Token | address |
Token ID | 2209 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
esame | +4.288 |
(% | +4.073 |
ordan | +3.637 |
atos | +3.522 |
ateral | +3.165 |
Neg logit contributions | |
theless | -7.980 |
miscar | -7.943 |
pard | -7.757 |
Ern | -7.452 |
hower | -7.414 |
Token | . |
Token ID | 13 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
esame | +3.377 |
(% | +3.216 |
atos | +2.933 |
ordan | +2.916 |
otal | +2.704 |
Neg logit contributions | |
miscar | -4.228 |
pard | -4.146 |
theless | -4.061 |
Ern | -3.853 |
hower | -3.776 |
Token | Please |
Token ID | 4222 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
(% | +5.024 |
esame | +4.982 |
atos | +4.516 |
ordan | +4.487 |
otal | +4.226 |
Neg logit contributions | |
miscar | -4.395 |
pard | -4.374 |
theless | -4.164 |
ricanes | -4.055 |
roe | -4.012 |
Token | re |
Token ID | 302 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
(% | +5.249 |
esame | +5.147 |
atos | +4.622 |
ordan | +4.493 |
otal | +4.174 |
Neg logit contributions | |
miscar | -7.534 |
theless | -7.380 |
pard | -7.294 |
hower | -7.146 |
Ern | -7.070 |
Token | - |
Token ID | 12 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
esame | +3.084 |
(% | +2.926 |
atos | +2.723 |
ordan | +2.680 |
otal | +2.533 |
Neg logit contributions | |
miscar | -3.460 |
pard | -3.385 |
theless | -3.303 |
Ern | -3.183 |
hower | -3.118 |
Token | 20 |
Token ID | 1160 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
esame | +2.116 |
(% | +1.989 |
atos | +1.850 |
ordan | +1.802 |
otal | +1.701 |
Neg logit contributions | |
miscar | -2.850 |
pard | -2.797 |
theless | -2.678 |
Ern | -2.599 |
\": | -2.558 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
esame | +0.831 |
(% | +0.784 |
atos | +0.740 |
ordan | +0.726 |
otal | +0.692 |
Neg logit contributions | |
miscar | -0.834 |
pard | -0.814 |
theless | -0.771 |
Ern | -0.752 |
\": | -0.735 |
Token | 07 |
Token ID | 8753 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
esame | +1.657 |
(% | +1.542 |
atos | +1.439 |
ordan | +1.404 |
otal | +1.326 |
Neg logit contributions | |
miscar | -2.322 |
pard | -2.276 |
theless | -2.171 |
Ern | -2.126 |
\": | -2.085 |
Token | : |
Token ID | 25 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
esame | +1.321 |
(% | +1.249 |
atos | +1.191 |
ordan | +1.171 |
otal | +1.124 |
Neg logit contributions | |
miscar | -1.033 |
pard | -1.008 |
theless | -0.940 |
Ern | -0.920 |
\": | -0.897 |
Token | 50 |
Token ID | 1120 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
esame | +0.158 |
(% | +0.147 |
atos | +0.140 |
ordan | +0.138 |
otal | +0.132 |
Neg logit contributions | |
miscar | -0.144 |
pard | -0.141 |
theless | -0.132 |
Ern | -0.130 |
\": | -0.128 |
Token | pur |
Token ID | 1308 |
Feature activation | +8.31e+00 |
Pos logit contributions | |
esame | +0.299 |
(% | +0.282 |
atos | +0.268 |
ordan | +0.263 |
otal | +0.251 |
Neg logit contributions | |
miscar | -0.272 |
pard | -0.265 |
theless | -0.250 |
Ern | -0.244 |
\": | -0.238 |
Token | ak |
Token ID | 461 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
esame | +4.118 |
(% | +3.704 |
atos | +3.648 |
ordan | +3.311 |
otal | +3.167 |
Neg logit contributions | |
miscar | -8.482 |
pard | -8.165 |
theless | -7.972 |
Ern | -7.872 |
hower | -7.512 |
Token | ushi |
Token ID | 17731 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
esame | +3.849 |
(% | +3.481 |
atos | +3.321 |
ordan | +3.227 |
otal | +3.081 |
Neg logit contributions | |
miscar | -5.325 |
pard | -5.203 |
theless | -5.025 |
Ern | -4.924 |
\": | -4.693 |
Token | wrote |
Token ID | 2630 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
esame | +1.392 |
(% | +1.329 |
atos | +1.259 |
ordan | +1.227 |
otal | +1.182 |
Neg logit contributions | |
miscar | -1.264 |
pard | -1.232 |
theless | -1.176 |
Ern | -1.135 |
\": | -1.103 |
Token | : |
Token ID | 25 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
esame | +0.462 |
(% | +0.436 |
atos | +0.416 |
ordan | +0.410 |
otal | +0.393 |
Neg logit contributions | |
miscar | -0.358 |
pard | -0.349 |
theless | -0.324 |
Ern | -0.318 |
\": | -0.311 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
miscar | +1.403 |
pard | +1.374 |
\": | +1.245 |
theless | +1.240 |
Ern | +1.231 |
Neg logit contributions | |
esame | -1.920 |
(% | -1.771 |
atos | -1.729 |
ordan | -1.699 |
otal | -1.636 |
Token | clicking |
Token ID | 12264 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
esame | +0.753 |
(% | +0.683 |
atos | +0.630 |
ordan | +0.613 |
otal | +0.567 |
Neg logit contributions | |
miscar | -1.473 |
pard | -1.450 |
theless | -1.384 |
Ern | -1.366 |
\": | -1.341 |
Token | the |
Token ID | 262 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
esame | +1.799 |
(% | +1.688 |
atos | +1.588 |
ordan | +1.556 |
otal | +1.477 |
Neg logit contributions | |
miscar | -1.995 |
pard | -1.952 |
theless | -1.873 |
Ern | -1.821 |
\": | -1.778 |
Token | box |
Token ID | 3091 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
esame | +1.568 |
(% | +1.436 |
atos | +1.292 |
ordan | +1.253 |
otal | +1.161 |
Neg logit contributions | |
miscar | -3.283 |
pard | -3.218 |
theless | -3.109 |
Ern | -3.060 |
\": | -2.998 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
esame | +0.100 |
(% | +0.093 |
atos | +0.089 |
ordan | +0.087 |
otal | +0.083 |
Neg logit contributions | |
miscar | -0.105 |
pard | -0.103 |
theless | -0.096 |
Ern | -0.095 |
\": | -0.093 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
esame | +1.256 |
(% | +1.177 |
atos | +1.097 |
ordan | +1.073 |
otal | +1.012 |
Neg logit contributions | |
miscar | -1.654 |
pard | -1.622 |
theless | -1.549 |
Ern | -1.510 |
\": | -1.477 |
Token | email |
Token ID | 3053 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
esame | +2.283 |
(% | +2.164 |
atos | +2.001 |
ordan | +1.969 |
otal | +1.850 |
Neg logit contributions | |
miscar | -2.929 |
pard | -2.826 |
theless | -2.793 |
Ern | -2.680 |
hower | -2.635 |
Token | address |
Token ID | 2209 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
esame | +4.136 |
(% | +3.949 |
ordan | +3.537 |
atos | +3.421 |
ateral | +3.078 |
Neg logit contributions | |
theless | -7.651 |
miscar | -7.627 |
pard | -7.446 |
Ern | -7.145 |
hower | -7.077 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
esame | +3.176 |
(% | +3.025 |
atos | +2.771 |
ordan | +2.751 |
otal | +2.555 |
Neg logit contributions | |
miscar | -3.930 |
pard | -3.851 |
theless | -3.756 |
Ern | -3.575 |
hower | -3.496 |
Token | Please |
Token ID | 4222 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
(% | +4.939 |
esame | +4.912 |
atos | +4.474 |
ordan | +4.446 |
otal | +4.203 |
Neg logit contributions | |
miscar | -4.222 |
pard | -4.190 |
theless | -3.994 |
ricanes | -3.841 |
roe | -3.809 |
Token | re |
Token ID | 302 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
(% | +5.206 |
esame | +5.034 |
atos | +4.569 |
ordan | +4.431 |
otal | +4.105 |
Neg logit contributions | |
miscar | -7.516 |
theless | -7.332 |
pard | -7.247 |
hower | -7.082 |
Ern | -6.992 |
Token | - |
Token ID | 12 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
esame | +2.854 |
(% | +2.705 |
atos | +2.525 |
ordan | +2.483 |
otal | +2.352 |
Neg logit contributions | |
miscar | -3.137 |
pard | -3.069 |
theless | -2.979 |
Ern | -2.875 |
hower | -2.811 |
Token | angle |
Token ID | 9248 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
esame | +0.802 |
(% | +0.752 |
atos | +0.704 |
ordan | +0.689 |
otal | +0.652 |
Neg logit contributions | |
miscar | -1.012 |
pard | -0.991 |
theless | -0.944 |
Ern | -0.921 |
\": | -0.902 |
Token | F |
Token ID | 37 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
esame | +1.782 |
(% | +1.701 |
atos | +1.580 |
ordan | +1.553 |
otal | +1.478 |
Neg logit contributions | |
miscar | -1.909 |
pard | -1.865 |
theless | -1.771 |
Ern | -1.708 |
\": | -1.683 |
Token | ( |
Token ID | 357 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
esame | +3.317 |
(% | +3.129 |
atos | +2.896 |
ordan | +2.854 |
otal | +2.692 |
Neg logit contributions | |
miscar | -4.495 |
pard | -4.371 |
theless | -4.164 |
Ern | -4.058 |
\": | -3.965 |
Token | 0 |
Token ID | 15 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
esame | +1.643 |
(% | +1.563 |
atos | +1.455 |
ordan | +1.423 |
otal | +1.358 |
Neg logit contributions | |
miscar | -1.769 |
pard | -1.735 |
theless | -1.647 |
Ern | -1.598 |
\": | -1.573 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
esame | +3.024 |
(% | +2.840 |
atos | +2.616 |
ordan | +2.595 |
otal | +2.464 |
Neg logit contributions | |
miscar | -3.739 |
pard | -3.668 |
theless | -3.531 |
Ern | -3.414 |
\": | -3.359 |
Token | ($ |
Token ID | 16763 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
esame | +2.475 |
(% | +2.342 |
atos | +2.166 |
ordan | +2.123 |
otal | +2.010 |
Neg logit contributions | |
miscar | -3.144 |
pard | -3.076 |
theless | -2.926 |
Ern | -2.852 |
\": | -2.805 |
Token | s |
Token ID | 82 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
esame | +5.657 |
(% | +5.333 |
atos | +5.102 |
ordan | +4.973 |
ADS | +4.736 |
Neg logit contributions | |
miscar | -6.222 |
pard | -5.949 |
theless | -5.829 |
Ern | -5.570 |
hower | -5.363 |
Token | z |
Token ID | 89 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
esame | +2.437 |
(% | +2.301 |
atos | +2.178 |
ordan | +2.141 |
otal | +2.047 |
Neg logit contributions | |
miscar | -2.203 |
pard | -2.139 |
theless | -2.037 |
Ern | -1.986 |
\": | -1.904 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
esame | +1.043 |
(% | +0.973 |
atos | +0.906 |
ordan | +0.884 |
otal | +0.840 |
Neg logit contributions | |
miscar | -1.409 |
pard | -1.375 |
theless | -1.328 |
Ern | -1.283 |
\": | -1.249 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
esame | +1.217 |
(% | +1.139 |
atos | +1.073 |
ordan | +1.052 |
otal | +1.000 |
Neg logit contributions | |
miscar | -1.379 |
pard | -1.349 |
theless | -1.279 |
Ern | -1.253 |
\": | -1.225 |
Token | Height |
Token ID | 23106 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
esame | +2.467 |
(% | +2.329 |
atos | +2.187 |
ordan | +2.151 |
otal | +2.060 |
Neg logit contributions | |
miscar | -2.485 |
pard | -2.432 |
theless | -2.318 |
Ern | -2.243 |
hower | -2.171 |
Token | re |
Token ID | 302 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
(% | +5.249 |
esame | +5.147 |
atos | +4.622 |
ordan | +4.493 |
otal | +4.174 |
Neg logit contributions | |
miscar | -7.534 |
theless | -7.380 |
pard | -7.294 |
hower | -7.146 |
Ern | -7.070 |
Token | - |
Token ID | 12 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
esame | +3.084 |
(% | +2.926 |
atos | +2.723 |
ordan | +2.680 |
otal | +2.533 |
Neg logit contributions | |
miscar | -3.460 |
pard | -3.385 |
theless | -3.303 |
Ern | -3.183 |
hower | -3.118 |
Token | enter |
Token ID | 9255 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
esame | +1.532 |
(% | +1.362 |
atos | +1.152 |
ordan | +1.101 |
otal | +0.971 |
Neg logit contributions | |
miscar | -5.402 |
pard | -5.318 |
theless | -5.160 |
Ern | -5.075 |
hower | -5.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
esame | +3.492 |
(% | +3.346 |
atos | +3.059 |
ordan | +3.018 |
ateral | +2.792 |
Neg logit contributions | |
miscar | -4.829 |
pard | -4.796 |
theless | -4.758 |
Ern | -4.485 |
hower | -4.473 |
Token | You |
Token ID | 921 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
esame | +2.768 |
(% | +2.653 |
atos | +2.511 |
ordan | +2.451 |
otal | +2.331 |
Neg logit contributions | |
miscar | -2.294 |
pard | -2.246 |
theless | -2.149 |
Ern | -2.047 |
roe | -1.988 |
Token | must |
Token ID | 1276 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
esame | +4.641 |
(% | +4.563 |
atos | +4.129 |
ordan | +4.090 |
otal | +3.816 |
Neg logit contributions | |
miscar | -4.754 |
theless | -4.636 |
pard | -4.613 |
Ern | -4.374 |
hower | -4.332 |
Token | select |
Token ID | 2922 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
esame | +4.683 |
(% | +4.588 |
atos | +4.055 |
ordan | +3.822 |
otal | +3.689 |
Neg logit contributions | |
miscar | -7.004 |
theless | -6.975 |
pard | -6.795 |
Ern | -6.613 |
hower | -6.480 |
Token | a |
Token ID | 257 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
esame | +3.558 |
(% | +3.407 |
atos | +3.068 |
ordan | +3.036 |
otal | +2.830 |
Neg logit contributions | |
miscar | -5.024 |
pard | -4.889 |
theless | -4.844 |
Ern | -4.661 |
hower | -4.565 |
Token | newsletter |
Token ID | 13129 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
esame | +4.242 |
(% | +4.057 |
atos | +3.716 |
ordan | +3.711 |
ateral | +3.493 |
Neg logit contributions | |
miscar | -3.958 |
theless | -3.801 |
pard | -3.775 |
Ern | -3.644 |
\": | -3.528 |
Token | to |
Token ID | 284 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
esame | +1.988 |
(% | +1.866 |
atos | +1.726 |
ordan | +1.699 |
otal | +1.590 |
Neg logit contributions | |
miscar | -2.696 |
pard | -2.645 |
theless | -2.548 |
Ern | -2.474 |
\": | -2.417 |
Token | subscribe |
Token ID | 12383 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
esame | +1.573 |
(% | +1.445 |
atos | +1.301 |
ordan | +1.282 |
otal | +1.181 |
Neg logit contributions | |
miscar | -3.127 |
pard | -3.083 |
theless | -2.972 |
Ern | -2.902 |
\": | -2.851 |
Token | clicking |
Token ID | 12264 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
esame | +0.876 |
(% | +0.797 |
atos | +0.730 |
ordan | +0.707 |
otal | +0.655 |
Neg logit contributions | |
miscar | -1.764 |
pard | -1.734 |
theless | -1.663 |
Ern | -1.636 |
\": | -1.608 |
Token | the |
Token ID | 262 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
esame | +1.796 |
(% | +1.686 |
atos | +1.585 |
ordan | +1.557 |
otal | +1.476 |
Neg logit contributions | |
miscar | -1.983 |
pard | -1.941 |
theless | -1.860 |
Ern | -1.811 |
\": | -1.768 |
Token | box |
Token ID | 3091 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
esame | +1.597 |
(% | +1.463 |
atos | +1.312 |
ordan | +1.275 |
otal | +1.178 |
Neg logit contributions | |
miscar | -3.362 |
pard | -3.296 |
theless | -3.188 |
Ern | -3.136 |
\": | -3.073 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
esame | +0.405 |
(% | +0.378 |
atos | +0.359 |
ordan | +0.351 |
otal | +0.336 |
Neg logit contributions | |
miscar | -0.434 |
pard | -0.425 |
theless | -0.399 |
Ern | -0.393 |
\": | -0.385 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
esame | +1.253 |
(% | +1.176 |
atos | +1.094 |
ordan | +1.071 |
otal | +1.008 |
Neg logit contributions | |
miscar | -1.657 |
pard | -1.627 |
theless | -1.554 |
Ern | -1.513 |
roe | -1.482 |
Token | email |
Token ID | 3053 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
esame | +2.502 |
(% | +2.377 |
atos | +2.184 |
ordan | +2.158 |
otal | +2.029 |
Neg logit contributions | |
miscar | -3.258 |
pard | -3.141 |
theless | -3.111 |
Ern | -2.983 |
hower | -2.943 |
Token | address |
Token ID | 2209 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
esame | +4.094 |
(% | +3.899 |
ordan | +3.491 |
atos | +3.371 |
ateral | +3.034 |
Neg logit contributions | |
theless | -7.550 |
miscar | -7.534 |
pard | -7.349 |
Ern | -7.050 |
hower | -7.009 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
esame | +3.208 |
(% | +3.049 |
atos | +2.789 |
ordan | +2.775 |
otal | +2.577 |
Neg logit contributions | |
miscar | -3.979 |
pard | -3.899 |
theless | -3.809 |
Ern | -3.622 |
\": | -3.542 |
Token | Please |
Token ID | 4222 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
(% | +4.880 |
esame | +4.853 |
atos | +4.429 |
ordan | +4.376 |
Matrix | +4.136 |
Neg logit contributions | |
miscar | -4.231 |
pard | -4.216 |
theless | -4.020 |
ricanes | -3.875 |
roe | -3.844 |
Token | re |
Token ID | 302 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
(% | +5.048 |
esame | +4.954 |
atos | +4.465 |
ordan | +4.318 |
otal | +4.030 |
Neg logit contributions | |
miscar | -7.110 |
theless | -6.914 |
pard | -6.892 |
hower | -6.700 |
Ern | -6.652 |
Token | - |
Token ID | 12 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
esame | +2.930 |
(% | +2.775 |
atos | +2.590 |
ordan | +2.548 |
otal | +2.409 |
Neg logit contributions | |
miscar | -3.243 |
pard | -3.173 |
theless | -3.086 |
Ern | -2.978 |
hower | -2.912 |
Token | re |
Token ID | 302 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
(% | +5.048 |
esame | +4.954 |
atos | +4.465 |
ordan | +4.318 |
otal | +4.030 |
Neg logit contributions | |
miscar | -7.110 |
theless | -6.914 |
pard | -6.892 |
hower | -6.700 |
Ern | -6.652 |
Token | - |
Token ID | 12 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
esame | +2.930 |
(% | +2.775 |
atos | +2.590 |
ordan | +2.548 |
otal | +2.409 |
Neg logit contributions | |
miscar | -3.243 |
pard | -3.173 |
theless | -3.086 |
Ern | -2.978 |
hower | -2.912 |
Token | enter |
Token ID | 9255 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
esame | +1.458 |
(% | +1.298 |
atos | +1.104 |
ordan | +1.053 |
otal | +0.932 |
Neg logit contributions | |
miscar | -5.062 |
pard | -4.982 |
theless | -4.836 |
Ern | -4.759 |
hower | -4.692 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
esame | +3.292 |
(% | +3.150 |
atos | +2.888 |
ordan | +2.850 |
ateral | +2.636 |
Neg logit contributions | |
miscar | -4.453 |
pard | -4.413 |
theless | -4.359 |
Ern | -4.128 |
hower | -4.099 |
Token | You |
Token ID | 921 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
esame | +2.671 |
(% | +2.562 |
atos | +2.426 |
ordan | +2.365 |
otal | +2.248 |
Neg logit contributions | |
miscar | -2.231 |
pard | -2.186 |
theless | -2.095 |
Ern | -1.991 |
hower | -1.934 |
Token | must |
Token ID | 1276 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
esame | +4.551 |
(% | +4.453 |
atos | +4.061 |
ordan | +4.017 |
otal | +3.752 |
Neg logit contributions | |
miscar | -4.595 |
pard | -4.455 |
theless | -4.447 |
Ern | -4.214 |
hower | -4.156 |
Token | select |
Token ID | 2922 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
esame | +4.652 |
(% | +4.552 |
atos | +4.055 |
ordan | +3.796 |
otal | +3.667 |
Neg logit contributions | |
miscar | -6.991 |
theless | -6.933 |
pard | -6.766 |
Ern | -6.579 |
hower | -6.426 |
Token | a |
Token ID | 257 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
esame | +3.501 |
(% | +3.357 |
atos | +3.025 |
ordan | +2.994 |
ateral | +2.789 |
Neg logit contributions | |
miscar | -4.935 |
pard | -4.803 |
theless | -4.756 |
Ern | -4.571 |
hower | -4.480 |
Token | newsletter |
Token ID | 13129 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
esame | +4.138 |
(% | +3.966 |
atos | +3.644 |
ordan | +3.631 |
ateral | +3.424 |
Neg logit contributions | |
miscar | -3.770 |
pard | -3.601 |
theless | -3.598 |
Ern | -3.451 |
\": | -3.347 |
Token | to |
Token ID | 284 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
esame | +1.661 |
(% | +1.554 |
atos | +1.446 |
ordan | +1.419 |
otal | +1.335 |
Neg logit contributions | |
miscar | -2.198 |
pard | -2.155 |
theless | -2.064 |
Ern | -2.013 |
\": | -1.968 |
Token | subscribe |
Token ID | 12383 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
esame | +1.414 |
(% | +1.298 |
atos | +1.173 |
ordan | +1.154 |
otal | +1.064 |
Neg logit contributions | |
miscar | -2.780 |
pard | -2.738 |
theless | -2.636 |
Ern | -2.578 |
\": | -2.533 |
Token | cv |
Token ID | 33967 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
esame | +0.229 |
(% | +0.213 |
atos | +0.200 |
ordan | +0.196 |
otal | +0.186 |
Neg logit contributions | |
miscar | -0.284 |
pard | -0.278 |
theless | -0.264 |
Ern | -0.259 |
\": | -0.254 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
esame | +1.307 |
(% | +1.225 |
atos | +1.155 |
ordan | +1.131 |
otal | +1.078 |
Neg logit contributions | |
miscar | -1.430 |
pard | -1.399 |
theless | -1.318 |
Ern | -1.297 |
\": | -1.271 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
esame | +1.039 |
(% | +0.970 |
atos | +0.921 |
ordan | +0.900 |
otal | +0.862 |
Neg logit contributions | |
miscar | -1.089 |
pard | -1.064 |
theless | -0.995 |
Ern | -0.984 |
\": | -0.970 |
Token | M |
Token ID | 44 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
esame | +1.322 |
(% | +1.237 |
atos | +1.162 |
ordan | +1.140 |
otal | +1.083 |
Neg logit contributions | |
miscar | -1.538 |
pard | -1.509 |
theless | -1.429 |
Ern | -1.400 |
\": | -1.368 |
Token | OR |
Token ID | 1581 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
esame | +1.862 |
