Token | of |
Token ID | 286 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
oaded | +2.042 |
atorial | +1.939 |
otle | +1.909 |
icion | +1.897 |
ornia | +1.875 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.982 |
theless | -1.934 |
lasting | -1.831 |
™: | -1.829 |
livest | -1.823 |
Token | life |
Token ID | 1204 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
oaded | +0.873 |
indal | +0.841 |
atorial | +0.832 |
clusively | +0.829 |
ornia | +0.824 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.867 |
theless | -0.832 |
lasting | -0.816 |
™: | -0.789 |
livest | -0.789 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.811 |
lasting | +0.765 |
theless | +0.762 |
wonder | +0.731 |
™: | +0.729 |
Neg logit contributions | |
oaded | -0.996 |
atorial | -0.936 |
indal | -0.936 |
icion | -0.919 |
clusively | -0.914 |
Token | in |
Token ID | 287 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.245 |
theless | +0.237 |
lasting | +0.231 |
wonder | +0.224 |
™: | +0.221 |
Neg logit contributions | |
oaded | -0.293 |
indal | -0.283 |
atorial | -0.279 |
clusively | -0.277 |
ornia | -0.276 |
Token | your |
Token ID | 534 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
oaded | +1.303 |
clusively | +1.255 |
indal | +1.246 |
atorial | +1.234 |
efficients | +1.200 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.263 |
theless | -1.254 |
lasting | -1.226 |
livest | -1.190 |
wonder | -1.189 |
Token | poker |
Token ID | 27101 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
oaded | +2.197 |
clusively | +2.107 |
atorial | +2.107 |
indal | +2.085 |
icion | +2.084 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.441 |
theless | -2.398 |
lasting | -2.221 |
™: | -2.215 |
hm | -2.205 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
oaded | +4.657 |
atorial | +4.513 |
icion | +4.370 |
ornia | +4.275 |
indal | +4.223 |
Neg logit contributions | |
theless | -6.036 |
\\\\\\\\\\\\\\\\ | -6.024 |
livest | -5.827 |
lasting | -5.715 |
phrine | -5.673 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
oaded | +2.811 |
indal | +2.661 |
atorial | +2.628 |
icion | +2.604 |
ornia | +2.573 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.310 |
theless | -2.253 |
lasting | -2.229 |
wonder | -2.160 |
livest | -2.111 |
Token | life |
Token ID | 1204 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
oaded | +1.758 |
indal | +1.675 |
atorial | +1.668 |
clusively | +1.664 |
ornia | +1.653 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.506 |
theless | -1.429 |
livest | -1.369 |
lasting | -1.367 |
™: | -1.345 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.407 |
lasting | +0.395 |
theless | +0.391 |
wonder | +0.382 |
™: | +0.367 |
Neg logit contributions | |
oaded | -0.539 |
indal | -0.511 |
atorial | -0.507 |
icion | -0.499 |
Moroc | -0.498 |
Token | those |
Token ID | 883 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
oaded | +0.196 |
indal | +0.184 |
atorial | +0.184 |
clusively | +0.180 |
icion | +0.179 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.168 |
theless | -0.159 |
lasting | -0.155 |
quin | -0.150 |
wonder | -0.150 |
Token | based |
Token ID | 3106 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.923 |
lasting | +0.913 |
wonder | +0.883 |
theless | +0.881 |
livest | +0.844 |
Neg logit contributions | |
oaded | -0.865 |
indal | -0.817 |
atorial | -0.797 |
ornia | -0.794 |
icion | -0.791 |
Token | Vol |
Token ID | 4709 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
oaded | +1.397 |
indal | +1.329 |
atorial | +1.318 |
Moroc | +1.311 |
icion | +1.293 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.407 |
lasting | -1.361 |
theless | -1.310 |
wonder | -1.289 |
™: | -1.265 |
Token | ody |
Token ID | 1118 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.048 |
lasting | +0.048 |
theless | +0.046 |
wonder | +0.046 |
livest | +0.044 |
Neg logit contributions | |
oaded | -0.041 |
indal | -0.038 |
atorial | -0.037 |
ornia | -0.037 |
icion | -0.037 |
Token | my |
Token ID | 1820 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
oaded | +2.831 |
indal | +2.726 |
atorial | +2.682 |
ornia | +2.669 |
Moroc | +2.660 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.587 |
lasting | -1.562 |
wonder | -1.481 |
theless | -1.457 |
livest | -1.378 |
Token | r |
