Token | ulse |
Token ID | 9615 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
anon | +1.570 |
Article | +1.525 |
ovarian | +1.489 |
favors | +1.484 |
Frag | +1.449 |
Neg logit contributions | |
acements | -1.171 |
dinand | -1.115 |
ortment | -1.031 |
gered | -0.965 |
OPLE | -0.946 |
Token | Per |
Token ID | 5990 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
acements | +1.912 |
dinand | +1.817 |
ortment | +1.723 |
gered | +1.639 |
OPLE | +1.617 |
Neg logit contributions | |
anon | -1.611 |
ovarian | -1.527 |
Article | -1.523 |
favors | -1.513 |
Moroccan | -1.446 |
Token | iod |
Token ID | 2101 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
anon | +0.292 |
Article | +0.282 |
favors | +0.280 |
ovarian | +0.278 |
Moroccan | +0.269 |
Neg logit contributions | |
acements | -0.242 |
dinand | -0.228 |
ortment | -0.214 |
gered | -0.203 |
OPLE | -0.194 |
Token | (" |
Token ID | 5855 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
acements | +2.246 |
dinand | +2.132 |
ortment | +2.024 |
gered | +1.936 |
OPLE | +1.901 |
Neg logit contributions | |
anon | -1.951 |
Article | -1.869 |
ovarian | -1.832 |
favors | -1.811 |
Moroccan | -1.749 |
Token | P |
Token ID | 47 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
acements | +4.342 |
dinand | +4.111 |
ortment | +3.898 |
gered | +3.750 |
OPLE | +3.714 |
Neg logit contributions | |
anon | -3.190 |
favors | -3.079 |
ovarian | -3.030 |
Article | -3.015 |
Moroccan | -2.916 |
Token | ulse |
Token ID | 9615 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
acements | +2.419 |
dinand | +2.199 |
ortment | +2.105 |
gered | +1.912 |
OPLE | +1.803 |
Neg logit contributions | |
anon | -4.039 |
favors | -3.946 |
Article | -3.940 |
ovarian | -3.893 |
Moroccan | -3.823 |
Token | period |
Token ID | 2278 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
acements | +8.553 |
dinand | +8.102 |
ortment | +7.767 |
gered | +7.308 |
OPLE | +7.094 |
Neg logit contributions | |
anon | -8.425 |
Article | -8.209 |
favors | -7.876 |
Frag | -7.876 |
ovarian | -7.812 |
Token | ", |
Token ID | 1600 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
acements | +0.165 |
dinand | +0.158 |
ortment | +0.148 |
gered | +0.140 |
OPLE | +0.138 |
Neg logit contributions | |
anon | -0.158 |
Article | -0.153 |
ovarian | -0.149 |
favors | -0.149 |
Frag | -0.144 |
Token | Float |
Token ID | 48436 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
anon | +2.978 |
Article | +2.873 |
ovarian | +2.794 |
favors | +2.792 |
Frag | +2.718 |
Neg logit contributions | |
acements | -4.115 |
dinand | -4.007 |
ortment | -3.733 |
gered | -3.588 |
OPLE | -3.516 |
Token | ) |
Token ID | 8 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
acements | +0.160 |
dinand | +0.154 |
ortment | +0.145 |
gered | +0.139 |
OPLE | +0.137 |
Neg logit contributions | |
anon | -0.116 |
Article | -0.110 |
ovarian | -0.108 |
favors | -0.107 |
Myst | -0.102 |
Token | = |
Token ID | 796 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
acements | +0.142 |
dinand | +0.137 |
ortment | +0.131 |
gered | +0.125 |
OPLE | +0.123 |
Neg logit contributions | |
anon | -0.087 |
Article | -0.083 |
favors | -0.080 |
ovarian | -0.080 |
Frag | -0.077 |
Token | RI |
Token ID | 7112 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
acements | +0.479 |
dinand | +0.463 |
ortment | +0.439 |
gered | +0.421 |
OPLE | +0.417 |
Neg logit contributions | |
anon | -0.304 |
Article | -0.291 |
ovarian | -0.282 |
favors | -0.281 |
Frag | -0.269 |
Token | ER |
Token ID | 1137 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
acements | +2.602 |
dinand | +2.508 |
ortment | +2.365 |
OPLE | +2.280 |
gered | +2.277 |
Neg logit contributions | |
anon | -2.074 |
Article | -1.967 |
ovarian | -1.943 |
favors | -1.920 |
Frag | -1.848 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
acements | +0.498 |
dinand | +0.478 |
ortment | +0.450 |
gered | +0.429 |
OPLE | +0.423 |
Neg logit contributions | |
anon | -0.425 |
Article | -0.409 |
ovarian | -0.398 |
favors | -0.396 |
Frag | -0.383 |
Token |
|
Token ID | 198 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
acements | +2.085 |
dinand | +1.850 |
ortment | +1.831 |
gered | +1.765 |
esm | +1.661 |
Neg logit contributions | |
anon | -2.431 |
ovarian | -2.376 |
Article | -2.367 |
favors | -2.325 |
enthusi | -2.291 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
acements | +1.594 |
dinand | +1.505 |
ortment | +1.432 |
gered | +1.368 |
OPLE | +1.345 |
Neg logit contributions | |
anon | -1.343 |
ovarian | -1.294 |
favors | -1.289 |
Article | -1.287 |
Myst | -1.228 |
Token | a |
Token ID | 64 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
anon | +0.056 |
Article | +0.054 |
ovarian | +0.052 |
favors | +0.051 |
Frag | +0.049 |
Neg logit contributions | |
acements | -0.088 |
dinand | -0.085 |
ortment | -0.081 |
gered | -0.077 |
OPLE | -0.076 |
Token | 11 |
Token ID | 1367 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
acements | +6.470 |
dinand | +6.265 |
ortment | +5.782 |
gered | +5.216 |
OPLE | +5.049 |
Neg logit contributions | |
anon | -9.377 |
ovarian | -9.240 |
Article | -9.234 |
favors | -9.208 |
Frag | -9.041 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
acements | +2.553 |
dinand | +2.337 |
ortment | +2.293 |
gered | +2.215 |
esm | +2.121 |
Neg logit contributions | |
anon | -1.975 |
ovarian | -1.907 |
Article | -1.889 |
favors | -1.875 |
Moroccan | -1.789 |
Token | Weapon |
Token ID | 13072 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
anon | +1.356 |
Article | +1.305 |
ovarian | +1.267 |
favors | +1.262 |
Frag | +1.217 |
Neg logit contributions | |
acements | -1.777 |
dinand | -1.709 |
ortment | -1.616 |
gered | -1.540 |
OPLE | -1.516 |
Token | person |
Token ID | 1048 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
acements | +1.325 |
dinand | +1.269 |
ortment | +1.200 |
gered | +1.141 |
OPLE | +1.114 |
Neg logit contributions | |
anon | -1.188 |
Article | -1.145 |
ovarian | -1.115 |
favors | -1.103 |
Frag | -1.075 |
Token | loaded |
Token ID | 9639 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
acements | +0.579 |
dinand | +0.555 |
ortment | +0.527 |
gered | +0.505 |
OPLE | +0.492 |
Neg logit contributions | |
anon | -0.456 |
Article | -0.438 |
ovarian | -0.425 |
favors | -0.420 |
Frag | -0.409 |
Token | ulse |
Token ID | 9615 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
anon | +1.316 |
Article | +1.279 |
ovarian | +1.251 |
favors | +1.247 |
Frag | +1.215 |
Neg logit contributions | |
acements | -0.969 |
dinand | -0.919 |
ortment | -0.851 |
gered | -0.796 |
OPLE | -0.779 |
Token | Amount |
Token ID | 31264 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
acements | +1.076 |
dinand | +1.028 |
ortment | +0.970 |
gered | +0.921 |
OPLE | +0.905 |
Neg logit contributions | |
anon | -0.977 |
Article | -0.936 |
ovarian | -0.921 |
favors | -0.916 |
Frag | -0.877 |
Token | ( |
Token ID | 357 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
acements | +0.105 |
dinand | +0.101 |
ortment | +0.096 |
gered | +0.091 |
OPLE | +0.090 |
Neg logit contributions | |
anon | -0.074 |
Article | -0.071 |
ovarian | -0.069 |
favors | -0.069 |
Frag | -0.066 |
Token | " |
Token ID | 366 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
anon | +0.185 |
Article | +0.179 |
ovarian | +0.174 |
favors | +0.174 |
Frag | +0.168 |
Neg logit contributions | |
acements | -0.225 |
dinand | -0.217 |
ortment | -0.205 |
gered | -0.195 |
OPLE | -0.191 |
Token | P |
Token ID | 47 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
acements | +1.678 |
dinand | +1.582 |
ortment | +1.526 |
gered | +1.462 |
OPLE | +1.436 |
Neg logit contributions | |
anon | -1.200 |
favors | -1.144 |
ovarian | -1.138 |
Article | -1.123 |
Moroccan | -1.082 |
Token | ulse |
Token ID | 9615 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
acements | +2.255 |
dinand | +2.058 |
ortment | +1.948 |
gered | +1.816 |
esm | +1.684 |
Neg logit contributions | |
anon | -3.811 |
Article | -3.739 |
favors | -3.700 |
ovarian | -3.660 |
Moroccan | -3.586 |
Token | amount |
Token ID | 2033 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
acements | +4.960 |
ortment | +4.512 |
gered | +4.010 |
dinand | +4.006 |
ption | +3.657 |
Neg logit contributions | |
anon | -9.948 |
Article | -9.567 |
Chero | -9.484 |
enthusi | -9.478 |
Frag | -9.415 |
Token | " |
Token ID | 1 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
anon | +0.502 |
Article | +0.487 |
ovarian | +0.475 |
favors | +0.474 |
Frag | +0.457 |
Neg logit contributions | |
acements | -0.486 |
dinand | -0.459 |
ortment | -0.436 |
gered | -0.412 |
OPLE | -0.401 |
Token | , |
Token ID | 837 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
anon | +2.027 |
Article | +1.925 |
ovarian | +1.845 |
favors | +1.830 |
Frag | +1.735 |
Neg logit contributions | |
acements | -5.459 |
dinand | -5.332 |
ortment | -5.069 |
gered | -4.892 |
OPLE | -4.859 |
Token | Range |
Token ID | 13667 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
anon | +0.523 |
Article | +0.503 |
ovarian | +0.489 |
favors | +0.486 |
Frag | +0.468 |
Neg logit contributions | |
acements | -0.605 |
dinand | -0.578 |
ortment | -0.548 |
gered | -0.520 |
OPLE | -0.511 |
Token | ( |
Token ID | 357 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
anon | +1.559 |
Article | +1.499 |
ovarian | +1.456 |
favors | +1.451 |
Frag | +1.397 |
Neg logit contributions | |
acements | -2.084 |
dinand | -2.003 |
ortment | -1.897 |
gered | -1.809 |
OPLE | -1.780 |
Token | that |
Token ID | 326 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
acements | +0.213 |
dinand | +0.204 |
ortment | +0.194 |
gered | +0.185 |
OPLE | +0.181 |
Neg logit contributions | |
anon | -0.163 |
Article | -0.157 |
ovarian | -0.152 |
favors | -0.150 |
Frag | -0.146 |
Token | certain |
Token ID | 1728 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
acements | +0.476 |
dinand | +0.455 |
ortment | +0.431 |
gered | +0.411 |
OPLE | +0.403 |
Neg logit contributions | |
anon | -0.400 |
Article | -0.384 |
ovarian | -0.373 |
favors | -0.367 |
Frag | -0.359 |
Token | moments |
Token ID | 7188 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
acements | +1.828 |
dinand | +1.727 |
ortment | +1.638 |
gered | +1.558 |
OPLE | +1.513 |
Neg logit contributions | |
anon | -1.850 |
Article | -1.764 |
ovarian | -1.718 |
favors | -1.678 |
Frag | -1.668 |
Token | worked |
Token ID | 3111 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
acements | +2.030 |
dinand | +1.925 |
ortment | +1.858 |
gered | +1.765 |
OPLE | +1.711 |
Neg logit contributions | |
anon | -1.612 |
Article | -1.547 |
ovarian | -1.502 |
favors | -1.472 |
Frag | -1.459 |
Token | and |
Token ID | 290 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
anon | +0.112 |
Article | +0.107 |
ovarian | +0.104 |
favors | +0.104 |
Frag | +0.100 |
Neg logit contributions | |
acements | -0.143 |
dinand | -0.138 |
ortment | -0.130 |
gered | -0.124 |
OPLE | -0.122 |
Token | others |
Token ID | 1854 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
acements | +2.330 |
dinand | +2.199 |
ortment | +2.094 |
gered | +2.005 |
OPLE | +1.945 |
Neg logit contributions | |
anon | -2.037 |
Article | -1.958 |
ovarian | -1.902 |
favors | -1.853 |
Frag | -1.841 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
acements | +7.599 |
ortment | +6.777 |
dinand | +6.714 |
gered | +6.474 |
ampires | +6.027 |
Neg logit contributions | |
anon | -7.703 |
Article | -7.456 |
ovarian | -7.150 |
Frag | -7.050 |
Moroccan | -6.818 |
Token | 't |
Token ID | 470 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
acements | +2.204 |
dinand | +1.958 |
ortment | +1.928 |
gered | +1.885 |
esm | +1.737 |
Neg logit contributions | |
anon | -2.480 |
ovarian | -2.407 |
Article | -2.396 |
favors | -2.369 |
Moroccan | -2.333 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
acements | +4.343 |
dinand | +4.172 |
ortment | +3.988 |
gered | +3.816 |
OPLE | +3.682 |
Neg logit contributions | |
anon | -3.267 |
Article | -3.096 |
ovarian | -2.997 |
Frag | -2.918 |
favors | -2.906 |
Token | He |
Token ID | 679 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
anon | +0.720 |
Article | +0.694 |
ovarian | +0.676 |
favors | +0.672 |
Frag | +0.649 |
Neg logit contributions | |
acements | -0.853 |
dinand | -0.817 |
ortment | -0.773 |
gered | -0.734 |
OPLE | -0.722 |
Token | also |
Token ID | 635 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
anon | +0.168 |
Article | +0.162 |
ovarian | +0.157 |
favors | +0.151 |
Frag | +0.150 |
Neg logit contributions | |
acements | -0.259 |
dinand | -0.249 |
ortment | -0.238 |
gered | -0.227 |
OPLE | -0.222 |
Token | Per |
Token ID | 5990 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
anon | +0.862 |
Article | +0.806 |
ovarian | +0.796 |
favors | +0.791 |
Myst | +0.734 |
Neg logit contributions | |
acements | -1.893 |
dinand | -1.816 |
ortment | -1.750 |
gered | -1.678 |
OPLE | -1.662 |
Token | iod |
Token ID | 2101 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
anon | +0.978 |
Article | +0.947 |
ovarian | +0.930 |
favors | +0.930 |
Frag | +0.898 |
Neg logit contributions | |
acements | -0.838 |
dinand | -0.794 |
ortment | -0.745 |
gered | -0.702 |
OPLE | -0.679 |
Token | ( |
Token ID | 357 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
acements | +4.110 |
dinand | +3.771 |
ortment | +3.705 |
gered | +3.544 |
OPLE | +3.396 |
Neg logit contributions | |
anon | -3.846 |
Article | -3.630 |
ovarian | -3.605 |
favors | -3.563 |
Moroccan | -3.414 |
Token | " |
Token ID | 366 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
acements | +0.232 |
dinand | +0.221 |
ortment | +0.209 |
gered | +0.198 |
OPLE | +0.195 |
Neg logit contributions | |
anon | -0.211 |
Article | -0.203 |
ovarian | -0.198 |
favors | -0.197 |
Frag | -0.191 |
Token | P |
Token ID | 47 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
acements | +3.019 |
dinand | +2.732 |
ortment | +2.729 |
gered | +2.596 |
OPLE | +2.555 |
Neg logit contributions | |
anon | -2.406 |
ovarian | -2.375 |
favors | -2.375 |
enthusi | -2.278 |
Moroccan | -2.251 |
Token | ulse |
Token ID | 9615 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
acements | +1.871 |
dinand | +1.714 |
ortment | +1.622 |
gered | +1.499 |
oker | +1.401 |
Neg logit contributions | |
anon | -3.103 |
Article | -3.040 |
favors | -3.025 |
ovarian | -2.983 |
Myst | -2.922 |
Token | period |
Token ID | 2278 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
acements | +5.224 |
ortment | +4.668 |
dinand | +4.405 |
gered | +4.059 |
ption | +3.929 |
Neg logit contributions | |
anon | -9.144 |
Article | -8.820 |
enthusi | -8.717 |
Frag | -8.708 |
Chero | -8.580 |
Token | " |
Token ID | 1 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
acements | +0.519 |
dinand | +0.480 |
ortment | +0.465 |
gered | +0.440 |
OPLE | +0.424 |
Neg logit contributions | |
anon | -0.518 |
Article | -0.501 |
ovarian | -0.493 |
favors | -0.489 |
Myst | -0.470 |
Token | , |
Token ID | 837 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
anon | +1.568 |
Article | +1.483 |
ovarian | +1.412 |
favors | +1.407 |
Frag | +1.330 |
Neg logit contributions | |
acements | -3.809 |
dinand | -3.702 |
ortment | -3.531 |
gered | -3.402 |
OPLE | -3.365 |
Token | Float |
Token ID | 48436 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
anon | +0.893 |
Article | +0.852 |
ovarian | +0.823 |
favors | +0.813 |
Frag | +0.771 |
Neg logit contributions | |
acements | -1.629 |
dinand | -1.563 |
ortment | -1.500 |
gered | -1.439 |
OPLE | -1.413 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
anon | +0.799 |
Article | +0.756 |
ovarian | +0.737 |
favors | +0.731 |
Frag | +0.694 |
Neg logit contributions | |
acements | -1.538 |
dinand | -1.478 |
ortment | -1.417 |
gered | -1.363 |
OPLE | -1.340 |
Token | ON |
Token ID | 6177 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
acements | +4.225 |
dinand | +4.084 |
ortment | +3.825 |
gered | +3.691 |
OPLE | +3.595 |
Neg logit contributions | |
anon | -3.445 |
Article | -3.333 |
ovarian | -3.280 |
favors | -3.223 |
Frag | -3.147 |
Token | FIRE |
Token ID | 39110 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
acements | +1.395 |
dinand | +1.330 |
ortment | +1.212 |
gered | +1.142 |
OPLE | +1.142 |
Neg logit contributions | |
anon | -2.247 |
Article | -2.180 |
ovarian | -2.140 |
favors | -2.128 |
Frag | -2.069 |
Token |
|
Token ID | 198 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
anon | +2.213 |
Article | +2.135 |
favors | +2.076 |
ovarian | +2.071 |
Frag | +1.979 |
Neg logit contributions | |
acements | -3.068 |
dinand | -2.955 |
ortment | -2.800 |
gered | -2.659 |
OPLE | -2.626 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
acements | +2.069 |
dinand | +1.833 |
ortment | +1.818 |
gered | +1.757 |
esm | +1.650 |
Neg logit contributions | |
anon | -2.441 |
ovarian | -2.392 |
Article | -2.375 |
favors | -2.336 |
enthusi | -2.316 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
acements | +2.321 |
dinand | +2.176 |
ortment | +2.066 |
gered | +1.980 |
OPLE | +1.924 |
Neg logit contributions | |
anon | -2.203 |
ovarian | -2.151 |
favors | -2.143 |
Article | -2.120 |
Myst | -2.050 |
Token | a |
Token ID | 64 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
acements | +0.176 |
dinand | +0.169 |
ortment | +0.161 |
gered | +0.153 |
OPLE | +0.151 |
Neg logit contributions | |
anon | -0.122 |
Article | -0.117 |
ovarian | -0.114 |
favors | -0.114 |
Frag | -0.109 |
Token | 1 |
Token ID | 352 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
acements | +7.068 |
dinand | +6.819 |
ortment | +6.450 |
gered | +5.988 |
OPLE | +5.880 |
Neg logit contributions | |
anon | -7.033 |
ovarian | -6.692 |
Article | -6.668 |
favors | -6.555 |
Frag | -6.401 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
acements | +2.813 |
dinand | +2.599 |
ortment | +2.527 |
gered | +2.430 |
esm | +2.330 |
Neg logit contributions | |
anon | -2.174 |
ovarian | -2.088 |
Article | -2.074 |
favors | -2.054 |
Frag | -1.956 |
Token | Sw |
Token ID | 2451 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
acements | +1.668 |
dinand | +1.587 |
ortment | +1.522 |
gered | +1.455 |
OPLE | +1.429 |
Neg logit contributions | |
anon | -1.200 |
Article | -1.146 |
ovarian | -1.122 |
favors | -1.113 |
Frag | -1.065 |
Token | immer |
Token ID | 10957 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
acements | +2.288 |
dinand | +2.065 |
ortment | +1.778 |
gered | +1.539 |
oker | +1.382 |
Neg logit contributions | |
anon | -6.763 |
Article | -6.728 |
favors | -6.619 |
ovarian | -6.583 |
Frag | -6.411 |
Token | means |
Token ID | 1724 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
acements | +0.008 |
dinand | +0.007 |
ortment | +0.007 |
gered | +0.007 |
OPLE | +0.006 |
Neg logit contributions | |
anon | -0.005 |
Article | -0.005 |
ovarian | -0.005 |
favors | -0.005 |
Frag | -0.005 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
acements | +1.490 |
dinand | +1.321 |
ortment | +1.294 |
gered | +1.241 |
esm | +1.180 |
Neg logit contributions | |
anon | -1.820 |
ovarian | -1.793 |
Article | -1.779 |
favors | -1.753 |
Moroccan | -1.719 |
Token | www |
Token ID | 2503 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
acements | +1.913 |
dinand | +1.848 |
ortment | +1.748 |
gered | +1.677 |
OPLE | +1.645 |
Neg logit contributions | |
anon | -1.119 |
Article | -1.081 |
ovarian | -1.056 |
favors | -1.052 |
Myst | -1.007 |
Token | . |
Token ID | 13 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
acements | +1.105 |
dinand | +1.023 |
ortment | +0.997 |
gered | +0.961 |
esm | +0.924 |
Neg logit contributions | |
anon | -0.816 |
ovarian | -0.795 |
Article | -0.789 |
favors | -0.781 |
Moroccan | -0.754 |
Token | cd |
Token ID | 10210 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
acements | +3.302 |
dinand | +3.176 |
ortment | +2.845 |
gered | +2.715 |
OPLE | +2.591 |
Neg logit contributions | |
anon | -4.675 |
Article | -4.662 |
ovarian | -4.630 |
favors | -4.581 |
Myst | -4.534 |
Token | c |
Token ID | 66 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
acements | +3.285 |
dinand | +2.784 |
ortment | +2.685 |
gered | +2.546 |
oker | +2.484 |
Neg logit contributions | |
Article | -7.474 |
ovarian | -7.360 |
Myst | -7.322 |
favors | -7.319 |
enthusi | -7.300 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
acements | +3.206 |
dinand | +2.949 |
ortment | +2.914 |
gered | +2.807 |
esm | +2.705 |
Neg logit contributions | |
anon | -2.658 |
ovarian | -2.646 |
Article | -2.614 |
enthusi | -2.579 |
favors | -2.569 |
Token | gov |
Token ID | 9567 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
acements | +4.180 |
dinand | +3.725 |
ortment | +3.557 |
gered | +3.433 |
esm | +3.245 |
Neg logit contributions | |
Article | -9.636 |
ovarian | -9.543 |
Moroccan | -9.452 |
enthusi | -9.414 |
anon | -9.365 |
Token | / |
Token ID | 14 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
acements | +3.857 |
ortment | +3.450 |
dinand | +3.443 |
gered | +3.300 |
esm | +3.172 |
Neg logit contributions | |
anon | -3.572 |
ovarian | -3.568 |
enthusi | -3.519 |
Article | -3.504 |
favors | -3.471 |
Token | home |
Token ID | 11195 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
acements | +2.427 |
dinand | +2.308 |
ortment | +2.169 |
gered | +2.049 |
OPLE | +2.024 |
Neg logit contributions | |
anon | -2.340 |
Article | -2.265 |
ovarian | -2.255 |
favors | -2.248 |
Moroccan | -2.171 |
Token | andre |
Token ID | 49078 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
anon | +1.605 |
Article | +1.553 |
ovarian | +1.467 |
favors | +1.451 |
Frag | +1.400 |
Neg logit contributions | |
acements | -2.474 |
dinand | -2.382 |
ortment | -2.262 |
gered | -2.176 |
OPLE | -2.145 |
Token | cre |
Token ID | 7513 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
acements | +1.605 |
dinand | +1.537 |
ortment | +1.447 |
gered | +1.377 |
OPLE | +1.360 |
Neg logit contributions | |
anon | -1.305 |
Article | -1.262 |
ovarian | -1.236 |
favors | -1.228 |
Frag | -1.185 |
Token | aware |
Token ID | 3910 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
acements | +0.982 |
dinand | +0.909 |
ortment | +0.868 |
gered | +0.815 |
OPLE | +0.757 |
Neg logit contributions | |
anon | -1.321 |
Article | -1.284 |
ovarian | -1.266 |
Frag | -1.255 |
favors | -1.246 |
Token | of |
Token ID | 286 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
acements | +1.922 |
dinand | +1.755 |
ortment | +1.752 |
gered | +1.667 |
esm | +1.595 |
Neg logit contributions | |
anon | -1.733 |
Article | -1.659 |
ovarian | -1.633 |
favors | -1.616 |
Frag | -1.590 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
acements | +2.048 |
dinand | +1.906 |
ortment | +1.847 |
gered | +1.790 |
esm | +1.699 |
Neg logit contributions | |
anon | -1.609 |
Article | -1.548 |
ovarian | -1.518 |
favors | -1.498 |
Frag | -1.463 |
Token | In |
Token ID | 554 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
acements | +1.438 |
dinand | +1.380 |
ortment | +1.315 |
gered | +1.250 |
OPLE | +1.233 |
Neg logit contributions | |
anon | -1.003 |
Article | -0.959 |
ovarian | -0.933 |
favors | -0.929 |
Frag | -0.889 |
Token | this |
Token ID | 428 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
anon | +0.889 |
Article | +0.858 |
ovarian | +0.835 |
favors | +0.833 |
Frag | +0.811 |
Neg logit contributions | |
acements | -1.034 |
dinand | -0.992 |
ortment | -0.943 |
gered | -0.899 |
OPLE | -0.862 |
Token | post |
Token ID | 1281 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
acements | +0.914 |
dinand | +0.869 |
ortment | +0.839 |
gered | +0.818 |
oker | +0.762 |
Neg logit contributions | |
anon | -0.735 |
Article | -0.705 |
favors | -0.695 |