(% | +1.737 |
atos | +1.632 |
ordan | +1.598 |
otal | +1.515 |
Neg logit contributions | |
miscar | -2.296 |
pard | -2.249 |
theless | -2.138 |
Ern | -2.096 |
\": | -2.049 |
Token | PH |
Token ID | 11909 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
esame | +3.082 |
(% | +2.913 |
atos | +2.713 |
ordan | +2.674 |
otal | +2.548 |
Neg logit contributions | |
miscar | -3.305 |
pard | -3.242 |
theless | -3.129 |
Ern | -3.024 |
roe | -2.913 |
Token | _ |
Token ID | 62 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
esame | +4.843 |
(% | +4.731 |
atos | +4.254 |
ordan | +4.133 |
otal | +3.914 |
Neg logit contributions | |
miscar | -6.869 |
pard | -6.767 |
theless | -6.695 |
Ern | -6.343 |
hower | -6.266 |
Token | RECT |
Token ID | 23988 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
esame | +0.749 |
(% | +0.710 |
atos | +0.678 |
ordan | +0.667 |
otal | +0.642 |
Neg logit contributions | |
miscar | -0.537 |
pard | -0.523 |
theless | -0.487 |
Ern | -0.475 |
\": | -0.461 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
esame | +2.945 |
(% | +2.784 |
atos | +2.544 |
ordan | +2.529 |
otal | +2.419 |
Neg logit contributions | |
miscar | -3.667 |
pard | -3.601 |
theless | -3.432 |
Ern | -3.369 |
\": | -3.297 |
Token | ( |
Token ID | 357 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
esame | +1.515 |
(% | +1.447 |
atos | +1.347 |
ordan | +1.325 |
otal | +1.265 |
Neg logit contributions | |
miscar | -1.590 |
pard | -1.550 |
theless | -1.476 |
Ern | -1.436 |
\": | -1.408 |
Token | 21 |
Token ID | 2481 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
esame | +3.114 |
(% | +2.930 |
atos | +2.759 |
ordan | +2.696 |
otal | +2.557 |
Neg logit contributions | |
miscar | -3.692 |
pard | -3.609 |
theless | -3.444 |
Ern | -3.373 |
\": | -3.262 |
Token | with |
Token ID | 351 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
esame | +2.219 |
(% | +2.136 |
atos | +1.992 |
ordan | +1.963 |
otal | +1.872 |
Neg logit contributions | |
miscar | -2.033 |
pard | -1.978 |
theless | -1.913 |
Ern | -1.836 |
roe | -1.777 |
Token | kindred |
Token ID | 46449 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
miscar | +0.949 |
pard | +0.933 |
theless | +0.866 |
Ern | +0.855 |
\": | +0.834 |
Neg logit contributions | |
esame | -1.041 |
(% | -0.973 |
atos | -0.928 |
ordan | -0.910 |
otal | -0.870 |
Token | spirits |
Token ID | 13747 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
esame | +1.481 |
(% | +1.371 |
atos | +1.256 |
ordan | +1.218 |
otal | +1.139 |
Neg logit contributions | |
miscar | -2.621 |
pard | -2.558 |
theless | -2.479 |
Ern | -2.443 |
hower | -2.400 |
Token | . |
Token ID | 13 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
esame | +1.891 |
(% | +1.777 |
atos | +1.667 |
ordan | +1.636 |
otal | +1.551 |
Neg logit contributions | |
miscar | -2.155 |
pard | -2.109 |
theless | -2.014 |
Ern | -1.959 |
\": | -1.907 |
Token |
|
Token ID | 198 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
esame | +4.608 |
(% | +4.482 |
atos | +4.124 |
ordan | +4.067 |
otal | +3.790 |
Neg logit contributions | |
miscar | -5.018 |
pard | -4.904 |
theless | -4.835 |
Ern | -4.552 |
roe | -4.471 |
Token |
|
Token ID | 198 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
esame | +4.757 |
(% | +4.645 |
atos | +4.262 |
ordan | +4.202 |
otal | +3.930 |
Neg logit contributions | |
miscar | -5.370 |
pard | -5.290 |
theless | -5.266 |
Ern | -4.955 |
hower | -4.862 |
Token | Sign |
Token ID | 11712 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
esame | +4.529 |
(% | +4.236 |
atos | +4.068 |
ordan | +3.850 |
otal | +3.606 |
Neg logit contributions | |
miscar | -7.371 |
pard | -7.155 |
theless | -6.971 |
Ern | -6.661 |
roe | -6.636 |
Token | up |
Token ID | 510 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
esame | +1.516 |
(% | +1.385 |
atos | +1.274 |
ordan | +1.238 |
otal | +1.153 |
Neg logit contributions | |
miscar | -2.814 |
pard | -2.762 |
theless | -2.649 |
Ern | -2.604 |
\": | -2.555 |
Token | for |
Token ID | 329 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
esame | +1.055 |
(% | +0.974 |
atos | +0.919 |
ordan | +0.899 |
otal | +0.850 |
Neg logit contributions | |
miscar | -1.426 |
pard | -1.402 |
theless | -1.317 |
Ern | -1.304 |
\": | -1.283 |
Token | our |
Token ID | 674 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
esame | +3.244 |
(% | +3.079 |
atos | +2.931 |
ordan | +2.884 |
otal | +2.762 |
Neg logit contributions | |
miscar | -2.757 |
pard | -2.679 |
theless | -2.544 |
Ern | -2.461 |
roe | -2.396 |
Token | Wine |
Token ID | 20447 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
esame | +1.529 |
(% | +1.421 |
atos | +1.334 |
ordan | +1.300 |
otal | +1.233 |
Neg logit contributions | |
miscar | -2.024 |
pard | -1.984 |
theless | -1.887 |
Ern | -1.850 |
\": | -1.815 |
Token | , |
Token ID | 11 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
esame | +1.828 |
(% | +1.726 |
atos | +1.613 |
ordan | +1.580 |
otal | +1.498 |
Neg logit contributions | |
miscar | -2.116 |
pard | -2.075 |
theless | -1.984 |
Ern | -1.932 |
\": | -1.876 |
Token | and |
Token ID | 290 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
esame | +3.129 |
(% | +2.991 |
atos | +2.777 |
ordan | +2.731 |
otal | +2.593 |
Neg logit contributions | |
miscar | -3.311 |
pard | -3.252 |
theless | -3.168 |
Ern | -3.023 |
hower | -2.966 |
Token | must |
Token ID | 1276 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
esame | +3.935 |
(% | +3.771 |
atos | +3.447 |
ordan | +3.336 |
otal | +3.297 |
Neg logit contributions | |
miscar | -3.886 |
theless | -3.805 |
pard | -3.789 |
Ern | -3.592 |
hower | -3.535 |
Token | roll |
Token ID | 4836 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
esame | +2.570 |
(% | +2.458 |
atos | +2.238 |
ordan | +2.194 |
otal | +2.133 |
Neg logit contributions | |
miscar | -3.245 |
pard | -3.207 |
theless | -3.103 |
Ern | -2.989 |
hower | -2.915 |
Token | to |
Token ID | 284 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
esame | +3.885 |
(% | +3.715 |
atos | +3.283 |
ordan | +3.247 |
otal | +3.025 |
Neg logit contributions | |
miscar | -6.291 |
pard | -6.169 |
theless | -6.154 |
Ern | -5.900 |
hower | -5.813 |
Token | avoid |
Token ID | 3368 |
Feature activation | +7.78e+00 |
Pos logit contributions | |
esame | +2.392 |
(% | +2.245 |
atos | +2.111 |
ordan | +2.086 |
otal | +1.969 |
Neg logit contributions | |
miscar | -2.696 |
pard | -2.646 |
theless | -2.513 |
Ern | -2.455 |
\": | -2.396 |
Token | following |
Token ID | 1708 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
esame | +4.383 |
(% | +4.374 |
atos | +3.933 |
ordan | +3.768 |
otal | +3.631 |
Neg logit contributions | |
pard | -6.846 |
miscar | -6.844 |
theless | -6.690 |
Ern | -6.552 |
roe | -6.346 |
Token | the |
Token ID | 262 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
esame | +3.252 |
(% | +3.104 |
atos | +2.881 |
ordan | +2.818 |
ateral | +2.636 |
Neg logit contributions | |
miscar | -4.090 |
pard | -4.020 |
theless | -3.936 |
Ern | -3.747 |
roe | -3.687 |
Token | commands |
Token ID | 9729 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
esame | +1.943 |
(% | +1.843 |
atos | +1.732 |
ordan | +1.694 |
otal | +1.600 |
Neg logit contributions | |
miscar | -2.145 |
pard | -2.088 |
theless | -2.044 |
Ern | -1.975 |
roe | -1.909 |
Token | in |
Token ID | 287 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
esame | +0.305 |
(% | +0.288 |
atos | +0.274 |
ordan | +0.269 |
otal | +0.258 |
Neg logit contributions | |
miscar | -0.258 |
pard | -0.252 |
theless | -0.236 |
Ern | -0.231 |
\": | -0.225 |
Token | his |
Token ID | 465 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
esame | +0.943 |
(% | +0.880 |
atos | +0.825 |
ordan | +0.806 |
otal | +0.763 |
Neg logit contributions | |
miscar | -1.208 |
pard | -1.184 |
theless | -1.127 |
Ern | -1.105 |
\": | -1.081 |
Token | re |
Token ID | 302 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
(% | +5.092 |
esame | +5.013 |
atos | +4.489 |
ordan | +4.339 |
otal | +4.065 |
Neg logit contributions | |
miscar | -7.180 |
theless | -6.994 |
pard | -6.962 |
hower | -6.794 |
Ern | -6.725 |
Token | - |
Token ID | 12 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
esame | +3.012 |
(% | +2.854 |
atos | +2.657 |
ordan | +2.621 |
otal | +2.470 |
Neg logit contributions | |
miscar | -3.374 |
pard | -3.300 |
theless | -3.219 |
Ern | -3.100 |
hower | -3.043 |
Token | enter |
Token ID | 9255 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
esame | +1.399 |
(% | +1.242 |
atos | +1.063 |
ordan | +1.020 |
otal | +0.896 |
Neg logit contributions | |
miscar | -4.731 |
pard | -4.657 |
theless | -4.517 |
Ern | -4.444 |
hower | -4.380 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
esame | +3.062 |
(% | +2.926 |
atos | +2.692 |
ordan | +2.654 |
ateral | +2.456 |
Neg logit contributions | |
miscar | -4.067 |
pard | -4.030 |
theless | -3.969 |
Ern | -3.768 |
hower | -3.734 |
Token | You |
Token ID | 921 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
esame | +2.330 |
(% | +2.235 |
atos | +2.118 |
ordan | +2.066 |
otal | +1.964 |
Neg logit contributions | |
miscar | -1.925 |
pard | -1.882 |
theless | -1.800 |
Ern | -1.715 |
roe | -1.666 |
Token | must |
Token ID | 1276 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
esame | +4.376 |
(% | +4.274 |
atos | +3.901 |
ordan | +3.853 |
otal | +3.606 |
Neg logit contributions | |
miscar | -4.372 |
pard | -4.234 |
theless | -4.220 |
Ern | -3.997 |
hower | -3.942 |
Token | select |
Token ID | 2922 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
esame | +4.578 |
(% | +4.485 |
atos | +3.994 |
ordan | +3.747 |
otal | +3.607 |
Neg logit contributions | |
miscar | -6.857 |
theless | -6.784 |
pard | -6.629 |
Ern | -6.431 |
hower | -6.326 |
Token | a |
Token ID | 257 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
esame | +3.253 |
(% | +3.108 |
atos | +2.825 |
ordan | +2.781 |
otal | +2.601 |
Neg logit contributions | |
miscar | -4.478 |
pard | -4.361 |
theless | -4.288 |
Ern | -4.137 |
hower | -4.050 |
Token | newsletter |
Token ID | 13129 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
esame | +3.872 |
(% | +3.703 |
atos | +3.417 |
ordan | +3.413 |
ateral | +3.203 |
Neg logit contributions | |
miscar | -3.513 |
pard | -3.362 |
theless | -3.346 |
Ern | -3.209 |
\": | -3.134 |
Token | to |
Token ID | 284 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
esame | +1.567 |
(% | +1.465 |
atos | +1.365 |
ordan | +1.339 |
otal | +1.260 |
Neg logit contributions | |
miscar | -2.065 |
pard | -2.025 |
theless | -1.938 |
Ern | -1.891 |
\": | -1.849 |
Token | subscribe |
Token ID | 12383 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
esame | +1.391 |
(% | +1.278 |
atos | +1.154 |
ordan | +1.134 |
otal | +1.046 |
Neg logit contributions | |
miscar | -2.745 |
pard | -2.705 |
theless | -2.604 |
Ern | -2.546 |
\": | -2.501 |
Token | re |
Token ID | 302 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
(% | +5.206 |
esame | +5.034 |
atos | +4.569 |
ordan | +4.431 |
otal | +4.105 |
Neg logit contributions | |
miscar | -7.516 |
theless | -7.332 |
pard | -7.247 |
hower | -7.082 |
Ern | -6.992 |
Token | - |
Token ID | 12 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
esame | +2.854 |
(% | +2.705 |
atos | +2.525 |
ordan | +2.483 |
otal | +2.352 |
Neg logit contributions | |
miscar | -3.137 |
pard | -3.069 |
theless | -2.979 |
Ern | -2.875 |
hower | -2.811 |
Token | enter |
Token ID | 9255 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
esame | +1.512 |
(% | +1.348 |
atos | +1.150 |
ordan | +1.093 |
otal | +0.963 |
Neg logit contributions | |
miscar | -5.236 |
pard | -5.153 |
theless | -5.002 |
Ern | -4.919 |
hower | -4.850 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
esame | +3.399 |
(% | +3.261 |
atos | +2.984 |
ordan | +2.942 |
ateral | +2.720 |
Neg logit contributions | |
miscar | -4.660 |
pard | -4.622 |
theless | -4.572 |
Ern | -4.321 |
hower | -4.296 |
Token | You |
Token ID | 921 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
esame | +2.637 |
(% | +2.532 |
atos | +2.396 |
ordan | +2.337 |
otal | +2.225 |
Neg logit contributions | |
miscar | -2.182 |
pard | -2.135 |
theless | -2.042 |
Ern | -1.945 |
roe | -1.888 |
Token | must |
Token ID | 1276 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
esame | +4.494 |
(% | +4.398 |
atos | +3.985 |
ordan | +3.951 |
otal | +3.695 |
Neg logit contributions | |
miscar | -4.570 |
pard | -4.438 |
theless | -4.432 |
Ern | -4.185 |
hower | -4.129 |
Token | select |
Token ID | 2922 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
esame | +4.481 |
(% | +4.444 |
atos | +3.905 |
ordan | +3.634 |
otal | +3.546 |
Neg logit contributions | |
miscar | -6.855 |
theless | -6.806 |
pard | -6.624 |
Ern | -6.433 |
hower | -6.291 |
Token | a |
Token ID | 257 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
esame | +3.313 |
(% | +3.171 |
atos | +2.877 |
ordan | +2.831 |
otal | +2.651 |
Neg logit contributions | |
miscar | -4.547 |
pard | -4.418 |
theless | -4.348 |
Ern | -4.187 |
\": | -4.097 |
Token | newsletter |
Token ID | 13129 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
esame | +3.842 |
(% | +3.687 |
atos | +3.391 |
ordan | +3.377 |
otal | +3.176 |
Neg logit contributions | |
miscar | -3.479 |
pard | -3.318 |
theless | -3.306 |
Ern | -3.170 |
\": | -3.081 |
Token | to |
Token ID | 284 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
esame | +1.831 |
(% | +1.715 |
atos | +1.593 |
ordan | +1.565 |
otal | +1.470 |
Neg logit contributions | |
miscar | -2.441 |
pard | -2.395 |
theless | -2.296 |
Ern | -2.238 |
\": | -2.187 |
Token | subscribe |
Token ID | 12383 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
esame | +1.519 |
(% | +1.395 |
atos | +1.262 |
ordan | +1.240 |
otal | +1.145 |
Neg logit contributions | |
miscar | -2.981 |
pard | -2.936 |
theless | -2.826 |
Ern | -2.764 |
\": | -2.716 |
Token | An |
Token ID | 1052 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
esame | +2.407 |
(% | +2.234 |
atos | +2.088 |
ordan | +2.039 |
otal | +1.923 |
Neg logit contributions | |
miscar | -3.378 |
pard | -3.313 |
theless | -3.155 |
Ern | -3.097 |
\": | -3.034 |
Token | error |
Token ID | 4049 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
esame | +2.416 |
(% | +2.299 |
atos | +2.201 |
ordan | +2.169 |
otal | +2.091 |
Neg logit contributions | |
miscar | -1.486 |
pard | -1.441 |
theless | -1.339 |
Ern | -1.298 |
\": | -1.256 |
Token | has |
Token ID | 468 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
esame | +1.341 |
(% | +1.262 |
atos | +1.191 |
ordan | +1.171 |
otal | +1.118 |
Neg logit contributions | |
miscar | -1.337 |
pard | -1.306 |
theless | -1.235 |
Ern | -1.209 |
\": | -1.179 |
Token | occurred |
Token ID | 5091 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
esame | +5.212 |
(% | +5.052 |
ordan | +4.688 |
atos | +4.662 |
ateral | +4.465 |
Neg logit contributions | |
miscar | -3.933 |
pard | -3.857 |
theless | -3.775 |
Ern | -3.637 |
\": | -3.553 |
Token | . |
Token ID | 13 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
esame | +2.595 |
(% | +2.464 |
atos | +2.280 |
ordan | +2.252 |
otal | +2.104 |
Neg logit contributions | |
miscar | -3.213 |
pard | -3.163 |
theless | -3.087 |
Ern | -2.953 |
hower | -2.877 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
esame | +4.984 |
(% | +4.974 |
atos | +4.602 |
ordan | +4.495 |
Matrix | +4.283 |
Neg logit contributions | |
miscar | -4.244 |
pard | -4.242 |
theless | -4.119 |
ricanes | -3.845 |
Ern | -3.805 |
Token | try |
Token ID | 1949 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
esame | +3.928 |
(% | +3.830 |
atos | +3.344 |
ordan | +3.288 |
otal | +3.027 |
Neg logit contributions | |
miscar | -7.286 |
pard | -7.073 |
theless | -7.053 |
Ern | -6.843 |
\": | -6.733 |
Token | again |
Token ID | 757 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
esame | +2.674 |
(% | +2.526 |
atos | +2.298 |
ordan | +2.255 |
otal | +2.088 |
Neg logit contributions | |
miscar | -4.324 |
pard | -4.236 |
theless | -4.192 |
Ern | -4.032 |
hower | -3.973 |
Token | later |
Token ID | 1568 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
esame | +2.743 |
(% | +2.611 |
atos | +2.388 |
ordan | +2.307 |
ateral | +2.175 |
Neg logit contributions | |
miscar | -4.432 |
pard | -4.360 |
theless | -4.289 |
Ern | -4.116 |
\": | -4.046 |
Token | . |
Token ID | 13 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
esame | +3.903 |
(% | +3.735 |
atos | +3.426 |
ordan | +3.383 |
ateral | +3.124 |
Neg logit contributions | |
miscar | -5.259 |
pard | -5.192 |
theless | -5.168 |
Ern | -4.828 |
hower | -4.788 |
Token | View |
Token ID | 3582 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
esame | +3.068 |
(% | +3.004 |
atos | +2.745 |
ordan | +2.658 |
ateral | +2.483 |
Neg logit contributions | |
miscar | -4.079 |
pard | -4.046 |
theless | -3.916 |
Ern | -3.770 |
hower | -3.692 |
Token | An |
Token ID | 1052 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
esame | +2.424 |
(% | +2.248 |
atos | +2.103 |
ordan | +2.054 |
otal | +1.939 |
Neg logit contributions | |
miscar | -3.382 |
pard | -3.316 |
theless | -3.155 |
Ern | -3.102 |
\": | -3.038 |
Token | error |
Token ID | 4049 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
esame | +2.039 |
(% | +1.939 |
atos | +1.858 |
ordan | +1.829 |
otal | +1.765 |
Neg logit contributions | |
miscar | -1.222 |
pard | -1.186 |
theless | -1.091 |
Ern | -1.064 |
\": | -1.029 |
Token | has |
Token ID | 468 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
esame | +1.179 |
(% | +1.108 |
atos | +1.051 |
ordan | +1.030 |
otal | +0.983 |
Neg logit contributions | |
miscar | -1.159 |
pard | -1.133 |
theless | -1.067 |
Ern | -1.045 |
\": | -1.020 |
Token | occurred |
Token ID | 5091 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
esame | +5.146 |
(% | +4.983 |
ordan | +4.632 |
atos | +4.612 |
ateral | +4.409 |
Neg logit contributions | |
miscar | -3.834 |
pard | -3.756 |
theless | -3.673 |
Ern | -3.538 |
\": | -3.449 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
esame | +2.562 |
(% | +2.431 |
atos | +2.252 |
ordan | +2.223 |
otal | +2.077 |
Neg logit contributions | |
miscar | -3.151 |
pard | -3.098 |
theless | -3.020 |
Ern | -2.893 |
hower | -2.815 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
esame | +4.889 |
(% | +4.871 |
atos | +4.514 |
ordan | +4.411 |
Matrix | +4.200 |
Neg logit contributions | |
miscar | -4.147 |
pard | -4.137 |
theless | -4.021 |
ricanes | -3.747 |
Ern | -3.717 |
Token | try |
Token ID | 1949 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
esame | +3.837 |
(% | +3.743 |
atos | +3.273 |
ordan | +3.220 |
otal | +2.956 |
Neg logit contributions | |
miscar | -7.110 |
pard | -6.902 |
theless | -6.877 |
Ern | -6.671 |
\": | -6.584 |
Token | again |
Token ID | 757 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
esame | +2.668 |
(% | +2.519 |
atos | +2.293 |
ordan | +2.250 |
otal | +2.083 |
Neg logit contributions | |
miscar | -4.302 |
pard | -4.213 |
theless | -4.163 |
Ern | -4.008 |
hower | -3.946 |
Token | later |
Token ID | 1568 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
esame | +2.714 |
(% | +2.581 |
atos | +2.362 |
ordan | +2.286 |
ateral | +2.150 |
Neg logit contributions | |
miscar | -4.368 |
pard | -4.295 |
theless | -4.218 |
Ern | -4.051 |
\": | -3.989 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
esame | +3.920 |
(% | +3.745 |
atos | +3.442 |
ordan | +3.396 |
ateral | +3.134 |
Neg logit contributions | |
miscar | -5.279 |
pard | -5.206 |
theless | -5.184 |
Ern | -4.838 |
hower | -4.797 |
Token | View |
Token ID | 3582 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
esame | +2.994 |
(% | +2.944 |
atos | +2.678 |
ordan | +2.598 |
Matrix | +2.422 |
Neg logit contributions | |
miscar | -4.081 |
pard | -4.056 |
theless | -3.935 |
Ern | -3.787 |
hower | -3.709 |
Token | An |
Token ID | 1052 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
esame | +2.492 |
(% | +2.307 |
atos | +2.162 |
ordan | +2.112 |
otal | +1.998 |
Neg logit contributions | |
miscar | -3.442 |
pard | -3.373 |
theless | -3.207 |
Ern | -3.159 |
\": | -3.094 |
Token | error |
Token ID | 4049 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
esame | +2.320 |
(% | +2.207 |
atos | +2.114 |
ordan | +2.082 |
otal | +2.008 |
Neg logit contributions | |