Token ID | 81 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
oaded | +0.175 |
indal | +0.166 |
atorial | +0.163 |
ornia | +0.162 |
Moroc | +0.161 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.155 |
lasting | -0.154 |
theless | -0.148 |
wonder | -0.147 |
livest | -0.140 |
Token | Gol |
Token ID | 26849 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
oaded | +0.019 |
indal | +0.018 |
atorial | +0.017 |
Moroc | +0.017 |
icion | +0.017 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.031 |
lasting | -0.031 |
theless | -0.030 |
wonder | -0.030 |
livest | -0.029 |
Token | ov |
Token ID | 709 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
oaded | +4.053 |
indal | +3.853 |
iov | +3.824 |
atorial | +3.625 |
icion | +3.623 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -7.298 |
livest | -7.108 |
theless | -7.047 |
lasting | -7.030 |
wonder | -6.616 |
Token | ko |
Token ID | 7204 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.322 |
theless | +0.314 |
lasting | +0.310 |
livest | +0.303 |
wonder | +0.300 |
Neg logit contributions | |
oaded | -0.337 |
indal | -0.314 |
atorial | -0.313 |
icion | -0.309 |
ornia | -0.308 |
Token | is |
Token ID | 318 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.149 |
lasting | +0.144 |
theless | +0.143 |
wonder | +0.138 |
livest | +0.133 |
Neg logit contributions | |
oaded | -0.184 |
indal | -0.177 |
atorial | -0.174 |
icion | -0.171 |
ornia | -0.171 |
Token | a |
Token ID | 257 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.654 |
lasting | +0.640 |
theless | +0.628 |
wonder | +0.616 |
™: | +0.597 |
Neg logit contributions | |
oaded | -0.703 |
indal | -0.674 |
atorial | -0.658 |
clusively | -0.653 |
icion | -0.649 |
Token | former |
Token ID | 1966 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.382 |
lasting | +0.368 |
theless | +0.367 |
wonder | +0.356 |
™: | +0.350 |
Neg logit contributions | |
oaded | -0.321 |
indal | -0.306 |
atorial | -0.299 |
icion | -0.297 |
clusively | -0.295 |
Token | Rights |
Token ID | 6923 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
oaded | +0.103 |
indal | +0.096 |
atorial | +0.093 |
ornia | +0.092 |
Moroc | +0.092 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.151 |
lasting | -0.150 |
theless | -0.146 |
wonder | -0.146 |
longer | -0.140 |
Token | Director |
Token ID | 5890 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.159 |
lasting | +1.139 |
theless | +1.127 |
wonder | +1.110 |
livest | +1.056 |
Neg logit contributions | |
oaded | -1.223 |
indal | -1.154 |
ornia | -1.139 |
atorial | -1.134 |
icion | -1.123 |
Token | V |
Token ID | 569 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.196 |
lasting | +2.186 |
theless | +2.130 |
wonder | +2.112 |
livest | +2.011 |
Neg logit contributions | |
oaded | -2.095 |
indal | -1.975 |
atorial | -1.935 |
ornia | -1.920 |
Moroc | -1.911 |
Token | elve |
Token ID | 9954 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.717 |
lasting | +0.710 |
theless | +0.690 |
wonder | +0.683 |
livest | +0.652 |
Neg logit contributions | |
oaded | -0.716 |
indal | -0.683 |
atorial | -0.661 |
ornia | -0.660 |
icion | -0.653 |
Token | ta |
Token ID | 8326 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.111 |
lasting | +1.097 |
theless | +1.067 |
wonder | +1.060 |
livest | +1.019 |
Neg logit contributions | |
oaded | -1.148 |
indal | -1.097 |
atorial | -1.076 |
ornia | -1.061 |
icion | -1.052 |
Token | Gol |
Token ID | 26849 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.871 |
lasting | +0.867 |
theless | +0.844 |
wonder | +0.836 |
livest | +0.800 |
Neg logit contributions | |
oaded | -0.915 |
indal | -0.867 |
atorial | -0.852 |
ornia | -0.845 |
Moroc | -0.841 |
Token | ight |
Token ID | 432 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
oaded | +5.726 |
indal | +5.687 |
atorial | +5.319 |
ornia | +5.305 |
icion | +5.292 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.499 |
lasting | -5.404 |
livest | -5.263 |
wonder | -5.162 |
theless | -5.146 |
Token | ly |
Token ID | 306 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
oaded | +1.987 |
indal | +1.894 |
atorial | +1.845 |
icion | +1.837 |
ornia | +1.824 |
Neg logit contributions | |
lasting | -1.573 |
\\\\\\\\\\\\\\\\ | -1.568 |
theless | -1.535 |
wonder | -1.500 |
livest | -1.478 |
Token | - |
