Token | , |
Token ID | 11 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
zzo | +2.677 |
matured | +2.653 |
rhy | +2.540 |
irit | +2.447 |
Dise | +2.408 |
Neg logit contributions | |
Osw | -3.020 |
appropriately | -2.838 |
med | -2.819 |
gest | -2.808 |
oid | -2.792 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
zzo | +0.049 |
matured | +0.048 |
rhy | +0.046 |
irit | +0.045 |
Dise | +0.044 |
Neg logit contributions | |
Osw | -0.063 |
med | -0.060 |
appropriately | -0.059 |
gest | -0.059 |
ifiable | -0.059 |
Token | top |
Token ID | 1353 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
zzo | +0.890 |
matured | +0.868 |
rhy | +0.847 |
irit | +0.821 |
Dise | +0.812 |
Neg logit contributions | |
Osw | -0.973 |
med | -0.913 |
appropriately | -0.909 |
gest | -0.904 |
ifiable | -0.900 |
Token | five |
Token ID | 1936 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
zzo | +0.331 |
matured | +0.322 |
rhy | +0.313 |
irit | +0.306 |
Dise | +0.301 |
Neg logit contributions | |
Osw | -0.369 |
med | -0.348 |
appropriately | -0.345 |
gest | -0.343 |
ifiable | -0.340 |
Token | most |
Token ID | 749 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Osw | +2.147 |
med | +2.062 |
gest | +2.041 |
ifiable | +2.031 |
appropriately | +2.023 |
Neg logit contributions | |
zzo | -1.669 |
matured | -1.591 |
irit | -1.534 |
rhy | -1.525 |
Dise | -1.510 |
Token | rev |
Token ID | 2710 |
Feature activation | +1.69e+01 |
Pos logit contributions | |
zzo | +0.104 |
matured | +0.101 |
rhy | +0.098 |
irit | +0.096 |
Dise | +0.094 |
Neg logit contributions | |
Osw | -0.117 |
med | -0.111 |
appropriately | -0.110 |
gest | -0.109 |
ifiable | -0.109 |
Token | iled |
Token ID | 3902 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
irit | +6.250 |
zzo | +5.925 |
matured | +5.678 |
gae | +5.603 |
lang | +5.118 |
Neg logit contributions | |
Osw | -14.274 |
sonian | -13.094 |
appropriately | -13.029 |
gest | -13.017 |
meal | -12.996 |
Token | institutions |
Token ID | 6712 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
Osw | +0.387 |
med | +0.369 |
appropriately | +0.366 |
gest | +0.365 |
ifiable | +0.364 |
Neg logit contributions | |
zzo | -0.248 |
matured | -0.238 |
rhy | -0.229 |
irit | -0.225 |
Dise | -0.221 |
Token | are |
Token ID | 389 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
Osw | +0.050 |
med | +0.047 |
appropriately | +0.046 |
gest | +0.046 |
ifiable | +0.046 |
Neg logit contributions | |
zzo | -0.049 |
matured | -0.048 |
rhy | -0.046 |
irit | -0.046 |
Dise | -0.045 |
Token | Bank |
Token ID | 5018 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
zzo | +0.222 |
matured | +0.217 |
rhy | +0.210 |
irit | +0.205 |
Dise | +0.203 |
Neg logit contributions | |
Osw | -0.244 |
med | -0.230 |
appropriately | -0.228 |
gest | -0.228 |
ifiable | -0.226 |
Token | of |
Token ID | 286 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
Osw | +4.156 |
med | +3.989 |
ifiable | +3.876 |
gest | +3.868 |
\": | +3.800 |
Neg logit contributions | |
zzo | -5.570 |
matured | -5.391 |
rhy | -5.321 |
irit | -5.178 |
Dise | -5.158 |
Token | hash |
Token ID | 17831 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Osw | +1.711 |
med | +1.584 |
gest | +1.556 |
appropriately | +1.527 |
ifiable | +1.525 |
Neg logit contributions | |
zzo | -4.088 |
matured | -4.018 |
rhy | -3.929 |
Dise | -3.868 |
irit | -3.866 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Osw | +0.758 |
appropriately | +0.713 |
med | +0.700 |
ifiable | +0.693 |
gest | +0.691 |
Neg logit contributions | |
zzo | -0.750 |
matured | -0.715 |
rhy | -0.700 |
irit | -0.690 |
Dise | -0.671 |
Token | com |
Token ID | 785 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
Osw | +0.789 |
appropriately | +0.729 |
med | +0.717 |
ifiable | +0.717 |
gest | +0.713 |
Neg logit contributions | |
zzo | -0.858 |
matured | -0.814 |
rhy | -0.797 |
irit | -0.784 |
Dise | -0.760 |
Token | , |
Token ID | 11 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
zzo | +3.660 |
matured | +3.360 |
rhy | +3.276 |
irit | +3.093 |
lang | +3.086 |
Neg logit contributions | |
Osw | -5.272 |
appropriately | -5.166 |
anked | -4.886 |
ifiable | -4.862 |
gest | -4.848 |
Token | but |
Token ID | 475 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
zzo | +3.688 |
matured | +3.607 |
rhy | +3.334 |
branch | +3.267 |
irit | +3.149 |
Neg logit contributions | |
Osw | -6.753 |
appropriately | -6.603 |
gest | -6.377 |
ifiable | -6.292 |
elfare | -6.280 |
Token | will |
Token ID | 481 |
Feature activation | +1.63e+01 |
Pos logit contributions | |
zzo | +4.457 |
matured | +4.176 |
closed | +3.882 |
branch | +3.814 |
rhy | +3.656 |
Neg logit contributions | |
Osw | -10.223 |
appropriately | -9.914 |
elfare | -9.691 |
oid | -9.686 |
sonian | -9.581 |
Token | be |
Token ID | 307 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
zzo | +4.579 |
matured | +4.105 |
branch | +3.892 |
closed | +3.874 |
rhy | +3.834 |
Neg logit contributions | |
Osw | -15.536 |
MPG | -14.620 |
appropriately | -14.507 |
\": | -14.321 |
mares | -14.259 |
Token | disabled |
Token ID | 10058 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
zzo | +6.045 |
matured | +5.930 |
closed | +5.692 |
irit | +5.220 |
rhy | +5.200 |
Neg logit contributions | |
Osw | -7.242 |
sonian | -6.768 |
\": | -6.740 |
appropriately | -6.562 |
MPG | -6.552 |
Token | eventually |
Token ID | 4191 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
zzo | +2.941 |
matured | +2.810 |
branch | +2.470 |
rhy | +2.430 |
thereto | +2.416 |
Neg logit contributions | |
Osw | -6.680 |
gest | -6.338 |
elfare | -6.271 |
appropriately | -6.205 |
MPG | -6.193 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
zzo | +3.193 |
lang | +2.806 |
matured | +2.747 |
rhy | +2.719 |
irit | +2.710 |
Neg logit contributions | |
Osw | -4.660 |
appropriately | -4.583 |
anked | -4.275 |
mares | -4.246 |
ifiable | -4.198 |
Token | There |
Token ID | 1318 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
Osw | +0.193 |
med | +0.182 |
appropriately | +0.180 |
gest | +0.179 |
ifiable | +0.178 |
Neg logit contributions | |
zzo | -0.188 |
matured | -0.183 |
rhy | -0.177 |
irit | -0.175 |
Dise | -0.171 |
Token | ways |
Token ID | 2842 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Osw | +0.030 |
med | +0.029 |
appropriately | +0.028 |
gest | +0.028 |
ifiable | +0.028 |
Neg logit contributions | |
zzo | -0.029 |
matured | -0.028 |
rhy | -0.027 |
irit | -0.026 |
Dise | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
zzo | +1.004 |
matured | +0.977 |
rhy | +0.947 |
irit | +0.927 |
Dise | +0.912 |
Neg logit contributions | |
Osw | -1.139 |
med | -1.070 |
appropriately | -1.067 |
gest | -1.060 |
ifiable | -1.051 |
Token | use |
Token ID | 779 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
zzo | +1.844 |
matured | +1.818 |
rhy | +1.770 |
irit | +1.724 |
Dise | +1.674 |
Neg logit contributions | |
Osw | -2.276 |
appropriately | -2.113 |
med | -2.090 |
gest | -2.082 |
ifiable | -2.080 |
Token | cannabis |
Token ID | 9499 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
Osw | +2.495 |
med | +2.440 |
gest | +2.362 |
ifiable | +2.357 |
appropriately | +2.347 |
Neg logit contributions | |
zzo | -2.423 |
matured | -2.271 |
irit | -2.215 |
rhy | -2.213 |
Dise | -2.188 |
Token | . |
Token ID | 13 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Osw | +2.942 |
med | +2.894 |
ifiable | +2.797 |
oid | +2.791 |
gest | +2.773 |
Neg logit contributions | |
zzo | -3.641 |
matured | -3.471 |
irit | -3.405 |
rhy | -3.390 |
Dise | -3.367 |
Token | Ed |
Token ID | 1717 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
zzo | +0.193 |
matured | +0.187 |
rhy | +0.182 |
irit | +0.179 |
Dise | +0.178 |
Neg logit contributions | |
Osw | -0.191 |
med | -0.179 |
appropriately | -0.179 |
gest | -0.177 |
ifiable | -0.177 |
Token | ibles |
Token ID | 18764 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
matured | +8.825 |
gae | +8.771 |
zzo | +8.675 |
irit | +8.541 |
dies | +8.397 |
Neg logit contributions | |
Osw | -9.374 |
appropriately | -9.184 |
\": | -8.380 |
elfare | -8.361 |
oid | -8.254 |
Token | , |
Token ID | 11 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
zzo | +1.907 |
matured | +1.878 |
rhy | +1.817 |
irit | +1.768 |
Dise | +1.734 |
Neg logit contributions | |
Osw | -1.946 |
appropriately | -1.808 |
med | -1.790 |
gest | -1.785 |
ifiable | -1.771 |
Token | vapor |
Token ID | 20199 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Osw | +0.373 |
med | +0.353 |
appropriately | +0.349 |
gest | +0.348 |
ifiable | +0.346 |
Neg logit contributions | |
zzo | -0.335 |
matured | -0.324 |
rhy | -0.314 |
irit | -0.310 |
Dise | -0.305 |
Token | izers |
Token ID | 11341 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
zzo | +1.663 |
matured | +1.632 |
rhy | +1.592 |
irit | +1.570 |
Dise | +1.549 |
Neg logit contributions | |
Osw | -0.953 |
med | -0.867 |
appropriately | -0.859 |
gest | -0.854 |
ifiable | -0.842 |
Token | … |
Token ID | 1399 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Osw | +1.580 |
med | +1.550 |
gest | +1.490 |
ifiable | +1.489 |
oid | +1.488 |
Neg logit contributions | |
zzo | -1.977 |
matured | -1.910 |
rhy | -1.863 |
Dise | -1.857 |
irit | -1.856 |
Token | they |
Token ID | 484 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
Osw | +2.636 |
med | +2.514 |
ifiable | +2.446 |
appropriately | +2.436 |
gest | +2.420 |
Neg logit contributions | |
zzo | -2.731 |
matured | -2.612 |
rhy | -2.501 |
Dise | -2.485 |
irit | -2.484 |
Token | see |
Token ID | 766 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Osw | +0.027 |
med | +0.025 |
appropriately | +0.025 |
gest | +0.025 |
ifiable | +0.025 |
Neg logit contributions | |
zzo | -0.023 |
matured | -0.023 |
rhy | -0.022 |
irit | -0.021 |
Dise | -0.021 |
Token | their |
Token ID | 511 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
zzo | +0.448 |
matured | +0.438 |
rhy | +0.425 |
irit | +0.417 |
Dise | +0.410 |
Neg logit contributions | |
Osw | -0.449 |
med | -0.421 |
appropriately | -0.418 |
gest | -0.417 |
ifiable | -0.412 |
Token | lives |
Token ID | 3160 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
Osw | +0.777 |
med | +0.737 |
gest | +0.724 |
appropriately | +0.724 |
ifiable | +0.721 |
Neg logit contributions | |
zzo | -0.657 |
matured | -0.633 |
rhy | -0.611 |
irit | -0.604 |
Dise | -0.593 |
Token | turned |
Token ID | 2900 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
matured | +2.989 |
zzo | +2.983 |
rhy | +2.905 |
irit | +2.770 |
Dise | +2.698 |
Neg logit contributions | |
Osw | -3.691 |
appropriately | -3.456 |
gest | -3.406 |
med | -3.402 |
\": | -3.389 |
Token | upside |
Token ID | 17196 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
zzo | +1.574 |
matured | +1.497 |
rhy | +1.457 |
irit | +1.269 |
Dise | +1.225 |
Neg logit contributions | |
Osw | -6.611 |
gest | -6.330 |
appropriately | -6.310 |
med | -6.244 |
\": | -6.227 |
Token | down |
Token ID | 866 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
zzo | +5.788 |
rhy | +5.640 |
matured | +5.598 |
branch | +5.334 |
irit | +5.320 |
Neg logit contributions | |
Osw | -12.642 |
gest | -12.210 |
ifiable | -12.159 |
appropriately | -12.108 |
hip | -11.877 |
Token | by |
Token ID | 416 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
zzo | +0.256 |
matured | +0.249 |
rhy | +0.242 |
irit | +0.239 |
Dise | +0.236 |
Neg logit contributions | |
Osw | -0.233 |
med | -0.220 |
appropriately | -0.216 |
gest | -0.216 |
ifiable | -0.215 |
Token | doctors |
Token ID | 7519 |
Feature activation | -8.01e+00 |
Pos logit contributions | |
Osw | +0.826 |
med | +0.781 |
appropriately | +0.769 |
gest | +0.767 |
ifiable | +0.764 |
Neg logit contributions | |
zzo | -0.794 |
matured | -0.768 |
rhy | -0.743 |
irit | -0.733 |
Dise | -0.723 |
Token | pressured |
Token ID | 32098 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
Osw | +4.889 |
med | +4.858 |
ifiable | +4.729 |
hip | +4.690 |
gest | +4.653 |
Neg logit contributions | |
zzo | -5.527 |
matured | -5.253 |
irit | -5.165 |
Dise | -5.128 |
sqor | -4.972 |
Token | to |
Token ID | 284 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
Osw | +3.995 |
med | +3.956 |
ifiable | +3.798 |
oid | +3.798 |
gest | +3.773 |
Neg logit contributions | |
zzo | -4.826 |
matured | -4.732 |
Dise | -4.583 |
irit | -4.567 |
rhy | -4.443 |
Token | be |
Token ID | 307 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
Osw | +2.143 |
med | +2.051 |
gest | +2.008 |
ifiable | +2.001 |
appropriately | +1.998 |
Neg logit contributions | |
zzo | -2.174 |
matured | -2.118 |
rhy | -2.025 |
irit | -2.016 |
Dise | -2.006 |
Token | refused |
Token ID | 6520 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
Osw | +3.226 |
med | +3.053 |
ifiable | +3.004 |
gest | +2.998 |
appropriately | +2.988 |
Neg logit contributions | |
zzo | -3.162 |
matured | -3.027 |
irit | -2.928 |
rhy | -2.922 |
Dise | -2.901 |
Token | one |
Token ID | 530 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Osw | +3.950 |
med | +3.846 |
ifiable | +3.738 |
gest | +3.694 |
appropriately | +3.645 |
Neg logit contributions | |
zzo | -4.515 |
matured | -4.358 |
irit | -4.241 |
rhy | -4.173 |
Dise | -4.132 |
Token | . |
Token ID | 13 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
Osw | +2.107 |
med | +2.004 |
ifiable | +1.966 |
gest | +1.963 |
appropriately | +1.955 |
Neg logit contributions | |
zzo | -2.403 |
matured | -2.344 |
rhy | -2.256 |
irit | -2.251 |
Dise | -2.227 |
Token | From |
Token ID | 3574 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
Osw | +0.544 |
med | +0.513 |
appropriately | +0.510 |
gest | +0.506 |
ifiable | +0.504 |
Neg logit contributions | |
zzo | -0.542 |
matured | -0.525 |
rhy | -0.511 |
irit | -0.502 |
Dise | -0.497 |
Token | Ed |
Token ID | 1717 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
zzo | +3.162 |
matured | +3.076 |
rhy | +2.991 |
Dise | +2.833 |
irit | +2.813 |
Neg logit contributions | |
Osw | -4.384 |
appropriately | -4.151 |
med | -4.136 |
oid | -4.124 |
gest | -4.121 |
Token | Koch |
Token ID | 17009 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
zzo | +9.262 |
gae | +8.819 |
rhy | +8.620 |
matured | +8.613 |
irit | +8.597 |
Neg logit contributions | |
appropriately | -9.044 |
Osw | -8.865 |
\": | -8.563 |
oid | -7.988 |
meal | -7.957 |
Token | on |
Token ID | 319 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
zzo | +2.053 |
matured | +1.984 |
rhy | +1.945 |
irit | +1.903 |
Dise | +1.876 |
Neg logit contributions | |
Osw | -1.853 |
appropriately | -1.728 |
med | -1.719 |
gest | -1.711 |
ifiable | -1.710 |
Token | down |
Token ID | 866 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
zzo | +1.866 |
matured | +1.785 |
rhy | +1.723 |
irit | +1.677 |
Dise | +1.643 |
Neg logit contributions | |
Osw | -2.994 |
med | -2.850 |
appropriately | -2.836 |
gest | -2.828 |
ifiable | -2.810 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Osw | +1.022 |
med | +0.972 |
gest | +0.955 |
appropriately | +0.942 |
ifiable | +0.938 |
Neg logit contributions | |
zzo | -1.166 |
matured | -1.140 |
rhy | -1.095 |
irit | -1.094 |
Dise | -1.073 |
Token | every |
Token ID | 790 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
zzo | +0.119 |
matured | +0.116 |
rhy | +0.112 |
irit | +0.110 |
Dise | +0.108 |
Neg logit contributions | |
Osw | -0.132 |
med | -0.125 |
appropriately | -0.123 |
gest | -0.123 |
ifiable | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Osw | +0.827 |
appropriately | +0.778 |
med | +0.759 |
ifiable | +0.751 |
gest | +0.748 |
Neg logit contributions | |
zzo | -0.788 |
matured | -0.743 |
rhy | -0.735 |
irit | -0.715 |
Dise | -0.695 |
Token | Paul |
Token ID | 12041 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Osw | +1.121 |
med | +1.085 |
gest | +1.064 |
appropriately | +1.058 |
ifiable | +1.050 |
Neg logit contributions | |
zzo | -1.011 |
matured | -0.997 |
rhy | -0.953 |
Dise | -0.941 |
irit | -0.932 |
Token | Sol |
Token ID | 4294 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
Osw | +1.085 |
appropriately | +1.039 |
med | +1.029 |
gest | +1.024 |
ifiable | +1.018 |
Neg logit contributions | |
zzo | -0.898 |
matured | -0.855 |
rhy | -0.833 |
irit | -0.819 |
Dise | -0.803 |
Token | man |
Token ID | 805 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
zzo | +3.659 |
lang | +3.424 |
matured | +3.345 |
ago | +3.337 |
rhy | +3.334 |
Neg logit contributions | |
Osw | -2.228 |
appropriately | -1.936 |
elfare | -1.790 |
\": | -1.771 |
MPG | -1.761 |
Token | : |
Token ID | 25 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Osw | +0.460 |
appropriately | +0.425 |
med | +0.412 |
ifiable | +0.408 |
gest | +0.403 |
Neg logit contributions | |
zzo | -0.734 |
matured | -0.704 |
rhy | -0.693 |
irit | -0.680 |
Dise | -0.668 |
Token | Ed |
Token ID | 1717 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
zzo | +2.308 |
matured | +2.193 |
Dise | +2.186 |
rhy | +2.169 |
irit | +2.080 |
Neg logit contributions | |
Osw | -2.487 |
appropriately | -2.443 |
med | -2.365 |
ifiable | -2.359 |
gest | -2.344 |
Token | ibles |
Token ID | 18764 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
zzo | +5.758 |
matured | +5.650 |
gae | +5.495 |
irit | +5.451 |
dies | +5.240 |
Neg logit contributions | |
Osw | -12.480 |
appropriately | -11.965 |
\": | -11.334 |
med | -11.246 |
elfare | -11.152 |
Token | , |
Token ID | 11 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
zzo | +1.161 |
matured | +1.137 |
rhy | +1.105 |
irit | +1.083 |
Dise | +1.066 |
Neg logit contributions | |
Osw | -1.037 |
appropriately | -0.962 |
med | -0.962 |
gest | -0.953 |
ifiable | -0.945 |
Token | at |
Token ID | 379 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
zzo | +0.353 |
matured | +0.343 |
rhy | +0.333 |
irit | +0.326 |
Dise | +0.321 |
Neg logit contributions | |
Osw | -0.405 |
med | -0.382 |
appropriately | -0.379 |
gest | -0.378 |
ifiable | -0.375 |
Token | least |
Token ID | 1551 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
zzo | +1.714 |
matured | +1.673 |
rhy | +1.627 |
irit | +1.576 |
Dise | +1.554 |
Neg logit contributions | |
Osw | -2.318 |
med | -2.180 |
appropriately | -2.178 |
ifiable | -2.157 |
gest | -2.155 |
Token | back |
Token ID | 736 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
Osw | +2.275 |
med | +2.177 |
gest | +2.131 |
ifiable | +2.121 |
appropriately | +2.109 |
Neg logit contributions | |
zzo | -2.408 |
matured | -2.283 |
irit | -2.242 |
rhy | -2.236 |
Dise | -2.197 |
Token | Land |
Token ID | 6379 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
zzo | +0.646 |
matured | +0.628 |
rhy | +0.610 |
irit | +0.598 |
Dise | +0.590 |
Neg logit contributions | |
Osw | -0.671 |
med | -0.632 |
appropriately | -0.627 |
gest | -0.624 |
ifiable | -0.620 |
Token | sc |
Token ID | 1416 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Osw | +2.951 |
med | +2.888 |
appropriately | +2.792 |
gest | +2.791 |
oid | +2.746 |
Neg logit contributions | |
zzo | -2.738 |
matured | -2.645 |
rhy | -2.555 |
irit | -2.516 |
Dise | -2.476 |
Token | aping |
Token ID | 9269 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Osw | +1.551 |
med | +1.487 |
gest | +1.436 |
oid | +1.415 |
ifiable | +1.409 |
Neg logit contributions | |
zzo | -2.167 |
matured | -2.135 |
rhy | -2.080 |
Dise | -2.031 |
irit | -1.996 |
Token | Gold |
Token ID | 3561 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
zzo | +0.894 |
matured | +0.869 |
rhy | +0.844 |
irit | +0.829 |
Dise | +0.817 |
Neg logit contributions | |
Osw | -0.894 |
med | -0.840 |
appropriately | -0.833 |
gest | -0.829 |
ifiable | -0.825 |
Token | Coast |
Token ID | 8545 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
Osw | +0.348 |
med | +0.332 |
gest | +0.325 |
appropriately | +0.324 |
ifiable | +0.322 |
Neg logit contributions | |
zzo | -0.339 |
matured | -0.328 |
rhy | -0.318 |
irit | -0.313 |
Dise | -0.307 |
Token | professionally |
Token ID | 28049 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
zzo | +2.461 |
matured | +2.388 |
rhy | +2.335 |
irit | +2.263 |
Dise | +2.258 |
Neg logit contributions | |
Osw | -2.526 |
appropriately | -2.381 |
med | -2.359 |
gest | -2.348 |
ifiable | -2.345 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
matured | +8.226 |
zzo | +7.947 |
rhy | +7.591 |
Dise | +7.322 |
practise | +7.306 |
Neg logit contributions | |
Osw | -9.963 |
appropriately | -9.568 |
gest | -9.372 |
\": | -9.350 |
wk | -9.180 |
Token | Hillary |
Token ID | 20397 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
zzo | +3.854 |
matured | +3.600 |
irit | +3.559 |
rhy | +3.540 |
Rog | +3.474 |
Neg logit contributions | |
Osw | -4.133 |
appropriately | -3.734 |
ifiable | -3.729 |
gest | -3.693 |
med | -3.685 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
zzo | +1.016 |
matured | +0.981 |
rhy | +0.946 |
irit | +0.925 |
Dise | +0.906 |
Neg logit contributions | |
Osw | -1.352 |
med | -1.281 |
appropriately | -1.279 |
gest | -1.266 |
ifiable | -1.264 |
Token | 's |
Token ID | 338 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
zzo | +1.348 |
matured | +1.316 |
rhy | +1.274 |
irit | +1.238 |
Dise | +1.219 |
Neg logit contributions | |
Osw | -1.350 |
med | -1.274 |
appropriately | -1.264 |
gest | -1.254 |
ifiable | -1.252 |
Token | campaign |
Token ID | 1923 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Osw | +2.285 |
med | +2.181 |
gest | +2.155 |
appropriately | +2.137 |
ifiable | +2.133 |
Neg logit contributions | |
zzo | -1.743 |
matured | -1.672 |
irit | -1.620 |
rhy | -1.614 |
Dise | -1.574 |
Token | based |
Token ID | 1912 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
zzo | +1.518 |
matured | +1.497 |
rhy | +1.441 |
irit | +1.400 |
Dise | +1.373 |
Neg logit contributions | |
Osw | -1.662 |
med | -1.568 |
appropriately | -1.562 |
gest | -1.549 |
ifiable | -1.543 |
Token | on |
Token ID | 319 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
zzo | +0.685 |
matured | +0.668 |
rhy | +0.648 |
irit | +0.638 |
Dise | +0.631 |
Neg logit contributions | |
Osw | -0.611 |
med | -0.578 |
appropriately | -0.569 |
gest | -0.568 |
ifiable | -0.561 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
zzo | +0.830 |
matured | +0.806 |
rhy | +0.782 |
irit | +0.768 |
Dise | +0.756 |
Neg logit contributions | |
Osw | -0.896 |
med | -0.845 |
appropriately | -0.837 |
gest | -0.834 |
ifiable | -0.829 |
Token | exploits |
Token ID | 27062 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
zzo | +0.294 |
matured | +0.285 |
rhy | +0.276 |
irit | +0.271 |
Dise | +0.266 |
Neg logit contributions | |
Osw | -0.358 |
med | -0.339 |
appropriately | -0.336 |
gest | -0.335 |
ifiable | -0.333 |
Token | of |
Token ID | 286 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Osw | +0.144 |
med | +0.136 |
gest | +0.133 |
appropriately | +0.132 |
oid | +0.132 |
Neg logit contributions | |
zzo | -0.160 |
matured | -0.154 |
rhy | -0.151 |
Dise | -0.148 |
irit | -0.147 |
Token | Ed |