miscar | -1.413 |
pard | -1.371 |
theless | -1.269 |
Ern | -1.233 |
\": | -1.192 |
Token | has |
Token ID | 468 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
esame | +1.189 |
(% | +1.117 |
atos | +1.059 |
ordan | +1.038 |
otal | +0.991 |
Neg logit contributions | |
miscar | -1.171 |
pard | -1.145 |
theless | -1.079 |
Ern | -1.057 |
\": | -1.031 |
Token | occurred |
Token ID | 5091 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
esame | +5.055 |
(% | +4.886 |
ordan | +4.538 |
atos | +4.525 |
ateral | +4.322 |
Neg logit contributions | |
miscar | -3.789 |
pard | -3.715 |
theless | -3.630 |
Ern | -3.492 |
\": | -3.411 |
Token | . |
Token ID | 13 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
esame | +2.522 |
(% | +2.391 |
atos | +2.217 |
ordan | +2.184 |
otal | +2.043 |
Neg logit contributions | |
miscar | -3.099 |
pard | -3.047 |
theless | -2.966 |
Ern | -2.843 |
hower | -2.767 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
esame | +4.462 |
(% | +4.401 |
atos | +4.114 |
ordan | +4.022 |
ateral | +3.809 |
Neg logit contributions | |
miscar | -3.654 |
pard | -3.627 |
theless | -3.501 |
Ern | -3.267 |
ricanes | -3.256 |
Token | try |
Token ID | 1949 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
esame | +3.810 |
(% | +3.704 |
atos | +3.236 |
ordan | +3.182 |
otal | +2.924 |
Neg logit contributions | |
miscar | -7.117 |
pard | -6.898 |
theless | -6.884 |
Ern | -6.676 |
\": | -6.585 |
Token | again |
Token ID | 757 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
esame | +2.733 |
(% | +2.577 |
atos | +2.343 |
ordan | +2.299 |
otal | +2.126 |
Neg logit contributions | |
miscar | -4.461 |
pard | -4.366 |
theless | -4.320 |
Ern | -4.161 |
hower | -4.101 |
Token | later |
Token ID | 1568 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
esame | +2.774 |
(% | +2.644 |
atos | +2.417 |
ordan | +2.326 |
ateral | +2.196 |
Neg logit contributions | |
miscar | -4.552 |
pard | -4.478 |
theless | -4.410 |
Ern | -4.234 |
\": | -4.159 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
esame | +3.859 |
(% | +3.686 |
atos | +3.391 |
ordan | +3.341 |
ateral | +3.080 |
Neg logit contributions | |
miscar | -5.221 |
pard | -5.149 |
theless | -5.121 |
Ern | -4.779 |
hower | -4.745 |
Token | View |
Token ID | 3582 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
esame | +2.785 |
(% | +2.734 |
atos | +2.505 |
ordan | +2.420 |
Matrix | +2.257 |
Neg logit contributions | |
miscar | -3.705 |
pard | -3.678 |
theless | -3.555 |
Ern | -3.428 |
hower | -3.347 |
Token | in |
Token ID | 287 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
miscar | +1.669 |
pard | +1.647 |
Ern | +1.506 |
theless | +1.503 |
\": | +1.465 |
Neg logit contributions | |
esame | -1.770 |
(% | -1.622 |
atos | -1.568 |
ordan | -1.561 |
otal | -1.476 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
miscar | +0.380 |
pard | +0.374 |
theless | +0.349 |
Ern | +0.347 |
\": | +0.337 |
Neg logit contributions | |
esame | -0.353 |
(% | -0.329 |
atos | -0.312 |
ordan | -0.307 |
otal | -0.292 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
esame | +1.102 |
(% | +1.032 |
atos | +0.975 |
ordan | +0.956 |
otal | +0.910 |
Neg logit contributions | |
miscar | -1.189 |
pard | -1.163 |
theless | -1.099 |
Ern | -1.078 |
\": | -1.053 |
Token | Steve |
Token ID | 6542 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
miscar | +0.035 |
pard | +0.035 |
theless | +0.032 |
Ern | +0.032 |
\": | +0.031 |
Neg logit contributions | |
esame | -0.030 |
(% | -0.028 |
atos | -0.027 |
ordan | -0.026 |
otal | -0.025 |
Token | Kor |
Token ID | 14769 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
esame | +0.153 |
(% | +0.143 |
atos | +0.137 |
ordan | +0.133 |
otal | +0.128 |
Neg logit contributions | |
miscar | -0.143 |
pard | -0.140 |
theless | -0.131 |
Ern | -0.129 |
\": | -0.126 |
Token | |
Token ID | 3907 |
Feature activation | -9.31e+00 |
Pos logit contributions | |
miscar | +0.172 |
pard | +0.167 |
theless | +0.149 |
Ern | +0.146 |
\": | +0.140 |
Neg logit contributions | |
esame | -0.372 |
(% | -0.356 |
atos | -0.341 |
ordan | -0.336 |
otal | -0.325 |
Token | n |
Token ID | 77 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
pard | +7.083 |
miscar | +7.012 |
roe | +6.742 |
theless | +6.675 |
hower | +6.515 |
Neg logit contributions | |
esame | -6.127 |
(% | -5.920 |
atos | -5.235 |
ordan | -5.153 |
-+-+ | -5.141 |
Token | ack |
Token ID | 441 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
miscar | +1.932 |
pard | +1.912 |
theless | +1.792 |
Ern | +1.762 |
roe | +1.731 |
Neg logit contributions | |
esame | -1.824 |
(% | -1.719 |
atos | -1.581 |
ordan | -1.555 |
ateral | -1.497 |
Token | i |
Token ID | 72 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
esame | +0.899 |
(% | +0.838 |
atos | +0.789 |
ordan | +0.775 |
otal | +0.735 |
Neg logit contributions | |
miscar | -1.056 |
pard | -1.036 |
theless | -0.978 |
Ern | -0.961 |
\": | -0.940 |
Token | has |
Token ID | 468 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
esame | +0.616 |
(% | +0.579 |
atos | +0.548 |
ordan | +0.538 |
otal | +0.514 |
Neg logit contributions | |
miscar | -0.603 |
pard | -0.590 |
theless | -0.555 |
Ern | -0.544 |
\": | -0.531 |
Token | noted |
Token ID | 4367 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
esame | +0.260 |
(% | +0.243 |
atos | +0.231 |
ordan | +0.227 |
otal | +0.217 |
Neg logit contributions | |
miscar | -0.254 |
pard | -0.249 |
theless | -0.233 |
Ern | -0.228 |
\": | -0.223 |
Token | di |
Token ID | 10989 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
miscar | +4.070 |
pard | +4.037 |
theless | +3.813 |
roe | +3.787 |
\": | +3.679 |
Neg logit contributions | |
esame | -3.602 |
(% | -3.518 |
atos | -3.219 |
ordan | -3.100 |
-+-+ | -3.074 |
Token | |
Token ID | 3907 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
miscar | +0.572 |
pard | +0.560 |
theless | +0.483 |
Ern | +0.472 |
\": | +0.450 |
Neg logit contributions | |
esame | -1.604 |
(% | -1.538 |
atos | -1.481 |
ordan | -1.464 |
ateral | -1.412 |
Token | um |
Token ID | 388 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
miscar | +4.505 |
pard | +4.408 |
roe | +4.118 |
theless | +4.065 |
hower | +4.019 |
Neg logit contributions | |
esame | -4.807 |
(% | -4.691 |
atos | -4.292 |
ordan | -4.198 |
-+-+ | -4.180 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
esame | +1.240 |
(% | +1.170 |
atos | +1.116 |
ordan | +1.101 |
otal | +1.053 |
Neg logit contributions | |
miscar | -0.962 |
pard | -0.939 |
theless | -0.875 |
Ern | -0.856 |
\": | -0.832 |
Token | al |
Token ID | 435 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
esame | +1.662 |
(% | +1.561 |
atos | +1.479 |
ordan | +1.451 |
otal | +1.385 |
Neg logit contributions | |
miscar | -1.660 |
pard | -1.623 |
theless | -1.530 |
Ern | -1.499 |
\": | -1.462 |
Token | |
Token ID | 3907 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
miscar | +0.543 |
pard | +0.521 |
theless | +0.462 |
Ern | +0.447 |
roe | +0.426 |
Neg logit contributions | |
esame | -1.392 |
(% | -1.335 |
atos | -1.286 |
ordan | -1.273 |
otal | -1.233 |
Token | l |
Token ID | 75 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
miscar | +6.770 |
pard | +6.608 |
theless | +6.488 |
hower | +6.191 |
roe | +6.134 |
Neg logit contributions | |
esame | -5.947 |
(% | -5.757 |
atos | -5.248 |
Matrix | -5.174 |
-+-+ | -5.136 |
Token | owed |
Token ID | 6972 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
miscar | +1.591 |
pard | +1.557 |
theless | +1.466 |
roe | +1.419 |
Ern | +1.418 |
Neg logit contributions | |
esame | -1.471 |
(% | -1.394 |
atos | -1.307 |
ordan | -1.275 |
otal | -1.201 |
Token | only |
Token ID | 691 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
esame | +0.423 |
(% | +0.394 |
atos | +0.374 |
ordan | +0.367 |
otal | +0.348 |
Neg logit contributions | |
miscar | -0.481 |
pard | -0.473 |
theless | -0.443 |
Ern | -0.437 |
\": | -0.425 |
Token | a |
Token ID | 257 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
esame | +0.123 |
(% | +0.114 |
atos | +0.109 |
ordan | +0.107 |
otal | +0.101 |
Neg logit contributions | |
miscar | -0.143 |
pard | -0.141 |
theless | -0.132 |
Ern | -0.131 |
\": | -0.127 |
Token | brief |
Token ID | 4506 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
miscar | +0.614 |
pard | +0.607 |
theless | +0.562 |
Ern | +0.556 |
\": | +0.543 |
Neg logit contributions | |
esame | -0.574 |
(% | -0.534 |
atos | -0.510 |
ordan | -0.499 |
otal | -0.473 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
esame | +1.078 |
(% | +1.017 |
atos | +0.960 |
ordan | +0.940 |
otal | +0.898 |
Neg logit contributions | |
miscar | -1.065 |
pard | -1.039 |
theless | -0.989 |
Ern | -0.958 |
\": | -0.945 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
esame | +0.156 |
(% | +0.147 |
atos | +0.140 |
ordan | +0.138 |
otal | +0.133 |
Neg logit contributions | |
miscar | -0.129 |
pard | -0.126 |
theless | -0.116 |
Ern | -0.115 |
\": | -0.112 |
Token | Jo |
Token ID | 9908 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
miscar | +0.105 |
pard | +0.102 |
theless | +0.096 |
Ern | +0.094 |
\": | +0.092 |
Neg logit contributions | |
esame | -0.120 |
(% | -0.114 |
atos | -0.108 |
ordan | -0.106 |
otal | -0.101 |
Token | ong |
Token ID | 506 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
esame | +1.274 |
(% | +1.159 |
atos | +1.064 |
ordan | +1.031 |
otal | +0.956 |
Neg logit contributions | |
miscar | -2.526 |
pard | -2.483 |
theless | -2.378 |
Ern | -2.342 |
\": | -2.301 |
Token | Ang |
Token ID | 13450 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
miscar | +0.478 |
pard | +0.468 |
theless | +0.441 |
Ern | +0.431 |
\": | +0.422 |
Neg logit contributions | |
esame | -0.507 |
(% | -0.476 |
atos | -0.451 |
ordan | -0.444 |
otal | -0.423 |
Token | Il |
Token ID | 13778 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
miscar | +1.919 |
pard | +1.888 |
theless | +1.810 |
Ern | +1.791 |
\": | +1.751 |
Neg logit contributions | |
esame | -0.861 |
(% | -0.774 |
atos | -0.711 |
ordan | -0.684 |
otal | -0.627 |
Token | bo |
Token ID | 2127 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
pard | +1.687 |
miscar | +1.684 |
roe | +1.299 |
\": | +1.229 |
gow | +1.220 |
Neg logit contributions | |
esame | -11.026 |
(% | -10.519 |
-+-+ | -10.147 |
atos | -10.101 |
ordan | -9.934 |
Token | reported |
Token ID | 2098 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
miscar | +0.960 |
pard | +0.934 |
theless | +0.879 |
Ern | +0.862 |
\": | +0.837 |
Neg logit contributions | |
esame | -1.018 |
(% | -0.953 |
atos | -0.906 |
ordan | -0.890 |
otal | -0.850 |
Token | that |
Token ID | 326 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
esame | +1.789 |
(% | +1.679 |
atos | +1.580 |
ordan | +1.549 |
otal | +1.486 |
Neg logit contributions | |
miscar | -1.932 |
pard | -1.890 |
theless | -1.804 |
Ern | -1.746 |
\": | -1.721 |
Token | in |
Token ID | 287 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
esame | +1.280 |
(% | +1.203 |
atos | +1.134 |
ordan | +1.110 |
otal | +1.060 |
Neg logit contributions | |
miscar | -1.359 |
pard | -1.330 |
theless | -1.264 |
Ern | -1.232 |
\": | -1.209 |
Token | W |
Token ID | 370 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
miscar | +0.250 |
pard | +0.244 |
theless | +0.230 |
Ern | +0.227 |
\": | +0.221 |
Neg logit contributions | |
esame | -0.231 |
(% | -0.217 |
atos | -0.205 |
ordan | -0.201 |
otal | -0.191 |
Token | with |
Token ID | 351 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
miscar | +1.457 |
pard | +1.436 |
theless | +1.320 |
Ern | +1.306 |
\": | +1.280 |
Neg logit contributions | |
esame | -1.442 |
(% | -1.330 |
atos | -1.287 |
ordan | -1.267 |
otal | -1.206 |
Token | Cuba |
Token ID | 14159 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
esame | +1.375 |
(% | +1.291 |
atos | +1.220 |
ordan | +1.196 |
otal | +1.140 |
Neg logit contributions | |
miscar | -1.435 |
pard | -1.402 |
theless | -1.327 |
Ern | -1.299 |
\": | -1.269 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
esame | +1.890 |
(% | +1.781 |
atos | +1.675 |
ordan | +1.641 |
otal | +1.568 |
Neg logit contributions | |
miscar | -1.974 |
pard | -1.928 |
theless | -1.836 |
Ern | -1.792 |
\": | -1.748 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
esame | +1.425 |
(% | +1.348 |
atos | +1.275 |
ordan | +1.251 |
otal | +1.196 |
Neg logit contributions | |
miscar | -1.309 |
pard | -1.278 |
theless | -1.205 |
Ern | -1.174 |
\": | -1.146 |
Token | Rom |
Token ID | 3570 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
esame | +0.776 |
(% | +0.726 |
atos | +0.684 |
ordan | +0.670 |
otal | +0.637 |
Neg logit contributions | |
miscar | -0.891 |
pard | -0.872 |
theless | -0.826 |
Ern | -0.810 |
\": | -0.792 |
Token | |
Token ID | 3907 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
miscar | +0.444 |
pard | +0.431 |
theless | +0.378 |
Ern | +0.369 |
\": | +0.353 |
Neg logit contributions | |
esame | -1.229 |
(% | -1.176 |
atos | -1.129 |
ordan | -1.120 |
otal | -1.087 |
Token | ney |
Token ID | 1681 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
pard | +5.993 |
miscar | +5.891 |
theless | +5.569 |
\": | +5.473 |
roe | +5.459 |
Neg logit contributions | |
esame | -6.494 |
(% | -6.471 |
atos | -5.832 |
ateral | -5.765 |
-+-+ | -5.762 |
Token | made |
Token ID | 925 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
miscar | +0.690 |
pard | +0.677 |
theless | +0.634 |
Ern | +0.622 |
\": | +0.608 |
Neg logit contributions | |
esame | -0.686 |
(% | -0.639 |
atos | -0.607 |
ordan | -0.596 |
otal | -0.571 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
esame | +0.818 |
(% | +0.767 |
atos | +0.725 |
ordan | +0.711 |
otal | +0.678 |
Neg logit contributions | |
miscar | -0.863 |
pard | -0.845 |
theless | -0.796 |
Ern | -0.782 |
\": | -0.763 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
esame | +1.143 |
(% | +1.070 |
atos | +1.012 |
ordan | +0.992 |
otal | +0.945 |
Neg logit contributions | |
miscar | -1.226 |
pard | -1.201 |
theless | -1.133 |
Ern | -1.112 |
\": | -1.085 |
Token | - |
Token ID | 12 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
esame | +1.324 |
(% | +1.243 |
atos | +1.177 |
ordan | +1.151 |
otal | +1.098 |
Neg logit contributions | |
miscar | -1.368 |
pard | -1.333 |
theless | -1.268 |
Ern | -1.238 |
\": | -1.209 |
Token | Sh |
Token ID | 911 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
miscar | +1.416 |
pard | +1.369 |
Ern | +1.273 |
theless | +1.236 |
\": | +1.230 |
Neg logit contributions | |
esame | -1.793 |
(% | -1.667 |
atos | -1.621 |
ordan | -1.588 |
otal | -1.549 |
Token | and |
Token ID | 392 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
miscar | +0.216 |
pard | +0.211 |
theless | +0.194 |
\": | +0.193 |
Ern | +0.192 |
Neg logit contributions | |
esame | -0.222 |
(% | -0.209 |
atos | -0.197 |
ordan | -0.192 |
otal | -0.184 |
Token | ling |
Token ID | 1359 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
esame | +1.453 |
(% | +1.358 |
atos | +1.275 |
ordan | +1.251 |
otal | +1.188 |
Neg logit contributions | |
miscar | -1.742 |
pard | -1.707 |
theless | -1.620 |
Ern | -1.590 |
\": | -1.551 |
Token | 1999 |
Token ID | 7358 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
esame | +3.278 |
(% | +3.028 |
ordan | +2.636 |
atos | +2.631 |
otal | +2.393 |
Neg logit contributions | |
miscar | -5.800 |
pard | -5.651 |
theless | -5.513 |
Ern | -5.336 |
\": | -5.330 |
Token | John |
Token ID | 1757 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
miscar | +0.160 |
pard | +0.156 |
theless | +0.147 |
Ern | +0.146 |
\": | +0.142 |
Neg logit contributions | |
esame | -0.153 |
(% | -0.144 |
atos | -0.136 |
ordan | -0.133 |
otal | -0.128 |
Token | Lith |
Token ID | 19730 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
miscar | +0.747 |
pard | +0.726 |
theless | +0.665 |
Ern | +0.662 |
\": | +0.637 |
Neg logit contributions | |
esame | -1.171 |
(% | -1.108 |
atos | -1.065 |
ordan | -1.048 |
otal | -1.013 |
Token | gow |
Token ID | 21175 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
gow | +0.048 |
miscar | -0.006 |
pard | -0.308 |
roe | -0.489 |
\": | -0.567 |
Neg logit contributions | |
esame | -12.068 |
(% | -11.721 |
-+-+ | -11.437 |
atos | -11.428 |
ADS | -11.378 |
Token |
|
Token ID | 198 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
miscar | +1.667 |
pard | +1.621 |
\": | +1.473 |
Ern | +1.449 |
theless | +1.438 |
Neg logit contributions | |
esame | -2.319 |
(% | -2.142 |
atos | -2.093 |
ordan | -2.043 |
otal | -1.999 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
miscar | +0.591 |
pard | +0.574 |
\": | +0.521 |
Ern | +0.521 |
theless | +0.516 |
Neg logit contributions | |
esame | -0.792 |
(% | -0.735 |
atos | -0.713 |
ordan | -0.697 |
otal | -0.676 |
Token | 1999 |
Token ID | 18946 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
miscar | +0.189 |
pard | +0.185 |
theless | +0.177 |
Ern | +0.174 |
\": | +0.170 |
Neg logit contributions | |
esame | -0.121 |
(% | -0.112 |
atos | -0.104 |
ordan | -0.101 |
otal | -0.095 |
Token | Michael |
Token ID | 3899 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
esame | +1.659 |
(% | +1.552 |
atos | +1.467 |
ordan | +1.438 |
otal | +1.364 |
Neg logit contributions | |
miscar | -1.817 |
pard | -1.778 |
theless | -1.686 |
Ern | -1.639 |
\": | -1.609 |
Token | ce |
Token ID | 344 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
miscar | +3.944 |
pard | +3.924 |
theless | +3.666 |
roe | +3.538 |
\": | +3.488 |
Neg logit contributions | |
esame | -4.130 |
(% | -3.976 |
atos | -3.756 |
ordan | -3.640 |
ateral | -3.521 |
Token | ives |
Token ID | 1083 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
miscar | +0.669 |
pard | +0.657 |
theless | +0.627 |
Ern | +0.613 |
\": | +0.606 |
Neg logit contributions | |
esame | -0.398 |
(% | -0.367 |
atos | -0.339 |
ordan | -0.329 |
otal | -0.307 |
Token | from |
Token ID | 422 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
miscar | +1.052 |
pard | +1.035 |
theless | +0.950 |
Ern | +0.944 |
\": | +0.925 |
Neg logit contributions | |
esame | -1.007 |
(% | -0.931 |
atos | -0.896 |
ordan | -0.885 |
otal | -0.836 |
Token | his |
Token ID | 465 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
esame | +1.368 |
(% | +1.281 |
atos | +1.208 |
ordan | +1.183 |
otal | +1.126 |
Neg logit contributions | |
miscar | -1.524 |
pard | -1.491 |
theless | -1.412 |
Ern | -1.384 |
\": | -1.353 |
Token | fel |
Token ID | 10756 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
miscar | +0.387 |
pard | +0.382 |
theless | +0.354 |
Ern | +0.351 |
\": | +0.342 |
Neg logit contributions | |
esame | -0.357 |
(% | -0.330 |
atos | -0.315 |
ordan | -0.310 |
otal | -0.294 |
Token | |
Token ID | 3907 |
Feature activation | -8.00e+00 |
Pos logit contributions | |
miscar | +0.844 |
pard | +0.813 |
theless | +0.710 |
Ern | +0.687 |
\": | +0.669 |
Neg logit contributions | |
esame | -2.088 |
(% | -1.993 |
atos | -1.922 |
ordan | -1.905 |
otal | -1.860 |
Token | low |
Token ID | 9319 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
miscar | +5.543 |
pard | +5.345 |
theless | +5.156 |
roe | +4.982 |
ricanes | +4.856 |
Neg logit contributions | |
esame | -5.985 |
(% | -5.766 |
-+-+ | -5.351 |
Matrix | -5.279 |
atos | -5.210 |
Token | Demo |
Token ID | 34588 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
miscar | +1.691 |
pard | +1.683 |
theless | +1.530 |
Ern | +1.519 |
\": | +1.486 |
Neg logit contributions | |
esame | -2.034 |
(% | -1.909 |
atos | -1.829 |
ordan | -1.807 |
otal | -1.705 |
Token | |
Token ID | 3907 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
esame | +0.502 |
(% | +0.480 |
atos | +0.462 |
ordan | +0.458 |
otal | +0.443 |
Neg logit contributions | |
miscar | -0.198 |
pard | -0.190 |
theless | -0.168 |
Ern | -0.164 |
\": | -0.157 |
Token | cr |
Token ID | 6098 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
miscar | +1.981 |
pard | +1.979 |
theless | +1.679 |
\": | +1.647 |
roe | +1.600 |
Neg logit contributions | |
esame | -5.344 |
(% | -5.174 |
atos | -4.973 |
ordan | -4.908 |
ateral | -4.762 |
Token | ats |
Token ID | 1381 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
esame | +0.990 |
(% | +0.922 |
atos | +0.874 |
ordan | +0.848 |
otal | +0.810 |
Neg logit contributions | |
miscar | -1.186 |
pard | -1.159 |
theless | -1.105 |
Ern | -1.083 |
