Token | bind |
Token ID | 21653 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Container | +2.933 |
Bundy | +2.439 |
Columb | +2.175 |
container | +2.153 |
Clifford | +2.136 |
Neg logit contributions | |
wives | -3.063 |
Ov | -2.953 |
emale | -2.872 |
romy | -2.596 |
etz | -2.535 |
Token | directive |
Token ID | 22644 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Container | +1.181 |
Bundy | +1.003 |
Columb | +0.897 |
Clifford | +0.877 |
STL | +0.866 |
Neg logit contributions | |
wives | -1.203 |
Ov | -1.144 |
emale | -1.109 |
romy | -1.014 |
etz | -0.991 |
Token | : |
Token ID | 25 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Container | +1.810 |
Bundy | +1.506 |
Columb | +1.329 |
Clifford | +1.300 |
container | +1.291 |
Neg logit contributions | |
wives | -2.157 |
Ov | -2.059 |
emale | -2.014 |
romy | -1.849 |
etz | -1.802 |
Token |
|
Token ID | 198 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
Container | +2.168 |
Bundy | +1.737 |
Columb | +1.514 |
container | +1.488 |
Clifford | +1.472 |
Neg logit contributions | |
wives | -3.107 |
Ov | -2.970 |
emale | -2.934 |
romy | -2.698 |
etz | -2.646 |
Token |
|
Token ID | 198 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Container | +3.003 |
Bundy | +2.426 |
Columb | +2.056 |
STL | +1.983 |
Clifford | +1.979 |
Neg logit contributions | |
wives | -4.917 |
emale | -4.879 |
Ov | -4.745 |
romy | -4.380 |
etz | -4.243 |
Token | < |
Token ID | 27 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Container | +3.222 |
Bundy | +2.578 |
Columb | +2.291 |
container | +2.259 |
Container | +2.227 |
Neg logit contributions | |
wives | -4.327 |
Ov | -4.188 |
emale | -4.130 |
romy | -3.740 |
etz | -3.690 |
Token | body |
Token ID | 2618 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
Container | +7.636 |
Bundy | +5.875 |
container | +5.604 |
Container | +5.464 |
container | +5.401 |
Neg logit contributions | |
wives | -9.038 |
emale | -8.679 |
Ov | -8.604 |
etz | -7.769 |
romy | -7.691 |
Token | ng |
Token ID | 23370 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Container | +2.874 |
Bundy | +2.207 |
container | +1.926 |
Columb | +1.894 |
Clifford | +1.810 |
Neg logit contributions | |
wives | -4.859 |
emale | -4.625 |
Ov | -4.593 |
romy | -4.251 |
etz | -4.151 |
Token | - |
Token ID | 12 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Container | +1.386 |
Bundy | +1.139 |
Columb | +0.992 |
Clifford | +0.964 |
container | +0.955 |
Neg logit contributions | |
wives | -1.883 |
Ov | -1.803 |
emale | -1.766 |
romy | -1.625 |
etz | -1.594 |
Token | controller |
Token ID | 36500 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Container | +3.156 |
Bundy | +2.607 |
Columb | +2.306 |
container | +2.285 |
Clifford | +2.266 |
Neg logit contributions | |
wives | -3.555 |
Ov | -3.446 |
emale | -3.352 |
romy | -3.044 |
etz | -2.986 |
Token | =" |
Token ID | 2625 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
wives | +0.871 |
Ov | +0.834 |
emale | +0.811 |
romy | +0.755 |
etz | +0.743 |
Neg logit contributions | |
Container | -0.565 |
Bundy | -0.461 |
Columb | -0.396 |
Clifford | -0.385 |
STL | -0.377 |
Token | { |
Token ID | 1391 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Container | +2.901 |
Bundy | +2.347 |
STL | +1.974 |
Columb | +1.957 |
container | +1.948 |
Neg logit contributions | |
wives | -4.280 |
emale | -4.058 |
Ov | -4.007 |
romy | -3.726 |
etz | -3.703 |
Token | ( |
Token ID | 7 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Container | +1.555 |
Bundy | +1.300 |
Columb | +1.144 |
Clifford | +1.114 |
STL | +1.103 |
Neg logit contributions | |
wives | -1.897 |
Ov | -1.817 |
emale | -1.802 |
romy | -1.638 |
etz | -1.597 |
Token | 6 |
Token ID | 21 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Container | +3.048 |
Bundy | +2.621 |
Columb | +2.329 |
Clifford | +2.288 |
STL | +2.278 |
Neg logit contributions | |
wives | -2.960 |
Ov | -2.801 |
emale | -2.740 |
romy | -2.495 |
etz | -2.429 |
Token | s |
Token ID | 82 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Container | +1.879 |
Bundy | +1.576 |
Columb | +1.393 |
Clifford | +1.363 |
STL | +1.362 |
Neg logit contributions | |
wives | -2.071 |
Ov | -1.955 |
emale | -1.942 |
romy | -1.773 |
etz | -1.714 |
Token | )} |
Token ID | 38165 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Container | +3.239 |
Bundy | +2.805 |
Clifford | +2.522 |
Columb | +2.517 |
STL | +2.482 |
Neg logit contributions | |
wives | -2.562 |
emale | -2.428 |
Ov | -2.419 |
romy | -2.108 |
etz | -2.057 |
Token | B |
Token ID | 347 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Container | +2.241 |
Bundy | +1.899 |
Columb | +1.666 |
Clifford | +1.632 |
STL | +1.615 |
Neg logit contributions | |
wives | -2.547 |
emale | -2.399 |
Ov | -2.375 |
romy | -2.175 |
etz | -2.147 |
Token | c |
Token ID | 66 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
Container | +7.526 |
Bundy | +6.554 |
Columb | +5.831 |
estic | +5.660 |
Clifford | +5.554 |
Neg logit contributions | |
wives | -7.780 |
emale | -7.563 |
Ov | -7.414 |
romy | -6.641 |
etz | -6.428 |
Token | 6 |
Token ID | 21 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Container | +4.098 |
Bundy | +3.445 |
Columb | +3.016 |
Clifford | +2.943 |
STL | +2.916 |
Neg logit contributions | |
wives | -5.125 |
Ov | -4.870 |
emale | -4.848 |
romy | -4.373 |
etz | -4.266 |
Token | { |
Token ID | 1391 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Container | +2.711 |
Bundy | +2.223 |
Columb | +1.915 |
Clifford | +1.877 |
container | +1.865 |
Neg logit contributions | |
wives | -3.706 |
emale | -3.524 |
Ov | -3.507 |
romy | -3.213 |
etz | -3.149 |
Token | ( |
Token ID | 7 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Container | +1.721 |
Bundy | +1.435 |
Columb | +1.264 |
Clifford | +1.230 |
STL | +1.217 |
Neg logit contributions | |
wives | -2.124 |
Ov | -2.036 |
emale | -2.027 |
romy | -1.840 |
etz | -1.792 |
Token | 153 |
Token ID | 21395 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
Container | +3.126 |
Bundy | +2.680 |
Columb | +2.383 |
Clifford | +2.347 |
STL | +2.333 |
Neg logit contributions | |
wives | -3.067 |
Ov | -2.901 |
emale | -2.850 |
romy | -2.596 |
etz | -2.525 |
Token | Angular |
Token ID | 28147 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
wives | +0.072 |
Ov | +0.069 |
emale | +0.066 |
romy | +0.062 |
etz | +0.060 |
Neg logit contributions | |
Container | -0.057 |
Bundy | -0.048 |
Columb | -0.042 |
Clifford | -0.041 |
STL | -0.040 |
Token | tutorial |
Token ID | 11808 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Container | +0.827 |
Bundy | +0.677 |
Columb | +0.589 |
Clifford | +0.579 |
container | +0.577 |
Neg logit contributions | |
wives | -1.090 |
Ov | -1.039 |
emale | -1.023 |
romy | -0.937 |
etz | -0.920 |
Token | : |
Token ID | 25 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Container | +1.240 |
Bundy | +1.039 |
Columb | +0.922 |
Clifford | +0.901 |
container | +0.896 |
Neg logit contributions | |
wives | -1.392 |
Ov | -1.322 |
emale | -1.296 |
romy | -1.186 |
etz | -1.155 |
Token |
|
Token ID | 198 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Container | +1.546 |
Bundy | +1.266 |
Columb | +1.108 |
Clifford | +1.080 |
container | +1.072 |
Neg logit contributions | |
wives | -2.071 |
Ov | -1.974 |
emale | -1.939 |
romy | -1.788 |
etz | -1.750 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Container | +1.794 |
Bundy | +1.469 |
Columb | +1.268 |
Clifford | +1.229 |
STL | +1.217 |
Neg logit contributions | |
wives | -2.616 |
Ov | -2.509 |
emale | -2.501 |
romy | -2.288 |
etz | -2.230 |
Token | < |
Token ID | 27 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Container | +2.612 |
Bundy | +2.219 |
Columb | +2.003 |
container | +1.952 |
Clifford | +1.947 |
Neg logit contributions | |
wives | -2.469 |
Ov | -2.370 |
emale | -2.319 |
romy | -2.078 |
etz | -2.034 |
Token | body |
Token ID | 2618 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
Container | +7.176 |
Bundy | +5.582 |
container | +5.329 |
Container | +5.051 |
Clifford | +5.022 |
Neg logit contributions | |
wives | -8.009 |
emale | -7.658 |
Ov | -7.484 |
romy | -6.882 |
etz | -6.860 |
Token | ng |
Token ID | 23370 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Container | +2.603 |
Bundy | +2.121 |
container | +1.879 |
Columb | +1.873 |
Clifford | +1.824 |
Neg logit contributions | |
wives | -3.210 |
Ov | -3.018 |
emale | -3.014 |
romy | -2.765 |
etz | -2.663 |
Token | - |
Token ID | 12 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
Container | +0.733 |
Bundy | +0.602 |
Columb | +0.524 |
Clifford | +0.509 |
container | +0.508 |
Neg logit contributions | |
wives | -0.990 |
Ov | -0.944 |
emale | -0.929 |
romy | -0.854 |
etz | -0.837 |
Token | controller |
Token ID | 36500 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Container | +0.159 |
Bundy | +0.135 |
Columb | +0.121 |
Clifford | +0.118 |
STL | +0.117 |
Neg logit contributions | |
wives | -0.167 |
Ov | -0.158 |
emale | -0.153 |
romy | -0.141 |
etz | -0.138 |
Token | =" |
Token ID | 2625 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
wives | +2.705 |
Ov | +2.586 |
emale | +2.464 |
romy | +2.282 |
etz | +2.257 |
Neg logit contributions | |
Container | -2.303 |
Bundy | -1.960 |
Columb | -1.728 |
Clifford | -1.691 |
STL | -1.663 |
Token | itant |
Token ID | 23737 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Container | +1.150 |
Bundy | +0.909 |
Columb | +0.764 |
Clifford | +0.739 |
STL | +0.723 |
Neg logit contributions | |
wives | -2.080 |
Ov | -2.000 |
emale | -1.952 |
romy | -1.824 |
etz | -1.792 |
Token | faction |
Token ID | 17710 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
Container | +0.906 |
Bundy | +0.733 |
Columb | +0.624 |
Clifford | +0.607 |
container | +0.594 |
Neg logit contributions | |
wives | -1.452 |
Ov | -1.392 |
emale | -1.362 |
romy | -1.268 |
etz | -1.241 |
Token | on |
Token ID | 319 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
wives | +0.508 |
Ov | +0.483 |
emale | +0.469 |
romy | +0.430 |
etz | +0.420 |
Neg logit contributions | |
Container | -0.484 |
Bundy | -0.410 |
Columb | -0.366 |
Clifford | -0.358 |
container | -0.353 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Container | +0.249 |
Bundy | +0.212 |
Columb | +0.188 |
Clifford | +0.183 |
container | +0.180 |
Neg logit contributions | |
wives | -0.277 |
Ov | -0.263 |
emale | -0.257 |
romy | -0.235 |
etz | -0.229 |
Token | one |
Token ID | 530 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Container | +0.804 |
Bundy | +0.688 |
Columb | +0.615 |
Clifford | +0.600 |
STL | +0.592 |
Neg logit contributions | |
wives | -0.818 |
Ov | -0.773 |
emale | -0.757 |
romy | -0.689 |
etz | -0.672 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Container | +0.653 |
Bundy | +0.542 |
Columb | +0.472 |
Clifford | +0.463 |
container | +0.456 |
Neg logit contributions | |
wives | -0.899 |
Ov | -0.854 |
emale | -0.844 |
romy | -0.773 |
etz | -0.757 |
Token | and |
Token ID | 290 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Container | +5.983 |
Bundy | +5.021 |
Clifford | +4.297 |
Columb | +4.288 |
container | +4.227 |
Neg logit contributions | |
wives | -8.632 |
Ov | -8.335 |
emale | -8.096 |
romy | -7.540 |
etz | -7.284 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Container | +2.151 |
Bundy | +1.808 |
Columb | +1.592 |
Clifford | +1.558 |
STL | +1.510 |
Neg logit contributions | |
wives | -2.767 |
Ov | -2.636 |
emale | -2.589 |
romy | -2.386 |
etz | -2.340 |
Token | Old |
Token ID | 5706 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Container | +0.888 |
Bundy | +0.755 |
Columb | +0.673 |
Clifford | +0.657 |
STL | +0.647 |
Neg logit contributions | |
wives | -0.961 |
Ov | -0.912 |
emale | -0.890 |
romy | -0.816 |
etz | -0.797 |
Token | Guard |
Token ID | 4932 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
wives | +1.076 |
Ov | +1.028 |
emale | +0.980 |
romy | +0.907 |
etz | +0.892 |
Neg logit contributions | |
Container | -0.963 |
Bundy | -0.806 |
Columb | -0.723 |
Clifford | -0.701 |
container | -0.699 |
Token | faction |
Token ID | 17710 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
wives | +0.247 |
Ov | +0.237 |
emale | +0.229 |
romy | +0.210 |
etz | +0.207 |
Neg logit contributions | |
Container | -0.215 |
Bundy | -0.179 |
Columb | -0.160 |
Clifford | -0.155 |
STL | -0.154 |
Token | Point |
Token ID | 12727 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Container | +3.751 |
Bundy | +2.878 |
Columb | +2.461 |
Clifford | +2.399 |
container | +2.322 |
Neg logit contributions | |
wives | -6.924 |
Ov | -6.654 |
emale | -6.602 |
romy | -6.145 |
etz | -5.975 |
Token | slide |
Token ID | 10649 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
Container | +3.989 |
Bundy | +2.833 |
container | +2.456 |
Columb | +2.433 |
STL | +2.389 |
Neg logit contributions | |
wives | -8.168 |
emale | -7.800 |
Ov | -7.699 |
romy | -7.251 |
etz | -6.921 |
Token | PNG |
Token ID | 36182 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Container | +2.924 |
Bundy | +2.351 |
Columb | +2.016 |
Clifford | +1.957 |
STL | +1.937 |
Neg logit contributions | |
wives | -4.570 |
Ov | -4.361 |
emale | -4.294 |
romy | -3.984 |
etz | -3.881 |
Token | larger |
Token ID | 4025 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Container | +2.492 |
Bundy | +2.088 |
container | +1.866 |
STL | +1.829 |
Columb | +1.827 |
Neg logit contributions | |
wives | -2.887 |
Ov | -2.725 |
emale | -2.718 |
romy | -2.528 |
etz | -2.365 |
Token | image |
Token ID | 2939 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
Container | +2.415 |
Bundy | +1.936 |
container | +1.708 |
Columb | +1.693 |
Clifford | +1.633 |
Neg logit contributions | |
wives | -3.609 |
emale | -3.483 |
Ov | -3.419 |
romy | -3.188 |
etz | -3.056 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Container | +4.031 |
Bundy | +3.089 |
Columb | +2.601 |
Clifford | +2.587 |
STL | +2.577 |
Neg logit contributions | |
emale | -7.456 |
wives | -7.328 |
Ov | -6.751 |
romy | -6.620 |
etz | -6.182 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Container | +4.683 |
Bundy | +3.714 |
Columb | +3.096 |
STL | +2.998 |
container | +2.892 |
Neg logit contributions | |
emale | -10.079 |
wives | -9.647 |
Ov | -9.277 |
romy | -8.837 |
ntil | -8.691 |
Token | larg |
Token ID | 15521 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Container | +6.083 |
Bundy | +4.728 |
Container | +4.511 |
grid | +4.449 |
STL | +4.267 |
Neg logit contributions | |
emale | -7.846 |
wives | -7.828 |
Ov | -7.631 |
romy | -6.908 |
etz | -6.864 |
Token | er |
Token ID | 263 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Container | +2.919 |
Bundy | +2.452 |
Columb | +2.145 |
container | +2.132 |
STL | +2.101 |
Neg logit contributions | |
wives | -3.505 |
Ov | -3.326 |
emale | -3.276 |
romy | -2.999 |
etz | -2.883 |
Token | image |
Token ID | 2939 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Container | +4.851 |
Bundy | +3.729 |
container | +3.507 |
Columb | +3.167 |
STL | +3.165 |
Neg logit contributions | |
wives | -8.850 |
emale | -8.752 |
Ov | -8.247 |
romy | -7.844 |
kos | -7.395 |
Token | T |
Token ID | 309 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Container | +5.283 |
Bundy | +4.123 |
STL | +3.657 |
container | +3.615 |
Columb | +3.532 |
Neg logit contributions | |
wives | -8.242 |
emale | -8.170 |
Ov | -7.550 |
romy | -7.192 |
ominated | -6.826 |
Token | s |
Token ID | 82 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
wives | +1.414 |
Ov | +1.346 |
emale | +1.281 |
romy | +1.185 |
etz | +1.158 |
Neg logit contributions | |
Container | -1.401 |
Bundy | -1.189 |
Columb | -1.066 |
Clifford | -1.044 |
container | -1.026 |
Token | )} |
Token ID | 38165 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Container | +0.469 |
Bundy | +0.409 |
Columb | +0.374 |
Clifford | +0.368 |
STL | +0.364 |
Neg logit contributions | |
wives | -0.323 |
Ov | -0.304 |
emale | -0.293 |
romy | -0.261 |
etz | -0.253 |
Token | 13 |
Token ID | 1511 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Container | +0.157 |
Bundy | +0.133 |
Columb | +0.119 |
Clifford | +0.116 |
STL | +0.115 |
Neg logit contributions | |
wives | -0.161 |
Ov | -0.153 |
emale | -0.149 |
romy | -0.136 |
etz | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
wives | +2.026 |
Ov | +1.926 |
emale | +1.768 |
romy | +1.655 |
etz | +1.620 |
Neg logit contributions | |
Container | -2.324 |
Bundy | -1.992 |
Columb | -1.801 |
Clifford | -1.768 |
container | -1.755 |
Token | R |
Token ID | 371 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
Container | +2.531 |
Bundy | +2.153 |
Columb | +1.892 |
Clifford | +1.859 |
STL | +1.844 |
Neg logit contributions | |
wives | -2.796 |
emale | -2.626 |
Ov | -2.595 |
romy | -2.379 |
etz | -2.359 |
Token | c |
Token ID | 66 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Container | +5.092 |
Bundy | +4.382 |
Columb | +3.926 |
estic | +3.824 |
STL | +3.796 |
Neg logit contributions | |
wives | -5.261 |
Ov | -5.098 |
emale | -4.955 |
romy | -4.460 |
etz | -4.318 |
Token | 1 |
Token ID | 16 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
Container | +6.439 |
Bundy | +5.576 |
Columb | +4.867 |
Container | +4.849 |
STL | +4.845 |
Neg logit contributions | |
wives | -7.371 |
emale | -7.093 |
Ov | -7.044 |
romy | -6.275 |
etz | -6.152 |
Token | { |
Token ID | 1391 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Container | +3.154 |
Bundy | +2.544 |
STL | +2.153 |
Columb | +2.125 |
container | +2.104 |
Neg logit contributions | |
wives | -4.654 |
emale | -4.414 |
Ov | -4.341 |
romy | -4.059 |
etz | -4.031 |
Token | ( |
Token ID | 7 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Container | +1.854 |
Bundy | +1.547 |
Columb | +1.359 |
Clifford | +1.325 |
STL | +1.312 |
Neg logit contributions | |
wives | -2.292 |
Ov | -2.196 |
emale | -2.184 |
romy | -1.984 |
etz | -1.934 |
Token | 12 |
Token ID | 1065 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Container | +3.869 |
Bundy | +3.329 |
Columb | +2.947 |
Clifford | +2.912 |
STL | +2.900 |
Neg logit contributions | |
wives | -3.773 |
Ov | -3.561 |
emale | -3.502 |
romy | -3.189 |
etz | -3.107 |
Token | 59 |
Token ID | 3270 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Container | +1.374 |
Bundy | +1.163 |
Columb | +1.030 |
Clifford | +1.012 |
STL | +1.003 |
Neg logit contributions | |
wives | -1.443 |
Ov | -1.364 |
emale | -1.351 |
romy | -1.229 |
etz | -1.196 |
Token | slide |
Token ID | 10649 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
Container | +3.989 |
Bundy | +2.833 |
container | +2.456 |
Columb | +2.433 |
STL | +2.389 |
Neg logit contributions | |
wives | -8.168 |
emale | -7.800 |
Ov | -7.699 |
romy | -7.251 |
etz | -6.921 |
Token | PNG |
Token ID | 36182 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Container | +2.924 |
Bundy | +2.351 |
Columb | +2.016 |
Clifford | +1.957 |
STL | +1.937 |
Neg logit contributions | |
wives | -4.570 |
Ov | -4.361 |
emale | -4.294 |
romy | -3.984 |
etz | -3.881 |
Token | larger |
Token ID | 4025 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Container | +2.492 |
Bundy | +2.088 |
container | +1.866 |
STL | +1.829 |
Columb | +1.827 |
Neg logit contributions | |
wives | -2.887 |
Ov | -2.725 |
emale | -2.718 |
romy | -2.528 |
etz | -2.365 |
Token | image |
Token ID | 2939 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
Container | +2.415 |
Bundy | +1.936 |
container | +1.708 |
Columb | +1.693 |
Clifford | +1.633 |
Neg logit contributions | |
wives | -3.609 |
emale | -3.483 |
Ov | -3.419 |
romy | -3.188 |
etz | -3.056 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Container | +4.031 |
Bundy | +3.089 |
Columb | +2.601 |
Clifford | +2.587 |
STL | +2.577 |
Neg logit contributions | |
emale | -7.456 |
wives | -7.328 |
Ov | -6.751 |
romy | -6.620 |
etz | -6.182 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Container | +4.683 |
Bundy | +3.714 |
Columb | +3.096 |
STL | +2.998 |
container | +2.892 |
Neg logit contributions | |
emale | -10.079 |
wives | -9.647 |
Ov | -9.277 |
romy | -8.837 |
ntil | -8.691 |
Token | larg |
Token ID | 15521 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Container | +6.083 |
Bundy | +4.728 |
Container | +4.511 |
grid | +4.449 |
STL | +4.267 |
Neg logit contributions | |
emale | -7.846 |
wives | -7.828 |
Ov | -7.631 |
romy | -6.908 |
etz | -6.864 |
Token | er |
Token ID | 263 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Container | +2.919 |
Bundy | +2.452 |
Columb | +2.145 |
container | +2.132 |
STL | +2.101 |
Neg logit contributions | |
wives | -3.505 |
Ov | -3.326 |
emale | -3.276 |
romy | -2.999 |
etz | -2.883 |
Token | image |
Token ID | 2939 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Container | +4.851 |
Bundy | +3.729 |
container | +3.507 |
Columb | +3.167 |
STL | +3.165 |
Neg logit contributions | |
wives | -8.850 |
emale | -8.752 |
Ov | -8.247 |
romy | -7.844 |
kos | -7.395 |
Token | T |
Token ID | 309 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Container | +5.283 |
Bundy | +4.123 |
STL | +3.657 |
container | +3.615 |
Columb | +3.532 |
Neg logit contributions | |
wives | -8.242 |
emale | -8.170 |
Ov | -7.550 |
romy | -7.192 |
ominated | -6.826 |
Token | IFF |
Token ID | 29267 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Container | +3.591 |
Bundy | +2.713 |
STL | +2.298 |
container | +2.200 |
Clifford | +2.179 |
Neg logit contributions | |
wives | -7.686 |
emale | -7.475 |
Ov | -7.293 |
romy | -6.802 |
etz | -6.574 |
Token | Settings |
Token ID | 16163 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
Container | +1.713 |
Bundy | +1.440 |
Columb | +1.286 |
container | +1.262 |
Clifford | +1.252 |
Neg logit contributions | |
wives | -1.747 |
Ov | -1.638 |
emale | -1.631 |
romy | -1.477 |
etz | -1.429 |
Token | Icon |
Token ID | 26544 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Container | +0.573 |
Bundy | +0.488 |
Columb | +0.439 |
Clifford | +0.430 |
container | +0.427 |
Neg logit contributions | |
wives | -0.536 |
Ov | -0.505 |
emale | -0.494 |
romy | -0.449 |
etz | -0.436 |
Token | in |
Token ID | 287 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Container | +2.023 |
Bundy | +1.675 |
Columb | +1.487 |
container | +1.457 |
Clifford | +1.453 |
Neg logit contributions | |
wives | -2.258 |
Ov | -2.129 |
emale | -2.109 |
romy | -1.938 |
etz | -1.875 |
Token | the |
Token ID | 262 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Container | +1.250 |
Bundy | +1.029 |
Columb | +0.901 |
Clifford | +0.877 |
container | +0.872 |
Neg logit contributions | |
wives | -1.608 |
Ov | -1.530 |
emale | -1.502 |
romy | -1.384 |
etz | -1.352 |
Token | top |
Token ID | 1353 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Container | +2.198 |
Bundy | +1.805 |
Columb | +1.579 |
container | +1.579 |
Clifford | +1.552 |
Neg logit contributions | |
wives | -2.589 |
emale | -2.439 |
Ov | -2.430 |
romy | -2.219 |
etz | -2.162 |
Token | left |
Token ID | 1364 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Container | +2.029 |