Token ID | 1717 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
zzo | +1.574 |
matured | +1.533 |
rhy | +1.489 |
irit | +1.461 |
Dise | +1.432 |
Neg logit contributions | |
Osw | -1.686 |
med | -1.601 |
appropriately | -1.593 |
gest | -1.585 |
ifiable | -1.578 |
Token | Ge |
Token ID | 10082 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
zzo | +8.499 |
rhy | +8.129 |
matured | +8.093 |
gae | +8.044 |
irit | +8.011 |
Neg logit contributions | |
appropriately | -8.649 |
Osw | -8.556 |
\": | -8.547 |
gest | -7.989 |
oid | -7.905 |
Token | in |
Token ID | 259 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
zzo | +1.546 |
matured | +1.496 |
rhy | +1.453 |
irit | +1.433 |
Dise | +1.405 |
Neg logit contributions | |
Osw | -1.577 |
med | -1.483 |
appropriately | -1.467 |
gest | -1.461 |
ifiable | -1.457 |
Token | , |
Token ID | 11 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
zzo | +0.807 |
matured | +0.787 |
rhy | +0.766 |
irit | +0.755 |
Dise | +0.745 |
Neg logit contributions | |
Osw | -0.655 |
med | -0.612 |
appropriately | -0.604 |
gest | -0.602 |
ifiable | -0.596 |
Token | the |
Token ID | 262 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
zzo | +2.056 |
matured | +2.009 |
rhy | +1.948 |
irit | +1.895 |
Dise | +1.872 |
Neg logit contributions | |
Osw | -2.282 |
med | -2.175 |
appropriately | -2.152 |
gest | -2.149 |
ifiable | -2.136 |
Token | cannibal |
Token ID | 39904 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
zzo | +1.435 |
matured | +1.400 |
rhy | +1.360 |
irit | +1.323 |
Dise | +1.307 |
Neg logit contributions | |
Osw | -1.617 |
med | -1.525 |
appropriately | -1.521 |
gest | -1.513 |
ifiable | -1.503 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
Osw | +1.321 |
med | +1.252 |
appropriately | +1.226 |
gest | +1.225 |
oid | +1.211 |
Neg logit contributions | |
zzo | -1.341 |
matured | -1.285 |
rhy | -1.246 |
irit | -1.240 |
Dise | -1.225 |
Token | site |
Token ID | 2524 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
Osw | +3.613 |
med | +3.513 |
oid | +3.422 |
appropriately | +3.361 |
\": | +3.355 |
Neg logit contributions | |
zzo | -4.481 |
matured | -4.243 |
irit | -4.193 |
Dise | -4.163 |
rhy | -4.126 |
Token | is |
Token ID | 318 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Osw | +3.939 |
med | +3.677 |
oid | +3.629 |
gest | +3.597 |
appropriately | +3.589 |
Neg logit contributions | |
zzo | -5.603 |
matured | -5.416 |
irit | -5.333 |
Dise | -5.266 |
sqor | -5.170 |
Token | " |
Token ID | 366 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
Osw | +1.322 |
med | +1.237 |
appropriately | +1.208 |
gest | +1.206 |
\": | +1.193 |
Neg logit contributions | |
zzo | -1.949 |
matured | -1.878 |
irit | -1.827 |
rhy | -1.825 |
Dise | -1.812 |
Token | We |
Token ID | 1135 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
zzo | +3.116 |
matured | +3.030 |
rhy | +2.931 |
irit | +2.922 |
Dise | +2.826 |
Neg logit contributions | |
Osw | -3.419 |
ifiable | -3.121 |
appropriately | -3.099 |
med | -3.092 |
oid | -3.067 |
Token | open |
Token ID | 1280 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
zzo | +0.075 |
matured | +0.073 |
rhy | +0.071 |
irit | +0.069 |
Dise | +0.068 |
Neg logit contributions | |
Osw | -0.075 |
med | -0.071 |
appropriately | -0.070 |
gest | -0.070 |
ifiable | -0.069 |
Token | governments |
Token ID | 6905 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
matured | +7.506 |
zzo | +7.387 |
rhy | +7.367 |
valves | +7.147 |
closed | +7.019 |
Neg logit contributions | |
Osw | -9.872 |
appropriately | -9.236 |
med | -9.147 |
sonian | -9.139 |
gest | -9.060 |
Token | ". |
Token ID | 1911 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
zzo | +6.076 |
matured | +6.026 |
rhy | +5.859 |
valves | +5.481 |
Dise | +5.471 |
Neg logit contributions | |
Osw | -7.367 |
gest | -6.864 |
appropriately | -6.856 |
med | -6.766 |
ifiable | -6.705 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
zzo | +0.632 |
matured | +0.619 |
rhy | +0.598 |
irit | +0.587 |
Dise | +0.576 |
Neg logit contributions | |
Osw | -0.599 |
med | -0.563 |
gest | -0.556 |
appropriately | -0.549 |
oid | -0.548 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Osw | +0.183 |
appropriately | +0.173 |
med | +0.168 |
ifiable | +0.167 |
gest | +0.166 |
Neg logit contributions | |
zzo | -0.171 |
matured | -0.160 |
rhy | -0.159 |
irit | -0.154 |
Dise | -0.151 |
Token | Another |
Token ID | 6610 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
zzo | +0.883 |
matured | +0.855 |
rhy | +0.832 |
irit | +0.822 |
Dise | +0.803 |
Neg logit contributions | |
Osw | -0.865 |
med | -0.805 |
appropriately | -0.802 |
gest | -0.795 |
ifiable | -0.795 |
Token | back |
Token ID | 736 |
Feature activation | +6.23e+00 |
Pos logit contributions | |
matured | +4.650 |
zzo | +4.585 |
rhy | +4.451 |
irit | +4.122 |
valves | +4.067 |
Neg logit contributions | |
Osw | -7.198 |
appropriately | -6.955 |
\": | -6.823 |
ifiable | -6.805 |
med | -6.690 |
Token | on |
Token ID | 319 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
zzo | +3.862 |
matured | +3.745 |
rhy | +3.664 |
irit | +3.562 |
Dise | +3.455 |
Neg logit contributions | |
Osw | -4.325 |
appropriately | -4.097 |
gest | -4.038 |
ifiable | -4.037 |
med | -3.994 |
Token | Europe |
Token ID | 2031 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
Osw | +1.477 |
med | +1.386 |
gest | +1.363 |
ifiable | +1.352 |
appropriately | +1.345 |
Neg logit contributions | |
zzo | -1.453 |
matured | -1.390 |
rhy | -1.343 |
irit | -1.341 |
Dise | -1.325 |
Token | would |
Token ID | 561 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
Osw | +3.240 |
med | +3.072 |
gest | +2.997 |
appropriately | +2.964 |
oid | +2.955 |
Neg logit contributions | |
zzo | -3.352 |
matured | -3.220 |
irit | -3.154 |
rhy | -3.130 |
Dise | -3.050 |
Token | risk |
Token ID | 2526 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Osw | +2.194 |
med | +2.094 |
gest | +2.080 |
appropriately | +2.053 |
oid | +2.048 |
Neg logit contributions | |
zzo | -1.986 |
matured | -1.901 |
irit | -1.826 |
rhy | -1.811 |
Dise | -1.800 |
Token | rev |
Token ID | 2710 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
zzo | +1.864 |
matured | +1.834 |
rhy | +1.789 |
irit | +1.727 |
Dise | +1.696 |
Neg logit contributions | |
Osw | -2.363 |
med | -2.244 |
appropriately | -2.241 |
gest | -2.217 |
ifiable | -2.204 |
Token | iving |
Token ID | 1412 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
zzo | +5.564 |
irit | +5.493 |
matured | +5.253 |
gae | +5.014 |
lang | +4.948 |
Neg logit contributions | |
Osw | -11.664 |
\": | -11.148 |
appropriately | -11.050 |
gest | -10.810 |
ifiable | -10.756 |
Token | the |
Token ID | 262 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
zzo | +3.757 |
matured | +3.722 |
rhy | +3.634 |
irit | +3.496 |
Dise | +3.409 |
Neg logit contributions | |
Osw | -4.563 |
appropriately | -4.391 |
\": | -4.338 |
gest | -4.331 |
med | -4.327 |
Token | � |
Token ID | 564 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
zzo | +2.379 |
matured | +2.339 |
rhy | +2.289 |
irit | +2.205 |
Dise | +2.186 |
Neg logit contributions | |
Osw | -2.765 |
appropriately | -2.643 |
med | -2.635 |
\": | -2.588 |
gest | -2.587 |
Token | � |
Token ID | 246 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
zzo | +0.707 |
matured | +0.682 |
rhy | +0.658 |
irit | +0.644 |
Dise | +0.633 |
Neg logit contributions | |
Osw | -1.020 |
med | -0.970 |
appropriately | -0.961 |
gest | -0.959 |
ifiable | -0.953 |
Token | German |
Token ID | 16010 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
zzo | +0.673 |
matured | +0.654 |
rhy | +0.636 |
irit | +0.625 |
Dise | +0.616 |
Neg logit contributions | |
Osw | -0.640 |
med | -0.602 |
appropriately | -0.595 |
gest | -0.594 |
ifiable | -0.589 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
zzo | +2.120 |
rhy | +1.913 |
matured | +1.903 |
irit | +1.878 |
lang | +1.859 |
Neg logit contributions | |
Osw | -2.658 |
appropriately | -2.602 |
ifiable | -2.482 |
anked | -2.449 |
med | -2.443 |
Token | Other |
Token ID | 3819 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
zzo | +1.569 |
matured | +1.471 |
rhy | +1.426 |
irit | +1.392 |
Dise | +1.378 |
Neg logit contributions | |
Osw | -2.894 |
med | -2.782 |
appropriately | -2.779 |
ifiable | -2.769 |
gest | -2.765 |
Token | filming |
Token ID | 17691 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
zzo | +2.441 |
matured | +2.385 |
rhy | +2.210 |
branch | +2.131 |
irit | +2.099 |
Neg logit contributions | |
Osw | -4.417 |
appropriately | -4.089 |
elfare | -3.947 |
med | -3.945 |
\": | -3.941 |
Token | locations |
Token ID | 7064 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
zzo | +2.077 |
matured | +2.064 |
rhy | +1.821 |
closed | +1.760 |
valves | +1.720 |
Neg logit contributions | |
Osw | -5.359 |
appropriately | -5.199 |
elfare | -5.114 |
oid | -5.104 |
hip | -5.098 |
Token | in |
Token ID | 287 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
zzo | +1.703 |
matured | +1.623 |
rhy | +1.598 |
irit | +1.534 |
lang | +1.467 |
Neg logit contributions | |
Osw | -2.187 |
appropriately | -2.081 |
ifiable | -2.023 |
\": | -2.007 |
gest | -1.995 |
Token | Massachusetts |
Token ID | 10140 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
zzo | +2.831 |
matured | +2.754 |
rhy | +2.659 |
irit | +2.613 |
Dise | +2.567 |
Neg logit contributions | |
Osw | -3.300 |
appropriately | -3.072 |
gest | -3.063 |
med | -3.062 |
ifiable | -3.047 |
Token | were |
Token ID | 547 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
matured | +4.054 |
zzo | +3.724 |
rhy | +3.614 |
closed | +3.575 |
branch | +3.117 |
Neg logit contributions | |
Osw | -13.262 |
appropriately | -12.840 |
mares | -12.516 |
elfare | -12.457 |
gest | -12.347 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
zzo | +2.600 |
matured | +2.384 |
rhy | +2.363 |
irit | +2.254 |
lang | +2.174 |
Neg logit contributions | |
Osw | -4.055 |
appropriately | -3.940 |
ifiable | -3.785 |
elfare | -3.757 |
gest | -3.742 |
Token | Y |
Token ID | 575 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
zzo | +1.273 |
matured | +1.237 |
rhy | +1.207 |
irit | +1.188 |
Dise | +1.171 |
Neg logit contributions | |
Osw | -1.086 |
med | -1.013 |
appropriately | -1.004 |
gest | -1.000 |
ifiable | -0.995 |
Token | aw |
Token ID | 707 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
zzo | +2.519 |
irit | +2.372 |
matured | +2.365 |
rhy | +2.347 |
lang | +2.327 |
Neg logit contributions | |
Osw | -1.789 |
appropriately | -1.598 |
MPG | -1.576 |
ifiable | -1.542 |
\": | -1.530 |
Token | key |
Token ID | 2539 |
Feature activation | +8.39e+00 |
Pos logit contributions | |
zzo | +2.651 |
rhy | +2.417 |
irit | +2.408 |
lang | +2.396 |
gae | +2.368 |
Neg logit contributions | |
Osw | -2.707 |
appropriately | -2.424 |
MPG | -2.397 |
\": | -2.359 |
ifiable | -2.348 |
Token | best |
Token ID | 1266 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
zzo | +0.800 |
matured | +0.783 |
rhy | +0.762 |
irit | +0.744 |
Dise | +0.732 |
Neg logit contributions | |
Osw | -0.849 |
med | -0.800 |
appropriately | -0.794 |
gest | -0.788 |
ifiable | -0.785 |
Token | example |
Token ID | 1672 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
zzo | +3.641 |
matured | +3.638 |
rhy | +3.576 |
irit | +3.388 |
Dise | +3.318 |
Neg logit contributions | |
Osw | -4.462 |
med | -4.227 |
appropriately | -4.202 |
gest | -4.145 |
\": | -4.127 |
Token | of |
Token ID | 286 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
zzo | +2.331 |
matured | +2.270 |
rhy | +2.199 |
irit | +2.143 |
Dise | +2.118 |
Neg logit contributions | |
Osw | -2.525 |
appropriately | -2.383 |
med | -2.381 |
gest | -2.372 |
ifiable | -2.346 |
Token | this |
Token ID | 428 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
matured | +3.452 |
zzo | +3.419 |
rhy | +3.326 |
irit | +3.195 |
Dise | +3.165 |
Neg logit contributions | |
Osw | -4.520 |
gest | -4.316 |
med | -4.305 |
appropriately | -4.304 |
oid | -4.242 |
Token | was |
Token ID | 373 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
zzo | +0.704 |
matured | +0.686 |
rhy | +0.667 |
irit | +0.654 |
Dise | +0.643 |
Neg logit contributions | |
Osw | -0.714 |
med | -0.672 |
appropriately | -0.666 |
gest | -0.664 |
ifiable | -0.658 |
Token | Ed |
Token ID | 1717 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
Osw | +1.166 |
med | +1.096 |
appropriately | +1.083 |
gest | +1.079 |
ifiable | +1.074 |
Neg logit contributions | |
zzo | -1.094 |
matured | -1.058 |
rhy | -1.026 |
irit | -1.013 |
Dise | -0.996 |
Token | Miliband |
Token ID | 38199 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
zzo | +6.782 |
irit | +6.599 |
rhy | +6.535 |
lang | +6.406 |
matured | +6.392 |
Neg logit contributions | |
appropriately | -9.684 |
Osw | -9.462 |
\": | -9.384 |
med | -8.915 |
hip | -8.895 |
Token | � |
Token ID | 447 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
zzo | +3.159 |
matured | +3.089 |
rhy | +3.064 |
irit | +2.942 |
Dise | +2.861 |
Neg logit contributions | |
Osw | -2.850 |
med | -2.666 |
appropriately | -2.664 |
ifiable | -2.641 |
gest | -2.620 |
Token | � |
Token ID | 247 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
zzo | +0.143 |
matured | +0.136 |
rhy | +0.131 |
irit | +0.128 |
Dise | +0.120 |
Neg logit contributions | |
Osw | -0.262 |
med | -0.245 |
ifiable | -0.245 |
appropriately | -0.244 |
gest | -0.241 |
Token | s |
Token ID | 82 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
Osw | +1.009 |
med | +0.957 |
gest | +0.942 |
appropriately | +0.939 |
ifiable | +0.924 |
Neg logit contributions | |
zzo | -1.168 |
matured | -1.138 |
rhy | -1.103 |
irit | -1.091 |
Dise | -1.081 |
Token | xen |
Token ID | 27132 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Osw | +4.058 |
med | +3.866 |
gest | +3.798 |
appropriately | +3.783 |
ifiable | +3.764 |
Neg logit contributions | |
zzo | -3.631 |
matured | -3.443 |
irit | -3.343 |
Dise | -3.310 |
rhy | -3.273 |
Token | Man |
Token ID | 1869 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
zzo | +2.792 |
matured | +2.707 |
rhy | +2.655 |
irit | +2.600 |
Dise | +2.573 |
Neg logit contributions | |
Osw | -2.810 |
appropriately | -2.721 |
gest | -2.705 |
med | -2.696 |
ifiable | -2.656 |
Token | Singh |
Token ID | 14403 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Osw | +0.428 |
med | +0.404 |
appropriately | +0.398 |
gest | +0.398 |
ifiable | +0.395 |
Neg logit contributions | |
zzo | -0.415 |
matured | -0.404 |
rhy | -0.393 |
irit | -0.385 |
Dise | -0.381 |
Token | Dal |
Token ID | 12348 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Osw | +0.108 |
med | +0.101 |
appropriately | +0.100 |
gest | +0.100 |
ifiable | +0.099 |
Neg logit contributions | |
zzo | -0.104 |
matured | -0.101 |
rhy | -0.098 |
irit | -0.096 |
Dise | -0.095 |
Token | al |
Token ID | 282 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
zzo | +0.395 |
matured | +0.384 |
rhy | +0.374 |
irit | +0.369 |
Dise | +0.363 |
Neg logit contributions | |
Osw | -0.364 |
med | -0.341 |
appropriately | -0.338 |
gest | -0.337 |
ifiable | -0.335 |
Token | ( |
Token ID | 357 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
zzo | +1.286 |
matured | +1.246 |
rhy | +1.218 |
irit | +1.197 |
Dise | +1.173 |
Neg logit contributions | |
Osw | -1.340 |
med | -1.267 |
appropriately | -1.262 |
gest | -1.258 |
ifiable | -1.247 |
Token | Ret |
Token ID | 9781 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
zzo | +1.726 |
matured | +1.672 |
rhy | +1.624 |
irit | +1.605 |
Dise | +1.574 |
Neg logit contributions | |
Osw | -1.712 |
med | -1.587 |
appropriately | -1.577 |
gest | -1.576 |
ifiable | -1.575 |
Token | d |
Token ID | 67 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
zzo | +8.804 |
Dise | +8.202 |
matured | +8.057 |
irit | +7.893 |
rhy | +7.839 |
Neg logit contributions | |
Osw | -8.582 |
\": | -8.263 |
appropriately | -8.048 |
gest | -7.750 |
ifiable | -7.666 |
Token | ) |
Token ID | 8 |
Feature activation | +9.12e+00 |
Pos logit contributions | |
zzo | +0.679 |
matured | +0.659 |
rhy | +0.640 |
irit | +0.628 |
Dise | +0.618 |
Neg logit contributions | |
Osw | -0.693 |
med | -0.656 |
appropriately | -0.645 |
gest | -0.644 |
ifiable | -0.640 |
Token | to |
Token ID | 284 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
zzo | +5.726 |
rhy | +5.581 |
matured | +5.481 |
irit | +5.311 |
Dise | +5.218 |
Neg logit contributions | |
Osw | -5.769 |
med | -5.568 |
appropriately | -5.556 |
gest | -5.551 |
ifiable | -5.447 |
Token | stir |
Token ID | 11240 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
zzo | +2.506 |
rhy | +2.482 |
matured | +2.472 |
irit | +2.325 |
Dise | +2.304 |
Neg logit contributions | |
Osw | -2.710 |
med | -2.557 |
appropriately | -2.540 |
gest | -2.532 |
oid | -2.492 |
Token | up |
Token ID | 510 |
Feature activation | +8.53e+00 |
Pos logit contributions | |
zzo | +2.342 |
matured | +2.252 |
rhy | +2.201 |
irit | +2.128 |
Dise | +2.060 |
Neg logit contributions | |
Osw | -3.639 |
gest | -3.445 |
med | -3.432 |
appropriately | -3.428 |
oid | -3.404 |
Token | a |
Token ID | 257 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
zzo | +1.740 |
matured | +1.695 |
rhy | +1.650 |
irit | +1.606 |
Dise | +1.585 |
Neg logit contributions | |
Osw | -2.003 |
appropriately | -1.889 |
med | -1.883 |
gest | -1.877 |
ifiable | -1.861 |
Token | sc |
Token ID | 629 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Osw | +0.623 |
med | +0.591 |
gest | +0.582 |
appropriately | +0.581 |
ifiable | +0.581 |
Neg logit contributions | |
zzo | -0.526 |
matured | -0.508 |
rhy | -0.491 |
irit | -0.485 |
Dise | -0.476 |
Token | int |
Token ID | 600 |
Feature activation | +9.13e+00 |
Pos logit contributions | |
zzo | +0.802 |
matured | +0.778 |
rhy | +0.756 |
irit | +0.746 |
Dise | +0.733 |
Neg logit contributions | |
Osw | -0.777 |
med | -0.722 |
appropriately | -0.720 |
gest | -0.716 |
ifiable | -0.706 |
Token | ill |
Token ID | 359 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
zzo | +4.271 |
matured | +3.928 |
irit | +3.917 |
rhy | +3.870 |
gae | +3.566 |
Neg logit contributions | |
Osw | -8.010 |
appropriately | -7.478 |
med | -7.403 |
\": | -7.352 |
gest | -7.309 |
Token | ating |
Token ID | 803 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
zzo | +0.618 |
matured | +0.605 |
rhy | +0.592 |
irit | +0.585 |
Dise | +0.578 |
Neg logit contributions | |
Osw | -0.310 |
med | -0.282 |
appropriately | -0.278 |
gest | -0.276 |
ifiable | -0.273 |
Token | Ev |
Token ID | 4319 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
Osw | +0.592 |
med | +0.560 |
gest | +0.551 |
appropriately | +0.551 |
ifiable | +0.549 |
Neg logit contributions | |
zzo | -0.503 |
matured | -0.487 |
rhy | -0.469 |
irit | -0.465 |
Dise | -0.455 |
Token | gen |
Token ID | 5235 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
zzo | +4.653 |
rhy | +4.146 |
matured | +4.042 |
gae | +4.005 |
irit | +3.777 |
Neg logit contributions | |
appropriately | -12.492 |
Osw | -12.388 |
\": | -12.331 |
ifiable | -11.841 |
oid | -11.775 |
Token | y |
Token ID | 88 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
zzo | +3.571 |
matured | +3.452 |
rhy | +3.413 |
irit | +3.396 |
Dise | +3.285 |
Neg logit contributions | |
Osw | -4.566 |
appropriately | -4.373 |
med | -4.282 |
ifiable | -4.259 |
gest | -4.240 |
Token | K |
Token ID | 509 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
zzo | +1.210 |
matured | +1.185 |
rhy | +1.153 |
irit | +1.140 |
Dise | +1.122 |
Neg logit contributions | |
Osw | -1.004 |
appropriately | -0.944 |
gest | -0.934 |
med | -0.932 |
ifiable | -0.925 |
Token | uz |
Token ID | 10277 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Osw | +2.168 |
med | +2.097 |
appropriately | +2.075 |
gest | +2.072 |
ifiable | +2.060 |
Neg logit contributions | |
zzo | -0.775 |
matured | -0.751 |
rhy | -0.698 |
irit | -0.667 |
Dise | -0.662 |
Token | net |
Token ID | 3262 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Osw | +2.296 |
med | +2.218 |
gest | +2.160 |
appropriately | +2.128 |
oid | +2.122 |
Neg logit contributions | |
zzo | -3.041 |
matured | -2.982 |
rhy | -2.900 |
irit | -2.859 |
Dise | -2.809 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Osw | +0.992 |
med | +0.938 |
appropriately | +0.926 |
gest | +0.920 |
ifiable | +0.916 |
Neg logit contributions | |
zzo | -1.105 |
matured | -1.076 |
rhy | -1.045 |
irit | -1.033 |
Dise | -1.025 |
Token | M |
Token ID | 337 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
zzo | +1.295 |
matured | +1.251 |
rhy | +1.219 |
irit | +1.195 |
Dise | +1.192 |
Neg logit contributions | |
Osw | -1.266 |
med | -1.192 |
appropriately | -1.185 |
gest | -1.176 |
ifiable | -1.174 |
Token | oom |
Token ID | 4207 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
zzo | +1.831 |
matured | +1.786 |
rhy | +1.749 |
irit | +1.747 |
Dise | +1.700 |
Neg logit contributions | |
Osw | -0.733 |
med | -0.646 |
gest | -0.643 |
appropriately | -0.640 |
ifiable | -0.634 |
Token | in |
Token ID | 259 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
zzo | +2.279 |
matured | +2.093 |
irit | +2.092 |
rhy | +2.059 |
gae | +1.967 |
Neg logit contributions | |
Osw | -3.359 |
appropriately | -3.141 |
\": | -3.047 |
gest | -3.044 |
ifiable | -3.038 |
Token | World |
Token ID | 2159 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
Osw | +1.213 |
med | +1.151 |
gest | +1.129 |
appropriately | +1.124 |
oid | +1.119 |
Neg logit contributions | |
zzo | -1.280 |
matured | -1.249 |
rhy | -1.209 |
irit | -1.196 |
Dise | -1.176 |
Token | opens |
Token ID | 9808 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
zzo | +0.623 |
matured | +0.606 |
rhy | +0.588 |
irit | +0.577 |
Dise | +0.568 |
Neg logit contributions | |
Osw | -0.652 |
med | -0.614 |
appropriately | -0.608 |
gest | -0.606 |
ifiable | -0.603 |
Token | for |
Token ID | 329 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
rhy | +6.986 |
matured | +6.910 |
zzo | +6.852 |
closed | +6.494 |
branch | +6.366 |
Neg logit contributions | |
Osw | -9.816 |
appropriately | -9.487 |
elfare | -9.255 |
\": | -9.225 |
ifiable | -9.221 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
zzo | +5.821 |
matured | +5.678 |
rhy | +5.659 |
practise | +5.373 |
closed | +5.349 |
Neg logit contributions | |
Osw | -7.149 |
appropriately | -6.966 |
ionic | -6.710 |
ifiable | -6.658 |
med | -6.559 |
Token | Summer |
Token ID | 10216 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
zzo | +2.426 |
matured | +2.388 |
rhy | +2.328 |
irit | +2.252 |
Dise | +2.245 |
Neg logit contributions | |
Osw | -2.375 |
appropriately | -2.257 |
ifiable | -2.213 |
med | -2.211 |
gest | -2.191 |
Token | season |
Token ID | 1622 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
zzo | +3.948 |
matured | +3.817 |
rhy | +3.692 |
irit | +3.609 |
Dise | +3.598 |
Neg logit contributions | |
Osw | -3.770 |
ifiable | -3.485 |
appropriately | -3.478 |
gest | -3.452 |
\": | -3.425 |
Token | . |