ovarian | -0.695 |
Frag | -0.679 |
Token | I |
Token ID | 314 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
acements | +5.559 |
dinand | +4.891 |
ortment | +4.722 |
gered | +4.434 |
oker | +4.298 |
Neg logit contributions | |
anon | -8.097 |
ovarian | -7.717 |
Article | -7.691 |
favors | -7.661 |
Niet | -7.600 |
Token | 'll |
Token ID | 1183 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
acements | +4.615 |
dinand | +4.136 |
ortment | +3.987 |
gered | +3.881 |
ople | +3.736 |
Neg logit contributions | |
anon | -4.901 |
Article | -4.868 |
Frag | -4.683 |
ovarian | -4.652 |
Moroccan | -4.596 |
Token | round |
Token ID | 2835 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
acements | +0.513 |
dinand | +0.480 |
ortment | +0.469 |
gered | +0.442 |
OPLE | +0.427 |
Neg logit contributions | |
anon | -0.419 |
Article | -0.405 |
ovarian | -0.389 |
favors | -0.387 |
Frag | -0.384 |
Token | up |
Token ID | 510 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
acements | +2.269 |
dinand | +2.115 |
ortment | +2.026 |
gered | +1.967 |
OPLE | +1.827 |
Neg logit contributions | |
anon | -2.482 |
Article | -2.421 |
ovarian | -2.328 |
favors | -2.307 |
Frag | -2.303 |
Token | some |
Token ID | 617 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
acements | +0.259 |
dinand | +0.243 |
ortment | +0.235 |
gered | +0.223 |
OPLE | +0.215 |
Neg logit contributions | |
anon | -0.208 |
Article | -0.201 |
ovarian | -0.197 |
favors | -0.191 |
Frag | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
anon | +0.867 |
Article | +0.835 |
ovarian | +0.811 |
favors | +0.806 |
Frag | +0.782 |
Neg logit contributions | |
acements | -1.129 |
dinand | -1.088 |
ortment | -1.029 |
gered | -0.983 |
OPLE | -0.964 |
Token | Image |
Token ID | 7412 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
acements | +0.011 |
dinand | +0.011 |
ortment | +0.010 |
gered | +0.010 |
OPLE | +0.009 |
Neg logit contributions | |
anon | -0.009 |
Article | -0.009 |
ovarian | -0.008 |
favors | -0.008 |
Frag | -0.008 |
Token | courtesy |
Token ID | 12537 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
acements | +3.461 |
dinand | +3.354 |
ortment | +3.175 |
gered | +3.052 |
OPLE | +2.964 |
Neg logit contributions | |
anon | -2.172 |
Article | -2.080 |
ovarian | -2.037 |
favors | -1.983 |
Frag | -1.955 |
Token | of |
Token ID | 286 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
acements | +2.136 |
dinand | +2.058 |
ortment | +1.948 |
gered | +1.860 |
OPLE | +1.825 |
Neg logit contributions | |
anon | -1.574 |
Article | -1.515 |
ovarian | -1.470 |
favors | -1.461 |
Frag | -1.416 |
Token | Columbia |
Token ID | 9309 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
acements | +2.241 |
dinand | +2.146 |
ortment | +2.030 |
gered | +1.943 |
OPLE | +1.906 |
Neg logit contributions | |
anon | -1.718 |
Article | -1.646 |
ovarian | -1.599 |
favors | -1.590 |
Frag | -1.543 |
Token | Pictures |
Token ID | 20051 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
acements | +3.738 |
dinand | +3.591 |
ortment | +3.380 |
gered | +3.124 |
OPLE | +3.101 |
Neg logit contributions | |
anon | -4.264 |
Article | -4.066 |
ovarian | -4.047 |
favors | -3.939 |
Frag | -3.893 |
Token | The |
Token ID | 383 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
acements | +7.156 |
dinand | +6.553 |
ortment | +6.315 |
gered | +6.010 |
OPLE | +5.847 |
Neg logit contributions | |
anon | -6.974 |
Article | -6.555 |
ovarian | -6.462 |
Frag | -6.359 |
favors | -6.351 |
Token | iconic |
Token ID | 14133 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
acements | +0.657 |
dinand | +0.631 |
ortment | +0.584 |
gered | +0.559 |
OPLE | +0.540 |
Neg logit contributions | |
anon | -0.744 |
Article | -0.718 |
ovarian | -0.700 |
favors | -0.698 |
Frag | -0.684 |
Token | old |
Token ID | 1468 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
acements | +0.792 |
dinand | +0.760 |
ortment | +0.716 |
gered | +0.684 |
OPLE | +0.667 |
Neg logit contributions | |
anon | -0.679 |
Article | -0.653 |
ovarian | -0.635 |
favors | -0.633 |
Frag | -0.617 |
Token | headquarters |
Token ID | 10043 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
acements | +3.818 |
dinand | +3.677 |
ortment | +3.403 |
gered | +3.313 |
OPLE | +3.286 |
Neg logit contributions | |
anon | -2.828 |
Article | -2.729 |
favors | -2.689 |
Frag | -2.617 |
ovarian | -2.611 |
Token | of |
Token ID | 286 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
acements | +1.000 |
dinand | +0.928 |
ortment | +0.910 |
gered | +0.863 |
OPLE | +0.825 |
Neg logit contributions | |
anon | -0.828 |
Article | -0.796 |
ovarian | -0.791 |
favors | -0.782 |
Frag | -0.751 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
acements | +1.640 |
dinand | +1.446 |
ortment | +1.423 |
gered | +1.364 |
esm | +1.298 |
Neg logit contributions | |
anon | -2.020 |
ovarian | -1.991 |
Article | -1.978 |
favors | -1.946 |
Moroccan | -1.913 |
Token | www |
Token ID | 2503 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
acements | +1.596 |
dinand | +1.541 |
ortment | +1.463 |
gered | +1.402 |
OPLE | +1.381 |
Neg logit contributions | |
anon | -0.901 |
Article | -0.867 |
ovarian | -0.841 |
favors | -0.838 |
Frag | -0.801 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
acements | +1.382 |
dinand | +1.276 |
ortment | +1.244 |
gered | +1.202 |
esm | +1.154 |
Neg logit contributions | |
anon | -1.034 |
ovarian | -1.008 |
Article | -1.002 |
favors | -0.990 |
Moroccan | -0.958 |
Token | cd |
Token ID | 10210 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
acements | +2.909 |
dinand | +2.758 |
ortment | +2.474 |
gered | +2.373 |
esm | +2.243 |
Neg logit contributions | |
Article | -4.367 |
ovarian | -4.331 |
anon | -4.324 |
favors | -4.284 |
Myst | -4.283 |
Token | c |
Token ID | 66 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
acements | +3.365 |
dinand | +2.824 |
ortment | +2.740 |
gered | +2.598 |
oker | +2.534 |
Neg logit contributions | |
Article | -7.697 |
ovarian | -7.583 |
Myst | -7.557 |
enthusi | -7.551 |
favors | -7.543 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
acements | +3.464 |
dinand | +3.150 |
ortment | +3.137 |
gered | +3.034 |
esm | +2.922 |
Neg logit contributions | |
anon | -2.947 |
ovarian | -2.937 |
enthusi | -2.928 |
Article | -2.902 |
favors | -2.850 |
Token | gov |
Token ID | 9567 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
acements | +4.191 |
dinand | +3.638 |
ortment | +3.546 |
gered | +3.415 |
esm | +3.300 |
Neg logit contributions | |
Article | -9.524 |
ovarian | -9.492 |
enthusi | -9.442 |
Moroccan | -9.351 |
anon | -9.282 |
Token | / |
Token ID | 14 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
acements | +4.058 |
ortment | +3.617 |
dinand | +3.595 |
gered | +3.457 |
esm | +3.334 |
Neg logit contributions | |
enthusi | -3.826 |
anon | -3.817 |
ovarian | -3.817 |
Article | -3.761 |
favors | -3.714 |
Token | violence |
Token ID | 37502 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
acements | +2.126 |
dinand | +2.019 |
ortment | +1.908 |
gered | +1.798 |
OPLE | +1.789 |
Neg logit contributions | |
anon | -1.948 |
Article | -1.889 |
ovarian | -1.868 |
favors | -1.865 |
Moroccan | -1.795 |
Token | pre |
Token ID | 3866 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
acements | +1.689 |
dinand | +1.625 |
ortment | +1.541 |
gered | +1.471 |
OPLE | +1.449 |
Neg logit contributions | |
anon | -1.178 |
Article | -1.131 |
ovarian | -1.099 |
favors | -1.095 |
Frag | -1.052 |
Token | vention |
Token ID | 4018 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
acements | +0.329 |
dinand | +0.313 |
ortment | +0.292 |
gered | +0.275 |
OPLE | +0.269 |
Neg logit contributions | |
anon | -0.388 |
Article | -0.377 |
ovarian | -0.369 |
favors | -0.367 |
Frag | -0.357 |
Token | regional |
Token ID | 7915 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
anon | +1.915 |
Article | +1.849 |
ovarian | +1.802 |
favors | +1.796 |
Frag | +1.729 |
Neg logit contributions | |
acements | -2.470 |
dinand | -2.382 |
ortment | -2.246 |
gered | -2.131 |
OPLE | -2.103 |
Token | powers |
Token ID | 5635 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
acements | +0.302 |
dinand | +0.287 |
ortment | +0.270 |
gered | +0.257 |
OPLE | +0.253 |
Neg logit contributions | |
anon | -0.287 |
Article | -0.277 |
ovarian | -0.269 |
favors | -0.267 |
Frag | -0.259 |
Token | ; |
Token ID | 26 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
acements | +1.193 |
dinand | +1.146 |
ortment | +1.091 |
gered | +1.047 |
OPLE | +1.025 |
Neg logit contributions | |
anon | -0.789 |
Article | -0.743 |
ovarian | -0.723 |
favors | -0.717 |
Frag | -0.689 |
Token | but |
Token ID | 475 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
anon | +0.974 |
Article | +0.938 |
ovarian | +0.912 |
favors | +0.909 |
Frag | +0.875 |
Neg logit contributions | |
acements | -1.272 |
dinand | -1.223 |
ortment | -1.157 |
gered | -1.102 |
OPLE | -1.085 |
Token | at |
Token ID | 379 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
acements | +0.739 |
dinand | +0.707 |
ortment | +0.667 |
gered | +0.640 |
OPLE | +0.625 |
Neg logit contributions | |
anon | -0.623 |
Article | -0.599 |
ovarian | -0.575 |
favors | -0.571 |
Frag | -0.556 |
Token | other |
Token ID | 584 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
acements | +3.464 |
dinand | +3.316 |
ortment | +3.098 |
gered | +2.902 |
OPLE | +2.827 |
Neg logit contributions | |
anon | -3.864 |
Article | -3.756 |
ovarian | -3.611 |
favors | -3.589 |
Frag | -3.523 |
Token | times |
Token ID | 1661 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
acements | +5.648 |
dinand | +5.002 |
ortment | +4.631 |
gered | +4.424 |
OPLE | +4.201 |
Neg logit contributions | |
anon | -8.469 |
Article | -8.173 |
ovarian | -7.672 |
favors | -7.589 |
Frag | -7.583 |
Token | it |
Token ID | 340 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
acements | +4.253 |
dinand | +4.025 |
ortment | +3.776 |
gered | +3.733 |
OPLE | +3.617 |
Neg logit contributions | |
anon | -3.659 |
Article | -3.453 |
ovarian | -3.294 |
favors | -3.280 |
Frag | -3.205 |
Token | was |
Token ID | 373 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
acements | +1.946 |
dinand | +1.843 |
ortment | +1.751 |
gered | +1.706 |
OPLE | +1.622 |
Neg logit contributions | |
anon | -1.533 |
Article | -1.476 |
ovarian | -1.423 |
Frag | -1.387 |
favors | -1.377 |
Token | the |
Token ID | 262 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
acements | +0.782 |
dinand | +0.748 |
ortment | +0.706 |
gered | +0.676 |
OPLE | +0.662 |
Neg logit contributions | |
anon | -0.678 |
Article | -0.650 |
ovarian | -0.629 |
favors | -0.629 |
Frag | -0.606 |
Token | regional |
Token ID | 7915 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
acements | +0.457 |
dinand | +0.437 |
ortment | +0.413 |
gered | +0.395 |
OPLE | +0.386 |
Neg logit contributions | |
anon | -0.407 |
Article | -0.393 |
favors | -0.378 |
ovarian | -0.378 |
Frag | -0.366 |
Token | OM |
Token ID | 2662 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
acements | +0.136 |
dinand | +0.131 |
ortment | +0.124 |
gered | +0.118 |
OPLE | +0.117 |
Neg logit contributions | |
anon | -0.092 |
Article | -0.089 |
ovarian | -0.086 |
favors | -0.086 |
Frag | -0.082 |
Token | B |
Token ID | 33 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
acements | +2.312 |
dinand | +2.235 |
ortment | +2.097 |
gered | +2.024 |
OPLE | +1.989 |
Neg logit contributions | |
anon | -1.832 |
Article | -1.747 |
ovarian | -1.713 |
favors | -1.698 |
Frag | -1.636 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
acements | +0.683 |
dinand | +0.657 |
ortment | +0.622 |
gered | +0.595 |
OPLE | +0.585 |
Neg logit contributions | |
anon | -0.502 |
Article | -0.481 |
ovarian | -0.468 |
favors | -0.464 |
Frag | -0.448 |
Token |
|
Token ID | 198 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
acements | +2.164 |
dinand | +1.915 |
ortment | +1.899 |
gered | +1.834 |
esm | +1.727 |
Neg logit contributions | |
anon | -2.545 |
ovarian | -2.492 |
Article | -2.475 |
favors | -2.436 |
enthusi | -2.411 |
Token | 1 |
Token ID | 16 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
acements | +2.718 |
dinand | +2.521 |
ortment | +2.394 |
gered | +2.292 |
OPLE | +2.230 |
Neg logit contributions | |
anon | -2.991 |
ovarian | -2.927 |
favors | -2.922 |
Article | -2.872 |
Myst | -2.809 |
Token | d |
Token ID | 67 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
acements | +0.336 |
dinand | +0.324 |
ortment | +0.309 |
gered | +0.296 |
OPLE | +0.292 |
Neg logit contributions | |
anon | -0.201 |
Article | -0.192 |
ovarian | -0.185 |
favors | -0.185 |
Frag | -0.177 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
acements | +6.728 |
dinand | +6.497 |
ortment | +6.143 |
gered | +5.671 |
OPLE | +5.615 |
Neg logit contributions | |
anon | -6.753 |
ovarian | -6.534 |
Article | -6.468 |
favors | -6.462 |
Frag | -6.264 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
acements | +2.302 |
dinand | +2.141 |
ortment | +2.077 |
gered | +1.990 |
esm | +1.909 |
Neg logit contributions | |
anon | -1.732 |
Article | -1.652 |
ovarian | -1.647 |
favors | -1.626 |
Frag | -1.555 |
Token | Old |
Token ID | 5706 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
anon | +0.852 |
Article | +0.819 |
ovarian | +0.798 |
favors | +0.795 |
Frag | +0.765 |
Neg logit contributions | |
acements | -1.085 |
dinand | -1.041 |
ortment | -0.986 |
gered | -0.939 |
OPLE | -0.923 |
Token | gift |
Token ID | 6979 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
anon | +1.140 |
Article | +1.086 |
ovarian | +1.043 |
favors | +1.042 |
Frag | +0.985 |
Neg logit contributions | |
acements | -2.587 |
dinand | -2.499 |
ortment | -2.387 |
gered | -2.299 |
OPLE | -2.276 |
Token | – |
Token ID | 1906 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
acements | +1.397 |
dinand | +1.348 |
ortment | +1.285 |
gered | +1.231 |
OPLE | +1.214 |
Neg logit contributions | |
anon | -0.829 |
Article | -0.793 |
ovarian | -0.764 |
favors | -0.757 |
Frag | -0.728 |
Token | . |
Token ID | 13 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
acements | +0.024 |
dinand | +0.022 |
ortment | +0.021 |
gered | +0.021 |
OPLE | +0.020 |
Neg logit contributions | |
anon | -0.016 |
Article | -0.016 |
ovarian | -0.015 |
favors | -0.015 |
Moroccan | -0.015 |
Token | ed |
Token ID | 276 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
acements | +3.169 |
dinand | +3.047 |
ortment | +2.833 |
gered | +2.711 |
OPLE | +2.590 |
Neg logit contributions | |
anon | -3.049 |
ovarian | -3.012 |
Article | -3.002 |
favors | -2.977 |
Moroccan | -2.890 |
Token | wards |
Token ID | 2017 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
acements | +3.639 |
dinand | +3.461 |
ortment | +3.229 |
gered | +3.111 |
esm | +2.999 |
Neg logit contributions | |
anon | -3.118 |
Article | -3.058 |
ovarian | -2.998 |
favors | -2.958 |
Moroccan | -2.911 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
acements | +1.259 |
dinand | +1.212 |
ortment | +1.147 |
gered | +1.094 |
OPLE | +1.075 |
Neg logit contributions | |
anon | -0.915 |
Article | -0.883 |
ovarian | -0.858 |
favors | -0.854 |
Frag | -0.823 |
Token | af |
Token ID | 1878 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
acements | +1.097 |
dinand | +1.050 |
ortment | +0.987 |
gered | +0.936 |
OPLE | +0.919 |
Neg logit contributions | |
anon | -1.038 |
Article | -1.004 |
ovarian | -0.978 |
favors | -0.975 |
Frag | -0.943 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
acements | +1.471 |
dinand | +1.399 |
ortment | +1.340 |
gered | +1.287 |
esm | +1.230 |
Neg logit contributions | |
anon | -1.048 |
Article | -1.029 |
ovarian | -1.011 |
favors | -0.994 |
Frag | -0.962 |
Token | mil |
Token ID | 25433 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
acements | +5.654 |
dinand | +5.257 |
ortment | +4.915 |
esm | +4.676 |
gered | +4.626 |
Neg logit contributions | |
Article | -7.868 |
ovarian | -7.716 |
anon | -7.601 |
favors | -7.487 |
Moroccan | -7.380 |
Token | / |
Token ID | 14 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
acements | +3.436 |
dinand | +3.316 |
ortment | +3.132 |
gered | +2.985 |
OPLE | +2.917 |
Neg logit contributions | |
anon | -2.556 |
Article | -2.451 |
ovarian | -2.400 |
favors | -2.395 |
Frag | -2.304 |
Token | gallery |
Token ID | 24460 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
anon | +0.017 |
Article | +0.016 |
ovarian | +0.016 |
favors | +0.016 |
Frag | +0.015 |
Neg logit contributions | |
acements | -0.015 |
dinand | -0.014 |
ortment | -0.013 |
gered | -0.013 |
OPLE | -0.012 |
Token | / |
Token ID | 14 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
acements | +0.699 |
dinand | +0.673 |
ortment | +0.638 |
gered | +0.609 |
OPLE | +0.600 |
Neg logit contributions | |
anon | -0.493 |
Article | -0.472 |
ovarian | -0.461 |
favors | -0.459 |
Frag | -0.440 |
Token | ye |
Token ID | 5948 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
anon | +1.119 |
Article | +1.082 |
ovarian | +1.046 |
favors | +1.044 |
Frag | +1.011 |
Neg logit contributions | |
acements | -1.261 |
dinand | -1.207 |
ortment | -1.137 |
gered | -1.082 |
OPLE | -1.062 |
Token | pin |
Token ID | 6757 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
anon | +0.148 |
Article | +0.141 |
ovarian | +0.135 |
favors | +0.135 |
Frag | +0.128 |
Neg logit contributions | |
acements | -0.310 |
dinand | -0.300 |
ortment | -0.286 |
gered | -0.275 |
OPLE | -0.272 |
Token | hole |
Token ID | 13207 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
anon | +1.595 |
Article | +1.532 |
ovarian | +1.485 |
favors | +1.479 |
Frag | +1.424 |
Neg logit contributions | |
acements | -2.247 |
dinand | -2.164 |
ortment | -2.051 |
gered | -1.956 |
OPLE | -1.930 |
Token | images |
Token ID | 4263 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
acements | +1.803 |
dinand | +1.711 |
ortment | +1.613 |
gered | +1.530 |
OPLE | +1.489 |
Neg logit contributions | |
anon | -1.779 |
Article | -1.745 |
ovarian | -1.683 |
favors | -1.667 |
Frag | -1.634 |
Token | showing |
Token ID | 4478 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
acements | +3.500 |
dinand | +3.222 |
ortment | +3.127 |
gered | +2.934 |
OPLE | +2.785 |
Neg logit contributions | |
anon | -3.936 |
Article | -3.868 |
ovarian | -3.718 |
favors | -3.670 |
Frag | -3.634 |
Token | typical |
Token ID | 7226 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
anon | +0.995 |
Article | +0.948 |
ovarian | +0.911 |
favors | +0.905 |
Frag | +0.863 |
Neg logit contributions | |
acements | -1.972 |
dinand | -1.905 |
ortment | -1.820 |
gered | -1.748 |
OPLE | -1.723 |
Token | variation |
Token ID | 12291 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
acements | +1.360 |
dinand | +1.303 |
ortment | +1.242 |
gered | +1.186 |
OPLE | +1.154 |
Neg logit contributions | |
anon | -0.971 |
Article | -0.945 |
ovarian | -0.904 |
favors | -0.902 |
Frag | -0.873 |
Token | for |
Token ID | 329 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
acements | +5.553 |
dinand | +5.185 |
ortment | +4.952 |
gered | +4.518 |
OPLE | +4.329 |
Neg logit contributions | |
anon | -7.927 |
Article | -7.820 |
ovarian | -7.578 |
favors | -7.384 |
Frag | -7.350 |
Token | a |
Token ID | 257 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
anon | +0.801 |
Article | +0.771 |
ovarian | +0.746 |
favors | +0.743 |
Frag | +0.715 |
Neg logit contributions | |
acements | -1.152 |
dinand | -1.108 |
ortment | -1.051 |
gered | -1.003 |
OPLE | -0.988 |
Token | 16 |
Token ID | 1467 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
anon | +0.316 |
Article | +0.306 |
favors | +0.293 |
ovarian | +0.293 |
Frag | +0.281 |
Neg logit contributions | |
acements | -0.480 |
dinand | -0.463 |
ortment | -0.441 |
gered | -0.418 |
OPLE | -0.412 |
Token | - |
Token ID | 12 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
acements | +1.480 |
dinand | +1.411 |
ortment | +1.323 |
gered | +1.250 |
OPLE | +1.224 |
Neg logit contributions | |
anon | -1.587 |
Article | -1.539 |
ovarian | -1.503 |
favors | -1.499 |
Frag | -1.454 |
Token | 35 |
Token ID | 2327 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
acements | +1.221 |
dinand | +1.177 |
ortment | +1.123 |
gered | +1.076 |
OPLE | +1.060 |
Neg logit contributions | |
anon | -0.669 |
Article | -0.637 |
ovarian | -0.621 |
favors | -0.616 |
Frag | -0.585 |
Token | their |
Token ID | 511 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
acements | +1.726 |
dinand | +1.663 |
ortment | +1.567 |
gered | +1.498 |
OPLE | +1.466 |
Neg logit contributions | |
anon | -1.465 |
Article | -1.396 |
favors | -1.355 |
ovarian | -1.344 |
Frag | -1.330 |
Token | son |
Token ID | 3367 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
acements | +1.436 |
dinand | +1.389 |
ortment | +1.307 |
gered | +1.257 |
OPLE | +1.234 |
Neg logit contributions | |
anon | -1.078 |
Article | -1.024 |
favors | -0.997 |
ovarian | -0.989 |
Frag | -0.968 |
Token | , |
Token ID | 11 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
acements | +5.660 |
dinand | +5.549 |
ortment | +5.168 |
gered | +4.951 |
OPLE | +4.914 |
Neg logit contributions | |
anon | -4.188 |
Article | -4.050 |
favors | -3.911 |
ovarian | -3.873 |
Frag | -3.793 |
Token | Holl |
Token ID | 11806 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
acements | +4.833 |
dinand | +4.712 |
ortment | +4.357 |
gered | +4.186 |
OPLE | +4.099 |
Neg logit contributions | |
anon | -4.018 |
Article | -3.890 |
ovarian | -3.791 |
favors | -3.778 |
Frag | -3.727 |
Token | is |
Token ID | 271 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
acements | +3.975 |
dinand | +3.744 |
ortment | +3.577 |
gered | +3.351 |
OPLE | +3.227 |
Neg logit contributions | |
anon | -3.473 |
Article | -3.439 |
ovarian | -3.395 |
favors | -3.352 |
Frag | -3.249 |
Token | Alvin |
Token ID | 49939 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
acements | +0.501 |
dinand | +0.484 |
ortment | +0.457 |
gered | +0.435 |
OPLE | +0.428 |
Neg logit contributions | |
anon | -0.391 |
Article | -0.377 |
ovarian | -0.366 |
favors | -0.364 |
Frag | -0.352 |
Token | James |
Token ID | 3700 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
acements | +6.502 |
dinand | +6.318 |
ortment | +5.882 |
gered | +5.520 |
OPLE | +5.420 |
Neg logit contributions | |
anon | -6.797 |
Article | -6.590 |
ovarian | -6.481 |
Frag | -6.307 |
favors | -6.302 |
Token | Reid |
Token ID | 16095 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
acements | +2.659 |
dinand | +2.573 |
ortment | +2.403 |
gered | +2.262 |
OPLE | +2.206 |
Neg logit contributions | |
anon | -2.680 |
Article | -2.596 |
ovarian | -2.547 |
favors | -2.513 |
Frag | -2.469 |
Token | Daniels |
Token ID | 28162 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
acements | +3.804 |
dinand | +3.687 |
ortment | +3.471 |
gered | +3.300 |
OPLE | +3.252 |
Neg logit contributions | |
anon | -2.845 |
Article | -2.746 |
ovarian | -2.687 |
favors | -2.650 |
Frag | -2.576 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
acements | +3.692 |
dinand | +3.584 |
ortment | +3.365 |
gered | +3.204 |
OPLE | +3.166 |
Neg logit contributions | |
anon | -2.876 |
Article | -2.757 |
ovarian | -2.675 |
favors | -2.650 |
Frag | -2.583 |
Token | HI |
Token ID | 36210 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
acements | +1.327 |
dinand | +1.275 |
ortment | +1.201 |
gered | +1.145 |
OPLE | +1.125 |
Neg logit contributions | |
anon | -1.128 |
Article | -1.086 |
ovarian | -1.054 |
favors | -1.049 |
Frag | -1.019 |
Token | single |
Token ID | 2060 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
anon | +0.809 |
Article | +0.766 |