Bundy | +1.609 |
Columb | +1.376 |
container | +1.358 |
Clifford | +1.353 |
Neg logit contributions | |
wives | -3.162 |
Ov | -3.023 |
emale | -2.988 |
romy | -2.760 |
etz | -2.700 |
Token | corner |
Token ID | 5228 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Container | +5.723 |
Bundy | +4.304 |
container | +3.901 |
Columb | +3.798 |
Clifford | +3.776 |
Neg logit contributions | |
wives | -8.529 |
emale | -8.198 |
Ov | -7.991 |
romy | -7.509 |
etz | -7.223 |
Token | . |
Token ID | 13 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
Container | +3.015 |
Bundy | +2.431 |
Columb | +2.148 |
container | +2.123 |
Clifford | +2.107 |
Neg logit contributions | |
wives | -3.715 |
emale | -3.507 |
Ov | -3.495 |
romy | -3.232 |
etz | -3.096 |
Token | Then |
Token ID | 3244 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
Container | +0.638 |
Bundy | +0.539 |
Columb | +0.481 |
Clifford | +0.471 |
STL | +0.464 |
Neg logit contributions | |
wives | -0.661 |
Ov | -0.623 |
emale | -0.616 |
romy | -0.561 |
etz | -0.545 |
Token | , |
Token ID | 11 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
wives | +0.625 |
Ov | +0.598 |
emale | +0.578 |
romy | +0.533 |
etz | +0.522 |
Neg logit contributions | |
Container | -0.544 |
Bundy | -0.457 |
Columb | -0.405 |
Clifford | -0.395 |
STL | -0.390 |
Token | go |
Token ID | 467 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
Container | +0.491 |
Bundy | +0.413 |
Columb | +0.367 |
Clifford | +0.359 |
container | +0.355 |
Neg logit contributions | |
wives | -0.542 |
Ov | -0.513 |
emale | -0.504 |
romy | -0.460 |
etz | -0.450 |
Token | with |
Token ID | 351 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Container | +0.307 |
Bundy | +0.258 |
Columb | +0.228 |
Clifford | +0.224 |
STL | +0.220 |
Neg logit contributions | |
wives | -0.364 |
Ov | -0.343 |
emale | -0.339 |
romy | -0.312 |
etz | -0.304 |
Token | more |
Token ID | 517 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Container | +2.550 |
Bundy | +2.177 |
Columb | +1.956 |
Clifford | +1.913 |
STL | +1.871 |
Neg logit contributions | |
wives | -2.857 |
Ov | -2.637 |
emale | -2.637 |
romy | -2.413 |
etz | -2.353 |
Token | than |
Token ID | 621 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Container | +1.549 |
Bundy | +1.314 |
Columb | +1.182 |
Clifford | +1.142 |
container | +1.138 |
Neg logit contributions | |
wives | -1.709 |
Ov | -1.606 |
emale | -1.588 |
romy | -1.443 |
etz | -1.413 |
Token | three |
Token ID | 1115 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Container | +3.126 |
Bundy | +2.658 |
Columb | +2.347 |
Clifford | +2.276 |
container | +2.274 |
Neg logit contributions | |
wives | -3.716 |
emale | -3.487 |
Ov | -3.468 |
romy | -3.188 |
etz | -3.095 |
Token | minutes |
Token ID | 2431 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
Container | +2.141 |
Bundy | +1.841 |
Columb | +1.668 |
container | +1.634 |
Clifford | +1.632 |
Neg logit contributions | |
wives | -1.986 |
emale | -1.885 |
Ov | -1.868 |
romy | -1.706 |
etz | -1.652 |
Token | left |
Token ID | 1364 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Container | +3.422 |
Bundy | +2.756 |
Columb | +2.392 |
container | +2.358 |
Clifford | +2.309 |
Neg logit contributions | |
wives | -5.440 |
emale | -5.244 |
Ov | -5.219 |
romy | -4.793 |
etz | -4.667 |
Token | in |
Token ID | 287 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Container | +5.705 |
Bundy | +4.719 |
Columb | +4.183 |
Clifford | +4.114 |
STL | +3.988 |
Neg logit contributions | |
wives | -8.225 |
emale | -7.942 |
Ov | -7.667 |
romy | -7.334 |
etz | -6.988 |
Token | the |
Token ID | 262 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Container | +2.949 |
Bundy | +2.408 |
Columb | +2.163 |
Clifford | +2.091 |
container | +2.038 |
Neg logit contributions | |
wives | -4.419 |
emale | -4.160 |
Ov | -4.108 |
romy | -3.808 |
etz | -3.716 |
Token | game |
Token ID | 983 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
Container | +1.856 |
Bundy | +1.600 |
Columb | +1.455 |
Clifford | +1.422 |
container | +1.406 |
Neg logit contributions | |
wives | -1.900 |
emale | -1.777 |
Ov | -1.755 |
romy | -1.610 |
etz | -1.569 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Container | +0.187 |
Bundy | +0.157 |
Columb | +0.138 |
Clifford | +0.135 |
STL | +0.133 |
Neg logit contributions | |
wives | -0.219 |
Ov | -0.210 |
emale | -0.203 |
romy | -0.187 |
etz | -0.183 |
Token | coach |
Token ID | 3985 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Container | +1.274 |
Bundy | +1.070 |
Columb | +0.941 |
Clifford | +0.922 |
STL | +0.906 |
Neg logit contributions | |
wives | -1.612 |
Ov | -1.520 |
emale | -1.509 |
romy | -1.391 |
etz | -1.359 |
Token | rah |
Token ID | 11392 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Container | +0.099 |
Bundy | +0.087 |
Columb | +0.080 |
Clifford | +0.078 |
STL | +0.077 |
Neg logit contributions | |
wives | -0.067 |
Ov | -0.063 |
emale | -0.060 |
romy | -0.053 |
etz | -0.052 |
Token | W |
Token ID | 370 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Container | +1.197 |
Bundy | +1.023 |
Columb | +0.918 |
Clifford | +0.900 |
STL | +0.889 |
Neg logit contributions | |
wives | -1.144 |
Ov | -1.086 |
emale | -1.067 |
romy | -0.968 |
etz | -0.939 |
Token | ether |
Token ID | 6750 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Container | +4.143 |
Bundy | +3.648 |
Columb | +3.354 |
container | +3.283 |
Clifford | +3.271 |
Neg logit contributions | |
wives | -2.608 |
Ov | -2.494 |
emale | -2.365 |
romy | -2.074 |
etz | -1.961 |
Token | s |
Token ID | 82 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
wives | +1.036 |
Ov | +0.983 |
emale | +0.944 |
romy | +0.870 |
etz | +0.854 |
Neg logit contributions | |
Container | -0.996 |
Bundy | -0.842 |
Columb | -0.752 |
Clifford | -0.737 |
STL | -0.726 |
Token | Mysteries |
Token ID | 28298 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
Container | +0.457 |
Bundy | +0.382 |
Columb | +0.339 |
Clifford | +0.328 |
STL | +0.322 |
Neg logit contributions | |
wives | -0.564 |
Ov | -0.538 |
emale | -0.537 |
romy | -0.487 |
etz | -0.477 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Container | +3.798 |
Bundy | +3.177 |
Columb | +2.721 |
Clifford | +2.673 |
STL | +2.589 |
Neg logit contributions | |
wives | -5.343 |
emale | -5.219 |
Ov | -5.077 |
romy | -4.689 |
etz | -4.538 |
Token | comic |
Token ID | 9048 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Container | +4.448 |
Bundy | +3.400 |
Columb | +2.974 |
container | +2.896 |
Clifford | +2.759 |
Neg logit contributions | |
wives | -9.574 |
emale | -9.367 |
Ov | -9.109 |
etz | -8.446 |
romy | -8.351 |
Token | book |
Token ID | 1492 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
Container | +1.646 |
Bundy | +1.369 |
Columb | +1.206 |
container | +1.173 |
Clifford | +1.166 |
Neg logit contributions | |
wives | -2.156 |
Ov | -2.054 |
emale | -2.034 |
romy | -1.857 |
etz | -1.820 |
Token | short |
Token ID | 1790 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Container | +3.532 |
Bundy | +2.964 |
Columb | +2.545 |
container | +2.535 |
Clifford | +2.516 |
Neg logit contributions | |
wives | -5.182 |
emale | -4.980 |
Ov | -4.937 |
romy | -4.486 |
etz | -4.441 |
Token | stories |
Token ID | 3923 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
Container | +1.830 |
Bundy | +1.616 |
Columb | +1.464 |
container | +1.440 |
Clifford | +1.437 |
Neg logit contributions | |
wives | -1.452 |
emale | -1.421 |
Ov | -1.381 |
romy | -1.224 |
etz | -1.176 |
Token | , |
Token ID | 11 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
Container | +3.712 |
Bundy | +3.099 |
Columb | +2.672 |
Clifford | +2.622 |
container | +2.557 |
Neg logit contributions | |
wives | -5.257 |
emale | -5.157 |
Ov | -5.010 |
romy | -4.630 |
etz | -4.501 |
Token | 20 |
Token ID | 1238 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Container | +2.618 |
Bundy | +2.213 |
Columb | +1.967 |
Clifford | +1.924 |
STL | +1.917 |
Neg logit contributions | |
wives | -2.755 |
Ov | -2.619 |
emale | -2.599 |
romy | -2.349 |
etz | -2.288 |
Token | s |
Token ID | 82 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
Container | +1.705 |
Bundy | +1.426 |
Columb | +1.259 |
Clifford | +1.228 |
STL | +1.223 |
Neg logit contributions | |
wives | -2.000 |
Ov | -1.907 |
emale | -1.902 |
romy | -1.716 |
etz | -1.676 |
Token | )} |
Token ID | 38165 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
Container | +0.679 |
Bundy | +0.592 |
Columb | +0.540 |
Clifford | +0.532 |
STL | +0.527 |
Neg logit contributions | |
wives | -0.474 |
Ov | -0.446 |
emale | -0.431 |
romy | -0.383 |
etz | -0.372 |
Token | 9 |
Token ID | 860 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
wives | +0.576 |
Ov | +0.550 |
emale | +0.532 |
romy | +0.490 |
etz | +0.479 |
Neg logit contributions | |
Container | -0.499 |
Bundy | -0.419 |
Columb | -0.371 |
Clifford | -0.362 |
STL | -0.357 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
wives | +1.943 |
Ov | +1.836 |
emale | +1.679 |
romy | +1.573 |
etz | +1.550 |
Neg logit contributions | |
Container | -2.260 |
Bundy | -1.935 |
Columb | -1.750 |
Clifford | -1.722 |
container | -1.704 |
Token | B |
Token ID | 347 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Container | +2.771 |
Bundy | +2.357 |
Columb | +2.061 |
Clifford | +2.029 |
STL | +2.018 |
Neg logit contributions | |
wives | -3.143 |
emale | -2.969 |
Ov | -2.902 |
romy | -2.685 |
etz | -2.673 |
Token | g |
Token ID | 70 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Container | +6.259 |
Bundy | +5.365 |
Columb | +4.736 |
estic | +4.609 |
STL | +4.550 |
Neg logit contributions | |
wives | -7.204 |
emale | -6.986 |
Ov | -6.877 |
romy | -6.194 |
etz | -6.095 |
Token | 5 |
Token ID | 20 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Container | +2.815 |
Bundy | +2.344 |
Columb | +2.043 |
Clifford | +2.001 |
STL | +1.997 |
Neg logit contributions | |
wives | -3.572 |
Ov | -3.410 |
emale | -3.389 |
romy | -3.053 |
etz | -3.015 |
Token | { |
Token ID | 1391 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Container | +2.593 |
Bundy | +2.117 |
Columb | +1.800 |
STL | +1.788 |
Clifford | +1.775 |
Neg logit contributions | |
wives | -3.630 |
emale | -3.435 |
Ov | -3.406 |
romy | -3.156 |
etz | -3.122 |
Token | ( |
Token ID | 7 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Container | +1.218 |
Bundy | +1.020 |
Columb | +0.900 |
Clifford | +0.877 |
STL | +0.867 |
Neg logit contributions | |
wives | -1.453 |
Ov | -1.390 |
emale | -1.367 |
romy | -1.249 |
etz | -1.219 |
Token | 8 |
Token ID | 23 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Container | +1.908 |
Bundy | +1.630 |
Columb | +1.450 |
Clifford | +1.424 |
STL | +1.414 |
Neg logit contributions | |
wives | -1.908 |
Ov | -1.806 |
emale | -1.769 |
romy | -1.615 |
etz | -1.573 |
Token | a |
Token ID | 257 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
wives | +0.704 |
Ov | +0.668 |
emale | +0.650 |
romy | +0.595 |
etz | +0.581 |
Neg logit contributions | |
Container | -0.683 |
Bundy | -0.579 |
Columb | -0.518 |
Clifford | -0.506 |
STL | -0.500 |
Token | brilliant |
Token ID | 10457 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
wives | +0.304 |
Ov | +0.287 |
emale | +0.278 |
romy | +0.253 |
etz | +0.247 |
Neg logit contributions | |
Container | -0.333 |
Bundy | -0.286 |
Columb | -0.257 |
Clifford | -0.252 |
container | -0.249 |
Token | entrepreneur |
Token ID | 19500 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
Container | +0.143 |
Bundy | +0.123 |
Columb | +0.112 |
Clifford | +0.109 |
STL | +0.108 |
Neg logit contributions | |
wives | -0.124 |
Ov | -0.117 |
emale | -0.114 |
romy | -0.103 |
etz | -0.101 |
Token | on |
Token ID | 319 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
wives | +0.283 |
Ov | +0.270 |
emale | +0.262 |
romy | +0.242 |
etz | +0.237 |
Neg logit contributions | |
Container | -0.236 |
Bundy | -0.197 |
Columb | -0.174 |
Clifford | -0.170 |
STL | -0.167 |
Token | one |
Token ID | 530 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
wives | +1.013 |
Ov | +0.970 |
emale | +0.936 |
romy | +0.862 |
etz | +0.844 |
Neg logit contributions | |
Container | -0.876 |
Bundy | -0.735 |
Columb | -0.650 |
Clifford | -0.636 |
STL | -0.626 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
wives | +0.777 |
Ov | +0.741 |
emale | +0.722 |
romy | +0.664 |
etz | +0.650 |
Neg logit contributions | |
Container | -0.643 |
Bundy | -0.537 |
Columb | -0.474 |
Clifford | -0.463 |
container | -0.456 |
Token | , |
Token ID | 11 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Container | +5.338 |
Bundy | +4.427 |
Columb | +3.749 |
Clifford | +3.725 |
container | +3.640 |
Neg logit contributions | |
wives | -8.363 |
Ov | -7.953 |
emale | -7.917 |
romy | -7.336 |
etz | -7.151 |
Token | and |
Token ID | 290 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Container | +2.003 |
Bundy | +1.678 |
Columb | +1.471 |
Clifford | +1.441 |
container | +1.413 |
Neg logit contributions | |
wives | -2.580 |
Ov | -2.427 |
emale | -2.421 |
romy | -2.215 |
etz | -2.175 |
Token | on |
Token ID | 319 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Container | +2.704 |
Bundy | +2.274 |
Columb | +1.994 |
Clifford | +1.959 |
container | +1.927 |
Neg logit contributions | |
wives | -3.328 |
emale | -3.140 |
Ov | -3.091 |
romy | -2.855 |
etz | -2.809 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Container | +1.717 |
Bundy | +1.422 |
Columb | +1.237 |
Clifford | +1.203 |
container | +1.193 |
Neg logit contributions | |
wives | -2.403 |
Ov | -2.285 |
emale | -2.274 |
romy | -2.085 |
etz | -2.036 |
Token | other |
Token ID | 584 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Container | +1.125 |
Bundy | +0.955 |
Columb | +0.853 |
Clifford | +0.838 |
container | +0.832 |
Neg logit contributions | |
wives | -1.188 |
Ov | -1.120 |
emale | -1.111 |
romy | -1.006 |
etz | -0.983 |
Token | { |
Token ID | 1391 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Container | +2.802 |
Bundy | +2.278 |
STL | +1.911 |
Columb | +1.908 |
Clifford | +1.890 |
Neg logit contributions | |
wives | -4.080 |
emale | -3.872 |
Ov | -3.823 |
romy | -3.542 |
etz | -3.524 |
Token | ( |
Token ID | 7 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Container | +0.919 |
Bundy | +0.770 |
Columb | +0.681 |
Clifford | +0.664 |
STL | +0.656 |
Neg logit contributions | |
wives | -1.074 |
Ov | -1.026 |
emale | -1.004 |
romy | -0.919 |
etz | -0.898 |
Token | 132 |
Token ID | 19924 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Container | +2.838 |
Bundy | +2.442 |
Columb | +2.166 |
Clifford | +2.131 |
STL | +2.120 |
Neg logit contributions | |
wives | -2.764 |
Ov | -2.616 |
emale | -2.556 |
romy | -2.331 |
etz | -2.268 |
Token | s |
Token ID | 82 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
Container | +1.029 |
Bundy | +0.866 |
Columb | +0.760 |
Clifford | +0.740 |
container | +0.737 |
Neg logit contributions | |
wives | -1.205 |
Ov | -1.155 |
emale | -1.147 |
romy | -1.038 |
etz | -1.010 |
Token | )} |
Token ID | 38165 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Container | +0.764 |
Bundy | +0.667 |
Columb | +0.607 |
Clifford | +0.600 |
STL | +0.593 |
Neg logit contributions | |
wives | -0.539 |
Ov | -0.507 |
emale | -0.492 |
romy | -0.436 |
etz | -0.423 |
Token | B |
Token ID | 347 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Container | +1.030 |
Bundy | +0.874 |
Columb | +0.771 |
Clifford | +0.757 |
STL | +0.750 |
Neg logit contributions | |
wives | -1.118 |
Ov | -1.048 |
emale | -1.047 |
romy | -0.950 |
etz | -0.934 |
Token | d |
Token ID | 67 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
Container | +6.313 |
Bundy | +5.494 |
Columb | +4.857 |
estic | +4.727 |
Clifford | +4.675 |
Neg logit contributions | |
wives | -6.763 |
emale | -6.541 |
Ov | -6.497 |
romy | -5.815 |
etz | -5.650 |
Token | 7 |
Token ID | 22 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Container | +2.148 |
Bundy | +1.802 |
Columb | +1.597 |
STL | +1.557 |
Clifford | +1.548 |
Neg logit contributions | |
wives | -2.503 |
Ov | -2.389 |
emale | -2.358 |
romy | -2.124 |
etz | -2.075 |
Token | { |
Token ID | 1391 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Container | +2.283 |
Bundy | +1.836 |
Columb | +1.581 |
STL | +1.559 |
container | +1.556 |
Neg logit contributions | |
wives | -3.231 |
emale | -3.084 |
Ov | -3.032 |
romy | -2.801 |
etz | -2.768 |
Token | ( |
Token ID | 7 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Container | +1.232 |
Bundy | +1.031 |
Columb | +0.910 |
Clifford | +0.887 |
STL | +0.877 |
Neg logit contributions | |
wives | -1.477 |
Ov | -1.413 |
emale | -1.393 |
romy | -1.270 |
etz | -1.239 |
Token | 507 |
Token ID | 35378 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Container | +3.428 |
Bundy | +2.945 |
Columb | +2.611 |
Clifford | +2.576 |
STL | +2.566 |
Neg logit contributions | |
wives | -3.336 |
Ov | -3.155 |
emale | -3.093 |
romy | -2.821 |
etz | -2.745 |
Token | told |
Token ID | 1297 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Container | +1.215 |
Bundy | +1.027 |
Columb | +0.910 |
Clifford | +0.888 |
STL | +0.875 |
Neg logit contributions | |
wives | -1.374 |
Ov | -1.308 |
emale | -1.281 |
romy | -1.173 |
etz | -1.139 |
Token | a |
Token ID | 257 |
Feature activation | -5.42e-04 |
Pos logit contributions | |
wives | +0.857 |
Ov | +0.823 |
emale | +0.788 |
romy | +0.726 |
etz | +0.708 |
Neg logit contributions | |
Container | -0.801 |
Bundy | -0.676 |
Columb | -0.597 |
Clifford | -0.586 |
container | -0.582 |
Token | Phoenix |
Token ID | 9643 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
wives | +0.004 |
Ov | +0.003 |
emale | +0.003 |
romy | +0.003 |
etz | +0.003 |
Neg logit contributions | |
Container | -0.004 |
Bundy | -0.003 |
Columb | -0.003 |
Clifford | -0.003 |
STL | -0.003 |
Token | ra |
Token ID | 2179 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
Container | +1.483 |
Bundy | +1.274 |
Columb | +1.147 |
Clifford | +1.117 |
STL | +1.105 |
Neg logit contributions | |
wives | -1.401 |
Ov | -1.319 |
emale | -1.291 |
romy | -1.171 |
etz | -1.141 |
Token | |
Token ID | 3907 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Container | +0.317 |
Bundy | +0.265 |
Columb | +0.233 |
Clifford | +0.228 |
STL | +0.225 |
Neg logit contributions | |
wives | -0.385 |
Ov | -0.368 |
emale | -0.357 |
romy | -0.330 |
etz | -0.323 |
Token | d |
Token ID | 67 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Container | +3.505 |
Bundy | +2.996 |
Columb | +2.706 |
container | +2.649 |
Clifford | +2.638 |
Neg logit contributions | |
wives | -3.132 |
Ov | -2.986 |
emale | -2.851 |
romy | -2.621 |
etz | -2.501 |
Token | io |
Token ID | 952 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Container | +6.478 |
Bundy | +5.544 |
Columb | +4.958 |
estic | +4.900 |
container | +4.756 |
Neg logit contributions | |
wives | -6.961 |
Ov | -6.689 |
emale | -6.502 |
romy | -5.804 |
etz | -5.630 |
Token | st |
Token ID | 336 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Container | +0.973 |
Bundy | +0.831 |
Columb | +0.745 |
Clifford | +0.722 |
container | +0.714 |
Neg logit contributions | |
wives | -1.022 |
Ov | -0.970 |
emale | -0.949 |
romy | -0.864 |
etz | -0.842 |
Token | a |
Token ID | 64 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Container | +2.835 |
Bundy | +2.403 |
Columb | +2.133 |
Clifford | +2.069 |
estic | +2.038 |
Neg logit contributions | |
wives | -3.410 |
Ov | -3.236 |
emale | -3.177 |
romy | -2.917 |
etz | -2.828 |
Token | |
Token ID | 3907 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Container | +2.564 |
Bundy | +2.093 |
Columb | +1.868 |
Clifford | +1.779 |
container | +1.749 |
Neg logit contributions | |
wives | -3.728 |
Ov | -3.532 |
emale | -3.509 |
romy | -3.238 |
etz | -3.105 |
Token | tion |
Token ID | 5378 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Container | +2.703 |
Bundy | +2.294 |
Columb | +2.044 |
Clifford | +1.994 |
container | +1.991 |
Neg logit contributions | |
wives | -2.816 |
Ov | -2.720 |
emale | -2.632 |
romy | -2.392 |
etz | -2.312 |
Token | 2019 |
Token ID | 13130 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
wives | +0.539 |
Ov | +0.512 |
emale | +0.499 |
romy | +0.458 |
etz | +0.449 |
Neg logit contributions | |
Container | -0.476 |
Bundy | -0.401 |
Columb | -0.355 |
Clifford | -0.348 |
STL | -0.343 |
Token | The |
Token ID | 383 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
wives | +1.232 |
Ov | +1.168 |
emale | +1.131 |
romy | +1.029 |
etz | +1.004 |
Neg logit contributions | |
Container | -1.329 |
Bundy | -1.137 |
Columb | -1.023 |
Clifford | -1.002 |
STL | -0.990 |
Token | Washington |
Token ID | 2669 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Container | +2.608 |
Bundy | +2.011 |
Columb | +1.725 |
STL | +1.644 |
Clifford | +1.637 |
Neg logit contributions | |
wives | -4.967 |
emale | -4.704 |
Ov | -4.686 |
romy | -4.379 |
etz | -4.301 |
Token | Times |
Token ID | 3782 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
Container | +2.835 |
Bundy | +2.442 |
Columb | +2.206 |
Clifford | +2.159 |
STL | +2.143 |
Neg logit contributions | |
wives | -2.407 |
Ov | -2.267 |
emale | -2.232 |
romy | -2.002 |
etz | -1.940 |
Token | , |
Token ID | 11 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
Container | +4.834 |
Bundy | +3.982 |
Columb | +3.502 |
Clifford | +3.390 |
STL | +3.302 |
Neg logit contributions | |
wives | -6.953 |
emale | -6.711 |
Ov | -6.626 |
romy | -6.186 |
etz | -5.959 |
Token | LLC |
Token ID | 11419 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Container | +4.332 |
Bundy | +3.622 |
Columb | +3.198 |
Clifford | +3.156 |
STL | +3.100 |
Neg logit contributions | |
wives | -5.223 |
Ov | -4.896 |
emale | -4.851 |
romy | -4.436 |
etz | -4.378 |
Token | . |
Token ID | 13 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Container | +5.610 |
Bundy | +4.792 |
Clifford | +4.075 |
Booster | +3.907 |
Columb | +3.893 |
Neg logit contributions | |
wives | -7.905 |
emale | -7.817 |
Ov | -7.367 |
romy | -6.974 |
etz | -6.586 |
Token | Click |
Token ID | 6914 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Container | +3.217 |
Bundy | +2.568 |
Clifford | +2.159 |
Columb | +2.092 |
STL | +2.009 |
Neg logit contributions | |
wives | -5.697 |
emale | -5.427 |
Ov | -5.382 |
romy | -5.031 |
etz | -4.923 |
Token | here |
Token ID | 994 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Container | +2.321 |
Bundy | +1.947 |
Columb | +1.688 |
Clifford | +1.656 |
STL | +1.641 |
Neg logit contributions | |
wives | -2.997 |
Ov | -2.842 |
emale | -2.811 |
romy | -2.561 |
etz | -2.484 |
Token | for |
Token ID | 329 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Container | +0.700 |
Bundy | +0.583 |
Columb | +0.514 |
Clifford | +0.502 |
container | +0.494 |
Neg logit contributions | |
wives | -0.861 |
Ov | -0.822 |
emale | -0.802 |
romy | -0.738 |
etz | -0.721 |
Token | reprint |
Token ID | 26589 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Container | +0.437 |
Bundy | +0.299 |