Token ID | 13 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
zzo | +1.937 |
matured | +1.882 |
rhy | +1.830 |
irit | +1.776 |
Dise | +1.742 |
Neg logit contributions | |
Osw | -2.052 |
med | -1.921 |
appropriately | -1.920 |
gest | -1.904 |
ifiable | -1.896 |
Token | interest |
Token ID | 1393 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
zzo | +4.618 |
rhy | +4.556 |
matured | +4.549 |
irit | +4.295 |
branch | +4.074 |
Neg logit contributions | |
Osw | -6.429 |
appropriately | -6.206 |
gest | -6.103 |
med | -6.087 |
\": | -6.053 |
Token | litigation |
Token ID | 19284 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
matured | +4.055 |
rhy | +4.030 |
zzo | +3.985 |
irit | +3.773 |
practise | +3.611 |
Neg logit contributions | |
Osw | -7.050 |
appropriately | -6.928 |
gest | -6.802 |
med | -6.756 |
\": | -6.675 |
Token | ( |
Token ID | 357 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
matured | +3.246 |
zzo | +3.244 |
rhy | +3.114 |
irit | +2.995 |
revolving | +2.897 |
Neg logit contributions | |
Osw | -4.173 |
appropriately | -4.045 |
\": | -3.969 |
gest | -3.964 |
med | -3.944 |
Token | P |
Token ID | 47 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
zzo | +3.201 |
matured | +3.060 |
rhy | +2.985 |
irit | +2.970 |
Dise | +2.894 |
Neg logit contributions | |
Osw | -3.416 |
med | -3.161 |
ifiable | -3.141 |
appropriately | -3.135 |
gest | -3.134 |
Token | IL |
Token ID | 4146 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
zzo | +1.989 |
matured | +1.892 |
irit | +1.861 |
rhy | +1.847 |
Dise | +1.725 |
Neg logit contributions | |
Osw | -3.765 |
appropriately | -3.559 |
med | -3.527 |
ifiable | -3.520 |
gest | -3.516 |
Token | ) |
Token ID | 8 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
zzo | +3.315 |
matured | +3.244 |
rhy | +3.136 |
irit | +3.090 |
Dise | +2.978 |
Neg logit contributions | |
Osw | -3.858 |
appropriately | -3.646 |
gest | -3.625 |
med | -3.607 |
\": | -3.589 |
Token | in |
Token ID | 287 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
matured | +6.789 |
zzo | +6.583 |
rhy | +6.331 |
revolving | +6.240 |
branch | +6.083 |
Neg logit contributions | |
appropriately | -9.891 |
Osw | -9.827 |
sonian | -9.560 |
\": | -9.518 |
gest | -9.504 |
Token | the |
Token ID | 262 |
Feature activation | +8.57e+00 |
Pos logit contributions | |
zzo | +4.419 |
rhy | +4.299 |
matured | +4.289 |
irit | +4.051 |
Dise | +3.967 |
Neg logit contributions | |
Osw | -5.584 |
ifiable | -5.404 |
med | -5.397 |
appropriately | -5.395 |
\": | -5.369 |
Token | high |
Token ID | 1029 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
zzo | +4.330 |
matured | +4.258 |
rhy | +4.238 |
irit | +3.961 |
Dise | +3.905 |
Neg logit contributions | |
Osw | -6.393 |
appropriately | -6.337 |
gest | -6.300 |
ifiable | -6.284 |
med | -6.280 |
Token | court |
Token ID | 2184 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
zzo | +1.497 |
matured | +1.431 |
rhy | +1.369 |
irit | +1.348 |
Dise | +1.322 |
Neg logit contributions | |
Osw | -2.588 |
med | -2.474 |
appropriately | -2.449 |
gest | -2.443 |
ifiable | -2.432 |
Token | . |
Token ID | 13 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
zzo | +3.050 |
matured | +2.978 |
rhy | +2.908 |
irit | +2.797 |
Dise | +2.701 |
Neg logit contributions | |
Osw | -3.701 |
appropriately | -3.535 |
med | -3.519 |
gest | -3.499 |
ifiable | -3.455 |
Token | world |
Token ID | 995 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
zzo | +0.376 |
matured | +0.362 |
rhy | +0.349 |
irit | +0.343 |
Dise | +0.336 |
Neg logit contributions | |
Osw | -0.540 |
med | -0.514 |
appropriately | -0.508 |
gest | -0.507 |
ifiable | -0.505 |
Token | for |
Token ID | 329 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
zzo | +3.893 |
matured | +3.778 |
rhy | +3.660 |
irit | +3.517 |
Dise | +3.501 |
Neg logit contributions | |
Osw | -4.400 |
appropriately | -4.083 |
gest | -4.007 |
ifiable | -4.006 |
med | -3.997 |
Token | this |
Token ID | 428 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
zzo | +2.357 |
matured | +2.342 |
rhy | +2.282 |
irit | +2.208 |
Dise | +2.130 |
Neg logit contributions | |
Osw | -2.895 |
appropriately | -2.699 |
med | -2.690 |
gest | -2.671 |
ifiable | -2.663 |
Token | reason |
Token ID | 1738 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
zzo | +0.672 |
matured | +0.650 |
rhy | +0.623 |
irit | +0.607 |
Dise | +0.590 |
Neg logit contributions | |
Osw | -1.208 |
med | -1.146 |
appropriately | -1.143 |
gest | -1.136 |
ifiable | -1.128 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
Osw | +0.808 |
med | +0.768 |
gest | +0.753 |
ifiable | +0.749 |
appropriately | +0.747 |
Neg logit contributions | |
zzo | -0.974 |
matured | -0.954 |
rhy | -0.927 |
irit | -0.916 |
Dise | -0.910 |
Token | Open |
Token ID | 4946 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
zzo | +2.753 |
matured | +2.623 |
rhy | +2.559 |
Dise | +2.535 |
irit | +2.520 |
Neg logit contributions | |
Osw | -2.916 |
appropriately | -2.721 |
med | -2.711 |
ifiable | -2.704 |
gest | -2.674 |
Token | ended |
Token ID | 4444 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
matured | +8.825 |
zzo | +8.775 |
rhy | +8.541 |
irit | +8.151 |
branch | +8.072 |
Neg logit contributions | |
Osw | -8.272 |
appropriately | -7.681 |
ifiable | -7.385 |
\": | -7.373 |
med | -7.247 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
zzo | +4.192 |
matured | +4.161 |
rhy | +4.088 |
irit | +3.890 |
Dise | +3.817 |
Neg logit contributions | |
Osw | -4.534 |
appropriately | -4.201 |
med | -4.118 |
ifiable | -4.105 |
gest | -4.089 |
Token | like |
Token ID | 588 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
zzo | +0.998 |
matured | +0.975 |
rhy | +0.945 |
irit | +0.921 |
Dise | +0.910 |
Neg logit contributions | |
Osw | -1.041 |
med | -0.974 |
appropriately | -0.971 |
gest | -0.965 |
ifiable | -0.958 |
Token | blocks |
Token ID | 7021 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
zzo | +2.735 |
matured | +2.676 |
rhy | +2.621 |
irit | +2.518 |
Dise | +2.513 |
Neg logit contributions | |
Osw | -2.872 |
med | -2.692 |
appropriately | -2.686 |
ifiable | -2.669 |
gest | -2.666 |
Token | and |
Token ID | 290 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Osw | +0.822 |
med | +0.783 |
appropriately | +0.767 |
gest | +0.764 |
ifiable | +0.763 |
Neg logit contributions | |
zzo | -0.920 |
matured | -0.892 |
rhy | -0.865 |
irit | -0.859 |
Dise | -0.850 |
Token | party |
Token ID | 2151 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
zzo | +0.810 |
matured | +0.791 |
rhy | +0.768 |
irit | +0.745 |
Dise | +0.735 |
Neg logit contributions | |
Osw | -0.933 |
med | -0.876 |
appropriately | -0.874 |
gest | -0.869 |
ifiable | -0.864 |
Token | still |
Token ID | 991 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
zzo | +0.450 |
matured | +0.440 |
rhy | +0.426 |
irit | +0.417 |
Dise | +0.411 |
Neg logit contributions | |
Osw | -0.464 |
med | -0.436 |
appropriately | -0.434 |
gest | -0.431 |
ifiable | -0.428 |
Token | needs |
Token ID | 2476 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
zzo | +0.497 |
matured | +0.486 |
rhy | +0.471 |
irit | +0.461 |
Dise | +0.454 |
Neg logit contributions | |
Osw | -0.493 |
med | -0.461 |
appropriately | -0.459 |
gest | -0.456 |
ifiable | -0.452 |
Token | a |
Token ID | 257 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
zzo | +2.489 |
matured | +2.455 |
rhy | +2.379 |
irit | +2.313 |
Dise | +2.246 |
Neg logit contributions | |
Osw | -3.029 |
appropriately | -2.860 |
med | -2.854 |
gest | -2.834 |
ifiable | -2.819 |
Token | major |
Token ID | 1688 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
zzo | +0.591 |
matured | +0.577 |
rhy | +0.559 |
irit | +0.545 |
Dise | +0.536 |
Neg logit contributions | |
Osw | -0.702 |
med | -0.662 |
appropriately | -0.660 |
gest | -0.655 |
ifiable | -0.650 |
Token | rev |
Token ID | 2710 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
zzo | +0.953 |
matured | +0.933 |
rhy | +0.910 |
irit | +0.887 |
Dise | +0.872 |
Neg logit contributions | |
Osw | -0.917 |
med | -0.861 |
appropriately | -0.859 |
gest | -0.848 |
ifiable | -0.844 |
Token | amp |
Token ID | 696 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
irit | +8.425 |
zzo | +8.331 |
matured | +8.194 |
gae | +7.753 |
rhy | +7.641 |
Neg logit contributions | |
Osw | -8.847 |
appropriately | -8.237 |
ifiable | -7.937 |
gest | -7.926 |
med | -7.781 |
Token | of |
Token ID | 286 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Osw | +0.609 |
med | +0.575 |
appropriately | +0.566 |
gest | +0.565 |
ifiable | +0.563 |
Neg logit contributions | |
zzo | -0.631 |
matured | -0.613 |
rhy | -0.595 |
irit | -0.588 |
Dise | -0.581 |
Token | its |
Token ID | 663 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Osw | +0.927 |
med | +0.884 |
appropriately | +0.871 |
gest | +0.866 |
ifiable | +0.864 |
Neg logit contributions | |
zzo | -0.746 |
matured | -0.715 |
rhy | -0.686 |
irit | -0.684 |
Dise | -0.674 |
Token | rhetoric |
Token ID | 13214 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Osw | +1.580 |
med | +1.514 |
gest | +1.487 |
appropriately | +1.486 |
ifiable | +1.478 |
Neg logit contributions | |
zzo | -1.334 |
matured | -1.276 |
rhy | -1.231 |
irit | -1.226 |
Dise | -1.210 |
Token | . |
Token ID | 13 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
zzo | +1.023 |
matured | +0.997 |
rhy | +0.969 |
irit | +0.947 |
Dise | +0.931 |
Neg logit contributions | |
Osw | -1.039 |
med | -0.974 |
appropriately | -0.969 |
gest | -0.963 |
ifiable | -0.954 |
Token | a |
Token ID | 257 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
zzo | +1.194 |
matured | +1.166 |
rhy | +1.132 |
irit | +1.104 |
Dise | +1.090 |
Neg logit contributions | |
Osw | -1.373 |
med | -1.295 |
appropriately | -1.288 |
gest | -1.281 |
ifiable | -1.268 |
Token | mass |
Token ID | 2347 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
zzo | +1.420 |
matured | +1.390 |
rhy | +1.353 |
irit | +1.312 |
Dise | +1.297 |
Neg logit contributions | |
Osw | -1.739 |
med | -1.631 |
appropriately | -1.630 |
gest | -1.613 |
ifiable | -1.596 |
Token | of |
Token ID | 286 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
zzo | +1.223 |
matured | +1.197 |
rhy | +1.165 |
irit | +1.133 |
Dise | +1.110 |
Neg logit contributions | |
Osw | -1.552 |
appropriately | -1.457 |
med | -1.456 |
gest | -1.449 |
\": | -1.424 |
Token | lies |
Token ID | 7363 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Osw | +0.527 |
med | +0.499 |
appropriately | +0.493 |
gest | +0.492 |
ifiable | +0.492 |
Neg logit contributions | |
zzo | -0.451 |
matured | -0.434 |
rhy | -0.419 |
irit | -0.415 |
Dise | -0.408 |
Token | , |
Token ID | 11 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
zzo | +0.229 |
matured | +0.223 |
rhy | +0.217 |
irit | +0.213 |
Dise | +0.210 |
Neg logit contributions | |
Osw | -0.204 |
med | -0.191 |
appropriately | -0.189 |
gest | -0.188 |
ifiable | -0.187 |
Token | ev |
Token ID | 819 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
zzo | +1.737 |
matured | +1.706 |
rhy | +1.658 |
irit | +1.603 |
Dise | +1.589 |
Neg logit contributions | |
Osw | -2.127 |
appropriately | -2.006 |
med | -1.997 |
gest | -1.985 |
ifiable | -1.963 |
Token | asions |
Token ID | 39327 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
zzo | +6.156 |
irit | +5.734 |
matured | +5.629 |
lang | +5.360 |
rhy | +5.329 |
Neg logit contributions | |
Osw | -10.998 |
appropriately | -10.527 |
\": | -10.382 |
meal | -10.167 |
MPG | -9.977 |
Token | , |
Token ID | 11 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
Osw | +0.166 |
med | +0.157 |
ifiable | +0.154 |
gest | +0.153 |
oid | +0.153 |
Neg logit contributions | |
zzo | -0.202 |
matured | -0.197 |
rhy | -0.191 |
irit | -0.189 |
Dise | -0.188 |
Token | folly |
Token ID | 43411 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
zzo | +0.517 |
matured | +0.502 |
rhy | +0.486 |
irit | +0.478 |
Dise | +0.470 |
Neg logit contributions | |
Osw | -0.574 |
med | -0.542 |
appropriately | -0.536 |
gest | -0.535 |
ifiable | -0.532 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
zzo | +0.375 |
matured | +0.366 |
rhy | +0.355 |
irit | +0.351 |
Dise | +0.346 |
Neg logit contributions | |
Osw | -0.313 |
med | -0.294 |
gest | -0.289 |
appropriately | -0.289 |
ifiable | -0.287 |
Token | hatred |
Token ID | 13763 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
zzo | +0.136 |
matured | +0.131 |
rhy | +0.127 |
irit | +0.125 |
Dise | +0.123 |
Neg logit contributions | |
Osw | -0.148 |
med | -0.140 |
appropriately | -0.138 |
gest | -0.138 |
ifiable | -0.137 |
Token | of |
Token ID | 286 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Osw | +3.547 |
med | +3.309 |
ifiable | +3.259 |
gest | +3.258 |
appropriately | +3.242 |
Neg logit contributions | |
zzo | -3.757 |
matured | -3.632 |
irit | -3.590 |
Dise | -3.542 |
gae | -3.468 |
Token | which |
Token ID | 543 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
zzo | +1.622 |
matured | +1.569 |
rhy | +1.515 |
irit | +1.470 |
Dise | +1.433 |
Neg logit contributions | |
Osw | -2.654 |
med | -2.530 |
appropriately | -2.516 |
gest | -2.500 |
ifiable | -2.494 |
Token | involved |
Token ID | 2950 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Osw | +1.112 |
med | +1.048 |
appropriately | +1.033 |
gest | +1.030 |
ifiable | +1.025 |
Neg logit contributions | |
zzo | -0.983 |
matured | -0.951 |
rhy | -0.916 |
irit | -0.909 |
Dise | -0.898 |
Token | kicking |
Token ID | 17997 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
Osw | +0.722 |
med | +0.682 |
appropriately | +0.672 |
gest | +0.671 |
ifiable | +0.669 |
Neg logit contributions | |
zzo | -0.634 |
matured | -0.615 |
rhy | -0.591 |
irit | -0.586 |
Dise | -0.578 |
Token | the |
Token ID | 262 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
zzo | +3.091 |
matured | +2.942 |
rhy | +2.923 |
irit | +2.840 |
Dise | +2.728 |
Neg logit contributions | |
Osw | -3.764 |
appropriately | -3.580 |
gest | -3.526 |
med | -3.524 |
\": | -3.522 |
Token | public |
Token ID | 1171 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
zzo | +3.690 |
matured | +3.562 |
rhy | +3.537 |
irit | +3.311 |
Dise | +3.281 |
Neg logit contributions | |
Osw | -4.769 |
appropriately | -4.549 |
gest | -4.486 |
med | -4.472 |
\": | -4.439 |
Token | out |
Token ID | 503 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
rhy | +7.140 |
zzo | +6.938 |
matured | +6.937 |
branch | +6.779 |
revolving | +6.685 |
Neg logit contributions | |
Osw | -9.585 |
appropriately | -9.027 |
med | -9.000 |
\": | -8.871 |
gest | -8.790 |
Token | -- |
Token ID | 1377 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
zzo | +2.404 |
matured | +2.314 |
rhy | +2.281 |
irit | +2.184 |
Dise | +2.167 |
Neg logit contributions | |
Osw | -2.688 |
med | -2.517 |
appropriately | -2.500 |
gest | -2.488 |
ifiable | -2.478 |
Token | he |
Token ID | 339 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
zzo | +0.628 |
matured | +0.609 |
rhy | +0.592 |
irit | +0.581 |
Dise | +0.571 |
Neg logit contributions | |
Osw | -0.690 |
med | -0.651 |
appropriately | -0.646 |
gest | -0.644 |
ifiable | -0.640 |
Token | even |
Token ID | 772 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
zzo | +0.278 |
matured | +0.271 |
rhy | +0.263 |
irit | +0.256 |
Dise | +0.251 |
Neg logit contributions | |
Osw | -0.302 |
med | -0.284 |
appropriately | -0.282 |
gest | -0.280 |
ifiable | -0.279 |
Token | noted |
Token ID | 4367 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
Osw | +0.910 |
med | +0.859 |
appropriately | +0.849 |
gest | +0.847 |
ifiable | +0.842 |
Neg logit contributions | |
zzo | -0.886 |
matured | -0.859 |
rhy | -0.833 |
irit | -0.823 |
Dise | -0.811 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Osw | +2.577 |
med | +2.434 |
gest | +2.396 |
ifiable | +2.358 |
appropriately | +2.358 |
Neg logit contributions | |
zzo | -3.719 |
matured | -3.676 |
rhy | -3.571 |
irit | -3.512 |
Dise | -3.494 |
Token | www |
Token ID | 2503 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
zzo | +1.884 |
matured | +1.812 |
rhy | +1.753 |
irit | +1.739 |
Dise | +1.692 |
Neg logit contributions | |
Osw | -2.134 |
appropriately | -1.975 |
med | -1.969 |
ifiable | -1.956 |
gest | -1.953 |
Token | . |
Token ID | 13 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
zzo | +0.633 |
matured | +0.583 |
rhy | +0.578 |
irit | +0.571 |
lang | +0.558 |
Neg logit contributions | |
Osw | -0.720 |
appropriately | -0.682 |
med | -0.654 |
ifiable | -0.652 |
gest | -0.644 |
Token | board |
Token ID | 3526 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
Osw | +0.284 |
med | +0.269 |
appropriately | +0.263 |
gest | +0.263 |
ifiable | +0.260 |
Neg logit contributions | |
zzo | -0.387 |
matured | -0.379 |
rhy | -0.370 |
irit | -0.362 |
Dise | -0.360 |
Token | game |
Token ID | 6057 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
med | +2.765 |
Osw | +2.722 |
gest | +2.712 |
oid | +2.583 |
appropriately | +2.571 |
Neg logit contributions | |
zzo | -5.409 |
matured | -5.347 |
rhy | -5.218 |
Dise | -5.177 |
irit | -5.108 |
Token | ge |
Token ID | 469 |
Feature activation | -1.62e+01 |
Pos logit contributions | |
med | +1.376 |
Osw | +1.375 |
gest | +1.335 |
oid | +1.264 |
ifiable | +1.236 |
Neg logit contributions | |
matured | -3.436 |
zzo | -3.424 |
rhy | -3.343 |
Dise | -3.317 |
irit | -3.274 |
Token | ek |
Token ID | 988 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
med | +5.256 |
oid | +5.025 |
gest | +4.795 |
wk | +4.753 |
hip | +4.530 |
Neg logit contributions | |
exting | -15.387 |
Dise | -15.197 |
matured | -15.141 |
sqor | -14.909 |
Interstitial | -14.742 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
med | +4.265 |
Osw | +4.241 |
gest | +4.152 |
oid | +4.078 |
ifiable | +3.983 |
Neg logit contributions | |
matured | -6.093 |
zzo | -5.977 |
rhy | -5.862 |
Dise | -5.830 |
irit | -5.725 |
Token | com |
Token ID | 785 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
Osw | +3.073 |
med | +2.961 |
gest | +2.891 |
appropriately | +2.847 |
ifiable | +2.832 |
Neg logit contributions | |
zzo | -4.174 |
matured | -4.153 |
rhy | -4.027 |
irit | -3.965 |
Dise | -3.941 |
Token | / |
Token ID | 14 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
Osw | +2.123 |
med | +1.973 |
appropriately | +1.945 |
gest | +1.939 |
ifiable | +1.923 |
Neg logit contributions | |
zzo | -3.082 |
matured | -3.011 |
rhy | -2.936 |
irit | -2.895 |
Dise | -2.860 |
Token | thread |
Token ID | 16663 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
Osw | +2.443 |
med | +2.435 |
gest | +2.406 |
oid | +2.376 |
appropriately | +2.340 |
Neg logit contributions | |
zzo | -1.510 |
matured | -1.508 |
rhy | -1.438 |
Dise | -1.390 |
irit | -1.360 |
Token | Arab |
Token ID | 4498 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
Osw | +0.858 |
med | +0.809 |
appropriately | +0.798 |
gest | +0.797 |
ifiable | +0.792 |
Neg logit contributions | |
zzo | -0.806 |
matured | -0.780 |
rhy | -0.755 |
irit | -0.746 |
Dise | -0.735 |
Token | League |
Token ID | 4041 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
Osw | +3.708 |
med | +3.541 |
gest | +3.523 |
oid | +3.518 |
ifiable | +3.461 |
Neg logit contributions | |
zzo | -3.101 |
matured | -2.935 |
irit | -2.840 |
rhy | -2.835 |
Dise | -2.816 |
Token | and |
Token ID | 290 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Osw | +3.457 |
med | +3.295 |
gest | +3.232 |
appropriately | +3.231 |
ifiable | +3.201 |
Neg logit contributions | |
zzo | -3.333 |
matured | -3.164 |
irit | -3.113 |
rhy | -3.082 |
Dise | -3.062 |
Token | Organisation |
Token ID | 30801 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
Osw | +1.682 |
med | +1.589 |
appropriately | +1.564 |
gest | +1.558 |
ifiable | +1.548 |
Neg logit contributions | |
zzo | -1.680 |
matured | -1.614 |
rhy | -1.574 |
irit | -1.555 |
Dise | -1.538 |
Token | of |
Token ID | 286 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
Osw | +1.732 |
med | +1.632 |
gest | +1.603 |
appropriately | +1.600 |
ifiable | +1.587 |
Neg logit contributions | |
zzo | -2.041 |
matured | -1.975 |
rhy | -1.933 |
irit | -1.911 |
Dise | -1.876 |
Token | Islamic |
Token ID | 5533 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
Osw | +3.230 |
med | +3.059 |
gest | +3.029 |
appropriately | +2.988 |
ifiable | +2.969 |
Neg logit contributions | |
zzo | -4.160 |
matured | -4.072 |
rhy | -4.032 |
irit | -3.978 |
gae | -3.825 |
Token | Co |
Token ID | 1766 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
Osw | +7.460 |
oid | +7.182 |
med | +7.018 |
ification | +6.912 |
ifiable | +6.398 |
Neg logit contributions | |
zzo | -12.003 |
sqor | -11.545 |
matured | -11.526 |
irit | -11.462 |
rhy | -11.352 |
Token | - |
Token ID | 12 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
Osw | +2.433 |
gest | +2.289 |
med | +2.282 |
ifiable | +2.235 |
appropriately | +2.223 |
Neg logit contributions | |
zzo | -3.849 |
matured | -3.785 |
rhy | -3.693 |
Dise | -3.593 |
irit | -3.586 |
Token | operation |
Token ID | 27184 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Osw | +2.682 |
med | +2.625 |
oid | +2.490 |
ifiable | +2.442 |
appropriately | +2.440 |
Neg logit contributions | |
zzo | -6.139 |
matured | -5.984 |
rhy | -5.893 |
irit | -5.813 |
Dise | -5.661 |
Token | and |
Token ID | 290 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
Osw | +1.220 |
med | +1.148 |
appropriately | +1.132 |
gest | +1.130 |
ifiable | +1.122 |
Neg logit contributions | |
zzo | -1.282 |
matured | -1.241 |
rhy | -1.206 |
irit | -1.196 |
Dise | -1.177 |
Token | Gulf |
Token ID | 12108 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Osw | +2.741 |
med | +2.605 |
appropriately | +2.583 |
gest | +2.570 |
ifiable | +2.552 |
Neg logit contributions | |
zzo | -1.960 |
matured | -1.878 |
rhy | -1.814 |
irit | -1.790 |
Dise | -1.733 |
Token | was |
Token ID | 373 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
Osw | +1.764 |
med | +1.669 |
appropriately | +1.649 |
gest | +1.633 |
ifiable | +1.632 |
Neg logit contributions | |
zzo | -1.698 |
matured | -1.634 |
irit | -1.592 |
rhy | -1.579 |
Dise | -1.567 |
Token | responsible |
Token ID | 4497 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
Osw | +4.490 |
med | +4.292 |
appropriately | +4.207 |
ifiable | +4.205 |
gest | +4.173 |
Neg logit contributions | |
zzo | -4.281 |
irit | -4.079 |
matured | -4.055 |
Dise | -3.989 |
sqor | -3.932 |
Token | . |
Token ID | 13 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
Osw | +3.324 |
med | +3.228 |
gest | +3.181 |
ifiable | +3.162 |
oid | +3.125 |
Neg logit contributions | |
zzo | -4.895 |
matured | -4.725 |
irit | -4.711 |
Dise | -4.634 |
rhy | -4.561 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Osw | +2.026 |
med | +1.897 |
gest | +1.865 |
appropriately | +1.856 |
oid | +1.845 |
Neg logit contributions | |
zzo | -2.147 |
matured | -2.120 |
rhy | -2.038 |
irit | -2.025 |