\": | -1.055 |
Token | NS |
Token ID | 8035 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
esame | +0.183 |
(% | +0.172 |
atos | +0.163 |
ordan | +0.161 |
otal | +0.154 |
Neg logit contributions | |
miscar | -0.161 |
pard | -0.158 |
theless | -0.147 |
Ern | -0.144 |
\": | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
esame | +1.199 |
(% | +1.126 |
atos | +1.063 |
ordan | +1.042 |
otal | +0.993 |
Neg logit contributions | |
miscar | -1.270 |
pard | -1.242 |
theless | -1.176 |
Ern | -1.152 |
\": | -1.125 |
Token |
|
Token ID | 198 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
esame | +1.079 |
(% | +1.019 |
atos | +0.965 |
ordan | +0.946 |
otal | +0.905 |
Neg logit contributions | |
miscar | -1.027 |
pard | -1.005 |
theless | -0.947 |
Ern | -0.923 |
\": | -0.902 |
Token |
|
Token ID | 198 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
esame | +1.262 |
(% | +1.189 |
atos | +1.132 |
ordan | +1.112 |
otal | +1.066 |
Neg logit contributions | |
miscar | -1.081 |
pard | -1.054 |
theless | -0.987 |
Ern | -0.967 |
\": | -0.944 |
Token | Lim |
Token ID | 19352 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
esame | +1.802 |
(% | +1.697 |
atos | +1.624 |
ordan | +1.590 |
otal | +1.525 |
Neg logit contributions | |
miscar | -1.597 |
pard | -1.560 |
theless | -1.470 |
Ern | -1.437 |
\": | -1.386 |
Token | itations |
Token ID | 20597 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
miscar | +1.513 |
pard | +1.471 |
theless | +1.392 |
roe | +1.372 |
Ern | +1.366 |
Neg logit contributions | |
esame | -1.742 |
(% | -1.639 |
atos | -1.511 |
ordan | -1.510 |
otal | -1.446 |
Token | Patients |
Token ID | 28021 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
miscar | +5.219 |
pard | +4.986 |
theless | +4.593 |
Ern | +4.557 |
roe | +4.353 |
Neg logit contributions | |
esame | -6.668 |
(% | -6.116 |
ordan | -5.901 |
atos | -5.887 |
-+-+ | -5.594 |
Token | were |
Token ID | 547 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
miscar | +0.908 |
pard | +0.885 |
theless | +0.825 |
Ern | +0.807 |
\": | +0.789 |
Neg logit contributions | |
esame | -1.029 |
(% | -0.960 |
atos | -0.923 |
ordan | -0.912 |
otal | -0.867 |
Token | not |
Token ID | 407 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
esame | +0.007 |
(% | +0.007 |
atos | +0.007 |
ordan | +0.006 |
otal | +0.006 |
Neg logit contributions | |
miscar | -0.008 |
pard | -0.008 |
theless | -0.007 |
Ern | -0.007 |
\": | -0.007 |
Token | randomized |
Token ID | 23925 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
esame | +0.422 |
(% | +0.393 |
atos | +0.373 |
ordan | +0.366 |
otal | +0.348 |
Neg logit contributions | |
miscar | -0.477 |
pard | -0.469 |
theless | -0.441 |
Ern | -0.434 |
\": | -0.422 |
Token | in |
Token ID | 287 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
miscar | +1.679 |
pard | +1.635 |
theless | +1.536 |
Ern | +1.504 |
\": | +1.472 |
Neg logit contributions | |
esame | -1.595 |
(% | -1.470 |
atos | -1.415 |
ordan | -1.389 |
otal | -1.312 |
Token |
|
Token ID | 198 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
miscar | +0.583 |
pard | +0.567 |
Ern | +0.531 |
theless | +0.530 |
\": | +0.513 |
Neg logit contributions | |
esame | -0.680 |
(% | -0.635 |
atos | -0.607 |
ordan | -0.598 |
otal | -0.576 |
Token |
|
Token ID | 198 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
miscar | +0.044 |
pard | +0.043 |
theless | +0.039 |
Ern | +0.039 |
\": | +0.038 |
Neg logit contributions | |
esame | -0.056 |
(% | -0.052 |
atos | -0.050 |
ordan | -0.049 |
otal | -0.047 |
Token | " |
Token ID | 1 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
miscar | +0.562 |
pard | +0.549 |
theless | +0.514 |
Ern | +0.507 |
\": | +0.500 |
Neg logit contributions | |
esame | -0.600 |
(% | -0.565 |
atos | -0.533 |
ordan | -0.525 |
otal | -0.502 |
Token | Understanding |
Token ID | 43467 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
esame | +0.930 |
(% | +0.881 |
atos | +0.841 |
ordan | +0.824 |
otal | +0.789 |
Neg logit contributions | |
miscar | -0.764 |
pard | -0.745 |
theless | -0.700 |
Ern | -0.680 |
\": | -0.658 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
miscar | +0.154 |
pard | +0.151 |
theless | +0.142 |
Ern | +0.139 |
\": | +0.136 |
Neg logit contributions | |
esame | -0.158 |
(% | -0.148 |
atos | -0.140 |
ordan | -0.138 |
otal | -0.131 |
Token | pseud |
Token ID | 25038 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
miscar | +1.616 |
pard | +1.592 |
theless | +1.491 |
Ern | +1.470 |
\": | +1.436 |
Neg logit contributions | |
esame | -1.490 |
(% | -1.379 |
atos | -1.305 |
ordan | -1.287 |
otal | -1.227 |
Token | og |
Token ID | 519 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
miscar | +5.618 |
pard | +5.607 |
roe | +5.365 |
gow | +5.110 |
theless | +5.050 |
Neg logit contributions | |
esame | -5.425 |
(% | -5.227 |
atos | -4.888 |
ordan | -4.786 |
-+-+ | -4.765 |
Token | ap |
Token ID | 499 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
miscar | +1.286 |
pard | +1.264 |
theless | +1.190 |
Ern | +1.161 |
\": | +1.142 |
Neg logit contributions | |
esame | -1.233 |
(% | -1.159 |
atos | -1.092 |
ordan | -1.080 |
otal | -1.019 |
Token | is |
Token ID | 318 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
miscar | +2.154 |
pard | +2.115 |
theless | +1.986 |
Ern | +1.952 |
\": | +1.925 |
Neg logit contributions | |
esame | -1.887 |
(% | -1.731 |
atos | -1.647 |
ordan | -1.631 |
otal | -1.544 |
Token | as |
Token ID | 355 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
esame | +0.705 |
(% | +0.657 |
atos | +0.618 |
ordan | +0.605 |
otal | +0.576 |
Neg logit contributions | |
miscar | -0.842 |
pard | -0.825 |
theless | -0.781 |
Ern | -0.767 |
\": | -0.750 |
Token | important |
Token ID | 1593 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
esame | +0.507 |
(% | +0.462 |
atos | +0.427 |
ordan | +0.418 |
otal | +0.394 |
Neg logit contributions | |
miscar | -0.807 |
pard | -0.795 |
theless | -0.756 |
Ern | -0.745 |
\": | -0.731 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
esame | +0.720 |
(% | +0.668 |
atos | +0.638 |
ordan | +0.627 |
otal | +0.596 |
Neg logit contributions | |
miscar | -0.760 |
pard | -0.745 |
theless | -0.693 |
Ern | -0.688 |
\": | -0.672 |
Token | When |
Token ID | 1649 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
esame | +0.912 |
(% | +0.855 |
atos | +0.814 |
ordan | +0.799 |
otal | +0.764 |
Neg logit contributions | |
miscar | -0.864 |
pard | -0.845 |
theless | -0.794 |
Ern | -0.781 |
\": | -0.760 |
Token | Re |
Token ID | 797 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
miscar | +0.087 |
pard | +0.085 |
theless | +0.080 |
Ern | +0.079 |
\": | +0.077 |
Neg logit contributions | |
esame | -0.074 |
(% | -0.068 |
atos | -0.065 |
ordan | -0.064 |
otal | -0.061 |
Token | |
Token ID | 3907 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
miscar | +0.762 |
pard | +0.749 |
theless | +0.659 |
Ern | +0.646 |
\": | +0.624 |
Neg logit contributions | |
esame | -1.809 |
(% | -1.746 |
atos | -1.666 |
ordan | -1.646 |
otal | -1.604 |
Token | pub |
Token ID | 12984 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
pard | +3.312 |
miscar | +3.250 |
theless | +2.955 |
\": | +2.843 |
roe | +2.843 |
Neg logit contributions | |
esame | -4.631 |
(% | -4.464 |
atos | -4.260 |
ordan | -4.116 |
ateral | -4.114 |
Token | |
Token ID | 3907 |
Feature activation | -7.81e+00 |
Pos logit contributions | |
miscar | +0.377 |
pard | +0.362 |
theless | +0.326 |
Ern | +0.314 |
\": | +0.300 |
Neg logit contributions | |
esame | -0.935 |
(% | -0.896 |
atos | -0.863 |
ordan | -0.852 |
otal | -0.825 |
Token | lic |
Token ID | 677 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
pard | +5.099 |
miscar | +5.066 |
roe | +4.637 |
theless | +4.613 |
\": | +4.512 |
Neg logit contributions | |
esame | -6.281 |
(% | -6.183 |
atos | -5.723 |
ordan | -5.547 |
-+-+ | -5.530 |
Token | |
Token ID | 3907 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
miscar | +1.693 |
pard | +1.669 |
theless | +1.454 |
\": | +1.408 |
Ern | +1.396 |
Neg logit contributions | |
esame | -3.906 |
(% | -3.729 |
atos | -3.599 |
ordan | -3.548 |
otal | -3.453 |
Token | ans |
Token ID | 504 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
pard | +5.474 |
miscar | +5.465 |
theless | +5.066 |
roe | +5.019 |
\": | +5.010 |
Neg logit contributions | |
esame | -4.051 |
(% | -3.892 |
-+-+ | -3.449 |
atos | -3.417 |
ordan | -3.364 |
Token | want |
Token ID | 765 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
miscar | +0.621 |
pard | +0.609 |
theless | +0.566 |
Ern | +0.559 |
\": | +0.547 |
Neg logit contributions | |
esame | -0.607 |
(% | -0.564 |
atos | -0.538 |
ordan | -0.531 |
otal | -0.505 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
esame | +0.143 |
(% | +0.133 |
atos | +0.126 |
ordan | +0.124 |
otal | +0.118 |
Neg logit contributions | |
miscar | -0.167 |
pard | -0.165 |
theless | -0.154 |
Ern | -0.152 |
\": | -0.149 |
Token | END |
Token ID | 10619 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
miscar | +0.664 |
pard | +0.642 |
\": | +0.598 |
theless | +0.595 |
Ern | +0.594 |
Neg logit contributions | |
esame | -0.836 |
(% | -0.782 |
atos | -0.758 |
ordan | -0.732 |
otal | -0.710 |
Token | AN |
Token ID | 1565 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
esame | +1.195 |
(% | +1.116 |
atos | +1.048 |
ordan | +1.026 |
otal | +0.973 |
Neg logit contributions | |
miscar | -1.473 |
pard | -1.442 |
theless | -1.370 |
Ern | -1.343 |
\": | -1.312 |
Token | TS |
Token ID | 4694 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
esame | +0.726 |
(% | +0.682 |
atos | +0.652 |
ordan | +0.647 |
otal | +0.620 |
Neg logit contributions | |
miscar | -0.500 |
pard | -0.487 |
theless | -0.451 |
Ern | -0.440 |
\": | -0.435 |
Token | � |
Token ID | 447 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
miscar | +0.537 |
pard | +0.520 |
theless | +0.479 |
Ern | +0.465 |
\": | +0.449 |
Neg logit contributions | |
esame | -0.938 |
(% | -0.893 |
atos | -0.856 |
ordan | -0.844 |
otal | -0.814 |
Token | � |
Token ID | 247 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
miscar | +1.093 |
pard | +1.067 |
Ern | +0.989 |
\": | +0.988 |
theless | +0.982 |
Neg logit contributions | |
esame | -0.888 |
(% | -0.812 |
atos | -0.773 |
ordan | -0.750 |
otal | -0.712 |
Token | C |
Token ID | 327 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
miscar | +0.124 |
pard | +0.121 |
theless | +0.113 |
Ern | +0.111 |
\": | +0.108 |
Neg logit contributions | |
esame | -0.141 |
(% | -0.133 |
atos | -0.126 |
ordan | -0.124 |
otal | -0.119 |
Token | OU |
Token ID | 2606 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
miscar | +3.191 |
\": | +2.984 |
pard | +2.945 |
roe | +2.763 |
…………………… | +2.623 |
Neg logit contributions | |
esame | -8.032 |
(% | -7.534 |
atos | -7.361 |
ordan | -7.254 |
Matrix | -7.061 |
Token | NS |
Token ID | 8035 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
miscar | +1.451 |
pard | +1.398 |
\": | +1.306 |
Ern | +1.270 |
theless | +1.267 |
Neg logit contributions | |
esame | -1.955 |
(% | -1.792 |
atos | -1.735 |
ordan | -1.721 |
otal | -1.662 |
Token | EL |
Token ID | 3698 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
miscar | +2.509 |
pard | +2.457 |
\": | +2.341 |
Ern | +2.256 |
roe | +2.209 |
Neg logit contributions | |
esame | -2.562 |
(% | -2.366 |
atos | -2.326 |
ordan | -2.257 |
otal | -2.161 |
Token | : |
Token ID | 25 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
miscar | +0.215 |
pard | +0.209 |
theless | +0.193 |
Ern | +0.190 |
\": | +0.189 |
Neg logit contributions | |
esame | -0.291 |
(% | -0.273 |
atos | -0.263 |
ordan | -0.258 |
otal | -0.249 |
Token | We |
Token ID | 775 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
miscar | +2.695 |
pard | +2.607 |
Ern | +2.453 |
theless | +2.384 |
\": | +2.343 |
Neg logit contributions | |
esame | -3.347 |
(% | -3.087 |
atos | -3.018 |
ordan | -2.954 |
otal | -2.851 |
Token | McCorm |
Token ID | 42037 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
miscar | +2.088 |
pard | +2.032 |
theless | +1.896 |
Ern | +1.881 |
\": | +1.793 |
Neg logit contributions | |
esame | -2.902 |
(% | -2.735 |
atos | -2.628 |
ordan | -2.567 |
otal | -2.499 |
Token | ack |
Token ID | 441 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
miscar | +1.434 |
pard | +1.392 |
\": | +1.268 |
theless | +1.259 |
roe | +1.254 |
Neg logit contributions | |
esame | -1.768 |
(% | -1.663 |
atos | -1.581 |
ordan | -1.540 |
otal | -1.496 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
esame | +0.482 |
(% | +0.457 |
atos | +0.431 |
ordan | +0.424 |
otal | +0.405 |
Neg logit contributions | |
miscar | -0.442 |
pard | -0.431 |
theless | -0.407 |
Ern | -0.398 |
\": | -0.388 |
Token |
|
Token ID | 198 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
esame | +0.336 |
(% | +0.314 |
atos | +0.302 |
ordan | +0.296 |
otal | +0.285 |
Neg logit contributions | |
miscar | -0.271 |
pard | -0.263 |
theless | -0.242 |
Ern | -0.240 |
\": | -0.237 |
Token | 2005 |
Token ID | 14315 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
miscar | +0.553 |
pard | +0.544 |
theless | +0.515 |
Ern | +0.503 |
\": | +0.500 |
Neg logit contributions | |
esame | -0.397 |
(% | -0.365 |
atos | -0.346 |
ordan | -0.335 |
otal | -0.315 |
Token | Ray |
Token ID | 7760 |
Feature activation | -7.62e+00 |
Pos logit contributions | |
esame | +1.141 |
(% | +1.072 |
atos | +1.015 |
ordan | +0.994 |
otal | +0.950 |
Neg logit contributions | |
miscar | -1.200 |
pard | -1.173 |
theless | -1.105 |
Ern | -1.094 |
\": | -1.060 |
Token | Rom |
Token ID | 3570 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
miscar | +5.036 |
pard | +4.895 |
Ern | +4.774 |
roe | +4.480 |
\": | +4.420 |
Neg logit contributions | |
esame | -6.086 |
(% | -5.688 |
atos | -5.539 |
otal | -5.297 |
ateral | -5.233 |
Token | ano |
Token ID | 5733 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
miscar | +2.681 |
pard | +2.649 |
roe | +2.457 |
\": | +2.425 |
theless | +2.418 |
Neg logit contributions | |
esame | -2.490 |
(% | -2.317 |
atos | -2.167 |
-+-+ | -2.091 |
ordan | -2.077 |
Token | 2006 |
Token ID | 4793 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
esame | +1.735 |
(% | +1.655 |
atos | +1.523 |
ordan | +1.510 |
otal | +1.426 |
Neg logit contributions | |
miscar | -2.008 |
pard | -1.958 |
theless | -1.876 |
Ern | -1.843 |
\": | -1.791 |
Token | Tony |
Token ID | 8832 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
miscar | +0.101 |
pard | +0.099 |
Ern | +0.093 |
theless | +0.093 |
\": | +0.090 |
Neg logit contributions | |
esame | -0.088 |
(% | -0.083 |
atos | -0.078 |
ordan | -0.076 |
otal | -0.073 |
Token | Shal |
Token ID | 47974 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
miscar | +0.527 |
pard | +0.509 |
Ern | +0.467 |
theless | +0.463 |
\": | +0.449 |
Neg logit contributions | |
esame | -0.781 |
(% | -0.736 |
atos | -0.708 |
ordan | -0.696 |
otal | -0.674 |
Token | McCorm |
Token ID | 42037 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
miscar | +1.824 |
pard | +1.779 |
theless | +1.673 |
Ern | +1.651 |
\": | +1.580 |
Neg logit contributions | |
esame | -2.353 |
(% | -2.213 |
atos | -2.126 |
ordan | -2.075 |
otal | -2.016 |
Token | ack |
Token ID | 441 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
miscar | +1.076 |
pard | +1.047 |
\": | +0.953 |
theless | +0.948 |
roe | +0.945 |
Neg logit contributions | |
esame | -1.313 |
(% | -1.242 |
atos | -1.172 |
ordan | -1.151 |
otal | -1.114 |
Token |
|
Token ID | 198 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
esame | +1.044 |
(% | +0.983 |
atos | +0.915 |
ordan | +0.892 |
otal | +0.850 |
Neg logit contributions | |
miscar | -1.248 |
pard | -1.216 |
theless | -1.163 |
Ern | -1.136 |
\": | -1.112 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
esame | +0.043 |
(% | +0.040 |
atos | +0.038 |
ordan | +0.038 |
otal | +0.036 |
Neg logit contributions | |
miscar | -0.034 |
pard | -0.033 |
theless | -0.030 |
Ern | -0.030 |
\": | -0.029 |
Token | 2003 |
Token ID | 16088 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
miscar | +1.791 |
pard | +1.748 |
theless | +1.676 |
Ern | +1.654 |
\": | +1.651 |
Neg logit contributions | |
esame | -1.166 |
(% | -1.061 |
atos | -0.997 |
ordan | -0.976 |
otal | -0.904 |
Token | Ray |
Token ID | 7760 |
Feature activation | -7.60e+00 |
Pos logit contributions | |
esame | +1.082 |
(% | +1.016 |
atos | +0.962 |
ordan | +0.940 |
otal | +0.899 |
Neg logit contributions | |
miscar | -1.154 |
pard | -1.129 |
theless | -1.063 |
Ern | -1.053 |
\": | -1.021 |
Token | Rom |
Token ID | 3570 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
miscar | +5.002 |
pard | +4.870 |
Ern | +4.765 |
roe | +4.436 |
\": | +4.378 |
Neg logit contributions | |
esame | -6.064 |
(% | -5.702 |
atos | -5.558 |
otal | -5.324 |
ateral | -5.242 |
Token | ano |
Token ID | 5733 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
miscar | +2.823 |
pard | +2.789 |
roe | +2.590 |
\": | +2.552 |
theless | +2.543 |
Neg logit contributions | |
esame | -2.640 |
(% | -2.468 |
atos | -2.296 |
-+-+ | -2.226 |
ordan | -2.206 |
Token | 2004 |
Token ID | 5472 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
esame | +1.795 |
(% | +1.690 |
atos | +1.523 |
ordan | +1.474 |
otal | +1.389 |
Neg logit contributions | |
miscar | -2.967 |
pard | -2.898 |
theless | -2.809 |
Ern | -2.730 |
\": | -2.693 |
Token | Kel |
Token ID | 15150 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
esame | +0.622 |
(% | +0.577 |
atos | +0.543 |
ordan | +0.527 |
otal | +0.502 |
Neg logit contributions | |
miscar | -0.870 |
pard | -0.853 |
Ern | -0.807 |
theless | -0.806 |
\": | -0.781 |
Token | sey |
Token ID | 4397 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
miscar | +1.504 |
pard | +1.486 |
theless | +1.362 |
Ern | +1.356 |
roe | +1.343 |
Neg logit contributions | |
esame | -1.413 |
(% | -1.339 |
atos | -1.252 |
ordan | -1.227 |
otal | -1.181 |
Token | GR |
Token ID | 10761 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
miscar | +2.846 |
pard | +2.754 |
\": | +2.567 |
roe | +2.562 |
theless | +2.558 |
Neg logit contributions | |
esame | -2.734 |
(% | -2.513 |
atos | -2.473 |
ordan | -2.325 |
otal | -2.264 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
miscar | +2.189 |
pard | +2.123 |
Ern | +1.962 |
theless | +1.950 |
\": | +1.949 |
Neg logit contributions | |
esame | -2.378 |
(% | -2.215 |
atos | -2.133 |
ordan | -2.077 |
otal | -2.011 |
Token | G |
Token ID | 38 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
miscar | +0.940 |
pard | +0.901 |
theless | +0.829 |
Ern | +0.820 |
\": | +0.810 |
Neg logit contributions | |
esame | -1.373 |
(% | -1.267 |
atos | -1.240 |
ordan | -1.216 |
otal | -1.178 |
Token | RAY |
Token ID | 30631 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
miscar | +0.752 |
pard | +0.692 |
roe | +0.476 |
\": | +0.472 |
Ern | +0.441 |
Neg logit contributions | |
esame | -4.791 |
(% | -4.593 |
atos | -4.480 |
ordan | -4.362 |
otal | -4.306 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
miscar | +0.427 |
pard | +0.418 |
theless | +0.391 |
Ern | +0.388 |
\": | +0.379 |
Neg logit contributions | |
esame | -0.372 |
(% | -0.344 |
atos | -0.328 |
ordan | -0.321 |
otal | -0.306 |
Token | # |
Token ID | 1303 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
esame | +0.029 |
(% | +0.028 |
atos | +0.026 |
ordan | +0.025 |
otal | +0.024 |
Neg logit contributions | |
miscar | -0.034 |
pard | -0.034 |
theless | -0.032 |
Ern | -0.031 |
\": | -0.031 |
Token | smooth |
Token ID | 7209 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
pard | +5.082 |
miscar | +5.027 |
theless | +4.647 |
Ern | +4.514 |
\": | +4.470 |
Neg logit contributions | |
esame | -6.109 |
(% | -5.620 |
atos | -5.442 |
ordan | -5.357 |
otal | -5.181 |
Token | the |
Token ID | 262 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
miscar | +1.609 |
pard | +1.576 |
Ern | +1.446 |
theless | +1.433 |
\": | +1.426 |
Neg logit contributions | |
esame | -1.817 |
(% | -1.681 |
atos | -1.624 |
ordan | -1.587 |
otal | -1.530 |
Token | image |
Token ID | 2939 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
miscar | +2.749 |
pard | +2.710 |
Ern | +2.399 |
\": | +2.369 |
theless | +2.318 |
Neg logit contributions | |
esame | -4.098 |
(% | -3.834 |
atos | -3.803 |