Columb | +0.216 |
Clifford | +0.201 |
STL | +0.193 |
Neg logit contributions | |
wives | -1.410 |
Ov | -1.365 |
emale | -1.338 |
romy | -1.264 |
etz | -1.246 |
Token | 153 |
Token ID | 21395 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
Container | +3.126 |
Bundy | +2.680 |
Columb | +2.383 |
Clifford | +2.347 |
STL | +2.333 |
Neg logit contributions | |
wives | -3.067 |
Ov | -2.901 |
emale | -2.850 |
romy | -2.596 |
etz | -2.525 |
Token | s |
Token ID | 82 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
Container | +0.543 |
Bundy | +0.457 |
Columb | +0.404 |
Clifford | +0.394 |
STL | +0.391 |
Neg logit contributions | |
wives | -0.620 |
Ov | -0.593 |
emale | -0.586 |
romy | -0.531 |
etz | -0.518 |
Token | )} |
Token ID | 38165 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
Container | +0.783 |
Bundy | +0.684 |
Columb | +0.623 |
Clifford | +0.615 |
STL | +0.608 |
Neg logit contributions | |
wives | -0.550 |
Ov | -0.517 |
emale | -0.501 |
romy | -0.444 |
etz | -0.432 |
Token | 25 |
Token ID | 1679 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
wives | +0.314 |
Ov | +0.304 |
emale | +0.291 |
romy | +0.271 |
etz | +0.265 |
Neg logit contributions | |
Container | -0.218 |
Bundy | -0.178 |
Columb | -0.155 |
Clifford | -0.150 |
STL | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
wives | +1.753 |
Ov | +1.668 |
emale | +1.542 |
romy | +1.438 |
etz | +1.409 |
Neg logit contributions | |
Container | -1.982 |
Bundy | -1.694 |
Columb | -1.529 |
Clifford | -1.503 |
container | -1.491 |
Token | B |
Token ID | 347 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Container | +2.133 |
Bundy | +1.810 |
Columb | +1.583 |
Clifford | +1.555 |
STL | +1.540 |
Neg logit contributions | |
wives | -2.442 |
emale | -2.296 |
Ov | -2.270 |
romy | -2.080 |
etz | -2.059 |
Token | xc |
Token ID | 25306 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Container | +6.503 |
Bundy | +5.633 |
Columb | +5.014 |
estic | +4.903 |
Clifford | +4.827 |
Neg logit contributions | |
wives | -6.567 |
emale | -6.291 |
Ov | -6.248 |
romy | -5.549 |
etz | -5.418 |
Token | 6 |
Token ID | 21 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
Container | +0.714 |
Bundy | +0.591 |
Columb | +0.517 |
Clifford | +0.506 |
container | +0.498 |
Neg logit contributions | |
wives | -0.925 |
Ov | -0.880 |
emale | -0.859 |
romy | -0.793 |
etz | -0.776 |
Token | { |
Token ID | 1391 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Container | +3.367 |
Bundy | +2.716 |
STL | +2.289 |
container | +2.278 |
Columb | +2.277 |
Neg logit contributions | |
wives | -4.960 |
emale | -4.737 |
Ov | -4.648 |
romy | -4.312 |
etz | -4.260 |
Token | ( |
Token ID | 7 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Container | +2.448 |
Bundy | +2.037 |
Columb | +1.781 |
Clifford | +1.730 |
STL | +1.719 |
Neg logit contributions | |
wives | -3.162 |
emale | -3.066 |
Ov | -3.036 |
romy | -2.762 |
etz | -2.684 |
Token | 222 |
Token ID | 23148 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Container | +4.034 |
Bundy | +3.464 |
Columb | +3.065 |
Clifford | +3.020 |
STL | +3.013 |
Neg logit contributions | |
wives | -3.994 |
Ov | -3.779 |
emale | -3.717 |
romy | -3.386 |
etz | -3.294 |
Token | larger |
Token ID | 4025 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Container | +2.492 |
Bundy | +2.088 |
container | +1.866 |
STL | +1.829 |
Columb | +1.827 |
Neg logit contributions | |
wives | -2.887 |
Ov | -2.725 |
emale | -2.718 |
romy | -2.528 |
etz | -2.365 |
Token | image |
Token ID | 2939 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
Container | +2.415 |
Bundy | +1.936 |
container | +1.708 |
Columb | +1.693 |
Clifford | +1.633 |
Neg logit contributions | |
wives | -3.609 |
emale | -3.483 |
Ov | -3.419 |
romy | -3.188 |
etz | -3.056 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Container | +4.031 |
Bundy | +3.089 |
Columb | +2.601 |
Clifford | +2.587 |
STL | +2.577 |
Neg logit contributions | |
emale | -7.456 |
wives | -7.328 |
Ov | -6.751 |
romy | -6.620 |
etz | -6.182 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Container | +4.683 |
Bundy | +3.714 |
Columb | +3.096 |
STL | +2.998 |
container | +2.892 |
Neg logit contributions | |
emale | -10.079 |
wives | -9.647 |
Ov | -9.277 |
romy | -8.837 |
ntil | -8.691 |
Token | larg |
Token ID | 15521 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Container | +6.083 |
Bundy | +4.728 |
Container | +4.511 |
grid | +4.449 |
STL | +4.267 |
Neg logit contributions | |
emale | -7.846 |
wives | -7.828 |
Ov | -7.631 |
romy | -6.908 |
etz | -6.864 |
Token | er |
Token ID | 263 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Container | +2.919 |
Bundy | +2.452 |
Columb | +2.145 |
container | +2.132 |
STL | +2.101 |
Neg logit contributions | |
wives | -3.505 |
Ov | -3.326 |
emale | -3.276 |
romy | -2.999 |
etz | -2.883 |
Token | image |
Token ID | 2939 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Container | +4.851 |
Bundy | +3.729 |
container | +3.507 |
Columb | +3.167 |
STL | +3.165 |
Neg logit contributions | |
wives | -8.850 |
emale | -8.752 |
Ov | -8.247 |
romy | -7.844 |
kos | -7.395 |
Token | T |
Token ID | 309 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Container | +5.283 |
Bundy | +4.123 |
STL | +3.657 |
container | +3.615 |
Columb | +3.532 |
Neg logit contributions | |
wives | -8.242 |
emale | -8.170 |
Ov | -7.550 |
romy | -7.192 |
ominated | -6.826 |
Token | IFF |
Token ID | 29267 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Container | +3.591 |
Bundy | +2.713 |
STL | +2.298 |
container | +2.200 |
Clifford | +2.179 |
Neg logit contributions | |
wives | -7.686 |
emale | -7.475 |
Ov | -7.293 |
romy | -6.802 |
etz | -6.574 |
Token | original |
Token ID | 2656 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Container | +1.522 |
Bundy | +1.242 |
Columb | +1.118 |
container | +1.105 |
STL | +1.087 |
Neg logit contributions | |
wives | -1.960 |
emale | -1.862 |
Ov | -1.859 |
romy | -1.713 |
etz | -1.653 |
Token | image |
Token ID | 2939 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
Container | +1.657 |
Bundy | +1.354 |
Columb | +1.176 |
container | +1.160 |
STL | +1.143 |
Neg logit contributions | |
wives | -2.316 |
Ov | -2.208 |
emale | -2.185 |
romy | -2.004 |
etz | -1.957 |
Token | =" |
Token ID | 2625 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
wives | +0.871 |
Ov | +0.834 |
emale | +0.811 |
romy | +0.755 |
etz | +0.743 |
Neg logit contributions | |
Container | -0.565 |
Bundy | -0.461 |
Columb | -0.396 |
Clifford | -0.385 |
STL | -0.377 |
Token | Phone |
Token ID | 6132 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
wives | +0.136 |
Ov | +0.128 |
emale | +0.123 |
romy | +0.110 |
etz | +0.106 |
Neg logit contributions | |
Container | -0.199 |
Bundy | -0.174 |
Columb | -0.159 |
Clifford | -0.156 |
STL | -0.155 |
Token | List |
Token ID | 8053 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
Container | +3.496 |
Bundy | +2.793 |
Columb | +2.390 |
container | +2.372 |
Clifford | +2.342 |
Neg logit contributions | |
wives | -4.971 |
emale | -4.786 |
Ov | -4.752 |
romy | -4.329 |
etz | -4.263 |
Token | Ctrl |
Token ID | 40069 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Container | +0.392 |
Bundy | +0.330 |
Columb | +0.292 |
Clifford | +0.285 |
STL | +0.281 |
Neg logit contributions | |
wives | -0.451 |
Ov | -0.430 |
emale | -0.417 |
romy | -0.384 |
etz | -0.375 |
Token | "> |
Token ID | 5320 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
wives | +1.381 |
Ov | +1.297 |
emale | +1.222 |
romy | +1.107 |
etz | +1.072 |
Neg logit contributions | |
Container | -1.956 |
Bundy | -1.722 |
Columb | -1.565 |
Clifford | -1.546 |
STL | -1.528 |
Token | < |
Token ID | 1279 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Container | +1.126 |
Bundy | +0.940 |
Columb | +0.831 |
Clifford | +0.810 |
container | +0.802 |
Neg logit contributions | |
wives | -1.327 |
Ov | -1.266 |
emale | -1.236 |
romy | -1.134 |
etz | -1.110 |
Token | ul |
Token ID | 377 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Container | +6.461 |
Bundy | +5.220 |
container | +4.750 |
estic | +4.657 |
Container | +4.656 |
Neg logit contributions | |
wives | -6.853 |
Ov | -6.579 |
emale | -6.514 |
romy | -5.757 |
etz | -5.751 |
Token | > |
Token ID | 29 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Container | +1.604 |
Bundy | +1.335 |
Columb | +1.185 |
container | +1.172 |
Clifford | +1.154 |
Neg logit contributions | |
wives | -1.780 |
Ov | -1.682 |
emale | -1.655 |
romy | -1.512 |
etz | -1.467 |
Token | < |
Token ID | 1279 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
Container | +1.234 |
Bundy | +1.026 |
Columb | +0.907 |
Clifford | +0.882 |
container | +0.877 |
Neg logit contributions | |
wives | -1.475 |
Ov | -1.406 |
emale | -1.377 |
romy | -1.262 |
etz | -1.234 |
Token | li |
Token ID | 4528 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Container | +7.025 |
Bundy | +6.004 |
container | +5.519 |
Clifford | +5.448 |
estic | +5.445 |
Neg logit contributions | |
wives | -4.604 |
Ov | -4.347 |
emale | -4.276 |
romy | -3.667 |
etz | -3.588 |
Token | ng |
Token ID | 23370 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Container | +0.762 |
Bundy | +0.610 |
Columb | +0.526 |
container | +0.509 |
Clifford | +0.508 |
Neg logit contributions | |
wives | -1.182 |
Ov | -1.131 |
emale | -1.109 |
romy | -1.026 |
etz | -1.010 |
Token | { |
Token ID | 1391 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Container | +3.195 |
Bundy | +2.585 |
STL | +2.179 |
container | +2.150 |
Columb | +2.145 |
Neg logit contributions | |
wives | -4.792 |
emale | -4.575 |
Ov | -4.475 |
romy | -4.195 |
etz | -4.175 |
Token | ( |
Token ID | 7 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Container | +1.928 |
Bundy | +1.608 |
Columb | +1.410 |
Clifford | +1.374 |
STL | +1.361 |
Neg logit contributions | |
wives | -2.413 |
Ov | -2.315 |
emale | -2.309 |
romy | -2.093 |
etz | -2.038 |
Token | 21 |
Token ID | 2481 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Container | +4.092 |
Bundy | +3.523 |
Columb | +3.113 |
Clifford | +3.069 |
STL | +3.067 |
Neg logit contributions | |
wives | -4.010 |
Ov | -3.788 |
emale | -3.712 |
romy | -3.386 |
etz | -3.297 |
Token | s |
Token ID | 82 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Container | +2.029 |
Bundy | +1.695 |
Columb | +1.481 |
Clifford | +1.456 |
STL | +1.446 |
Neg logit contributions | |
wives | -2.437 |
emale | -2.312 |
Ov | -2.309 |
romy | -2.103 |
etz | -2.033 |
Token | )} |
Token ID | 38165 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Container | +1.711 |
Bundy | +1.489 |
Columb | +1.351 |
Clifford | +1.339 |
STL | +1.322 |
Neg logit contributions | |
wives | -1.261 |
Ov | -1.188 |
emale | -1.168 |
romy | -1.026 |
etz | -0.998 |
Token | N |
Token ID | 399 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Container | +1.651 |
Bundy | +1.399 |
Columb | +1.230 |
Clifford | +1.207 |
STL | +1.199 |
Neg logit contributions | |
wives | -1.824 |
emale | -1.720 |
Ov | -1.700 |
romy | -1.558 |
etz | -1.533 |
Token | b |
Token ID | 65 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Container | +6.090 |
Bundy | +5.322 |
estic | +4.649 |
Columb | +4.638 |
grid | +4.537 |
Neg logit contributions | |
wives | -6.683 |
Ov | -6.452 |
emale | -6.424 |
romy | -5.669 |
etz | -5.535 |
Token | 4 |
Token ID | 19 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Container | +4.123 |
Bundy | +3.447 |
Columb | +3.018 |
Clifford | +2.977 |
container | +2.976 |
Neg logit contributions | |
wives | -5.100 |
emale | -4.905 |
Ov | -4.825 |
romy | -4.376 |
etz | -4.286 |
Token | { |
Token ID | 1391 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Container | +2.715 |
Bundy | +2.178 |
Columb | +1.853 |
STL | +1.833 |
container | +1.831 |
Neg logit contributions | |
wives | -3.916 |
emale | -3.756 |
Ov | -3.667 |
romy | -3.431 |
etz | -3.369 |
Token | ( |
Token ID | 7 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Container | +0.277 |
Bundy | +0.233 |
Columb | +0.206 |
Clifford | +0.201 |
STL | +0.199 |
Neg logit contributions | |
wives | -0.314 |
Ov | -0.299 |
emale | -0.290 |
romy | -0.267 |
etz | -0.261 |
Token | 82 |
Token ID | 6469 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
Container | +2.362 |
Bundy | +2.028 |
Columb | +1.803 |
Clifford | +1.773 |
STL | +1.762 |
Neg logit contributions | |
wives | -2.301 |
Ov | -2.179 |
emale | -2.129 |
romy | -1.942 |
etz | -1.890 |
Token | er |
Token ID | 263 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Container | +0.930 |
Bundy | +0.773 |
Columb | +0.681 |
Clifford | +0.664 |
container | +0.660 |
Neg logit contributions | |
wives | -1.106 |
Ov | -1.052 |
emale | -1.030 |
romy | -0.950 |
etz | -0.924 |
Token | Icon |
Token ID | 26544 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
wives | +1.328 |
Ov | +1.271 |
emale | +1.222 |
romy | +1.121 |
etz | +1.103 |
Neg logit contributions | |
Container | -1.225 |
Bundy | -1.042 |
Columb | -0.928 |
Clifford | -0.906 |
STL | -0.892 |
Token | at |
Token ID | 379 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Container | +1.601 |
Bundy | +1.331 |
Columb | +1.181 |
container | +1.157 |
Clifford | +1.152 |
Neg logit contributions | |
wives | -1.766 |
Ov | -1.672 |
emale | -1.645 |
romy | -1.513 |
etz | -1.465 |
Token | the |
Token ID | 262 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Container | +0.951 |
Bundy | +0.777 |
Columb | +0.675 |
Clifford | +0.656 |
container | +0.654 |
Neg logit contributions | |
wives | -1.304 |
Ov | -1.240 |
emale | -1.222 |
romy | -1.129 |
etz | -1.099 |
Token | top |
Token ID | 1353 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Container | +1.846 |
Bundy | +1.537 |
Columb | +1.357 |
container | +1.343 |
Clifford | +1.320 |
Neg logit contributions | |
wives | -2.072 |
emale | -1.949 |
Ov | -1.934 |
romy | -1.765 |
etz | -1.713 |
Token | left |
Token ID | 1364 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Container | +1.715 |
Bundy | +1.373 |
Columb | +1.181 |
container | +1.154 |
Clifford | +1.153 |
Neg logit contributions | |
wives | -2.608 |
Ov | -2.495 |
emale | -2.462 |
romy | -2.277 |
etz | -2.219 |
Token | corner |
Token ID | 5228 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Container | +5.243 |
Bundy | +3.926 |
container | +3.529 |
Columb | +3.475 |
Clifford | +3.412 |
Neg logit contributions | |
wives | -8.227 |
emale | -7.900 |
Ov | -7.791 |
romy | -7.284 |
etz | -6.986 |
Token | . |
Token ID | 13 |
Feature activation | +5.42e-03 |
Pos logit contributions | |
Container | +2.497 |
Bundy | +2.054 |
Columb | +1.832 |
container | +1.799 |
Clifford | +1.790 |
Neg logit contributions | |
wives | -2.775 |
Ov | -2.625 |
emale | -2.608 |
romy | -2.390 |
etz | -2.302 |
Token | Choose |
Token ID | 17489 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Container | +0.037 |
Bundy | +0.031 |
Columb | +0.028 |
Clifford | +0.027 |
STL | +0.027 |
Neg logit contributions | |
wives | -0.037 |
Ov | -0.035 |
emale | -0.034 |
romy | -0.031 |
etz | -0.030 |
Token | � |
Token ID | 564 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Container | +0.950 |
Bundy | +0.797 |
Columb | +0.707 |
Clifford | +0.689 |
container | +0.682 |
Neg logit contributions | |
wives | -1.059 |
Ov | -1.005 |
emale | -0.985 |
romy | -0.900 |
etz | -0.880 |
Token | � |
Token ID | 246 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Container | +1.184 |
Bundy | +0.911 |
Columb | +0.743 |
Clifford | +0.708 |
container | +0.698 |
Neg logit contributions | |
wives | -2.490 |
Ov | -2.403 |
emale | -2.358 |
romy | -2.194 |
etz | -2.162 |
Token | != |
Token ID | 14512 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
wives | +3.123 |
Ov | +2.963 |
emale | +2.779 |
romy | +2.454 |
etz | +2.408 |
Neg logit contributions | |
Container | -4.944 |
Bundy | -4.377 |
Columb | -3.981 |
Clifford | -3.942 |
STL | -3.890 |
Token | " |
Token ID | 366 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
Container | +0.149 |
Bundy | +0.125 |
Columb | +0.110 |
Clifford | +0.107 |
STL | +0.106 |
Neg logit contributions | |
wives | -0.177 |
Ov | -0.169 |
emale | -0.164 |
romy | -0.151 |
etz | -0.148 |
Token | D |
Token ID | 35 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
wives | +0.553 |
Ov | +0.528 |
emale | +0.512 |
romy | +0.473 |
etz | +0.463 |
Neg logit contributions | |
Container | -0.451 |
Bundy | -0.376 |
Columb | -0.331 |
Clifford | -0.323 |
STL | -0.318 |
Token | " |
Token ID | 1 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
wives | +1.741 |
Ov | +1.661 |
emale | +1.605 |
romy | +1.470 |
etz | +1.446 |
Neg logit contributions | |
Container | -1.692 |
Bundy | -1.438 |
Columb | -1.283 |
Clifford | -1.255 |
STL | -1.235 |
Token | & |
Token ID | 1222 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
wives | +3.303 |
Ov | +3.178 |
emale | +3.061 |
romy | +2.832 |
etz | +2.788 |
Neg logit contributions | |
Container | -2.485 |
Bundy | -2.081 |
Columb | -1.818 |
Clifford | -1.757 |
STL | -1.734 |
Token | ] |
Token ID | 60 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
wives | +3.081 |
Ov | +2.937 |
emale | +2.759 |
romy | +2.447 |
etz | +2.393 |
Neg logit contributions | |
Container | -4.775 |
Bundy | -4.250 |
Columb | -3.875 |
Clifford | -3.797 |
STL | -3.776 |
Token | @ |
Token ID | 31 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
wives | +8.052 |
Ov | +7.602 |
emale | +7.020 |
romy | +6.425 |
etz | +6.346 |
Neg logit contributions | |
Container | -10.262 |
Bundy | -9.369 |
Columb | -8.508 |
STL | -8.203 |
Clifford | -8.165 |
Token | Key |
Token ID | 7383 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
wives | +3.512 |
Ov | +3.263 |
emale | +3.166 |
romy | +2.908 |
etz | +2.848 |
Neg logit contributions | |
Container | -3.629 |
Bundy | -3.124 |
Columb | -2.817 |
Clifford | -2.740 |
STL | -2.737 |
Token | Take |
Token ID | 12322 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
wives | +2.038 |
Ov | +1.942 |
emale | +1.874 |
romy | +1.718 |
etz | +1.687 |
Neg logit contributions | |
Container | -1.883 |
Bundy | -1.603 |
Columb | -1.424 |
Clifford | -1.392 |
STL | -1.380 |
Token | [ |
Token ID | 58 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
wives | +1.623 |
Ov | +1.546 |
emale | +1.493 |
romy | +1.370 |
etz | +1.343 |
Neg logit contributions | |
Container | -1.501 |
Bundy | -1.276 |
Columb | -1.135 |
Clifford | -1.107 |
STL | -1.092 |
Token | index |
Token ID | 9630 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
wives | +1.836 |
Ov | +1.746 |
emale | +1.682 |
romy | +1.547 |
etz | +1.509 |
Neg logit contributions | |
Container | -1.770 |
Bundy | -1.514 |
Columb | -1.351 |
Clifford | -1.313 |
STL | -1.305 |
Token | th |
Token ID | 294 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
wives | +4.530 |
Ov | +4.271 |
emale | +4.115 |
romy | +3.803 |
etz | +3.735 |
Neg logit contributions | |
Container | -4.133 |
Bundy | -3.477 |
Columb | -3.106 |
Clifford | -3.018 |
STL | -2.957 |
Token | om |
Token ID | 296 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
wives | +4.443 |
Ov | +4.023 |
emale | +3.974 |
romy | +3.634 |
etz | +3.551 |
Neg logit contributions | |
Container | -5.525 |
Bundy | -4.819 |
Columb | -4.301 |
Clifford | -4.278 |
STL | -4.209 |
Token | asc |
Token ID | 3372 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
wives | +2.499 |
Ov | +2.342 |
emale | +2.279 |
romy | +2.084 |
etz | +2.049 |
Neg logit contributions | |
Container | -2.709 |
Bundy | -2.322 |
Columb | -2.075 |
Clifford | -2.041 |
STL | -2.020 |
Token | ook |
Token ID | 566 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
wives | +0.691 |
Ov | +0.659 |
emale | +0.634 |
romy | +0.576 |
etz | +0.562 |
Neg logit contributions | |
Container | -0.752 |
Bundy | -0.643 |
Columb | -0.580 |
Clifford | -0.568 |
container | -0.562 |
Token | sign |
Token ID | 12683 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
wives | +3.232 |
Ov | +2.980 |
emale | +2.940 |
romy | +2.691 |
etz | +2.678 |
Neg logit contributions | |
Container | -3.292 |
Bundy | -2.831 |
Columb | -2.524 |
Clifford | -2.483 |
STL | -2.422 |
Token | ature |
Token ID | 1300 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
wives | +4.137 |
Ov | +3.785 |
emale | +3.753 |
etz | +3.329 |
romy | +3.245 |
Neg logit contributions | |
Container | -6.519 |
Bundy | -5.705 |
Columb | -5.259 |
Clifford | -5.188 |
STL | -5.097 |
Token | . |
Token ID | 13 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
wives | +7.192 |
Ov | +6.370 |
emale | +6.213 |
etz | +5.796 |
romy | +5.646 |
Neg logit contributions | |
Container | -8.359 |
Bundy | -7.487 |
Columb | -6.555 |
Clifford | -6.496 |
STL | -6.419 |
Token | com |
Token ID | 785 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
wives | +2.901 |
Ov | +2.718 |
emale | +2.576 |
romy | +2.368 |
etz | +2.339 |
Neg logit contributions | |
Container | -3.301 |
Bundy | -2.851 |
Columb | -2.574 |
Clifford | -2.518 |
STL | -2.509 |
Token | ), |
Token ID | 828 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
wives | +2.669 |
Ov | +2.523 |
emale | +2.429 |
romy | +2.179 |
etz | +2.163 |
Neg logit contributions | |
Container | -3.029 |
Bundy | -2.633 |
Columb | -2.374 |
Clifford | -2.314 |
STL | -2.297 |
Token | the |
Token ID | 262 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
Container | +0.531 |
Bundy | +0.445 |
Columb | +0.396 |
Clifford | +0.387 |
container | +0.382 |
Neg logit contributions | |
wives | -0.602 |
Ov | -0.574 |
emale | -0.561 |
romy | -0.518 |
etz | -0.503 |
Token | company |
Token ID | 1664 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
wives | +0.063 |
Ov | +0.060 |
emale | +0.059 |
romy | +0.054 |
etz | +0.052 |
Neg logit contributions | |
Container | -0.061 |
Bundy | -0.052 |
Columb | -0.046 |
Clifford | -0.045 |
container | -0.045 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
Container | +1.159 |
Bundy | +1.014 |
Columb | +0.930 |
Clifford | +0.914 |
container | +0.901 |
Neg logit contributions | |
wives | -0.796 |
Ov | -0.728 |
emale | -0.724 |
romy | -0.648 |
etz | -0.619 |
Token | , |
Token ID | 11 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
wives | +0.148 |
Ov | +0.142 |
emale | +0.138 |
romy | +0.128 |
etz | +0.124 |
Neg logit contributions | |
Container | -0.125 |
Bundy | -0.105 |
Columb | -0.093 |
Clifford | -0.091 |
container | -0.089 |
Token | California |
Token ID | 3442 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Container | +0.397 |
Bundy | +0.327 |
Columb | +0.285 |
Clifford | +0.277 |
container | +0.273 |
Neg logit contributions | |
wives | -0.542 |
Ov | -0.518 |
emale | -0.506 |
romy | -0.469 |
etz | -0.459 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
wives | +0.897 |
Ov | +0.851 |
emale | +0.824 |
romy | +0.750 |
etz | +0.734 |
Neg logit contributions | |
Container | -0.932 |
Bundy | -0.795 |
Columb | -0.714 |
Clifford | -0.698 |
STL | -0.692 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
wives | +2.008 |
Ov | +1.924 |
emale | +1.815 |
romy | +1.660 |
etz | +1.622 |
Neg logit contributions | |
Container | -2.021 |