Dise | -1.944 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Osw | +1.686 |
appropriately | +1.572 |
med | +1.570 |
gest | +1.548 |
ifiable | +1.542 |
Neg logit contributions | |
zzo | -1.779 |
matured | -1.715 |
rhy | -1.676 |
irit | -1.642 |
Dise | -1.616 |
Token | TABLE |
Token ID | 38148 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
Osw | +1.579 |
med | +1.517 |
gest | +1.488 |
appropriately | +1.487 |
ifiable | +1.469 |
Neg logit contributions | |
zzo | -1.616 |
matured | -1.598 |
rhy | -1.537 |
irit | -1.510 |
Dise | -1.501 |
Token | 5 |
Token ID | 642 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
Osw | +5.230 |
gest | +5.179 |
med | +5.116 |
ifiable | +5.056 |
MPG | +5.026 |
Neg logit contributions | |
matured | -12.467 |
zzo | -12.441 |
irit | -12.050 |
rhy | -11.861 |
ataka | -11.722 |
Token |
|
Token ID | 198 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
Osw | +4.781 |
med | +4.371 |
gest | +4.270 |
oid | +4.258 |
ifiable | +4.257 |
Neg logit contributions | |
matured | -5.951 |
zzo | -5.922 |
irit | -5.721 |
rhy | -5.587 |
gae | -5.518 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Osw | +2.520 |
med | +2.369 |
gest | +2.334 |
appropriately | +2.333 |
ifiable | +2.316 |
Neg logit contributions | |
zzo | -2.853 |
matured | -2.785 |
rhy | -2.705 |
irit | -2.666 |
Dise | -2.631 |
Token | Table |
Token ID | 10962 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
Osw | +1.575 |
med | +1.513 |
appropriately | +1.483 |
gest | +1.481 |
ifiable | +1.463 |
Neg logit contributions | |
zzo | -1.714 |
matured | -1.692 |
rhy | -1.635 |
irit | -1.604 |
Dise | -1.592 |
Token | 5 |
Token ID | 642 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
Osw | +4.775 |
ifiable | +4.656 |
med | +4.605 |
gest | +4.527 |
oid | +4.359 |
Neg logit contributions | |
zzo | -8.495 |
matured | -8.265 |
irit | -8.071 |
Dise | -7.970 |
rhy | -7.930 |
Token | ml |
Token ID | 4029 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
zzo | +1.429 |
matured | +1.384 |
irit | +1.325 |
rhy | +1.318 |
Dise | +1.281 |
Neg logit contributions | |
Osw | -1.502 |
appropriately | -1.404 |
gest | -1.382 |
med | -1.382 |
ifiable | -1.381 |
Token | , |
Token ID | 837 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
zzo | +3.359 |
matured | +3.232 |
rhy | +3.141 |
irit | +3.073 |
Dise | +2.969 |
Neg logit contributions | |
Osw | -3.732 |
appropriately | -3.469 |
med | -3.415 |
gest | -3.409 |
ifiable | -3.347 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
zzo | +0.692 |
matured | +0.670 |
rhy | +0.648 |
irit | +0.632 |
Dise | +0.620 |
Neg logit contributions | |
Osw | -0.931 |
med | -0.882 |
appropriately | -0.876 |
gest | -0.872 |
ifiable | -0.867 |
Token | command |
Token ID | 3141 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
zzo | +1.234 |
matured | +1.201 |
rhy | +1.162 |
irit | +1.130 |
Dise | +1.106 |
Neg logit contributions | |
Osw | -1.487 |
med | -1.408 |
appropriately | -1.399 |
gest | -1.389 |
ifiable | -1.379 |
Token | becomes |
Token ID | 4329 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
Osw | +3.786 |
med | +3.651 |
oid | +3.611 |
\": | +3.576 |
gest | +3.575 |
Neg logit contributions | |
zzo | -3.915 |
matured | -3.834 |
Dise | -3.763 |
irit | -3.749 |
rhy | -3.696 |
Token | sl |
Token ID | 1017 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
Osw | +2.844 |
med | +2.708 |
gest | +2.643 |
appropriately | +2.642 |
oid | +2.628 |
Neg logit contributions | |
zzo | -3.716 |
matured | -3.616 |
irit | -3.527 |
rhy | -3.525 |
Dise | -3.521 |
Token | s |
Token ID | 82 |
Feature activation | -9.70e+00 |
Pos logit contributions | |
med | +6.621 |
gest | +6.371 |
oid | +6.300 |
wk | +6.187 |
Osw | +6.147 |
Neg logit contributions | |
Dise | -11.495 |
zzo | -11.317 |
matured | -11.300 |
rhy | -10.972 |
irit | -10.628 |
Token | invoke |
Token ID | 26342 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
med | +5.388 |
gest | +5.265 |
ifiable | +5.251 |
Osw | +5.238 |
oid | +5.228 |
Neg logit contributions | |
zzo | -6.810 |
Dise | -6.501 |
matured | -6.458 |
irit | -6.317 |
rhy | -6.304 |
Token | local |
Token ID | 1957 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Osw | +4.123 |
med | +4.009 |
gest | +3.887 |
oid | +3.886 |
ifiable | +3.852 |
Neg logit contributions | |
zzo | -4.582 |
matured | -4.389 |
irit | -4.361 |
Dise | -4.311 |
rhy | -4.246 |
Token | - |
Token ID | 532 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
Osw | +2.449 |
med | +2.369 |
oid | +2.324 |
gest | +2.303 |
appropriately | +2.297 |
Neg logit contributions | |
zzo | -2.824 |
matured | -2.712 |
irit | -2.646 |
rhy | -2.645 |
Dise | -2.622 |
Token | f |
Token ID | 69 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
Osw | +2.606 |
med | +2.512 |
gest | +2.465 |
oid | +2.436 |
ifiable | +2.402 |
Neg logit contributions | |
zzo | -7.404 |
matured | -7.299 |
Dise | -7.195 |
rhy | -7.126 |
irit | -7.063 |
Token | ) |
Token ID | 1267 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
Osw | +2.407 |
med | +2.348 |
gest | +2.291 |
appropriately | +2.277 |
oid | +2.275 |
Neg logit contributions | |
zzo | -2.753 |
matured | -2.718 |
rhy | -2.620 |
Dise | -2.591 |
irit | -2.582 |
Token | to |
Token ID | 284 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
zzo | +3.383 |
matured | +3.256 |
rhy | +3.186 |
irit | +3.105 |
Dise | +2.990 |
Neg logit contributions | |
Osw | -4.413 |
appropriately | -4.133 |
med | -4.108 |
gest | -4.075 |
\": | -4.048 |
Token | the |
Token ID | 262 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
Osw | +0.047 |
med | +0.044 |
appropriately | +0.044 |
gest | +0.044 |
ifiable | +0.043 |
Neg logit contributions | |
zzo | -0.044 |
matured | -0.043 |
rhy | -0.042 |
irit | -0.041 |
Dise | -0.041 |
Token | 19 |
Token ID | 678 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
Osw | +1.869 |
med | +1.770 |
gest | +1.738 |
ifiable | +1.730 |
appropriately | +1.729 |
Neg logit contributions | |
zzo | -1.976 |
matured | -1.918 |
rhy | -1.859 |
irit | -1.852 |
Dise | -1.822 |
Token | th |
Token ID | 400 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
Osw | +2.747 |
med | +2.677 |
gest | +2.670 |
oid | +2.487 |
ifiable | +2.460 |
Neg logit contributions | |
zzo | -7.314 |
matured | -7.283 |
rhy | -7.030 |
irit | -6.998 |
Dise | -6.990 |
Token | partition |
Token ID | 18398 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
Osw | +2.522 |
med | +2.406 |
ifiable | +2.392 |
gest | +2.379 |
oid | +2.344 |
Neg logit contributions | |
zzo | -3.674 |
matured | -3.587 |
irit | -3.440 |
rhy | -3.431 |
Dise | -3.411 |
Token | (/ |
Token ID | 50247 |
Feature activation | -8.39e+00 |
Pos logit contributions | |
Osw | +5.751 |
oid | +5.651 |
med | +5.560 |
ifiable | +5.379 |
hip | +5.355 |
Neg logit contributions | |
zzo | -11.526 |
matured | -11.420 |
irit | -11.070 |
Dise | -11.057 |
gae | -10.767 |
Token | dev |
Token ID | 7959 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
med | +4.044 |
Osw | +3.826 |
oid | +3.799 |
gest | +3.726 |
wk | +3.622 |
Neg logit contributions | |
zzo | -6.803 |
matured | -6.704 |
rhy | -6.588 |
Dise | -6.464 |
irit | -6.439 |
Token | / |
Token ID | 14 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
zzo | +1.242 |
matured | +1.169 |
rhy | +1.157 |
irit | +1.134 |
lang | +1.118 |
Neg logit contributions | |
Osw | -1.111 |
appropriately | -1.034 |
med | -0.991 |
gest | -0.982 |
ifiable | -0.978 |
Token | block |
Token ID | 9967 |
Feature activation | -8.02e+00 |
Pos logit contributions | |
Osw | +1.223 |
med | +1.177 |
gest | +1.142 |
oid | +1.129 |
ifiable | +1.127 |
Neg logit contributions | |
zzo | -1.755 |
matured | -1.731 |
rhy | -1.675 |
Dise | -1.667 |
irit | -1.652 |
Token | / |
Token ID | 14 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
Osw | +4.408 |
oid | +4.341 |
med | +4.310 |
ifiable | +4.202 |
meal | +4.155 |
Neg logit contributions | |
zzo | -5.989 |
matured | -5.891 |
Dise | -5.744 |
irit | -5.651 |
rhy | -5.583 |
Token | through |
Token ID | 832 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
zzo | +3.792 |
matured | +3.742 |
rhy | +3.590 |
irit | +3.425 |
gae | +3.287 |
Neg logit contributions | |
Osw | -3.964 |
appropriately | -3.772 |
gest | -3.738 |
oid | -3.627 |
\": | -3.609 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
zzo | +1.949 |
matured | +1.884 |
rhy | +1.841 |
irit | +1.777 |
Dise | +1.765 |
Neg logit contributions | |
Osw | -2.117 |
appropriately | -1.979 |
med | -1.953 |
gest | -1.946 |
ifiable | -1.945 |
Token | air |
Token ID | 1633 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
zzo | +0.486 |
matured | +0.464 |
rhy | +0.444 |
irit | +0.428 |
Dise | +0.418 |
Neg logit contributions | |
Osw | -1.075 |
med | -1.028 |
appropriately | -1.023 |
gest | -1.018 |
ifiable | -1.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
zzo | +0.243 |
matured | +0.237 |
rhy | +0.231 |
irit | +0.227 |
Dise | +0.224 |
Neg logit contributions | |
Osw | -0.198 |
med | -0.184 |
appropriately | -0.183 |
gest | -0.182 |
ifiable | -0.180 |
Token | Per |
Token ID | 2448 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
Osw | +1.930 |
med | +1.798 |
gest | +1.778 |
appropriately | +1.756 |
ifiable | +1.754 |
Neg logit contributions | |
zzo | -1.815 |
matured | -1.785 |
rhy | -1.724 |
irit | -1.704 |
Dise | -1.645 |
Token | Football |
Token ID | 9957 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
Osw | +6.688 |
med | +6.134 |
ifiable | +6.022 |
oid | +5.931 |
gest | +5.888 |
Neg logit contributions | |
zzo | -7.565 |
matured | -7.524 |
irit | -7.316 |
rhy | -7.067 |
Dise | -7.058 |
Token | Outs |
Token ID | 46580 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
Osw | +6.408 |
gest | +5.820 |
med | +5.812 |
oid | +5.553 |
ifiable | +5.219 |
Neg logit contributions | |
matured | -11.916 |
sqor | -11.610 |
rhy | -11.548 |
irit | -11.422 |
zzo | -11.398 |
Token | iders |
Token ID | 4157 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
Osw | +3.034 |
med | +2.863 |
gest | +2.818 |
appropriately | +2.816 |
ifiable | +2.796 |
Neg logit contributions | |
zzo | -3.546 |
matured | -3.475 |
rhy | -3.386 |
irit | -3.320 |
Dise | -3.291 |
Token | chart |
Token ID | 8262 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
Osw | +3.359 |
med | +3.153 |
gest | +3.046 |
hip | +3.026 |
\": | +3.004 |
Neg logit contributions | |
zzo | -4.612 |
matured | -4.605 |
irit | -4.425 |
rhy | -4.380 |
Dise | -4.368 |
Token | ing |
Token ID | 278 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Osw | +3.656 |
med | +3.597 |
ifiable | +3.461 |
oid | +3.400 |
gest | +3.397 |
Neg logit contributions | |
zzo | -4.404 |
matured | -4.235 |
Dise | -4.110 |
irit | -4.084 |
rhy | -4.084 |
Token | , |
Token ID | 11 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Osw | +0.244 |
med | +0.230 |
appropriately | +0.227 |
gest | +0.227 |
ifiable | +0.226 |
Neg logit contributions | |
zzo | -0.237 |
matured | -0.230 |
rhy | -0.223 |
irit | -0.221 |
Dise | -0.217 |
Token | om |
Token ID | 296 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Osw | +0.559 |
med | +0.525 |
appropriately | +0.514 |
oid | +0.513 |
gest | +0.512 |
Neg logit contributions | |
zzo | -0.742 |
matured | -0.722 |
rhy | -0.703 |
irit | -0.694 |
Dise | -0.688 |
Token | ation |
Token ID | 341 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
Osw | +0.306 |
med | +0.281 |
appropriately | +0.273 |
gest | +0.272 |
ifiable | +0.270 |
Neg logit contributions | |
zzo | -0.621 |
matured | -0.609 |
rhy | -0.597 |
irit | -0.588 |
Dise | -0.583 |
Token | - |
Token ID | 12 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Osw | +2.679 |
med | +2.560 |
gest | +2.496 |
ifiable | +2.476 |
appropriately | +2.471 |
Neg logit contributions | |
zzo | -4.159 |
matured | -4.084 |
rhy | -3.977 |
Dise | -3.938 |
irit | -3.926 |
Token | rather |
Token ID | 34330 |
Feature activation | -9.64e+00 |
Pos logit contributions | |
Osw | +2.210 |
med | +2.180 |
appropriately | +2.138 |
gest | +2.127 |
oid | +2.087 |
Neg logit contributions | |
zzo | -2.007 |
matured | -1.977 |
rhy | -1.933 |
Dise | -1.888 |
irit | -1.850 |
Token | - |
Token ID | 12 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
med | +4.323 |
gest | +4.226 |
Osw | +4.207 |
ifiable | +4.158 |
oid | +4.152 |
Neg logit contributions | |
zzo | -8.104 |
matured | -8.010 |
Dise | -7.882 |
rhy | -7.755 |
irit | -7.640 |
Token | than |
Token ID | 14813 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
med | +2.410 |
Osw | +2.400 |
gest | +2.358 |
ifiable | +2.336 |
appropriately | +2.326 |
Neg logit contributions | |
zzo | -2.451 |
matured | -2.398 |
rhy | -2.356 |
Dise | -2.321 |
irit | -2.254 |
Token | - |
Token ID | 12 |
Feature activation | -9.17e+00 |
Pos logit contributions | |
med | +4.908 |
ifiable | +4.886 |
oid | +4.863 |
\": | +4.808 |
gest | +4.805 |
Neg logit contributions | |
Dise | -12.852 |
matured | -12.767 |
zzo | -12.709 |
exting | -12.651 |
sqor | -12.240 |
Token | bre |
Token ID | 4679 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
med | +5.937 |
gest | +5.800 |
hip | +5.730 |
ifiable | +5.701 |
oid | +5.696 |
Neg logit contributions | |
zzo | -6.012 |
matured | -5.947 |
Dise | -5.936 |
rhy | -5.818 |
Siren | -5.664 |
Token | xit |
Token ID | 10198 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Osw | +3.476 |
med | +3.301 |
appropriately | +3.271 |
gest | +3.261 |
ifiable | +3.244 |
Neg logit contributions | |
zzo | -2.520 |
matured | -2.435 |
rhy | -2.351 |
irit | -2.304 |
Dise | -2.262 |
Token | - |
Token ID | 12 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
zzo | +1.604 |
matured | +1.514 |
rhy | +1.501 |
irit | +1.470 |
lang | +1.431 |
Neg logit contributions | |
Osw | -1.464 |
appropriately | -1.339 |
med | -1.295 |
ifiable | -1.281 |
gest | -1.274 |
Token | is |
Token ID | 271 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
zzo | +1.687 |
matured | +1.601 |
rhy | +1.530 |
irit | +1.523 |
Dise | +1.443 |
Neg logit contributions | |
Osw | -2.646 |
med | -2.447 |
appropriately | -2.439 |
ifiable | -2.436 |
gest | -2.429 |
Token | . |
Token ID | 13 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
Osw | +1.879 |
med | +1.769 |
gest | +1.745 |
oid | +1.731 |
ifiable | +1.722 |
Neg logit contributions | |
zzo | -2.233 |
matured | -2.158 |
rhy | -2.087 |
irit | -2.080 |
Dise | -2.046 |
Token | The |
Token ID | 383 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
zzo | +0.499 |
matured | +0.486 |
rhy | +0.472 |
irit | +0.464 |
Dise | +0.460 |
Neg logit contributions | |
Osw | -0.501 |
med | -0.471 |
appropriately | -0.471 |
gest | -0.467 |
ifiable | -0.465 |
Token | Angels |
Token ID | 17654 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Osw | +1.174 |
med | +1.112 |
gest | +1.092 |
appropriately | +1.091 |
ifiable | +1.083 |
Neg logit contributions | |
zzo | -1.149 |
matured | -1.114 |
rhy | -1.083 |
irit | -1.062 |
Dise | -1.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
zzo | +0.120 |
matured | +0.117 |
rhy | +0.113 |
irit | +0.112 |
Dise | +0.110 |
Neg logit contributions | |
Osw | -0.108 |
med | -0.101 |
appropriately | -0.100 |
gest | -0.099 |
ifiable | -0.099 |
Token | The |
Token ID | 383 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
zzo | +1.254 |
matured | +1.220 |
rhy | +1.187 |
Dise | +1.165 |
irit | +1.164 |
Neg logit contributions | |
Osw | -1.269 |
appropriately | -1.204 |
med | -1.197 |
gest | -1.191 |
ifiable | -1.185 |
Token | Six |
Token ID | 9699 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
Osw | +0.915 |
med | +0.864 |
gest | +0.851 |
appropriately | +0.850 |
ifiable | +0.845 |
Neg logit contributions | |
zzo | -0.866 |
matured | -0.840 |
rhy | -0.816 |
irit | -0.803 |
Dise | -0.787 |
Token | Days |
Token ID | 12579 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
Osw | +9.684 |
gest | +9.510 |
med | +9.488 |
teen | +9.411 |
oid | +9.198 |
Neg logit contributions | |
zzo | -8.095 |
matured | -8.003 |
rhy | -7.930 |
irit | -7.578 |
gae | -7.517 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Osw | +2.097 |
med | +1.997 |
gest | +1.948 |
hip | +1.942 |
ifiable | +1.927 |
Neg logit contributions | |
zzo | -2.472 |
matured | -2.394 |
rhy | -2.320 |
irit | -2.315 |
Dise | -2.284 |
Token | Man |
Token ID | 1869 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
zzo | +1.333 |
matured | +1.294 |
rhy | +1.262 |
Dise | +1.238 |
irit | +1.235 |
Neg logit contributions | |
Osw | -1.333 |
appropriately | -1.267 |
med | -1.258 |
gest | -1.252 |
ifiable | -1.247 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Osw | +1.489 |
med | +1.402 |
gest | +1.383 |
oid | +1.371 |
ifiable | +1.362 |
Neg logit contributions | |
zzo | -1.793 |
matured | -1.745 |
rhy | -1.713 |
irit | -1.674 |
Dise | -1.665 |
Token | The |
Token ID | 383 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
zzo | +1.790 |
matured | +1.739 |
rhy | +1.693 |
Dise | +1.675 |
irit | +1.660 |
Neg logit contributions | |
Osw | -1.835 |
appropriately | -1.758 |
med | -1.737 |
gest | -1.728 |
ifiable | -1.724 |
Token | with |
Token ID | 351 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Osw | +3.586 |
med | +3.525 |
oid | +3.434 |
hip | +3.357 |
ifiable | +3.348 |
Neg logit contributions | |
zzo | -5.640 |
matured | -5.596 |
rhy | -5.469 |
Dise | -5.395 |
irit | -5.372 |
Token | the |
Token ID | 262 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Osw | +0.099 |
med | +0.094 |
appropriately | +0.093 |
gest | +0.093 |
ifiable | +0.092 |
Neg logit contributions | |
zzo | -0.091 |
matured | -0.088 |
rhy | -0.086 |
irit | -0.084 |
Dise | -0.083 |
Token | areas |
Token ID | 3006 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Osw | +1.873 |
med | +1.787 |
gest | +1.767 |
ifiable | +1.758 |
appropriately | +1.758 |
Neg logit contributions | |
zzo | -1.574 |
matured | -1.513 |
rhy | -1.473 |
irit | -1.454 |
Dise | -1.431 |
Token | under |
Token ID | 739 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Osw | +1.070 |
med | +1.016 |
appropriately | +1.002 |
gest | +0.999 |
ifiable | +0.993 |
Neg logit contributions | |
zzo | -0.942 |
matured | -0.912 |
rhy | -0.883 |
irit | -0.870 |
Dise | -0.856 |
Token | military |
Token ID | 2422 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
Osw | +0.198 |
med | +0.187 |
appropriately | +0.185 |
gest | +0.185 |
ifiable | +0.183 |
Neg logit contributions | |
zzo | -0.200 |
matured | -0.194 |
rhy | -0.189 |
irit | -0.186 |
Dise | -0.183 |
Token | occupation |
Token ID | 13755 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
Osw | +3.421 |
med | +3.297 |
ifiable | +3.236 |
gest | +3.194 |
appropriately | +3.188 |
Neg logit contributions | |
zzo | -3.837 |
matured | -3.750 |
irit | -3.636 |
Dise | -3.574 |
rhy | -3.567 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Osw | +6.686 |
med | +6.639 |
hip | +6.333 |
ifiable | +6.216 |
oid | +6.215 |
Neg logit contributions | |
matured | -10.256 |
irit | -10.238 |
zzo | -10.194 |
Dise | -9.931 |
rhy | -9.871 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Osw | +1.585 |
med | +1.479 |
gest | +1.460 |
oid | +1.441 |
\": | +1.434 |
Neg logit contributions | |
zzo | -1.861 |
matured | -1.858 |
rhy | -1.784 |
irit | -1.763 |
Dise | -1.699 |
Token |
|
Token ID | 198 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
Osw | +0.097 |
appropriately | +0.092 |
med | +0.089 |
ifiable | +0.088 |
gest | +0.088 |
Neg logit contributions | |
zzo | -0.089 |
matured | -0.083 |
rhy | -0.082 |
irit | -0.080 |
lang | -0.078 |
Token | Per |
Token ID | 5990 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
Osw | +0.392 |
med | +0.371 |
appropriately | +0.367 |
gest | +0.366 |
ifiable | +0.363 |
Neg logit contributions | |
zzo | -0.363 |
matured | -0.352 |
rhy | -0.342 |
irit | -0.335 |
Dise | -0.330 |
Token | ceptions |
Token ID | 11755 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Osw | +5.102 |
med | +5.056 |
gest | +4.874 |
oid | +4.842 |
appropriately | +4.823 |
Neg logit contributions | |
zzo | -4.671 |
matured | -4.652 |
rhy | -4.471 |
Dise | -4.444 |
irit | -4.392 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
zzo | +0.676 |
matured | +0.623 |
rhy | +0.621 |
irit | +0.601 |
lang | +0.596 |
Neg logit contributions | |
Osw | -0.773 |
appropriately | -0.733 |
med | -0.702 |
ifiable | -0.700 |
gest | -0.694 |
Token | Section |
Token ID | 16375 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
zzo | +1.373 |
matured | +1.321 |
rhy | +1.284 |
irit | +1.265 |
Dise | +1.240 |
Neg logit contributions | |
Osw | -1.473 |
med | -1.364 |
appropriately | -1.360 |
gest | -1.351 |
ifiable | -1.351 |
Token | III |
Token ID | 6711 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Osw | +0.880 |
med | +0.829 |
appropriately | +0.816 |
gest | +0.814 |
ifiable | +0.808 |
Neg logit contributions | |
zzo | -1.038 |
matured | -1.011 |
rhy | -0.984 |
irit | -0.968 |
Dise | -0.956 |
Token | : |
Token ID | 25 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
zzo | +1.619 |
matured | +1.577 |
rhy | +1.537 |
irit | +1.513 |
Dise | +1.501 |
Neg logit contributions | |
Osw | -1.232 |
med | -1.141 |
appropriately | -1.136 |
gest | -1.128 |
ifiable | -1.123 |
Token | Lean |
Token ID | 45661 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
zzo | +2.775 |
matured | +2.669 |
rhy | +2.599 |
Dise | +2.584 |
irit | +2.536 |
Neg logit contributions | |
Osw | -2.730 |
appropriately | -2.573 |
med | -2.563 |
ifiable | -2.543 |
gest | -2.527 |
Token | Six |
Token ID | 9699 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
Osw | +1.559 |
med | +1.485 |
gest | +1.469 |
appropriately | +1.455 |
ifiable | +1.441 |
Neg logit contributions | |
zzo | -1.515 |
matured | -1.472 |
rhy | -1.437 |
irit | -1.414 |
Dise | -1.379 |
Token | Sigma |
Token ID | 31669 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
gest | +4.405 |
Osw | +4.233 |
oid | +4.071 |
med | +4.002 |
teen | +3.938 |
Neg logit contributions | |
zzo | -12.710 |
rhy | -12.364 |
irit | -12.240 |
matured | -12.228 |
Interstitial | -11.967 |
Token |
|
Token ID | 198 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
zzo | +0.521 |
matured | +0.505 |
rhy | +0.489 |
irit | +0.479 |
Dise | +0.475 |
Neg logit contributions | |
Osw | -0.554 |
med | -0.521 |
appropriately | -0.519 |
gest | -0.515 |
ifiable | -0.513 |
Token |
|
Token ID | 198 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
Osw | +0.422 |
appropriately | +0.398 |
med | +0.389 |
ifiable | +0.385 |
gest | +0.384 |
Neg logit contributions | |
zzo | -0.408 |
matured | -0.385 |
rhy | -0.380 |
irit | -0.370 |
Dise | -0.362 |
Token | What |
Token ID | 2061 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
zzo | +0.548 |
matured | +0.530 |
rhy | +0.514 |
irit | +0.506 |
Dise | +0.496 |
Neg logit contributions | |
Osw | -0.611 |
med | -0.573 |
appropriately | -0.568 |
gest | -0.566 |
ifiable | -0.564 |
Token | is |
Token ID | 318 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Osw | +2.414 |
med | +2.303 |
gest | +2.273 |