ordan | -3.645 |
-+-+ | -3.602 |
Token | using |
Token ID | 1262 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
miscar | +1.838 |
pard | +1.811 |
theless | +1.655 |
Ern | +1.614 |
\": | +1.552 |
Neg logit contributions | |
esame | -2.521 |
(% | -2.323 |
atos | -2.270 |
ordan | -2.254 |
otal | -2.165 |
Token | a |
Token ID | 257 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
miscar | +1.858 |
pard | +1.849 |
Ern | +1.662 |
\": | +1.651 |
theless | +1.635 |
Neg logit contributions | |
esame | -1.937 |
(% | -1.794 |
atos | -1.727 |
ordan | -1.713 |
otal | -1.639 |
Token | . |
Token ID | 13 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
miscar | +1.476 |
pard | +1.451 |
theless | +1.357 |
Ern | +1.330 |
\": | +1.289 |
Neg logit contributions | |
esame | -1.470 |
(% | -1.366 |
atos | -1.306 |
ordan | -1.282 |
otal | -1.207 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
miscar | +0.492 |
pard | +0.480 |
theless | +0.452 |
Ern | +0.444 |
\": | +0.432 |
Neg logit contributions | |
esame | -0.573 |
(% | -0.536 |
atos | -0.512 |
ordan | -0.504 |
otal | -0.483 |
Token |
|
Token ID | 198 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
esame | +0.944 |
(% | +0.892 |
atos | +0.847 |
ordan | +0.832 |
otal | +0.796 |
Neg logit contributions | |
miscar | -0.826 |
pard | -0.806 |
theless | -0.758 |
Ern | -0.740 |
\": | -0.720 |
Token | J |
Token ID | 41 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
esame | +0.724 |
(% | +0.683 |
atos | +0.650 |
ordan | +0.637 |
otal | +0.610 |
Neg logit contributions | |
miscar | -0.638 |
pard | -0.623 |
theless | -0.585 |
Ern | -0.572 |
\": | -0.555 |
Token | ER |
Token ID | 1137 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
esame | +1.600 |
(% | +1.500 |
atos | +1.422 |
ordan | +1.402 |
otal | +1.331 |
Neg logit contributions | |
miscar | -1.605 |
pard | -1.563 |
theless | -1.481 |
Ern | -1.451 |
\": | -1.413 |
Token | US |
Token ID | 2937 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
miscar | +4.508 |
pard | +4.352 |
Ern | +3.953 |
\": | +3.924 |
roe | +3.877 |
Neg logit contributions | |
esame | -5.215 |
(% | -4.850 |
atos | -4.599 |
ordan | -4.522 |
otal | -4.475 |
Token | AL |
Token ID | 1847 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
miscar | +4.730 |
pard | +4.657 |
Ern | +3.983 |
…………………… | +3.917 |
paramilitary | +3.879 |
Neg logit contributions | |
esame | -6.493 |
(% | -5.960 |
ordan | -5.774 |
atos | -5.609 |
chapter | -5.469 |
Token | EM |
Token ID | 3620 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
miscar | +0.476 |
pard | +0.473 |
theless | +0.440 |
Ern | +0.437 |
roe | +0.428 |
Neg logit contributions | |
esame | -0.386 |
(% | -0.349 |
atos | -0.336 |
ordan | -0.329 |
otal | -0.310 |
Token | — |
Token ID | 851 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
miscar | +2.027 |
pard | +1.976 |
theless | +1.849 |
Ern | +1.806 |
\": | +1.771 |
Neg logit contributions | |
esame | -2.595 |
(% | -2.397 |
atos | -2.325 |
ordan | -2.291 |
otal | -2.205 |
Token | Israeli |
Token ID | 6085 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
miscar | +1.855 |
pard | +1.816 |
theless | +1.709 |
Ern | +1.708 |
\": | +1.647 |
Neg logit contributions | |
esame | -1.828 |
(% | -1.684 |
atos | -1.610 |
ordan | -1.581 |
otal | -1.521 |
Token | and |
Token ID | 290 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
miscar | +1.866 |
pard | +1.851 |
theless | +1.700 |
Ern | +1.666 |
\": | +1.626 |
Neg logit contributions | |
esame | -2.045 |
(% | -1.915 |
atos | -1.824 |
ordan | -1.797 |
otal | -1.715 |
Token | :" |
Token ID | 11097 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
miscar | +0.017 |
pard | +0.016 |
theless | +0.016 |
Ern | +0.015 |
\": | +0.015 |
Neg logit contributions | |
esame | -0.010 |
(% | -0.009 |
atos | -0.009 |
ordan | -0.009 |
otal | -0.008 |
Token | or |
Token ID | 393 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
esame | +0.500 |
(% | +0.468 |
atos | +0.446 |
ordan | +0.438 |
otal | +0.418 |
Neg logit contributions | |
miscar | -0.479 |
pard | -0.470 |
theless | -0.436 |
Ern | -0.429 |
\": | -0.422 |
Token | " |
Token ID | 366 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
miscar | +2.110 |
pard | +2.060 |
Ern | +1.875 |
\": | +1.871 |
theless | +1.836 |
Neg logit contributions | |
esame | -2.250 |
(% | -2.037 |
atos | -1.992 |
ordan | -1.964 |
otal | -1.880 |
Token | ex |
Token ID | 1069 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
miscar | +0.112 |
pard | +0.111 |
theless | +0.103 |
Ern | +0.101 |
\": | +0.101 |
Neg logit contributions | |
esame | -0.103 |
(% | -0.097 |
atos | -0.091 |
ordan | -0.089 |
otal | -0.085 |
Token | :" |
Token ID | 11097 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
miscar | +1.307 |
pard | +1.288 |
theless | +1.230 |
\": | +1.211 |
Ern | +1.203 |
Neg logit contributions | |
esame | -0.935 |
(% | -0.855 |
atos | -0.818 |
ordan | -0.803 |
otal | -0.753 |
Token | [ |
Token ID | 685 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
miscar | +0.691 |
pard | +0.678 |
theless | +0.633 |
Ern | +0.621 |
\": | +0.603 |
Neg logit contributions | |
esame | -0.741 |
(% | -0.691 |
atos | -0.662 |
ordan | -0.653 |
otal | -0.622 |
Token | white |
Token ID | 11186 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
pard | +4.965 |
miscar | +4.958 |
theless | +4.798 |
\": | +4.482 |
roe | +4.470 |
Neg logit contributions | |
esame | -5.876 |
(% | -5.483 |
ordan | -5.240 |
atos | -5.223 |
ateral | -4.884 |
Token | ] |
Token ID | 60 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
miscar | +0.656 |
pard | +0.638 |
theless | +0.596 |
Ern | +0.582 |
\": | +0.565 |
Neg logit contributions | |
esame | -0.874 |
(% | -0.828 |
atos | -0.789 |
ordan | -0.776 |
otal | -0.746 |
Token | optional |
Token ID | 11902 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
esame | +0.047 |
(% | +0.044 |
atos | +0.042 |
ordan | +0.041 |
otal | +0.039 |
Neg logit contributions | |
miscar | -0.050 |
pard | -0.049 |
theless | -0.046 |
Ern | -0.045 |
\": | -0.044 |
Token | white |
Token ID | 2330 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
pard | +3.279 |
miscar | +3.244 |
theless | +3.020 |
Ern | +2.881 |
\": | +2.874 |
Neg logit contributions | |
esame | -4.716 |
(% | -4.368 |
atos | -4.298 |
ordan | -4.259 |
otal | -4.033 |
Token | space |
Token ID | 2272 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
miscar | +2.155 |
pard | +2.125 |
theless | +2.001 |
Ern | +1.951 |
\": | +1.927 |
Neg logit contributions | |
esame | -1.925 |
(% | -1.783 |
atos | -1.713 |
ordan | -1.676 |
otal | -1.587 |
Token | io |
Token ID | 952 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
miscar | +1.218 |
pard | +1.194 |
theless | +1.129 |
Ern | +1.107 |
roe | +1.091 |
Neg logit contributions | |
esame | -1.035 |
(% | -0.972 |
atos | -0.904 |
ordan | -0.891 |
otal | -0.839 |
Token | on |
Token ID | 319 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
esame | +0.489 |
(% | +0.459 |
atos | +0.434 |
ordan | +0.426 |
otal | +0.406 |
Neg logit contributions | |
miscar | -0.503 |
pard | -0.492 |
theless | -0.465 |
Ern | -0.455 |
\": | -0.445 |
Token | Fox |
Token ID | 5426 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
esame | +1.023 |
(% | +0.960 |
atos | +0.909 |
ordan | +0.892 |
otal | +0.849 |
Neg logit contributions | |
miscar | -1.076 |
pard | -1.053 |
theless | -0.993 |
Ern | -0.975 |
\": | -0.950 |
Token | News |
Token ID | 3000 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
esame | +1.423 |
(% | +1.336 |
atos | +1.260 |
ordan | +1.233 |
otal | +1.174 |
Neg logit contributions | |
miscar | -1.528 |
pard | -1.493 |
theless | -1.420 |
Ern | -1.384 |
\": | -1.352 |
Token | Chan |
Token ID | 18704 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
esame | +1.024 |
(% | +0.962 |
atos | +0.907 |
ordan | +0.889 |
otal | +0.847 |
Neg logit contributions | |
miscar | -1.080 |
pard | -1.056 |
theless | -1.000 |
Ern | -0.977 |
\": | -0.954 |
Token | |
Token ID | 3907 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
miscar | +0.012 |
pard | +0.011 |
theless | +0.010 |
Ern | +0.010 |
\": | +0.009 |
Neg logit contributions | |
esame | -0.029 |
(% | -0.028 |
atos | -0.027 |
ordan | -0.027 |
otal | -0.026 |
Token | nel |
Token ID | 4954 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
miscar | +5.606 |
pard | +5.563 |
theless | +5.209 |
roe | +5.140 |
hower | +5.125 |
Neg logit contributions | |
esame | -5.228 |
(% | -5.064 |
atos | -4.592 |
ordan | -4.580 |
ateral | -4.399 |
Token | after |
Token ID | 706 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
miscar | +1.012 |
pard | +0.989 |
theless | +0.925 |
Ern | +0.913 |
\": | +0.890 |
Neg logit contributions | |
esame | -1.048 |
(% | -0.986 |
atos | -0.937 |
ordan | -0.918 |
otal | -0.879 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
esame | +1.375 |
(% | +1.286 |
atos | +1.214 |
ordan | +1.189 |
otal | +1.130 |
Neg logit contributions | |
miscar | -1.564 |
pard | -1.532 |
theless | -1.449 |
Ern | -1.423 |
\": | -1.390 |
Token | nor |
Token ID | 4249 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
esame | +0.089 |
(% | +0.084 |
atos | +0.079 |
ordan | +0.078 |
otal | +0.074 |
Neg logit contributions | |
miscar | -0.093 |
pard | -0.091 |
theless | -0.085 |
Ern | -0.084 |
\": | -0.082 |
Token | |
Token ID | 3907 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
miscar | +0.494 |
pard | +0.486 |
theless | +0.437 |
Ern | +0.429 |
\": | +0.412 |
Neg logit contributions | |
esame | -0.895 |
(% | -0.853 |
atos | -0.821 |
ordan | -0.811 |
otal | -0.783 |
Token | : |
Token ID | 25 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
miscar | +1.100 |
pard | +1.074 |
theless | +1.009 |
Ern | +0.992 |
\": | +0.968 |
Neg logit contributions | |
esame | -1.092 |
(% | -1.022 |
atos | -0.972 |
ordan | -0.953 |
otal | -0.908 |
Token | you |
Token ID | 345 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
esame | +0.238 |
(% | +0.224 |
atos | +0.211 |
ordan | +0.207 |
otal | +0.198 |
Neg logit contributions | |
miscar | -0.244 |
pard | -0.239 |
theless | -0.226 |
Ern | -0.221 |
\": | -0.216 |
Token | � |
Token ID | 447 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
miscar | +0.763 |
pard | +0.744 |
theless | +0.696 |
Ern | +0.685 |
\": | +0.671 |
Neg logit contributions | |
esame | -0.761 |
(% | -0.712 |
atos | -0.677 |
ordan | -0.665 |
otal | -0.635 |
Token | � |
Token ID | 247 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
esame | +0.541 |
(% | +0.501 |
atos | +0.472 |
ordan | +0.458 |
otal | +0.433 |
Neg logit contributions | |
miscar | -0.712 |
pard | -0.697 |
theless | -0.656 |
Ern | -0.648 |
\": | -0.639 |
Token | re |
Token ID | 260 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
esame | +0.520 |
(% | +0.489 |
atos | +0.464 |
ordan | +0.456 |
otal | +0.435 |
Neg logit contributions | |
miscar | -0.491 |
pard | -0.480 |
theless | -0.452 |
Ern | -0.442 |
\": | -0.432 |
Token | either |
Token ID | 2035 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
miscar | +0.826 |
pard | +0.812 |
theless | +0.762 |
Ern | +0.750 |
\": | +0.732 |
Neg logit contributions | |
esame | -0.793 |
(% | -0.738 |
atos | -0.699 |
ordan | -0.687 |
otal | -0.652 |
Token | one |
Token ID | 530 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
pard | +5.503 |
miscar | +5.460 |
Ern | +5.045 |
theless | +4.923 |
Scotland | +4.844 |
Neg logit contributions | |
esame | -5.601 |
(% | -4.980 |
ordan | -4.845 |
atos | -4.832 |
otal | -4.550 |
Token | of |
Token ID | 286 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
miscar | +1.041 |
pard | +1.022 |
theless | +0.958 |
Ern | +0.941 |
\": | +0.918 |
Neg logit contributions | |
esame | -1.052 |
(% | -0.980 |
atos | -0.934 |
ordan | -0.918 |
otal | -0.875 |
Token | us |
Token ID | 514 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
miscar | +0.888 |
pard | +0.869 |
theless | +0.819 |
Ern | +0.808 |
\": | +0.786 |
Neg logit contributions | |
esame | -0.856 |
(% | -0.800 |
atos | -0.757 |
ordan | -0.743 |
otal | -0.708 |
Token | , |
Token ID | 11 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
esame | +0.177 |
(% | +0.167 |
atos | +0.158 |
ordan | +0.155 |
otal | +0.147 |
Neg logit contributions | |
miscar | -0.180 |
pard | -0.176 |
theless | -0.167 |
Ern | -0.163 |
\": | -0.159 |
Token | or |
Token ID | 393 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
esame | +0.441 |
(% | +0.414 |
atos | +0.392 |
ordan | +0.384 |
otal | +0.367 |
Neg logit contributions | |
miscar | -0.447 |
pard | -0.437 |
theless | -0.413 |
Ern | -0.405 |
\": | -0.395 |
Token | at |
Token ID | 379 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
miscar | +1.198 |
pard | +1.170 |
theless | +1.095 |
Ern | +1.076 |
\": | +1.053 |
Neg logit contributions | |
esame | -1.277 |
(% | -1.195 |
atos | -1.138 |
ordan | -1.122 |
otal | -1.070 |
Token | the |
Token ID | 262 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
miscar | +3.396 |
pard | +3.319 |
\": | +3.005 |
Ern | +2.998 |
theless | +2.901 |
Neg logit contributions | |
esame | -4.110 |
(% | -3.780 |
atos | -3.761 |
ordan | -3.637 |
otal | -3.478 |
Token | margin |
Token ID | 10330 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
miscar | +3.871 |
pard | +3.819 |
Ern | +3.405 |
\": | +3.397 |
theless | +3.364 |
Neg logit contributions | |
esame | -4.114 |
atos | -3.854 |
(% | -3.781 |
ordan | -3.638 |
otal | -3.522 |
Token | , |
Token ID | 11 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
miscar | +2.877 |
pard | +2.807 |
theless | +2.640 |
Ern | +2.584 |
\": | +2.528 |
Neg logit contributions | |
esame | -2.899 |
(% | -2.686 |
atos | -2.588 |
ordan | -2.538 |
otal | -2.405 |
Token | as |
Token ID | 355 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
miscar | +2.002 |
pard | +1.951 |
theless | +1.831 |
Ern | +1.788 |
\": | +1.742 |
Neg logit contributions | |
esame | -2.284 |
(% | -2.148 |
atos | -2.056 |
ordan | -2.018 |
otal | -1.935 |
Token | the |
Token ID | 262 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
miscar | +2.666 |
pard | +2.592 |
theless | +2.450 |
Ern | +2.410 |
\": | +2.353 |
Neg logit contributions | |
esame | -2.725 |
(% | -2.535 |
atos | -2.436 |
ordan | -2.393 |
otal | -2.264 |
Token | dwelling |
Token ID | 26765 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
miscar | +3.179 |
pard | +3.068 |
theless | +2.901 |
Ern | +2.672 |
roe | +2.619 |
Neg logit contributions | |
esame | -7.643 |
(% | -7.170 |
atos | -7.084 |
ordan | -6.888 |
otal | -6.701 |
Token | supply |
Token ID | 5127 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
miscar | +0.184 |
pard | +0.181 |
theless | +0.170 |
Ern | +0.168 |
\": | +0.166 |
Neg logit contributions | |
esame | -0.142 |
(% | -0.131 |
atos | -0.124 |
ordan | -0.120 |
otal | -0.114 |
Token | builds |
Token ID | 12188 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
miscar | +0.148 |
pard | +0.144 |
theless | +0.134 |
Ern | +0.131 |
\": | +0.131 |
Neg logit contributions | |
esame | -0.125 |
(% | -0.113 |
atos | -0.109 |
ordan | -0.107 |
otal | -0.101 |
Token | over |
Token ID | 625 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
miscar | +1.754 |
pard | +1.716 |
theless | +1.594 |
Ern | +1.571 |
\": | +1.558 |
Neg logit contributions | |
esame | -1.517 |
(% | -1.367 |
atos | -1.346 |
ordan | -1.293 |
otal | -1.239 |
Token | time |
Token ID | 640 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
miscar | +1.278 |
pard | +1.261 |
theless | +1.087 |
\": | +1.086 |
Ern | +1.084 |
Neg logit contributions | |
esame | -2.135 |
(% | -1.986 |
atos | -1.945 |
ordan | -1.894 |
otal | -1.847 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
esame | +1.942 |
(% | +1.816 |
atos | +1.686 |
ordan | +1.642 |
otal | +1.565 |
Neg logit contributions | |
miscar | -2.634 |
pard | -2.589 |
theless | -2.491 |
Ern | -2.408 |
\": | -2.392 |
Token | looks |
Token ID | 3073 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
esame | +1.779 |
(% | +1.674 |
atos | +1.572 |
ordan | +1.540 |
otal | +1.472 |
Neg logit contributions | |
miscar | -1.922 |
pard | -1.874 |
theless | -1.790 |
Ern | -1.740 |
\": | -1.712 |
Token | like |
Token ID | 588 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
miscar | +0.028 |
pard | +0.027 |
theless | +0.026 |
Ern | +0.025 |
\": | +0.025 |
Neg logit contributions | |
esame | -0.025 |
(% | -0.024 |
atos | -0.023 |
ordan | -0.022 |
otal | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
esame | +0.360 |
(% | +0.338 |
atos | +0.319 |
ordan | +0.312 |
otal | +0.297 |
Neg logit contributions | |
miscar | -0.401 |
pard | -0.394 |
theless | -0.374 |
Ern | -0.365 |
\": | -0.357 |
Token | and |
Token ID | 290 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
miscar | +1.562 |
pard | +1.522 |
theless | +1.411 |
Ern | +1.393 |
\": | +1.352 |
Neg logit contributions | |
esame | -1.692 |
(% | -1.593 |
atos | -1.511 |
ordan | -1.490 |
otal | -1.421 |
Token | smells |
Token ID | 25760 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
miscar | +2.624 |
pard | +2.558 |
theless | +2.383 |
Ern | +2.347 |
\": | +2.285 |
Neg logit contributions | |
esame | -2.562 |
(% | -2.381 |
atos | -2.246 |
ordan | -2.234 |
otal | -2.118 |
Token | like |
Token ID | 588 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
miscar | +5.111 |
pard | +4.982 |
Ern | +4.577 |
theless | +4.513 |
\": | +4.475 |
Neg logit contributions | |
esame | -5.807 |
(% | -5.370 |
ordan | -5.113 |
atos | -5.068 |
otal | -4.822 |
Token | in |
Token ID | 287 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
miscar | +0.403 |
pard | +0.394 |
theless | +0.371 |
Ern | +0.364 |
\": | +0.355 |
Neg logit contributions | |
esame | -0.406 |
(% | -0.380 |
atos | -0.361 |
ordan | -0.354 |
otal | -0.338 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
miscar | +1.144 |
pard | +1.121 |
theless | +1.054 |
Ern | +1.041 |
\": | +1.015 |
Neg logit contributions | |
esame | -1.077 |
(% | -1.009 |
atos | -0.950 |
ordan | -0.938 |
otal | -0.890 |
Token | cl |
Token ID | 537 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
miscar | +0.819 |
pard | +0.804 |
theless | +0.749 |
Ern | +0.744 |
\": | +0.725 |
Neg logit contributions | |
esame | -0.765 |
(% | -0.713 |
atos | -0.675 |
ordan | -0.666 |
otal | -0.631 |
Token | atter |
Token ID | 1436 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
esame | +0.444 |
(% | +0.417 |
atos | +0.392 |
ordan | +0.386 |
otal | +0.366 |
Neg logit contributions | |
miscar | -0.471 |
pard | -0.460 |
theless | -0.434 |
Ern | -0.426 |
\": | -0.416 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
esame | +1.464 |
(% | +1.376 |
atos | +1.265 |
ordan | +1.251 |
otal | +1.189 |
Neg logit contributions | |
miscar | -1.834 |
pard | -1.787 |
theless | -1.732 |
Ern | -1.667 |
\": | -1.652 |
Token | To |
Token ID | 1675 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
miscar | +1.237 |
pard | +1.211 |
theless | +1.145 |
Ern | +1.124 |
\": | +1.097 |
Neg logit contributions | |
esame | -1.116 |
(% | -1.045 |
atos | -0.987 |
ordan | -0.966 |
otal | -0.920 |
Token | better |
Token ID | 1365 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
miscar | +1.357 |
pard | +1.333 |
theless | +1.255 |
Ern | +1.238 |
\": | +1.204 |
Neg logit contributions | |
esame | -1.183 |
(% | -1.105 |
atos | -1.045 |
ordan | -1.024 |
otal | -0.970 |
Token | understand |
Token ID | 1833 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
miscar | +0.700 |
pard | +0.681 |
theless | +0.624 |
Ern | +0.618 |
\": | +0.597 |
Neg logit contributions | |
esame | -1.017 |
(% | -0.969 |
atos | -0.924 |
ordan | -0.910 |
otal | -0.876 |
Token | the |
Token ID | 262 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
esame | +0.739 |
(% | +0.694 |
atos | +0.656 |
ordan | +0.643 |
otal | +0.613 |
Neg logit contributions | |
miscar | -0.775 |
pard | -0.758 |
theless | -0.716 |
Ern | -0.702 |
\": | -0.685 |
Token | selection |
Token ID | 6356 |
Feature activation | -7.25e+00 |
Pos logit contributions | |
miscar | +1.360 |
pard | +1.342 |
theless | +1.223 |
Ern | +1.217 |
\": | +1.184 |
Neg logit contributions | |
esame | -1.509 |
(% | -1.420 |
atos | -1.355 |
ordan | -1.324 |
otal | -1.271 |
Token | process |
Token ID | 1429 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
miscar | +3.414 |
pard | +3.202 |
Ern | +2.684 |
\": | +2.645 |