Token ID | 12 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
oaded | +1.238 |
indal | +1.185 |
ornia | +1.163 |
atorial | +1.159 |
icion | +1.150 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.852 |
theless | -0.834 |
lasting | -0.825 |
wonder | -0.807 |
livest | -0.766 |
Token | How |
Token ID | 2437 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
oaded | +0.936 |
indal | +0.886 |
atorial | +0.854 |
ornia | +0.853 |
icion | +0.851 |
Neg logit contributions | |
lasting | -1.023 |
\\\\\\\\\\\\\\\\ | -1.019 |
theless | -0.995 |
wonder | -0.988 |
livest | -0.953 |
Token | ell |
Token ID | 695 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.782 |
lasting | +0.773 |
theless | +0.759 |
wonder | +0.740 |
livest | +0.716 |
Neg logit contributions | |
oaded | -0.752 |
indal | -0.721 |
ornia | -0.701 |
atorial | -0.695 |
icion | -0.691 |
Token | " |
Token ID | 366 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.092 |
lasting | +1.078 |
theless | +1.056 |
wonder | +1.037 |
livest | +0.989 |
Neg logit contributions | |
oaded | -1.309 |
indal | -1.242 |
atorial | -1.219 |
ornia | -1.207 |
clusively | -1.198 |
Token | The |
Token ID | 464 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
oaded | +1.639 |
indal | +1.549 |
atorial | +1.516 |
clusively | +1.481 |
ornia | +1.479 |
Neg logit contributions | |
theless | -1.885 |
lasting | -1.882 |
\\\\\\\\\\\\\\\\ | -1.849 |
wonder | -1.834 |
livest | -1.795 |
Token | Inner |
Token ID | 24877 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
oaded | +1.150 |
indal | +1.098 |
atorial | +1.079 |
icion | +1.063 |
ornia | +1.062 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.907 |
theless | -0.892 |
lasting | -0.888 |
wonder | -0.857 |
livest | -0.835 |
Token | Game |
Token ID | 3776 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
oaded | +1.279 |
indal | +1.207 |
atorial | +1.185 |
ornia | +1.167 |
Moroc | +1.166 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.290 |
lasting | -1.286 |
theless | -1.252 |
wonder | -1.238 |
livest | -1.179 |
Token | of |
Token ID | 286 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
oaded | +1.736 |
indal | +1.671 |
atorial | +1.633 |
ornia | +1.617 |
clusively | +1.616 |
Neg logit contributions | |
theless | -1.399 |
\\\\\\\\\\\\\\\\ | -1.397 |
lasting | -1.371 |
wonder | -1.322 |
livest | -1.281 |
Token | Golf |
Token ID | 19709 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
oaded | +2.278 |
clusively | +2.171 |
atorial | +2.168 |
indal | +2.163 |
ornia | +2.129 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.037 |
theless | -1.958 |
lasting | -1.948 |
wonder | -1.894 |
livest | -1.861 |
Token | " |
Token ID | 1 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
oaded | +5.481 |
icion | +5.247 |
indal | +5.244 |
atorial | +5.186 |
ornia | +5.173 |
Neg logit contributions | |
theless | -5.335 |
\\\\\\\\\\\\\\\\ | -5.301 |
lasting | -5.087 |
livest | -5.043 |
wonder | -4.949 |
Token | by |
Token ID | 416 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
oaded | +1.591 |
indal | +1.512 |
atorial | +1.475 |
ornia | +1.464 |
clusively | +1.460 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.593 |
theless | -1.542 |
lasting | -1.531 |
wonder | -1.478 |
livest | -1.417 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
oaded | +0.084 |
indal | +0.079 |
atorial | +0.078 |
icion | +0.077 |
Moroc | +0.077 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.096 |
lasting | -0.094 |
theless | -0.092 |
wonder | -0.090 |
livest | -0.087 |
Token | Gall |
Token ID | 7096 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
oaded | +1.871 |
indal | +1.796 |
atorial | +1.755 |
icion | +1.741 |
ornia | +1.740 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.792 |
lasting | -1.778 |
theless | -1.724 |
wonder | -1.694 |
livest | -1.652 |
Token | we |
Token ID | 732 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
oaded | +1.771 |
indal | +1.718 |
atorial | +1.660 |
ornia | +1.650 |
swick | +1.613 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.946 |
theless | -1.860 |
lasting | -1.844 |
wonder | -1.790 |
livest | -1.777 |
Token | Broad |
Token ID | 9765 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.193 |
lasting | +0.188 |
theless | +0.186 |
quin | +0.176 |
wonder | +0.175 |
Neg logit contributions | |
oaded | -0.212 |