appropriately | +2.261 |
ifiable | +2.258 |
Neg logit contributions | |
zzo | -2.642 |
matured | -2.513 |
irit | -2.476 |
rhy | -2.463 |
Dise | -2.383 |
Token | Y |
Token ID | 575 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
matured | +3.297 |
rhy | +3.242 |
zzo | +3.232 |
irit | +3.045 |
Dise | +3.000 |
Neg logit contributions | |
Osw | -3.404 |
appropriately | -3.360 |
gest | -3.336 |
med | -3.282 |
\": | -3.229 |
Token | anda |
Token ID | 5282 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Osw | +0.207 |
appropriately | +0.189 |
med | +0.188 |
gest | +0.187 |
\": | +0.185 |
Neg logit contributions | |
zzo | -0.223 |
matured | -0.211 |
rhy | -0.208 |
irit | -0.201 |
Dise | -0.199 |
Token | — |
Token ID | 851 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
zzo | +3.015 |
matured | +2.890 |
rhy | +2.834 |
irit | +2.775 |
Dise | +2.715 |
Neg logit contributions | |
Osw | -2.720 |
appropriately | -2.554 |
med | -2.540 |
gest | -2.527 |
ifiable | -2.510 |
Token | per |
Token ID | 583 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
zzo | +1.879 |
matured | +1.826 |
rhy | +1.774 |
irit | +1.723 |
Dise | +1.691 |
Neg logit contributions | |
Osw | -1.878 |
med | -1.754 |
appropriately | -1.749 |
gest | -1.731 |
\": | -1.723 |
Token | Pro |
Token ID | 1041 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
Osw | +5.280 |
med | +4.923 |
ifiable | +4.830 |
oid | +4.821 |
appropriately | +4.802 |
Neg logit contributions | |
zzo | -5.837 |
matured | -5.813 |
irit | -5.630 |
rhy | -5.500 |
gae | -5.407 |
Token | Football |
Token ID | 9957 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
Osw | +0.583 |
med | +0.550 |
gest | +0.545 |
appropriately | +0.538 |
ifiable | +0.537 |
Neg logit contributions | |
zzo | -0.639 |
matured | -0.629 |
rhy | -0.609 |
irit | -0.604 |
Dise | -0.593 |
Token | Focus |
Token ID | 17061 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
Osw | +2.699 |
gest | +1.962 |
med | +1.956 |
oid | +1.932 |
ifiable | +1.736 |
Neg logit contributions | |
matured | -15.279 |
zzo | -15.198 |
irit | -15.030 |
rhy | -14.783 |
Dise | -14.758 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Osw | +3.941 |
med | +3.690 |
gest | +3.596 |
oid | +3.535 |
hip | +3.529 |
Neg logit contributions | |
matured | -5.406 |
zzo | -5.399 |
rhy | -5.194 |
Dise | -5.136 |
irit | -5.117 |
Token |
|
Token ID | 198 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Osw | +2.433 |
med | +2.270 |
gest | +2.260 |
oid | +2.215 |
appropriately | +2.211 |
Neg logit contributions | |
zzo | -2.326 |
matured | -2.321 |
rhy | -2.225 |
irit | -2.205 |
Dise | -2.116 |
Token |
|
Token ID | 198 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Osw | +1.609 |
appropriately | +1.504 |
med | +1.498 |
gest | +1.477 |
ifiable | +1.472 |
Neg logit contributions | |
zzo | -1.689 |
matured | -1.626 |
rhy | -1.590 |
irit | -1.558 |
Dise | -1.528 |
Token | A |
Token ID | 32 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Osw | +1.593 |
med | +1.523 |
gest | +1.501 |
appropriately | +1.490 |
ifiable | +1.476 |
Neg logit contributions | |
zzo | -1.648 |
matured | -1.631 |
rhy | -1.576 |
irit | -1.544 |
Dise | -1.538 |
Token | partnership |
Token ID | 10413 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
zzo | +1.850 |
matured | +1.799 |
rhy | +1.741 |
irit | +1.638 |
Dise | +1.624 |
Neg logit contributions | |
Osw | -3.567 |
appropriately | -3.427 |
gest | -3.375 |
med | -3.359 |
ifiable | -3.352 |
Token | between |
Token ID | 1022 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
zzo | +0.819 |
matured | +0.795 |
rhy | +0.770 |
irit | +0.753 |
Dise | +0.746 |
Neg logit contributions | |
Osw | -0.851 |
med | -0.800 |
appropriately | -0.800 |
gest | -0.797 |
ifiable | -0.789 |
Token | NPR |
Token ID | 17921 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
zzo | +0.123 |
matured | +0.119 |
rhy | +0.116 |
irit | +0.114 |
Dise | +0.113 |
Neg logit contributions | |
Osw | -0.106 |
med | -0.099 |
appropriately | -0.098 |
gest | -0.097 |
ifiable | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Osw | +2.787 |
med | +2.740 |
gest | +2.555 |
ifiable | +2.542 |
appropriately | +2.473 |
Neg logit contributions | |
zzo | -3.974 |
matured | -3.849 |
rhy | -3.772 |
irit | -3.685 |
Dise | -3.640 |
Token | Kaiser |
Token ID | 32670 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
zzo | +1.352 |
matured | +1.312 |
rhy | +1.279 |
irit | +1.250 |
Dise | +1.245 |
Neg logit contributions | |
Osw | -1.266 |
appropriately | -1.190 |
med | -1.187 |
gest | -1.181 |
ifiable | -1.170 |
Token | Health |
Token ID | 3893 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
Osw | +2.500 |
med | +2.305 |
gest | +2.273 |
ifiable | +2.255 |
appropriately | +2.211 |
Neg logit contributions | |
zzo | -2.961 |
matured | -2.922 |
rhy | -2.803 |
irit | -2.764 |
Dise | -2.737 |
Token | News |
Token ID | 3000 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
Osw | +4.542 |
med | +4.473 |
ifiable | +3.840 |
meal | +3.829 |
gest | +3.822 |
Neg logit contributions | |
zzo | -13.368 |
matured | -13.114 |
rhy | -12.521 |
gae | -12.431 |
osponsors | -12.429 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Osw | +1.969 |
med | +1.887 |
ifiable | +1.824 |
gest | +1.811 |
appropriately | +1.783 |
Neg logit contributions | |
zzo | -2.390 |
matured | -2.341 |
rhy | -2.278 |
irit | -2.263 |
Dise | -2.201 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
zzo | +0.803 |
matured | +0.771 |
rhy | +0.754 |
irit | +0.737 |
Dise | +0.736 |
Neg logit contributions | |
Osw | -0.858 |
appropriately | -0.810 |
med | -0.807 |
gest | -0.802 |
ifiable | -0.798 |
Token | When |
Token ID | 2215 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
zzo | +3.667 |
matured | +3.423 |
irit | +3.382 |
rhy | +3.368 |
Rog | +3.302 |
Neg logit contributions | |
Osw | -3.955 |
appropriately | -3.579 |
ifiable | -3.572 |
gest | -3.540 |
med | -3.536 |
Token | M |
Token ID | 337 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
zzo | +1.221 |
matured | +1.188 |
rhy | +1.153 |
irit | +1.129 |
Dise | +1.113 |
Neg logit contributions | |
Osw | -1.331 |
med | -1.259 |
appropriately | -1.249 |
gest | -1.243 |
ifiable | -1.234 |
Token | AWS |
Token ID | 30865 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
zzo | +0.637 |
matured | +0.621 |
rhy | +0.601 |
irit | +0.588 |
Dise | +0.580 |
Neg logit contributions | |
Osw | -0.662 |
med | -0.624 |
appropriately | -0.619 |
gest | -0.617 |
ifiable | -0.613 |
Token | using |
Token ID | 1262 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Osw | +0.694 |
med | +0.653 |
appropriately | +0.647 |
gest | +0.644 |
ifiable | +0.640 |
Neg logit contributions | |
zzo | -0.678 |
matured | -0.659 |
rhy | -0.640 |
irit | -0.629 |
Dise | -0.620 |
Token | the |
Token ID | 262 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
zzo | +0.205 |
matured | +0.199 |
rhy | +0.193 |
irit | +0.190 |
Dise | +0.187 |
Neg logit contributions | |
Osw | -0.211 |
med | -0.199 |
appropriately | -0.196 |
gest | -0.196 |
ifiable | -0.194 |
Token | command |
Token ID | 3141 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
Osw | +1.422 |
med | +1.340 |
gest | +1.322 |
appropriately | +1.319 |
ifiable | +1.307 |
Neg logit contributions | |
zzo | -1.422 |
matured | -1.369 |
rhy | -1.335 |
irit | -1.322 |
Dise | -1.306 |
Token | , |
Token ID | 11 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Osw | +3.826 |
med | +3.697 |
oid | +3.660 |
\": | +3.634 |
gest | +3.591 |
Neg logit contributions | |
zzo | -4.327 |
matured | -4.222 |
Dise | -4.159 |
irit | -4.113 |
rhy | -4.086 |
Token | sl |
Token ID | 1017 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
Osw | +1.929 |
med | +1.828 |
appropriately | +1.803 |
gest | +1.800 |
oid | +1.787 |
Neg logit contributions | |
zzo | -1.932 |
matured | -1.856 |
rhy | -1.802 |
irit | -1.794 |
Dise | -1.775 |
Token | s |
Token ID | 82 |
Feature activation | -8.69e+00 |
Pos logit contributions | |
med | +5.903 |
wk | +5.844 |
gest | +5.804 |
Osw | +5.760 |
oid | +5.595 |
Neg logit contributions | |
zzo | -10.807 |
Dise | -10.427 |
rhy | -10.286 |
matured | -10.279 |
irit | -10.072 |
Token | invoke |
Token ID | 26342 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
Osw | +5.504 |
med | +5.281 |
gest | +5.246 |
oid | +5.136 |
appropriately | +5.086 |
Neg logit contributions | |
zzo | -5.697 |
rhy | -5.379 |
Dise | -5.333 |
matured | -5.318 |
irit | -5.237 |
Token | - |
Token ID | 532 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
Osw | +3.569 |
med | +3.410 |
gest | +3.346 |
ifiable | +3.292 |
appropriately | +3.291 |
Neg logit contributions | |
zzo | -3.795 |
irit | -3.570 |
matured | -3.559 |
rhy | -3.553 |
Dise | -3.496 |
Token | f |
Token ID | 69 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
Osw | +4.318 |
med | +4.194 |
gest | +4.135 |
oid | +4.081 |
appropriately | +4.078 |
Neg logit contributions | |
zzo | -4.950 |
rhy | -4.773 |
matured | -4.750 |
Dise | -4.695 |
irit | -4.596 |
Token | test |
Token ID | 1332 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Osw | +3.383 |
med | +3.224 |
gest | +3.151 |
appropriately | +3.118 |
oid | +3.114 |
Neg logit contributions | |
zzo | -3.721 |
matured | -3.515 |
rhy | -3.507 |
irit | -3.491 |
Dise | -3.457 |
Token | advanced |
Token ID | 6190 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
zzo | +2.640 |
matured | +2.569 |
rhy | +2.506 |
Dise | +2.432 |
irit | +2.420 |
Neg logit contributions | |
Osw | -2.807 |
appropriately | -2.637 |
med | -2.612 |
ifiable | -2.585 |
gest | -2.584 |
Token | metrics |
Token ID | 20731 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
zzo | +3.353 |
matured | +3.292 |
rhy | +3.238 |
irit | +3.032 |
Dise | +3.006 |
Neg logit contributions | |
Osw | -3.532 |
appropriately | -3.408 |
\": | -3.295 |
gest | -3.294 |
med | -3.270 |
Token | courtesy |
Token ID | 12537 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
zzo | +1.163 |
matured | +1.138 |
rhy | +1.106 |
irit | +1.073 |
Dise | +1.061 |
Neg logit contributions | |
Osw | -1.197 |
appropriately | -1.123 |
med | -1.120 |
gest | -1.116 |
ifiable | -1.103 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Osw | +0.081 |
med | +0.076 |
ifiable | +0.075 |
gest | +0.074 |
oid | +0.074 |
Neg logit contributions | |
zzo | -0.087 |
matured | -0.085 |
rhy | -0.083 |
irit | -0.081 |
Dise | -0.080 |
Token | Pro |
Token ID | 1041 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Osw | +1.033 |
med | +0.973 |
appropriately | +0.957 |
gest | +0.955 |
ifiable | +0.952 |
Neg logit contributions | |
zzo | -0.991 |
matured | -0.963 |
rhy | -0.935 |
irit | -0.922 |
Dise | -0.904 |
Token | Football |
Token ID | 9957 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
Osw | +0.193 |
med | +0.181 |
appropriately | +0.179 |
gest | +0.179 |
ifiable | +0.177 |
Neg logit contributions | |
zzo | -0.203 |
matured | -0.198 |
rhy | -0.192 |
irit | -0.189 |
Dise | -0.186 |
Token | Focus |
Token ID | 17061 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Osw | +7.731 |
med | +7.171 |
gest | +6.958 |
oid | +6.863 |
ifiable | +6.725 |
Neg logit contributions | |
matured | -9.750 |
zzo | -9.698 |
irit | -9.613 |
rhy | -9.560 |
gae | -9.255 |
Token | unless |
Token ID | 4556 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
Osw | +1.937 |
med | +1.833 |
ifiable | +1.785 |
gest | +1.783 |
appropriately | +1.762 |
Neg logit contributions | |
zzo | -2.310 |
matured | -2.245 |
rhy | -2.195 |
irit | -2.180 |
Dise | -2.139 |
Token | otherwise |
Token ID | 4306 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
zzo | +3.157 |
matured | +3.119 |
rhy | +3.043 |
irit | +2.964 |
Dise | +2.916 |
Neg logit contributions | |
Osw | -1.797 |
appropriately | -1.633 |
gest | -1.622 |
med | -1.617 |
\": | -1.589 |
Token | indicated |
Token ID | 8203 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
zzo | +0.637 |
matured | +0.618 |
rhy | +0.601 |
irit | +0.586 |
Dise | +0.578 |
Neg logit contributions | |
Osw | -0.626 |
med | -0.585 |
appropriately | -0.583 |
gest | -0.581 |
ifiable | -0.575 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Osw | +3.268 |
med | +3.130 |
ifiable | +3.030 |
gest | +2.998 |
oid | +2.972 |
Neg logit contributions | |
zzo | -4.392 |
matured | -4.345 |
irit | -4.232 |
rhy | -4.223 |
Dise | -4.111 |
Token | bonds |
Token ID | 13100 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Osw | +3.174 |
med | +3.070 |
ifiable | +2.991 |
gest | +2.970 |
appropriately | +2.948 |
Neg logit contributions | |
zzo | -2.713 |
matured | -2.582 |
irit | -2.528 |
rhy | -2.496 |
Dise | -2.483 |
Token | open |
Token ID | 1280 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
Osw | +2.003 |
med | +1.924 |
gest | +1.883 |
ifiable | +1.877 |
appropriately | +1.875 |
Neg logit contributions | |
zzo | -1.976 |
matured | -1.889 |
rhy | -1.848 |
irit | -1.836 |
Dise | -1.811 |
Token | the |
Token ID | 262 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
zzo | +5.861 |
matured | +5.815 |
rhy | +5.593 |
irit | +5.321 |
valves | +5.115 |
Neg logit contributions | |
Osw | -7.777 |
appropriately | -7.395 |
\": | -7.231 |
med | -7.164 |
ifiable | -7.152 |
Token | way |
Token ID | 835 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
matured | +5.144 |
zzo | +5.098 |
rhy | +5.030 |
irit | +4.689 |
valves | +4.614 |
Neg logit contributions | |
Osw | -6.852 |
appropriately | -6.706 |
oid | -6.486 |
\": | -6.477 |
ifiable | -6.443 |
Token | to |
Token ID | 284 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
zzo | +3.872 |
matured | +3.762 |
rhy | +3.649 |
irit | +3.575 |
Dise | +3.513 |
Neg logit contributions | |
Osw | -3.902 |
appropriately | -3.679 |
med | -3.646 |
gest | -3.635 |
ifiable | -3.603 |
Token | Islamic |
Token ID | 5533 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
zzo | +0.314 |
matured | +0.304 |
rhy | +0.295 |
irit | +0.290 |
Dise | +0.286 |
Neg logit contributions | |
Osw | -0.339 |
med | -0.320 |
appropriately | -0.316 |
gest | -0.315 |
ifiable | -0.314 |
Token | law |
Token ID | 1099 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
Osw | +8.677 |
med | +8.563 |
ification | +8.310 |
oid | +8.261 |
ifiable | +8.138 |
Neg logit contributions | |
zzo | -8.477 |
sqor | -7.999 |
Dise | -7.881 |
matured | -7.646 |
rhy | -7.555 |
Token | being |
Token ID | 852 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Osw | +3.230 |
med | +3.129 |
ifiable | +3.047 |
gest | +3.028 |
appropriately | +2.992 |
Neg logit contributions | |
zzo | -3.473 |
matured | -3.305 |
rhy | -3.227 |
Dise | -3.223 |
irit | -3.207 |
Token | enforced |
Token ID | 20326 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Osw | +0.762 |
med | +0.720 |
appropriately | +0.711 |
gest | +0.709 |
ifiable | +0.707 |
Neg logit contributions | |
zzo | -0.707 |
matured | -0.682 |
rhy | -0.664 |
irit | -0.653 |
Dise | -0.646 |
Token | at |
Token ID | 379 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Osw | +2.262 |
med | +2.170 |
gest | +2.122 |
ifiable | +2.114 |
appropriately | +2.091 |
Neg logit contributions | |
zzo | -2.669 |
matured | -2.581 |
irit | -2.517 |
rhy | -2.503 |
Dise | -2.485 |
Token | the |
Token ID | 262 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
zzo | +0.274 |
matured | +0.266 |
rhy | +0.258 |
irit | +0.253 |
Dise | +0.250 |
Neg logit contributions | |
Osw | -0.295 |
med | -0.278 |
appropriately | -0.275 |
gest | -0.274 |
ifiable | -0.273 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Osw | +1.267 |
appropriately | +1.189 |
med | +1.176 |
gest | +1.160 |
ifiable | +1.159 |
Neg logit contributions | |
zzo | -1.288 |
matured | -1.229 |
rhy | -1.208 |
irit | -1.178 |
Dise | -1.157 |
Token | Hopefully |
Token ID | 32365 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Osw | +1.131 |
med | +1.069 |
appropriately | +1.056 |
gest | +1.054 |
ifiable | +1.046 |
Neg logit contributions | |
zzo | -1.084 |
matured | -1.056 |
rhy | -1.024 |
irit | -1.006 |
Dise | -0.992 |
Token | Barbara |
Token ID | 16685 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
zzo | +0.447 |
matured | +0.435 |
rhy | +0.422 |
irit | +0.412 |
Dise | +0.407 |
Neg logit contributions | |
Osw | -0.451 |
med | -0.424 |
appropriately | -0.421 |
gest | -0.419 |
ifiable | -0.416 |
Token | will |
Token ID | 481 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
Osw | +2.849 |
med | +2.654 |
appropriately | +2.605 |
gest | +2.593 |
ifiable | +2.588 |
Neg logit contributions | |
zzo | -2.944 |
matured | -2.862 |
irit | -2.822 |
rhy | -2.786 |
Dise | -2.735 |
Token | be |
Token ID | 307 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
Osw | +2.294 |
med | +2.182 |
appropriately | +2.157 |
gest | +2.155 |
ifiable | +2.138 |
Neg logit contributions | |
zzo | -2.157 |
matured | -2.089 |
irit | -2.030 |
rhy | -2.005 |
Dise | -1.988 |
Token | there |
Token ID | 612 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
Osw | +4.302 |
med | +4.023 |
gest | +3.958 |
appropriately | +3.958 |
ifiable | +3.954 |
Neg logit contributions | |
zzo | -4.522 |
matured | -4.320 |
irit | -4.309 |
Dise | -4.220 |
rhy | -4.215 |
Token | to |
Token ID | 284 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
Osw | +7.616 |
med | +7.354 |
gest | +7.082 |
appropriately | +7.026 |
oid | +6.953 |
Neg logit contributions | |
irit | -9.365 |
zzo | -9.079 |
Dise | -8.866 |
matured | -8.751 |
Rog | -8.512 |
Token | witness |
Token ID | 4973 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
Osw | +3.712 |
med | +3.516 |
gest | +3.461 |
appropriately | +3.443 |
ifiable | +3.412 |
Neg logit contributions | |
zzo | -4.031 |
matured | -3.905 |
irit | -3.797 |
rhy | -3.733 |
Dise | -3.703 |
Token | it |
Token ID | 340 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
Osw | +4.470 |
med | +4.180 |
gest | +4.113 |
appropriately | +4.108 |
ifiable | +4.071 |
Neg logit contributions | |
zzo | -5.062 |
irit | -4.849 |
matured | -4.840 |
rhy | -4.805 |
Dise | -4.717 |
Token | all |
Token ID | 477 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Osw | +2.508 |
med | +2.402 |
gest | +2.351 |
appropriately | +2.333 |
oid | +2.327 |
Neg logit contributions | |
zzo | -2.822 |
matured | -2.719 |
irit | -2.680 |
Dise | -2.676 |
rhy | -2.675 |
Token | later |
Token ID | 1568 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Osw | +0.834 |
med | +0.788 |
appropriately | +0.774 |
gest | +0.773 |
ifiable | +0.767 |
Neg logit contributions | |
zzo | -0.903 |
matured | -0.877 |
rhy | -0.856 |
irit | -0.846 |
Dise | -0.836 |
Token | t |
Token ID | 83 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
Osw | +0.924 |
med | +0.885 |
gest | +0.864 |
appropriately | +0.862 |
oid | +0.849 |
Neg logit contributions | |
zzo | -1.074 |
matured | -1.057 |
rhy | -1.026 |
irit | -1.007 |
Dise | -1.006 |
Token | oxic |
Token ID | 18047 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Osw | +1.832 |
med | +1.769 |
gest | +1.729 |
appropriately | +1.714 |
oid | +1.710 |
Neg logit contributions | |
zzo | -1.976 |
matured | -1.962 |
rhy | -1.899 |
Dise | -1.875 |
irit | -1.822 |
Token | _ |
Token ID | 62 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
Osw | +1.121 |
med | +1.079 |
gest | +1.060 |
appropriately | +1.049 |
oid | +1.046 |
Neg logit contributions | |
zzo | -1.301 |
matured | -1.277 |
rhy | -1.241 |
Dise | -1.217 |
irit | -1.210 |
Token | l |
Token ID | 75 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
Osw | +2.571 |
med | +2.566 |
gest | +2.488 |
oid | +2.462 |
appropriately | +2.418 |
Neg logit contributions | |
zzo | -2.810 |
matured | -2.798 |
rhy | -2.717 |
Dise | -2.699 |
irit | -2.628 |
Token | azer |
Token ID | 19178 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
med | +5.554 |
Osw | +5.541 |
oid | +5.524 |
gest | +5.290 |
hip | +5.197 |
Neg logit contributions | |
matured | -5.051 |
zzo | -5.005 |
Dise | -4.901 |
rhy | -4.867 |
Siren | -4.636 |
Token | z |
Token ID | 89 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
med | +3.327 |
oid | +3.254 |
Osw | +3.215 |
gest | +3.156 |
hip | +3.108 |
Neg logit contributions | |
matured | -5.909 |
zzo | -5.859 |
rhy | -5.809 |
Dise | -5.729 |
irit | -5.551 |
Token | > |
Token ID | 29 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
oid | +7.368 |
med | +7.132 |
hip | +6.872 |
gest | +6.668 |
Osw | +6.638 |
Neg logit contributions | |
matured | -9.448 |
Dise | -9.421 |
zzo | -9.269 |
rhy | -9.257 |
Interstitial | -8.924 |
Token | / |
Token ID | 1220 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
Osw | +1.580 |
med | +1.487 |
gest | +1.459 |
appropriately | +1.448 |
ifiable | +1.441 |
Neg logit contributions | |
zzo | -1.685 |
matured | -1.632 |
irit | -1.583 |
rhy | -1.564 |
Dise | -1.538 |
Token | clear |
Token ID | 20063 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Osw | +1.954 |
med | +1.895 |
gest | +1.850 |
appropriately | +1.827 |
ifiable | +1.815 |
Neg logit contributions | |
zzo | -2.136 |
matured | -2.084 |
rhy | -2.017 |
irit | -1.975 |
Dise | -1.971 |
Token | chat |
Token ID | 8537 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Osw | +0.266 |
med | +0.254 |
gest | +0.249 |
appropriately | +0.248 |
ifiable | +0.246 |
Neg logit contributions | |
zzo | -0.293 |
matured | -0.286 |
rhy | -0.278 |
irit | -0.274 |
Dise | -0.272 |
Token | [ |
Token ID | 685 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
zzo | +0.381 |
matured | +0.371 |
rhy | +0.360 |
irit | +0.355 |
Dise | +0.351 |
Neg logit contributions | |
Osw | -0.349 |
med | -0.331 |
appropriately | -0.324 |
gest | -0.324 |
oid | -0.321 |
Token | published |
Token ID | 30271 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
zzo | +1.776 |
matured | +1.728 |
rhy | +1.668 |
irit | +1.636 |
Dise | +1.600 |
Neg logit contributions | |
Osw | -1.832 |
appropriately | -1.686 |
med | -1.679 |
gest | -1.676 |
ifiable | -1.667 |
Token | author |
Token ID | 1772 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
Osw | +2.370 |
med | +2.258 |
ifiable | +2.227 |
gest | +2.224 |
appropriately | +2.209 |
Neg logit contributions | |
zzo | -2.205 |
matured | -2.115 |
irit | -2.036 |
rhy | -2.024 |
Dise | -2.012 |
Token | , |
Token ID | 11 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
Osw | +2.083 |
med | +2.010 |
ifiable | +1.960 |
gest | +1.955 |
appropriately | +1.942 |
Neg logit contributions | |
zzo | -2.490 |
matured | -2.408 |
Dise | -2.348 |
irit | -2.342 |
rhy | -2.339 |
Token | and |
Token ID | 290 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
Osw | +3.508 |
med | +3.313 |
appropriately | +3.214 |
gest | +3.208 |
ifiable | +3.189 |
Neg logit contributions | |
zzo | -4.095 |
matured | -3.867 |
irit | -3.847 |
Dise | -3.840 |
rhy | -3.796 |
Token | earns |
Token ID | 29339 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
Osw | +3.663 |
med | +3.470 |
appropriately | +3.367 |
gest | +3.360 |
ifiable | +3.348 |
Neg logit contributions | |
zzo | -3.623 |
matured | -3.455 |
irit | -3.405 |
Dise | -3.378 |