ovarian | +0.733 |
favors | +0.731 |
Frag | +0.704 |
Neg logit contributions | |
acements | -1.411 |
dinand | -1.368 |
ortment | -1.303 |
gered | -1.253 |
OPLE | -1.227 |
Token | line |
Token ID | 1627 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
acements | +1.601 |
dinand | +1.530 |
ortment | +1.484 |
gered | +1.442 |
OPLE | +1.365 |
Neg logit contributions | |
anon | -1.232 |
Article | -1.158 |
ovarian | -1.117 |
Frag | -1.110 |
favors | -1.109 |
Token | blocks |
Token ID | 7021 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
acements | +2.936 |
dinand | +2.661 |
ortment | +2.521 |
gered | +2.480 |
OPLE | +2.308 |
Neg logit contributions | |
anon | -2.991 |
Article | -2.959 |
ovarian | -2.823 |
favors | -2.742 |
Frag | -2.739 |
Token | and |
Token ID | 290 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
anon | +0.140 |
Article | +0.134 |
ovarian | +0.130 |
favors | +0.128 |
Frag | +0.125 |
Neg logit contributions | |
acements | -0.220 |
dinand | -0.209 |
ortment | -0.201 |
gered | -0.193 |
OPLE | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
anon | +0.033 |
Article | +0.032 |
ovarian | +0.031 |
favors | +0.031 |
Frag | +0.031 |
Neg logit contributions | |
acements | -0.033 |
dinand | -0.031 |
ortment | -0.030 |
gered | -0.028 |
OPLE | -0.027 |
Token | other |
Token ID | 584 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
acements | +0.508 |
dinand | +0.472 |
ortment | +0.458 |
gered | +0.434 |
OPLE | +0.402 |
Neg logit contributions | |
anon | -0.627 |
Article | -0.612 |
ovarian | -0.596 |
Frag | -0.592 |
favors | -0.589 |
Token | for |
Token ID | 329 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
acements | +4.051 |
ortment | +3.533 |
dinand | +3.494 |
gered | +3.362 |
oker | +2.911 |
Neg logit contributions | |
anon | -9.060 |
Article | -8.800 |
ovarian | -8.510 |
enthusi | -8.453 |
Frag | -8.383 |
Token | multi |
Token ID | 5021 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
anon | +0.707 |
Article | +0.683 |
ovarian | +0.660 |
favors | +0.659 |
Frag | +0.638 |
Neg logit contributions | |
acements | -0.894 |
dinand | -0.859 |
ortment | -0.814 |
gered | -0.777 |
OPLE | -0.762 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
acements | +0.363 |
dinand | +0.339 |
ortment | +0.326 |
gered | +0.309 |
OPLE | +0.289 |
Neg logit contributions | |
anon | -0.459 |
Article | -0.442 |
ovarian | -0.431 |
favors | -0.430 |
Frag | -0.424 |
Token | line |
Token ID | 1370 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
acements | +0.607 |
dinand | +0.570 |
ortment | +0.553 |
gered | +0.529 |
esm | +0.493 |
Neg logit contributions | |
anon | -0.602 |
ovarian | -0.589 |
favors | -0.585 |
Article | -0.581 |
Moroccan | -0.569 |
Token | ? |
Token ID | 30 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
acements | +1.759 |
dinand | +1.636 |
ortment | +1.547 |
gered | +1.514 |
OPLE | +1.416 |
Neg logit contributions | |
anon | -1.607 |
Article | -1.560 |
ovarian | -1.493 |
favors | -1.467 |
Moroccan | -1.448 |
Token | com |
Token ID | 785 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
acements | +1.471 |
dinand | +1.416 |
ortment | +1.337 |
gered | +1.267 |
OPLE | +1.248 |
Neg logit contributions | |
anon | -1.313 |
Article | -1.262 |
ovarian | -1.244 |
favors | -1.234 |
Moroccan | -1.188 |
Token | The |
Token ID | 383 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
acements | +5.675 |
dinand | +5.420 |
ortment | +5.068 |
gered | +4.832 |
OPLE | +4.758 |
Neg logit contributions | |
anon | -4.987 |
Article | -4.752 |
ovarian | -4.715 |
favors | -4.630 |
Frag | -4.531 |
Token | old |
Token ID | 1468 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
anon | +0.091 |
Article | +0.087 |
ovarian | +0.085 |
favors | +0.084 |
Frag | +0.082 |
Neg logit contributions | |
acements | -0.114 |
dinand | -0.110 |
ortment | -0.104 |
gered | -0.099 |
OPLE | -0.097 |
Token | building |
Token ID | 16894 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
acements | +2.710 |
dinand | +2.543 |
ortment | +2.319 |
gered | +2.156 |
OPLE | +2.059 |
Neg logit contributions | |
anon | -4.821 |
Article | -4.679 |
ovarian | -4.651 |
favors | -4.618 |
Frag | -4.503 |
Token | was |
Token ID | 373 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
acements | +2.298 |
dinand | +2.206 |
ortment | +2.088 |
gered | +2.003 |
OPLE | +1.958 |
Neg logit contributions | |
anon | -1.683 |
Article | -1.615 |
ovarian | -1.562 |
favors | -1.560 |
Frag | -1.502 |
Token | renamed |
Token ID | 25121 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
acements | +0.428 |
dinand | +0.410 |
ortment | +0.384 |
gered | +0.367 |
OPLE | +0.359 |
Neg logit contributions | |
anon | -0.400 |
Article | -0.385 |
favors | -0.374 |
ovarian | -0.374 |
Frag | -0.362 |
Token | for |
Token ID | 1640 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
acements | +7.026 |
dinand | +6.788 |
ortment | +6.266 |
gered | +6.026 |
OPLE | +5.870 |
Neg logit contributions | |
anon | -6.357 |
ovarian | -6.143 |
Article | -5.982 |
favors | -5.961 |
Moroccan | -5.782 |
Token | the |
Token ID | 262 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
acements | +4.082 |
dinand | +3.899 |
ortment | +3.654 |
gered | +3.457 |
OPLE | +3.362 |
Neg logit contributions | |
anon | -4.244 |
Article | -4.068 |
ovarian | -4.015 |
favors | -3.952 |
Frag | -3.859 |
Token | shooting |
Token ID | 4395 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
anon | +1.034 |
Article | +0.993 |
ovarian | +0.963 |
favors | +0.962 |
Frag | +0.929 |
Neg logit contributions | |
acements | -1.279 |
dinand | -1.228 |
ortment | -1.164 |
gered | -1.110 |
OPLE | -1.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
anon | +1.097 |
Article | +1.050 |
ovarian | +1.027 |
favors | +1.017 |
Frag | +0.974 |
Neg logit contributions | |
acements | -1.685 |
dinand | -1.615 |
ortment | -1.541 |
gered | -1.476 |
OPLE | -1.445 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
anon | +0.852 |
Article | +0.829 |
ovarian | +0.792 |
favors | +0.789 |
Frag | +0.770 |
Neg logit contributions | |
acements | -1.044 |
dinand | -1.003 |
ortment | -0.948 |
gered | -0.897 |
OPLE | -0.891 |
Token | ulse |
Token ID | 9615 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
anon | +4.199 |
Article | +4.074 |
ovarian | +3.938 |
favors | +3.909 |
Frag | +3.883 |
Neg logit contributions | |
acements | -3.472 |
dinand | -3.387 |
ortment | -3.092 |
OPLE | -2.902 |
gered | -2.894 |
Token | Amount |
Token ID | 31264 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
anon | +1.346 |
Article | +1.273 |
ovarian | +1.238 |
favors | +1.230 |
Frag | +1.157 |
Neg logit contributions | |
acements | -2.680 |
dinand | -2.584 |
ortment | -2.471 |
gered | -2.374 |
OPLE | -2.344 |
Token | ; |
Token ID | 26 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
anon | +2.215 |
Article | +2.113 |
ovarian | +2.050 |
favors | +2.035 |
Frag | +1.971 |
Neg logit contributions | |
acements | -3.773 |
dinand | -3.663 |
ortment | -3.481 |
gered | -3.319 |
OPLE | -3.291 |
Token | } |
Token ID | 1782 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
acements | +0.905 |
dinand | +0.860 |
ortment | +0.813 |
gered | +0.779 |
OPLE | +0.760 |
Neg logit contributions | |
anon | -0.796 |
Article | -0.769 |
ovarian | -0.746 |
favors | -0.740 |
Frag | -0.715 |
Token | 1 |
Token ID | 352 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
acements | +4.773 |
dinand | +4.485 |
ortment | +4.250 |
gered | +4.074 |
OPLE | +4.018 |
Neg logit contributions | |
anon | -4.492 |
Article | -4.264 |
ovarian | -4.223 |
favors | -4.165 |
Moroccan | -4.027 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
acements | +3.656 |
dinand | +3.210 |
ortment | +3.108 |
gered | +2.969 |
oker | +2.751 |
Neg logit contributions | |
anon | -4.433 |
Article | -4.195 |
ovarian | -4.156 |
favors | -4.046 |
Moroccan | -3.983 |
Token | 3 |
Token ID | 513 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
acements | +5.916 |
dinand | +5.388 |
gered | +5.018 |
ortment | +4.978 |
ople | +4.613 |
Neg logit contributions | |
anon | -7.214 |
Article | -6.839 |
ovarian | -6.820 |
favors | -6.668 |
Moroccan | -6.575 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
acements | +3.992 |
dinand | +3.714 |
ortment | +3.491 |
gered | +3.276 |
OPLE | +3.209 |
Neg logit contributions | |
anon | -4.394 |
Article | -4.237 |
ovarian | -4.188 |
favors | -4.144 |
Moroccan | -4.070 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
acements | +2.733 |
dinand | +2.566 |
ortment | +2.416 |
gered | +2.297 |
OPLE | +2.243 |
Neg logit contributions | |
anon | -2.737 |
Article | -2.647 |
ovarian | -2.604 |
favors | -2.567 |
Frag | -2.497 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
acements | +2.900 |
dinand | +2.740 |
ortment | +2.572 |
gered | +2.408 |
OPLE | +2.380 |
Neg logit contributions | |
anon | -3.255 |
Article | -3.136 |
ovarian | -3.065 |
favors | -3.037 |
Moroccan | -2.983 |
Token | 7 |
Token ID | 767 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
acements | +1.599 |
dinand | +1.523 |
ortment | +1.431 |
gered | +1.351 |
OPLE | +1.328 |
Neg logit contributions | |
anon | -1.676 |
Article | -1.621 |
ovarian | -1.580 |
favors | -1.571 |
Frag | -1.527 |
Token | toward |
Token ID | 3812 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
acements | +2.389 |
dinand | +2.280 |
ortment | +2.193 |
gered | +2.083 |
OPLE | +2.032 |
Neg logit contributions | |
anon | -1.917 |
Article | -1.834 |
ovarian | -1.770 |
Frag | -1.720 |
favors | -1.706 |
Token | renewables |
Token ID | 36351 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
anon | +0.303 |
Article | +0.293 |
ovarian | +0.285 |
favors | +0.283 |
Frag | +0.275 |
Neg logit contributions | |
acements | -0.341 |
dinand | -0.327 |
ortment | -0.308 |
gered | -0.293 |
OPLE | -0.288 |
Token | and |
Token ID | 290 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
acements | +1.692 |
dinand | +1.605 |
ortment | +1.529 |
gered | +1.486 |
OPLE | +1.433 |
Neg logit contributions | |
anon | -1.274 |
Article | -1.222 |
ovarian | -1.165 |
Frag | -1.142 |
favors | -1.122 |
Token | away |
Token ID | 1497 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
acements | +2.207 |
dinand | +2.082 |
ortment | +1.990 |
gered | +1.901 |
OPLE | +1.854 |
Neg logit contributions | |
anon | -1.944 |
Article | -1.872 |
ovarian | -1.798 |
favors | -1.765 |
Frag | -1.759 |
Token | from |
Token ID | 422 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
acements | +1.259 |
dinand | +1.180 |
ortment | +1.136 |
gered | +1.091 |
OPLE | +1.059 |
Neg logit contributions | |
anon | -0.917 |
Article | -0.867 |
ovarian | -0.820 |
Frag | -0.812 |
Myst | -0.804 |
Token | fossil |
Token ID | 12584 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
acements | +2.058 |
dinand | +1.974 |
ortment | +1.874 |
gered | +1.820 |
OPLE | +1.775 |
Neg logit contributions | |
anon | -1.336 |
Article | -1.275 |
ovarian | -1.216 |
favors | -1.195 |
Frag | -1.180 |
Token | fuel |
Token ID | 5252 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
acements | +4.952 |
dinand | +4.558 |
gered | +4.105 |
ortment | +4.012 |
OPLE | +3.773 |
Neg logit contributions | |
anon | -8.279 |
Article | -8.157 |
ovarian | -7.720 |
Frag | -7.710 |
Myst | -7.652 |
Token | generation |
Token ID | 5270 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
acements | +3.926 |
dinand | +3.740 |
ortment | +3.453 |
gered | +3.441 |
OPLE | +3.254 |
Neg logit contributions | |
anon | -3.831 |
Article | -3.706 |
ovarian | -3.529 |
Frag | -3.516 |
Myst | -3.444 |
Token | won |
Token ID | 1839 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
acements | +5.752 |
dinand | +5.301 |
gered | +5.069 |
ortment | +5.050 |
OPLE | +4.708 |
Neg logit contributions | |
anon | -4.678 |
Article | -4.544 |
Frag | -4.275 |
ovarian | -4.225 |
Myst | -4.073 |
Token | 't |
Token ID | 470 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
anon | +0.983 |
Article | +0.948 |
ovarian | +0.930 |
favors | +0.922 |
Frag | +0.892 |
Neg logit contributions | |
acements | -1.037 |
dinand | -0.981 |
ortment | -0.931 |
gered | -0.887 |
OPLE | -0.865 |
Token | somehow |
Token ID | 7599 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
acements | +0.299 |
dinand | +0.281 |
ortment | +0.268 |
gered | +0.258 |
OPLE | +0.247 |
Neg logit contributions | |
anon | -0.293 |
Article | -0.286 |
ovarian | -0.277 |
Frag | -0.271 |
favors | -0.271 |
Token | uble |
Token ID | 26664 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
acements | +0.753 |
dinand | +0.710 |
ortment | +0.658 |
gered | +0.617 |
OPLE | +0.596 |
Neg logit contributions | |
anon | -1.065 |
Article | -1.039 |
ovarian | -1.016 |
favors | -1.015 |
Frag | -0.986 |
Token | problem |
Token ID | 1917 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
anon | +0.245 |
Article | +0.234 |
ovarian | +0.225 |
favors | +0.225 |
Frag | +0.220 |
Neg logit contributions | |
acements | -0.318 |
dinand | -0.302 |
ortment | -0.290 |
gered | -0.281 |
OPLE | -0.274 |
Token | ; |
Token ID | 26 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
acements | +1.871 |
dinand | +1.792 |
ortment | +1.710 |
gered | +1.677 |
OPLE | +1.614 |
Neg logit contributions | |
anon | -1.310 |
Article | -1.235 |
ovarian | -1.201 |
favors | -1.169 |
Frag | -1.153 |
Token | to |
Token ID | 284 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
acements | +1.140 |
dinand | +1.092 |
ortment | +1.035 |
gered | +0.989 |
OPLE | +0.977 |
Neg logit contributions | |
anon | -0.914 |
Article | -0.880 |
ovarian | -0.853 |
favors | -0.840 |
Frag | -0.825 |
Token | Obama |
Token ID | 2486 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
acements | +0.335 |
dinand | +0.321 |
ortment | +0.304 |
gered | +0.291 |
OPLE | +0.287 |
Neg logit contributions | |
anon | -0.261 |
Article | -0.252 |
ovarian | -0.244 |
favors | -0.242 |
Frag | -0.236 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
acements | +3.003 |
dinand | +2.891 |
ortment | +2.753 |
gered | +2.657 |
OPLE | +2.637 |
Neg logit contributions | |
anon | -1.849 |
Article | -1.778 |
ovarian | -1.677 |
favors | -1.644 |
Frag | -1.616 |
Token | they |
Token ID | 484 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
acements | +6.511 |
dinand | +5.940 |
ortment | +5.718 |
gered | +5.708 |
OPLE | +5.490 |
Neg logit contributions | |
anon | -6.526 |
Article | -6.310 |
Frag | -6.029 |
ovarian | -6.004 |
favors | -5.791 |
Token | 're |
Token ID | 821 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
acements | +4.191 |
dinand | +3.770 |
ortment | +3.694 |
gered | +3.618 |
esm | +3.275 |
Neg logit contributions | |
anon | -4.613 |
Article | -4.440 |
ovarian | -4.349 |
Frag | -4.332 |
favors | -4.222 |
Token | a |
Token ID | 257 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
acements | +4.133 |
dinand | +3.880 |
ortment | +3.740 |
gered | +3.668 |
OPLE | +3.488 |
Neg logit contributions | |
anon | -3.679 |
Article | -3.514 |
ovarian | -3.372 |
Frag | -3.338 |
favors | -3.318 |
Token | tool |
Token ID | 2891 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
acements | +1.581 |
dinand | +1.505 |
ortment | +1.439 |
gered | +1.401 |
OPLE | +1.346 |
Neg logit contributions | |
anon | -1.267 |
Article | -1.224 |
ovarian | -1.169 |
favors | -1.151 |
Frag | -1.134 |
Token | to |
Token ID | 284 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
acements | +1.166 |
dinand | +1.114 |
ortment | +1.057 |
gered | +1.017 |
OPLE | +0.991 |
Neg logit contributions | |
anon | -0.979 |
Article | -0.940 |
ovarian | -0.913 |
favors | -0.905 |
Frag | -0.882 |
Token | £ |
Token ID | 4248 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
anon | +2.210 |
Article | +2.126 |
ovarian | +2.079 |
favors | +2.072 |
Moroccan | +2.002 |
Neg logit contributions | |
acements | -2.499 |
dinand | -2.413 |
ortment | -2.254 |
gered | -2.140 |
OPLE | -2.124 |
Token | 6 |
Token ID | 21 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
anon | +1.619 |
Article | +1.562 |
favors | +1.508 |
ovarian | +1.501 |
Frag | +1.462 |
Neg logit contributions | |
acements | -1.738 |
dinand | -1.680 |
ortment | -1.568 |
gered | -1.489 |
OPLE | -1.459 |
Token | 19 |
Token ID | 1129 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
anon | +1.275 |
Article | +1.229 |
ovarian | +1.197 |
favors | +1.194 |
Frag | +1.152 |
Neg logit contributions | |
acements | -1.490 |
dinand | -1.428 |
ortment | -1.345 |
gered | -1.278 |
OPLE | -1.256 |
Token | b |
Token ID | 275 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
anon | +1.968 |
Article | +1.899 |
ovarian | +1.857 |
favors | +1.852 |
Frag | +1.781 |
Neg logit contributions | |
acements | -2.580 |
dinand | -2.468 |
ortment | -2.332 |
gered | -2.232 |
OPLE | -2.200 |
Token | & |
Token ID | 1222 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
anon | +2.450 |
Article | +2.362 |
ovarian | +2.293 |
favors | +2.284 |
Frag | +2.202 |
Neg logit contributions | |
acements | -3.536 |
dinand | -3.382 |
ortment | -3.215 |
gered | -3.078 |
OPLE | -3.045 |
Token | b |
Token ID | 275 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
acements | +1.247 |
dinand | +1.196 |
ortment | +1.124 |
gered | +1.064 |
OPLE | +1.037 |
Neg logit contributions | |
anon | -1.246 |
Article | -1.202 |
ovarian | -1.166 |
favors | -1.160 |
Frag | -1.133 |
Token | departing |
Token ID | 37717 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
anon | +5.542 |
Article | +5.346 |
favors | +5.320 |
ovarian | +5.264 |
Moroccan | +5.079 |
Neg logit contributions | |
acements | -8.933 |
dinand | -8.583 |
ortment | -8.088 |
OPLE | -7.799 |
gered | -7.768 |
Token | from |
Token ID | 422 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
acements | +1.557 |
dinand | +1.485 |
ortment | +1.399 |
gered | +1.328 |
OPLE | +1.295 |
Neg logit contributions | |
anon | -1.496 |
Article | -1.450 |
ovarian | -1.405 |
favors | -1.398 |
Frag | -1.359 |
Token | Manchester |
Token ID | 9502 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
acements | +0.836 |
dinand | +0.795 |
ortment | +0.755 |
gered | +0.720 |
OPLE | +0.707 |
Neg logit contributions | |
anon | -0.666 |
Article | -0.643 |
ovarian | -0.618 |
favors | -0.616 |
Frag | -0.599 |
Token | on |
Token ID | 319 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
acements | +1.064 |
dinand | +1.020 |
ortment | +0.953 |
gered | +0.899 |
OPLE | +0.872 |
Neg logit contributions | |
anon | -1.156 |
Article | -1.127 |
ovarian | -1.091 |
favors | -1.089 |
Frag | -1.057 |
Token | December |
Token ID | 3426 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
acements | +1.111 |
dinand | +1.055 |
ortment | +0.989 |
gered | +0.936 |
OPLE | +0.910 |
Neg logit contributions | |
anon | -1.268 |
Article | -1.229 |
ovarian | -1.198 |
favors | -1.195 |
Frag | -1.163 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
anon | +0.506 |
Article | +0.483 |
ovarian | +0.470 |
favors | +0.465 |
Frag | +0.452 |
Neg logit contributions | |
acements | -0.679 |
dinand | -0.652 |
ortment | -0.617 |
gered | -0.592 |
OPLE | -0.580 |
Token | 153 |
Token ID | 21395 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
acements | +0.649 |
dinand | +0.613 |
ortment | +0.583 |
gered | +0.558 |
OPLE | +0.545 |
Neg logit contributions | |
anon | -0.580 |
Article | -0.555 |
ovarian | -0.552 |
favors | -0.548 |
Frag | -0.524 |
Token | ] |
Token ID | 60 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
acements | +3.436 |
dinand | +3.283 |
ortment | +3.097 |
gered | +2.960 |
OPLE | +2.914 |
Neg logit contributions | |
anon | -2.505 |
Article | -2.395 |
ovarian | -2.339 |
favors | -2.319 |
Frag | -2.241 |
Token | Likewise |
Token ID | 22660 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
acements | +0.578 |
dinand | +0.547 |
ortment | +0.518 |
gered | +0.495 |
OPLE | +0.488 |
Neg logit contributions | |
anon | -0.502 |
Article | -0.485 |
ovarian | -0.475 |
favors | -0.471 |
Frag | -0.455 |
Token | , |
Token ID | 11 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
acements | +2.400 |
dinand | +2.300 |
ortment | +2.176 |
gered | +2.109 |
OPLE | +2.090 |
Neg logit contributions | |
anon | -1.452 |
Article | -1.395 |
ovarian | -1.336 |
favors | -1.319 |
Frag | -1.278 |
Token | IGN |
Token ID | 28730 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
anon | +0.237 |
Article | +0.229 |
ovarian | +0.222 |
favors | +0.221 |
Frag | +0.214 |
Neg logit contributions | |
acements | -0.278 |
dinand | -0.264 |
ortment | -0.249 |
gered | -0.238 |
OPLE | -0.235 |
Token | gave |
Token ID | 2921 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
anon | +5.968 |
Article | +5.742 |
favors | +5.572 |
ovarian | +5.356 |
Frag | +5.269 |
Neg logit contributions | |
acements | -8.595 |
dinand | -8.389 |
ortment | -7.829 |
gered | -7.453 |
OPLE | -7.358 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
anon | +2.060 |
Article | +1.989 |
favors | +1.942 |
ovarian | +1.930 |
Myst | +1.862 |
Neg logit contributions | |
acements | -2.560 |
dinand | -2.470 |
ortment | -2.334 |
gered | -2.201 |
OPLE | -2.190 |
Token | game |
Token ID | 983 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
anon | +0.098 |
Article | +0.094 |
ovarian | +0.091 |
favors | +0.090 |
Frag | +0.087 |
Neg logit contributions | |
acements | -0.149 |
dinand | -0.144 |
ortment | -0.136 |
gered | -0.132 |
OPLE | -0.129 |
Token | a |
Token ID | 257 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
acements | +0.140 |
dinand | +0.133 |
ortment | +0.127 |
gered | +0.121 |
OPLE | +0.118 |
Neg logit contributions | |
anon | -0.106 |
Article | -0.102 |
ovarian | -0.099 |
favors | -0.098 |
Frag | -0.095 |
Token | ' |
Token ID | 705 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
anon | +2.159 |
Article | +2.083 |
ovarian | +2.031 |
favors | +2.030 |
Frag | +1.960 |
Neg logit contributions | |
acements | -2.310 |
dinand | -2.226 |
ortment | -2.084 |
gered | -1.970 |
OPLE | -1.951 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
anon | +2.079 |
Article | +2.006 |
favors | +1.915 |
ovarian | +1.907 |
Frag | +1.859 |
Neg logit contributions | |
acements | -3.637 |
dinand | -3.528 |
ortment | -3.358 |
gered | -3.217 |
OPLE | -3.169 |
Token | Size |
Token ID | 10699 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
anon | +0.163 |
Article | +0.157 |
ovarian | +0.154 |
favors | +0.153 |
Moroccan | +0.147 |
Neg logit contributions | |
acements | -0.186 |
dinand | -0.177 |
ortment | -0.167 |
gered | -0.159 |
OPLE | -0.156 |
Token | () |
Token ID | 3419 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
acements | +0.770 |
dinand | +0.728 |
ortment | +0.691 |
gered | +0.662 |
OPLE | +0.645 |
Neg logit contributions | |
anon | -0.660 |
Article | -0.633 |
ovarian | -0.627 |
favors | -0.623 |
Moroccan | -0.597 |
Token | ; |
Token ID | 2162 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
acements | +0.483 |
dinand | +0.464 |
ortment | +0.439 |
gered | +0.419 |
OPLE | +0.412 |
Neg logit contributions | |
anon | -0.369 |
Article | -0.356 |
ovarian | -0.345 |
favors | -0.343 |
Frag | -0.330 |
Token | for |
Token ID | 329 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
acements | +2.760 |
dinand | +2.601 |
ortment | +2.481 |
gered | +2.360 |
OPLE | +2.308 |
Neg logit contributions | |
anon | -2.273 |
Article | -2.190 |
ovarian | -2.117 |
favors | -2.070 |
Moroccan | -2.016 |
Token | ( |
Token ID | 7 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
acements | +0.322 |
dinand | +0.309 |
ortment | +0.292 |
gered | +0.279 |
OPLE | +0.275 |
Neg logit contributions | |
anon | -0.241 |
Article | -0.232 |
ovarian | -0.225 |
favors | -0.224 |
Frag | -0.216 |
Token | size |
Token ID | 2546 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