indal | -0.201 |
atorial | -0.196 |
icion | -0.196 |
ornia | -0.195 |
Token | band |
Token ID | 3903 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.018 |
lasting | +1.010 |
theless | +0.965 |
wonder | +0.964 |
livest | +0.923 |
Neg logit contributions | |
oaded | -1.247 |
indal | -1.190 |
ornia | -1.171 |
atorial | -1.160 |
icion | -1.148 |
Token | Connection |
Token ID | 26923 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
oaded | +0.133 |
indal | +0.127 |
atorial | +0.124 |
ornia | +0.124 |
icion | +0.122 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.131 |
lasting | -0.130 |
theless | -0.127 |
wonder | -0.126 |
livest | -0.120 |
Token | ( |
Token ID | 357 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
oaded | +2.547 |
indal | +2.438 |
atorial | +2.370 |
clusively | +2.362 |
icion | +2.340 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.023 |
lasting | -1.964 |
theless | -1.914 |
wonder | -1.845 |
ishable | -1.835 |
Token | Co |
Token ID | 7222 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.516 |
lasting | +0.514 |
theless | +0.496 |
wonder | +0.495 |
longer | +0.465 |
Neg logit contributions | |
oaded | -0.655 |
indal | -0.622 |
atorial | -0.609 |
ornia | -0.605 |
Moroc | -0.603 |
Token | ax |
Token ID | 897 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
oaded | +1.043 |
atorial | +0.948 |
indal | +0.936 |
ornia | +0.928 |
clusively | +0.906 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.558 |
theless | -2.528 |
lasting | -2.508 |
livest | -2.489 |
wonder | -2.423 |
Token | ) |
Token ID | 8 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
oaded | +5.302 |
indal | +4.952 |
atorial | +4.921 |
ornia | +4.872 |
clusively | +4.857 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.541 |
lasting | -5.448 |
theless | -5.327 |
wonder | -5.226 |
livest | -5.116 |
Token | should |
Token ID | 815 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
oaded | +0.477 |
indal | +0.454 |
atorial | +0.446 |
ornia | +0.441 |
clusively | +0.441 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.351 |
lasting | -0.340 |
theless | -0.333 |
wonder | -0.324 |
ishable | -0.312 |
Token | still |
Token ID | 991 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
oaded | +2.329 |
indal | +2.141 |
clusively | +2.111 |
atorial | +2.086 |
swick | +2.073 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.772 |
lasting | -2.672 |
theless | -2.656 |
quin | -2.527 |
wonder | -2.489 |
Token | show |
Token ID | 905 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.150 |
lasting | +1.125 |
theless | +1.104 |
wonder | +1.079 |
quin | +1.047 |
Neg logit contributions | |
oaded | -0.904 |
indal | -0.837 |
atorial | -0.818 |
clusively | -0.816 |
ornia | -0.811 |
Token | up |
Token ID | 510 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.776 |
lasting | +0.754 |
theless | +0.743 |
wonder | +0.725 |
quin | +0.694 |
Neg logit contributions | |
oaded | -0.984 |
indal | -0.925 |
atorial | -0.899 |
clusively | -0.899 |
ornia | -0.893 |
Token | AP |
Token ID | 3486 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
oaded | +1.404 |
indal | +1.344 |
atorial | +1.316 |
swick | +1.308 |
SON | +1.295 |
Neg logit contributions | |
lasting | -1.397 |
theless | -1.394 |
\\\\\\\\\\\\\\\\ | -1.379 |
wonder | -1.337 |
livest | -1.335 |
Token | AC |
Token ID | 2246 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
oaded | +1.981 |
indal | +1.882 |
atorial | +1.799 |
swick | +1.798 |
otle | +1.794 |
Neg logit contributions | |
theless | -2.586 |
lasting | -2.561 |
\\\\\\\\\\\\\\\\ | -2.523 |
wonder | -2.459 |
livest | -2.448 |
Token | HE |
Token ID | 13909 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
oaded | +2.777 |
SON | +2.557 |
indal | +2.533 |
atorial | +2.525 |
LIN | +2.480 |
Neg logit contributions | |
theless | -3.644 |
lasting | -3.602 |
livest | -3.521 |
\\\\\\\\\\\\\\\\ | -3.502 |
wonder | -3.461 |
Token | T |
Token ID | 309 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
oaded | +1.353 |
indal | +1.287 |
atorial | +1.252 |
swick | +1.247 |
Moroc | +1.239 |
Neg logit contributions | |
lasting | -1.301 |
\\\\\\\\\\\\\\\\ | -1.270 |
theless | -1.267 |
wonder | -1.238 |
livest | -1.231 |
Token | OC |
Token ID | 4503 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
oaded | +2.146 |