Bundy | -1.715 |
Columb | -1.540 |
container | -1.514 |
Clifford | -1.509 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
wives | +0.987 |
Ov | +0.956 |
emale | +0.913 |
romy | +0.860 |
etz | +0.855 |
Neg logit contributions | |
Container | -0.503 |
Bundy | -0.393 |
Columb | -0.327 |
Clifford | -0.314 |
container | -0.309 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
wives | +6.223 |
Ov | +6.214 |
Women | +4.902 |
Lis | +4.777 |
etz | +4.605 |
Neg logit contributions | |
Container | -7.238 |
berra | -6.577 |
Bundy | -6.447 |
estic | -6.422 |
Columb | -5.960 |
Token | of |
Token ID | 286 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
wives | +2.818 |
Ov | +2.669 |
emale | +2.403 |
etz | +2.320 |
romy | +2.311 |
Neg logit contributions | |
Container | -2.379 |
Bundy | -1.959 |
Columb | -1.732 |
Clifford | -1.705 |
berra | -1.702 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Container | +1.564 |
Bundy | +1.283 |
Columb | +1.113 |
Clifford | +1.084 |
STL | +1.067 |
Neg logit contributions | |
wives | -2.209 |
Ov | -2.115 |
emale | -2.066 |
romy | -1.913 |
etz | -1.874 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
wives | +1.363 |
Ov | +1.294 |
emale | +1.190 |
romy | +1.094 |
etz | +1.083 |
Neg logit contributions | |
Container | -1.716 |
Bundy | -1.484 |
Columb | -1.348 |
Clifford | -1.329 |
container | -1.321 |
Token | : |
Token ID | 25 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
wives | +2.843 |
Ov | +2.705 |
emale | +2.422 |
etz | +2.339 |
romy | +2.329 |
Neg logit contributions | |
Container | -2.420 |
Bundy | -2.001 |
Columb | -1.787 |
berra | -1.757 |
Clifford | -1.745 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
Container | +1.536 |
Bundy | +1.337 |
Columb | +1.220 |
Clifford | +1.196 |
container | +1.175 |
Neg logit contributions | |
wives | -1.185 |
Ov | -1.081 |
emale | -1.080 |
romy | -0.975 |
etz | -0.935 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Container | +0.168 |
Bundy | +0.140 |
Columb | +0.124 |
Clifford | +0.121 |
STL | +0.119 |
Neg logit contributions | |
wives | -0.201 |
Ov | -0.192 |
emale | -0.187 |
romy | -0.172 |
etz | -0.168 |
Token | California |
Token ID | 3442 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Container | +0.747 |
Bundy | +0.613 |
Columb | +0.534 |
Clifford | +0.519 |
container | +0.512 |
Neg logit contributions | |
wives | -1.045 |
Ov | -0.999 |
emale | -0.983 |
romy | -0.909 |
etz | -0.888 |
Token | . |
Token ID | 13 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
wives | +0.839 |
Ov | +0.795 |
emale | +0.769 |
romy | +0.698 |
etz | +0.685 |
Neg logit contributions | |
Container | -0.888 |
Bundy | -0.758 |
Columb | -0.682 |
Clifford | -0.666 |
STL | -0.662 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
wives | +2.797 |
Ov | +2.708 |
emale | +2.527 |
romy | +2.290 |
etz | +2.256 |
Neg logit contributions | |
Container | -2.764 |
Bundy | -2.356 |
Columb | -2.108 |
estic | -2.083 |
container | -2.078 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
wives | +1.666 |
Ov | +1.620 |
emale | +1.527 |
romy | +1.444 |
etz | +1.442 |
Neg logit contributions | |
Container | -0.876 |
Bundy | -0.687 |
Columb | -0.578 |
Clifford | -0.554 |
estic | -0.545 |
Token | 9 |
Token ID | 860 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
wives | +6.083 |
Ov | +6.013 |
etz | +4.961 |
Lis | +4.775 |
Women | +4.754 |
Neg logit contributions | |
Container | -7.368 |
Bundy | -6.478 |
berra | -6.294 |
estic | -6.178 |
brance | -6.007 |
Token | of |
Token ID | 286 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
wives | +3.196 |
Ov | +3.017 |
emale | +2.675 |
etz | +2.618 |
romy | +2.594 |
Neg logit contributions | |
Container | -2.789 |
Bundy | -2.290 |
Columb | -2.033 |
berra | -2.024 |
Clifford | -2.011 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Container | +1.595 |
Bundy | +1.308 |
Columb | +1.134 |
Clifford | +1.105 |
STL | +1.088 |
Neg logit contributions | |
wives | -2.260 |
Ov | -2.165 |
emale | -2.117 |
romy | -1.960 |
etz | -1.918 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
wives | +1.239 |
Ov | +1.178 |
emale | +1.084 |
romy | +0.997 |
etz | +0.985 |
Neg logit contributions | |
Container | -1.559 |
Bundy | -1.348 |
Columb | -1.224 |
Clifford | -1.206 |
container | -1.201 |
Token | : |
Token ID | 25 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
wives | +2.834 |
Ov | +2.693 |
emale | +2.412 |
etz | +2.331 |
romy | +2.320 |
Neg logit contributions | |
Container | -2.417 |
Bundy | -2.001 |
Columb | -1.788 |
berra | -1.759 |
Clifford | -1.745 |
Token | ) |
Token ID | 8 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
wives | +3.957 |
Ov | +3.702 |
emale | +3.608 |
romy | +3.249 |
etz | +3.195 |
Neg logit contributions | |
Container | -4.504 |
Bundy | -3.887 |
Columb | -3.512 |
Clifford | -3.432 |
container | -3.388 |
Token | on |
Token ID | 319 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
wives | +2.102 |
Ov | +2.009 |
emale | +1.865 |
romy | +1.745 |
etz | +1.704 |
Neg logit contributions | |
Container | -2.287 |
Bundy | -1.951 |
Columb | -1.741 |
Clifford | -1.717 |
estic | -1.696 |
Token | Jan |
Token ID | 2365 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
wives | +0.826 |
Ov | +0.784 |
emale | +0.743 |
romy | +0.666 |
etz | +0.650 |
Neg logit contributions | |
Container | -1.159 |
Bundy | -1.012 |
Columb | -0.919 |
Clifford | -0.906 |
container | -0.897 |
Token | 16 |
Token ID | 1467 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
wives | +2.906 |
Ov | +2.805 |
emale | +2.612 |
etz | +2.414 |
romy | +2.407 |
Neg logit contributions | |
Container | -2.792 |
Bundy | -2.346 |
Columb | -2.095 |
Clifford | -2.051 |
container | -2.035 |
Token | , |
Token ID | 11 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
wives | +3.454 |
Ov | +3.283 |
emale | +2.999 |
romy | +2.852 |
etz | +2.831 |
Neg logit contributions | |
Container | -3.548 |
Bundy | -2.988 |
Columb | -2.669 |
berra | -2.635 |
Clifford | -2.618 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
wives | +4.014 |
Ov | +3.909 |
emale | +3.645 |
romy | +3.365 |
etz | +3.296 |
Neg logit contributions | |
Container | -4.257 |
Bundy | -3.656 |
Columb | -3.257 |
Clifford | -3.196 |
estic | -3.153 |
Token | at |
Token ID | 379 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
wives | +5.393 |
Ov | +5.131 |
emale | +4.352 |
etz | +4.235 |
romy | +4.172 |
Neg logit contributions | |
Container | -8.598 |
Bundy | -7.360 |
Columb | -6.724 |
estic | -6.700 |
berra | -6.673 |
Token | 9 |
Token ID | 860 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
wives | +2.138 |
Ov | +2.056 |
emale | +1.952 |
romy | +1.800 |
etz | +1.772 |
Neg logit contributions | |
Container | -1.969 |
Bundy | -1.653 |
Columb | -1.469 |
Clifford | -1.439 |
container | -1.424 |
Token | : |
Token ID | 25 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
wives | +0.686 |
Ov | +0.655 |
emale | +0.625 |
romy | +0.585 |
etz | +0.577 |
Neg logit contributions | |
Container | -0.517 |
Bundy | -0.427 |
Columb | -0.373 |
Clifford | -0.364 |
container | -0.357 |
Token | 28 |
Token ID | 2078 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
wives | +1.621 |
Ov | +1.535 |
emale | +1.457 |
romy | +1.342 |
etz | +1.320 |
Neg logit contributions | |
Container | -1.688 |
Bundy | -1.438 |
Columb | -1.288 |
Clifford | -1.267 |
container | -1.254 |
Token | am |
Token ID | 321 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
wives | +1.769 |
Ov | +1.631 |
emale | +1.578 |
romy | +1.384 |
etz | +1.343 |
Neg logit contributions | |
Container | -2.987 |
Bundy | -2.633 |
Columb | -2.422 |
Clifford | -2.384 |
STL | -2.361 |
Token | == |
Token ID | 6624 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
wives | +1.797 |
Ov | +1.699 |
emale | +1.573 |
romy | +1.416 |
etz | +1.387 |
Neg logit contributions | |
Container | -2.809 |
Bundy | -2.453 |
Columb | -2.248 |
Clifford | -2.225 |
container | -2.191 |
Token | " |
Token ID | 366 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
Container | +1.335 |
Bundy | +1.111 |
Columb | +0.977 |
Clifford | +0.951 |
STL | +0.939 |
Neg logit contributions | |
wives | -1.684 |
Ov | -1.604 |
emale | -1.582 |
romy | -1.449 |
etz | -1.413 |
Token | D |
Token ID | 35 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
wives | +0.254 |
Ov | +0.243 |
emale | +0.234 |
romy | +0.219 |
etz | +0.216 |
Neg logit contributions | |
Container | -0.170 |
Bundy | -0.138 |
Columb | -0.119 |
Clifford | -0.115 |
container | -0.114 |
Token | " |
Token ID | 1 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
wives | +1.279 |
Ov | +1.217 |
emale | +1.156 |
romy | +1.075 |
etz | +1.062 |
Neg logit contributions | |
Container | -1.243 |
Bundy | -1.051 |
Columb | -0.939 |
Clifford | -0.920 |
container | -0.906 |
Token | & |
Token ID | 1222 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
wives | +1.917 |
Ov | +1.842 |
emale | +1.791 |
romy | +1.670 |
etz | +1.642 |
Neg logit contributions | |
Container | -1.172 |
Bundy | -0.947 |
Columb | -0.809 |
Clifford | -0.780 |
STL | -0.766 |
Token | ] |
Token ID | 60 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
wives | +2.059 |
Ov | +1.943 |
emale | +1.837 |
romy | +1.620 |
etz | +1.578 |
Neg logit contributions | |
Container | -3.463 |
Bundy | -3.072 |
Columb | -2.814 |
Clifford | -2.762 |
STL | -2.744 |
Token | @ |
Token ID | 31 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
wives | +4.488 |
Ov | +4.106 |
emale | +3.690 |
romy | +3.312 |
etz | +3.221 |
Neg logit contributions | |
Container | -9.299 |
Bundy | -8.509 |
Columb | -7.886 |
STL | -7.656 |
Clifford | -7.643 |
Token | index |
Token ID | 9630 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
wives | +2.401 |
Ov | +2.277 |
emale | +2.185 |
romy | +2.006 |
etz | +1.963 |
Neg logit contributions | |
Container | -2.504 |
Bundy | -2.157 |
Columb | -1.942 |
Clifford | -1.881 |
STL | -1.879 |
Token | State |
Token ID | 9012 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
wives | +1.114 |
Ov | +1.066 |
emale | +1.020 |
romy | +0.950 |
etz | +0.936 |
Neg logit contributions | |
Container | -0.849 |
Bundy | -0.708 |
Columb | -0.623 |
Clifford | -0.602 |
STL | -0.594 |
Token | < |
Token ID | 1279 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
wives | +0.547 |
Ov | +0.521 |
emale | +0.506 |
romy | +0.466 |
etz | +0.456 |
Neg logit contributions | |
Container | -0.472 |
Bundy | -0.396 |
Columb | -0.351 |
Clifford | -0.342 |
STL | -0.338 |
Token | | |
Token ID | 91 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Container | +2.882 |
Bundy | +2.398 |
Columb | +2.145 |
Clifford | +2.128 |
container | +2.102 |
Neg logit contributions | |
wives | -3.025 |
Ov | -2.854 |
emale | -2.824 |
romy | -2.560 |
etz | -2.506 |
Token | in |
Token ID | 259 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
wives | +1.244 |
Ov | +1.190 |
emale | +1.157 |
etz | +1.074 |
romy | +1.072 |
Neg logit contributions | |
Container | -1.007 |
Bundy | -0.845 |
Columb | -0.741 |
Clifford | -0.719 |
container | -0.715 |
Token | , |
Token ID | 11 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
Container | +0.782 |
Bundy | +0.657 |
Columb | +0.578 |
Clifford | +0.564 |
STL | +0.555 |
Neg logit contributions | |
wives | -0.937 |
Ov | -0.892 |
emale | -0.873 |
romy | -0.805 |
etz | -0.782 |
Token | Iowa |
Token ID | 9406 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Container | +0.670 |
Bundy | +0.570 |
Columb | +0.513 |
Clifford | +0.499 |
STL | +0.493 |
Neg logit contributions | |
wives | -0.675 |
Ov | -0.639 |
emale | -0.627 |
romy | -0.571 |
etz | -0.557 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Container | +1.256 |
Bundy | +1.072 |
Columb | +0.957 |
Clifford | +0.939 |
STL | +0.923 |
Neg logit contributions | |
wives | -1.256 |
Ov | -1.194 |
emale | -1.160 |
romy | -1.061 |
etz | -1.033 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
wives | +2.586 |
Ov | +2.495 |
emale | +2.341 |
romy | +2.114 |
etz | +2.081 |
Neg logit contributions | |
Container | -2.620 |
Bundy | -2.219 |
Columb | -1.996 |
container | -1.967 |
Clifford | -1.957 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
wives | +0.971 |
Ov | +0.941 |
emale | +0.894 |
romy | +0.843 |
etz | +0.841 |
Neg logit contributions | |
Container | -0.504 |
Bundy | -0.393 |
Columb | -0.329 |
Clifford | -0.315 |
container | -0.311 |
Token | 5 |
Token ID | 642 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Ov | +6.241 |
wives | +6.196 |
etz | +5.130 |
Lis | +5.017 |
Women | +4.918 |
Neg logit contributions | |
Container | -6.589 |
Bundy | -5.893 |
berra | -5.689 |
estic | -5.663 |
discont | -5.460 |
Token | of |
Token ID | 286 |
Feature activation | +9.30e-03 |
Pos logit contributions | |
wives | +3.915 |
Ov | +3.690 |
emale | +3.202 |
etz | +3.160 |
Women | +3.144 |
Neg logit contributions | |
Container | -3.552 |
Bundy | -2.937 |
berra | -2.647 |
Columb | -2.620 |
Clifford | -2.589 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Container | +0.055 |
Bundy | +0.045 |
Columb | +0.040 |
Clifford | +0.038 |
estic | +0.038 |
Neg logit contributions | |
wives | -0.071 |
Ov | -0.068 |
emale | -0.065 |
romy | -0.060 |
etz | -0.060 |
Token | Photos |
Token ID | 9434 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
wives | +1.347 |
Ov | +1.276 |
emale | +1.174 |
romy | +1.080 |
etz | +1.064 |
Neg logit contributions | |
Container | -1.708 |
Bundy | -1.475 |
Columb | -1.344 |
Clifford | -1.321 |
container | -1.320 |
Token | : |
Token ID | 25 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
wives | +2.888 |
Ov | +2.744 |
emale | +2.446 |
etz | +2.364 |
romy | +2.347 |
Neg logit contributions | |
Container | -2.471 |
Bundy | -2.056 |
Columb | -1.840 |
berra | -1.821 |
estic | -1.801 |
Token | Women |
Token ID | 6926 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
wives | +0.608 |
Ov | +0.569 |
emale | +0.547 |
romy | +0.485 |
etz | +0.470 |
Neg logit contributions | |
Container | -0.938 |
Bundy | -0.823 |
Columb | -0.754 |
Clifford | -0.741 |
STL | -0.733 |
Token | in |
Token ID | 287 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Container | +0.951 |
Bundy | +0.802 |
Columb | +0.703 |
Clifford | +0.685 |
container | +0.674 |
Neg logit contributions | |
wives | -1.148 |
Ov | -1.094 |
emale | -1.077 |
romy | -0.990 |
etz | -0.959 |
Token | politics |
Token ID | 4819 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Container | +0.914 |
Bundy | +0.774 |
Columb | +0.692 |
Clifford | +0.675 |
container | +0.669 |
Neg logit contributions | |
wives | -0.964 |
Ov | -0.908 |
emale | -0.888 |
romy | -0.820 |
etz | -0.796 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
wives | +1.522 |
Ov | +1.452 |
emale | +1.405 |
romy | +1.289 |
etz | +1.263 |
Neg logit contributions | |
Container | -1.404 |
Bundy | -1.184 |
Columb | -1.054 |
Clifford | -1.029 |
STL | -1.016 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
wives | +1.901 |
Ov | +1.822 |
emale | +1.741 |
romy | +1.585 |
etz | +1.555 |
Neg logit contributions | |
Container | -1.867 |
Bundy | -1.579 |
Columb | -1.415 |
Clifford | -1.385 |
container | -1.379 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
wives | +1.687 |
Ov | +1.637 |
emale | +1.554 |
romy | +1.465 |
etz | +1.458 |
Neg logit contributions | |
Container | -0.876 |
Bundy | -0.682 |
Columb | -0.573 |
Clifford | -0.550 |
container | -0.539 |
Token | 7 |
Token ID | 767 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
wives | +5.781 |
Ov | +5.757 |
etz | +4.614 |
emale | +4.543 |
kos | +4.539 |
Neg logit contributions | |
Container | -7.415 |
Bundy | -6.595 |
berra | -6.221 |
estic | -6.073 |
discont | -6.012 |
Token | of |
Token ID | 286 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
wives | +3.286 |
Ov | +3.105 |
emale | +2.761 |
etz | +2.693 |
romy | +2.667 |
Neg logit contributions | |
Container | -2.874 |
Bundy | -2.369 |
Columb | -2.095 |
berra | -2.078 |
Clifford | -2.077 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Container | +0.926 |
Bundy | +0.760 |
Columb | +0.663 |
Clifford | +0.644 |
container | +0.634 |
Neg logit contributions | |
wives | -1.276 |
Ov | -1.222 |
emale | -1.184 |
romy | -1.098 |
etz | -1.079 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
wives | +1.515 |
Ov | +1.438 |
emale | +1.320 |
romy | +1.214 |
etz | +1.201 |
Neg logit contributions | |
Container | -1.920 |
Bundy | -1.661 |
Columb | -1.508 |
Clifford | -1.488 |
container | -1.482 |
Token | : |
Token ID | 25 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
wives | +2.618 |
Ov | +2.489 |
emale | +2.245 |
etz | +2.157 |
romy | +2.150 |
Neg logit contributions | |
Container | -2.206 |
Bundy | -1.827 |
Columb | -1.629 |
berra | -1.596 |
Clifford | -1.591 |
Token | in |
Token ID | 287 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
wives | +3.694 |
Ov | +3.524 |
emale | +3.196 |
romy | +3.061 |
etz | +3.026 |
Neg logit contributions | |
Container | -3.813 |
Bundy | -3.257 |
Columb | -2.875 |
Clifford | -2.870 |
estic | -2.790 |
Token | games |
Token ID | 1830 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
wives | +1.017 |
Ov | +0.955 |
emale | +0.928 |
romy | +0.815 |
etz | +0.792 |
Neg logit contributions | |
Container | -1.527 |
Bundy | -1.338 |
Columb | -1.226 |
Clifford | -1.203 |
container | -1.194 |
Token | ) |
Token ID | 8 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
wives | +1.648 |
Ov | +1.563 |
emale | +1.488 |
romy | +1.363 |
etz | +1.338 |
Neg logit contributions | |
Container | -1.838 |
Bundy | -1.574 |
Columb | -1.419 |
Clifford | -1.387 |
container | -1.374 |
Token | since |
Token ID | 1201 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
wives | +3.734 |
Ov | +3.483 |
emale | +3.235 |
romy | +2.928 |
etz | +2.900 |
Neg logit contributions | |
Container | -4.937 |
Bundy | -4.259 |
Columb | -3.865 |
Clifford | -3.804 |
STL | -3.798 |
Token | my |
Token ID | 616 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
wives | +2.924 |
Ov | +2.783 |
emale | +2.592 |
romy | +2.492 |
etz | +2.378 |
Neg logit contributions | |
Container | -3.182 |
Bundy | -2.661 |
Columb | -2.391 |
Clifford | -2.349 |
Booster | -2.326 |
Token | hardware |
Token ID | 6890 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
wives | +3.659 |
Ov | +3.500 |
emale | +3.269 |
romy | +3.076 |
etz | +2.955 |
Neg logit contributions | |
Container | -3.670 |
Bundy | -3.081 |
Columb | -2.770 |
Clifford | -2.704 |
STL | -2.674 |
Token | is |
Token ID | 318 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
wives | +5.115 |
Ov | +4.864 |
emale | +3.922 |
etz | +3.844 |
romy | +3.820 |
Neg logit contributions | |
Container | -8.459 |
Bundy | -7.378 |
berra | -6.664 |
Columb | -6.656 |
Clifford | -6.653 |
Token | almost |
Token ID | 2048 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
wives | +3.030 |
Ov | +2.798 |
emale | +2.514 |
romy | +2.231 |
etz | +2.158 |
Neg logit contributions | |
Container | -6.310 |
Bundy | -5.495 |
Columb | -5.098 |
Clifford | -5.080 |
STL | -5.044 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
wives | +4.053 |
Ov | +3.928 |
emale | +3.642 |
romy | +3.410 |
etz | +3.368 |
Neg logit contributions | |
Container | -3.834 |
Bundy | -3.189 |
Columb | -2.837 |
Clifford | -2.821 |
STL | -2.769 |
Token | years |
Token ID | 812 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
wives | +1.796 |
Ov | +1.700 |
emale | +1.632 |
romy | +1.487 |
etz | +1.452 |
Neg logit contributions | |
Container | -2.028 |
Bundy | -1.740 |
Columb | -1.568 |
Clifford | -1.538 |
STL | -1.518 |
Token | old |
Token ID | 1468 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
wives | +2.347 |
Ov | +2.197 |
emale | +1.963 |
romy | +1.758 |
etz | +1.708 |
Neg logit contributions | |
Container | -4.771 |
Bundy | -4.222 |
Columb | -3.887 |
Clifford | -3.860 |
STL | -3.797 |
Token | :: |
Token ID | 7904 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
wives | +0.354 |
Ov | +0.336 |
emale | +0.325 |
romy | +0.296 |
etz | +0.290 |
Neg logit contributions | |
Container | -0.365 |
Bundy | -0.312 |
Columb | -0.280 |
Clifford | -0.274 |
STL | -0.270 |
Token | clone |
Token ID | 17271 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
wives | +1.525 |
Ov | +1.463 |
emale | +1.405 |
romy | +1.287 |
etz | +1.259 |
Neg logit contributions | |
Container | -1.461 |
Bundy | -1.250 |
Columb | -1.111 |
Clifford | -1.087 |
STL | -1.067 |
Token | ( |
Token ID | 357 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
wives | +3.232 |
Ov | +3.040 |
emale | +2.947 |
romy | +2.643 |
etz | +2.615 |
Neg logit contributions | |
Container | -3.909 |
Bundy | -3.426 |
Columb | -3.094 |
Clifford | -3.031 |
Booster | -2.963 |
Token | self |
Token ID | 2116 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
wives | +1.377 |
Ov | +1.310 |
emale | +1.267 |
romy | +1.161 |
etz | +1.135 |
Neg logit contributions | |
Container | -1.325 |
Bundy | -1.126 |
Columb | -1.005 |
Clifford | -0.982 |
STL | -0.969 |
Token | . |
Token ID | 764 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
wives | +2.592 |
Ov | +2.476 |
emale | +2.393 |
romy | +2.211 |
etz | +2.170 |
Neg logit contributions | |
Container | -2.167 |
Bundy | -1.822 |
Columb | -1.608 |
Clifford | -1.566 |
STL | -1.540 |
Token | prev |
Token ID | 47050 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
wives | +1.544 |
Ov | +1.469 |
emale | +1.424 |
romy | +1.310 |
etz | +1.281 |
Neg logit contributions | |
Container | -1.359 |
Bundy | -1.148 |
Columb | -1.015 |
Clifford | -0.991 |
STL | -0.976 |
Token | _ |
Token ID | 62 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
wives | +5.056 |
Ov | +4.636 |
emale | +4.432 |
etz | +3.950 |
romy | +3.842 |
Neg logit contributions | |
Container | -8.405 |
Bundy | -7.589 |
Columb | -6.998 |
Clifford | -6.775 |
Booster | -6.708 |
Token | state |
Token ID | 5219 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
wives | +0.668 |
Ov | +0.635 |
emale | +0.620 |
romy | +0.575 |
etz | +0.565 |
Neg logit contributions | |
Container | -0.480 |
Bundy | -0.396 |
Columb | -0.346 |
Clifford | -0.334 |
STL | -0.328 |
Token | . |
Token ID | 764 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
wives | +3.725 |
Ov | +3.541 |
emale | +3.412 |
romy | +3.118 |
etz | +3.092 |
Neg logit contributions | |
Container | -3.517 |
Bundy | -3.007 |
Columb | -2.697 |
Clifford | -2.613 |
STL | -2.566 |
Token | un |
Token ID | 403 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
wives | +0.166 |
Ov | +0.159 |
emale | +0.155 |
romy | +0.142 |
etz | +0.139 |
Neg logit contributions | |
Container | -0.146 |
Bundy | -0.122 |
Columb | -0.108 |
Clifford | -0.106 |
container | -0.105 |
Token | wrap |
Token ID | 37150 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
wives | +5.450 |
Ov | +5.078 |
emale | +5.000 |
etz | +4.556 |
romy | +4.534 |
Neg logit contributions | |
Container | -4.892 |
Bundy | -4.232 |
Columb | -3.725 |
Clifford | -3.631 |
Booster | -3.553 |
Token | state |
Token ID | 5219 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
wives | +0.668 |
Ov | +0.635 |
emale | +0.620 |
romy | +0.575 |