theless | +2.467 |
Neg logit contributions | |
esame | -7.650 |
(% | -7.120 |
atos | -6.995 |
ordan | -6.827 |
otal | -6.723 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
miscar | +1.734 |
pard | +1.690 |
Ern | +1.513 |
theless | +1.504 |
\": | +1.500 |
Neg logit contributions | |
esame | -2.218 |
(% | -2.064 |
atos | -2.008 |
ordan | -1.959 |
otal | -1.892 |
Token | eligibility |
Token ID | 20069 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
esame | +0.208 |
(% | +0.198 |
atos | +0.191 |
ordan | +0.188 |
otal | +0.181 |
Neg logit contributions | |
miscar | -0.121 |
pard | -0.118 |
theless | -0.108 |
Ern | -0.105 |
\": | -0.101 |
Token | for |
Token ID | 329 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
esame | +0.406 |
(% | +0.373 |
atos | +0.353 |
ordan | +0.344 |
otal | +0.329 |
Neg logit contributions | |
miscar | -0.540 |
pard | -0.530 |
theless | -0.494 |
Ern | -0.492 |
\": | -0.483 |
Token | the |
Token ID | 262 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
esame | +0.535 |
(% | +0.502 |
atos | +0.477 |
ordan | +0.466 |
otal | +0.446 |
Neg logit contributions | |
miscar | -0.544 |
pard | -0.533 |
theless | -0.499 |
Ern | -0.491 |
\": | -0.480 |
Token | a |
Token ID | 257 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
esame | +0.566 |
(% | +0.527 |
atos | +0.498 |
ordan | +0.489 |
otal | +0.464 |
Neg logit contributions | |
miscar | -0.647 |
pard | -0.635 |
theless | -0.596 |
Ern | -0.587 |
\": | -0.576 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
miscar | +1.075 |
pard | +1.047 |
Ern | +0.963 |
theless | +0.950 |
\": | +0.946 |
Neg logit contributions | |
esame | -0.890 |
(% | -0.807 |
atos | -0.778 |
ordan | -0.756 |
otal | -0.719 |
Token | idea |
Token ID | 2126 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
miscar | +0.306 |
pard | +0.301 |
theless | +0.283 |
Ern | +0.281 |
\": | +0.274 |
Neg logit contributions | |
esame | -0.228 |
(% | -0.209 |
atos | -0.197 |
ordan | -0.193 |
otal | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
miscar | +0.544 |
pard | +0.531 |
Ern | +0.486 |
theless | +0.482 |
\": | +0.481 |
Neg logit contributions | |
esame | -0.574 |
(% | -0.531 |
atos | -0.513 |
ordan | -0.501 |
otal | -0.481 |
Token |
|
Token ID | 198 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
miscar | +1.373 |
pard | +1.340 |
theless | +1.243 |
Ern | +1.231 |
\": | +1.188 |
Neg logit contributions | |
esame | -1.767 |
(% | -1.665 |
atos | -1.590 |
ordan | -1.566 |
otal | -1.505 |
Token |
|
Token ID | 198 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
esame | +3.684 |
(% | +3.536 |
atos | +3.291 |
ordan | +3.236 |
otal | +3.079 |
Neg logit contributions | |
miscar | -3.686 |
pard | -3.604 |
theless | -3.506 |
Ern | -3.360 |
hower | -3.265 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
esame | +3.110 |
(% | +2.818 |
atos | +2.632 |
ordan | +2.542 |
otal | +2.390 |
Neg logit contributions | |
miscar | -5.975 |
pard | -5.805 |
theless | -5.651 |
Ern | -5.546 |
hower | -5.346 |
Token | : |
Token ID | 25 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
esame | +2.916 |
(% | +2.792 |
atos | +2.611 |
ordan | +2.582 |
otal | +2.449 |
Neg logit contributions | |
miscar | -2.610 |
pard | -2.537 |
theless | -2.469 |
Ern | -2.363 |
hower | -2.285 |
Token | Mike |
Token ID | 4995 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
esame | +1.697 |
(% | +1.595 |
atos | +1.505 |
ordan | +1.477 |
otal | +1.407 |
Neg logit contributions | |
miscar | -1.736 |
pard | -1.692 |
theless | -1.607 |
Ern | -1.566 |
\": | -1.542 |
Token | M |
Token ID | 44 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
esame | +1.599 |
(% | +1.507 |
atos | +1.428 |
ordan | +1.404 |
otal | +1.339 |
Neg logit contributions | |
miscar | -1.507 |
pard | -1.467 |
theless | -1.387 |
Ern | -1.346 |
\": | -1.322 |
Token | anners |
Token ID | 15672 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
esame | +1.201 |
(% | +1.126 |
atos | +1.063 |
ordan | +1.047 |
otal | +0.992 |
Neg logit contributions | |
miscar | -1.345 |
pard | -1.310 |
theless | -1.243 |
Ern | -1.221 |
\": | -1.189 |
Token | Stanford |
Token ID | 13863 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
esame | +3.081 |
(% | +2.916 |
atos | +2.734 |
ordan | +2.699 |
otal | +2.542 |
Neg logit contributions | |
miscar | -3.241 |
pard | -3.153 |
theless | -2.998 |
Ern | -2.904 |
\": | -2.871 |
Token | � |
Token ID | 447 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
esame | +1.174 |
(% | +1.095 |
atos | +1.027 |
ordan | +1.005 |
otal | +0.951 |
Neg logit contributions | |
miscar | -1.465 |
pard | -1.434 |
theless | -1.363 |
Ern | -1.337 |
\": | -1.311 |
Token | � |
Token ID | 247 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
esame | +0.051 |
(% | +0.048 |
atos | +0.046 |
ordan | +0.045 |
otal | +0.044 |
Neg logit contributions | |
miscar | -0.034 |
pard | -0.033 |
theless | -0.030 |
Ern | -0.030 |
\": | -0.029 |
Token | s |
Token ID | 82 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
miscar | +0.662 |
pard | +0.648 |
theless | +0.613 |
Ern | +0.601 |
\": | +0.586 |
Neg logit contributions | |
esame | -0.713 |
(% | -0.670 |
atos | -0.635 |
ordan | -0.623 |
otal | -0.597 |
Token | Darrell |
Token ID | 44882 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
esame | +0.957 |
(% | +0.899 |
atos | +0.851 |
ordan | +0.834 |
otal | +0.796 |
Neg logit contributions | |
miscar | -0.968 |
pard | -0.946 |
theless | -0.893 |
Ern | -0.877 |
\": | -0.853 |
Token | Duff |
Token ID | 50209 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
esame | +0.450 |
(% | +0.422 |
atos | +0.399 |
ordan | +0.392 |
otal | +0.373 |
Neg logit contributions | |
miscar | -0.463 |
pard | -0.453 |
theless | -0.427 |
Ern | -0.419 |
\": | -0.409 |
Token | ie |
Token ID | 494 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
esame | +3.883 |
(% | +3.672 |
atos | +3.451 |
ordan | +3.427 |
otal | +3.174 |
Neg logit contributions | |
miscar | -4.763 |
pard | -4.633 |
theless | -4.525 |
Ern | -4.319 |
\": | -4.185 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
esame | +0.219 |
(% | +0.207 |
atos | +0.196 |
ordan | +0.193 |
otal | +0.185 |
Neg logit contributions | |
miscar | -0.192 |
pard | -0.187 |
theless | -0.176 |
Ern | -0.172 |
\": | -0.167 |
Token | and |
Token ID | 290 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
miscar | +1.186 |
pard | +1.168 |
theless | +1.086 |
Ern | +1.078 |
\": | +1.046 |
Neg logit contributions | |
esame | -1.258 |
(% | -1.174 |
atos | -1.126 |
ordan | -1.102 |
otal | -1.055 |
Token | he |
Token ID | 339 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
miscar | +1.540 |
pard | +1.506 |
theless | +1.422 |
Ern | +1.402 |
\": | +1.359 |
Neg logit contributions | |
esame | -1.390 |
(% | -1.289 |
atos | -1.234 |
ordan | -1.203 |
otal | -1.153 |
Token | added |
Token ID | 2087 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
esame | +0.445 |
(% | +0.419 |
atos | +0.396 |
ordan | +0.388 |
otal | +0.370 |
Neg logit contributions | |
miscar | -0.456 |
pard | -0.446 |
theless | -0.422 |
Ern | -0.414 |
\": | -0.403 |
Token | - |
Token ID | 12 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
esame | +1.527 |
(% | +1.433 |
atos | +1.358 |
ordan | +1.332 |
otal | +1.272 |
Neg logit contributions | |
miscar | -1.526 |
pard | -1.492 |
theless | -1.410 |
Ern | -1.378 |
\": | -1.345 |
Token | f |
Token ID | 69 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
miscar | +0.908 |
pard | +0.885 |
theless | +0.831 |
Ern | +0.816 |
roe | +0.809 |
Neg logit contributions | |
esame | -0.877 |
(% | -0.842 |
atos | -0.782 |
ordan | -0.762 |
otal | -0.733 |
Token | antasy |
Token ID | 34921 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
miscar | +0.365 |
pard | +0.357 |
theless | +0.341 |
Ern | +0.335 |
roe | +0.331 |
Neg logit contributions | |
esame | -0.248 |
(% | -0.232 |
atos | -0.215 |
ordan | -0.208 |
otal | -0.197 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
esame | +1.380 |
(% | +1.288 |
atos | +1.211 |
ordan | +1.186 |
otal | +1.125 |
Neg logit contributions | |
miscar | -1.667 |
pard | -1.633 |
theless | -1.550 |
Ern | -1.520 |
\": | -1.488 |
Token | action |
Token ID | 2223 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
esame | +0.198 |
(% | +0.185 |
atos | +0.175 |
ordan | +0.171 |
otal | +0.163 |
Neg logit contributions | |
miscar | -0.220 |
pard | -0.215 |
theless | -0.203 |
Ern | -0.199 |
\": | -0.194 |
Token | shooter |
Token ID | 14273 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
miscar | +0.232 |
pard | +0.226 |
theless | +0.214 |
Ern | +0.209 |
\": | +0.206 |
Neg logit contributions | |
esame | -0.243 |
(% | -0.227 |
atos | -0.216 |
ordan | -0.212 |
otal | -0.203 |
Token | " |
Token ID | 1 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
esame | +4.074 |
(% | +3.798 |
atos | +3.586 |
ordan | +3.455 |
otal | +3.291 |
Neg logit contributions | |
miscar | -5.528 |
pard | -5.417 |
theless | -5.162 |
Ern | -5.026 |
hower | -4.937 |
Token | series |
Token ID | 2168 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
esame | +1.216 |
(% | +1.134 |
atos | +1.067 |
ordan | +1.047 |
otal | +0.992 |
Neg logit contributions | |
miscar | -1.450 |
pard | -1.420 |
theless | -1.345 |
Ern | -1.321 |
\": | -1.292 |
Token | is |
Token ID | 318 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
esame | +0.640 |
(% | +0.597 |
atos | +0.565 |
ordan | +0.556 |
otal | +0.530 |
Neg logit contributions | |
miscar | -0.653 |
pard | -0.638 |
theless | -0.599 |
Ern | -0.589 |
\": | -0.575 |
Token | planned |
Token ID | 6027 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
miscar | +0.419 |
pard | +0.409 |
theless | +0.383 |
Ern | +0.378 |
\": | +0.368 |
Neg logit contributions | |
esame | -0.438 |
(% | -0.407 |
atos | -0.385 |
ordan | -0.381 |
otal | -0.363 |
Token | for |
Token ID | 329 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
esame | +0.579 |
(% | +0.538 |
atos | +0.504 |
ordan | +0.493 |
otal | +0.467 |
Neg logit contributions | |
miscar | -0.766 |
pard | -0.750 |
theless | -0.713 |
Ern | -0.701 |
\": | -0.686 |
Token | screen |
Token ID | 3159 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
miscar | +1.407 |
pard | +1.378 |
theless | +1.273 |
Ern | +1.260 |
\": | +1.219 |
Neg logit contributions | |
esame | -1.674 |
(% | -1.574 |
atos | -1.503 |
ordan | -1.481 |
otal | -1.416 |
Token | grab |
Token ID | 5552 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
miscar | +1.861 |
pard | +1.831 |
theless | +1.735 |
Ern | +1.709 |
\": | +1.677 |
Neg logit contributions | |
esame | -1.288 |
(% | -1.193 |
atos | -1.115 |
ordan | -1.086 |
otal | -1.024 |
Token | ] |
Token ID | 60 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
miscar | +1.769 |
pard | +1.732 |
theless | +1.610 |
Ern | +1.580 |
roe | +1.531 |
Neg logit contributions | |
esame | -2.015 |
(% | -1.886 |
atos | -1.799 |
ordan | -1.770 |
otal | -1.698 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
esame | +0.534 |
(% | +0.504 |
atos | +0.478 |
ordan | +0.468 |
otal | +0.450 |
Neg logit contributions | |
miscar | -0.487 |
pard | -0.475 |
theless | -0.445 |
Ern | -0.434 |
\": | -0.423 |
Token | ( |
Token ID | 7 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
esame | +0.302 |
(% | +0.284 |
atos | +0.270 |
ordan | +0.265 |
otal | +0.254 |
Neg logit contributions | |
miscar | -0.269 |
pard | -0.263 |
theless | -0.247 |
Ern | -0.242 |
\": | -0.236 |
Token | Updated |
Token ID | 17354 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
esame | +1.456 |
(% | +1.371 |
atos | +1.304 |
ordan | +1.275 |
otal | +1.221 |
Neg logit contributions | |
miscar | -1.363 |
pard | -1.332 |
theless | -1.259 |
Ern | -1.226 |
\": | -1.191 |
Token | below |
Token ID | 2174 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
esame | +3.938 |
(% | +3.745 |
atos | +3.489 |
ordan | +3.386 |
otal | +3.265 |
Neg logit contributions | |
miscar | -4.039 |
pard | -3.945 |
theless | -3.839 |
Ern | -3.656 |
\": | -3.616 |
Token | ) |
Token ID | 8 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
esame | +2.152 |
(% | +2.023 |
atos | +1.910 |
ordan | +1.872 |
otal | +1.792 |
Neg logit contributions | |
miscar | -2.160 |
pard | -2.109 |
theless | -2.003 |
Ern | -1.957 |
\": | -1.913 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
esame | +0.978 |
(% | +0.922 |
atos | +0.872 |
ordan | +0.856 |
otal | +0.818 |
Neg logit contributions | |
miscar | -0.916 |
pard | -0.895 |
theless | -0.845 |
Ern | -0.823 |
\": | -0.804 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
esame | +0.896 |
(% | +0.844 |
atos | +0.804 |
ordan | +0.789 |
otal | +0.757 |
Neg logit contributions | |
miscar | -0.766 |
pard | -0.747 |
theless | -0.699 |
Ern | -0.685 |
\": | -0.669 |
Token | The |
Token ID | 464 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
esame | +1.045 |
(% | +0.986 |
atos | +0.937 |
ordan | +0.919 |
otal | +0.879 |
Neg logit contributions | |
miscar | -0.940 |
pard | -0.917 |
theless | -0.865 |
Ern | -0.843 |
\": | -0.818 |
Token | world |
Token ID | 995 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
esame | +0.197 |
(% | +0.176 |
atos | +0.164 |
ordan | +0.157 |
otal | +0.144 |
Neg logit contributions | |
miscar | -0.446 |
pard | -0.440 |
Ern | -0.416 |
theless | -0.415 |
\": | -0.409 |
Token | with |
Token ID | 351 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
esame | +2.219 |
(% | +2.136 |
atos | +1.992 |
ordan | +1.963 |
otal | +1.872 |
Neg logit contributions | |
miscar | -2.033 |
pard | -1.978 |
theless | -1.913 |
Ern | -1.836 |
roe | -1.777 |
Token | kindred |
Token ID | 46449 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
miscar | +0.949 |
pard | +0.933 |
theless | +0.866 |
Ern | +0.855 |
\": | +0.834 |
Neg logit contributions | |
esame | -1.041 |
(% | -0.973 |
atos | -0.928 |
ordan | -0.910 |
otal | -0.870 |
Token | spirits |
Token ID | 13747 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
esame | +1.481 |
(% | +1.371 |
atos | +1.256 |
ordan | +1.218 |
otal | +1.139 |
Neg logit contributions | |
miscar | -2.621 |
pard | -2.558 |
theless | -2.479 |
Ern | -2.443 |
hower | -2.400 |
Token | . |
Token ID | 13 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
esame | +1.891 |
(% | +1.777 |
atos | +1.667 |
ordan | +1.636 |
otal | +1.551 |
Neg logit contributions | |
miscar | -2.155 |
pard | -2.109 |
theless | -2.014 |
Ern | -1.959 |
\": | -1.907 |
Token |
|
Token ID | 198 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
esame | +4.608 |
(% | +4.482 |
atos | +4.124 |
ordan | +4.067 |
otal | +3.790 |
Neg logit contributions | |
miscar | -5.018 |
pard | -4.904 |
theless | -4.835 |
Ern | -4.552 |
roe | -4.471 |
Token |
|
Token ID | 198 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
esame | +4.757 |
(% | +4.645 |
atos | +4.262 |
ordan | +4.202 |
otal | +3.930 |
Neg logit contributions | |
miscar | -5.370 |
pard | -5.290 |
theless | -5.266 |
Ern | -4.955 |
hower | -4.862 |
Token | Sign |
Token ID | 11712 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
esame | +4.529 |
(% | +4.236 |
atos | +4.068 |
ordan | +3.850 |
otal | +3.606 |
Neg logit contributions | |
miscar | -7.371 |
pard | -7.155 |
theless | -6.971 |
Ern | -6.661 |
roe | -6.636 |
Token | up |
Token ID | 510 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
esame | +1.516 |
(% | +1.385 |
atos | +1.274 |
ordan | +1.238 |
otal | +1.153 |
Neg logit contributions | |
miscar | -2.814 |
pard | -2.762 |
theless | -2.649 |
Ern | -2.604 |
\": | -2.555 |
Token | for |
Token ID | 329 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
esame | +1.055 |
(% | +0.974 |
atos | +0.919 |
ordan | +0.899 |
otal | +0.850 |
Neg logit contributions | |
miscar | -1.426 |
pard | -1.402 |
theless | -1.317 |
Ern | -1.304 |
\": | -1.283 |
Token | our |
Token ID | 674 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
esame | +3.244 |
(% | +3.079 |
atos | +2.931 |
ordan | +2.884 |
otal | +2.762 |
Neg logit contributions | |
miscar | -2.757 |
pard | -2.679 |
theless | -2.544 |
Ern | -2.461 |
roe | -2.396 |
Token | carry |
Token ID | 3283 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
esame | +0.757 |
(% | +0.711 |
atos | +0.672 |
ordan | +0.659 |
otal | +0.629 |
Neg logit contributions | |
miscar | -0.772 |
pard | -0.755 |
theless | -0.714 |
Ern | -0.699 |
\": | -0.682 |
Token | the |
Token ID | 262 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
esame | +1.527 |
(% | +1.438 |
atos | +1.357 |
ordan | +1.329 |
otal | +1.267 |
Neg logit contributions | |
miscar | -1.580 |
pard | -1.544 |
theless | -1.466 |
Ern | -1.431 |
\": | -1.398 |
Token | ball |
Token ID | 2613 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
esame | +0.198 |
(% | +0.184 |
atos | +0.175 |
ordan | +0.171 |
otal | +0.163 |
Neg logit contributions | |
miscar | -0.225 |
pard | -0.221 |
theless | -0.208 |
Ern | -0.205 |
\": | -0.200 |
Token | every |
Token ID | 790 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
esame | +2.288 |
(% | +2.165 |
atos | +2.025 |
ordan | +1.985 |
otal | +1.887 |
Neg logit contributions | |
miscar | -2.521 |
pard | -2.468 |
theless | -2.362 |
Ern | -2.296 |
\": | -2.239 |
Token | time |
Token ID | 640 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
esame | +0.758 |
(% | +0.712 |
atos | +0.677 |
ordan | +0.664 |
otal | +0.634 |
Neg logit contributions | |
miscar | -0.729 |
pard | -0.713 |
theless | -0.670 |
Ern | -0.657 |
\": | -0.640 |
Token | and |
Token ID | 290 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
esame | +1.527 |
(% | +1.437 |
atos | +1.343 |
ordan | +1.314 |
otal | +1.247 |
Neg logit contributions | |
miscar | -1.759 |
pard | -1.723 |
theless | -1.642 |
Ern | -1.595 |
\": | -1.566 |
Token | get |
Token ID | 651 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
esame | +0.959 |
(% | +0.900 |
atos | +0.852 |
ordan | +0.835 |
otal | +0.797 |
Neg logit contributions | |
miscar | -0.992 |
pard | -0.970 |
theless | -0.915 |
Ern | -0.897 |
\": | -0.876 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
miscar | +0.410 |
pard | +0.404 |
theless | +0.376 |
Ern | +0.373 |
\": | +0.361 |
Neg logit contributions | |
esame | -0.404 |
(% | -0.374 |
atos | -0.358 |
ordan | -0.351 |
otal | -0.336 |
Token | record |
Token ID | 1700 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
esame | +0.233 |
(% | +0.217 |
atos | +0.205 |
ordan | +0.201 |
otal | +0.192 |
Neg logit contributions | |
miscar | -0.253 |
pard | -0.248 |
theless | -0.233 |
Ern | -0.230 |
\": | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
esame | +0.468 |
(% | +0.433 |
atos | +0.412 |
ordan | +0.403 |
otal | +0.385 |
Neg logit contributions | |
miscar | -0.532 |
pard | -0.521 |
theless | -0.491 |
Ern | -0.485 |
\": | -0.475 |
Token | � |
Token ID | 447 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
esame | +0.412 |
(% | +0.387 |
atos | +0.368 |
ordan | +0.361 |
otal | +0.346 |
Neg logit contributions | |
miscar | -0.385 |
pard | -0.376 |
theless | -0.353 |
Ern | -0.347 |
\": | -0.337 |
Token | New |
Token ID | 3791 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
esame | +2.254 |
(% | +2.129 |
atos | +2.003 |
ordan | +1.939 |
otal | +1.855 |
Neg logit contributions | |
miscar | -2.646 |
pard | -2.592 |
theless | -2.474 |
Ern | -2.396 |
hower | -2.345 |
Token | ]] |
Token ID | 11907 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
miscar | +1.482 |
pard | +1.438 |
theless | +1.321 |
Ern | +1.287 |
\": | +1.270 |
Neg logit contributions | |
esame | -2.340 |
(% | -2.193 |
atos | -2.125 |
ordan | -2.083 |
otal | -2.014 |
Token | } |
Token ID | 92 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
miscar | +0.616 |
pard | +0.602 |
theless | +0.559 |
Ern | +0.550 |
\": | +0.541 |
Neg logit contributions | |
esame | -0.720 |
(% | -0.671 |
atos | -0.645 |
ordan | -0.632 |
otal | -0.608 |
Token | ]; |
Token ID | 11208 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
miscar | +0.845 |
pard | +0.832 |
theless | +0.778 |
Ern | +0.772 |
\": | +0.753 |
Neg logit contributions | |
esame | -0.743 |
(% | -0.678 |
atos | -0.656 |
ordan | -0.639 |
otal | -0.605 |
Token | step |
Token ID | 2239 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
esame | +0.801 |
(% | +0.749 |
atos | +0.705 |
ordan | +0.690 |
otal | +0.655 |
Neg logit contributions | |
miscar | -0.948 |
pard | -0.928 |