indal | +1.982 |
atorial | +1.906 |
ornia | +1.885 |
icion | +1.877 |
Neg logit contributions | |
theless | -3.212 |
lasting | -3.176 |
\\\\\\\\\\\\\\\\ | -3.174 |
wonder | -3.070 |
livest | -3.023 |
Token | AK |
Token ID | 15837 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
oaded | +2.659 |
indal | +2.521 |
atorial | +2.452 |
swick | +2.442 |
otle | +2.420 |
Neg logit contributions | |
lasting | -2.537 |
\\\\\\\\\\\\\\\\ | -2.518 |
theless | -2.506 |
wonder | -2.436 |
livest | -2.413 |
Token | NOW |
Token ID | 45669 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
oaded | +3.588 |
JUST | +3.444 |
SON | +3.441 |
ERAL | +3.276 |
LIN | +3.171 |
Neg logit contributions | |
livest | -7.133 |
theless | -6.915 |
lasting | -6.744 |
\\\\\\\\\\\\\\\\ | -6.654 |
phrine | -6.643 |
Token | LED |
Token ID | 30465 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
oaded | +1.863 |
indal | +1.641 |
SON | +1.551 |
swick | +1.539 |
atorial | +1.519 |
Neg logit contributions | |
livest | -3.594 |
theless | -3.519 |
lasting | -3.512 |
\\\\\\\\\\\\\\\\ | -3.482 |
wonder | -3.413 |
Token | G |
Token ID | 38 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
oaded | +1.903 |
SON | +1.815 |
atorial | +1.736 |
otle | +1.723 |
swick | +1.710 |
Neg logit contributions | |
livest | -4.356 |
theless | -4.265 |
lasting | -4.092 |
\\\\\\\\\\\\\\\\ | -4.027 |
wonder | -3.970 |
Token | ED |
Token ID | 1961 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
oaded | +4.213 |
SON | +3.828 |
nell | +3.765 |
indal | +3.751 |
ERAL | +3.730 |
Neg logit contributions | |
livest | -5.917 |
theless | -5.676 |
\\\\\\\\\\\\\\\\ | -5.491 |
lasting | -5.404 |
wonder | -5.212 |
Token | NET |
Token ID | 30502 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
oaded | +2.005 |
indal | +1.903 |
atorial | +1.873 |
swick | +1.848 |
clusively | +1.843 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.733 |
lasting | -1.724 |
theless | -1.684 |
wonder | -1.671 |
livest | -1.611 |
Token | cision |
Token ID | 16005 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.053 |
lasting | +1.049 |
wonder | +1.013 |
theless | +1.008 |
™: | +0.952 |
Neg logit contributions | |
oaded | -1.165 |
indal | -1.110 |
atorial | -1.093 |
icion | -1.081 |
ornia | -1.078 |
Token | finale |
Token ID | 19523 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
oaded | +0.342 |
indal | +0.329 |
atorial | +0.326 |
icion | +0.325 |
clusively | +0.323 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.305 |
lasting | -0.298 |
theless | -0.291 |
wonder | -0.284 |
livest | -0.274 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
oaded | +0.703 |
indal | +0.676 |
atorial | +0.670 |
icion | +0.670 |
clusively | +0.665 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.615 |
lasting | -0.599 |
theless | -0.589 |
wonder | -0.570 |
livest | -0.548 |
Token | . |
Token ID | 764 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
oaded | +1.451 |
indal | +1.399 |
atorial | +1.385 |
Moroc | +1.378 |
icion | +1.361 |
Neg logit contributions | |
lasting | -1.732 |
theless | -1.710 |
\\\\\\\\\\\\\\\\ | -1.708 |
wonder | -1.663 |
livest | -1.653 |
Token | En |
Token ID | 4834 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
oaded | +1.196 |
indal | +1.149 |
atorial | +1.128 |
Moroc | +1.119 |
icion | +1.108 |
Neg logit contributions | |
lasting | -1.423 |
\\\\\\\\\\\\\\\\ | -1.414 |
theless | -1.396 |
wonder | -1.369 |
livest | -1.331 |
Token | ag |
Token ID | 556 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
oaded | +1.298 |
indal | +1.236 |
clusively | +1.228 |
atorial | +1.218 |
icion | +1.218 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.063 |
lasting | -1.030 |
theless | -1.019 |
wonder | -0.989 |
™: | -0.953 |
Token | iss |
Token ID | 747 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
oaded | +4.816 |
icion | +4.714 |
iov | +4.545 |
indal | +4.544 |
atorial | +4.525 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -6.073 |
theless | -5.886 |
lasting | -5.808 |
wonder | -5.522 |
livest | -5.409 |
Token | ant |
Token ID | 415 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.647 |
lasting | +0.635 |
theless | +0.625 |
wonder | +0.605 |
livest | +0.576 |
Neg logit contributions | |
oaded | -0.944 |
indal | -0.911 |
atorial | -0.898 |
icion | -0.892 |
ornia | -0.882 |