etz | +0.565 |
Neg logit contributions | |
Container | -0.480 |
Bundy | -0.396 |
Columb | -0.346 |
Clifford | -0.334 |
STL | -0.328 |
Token | . |
Token ID | 764 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
wives | +3.725 |
Ov | +3.541 |
emale | +3.412 |
romy | +3.118 |
etz | +3.092 |
Neg logit contributions | |
Container | -3.517 |
Bundy | -3.007 |
Columb | -2.697 |
Clifford | -2.613 |
STL | -2.566 |
Token | un |
Token ID | 403 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
wives | +0.166 |
Ov | +0.159 |
emale | +0.155 |
romy | +0.142 |
etz | +0.139 |
Neg logit contributions | |
Container | -0.146 |
Bundy | -0.122 |
Columb | -0.108 |
Clifford | -0.106 |
container | -0.105 |
Token | wrap |
Token ID | 37150 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
wives | +5.450 |
Ov | +5.078 |
emale | +5.000 |
etz | +4.556 |
romy | +4.534 |
Neg logit contributions | |
Container | -4.892 |
Bundy | -4.232 |
Columb | -3.725 |
Clifford | -3.631 |
Booster | -3.553 |
Token | ()) |
Token ID | 32865 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
wives | +2.957 |
Ov | +2.730 |
emale | +2.639 |
romy | +2.308 |
etz | +2.291 |
Neg logit contributions | |
Container | -4.691 |
Bundy | -4.151 |
Columb | -3.826 |
Clifford | -3.734 |
STL | -3.674 |
Token | } |
Token ID | 1782 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
wives | +4.747 |
Ov | +4.543 |
emale | +4.277 |
romy | +3.907 |
etz | +3.880 |
Neg logit contributions | |
Container | -5.402 |
Bundy | -4.741 |
Columb | -4.287 |
Clifford | -4.187 |
estic | -4.094 |
Token | } |
Token ID | 1782 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
wives | +5.388 |
Ov | +5.257 |
emale | +4.802 |
romy | +4.369 |
etz | +4.238 |
Neg logit contributions | |
Container | -7.723 |
Bundy | -6.964 |
Columb | -6.337 |
Clifford | -6.178 |
estic | -6.124 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
wives | +4.608 |
Ov | +4.477 |
emale | +4.204 |
romy | +3.890 |
etz | +3.842 |
Neg logit contributions | |
Container | -4.565 |
Bundy | -4.011 |
Columb | -3.573 |
Clifford | -3.480 |
estic | -3.397 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
wives | +0.864 |
Ov | +0.820 |
emale | +0.793 |
romy | +0.721 |
etz | +0.705 |
Neg logit contributions | |
Container | -0.929 |
Bundy | -0.795 |
Columb | -0.715 |
Clifford | -0.700 |
STL | -0.692 |
Token | apply |
Token ID | 4174 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
wives | +1.182 |
Ov | +1.120 |
emale | +1.086 |
romy | +0.989 |
etz | +0.965 |
Neg logit contributions | |
Container | -1.247 |
Bundy | -1.065 |
Columb | -0.958 |
Clifford | -0.938 |
container | -0.928 |
Token | _ |
Token ID | 62 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
wives | +1.932 |
Ov | +1.821 |
emale | +1.721 |
romy | +1.538 |
etz | +1.528 |
Neg logit contributions | |
Container | -3.001 |
Bundy | -2.654 |
Columb | -2.434 |
Clifford | -2.387 |
container | -2.333 |
Token | ) |
Token ID | 8 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
wives | +3.475 |
Ov | +3.255 |
emale | +3.166 |
romy | +2.874 |
etz | +2.840 |
Neg logit contributions | |
Container | -3.791 |
Bundy | -3.232 |
Columb | -2.923 |
Clifford | -2.857 |
container | -2.822 |
Token | on |
Token ID | 319 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
wives | +2.761 |
Ov | +2.638 |
emale | +2.405 |
romy | +2.253 |
etz | +2.227 |
Neg logit contributions | |
Container | -3.089 |
Bundy | -2.630 |
Columb | -2.362 |
Clifford | -2.329 |
estic | -2.312 |
Token | Sep |
Token ID | 8621 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
wives | +0.948 |
Ov | +0.898 |
emale | +0.852 |
romy | +0.761 |
etz | +0.743 |
Neg logit contributions | |
Container | -1.354 |
Bundy | -1.182 |
Columb | -1.077 |
Clifford | -1.060 |
container | -1.050 |
Token | 30 |
Token ID | 1542 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
wives | +3.591 |
Ov | +3.474 |
emale | +3.199 |
etz | +2.975 |
romy | +2.958 |
Neg logit contributions | |
Container | -3.529 |
Bundy | -2.963 |
Columb | -2.638 |
berra | -2.603 |
Clifford | -2.594 |
Token | , |
Token ID | 11 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
wives | +2.941 |
Ov | +2.811 |
emale | +2.554 |
romy | +2.420 |
etz | +2.415 |
Neg logit contributions | |
Container | -2.969 |
Bundy | -2.500 |
Columb | -2.234 |
berra | -2.195 |
Clifford | -2.185 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
wives | +3.387 |
Ov | +3.289 |
emale | +3.127 |
romy | +2.878 |
etz | +2.817 |
Neg logit contributions | |
Container | -3.223 |
Bundy | -2.727 |
Columb | -2.432 |
Clifford | -2.374 |
STL | -2.332 |
Token | at |
Token ID | 379 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
wives | +4.979 |
Ov | +4.789 |
etz | +3.911 |
emale | +3.790 |
romy | +3.765 |
Neg logit contributions | |
Container | -8.295 |
Bundy | -7.137 |
berra | -6.522 |
estic | -6.493 |
Columb | -6.489 |
Token | 9 |
Token ID | 860 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
wives | +1.629 |
Ov | +1.562 |
emale | +1.492 |
romy | +1.375 |
etz | +1.353 |
Neg logit contributions | |
Container | -1.482 |
Bundy | -1.245 |
Columb | -1.106 |
Clifford | -1.083 |
container | -1.070 |
Token | : |
Token ID | 25 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
wives | +0.069 |
Ov | +0.066 |
emale | +0.063 |
romy | +0.059 |
etz | +0.058 |
Neg logit contributions | |
Container | -0.051 |
Bundy | -0.042 |
Columb | -0.037 |
Clifford | -0.036 |
container | -0.035 |
Token | 01 |
Token ID | 486 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
wives | +1.216 |
Ov | +1.154 |
emale | +1.100 |
romy | +1.011 |
etz | +0.993 |
Neg logit contributions | |
Container | -1.254 |
Bundy | -1.067 |
Columb | -0.956 |
Clifford | -0.939 |
container | -0.929 |
Token | am |
Token ID | 321 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
wives | +1.301 |
Ov | +1.203 |
emale | +1.165 |
romy | +1.026 |
etz | +0.996 |
Neg logit contributions | |
Container | -2.137 |
Bundy | -1.876 |
Columb | -1.726 |
Clifford | -1.699 |
STL | -1.681 |
Token | activist |
Token ID | 11276 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Container | +1.984 |
Bundy | +1.682 |
Columb | +1.489 |
Clifford | +1.451 |
container | +1.439 |
Neg logit contributions | |
wives | -2.252 |
Ov | -2.129 |
emale | -2.095 |
romy | -1.910 |
etz | -1.862 |
Token | had |
Token ID | 550 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Container | +2.216 |
Bundy | +1.876 |
Columb | +1.682 |
Clifford | +1.650 |
STL | +1.606 |
Neg logit contributions | |
wives | -2.549 |
Ov | -2.392 |
emale | -2.382 |
romy | -2.181 |
etz | -2.131 |
Token | received |
Token ID | 2722 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Container | +1.101 |
Bundy | +0.950 |
Columb | +0.850 |
Clifford | +0.833 |
container | +0.824 |
Neg logit contributions | |
wives | -1.078 |
Ov | -1.018 |
emale | -1.008 |
romy | -0.916 |
etz | -0.889 |
Token | th |
Token ID | 294 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
Container | +1.401 |
Bundy | +1.197 |
Columb | +1.061 |
Clifford | +1.049 |
container | +1.032 |
Neg logit contributions | |
wives | -1.464 |
Ov | -1.371 |
emale | -1.354 |
romy | -1.237 |
etz | -1.206 |
Token | rea |
Token ID | 21468 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
wives | +0.267 |
Ov | +0.255 |
emale | +0.247 |
romy | +0.228 |
etz | +0.223 |
Neg logit contributions | |
Container | -0.219 |
Bundy | -0.183 |
Columb | -0.161 |
Clifford | -0.157 |
STL | -0.155 |
Token | ... |
Token ID | 986 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
Container | +2.437 |
Bundy | +2.038 |
Columb | +1.782 |
Clifford | +1.749 |
container | +1.739 |
Neg logit contributions | |
wives | -3.135 |
Ov | -2.996 |
emale | -2.905 |
romy | -2.696 |
etz | -2.629 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
wives | +6.903 |
Ov | +6.645 |
emale | +6.231 |
etz | +5.701 |
romy | +5.616 |
Neg logit contributions | |
Container | -6.175 |
Bundy | -5.163 |
Columb | -4.550 |
container | -4.460 |
estic | -4.437 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
wives | +2.901 |
Ov | +2.752 |
emale | +2.492 |
romy | +2.398 |
etz | +2.390 |
Neg logit contributions | |
Container | -2.584 |
Bundy | -2.158 |
Columb | -1.922 |
Clifford | -1.887 |
berra | -1.872 |
Token | From |
Token ID | 4863 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
wives | +1.220 |
Ov | +1.152 |
emale | +1.112 |
romy | +1.012 |
etz | +0.987 |
Neg logit contributions | |
Container | -1.369 |
Bundy | -1.172 |
Columb | -1.057 |
Clifford | -1.038 |
container | -1.027 |
Token | : |
Token ID | 25 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Container | +0.070 |
Bundy | +0.059 |
Columb | +0.052 |
Clifford | +0.051 |
STL | +0.050 |
Neg logit contributions | |
wives | -0.080 |
Ov | -0.076 |
emale | -0.074 |
romy | -0.068 |
etz | -0.067 |
Token | A |
Token ID | 317 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
wives | +2.146 |
Ov | +2.051 |
emale | +1.983 |
romy | +1.819 |
etz | +1.778 |
Neg logit contributions | |
Container | -2.034 |
Bundy | -1.717 |
Columb | -1.529 |
Clifford | -1.489 |
container | -1.480 |
Token | AA |
Token ID | 15923 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
wives | +2.396 |
Ov | +2.316 |
emale | +2.092 |
romy | +1.899 |
etz | +1.851 |
Neg logit contributions | |
Container | -3.802 |
Bundy | -3.304 |
Columb | -3.046 |
Clifford | -3.021 |
estic | -2.945 |
Token | on |
Token ID | 319 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
wives | +3.088 |
Ov | +2.938 |
emale | +2.634 |
romy | +2.501 |
etz | +2.494 |
Neg logit contributions | |
Container | -3.703 |
Bundy | -3.194 |
Columb | -2.867 |
Clifford | -2.850 |
estic | -2.798 |
Token | ( |
Token ID | 357 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
wives | +0.815 |
Ov | +0.781 |
emale | +0.745 |
romy | +0.688 |
etz | +0.678 |
Neg logit contributions | |
Container | -0.717 |
Bundy | -0.602 |
Columb | -0.532 |
Clifford | -0.521 |
container | -0.514 |
Token | Anti |
Token ID | 28795 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
wives | +0.375 |
Ov | +0.354 |
emale | +0.336 |
romy | +0.305 |
etz | +0.297 |
Neg logit contributions | |
Container | -0.493 |
Bundy | -0.427 |
Columb | -0.390 |
Clifford | -0.383 |
STL | -0.379 |
Token | Ali |
Token ID | 37893 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
wives | +2.364 |
Ov | +2.183 |
emale | +1.958 |
romy | +1.738 |
etz | +1.702 |
Neg logit contributions | |
Container | -5.041 |
Bundy | -4.451 |
Columb | -4.121 |
Clifford | -4.076 |
container | -4.057 |
Token | asing |
Token ID | 2313 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
wives | +4.313 |
Ov | +3.922 |
emale | +3.860 |
romy | +3.426 |
etz | +3.357 |
Neg logit contributions | |
Container | -5.752 |
Bundy | -4.885 |
Columb | -4.478 |
Clifford | -4.428 |
container | -4.338 |
Token | is |
Token ID | 318 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
wives | +5.100 |
Ov | +4.831 |
emale | +4.159 |
romy | +3.969 |
etz | +3.967 |
Neg logit contributions | |
Container | -7.881 |
Bundy | -6.957 |
Columb | -6.344 |
Clifford | -6.233 |
estic | -6.112 |
Token | a |
Token ID | 257 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
wives | +1.482 |
Ov | +1.416 |
emale | +1.352 |
romy | +1.265 |
etz | +1.248 |
Neg logit contributions | |
Container | -1.171 |
Bundy | -0.976 |
Columb | -0.855 |
Clifford | -0.834 |
STL | -0.818 |
Token | technique |
Token ID | 8173 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Container | +0.437 |
Bundy | +0.366 |
Columb | +0.323 |
Clifford | +0.315 |
STL | +0.311 |
Neg logit contributions | |
wives | -0.518 |
Ov | -0.494 |
emale | -0.479 |
romy | -0.442 |
etz | -0.433 |
Token | used |
Token ID | 973 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
wives | +2.713 |
Ov | +2.477 |
emale | +2.238 |
etz | +2.056 |
romy | +2.048 |
Neg logit contributions | |
Container | -5.077 |
Bundy | -4.478 |
Columb | -4.117 |
Clifford | -4.079 |
Booster | -4.011 |
Token | to |
Token ID | 284 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
wives | +2.194 |
Ov | +2.085 |
emale | +1.954 |
romy | +1.850 |
etz | +1.826 |
Neg logit contributions | |
Container | -1.882 |
Bundy | -1.583 |
Columb | -1.386 |
Clifford | -1.354 |
STL | -1.328 |
Token | Keys |
Token ID | 26363 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
wives | +3.282 |
Ov | +3.144 |
emale | +3.005 |
romy | +2.775 |
etz | +2.722 |
Neg logit contributions | |
Container | -3.116 |
Bundy | -2.666 |
Columb | -2.386 |
STL | -2.309 |
Clifford | -2.303 |
Token | [ |
Token ID | 58 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
wives | +2.379 |
Ov | +2.267 |
emale | +2.195 |
romy | +2.009 |
etz | +1.971 |
Neg logit contributions | |
Container | -2.259 |
Bundy | -1.921 |
Columb | -1.710 |
Clifford | -1.673 |
STL | -1.656 |
Token | step |
Token ID | 9662 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
wives | +1.424 |
Ov | +1.353 |
emale | +1.308 |
romy | +1.202 |
etz | +1.174 |
Neg logit contributions | |
Container | -1.378 |
Bundy | -1.174 |
Columb | -1.049 |
Clifford | -1.021 |
STL | -1.012 |
Token | Old |
Token ID | 19620 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
wives | +3.237 |
Ov | +3.020 |
emale | +2.836 |
romy | +2.529 |
etz | +2.507 |
Neg logit contributions | |
Container | -5.238 |
Bundy | -4.645 |
Columb | -4.249 |
Clifford | -4.189 |
STL | -4.149 |
Token | ], |
Token ID | 4357 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
wives | +3.214 |
Ov | +3.069 |
emale | +2.954 |
romy | +2.702 |
etz | +2.652 |
Neg logit contributions | |
Container | -3.118 |
Bundy | -2.658 |
Columb | -2.379 |
Clifford | -2.314 |
STL | -2.296 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
wives | +4.750 |
Ov | +4.598 |
emale | +4.284 |
romy | +3.996 |
etz | +3.925 |
Neg logit contributions | |
Container | -4.264 |
Bundy | -3.697 |
Columb | -3.248 |
STL | -3.135 |
estic | -3.122 |
Token | ] |
Token ID | 60 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
wives | +6.134 |
Ov | +5.918 |
emale | +5.615 |
romy | +5.132 |
etz | +5.084 |
Neg logit contributions | |
Container | -6.683 |
Bundy | -5.756 |
Columb | -5.278 |
Clifford | -5.059 |
STL | -5.011 |
Token | ], |
Token ID | 4357 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
wives | +6.060 |
Ov | +5.827 |
emale | +5.519 |
romy | +5.104 |
etz | +5.049 |
Neg logit contributions | |
Container | -5.313 |
Bundy | -4.601 |
Columb | -4.070 |
Clifford | -3.909 |
STL | -3.869 |
Token | step |
Token ID | 2239 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
wives | +6.697 |
Ov | +6.580 |
emale | +6.017 |
romy | +5.634 |
etz | +5.536 |
Neg logit contributions | |
Container | -5.774 |
Bundy | -5.116 |
Columb | -4.443 |
estic | -4.300 |
STL | -4.270 |
Token | Old |
Token ID | 19620 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
wives | +4.050 |
Ov | +3.710 |
emale | +3.389 |
Women | +2.974 |
etz | +2.949 |
Neg logit contributions | |
Container | -7.631 |
Bundy | -6.798 |
Columb | -6.256 |
Clifford | -6.190 |
container | -6.133 |
Token | ] |
Token ID | 60 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
wives | +4.819 |
Ov | +4.606 |
emale | +4.386 |
romy | +4.012 |
etz | +3.950 |
Neg logit contributions | |
Container | -4.851 |
Bundy | -4.176 |
Columb | -3.733 |
Clifford | -3.649 |
STL | -3.601 |
Token | G |
Token ID | 402 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
wives | +1.180 |
Ov | +1.131 |
emale | +1.079 |
romy | +0.983 |
etz | +0.967 |
Neg logit contributions | |
Container | -1.278 |
Bundy | -1.091 |
Columb | -0.985 |
Clifford | -0.966 |
container | -0.951 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
Container | +1.049 |
Bundy | +0.885 |
Columb | +0.782 |
Clifford | +0.764 |
STL | +0.759 |
Neg logit contributions | |
wives | -1.177 |
Ov | -1.118 |
emale | -1.089 |
romy | -0.996 |
etz | -0.972 |
Token | G |
Token ID | 38 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
wives | +0.353 |
Ov | +0.334 |
emale | +0.314 |
romy | +0.290 |
etz | +0.284 |
Neg logit contributions | |
Container | -0.404 |
Bundy | -0.346 |
Columb | -0.315 |
Clifford | -0.309 |
container | -0.305 |
Token | AU |
Token ID | 27548 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
wives | +1.688 |
Ov | +1.607 |
emale | +1.511 |
romy | +1.342 |
etz | +1.322 |
Neg logit contributions | |
Container | -2.563 |
Bundy | -2.242 |
Columb | -2.057 |
Clifford | -2.022 |
container | -2.000 |
Token | Opt |
Token ID | 13123 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
wives | +0.521 |
Ov | +0.492 |
emale | +0.432 |
romy | +0.368 |
etz | +0.358 |
Neg logit contributions | |
Container | -1.324 |
Bundy | -1.187 |
Columb | -1.103 |
Clifford | -1.090 |
container | -1.084 |
Token | ronics |
Token ID | 20844 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
wives | +1.654 |
Ov | +1.530 |
emale | +1.432 |
romy | +1.317 |
etz | +1.281 |
Neg logit contributions | |
Container | -2.608 |
Bundy | -2.280 |
Columb | -2.094 |
Clifford | -2.062 |
container | -2.041 |
Token | TN |
Token ID | 29025 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Ov | +4.310 |
wives | +4.222 |
emale | +3.464 |
etz | +3.195 |
romy | +3.030 |
Neg logit contributions | |
Container | -8.492 |
Bundy | -7.432 |
Columb | -6.986 |
berra | -6.966 |
estic | -6.912 |
Token | Film |
Token ID | 13741 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
wives | +0.909 |
Ov | +0.875 |
emale | +0.840 |
romy | +0.774 |
etz | +0.760 |
Neg logit contributions | |
Container | -0.771 |
Bundy | -0.648 |
Columb | -0.575 |
Clifford | -0.561 |
container | -0.549 |
Token | @ |
Token ID | 2488 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
wives | +2.310 |
Ov | +2.224 |
emale | +2.118 |
romy | +1.944 |
etz | +1.920 |
Neg logit contributions | |
Container | -2.185 |
Bundy | -1.857 |
Columb | -1.653 |
Clifford | -1.619 |
container | -1.595 |
Token | 144 |
Token ID | 20224 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
wives | +1.887 |
Ov | +1.807 |
emale | +1.719 |
romy | +1.559 |
etz | +1.528 |
Neg logit contributions | |
Container | -2.246 |
Bundy | -1.936 |
Columb | -1.756 |
Clifford | -1.722 |
container | -1.699 |
Token | Hz |
Token ID | 7399 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
wives | +0.360 |
Ov | +0.334 |
emale | +0.318 |
romy | +0.276 |
etz | +0.266 |
Neg logit contributions | |
Container | -0.695 |
Bundy | -0.616 |
Columb | -0.569 |
Clifford | -0.560 |
STL | -0.555 |
Token | Kong |
Token ID | 9071 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
wives | +2.414 |
Ov | +2.278 |
emale | +2.170 |
romy | +1.984 |
etz | +1.936 |
Neg logit contributions | |
Container | -3.169 |
Bundy | -2.748 |
Columb | -2.517 |
Clifford | -2.458 |
STL | -2.433 |
Token | SAR |
Token ID | 47341 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
wives | +1.241 |
Ov | +1.170 |
emale | +1.123 |
romy | +1.006 |
etz | +0.977 |
Neg logit contributions | |
Container | -1.724 |
Bundy | -1.500 |
Columb | -1.371 |
Clifford | -1.347 |
container | -1.330 |
Token | 0 |
Token ID | 657 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
wives | +1.011 |
Ov | +0.963 |
emale | +0.927 |
romy | +0.844 |
etz | +0.825 |
Neg logit contributions | |
Container | -1.064 |
Bundy | -0.909 |
Columb | -0.817 |
Clifford | -0.800 |
container | -0.790 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
Container | +0.239 |
Bundy | +0.197 |
Columb | +0.171 |
Clifford | +0.167 |
STL | +0.164 |
Neg logit contributions | |
wives | -0.327 |
Ov | -0.313 |
emale | -0.305 |
romy | -0.282 |
etz | -0.276 |
Token | 1 |
Token ID | 16 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
wives | +0.133 |
Ov | +0.126 |
emale | +0.123 |
romy | +0.112 |
etz | +0.109 |
Neg logit contributions | |
Container | -0.135 |
Bundy | -0.115 |
Columb | -0.103 |
Clifford | -0.101 |
STL | -0.100 |
Token | 3 |
Token ID | 513 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
wives | +2.407 |
Ov | +2.305 |
emale | +2.230 |
romy | +2.051 |
etz | +2.018 |
Neg logit contributions | |
Container | -1.941 |
Bundy | -1.615 |
Columb | -1.425 |
Clifford | -1.379 |
container | -1.365 |
Token | Brune |
Token ID | 46070 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
wives | +5.576 |
Ov | +5.531 |
emale | +4.807 |
romy | +4.506 |
etz | +4.416 |
Neg logit contributions | |
Container | -7.182 |
Bundy | -6.172 |
estic | -5.684 |
Columb | -5.589 |
brance | -5.576 |
Token | i |
Token ID | 72 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
wives | +1.532 |
Ov | +1.461 |
emale | +1.411 |
romy | +1.302 |
etz | +1.293 |
Neg logit contributions | |
Container | -1.268 |
Bundy | -1.058 |
Columb | -0.936 |
Clifford | -0.914 |
STL | -0.902 |
Token | Dar |
Token ID | 7491 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Container | +1.130 |
Bundy | +0.956 |
Columb | +0.864 |
Clifford | +0.843 |
container | +0.836 |
Neg logit contributions | |
wives | -1.086 |
Ov | -1.031 |
emale | -1.007 |
romy | -0.915 |
etz | -0.889 |
Token | uss |
Token ID | 1046 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
wives | +0.855 |
Ov | +0.798 |
emale | +0.768 |
romy | +0.672 |
etz | +0.647 |
Neg logit contributions | |
Container | -1.472 |
Bundy | -1.297 |
Columb | -1.192 |
Clifford | -1.174 |
container | -1.164 |
Token | alam |
Token ID | 44949 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
wives | +1.203 |
Ov | +1.128 |
emale | +1.084 |
romy | +0.955 |
etz | +0.916 |
Neg logit contributions | |
Container | -1.960 |
Bundy | -1.727 |
Columb | -1.585 |
Clifford | -1.552 |
STL | -1.547 |
Token | certain |
Token ID | 1728 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Container | +2.015 |
Bundy | +1.744 |
Columb | +1.549 |
Clifford | +1.528 |
container | +1.492 |
Neg logit contributions | |
wives | -2.173 |
Ov | -2.047 |
emale | -2.035 |
romy | -1.863 |
etz | -1.817 |
Token | issues |
Token ID | 2428 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
Container | +1.118 |
Bundy | +0.970 |
Columb | +0.875 |
Clifford | +0.858 |
container | +0.847 |
Neg logit contributions | |
wives | -1.011 |
Ov | -0.954 |
emale | -0.938 |
romy | -0.847 |
etz | -0.826 |
Token | , |
Token ID | 11 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Container | +2.266 |
Bundy | +1.907 |
Columb | +1.667 |
Clifford | +1.650 |
STL | +1.594 |
Neg logit contributions | |
wives | -2.910 |
emale | -2.772 |
Ov | -2.772 |
romy | -2.523 |
etz | -2.457 |
Token | to |
Token ID | 284 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Container | +1.975 |
Bundy | +1.689 |
Columb | +1.498 |
Clifford | +1.479 |
STL | +1.441 |
Neg logit contributions | |
wives | -2.151 |
Ov | -2.018 |
emale | -2.012 |
romy | -1.832 |
etz | -1.792 |
Token | O |
Token ID | 440 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Container | +2.714 |
Bundy | +2.346 |
Columb | +2.072 |
Clifford | +2.045 |
STL | +1.999 |
Neg logit contributions | |
wives | -3.111 |
Ov | -2.928 |
emale | -2.880 |
romy | -2.641 |
etz | -2.585 |
Token | ' |
Token ID | 6 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
wives | +0.734 |
Ov | +0.700 |
emale | +0.679 |
romy | +0.625 |
etz | +0.612 |
Neg logit contributions | |
Container | -0.644 |