anon | +5.073 |
Article | +4.889 |
favors | +4.734 |
Frag | +4.665 |
ovarian | +4.540 |
Neg logit contributions | |
acements | -9.020 |
dinand | -8.963 |
ortment | -8.444 |
gered | -7.991 |
OPLE | -7.909 |
Token | _ |
Token ID | 62 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
anon | +3.429 |
Article | +3.281 |
favors | +3.096 |
ovarian | +3.060 |
Frag | +3.000 |
Neg logit contributions | |
acements | -6.748 |
dinand | -6.630 |
ortment | -6.265 |
gered | -5.996 |
OPLE | -5.969 |
Token | t |
Token ID | 83 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
anon | +2.849 |
Article | +2.733 |
favors | +2.636 |
ovarian | +2.619 |
Frag | +2.540 |
Neg logit contributions | |
acements | -3.790 |
dinand | -3.673 |
ortment | -3.454 |
gered | -3.293 |
OPLE | -3.271 |
Token | u |
Token ID | 334 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
anon | +1.510 |
Article | +1.457 |
ovarian | +1.419 |
favors | +1.414 |
Frag | +1.367 |
Neg logit contributions | |
acements | -1.697 |
dinand | -1.626 |
ortment | -1.532 |
gered | -1.455 |
OPLE | -1.430 |
Token | Part |
Token ID | 7841 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
anon | +1.259 |
Article | +1.209 |
ovarian | +1.169 |
favors | +1.166 |
Frag | +1.121 |
Neg logit contributions | |
acements | -1.882 |
dinand | -1.814 |
ortment | -1.720 |
gered | -1.645 |
OPLE | -1.620 |
Token | requests |
Token ID | 7007 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
acements | +1.319 |
dinand | +1.263 |
ortment | +1.191 |
gered | +1.163 |
OPLE | +1.130 |
Neg logit contributions | |
anon | -1.081 |
Article | -1.037 |
ovarian | -1.000 |
favors | -0.980 |
Frag | -0.972 |
Token | for |
Token ID | 329 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
anon | +0.544 |
Article | +0.529 |
ovarian | +0.517 |
favors | +0.517 |
Frag | +0.501 |
Neg logit contributions | |
acements | -0.427 |
dinand | -0.406 |
ortment | -0.377 |
gered | -0.353 |
OPLE | -0.346 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
anon | +0.668 |
Article | +0.639 |
ovarian | +0.618 |
favors | +0.616 |
Frag | +0.589 |
Neg logit contributions | |
acements | -1.105 |
dinand | -1.066 |
ortment | -1.014 |
gered | -0.971 |
OPLE | -0.957 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
anon | +0.934 |
Article | +0.897 |
ovarian | +0.869 |
favors | +0.867 |
Frag | +0.831 |
Neg logit contributions | |
acements | -1.392 |
dinand | -1.340 |
ortment | -1.272 |
gered | -1.213 |
OPLE | -1.199 |
Token | Boh |
Token ID | 44366 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
anon | +0.799 |
Article | +0.764 |
ovarian | +0.736 |
favors | +0.728 |
Frag | +0.711 |
Neg logit contributions | |
acements | -1.083 |
dinand | -1.034 |
ortment | -0.986 |
gered | -0.945 |
OPLE | -0.923 |
Token | oli |
Token ID | 11106 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
anon | +2.195 |
Article | +2.094 |
ovarian | +2.036 |
favors | +2.021 |
Frag | +1.958 |
Neg logit contributions | |
acements | -2.625 |
dinand | -2.511 |
ortment | -2.364 |
gered | -2.273 |
OPLE | -2.235 |
Token | ub |
Token ID | 549 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
anon | +4.119 |
Article | +3.846 |
ovarian | +3.668 |
favors | +3.662 |
Frag | +3.485 |
Neg logit contributions | |
acements | -10.029 |
dinand | -9.857 |
ortment | -9.381 |
OPLE | -9.045 |
gered | -8.989 |
Token | ov |
Token ID | 709 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
anon | +3.054 |
Article | +2.883 |
ovarian | +2.809 |
favors | +2.783 |
Frag | +2.666 |
Neg logit contributions | |
acements | -4.453 |
dinand | -4.325 |
ortment | -4.075 |
OPLE | -3.904 |
gered | -3.886 |
Token | could |
Token ID | 714 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
anon | +0.776 |
Article | +0.745 |
ovarian | +0.723 |
favors | +0.718 |
Frag | +0.691 |
Neg logit contributions | |
acements | -1.141 |
dinand | -1.100 |
ortment | -1.044 |
gered | -0.999 |
OPLE | -0.981 |
Token | not |
Token ID | 407 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
acements | +0.518 |
dinand | +0.496 |
ortment | +0.472 |
gered | +0.447 |
OPLE | +0.437 |
Neg logit contributions | |
anon | -0.437 |
Article | -0.421 |
ovarian | -0.408 |
favors | -0.408 |
Frag | -0.396 |
Token | be |
Token ID | 307 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
anon | +1.970 |
Article | +1.905 |
ovarian | +1.861 |
favors | +1.852 |
Frag | +1.778 |
Neg logit contributions | |
acements | -1.986 |
dinand | -1.920 |
ortment | -1.795 |
gered | -1.688 |
OPLE | -1.674 |
Token | � |
Token ID | 447 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
anon | +0.056 |
Article | +0.054 |
ovarian | +0.054 |
favors | +0.053 |
Frag | +0.052 |
Neg logit contributions | |
acements | -0.043 |
dinand | -0.040 |
ortment | -0.037 |
gered | -0.035 |
OPLE | -0.034 |
Token | � |
Token ID | 247 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
anon | +0.609 |
Article | +0.571 |
ovarian | +0.542 |
favors | +0.539 |
Frag | +0.505 |
Neg logit contributions | |
acements | -1.666 |
dinand | -1.609 |
ortment | -1.546 |
gered | -1.501 |
OPLE | -1.468 |
Token | t |
Token ID | 83 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
acements | +0.864 |
dinand | +0.809 |
ortment | +0.772 |
gered | +0.746 |
OPLE | +0.706 |
Neg logit contributions | |
anon | -0.773 |
Article | -0.754 |
ovarian | -0.741 |
favors | -0.730 |
Moroccan | -0.715 |
Token | take |
Token ID | 1011 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
anon | +1.598 |
Article | +1.539 |
ovarian | +1.511 |
favors | +1.502 |
Frag | +1.444 |
Neg logit contributions | |
acements | -1.894 |
dinand | -1.829 |
ortment | -1.713 |
gered | -1.627 |
OPLE | -1.605 |
Token | my |
Token ID | 616 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
anon | +0.049 |
Article | +0.047 |
ovarian | +0.046 |
favors | +0.046 |
Frag | +0.044 |
Neg logit contributions | |
acements | -0.064 |
dinand | -0.061 |
ortment | -0.058 |
gered | -0.055 |
OPLE | -0.054 |
Token | word |
Token ID | 1573 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
anon | +1.075 |
Article | +1.023 |
ovarian | +0.985 |
favors | +0.980 |
Frag | +0.931 |
Neg logit contributions | |
acements | -2.188 |
dinand | -2.116 |
ortment | -2.021 |
gered | -1.940 |
OPLE | -1.918 |
Token | for |
Token ID | 329 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
Article | +6.693 |
anon | +6.693 |
favors | +6.452 |
ovarian | +6.352 |
prayer | +6.302 |
Neg logit contributions | |
acements | -7.058 |
dinand | -6.711 |
ortment | -6.216 |
OPLE | -6.156 |
gered | -5.785 |
Token | it |
Token ID | 340 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
anon | +3.874 |
Article | +3.821 |
favors | +3.748 |
ovarian | +3.725 |
Myst | +3.542 |
Neg logit contributions | |
acements | -6.103 |
dinand | -5.861 |
ortment | -5.576 |
OPLE | -5.258 |
gered | -5.232 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
anon | +2.742 |
Article | +2.657 |
favors | +2.569 |
ovarian | +2.545 |
Frag | +2.411 |
Neg logit contributions | |
acements | -5.133 |
dinand | -4.954 |
ortment | -4.717 |
gered | -4.506 |
OPLE | -4.502 |
Token | Just |
Token ID | 2329 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
anon | +0.872 |
Article | +0.840 |
ovarian | +0.816 |
favors | +0.813 |
Frag | +0.785 |
Neg logit contributions | |
acements | -1.097 |
dinand | -1.056 |
ortment | -0.995 |
gered | -0.949 |
OPLE | -0.933 |
Token | watch |
Token ID | 2342 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
anon | +0.269 |
Article | +0.258 |
ovarian | +0.251 |
favors | +0.250 |
Frag | +0.243 |
Neg logit contributions | |
acements | -0.314 |
dinand | -0.301 |
ortment | -0.285 |
gered | -0.271 |
OPLE | -0.265 |
Token | that |
Token ID | 326 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
acements | +1.472 |
dinand | +1.415 |
ortment | +1.338 |
gered | +1.311 |
OPLE | +1.260 |
Neg logit contributions | |
anon | -1.088 |
Article | -1.040 |
ovarian | -0.998 |
favors | -0.981 |
Frag | -0.966 |
Token | the |
Token ID | 262 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
acements | +1.884 |
dinand | +1.788 |
ortment | +1.689 |
gered | +1.656 |
OPLE | +1.586 |
Neg logit contributions | |
anon | -1.616 |
Article | -1.550 |
ovarian | -1.489 |
favors | -1.462 |
Frag | -1.451 |
Token | volatility |
Token ID | 30772 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
acements | +0.043 |
dinand | +0.041 |
ortment | +0.039 |
gered | +0.037 |
OPLE | +0.036 |
Neg logit contributions | |
anon | -0.036 |
Article | -0.035 |
ovarian | -0.034 |
favors | -0.033 |
Frag | -0.033 |
Token | is |
Token ID | 318 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
acements | +0.256 |
dinand | +0.244 |
ortment | +0.234 |
gered | +0.227 |
OPLE | +0.219 |
Neg logit contributions | |
anon | -0.193 |
Article | -0.183 |
ovarian | -0.176 |
Frag | -0.173 |
favors | -0.170 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
anon | +0.890 |
Article | +0.859 |
ovarian | +0.836 |
favors | +0.834 |
Frag | +0.803 |
Neg logit contributions | |
acements | -1.082 |
dinand | -1.039 |
ortment | -0.980 |
gered | -0.932 |
OPLE | -0.918 |
Token | result |
Token ID | 1255 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
anon | +0.910 |
Article | +0.874 |
ovarian | +0.838 |
favors | +0.830 |
Frag | +0.807 |
Neg logit contributions | |
acements | -1.280 |
dinand | -1.229 |
ortment | -1.169 |
gered | -1.123 |
OPLE | -1.096 |
Token | of |
Token ID | 286 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
anon | +4.801 |
Article | +4.669 |
favors | +4.653 |
ovarian | +4.633 |
Myst | +4.239 |
Neg logit contributions | |
acements | -9.057 |
dinand | -8.820 |
ortment | -8.253 |
OPLE | -8.036 |
gered | -7.764 |
Token | supply |
Token ID | 5127 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
anon | +3.052 |
Article | +2.961 |
favors | +2.934 |
ovarian | +2.912 |
Moroccan | +2.761 |
Neg logit contributions | |
acements | -4.021 |
dinand | -3.893 |
ortment | -3.673 |
OPLE | -3.450 |
gered | -3.426 |
Token | - |
Token ID | 12 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
anon | +0.091 |
Article | +0.088 |
ovarian | +0.086 |
favors | +0.085 |
Frag | +0.083 |
Neg logit contributions | |
acements | -0.107 |
dinand | -0.103 |
ortment | -0.097 |
gered | -0.092 |
OPLE | -0.090 |
Token | and |
Token ID | 392 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
acements | +1.179 |
dinand | +1.129 |
ortment | +1.056 |
gered | +1.008 |
OPLE | +0.973 |
Neg logit contributions | |
anon | -1.149 |
Article | -1.110 |
ovarian | -1.089 |
favors | -1.078 |
Frag | -1.046 |
Token | - |
Token ID | 12 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
acements | +1.866 |
dinand | +1.744 |
ortment | +1.649 |
gered | +1.563 |
OPLE | +1.500 |
Neg logit contributions | |
anon | -2.211 |
Article | -2.147 |
ovarian | -2.096 |
favors | -2.066 |
Frag | -2.036 |
Token | salaries |
Token ID | 17058 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
acements | +0.224 |
dinand | +0.214 |
ortment | +0.202 |
gered | +0.193 |
OPLE | +0.189 |
Neg logit contributions | |
anon | -0.194 |
Article | -0.185 |
ovarian | -0.180 |
favors | -0.177 |
Frag | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
anon | +0.977 |
Article | +0.937 |
favors | +0.906 |
ovarian | +0.905 |
Frag | +0.861 |
Neg logit contributions | |
acements | -1.672 |
dinand | -1.614 |
ortment | -1.533 |
gered | -1.468 |
OPLE | -1.453 |
Token | upkeep |
Token ID | 47363 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
acements | +2.315 |
dinand | +2.212 |
ortment | +2.091 |
gered | +2.015 |
OPLE | +1.956 |
Neg logit contributions | |
anon | -2.044 |
Article | -1.938 |
ovarian | -1.884 |
Frag | -1.878 |
Myst | -1.807 |
Token | ? |
Token ID | 30 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
anon | +0.278 |
Article | +0.266 |
ovarian | +0.258 |
favors | +0.256 |
Frag | +0.247 |
Neg logit contributions | |
acements | -0.413 |
dinand | -0.397 |
ortment | -0.377 |
gered | -0.361 |
OPLE | -0.354 |
Token | V |
Token ID | 569 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
anon | +2.119 |
Article | +2.046 |
ovarian | +1.981 |
favors | +1.979 |
Frag | +1.908 |
Neg logit contributions | |
acements | -2.691 |
dinand | -2.596 |
ortment | -2.438 |
gered | -2.327 |
OPLE | -2.287 |
Token | orn |
Token ID | 1211 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
acements | +0.369 |
dinand | +0.350 |
ortment | +0.325 |
gered | +0.305 |
OPLE | +0.299 |
Neg logit contributions | |
anon | -0.472 |
Article | -0.459 |
ovarian | -0.449 |
favors | -0.447 |
Frag | -0.435 |
Token | ado |
Token ID | 4533 |
Feature activation | +6.57e-04 |
Pos logit contributions | |
anon | +4.837 |
Article | +4.483 |
ovarian | +4.297 |
favors | +4.278 |
atively | +4.096 |
Neg logit contributions | |
acements | -9.010 |
dinand | -8.805 |
ortment | -8.356 |
OPLE | -8.190 |
gered | -7.957 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
acements | +0.004 |
dinand | +0.004 |
ortment | +0.004 |
gered | +0.004 |
OPLE | +0.004 |
Neg logit contributions | |
anon | -0.004 |
Article | -0.003 |
ovarian | -0.003 |
favors | -0.003 |
Frag | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
acements | +0.804 |
dinand | +0.770 |
ortment | +0.732 |
gered | +0.690 |
OPLE | +0.675 |
Neg logit contributions | |
anon | -0.732 |
Article | -0.702 |
ovarian | -0.685 |
favors | -0.679 |
Frag | -0.659 |
Token | top |
Token ID | 1353 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
acements | +0.454 |
dinand | +0.436 |
ortment | +0.418 |
gered | +0.395 |
OPLE | +0.386 |
Neg logit contributions | |
anon | -0.350 |
Article | -0.333 |
ovarian | -0.323 |
favors | -0.320 |
Frag | -0.312 |
Token | RE |
Token ID | 4526 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
acements | +1.335 |
dinand | +1.278 |
ortment | +1.224 |
gered | +1.159 |
OPLE | +1.128 |
Neg logit contributions | |
anon | -1.143 |
Article | -1.092 |
ovarian | -1.055 |
favors | -1.055 |
Frag | -1.028 |
Token | eligibility |
Token ID | 20069 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
anon | +1.195 |
Article | +1.162 |
ovarian | +1.128 |
favors | +1.126 |
Frag | +1.108 |
Neg logit contributions | |
acements | -0.844 |
dinand | -0.791 |
ortment | -0.739 |
gered | -0.691 |
OPLE | -0.671 |
Token | for |
Token ID | 329 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
acements | +0.201 |
dinand | +0.184 |
ortment | +0.174 |
gered | +0.164 |
OPLE | +0.154 |
Neg logit contributions | |
anon | -0.304 |
Article | -0.297 |
ovarian | -0.290 |
favors | -0.286 |
Frag | -0.283 |
Token | the |
Token ID | 262 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
anon | +1.788 |
Article | +1.730 |
ovarian | +1.682 |
favors | +1.673 |
Frag | +1.627 |
Neg logit contributions | |
acements | -1.890 |
dinand | -1.800 |
ortment | -1.697 |
gered | -1.610 |
OPLE | -1.574 |
Token | award |
Token ID | 5764 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
anon | +2.875 |
Article | +2.758 |
ovarian | +2.676 |
favors | +2.669 |
Frag | +2.550 |
Neg logit contributions | |
acements | -4.486 |
dinand | -4.340 |
ortment | -4.108 |
gered | -3.935 |
OPLE | -3.879 |
Token | , |
Token ID | 11 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
anon | +3.540 |
Article | +3.316 |
favors | +3.279 |
ovarian | +3.231 |
Myst | +3.025 |
Neg logit contributions | |
acements | -7.674 |
dinand | -7.515 |
ortment | -7.130 |
gered | -6.838 |
OPLE | -6.825 |
Token | please |
Token ID | 3387 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
anon | +2.691 |
Article | +2.582 |
ovarian | +2.502 |
favors | +2.492 |
Frag | +2.398 |
Neg logit contributions | |
acements | -3.899 |
dinand | -3.753 |
ortment | -3.560 |
gered | -3.402 |
OPLE | -3.348 |
Token | review |
Token ID | 2423 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
anon | +6.767 |
Article | +6.570 |
ovarian | +6.512 |
favors | +6.426 |
Myst | +6.176 |
Neg logit contributions | |
acements | -7.082 |
dinand | -6.745 |
ortment | -6.275 |
gered | -6.001 |
OPLE | -5.978 |
Token | the |
Token ID | 262 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
anon | +4.551 |
Article | +4.431 |
favors | +4.278 |
ovarian | +4.248 |
Myst | +4.073 |
Neg logit contributions | |
acements | -5.941 |
dinand | -5.760 |
ortment | -5.399 |
gered | -5.216 |
OPLE | -5.096 |
Token | Rules |
Token ID | 14252 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
anon | +2.417 |
Article | +2.327 |
favors | +2.259 |
ovarian | +2.249 |
Myst | +2.149 |
Neg logit contributions | |
acements | -3.299 |
dinand | -3.193 |
ortment | -2.998 |
gered | -2.869 |
OPLE | -2.824 |
Token | , |
Token ID | 11 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
anon | +1.443 |
Article | +1.391 |
ovarian | +1.353 |
favors | +1.348 |
Frag | +1.301 |
Neg logit contributions | |
acements | -1.745 |
dinand | -1.675 |
ortment | -1.581 |
gered | -1.504 |
OPLE | -1.480 |
Token | Regulations |
Token ID | 26108 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
anon | +2.845 |
Article | +2.770 |
ovarian | +2.676 |
favors | +2.670 |
Frag | +2.561 |
Neg logit contributions | |
acements | -3.569 |
dinand | -3.447 |
ortment | -3.226 |
gered | -3.100 |
OPLE | -3.046 |
Token | that |
Token ID | 326 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
acements | +0.849 |
dinand | +0.788 |
ortment | +0.764 |
gered | +0.736 |
esm | +0.699 |
Neg logit contributions | |
anon | -0.656 |
Article | -0.624 |
ovarian | -0.612 |
favors | -0.603 |
Frag | -0.590 |
Token | post |
Token ID | 1281 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
anon | +1.142 |
Article | +1.088 |
ovarian | +1.065 |
favors | +1.061 |
Frag | +1.028 |
Neg logit contributions | |
acements | -1.693 |
dinand | -1.622 |
ortment | -1.554 |
gered | -1.495 |
OPLE | -1.442 |
Token | is |
Token ID | 318 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
acements | +0.422 |
dinand | +0.396 |
ortment | +0.388 |
gered | +0.370 |
esm | +0.352 |
Neg logit contributions | |
anon | -0.285 |
Article | -0.276 |
ovarian | -0.269 |
favors | -0.260 |
Frag | -0.258 |
Token | ready |
Token ID | 3492 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
acements | +0.469 |
dinand | +0.426 |
ortment | +0.424 |
gered | +0.404 |
OPLE | +0.375 |
Neg logit contributions | |
anon | -0.488 |
Article | -0.472 |
ovarian | -0.460 |
Frag | -0.453 |
favors | -0.453 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
acements | +0.187 |
dinand | +0.174 |
ortment | +0.170 |
gered | +0.164 |
esm | +0.158 |
Neg logit contributions | |
anon | -0.118 |
Article | -0.114 |
ovarian | -0.112 |
favors | -0.109 |
Frag | -0.105 |
Token | enter |
Token ID | 3802 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
anon | +1.355 |
Article | +1.295 |
favors | +1.255 |
ovarian | +1.255 |
Frag | +1.213 |
Neg logit contributions | |
acements | -1.900 |
dinand | -1.821 |
ortment | -1.733 |
gered | -1.655 |
OPLE | -1.619 |
Token | your |
Token ID | 534 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
anon | +4.562 |
Article | +4.412 |
favors | +4.345 |
ovarian | +4.318 |
Frag | +3.986 |
Neg logit contributions | |
acements | -9.067 |
dinand | -8.792 |
ortment | -8.367 |
OPLE | -8.085 |
gered | -7.938 |
Token | email |
Token ID | 3053 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
anon | +0.157 |
Article | +0.149 |
favors | +0.142 |
ovarian | +0.142 |
Frag | +0.138 |
Neg logit contributions | |
acements | -0.260 |
dinand | -0.250 |
ortment | -0.238 |
gered | -0.233 |
OPLE | -0.223 |
Token | below |
Token ID | 2174 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
acements | +1.332 |
dinand | +1.258 |
ortment | +1.213 |
gered | +1.158 |
OPLE | +1.124 |
Neg logit contributions | |
anon | -0.975 |
Article | -0.930 |
ovarian | -0.903 |
favors | -0.887 |
Frag | -0.882 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
acements | +0.121 |
dinand | +0.114 |
ortment | +0.110 |
gered | +0.105 |
OPLE | +0.102 |
Neg logit contributions | |
anon | -0.085 |
Article | -0.080 |
ovarian | -0.080 |
favors | -0.079 |
Frag | -0.076 |
Token | Notes |
Token ID | 11822 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
acements | +0.731 |
dinand | +0.700 |
ortment | +0.662 |
gered | +0.630 |
OPLE | +0.618 |
Neg logit contributions | |
anon | -0.623 |
Article | -0.597 |
ovarian | -0.585 |
favors | -0.582 |
Frag | -0.563 |
Token | R |
Token ID | 371 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
anon | +0.787 |
Article | +0.751 |
ovarian | +0.721 |
favors | +0.718 |
Frag | +0.693 |
Neg logit contributions | |
acements | -1.351 |
dinand | -1.301 |
ortment | -1.241 |
gered | -1.190 |
OPLE | -1.174 |
Token | upp |
Token ID | 7211 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
acements | +0.494 |
dinand | +0.462 |
ortment | +0.428 |
gered | +0.396 |
OPLE | +0.384 |
Neg logit contributions | |
anon | -0.761 |
Article | -0.737 |
ovarian | -0.731 |
favors | -0.726 |
Myst | -0.710 |
Token | e |
Token ID | 68 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
acements | +0.751 |
dinand | +0.715 |
ortment | +0.683 |
gered | +0.651 |
OPLE | +0.626 |
Neg logit contributions | |
anon | -0.590 |
Article | -0.569 |
ovarian | -0.561 |
favors | -0.554 |
Myst | -0.536 |
Token | Award |
Token ID | 11289 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
anon | +1.248 |
Article | +1.191 |
ovarian | +1.147 |
favors | +1.142 |
Frag | +1.088 |
Neg logit contributions | |
acements | -2.402 |
dinand | -2.325 |
ortment | -2.215 |
gered | -2.125 |
OPLE | -2.098 |
Token | , |
Token ID | 11 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
anon | +2.400 |
Article | +2.300 |
favors | +2.262 |
ovarian | +2.220 |
Frag | +2.106 |
Neg logit contributions | |
acements | -5.171 |
dinand | -5.017 |
ortment | -4.745 |
gered | -4.573 |
OPLE | -4.544 |
Token | please |
Token ID | 3387 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
anon | +2.144 |
Article | +2.069 |
ovarian | +2.010 |
favors | +2.001 |
Frag | +1.892 |
Neg logit contributions | |
acements | -3.421 |
dinand | -3.285 |
ortment | -3.119 |
gered | -2.990 |
OPLE | -2.950 |
Token | download |
Token ID | 4321 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
anon | +6.448 |
Article | +6.273 |
ovarian | +6.178 |
favors | +6.091 |
prayer | +5.861 |
Neg logit contributions | |
acements | -6.934 |
dinand | -6.632 |
ortment | -6.113 |
gered | -5.914 |
OPLE | -5.842 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
anon | +1.473 |
Article | +1.426 |
favors | +1.382 |
ovarian | +1.381 |
Frag | +1.327 |
Neg logit contributions | |
acements | -1.698 |
dinand | -1.636 |
ortment | -1.539 |
gered | -1.461 |
OPLE | -1.440 |
Token | R |
Token ID | 371 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
anon | +1.077 |
Article | +1.027 |
ovarian | +0.990 |
favors | +0.985 |
Frag | +0.941 |
Neg logit contributions | |
acements | -1.974 |
dinand | -1.905 |
ortment | -1.816 |
gered | -1.743 |
OPLE | -1.720 |
Token | upp |
Token ID | 7211 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
acements | +0.237 |
dinand | +0.221 |
ortment | +0.205 |
gered | +0.189 |
OPLE | +0.184 |
Neg logit contributions | |
anon | -0.364 |
Article | -0.352 |
ovarian | -0.349 |
favors | -0.347 |
Myst | -0.339 |
Token | e |
Token ID | 68 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
acements | +1.735 |
dinand | +1.641 |
ortment | +1.579 |
gered | +1.505 |
esm | +1.447 |
Neg logit contributions | |
anon | -1.431 |
Article | -1.375 |
ovarian | -1.372 |
favors | -1.350 |
Myst | -1.318 |
Token | � |
Token ID | 447 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
acements | +2.138 |
dinand | +2.043 |
ortment | +1.927 |
gered | +1.861 |
OPLE | +1.791 |
Neg logit contributions | |
anon | -1.819 |
Article | -1.770 |
ovarian | -1.702 |
favors | -1.694 |