Token | comm |
Token ID | 725 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
oaded | +0.449 |
indal | +0.427 |
atorial | +0.423 |
clusively | +0.420 |
icion | +0.419 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.391 |
lasting | -0.381 |
theless | -0.374 |
wonder | -0.365 |
livest | -0.348 |
Token | e |
Token ID | 68 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
oaded | +0.378 |
indal | +0.360 |
icion | +0.358 |
atorial | +0.354 |
ornia | +0.350 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.369 |
lasting | -0.368 |
theless | -0.353 |
wonder | -0.345 |
livest | -0.340 |
Token | il |
Token ID | 4229 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
oaded | +0.982 |
indal | +0.945 |
atorial | +0.939 |
icion | +0.936 |
clusively | +0.934 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.891 |
lasting | -0.864 |
theless | -0.850 |
wonder | -0.829 |
™: | -0.798 |
Token | Broad |
Token ID | 9765 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.970 |
lasting | +1.943 |
theless | +1.897 |
wonder | +1.868 |
quin | +1.775 |
Neg logit contributions | |
oaded | -2.137 |
indal | -2.027 |
atorial | -1.970 |
ornia | -1.955 |
icion | -1.948 |
Token | band |
Token ID | 3903 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.759 |
lasting | +1.749 |
theless | +1.689 |
wonder | +1.684 |
livest | +1.590 |
Neg logit contributions | |
oaded | -1.999 |
indal | -1.900 |
ornia | -1.859 |
atorial | -1.853 |
icion | -1.833 |
Token | Connection |
Token ID | 26923 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.383 |
lasting | +0.373 |
theless | +0.369 |
wonder | +0.363 |
livest | +0.345 |
Neg logit contributions | |
oaded | -0.414 |
indal | -0.397 |
ornia | -0.387 |
atorial | -0.385 |
clusively | -0.383 |
Token | ( |
Token ID | 357 |
Feature activation | +4.83e-05 |
Pos logit contributions | |
oaded | +1.657 |
indal | +1.592 |
clusively | +1.546 |
atorial | +1.528 |
ornia | +1.526 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.482 |
theless | -1.431 |
lasting | -1.424 |
wonder | -1.378 |
livest | -1.353 |
Token | Co |
Token ID | 7222 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
oaded | +0.000 |
indal | +0.000 |
atorial | +0.000 |
ornia | +0.000 |
clusively | +0.000 |
Neg logit contributions | |
lasting | -0.000 |
\\\\\\\\\\\\\\\\ | -0.000 |
theless | -0.000 |
wonder | -0.000 |
livest | -0.000 |
Token | ax |
Token ID | 897 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
oaded | +0.913 |
indal | +0.871 |
atorial | +0.867 |
ornia | +0.855 |
clusively | +0.849 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.895 |
theless | -0.878 |
lasting | -0.875 |
wonder | -0.844 |
livest | -0.818 |
Token | ) |
Token ID | 8 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
oaded | +4.742 |
atorial | +4.568 |
icion | +4.385 |
indal | +4.372 |
clusively | +4.367 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.820 |
theless | -5.673 |
lasting | -5.649 |
wonder | -5.442 |
livest | -5.407 |
Token | under |
Token ID | 739 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
oaded | +0.392 |
indal | +0.372 |
clusively | +0.362 |
atorial | +0.362 |
ornia | +0.362 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.339 |
lasting | -0.328 |
theless | -0.326 |
wonder | -0.317 |
livest | -0.305 |
Token | the |
Token ID | 262 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
lasting | +0.362 |
\\\\\\\\\\\\\\\\ | +0.361 |
theless | +0.353 |
wonder | +0.345 |
livest | +0.331 |
Neg logit contributions | |
oaded | -0.309 |
indal | -0.292 |
atorial | -0.285 |
ornia | -0.282 |
clusively | -0.280 |
Token | list |
Token ID | 1351 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.431 |
lasting | +0.429 |
theless | +0.422 |
wonder | +0.410 |
quin | +0.395 |
Neg logit contributions | |
oaded | -0.379 |
indal | -0.358 |
atorial | -0.353 |
ornia | -0.348 |
Moroc | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.879 |
lasting | +0.872 |
theless | +0.859 |
wonder | +0.836 |
livest | +0.791 |
Neg logit contributions | |
oaded | -1.320 |
indal | -1.254 |
atorial | -1.239 |
icion | -1.221 |
ornia | -1.219 |
Token | ar |
Token ID | 283 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
oaded | +2.926 |
indal | +2.886 |
atorial | +2.847 |
icion | +2.785 |
iov | +2.765 |
Neg logit contributions | |
theless | -3.085 |