Bundy | -0.541 |
Columb | -0.479 |
Clifford | -0.468 |
STL | -0.462 |
Token | Neill |
Token ID | 26538 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
wives | +5.114 |
Ov | +4.724 |
emale | +4.373 |
romy | +4.100 |
etz | +3.966 |
Neg logit contributions | |
Container | -7.927 |
Bundy | -6.767 |
Columb | -6.282 |
container | -6.215 |
STL | -6.146 |
Token | 's |
Token ID | 338 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Container | +1.002 |
Bundy | +0.838 |
Columb | +0.731 |
Clifford | +0.717 |
STL | +0.699 |
Neg logit contributions | |
wives | -1.297 |
Ov | -1.234 |
emale | -1.211 |
romy | -1.116 |
etz | -1.089 |
Token | open |
Token ID | 1280 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Container | +1.023 |
Bundy | +0.887 |
Columb | +0.807 |
container | +0.785 |
Clifford | +0.784 |
Neg logit contributions | |
wives | -0.913 |
emale | -0.860 |
Ov | -0.848 |
romy | -0.768 |
etz | -0.738 |
Token | - |
Token ID | 12 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
Container | +2.108 |
Bundy | +1.795 |
Columb | +1.600 |
container | +1.581 |
Clifford | +1.573 |
Neg logit contributions | |
wives | -2.113 |
Ov | -1.993 |
emale | -1.973 |
romy | -1.790 |
etz | -1.727 |
Token | j |
Token ID | 73 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Container | +0.579 |
Bundy | +0.499 |
Columb | +0.450 |
Clifford | +0.442 |
container | +0.437 |
Neg logit contributions | |
wives | -0.503 |
Ov | -0.478 |
emale | -0.461 |
romy | -0.417 |
etz | -0.408 |
Token | ment |
Token ID | 434 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Container | +0.365 |
Bundy | +0.287 |
Columb | +0.238 |
Clifford | +0.231 |
STL | +0.226 |
Neg logit contributions | |
wives | -0.685 |
Ov | -0.659 |
emale | -0.643 |
romy | -0.602 |
etz | -0.592 |
Token | ( |
Token ID | 357 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
wives | +2.760 |
Ov | +2.639 |
emale | +2.532 |
romy | +2.316 |
etz | +2.288 |
Neg logit contributions | |
Container | -2.539 |
Bundy | -2.150 |
Columb | -1.891 |
Clifford | -1.854 |
STL | -1.839 |
Token | with |
Token ID | 4480 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
wives | +1.232 |
Ov | +1.163 |
emale | +1.130 |
romy | +1.033 |
etz | +1.013 |
Neg logit contributions | |
Container | -1.183 |
Bundy | -1.005 |
Columb | -0.892 |
Clifford | -0.876 |
STL | -0.867 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
wives | +1.292 |
Ov | +1.232 |
emale | +1.195 |
romy | +1.094 |
etz | +1.075 |
Neg logit contributions | |
Container | -1.148 |
Bundy | -0.965 |
Columb | -0.853 |
Clifford | -0.835 |
STL | -0.825 |
Token | exception |
Token ID | 6631 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
wives | +1.587 |
Ov | +1.520 |
emale | +1.477 |
romy | +1.360 |
etz | +1.337 |
Neg logit contributions | |
Container | -1.240 |
Bundy | -1.028 |
Columb | -0.899 |
Clifford | -0.879 |
STL | -0.865 |
Token | of |
Token ID | 286 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
wives | +5.066 |
Ov | +4.808 |
emale | +4.640 |
romy | +4.214 |
etz | +4.205 |
Neg logit contributions | |
Container | -4.151 |
Bundy | -3.465 |
Columb | -3.006 |
STL | -2.981 |
Clifford | -2.971 |
Token | South |
Token ID | 2520 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
wives | +6.623 |
Ov | +6.377 |
emale | +5.941 |
romy | +5.452 |
etz | +5.354 |
Neg logit contributions | |
Container | -6.292 |
Bundy | -5.234 |
estic | -4.617 |
Clifford | -4.591 |
Columb | -4.576 |
Token | Australia |
Token ID | 4505 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
wives | +1.390 |
Ov | +1.299 |
emale | +1.245 |
romy | +1.117 |
etz | +1.091 |
Neg logit contributions | |
Container | -1.937 |
Bundy | -1.686 |
Columb | -1.528 |
Clifford | -1.511 |
STL | -1.501 |
Token | ).[ |
Token ID | 42669 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
wives | +1.434 |
Ov | +1.366 |
emale | +1.327 |
romy | +1.219 |
etz | +1.200 |
Neg logit contributions | |
Container | -1.197 |
Bundy | -0.999 |
Columb | -0.879 |
Clifford | -0.859 |
STL | -0.851 |
Token | 188 |
Token ID | 20356 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Container | +0.484 |
Bundy | +0.421 |
Columb | +0.382 |
Clifford | +0.376 |
container | +0.371 |
Neg logit contributions | |
wives | -0.379 |
Ov | -0.362 |
emale | -0.345 |
romy | -0.312 |
etz | -0.303 |
Token | ] |
Token ID | 60 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
wives | +0.710 |
Ov | +0.664 |
emale | +0.637 |
romy | +0.560 |
etz | +0.543 |
Neg logit contributions | |
Container | -1.179 |
Bundy | -1.037 |
Columb | -0.953 |
Clifford | -0.937 |
STL | -0.929 |
Token | end |
Token ID | 437 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
wives | +1.674 |
Ov | +1.580 |
emale | +1.531 |
romy | +1.432 |
etz | +1.410 |
Neg logit contributions | |
Container | -1.391 |
Bundy | -1.179 |
Columb | -1.028 |
Clifford | -1.006 |
STL | -0.988 |
Token | T |
Token ID | 51 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
wives | +3.390 |
Ov | +3.215 |
emale | +3.088 |
romy | +2.833 |
etz | +2.786 |
Neg logit contributions | |
Container | -3.685 |
Bundy | -3.174 |
Columb | -2.858 |
Clifford | -2.789 |
container | -2.772 |
Token | ear |
Token ID | 451 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
wives | +2.007 |
Ov | +1.896 |
emale | +1.851 |
romy | +1.690 |
etz | +1.650 |
Neg logit contributions | |
Container | -2.271 |
Bundy | -1.949 |
Columb | -1.765 |
Clifford | -1.714 |
STL | -1.708 |
Token | V |
Token ID | 53 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
wives | +2.996 |
Ov | +2.870 |
emale | +2.753 |
romy | +2.528 |
etz | +2.467 |
Neg logit contributions | |
Container | -3.051 |
Bundy | -2.609 |
Columb | -2.340 |
Clifford | -2.279 |
container | -2.259 |
Token | oid |
Token ID | 1868 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
wives | +1.106 |
Ov | +1.030 |
emale | +0.970 |
romy | +0.850 |
etz | +0.819 |
Neg logit contributions | |
Container | -2.301 |
Bundy | -2.046 |
Columb | -1.898 |
Clifford | -1.879 |
STL | -1.847 |
Token | Ray |
Token ID | 19591 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
wives | +3.968 |
Ov | +3.719 |
emale | +3.580 |
romy | +3.331 |
etz | +3.208 |
Neg logit contributions | |
Container | -4.703 |
Bundy | -4.029 |
Columb | -3.710 |
Clifford | -3.611 |
container | -3.559 |
Token | J |
Token ID | 41 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
wives | +5.607 |
Ov | +5.310 |
emale | +5.128 |
romy | +4.698 |
etz | +4.603 |
Neg logit contributions | |
Container | -7.142 |
Bundy | -6.200 |
Columb | -5.667 |
container | -5.512 |
Clifford | -5.478 |
Token | KS |
Token ID | 27015 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
wives | +4.566 |
Ov | +4.272 |
emale | +4.203 |
etz | +3.849 |
romy | +3.835 |
Neg logit contributions | |
Container | -3.700 |
Bundy | -3.085 |
Columb | -2.727 |
Clifford | -2.610 |
container | -2.605 |
Token | Le |
Token ID | 3123 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
wives | +2.294 |
Ov | +2.172 |
emale | +2.109 |
romy | +1.912 |
etz | +1.875 |
Neg logit contributions | |
Container | -2.623 |
Bundy | -2.268 |
Columb | -2.040 |
Clifford | -1.999 |
container | -1.982 |
Token | en |
Token ID | 268 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
wives | +1.459 |
Ov | +1.284 |
emale | +1.209 |
etz | +1.046 |
romy | +1.031 |
Neg logit contributions | |
Container | -3.703 |
Bundy | -3.303 |
Columb | -3.058 |
Clifford | -3.029 |
container | -3.000 |
Token | ock |
Token ID | 735 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
Container | +0.144 |
Bundy | +0.119 |
Columb | +0.103 |
Clifford | +0.100 |
STL | +0.099 |
Neg logit contributions | |
wives | -0.202 |
Ov | -0.194 |
emale | -0.188 |
romy | -0.175 |
etz | -0.172 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Container | +2.075 |
Bundy | +1.838 |
Columb | +1.679 |
Clifford | +1.633 |
container | +1.626 |
Neg logit contributions | |
wives | -1.343 |
Ov | -1.283 |
emale | -1.242 |
romy | -1.075 |
etz | -1.035 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
wives | +1.832 |
Ov | +1.715 |
emale | +1.647 |
romy | +1.468 |
etz | +1.455 |
Neg logit contributions | |
Container | -2.581 |
Bundy | -2.243 |
Columb | -2.058 |
Clifford | -2.021 |
STL | -2.004 |
Token | + |
Token ID | 1343 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
wives | +0.687 |
Ov | +0.649 |
emale | +0.621 |
romy | +0.556 |
etz | +0.543 |
Neg logit contributions | |
Container | -0.951 |
Bundy | -0.830 |
Columb | -0.757 |
Clifford | -0.744 |
STL | -0.735 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
Container | +1.498 |
Bundy | +1.325 |
Columb | +1.211 |
Clifford | +1.183 |
STL | +1.177 |
Neg logit contributions | |
wives | -0.940 |
Ov | -0.891 |
emale | -0.862 |
romy | -0.748 |
etz | -0.721 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
wives | +0.161 |
Ov | +0.152 |
emale | +0.147 |
romy | +0.132 |
etz | +0.129 |
Neg logit contributions | |
Container | -0.203 |
Bundy | -0.176 |
Columb | -0.160 |
Clifford | -0.157 |
STL | -0.155 |
Token | < |
Token ID | 1279 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
Container | +3.259 |
Bundy | +2.669 |
Columb | +2.345 |
container | +2.311 |
STL | +2.296 |
Neg logit contributions | |
wives | -4.031 |
Ov | -3.796 |
emale | -3.787 |
romy | -3.482 |
etz | -3.345 |
Token | -- |
Token ID | 438 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Container | +3.928 |
Bundy | +3.104 |
Columb | +2.621 |
container | +2.598 |
STL | +2.592 |
Neg logit contributions | |
wives | -6.446 |
emale | -6.387 |
Ov | -6.294 |
romy | -5.716 |
etz | -5.580 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
Container | +1.890 |
Bundy | +1.557 |
Columb | +1.392 |
Clifford | +1.353 |
container | +1.353 |
Neg logit contributions | |
wives | -2.152 |
Ov | -2.017 |
emale | -2.006 |
romy | -1.830 |
etz | -1.778 |
Token | of |
Token ID | 286 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
wives | +0.274 |
Ov | +0.263 |
emale | +0.253 |
romy | +0.236 |
etz | +0.232 |
Neg logit contributions | |
Container | -0.199 |
Bundy | -0.164 |
Columb | -0.142 |
Clifford | -0.139 |
STL | -0.136 |
Token | system |
Token ID | 1080 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
Container | +1.448 |
Bundy | +1.241 |
Columb | +1.124 |
container | +1.110 |
STL | +1.101 |
Neg logit contributions | |
wives | -1.233 |
Ov | -1.154 |
emale | -1.134 |
romy | -1.008 |
etz | -0.987 |
Token | () |
Token ID | 3419 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
wives | +0.213 |
Ov | +0.197 |
emale | +0.189 |
romy | +0.163 |
etz | +0.157 |
Neg logit contributions | |
Container | -0.422 |
Bundy | -0.375 |
Columb | -0.346 |
Clifford | -0.341 |
STL | -0.339 |
Token | x |
Token ID | 2124 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Container | +1.295 |
Bundy | +1.101 |
Columb | +0.981 |
Clifford | +0.963 |
container | +0.959 |
Neg logit contributions | |
wives | -1.279 |
Ov | -1.195 |
emale | -1.193 |
romy | -1.075 |
etz | -1.044 |
Token | . |
Token ID | 13 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
Container | +2.569 |
Bundy | +2.189 |
Columb | +1.936 |
Clifford | +1.885 |
STL | +1.873 |
Neg logit contributions | |
wives | -2.903 |
emale | -2.843 |
Ov | -2.777 |
romy | -2.515 |
etz | -2.422 |
Token | x |
Token ID | 87 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Container | +3.798 |
Bundy | +3.245 |
Columb | +2.866 |
Clifford | +2.796 |
STL | +2.776 |
Neg logit contributions | |
wives | -4.020 |
emale | -3.914 |
Ov | -3.890 |
romy | -3.453 |
etz | -3.322 |
Token | . |
Token ID | 13 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Container | +2.029 |
Bundy | +1.728 |
Columb | +1.538 |
Clifford | +1.495 |
STL | +1.483 |
Neg logit contributions | |
wives | -2.191 |
emale | -2.109 |
Ov | -2.097 |
romy | -1.881 |
etz | -1.817 |
Token | x |
Token ID | 87 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Container | +4.039 |
Bundy | +3.446 |
Columb | +3.045 |
container | +2.940 |
Clifford | +2.938 |
Neg logit contributions | |
wives | -4.296 |
emale | -4.196 |
Ov | -4.187 |
romy | -3.697 |
etz | -3.557 |
Token | . |
Token ID | 13 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Container | +2.687 |
Bundy | +2.285 |
Columb | +2.032 |
Clifford | +1.959 |
STL | +1.955 |
Neg logit contributions | |
wives | -2.970 |
emale | -2.877 |
Ov | -2.865 |
romy | -2.559 |
etz | -2.465 |
Token | 101 |
Token ID | 8784 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Container | +3.281 |
Bundy | +2.640 |
Columb | +2.300 |
container | +2.232 |
Clifford | +2.192 |
Neg logit contributions | |
wives | -4.914 |
Ov | -4.869 |
emale | -4.720 |
romy | -4.393 |
etz | -4.208 |
Token | 114 |
Token ID | 17342 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
wives | +1.292 |
Ov | +1.227 |
emale | +1.184 |
romy | +1.078 |
etz | +1.054 |
Neg logit contributions | |
Container | -1.380 |
Bundy | -1.181 |
Columb | -1.061 |
Clifford | -1.040 |
container | -1.027 |
Token | 65 |
Token ID | 2996 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
wives | +0.281 |
Ov | +0.267 |
emale | +0.258 |
romy | +0.235 |
etz | +0.230 |
Neg logit contributions | |
Container | -0.293 |
Bundy | -0.250 |
Columb | -0.225 |
Clifford | -0.220 |
container | -0.217 |
Token | 24 |
Token ID | 1731 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
wives | +0.535 |
Ov | +0.507 |
emale | +0.492 |
romy | +0.447 |
etz | +0.437 |
Neg logit contributions | |
Container | -0.570 |
Bundy | -0.488 |
Columb | -0.438 |
Clifford | -0.429 |
STL | -0.424 |
Token | x |
Token ID | 2124 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Container | +0.312 |
Bundy | +0.267 |
Columb | +0.240 |
Clifford | +0.235 |
STL | +0.233 |
Neg logit contributions | |
wives | -0.288 |
Ov | -0.273 |
emale | -0.265 |
romy | -0.241 |
etz | -0.235 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Container | +0.222 |
Bundy | +0.185 |
Columb | +0.162 |
Clifford | +0.158 |
container | +0.157 |
Neg logit contributions | |
wives | -0.269 |
Ov | -0.257 |
emale | -0.251 |
romy | -0.230 |
etz | -0.225 |
Token | full |
Token ID | 1336 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
wives | +0.223 |
Ov | +0.213 |
emale | +0.208 |
romy | +0.190 |
etz | +0.186 |
Neg logit contributions | |
Container | -0.199 |
Bundy | -0.168 |
Columb | -0.148 |
Clifford | -0.144 |
container | -0.144 |
Token | path |
Token ID | 3108 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
wives | +0.660 |
Ov | +0.629 |
emale | +0.610 |
romy | +0.560 |
etz | +0.548 |
Neg logit contributions | |
Container | -0.602 |
Bundy | -0.508 |
Columb | -0.452 |
Clifford | -0.442 |
STL | -0.436 |
Token | to |
Token ID | 284 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Container | +2.367 |
Bundy | +1.952 |
Columb | +1.689 |
container | +1.686 |
Clifford | +1.654 |
Neg logit contributions | |
wives | -2.948 |
Ov | -2.835 |
emale | -2.797 |
romy | -2.547 |
etz | -2.471 |
Token | i |
Token ID | 1312 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
Container | +2.581 |
Bundy | +2.173 |
Columb | +1.895 |
container | +1.880 |
STL | +1.845 |
Neg logit contributions | |
wives | -3.003 |
Ov | -2.859 |
emale | -2.844 |
romy | -2.580 |
etz | -2.491 |
Token | w |
Token ID | 86 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Container | +0.477 |
Bundy | +0.395 |
Columb | +0.344 |
Clifford | +0.335 |
container | +0.335 |
Neg logit contributions | |
wives | -0.621 |
Ov | -0.598 |
emale | -0.580 |
romy | -0.537 |
etz | -0.524 |
Token | config |
Token ID | 11250 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
Container | +4.312 |
Bundy | +3.587 |
Columb | +3.163 |
container | +3.157 |
STL | +3.077 |
Neg logit contributions | |
wives | -4.668 |
Ov | -4.549 |
emale | -4.409 |
romy | -3.968 |
etz | -3.866 |
Token | ? |
Token ID | 30 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
wives | +0.269 |
Ov | +0.257 |
emale | +0.249 |
romy | +0.229 |
etz | +0.224 |
Neg logit contributions | |
Container | -0.240 |
Bundy | -0.202 |
Columb | -0.179 |
Clifford | -0.175 |
STL | -0.173 |
Token | That |
Token ID | 1320 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Container | +1.592 |
Bundy | +1.338 |
Columb | +1.189 |
container | +1.154 |
Clifford | +1.148 |
Neg logit contributions | |
wives | -1.734 |
Ov | -1.636 |
emale | -1.628 |
romy | -1.483 |
etz | -1.435 |
Token | � |
Token ID | 447 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Container | +0.745 |
Bundy | +0.630 |
Columb | +0.559 |
Clifford | +0.546 |
container | +0.545 |
Neg logit contributions | |
wives | -0.803 |
Ov | -0.763 |
emale | -0.744 |
romy | -0.682 |
etz | -0.662 |
Token | � |
Token ID | 247 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Container | +0.535 |
Bundy | +0.398 |
Columb | +0.313 |
Clifford | +0.297 |
container | +0.289 |
Neg logit contributions | |
wives | -1.334 |
Ov | -1.288 |
emale | -1.263 |
romy | -1.186 |
etz | -1.168 |
Token | � |
Token ID | 251 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
wives | +0.407 |
Ov | +0.387 |
emale | +0.376 |
romy | +0.345 |
etz | +0.337 |
Neg logit contributions | |
Container | -0.373 |
Bundy | -0.315 |
Columb | -0.280 |
Clifford | -0.274 |
STL | -0.270 |
Token |
|
Token ID | 198 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
wives | +0.731 |
Ov | +0.699 |
emale | +0.680 |
romy | +0.628 |
etz | +0.615 |
Neg logit contributions | |
Container | -0.573 |
Bundy | -0.476 |
Columb | -0.418 |
Clifford | -0.407 |
STL | -0.401 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Container | +0.396 |
Bundy | +0.327 |
Columb | +0.285 |
Clifford | +0.278 |
STL | +0.273 |
Neg logit contributions | |
wives | -0.531 |
Ov | -0.508 |
emale | -0.492 |
romy | -0.456 |
etz | -0.448 |
Token | PF |
Token ID | 42668 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Container | +1.066 |
Bundy | +0.918 |
Columb | +0.828 |
Clifford | +0.808 |
STL | +0.798 |
Neg logit contributions | |
wives | -0.963 |
Ov | -0.920 |
emale | -0.898 |
romy | -0.808 |
etz | -0.786 |
Token | Bentley |
Token ID | 38881 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
Container | +3.700 |
Bundy | +3.246 |
Columb | +2.935 |
Clifford | +2.898 |
STL | +2.843 |
Neg logit contributions | |
wives | -2.926 |
Ov | -2.723 |
emale | -2.695 |
romy | -2.426 |
etz | -2.328 |
Token | / |
Token ID | 14 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Container | +2.472 |
Bundy | +2.027 |
Columb | +1.754 |
Clifford | +1.682 |
STL | +1.667 |
Neg logit contributions | |
wives | -3.697 |
emale | -3.563 |
Ov | -3.524 |
romy | -3.279 |
etz | -3.156 |
Token | Civil |
Token ID | 32610 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Container | +5.176 |
Bundy | +4.494 |
Columb | +4.120 |
Clifford | +3.967 |
STL | +3.954 |
Neg logit contributions | |
wives | -4.156 |
emale | -4.040 |
Ov | -4.003 |
romy | -3.525 |
etz | -3.350 |
Token | Beat |
Token ID | 12568 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Container | +1.137 |
Bundy | +0.977 |
Columb | +0.881 |
Clifford | +0.863 |
STL | +0.854 |
Neg logit contributions | |
wives | -1.012 |
Ov | -0.958 |
emale | -0.928 |
romy | -0.842 |
etz | -0.820 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Container | +1.990 |
Bundy | +1.622 |
Columb | +1.397 |
Clifford | +1.365 |
STL | +1.342 |
Neg logit contributions | |
wives | -2.872 |
Ov | -2.753 |
emale | -2.705 |
romy | -2.514 |
etz | -2.436 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
Container | +0.846 |
Bundy | +0.696 |
Columb | +0.606 |
Clifford | +0.589 |
STL | +0.580 |
Neg logit contributions | |
wives | -1.167 |
Ov | -1.118 |
emale | -1.093 |
romy | -1.009 |
etz | -0.988 |
Token | Good |
Token ID | 10248 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
wives | +0.149 |
Ov | +0.142 |
emale | +0.137 |
romy | +0.124 |
etz | +0.121 |
Neg logit contributions | |
Container | -0.171 |
Bundy | -0.147 |
Columb | -0.133 |
Clifford | -0.130 |
STL | -0.128 |
Token | traffic |
Token ID | 4979 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
wives | +1.465 |
Ov | +1.390 |
emale | +1.347 |
romy | +1.231 |
etz | +1.205 |
Neg logit contributions | |
Container | -1.416 |
Bundy | -1.204 |
Columb | -1.074 |
Clifford | -1.050 |
STL | -1.036 |
Token | jumped |
Token ID | 11687 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
wives | +0.421 |
Ov | +0.399 |
emale | +0.386 |
romy | +0.351 |
etz | +0.343 |
Neg logit contributions | |
Container | -0.456 |
Bundy | -0.391 |
Columb | -0.351 |
Clifford | -0.344 |
STL | -0.340 |
Token | to |
Token ID | 284 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Container | +1.552 |
Bundy | +1.312 |
Columb | +1.155 |
Clifford | +1.146 |
container | +1.132 |
Neg logit contributions | |
wives | -1.762 |
Ov | -1.660 |
emale | -1.641 |
romy | -1.517 |
etz | -1.471 |
Token | about |
Token ID | 546 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Container | +1.125 |
Bundy | +0.954 |
Columb | +0.850 |
Clifford | +0.834 |
container | +0.825 |
Neg logit contributions | |
wives | -1.211 |
Ov | -1.138 |
emale | -1.124 |
romy | -1.031 |
etz | -1.004 |
Token | 16 |
Token ID | 1467 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Container | +1.424 |
Bundy | +1.200 |
Columb | +1.062 |
Clifford | +1.040 |
container | +1.030 |
Neg logit contributions | |
wives | -1.630 |
Ov | -1.533 |
emale | -1.522 |
romy | -1.396 |
etz | -1.359 |
Token | million |
Token ID | 1510 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Container | +2.041 |
Bundy | +1.745 |
Columb | +1.582 |
Clifford | +1.551 |
container | +1.541 |
Neg logit contributions | |
wives | -1.811 |
Ov | -1.709 |
emale | -1.674 |
romy | -1.516 |
etz | -1.474 |
Token | from |
Token ID | 422 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Container | +3.836 |
Bundy | +3.136 |
Columb | +2.838 |
Clifford | +2.782 |
container | +2.780 |
Neg logit contributions | |
wives | -4.529 |
emale | -4.234 |
Ov | -4.221 |
romy | -3.940 |
etz | -3.758 |
Token | about |
Token ID | 546 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Container | +0.809 |
Bundy | +0.685 |
Columb | +0.614 |
Clifford | +0.598 |
container | +0.593 |
Neg logit contributions | |
wives | -0.890 |
emale | -0.839 |
Ov | -0.837 |
romy | -0.765 |
etz | -0.749 |
Token | four |
Token ID | 1440 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Container | +2.930 |
Bundy | +2.454 |
Columb | +2.182 |
container | +2.123 |
Clifford | +2.117 |
Neg logit contributions | |
wives | -3.599 |
emale | -3.433 |
Ov | -3.360 |
romy | -3.128 |
etz | -3.044 |
Token | million |
Token ID | 1510 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
Container | +1.826 |
Bundy | +1.582 |
Columb | +1.442 |
Clifford | +1.410 |
container | +1.403 |
Neg logit contributions | |
wives | -1.471 |
Ov | -1.383 |
emale | -1.369 |
romy | -1.220 |
etz | -1.189 |
Token | unique |
Token ID | 3748 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Container | +4.876 |
Bundy | +3.980 |
Columb | +3.649 |
container | +3.475 |
Clifford | +3.465 |
Neg logit contributions | |
wives | -6.151 |
emale | -5.879 |
Ov | -5.706 |
romy | -5.427 |
etz | -5.198 |
Token | values |