rhy | -3.343 |
Token | six |
Token ID | 2237 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
Osw | +2.223 |
med | +2.124 |
ifiable | +2.079 |
gest | +2.075 |
appropriately | +2.066 |
Neg logit contributions | |
zzo | -2.548 |
matured | -2.461 |
irit | -2.378 |
Dise | -2.366 |
rhy | -2.365 |
Token | figures |
Token ID | 5538 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
teen | +6.670 |
ifiable | +6.666 |
Osw | +6.642 |
med | +6.592 |
oid | +6.458 |
Neg logit contributions | |
zzo | -9.854 |
matured | -9.198 |
Dise | -9.152 |
irit | -8.988 |
gae | -8.901 |
Token | per |
Token ID | 583 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
Osw | +2.887 |
med | +2.774 |
ifiable | +2.719 |
gest | +2.701 |
appropriately | +2.673 |
Neg logit contributions | |
zzo | -3.114 |
matured | -2.993 |
Dise | -2.916 |
irit | -2.914 |
rhy | -2.880 |
Token | year |
Token ID | 614 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
Osw | +3.572 |
med | +3.468 |
ifiable | +3.373 |
wk | +3.340 |
gest | +3.339 |
Neg logit contributions | |
zzo | -5.676 |
matured | -5.478 |
Dise | -5.384 |
irit | -5.351 |
rhy | -5.125 |
Token | . |
Token ID | 13 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
Osw | +3.128 |
med | +3.033 |
ifiable | +2.932 |
gest | +2.903 |
appropriately | +2.893 |
Neg logit contributions | |
zzo | -3.521 |
matured | -3.408 |
Dise | -3.311 |
irit | -3.296 |
rhy | -3.255 |
Token | Except |
Token ID | 18181 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Osw | +2.279 |
med | +2.130 |
gest | +2.102 |
oid | +2.069 |
ifiable | +2.063 |
Neg logit contributions | |
zzo | -2.552 |
matured | -2.517 |
rhy | -2.407 |
irit | -2.389 |
Dise | -2.311 |
Token | Israel |
Token ID | 2692 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
Osw | +1.013 |
med | +0.951 |
gest | +0.937 |
appropriately | +0.933 |
ifiable | +0.928 |
Neg logit contributions | |
zzo | -1.024 |
matured | -1.004 |
rhy | -0.974 |
irit | -0.956 |
Dise | -0.929 |
Token | continues |
Token ID | 4477 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
Osw | +4.310 |
med | +4.204 |
gest | +4.099 |
oid | +4.076 |
appropriately | +4.060 |
Neg logit contributions | |
zzo | -5.126 |
matured | -4.981 |
rhy | -4.878 |
irit | -4.770 |
Dise | -4.769 |
Token | to |
Token ID | 284 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Osw | +0.515 |
med | +0.487 |
ifiable | +0.482 |
gest | +0.481 |
appropriately | +0.475 |
Neg logit contributions | |
zzo | -0.509 |
matured | -0.494 |
rhy | -0.476 |
irit | -0.472 |
Dise | -0.468 |
Token | make |
Token ID | 787 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Osw | +1.611 |
med | +1.533 |
gest | +1.514 |
appropriately | +1.506 |
ifiable | +1.506 |
Neg logit contributions | |
zzo | -1.528 |
matured | -1.473 |
rhy | -1.419 |
irit | -1.408 |
Dise | -1.390 |
Token | the |
Token ID | 262 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
Osw | +1.160 |
med | +1.097 |
ifiable | +1.084 |
gest | +1.081 |
appropriately | +1.074 |
Neg logit contributions | |
zzo | -1.041 |
matured | -0.998 |
rhy | -0.966 |
irit | -0.965 |
Dise | -0.951 |
Token | claim |
Token ID | 1624 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Osw | +2.900 |
med | +2.732 |
ifiable | +2.710 |
gest | +2.707 |
oid | +2.655 |
Neg logit contributions | |
zzo | -2.678 |
matured | -2.550 |
irit | -2.475 |
rhy | -2.459 |
Dise | -2.438 |
Token | that |
Token ID | 326 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
Osw | +6.754 |
med | +6.596 |
ifiable | +6.561 |
oid | +6.536 |
meal | +6.306 |
Neg logit contributions | |
zzo | -9.578 |
matured | -9.222 |
irit | -9.193 |
Dise | -9.079 |
Interstitial | -9.017 |
Token | there |
Token ID | 612 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
Osw | +4.506 |
med | +4.250 |
ifiable | +4.205 |
gest | +4.108 |
oid | +4.078 |
Neg logit contributions | |
zzo | -4.613 |
matured | -4.428 |
irit | -4.345 |
rhy | -4.285 |
Dise | -4.230 |
Token | is |
Token ID | 318 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Osw | +3.905 |
med | +3.796 |
ifiable | +3.701 |
oid | +3.650 |
appropriately | +3.629 |
Neg logit contributions | |
zzo | -5.076 |
matured | -4.920 |
Dise | -4.842 |
irit | -4.834 |
rhy | -4.776 |
Token | no |
Token ID | 645 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
zzo | +0.277 |
matured | +0.268 |
rhy | +0.259 |
irit | +0.254 |
Dise | +0.250 |
Neg logit contributions | |
Osw | -0.354 |
med | -0.335 |
appropriately | -0.332 |
gest | -0.331 |
ifiable | -0.330 |
Token | Palestinian |
Token ID | 8501 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
zzo | +1.328 |
matured | +1.304 |
rhy | +1.282 |
irit | +1.222 |
Dise | +1.208 |
Neg logit contributions | |
Osw | -1.528 |
appropriately | -1.449 |
med | -1.442 |
gest | -1.432 |
oid | -1.421 |
Token | phone |
Token ID | 4862 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Osw | +1.332 |
med | +1.291 |
gest | +1.240 |
ifiable | +1.228 |
oid | +1.226 |
Neg logit contributions | |
zzo | -3.156 |
matured | -3.135 |
rhy | -3.041 |
Dise | -3.021 |
irit | -2.998 |
Token | in |
Token ID | 287 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
Osw | +1.404 |
med | +1.345 |
oid | +1.321 |
gest | +1.318 |
\": | +1.309 |
Neg logit contributions | |
zzo | -1.714 |
matured | -1.676 |
Dise | -1.608 |
irit | -1.603 |
rhy | -1.595 |
Token | phones |
Token ID | 9512 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
Osw | +2.819 |
med | +2.696 |
gest | +2.642 |
ifiable | +2.640 |
oid | +2.622 |
Neg logit contributions | |
zzo | -2.889 |
matured | -2.796 |
irit | -2.722 |
rhy | -2.694 |
Dise | -2.686 |
Token | "> |
Token ID | 5320 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
Osw | +2.197 |
med | +2.174 |
\": | +2.053 |
"}, | +1.976 |
ifiable | +1.975 |
Neg logit contributions | |
zzo | -7.169 |
matured | -7.057 |
Dise | -6.941 |
irit | -6.871 |
rhy | -6.777 |
Token | < |
Token ID | 1279 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Osw | +1.856 |
med | +1.787 |
ifiable | +1.712 |
gest | +1.701 |
appropriately | +1.695 |
Neg logit contributions | |
zzo | -3.063 |
matured | -3.045 |
rhy | -2.905 |
Dise | -2.885 |
irit | -2.871 |
Token | span |
Token ID | 12626 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Osw | +1.208 |
med | +1.178 |
ifiable | +1.145 |
gest | +1.135 |
\": | +1.133 |
Neg logit contributions | |
zzo | -2.127 |
matured | -2.115 |
Dise | -2.046 |
rhy | -2.032 |
irit | -1.991 |
Token | ng |
Token ID | 23370 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
med | +6.865 |
Osw | +6.451 |
\": | +6.359 |
ifiable | +6.303 |
oid | +6.244 |
Neg logit contributions | |
zzo | -9.983 |
Dise | -9.551 |
matured | -9.346 |
gae | -8.950 |
irit | -8.883 |
Token | - |
Token ID | 12 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
Osw | +1.581 |
med | +1.522 |
gest | +1.477 |
\": | +1.470 |
oid | +1.469 |
Neg logit contributions | |
zzo | -2.531 |
matured | -2.481 |
rhy | -2.405 |
irit | -2.378 |
Dise | -2.375 |
Token | bind |
Token ID | 21653 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
med | +3.221 |
Osw | +3.137 |
gest | +3.129 |
ifiable | +3.067 |
oid | +3.058 |
Neg logit contributions | |
zzo | -4.038 |
matured | -3.936 |
Dise | -3.869 |
rhy | -3.858 |
irit | -3.766 |
Token | =" |
Token ID | 2625 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
med | +4.129 |
Osw | +4.029 |
gest | +3.916 |
\": | +3.859 |
ifiable | +3.827 |
Neg logit contributions | |
zzo | -5.918 |
matured | -5.787 |
Dise | -5.530 |
rhy | -5.507 |
irit | -5.484 |
Token | phone |
Token ID | 4862 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
Osw | +3.253 |
med | +3.205 |
gest | +3.119 |
oid | +3.111 |
ifiable | +3.097 |
Neg logit contributions | |
zzo | -3.981 |
matured | -3.926 |
rhy | -3.778 |
Dise | -3.756 |
irit | -3.699 |
Token | delivers |
Token ID | 16316 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
zzo | +1.289 |
matured | +1.275 |
rhy | +1.238 |
irit | +1.188 |
Dise | +1.174 |
Neg logit contributions | |
Osw | -1.466 |
appropriately | -1.382 |
gest | -1.374 |
med | -1.371 |
ifiable | -1.347 |
Token | operating |
Token ID | 5361 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
zzo | +0.671 |
matured | +0.652 |
rhy | +0.633 |
irit | +0.622 |
Dise | +0.612 |
Neg logit contributions | |
Osw | -0.707 |
med | -0.666 |
appropriately | -0.660 |
gest | -0.657 |
ifiable | -0.653 |
Token | profits |
Token ID | 10177 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
zzo | +0.914 |
matured | +0.885 |
rhy | +0.852 |
irit | +0.821 |
Dise | +0.805 |
Neg logit contributions | |
Osw | -1.572 |
med | -1.496 |
appropriately | -1.488 |
gest | -1.483 |
ifiable | -1.472 |
Token | of |
Token ID | 286 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
zzo | +0.885 |
matured | +0.866 |
rhy | +0.843 |
irit | +0.820 |
Dise | +0.806 |
Neg logit contributions | |
Osw | -0.971 |
med | -0.911 |
appropriately | -0.910 |
gest | -0.904 |
ifiable | -0.893 |
Token | $ |
Token ID | 720 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
zzo | +0.986 |
matured | +0.965 |
rhy | +0.941 |
irit | +0.922 |
Dise | +0.911 |
Neg logit contributions | |
Osw | -0.782 |
med | -0.728 |
appropriately | -0.722 |
gest | -0.719 |
ifiable | -0.711 |
Token | 224 |
Token ID | 24137 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
zzo | +1.594 |
matured | +1.507 |
rhy | +1.469 |
irit | +1.451 |
Dise | +1.429 |
Neg logit contributions | |
Osw | -2.046 |
appropriately | -1.925 |
med | -1.916 |
gest | -1.900 |
ifiable | -1.897 |
Token | million |
Token ID | 1510 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
zzo | +5.434 |
matured | +5.322 |
rhy | +5.209 |
irit | +4.974 |
sqor | +4.849 |
Neg logit contributions | |
Osw | -6.429 |
appropriately | -6.104 |
gest | -6.019 |
oid | -5.937 |
med | -5.906 |
Token | . |
Token ID | 13 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
zzo | +4.644 |
matured | +4.608 |
rhy | +4.483 |
irit | +4.252 |
revolving | +4.125 |
Neg logit contributions | |
Osw | -5.363 |
appropriately | -5.099 |
gest | -5.003 |
\": | -4.939 |
oid | -4.905 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Osw | +0.299 |
med | +0.281 |
appropriately | +0.278 |
gest | +0.277 |
ifiable | +0.275 |
Neg logit contributions | |
zzo | -0.318 |
matured | -0.309 |
rhy | -0.301 |
irit | -0.296 |
Dise | -0.292 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Osw | +0.792 |
appropriately | +0.745 |
med | +0.728 |
ifiable | +0.722 |
gest | +0.720 |
Neg logit contributions | |
zzo | -0.762 |
matured | -0.721 |
rhy | -0.712 |
irit | -0.691 |
Dise | -0.678 |
Token | But |
Token ID | 1537 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
Osw | +0.807 |
med | +0.762 |
appropriately | +0.754 |
gest | +0.752 |
ifiable | +0.747 |
Neg logit contributions | |
zzo | -0.745 |
matured | -0.723 |
rhy | -0.701 |
irit | -0.689 |
Dise | -0.678 |
Token | have |
Token ID | 423 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
zzo | +0.502 |
matured | +0.488 |
rhy | +0.473 |
irit | +0.464 |
Dise | +0.457 |
Neg logit contributions | |
Osw | -0.545 |
med | -0.514 |
appropriately | -0.509 |
gest | -0.507 |
ifiable | -0.504 |
Token | moral |
Token ID | 6573 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
zzo | +2.213 |
matured | +2.195 |
rhy | +2.131 |
irit | +2.048 |
Dise | +1.998 |
Neg logit contributions | |
Osw | -2.532 |
med | -2.393 |
appropriately | -2.373 |
gest | -2.372 |
oid | -2.332 |
Token | payoff |
Token ID | 43843 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
matured | +3.274 |
zzo | +3.225 |
rhy | +3.206 |
irit | +3.061 |
gae | +2.899 |
Neg logit contributions | |
Osw | -3.873 |
med | -3.685 |
appropriately | -3.673 |
gest | -3.661 |
\": | -3.576 |
Token | without |
Token ID | 1231 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
zzo | +1.010 |
matured | +0.984 |
rhy | +0.959 |
irit | +0.937 |
Dise | +0.923 |
Neg logit contributions | |
Osw | -0.953 |
med | -0.891 |
appropriately | -0.886 |
gest | -0.881 |
ifiable | -0.871 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
rhy | +3.962 |
matured | +3.956 |
zzo | +3.921 |
irit | +3.666 |
Dise | +3.505 |
Neg logit contributions | |
Osw | -5.005 |
appropriately | -4.774 |
med | -4.702 |
gest | -4.693 |
\": | -4.636 |
Token | ed |
Token ID | 1225 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
zzo | +1.694 |
matured | +1.656 |
rhy | +1.616 |
irit | +1.568 |
Dise | +1.536 |
Neg logit contributions | |
Osw | -1.839 |
appropriately | -1.729 |
med | -1.727 |
gest | -1.717 |
ifiable | -1.699 |
Token | g |
Token ID | 70 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
zzo | +9.881 |
rhy | +9.838 |
dies | +9.834 |
gae | +9.804 |
irit | +9.790 |
Neg logit contributions | |
Osw | -4.952 |
appropriately | -4.547 |
\": | -4.225 |
med | -3.974 |
oid | -3.866 |
Token | iness |
Token ID | 1272 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
zzo | +1.186 |
matured | +1.163 |
rhy | +1.143 |
irit | +1.132 |
Dise | +1.115 |
Neg logit contributions | |
Osw | -0.414 |
med | -0.360 |
appropriately | -0.357 |
gest | -0.349 |
ifiable | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
zzo | +2.463 |
matured | +2.405 |
rhy | +2.352 |
irit | +2.286 |
Dise | +2.236 |
Neg logit contributions | |
Osw | -2.602 |
appropriately | -2.454 |
med | -2.438 |
gest | -2.417 |
ifiable | -2.399 |
Token | BU |
Token ID | 20571 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
zzo | +1.230 |
matured | +1.195 |
rhy | +1.162 |
irit | +1.134 |
Dise | +1.116 |
Neg logit contributions | |
Osw | -1.380 |
med | -1.302 |
appropriately | -1.292 |
gest | -1.288 |
ifiable | -1.278 |
Token | FF |
Token ID | 5777 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
zzo | +2.776 |
matured | +2.698 |
rhy | +2.651 |
irit | +2.568 |
Dise | +2.512 |
Neg logit contributions | |
Osw | -2.758 |
appropriately | -2.587 |
med | -2.558 |
gest | -2.541 |
ifiable | -2.527 |
Token | members |
Token ID | 1866 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
zzo | +1.857 |
matured | +1.827 |
rhy | +1.761 |
irit | +1.722 |
Dise | +1.668 |
Neg logit contributions | |
Osw | -2.495 |
med | -2.335 |
appropriately | -2.317 |
gest | -2.309 |
ifiable | -2.300 |
Token | and |
Token ID | 290 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
zzo | +4.212 |
matured | +4.161 |
rhy | +4.140 |
irit | +3.873 |
Dise | +3.798 |
Neg logit contributions | |
Osw | -5.464 |
appropriately | -5.109 |
gest | -5.044 |
med | -5.041 |
ifiable | -4.946 |
Token | like |
Token ID | 588 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
zzo | +2.497 |
matured | +2.485 |
rhy | +2.392 |
irit | +2.343 |
Dise | +2.246 |
Neg logit contributions | |
Osw | -3.263 |
med | -3.028 |
gest | -3.025 |
appropriately | -2.997 |
ifiable | -2.994 |
Token | - |
Token ID | 12 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
zzo | +3.863 |
matured | +3.782 |
rhy | +3.684 |
irit | +3.629 |
Dise | +3.571 |
Neg logit contributions | |
Osw | -2.937 |
med | -2.711 |
appropriately | -2.690 |
gest | -2.671 |
ifiable | -2.653 |
Token | minded |
Token ID | 14543 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
zzo | +0.852 |
matured | +0.779 |
irit | +0.639 |
rhy | +0.617 |
lang | +0.522 |
Neg logit contributions | |
Osw | -6.455 |
ifiable | -6.019 |
appropriately | -5.988 |
\": | -5.949 |
MPG | -5.931 |
Token | voters |
Token ID | 4446 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
matured | +2.915 |
zzo | +2.898 |
rhy | +2.828 |
irit | +2.747 |
Dise | +2.645 |
Neg logit contributions | |
Osw | -4.022 |
appropriately | -3.740 |
med | -3.716 |
gest | -3.698 |
ifiable | -3.623 |
Token | during |
Token ID | 1141 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
rhy | +5.541 |
matured | +5.532 |
zzo | +5.515 |
revolving | +5.093 |
Dise | +5.008 |
Neg logit contributions | |
Osw | -8.089 |
appropriately | -7.554 |
gest | -7.485 |
med | -7.381 |
ifiable | -7.259 |
Token | the |
Token ID | 262 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
zzo | +2.209 |
matured | +2.146 |
rhy | +2.094 |
irit | +2.043 |
Dise | +2.002 |
Neg logit contributions | |
Osw | -2.503 |
med | -2.368 |
appropriately | -2.341 |
gest | -2.333 |
ifiable | -2.324 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
zzo | +1.326 |
matured | +1.277 |
rhy | +1.240 |
irit | +1.202 |
Dise | +1.167 |
Neg logit contributions | |
Osw | -2.121 |
med | -2.014 |
appropriately | -2.012 |
ifiable | -1.998 |
gest | -1.994 |
Token | election |
Token ID | 3071 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
zzo | +1.278 |
matured | +1.229 |
rhy | +1.189 |
irit | +1.147 |
Dise | +1.127 |
Neg logit contributions | |
Osw | -1.950 |
appropriately | -1.836 |
med | -1.836 |
gest | -1.831 |
ifiable | -1.822 |
Token | that |
Token ID | 326 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
zzo | +1.145 |
matured | +1.114 |
rhy | +1.083 |
irit | +1.038 |
Dise | +1.031 |
Neg logit contributions | |
Osw | -1.552 |
med | -1.458 |
appropriately | -1.452 |
gest | -1.449 |
ifiable | -1.436 |
Token | , |
Token ID | 11 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
Osw | +1.972 |
med | +1.859 |
gest | +1.826 |
ifiable | +1.812 |
appropriately | +1.806 |
Neg logit contributions | |
zzo | -2.124 |
matured | -2.065 |
rhy | -1.998 |
irit | -1.993 |
Dise | -1.961 |
Token | telling |
Token ID | 5149 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Osw | +2.765 |
med | +2.611 |
gest | +2.588 |
appropriately | +2.575 |
oid | +2.549 |
Neg logit contributions | |
zzo | -2.705 |
matured | -2.612 |
irit | -2.532 |
rhy | -2.501 |
Dise | -2.495 |
Token | donors |
Token ID | 13334 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Osw | +1.373 |
med | +1.302 |
appropriately | +1.285 |
gest | +1.283 |
ifiable | +1.272 |
Neg logit contributions | |
zzo | -1.228 |
matured | -1.192 |
rhy | -1.151 |
irit | -1.139 |
Dise | -1.116 |
Token | in |
Token ID | 287 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
zzo | +1.093 |
matured | +1.058 |
rhy | +1.034 |
irit | +1.003 |
Dise | +0.987 |
Neg logit contributions | |
Osw | -1.197 |
med | -1.122 |
appropriately | -1.122 |
gest | -1.107 |
ifiable | -1.106 |
Token | a |
Token ID | 257 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
zzo | +0.538 |
matured | +0.523 |
rhy | +0.508 |
irit | +0.498 |
Dise | +0.491 |
Neg logit contributions | |
Osw | -0.564 |
med | -0.532 |
appropriately | -0.526 |
gest | -0.524 |
ifiable | -0.521 |
Token | private |
Token ID | 2839 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
zzo | +2.132 |
matured | +2.064 |
rhy | +2.015 |
irit | +1.910 |
Dise | +1.890 |
Neg logit contributions | |
Osw | -2.741 |
med | -2.590 |
appropriately | -2.585 |
gest | -2.554 |
oid | -2.545 |
Token | phone |
Token ID | 3072 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
zzo | +5.086 |
matured | +4.922 |
rhy | +4.846 |
branch | +4.549 |
irit | +4.530 |
Neg logit contributions | |
Osw | -6.454 |
appropriately | -6.076 |
med | -5.885 |
\": | -5.874 |
gest | -5.850 |
Token | call |
Token ID | 869 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
zzo | +0.600 |
matured | +0.586 |
rhy | +0.573 |
irit | +0.565 |
Dise | +0.559 |
Neg logit contributions | |
Osw | -0.350 |
med | -0.321 |
appropriately | -0.317 |
gest | -0.315 |
ifiable | -0.313 |
Token | that |
Token ID | 326 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
zzo | +0.610 |
matured | +0.591 |
rhy | +0.574 |
irit | +0.562 |
Dise | +0.553 |
Neg logit contributions | |
Osw | -0.670 |
med | -0.631 |
appropriately | -0.628 |
gest | -0.624 |
ifiable | -0.621 |
Token | he |
Token ID | 339 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Osw | +1.447 |
med | +1.375 |
gest | +1.350 |
appropriately | +1.348 |
ifiable | +1.342 |
Neg logit contributions | |
zzo | -1.434 |
matured | -1.389 |
rhy | -1.342 |
irit | -1.334 |
Dise | -1.308 |
Token | was |
Token ID | 373 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
zzo | +1.042 |
matured | +1.016 |
rhy | +0.977 |
irit | +0.954 |
Dise | +0.928 |
Neg logit contributions | |
Osw | -1.279 |
appropriately | -1.195 |
med | -1.192 |
gest | -1.182 |
ifiable | -1.179 |
Token | the |
Token ID | 262 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Osw | +1.045 |
med | +0.981 |
gest | +0.969 |
appropriately | +0.966 |
ifiable | +0.956 |
Neg logit contributions | |
zzo | -1.017 |
matured | -0.976 |
rhy | -0.949 |
irit | -0.943 |
Dise | -0.924 |
Token | team |
Token ID | 1074 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
zzo | +0.332 |
matured | +0.322 |
rhy | +0.313 |
irit | +0.307 |
Dise | +0.302 |
Neg logit contributions | |
Osw | -0.354 |
med | -0.334 |
appropriately | -0.331 |
gest | -0.329 |
ifiable | -0.328 |
Token | � |
Token ID | 447 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
matured | +3.001 |
zzo | +2.994 |
rhy | +2.853 |
irit | +2.768 |
Dise | +2.730 |
Neg logit contributions | |
Osw | -2.946 |
appropriately | -2.776 |
med | -2.710 |
ifiable | -2.698 |
gest | -2.692 |
Token | � |
Token ID | 247 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Osw | +0.784 |
med | +0.746 |
appropriately | +0.740 |
gest | +0.736 |
\": | +0.728 |
Neg logit contributions | |
zzo | -0.623 |
matured | -0.600 |
rhy | -0.582 |
irit | -0.567 |
Dise | -0.564 |
Token | s |
Token ID | 82 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Osw | +1.063 |
med | +1.008 |
gest | +0.991 |
appropriately | +0.989 |
ifiable | +0.975 |
Neg logit contributions | |
zzo | -1.200 |
matured | -1.168 |
rhy | -1.140 |
irit | -1.120 |
Dise | -1.108 |
Token | starting |
Token ID | 3599 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
Osw | +0.077 |
med | +0.072 |
appropriately | +0.072 |
gest | +0.071 |
ifiable | +0.071 |
Neg logit contributions | |
zzo | -0.072 |
matured | -0.070 |
rhy | -0.068 |
irit | -0.067 |
Dise | -0.066 |
Token | goalie |
Token ID | 31071 |
Feature activation | +8.53e+00 |
Pos logit contributions | |
matured | +6.421 |
rhy | +6.414 |
zzo | +6.303 |
revolving | +5.870 |
counterpart | +5.823 |
Neg logit contributions | |
Osw | -8.282 |
appropriately | -8.111 |
gest | -7.781 |
ifiable | -7.680 |
\": | -7.679 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
matured | +5.152 |
zzo | +5.137 |
rhy | +4.976 |
irit | +4.748 |
gae | +4.596 |
Neg logit contributions | |
Osw | -5.725 |
appropriately | -5.566 |
ifiable | -5.465 |
gest | -5.354 |
oid | -5.318 |
Token | His |
Token ID | 2399 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
zzo | +0.299 |
matured | +0.290 |
rhy | +0.282 |
irit | +0.277 |
Dise | +0.274 |
Neg logit contributions | |
Osw | -0.289 |
med | -0.272 |
appropriately | -0.270 |
gest | -0.268 |
ifiable | -0.267 |
Token | game |
Token ID | 983 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
zzo | +0.701 |
matured | +0.691 |
rhy | +0.669 |
irit | +0.645 |
Dise | +0.638 |
Neg logit contributions | |
Osw | -0.745 |
appropriately | -0.698 |
med | -0.698 |
gest | -0.689 |
ifiable | -0.689 |
Token | was |
Token ID | 373 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