Frag | -1.657 |
Token | � |
Token ID | 247 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
anon | +0.767 |
Article | +0.718 |
ovarian | +0.682 |
favors | +0.677 |
Frag | +0.632 |
Neg logit contributions | |
acements | -2.217 |
dinand | -2.150 |
ortment | -2.063 |
gered | -1.996 |
OPLE | -1.964 |
Token | ll |
Token ID | 297 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
anon | +0.941 |
Article | +0.913 |
ovarian | +0.892 |
favors | +0.889 |
Frag | +0.863 |
Neg logit contributions | |
acements | -0.816 |
dinand | -0.777 |
ortment | -0.725 |
gered | -0.685 |
OPLE | -0.668 |
Token | take |
Token ID | 1011 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
acements | +1.126 |
dinand | +1.070 |
ortment | +1.020 |
gered | +0.977 |
OPLE | +0.946 |
Neg logit contributions | |
anon | -0.950 |
Article | -0.920 |
ovarian | -0.886 |
favors | -0.883 |
Frag | -0.862 |
Token | your |
Token ID | 534 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
acements | +3.394 |
dinand | +3.238 |
ortment | +3.089 |
gered | +3.029 |
OPLE | +2.875 |
Neg logit contributions | |
anon | -2.829 |
Article | -2.707 |
ovarian | -2.612 |
Frag | -2.595 |
favors | -2.589 |
Token | word |
Token ID | 1573 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
anon | +2.205 |
Article | +2.110 |
ovarian | +2.058 |
favors | +2.052 |
Frag | +1.964 |
Neg logit contributions | |
acements | -2.962 |
dinand | -2.845 |
ortment | -2.699 |
gered | -2.553 |
OPLE | -2.535 |
Token | for |
Token ID | 329 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
anon | +6.472 |
Article | +6.355 |
favors | +6.201 |
ovarian | +6.056 |
prayer | +6.016 |
Neg logit contributions | |
acements | -6.738 |
dinand | -6.395 |
ortment | -6.010 |
OPLE | -5.814 |
gered | -5.672 |
Token | it |
Token ID | 340 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
anon | +4.693 |
favors | +4.588 |
Article | +4.539 |
ovarian | +4.488 |
prayer | +4.364 |
Neg logit contributions | |
acements | -7.780 |
dinand | -7.338 |
ortment | -7.097 |
OPLE | -6.637 |
gered | -6.537 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
anon | +1.850 |
Article | +1.774 |
ovarian | +1.713 |
favors | +1.712 |
Frag | +1.634 |
Neg logit contributions | |
acements | -2.933 |
dinand | -2.820 |
ortment | -2.680 |
gered | -2.564 |
OPLE | -2.536 |
Token | Perhaps |
Token ID | 8673 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
acements | +0.870 |
dinand | +0.828 |
ortment | +0.786 |
gered | +0.746 |
OPLE | +0.734 |
Neg logit contributions | |
anon | -0.777 |
Article | -0.751 |
ovarian | -0.733 |
favors | -0.732 |
Frag | -0.706 |
Token | there |
Token ID | 612 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
acements | +0.483 |
dinand | +0.461 |
ortment | +0.439 |
gered | +0.420 |
OPLE | +0.412 |
Neg logit contributions | |
anon | -0.366 |
Article | -0.353 |
ovarian | -0.340 |
favors | -0.340 |
Frag | -0.330 |
Token | actually |
Token ID | 1682 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
anon | +1.779 |
Article | +1.705 |
favors | +1.659 |
ovarian | +1.657 |
Frag | +1.598 |
Neg logit contributions | |
acements | -2.308 |
dinand | -2.215 |
ortment | -2.095 |
gered | -1.991 |
OPLE | -1.967 |
Token | gets |
Token ID | 3011 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
anon | +0.337 |
Article | +0.323 |
ovarian | +0.313 |
favors | +0.311 |
Frag | +0.299 |
Neg logit contributions | |
acements | -0.502 |
dinand | -0.483 |
ortment | -0.459 |
gered | -0.439 |
OPLE | -0.432 |
Token | loaded |
Token ID | 9639 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
acements | +0.657 |
dinand | +0.626 |
ortment | +0.595 |
gered | +0.571 |
OPLE | +0.554 |
Neg logit contributions | |
anon | -0.532 |
Article | -0.515 |
ovarian | -0.500 |
favors | -0.496 |
Frag | -0.481 |
Token | in |
Token ID | 287 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
acements | +1.299 |
dinand | +1.249 |
ortment | +1.180 |
gered | +1.141 |
OPLE | +1.109 |
Neg logit contributions | |
anon | -0.861 |
Article | -0.837 |
ovarian | -0.808 |
favors | -0.786 |
Frag | -0.771 |
Token | depends |
Token ID | 8338 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
acements | +0.062 |
dinand | +0.059 |
ortment | +0.056 |
gered | +0.053 |
OPLE | +0.052 |
Neg logit contributions | |
anon | -0.051 |
Article | -0.050 |
ovarian | -0.048 |
favors | -0.048 |
Frag | -0.047 |
Token | on |
Token ID | 319 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
anon | +2.960 |
Article | +2.863 |
favors | +2.800 |
ovarian | +2.794 |
Frag | +2.689 |
Neg logit contributions | |
acements | -3.226 |
dinand | -3.054 |
ortment | -2.859 |
gered | -2.708 |
OPLE | -2.705 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
anon | +5.333 |
Article | +4.960 |
ovarian | +4.954 |
favors | +4.954 |
Myst | +4.698 |
Neg logit contributions | |
acements | -7.992 |
dinand | -7.713 |
ortment | -7.175 |
gered | -6.820 |
OPLE | -6.797 |
Token | OS |
Token ID | 7294 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
anon | +2.898 |
Article | +2.778 |
favors | +2.717 |
ovarian | +2.717 |
Frag | +2.599 |
Neg logit contributions | |
acements | -3.509 |
dinand | -3.387 |
ortment | -3.167 |
gered | -3.006 |
OPLE | -2.980 |
Token | p |
Token ID | 279 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
anon | +2.432 |
Article | +2.337 |
ovarian | +2.264 |
favors | +2.260 |
Frag | +2.170 |
Neg logit contributions | |
acements | -3.481 |
dinand | -3.338 |
ortment | -3.162 |
gered | -3.012 |
OPLE | -2.978 |
Token | aging |
Token ID | 3039 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
anon | +1.264 |
Article | +1.220 |
ovarian | +1.188 |
favors | +1.184 |
Frag | +1.147 |
Neg logit contributions | |
acements | -1.358 |
dinand | -1.306 |
ortment | -1.224 |
gered | -1.161 |
OPLE | -1.142 |
Token | if |
Token ID | 611 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
anon | +1.011 |
Article | +0.973 |
ovarian | +0.945 |
favors | +0.942 |
Frag | +0.908 |
Neg logit contributions | |
acements | -1.297 |
dinand | -1.246 |
ortment | -1.178 |
gered | -1.122 |
OPLE | -1.104 |
Token | But |
Token ID | 887 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
anon | +1.319 |
Article | +1.269 |
ovarian | +1.235 |
favors | +1.230 |
Frag | +1.185 |
Neg logit contributions | |
acements | -1.658 |
dinand | -1.589 |
ortment | -1.506 |
gered | -1.433 |
OPLE | -1.411 |
Token | ultimately |
Token ID | 6165 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
anon | +1.505 |
Article | +1.446 |
ovarian | +1.399 |
favors | +1.392 |
Frag | +1.348 |
Neg logit contributions | |
acements | -1.931 |
dinand | -1.851 |
ortment | -1.755 |
gered | -1.674 |
OPLE | -1.646 |
Token | NASA |
Token ID | 8884 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
anon | +0.581 |
Article | +0.553 |
ovarian | +0.530 |
favors | +0.523 |
Frag | +0.510 |
Neg logit contributions | |
acements | -0.831 |
dinand | -0.793 |
ortment | -0.757 |
gered | -0.724 |
OPLE | -0.713 |
Token | doesn |
Token ID | 1595 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
anon | +3.371 |
Article | +3.213 |
favors | +3.191 |
ovarian | +3.131 |
Frag | +2.961 |
Neg logit contributions | |
acements | -5.766 |
dinand | -5.564 |
ortment | -5.291 |
gered | -5.039 |
OPLE | -5.009 |
Token | 't |
Token ID | 470 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
anon | +1.313 |
Article | +1.269 |
ovarian | +1.246 |
favors | +1.237 |
Frag | +1.195 |
Neg logit contributions | |
acements | -1.384 |
dinand | -1.307 |
ortment | -1.242 |
gered | -1.184 |
OPLE | -1.151 |
Token | care |
Token ID | 1337 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
anon | +1.700 |
Article | +1.643 |
ovarian | +1.593 |
favors | +1.582 |
Frag | +1.543 |
Neg logit contributions | |
acements | -1.969 |
dinand | -1.883 |
ortment | -1.781 |
gered | -1.697 |
OPLE | -1.662 |
Token | about |
Token ID | 546 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
anon | +4.891 |
Article | +4.776 |
favors | +4.735 |
ovarian | +4.648 |
Myst | +4.375 |
Neg logit contributions | |
acements | -8.309 |
dinand | -8.060 |
ortment | -7.566 |
OPLE | -7.236 |
gered | -7.189 |
Token | what |
Token ID | 644 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
acements | +0.118 |
dinand | +0.112 |
ortment | +0.107 |
gered | +0.102 |
OPLE | +0.099 |
Neg logit contributions | |
anon | -0.105 |
Article | -0.101 |
ovarian | -0.096 |
favors | -0.095 |
Frag | -0.094 |
Token | he |
Token ID | 339 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
anon | +1.346 |
Article | +1.289 |
ovarian | +1.239 |
favors | +1.227 |
Frag | +1.197 |
Neg logit contributions | |
acements | -1.874 |
dinand | -1.797 |
ortment | -1.711 |
gered | -1.639 |
OPLE | -1.606 |
Token | cares |
Token ID | 16609 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
anon | +0.335 |
Article | +0.324 |
ovarian | +0.307 |
Frag | +0.298 |
favors | +0.296 |
Neg logit contributions | |
acements | -0.574 |
dinand | -0.551 |
ortment | -0.528 |
gered | -0.508 |
OPLE | -0.496 |
Token | about |
Token ID | 546 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
anon | +1.315 |
Article | +1.265 |
ovarian | +1.228 |
favors | +1.224 |
Frag | +1.178 |
Neg logit contributions | |
acements | -1.753 |
dinand | -1.686 |
ortment | -1.595 |
gered | -1.521 |
OPLE | -1.498 |
Token | Offset |
Token ID | 34519 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
anon | +1.228 |
Article | +1.186 |
ovarian | +1.153 |
favors | +1.150 |
Frag | +1.115 |
Neg logit contributions | |
acements | -1.326 |
dinand | -1.272 |
ortment | -1.196 |
gered | -1.135 |
OPLE | -1.115 |
Token | Of |
Token ID | 5189 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
anon | +1.421 |
Article | +1.368 |
ovarian | +1.323 |
favors | +1.319 |
Frag | +1.276 |
Neg logit contributions | |
acements | -1.940 |
dinand | -1.872 |
ortment | -1.770 |
gered | -1.688 |
OPLE | -1.661 |
Token | Position |
Token ID | 26545 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
anon | +2.735 |
Article | +2.653 |
ovarian | +2.493 |
favors | +2.493 |
Frag | +2.481 |
Neg logit contributions | |
acements | -4.237 |
dinand | -4.134 |
ortment | -3.908 |
gered | -3.734 |
OPLE | -3.669 |
Token | ( |
Token ID | 7 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
anon | +2.389 |
Article | +2.306 |
ovarian | +2.208 |
favors | +2.207 |
Frag | +2.150 |
Neg logit contributions | |
acements | -3.420 |
dinand | -3.323 |
ortment | -3.128 |
gered | -2.990 |
OPLE | -2.941 |
Token | r |
Token ID | 374 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
anon | +2.397 |
Article | +2.312 |
favors | +2.228 |
ovarian | +2.228 |
Frag | +2.174 |
Neg logit contributions | |
acements | -3.106 |
dinand | -2.998 |
ortment | -2.834 |
gered | -2.719 |
OPLE | -2.664 |
Token | Position |
Token ID | 26545 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
anon | +1.558 |
Article | +1.493 |
ovarian | +1.336 |
Frag | +1.329 |
favors | +1.328 |
Neg logit contributions | |
acements | -4.947 |
dinand | -4.845 |
ortment | -4.643 |
gered | -4.510 |
OPLE | -4.414 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
Article | +3.918 |
anon | +3.861 |
Frag | +3.545 |
favors | +3.513 |
ovarian | +3.420 |
Neg logit contributions | |
acements | -9.066 |
dinand | -8.980 |
ortment | -8.490 |
gered | -8.278 |
etheless | -8.096 |
Token | ; |
Token ID | 2162 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
acements | +0.119 |
dinand | +0.114 |
ortment | +0.108 |
gered | +0.103 |
OPLE | +0.101 |
Neg logit contributions | |
anon | -0.093 |
Article | -0.090 |
ovarian | -0.087 |
favors | -0.087 |
Frag | -0.084 |
Token | // |
Token ID | 3373 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
acements | +2.309 |
dinand | +2.175 |
ortment | +2.088 |
gered | +1.990 |
OPLE | +1.934 |
Neg logit contributions | |
anon | -1.774 |
Article | -1.703 |
ovarian | -1.656 |
favors | -1.621 |
Moroccan | -1.571 |
Token | Note |
Token ID | 5740 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
acements | +3.431 |
dinand | +3.204 |
ortment | +3.098 |
gered | +2.920 |
OPLE | +2.856 |
Neg logit contributions | |
anon | -2.888 |
Article | -2.794 |
ovarian | -2.746 |
favors | -2.710 |
Moroccan | -2.616 |
Token | that |
Token ID | 326 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
acements | +0.946 |
dinand | +0.907 |
ortment | +0.865 |
gered | +0.827 |
OPLE | +0.815 |
Neg logit contributions | |
anon | -0.623 |
Article | -0.598 |
ovarian | -0.578 |
favors | -0.573 |
Frag | -0.550 |
Token | life |
Token ID | 1204 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
anon | +0.696 |
Article | +0.670 |
favors | +0.642 |
ovarian | +0.641 |
Frag | +0.620 |
Neg logit contributions | |
acements | -1.039 |
dinand | -1.000 |
ortment | -0.949 |
gered | -0.914 |
OPLE | -0.894 |
Token | took |
Token ID | 1718 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
acements | +0.331 |
dinand | +0.313 |
ortment | +0.303 |
gered | +0.293 |
OPLE | +0.284 |
Neg logit contributions | |
anon | -0.230 |
Article | -0.221 |
ovarian | -0.212 |
favors | -0.209 |
Frag | -0.206 |
Token | a |
Token ID | 257 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
anon | +1.136 |
Article | +1.091 |
ovarian | +1.057 |
favors | +1.053 |
Frag | +1.015 |
Neg logit contributions | |
acements | -1.595 |
dinand | -1.535 |
ortment | -1.455 |
gered | -1.391 |
OPLE | -1.368 |
Token | turn |
Token ID | 1210 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
anon | +2.757 |
Article | +2.665 |
ovarian | +2.607 |
favors | +2.587 |
Myst | +2.498 |
Neg logit contributions | |
acements | -3.533 |
dinand | -3.396 |
ortment | -3.204 |
gered | -3.032 |
OPLE | -3.007 |
Token | for |
Token ID | 329 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
anon | +0.829 |
Article | +0.804 |
ovarian | +0.786 |
favors | +0.784 |
Frag | +0.761 |
Neg logit contributions | |
acements | -0.701 |
dinand | -0.667 |
ortment | -0.622 |
gered | -0.585 |
OPLE | -0.573 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
anon | +3.348 |
favors | +3.238 |
Article | +3.218 |
ovarian | +3.165 |
Myst | +3.059 |
Neg logit contributions | |
acements | -4.454 |
dinand | -4.209 |
ortment | -4.049 |
OPLE | -3.813 |
gered | -3.807 |
Token | worse |
Token ID | 4785 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
anon | +6.253 |
favors | +6.090 |
Article | +6.038 |
ovarian | +5.907 |
Myst | +5.720 |
Neg logit contributions | |
acements | -7.012 |
dinand | -6.580 |
ortment | -6.232 |
gered | -5.999 |
OPLE | -5.835 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
anon | +3.925 |
Article | +3.763 |
ovarian | +3.659 |
favors | +3.622 |
Myst | +3.495 |
Neg logit contributions | |
acements | -6.395 |
dinand | -6.189 |
ortment | -5.920 |
gered | -5.586 |
OPLE | -5.555 |
Token | My |
Token ID | 2011 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
anon | +0.151 |
Article | +0.145 |
ovarian | +0.142 |
favors | +0.142 |
Frag | +0.136 |
Neg logit contributions | |
acements | -0.178 |
dinand | -0.169 |
ortment | -0.160 |
gered | -0.153 |
OPLE | -0.151 |
Token | father |
Token ID | 2988 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
anon | +0.129 |
Article | +0.124 |
favors | +0.119 |
ovarian | +0.119 |
Frag | +0.116 |
Neg logit contributions | |
acements | -0.165 |
dinand | -0.158 |
ortment | -0.150 |
gered | -0.144 |
OPLE | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
acements | +1.667 |
dinand | +1.578 |
ortment | +1.502 |
gered | +1.466 |
OPLE | +1.407 |
Neg logit contributions | |
anon | -1.263 |
Article | -1.251 |
ovarian | -1.171 |
Frag | -1.168 |
favors | -1.157 |
Token | { |
Token ID | 1391 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
acements | +3.745 |
dinand | +3.506 |
ortment | +3.349 |
gered | +3.170 |
OPLE | +3.161 |
Neg logit contributions | |
anon | -3.379 |
Article | -3.254 |
ovarian | -3.182 |
favors | -3.103 |
Frag | -3.048 |
Token | vi |
Token ID | 8903 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
anon | +0.227 |
Article | +0.219 |
ovarian | +0.213 |
favors | +0.212 |
Frag | +0.205 |
Neg logit contributions | |
acements | -0.286 |
dinand | -0.274 |
ortment | -0.259 |
gered | -0.247 |
OPLE | -0.243 |
Token | : |
Token ID | 25 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
acements | +2.007 |
dinand | +1.937 |
ortment | +1.848 |
gered | +1.773 |
OPLE | +1.751 |
Neg logit contributions | |
anon | -1.091 |
Article | -1.042 |
ovarian | -1.010 |
favors | -0.992 |
Frag | -0.952 |
Token | | |
Token ID | 91 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
anon | +4.350 |
Article | +4.110 |
favors | +3.984 |
ovarian | +3.918 |
Frag | +3.819 |
Neg logit contributions | |
acements | -6.072 |
dinand | -5.866 |
ortment | -5.564 |
gered | -5.286 |
OPLE | -5.197 |
Token | vim |
Token ID | 31124 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
anon | +0.078 |
Article | +0.075 |
ovarian | +0.073 |
favors | +0.072 |
Frag | +0.069 |
Neg logit contributions | |
acements | -0.106 |
dinand | -0.102 |
ortment | -0.096 |
gered | -0.092 |
OPLE | -0.090 |
Token | : |
Token ID | 25 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
acements | +0.106 |
dinand | +0.100 |
ortment | +0.097 |
gered | +0.093 |
OPLE | +0.090 |
Neg logit contributions | |
anon | -0.060 |
Article | -0.058 |
ovarian | -0.056 |
favors | -0.055 |
Moroccan | -0.053 |
Token | | |
Token ID | 91 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
anon | +5.162 |
Article | +4.869 |
favors | +4.692 |
ovarian | +4.620 |
Frag | +4.481 |
Neg logit contributions | |
acements | -7.931 |
dinand | -7.661 |
ortment | -7.290 |
gered | -6.917 |
OPLE | -6.850 |
Token | ex |
Token ID | 1069 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
anon | +2.810 |
Article | +2.642 |
favors | +2.528 |
ovarian | +2.486 |
Frag | +2.418 |
Neg logit contributions | |
acements | -5.140 |
dinand | -4.994 |
ortment | -4.753 |
gered | -4.512 |
OPLE | -4.505 |
Token | : |
Token ID | 25 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
acements | +1.968 |
dinand | +1.903 |
ortment | +1.815 |
gered | +1.745 |
OPLE | +1.710 |
Neg logit contributions | |
anon | -1.046 |
Article | -1.001 |
ovarian | -0.968 |
favors | -0.955 |
Frag | -0.917 |
Token | } |
Token ID | 92 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
acements | +1.212 |
dinand | +1.154 |
ortment | +1.084 |
gered | +1.024 |
OPLE | +1.006 |
Neg logit contributions | |
anon | -1.279 |
Article | -1.242 |
ovarian | -1.220 |
favors | -1.205 |
Frag | -1.171 |
Token | is |
Token ID | 318 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
acements | +0.559 |
dinand | +0.535 |
ortment | +0.509 |
gered | +0.488 |
OPLE | +0.481 |
Neg logit contributions | |
anon | -0.375 |
Article | -0.359 |
ovarian | -0.352 |
favors | -0.346 |
Frag | -0.332 |
Token | download |
Token ID | 4321 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
anon | +6.448 |
Article | +6.273 |
ovarian | +6.178 |
favors | +6.091 |
prayer | +5.861 |
Neg logit contributions | |
acements | -6.934 |
dinand | -6.632 |
ortment | -6.113 |
gered | -5.914 |
OPLE | -5.842 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
anon | +1.473 |
Article | +1.426 |
favors | +1.382 |
ovarian | +1.381 |
Frag | +1.327 |
Neg logit contributions | |
acements | -1.698 |
dinand | -1.636 |
ortment | -1.539 |
gered | -1.461 |
OPLE | -1.440 |
Token | R |
Token ID | 371 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
anon | +1.077 |
Article | +1.027 |
ovarian | +0.990 |
favors | +0.985 |
Frag | +0.941 |
Neg logit contributions | |
acements | -1.974 |
dinand | -1.905 |
ortment | -1.816 |
gered | -1.743 |
OPLE | -1.720 |
Token | upp |
Token ID | 7211 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
acements | +0.237 |
dinand | +0.221 |
ortment | +0.205 |
gered | +0.189 |
OPLE | +0.184 |
Neg logit contributions | |
anon | -0.364 |
Article | -0.352 |
ovarian | -0.349 |
favors | -0.347 |
Myst | -0.339 |
Token | e |
Token ID | 68 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
acements | +1.735 |
dinand | +1.641 |
ortment | +1.579 |
gered | +1.505 |
esm | +1.447 |
Neg logit contributions | |
anon | -1.431 |
Article | -1.375 |
ovarian | -1.372 |
favors | -1.350 |
Myst | -1.318 |
Token | Award |
Token ID | 11289 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
anon | +2.186 |
Article | +2.116 |
ovarian | +2.011 |
favors | +2.000 |
Frag | +1.914 |
Neg logit contributions | |
acements | -4.378 |
dinand | -4.268 |
ortment | -4.051 |
gered | -3.882 |
OPLE | -3.840 |
Token | Nom |
Token ID | 21198 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
anon | +4.710 |
Article | +4.603 |
favors | +4.402 |
ovarian | +4.386 |
Myst | +4.161 |
Neg logit contributions | |
acements | -8.354 |
dinand | -8.136 |
ortment | -7.613 |
OPLE | -7.385 |
gered | -7.355 |
Token | ination |
Token ID | 1883 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
anon | +0.517 |
Article | +0.500 |
ovarian | +0.491 |
favors | +0.491 |
Frag | +0.474 |
Neg logit contributions | |
acements | -0.431 |
dinand | -0.405 |
ortment | -0.381 |
gered | -0.358 |
OPLE | -0.343 |
Token | Pack |
Token ID | 6400 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
anon | +2.236 |
Article | +2.161 |
ovarian | +2.086 |
favors | +2.084 |
Frag | +2.003 |
Neg logit contributions | |
acements | -3.236 |
dinand | -3.116 |
ortment | -2.936 |
gered | -2.816 |
OPLE | -2.788 |
Token | et |
Token ID | 316 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
anon | +2.228 |
Article | +2.160 |
ovarian | +2.120 |
favors | +2.111 |
Frag | +2.052 |
Neg logit contributions | |
acements | -1.710 |
dinand | -1.625 |
ortment | -1.515 |
gered | -1.415 |
OPLE | -1.379 |
Token | and |
Token ID | 290 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
anon | +2.751 |
Article | +2.637 |
ovarian | +2.530 |
favors | +2.525 |
Frag | +2.420 |
Neg logit contributions | |
acements | -5.012 |
dinand | -4.837 |
ortment | -4.585 |
gered | -4.406 |
OPLE | -4.372 |
Token | with |
Token ID | 351 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
acements | +1.656 |
dinand | +1.582 |
ortment | +1.501 |
gered | +1.421 |
OPLE | +1.389 |
Neg logit contributions | |
anon | -1.471 |
Article | -1.418 |
ovarian | -1.385 |
favors | -1.360 |
Frag | -1.336 |
Token | musical |
Token ID | 10530 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
acements | +1.611 |
dinand | +1.545 |
ortment | +1.455 |
gered | +1.388 |
OPLE | +1.357 |
Neg logit contributions | |
anon | -1.408 |
Article | -1.356 |
ovarian | -1.320 |
favors | -1.305 |
Frag | -1.268 |
Token | intentions |
Token ID | 14953 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
anon | +0.053 |
Article | +0.051 |
ovarian | +0.050 |
favors | +0.049 |
Frag | +0.048 |
Neg logit contributions | |
acements | -0.064 |
dinand | -0.061 |
ortment | -0.058 |
gered | -0.055 |
OPLE | -0.054 |
Token | may |
Token ID | 743 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
anon | +1.117 |
Article | +1.075 |
ovarian | +1.043 |
favors | +1.037 |
Frag | +1.002 |
Neg logit contributions | |
acements | -1.490 |
dinand | -1.430 |
ortment | -1.357 |
gered | -1.294 |
OPLE | -1.271 |
Token | not |
Token ID | 407 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
anon | +3.403 |
Article | +3.275 |
favors | +3.262 |
ovarian | +3.211 |
Frag | +3.059 |
Neg logit contributions | |
acements | -4.248 |
dinand | -4.115 |
ortment | -3.818 |
gered | -3.637 |
OPLE | -3.637 |
Token | reflect |
Token ID | 4079 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
anon | +2.542 |
Article | +2.450 |
favors | +2.415 |
ovarian | +2.395 |
Frag | +2.283 |
Neg logit contributions | |
acements | -2.883 |
dinand | -2.784 |
ortment | -2.595 |
gered | -2.464 |
OPLE | -2.449 |
Token | a |
Token ID | 257 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