Token ID | 3815 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Container | +1.693 |
Bundy | +1.438 |
Columb | +1.289 |
container | +1.269 |
Clifford | +1.261 |
Neg logit contributions | |
wives | -1.638 |
Ov | -1.563 |
emale | -1.532 |
romy | -1.378 |
etz | -1.345 |
Token | to |
Token ID | 284 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
wives | +0.174 |
Ov | +0.166 |
emale | +0.161 |
romy | +0.148 |
etz | +0.145 |
Neg logit contributions | |
Container | -0.148 |
Bundy | -0.124 |
Columb | -0.109 |
Clifford | -0.107 |
STL | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
wives | +0.557 |
Ov | +0.532 |
emale | +0.518 |
romy | +0.475 |
etz | +0.465 |
Neg logit contributions | |
Container | -0.487 |
Bundy | -0.409 |
Columb | -0.362 |
Clifford | -0.354 |
container | -0.350 |
Token | right |
Token ID | 826 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Container | +0.544 |
Bundy | +0.459 |
Columb | +0.409 |
container | +0.401 |
Clifford | +0.400 |
Neg logit contributions | |
wives | -0.568 |
Ov | -0.540 |
emale | -0.531 |
romy | -0.484 |
etz | -0.472 |
Token | and |
Token ID | 290 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Container | +0.890 |
Bundy | +0.741 |
Columb | +0.652 |
Clifford | +0.635 |
container | +0.631 |
Neg logit contributions | |
wives | -1.096 |
Ov | -1.047 |
emale | -1.023 |
romy | -0.941 |
etz | -0.920 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Container | +1.323 |
Bundy | +1.124 |
Columb | +1.008 |
Clifford | +0.994 |
container | +0.988 |
Neg logit contributions | |
wives | -1.280 |
Ov | -1.210 |
emale | -1.195 |
romy | -1.077 |
etz | -1.046 |
Token | 0 |
Token ID | 657 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
wives | +0.078 |
Ov | +0.074 |
emale | +0.072 |
romy | +0.066 |
etz | +0.064 |
Neg logit contributions | |
Container | -0.078 |
Bundy | -0.066 |
Columb | -0.059 |
Clifford | -0.058 |
container | -0.057 |
Token | point |
Token ID | 966 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
wives | +0.564 |
Ov | +0.539 |
emale | +0.524 |
romy | +0.485 |
etz | +0.475 |
Neg logit contributions | |
Container | -0.428 |
Bundy | -0.355 |
Columb | -0.311 |
Clifford | -0.302 |
STL | -0.297 |
Token | value |
Token ID | 1988 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Container | +0.472 |
Bundy | +0.397 |
Columb | +0.354 |
Clifford | +0.345 |
container | +0.344 |
Neg logit contributions | |
wives | -0.511 |
Ov | -0.485 |
emale | -0.473 |
romy | -0.433 |
etz | -0.423 |
Token | would |
Token ID | 561 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Container | +0.651 |
Bundy | +0.543 |
Columb | +0.479 |
Clifford | +0.467 |
container | +0.463 |
Neg logit contributions | |
wives | -0.789 |
Ov | -0.753 |
emale | -0.734 |
romy | -0.676 |
etz | -0.660 |
Token | be |
Token ID | 307 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Container | +0.150 |
Bundy | +0.126 |
Columb | +0.112 |
Clifford | +0.109 |
container | +0.109 |
Neg logit contributions | |
wives | -0.170 |
Ov | -0.161 |
emale | -0.157 |
romy | -0.144 |
etz | -0.141 |
Token | Address |
Token ID | 20231 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
wives | +2.370 |
Ov | +2.194 |
emale | +2.069 |
romy | +1.870 |
etz | +1.822 |
Neg logit contributions | |
Container | -3.556 |
Bundy | -3.132 |
Columb | -2.862 |
Clifford | -2.817 |
STL | -2.793 |
Token | : |
Token ID | 25 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
wives | +0.455 |
Ov | +0.436 |
emale | +0.413 |
romy | +0.387 |
etz | +0.383 |
Neg logit contributions | |
Container | -0.344 |
Bundy | -0.283 |
Columb | -0.248 |
Clifford | -0.242 |
container | -0.239 |
Token | Jam |
Token ID | 9986 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
wives | +2.296 |
Ov | +2.220 |
emale | +2.095 |
romy | +1.920 |
etz | +1.882 |
Neg logit contributions | |
Container | -2.265 |
Bundy | -1.923 |
Columb | -1.717 |
Clifford | -1.681 |
container | -1.677 |
Token | n |
Token ID | 77 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Container | +1.128 |
Bundy | +0.960 |
Columb | +0.859 |
Clifford | +0.840 |
STL | +0.830 |
Neg logit contributions | |
wives | -1.121 |
Ov | -1.066 |
emale | -1.033 |
romy | -0.943 |
etz | -0.920 |
Token | agar |
Token ID | 32452 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Container | +1.182 |
Bundy | +1.033 |
Columb | +0.941 |
Clifford | +0.927 |
container | +0.916 |
Neg logit contributions | |
wives | -0.832 |
Ov | -0.780 |
emale | -0.753 |
romy | -0.671 |
etz | -0.648 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Container | +2.333 |
Bundy | +1.937 |
Columb | +1.699 |
Clifford | +1.657 |
STL | +1.646 |
Neg logit contributions | |
wives | -2.833 |
Ov | -2.695 |
emale | -2.651 |
romy | -2.438 |
etz | -2.373 |
Token | Dw |
Token ID | 19113 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
Container | +0.715 |
Bundy | +0.597 |
Columb | +0.527 |
Clifford | +0.511 |
STL | +0.506 |
Neg logit contributions | |
wives | -0.879 |
Ov | -0.835 |
emale | -0.824 |
romy | -0.757 |
etz | -0.742 |
Token | ark |
Token ID | 668 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
wives | +0.490 |
Ov | +0.467 |
emale | +0.452 |
romy | +0.411 |
etz | +0.400 |
Neg logit contributions | |
Container | -0.502 |
Bundy | -0.427 |
Columb | -0.382 |
Clifford | -0.375 |
container | -0.370 |
Token | a |
Token ID | 64 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
wives | +0.103 |
Ov | +0.099 |
emale | +0.097 |
romy | +0.090 |
etz | +0.089 |
Neg logit contributions | |
Container | -0.063 |
Bundy | -0.051 |
Columb | -0.043 |
Clifford | -0.042 |
STL | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Container | +0.893 |
Bundy | +0.749 |
Columb | +0.664 |
Clifford | +0.648 |
STL | +0.640 |
Neg logit contributions | |
wives | -1.018 |
Ov | -0.970 |
emale | -0.944 |
romy | -0.868 |
etz | -0.848 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Container | +0.351 |
Bundy | +0.295 |
Columb | +0.262 |
Clifford | +0.255 |
STL | +0.252 |
Neg logit contributions | |
wives | -0.398 |
Ov | -0.378 |
emale | -0.371 |
romy | -0.340 |
etz | -0.333 |
Token | you |
Token ID | 345 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Container | +0.716 |
Bundy | +0.603 |
Columb | +0.535 |
Clifford | +0.524 |
container | +0.518 |
Neg logit contributions | |
wives | -0.787 |
Ov | -0.749 |
emale | -0.730 |
romy | -0.669 |
etz | -0.652 |
Token | can |
Token ID | 460 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Container | +1.655 |
Bundy | +1.397 |
Columb | +1.238 |
container | +1.214 |
Clifford | +1.204 |
Neg logit contributions | |
wives | -1.795 |
Ov | -1.693 |
emale | -1.667 |
romy | -1.510 |
etz | -1.467 |
Token | find |
Token ID | 1064 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
Container | +0.870 |
Bundy | +0.736 |
Columb | +0.661 |
Clifford | +0.647 |
container | +0.646 |
Neg logit contributions | |
wives | -0.864 |
Ov | -0.816 |
emale | -0.801 |
romy | -0.727 |
etz | -0.706 |
Token | cos |
Token ID | 8615 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
wives | +0.130 |
Ov | +0.124 |
emale | +0.121 |
romy | +0.111 |
etz | +0.109 |
Neg logit contributions | |
Container | -0.114 |
Bundy | -0.096 |
Columb | -0.085 |
Clifford | -0.083 |
STL | -0.082 |
Token | player |
Token ID | 7829 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Container | +0.545 |
Bundy | +0.466 |
Columb | +0.418 |
Clifford | +0.410 |
container | +0.406 |
Neg logit contributions | |
wives | -0.514 |
Ov | -0.489 |
emale | -0.474 |
romy | -0.430 |
etz | -0.421 |
Token | fan |
Token ID | 4336 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
wives | +0.757 |
Ov | +0.720 |
emale | +0.699 |
romy | +0.640 |
etz | +0.624 |
Neg logit contributions | |
Container | -0.741 |
Bundy | -0.629 |
Columb | -0.563 |
Clifford | -0.551 |
STL | -0.544 |
Token | pages |
Token ID | 5468 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
wives | +0.392 |
Ov | +0.373 |
emale | +0.362 |
romy | +0.332 |
etz | +0.323 |
Neg logit contributions | |
Container | -0.375 |
Bundy | -0.318 |
Columb | -0.284 |
Clifford | -0.278 |
STL | -0.274 |
Token | if |
Token ID | 611 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
wives | +0.918 |
Ov | +0.875 |
emale | +0.848 |
romy | +0.780 |
etz | +0.765 |
Neg logit contributions | |
Container | -0.801 |
Bundy | -0.673 |
Columb | -0.596 |
Clifford | -0.582 |
STL | -0.574 |
Token | you |
Token ID | 345 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Container | +0.815 |
Bundy | +0.671 |
Columb | +0.587 |
Clifford | +0.572 |
container | +0.564 |
Neg logit contributions | |
wives | -1.090 |
Ov | -1.040 |
emale | -1.016 |
romy | -0.939 |
etz | -0.919 |
Token | � |
Token ID | 447 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
Container | +0.857 |
Bundy | +0.722 |
Columb | +0.637 |
Clifford | +0.622 |
container | +0.622 |
Neg logit contributions | |
wives | -0.980 |
Ov | -0.928 |
emale | -0.908 |
romy | -0.827 |
etz | -0.807 |
Token | � |
Token ID | 247 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Container | +0.615 |
Bundy | +0.526 |
Columb | +0.472 |
Clifford | +0.462 |
container | +0.457 |
Neg logit contributions | |
wives | -0.581 |
Ov | -0.551 |
emale | -0.534 |
romy | -0.487 |
etz | -0.474 |
Token | 30 |
Token ID | 1270 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
wives | +0.323 |
Ov | +0.307 |
emale | +0.298 |
romy | +0.272 |
etz | +0.266 |
Neg logit contributions | |
Container | -0.320 |
Bundy | -0.272 |
Columb | -0.243 |
Clifford | -0.238 |
container | -0.235 |
Token | 60 |
Token ID | 1899 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
wives | +1.236 |
Ov | +1.173 |
emale | +1.132 |
romy | +1.027 |
etz | +1.003 |
Neg logit contributions | |
Container | -1.326 |
Bundy | -1.134 |
Columb | -1.019 |
Clifford | -0.997 |
container | -0.987 |
Token | ).[ |
Token ID | 42669 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Container | +2.496 |
Bundy | +2.105 |
Columb | +1.856 |
Clifford | +1.806 |
container | +1.787 |
Neg logit contributions | |
wives | -3.039 |
Ov | -2.888 |
emale | -2.786 |
romy | -2.627 |
etz | -2.555 |
Token | 126 |
Token ID | 19420 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Container | +0.954 |
Bundy | +0.819 |
Columb | +0.741 |
Clifford | +0.729 |
container | +0.721 |
Neg logit contributions | |
wives | -0.816 |
Ov | -0.779 |
emale | -0.747 |
romy | -0.681 |
etz | -0.663 |
Token | ] |
Token ID | 60 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Container | +1.397 |
Bundy | +1.226 |
Columb | +1.121 |
Clifford | +1.106 |
STL | +1.094 |
Neg logit contributions | |
wives | -0.907 |
Ov | -0.849 |
emale | -0.816 |
romy | -0.727 |
etz | -0.701 |
Token | On |
Token ID | 1550 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
wives | +1.323 |
Ov | +1.268 |
emale | +1.212 |
romy | +1.109 |
etz | +1.084 |
Neg logit contributions | |
Container | -1.305 |
Bundy | -1.111 |
Columb | -0.990 |
Clifford | -0.969 |
container | -0.960 |
Token | April |
Token ID | 3035 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Container | +0.267 |
Bundy | +0.226 |
Columb | +0.201 |
Clifford | +0.197 |
STL | +0.194 |
Neg logit contributions | |
wives | -0.290 |
Ov | -0.275 |
emale | -0.270 |
romy | -0.247 |
etz | -0.241 |
Token | 9 |
Token ID | 860 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Container | +0.728 |
Bundy | +0.614 |
Columb | +0.544 |
Clifford | +0.531 |
STL | +0.524 |
Neg logit contributions | |
wives | -0.834 |
Ov | -0.793 |
emale | -0.780 |
romy | -0.715 |
etz | -0.695 |
Token | , |
Token ID | 11 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
Container | +1.278 |
Bundy | +1.065 |
Columb | +0.943 |
Clifford | +0.917 |
STL | +0.907 |
Neg logit contributions | |
wives | -1.582 |
Ov | -1.500 |
emale | -1.476 |
romy | -1.365 |
etz | -1.333 |
Token | O |
Token ID | 440 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
Container | +0.312 |
Bundy | +0.260 |
Columb | +0.230 |
Clifford | +0.224 |
STL | +0.222 |
Neg logit contributions | |
wives | -0.383 |
Ov | -0.363 |
emale | -0.356 |
romy | -0.329 |
etz | -0.322 |
Token | ka |
Token ID | 4914 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
Container | +0.287 |
Bundy | +0.256 |
Columb | +0.237 |
Clifford | +0.233 |
container | +0.231 |
Neg logit contributions | |
wives | -0.142 |
Ov | -0.132 |
emale | -0.126 |
romy | -0.108 |
etz | -0.103 |
Token | H |
Token ID | 367 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
wives | +1.254 |
Ov | +1.196 |
emale | +1.161 |
romy | +1.067 |
etz | +1.044 |
Neg logit contributions | |
Container | -1.097 |
Bundy | -0.922 |
Columb | -0.816 |
Clifford | -0.798 |
STL | -0.786 |
Token | EX |
Token ID | 6369 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Container | +0.277 |
Bundy | +0.237 |
Columb | +0.213 |
Clifford | +0.209 |
STL | +0.206 |
Neg logit contributions | |
wives | -0.255 |
Ov | -0.242 |
emale | -0.234 |
romy | -0.213 |
etz | -0.207 |
Token | AG |
Token ID | 4760 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Container | +2.863 |
Bundy | +2.430 |
Columb | +2.166 |
Clifford | +2.129 |
container | +2.119 |
Neg logit contributions | |
wives | -2.832 |
Ov | -2.679 |
emale | -2.607 |
romy | -2.388 |
etz | -2.331 |
Token | ON |
Token ID | 1340 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
wives | +1.359 |
Ov | +1.283 |
emale | +1.235 |
romy | +1.113 |
etz | +1.082 |
Neg logit contributions | |
Container | -1.746 |
Bundy | -1.513 |
Columb | -1.374 |
Clifford | -1.350 |
container | -1.332 |
Token | camera |
Token ID | 4676 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
wives | +0.613 |
Ov | +0.582 |
emale | +0.563 |
romy | +0.512 |
etz | +0.500 |
Neg logit contributions | |
Container | -0.653 |
Bundy | -0.558 |
Columb | -0.502 |
Clifford | -0.492 |
STL | -0.485 |
Token | � |
Token ID | 447 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
wives | +0.931 |
Ov | +0.888 |
emale | +0.860 |
romy | +0.791 |
etz | +0.774 |
Neg logit contributions | |
Container | -0.838 |
Bundy | -0.708 |
Columb | -0.627 |
Clifford | -0.614 |
STL | -0.604 |
Token | � |
Token ID | 251 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
wives | +0.385 |
Ov | +0.366 |
emale | +0.353 |
romy | +0.321 |
etz | +0.314 |
Neg logit contributions | |
Container | -0.426 |
Bundy | -0.365 |
Columb | -0.329 |
Clifford | -0.322 |
STL | -0.319 |
Token | system |
Token ID | 1080 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Container | +0.256 |
Bundy | +0.216 |
Columb | +0.192 |
Clifford | +0.187 |
STL | +0.185 |
Neg logit contributions | |
wives | -0.283 |
Ov | -0.270 |
emale | -0.262 |
romy | -0.240 |
etz | -0.235 |
Token | has |
Token ID | 468 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
wives | +1.690 |
Ov | +1.615 |
emale | +1.566 |
romy | +1.443 |
etz | +1.413 |
Neg logit contributions | |
Container | -1.458 |
Bundy | -1.230 |
Columb | -1.084 |
Clifford | -1.060 |
STL | -1.043 |
Token | been |
Token ID | 587 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
wives | +0.509 |
Ov | +0.482 |
emale | +0.467 |
romy | +0.424 |
etz | +0.414 |
Neg logit contributions | |
Container | -0.557 |
Bundy | -0.477 |
Columb | -0.429 |
Clifford | -0.421 |
STL | -0.416 |
Token | declass |
Token ID | 42794 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
wives | +0.311 |
Ov | +0.295 |
emale | +0.286 |
romy | +0.260 |
etz | +0.254 |
Neg logit contributions | |
Container | -0.326 |
Bundy | -0.278 |
Columb | -0.250 |
Clifford | -0.245 |
STL | -0.242 |
Token | En |
Token ID | 2039 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
wives | +3.168 |
Ov | +3.074 |
emale | +2.915 |
romy | +2.660 |
etz | +2.611 |
Neg logit contributions | |
Container | -3.073 |
Bundy | -2.612 |
Columb | -2.318 |
Clifford | -2.276 |
estic | -2.243 |
Token | V |
Token ID | 53 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
wives | +2.112 |
Ov | +2.034 |
emale | +1.926 |
etz | +1.758 |
romy | +1.752 |
Neg logit contributions | |
Container | -2.258 |
Bundy | -1.953 |
Columb | -1.747 |
Clifford | -1.728 |
container | -1.696 |
Token | y |
Token ID | 88 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Container | +0.549 |
Bundy | +0.476 |
Columb | +0.431 |
Clifford | +0.423 |
STL | +0.419 |
Neg logit contributions | |
wives | -0.432 |
Ov | -0.409 |
emale | -0.396 |
romy | -0.353 |
etz | -0.343 |
Token | Us |
Token ID | 5842 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
wives | +1.038 |
Ov | +0.987 |
emale | +0.947 |
romy | +0.855 |
etz | +0.839 |
Neg logit contributions | |
Container | -1.200 |
Bundy | -1.036 |
Columb | -0.937 |
Clifford | -0.919 |
STL | -0.905 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
wives | +2.900 |
Ov | +2.789 |
emale | +2.685 |
romy | +2.443 |
etz | +2.425 |
Neg logit contributions | |
Container | -2.525 |
Bundy | -2.113 |
Columb | -1.884 |
Clifford | -1.842 |
container | -1.811 |
Token | Titan |
Token ID | 11977 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
wives | +1.555 |
Ov | +1.492 |
emale | +1.441 |
romy | +1.322 |
etz | +1.298 |
Neg logit contributions | |
Container | -1.349 |
Bundy | -1.131 |
Columb | -0.999 |
Clifford | -0.978 |
container | -0.964 |
Token | and |
Token ID | 290 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
wives | +0.855 |
Ov | +0.817 |
emale | +0.792 |
romy | +0.730 |
etz | +0.716 |
Neg logit contributions | |
Container | -0.708 |
Bundy | -0.591 |
Columb | -0.522 |
Clifford | -0.509 |
container | -0.501 |
Token | P |
Token ID | 350 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
wives | +1.054 |
Ov | +1.006 |
emale | +0.971 |
romy | +0.887 |
etz | +0.868 |
Neg logit contributions | |
Container | -1.040 |
Bundy | -0.884 |
Columb | -0.789 |
Clifford | -0.773 |
container | -0.763 |
Token | ENT |
Token ID | 3525 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
wives | +1.502 |
Ov | +1.432 |
emale | +1.380 |
romy | +1.256 |
etz | +1.234 |
Neg logit contributions | |
Container | -1.688 |
Bundy | -1.447 |
Columb | -1.301 |
Clifford | -1.277 |
container | -1.261 |
Token | A |
Token ID | 32 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
wives | +2.182 |
Ov | +2.086 |
emale | +2.011 |
romy | +1.852 |
etz | +1.813 |
Neg logit contributions | |
Container | -2.160 |
Bundy | -1.838 |
Columb | -1.672 |
Clifford | -1.619 |
STL | -1.605 |
Token | . |
Token ID | 13 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
wives | +1.169 |
Ov | +1.115 |
emale | +1.081 |
romy | +0.987 |
etz | +0.970 |
Neg logit contributions | |
Container | -1.087 |
Bundy | -0.920 |
Columb | -0.820 |
Clifford | -0.803 |
STL | -0.790 |
Token | children |
Token ID | 1751 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Container | +1.350 |
Bundy | +1.135 |
Columb | +1.016 |
Clifford | +0.991 |
container | +0.981 |
Neg logit contributions | |
wives | -1.505 |
Ov | -1.431 |
emale | -1.403 |
romy | -1.284 |
etz | -1.256 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Container | +1.228 |
Bundy | +1.009 |
Columb | +0.887 |
Clifford | +0.861 |
container | +0.848 |
Neg logit contributions | |
wives | -1.663 |
Ov | -1.592 |
emale | -1.554 |
romy | -1.436 |
etz | -1.408 |
Token | use |
Token ID | 779 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Container | +0.858 |
Bundy | +0.727 |
Columb | +0.658 |
Clifford | +0.640 |
container | +0.638 |
Neg logit contributions | |
wives | -0.870 |
Ov | -0.825 |
emale | -0.809 |
romy | -0.736 |
etz | -0.720 |
Token | their |
Token ID | 511 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
Container | +1.100 |
Bundy | +0.911 |
Columb | +0.808 |
Clifford | +0.787 |
container | +0.779 |
Neg logit contributions | |
wives | -1.360 |
Ov | -1.298 |
emale | -1.271 |
romy | -1.169 |
etz | -1.145 |
Token | imagination |
Token ID | 13843 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
Container | +0.563 |
Bundy | +0.474 |
Columb | +0.421 |
Clifford | +0.411 |
STL | +0.406 |
Neg logit contributions | |
wives | -0.629 |
Ov | -0.599 |
emale | -0.582 |
romy | -0.535 |
etz | -0.523 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
wives | +0.439 |
Ov | +0.419 |
emale | +0.405 |
romy | +0.373 |
etz | +0.367 |
Neg logit contributions | |
Container | -0.354 |
Bundy | -0.295 |
Columb | -0.258 |
Clifford | -0.252 |
STL | -0.249 |
Token | creativity |
Token ID | 16389 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
wives | +0.815 |
Ov | +0.775 |
emale | +0.750 |
romy | +0.686 |
etz | +0.670 |
Neg logit contributions | |
Container | -0.812 |
Bundy | -0.690 |
Columb | -0.617 |
Clifford | -0.604 |
STL | -0.596 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
wives | +0.810 |
Ov | +0.772 |
emale | +0.745 |
romy | +0.685 |
etz | +0.674 |
Neg logit contributions | |
Container | -0.690 |
Bundy | -0.580 |
Columb | -0.510 |
Clifford | -0.498 |
STL | -0.492 |
Token | Customers |
Token ID | 36707 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
wives | +0.189 |
Ov | +0.180 |
emale | +0.174 |
romy | +0.159 |
etz | +0.156 |
Neg logit contributions | |
Container | -0.187 |
Bundy | -0.158 |
Columb | -0.142 |
Clifford | -0.139 |
STL | -0.137 |
Token | can |
Token ID | 460 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Container | +0.804 |
Bundy | +0.686 |
Columb | +0.618 |
Clifford | +0.603 |
container | +0.597 |
Neg logit contributions | |
wives | -0.772 |
Ov | -0.733 |
emale | -0.714 |
romy | -0.650 |
etz | -0.632 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Container | +0.808 |
Bundy | +0.687 |
Columb | +0.619 |
Clifford | +0.603 |
container | +0.601 |
Neg logit contributions | |
wives | -0.794 |
Ov | -0.754 |
emale | -0.734 |
romy | -0.668 |
etz | -0.651 |
Token | now |
Token ID | 783 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
Container | +1.382 |
Bundy | +1.168 |
Columb | +1.039 |
Clifford | +1.014 |
container | +1.006 |
Neg logit contributions | |
wives | -1.542 |
Ov | -1.452 |
emale | -1.435 |
romy | -1.311 |
etz | -1.278 |
Token | it |
Token ID | 340 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
Container | +0.559 |
Bundy | +0.470 |
Columb | +0.417 |
Clifford | +0.407 |
container | +0.401 |
Neg logit contributions | |
wives | -0.653 |
Ov | -0.619 |
emale | -0.611 |
romy | -0.559 |
etz | -0.545 |
Token | is |
Token ID | 318 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
Container | +0.623 |
Bundy | +0.530 |
Columb | +0.470 |
Clifford | +0.460 |
container | +0.457 |
Neg logit contributions | |
wives | -0.673 |
Ov | -0.639 |
emale | -0.629 |
romy | -0.575 |
etz | -0.554 |
Token | looking |
Token ID | 2045 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
wives | +0.519 |
Ov | +0.492 |
emale | +0.481 |
romy | +0.440 |
etz | +0.429 |
Neg logit contributions | |
Container | -0.485 |
Bundy | -0.411 |
Columb | -0.366 |
Clifford | -0.358 |
STL | -0.353 |
Token | for |
Token ID | 329 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Container | +0.410 |
Bundy | +0.345 |
Columb | +0.305 |
Clifford | +0.297 |
container | +0.293 |
Neg logit contributions | |
wives | -0.483 |
Ov | -0.460 |
emale | -0.451 |
romy | -0.414 |
etz | -0.404 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Container | +0.802 |
Bundy | +0.672 |
Columb | +0.600 |
Clifford | +0.585 |
container | +0.580 |