matured | +1.737 |
zzo | +1.732 |
rhy | +1.649 |
irit | +1.594 |
Dise | +1.565 |
Neg logit contributions | |
Osw | -1.957 |
appropriately | -1.829 |
med | -1.815 |
gest | -1.803 |
ifiable | -1.790 |
Token | action |
Token ID | 2223 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
zzo | +0.191 |
matured | +0.185 |
rhy | +0.180 |
irit | +0.176 |
Dise | +0.173 |
Neg logit contributions | |
Osw | -0.214 |
med | -0.202 |
appropriately | -0.200 |
gest | -0.200 |
ifiable | -0.198 |
Token | by |
Token ID | 416 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Osw | +1.190 |
med | +1.136 |
appropriately | +1.117 |
ifiable | +1.116 |
gest | +1.114 |
Neg logit contributions | |
zzo | -1.108 |
matured | -1.072 |
rhy | -1.040 |
irit | -1.028 |
Dise | -1.017 |
Token | both |
Token ID | 1111 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
zzo | +0.902 |
matured | +0.878 |
rhy | +0.852 |
irit | +0.835 |
Dise | +0.822 |
Neg logit contributions | |
Osw | -1.006 |
med | -0.947 |
appropriately | -0.939 |
gest | -0.937 |
ifiable | -0.931 |
Token | national |
Token ID | 2260 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
zzo | +1.524 |
matured | +1.500 |
rhy | +1.448 |
irit | +1.415 |
Dise | +1.389 |
Neg logit contributions | |
Osw | -1.834 |
med | -1.738 |
appropriately | -1.723 |
gest | -1.723 |
ifiable | -1.705 |
Token | governments |
Token ID | 6905 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
zzo | +2.233 |
matured | +2.195 |
rhy | +2.125 |
irit | +2.083 |
Dise | +2.015 |
Neg logit contributions | |
Osw | -2.618 |
appropriately | -2.439 |
gest | -2.433 |
med | -2.428 |
\": | -2.413 |
Token | and |
Token ID | 290 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
zzo | +2.359 |
matured | +2.301 |
rhy | +2.233 |
irit | +2.173 |
Dise | +2.132 |
Neg logit contributions | |
Osw | -2.385 |
appropriately | -2.232 |
med | -2.227 |
gest | -2.215 |
\": | -2.189 |
Token | international |
Token ID | 3230 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
zzo | +1.697 |
matured | +1.667 |
rhy | +1.605 |
irit | +1.567 |
Dise | +1.520 |
Neg logit contributions | |
Osw | -2.160 |
med | -2.033 |
gest | -2.025 |
appropriately | -2.014 |
ifiable | -2.001 |
Token | co |
Token ID | 763 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
zzo | +2.060 |
matured | +2.034 |
rhy | +1.965 |
irit | +1.900 |
Dise | +1.808 |
Neg logit contributions | |
Osw | -3.030 |
appropriately | -2.837 |
med | -2.830 |
gest | -2.822 |
\": | -2.815 |
Token | - |
Token ID | 12 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
zzo | +2.591 |
matured | +2.516 |
rhy | +2.460 |
irit | +2.431 |
Dise | +2.387 |
Neg logit contributions | |
Osw | -1.975 |
med | -1.826 |
appropriately | -1.807 |
gest | -1.794 |
ifiable | -1.781 |
Token | operation |
Token ID | 27184 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Osw | +0.318 |
med | +0.300 |
appropriately | +0.295 |
gest | +0.291 |
ifiable | +0.288 |
Neg logit contributions | |
zzo | -0.515 |
matured | -0.504 |
rhy | -0.494 |
irit | -0.484 |
Dise | -0.481 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
zzo | +2.630 |
matured | +2.597 |
rhy | +2.486 |
irit | +2.415 |
Dise | +2.363 |
Neg logit contributions | |
Osw | -3.267 |
med | -3.062 |
appropriately | -3.058 |
gest | -3.027 |
\": | -3.012 |
Token | has |
Token ID | 468 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Osw | +1.254 |
med | +1.185 |
appropriately | +1.166 |
gest | +1.165 |
ifiable | +1.154 |
Neg logit contributions | |
zzo | -1.377 |
matured | -1.339 |
rhy | -1.301 |
irit | -1.287 |
Dise | -1.273 |
Token | been |
Token ID | 587 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
zzo | +0.384 |
matured | +0.375 |
rhy | +0.362 |
irit | +0.355 |
Dise | +0.348 |
Neg logit contributions | |
Osw | -0.420 |
med | -0.397 |
appropriately | -0.393 |
gest | -0.392 |
ifiable | -0.389 |
Token | quick |
Token ID | 2068 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
Osw | +1.788 |
med | +1.692 |
gest | +1.678 |
appropriately | +1.675 |
ifiable | +1.665 |
Neg logit contributions | |
zzo | -1.657 |
matured | -1.593 |
irit | -1.541 |
rhy | -1.536 |
Dise | -1.528 |
Token | to |
Token ID | 284 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Osw | +3.263 |
ifiable | +3.162 |
med | +3.158 |
gest | +3.139 |
oid | +3.061 |
Neg logit contributions | |
zzo | -4.069 |
matured | -3.860 |
Dise | -3.761 |
irit | -3.733 |
rhy | -3.677 |
Token | initiate |
Token ID | 22118 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Osw | +2.851 |
med | +2.735 |
gest | +2.702 |
ifiable | +2.690 |
oid | +2.676 |
Neg logit contributions | |
zzo | -2.874 |
matured | -2.753 |
irit | -2.644 |
Dise | -2.620 |
rhy | -2.596 |
Token | judicial |
Token ID | 13657 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
zzo | +0.775 |
matured | +0.754 |
rhy | +0.732 |
irit | +0.714 |
Dise | +0.699 |
Neg logit contributions | |
Osw | -0.933 |
med | -0.881 |
appropriately | -0.873 |
gest | -0.870 |
ifiable | -0.862 |
Token | investigations |
Token ID | 10986 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
zzo | +1.265 |
matured | +1.243 |
rhy | +1.204 |
irit | +1.171 |
Dise | +1.137 |
Neg logit contributions | |
Osw | -1.676 |
med | -1.569 |
appropriately | -1.564 |
gest | -1.556 |
\": | -1.533 |
Token | against |
Token ID | 1028 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
Osw | +0.774 |
med | +0.737 |
appropriately | +0.726 |
gest | +0.726 |
ifiable | +0.725 |
Neg logit contributions | |
zzo | -0.693 |
matured | -0.669 |
rhy | -0.649 |
irit | -0.642 |
Dise | -0.632 |
Token | ex |
Token ID | 409 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
matured | +2.634 |
zzo | +2.620 |
rhy | +2.525 |
irit | +2.453 |
Dise | +2.382 |
Neg logit contributions | |
Osw | -3.588 |
appropriately | -3.396 |
med | -3.379 |
gest | -3.368 |
oid | -3.339 |
Token | - |
Token ID | 12 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
zzo | +4.555 |
matured | +4.431 |
irit | +4.237 |
rhy | +4.232 |
Dise | +4.185 |
Neg logit contributions | |
Osw | -4.096 |
\": | -3.719 |
appropriately | -3.679 |
ifiable | -3.661 |
gest | -3.654 |
Token | president |
Token ID | 22540 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Osw | +1.912 |
med | +1.872 |
appropriately | +1.833 |
gest | +1.822 |
oid | +1.772 |
Neg logit contributions | |
zzo | -2.142 |
matured | -2.091 |
rhy | -2.053 |
Dise | -1.983 |
irit | -1.974 |
Token | , |
Token ID | 11 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Osw | +0.890 |
med | +0.840 |
gest | +0.824 |
appropriately | +0.823 |
ifiable | +0.821 |
Neg logit contributions | |
zzo | -1.006 |
matured | -0.979 |
rhy | -0.949 |
irit | -0.940 |
Dise | -0.930 |
Token | � |
Token ID | 447 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Osw | +1.962 |
med | +1.865 |
appropriately | +1.837 |
gest | +1.828 |
ifiable | +1.819 |
Neg logit contributions | |
zzo | -2.250 |
matured | -2.182 |
rhy | -2.102 |
irit | -2.088 |
Dise | -2.064 |
Token | � |
Token ID | 251 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Osw | +1.193 |
med | +1.135 |
appropriately | +1.128 |
gest | +1.120 |
ifiable | +1.109 |
Neg logit contributions | |
zzo | -1.012 |
matured | -0.983 |
rhy | -0.948 |
irit | -0.931 |
Dise | -0.927 |
Token | he |
Token ID | 339 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
zzo | +0.640 |
matured | +0.615 |
rhy | +0.597 |
irit | +0.580 |
Dise | +0.572 |
Neg logit contributions | |
Osw | -0.915 |
med | -0.872 |
appropriately | -0.866 |
gest | -0.859 |
ifiable | -0.857 |
Token | said |
Token ID | 531 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
zzo | +1.761 |
matured | +1.683 |
rhy | +1.653 |
irit | +1.614 |
Dise | +1.571 |
Neg logit contributions | |
Osw | -1.894 |
med | -1.781 |
appropriately | -1.780 |
ifiable | -1.764 |
gest | -1.759 |
Token | in |
Token ID | 287 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Osw | +0.265 |
med | +0.248 |
gest | +0.244 |
appropriately | +0.242 |
oid | +0.241 |
Neg logit contributions | |
zzo | -0.314 |
matured | -0.311 |
rhy | -0.297 |
irit | -0.295 |
Dise | -0.293 |
Token | an |
Token ID | 281 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
zzo | +0.742 |
matured | +0.721 |
rhy | +0.701 |
irit | +0.689 |
Dise | +0.679 |
Neg logit contributions | |
Osw | -0.735 |
med | -0.692 |
appropriately | -0.685 |
gest | -0.682 |
ifiable | -0.678 |
Token | e |
Token ID | 304 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
zzo | +0.819 |
matured | +0.798 |
rhy | +0.779 |
irit | +0.766 |
Dise | +0.757 |
Neg logit contributions | |
Osw | -0.661 |
med | -0.620 |
appropriately | -0.613 |
gest | -0.612 |
ifiable | -0.605 |
Token | - |
Token ID | 12 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
zzo | +1.910 |
matured | +1.854 |
rhy | +1.809 |
irit | +1.785 |
Dise | +1.747 |
Neg logit contributions | |
Osw | -1.445 |
med | -1.342 |
appropriately | -1.327 |
ifiable | -1.305 |
gest | -1.304 |
Token | mail |
Token ID | 4529 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
zzo | +4.430 |
matured | +4.312 |
rhy | +4.205 |
irit | +4.162 |
lang | +4.087 |
Neg logit contributions | |
Osw | -2.255 |
ifiable | -1.964 |
appropriately | -1.943 |
\": | -1.933 |
med | -1.906 |
Token | . |
Token ID | 13 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Osw | +0.847 |
med | +0.813 |
gest | +0.784 |
oid | +0.777 |
ifiable | +0.777 |
Neg logit contributions | |
zzo | -1.025 |
matured | -1.011 |
rhy | -0.972 |
irit | -0.960 |
Dise | -0.950 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
med | +2.421 |
Osw | +2.354 |
gest | +2.296 |
oid | +2.278 |
hip | +2.256 |
Neg logit contributions | |
matured | -3.406 |
Dise | -3.375 |
rhy | -3.357 |
zzo | -3.336 |
irit | -3.126 |
Token | co |
Token ID | 1073 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Osw | +1.331 |
med | +1.299 |
appropriately | +1.247 |
gest | +1.246 |
oid | +1.235 |
Neg logit contributions | |
zzo | -1.817 |
matured | -1.815 |
rhy | -1.772 |
Dise | -1.740 |
irit | -1.727 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Osw | +0.501 |
appropriately | +0.470 |
med | +0.463 |
ifiable | +0.458 |
gest | +0.457 |
Neg logit contributions | |
zzo | -0.494 |
matured | -0.470 |
rhy | -0.458 |
irit | -0.456 |
Dise | -0.439 |
Token | uk |
Token ID | 2724 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Osw | +1.766 |
med | +1.683 |
appropriately | +1.677 |
gest | +1.669 |
ifiable | +1.662 |
Neg logit contributions | |
zzo | -0.855 |
matured | -0.811 |
rhy | -0.775 |
irit | -0.761 |
Dise | -0.735 |
Token | ) |
Token ID | 8 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
zzo | +1.222 |
matured | +1.189 |
rhy | +1.154 |
irit | +1.131 |
Dise | +1.121 |
Neg logit contributions | |
Osw | -1.212 |
med | -1.149 |
appropriately | -1.131 |
gest | -1.126 |
ifiable | -1.123 |
Token | has |
Token ID | 468 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
zzo | +3.844 |
matured | +3.786 |
rhy | +3.594 |
irit | +3.488 |
Dise | +3.388 |
Neg logit contributions | |
Osw | -4.803 |
gest | -4.562 |
appropriately | -4.530 |
med | -4.524 |
ifiable | -4.475 |
Token | a |
Token ID | 257 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
matured | +2.698 |
zzo | +2.683 |
rhy | +2.543 |
irit | +2.469 |
Dise | +2.413 |
Neg logit contributions | |
Osw | -3.136 |
gest | -2.940 |
med | -2.932 |
appropriately | -2.930 |
oid | -2.890 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
matured | +2.985 |
zzo | +2.964 |
rhy | +2.845 |
irit | +2.711 |
Dise | +2.682 |
Neg logit contributions | |
Osw | -3.648 |
appropriately | -3.420 |
med | -3.378 |
gest | -3.374 |
\": | -3.355 |
Token | - |
Token ID | 12 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
zzo | +0.907 |
matured | +0.884 |
rhy | +0.863 |
irit | +0.849 |
Dise | +0.837 |
Neg logit contributions | |
Osw | -0.684 |
med | -0.635 |
appropriately | -0.630 |
gest | -0.626 |
ifiable | -0.622 |
Token | day |
Token ID | 820 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
zzo | +0.610 |
matured | +0.598 |
rhy | +0.585 |
irit | +0.579 |
Dise | +0.572 |
Neg logit contributions | |
Osw | -0.264 |
med | -0.237 |
appropriately | -0.234 |
gest | -0.232 |
ifiable | -0.230 |
Token | V |
Token ID | 569 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
zzo | +0.431 |
matured | +0.421 |
rhy | +0.406 |
irit | +0.397 |
Dise | +0.388 |
Neg logit contributions | |
Osw | -0.495 |
appropriately | -0.464 |
med | -0.463 |
gest | -0.460 |
ifiable | -0.456 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Osw | +0.621 |
med | +0.586 |
appropriately | +0.580 |
gest | +0.578 |
ifiable | +0.574 |
Neg logit contributions | |
zzo | -0.576 |
matured | -0.559 |
rhy | -0.543 |
irit | -0.533 |
Dise | -0.525 |
Token | map |
Token ID | 3975 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
zzo | +0.702 |
matured | +0.682 |
rhy | +0.665 |
irit | +0.646 |
Dise | +0.637 |
Neg logit contributions | |
Osw | -0.754 |
med | -0.707 |
appropriately | -0.704 |
gest | -0.703 |
ifiable | -0.698 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Osw | +2.280 |
med | +2.179 |
appropriately | +2.146 |
gest | +2.127 |
oid | +2.122 |
Neg logit contributions | |
zzo | -2.199 |
matured | -2.129 |
rhy | -2.061 |
irit | -2.055 |
Dise | -2.024 |
Token | v |
Token ID | 85 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Osw | +0.846 |
med | +0.805 |
appropriately | +0.789 |
gest | +0.784 |
ifiable | +0.777 |
Neg logit contributions | |
zzo | -0.978 |
matured | -0.952 |
rhy | -0.925 |
irit | -0.915 |
Dise | -0.905 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
zzo | +0.954 |
matured | +0.926 |
rhy | +0.902 |
irit | +0.888 |
Dise | +0.872 |
Neg logit contributions | |
Osw | -0.842 |
med | -0.785 |
appropriately | -0.780 |
gest | -0.774 |
ifiable | -0.769 |
Token | against |
Token ID | 1028 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
zzo | +1.280 |
matured | +1.239 |
rhy | +1.208 |
irit | +1.163 |
Dise | +1.143 |
Neg logit contributions | |
Osw | -1.363 |
appropriately | -1.259 |
gest | -1.257 |
med | -1.256 |
ifiable | -1.250 |
Token | pre |
Token ID | 662 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
zzo | +2.296 |
matured | +2.233 |
rhy | +2.188 |
irit | +2.094 |
Dise | +2.076 |
Neg logit contributions | |
Osw | -2.512 |
appropriately | -2.357 |
med | -2.349 |
ifiable | -2.344 |
gest | -2.338 |
Token | - |
Token ID | 12 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Osw | +0.835 |
med | +0.802 |
appropriately | +0.773 |
gest | +0.772 |
ifiable | +0.763 |
Neg logit contributions | |
zzo | -1.039 |
matured | -1.019 |
rhy | -0.996 |
irit | -0.979 |
Dise | -0.972 |
Token | agh |
Token ID | 10471 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
Osw | +2.084 |
med | +2.038 |
appropriately | +1.958 |
gest | +1.952 |
oid | +1.923 |
Neg logit contributions | |
zzo | -2.284 |
matured | -2.250 |
rhy | -2.205 |
Dise | -2.156 |
irit | -2.152 |
Token | s |
Token ID | 82 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
med | +4.056 |
Osw | +4.004 |
oid | +3.820 |
gest | +3.802 |
ifiable | +3.748 |
Neg logit contributions | |
zzo | -4.246 |
matured | -4.121 |
rhy | -3.998 |
irit | -3.903 |
Dise | -3.898 |
Token | inv |
Token ID | 800 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
Osw | +1.120 |
med | +1.072 |
appropriately | +1.045 |
gest | +1.045 |
oid | +1.040 |
Neg logit contributions | |
zzo | -1.090 |
matured | -1.060 |
rhy | -1.026 |
irit | -1.013 |
Dise | -1.004 |
Token | to |
Token ID | 284 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
zzo | +2.202 |
matured | +2.159 |
rhy | +2.082 |
irit | +2.014 |
Dise | +1.969 |
Neg logit contributions | |
Osw | -2.832 |
med | -2.669 |
appropriately | -2.665 |
gest | -2.626 |
oid | -2.617 |
Token | work |
Token ID | 670 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Osw | +0.284 |
med | +0.267 |
appropriately | +0.265 |
gest | +0.263 |
ifiable | +0.262 |
Neg logit contributions | |
zzo | -0.263 |
matured | -0.256 |
rhy | -0.248 |
irit | -0.243 |
Dise | -0.239 |
Token | on |
Token ID | 319 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Osw | +0.359 |
med | +0.338 |
appropriately | +0.335 |
gest | +0.334 |
ifiable | +0.332 |
Neg logit contributions | |
zzo | -0.319 |
matured | -0.310 |
rhy | -0.300 |
irit | -0.295 |
Dise | -0.289 |
Token | some |
Token ID | 617 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
zzo | +0.813 |
matured | +0.792 |
rhy | +0.766 |
irit | +0.748 |
Dise | +0.732 |
Neg logit contributions | |
Osw | -1.004 |
med | -0.950 |
appropriately | -0.943 |
gest | -0.938 |
ifiable | -0.933 |
Token | details |
Token ID | 3307 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Osw | +1.534 |
med | +1.456 |
appropriately | +1.432 |
gest | +1.430 |
ifiable | +1.428 |
Neg logit contributions | |
zzo | -1.376 |
matured | -1.324 |
rhy | -1.285 |
irit | -1.271 |
Dise | -1.263 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
zzo | +0.269 |
matured | +0.262 |
rhy | +0.254 |
irit | +0.250 |
Dise | +0.246 |
Neg logit contributions | |
Osw | -0.265 |
med | -0.249 |
appropriately | -0.247 |
gest | -0.246 |
ifiable | -0.244 |
Token | but |
Token ID | 475 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
Osw | +0.068 |
med | +0.064 |
appropriately | +0.063 |
gest | +0.063 |
ifiable | +0.063 |
Neg logit contributions | |
zzo | -0.066 |
matured | -0.064 |
rhy | -0.062 |
irit | -0.061 |
Dise | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Osw | +2.737 |
med | +2.599 |
gest | +2.546 |
appropriately | +2.545 |
ifiable | +2.540 |
Neg logit contributions | |
zzo | -2.733 |
matured | -2.625 |
rhy | -2.567 |
irit | -2.541 |
Dise | -2.505 |
Token | crisis |
Token ID | 4902 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
zzo | +0.273 |
matured | +0.266 |
rhy | +0.257 |
irit | +0.252 |
Dise | +0.247 |
Neg logit contributions | |
Osw | -0.327 |
med | -0.309 |
appropriately | -0.307 |
gest | -0.305 |
ifiable | -0.304 |
Token | is |
Token ID | 318 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Osw | +0.341 |
med | +0.321 |
appropriately | +0.318 |
gest | +0.317 |
ifiable | +0.315 |
Neg logit contributions | |
zzo | -0.333 |
matured | -0.324 |
rhy | -0.314 |
irit | -0.308 |
Dise | -0.304 |
Token | on |
Token ID | 319 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
zzo | +0.162 |
matured | +0.157 |
rhy | +0.152 |
irit | +0.149 |
Dise | +0.147 |
Neg logit contributions | |
Osw | -0.195 |
med | -0.185 |
appropriately | -0.183 |
gest | -0.182 |
ifiable | -0.181 |
Token | far |
Token ID | 1290 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
Osw | +1.984 |
med | +1.882 |
ifiable | +1.856 |
gest | +1.855 |
appropriately | +1.841 |
Neg logit contributions | |
zzo | -1.924 |
matured | -1.846 |
rhy | -1.804 |
irit | -1.791 |
Dise | -1.765 |
Token | more |
Token ID | 517 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
med | +4.153 |
Osw | +4.073 |
oid | +3.912 |
gest | +3.889 |
hip | +3.833 |
Neg logit contributions | |
zzo | -3.811 |
rhy | -3.663 |
matured | -3.632 |
Dise | -3.591 |
irit | -3.557 |
Token | challenging |
Token ID | 9389 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Osw | +0.219 |
med | +0.206 |
appropriately | +0.204 |
gest | +0.203 |
ifiable | +0.202 |
Neg logit contributions | |
zzo | -0.204 |
matured | -0.198 |
rhy | -0.192 |
irit | -0.188 |
Dise | -0.185 |
Token | than |
Token ID | 621 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Osw | +1.005 |
med | +0.953 |
gest | +0.939 |
ifiable | +0.938 |
appropriately | +0.931 |
Neg logit contributions | |
zzo | -1.087 |
matured | -1.054 |
rhy | -1.023 |
irit | -1.017 |
Dise | -1.002 |
Token | most |
Token ID | 749 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
Osw | +1.085 |
med | +1.031 |
gest | +1.019 |
appropriately | +1.018 |
ifiable | +1.014 |
Neg logit contributions | |
zzo | -0.799 |
matured | -0.769 |
rhy | -0.742 |
irit | -0.732 |
Dise | -0.717 |
Token | people |
Token ID | 661 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
Osw | +2.884 |
med | +2.758 |
gest | +2.705 |
oid | +2.698 |
\": | +2.695 |
Neg logit contributions | |
zzo | -2.601 |
matured | -2.500 |
rhy | -2.419 |
irit | -2.417 |
Dise | -2.379 |
Token | realize |
Token ID | 6537 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Osw | +3.226 |
med | +3.093 |
gest | +3.021 |
oid | +3.010 |
\": | +3.001 |
Neg logit contributions | |
zzo | -2.992 |
matured | -2.903 |
irit | -2.805 |
rhy | -2.769 |
Dise | -2.759 |
Token | . |
Token ID | 13 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
Osw | +0.684 |
med | +0.648 |
gest | +0.634 |
appropriately | +0.633 |
ifiable | +0.632 |
Neg logit contributions | |
zzo | -0.785 |
matured | -0.762 |
rhy | -0.739 |
irit | -0.733 |
Dise | -0.724 |
Token | Implement |
Token ID | 48282 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Osw | +0.644 |
med | +0.606 |
appropriately | +0.600 |
gest | +0.598 |
ifiable | +0.594 |
Neg logit contributions | |
zzo | -0.642 |
matured | -0.624 |
rhy | -0.606 |
irit | -0.596 |
Dise | -0.587 |
Token | ing |
Token ID | 278 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
zzo | +0.693 |
matured | +0.678 |
rhy | +0.661 |
irit | +0.652 |
Dise | +0.643 |
Neg logit contributions | |
Osw | -0.447 |
med | -0.411 |
appropriately | -0.407 |
gest | -0.405 |
ifiable | -0.402 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
zzo | +1.890 |
matured | +1.866 |
rhy | +1.801 |
irit | +1.730 |
Dise | +1.721 |
Neg logit contributions | |
Osw | -2.051 |
appropriately | -1.919 |
med | -1.917 |
gest | -1.903 |
ifiable | -1.896 |
Token | then |
Token ID | 788 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
zzo | +0.701 |
matured | +0.679 |
rhy | +0.658 |
irit | +0.646 |
Dise | +0.629 |
Neg logit contributions | |
Osw | -0.805 |
med | -0.757 |
appropriately | -0.752 |
gest | -0.749 |
ifiable | -0.746 |
Token | called |
Token ID | 1444 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
zzo | +0.609 |
matured | +0.595 |
rhy | +0.578 |
irit | +0.562 |
Dise | +0.552 |
Neg logit contributions | |
Osw | -0.661 |
med | -0.624 |
appropriately | -0.620 |
gest | -0.617 |
ifiable | -0.612 |
Token | for |
Token ID | 329 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
zzo | +0.372 |
matured | +0.362 |
rhy | +0.352 |
irit | +0.346 |
Dise | +0.340 |
Neg logit contributions | |
Osw | -0.369 |
med | -0.347 |
appropriately | -0.344 |
gest | -0.343 |
ifiable | -0.340 |
Token | � |
Token ID | 564 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
zzo | +1.645 |
matured | +1.607 |
rhy | +1.569 |
irit | +1.532 |
Dise | +1.500 |
Neg logit contributions | |
Osw | -1.771 |
med | -1.673 |
appropriately | -1.670 |
gest | -1.659 |
ifiable | -1.635 |
Token | � |
Token ID | 250 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Osw | +1.005 |
med | +0.955 |
appropriately | +0.952 |
gest | +0.937 |
\": | +0.935 |
Neg logit contributions | |
zzo | -0.733 |
matured | -0.715 |
rhy | -0.685 |
Dise | -0.668 |
irit | -0.662 |
Token | femin |
Token ID | 33594 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