anon | +5.474 |
favors | +5.399 |
Article | +5.356 |
ovarian | +5.277 |
Myst | +5.019 |
Neg logit contributions | |
acements | -7.482 |
dinand | -7.226 |
ortment | -6.742 |
OPLE | -6.407 |
gered | -6.396 |
Token | true |
Token ID | 2081 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
anon | +2.744 |
Article | +2.643 |
favors | +2.603 |
ovarian | +2.591 |
Frag | +2.479 |
Neg logit contributions | |
acements | -3.601 |
dinand | -3.471 |
ortment | -3.259 |
gered | -3.110 |
OPLE | -3.063 |
Token | difference |
Token ID | 3580 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
anon | +1.482 |
Article | +1.424 |
ovarian | +1.382 |
favors | +1.378 |
Frag | +1.320 |
Neg logit contributions | |
acements | -2.204 |
dinand | -2.124 |
ortment | -2.011 |
gered | -1.922 |
OPLE | -1.896 |
Token | in |
Token ID | 287 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
anon | +1.520 |
Article | +1.462 |
ovarian | +1.418 |
favors | +1.414 |
Frag | +1.356 |
Neg logit contributions | |
acements | -2.193 |
dinand | -2.111 |
ortment | -1.999 |
gered | -1.911 |
OPLE | -1.883 |
Token | shared |
Token ID | 4888 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
anon | +0.505 |
Article | +0.486 |
ovarian | +0.471 |
favors | +0.469 |
Frag | +0.456 |
Neg logit contributions | |
acements | -0.583 |
dinand | -0.558 |
ortment | -0.529 |
gered | -0.503 |
OPLE | -0.493 |
Token | com |
Token ID | 785 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
acements | +2.329 |
dinand | +2.123 |
ortment | +2.106 |
gered | +1.981 |
esm | +1.928 |
Neg logit contributions | |
anon | -2.491 |
ovarian | -2.468 |
favors | -2.460 |
Article | -2.441 |
Moroccan | -2.353 |
Token | / |
Token ID | 14 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
acements | +0.950 |
dinand | +0.893 |
ortment | +0.861 |
gered | +0.816 |
OPLE | +0.790 |
Neg logit contributions | |
anon | -0.751 |
Article | -0.725 |
ovarian | -0.713 |
favors | -0.710 |
Frag | -0.682 |
Token | iv |
Token ID | 452 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
acements | +0.433 |
dinand | +0.416 |
ortment | +0.393 |
gered | +0.374 |
OPLE | +0.369 |
Neg logit contributions | |
anon | -0.332 |
Article | -0.318 |
favors | -0.313 |
ovarian | -0.312 |
Myst | -0.298 |
Token | xx |
Token ID | 5324 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
acements | +0.669 |
dinand | +0.641 |
ortment | +0.604 |
gered | +0.574 |
OPLE | +0.557 |
Neg logit contributions | |
anon | -0.582 |
Article | -0.563 |
ovarian | -0.550 |
favors | -0.547 |
Frag | -0.529 |
Token | brand |
Token ID | 17938 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
anon | +1.061 |
Article | +1.024 |
ovarian | +0.993 |
favors | +0.989 |
Frag | +0.956 |
Neg logit contributions | |
acements | -1.324 |
dinand | -1.271 |
ortment | -1.201 |
gered | -1.144 |
OPLE | -1.124 |
Token | ? |
Token ID | 30 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
acements | +0.058 |
dinand | +0.056 |
ortment | +0.053 |
gered | +0.050 |
OPLE | +0.049 |
Neg logit contributions | |
anon | -0.048 |
Article | -0.046 |
ovarian | -0.045 |
favors | -0.045 |
Frag | -0.043 |
Token | f |
Token ID | 69 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
anon | +6.276 |
Article | +6.152 |
ovarian | +5.824 |
favors | +5.744 |
Frag | +5.665 |
Neg logit contributions | |
acements | -6.639 |
dinand | -6.559 |
ortment | -6.016 |
OPLE | -5.691 |
gered | -5.634 |
Token | ref |
Token ID | 5420 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
anon | +2.797 |
Article | +2.707 |
ovarian | +2.617 |
favors | +2.609 |
Frag | +2.528 |
Neg logit contributions | |
acements | -3.146 |
dinand | -3.038 |
ortment | -2.845 |
gered | -2.686 |
OPLE | -2.658 |
Token | = |
Token ID | 28 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
acements | +1.655 |
dinand | +1.555 |
ortment | +1.468 |
gered | +1.389 |
OPLE | +1.358 |
Neg logit contributions | |
anon | -1.785 |
Article | -1.702 |
favors | -1.679 |
ovarian | -1.679 |
Myst | -1.620 |
Token | ts |
Token ID | 912 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
anon | +2.074 |
Article | +1.984 |
ovarian | +1.884 |
favors | +1.861 |
Frag | +1.807 |
Neg logit contributions | |
acements | -3.603 |
dinand | -3.479 |
ortment | -3.326 |
gered | -3.165 |
OPLE | -3.142 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
anon | +1.118 |
Article | +1.082 |
ovarian | +1.047 |
favors | +1.044 |
Frag | +1.009 |
Neg logit contributions | |
acements | -1.338 |
dinand | -1.285 |
ortment | -1.211 |
gered | -1.154 |
OPLE | -1.134 |
Token | the |
Token ID | 262 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
anon | +1.121 |
Article | +1.082 |
favors | +1.056 |
ovarian | +1.056 |
Frag | +1.015 |
Neg logit contributions | |
acements | -1.299 |
dinand | -1.248 |
ortment | -1.176 |
gered | -1.118 |
OPLE | -1.102 |
Token | Sh |
Token ID | 911 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
anon | +0.364 |
Article | +0.349 |
ovarian | +0.337 |
favors | +0.335 |
Frag | +0.323 |
Neg logit contributions | |
acements | -0.562 |
dinand | -0.540 |
ortment | -0.514 |
gered | -0.492 |
OPLE | -0.484 |
Token | river |
Token ID | 38291 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
acements | +0.945 |
dinand | +0.893 |
ortment | +0.835 |
gered | +0.791 |
OPLE | +0.742 |
Neg logit contributions | |
anon | -1.203 |
Article | -1.166 |
ovarian | -1.148 |
favors | -1.146 |
Myst | -1.116 |
Token | Award |
Token ID | 11289 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
anon | +0.854 |
Article | +0.813 |
ovarian | +0.784 |
favors | +0.780 |
Frag | +0.743 |
Neg logit contributions | |
acements | -1.666 |
dinand | -1.615 |
ortment | -1.538 |
gered | -1.477 |
OPLE | -1.460 |
Token | , |
Token ID | 11 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
anon | +0.640 |
Article | +0.612 |
ovarian | +0.591 |
favors | +0.588 |
Frag | +0.563 |
Neg logit contributions | |
acements | -1.098 |
dinand | -1.060 |
ortment | -1.008 |
gered | -0.967 |
OPLE | -0.953 |
Token | please |
Token ID | 3387 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
anon | +1.701 |
Article | +1.637 |
ovarian | +1.589 |
favors | +1.581 |
Frag | +1.505 |
Neg logit contributions | |
acements | -2.634 |
dinand | -2.530 |
ortment | -2.403 |
gered | -2.302 |
OPLE | -2.266 |
Token | download |
Token ID | 4321 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
anon | +6.258 |
Article | +6.069 |
ovarian | +5.991 |
favors | +5.884 |
Myst | +5.698 |
Neg logit contributions | |
acements | -6.679 |
dinand | -6.326 |
ortment | -5.868 |
gered | -5.668 |
OPLE | -5.570 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
anon | +1.362 |
Article | +1.319 |
favors | +1.278 |
ovarian | +1.276 |
Frag | +1.227 |
Neg logit contributions | |
acements | -1.573 |
dinand | -1.513 |
ortment | -1.420 |
gered | -1.352 |
OPLE | -1.333 |
Token | Sh |
Token ID | 911 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
anon | +0.746 |
Article | +0.715 |
ovarian | +0.694 |
favors | +0.690 |
Frag | +0.664 |
Neg logit contributions | |
acements | -1.098 |
dinand | -1.055 |
ortment | -1.003 |
gered | -0.958 |
OPLE | -0.944 |
Token | river |
Token ID | 38291 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
acements | +0.758 |
dinand | +0.717 |
ortment | +0.671 |
gered | +0.633 |
OPLE | +0.602 |
Neg logit contributions | |
anon | -0.944 |
Article | -0.913 |
favors | -0.897 |
ovarian | -0.897 |
Myst | -0.872 |
Token | Award |
Token ID | 11289 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
anon | +1.648 |
Article | +1.579 |
ovarian | +1.511 |
favors | +1.501 |
Frag | +1.432 |
Neg logit contributions | |
acements | -3.321 |
dinand | -3.227 |
ortment | -3.065 |
gered | -2.952 |
OPLE | -2.919 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
anon | +1.704 |
Article | +1.636 |
ovarian | +1.593 |
favors | +1.588 |
Frag | +1.524 |
Neg logit contributions | |
acements | -2.254 |
dinand | -2.166 |
ortment | -2.049 |
gered | -1.958 |
OPLE | -1.925 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
anon | +0.857 |
Article | +0.822 |
ovarian | +0.793 |
favors | +0.790 |
Frag | +0.757 |
Neg logit contributions | |
acements | -1.447 |
dinand | -1.395 |
ortment | -1.327 |
gered | -1.270 |
OPLE | -1.254 |
Token | return |
Token ID | 1441 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
anon | +0.547 |
Article | +0.526 |
ovarian | +0.511 |
favors | +0.509 |
Frag | +0.491 |
Neg logit contributions | |
acements | -0.706 |
dinand | -0.679 |
ortment | -0.642 |
gered | -0.611 |
OPLE | -0.602 |
Token | space |
Token ID | 2272 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
acements | +3.075 |
dinand | +2.841 |
ortment | +2.762 |
gered | +2.615 |
OPLE | +2.591 |
Neg logit contributions | |
anon | -2.700 |
Article | -2.530 |
ovarian | -2.473 |
favors | -2.467 |
Frag | -2.411 |
Token | ; |
Token ID | 26 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
anon | +1.202 |
Article | +1.149 |
ovarian | +1.111 |
favors | +1.106 |
Frag | +1.059 |
Neg logit contributions | |
acements | -2.004 |
dinand | -1.933 |
ortment | -1.839 |
gered | -1.762 |
OPLE | -1.737 |
Token | // |
Token ID | 3373 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
acements | +1.676 |
dinand | +1.572 |
ortment | +1.503 |
gered | +1.424 |
OPLE | +1.390 |
Neg logit contributions | |
anon | -1.632 |
Article | -1.572 |
ovarian | -1.523 |
favors | -1.511 |
Frag | -1.477 |
Token | 4 |
Token ID | 604 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
acements | +4.639 |
dinand | +4.284 |
ortment | +4.117 |
gered | +3.766 |
OPLE | +3.711 |
Neg logit contributions | |
anon | -5.647 |
Article | -5.417 |
favors | -5.383 |
ovarian | -5.319 |
Moroccan | -5.246 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
acements | +3.948 |
dinand | +3.533 |
ortment | +3.480 |
gered | +3.384 |
esm | +3.253 |
Neg logit contributions | |
anon | -3.288 |
ovarian | -3.173 |
Article | -3.148 |
favors | -3.083 |
Moroccan | -3.016 |
Token | Rec |
Token ID | 3311 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
anon | +0.105 |
Article | +0.101 |
ovarian | +0.098 |
favors | +0.098 |
Frag | +0.094 |
Neg logit contributions | |
acements | -0.122 |
dinand | -0.116 |
ortment | -0.111 |
gered | -0.105 |
OPLE | -0.103 |
Token | urs |
Token ID | 1834 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
acements | +0.722 |
dinand | +0.682 |
ortment | +0.636 |
gered | +0.604 |
OPLE | +0.585 |
Neg logit contributions | |
anon | -0.684 |
Article | -0.677 |
ovarian | -0.661 |
favors | -0.660 |
Moroccan | -0.639 |
Token | ively |
Token ID | 2280 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
anon | +0.296 |
Article | +0.282 |
favors | +0.272 |
ovarian | +0.272 |
Frag | +0.260 |
Neg logit contributions | |
acements | -0.502 |
dinand | -0.484 |
ortment | -0.462 |
gered | -0.446 |
OPLE | -0.436 |
Token | parts |
Token ID | 3354 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
acements | +2.375 |
dinand | +2.262 |
ortment | +2.168 |
gered | +2.112 |
OPLE | +2.021 |
Neg logit contributions | |
anon | -1.822 |
Article | -1.731 |
ovarian | -1.676 |
favors | -1.669 |
Frag | -1.619 |
Token | of |
Token ID | 286 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
acements | +1.089 |
dinand | +1.046 |
ortment | +0.989 |
gered | +0.944 |
OPLE | +0.934 |
Neg logit contributions | |
anon | -0.797 |
Article | -0.759 |
ovarian | -0.744 |
favors | -0.737 |
Frag | -0.707 |
Token | this |
Token ID | 428 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
acements | +1.355 |
dinand | +1.303 |
ortment | +1.227 |
gered | +1.170 |
OPLE | +1.143 |
Neg logit contributions | |
anon | -1.121 |
Article | -1.071 |
ovarian | -1.054 |
favors | -1.042 |
Frag | -1.011 |
Token | blog |
Token ID | 4130 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
acements | +1.436 |
dinand | +1.379 |
ortment | +1.317 |
gered | +1.260 |
OPLE | +1.221 |
Neg logit contributions | |
anon | -1.103 |
Article | -1.044 |
ovarian | -1.029 |
favors | -1.024 |
Frag | -0.977 |
Token | post |
Token ID | 1281 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
acements | +2.661 |
dinand | +2.566 |
ortment | +2.432 |
gered | +2.340 |
OPLE | +2.274 |
Neg logit contributions | |
anon | -2.002 |
Article | -1.891 |
ovarian | -1.886 |
favors | -1.880 |
Moroccan | -1.792 |
Token | , |
Token ID | 11 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
acements | +2.707 |
dinand | +2.610 |
ortment | +2.463 |
gered | +2.362 |
OPLE | +2.342 |
Neg logit contributions | |
anon | -1.818 |
Article | -1.719 |
ovarian | -1.704 |
favors | -1.678 |
Moroccan | -1.600 |
Token | I |
Token ID | 314 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
acements | +5.372 |
dinand | +5.128 |
ortment | +4.775 |
gered | +4.605 |
OPLE | +4.543 |
Neg logit contributions | |
anon | -4.541 |
Article | -4.278 |
ovarian | -4.240 |
favors | -4.167 |
Frag | -4.048 |
Token | will |
Token ID | 481 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
acements | +3.952 |
dinand | +3.626 |
ortment | +3.516 |
gered | +3.358 |
OPLE | +3.189 |
Neg logit contributions | |
anon | -3.771 |
Article | -3.703 |
ovarian | -3.541 |
Frag | -3.533 |
favors | -3.457 |
Token | go |
Token ID | 467 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
acements | +1.684 |
dinand | +1.585 |
ortment | +1.521 |
gered | +1.443 |
OPLE | +1.400 |
Neg logit contributions | |
anon | -1.566 |
Article | -1.529 |
ovarian | -1.470 |
favors | -1.464 |
Frag | -1.446 |
Token | into |
Token ID | 656 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
acements | +2.022 |
dinand | +1.932 |
ortment | +1.833 |
gered | +1.752 |
OPLE | +1.708 |
Neg logit contributions | |
anon | -1.611 |
Article | -1.547 |
favors | -1.496 |
ovarian | -1.494 |
Frag | -1.454 |
Token | the |
Token ID | 262 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
acements | +2.470 |
dinand | +2.374 |
ortment | +2.234 |
gered | +2.138 |
OPLE | +2.074 |
Neg logit contributions | |
anon | -2.167 |
Article | -2.098 |
ovarian | -2.032 |
favors | -2.012 |
Frag | -1.986 |
Token | assin |
Token ID | 44961 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
anon | +0.298 |
Article | +0.290 |
favors | +0.283 |
ovarian | +0.282 |
Frag | +0.274 |
Neg logit contributions | |
acements | -0.249 |
dinand | -0.235 |
ortment | -0.224 |
gered | -0.207 |
OPLE | -0.201 |
Token | � |
Token ID | 447 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
anon | +0.759 |
Article | +0.725 |
ovarian | +0.698 |
favors | +0.696 |
Frag | +0.664 |
Neg logit contributions | |
acements | -1.371 |
dinand | -1.324 |
ortment | -1.261 |
gered | -1.210 |
OPLE | -1.193 |
Token | � |
Token ID | 247 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
acements | +0.643 |
dinand | +0.608 |
ortment | +0.578 |
gered | +0.551 |
OPLE | +0.539 |
Neg logit contributions | |
anon | -0.597 |
Article | -0.577 |
ovarian | -0.562 |
favors | -0.559 |
Frag | -0.541 |
Token | s |
Token ID | 82 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
anon | +1.064 |
Article | +1.027 |
ovarian | +0.999 |
favors | +0.996 |
Frag | +0.962 |
Neg logit contributions | |
acements | -1.227 |
dinand | -1.177 |
ortment | -1.110 |
gered | -1.054 |
OPLE | -1.036 |
Token | Creed |
Token ID | 24299 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
anon | +1.017 |
Article | +0.980 |
ovarian | +0.952 |
favors | +0.949 |
Frag | +0.916 |
Neg logit contributions | |
acements | -1.234 |
dinand | -1.184 |
ortment | -1.118 |
gered | -1.064 |
OPLE | -1.046 |
Token | ® |
Token ID | 7461 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
acements | +2.196 |
dinand | +2.109 |
ortment | +2.008 |
gered | +1.904 |
OPLE | +1.861 |
Neg logit contributions | |
anon | -1.841 |
Article | -1.789 |
favors | -1.740 |
ovarian | -1.734 |
Frag | -1.667 |
Token | Liberation |
Token ID | 29235 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
acements | +5.306 |
dinand | +5.264 |
ortment | +4.915 |
gered | +4.709 |
OPLE | +4.590 |
Neg logit contributions | |
anon | -4.318 |
Article | -4.184 |
favors | -4.065 |
ovarian | -4.041 |
Frag | -3.893 |
Token | HD |
Token ID | 5572 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
acements | +2.765 |
dinand | +2.619 |
ortment | +2.548 |
gered | +2.364 |
OPLE | +2.333 |
Neg logit contributions | |
anon | -2.285 |
Article | -2.204 |
favors | -2.159 |
ovarian | -2.145 |
Frag | -2.067 |
Token | , |
Token ID | 11 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
acements | +0.303 |
dinand | +0.290 |
ortment | +0.276 |
gered | +0.262 |
OPLE | +0.257 |
Neg logit contributions | |
anon | -0.243 |
Article | -0.234 |
ovarian | -0.228 |
favors | -0.228 |
Frag | -0.220 |
Token | is |
Token ID | 318 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
acements | +0.450 |
dinand | +0.433 |
ortment | +0.410 |
gered | +0.390 |
OPLE | +0.382 |
Neg logit contributions | |
anon | -0.381 |
Article | -0.366 |
ovarian | -0.356 |
favors | -0.355 |
Frag | -0.343 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
acements | +0.650 |
dinand | +0.622 |
ortment | +0.589 |
gered | +0.561 |
OPLE | +0.547 |
Neg logit contributions | |
anon | -0.574 |
Article | -0.550 |
ovarian | -0.533 |
favors | -0.532 |
Frag | -0.515 |
Token | & |
Token ID | 1222 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
acements | +0.208 |
dinand | +0.199 |
ortment | +0.188 |
gered | +0.179 |
OPLE | +0.176 |
Neg logit contributions | |
anon | -0.169 |
Article | -0.163 |
ovarian | -0.158 |
favors | -0.158 |
Frag | -0.152 |
Token | Danny |
Token ID | 15105 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
anon | +2.243 |
Article | +2.151 |
ovarian | +2.096 |
favors | +2.089 |
Myst | +2.016 |
Neg logit contributions | |
acements | -2.884 |
dinand | -2.782 |
ortment | -2.621 |
gered | -2.495 |
OPLE | -2.465 |
Token | Fight |
Token ID | 10480 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
anon | +1.310 |
Article | +1.257 |
ovarian | +1.224 |
favors | +1.221 |
Frag | +1.179 |
Neg logit contributions | |
acements | -1.583 |
dinand | -1.534 |
ortment | -1.438 |
gered | -1.363 |
OPLE | -1.352 |
Token | With |
Token ID | 2080 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
acements | +2.621 |
dinand | +2.467 |
ortment | +2.345 |
gered | +2.256 |
OPLE | +2.174 |
Neg logit contributions | |
anon | -2.321 |
Article | -2.249 |
ovarian | -2.193 |
favors | -2.178 |
Frag | -2.094 |
Token | Each |
Token ID | 5501 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
anon | +0.672 |
Article | +0.648 |
ovarian | +0.629 |
favors | +0.627 |
Frag | +0.604 |
Neg logit contributions | |
acements | -0.844 |
dinand | -0.809 |
ortment | -0.766 |
gered | -0.730 |
OPLE | -0.717 |
Token | other |
Token ID | 847 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
anon | +0.658 |
Article | +0.637 |
ovarian | +0.623 |
favors | +0.619 |
Frag | +0.608 |
Neg logit contributions | |
acements | -0.461 |
dinand | -0.439 |
ortment | -0.400 |
gered | -0.375 |
OPLE | -0.370 |
Token | 200 |
Token ID | 939 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
acements | +5.358 |
dinand | +4.996 |
ortment | +4.710 |
gered | +4.536 |
OPLE | +4.303 |
Neg logit contributions | |
anon | -5.511 |
Article | -5.407 |
favors | -5.268 |
ovarian | -5.263 |
Frag | -5.091 |
Token | 80 |
Token ID | 1795 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
acements | +2.869 |
dinand | +2.535 |
ortment | +2.397 |
gered | +2.141 |
OPLE | +2.093 |
Neg logit contributions | |
anon | -6.217 |
Article | -6.082 |
ovarian | -5.994 |
favors | -5.930 |
Frag | -5.889 |
Token | 205 |
Token ID | 21261 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
acements | +1.479 |
dinand | +1.344 |
ortment | +1.291 |
gered | +1.216 |
OPLE | +1.183 |
Neg logit contributions | |
anon | -1.980 |
ovarian | -1.940 |
Article | -1.918 |
favors | -1.916 |
Myst | -1.872 |
Token | O |
Token ID | 440 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
acements | +0.914 |
dinand | +0.852 |
ortment | +0.834 |
gered | +0.792 |
OPLE | +0.776 |
Neg logit contributions | |
anon | -0.733 |
Article | -0.711 |
favors | -0.686 |
ovarian | -0.683 |
Frag | -0.662 |
Token | & |
Token ID | 5 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
anon | +0.016 |
Article | +0.015 |
ovarian | +0.015 |
favors | +0.015 |
Myst | +0.015 |
Neg logit contributions | |
acements | -0.013 |
dinand | -0.012 |
ortment | -0.011 |
gered | -0.011 |
OPLE | -0.010 |
Token | making |
Token ID | 1642 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
acements | +1.020 |
dinand | +0.953 |
ortment | +0.896 |
gered | +0.881 |
OPLE | +0.850 |
Neg logit contributions | |
anon | -0.942 |
Article | -0.908 |
ovarian | -0.861 |
Frag | -0.854 |
favors | -0.851 |
Token | a |
Token ID | 257 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
anon | +0.626 |
Article | +0.603 |
ovarian | +0.584 |
favors | +0.580 |
Frag | +0.563 |
Neg logit contributions | |
acements | -0.776 |
dinand | -0.740 |
ortment | -0.701 |
gered | -0.672 |
OPLE | -0.654 |
Token | single |
Token ID | 2060 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
acements | +2.253 |
dinand | +2.097 |
ortment | +1.992 |
gered | +1.929 |
OPLE | +1.845 |
Neg logit contributions | |
anon | -1.926 |
Article | -1.835 |
favors | -1.759 |
ovarian | -1.744 |
Frag | -1.678 |
Token | first |
Token ID | 717 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
acements | +1.708 |
dinand | +1.582 |
ortment | +1.498 |
gered | +1.428 |
OPLE | +1.340 |
Neg logit contributions | |
anon | -1.938 |
Article | -1.860 |
favors | -1.816 |
ovarian | -1.796 |
Frag | -1.747 |
Token | - |
Token ID | 12 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
acements | +0.114 |
dinand | +0.109 |
ortment | +0.103 |
gered | +0.098 |
OPLE | +0.095 |
Neg logit contributions | |
anon | -0.098 |
Article | -0.093 |
ovarian | -0.091 |
favors | -0.091 |
Frag | -0.088 |
Token | team |
Token ID | 15097 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
acements | +0.444 |
dinand | +0.425 |
ortment | +0.406 |
gered | +0.390 |
OPLE | +0.378 |
Neg logit contributions | |
anon | -0.244 |
Article | -0.229 |
ovarian | -0.226 |
favors | -0.225 |
Moroccan | -0.213 |
Token | appearance |
Token ID | 5585 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
acements | +4.780 |
dinand | +4.476 |
ortment | +4.159 |
gered | +3.964 |
OPLE | +3.600 |
Neg logit contributions | |
anon | -6.659 |
Article | -6.417 |
favors | -6.307 |
ovarian | -6.231 |
Niet | -6.103 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
acements | +0.426 |
dinand | +0.405 |
ortment | +0.384 |
gered | +0.369 |
OPLE | +0.356 |
Neg logit contributions | |
anon | -0.330 |
Article | -0.315 |
ovarian | -0.307 |
favors | -0.304 |
Frag | -0.296 |
Token | A |
Token ID | 317 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
acements | +0.132 |
dinand | +0.125 |
ortment | +0.119 |
gered | +0.113 |
OPLE | +0.111 |
Neg logit contributions | |
anon | -0.111 |
Article | -0.106 |
ovarian | -0.105 |
favors | -0.104 |
Frag | -0.100 |
Token | possible |
Token ID | 1744 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
acements | +0.096 |
dinand | +0.092 |
ortment | +0.087 |
gered | +0.084 |
OPLE | +0.081 |
Neg logit contributions | |
anon | -0.081 |
Article | -0.078 |
favors | -0.076 |
ovarian | -0.075 |
Frag | -0.073 |
Token | move |
Token ID | 1445 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
acements | +2.150 |
dinand | +2.030 |
ortment | +1.920 |
gered | +1.893 |
OPLE | +1.791 |
Neg logit contributions | |
anon | -1.874 |
Article | -1.804 |
favors | -1.733 |
ovarian | -1.696 |
Frag | -1.696 |
Token | avoided |
Token ID | 13941 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
anon | +0.303 |
Article | +0.292 |
ovarian | +0.282 |
favors | +0.281 |
Frag | +0.274 |