theless | -0.880 |
Ern | -0.863 |
\": | -0.844 |
Token | Old |
Token ID | 19620 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
esame | +2.042 |
(% | +1.932 |
atos | +1.806 |
ordan | +1.758 |
otal | +1.680 |
Neg logit contributions | |
miscar | -2.363 |
pard | -2.311 |
theless | -2.195 |
Ern | -2.137 |
\": | -2.082 |
Token | = |
Token ID | 796 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
esame | +0.756 |
(% | +0.704 |
atos | +0.661 |
ordan | +0.646 |
otal | +0.612 |
Neg logit contributions | |
miscar | -0.968 |
pard | -0.949 |
theless | -0.901 |
Ern | -0.885 |
\": | -0.866 |
Token | step |
Token ID | 2239 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
esame | +1.386 |
(% | +1.303 |
atos | +1.227 |
ordan | +1.204 |
otal | +1.147 |
Neg logit contributions | |
miscar | -1.481 |
pard | -1.447 |
theless | -1.371 |
Ern | -1.342 |
\": | -1.311 |
Token | New |
Token ID | 3791 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
esame | +2.182 |
(% | +2.061 |
atos | +1.940 |
ordan | +1.903 |
otal | +1.813 |
Neg logit contributions | |
miscar | -2.253 |
pard | -2.200 |
theless | -2.085 |
Ern | -2.033 |
\": | -1.982 |
Token | ; |
Token ID | 26 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
esame | +0.658 |
(% | +0.615 |
atos | +0.584 |
ordan | +0.572 |
otal | +0.545 |
Neg logit contributions | |
miscar | -0.691 |
pard | -0.677 |
theless | -0.638 |
Ern | -0.626 |
\": | -0.612 |
Token | ]; |
Token ID | 28013 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
esame | +1.152 |
(% | +1.082 |
atos | +1.018 |
ordan | +0.998 |
otal | +0.950 |
Neg logit contributions | |
miscar | -1.264 |
pard | -1.236 |
theless | -1.171 |
Ern | -1.147 |
\": | -1.122 |
Token | after |
Token ID | 706 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
miscar | +0.181 |
pard | +0.177 |
theless | +0.167 |
Ern | +0.164 |
\": | +0.159 |
Neg logit contributions | |
esame | -0.176 |
(% | -0.164 |
atos | -0.156 |
ordan | -0.153 |
otal | -0.146 |
Token | breakfast |
Token ID | 12607 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
esame | +0.831 |
(% | +0.778 |
atos | +0.735 |
ordan | +0.721 |
otal | +0.686 |
Neg logit contributions | |
miscar | -0.896 |
pard | -0.876 |
theless | -0.829 |
Ern | -0.812 |
\": | -0.793 |
Token | , |
Token ID | 11 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
esame | +1.302 |
(% | +1.224 |
atos | +1.156 |
ordan | +1.134 |
otal | +1.080 |
Neg logit contributions | |
miscar | -1.351 |
pard | -1.321 |
theless | -1.248 |
Ern | -1.222 |
\": | -1.194 |
Token | they |
Token ID | 484 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
esame | +0.446 |
(% | +0.419 |
atos | +0.397 |
ordan | +0.390 |
otal | +0.372 |
Neg logit contributions | |
miscar | -0.444 |
pard | -0.434 |
theless | -0.408 |
Ern | -0.401 |
\": | -0.390 |
Token | had |
Token ID | 550 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
esame | +0.506 |
(% | +0.475 |
atos | +0.449 |
ordan | +0.441 |
otal | +0.420 |
Neg logit contributions | |
miscar | -0.521 |
pard | -0.510 |
theless | -0.481 |
Ern | -0.471 |
\": | -0.460 |
Token | me |
Token ID | 502 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
miscar | +0.603 |
pard | +0.591 |
theless | +0.556 |
Ern | +0.546 |
\": | +0.532 |
Neg logit contributions | |
esame | -0.566 |
(% | -0.529 |
atos | -0.499 |
ordan | -0.492 |
otal | -0.469 |
Token | translate |
Token ID | 15772 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
esame | +1.223 |
(% | +1.149 |
atos | +1.085 |
ordan | +1.064 |
otal | +1.013 |
Neg logit contributions | |
miscar | -1.276 |
pard | -1.247 |
theless | -1.180 |
Ern | -1.156 |
\": | -1.129 |
Token | for |
Token ID | 329 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
esame | +1.422 |
(% | +1.333 |
atos | +1.259 |
ordan | +1.234 |
otal | +1.175 |
Neg logit contributions | |
miscar | -1.534 |
pard | -1.501 |
theless | -1.418 |
Ern | -1.391 |
\": | -1.358 |
Token | the |
Token ID | 262 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
esame | +1.076 |
(% | +1.004 |
atos | +0.945 |
ordan | +0.924 |
otal | +0.877 |
Neg logit contributions | |
miscar | -1.299 |
pard | -1.272 |
theless | -1.207 |
Ern | -1.184 |
\": | -1.158 |
Token | players |
Token ID | 1938 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
miscar | +0.309 |
pard | +0.302 |
theless | +0.285 |
Ern | +0.281 |
\": | +0.271 |
Neg logit contributions | |
esame | -0.285 |
(% | -0.266 |
atos | -0.253 |
ordan | -0.248 |
otal | -0.237 |
Token | � |
Token ID | 447 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
miscar | +0.372 |
pard | +0.365 |
theless | +0.342 |
Ern | +0.337 |
\": | +0.328 |
Neg logit contributions | |
esame | -0.372 |
(% | -0.347 |
atos | -0.330 |
ordan | -0.325 |
otal | -0.310 |
Token | � |
Token ID | 250 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
esame | +0.180 |
(% | +0.169 |
atos | +0.159 |
ordan | +0.156 |
otal | +0.149 |
Neg logit contributions | |
miscar | -0.200 |
pard | -0.195 |
theless | -0.185 |
Ern | -0.181 |
\": | -0.177 |
Token | If |
Token ID | 1532 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
esame | +0.314 |
(% | +0.296 |
atos | +0.281 |
ordan | +0.276 |
otal | +0.264 |
Neg logit contributions | |
miscar | -0.278 |
pard | -0.271 |
theless | -0.255 |
Ern | -0.249 |
\": | -0.242 |
Token | there |
Token ID | 612 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
miscar | +1.588 |
pard | +1.555 |
theless | +1.432 |
Ern | +1.410 |
\": | +1.373 |
Neg logit contributions | |
esame | -1.781 |
(% | -1.660 |
atos | -1.589 |
ordan | -1.563 |
otal | -1.493 |
Token | are |
Token ID | 389 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
esame | +2.164 |
(% | +2.044 |
atos | +1.944 |
ordan | +1.899 |
otal | +1.826 |
Neg logit contributions | |
miscar | -1.966 |
pard | -1.933 |
theless | -1.828 |
Ern | -1.793 |
\": | -1.735 |
Token | medicinal |
Token ID | 30381 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
esame | +1.199 |
(% | +1.126 |
atos | +1.064 |
ordan | +1.041 |
otal | +0.990 |
Neg logit contributions | |
miscar | -1.314 |
pard | -1.287 |
theless | -1.224 |
Ern | -1.199 |
\": | -1.172 |
Token | uses |
Token ID | 3544 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
esame | +0.659 |
(% | +0.616 |
atos | +0.583 |
ordan | +0.572 |
otal | +0.543 |
Neg logit contributions | |
miscar | -0.720 |
pard | -0.705 |
theless | -0.664 |
Ern | -0.651 |
\": | -0.636 |
Token | of |
Token ID | 286 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
esame | +0.949 |
(% | +0.888 |
atos | +0.834 |
ordan | +0.814 |
otal | +0.774 |
Neg logit contributions | |
miscar | -1.151 |
pard | -1.127 |
theless | -1.073 |
Ern | -1.052 |
\": | -1.027 |
Token | marijuana |
Token ID | 5727 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
esame | +1.661 |
(% | +1.551 |
atos | +1.448 |
ordan | +1.408 |
otal | +1.341 |
Neg logit contributions | |
miscar | -2.240 |
pard | -2.188 |
theless | -2.099 |
Ern | -2.055 |
roe | -2.012 |
Token | that |
Token ID | 326 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
esame | +1.850 |
(% | +1.752 |
atos | +1.645 |
ordan | +1.605 |
otal | +1.530 |
Neg logit contributions | |
miscar | -2.007 |
pard | -1.956 |
theless | -1.869 |
Ern | -1.831 |
\": | -1.783 |
Token | don |
Token ID | 836 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
esame | +0.158 |
(% | +0.148 |
atos | +0.141 |
ordan | +0.138 |
otal | +0.132 |
Neg logit contributions | |
miscar | -0.155 |
pard | -0.151 |
theless | -0.143 |
Ern | -0.140 |
\": | -0.137 |
Token | � |
Token ID | 447 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
esame | +0.463 |
(% | +0.434 |
atos | +0.415 |
ordan | +0.409 |
otal | +0.393 |
Neg logit contributions | |
miscar | -0.370 |
pard | -0.359 |
theless | -0.333 |
Ern | -0.329 |
\": | -0.326 |
Token | of |
Token ID | 286 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
miscar | +0.733 |
pard | +0.717 |
theless | +0.678 |
Ern | +0.664 |
\": | +0.649 |
Neg logit contributions | |
esame | -0.701 |
(% | -0.659 |
atos | -0.623 |
ordan | -0.610 |
otal | -0.581 |
Token | doses |
Token ID | 16376 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
esame | +1.947 |
(% | +1.850 |
atos | +1.755 |
ordan | +1.725 |
otal | +1.656 |
Neg logit contributions | |
miscar | -1.578 |
pard | -1.538 |
theless | -1.444 |
Ern | -1.410 |
\": | -1.374 |
Token | of |
Token ID | 286 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
esame | +1.633 |
(% | +1.543 |
atos | +1.450 |
ordan | +1.418 |
otal | +1.352 |
Neg logit contributions | |
miscar | -1.726 |
pard | -1.690 |
theless | -1.598 |
Ern | -1.570 |
\": | -1.531 |
Token | alcohol |
Token ID | 5548 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
esame | +1.868 |
(% | +1.769 |
atos | +1.687 |
ordan | +1.659 |
otal | +1.593 |
Neg logit contributions | |
miscar | -1.418 |
pard | -1.380 |
theless | -1.290 |
Ern | -1.259 |
\": | -1.223 |
Token | on |
Token ID | 319 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
esame | +2.290 |
(% | +2.177 |
atos | +2.037 |
ordan | +1.995 |
otal | +1.905 |
Neg logit contributions | |
miscar | -2.336 |
pard | -2.284 |
theless | -2.165 |
Ern | -2.127 |
\": | -2.060 |
Token | driving |
Token ID | 5059 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
miscar | +1.021 |
pard | +0.992 |
theless | +0.928 |
Ern | +0.914 |
\": | +0.885 |
Neg logit contributions | |
esame | -1.011 |
(% | -0.937 |
atos | -0.893 |
ordan | -0.880 |
otal | -0.840 |
Token | related |
Token ID | 3519 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
esame | +1.381 |
(% | +1.308 |
atos | +1.229 |
ordan | +1.206 |
otal | +1.150 |
Neg logit contributions | |
miscar | -1.381 |
pard | -1.353 |
theless | -1.285 |
Ern | -1.255 |
\": | -1.224 |
Token | skills |
Token ID | 4678 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
esame | +0.450 |
(% | +0.422 |
atos | +0.400 |
ordan | +0.392 |
otal | +0.374 |
Neg logit contributions | |
miscar | -0.460 |
pard | -0.449 |
theless | -0.424 |
Ern | -0.415 |
\": | -0.405 |
Token | . |
Token ID | 13 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
esame | +0.901 |
(% | +0.848 |
atos | +0.801 |
ordan | +0.786 |
otal | +0.750 |
Neg logit contributions | |
miscar | -0.911 |
pard | -0.891 |
theless | -0.841 |
Ern | -0.824 |
\": | -0.804 |
Token | Springfield |
Token ID | 27874 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
esame | +0.349 |
(% | +0.323 |
atos | +0.305 |
ordan | +0.302 |
otal | +0.288 |
Neg logit contributions | |
miscar | -0.385 |
pard | -0.375 |
Ern | -0.354 |
theless | -0.354 |
\": | -0.342 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
esame | +1.607 |
(% | +1.512 |
atos | +1.416 |
ordan | +1.379 |
otal | +1.322 |
Neg logit contributions | |
miscar | -1.868 |
pard | -1.830 |
theless | -1.751 |
Ern | -1.698 |
\": | -1.670 |
Token | between |
Token ID | 1022 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
esame | +0.830 |
(% | +0.780 |
atos | +0.733 |
ordan | +0.715 |
otal | +0.681 |
Neg logit contributions | |
miscar | -0.996 |
pard | -0.973 |
theless | -0.927 |
Ern | -0.906 |
\": | -0.890 |
Token | Dub |
Token ID | 10322 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
esame | +0.049 |
(% | +0.046 |
atos | +0.043 |
ordan | +0.043 |
otal | +0.040 |
Neg logit contributions | |
miscar | -0.058 |
pard | -0.057 |
theless | -0.053 |
Ern | -0.053 |
\": | -0.052 |
Token | o |
Token ID | 78 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
esame | +1.432 |
(% | +1.355 |
atos | +1.286 |
ordan | +1.261 |
otal | +1.200 |
Neg logit contributions | |
miscar | -1.261 |
pard | -1.227 |
theless | -1.152 |
Ern | -1.130 |
roe | -1.099 |
Token | ce |
Token ID | 344 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
miscar | +0.135 |
pard | +0.131 |
Ern | +0.123 |
theless | +0.121 |
roe | +0.120 |
Neg logit contributions | |
esame | -0.118 |
(% | -0.111 |
atos | -0.104 |
ordan | -0.102 |
otal | -0.096 |
Token | Avenue |
Token ID | 8878 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
esame | +0.758 |
(% | +0.710 |
atos | +0.668 |
ordan | +0.661 |
otal | +0.622 |
Neg logit contributions | |
miscar | -0.817 |
pard | -0.795 |
theless | -0.750 |
Ern | -0.740 |
\": | -0.721 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
esame | +1.258 |
(% | +1.186 |
atos | +1.123 |
ordan | +1.100 |
otal | +1.052 |
Neg logit contributions | |
miscar | -1.213 |
pard | -1.185 |
theless | -1.122 |
Ern | -1.092 |
\": | -1.067 |
Token | 16 |
Token ID | 1467 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
miscar | +0.261 |
pard | +0.255 |
theless | +0.241 |
Ern | +0.240 |
\": | +0.232 |
Neg logit contributions | |
esame | -0.226 |
(% | -0.211 |
atos | -0.199 |
ordan | -0.195 |
otal | -0.186 |
Token | th |
Token ID | 400 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
esame | +1.036 |
(% | +0.980 |
atos | +0.934 |
ordan | +0.918 |
otal | +0.881 |
Neg logit contributions | |
miscar | -0.830 |
pard | -0.809 |
theless | -0.758 |
Ern | -0.739 |
\": | -0.719 |
Token | Street |
Token ID | 3530 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
esame | +1.999 |
(% | +1.842 |
atos | +1.708 |
ordan | +1.653 |
otal | +1.543 |
Neg logit contributions | |
miscar | -3.368 |
pard | -3.314 |
theless | -3.170 |
Ern | -3.103 |
\": | -3.047 |
Token | , |
Token ID | 11 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
esame | +1.492 |
(% | +1.400 |
atos | +1.321 |
ordan | +1.290 |
otal | +1.231 |
Neg logit contributions | |
miscar | -1.658 |
pard | -1.622 |
theless | -1.540 |
Ern | -1.504 |
\": | -1.474 |
Token | travel |
Token ID | 3067 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
miscar | +0.703 |
pard | +0.685 |
Ern | +0.645 |
theless | +0.639 |
\": | +0.610 |
Neg logit contributions | |
esame | -0.704 |
(% | -0.656 |
atos | -0.626 |
ordan | -0.617 |
otal | -0.581 |
Token | in |
Token ID | 287 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
miscar | +0.185 |
pard | +0.182 |
theless | +0.170 |
Ern | +0.168 |
\": | +0.163 |
Neg logit contributions | |
esame | -0.184 |
(% | -0.172 |
atos | -0.164 |
ordan | -0.161 |
otal | -0.153 |
Token | DC |
Token ID | 6257 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
esame | +0.148 |
(% | +0.140 |
atos | +0.133 |
ordan | +0.130 |
otal | +0.124 |
Neg logit contributions | |
miscar | -0.152 |
pard | -0.149 |
theless | -0.140 |
Ern | -0.138 |
\": | -0.134 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
esame | +0.797 |
(% | +0.752 |
atos | +0.714 |
ordan | +0.702 |
otal | +0.672 |
Neg logit contributions | |
miscar | -0.695 |
pard | -0.678 |
theless | -0.638 |
Ern | -0.623 |
\": | -0.607 |
Token | 's |
Token ID | 338 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
miscar | +1.717 |
pard | +1.676 |
theless | +1.542 |
Ern | +1.541 |
\": | +1.508 |
Neg logit contributions | |
esame | -1.754 |
(% | -1.651 |
atos | -1.593 |
ordan | -1.547 |
otal | -1.465 |
Token | comic |
Token ID | 9048 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
esame | +1.872 |
(% | +1.754 |
atos | +1.652 |
ordan | +1.619 |
otal | +1.551 |
Neg logit contributions | |
miscar | -1.974 |
pard | -1.930 |
theless | -1.829 |
Ern | -1.788 |
\": | -1.753 |
Token | book |
Token ID | 1492 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
miscar | +0.569 |
pard | +0.557 |
theless | +0.522 |
Ern | +0.515 |
\": | +0.505 |
Neg logit contributions | |
esame | -0.476 |
(% | -0.445 |
atos | -0.419 |
ordan | -0.412 |
otal | -0.387 |
Token | mythology |
Token ID | 25871 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
miscar | +0.980 |
pard | +0.961 |
theless | +0.898 |
Ern | +0.891 |
\": | +0.875 |
Neg logit contributions | |
esame | -0.757 |
(% | -0.708 |
atos | -0.667 |
ordan | -0.654 |
otal | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
miscar | +0.404 |
pard | +0.395 |
theless | +0.369 |
Ern | +0.365 |
\": | +0.356 |
Neg logit contributions | |
esame | -0.394 |
(% | -0.369 |
atos | -0.351 |
ordan | -0.345 |
otal | -0.326 |
Token | Part |
Token ID | 2142 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
esame | +1.165 |
(% | +1.097 |
atos | +1.037 |
ordan | +1.018 |
otal | +0.972 |
Neg logit contributions | |
miscar | -1.143 |
pard | -1.117 |
theless | -1.054 |
Ern | -1.029 |
\": | -1.006 |
Token | of |
Token ID | 286 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
miscar | +0.583 |
pard | +0.572 |
theless | +0.540 |
Ern | +0.529 |
\": | +0.513 |
Neg logit contributions | |
esame | -0.566 |
(% | -0.534 |
atos | -0.503 |
ordan | -0.495 |
otal | -0.471 |
Token | the |
Token ID | 262 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
esame | +0.642 |
(% | +0.601 |
atos | +0.568 |
ordan | +0.557 |
otal | +0.531 |
Neg logit contributions | |
miscar | -0.686 |
pard | -0.670 |
theless | -0.634 |
Ern | -0.621 |
\": | -0.608 |
Token | In |
Token ID | 818 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
esame | +0.465 |
(% | +0.438 |
atos | +0.415 |
ordan | +0.407 |
otal | +0.389 |
Neg logit contributions | |
miscar | -0.440 |
pard | -0.430 |
theless | -0.405 |
Ern | -0.395 |
\": | -0.385 |
Token | humans |
Token ID | 5384 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
miscar | +0.102 |
pard | +0.100 |
theless | +0.094 |
Ern | +0.093 |
\": | +0.090 |
Neg logit contributions | |
esame | -0.095 |
(% | -0.089 |
atos | -0.084 |
ordan | -0.083 |
otal | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
esame | +0.032 |
(% | +0.030 |
atos | +0.029 |
ordan | +0.028 |
otal | +0.027 |
Neg logit contributions | |
miscar | -0.035 |
pard | -0.034 |
theless | -0.032 |
Ern | -0.031 |
\": | -0.031 |
Token | reptiles |
Token ID | 46617 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
miscar | +0.149 |
pard | +0.146 |
theless | +0.137 |
Ern | +0.135 |
\": | +0.131 |
Neg logit contributions | |
esame | -0.147 |
(% | -0.139 |
atos | -0.131 |
ordan | -0.128 |
otal | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
esame | +0.589 |
(% | +0.552 |
atos | +0.521 |
ordan | +0.511 |
otal | +0.486 |
Neg logit contributions | |
miscar | -0.634 |
pard | -0.620 |
theless | -0.587 |
Ern | -0.575 |
\": | -0.562 |
Token | teeth |
Token ID | 9941 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
esame | +0.124 |
(% | +0.116 |
atos | +0.110 |
ordan | +0.109 |
otal | +0.104 |
Neg logit contributions | |
miscar | -0.119 |
pard | -0.115 |
theless | -0.108 |
Ern | -0.107 |
\": | -0.103 |
Token | are |
Token ID | 389 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
miscar | +0.161 |
pard | +0.157 |
theless | +0.148 |
Ern | +0.145 |
\": | +0.141 |
Neg logit contributions | |
esame | -0.155 |
(% | -0.145 |
atos | -0.137 |
ordan | -0.135 |
otal | -0.129 |
Token | formed |
Token ID | 7042 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
esame | +1.422 |
(% | +1.334 |
atos | +1.262 |
ordan | +1.238 |
otal | +1.180 |
Neg logit contributions | |
miscar | -1.468 |
pard | -1.435 |
theless | -1.356 |
Ern | -1.328 |
\": | -1.297 |
Token | from |
Token ID | 422 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
esame | +0.235 |
(% | +0.220 |
atos | +0.208 |
ordan | +0.204 |
otal | +0.195 |
Neg logit contributions | |
miscar | -0.252 |
pard | -0.247 |
theless | -0.233 |
Ern | -0.228 |
\": | -0.223 |
Token | dent |
Token ID | 18794 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
esame | +0.936 |
(% | +0.878 |
atos | +0.831 |
ordan | +0.815 |
otal | +0.779 |
Neg logit contributions | |
miscar | -0.957 |
pard | -0.935 |
theless | -0.880 |
Ern | -0.865 |
\": | -0.842 |
Token | in |
Token ID | 259 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
esame | +1.246 |
(% | +1.153 |
atos | +1.079 |
ordan | +1.052 |
otal | +0.993 |
Neg logit contributions | |
miscar | -1.786 |
pard | -1.750 |
theless | -1.668 |
Ern | -1.641 |
\": | -1.605 |
Token | if |
Token ID | 611 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
esame | +0.167 |
(% | +0.154 |
atos | +0.146 |
ordan | +0.143 |
otal | +0.136 |
Neg logit contributions | |
miscar | -0.203 |
pard | -0.200 |
theless | -0.187 |
Ern | -0.186 |
\": | -0.181 |
Token | the |
Token ID | 262 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
esame | +0.455 |
(% | +0.425 |
atos | +0.402 |
ordan | +0.393 |
otal | +0.374 |
Neg logit contributions | |
miscar | -0.505 |
pard | -0.496 |
theless | -0.466 |
Ern | -0.458 |
\": | -0.447 |
Token | election |
Token ID | 3071 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
esame | +0.702 |
(% | +0.655 |