\\\\\\\\\\\\\\\\ | -3.061 |
livest | -3.029 |
lasting | -2.935 |
wonder | -2.742 |
Token | of |
Token ID | 286 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
oaded | +0.985 |
indal | +0.938 |
atorial | +0.929 |
ornia | +0.899 |
icion | +0.898 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.794 |
lasting | -0.757 |
theless | -0.752 |
wonder | -0.732 |
livest | -0.700 |
Token | the |
Token ID | 262 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
oaded | +0.740 |
indal | +0.706 |
atorial | +0.682 |
ornia | +0.680 |
Moroc | +0.675 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.778 |
lasting | -0.759 |
theless | -0.739 |
wonder | -0.731 |
livest | -0.711 |
Token | A |
Token ID | 317 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
oaded | +0.863 |
indal | +0.829 |
atorial | +0.808 |
clusively | +0.790 |
Moroc | +0.788 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.912 |
lasting | -0.874 |
theless | -0.853 |
livest | -0.833 |
™: | -0.833 |
Token | am |
Token ID | 321 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
oaded | +1.808 |
indal | +1.775 |
icion | +1.718 |
atorial | +1.689 |
clusively | +1.666 |
Neg logit contributions | |
theless | -1.231 |
\\\\\\\\\\\\\\\\ | -1.205 |
lasting | -1.181 |
wonder | -1.147 |
livest | -1.118 |
Token | Aad |
Token ID | 38746 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
oaded | +0.803 |
indal | +0.766 |
atorial | +0.750 |
ornia | +0.747 |
clusively | +0.733 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.175 |
lasting | -1.153 |
theless | -1.140 |
wonder | -1.103 |
livest | -1.087 |
Token | mi |
Token ID | 11632 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ornia | +3.565 |
netic | +3.503 |
atorial | +3.494 |
iov | +3.471 |
icion | +3.373 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -6.814 |
theless | -6.621 |
lasting | -6.467 |
livest | -6.462 |
™: | -6.374 |
Token | Party |
Token ID | 3615 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
oaded | +0.543 |
indal | +0.529 |
atorial | +0.527 |
ornia | +0.524 |
Moroc | +0.510 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.413 |
theless | -0.402 |
lasting | -0.392 |
™: | -0.372 |
wonder | -0.367 |
Token | , |
Token ID | 11 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
oaded | +0.334 |
indal | +0.321 |
atorial | +0.316 |
ornia | +0.311 |
Moroc | +0.306 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.278 |
theless | -0.265 |
lasting | -0.264 |
wonder | -0.255 |
quin | -0.245 |
Token | arrested |
Token ID | 5169 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
oaded | +0.614 |
indal | +0.581 |
atorial | +0.577 |
ornia | +0.567 |
Moroc | +0.562 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.529 |
lasting | -0.503 |
theless | -0.500 |
wonder | -0.485 |
™: | -0.465 |
Token | this |
Token ID | 428 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
oaded | +2.475 |
indal | +2.305 |
ornia | +2.246 |
atorial | +2.240 |
clusively | +2.236 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.456 |
theless | -2.316 |
lasting | -2.247 |
livest | -2.236 |
wonder | -2.225 |
Token | _ |
Token ID | 62 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
oaded | +2.350 |
indal | +2.190 |
atorial | +2.181 |
ornia | +2.151 |
icion | +2.131 |
Neg logit contributions | |
lasting | -2.134 |
\\\\\\\\\\\\\\\\ | -2.123 |
theless | -2.100 |
wonder | -2.041 |
livest | -1.945 |
Token | speed |
Token ID | 12287 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
oaded | +3.155 |
indal | +2.953 |
atorial | +2.924 |
ornia | +2.916 |
iov | +2.879 |
Neg logit contributions | |
lasting | -3.084 |
\\\\\\\\\\\\\\\\ | -3.082 |
wonder | -2.949 |
theless | -2.939 |
livest | -2.830 |
Token | _ |
Token ID | 62 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
oaded | +0.940 |
indal | +0.874 |
ornia | +0.860 |
atorial | +0.860 |
icion | +0.859 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.784 |
lasting | -0.781 |
theless | -0.763 |
wonder | -0.746 |
livest | -0.716 |
Token | com |
Token ID | 785 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
oaded | +2.821 |
indal | +2.627 |
atorial | +2.613 |
ornia | +2.608 |
clusively | +2.600 |
Neg logit contributions | |
lasting | -2.801 |
\\\\\\\\\\\\\\\\ | -2.786 |
theless | -2.693 |
wonder | -2.668 |
livest | -2.588 |
Token | par |