Neg logit contributions | |
wives | -0.923 |
Ov | -0.874 |
emale | -0.862 |
romy | -0.792 |
etz | -0.770 |
Token | private |
Token ID | 2839 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
wives | +0.912 |
Ov | +0.868 |
emale | +0.840 |
romy | +0.767 |
etz | +0.750 |
Neg logit contributions | |
Container | -0.902 |
Bundy | -0.768 |
Columb | -0.685 |
Clifford | -0.672 |
STL | -0.663 |
Token | company |
Token ID | 1664 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
Container | +1.209 |
Bundy | +1.019 |
Columb | +0.908 |
Clifford | +0.887 |
container | +0.882 |
Neg logit contributions | |
wives | -1.322 |
Ov | -1.254 |
emale | -1.223 |
romy | -1.125 |
etz | -1.096 |
Token | that |
Token ID | 326 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Container | +0.094 |
Bundy | +0.078 |
Columb | +0.069 |
Clifford | +0.067 |
STL | +0.066 |
Neg logit contributions | |
wives | -0.114 |
Ov | -0.109 |
emale | -0.106 |
romy | -0.097 |
etz | -0.096 |
Token | can |
Token ID | 460 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
wives | +0.847 |
Ov | +0.805 |
emale | +0.780 |
romy | +0.711 |
etz | +0.694 |
Neg logit contributions | |
Container | -0.877 |
Bundy | -0.748 |
Columb | -0.671 |
Clifford | -0.657 |
STL | -0.649 |
Token | bring |
Token ID | 2222 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
wives | +1.281 |
Ov | +1.217 |
emale | +1.174 |
romy | +1.076 |
etz | +1.052 |
Neg logit contributions | |
Container | -1.309 |
Bundy | -1.116 |
Columb | -1.000 |
Clifford | -0.980 |
STL | -0.964 |
Token | Five |
Token ID | 10579 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
Container | +0.266 |
Bundy | +0.224 |
Columb | +0.199 |
Clifford | +0.195 |
STL | +0.192 |
Neg logit contributions | |
wives | -0.291 |
Ov | -0.277 |
emale | -0.269 |
romy | -0.247 |
etz | -0.241 |
Token | Corn |
Token ID | 11424 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Container | +0.623 |
Bundy | +0.526 |
Columb | +0.471 |
Clifford | +0.460 |
STL | +0.453 |
Neg logit contributions | |
wives | -0.656 |
Ov | -0.623 |
emale | -0.606 |
romy | -0.556 |
etz | -0.543 |
Token | ers |
Token ID | 364 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
wives | +0.635 |
Ov | +0.598 |
emale | +0.571 |
romy | +0.512 |
etz | +0.499 |
Neg logit contributions | |
Container | -0.912 |
Bundy | -0.796 |
Columb | -0.726 |
Clifford | -0.717 |
STL | -0.709 |
Token | in |
Token ID | 287 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
wives | +1.548 |
Ov | +1.480 |
emale | +1.428 |
romy | +1.313 |
etz | +1.287 |
Neg logit contributions | |
Container | -1.354 |
Bundy | -1.142 |
Columb | -1.010 |
Clifford | -0.988 |
STL | -0.973 |
Token | Bur |
Token ID | 5481 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Container | +0.169 |
Bundy | +0.143 |
Columb | +0.127 |
Clifford | +0.125 |
STL | +0.123 |
Neg logit contributions | |
wives | -0.184 |
Ov | -0.174 |
emale | -0.170 |
romy | -0.156 |
etz | -0.152 |
Token | ien |
Token ID | 2013 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
wives | +1.932 |
Ov | +1.836 |
emale | +1.770 |
romy | +1.656 |
etz | +1.607 |
Neg logit contributions | |
Container | -1.630 |
Bundy | -1.361 |
Columb | -1.179 |
container | -1.170 |
Clifford | -1.168 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
wives | +1.264 |
Ov | +1.203 |
emale | +1.167 |
romy | +1.069 |
etz | +1.045 |
Neg logit contributions | |
Container | -1.199 |
Bundy | -1.015 |
Columb | -0.905 |
Clifford | -0.885 |
STL | -0.873 |
Token |
|
Token ID | 198 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
wives | +2.384 |
Ov | +2.270 |
emale | +2.115 |
romy | +1.992 |
etz | +1.975 |
Neg logit contributions | |
Container | -1.963 |
Bundy | -1.638 |
Columb | -1.444 |
Clifford | -1.424 |
container | -1.407 |
Token | P |
Token ID | 47 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
wives | +1.942 |
Ov | +1.816 |
emale | +1.745 |
romy | +1.596 |
etz | +1.559 |
Neg logit contributions | |
Container | -2.198 |
Bundy | -1.893 |
Columb | -1.698 |
Clifford | -1.682 |
STL | -1.656 |
Token | CC |
Token ID | 4093 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Container | +1.455 |
Bundy | +1.201 |
Columb | +1.059 |
Clifford | +1.027 |
STL | +1.014 |
Neg logit contributions | |
wives | -1.884 |
Ov | -1.804 |
emale | -1.753 |
romy | -1.621 |
etz | -1.579 |
Token | Natural |
Token ID | 12068 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
Container | +1.834 |
Bundy | +1.432 |
Columb | +1.238 |
Clifford | +1.179 |
container | +1.168 |
Neg logit contributions | |
wives | -3.192 |
Ov | -3.038 |
emale | -3.007 |
romy | -2.820 |
etz | -2.754 |
Token | ight |
Token ID | 432 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
wives | +0.040 |
Ov | +0.037 |
emale | +0.036 |
romy | +0.033 |
etz | +0.032 |
Neg logit contributions | |
Container | -0.046 |
Bundy | -0.039 |
Columb | -0.035 |
Clifford | -0.035 |
STL | -0.034 |
Token | said |
Token ID | 531 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
Container | +0.098 |
Bundy | +0.083 |
Columb | +0.073 |
Clifford | +0.071 |
STL | +0.070 |
Neg logit contributions | |
wives | -0.116 |
Ov | -0.110 |
emale | -0.108 |
romy | -0.099 |
etz | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
wives | +0.083 |
Ov | +0.079 |
emale | +0.077 |
romy | +0.070 |
etz | +0.068 |
Neg logit contributions | |
Container | -0.080 |
Bundy | -0.068 |
Columb | -0.060 |
Clifford | -0.059 |
container | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +8.56e-03 |
Pos logit contributions | |
Container | +0.307 |
Bundy | +0.253 |
Columb | +0.221 |
Clifford | +0.215 |
STL | +0.211 |
Neg logit contributions | |
wives | -0.418 |
Ov | -0.400 |
emale | -0.390 |
romy | -0.361 |
etz | -0.353 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
Container | +0.050 |
Bundy | +0.041 |
Columb | +0.036 |
Clifford | +0.035 |
STL | +0.035 |
Neg logit contributions | |
wives | -0.066 |
Ov | -0.063 |
emale | -0.061 |
romy | -0.057 |
etz | -0.056 |
Token | Others |
Token ID | 25599 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Container | +0.134 |
Bundy | +0.114 |
Columb | +0.102 |
Clifford | +0.100 |
STL | +0.098 |
Neg logit contributions | |
wives | -0.134 |
Ov | -0.128 |
emale | -0.125 |
romy | -0.113 |
etz | -0.111 |
Token | say |
Token ID | 910 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
wives | +1.189 |
Ov | +1.135 |
emale | +1.101 |
romy | +1.013 |
etz | +0.992 |
Neg logit contributions | |
Container | -1.027 |
Bundy | -0.862 |
Columb | -0.763 |
Clifford | -0.745 |
STL | -0.734 |
Token | Abrams |
Token ID | 32414 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Container | +1.140 |
Bundy | +0.978 |
Columb | +0.873 |
Clifford | +0.855 |
STL | +0.839 |
Neg logit contributions | |
wives | -1.172 |
Ov | -1.107 |
emale | -1.089 |
romy | -0.998 |
etz | -0.967 |
Token | has |
Token ID | 468 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
wives | +0.824 |
Ov | +0.785 |
emale | +0.760 |
romy | +0.697 |
etz | +0.683 |
Neg logit contributions | |
Container | -0.768 |
Bundy | -0.648 |
Columb | -0.577 |
Clifford | -0.564 |
STL | -0.557 |
Token | been |
Token ID | 587 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Container | +0.774 |
Bundy | +0.668 |
Columb | +0.596 |
Clifford | +0.586 |
container | +0.580 |
Neg logit contributions | |
wives | -0.762 |
Ov | -0.722 |
emale | -0.715 |
romy | -0.646 |
etz | -0.626 |
Token | reluctant |
Token ID | 18416 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Container | +1.599 |
Bundy | +1.369 |
Columb | +1.206 |
Clifford | +1.189 |
container | +1.177 |
Neg logit contributions | |
wives | -1.731 |
Ov | -1.641 |
emale | -1.623 |
romy | -1.475 |
etz | -1.427 |
Token | "( |
Token ID | 18109 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
Container | +2.709 |
Bundy | +2.295 |
Columb | +2.060 |
container | +2.017 |
Clifford | +2.015 |
Neg logit contributions | |
wives | -2.672 |
Ov | -2.533 |
emale | -2.451 |
romy | -2.255 |
etz | -2.167 |
Token | \ |
Token ID | 59 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
wives | +0.213 |
Ov | +0.203 |
emale | +0.197 |
romy | +0.181 |
etz | +0.177 |
Neg logit contributions | |
Container | -0.183 |
Bundy | -0.153 |
Columb | -0.136 |
Clifford | -0.133 |
container | -0.131 |
Token | S |
Token ID | 50 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Container | +1.440 |
Bundy | +1.228 |
Columb | +1.105 |
Clifford | +1.077 |
container | +1.067 |
Neg logit contributions | |
wives | -1.364 |
Ov | -1.289 |
emale | -1.264 |
romy | -1.140 |
etz | -1.110 |
Token | +) |
Token ID | 28988 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Container | +1.413 |
Bundy | +1.242 |
Columb | +1.144 |
Clifford | +1.121 |
container | +1.118 |
Neg logit contributions | |
wives | -0.826 |
Ov | -0.766 |
emale | -0.734 |
romy | -0.648 |
etz | -0.624 |
Token | "] |
Token ID | 8973 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
wives | +2.105 |
Ov | +2.008 |
emale | +1.942 |
romy | +1.762 |
etz | +1.735 |
Neg logit contributions | |
Container | -2.174 |
Bundy | -1.866 |
Columb | -1.667 |
Clifford | -1.640 |
STL | -1.615 |
Token | ' |
Token ID | 6 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
wives | +5.232 |
Ov | +5.025 |
emale | +4.800 |
etz | +4.329 |
romy | +4.327 |
Neg logit contributions | |
Container | -5.446 |
Bundy | -4.729 |
Columb | -4.211 |
Clifford | -4.143 |
STL | -4.080 |
Token | ) |
Token ID | 1267 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
wives | +4.764 |
Ov | +4.484 |
emale | +4.349 |
romy | +3.874 |
etz | +3.754 |
Neg logit contributions | |
Container | -6.283 |
Bundy | -5.545 |
Columb | -5.036 |
Clifford | -4.919 |
Booster | -4.832 |
Token | AS |
Token ID | 7054 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
wives | +3.421 |
Ov | +3.210 |
emale | +3.036 |
romy | +2.631 |
etz | +2.536 |
Neg logit contributions | |
Container | -6.385 |
Bundy | -5.730 |
Columb | -5.238 |
Clifford | -5.176 |
estic | -5.075 |
Token | version |
Token ID | 2196 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
Container | +0.188 |
Bundy | +0.158 |
Columb | +0.139 |
Clifford | +0.136 |
STL | +0.134 |
Neg logit contributions | |
wives | -0.217 |
Ov | -0.207 |
emale | -0.201 |
romy | -0.185 |
etz | -0.181 |
Token | , |
Token ID | 837 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
wives | +4.100 |
Ov | +3.911 |
emale | +3.752 |
romy | +3.414 |
etz | +3.400 |
Neg logit contributions | |
Container | -4.384 |
Bundy | -3.788 |
Columb | -3.392 |
Clifford | -3.298 |
STL | -3.226 |
Token | C |
Token ID | 327 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
wives | +3.459 |
Ov | +3.336 |
emale | +3.187 |
romy | +2.930 |
etz | +2.856 |
Neg logit contributions | |
Container | -3.390 |
Bundy | -2.893 |
Columb | -2.592 |
Clifford | -2.526 |
STL | -2.458 |
Token | ) |
Token ID | 8 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
wives | +3.475 |
Ov | +3.255 |
emale | +3.166 |
romy | +2.874 |
etz | +2.840 |
Neg logit contributions | |
Container | -3.791 |
Bundy | -3.232 |
Columb | -2.923 |
Clifford | -2.857 |
container | -2.822 |
Token | on |
Token ID | 319 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
wives | +2.761 |
Ov | +2.638 |
emale | +2.405 |
romy | +2.253 |
etz | +2.227 |
Neg logit contributions | |
Container | -3.089 |
Bundy | -2.630 |
Columb | -2.362 |
Clifford | -2.329 |
estic | -2.312 |
Token | Sep |
Token ID | 8621 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
wives | +0.948 |
Ov | +0.898 |
emale | +0.852 |
romy | +0.761 |
etz | +0.743 |
Neg logit contributions | |
Container | -1.354 |
Bundy | -1.182 |
Columb | -1.077 |
Clifford | -1.060 |
container | -1.050 |
Token | 30 |
Token ID | 1542 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
wives | +3.591 |
Ov | +3.474 |
emale | +3.199 |
etz | +2.975 |
romy | +2.958 |
Neg logit contributions | |
Container | -3.529 |
Bundy | -2.963 |
Columb | -2.638 |
berra | -2.603 |
Clifford | -2.594 |
Token | , |
Token ID | 11 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
wives | +2.941 |
Ov | +2.811 |
emale | +2.554 |
romy | +2.420 |
etz | +2.415 |
Neg logit contributions | |
Container | -2.969 |
Bundy | -2.500 |
Columb | -2.234 |
berra | -2.195 |
Clifford | -2.185 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
wives | +3.387 |
Ov | +3.289 |
emale | +3.127 |
romy | +2.878 |
etz | +2.817 |
Neg logit contributions | |
Container | -3.223 |
Bundy | -2.727 |
Columb | -2.432 |
Clifford | -2.374 |
STL | -2.332 |
Token | at |
Token ID | 379 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
wives | +4.979 |
Ov | +4.789 |
etz | +3.911 |
emale | +3.790 |
romy | +3.765 |
Neg logit contributions | |
Container | -8.295 |
Bundy | -7.137 |
berra | -6.522 |
estic | -6.493 |
Columb | -6.489 |
Token | 9 |
Token ID | 860 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
wives | +1.629 |
Ov | +1.562 |
emale | +1.492 |
romy | +1.375 |
etz | +1.353 |
Neg logit contributions | |
Container | -1.482 |
Bundy | -1.245 |
Columb | -1.106 |
Clifford | -1.083 |
container | -1.070 |
Token | : |
Token ID | 25 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
wives | +0.069 |
Ov | +0.066 |
emale | +0.063 |
romy | +0.059 |
etz | +0.058 |
Neg logit contributions | |
Container | -0.051 |
Bundy | -0.042 |
Columb | -0.037 |
Clifford | -0.036 |
container | -0.035 |
Token | 01 |
Token ID | 486 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
wives | +1.216 |
Ov | +1.154 |
emale | +1.100 |
romy | +1.011 |
etz | +0.993 |
Neg logit contributions | |
Container | -1.254 |
Bundy | -1.067 |
Columb | -0.956 |
Clifford | -0.939 |
container | -0.929 |
Token | am |
Token ID | 321 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
wives | +1.301 |
Ov | +1.203 |
emale | +1.165 |
romy | +1.026 |
etz | +0.996 |
Neg logit contributions | |
Container | -2.137 |
Bundy | -1.876 |
Columb | -1.726 |
Clifford | -1.699 |
STL | -1.681 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
wives | +1.031 |
Ov | +0.977 |
emale | +0.919 |
romy | +0.851 |
etz | +0.837 |
Neg logit contributions | |
Container | -1.125 |
Bundy | -0.962 |
Columb | -0.863 |
Clifford | -0.849 |
container | -0.836 |
Token | It |
Token ID | 632 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
Container | +1.130 |
Bundy | +0.956 |
Columb | +0.854 |
Clifford | +0.835 |
STL | +0.825 |
Neg logit contributions | |
wives | -1.174 |
Ov | -1.104 |
emale | -1.100 |
romy | -0.996 |
etz | -0.968 |
Token | will |
Token ID | 481 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Container | +0.578 |
Bundy | +0.493 |
Columb | +0.443 |
Clifford | +0.434 |
STL | +0.429 |
Neg logit contributions | |
wives | -0.558 |
Ov | -0.530 |
emale | -0.516 |
romy | -0.468 |
etz | -0.457 |
Token | also |
Token ID | 635 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
wives | +1.928 |
Ov | +1.829 |
emale | +1.714 |
romy | +1.576 |
etz | +1.566 |
Neg logit contributions | |
Container | -2.417 |
Bundy | -2.097 |
Columb | -1.880 |
Clifford | -1.863 |
Booster | -1.820 |
Token | included |
Token ID | 3017 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
wives | +3.334 |
Ov | +3.180 |
emale | +2.951 |
etz | +2.823 |
romy | +2.747 |
Neg logit contributions | |
Container | -3.703 |
Bundy | -3.162 |
Columb | -2.826 |
Clifford | -2.819 |
berra | -2.730 |
Token | the |
Token ID | 262 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
wives | +1.173 |
Ov | +1.127 |
emale | +1.054 |
romy | +0.996 |
etz | +0.985 |
Neg logit contributions | |
Container | -0.983 |
Bundy | -0.822 |
Columb | -0.724 |
Clifford | -0.710 |
STL | -0.693 |
Token | add |
Token ID | 751 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
wives | +3.761 |
Ov | +3.554 |
emale | +3.186 |
etz | +2.877 |
romy | +2.867 |
Neg logit contributions | |
Container | -6.840 |
Bundy | -6.127 |
Columb | -5.608 |
Clifford | -5.548 |
estic | -5.437 |
Token | t |
Token ID | 83 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Container | +1.861 |
Bundy | +1.551 |
Columb | +1.361 |
Clifford | +1.336 |
container | +1.323 |
Neg logit contributions | |
wives | -2.265 |
Ov | -2.175 |
emale | -2.132 |
romy | -1.939 |
etz | -1.892 |
Token | ional |
Token ID | 1538 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
wives | +1.078 |
Ov | +0.989 |
emale | +0.939 |
romy | +0.859 |
etz | +0.822 |
Neg logit contributions | |
Container | -1.929 |
Bundy | -1.704 |
Columb | -1.581 |
Clifford | -1.542 |
STL | -1.531 |
Token | resources |
Token ID | 4133 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
wives | +2.627 |
Ov | +2.472 |
emale | +2.226 |
romy | +2.138 |
etz | +2.078 |
Neg logit contributions | |
Container | -3.213 |
Bundy | -2.787 |
Columb | -2.518 |
Clifford | -2.499 |
STL | -2.403 |
Token | and |
Token ID | 290 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Container | +1.393 |
Bundy | +1.131 |
Columb | +0.976 |
Clifford | +0.945 |
container | +0.934 |
Neg logit contributions | |
wives | -2.124 |
Ov | -2.037 |
emale | -2.020 |
romy | -1.853 |
etz | -1.811 |
Token | ( |
Token ID | 357 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Container | +0.059 |
Bundy | +0.049 |
Columb | +0.044 |
Clifford | +0.043 |
STL | +0.042 |
Neg logit contributions | |
wives | -0.068 |
Ov | -0.065 |
emale | -0.063 |
romy | -0.058 |
etz | -0.057 |
Token | 13 |
Token ID | 1485 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Container | +1.189 |
Bundy | +1.005 |
Columb | +0.895 |
Clifford | +0.876 |
STL | +0.869 |
Neg logit contributions | |
wives | -1.257 |
Ov | -1.204 |
emale | -1.168 |
romy | -1.065 |
etz | -1.039 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Container | +0.730 |
Bundy | +0.611 |
Columb | +0.540 |
Clifford | +0.527 |
STL | +0.519 |
Neg logit contributions | |
wives | -0.860 |
Ov | -0.821 |
emale | -0.796 |
romy | -0.733 |
etz | -0.719 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Container | +1.114 |
Bundy | +0.905 |
Columb | +0.780 |
Clifford | +0.757 |
STL | +0.743 |
Neg logit contributions | |
wives | -1.685 |
Ov | -1.616 |
emale | -1.572 |
romy | -1.462 |
etz | -1.436 |
Token | )) |
Token ID | 4008 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Container | +0.842 |
Bundy | +0.716 |
Columb | +0.640 |
Clifford | +0.626 |
STL | +0.617 |
Neg logit contributions | |
wives | -0.863 |
Ov | -0.819 |
emale | -0.794 |
romy | -0.727 |
etz | -0.710 |
Token | sq |
Token ID | 19862 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
wives | +3.170 |
Ov | +3.024 |
emale | +2.869 |
romy | +2.625 |
etz | +2.515 |
Neg logit contributions | |
Container | -4.078 |
Bundy | -3.572 |
Columb | -3.216 |
Clifford | -3.206 |
Booster | -3.133 |
Token | K |
Token ID | 42 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
wives | +3.481 |
Ov | +3.173 |
emale | +2.499 |
kos | +2.495 |
Women | +2.482 |
Neg logit contributions | |
Container | -8.459 |
Bundy | -7.486 |
Columb | -7.100 |
berra | -7.031 |
Clifford | -7.019 |
Token | ernel |
Token ID | 7948 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
wives | +2.513 |
Ov | +2.206 |
emale | +1.987 |
romy | +1.855 |
etz | +1.685 |
Neg logit contributions | |
Container | -7.391 |
Bundy | -6.664 |
Columb | -6.222 |
Clifford | -6.213 |
Booster | -6.055 |
Token | = |
Token ID | 796 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
wives | +4.155 |
Ov | +3.939 |
emale | +3.475 |
romy | +3.316 |
etz | +3.312 |
Neg logit contributions | |
Container | -5.439 |
Bundy | -4.705 |
Columb | -4.293 |
Clifford | -4.266 |
berra | -4.260 |
Token | c |
Token ID | 269 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
wives | +1.348 |
Ov | +1.295 |
emale | +1.202 |
romy | +1.119 |
etz | +1.100 |
Neg logit contributions | |
Container | -1.531 |
Bundy | -1.321 |
Columb | -1.180 |
Clifford | -1.164 |
Booster | -1.146 |
Token | v |
Token ID | 85 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Container | +0.880 |
Bundy | +0.760 |
Columb | +0.688 |
Clifford | +0.675 |
STL | +0.667 |
Neg logit contributions | |
wives | -0.733 |
Ov | -0.694 |
emale | -0.672 |
romy | -0.606 |
etz | -0.590 |
Token | ment |
Token ID | 434 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Container | +0.365 |
Bundy | +0.287 |
Columb | +0.238 |
Clifford | +0.231 |
STL | +0.226 |
Neg logit contributions | |
wives | -0.685 |
Ov | -0.659 |
emale | -0.643 |
romy | -0.602 |
etz | -0.592 |
Token | ( |
Token ID | 357 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
wives | +2.760 |
Ov | +2.639 |
emale | +2.532 |
romy | +2.316 |
etz | +2.288 |
Neg logit contributions | |
Container | -2.539 |
Bundy | -2.150 |
Columb | -1.891 |
Clifford | -1.854 |
STL | -1.839 |
Token | with |
Token ID | 4480 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
wives | +1.232 |
Ov | +1.163 |
emale | +1.130 |
romy | +1.033 |
etz | +1.013 |
Neg logit contributions | |
Container | -1.183 |
Bundy | -1.005 |
Columb | -0.892 |
Clifford | -0.876 |
STL | -0.867 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
wives | +1.292 |
Ov | +1.232 |
emale | +1.195 |
romy | +1.094 |
etz | +1.075 |
Neg logit contributions | |
Container | -1.148 |
Bundy | -0.965 |
Columb | -0.853 |
Clifford | -0.835 |
STL | -0.825 |
Token | exception |
Token ID | 6631 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
wives | +1.587 |
Ov | +1.520 |
emale | +1.477 |
romy | +1.360 |
etz | +1.337 |
Neg logit contributions | |
Container | -1.240 |
Bundy | -1.028 |
Columb | -0.899 |
Clifford | -0.879 |
STL | -0.865 |
Token | of |
Token ID | 286 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
wives | +5.066 |
Ov | +4.808 |
emale | +4.640 |
romy | +4.214 |
etz | +4.205 |
Neg logit contributions | |
Container | -4.151 |
Bundy | -3.465 |
Columb | -3.006 |
STL | -2.981 |
Clifford | -2.971 |
Token | South |
Token ID | 2520 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
wives | +6.623 |
Ov | +6.377 |
emale | +5.941 |
romy | +5.452 |
etz | +5.354 |
Neg logit contributions | |
Container | -6.292 |
Bundy | -5.234 |
estic | -4.617 |
Clifford | -4.591 |
Columb | -4.576 |
Token | Australia |
Token ID | 4505 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
wives | +1.390 |
Ov | +1.299 |
emale | +1.245 |
romy | +1.117 |
etz | +1.091 |
Neg logit contributions | |
Container | -1.937 |
Bundy | -1.686 |
Columb | -1.528 |
Clifford | -1.511 |
STL | -1.501 |
Token | ).[ |
Token ID | 42669 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
wives | +1.434 |
Ov | +1.366 |
emale | +1.327 |
romy | +1.219 |
etz | +1.200 |
Neg logit contributions | |
Container | -1.197 |
Bundy | -0.999 |
Columb | -0.879 |
Clifford | -0.859 |
STL | -0.851 |
Token | 188 |
Token ID | 20356 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Container | +0.484 |
Bundy | +0.421 |
Columb | +0.382 |
Clifford | +0.376 |
container | +0.371 |
Neg logit contributions | |
wives | -0.379 |
Ov | -0.362 |
emale | -0.345 |
romy | -0.312 |
etz | -0.303 |
Token | ] |
Token ID | 60 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
wives | +0.710 |
Ov | +0.664 |
emale | +0.637 |
romy | +0.560 |
etz | +0.543 |
Neg logit contributions | |
Container | -1.179 |
Bundy | -1.037 |
Columb | -0.953 |
Clifford | -0.937 |
STL | -0.929 |