Neg logit contributions | |
acements | -0.338 |
dinand | -0.321 |
ortment | -0.304 |
gered | -0.291 |
OPLE | -0.283 |
Token | . |
Token ID | 13 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
acements | +1.316 |
dinand | +1.268 |
ortment | +1.187 |
gered | +1.161 |
OPLE | +1.112 |
Neg logit contributions | |
anon | -0.926 |
Article | -0.880 |
ovarian | -0.848 |
favors | -0.835 |
Frag | -0.817 |
Token | Security |
Token ID | 4765 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
acements | +0.237 |
dinand | +0.225 |
ortment | +0.215 |
gered | +0.204 |
OPLE | +0.201 |
Neg logit contributions | |
anon | -0.192 |
Article | -0.184 |
ovarian | -0.180 |
favors | -0.179 |
Frag | -0.172 |
Token | forces |
Token ID | 3386 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
anon | +1.003 |
Article | +0.958 |
ovarian | +0.934 |
favors | +0.921 |
Frag | +0.901 |
Neg logit contributions | |
acements | -1.281 |
dinand | -1.227 |
ortment | -1.163 |
gered | -1.108 |
OPLE | -1.089 |
Token | , |
Token ID | 11 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
anon | +0.519 |
Article | +0.501 |
ovarian | +0.485 |
favors | +0.481 |
Frag | +0.469 |
Neg logit contributions | |
acements | -0.648 |
dinand | -0.614 |
ortment | -0.585 |
gered | -0.557 |
OPLE | -0.548 |
Token | fearing |
Token ID | 33188 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
acements | +1.602 |
dinand | +1.525 |
ortment | +1.441 |
gered | +1.376 |
OPLE | +1.344 |
Neg logit contributions | |
anon | -1.474 |
Article | -1.423 |
ovarian | -1.378 |
favors | -1.365 |
Frag | -1.338 |
Token | worse |
Token ID | 4785 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
acements | +1.794 |
dinand | +1.691 |
ortment | +1.600 |
gered | +1.565 |
OPLE | +1.502 |
Neg logit contributions | |
anon | -1.561 |
Article | -1.488 |
ovarian | -1.419 |
favors | -1.415 |
Frag | -1.404 |
Token | violence |
Token ID | 3685 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
acements | +1.354 |
dinand | +1.282 |
ortment | +1.215 |
gered | +1.181 |
OPLE | +1.148 |
Neg logit contributions | |
anon | -1.017 |
Article | -0.978 |
ovarian | -0.924 |
favors | -0.923 |
Frag | -0.906 |
Token | if |
Token ID | 611 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
acements | +1.970 |
dinand | +1.839 |
ortment | +1.754 |
gered | +1.736 |
OPLE | +1.650 |
Neg logit contributions | |
anon | -1.387 |
Article | -1.335 |
ovarian | -1.261 |
favors | -1.237 |
Frag | -1.223 |
Token | there |
Token ID | 612 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
anon | +0.192 |
Article | +0.184 |
ovarian | +0.179 |
favors | +0.178 |
Frag | +0.172 |
Neg logit contributions | |
acements | -0.232 |
dinand | -0.222 |
ortment | -0.210 |
gered | -0.201 |
OPLE | -0.197 |
Token | is |
Token ID | 318 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
anon | +1.301 |
Article | +1.250 |
ovarian | +1.212 |
favors | +1.207 |
Frag | +1.162 |
Neg logit contributions | |
acements | -1.837 |
dinand | -1.768 |
ortment | -1.676 |
gered | -1.600 |
OPLE | -1.575 |
Token | P |
Token ID | 350 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
anon | +0.506 |
Article | +0.488 |
ovarian | +0.474 |
favors | +0.471 |
Frag | +0.455 |
Neg logit contributions | |
acements | -0.663 |
dinand | -0.635 |
ortment | -0.600 |
gered | -0.575 |
OPLE | -0.564 |
Token | 217 |
Token ID | 24591 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
acements | +1.340 |
dinand | +1.275 |
ortment | +1.195 |
gered | +1.147 |
OPLE | +1.129 |
Neg logit contributions | |
anon | -1.143 |
Article | -1.092 |
favors | -1.083 |
ovarian | -1.077 |
Frag | -1.035 |
Token | Gibson |
Token ID | 20400 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
anon | +0.062 |
Article | +0.059 |
ovarian | +0.058 |
favors | +0.057 |
Frag | +0.055 |
Neg logit contributions | |
acements | -0.081 |
dinand | -0.078 |
ortment | -0.073 |
gered | -0.070 |
OPLE | -0.069 |
Token | came |
Token ID | 1625 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
anon | +0.454 |
Article | +0.437 |
ovarian | +0.425 |
favors | +0.420 |
Frag | +0.408 |
Neg logit contributions | |
acements | -0.603 |
dinand | -0.578 |
ortment | -0.545 |
gered | -0.525 |
OPLE | -0.512 |
Token | fourth |
Token ID | 5544 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
acements | +0.867 |
dinand | +0.819 |
ortment | +0.781 |
gered | +0.742 |
OPLE | +0.719 |
Neg logit contributions | |
anon | -0.795 |
Article | -0.765 |
ovarian | -0.743 |
favors | -0.741 |
Frag | -0.725 |
Token | , |
Token ID | 11 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
anon | +0.443 |
Article | +0.428 |
ovarian | +0.413 |
favors | +0.411 |
Frag | +0.398 |
Neg logit contributions | |
acements | -0.594 |
dinand | -0.570 |
ortment | -0.540 |
gered | -0.517 |
OPLE | -0.505 |
Token | ahead |
Token ID | 4058 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
acements | +1.604 |
dinand | +1.520 |
ortment | +1.430 |
gered | +1.384 |
OPLE | +1.335 |
Neg logit contributions | |
anon | -1.378 |
Article | -1.322 |
ovarian | -1.280 |
favors | -1.266 |
Frag | -1.244 |
Token | of |
Token ID | 286 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
anon | +0.020 |
Article | +0.020 |
ovarian | +0.019 |
favors | +0.019 |
Frag | +0.018 |
Neg logit contributions | |
acements | -0.030 |
dinand | -0.028 |
ortment | -0.027 |
gered | -0.026 |
OPLE | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
acements | +1.647 |
dinand | +1.566 |
ortment | +1.474 |
gered | +1.421 |
OPLE | +1.380 |
Neg logit contributions | |
anon | -1.334 |
Article | -1.280 |
ovarian | -1.245 |
favors | -1.236 |
Frag | -1.203 |
Token | fastest |
Token ID | 14162 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
acements | +0.808 |
dinand | +0.774 |
ortment | +0.728 |
gered | +0.705 |
OPLE | +0.683 |
Neg logit contributions | |
anon | -0.629 |
Article | -0.605 |
ovarian | -0.584 |
favors | -0.579 |
Frag | -0.565 |
Token | L |
Token ID | 406 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
anon | +0.230 |
Article | +0.222 |
ovarian | +0.216 |
favors | +0.215 |
Frag | +0.208 |
Neg logit contributions | |
acements | -0.286 |
dinand | -0.274 |
ortment | -0.259 |
gered | -0.247 |
OPLE | -0.242 |
Token | , |
Token ID | 11 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
anon | +1.463 |
Article | +1.404 |
ovarian | +1.359 |
favors | +1.354 |
Frag | +1.298 |
Neg logit contributions | |
acements | -2.252 |
dinand | -2.168 |
ortment | -2.059 |
gered | -1.967 |
OPLE | -1.942 |
Token | � |
Token ID | 447 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
acements | +0.396 |
dinand | +0.380 |
ortment | +0.357 |
gered | +0.339 |
OPLE | +0.332 |
Neg logit contributions | |
anon | -0.403 |
Article | -0.385 |
ovarian | -0.378 |
favors | -0.376 |
Frag | -0.365 |
Token | � |
Token ID | 251 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
anon | +1.462 |
Article | +1.407 |
ovarian | +1.365 |
favors | +1.361 |
Frag | +1.310 |
Neg logit contributions | |
acements | -1.941 |
dinand | -1.866 |
ortment | -1.766 |
gered | -1.684 |
OPLE | -1.657 |
Token | Mr |
Token ID | 1770 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
anon | +0.547 |
Article | +0.524 |
ovarian | +0.510 |
favors | +0.507 |
Frag | +0.488 |
Neg logit contributions | |
acements | -0.775 |
dinand | -0.747 |
ortment | -0.707 |
gered | -0.676 |
OPLE | -0.666 |
Token | . |
Token ID | 13 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
anon | +1.063 |
Article | +1.018 |
ovarian | +0.992 |
favors | +0.983 |
Frag | +0.944 |
Neg logit contributions | |
acements | -1.650 |
dinand | -1.581 |
ortment | -1.508 |
gered | -1.447 |
OPLE | -1.414 |
Token | Gibbs |
Token ID | 41071 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
acements | +2.460 |
dinand | +2.360 |
ortment | +2.203 |
gered | +2.112 |
OPLE | +2.034 |
Neg logit contributions | |
anon | -2.627 |
Article | -2.517 |
ovarian | -2.484 |
favors | -2.443 |
Frag | -2.393 |
Token | said |
Token ID | 531 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
acements | +0.985 |
dinand | +0.938 |
ortment | +0.888 |
gered | +0.850 |
OPLE | +0.816 |
Neg logit contributions | |
anon | -0.972 |
Article | -0.938 |
ovarian | -0.914 |
favors | -0.903 |
Frag | -0.890 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
anon | +0.320 |
Article | +0.303 |
ovarian | +0.293 |
favors | +0.292 |
Frag | +0.282 |
Neg logit contributions | |
acements | -0.498 |
dinand | -0.481 |
ortment | -0.457 |
gered | -0.440 |
OPLE | -0.432 |
Token |
|
Token ID | 198 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
anon | +0.656 |
Article | +0.634 |
ovarian | +0.615 |
favors | +0.614 |
Frag | +0.593 |
Neg logit contributions | |
acements | -0.774 |
dinand | -0.743 |
ortment | -0.701 |
gered | -0.666 |
OPLE | -0.655 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
anon | +0.471 |
Article | +0.453 |
ovarian | +0.450 |
favors | +0.445 |
Frag | +0.428 |
Neg logit contributions | |
acements | -0.475 |
dinand | -0.443 |
ortment | -0.425 |
gered | -0.404 |
OPLE | -0.393 |
Token | Although |
Token ID | 7003 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
anon | +0.458 |
Article | +0.435 |
ovarian | +0.425 |
favors | +0.424 |
Frag | +0.401 |
Neg logit contributions | |
acements | -0.799 |
dinand | -0.768 |
ortment | -0.733 |
gered | -0.705 |
OPLE | -0.696 |
Token | Brian |
Token ID | 8403 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
acements | +0.974 |
dinand | +0.935 |
ortment | +0.885 |
gered | +0.848 |
OPLE | +0.833 |
Neg logit contributions | |
anon | -0.743 |
Article | -0.702 |
favors | -0.680 |
ovarian | -0.676 |
Frag | -0.669 |
Token | To |
Token ID | 1675 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
acements | +1.173 |
dinand | +1.121 |
ortment | +1.076 |
gered | +1.035 |
OPLE | +0.989 |
Neg logit contributions | |
anon | -0.881 |
Article | -0.845 |
favors | -0.811 |
ovarian | -0.811 |
Frag | -0.811 |
Token | pp |
Token ID | 381 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
acements | +0.596 |
dinand | +0.563 |
ortment | +0.530 |
gered | +0.495 |
OPLE | +0.482 |
Neg logit contributions | |
anon | -0.709 |
Article | -0.696 |
ovarian | -0.684 |
favors | -0.674 |
Frag | -0.661 |
Token | as |
Token ID | 355 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
anon | +1.183 |
Article | +1.139 |
favors | +1.108 |
ovarian | +1.108 |
Frag | +1.067 |
Neg logit contributions | |
acements | -1.325 |
dinand | -1.271 |
ortment | -1.196 |
gered | -1.134 |
OPLE | -1.120 |
Token | chief |
Token ID | 4039 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
acements | +0.495 |
dinand | +0.474 |
ortment | +0.452 |
gered | +0.433 |
OPLE | +0.427 |
Neg logit contributions | |
anon | -0.364 |
Article | -0.345 |
favors | -0.335 |
ovarian | -0.334 |
Frag | -0.327 |
Token | of |
Token ID | 286 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
acements | +1.820 |
dinand | +1.760 |
ortment | +1.692 |
gered | +1.591 |
OPLE | +1.559 |
Neg logit contributions | |
anon | -1.439 |
Article | -1.371 |
ovarian | -1.320 |
favors | -1.308 |
Frag | -1.303 |
Token | staff |
Token ID | 3085 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
acements | +2.761 |
dinand | +2.675 |
ortment | +2.591 |
gered | +2.458 |
OPLE | +2.419 |
Neg logit contributions | |
anon | -1.418 |
Article | -1.298 |
favors | -1.262 |
Frag | -1.258 |
ovarian | -1.243 |
Token | reflects |
Token ID | 12497 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
acements | +3.326 |
dinand | +3.157 |
ortment | +3.035 |
gered | +2.966 |
OPLE | +2.805 |
Neg logit contributions | |
anon | -2.448 |
Article | -2.331 |
ovarian | -2.256 |
Frag | -2.203 |
favors | -2.171 |
Token | her |
Token ID | 607 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
anon | +3.459 |
Article | +3.379 |
ovarian | +3.268 |
favors | +3.263 |
Myst | +3.115 |
Neg logit contributions | |
acements | -4.981 |
dinand | -4.795 |
ortment | -4.505 |
gered | -4.316 |
OPLE | -4.255 |
Token | strong |
Token ID | 1913 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
anon | +1.326 |
Article | +1.275 |
ovarian | +1.236 |
favors | +1.230 |
Frag | +1.192 |
Neg logit contributions | |
acements | -1.706 |
dinand | -1.637 |
ortment | -1.551 |
gered | -1.478 |
OPLE | -1.453 |
Token | personal |
Token ID | 2614 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
anon | +0.177 |
Article | +0.168 |
ovarian | +0.163 |
favors | +0.162 |
Frag | +0.159 |
Neg logit contributions | |
acements | -0.227 |
dinand | -0.218 |
ortment | -0.207 |
gered | -0.197 |
OPLE | -0.195 |
Token | package |
Token ID | 5301 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
anon | +0.469 |
Article | +0.450 |
ovarian | +0.439 |
favors | +0.436 |
Frag | +0.419 |
Neg logit contributions | |
acements | -0.652 |
dinand | -0.626 |
ortment | -0.596 |
gered | -0.569 |
OPLE | -0.559 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
anon | +0.268 |
Article | +0.259 |
ovarian | +0.250 |
favors | +0.247 |
Frag | +0.240 |
Neg logit contributions | |
acements | -0.346 |
dinand | -0.332 |
ortment | -0.316 |
gered | -0.303 |
OPLE | -0.294 |
Token | Likewise |
Token ID | 22660 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
acements | +1.964 |
dinand | +1.834 |
ortment | +1.781 |
gered | +1.681 |
OPLE | +1.668 |
Neg logit contributions | |
anon | -1.705 |
Article | -1.647 |
ovarian | -1.627 |
favors | -1.594 |
Frag | -1.540 |
Token | , |
Token ID | 11 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
acements | +5.639 |
dinand | +5.299 |
ortment | +5.153 |
gered | +4.943 |
OPLE | +4.931 |
Neg logit contributions | |
anon | -3.965 |
Article | -3.900 |
ovarian | -3.702 |
favors | -3.531 |
Frag | -3.521 |
Token | any |
Token ID | 597 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
acements | +2.515 |
dinand | +2.360 |
ortment | +2.295 |
gered | +2.181 |
OPLE | +2.160 |
Neg logit contributions | |
anon | -2.043 |
Article | -1.975 |
ovarian | -1.913 |
favors | -1.853 |
Frag | -1.833 |
Token | Linux |
Token ID | 7020 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
acements | +1.016 |
dinand | +0.963 |
ortment | +0.934 |
gered | +0.877 |
OPLE | +0.866 |
Neg logit contributions | |
anon | -0.918 |
Article | -0.889 |
ovarian | -0.867 |
favors | -0.853 |
Frag | -0.836 |
Token | distribution |
Token ID | 6082 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
acements | +0.894 |
dinand | +0.848 |
ortment | +0.806 |
gered | +0.758 |
OPLE | +0.748 |
Neg logit contributions | |
anon | -1.017 |
Article | -0.985 |
ovarian | -0.965 |
favors | -0.952 |
Frag | -0.930 |
Token | with |
Token ID | 351 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
acements | +2.569 |
dinand | +2.435 |
ortment | +2.336 |
gered | +2.252 |
OPLE | +2.140 |
Neg logit contributions | |
anon | -2.333 |
Article | -2.261 |
ovarian | -2.184 |
Frag | -2.128 |
favors | -2.093 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
acements | +2.286 |
dinand | +2.167 |
ortment | +2.099 |
gered | +2.015 |
OPLE | +1.978 |
Neg logit contributions | |
anon | -1.777 |
Article | -1.716 |
ovarian | -1.660 |
favors | -1.620 |
Frag | -1.602 |
Token | Flat |
Token ID | 21939 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
acements | +1.543 |
dinand | +1.460 |
ortment | +1.423 |
gered | +1.352 |
OPLE | +1.340 |
Neg logit contributions | |
anon | -1.049 |
Article | -1.007 |
ovarian | -0.974 |
favors | -0.954 |
Frag | -0.935 |
Token | pak |
Token ID | 41091 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
acements | +0.502 |
dinand | +0.479 |
ortment | +0.453 |
gered | +0.433 |
OPLE | +0.424 |
Neg logit contributions | |
anon | -0.424 |
Article | -0.410 |
ovarian | -0.401 |
favors | -0.397 |
Frag | -0.383 |
Token |
|
Token ID | 198 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
anon | +0.525 |
Article | +0.506 |
ovarian | +0.492 |
favors | +0.491 |
Frag | +0.474 |
Neg logit contributions | |
acements | -0.635 |
dinand | -0.609 |
ortment | -0.575 |
gered | -0.547 |
OPLE | -0.538 |
Token |
|
Token ID | 198 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
acements | +0.225 |
dinand | +0.209 |
ortment | +0.201 |
gered | +0.191 |
OPLE | +0.185 |
Neg logit contributions | |
anon | -0.227 |
Article | -0.220 |
ovarian | -0.219 |
favors | -0.216 |
Myst | -0.208 |
Token | � |
Token ID | 447 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
acements | +0.453 |
dinand | +0.432 |
ortment | +0.409 |
gered | +0.390 |
OPLE | +0.384 |
Neg logit contributions | |
anon | -0.400 |
Article | -0.383 |
ovarian | -0.379 |
favors | -0.378 |
Myst | -0.361 |
Token | � |
Token ID | 250 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
acements | +0.749 |
dinand | +0.721 |
ortment | +0.685 |
gered | +0.657 |
OPLE | +0.645 |
Neg logit contributions | |
anon | -0.498 |
Article | -0.476 |
ovarian | -0.462 |
favors | -0.460 |
Frag | -0.441 |
Token | I |
Token ID | 40 |
Feature activation | -1.94e-03 |
Pos logit contributions | |
acements | +0.018 |
dinand | +0.018 |
ortment | +0.017 |
gered | +0.016 |
OPLE | +0.016 |
Neg logit contributions | |
anon | -0.014 |
Article | -0.014 |
ovarian | -0.013 |
favors | -0.013 |
Frag | -0.013 |
Token | still |
Token ID | 991 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
anon | +0.011 |
Article | +0.010 |
ovarian | +0.010 |
favors | +0.010 |
Frag | +0.010 |
Neg logit contributions | |
acements | -0.013 |
dinand | -0.012 |
ortment | -0.012 |
gered | -0.011 |
OPLE | -0.011 |
Token | see |
Token ID | 766 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
anon | +1.085 |
Article | +1.044 |
ovarian | +1.017 |
favors | +1.015 |
Frag | +0.975 |
Neg logit contributions | |
acements | -1.332 |
dinand | -1.280 |
ortment | -1.207 |
gered | -1.146 |
OPLE | -1.133 |
Token | that |
Token ID | 326 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
anon | +1.528 |
Article | +1.475 |
ovarian | +1.435 |
favors | +1.431 |
Frag | +1.376 |
Neg logit contributions | |
acements | -1.916 |
dinand | -1.847 |
ortment | -1.737 |
gered | -1.642 |
OPLE | -1.631 |
Token | as |
Token ID | 355 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
anon | +1.495 |
Article | +1.443 |
ovarian | +1.402 |
favors | +1.397 |
Frag | +1.348 |
Neg logit contributions | |
acements | -1.810 |
dinand | -1.736 |
ortment | -1.637 |
gered | -1.550 |
OPLE | -1.533 |
Token | another |
Token ID | 1194 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
anon | +1.530 |
Article | +1.471 |
ovarian | +1.430 |
favors | +1.428 |
Frag | +1.366 |
Neg logit contributions | |
acements | -2.148 |
dinand | -2.066 |
ortment | -1.952 |
gered | -1.861 |
OPLE | -1.841 |
Token | record |
Token ID | 1700 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
anon | +0.941 |
Article | +0.906 |
ovarian | +0.879 |
favors | +0.875 |
Frag | +0.848 |
Neg logit contributions | |
acements | -1.132 |
dinand | -1.084 |
ortment | -1.027 |
gered | -0.981 |
OPLE | -0.959 |
Token | to |
Token ID | 284 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
anon | +0.631 |
Article | +0.607 |
ovarian | +0.594 |
favors | +0.593 |
Frag | +0.566 |
Neg logit contributions | |
acements | -0.772 |
dinand | -0.743 |
ortment | -0.700 |
gered | -0.662 |
OPLE | -0.656 |
Token | endure |
Token ID | 21178 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
anon | +0.532 |
Article | +0.514 |
ovarian | +0.501 |
favors | +0.499 |
Frag | +0.485 |
Neg logit contributions | |
acements | -0.530 |
dinand | -0.506 |
ortment | -0.476 |
gered | -0.451 |
OPLE | -0.442 |
Token | great |
Token ID | 1049 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
acements | +0.745 |
dinand | +0.711 |
ortment | +0.673 |
gered | +0.645 |
OPLE | +0.628 |
Neg logit contributions | |
anon | -0.622 |
Article | -0.598 |
ovarian | -0.575 |
favors | -0.571 |
Frag | -0.561 |
Token | mechanical |
Token ID | 12370 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
acements | +0.544 |
dinand | +0.517 |
ortment | +0.490 |
gered | +0.468 |
OPLE | +0.456 |
Neg logit contributions | |
anon | -0.482 |
Article | -0.463 |
ovarian | -0.446 |
favors | -0.442 |
Frag | -0.435 |
Token | stress |
Token ID | 5503 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
acements | +0.437 |
dinand | +0.414 |
ortment | +0.393 |
gered | +0.376 |
OPLE | +0.366 |
Neg logit contributions | |
anon | -0.372 |
Article | -0.358 |
ovarian | -0.344 |
favors | -0.339 |
Frag | -0.335 |
Token | ( |
Token ID | 357 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
acements | +1.425 |
dinand | +1.368 |
ortment | +1.298 |
gered | +1.244 |
OPLE | +1.208 |
Neg logit contributions | |
anon | -0.997 |
Article | -0.949 |
ovarian | -0.923 |
favors | -0.906 |
Frag | -0.887 |
Token | bending |
Token ID | 49667 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
anon | +0.148 |
Article | +0.143 |
ovarian | +0.140 |
favors | +0.139 |
Frag | +0.134 |
Neg logit contributions | |
acements | -0.174 |
dinand | -0.167 |
ortment | -0.157 |
gered | -0.150 |
OPLE | -0.147 |
Token | open |
Token ID | 1280 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
anon | +1.538 |
Article | +1.477 |
ovarian | +1.435 |
favors | +1.433 |
Frag | +1.373 |
Neg logit contributions | |
acements | -2.178 |
dinand | -2.099 |
ortment | -1.987 |
gered | -1.894 |
OPLE | -1.869 |
Token | and |
Token ID | 290 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
acements | +1.062 |
dinand | +1.017 |
ortment | +0.962 |
gered | +0.924 |
OPLE | +0.902 |
Neg logit contributions | |
anon | -0.877 |
Article | -0.846 |
ovarian | -0.819 |
favors | -0.810 |
Frag | -0.789 |
Token | slamming |
Token ID | 39603 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
anon | +0.207 |
Article | +0.200 |
ovarian | +0.194 |
favors | +0.193 |
Frag | +0.187 |
Neg logit contributions | |
acements | -0.223 |
dinand | -0.212 |
ortment | -0.200 |
gered | -0.190 |
OPLE | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
anon | +0.201 |
Article | +0.193 |
ovarian | +0.188 |
favors | +0.187 |
Frag | +0.181 |
Neg logit contributions | |
acements | -0.245 |
dinand | -0.235 |
ortment | -0.222 |
gered | -0.212 |
OPLE | -0.208 |
Token | was |
Token ID | 373 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
anon | +0.796 |
Article | +0.757 |
ovarian | +0.732 |
favors | +0.720 |
Frag | +0.708 |
Neg logit contributions | |
acements | -1.176 |
dinand | -1.122 |
ortment | -1.072 |
gered | -1.032 |
OPLE | -1.004 |
Token | highly |
Token ID | 4047 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
anon | +0.258 |
Article | +0.246 |
ovarian | +0.239 |
favors | +0.238 |
Frag | +0.232 |
Neg logit contributions | |
acements | -0.306 |
dinand | -0.293 |
ortment | -0.278 |
gered | -0.265 |
OPLE | -0.259 |
Token | uncertain |
Token ID | 8627 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
anon | +1.560 |
Article | +1.503 |
ovarian | +1.462 |
favors | +1.455 |
Frag | +1.409 |
Neg logit contributions | |
acements | -1.780 |
dinand | -1.706 |
ortment | -1.610 |
gered | -1.529 |
OPLE | -1.503 |
Token | as |
Token ID | 355 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
anon | +0.695 |
Article | +0.665 |
ovarian | +0.643 |
favors | +0.640 |
Frag | +0.614 |
Neg logit contributions | |
acements | -1.129 |
dinand | -1.089 |
ortment | -1.035 |
gered | -0.993 |
OPLE | -0.977 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
anon | +0.286 |
Article | +0.273 |
ovarian | +0.265 |
favors | +0.262 |
Frag | +0.255 |
Neg logit contributions | |
acements | -0.381 |
dinand | -0.365 |
ortment | -0.346 |
gered | -0.332 |
OPLE | -0.325 |
Token | leaders |
Token ID | 2766 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
acements | +1.032 |
dinand | +0.987 |
ortment | +0.931 |
gered | +0.897 |
OPLE | +0.878 |
Neg logit contributions | |
anon | -0.833 |
Article | -0.794 |
ovarian | -0.764 |