atos | +0.618 |
ordan | +0.606 |
otal | +0.578 |
Neg logit contributions | |
miscar | -0.784 |
pard | -0.771 |
theless | -0.722 |
Ern | -0.710 |
\": | -0.693 |
Token | were |
Token ID | 547 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
esame | +1.115 |
(% | +1.049 |
atos | +1.000 |
ordan | +0.983 |
otal | +0.943 |
Neg logit contributions | |
miscar | -0.933 |
pard | -0.909 |
theless | -0.849 |
Ern | -0.831 |
\": | -0.809 |
Token | held |
Token ID | 2714 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
esame | +0.497 |
(% | +0.457 |
atos | +0.438 |
ordan | +0.428 |
otal | +0.412 |
Neg logit contributions | |
miscar | -0.511 |
pard | -0.503 |
theless | -0.468 |
Ern | -0.465 |
\": | -0.448 |
Token | today |
Token ID | 1909 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
miscar | +0.228 |
pard | +0.226 |
theless | +0.206 |
Ern | +0.205 |
\": | +0.196 |
Neg logit contributions | |
esame | -0.311 |
(% | -0.290 |
atos | -0.281 |
ordan | -0.273 |
otal | -0.266 |
Token | , |
Token ID | 11 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
esame | +0.266 |
(% | +0.247 |
atos | +0.235 |
ordan | +0.230 |
otal | +0.220 |
Neg logit contributions | |
miscar | -0.282 |
pard | -0.278 |
theless | -0.260 |
Ern | -0.256 |
\": | -0.249 |
Token | they |
Token ID | 484 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
esame | +0.363 |
(% | +0.337 |
atos | +0.318 |
ordan | +0.311 |
otal | +0.294 |
Neg logit contributions | |
miscar | -0.457 |
pard | -0.450 |
theless | -0.423 |
Ern | -0.418 |
\": | -0.408 |
Token | would |
Token ID | 561 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
esame | +0.533 |
(% | +0.501 |
atos | +0.473 |
ordan | +0.464 |
otal | +0.442 |
Neg logit contributions | |
miscar | -0.557 |
pard | -0.544 |
theless | -0.515 |
Ern | -0.504 |
\": | -0.492 |
Token | vote |
Token ID | 3015 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
miscar | +0.645 |
pard | +0.637 |
theless | +0.590 |
Ern | +0.580 |
\": | +0.566 |
Neg logit contributions | |
esame | -0.611 |
(% | -0.564 |
atos | -0.538 |
ordan | -0.531 |
otal | -0.503 |
Token | for |
Token ID | 329 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
miscar | +1.793 |
pard | +1.777 |
Ern | +1.651 |
theless | +1.638 |
\": | +1.594 |
Neg logit contributions | |
esame | -1.514 |
(% | -1.384 |
atos | -1.311 |
ordan | -1.303 |
otal | -1.235 |
Token | particularly |
Token ID | 3573 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
miscar | +0.960 |
pard | +0.947 |
theless | +0.886 |
Ern | +0.866 |
\": | +0.837 |
Neg logit contributions | |
esame | -1.032 |
(% | -0.970 |
atos | -0.930 |
ordan | -0.914 |
otal | -0.869 |
Token | strong |
Token ID | 1913 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
miscar | +0.717 |
pard | +0.711 |
theless | +0.659 |
Ern | +0.649 |
\": | +0.637 |
Neg logit contributions | |
esame | -0.711 |
(% | -0.661 |
atos | -0.635 |
ordan | -0.623 |
otal | -0.595 |
Token | , |
Token ID | 11 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
miscar | +1.225 |
pard | +1.203 |
theless | +1.122 |
Ern | +1.105 |
\": | +1.078 |
Neg logit contributions | |
esame | -1.280 |
(% | -1.189 |
atos | -1.134 |
ordan | -1.122 |
otal | -1.060 |
Token | even |
Token ID | 772 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
miscar | +0.231 |
pard | +0.225 |
theless | +0.211 |
Ern | +0.207 |
\": | +0.200 |
Neg logit contributions | |
esame | -0.252 |
(% | -0.237 |
atos | -0.226 |
ordan | -0.222 |
otal | -0.211 |
Token | for |
Token ID | 329 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
esame | +0.172 |
(% | +0.161 |
atos | +0.153 |
ordan | +0.150 |
otal | +0.143 |
Neg logit contributions | |
miscar | -0.180 |
pard | -0.176 |
theless | -0.165 |
Ern | -0.162 |
\": | -0.157 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
miscar | +0.506 |
pard | +0.496 |
theless | +0.465 |
Ern | +0.460 |
\": | +0.447 |
Neg logit contributions | |
esame | -0.478 |
(% | -0.447 |
atos | -0.425 |
ordan | -0.417 |
otal | -0.395 |
Token | time |
Token ID | 640 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
miscar | +1.322 |
pard | +1.302 |
theless | +1.219 |
Ern | +1.210 |
\": | +1.171 |
Neg logit contributions | |
esame | -1.212 |
(% | -1.131 |
atos | -1.074 |
ordan | -1.055 |
otal | -1.002 |
Token | they |
Token ID | 484 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
miscar | +0.241 |
pard | +0.236 |
theless | +0.223 |
Ern | +0.219 |
\": | +0.213 |
Neg logit contributions | |
esame | -0.223 |
(% | -0.209 |
atos | -0.198 |
ordan | -0.194 |
otal | -0.185 |
Token | were |
Token ID | 547 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
miscar | +0.094 |
pard | +0.092 |
theless | +0.086 |
Ern | +0.084 |
\": | +0.082 |
Neg logit contributions | |
esame | -0.116 |
(% | -0.109 |
atos | -0.104 |
ordan | -0.102 |
otal | -0.098 |
Token | released |
Token ID | 2716 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
miscar | +0.453 |
pard | +0.443 |
theless | +0.413 |
Ern | +0.406 |
\": | +0.391 |
Neg logit contributions | |
esame | -0.508 |
(% | -0.476 |
atos | -0.455 |
ordan | -0.447 |
otal | -0.428 |
Token | , |
Token ID | 11 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
miscar | +0.692 |
pard | +0.680 |
theless | +0.636 |
Ern | +0.625 |
\": | +0.606 |
Neg logit contributions | |
esame | -0.681 |
(% | -0.632 |
atos | -0.608 |
ordan | -0.592 |
otal | -0.564 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
miscar | +1.174 |
pard | +1.147 |
theless | +1.074 |
Ern | +1.066 |
\": | +1.040 |
Neg logit contributions | |
esame | -1.340 |
(% | -1.250 |
atos | -1.197 |
ordan | -1.177 |
otal | -1.125 |
Token | us |
Token ID | 514 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
miscar | +1.795 |
pard | +1.746 |
theless | +1.618 |
Ern | +1.596 |
\": | +1.544 |
Neg logit contributions | |
esame | -2.671 |
(% | -2.530 |
atos | -2.409 |
ordan | -2.387 |
otal | -2.281 |
Token | know |
Token ID | 760 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
miscar | +0.733 |
pard | +0.718 |
theless | +0.672 |
Ern | +0.662 |
\": | +0.642 |
Neg logit contributions | |
esame | -0.783 |
(% | -0.736 |
atos | -0.698 |
ordan | -0.691 |
otal | -0.656 |
Token | in |
Token ID | 287 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
miscar | +1.488 |
pard | +1.450 |
theless | +1.351 |
Ern | +1.332 |
\": | +1.294 |
Neg logit contributions | |
esame | -1.860 |
(% | -1.736 |
atos | -1.654 |
ordan | -1.646 |
otal | -1.571 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
miscar | +1.529 |
pard | +1.498 |
theless | +1.406 |
Ern | +1.383 |
\": | +1.353 |
Neg logit contributions | |
esame | -1.531 |
(% | -1.435 |
atos | -1.357 |
ordan | -1.335 |
otal | -1.271 |
Token | comments |
Token ID | 3651 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
miscar | +1.485 |
pard | +1.452 |
theless | +1.356 |
Ern | +1.333 |
\": | +1.298 |
Neg logit contributions | |
esame | -1.772 |
(% | -1.671 |
atos | -1.588 |
ordan | -1.570 |
otal | -1.495 |
Token | below |
Token ID | 2174 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
miscar | +3.301 |
pard | +3.175 |
theless | +2.896 |
\": | +2.872 |
Ern | +2.858 |
Neg logit contributions | |
esame | -5.088 |
(% | -4.709 |
ordan | -4.582 |
atos | -4.542 |
otal | -4.349 |
Token | …. |
Token ID | 11580 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
miscar | +1.521 |
pard | +1.485 |
theless | +1.391 |
Ern | +1.363 |
\": | +1.334 |
Neg logit contributions | |
esame | -1.694 |
(% | -1.584 |
atos | -1.511 |
ordan | -1.488 |
otal | -1.422 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
miscar | +0.529 |
pard | +0.516 |
theless | +0.485 |
Ern | +0.474 |
\": | +0.461 |
Neg logit contributions | |
esame | -0.623 |
(% | -0.588 |
atos | -0.559 |
ordan | -0.549 |
otal | -0.526 |
Token | D |
Token ID | 35 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
esame | +0.178 |
(% | +0.168 |
atos | +0.160 |
ordan | +0.157 |
otal | +0.150 |
Neg logit contributions | |
miscar | -0.159 |
pard | -0.156 |
theless | -0.146 |
Ern | -0.143 |
\": | -0.140 |
Token | ish |
Token ID | 680 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
esame | +1.063 |
(% | +0.993 |
atos | +0.940 |
ordan | +0.922 |
otal | +0.879 |
Neg logit contributions | |
miscar | -1.142 |
pard | -1.117 |
theless | -1.059 |
Ern | -1.035 |
\": | -1.011 |
Token | more |
Token ID | 517 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
miscar | +3.128 |
pard | +3.060 |
theless | +2.815 |
Ern | +2.804 |
\": | +2.706 |
Neg logit contributions | |
esame | -3.319 |
(% | -3.025 |
atos | -2.930 |
ordan | -2.907 |
ateral | -2.748 |
Token | slowly |
Token ID | 6364 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
miscar | +0.855 |
pard | +0.835 |
theless | +0.786 |
Ern | +0.772 |
\": | +0.753 |
Neg logit contributions | |
esame | -0.844 |
(% | -0.786 |
atos | -0.747 |
ordan | -0.735 |
otal | -0.700 |
Token | than |
Token ID | 621 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
miscar | +1.730 |
pard | +1.690 |
theless | +1.590 |
Ern | +1.558 |
\": | +1.529 |
Neg logit contributions | |
esame | -1.715 |
(% | -1.557 |
atos | -1.508 |
ordan | -1.490 |
otal | -1.403 |
Token | boost |
Token ID | 5750 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
miscar | +0.448 |
pard | +0.441 |
theless | +0.421 |
Ern | +0.415 |
\": | +0.409 |
Neg logit contributions | |
esame | -0.221 |
(% | -0.198 |
atos | -0.183 |
ordan | -0.180 |
otal | -0.164 |
Token | serial |
Token ID | 11389 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
miscar | +1.904 |
pard | +1.858 |
theless | +1.744 |
Ern | +1.706 |
\": | +1.668 |
Neg logit contributions | |
esame | -1.922 |
(% | -1.777 |
atos | -1.706 |
ordan | -1.682 |
otal | -1.583 |
Token | ization |
Token ID | 1634 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
miscar | +3.215 |
pard | +3.165 |
theless | +2.958 |
\": | +2.903 |
Ern | +2.890 |
Neg logit contributions | |
esame | -2.704 |
(% | -2.469 |
atos | -2.389 |
ordan | -2.308 |
otal | -2.183 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
miscar | +3.559 |
pard | +3.430 |
theless | +3.241 |
Ern | +3.150 |
\": | +3.084 |
Neg logit contributions | |
esame | -3.794 |
(% | -3.402 |
atos | -3.346 |
ordan | -3.309 |
ateral | -3.129 |
Token | That |
Token ID | 1320 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
miscar | +1.086 |
pard | +1.055 |
theless | +0.993 |
Ern | +0.977 |
\": | +0.947 |
Neg logit contributions | |
esame | -1.279 |
(% | -1.190 |
atos | -1.147 |
ordan | -1.130 |
otal | -1.078 |
Token | � |
Token ID | 447 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
miscar | +0.247 |
pard | +0.241 |
theless | +0.228 |
Ern | +0.223 |
\": | +0.218 |
Neg logit contributions | |
esame | -0.234 |
(% | -0.218 |
atos | -0.207 |
ordan | -0.203 |
otal | -0.193 |
Token | � |
Token ID | 247 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
esame | +0.758 |
(% | +0.706 |
atos | +0.663 |
ordan | +0.649 |
otal | +0.614 |
Neg logit contributions | |
miscar | -0.976 |
pard | -0.957 |
theless | -0.911 |
Ern | -0.893 |
\": | -0.873 |
Token | s |
Token ID | 82 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
esame | +0.277 |
(% | +0.258 |
atos | +0.242 |
ordan | +0.237 |
otal | +0.224 |
Neg logit contributions | |
miscar | -0.354 |
pard | -0.347 |
theless | -0.330 |
Ern | -0.324 |
\": | -0.317 |
Token | Cav |
Token ID | 19931 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
miscar | +1.978 |
pard | +1.936 |
Ern | +1.814 |
theless | +1.803 |
\": | +1.748 |
Neg logit contributions | |
esame | -2.053 |
(% | -1.915 |
atos | -1.803 |
ordan | -1.771 |
otal | -1.709 |
Token | all |
Token ID | 439 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
esame | +0.276 |
(% | +0.259 |
atos | +0.244 |
ordan | +0.239 |
otal | +0.228 |
Neg logit contributions | |
miscar | -0.296 |
pard | -0.290 |
theless | -0.274 |
Ern | -0.269 |
\": | -0.263 |
Token | ari |
Token ID | 2743 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
miscar | +0.855 |
pard | +0.838 |
theless | +0.780 |
Ern | +0.772 |
roe | +0.756 |
Neg logit contributions | |
esame | -0.850 |
(% | -0.802 |
atos | -0.739 |
ordan | -0.736 |
otal | -0.706 |
Token | (@ |
Token ID | 4275 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
esame | +0.813 |
(% | +0.778 |
atos | +0.746 |
ordan | +0.735 |
otal | +0.709 |
Neg logit contributions | |
miscar | -0.438 |
pard | -0.423 |
theless | -0.391 |
Ern | -0.376 |
\": | -0.364 |
Token | k |
Token ID | 74 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
miscar | +1.785 |
pard | +1.747 |
theless | +1.656 |
Ern | +1.619 |
roe | +1.592 |
Neg logit contributions | |
esame | -1.848 |
(% | -1.737 |
atos | -1.623 |
ordan | -1.591 |
otal | -1.525 |
Token | rist |
Token ID | 1585 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
miscar | +3.523 |
pard | +3.439 |
theless | +3.324 |
roe | +3.245 |
Ern | +3.227 |
Neg logit contributions | |
esame | -3.734 |
(% | -3.530 |
atos | -3.217 |
ordan | -3.130 |
-+-+ | -3.127 |
Token | inc |
Token ID | 1939 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
miscar | +4.911 |
pard | +4.808 |
theless | +4.588 |
Ern | +4.530 |
roe | +4.529 |
Neg logit contributions | |
esame | -3.333 |
(% | -3.092 |
ordan | -2.702 |
atos | -2.698 |
Matrix | -2.622 |
Token | av |
Token ID | 615 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
miscar | +1.532 |
pard | +1.497 |
theless | +1.407 |
Ern | +1.355 |
\": | +1.354 |
Neg logit contributions | |
esame | -1.917 |
(% | -1.839 |
atos | -1.689 |
ordan | -1.667 |
Matrix | -1.608 |
Token | all |
Token ID | 439 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
miscar | +3.467 |
pard | +3.397 |
theless | +3.195 |
Ern | +3.135 |
roe | +3.110 |
Neg logit contributions | |
esame | -3.425 |
(% | -3.248 |
atos | -2.938 |
ordan | -2.916 |
Matrix | -2.783 |
Token | ari |
Token ID | 2743 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
miscar | +0.634 |
pard | +0.621 |
theless | +0.579 |
Ern | +0.568 |
\": | +0.556 |
Neg logit contributions | |
esame | -0.735 |
(% | -0.696 |
atos | -0.650 |
ordan | -0.642 |
otal | -0.616 |
Token | ) |
Token ID | 8 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
esame | +0.286 |
(% | +0.268 |
atos | +0.254 |
ordan | +0.250 |
otal | +0.238 |
Neg logit contributions | |
miscar | -0.285 |
pard | -0.278 |
theless | -0.263 |
Ern | -0.257 |
\": | -0.251 |
Token | Space |
Token ID | 14106 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
esame | +1.672 |
(% | +1.579 |
atos | +1.486 |
ordan | +1.448 |
otal | +1.392 |
Neg logit contributions | |
miscar | -1.693 |
pard | -1.649 |
theless | -1.567 |
Ern | -1.533 |
roe | -1.469 |
Token | > |
Token ID | 29 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
miscar | +0.813 |
pard | +0.790 |
theless | +0.688 |
\": | +0.687 |
Ern | +0.672 |
Neg logit contributions | |
esame | -1.770 |
(% | -1.664 |
atos | -1.639 |
ordan | -1.607 |
otal | -1.567 |
Token | or |
Token ID | 393 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
miscar | +1.835 |
pard | +1.816 |
theless | +1.671 |
Ern | +1.645 |
\": | +1.630 |
Neg logit contributions | |
esame | -2.054 |
(% | -1.914 |
atos | -1.842 |
ordan | -1.810 |
otal | -1.728 |
Token | < |
Token ID | 1279 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
miscar | +1.386 |
pard | +1.369 |
Ern | +1.263 |
theless | +1.251 |
\": | +1.245 |
Neg logit contributions | |
esame | -1.092 |
(% | -0.970 |
atos | -0.955 |
ordan | -0.946 |
otal | -0.886 |
Token | Tab |
Token ID | 33349 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
esame | +0.663 |
(% | +0.620 |
atos | +0.588 |
ordan | +0.580 |
otal | +0.552 |
Neg logit contributions | |
miscar | -0.678 |
pard | -0.663 |
theless | -0.623 |
Ern | -0.612 |
\": | -0.606 |
Token | >) |
Token ID | 43734 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
miscar | +2.277 |
pard | +2.243 |
theless | +2.105 |
\": | +2.056 |
Ern | +2.039 |
Neg logit contributions | |
esame | -2.346 |
(% | -2.176 |
atos | -2.099 |
ordan | -2.067 |
otal | -1.980 |
Token | { |
Token ID | 1391 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
pard | +3.479 |
miscar | +3.446 |
theless | +3.211 |
Ern | +3.089 |
\": | +3.064 |
Neg logit contributions | |
esame | -4.025 |
(% | -3.659 |
atos | -3.583 |
ordan | -3.565 |
otal | -3.391 |
Token | vi |
Token ID | 8903 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
miscar | +1.156 |
pard | +1.137 |
theless | +1.079 |
Ern | +1.048 |
\": | +1.032 |
Neg logit contributions | |
esame | -1.109 |
(% | -1.036 |
atos | -0.978 |
ordan | -0.963 |
otal | -0.913 |
Token | : |
Token ID | 25 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
esame | +0.066 |
(% | +0.062 |
atos | +0.060 |
ordan | +0.059 |
otal | +0.057 |
Neg logit contributions | |
miscar | -0.049 |
pard | -0.048 |
theless | -0.044 |
Ern | -0.043 |
\": | -0.043 |
Token | | |
Token ID | 91 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
miscar | +0.913 |
pard | +0.899 |
theless | +0.818 |
Ern | +0.799 |
\": | +0.798 |
Neg logit contributions | |
esame | -1.363 |
(% | -1.288 |
atos | -1.229 |
ordan | -1.217 |
otal | -1.169 |
Token | vim |
Token ID | 31124 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
miscar | +0.825 |
pard | +0.815 |
theless | +0.761 |
\": | +0.738 |
Ern | +0.737 |
Neg logit contributions | |
esame | -0.772 |
(% | -0.723 |
atos | -0.683 |
ordan | -0.667 |
otal | -0.634 |
Token | Today |
Token ID | 6288 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
esame | +1.930 |
(% | +1.824 |
atos | +1.722 |
ordan | +1.682 |
otal | +1.610 |
Neg logit contributions | |
miscar | -1.957 |
pard | -1.910 |
theless | -1.812 |
Ern | -1.763 |
\": | -1.722 |
Token | : |
Token ID | 25 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
esame | +0.408 |
(% | +0.383 |
atos | +0.362 |
ordan | +0.356 |
otal | +0.339 |
Neg logit contributions | |
miscar | -0.412 |
pard | -0.403 |
theless | -0.380 |
Ern | -0.373 |
\": | -0.363 |
Token | Sylvia |
Token ID | 45425 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
esame | +0.934 |
(% | +0.880 |
atos | +0.833 |
ordan | +0.816 |
otal | +0.780 |
Neg logit contributions | |
miscar | -0.916 |
pard | -0.895 |
theless | -0.845 |
Ern | -0.825 |
\": | -0.807 |
Token | 's |
Token ID | 338 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
esame | +0.563 |
(% | +0.529 |
atos | +0.501 |
ordan | +0.491 |
otal | +0.468 |
Neg logit contributions | |
miscar | -0.572 |
pard | -0.559 |
theless | -0.528 |
Ern | -0.517 |
\": | -0.505 |
Token | En |
Token ID | 2039 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
esame | +0.686 |
(% | +0.644 |
atos | +0.609 |
ordan | +0.597 |
otal | +0.570 |
Neg logit contributions | |
miscar | -0.709 |
pard | -0.693 |
theless | -0.655 |
Ern | -0.641 |
\": | -0.626 |
Token | ch |
Token ID | 354 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
miscar | +1.195 |
pard | +1.173 |
Ern | +1.089 |
roe | +1.072 |
theless | +1.070 |
Neg logit contributions | |
esame | -1.221 |
(% | -1.149 |
atos | -1.082 |
ordan | -1.074 |
otal | -1.009 |
Token | il |
Token ID | 346 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
miscar | +2.886 |
pard | +2.853 |
Ern | +2.539 |
theless | +2.535 |
\": | +2.526 |
Neg logit contributions | |
esame | -4.133 |
(% | -4.002 |
atos | -3.762 |
ordan | -3.693 |
otal | -3.529 |
Token | ada |
Token ID | 4763 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
miscar | +1.358 |
pard | +1.335 |
theless | +1.237 |
Ern | +1.233 |
roe | +1.208 |
Neg logit contributions | |
esame | -1.149 |
(% | -1.076 |
ordan | -0.989 |
atos | -0.988 |
otal | -0.937 |
Token | Kitchen |
Token ID | 22541 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
esame | +0.309 |
(% | +0.290 |
atos | +0.275 |
ordan | +0.270 |
otal | +0.258 |
Neg logit contributions | |
miscar | -0.308 |
pard | -0.301 |
theless | -0.284 |
Ern | -0.279 |
\": | -0.272 |
Token | Previously |
Token ID | 29875 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
miscar | +0.903 |
pard | +0.882 |
theless | +0.828 |
Ern | +0.817 |
\": | +0.792 |
Neg logit contributions | |
esame | -0.947 |
(% | -0.883 |
atos | -0.839 |
ordan | -0.830 |
otal | -0.792 |
Token | : |
Token ID | 25 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
esame | +0.622 |
(% | +0.586 |
atos | +0.556 |
ordan | +0.545 |
otal | +0.521 |
Neg logit contributions | |
miscar | -0.583 |
pard | -0.569 |
theless | -0.537 |
Ern | -0.525 |
\": | -0.512 |