zzo | +0.684 |
matured | +0.665 |
rhy | +0.646 |
irit | +0.636 |
Dise | +0.625 |
Neg logit contributions | |
Osw | -0.661 |
med | -0.618 |
appropriately | -0.613 |
gest | -0.611 |
ifiable | -0.608 |
Token | ine |
Token ID | 500 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
Osw | +2.832 |
med | +2.642 |
oid | +2.628 |
ifiable | +2.549 |
gest | +2.548 |
Neg logit contributions | |
zzo | -5.961 |
matured | -5.708 |
rhy | -5.633 |
Dise | -5.603 |
irit | -5.526 |
Token | women |
Token ID | 1466 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Osw | +2.668 |
med | +2.536 |
gest | +2.479 |
oid | +2.465 |
ifiable | +2.460 |
Neg logit contributions | |
zzo | -2.812 |
matured | -2.686 |
rhy | -2.590 |
irit | -2.581 |
Dise | -2.575 |
Token | who |
Token ID | 508 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Osw | +0.961 |
med | +0.910 |
gest | +0.888 |
appropriately | +0.883 |
ifiable | +0.882 |
Neg logit contributions | |
zzo | -1.071 |
matured | -1.037 |
rhy | -1.004 |
irit | -0.997 |
Dise | -0.984 |
Token | are |
Token ID | 389 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
zzo | +0.314 |
matured | +0.305 |
rhy | +0.297 |
irit | +0.290 |
Dise | +0.285 |
Neg logit contributions | |
Osw | -0.336 |
med | -0.315 |
appropriately | -0.314 |
gest | -0.312 |
ifiable | -0.310 |
Token | disgusted |
Token ID | 36943 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
Osw | +1.167 |
med | +1.104 |
appropriately | +1.092 |
gest | +1.088 |
ifiable | +1.085 |
Neg logit contributions | |
zzo | -0.978 |
matured | -0.944 |
rhy | -0.913 |
irit | -0.900 |
Dise | -0.887 |
Token | ron |
Token ID | 1313 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Osw | +1.229 |
med | +1.191 |
gest | +1.138 |
appropriately | +1.132 |
oid | +1.129 |
Neg logit contributions | |
zzo | -1.547 |
matured | -1.528 |
rhy | -1.475 |
irit | -1.459 |
Dise | -1.448 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
zzo | +0.354 |
matured | +0.347 |
rhy | +0.336 |
irit | +0.332 |
Dise | +0.329 |
Neg logit contributions | |
Osw | -0.307 |
med | -0.287 |
gest | -0.282 |
appropriately | -0.281 |
oid | -0.279 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Osw | +0.112 |
med | +0.104 |
gest | +0.103 |
ifiable | +0.101 |
appropriately | +0.101 |
Neg logit contributions | |
zzo | -0.135 |
matured | -0.134 |
rhy | -0.129 |
irit | -0.127 |
Dise | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Osw | +1.051 |
appropriately | +0.985 |
med | +0.977 |
gest | +0.963 |
ifiable | +0.962 |
Neg logit contributions | |
zzo | -1.082 |
matured | -1.037 |
rhy | -1.018 |
irit | -0.995 |
Dise | -0.976 |
Token | Mr |
Token ID | 5246 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Osw | +1.371 |
med | +1.322 |
gest | +1.302 |
appropriately | +1.287 |
\": | +1.279 |
Neg logit contributions | |
zzo | -1.371 |
matured | -1.361 |
rhy | -1.314 |
Dise | -1.278 |
irit | -1.273 |
Token | Ch |
Token ID | 609 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
zzo | +1.490 |
matured | +1.444 |
rhy | +1.399 |
irit | +1.374 |
Dise | +1.352 |
Neg logit contributions | |
Osw | -1.732 |
med | -1.638 |
appropriately | -1.624 |
gest | -1.617 |
ifiable | -1.607 |
Token | oud |
Token ID | 2778 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Osw | +0.450 |
appropriately | +0.416 |
med | +0.408 |
gest | +0.407 |
ifiable | +0.405 |
Neg logit contributions | |
zzo | -0.506 |
matured | -0.481 |
irit | -0.474 |
rhy | -0.471 |
gae | -0.450 |
Token | h |
Token ID | 71 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
zzo | +2.692 |
irit | +2.519 |
rhy | +2.516 |
matured | +2.501 |
gae | +2.458 |
Neg logit contributions | |
Osw | -2.494 |
appropriately | -2.324 |
MPG | -2.142 |
\": | -2.124 |
ifiable | -2.118 |
Token | rie |
Token ID | 5034 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
Osw | +2.466 |
med | +2.362 |
appropriately | +2.346 |
gest | +2.339 |
ifiable | +2.329 |
Neg logit contributions | |
zzo | -1.018 |
matured | -0.967 |
rhy | -0.920 |
irit | -0.893 |
Dise | -0.866 |
Token | and |
Token ID | 290 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
zzo | +0.345 |
matured | +0.335 |
rhy | +0.325 |
irit | +0.319 |
Dise | +0.314 |
Neg logit contributions | |
Osw | -0.347 |
med | -0.326 |
appropriately | -0.323 |
gest | -0.322 |
ifiable | -0.320 |
Token | his |
Token ID | 465 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Osw | +0.154 |
med | +0.145 |
appropriately | +0.143 |
gest | +0.143 |
ifiable | +0.142 |
Neg logit contributions | |
zzo | -0.151 |
matured | -0.146 |
rhy | -0.141 |
irit | -0.139 |
Dise | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
Osw | +2.090 |
med | +1.984 |
appropriately | +1.939 |
gest | +1.931 |
ifiable | +1.929 |
Neg logit contributions | |
zzo | -2.382 |
matured | -2.282 |
irit | -2.248 |
rhy | -2.233 |
Dise | -2.219 |
Token | we |
Token ID | 356 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Osw | +2.655 |
med | +2.515 |
ifiable | +2.479 |
appropriately | +2.472 |
gest | +2.455 |
Neg logit contributions | |
zzo | -2.456 |
matured | -2.351 |
irit | -2.301 |
Dise | -2.277 |
rhy | -2.275 |
Token | 've |
Token ID | 1053 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Osw | +2.133 |
med | +2.027 |
appropriately | +1.990 |
gest | +1.990 |
oid | +1.974 |
Neg logit contributions | |
zzo | -2.143 |
matured | -2.071 |
irit | -2.013 |
rhy | -2.011 |
Dise | -1.984 |
Token | seen |
Token ID | 1775 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
Osw | +0.572 |
med | +0.539 |
appropriately | +0.533 |
gest | +0.531 |
ifiable | +0.528 |
Neg logit contributions | |
zzo | -0.574 |
matured | -0.559 |
rhy | -0.542 |
irit | -0.532 |
Dise | -0.525 |
Token | a |
Token ID | 257 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
Osw | +2.145 |
med | +2.035 |
ifiable | +2.002 |
appropriately | +1.992 |
gest | +1.988 |
Neg logit contributions | |
zzo | -2.003 |
matured | -1.909 |
irit | -1.871 |
rhy | -1.861 |
Dise | -1.849 |
Token | very |
Token ID | 845 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
zzo | +0.491 |
matured | +0.480 |
rhy | +0.464 |
irit | +0.451 |
Dise | +0.442 |
Neg logit contributions | |
Osw | -0.625 |
med | -0.590 |
appropriately | -0.589 |
gest | -0.585 |
ifiable | -0.580 |
Token | different |
Token ID | 1180 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
zzo | +0.038 |
matured | +0.037 |
rhy | +0.036 |
irit | +0.035 |
Dise | +0.035 |
Neg logit contributions | |
Osw | -0.047 |
med | -0.044 |
appropriately | -0.044 |
gest | -0.044 |
ifiable | -0.043 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
zzo | +1.540 |
matured | +1.520 |
rhy | +1.465 |
irit | +1.412 |
Dise | +1.375 |
Neg logit contributions | |
Osw | -2.096 |
appropriately | -1.983 |
med | -1.980 |
gest | -1.970 |
\": | -1.945 |
Token | of |
Token ID | 286 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
zzo | +0.967 |
matured | +0.940 |
rhy | +0.918 |
irit | +0.874 |
gae | +0.832 |
Neg logit contributions | |
Osw | -1.251 |
appropriately | -1.198 |
med | -1.167 |
gest | -1.152 |
\": | -1.142 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
zzo | +2.319 |
matured | +2.306 |
rhy | +2.219 |
irit | +2.114 |
Dise | +2.053 |
Neg logit contributions | |
Osw | -2.789 |
appropriately | -2.649 |
med | -2.633 |
gest | -2.617 |
\": | -2.581 |
Token | emerge |
Token ID | 14740 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
zzo | +2.525 |
matured | +2.466 |
rhy | +2.386 |
irit | +2.296 |
Dise | +2.227 |
Neg logit contributions | |
Osw | -2.570 |
appropriately | -2.438 |
med | -2.399 |
gest | -2.397 |
ifiable | -2.347 |
Token | strat |
Token ID | 25369 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
zzo | +0.118 |
matured | +0.115 |
rhy | +0.112 |
irit | +0.109 |
Dise | +0.107 |
Neg logit contributions | |
Osw | -0.130 |
med | -0.123 |
appropriately | -0.122 |
gest | -0.121 |
ifiable | -0.120 |
Token | osp |
Token ID | 2117 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Osw | +0.780 |
med | +0.739 |
ifiable | +0.695 |
appropriately | +0.675 |
oid | +0.659 |
Neg logit contributions | |
zzo | -3.668 |
matured | -3.620 |
rhy | -3.562 |
irit | -3.519 |
Dise | -3.493 |
Token | her |
Token ID | 372 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
zzo | +0.157 |
matured | +0.153 |
rhy | +0.149 |
irit | +0.148 |
Dise | +0.144 |
Neg logit contributions | |
Osw | -0.134 |
appropriately | -0.123 |
med | -0.123 |
gest | -0.122 |
\": | -0.120 |
Token | ically |
Token ID | 1146 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
Osw | +1.461 |
med | +1.405 |
ifiable | +1.318 |
appropriately | +1.293 |
oid | +1.278 |
Neg logit contributions | |
zzo | -5.888 |
matured | -5.758 |
rhy | -5.707 |
Dise | -5.585 |
irit | -5.583 |
Token | ( |
Token ID | 357 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
zzo | +0.022 |
matured | +0.021 |
rhy | +0.020 |
irit | +0.020 |
Dise | +0.020 |
Neg logit contributions | |
Osw | -0.023 |
med | -0.022 |
appropriately | -0.022 |
gest | -0.022 |
ifiable | -0.022 |
Token | some |
Token ID | 11246 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
Osw | +3.047 |
med | +3.013 |
appropriately | +2.959 |
gest | +2.906 |
ifiable | +2.863 |
Neg logit contributions | |
zzo | -3.225 |
matured | -3.166 |
rhy | -3.078 |
irit | -3.003 |
Dise | -2.982 |
Token | would |
Token ID | 561 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Osw | +6.286 |
med | +6.155 |
ifiable | +5.914 |
oid | +5.894 |
appropriately | +5.887 |
Neg logit contributions | |
zzo | -6.577 |
matured | -6.479 |
Dise | -6.219 |
gae | -6.147 |
irit | -6.136 |
Token | say |
Token ID | 910 |
Feature activation | -9.52e+00 |
Pos logit contributions | |
Osw | +5.006 |
med | +4.838 |
gest | +4.769 |
oid | +4.655 |
appropriately | +4.592 |
Neg logit contributions | |
zzo | -8.336 |
matured | -8.139 |
Dise | -7.997 |
irit | -7.848 |
Interstitial | -7.697 |
Token | obscene |
Token ID | 33390 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
Osw | +6.213 |
med | +6.066 |
appropriately | +5.936 |
ifiable | +5.890 |
oid | +5.846 |
Neg logit contributions | |
zzo | -5.949 |
matured | -5.649 |
irit | -5.572 |
gae | -5.467 |
Dise | -5.409 |
Token | ly |
Token ID | 306 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Osw | +1.666 |
med | +1.599 |
appropriately | +1.514 |
gest | +1.504 |
ifiable | +1.503 |
Neg logit contributions | |
zzo | -5.968 |
matured | -5.832 |
irit | -5.722 |
Dise | -5.677 |
rhy | -5.676 |
Token | ) |
Token ID | 8 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Osw | +0.379 |
med | +0.360 |
appropriately | +0.354 |
gest | +0.352 |
ifiable | +0.352 |
Neg logit contributions | |
zzo | -0.369 |
matured | -0.359 |
rhy | -0.348 |
irit | -0.343 |
Dise | -0.338 |
Token | Smith |
Token ID | 17919 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
Osw | +3.909 |
med | +3.787 |
gest | +3.613 |
\": | +3.590 |
oid | +3.543 |
Neg logit contributions | |
matured | -5.758 |
zzo | -5.678 |
rhy | -5.494 |
Dise | -5.375 |
irit | -5.330 |
Token | sonian |
Token ID | 35202 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
Osw | +0.311 |
med | +0.169 |
gest | +0.077 |
ifiable | +0.039 |
sonian | +0.008 |
Neg logit contributions | |
matured | -10.861 |
zzo | -10.831 |
rhy | -10.632 |
Dise | -10.599 |
irit | -10.465 |
Token | Center |
Token ID | 3337 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Osw | +4.577 |
med | +4.386 |
gest | +4.309 |
ifiable | +4.244 |
oid | +4.226 |
Neg logit contributions | |
zzo | -5.862 |
matured | -5.610 |
rhy | -5.443 |
irit | -5.418 |
Dise | -5.375 |
Token | for |
Token ID | 329 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
zzo | +0.790 |
matured | +0.763 |
rhy | +0.746 |
irit | +0.737 |
Dise | +0.727 |
Neg logit contributions | |
Osw | -0.649 |
med | -0.615 |
gest | -0.603 |
appropriately | -0.602 |
ifiable | -0.598 |
Token | Ast |
Token ID | 8304 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
Osw | +1.671 |
med | +1.554 |
appropriately | +1.551 |
gest | +1.529 |
ifiable | +1.526 |
Neg logit contributions | |
zzo | -2.185 |
matured | -2.126 |
rhy | -2.072 |
irit | -2.038 |
Dise | -2.024 |
Token | roph |
Token ID | 10051 |
Feature activation | -8.19e+00 |
Pos logit contributions | |
Osw | +4.334 |
med | +4.230 |
gest | +4.160 |
ifiable | +4.131 |
oid | +4.130 |
Neg logit contributions | |
zzo | -4.728 |
matured | -4.728 |
rhy | -4.558 |
Dise | -4.458 |
irit | -4.416 |
Token | ysics |
Token ID | 23154 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Osw | +3.574 |
med | +3.523 |
oid | +3.459 |
ifiable | +3.418 |
gest | +3.381 |
Neg logit contributions | |
matured | -6.971 |
zzo | -6.956 |
rhy | -6.832 |
Dise | -6.669 |
sqor | -6.560 |
Token | added |
Token ID | 2087 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Osw | +2.290 |
med | +2.171 |
gest | +2.127 |
appropriately | +2.113 |
oid | +2.109 |
Neg logit contributions | |
zzo | -2.720 |
matured | -2.631 |
rhy | -2.555 |
irit | -2.554 |
Dise | -2.524 |
Token | : |
Token ID | 25 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
zzo | +0.275 |
matured | +0.268 |
rhy | +0.261 |
irit | +0.259 |
Dise | +0.256 |
Neg logit contributions | |
Osw | -0.182 |
med | -0.169 |
gest | -0.167 |
appropriately | -0.166 |
ifiable | -0.165 |
Token | � |
Token ID | 564 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
zzo | +2.166 |
matured | +2.111 |
rhy | +2.054 |
irit | +2.024 |
Dise | +1.996 |
Neg logit contributions | |
Osw | -1.759 |
med | -1.644 |
appropriately | -1.624 |
gest | -1.619 |
ifiable | -1.605 |
Token | � |
Token ID | 250 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
zzo | +1.335 |
matured | +1.291 |
rhy | +1.247 |
irit | +1.232 |
Dise | +1.199 |
Neg logit contributions | |
Osw | -1.727 |
med | -1.627 |
ifiable | -1.608 |
appropriately | -1.608 |
gest | -1.607 |
Token | Europe |
Token ID | 2031 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
zzo | +1.472 |
matured | +1.442 |
rhy | +1.402 |
irit | +1.372 |
Dise | +1.332 |
Neg logit contributions | |
Osw | -1.747 |
med | -1.650 |
appropriately | -1.638 |
gest | -1.628 |
ifiable | -1.624 |
Token | against |
Token ID | 1028 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
Osw | +0.455 |
med | +0.435 |
gest | +0.428 |
appropriately | +0.427 |
oid | +0.424 |
Neg logit contributions | |
zzo | -0.386 |
matured | -0.374 |
rhy | -0.363 |
irit | -0.357 |
Dise | -0.353 |
Token | short |
Token ID | 1790 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
matured | +3.548 |
zzo | +3.548 |
rhy | +3.421 |
irit | +3.333 |
Dise | +3.180 |
Neg logit contributions | |
Osw | -4.694 |
appropriately | -4.392 |
med | -4.376 |
oid | -4.360 |
gest | -4.335 |
Token | - |
Token ID | 12 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
zzo | +0.033 |
matured | +0.032 |
rhy | +0.031 |
irit | +0.031 |
Dise | +0.030 |
Neg logit contributions | |
Osw | -0.023 |
med | -0.021 |
appropriately | -0.021 |
gest | -0.021 |
ifiable | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Osw | +1.188 |
med | +1.154 |
gest | +1.145 |
appropriately | +1.125 |
oid | +1.106 |
Neg logit contributions | |
zzo | -1.872 |
matured | -1.801 |
rhy | -1.771 |
irit | -1.753 |
Dise | -1.723 |
Token | medium |
Token ID | 7090 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
Osw | +2.075 |
med | +2.043 |
ifiable | +1.979 |
gest | +1.968 |
appropriately | +1.958 |
Neg logit contributions | |
zzo | -1.895 |
matured | -1.818 |
rhy | -1.753 |
irit | -1.750 |
Dise | -1.741 |
Token | - |
Token ID | 12 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
med | +3.730 |
Osw | +3.655 |
gest | +3.615 |
ifiable | +3.485 |
oid | +3.472 |
Neg logit contributions | |
zzo | -7.517 |
matured | -7.273 |
irit | -7.132 |
rhy | -7.081 |
Dise | -7.039 |
Token | range |
Token ID | 9521 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Osw | +1.082 |
med | +1.063 |
gest | +1.047 |
appropriately | +1.029 |
oid | +1.002 |
Neg logit contributions | |
zzo | -1.927 |
matured | -1.865 |
rhy | -1.837 |
irit | -1.824 |
Dise | -1.791 |
Token | Iranian |
Token ID | 10704 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
Osw | +0.469 |
med | +0.448 |
appropriately | +0.443 |
gest | +0.442 |
ifiable | +0.440 |
Neg logit contributions | |
zzo | -0.299 |
matured | -0.287 |
rhy | -0.276 |
irit | -0.271 |
Dise | -0.266 |
Token | missiles |
Token ID | 12798 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Osw | +2.560 |
med | +2.468 |
gest | +2.448 |
appropriately | +2.442 |
ifiable | +2.432 |
Neg logit contributions | |
zzo | -1.406 |
matured | -1.321 |
rhy | -1.278 |
Dise | -1.240 |
irit | -1.234 |
Token | . |
Token ID | 13 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
zzo | +1.024 |
matured | +0.999 |
rhy | +0.967 |
irit | +0.951 |
Dise | +0.934 |
Neg logit contributions | |
Osw | -1.039 |
med | -0.973 |
appropriately | -0.967 |
gest | -0.961 |
ifiable | -0.957 |
Token | discovered |
Token ID | 5071 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Osw | +4.362 |
med | +4.156 |
ifiable | +4.104 |
appropriately | +4.045 |
hip | +4.004 |
Neg logit contributions | |
zzo | -4.246 |
irit | -4.021 |
matured | -3.991 |
Dise | -3.908 |
rhy | -3.873 |
Token | graffiti |
Token ID | 28530 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Osw | +1.095 |
med | +1.037 |
ifiable | +1.025 |
appropriately | +1.024 |
gest | +1.023 |
Neg logit contributions | |
zzo | -0.909 |
matured | -0.875 |
rhy | -0.840 |
irit | -0.839 |
Dise | -0.823 |
Token | on |
Token ID | 319 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
zzo | +0.267 |
matured | +0.259 |
rhy | +0.251 |
irit | +0.247 |
Dise | +0.244 |
Neg logit contributions | |
Osw | -0.278 |
med | -0.263 |
appropriately | -0.260 |
gest | -0.259 |
ifiable | -0.257 |
Token | both |
Token ID | 1111 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
Osw | +3.307 |
med | +3.061 |
appropriately | +2.973 |
ifiable | +2.971 |
gest | +2.960 |
Neg logit contributions | |
zzo | -3.541 |
matured | -3.485 |
irit | -3.394 |
rhy | -3.300 |
Dise | -3.296 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
Osw | +2.681 |
med | +2.506 |
ifiable | +2.444 |
gest | +2.442 |
appropriately | +2.433 |
Neg logit contributions | |
zzo | -2.267 |
matured | -2.199 |
irit | -2.115 |
rhy | -2.089 |
Dise | -2.058 |
Token | RAF |
Token ID | 28168 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
Osw | +2.979 |
med | +2.801 |
gest | +2.737 |
ifiable | +2.719 |
oid | +2.693 |
Neg logit contributions | |
zzo | -2.565 |
matured | -2.476 |
irit | -2.404 |
rhy | -2.349 |
Dise | -2.316 |
Token | Bomber |
Token ID | 38474 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
Osw | +5.580 |
med | +5.274 |
gest | +5.101 |
oid | +5.050 |
ifiable | +4.997 |
Neg logit contributions | |
zzo | -5.148 |
matured | -5.014 |
irit | -4.857 |
Dise | -4.665 |
rhy | -4.663 |
Token | Command |
Token ID | 9455 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
Osw | +1.521 |
med | +1.345 |
gest | +1.247 |
oid | +1.220 |
ifiable | +1.176 |
Neg logit contributions | |
zzo | -6.066 |
matured | -5.931 |
irit | -5.791 |
rhy | -5.713 |
Dise | -5.676 |
Token | war |
Token ID | 1175 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
Osw | +4.552 |
med | +4.324 |
gest | +4.138 |
hip | +4.094 |
ifiable | +4.045 |
Neg logit contributions | |
zzo | -6.374 |
matured | -6.170 |
irit | -6.114 |
rhy | -5.922 |
Dise | -5.913 |
Token | memorial |
Token ID | 17357 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
Osw | +3.027 |
med | +2.943 |
gest | +2.857 |
ifiable | +2.817 |
hip | +2.799 |
Neg logit contributions | |
zzo | -3.214 |
matured | -3.079 |
irit | -2.981 |
rhy | -2.950 |
Dise | -2.946 |
Token | in |
Token ID | 287 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Osw | +0.586 |
med | +0.549 |
appropriately | +0.537 |
gest | +0.537 |
ifiable | +0.535 |
Neg logit contributions | |
zzo | -0.678 |
matured | -0.661 |
rhy | -0.639 |
irit | -0.636 |
Dise | -0.627 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
Osw | +0.693 |
med | +0.658 |
appropriately | +0.649 |
gest | +0.649 |
ifiable | +0.645 |
Neg logit contributions | |
zzo | -0.562 |
matured | -0.544 |
rhy | -0.526 |
irit | -0.518 |
Dise | -0.509 |
Token | Republican |
Token ID | 3415 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Osw | +0.711 |
med | +0.675 |
appropriately | +0.667 |
gest | +0.666 |
ifiable | +0.662 |
Neg logit contributions | |
zzo | -0.556 |
matured | -0.538 |
rhy | -0.520 |
irit | -0.511 |
Dise | -0.502 |
Token | bill |
Token ID | 2855 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
Osw | +1.308 |
med | +1.241 |
gest | +1.224 |
oid | +1.214 |
ifiable | +1.213 |
Neg logit contributions | |
zzo | -1.224 |
matured | -1.191 |
rhy | -1.152 |
irit | -1.138 |
Dise | -1.123 |
Token | that |
Token ID | 326 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
zzo | +0.620 |
matured | +0.603 |
rhy | +0.585 |
irit | +0.568 |
Dise | +0.558 |
Neg logit contributions | |
Osw | -0.710 |
appropriately | -0.668 |
med | -0.666 |
gest | -0.660 |
ifiable | -0.656 |
Token | reduced |
Token ID | 5322 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
zzo | +0.133 |
matured | +0.130 |
rhy | +0.125 |
irit | +0.122 |
Dise | +0.120 |
Neg logit contributions | |
Osw | -0.156 |
med | -0.147 |
appropriately | -0.147 |
gest | -0.146 |
ifiable | -0.145 |
Token | early |
Token ID | 1903 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
Osw | +2.991 |
med | +2.892 |
gest | +2.819 |
ifiable | +2.790 |
appropriately | +2.768 |
Neg logit contributions | |
zzo | -3.166 |
matured | -3.074 |
irit | -2.998 |
Dise | -2.959 |
rhy | -2.951 |
Token | voting |
Token ID | 6709 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Osw | +4.341 |
med | +4.253 |
gest | +4.189 |
ifiable | +4.117 |
oid | +4.059 |
Neg logit contributions | |
zzo | -5.991 |
matured | -5.783 |
Dise | -5.701 |
irit | -5.658 |
rhy | -5.603 |
Token | in |
Token ID | 287 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Osw | +1.252 |
med | +1.188 |
gest | +1.167 |
appropriately | +1.167 |
ifiable | +1.161 |
Neg logit contributions | |
zzo | -1.339 |
matured | -1.299 |
rhy | -1.263 |
irit | -1.251 |
Dise | -1.229 |
Token | the |
Token ID | 262 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Osw | +1.770 |
med | +1.684 |
gest | +1.662 |
appropriately | +1.659 |
ifiable | +1.642 |
Neg logit contributions | |
zzo | -1.734 |
matured | -1.684 |
irit | -1.624 |
rhy | -1.624 |
Dise | -1.594 |
Token | state |
Token ID | 1181 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
Osw | +0.300 |
med | +0.282 |
appropriately | +0.280 |
gest | +0.279 |
ifiable | +0.277 |
Neg logit contributions | |
zzo | -0.273 |
matured | -0.265 |
rhy | -0.257 |
irit | -0.252 |
Dise | -0.248 |
Token | from |
Token ID | 422 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
zzo | +3.270 |
matured | +3.184 |
rhy | +3.087 |
Dise | +2.953 |
irit | +2.944 |
Neg logit contributions | |
Osw | -3.516 |
appropriately | -3.220 |
gest | -3.194 |
med | -3.192 |
ifiable | -3.177 |