favors | -0.753 |
Frag | -0.747 |
Token | quickly |
Token ID | 2952 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
acements | +0.346 |
dinand | +0.327 |
ortment | +0.312 |
gered | +0.298 |
OPLE | +0.289 |
Neg logit contributions | |
anon | -0.297 |
Article | -0.285 |
ovarian | -0.277 |
favors | -0.275 |
Frag | -0.270 |
Token | gathered |
Token ID | 9272 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
acements | +0.096 |
dinand | +0.091 |
ortment | +0.087 |
gered | +0.083 |
OPLE | +0.080 |
Neg logit contributions | |
anon | -0.082 |
Article | -0.079 |
ovarian | -0.076 |
favors | -0.076 |
Frag | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
anon | +1.083 |
Article | +1.045 |
ovarian | +1.017 |
favors | +1.015 |
Frag | +0.977 |
Neg logit contributions | |
acements | -1.321 |
dinand | -1.270 |
ortment | -1.198 |
gered | -1.139 |
OPLE | -1.121 |
Token | plot |
Token ID | 7110 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
anon | +1.144 |
Article | +1.102 |
ovarian | +1.070 |
favors | +1.065 |
Frag | +1.036 |
Neg logit contributions | |
acements | -1.315 |
dinand | -1.255 |
ortment | -1.187 |
gered | -1.131 |
OPLE | -1.110 |
Token | strategy |
Token ID | 4811 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
anon | +0.801 |
Article | +0.775 |
ovarian | +0.754 |
favors | +0.753 |
Frag | +0.723 |
Neg logit contributions | |
acements | -0.980 |
dinand | -0.942 |
ortment | -0.889 |
gered | -0.844 |
OPLE | -0.832 |
Token | iled |
Token ID | 3902 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
acements | +1.783 |
dinand | +1.703 |
ortment | +1.620 |
gered | +1.570 |
OPLE | +1.509 |
Neg logit contributions | |
anon | -1.371 |
Article | -1.324 |
ovarian | -1.285 |
favors | -1.273 |
Frag | -1.237 |
Token | by |
Token ID | 416 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
anon | +0.118 |
Article | +0.113 |
ovarian | +0.109 |
favors | +0.108 |
Frag | +0.105 |
Neg logit contributions | |
acements | -0.164 |
dinand | -0.158 |
ortment | -0.150 |
gered | -0.144 |
OPLE | -0.140 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
anon | +1.187 |
Article | +1.141 |
ovarian | +1.111 |
favors | +1.108 |
Frag | +1.064 |
Neg logit contributions | |
acements | -1.503 |
dinand | -1.447 |
ortment | -1.365 |
gered | -1.298 |
OPLE | -1.280 |
Token | combination |
Token ID | 6087 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
anon | +0.590 |
Article | +0.573 |
ovarian | +0.553 |
favors | +0.551 |
Frag | +0.534 |
Neg logit contributions | |
acements | -0.676 |
dinand | -0.645 |
ortment | -0.610 |
gered | -0.582 |
OPLE | -0.569 |
Token | of |
Token ID | 286 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
anon | +0.320 |
Article | +0.310 |
ovarian | +0.298 |
favors | +0.296 |
Frag | +0.290 |
Neg logit contributions | |
acements | -0.417 |
dinand | -0.397 |
ortment | -0.381 |
gered | -0.363 |
OPLE | -0.351 |
Token | the |
Token ID | 262 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
anon | +2.391 |
Article | +2.294 |
favors | +2.260 |
ovarian | +2.254 |
Myst | +2.156 |
Neg logit contributions | |
acements | -2.758 |
dinand | -2.653 |
ortment | -2.491 |
gered | -2.354 |
OPLE | -2.337 |
Token | Soon |
Token ID | 15894 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
anon | +1.399 |
Article | +1.350 |
ovarian | +1.315 |
favors | +1.310 |
Frag | +1.267 |
Neg logit contributions | |
acements | -1.568 |
dinand | -1.503 |
ortment | -1.415 |
gered | -1.344 |
OPLE | -1.321 |
Token | ers |
Token ID | 364 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
acements | +0.420 |
dinand | +0.393 |
ortment | +0.369 |
gered | +0.351 |
OPLE | +0.339 |
Neg logit contributions | |
anon | -0.464 |
Article | -0.452 |
ovarian | -0.442 |
favors | -0.441 |
Frag | -0.426 |
Token | ' |
Token ID | 6 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
anon | +0.669 |
Article | +0.641 |
ovarian | +0.623 |
favors | +0.621 |
Frag | +0.595 |
Neg logit contributions | |
acements | -0.963 |
dinand | -0.928 |
ortment | -0.879 |
gered | -0.839 |
OPLE | -0.828 |
Token | own |
Token ID | 898 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
acements | +1.125 |
dinand | +1.074 |
ortment | +1.018 |
gered | +0.972 |
OPLE | +0.939 |
Neg logit contributions | |
anon | -1.016 |
Article | -0.984 |
ovarian | -0.949 |
favors | -0.935 |
Frag | -0.925 |
Token | inept |
Token ID | 43891 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
anon | +0.041 |
Article | +0.040 |
ovarian | +0.038 |
favors | +0.038 |
Frag | +0.037 |
Neg logit contributions | |
acements | -0.044 |
dinand | -0.042 |
ortment | -0.040 |
gered | -0.038 |
OPLE | -0.037 |
Token | first |
Token ID | 717 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
anon | +0.263 |
Article | +0.253 |
ovarian | +0.243 |
favors | +0.242 |
Frag | +0.234 |
Neg logit contributions | |
acements | -0.347 |
dinand | -0.330 |
ortment | -0.316 |
gered | -0.301 |
OPLE | -0.295 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
anon | +1.951 |
Article | +1.876 |
ovarian | +1.821 |
favors | +1.815 |
Frag | +1.749 |
Neg logit contributions | |
acements | -2.558 |
dinand | -2.458 |
ortment | -2.326 |
gered | -2.218 |
OPLE | -2.181 |
Token | all |
Token ID | 477 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
anon | +0.950 |
Article | +0.920 |
ovarian | +0.898 |
favors | +0.894 |
Frag | +0.870 |
Neg logit contributions | |
acements | -0.832 |
dinand | -0.790 |
ortment | -0.742 |
gered | -0.699 |
OPLE | -0.683 |
Token | a |
Token ID | 257 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
anon | +0.013 |
Article | +0.012 |
ovarian | +0.012 |
favors | +0.012 |
Frag | +0.011 |
Neg logit contributions | |
acements | -0.016 |
dinand | -0.015 |
ortment | -0.015 |
gered | -0.014 |
OPLE | -0.013 |
Token | comparison |
Token ID | 7208 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
anon | +1.305 |
Article | +1.257 |
ovarian | +1.218 |
favors | +1.213 |
Frag | +1.170 |
Neg logit contributions | |
acements | -1.662 |
dinand | -1.593 |
ortment | -1.511 |
gered | -1.438 |
OPLE | -1.412 |
Token | against |
Token ID | 1028 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
anon | +0.897 |
Article | +0.863 |
ovarian | +0.836 |
favors | +0.833 |
Frag | +0.804 |
Neg logit contributions | |
acements | -1.162 |
dinand | -1.115 |
ortment | -1.058 |
gered | -1.010 |
OPLE | -0.989 |
Token | the |
Token ID | 262 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
anon | +1.975 |
Article | +1.904 |
ovarian | +1.855 |
favors | +1.851 |
Frag | +1.786 |
Neg logit contributions | |
acements | -2.348 |
dinand | -2.259 |
ortment | -2.125 |
gered | -2.022 |
OPLE | -1.992 |
Token | View |
Token ID | 3582 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
anon | +1.609 |
Article | +1.550 |
ovarian | +1.507 |
favors | +1.502 |
Frag | +1.449 |
Neg logit contributions | |
acements | -2.009 |
dinand | -1.930 |
ortment | -1.822 |
gered | -1.736 |
OPLE | -1.708 |
Token | S |
Token ID | 50 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
acements | +0.558 |
dinand | +0.526 |
ortment | +0.508 |
gered | +0.479 |
OPLE | +0.466 |
Neg logit contributions | |
anon | -0.470 |
Article | -0.451 |
ovarian | -0.451 |
favors | -0.448 |
Moroccan | -0.424 |
Token | onic |
Token ID | 9229 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
anon | +1.836 |
Article | +1.776 |
ovarian | +1.716 |
favors | +1.716 |
Frag | +1.632 |
Neg logit contributions | |
acements | -3.210 |
dinand | -3.068 |
ortment | -2.937 |
gered | -2.830 |
OPLE | -2.789 |
Token | VP |
Token ID | 23342 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
anon | +0.931 |
Article | +0.895 |
ovarian | +0.869 |
favors | +0.865 |
Frag | +0.832 |
Neg logit contributions | |
acements | -1.230 |
dinand | -1.177 |
ortment | -1.119 |
gered | -1.067 |
OPLE | -1.051 |
Token | � |
Token ID | 447 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
acements | +1.138 |
dinand | +1.033 |
ortment | +0.998 |
gered | +0.966 |
OPLE | +0.909 |
Neg logit contributions | |
anon | -1.308 |
ovarian | -1.261 |
favors | -1.257 |
Article | -1.256 |
Myst | -1.215 |
Token | � |
Token ID | 247 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
acements | +0.060 |
dinand | +0.058 |
ortment | +0.055 |
gered | +0.054 |
OPLE | +0.052 |
Neg logit contributions | |
anon | -0.033 |
Article | -0.032 |
favors | -0.030 |
ovarian | -0.030 |
Myst | -0.029 |
Token | t |
Token ID | 83 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
acements | +1.077 |
dinand | +1.027 |
ortment | +0.971 |
gered | +0.951 |
OPLE | +0.891 |
Neg logit contributions | |
anon | -0.947 |
Article | -0.923 |
ovarian | -0.910 |
favors | -0.900 |
Moroccan | -0.877 |
Token | stopped |
Token ID | 5025 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
anon | +1.564 |
Article | +1.507 |
ovarian | +1.462 |
favors | +1.457 |
Frag | +1.402 |
Neg logit contributions | |
acements | -2.026 |
dinand | -1.950 |
ortment | -1.843 |
gered | -1.752 |
OPLE | -1.728 |
Token | Sch |
Token ID | 3059 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
anon | +0.954 |
Article | +0.921 |
ovarian | +0.897 |
favors | +0.893 |
Frag | +0.865 |
Neg logit contributions | |
acements | -1.068 |
dinand | -1.021 |
ortment | -0.962 |
gered | -0.917 |
OPLE | -0.900 |
Token | um |
Token ID | 388 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
anon | +2.656 |
Article | +2.394 |
ovarian | +2.264 |
favors | +2.213 |
atively | +2.131 |
Neg logit contributions | |
acements | -7.142 |
dinand | -6.980 |
ortment | -6.674 |
OPLE | -6.488 |
gered | -6.413 |
Token | acher |
Token ID | 3493 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
anon | +3.292 |
Article | +3.173 |
favors | +3.071 |
ovarian | +3.038 |
Frag | +2.951 |
Neg logit contributions | |
acements | -3.855 |
dinand | -3.758 |
ortment | -3.546 |
OPLE | -3.379 |
gered | -3.308 |
Token | from |
Token ID | 422 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
anon | +1.170 |
Article | +1.132 |
ovarian | +1.104 |
favors | +1.100 |
Frag | +1.066 |
Neg logit contributions | |
acements | -1.169 |
dinand | -1.117 |
ortment | -1.049 |
gered | -0.992 |
OPLE | -0.974 |
Token | asking |
Token ID | 4737 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
anon | +0.051 |
Article | +0.049 |
ovarian | +0.047 |
favors | +0.047 |
Frag | +0.046 |
Neg logit contributions | |
acements | -0.053 |
dinand | -0.051 |
ortment | -0.048 |
gered | -0.045 |
OPLE | -0.044 |
Token | .) |
Token ID | 2014 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
anon | +2.540 |
Article | +2.475 |
favors | +2.411 |
ovarian | +2.398 |
Myst | +2.320 |
Neg logit contributions | |
acements | -2.705 |
dinand | -2.599 |
ortment | -2.431 |
gered | -2.274 |
OPLE | -2.248 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
acements | +0.965 |
dinand | +0.918 |
ortment | +0.873 |
gered | +0.836 |
OPLE | +0.820 |
Neg logit contributions | |
anon | -0.784 |
Article | -0.749 |
ovarian | -0.740 |
favors | -0.733 |
Frag | -0.705 |
Token | barrier |
Token ID | 13054 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
acements | +0.852 |
dinand | +0.794 |
ortment | +0.756 |
gered | +0.722 |
OPLE | +0.693 |
Neg logit contributions | |
anon | -0.881 |
Article | -0.863 |
ovarian | -0.829 |
favors | -0.823 |
Frag | -0.802 |
Token | for |
Token ID | 329 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
acements | +0.178 |
dinand | +0.170 |
ortment | +0.161 |
gered | +0.154 |
OPLE | +0.150 |
Neg logit contributions | |
anon | -0.139 |
Article | -0.133 |
ovarian | -0.129 |
favors | -0.128 |
Frag | -0.125 |
Token | the |
Token ID | 262 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
anon | +0.271 |
Article | +0.261 |
ovarian | +0.254 |
favors | +0.252 |
Frag | +0.246 |
Neg logit contributions | |
acements | -0.312 |
dinand | -0.299 |
ortment | -0.282 |
gered | -0.269 |
OPLE | -0.264 |
Token | third |
Token ID | 2368 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
anon | +1.333 |
Article | +1.269 |
ovarian | +1.223 |
favors | +1.219 |
Frag | +1.157 |
Neg logit contributions | |
acements | -2.629 |
dinand | -2.543 |
ortment | -2.426 |
gered | -2.329 |
OPLE | -2.300 |
Token | successive |
Token ID | 25175 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
anon | +2.674 |
Article | +2.593 |
ovarian | +2.528 |
favors | +2.522 |
Frag | +2.431 |
Neg logit contributions | |
acements | -2.834 |
dinand | -2.726 |
ortment | -2.554 |
gered | -2.417 |
OPLE | -2.383 |
Token | season |
Token ID | 1622 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
anon | +2.521 |
Article | +2.448 |
ovarian | +2.389 |
favors | +2.373 |
Myst | +2.289 |
Neg logit contributions | |
acements | -3.379 |
dinand | -3.304 |
ortment | -3.094 |
gered | -2.932 |
OPLE | -2.924 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
anon | +3.584 |
Article | +3.462 |
favors | +3.388 |
ovarian | +3.357 |
Myst | +3.205 |
Neg logit contributions | |
acements | -6.620 |
dinand | -6.462 |
ortment | -6.103 |
gered | -5.854 |
OPLE | -5.815 |
Token | After |
Token ID | 2293 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
acements | +0.776 |
dinand | +0.735 |
ortment | +0.705 |
gered | +0.665 |
OPLE | +0.652 |
Neg logit contributions | |
anon | -0.676 |
Article | -0.651 |
ovarian | -0.642 |
favors | -0.634 |
Frag | -0.614 |
Token | locking |
Token ID | 22656 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
anon | +0.313 |
Article | +0.301 |
ovarian | +0.294 |
favors | +0.292 |
Frag | +0.283 |
Neg logit contributions | |
acements | -0.368 |
dinand | -0.352 |
ortment | -0.332 |
gered | -0.317 |
OPLE | -0.309 |
Token | away |
Token ID | 1497 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
anon | +1.246 |
Article | +1.203 |
ovarian | +1.169 |
favors | +1.166 |
Frag | +1.123 |
Neg logit contributions | |
acements | -1.523 |
dinand | -1.464 |
ortment | -1.381 |
gered | -1.312 |
OPLE | -1.293 |
Token | the |
Token ID | 262 |
Feature activation | +9.23e-04 |
Pos logit contributions | |
acements | +0.831 |
dinand | +0.788 |
ortment | +0.744 |
gered | +0.715 |
OPLE | +0.691 |
Neg logit contributions | |
anon | -0.732 |
Article | -0.704 |
ovarian | -0.684 |
favors | -0.675 |
Frag | -0.666 |
Token | original |
Token ID | 2656 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
acements | +0.130 |
dinand | +0.122 |
ortment | +0.118 |
gered | +0.111 |
OPLE | +0.109 |
Neg logit contributions | |
anon | -0.115 |
Article | -0.111 |
ovarian | -0.107 |
favors | -0.105 |
Frag | -0.104 |
Token | content |
Token ID | 2695 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
acements | +0.291 |
dinand | +0.273 |
ortment | +0.262 |
gered | +0.246 |
OPLE | +0.241 |
Neg logit contributions | |
anon | -0.280 |
Article | -0.270 |
ovarian | -0.261 |
favors | -0.259 |
Frag | -0.254 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
anon | +0.306 |
Article | +0.293 |
ovarian | +0.283 |
favors | +0.278 |
Frag | +0.273 |
Neg logit contributions | |
acements | -0.426 |
dinand | -0.406 |
ortment | -0.388 |
gered | -0.371 |
OPLE | -0.362 |
Token | for |
Token ID | 329 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
anon | +0.219 |
Article | +0.211 |
ovarian | +0.205 |
favors | +0.201 |
Frag | +0.198 |
Neg logit contributions | |
acements | -0.251 |
dinand | -0.239 |
ortment | -0.228 |
gered | -0.216 |
OPLE | -0.211 |
Token | a |
Token ID | 257 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
anon | +1.542 |
Article | +1.484 |
ovarian | +1.444 |
favors | +1.440 |
Frag | +1.386 |
Neg logit contributions | |
acements | -1.992 |
dinand | -1.918 |
ortment | -1.810 |
gered | -1.723 |
OPLE | -1.697 |
Token | fraction |
Token ID | 13390 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
anon | +2.501 |
Article | +2.398 |
ovarian | +2.347 |
favors | +2.342 |
Frag | +2.254 |
Neg logit contributions | |
acements | -3.276 |
dinand | -3.164 |
ortment | -2.961 |
gered | -2.828 |
OPLE | -2.793 |
Token | of |
Token ID | 286 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
anon | +3.410 |
Article | +3.338 |
favors | +3.222 |
ovarian | +3.162 |
Frag | +3.068 |
Neg logit contributions | |
acements | -6.567 |
dinand | -6.336 |
ortment | -5.921 |
OPLE | -5.844 |
gered | -5.640 |
Token | what |
Token ID | 644 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
anon | +3.335 |
Article | +3.208 |
ovarian | +3.147 |
favors | +3.140 |
Frag | +3.004 |
Neg logit contributions | |
acements | -4.497 |
dinand | -4.393 |
ortment | -4.064 |
OPLE | -3.881 |
gered | -3.861 |
Token | you |
Token ID | 345 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
anon | +3.998 |
favors | +3.848 |
Article | +3.835 |
ovarian | +3.800 |
Frag | +3.602 |
Neg logit contributions | |
acements | -6.527 |
dinand | -6.468 |
ortment | -6.000 |
gered | -5.741 |
OPLE | -5.671 |
Token | 're |
Token ID | 821 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
anon | +1.338 |
Article | +1.284 |
ovarian | +1.250 |
favors | +1.243 |
Frag | +1.195 |
Neg logit contributions | |
acements | -1.791 |
dinand | -1.731 |
ortment | -1.632 |
gered | -1.551 |
OPLE | -1.535 |
Token | shelling |
Token ID | 38406 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
anon | +1.130 |
Article | +1.090 |
ovarian | +1.063 |
favors | +1.060 |
Frag | +1.019 |
Neg logit contributions | |
acements | -1.314 |
dinand | -1.264 |
ortment | -1.187 |
gered | -1.124 |
OPLE | -1.112 |
Token | Wal |
Token ID | 6445 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
anon | +3.490 |
Article | +3.347 |
ovarian | +3.264 |
favors | +3.239 |
Moroccan | +3.138 |
Neg logit contributions | |
acements | -5.418 |
dinand | -5.244 |
ortment | -4.934 |
gered | -4.715 |
OPLE | -4.699 |
Token | nuts |
Token ID | 31381 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
anon | +0.453 |
Article | +0.424 |
ovarian | +0.409 |
favors | +0.407 |
Frag | +0.379 |
Neg logit contributions | |
acements | -1.067 |
dinand | -1.031 |
ortment | -0.994 |
gered | -0.959 |
OPLE | -0.936 |
Token | Hal |
Token ID | 11023 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
anon | +2.180 |
Article | +2.098 |
ovarian | +2.011 |
favors | +2.002 |
Frag | +1.925 |
Neg logit contributions | |
acements | -4.233 |
dinand | -4.112 |
ortment | -3.877 |
gered | -3.726 |
OPLE | -3.703 |
Token | ves |
Token ID | 1158 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
anon | +0.717 |
Article | +0.682 |
ovarian | +0.657 |
favors | +0.655 |
Frag | +0.624 |
Neg logit contributions | |
acements | -1.366 |
dinand | -1.321 |
ortment | -1.259 |
gered | -1.208 |
OPLE | -1.195 |
Token | , |
Token ID | 837 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
anon | +2.778 |
Article | +2.673 |
favors | +2.561 |
ovarian | +2.546 |
Frag | +2.439 |
Neg logit contributions | |
acements | -6.038 |
dinand | -5.883 |
ortment | -5.518 |
OPLE | -5.326 |
gered | -5.324 |
Token | Mac |
Token ID | 4100 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
anon | +2.245 |
Article | +2.152 |
ovarian | +2.087 |
favors | +2.078 |
Frag | +1.997 |
Neg logit contributions | |
acements | -3.459 |
dinand | -3.337 |
ortment | -3.162 |
gered | -3.024 |
OPLE | -2.988 |
Token | ad |
Token ID | 324 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
anon | +3.357 |
Article | +3.204 |
ovarian | +3.083 |
favors | +3.058 |
Frag | +2.939 |
Neg logit contributions | |
acements | -4.722 |
dinand | -4.545 |
ortment | -4.293 |
gered | -4.094 |
OPLE | -4.077 |
Token | amia |
Token ID | 49442 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
anon | +0.024 |
Article | +0.024 |
ovarian | +0.023 |
favors | +0.023 |
Frag | +0.023 |
Neg logit contributions | |
acements | -0.021 |
dinand | -0.020 |
ortment | -0.018 |
gered | -0.017 |
OPLE | -0.017 |
Token | N |
Token ID | 399 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
acements | +0.859 |
dinand | +0.816 |
ortment | +0.783 |
gered | +0.750 |
OPLE | +0.730 |
Neg logit contributions | |
anon | -0.650 |
Article | -0.624 |
ovarian | -0.608 |
favors | -0.600 |
Frag | -0.571 |
Token | uts |
Token ID | 5500 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
acements | +0.444 |
dinand | +0.417 |
ortment | +0.392 |
gered | +0.368 |
OPLE | +0.361 |
Neg logit contributions | |
anon | -0.533 |
Article | -0.517 |
ovarian | -0.508 |
favors | -0.504 |
Frag | -0.486 |
Token | , |
Token ID | 837 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
anon | +3.005 |
Article | +2.889 |
favors | +2.776 |
ovarian | +2.775 |
Frag | +2.684 |
Neg logit contributions | |
acements | -6.238 |
dinand | -6.106 |
ortment | -5.707 |
gered | -5.499 |
OPLE | -5.473 |
Token | transgender |
Token ID | 10637 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
acements | +0.078 |
dinand | +0.075 |
ortment | +0.071 |
gered | +0.068 |
OPLE | +0.067 |
Neg logit contributions | |
anon | -0.060 |
Article | -0.058 |
ovarian | -0.056 |
favors | -0.056 |
Frag | -0.055 |
Token | activists |
Token ID | 7941 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
anon | +0.446 |
Article | +0.425 |
ovarian | +0.410 |
favors | +0.408 |
Frag | +0.393 |
Neg logit contributions | |
acements | -0.770 |
dinand | -0.743 |
ortment | -0.707 |
gered | -0.679 |
OPLE | -0.671 |
Token | don |
Token ID | 836 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
anon | +1.555 |
Article | +1.505 |
ovarian | +1.468 |
favors | +1.465 |
Frag | +1.405 |
Neg logit contributions | |
acements | -1.781 |
dinand | -1.714 |
ortment | -1.613 |
gered | -1.530 |
OPLE | -1.501 |
Token | � |
Token ID | 447 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
anon | +1.317 |
Article | +1.278 |
ovarian | +1.253 |
favors | +1.249 |
Frag | +1.213 |
Neg logit contributions | |
acements | -1.011 |
dinand | -0.955 |
ortment | -0.890 |
gered | -0.838 |
OPLE | -0.815 |
Token | � |
Token ID | 247 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
anon | +0.642 |
Article | +0.602 |
ovarian | +0.575 |
favors | +0.572 |
Frag | +0.539 |
Neg logit contributions | |
acements | -1.523 |
dinand | -1.469 |
ortment | -1.410 |
gered | -1.370 |
OPLE | -1.334 |
Token | t |
Token ID | 83 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
anon | +0.279 |
Article | +0.269 |
ovarian | +0.262 |
favors | +0.260 |
Frag | +0.252 |
Neg logit contributions | |
acements | -0.339 |
dinand | -0.325 |
ortment | -0.307 |
gered | -0.293 |
OPLE | -0.287 |
Token | want |
Token ID | 765 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
anon | +3.079 |
Article | +2.978 |
favors | +2.922 |
ovarian | +2.899 |
prayer | +2.737 |
Neg logit contributions | |
acements | -3.751 |
dinand | -3.606 |
ortment | -3.414 |
gered | -3.180 |
OPLE | -3.153 |
Token | to |
Token ID | 284 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
anon | +2.521 |
Article | +2.441 |
ovarian | +2.363 |
favors | +2.342 |
Myst | +2.246 |
Neg logit contributions | |
acements | -3.274 |
dinand | -3.156 |
ortment | -2.985 |
gered | -2.794 |
OPLE | -2.758 |
Token | talk |
Token ID | 1561 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
anon | +0.131 |
Article | +0.127 |
ovarian | +0.123 |
favors | +0.123 |
Frag | +0.120 |
Neg logit contributions | |
acements | -0.142 |
dinand | -0.136 |
ortment | -0.128 |
gered | -0.123 |
OPLE | -0.120 |
Token | about |
Token ID | 546 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
anon | +0.773 |
Article | +0.747 |
ovarian | +0.725 |
favors | +0.721 |
Frag | +0.693 |
Neg logit contributions | |
acements | -1.071 |
dinand | -1.029 |
ortment | -0.974 |
gered | -0.927 |
OPLE | -0.917 |
Token | , |
Token ID | 11 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
acements | +1.333 |
dinand | +1.284 |
ortment | +1.210 |
gered | +1.166 |
OPLE | +1.139 |
Neg logit contributions | |
anon | -1.053 |
Article | -1.007 |
ovarian | -0.978 |
favors | -0.974 |
Frag | -0.951 |