Token ID | 1845 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
oaded | +2.761 |
indal | +2.569 |
atorial | +2.568 |
efficients | +2.562 |
clusively | +2.551 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.286 |
lasting | -2.252 |
theless | -2.137 |
wonder | -2.135 |
livest | -2.080 |
Token | ison |
Token ID | 1653 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
oaded | +3.394 |
atorial | +3.378 |
icion | +3.287 |
indal | +3.103 |
clusively | +3.037 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.543 |
lasting | -5.446 |
theless | -5.392 |
livest | -5.242 |
wonder | -5.234 |
Token | , |
Token ID | 11 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
oaded | +5.304 |
atorial | +4.957 |
clusively | +4.897 |
indal | +4.890 |
ornia | +4.857 |
Neg logit contributions | |
theless | -5.054 |
\\\\\\\\\\\\\\\\ | -4.987 |
lasting | -4.955 |
wonder | -4.725 |
livest | -4.720 |
Token | 0 |
Token ID | 657 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
oaded | +1.423 |
indal | +1.331 |
atorial | +1.326 |
clusively | +1.304 |
ornia | +1.296 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.335 |
lasting | -1.319 |
theless | -1.303 |
wonder | -1.260 |
™: | -1.223 |
Token | ) |
Token ID | 8 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
oaded | +1.263 |
indal | +1.193 |
ornia | +1.172 |
atorial | +1.167 |
clusively | +1.157 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.133 |
lasting | -1.131 |
theless | -1.125 |
wonder | -1.081 |
livest | -1.057 |
Token | RE |
Token ID | 4526 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
oaded | +0.917 |
indal | +0.856 |
atorial | +0.853 |
ornia | +0.832 |
clusively | +0.831 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.992 |
theless | -0.970 |
lasting | -0.966 |
wonder | -0.924 |
quin | -0.901 |
Token | F |
Token ID | 37 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.201 |
lasting | +2.198 |
theless | +2.157 |
wonder | +2.119 |
livest | +2.053 |
Neg logit contributions | |
oaded | -1.412 |
indal | -1.291 |
atorial | -1.257 |
ornia | -1.251 |
clusively | -1.248 |
Token | the |
Token ID | 262 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
oaded | +0.483 |
indal | +0.462 |
atorial | +0.453 |
ornia | +0.444 |
Moroc | +0.443 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.433 |
theless | -0.424 |
lasting | -0.420 |
wonder | -0.409 |
™: | -0.395 |
Token | book |
Token ID | 1492 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
oaded | +0.788 |
indal | +0.764 |
atorial | +0.756 |
ornia | +0.731 |
clusively | +0.726 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.695 |
theless | -0.656 |
lasting | -0.653 |
wonder | -0.628 |
™: | -0.623 |
Token | he |
Token ID | 339 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.297 |
lasting | +1.279 |
theless | +1.251 |
wonder | +1.237 |
livest | +1.180 |
Neg logit contributions | |
oaded | -1.623 |
indal | -1.538 |
atorial | -1.515 |
ornia | -1.496 |
Moroc | -1.489 |
Token | learned |
Token ID | 4499 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.225 |
theless | +0.215 |
lasting | +0.210 |
livest | +0.202 |
ishable | +0.198 |
Neg logit contributions | |
oaded | -0.333 |
atorial | -0.316 |
ornia | -0.308 |
indal | -0.308 |
icion | -0.307 |
Token | that |
Token ID | 326 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
oaded | +0.799 |
indal | +0.757 |
atorial | +0.746 |
icion | +0.743 |
ornia | +0.736 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.577 |
lasting | -0.549 |
theless | -0.548 |
wonder | -0.523 |
livest | -0.518 |
Token | Georg |
Token ID | 6850 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
oaded | +0.865 |
indal | +0.818 |
atorial | +0.801 |
ornia | +0.800 |
icion | +0.795 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.819 |
theless | -0.788 |
lasting | -0.786 |
wonder | -0.758 |
livest | -0.737 |
Token | es |
Token ID | 274 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
oaded | +4.575 |
atorial | +4.364 |
indal | +4.348 |
otle | +4.183 |
ornia | +4.182 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.683 |
lasting | -5.628 |
theless | -5.605 |
wonder | -5.387 |
livest | -5.310 |
Token | Mé |
Token ID | 43579 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.665 |
lasting | +0.660 |
theless | +0.657 |
wonder | +0.631 |
livest | +0.617 |
Neg logit contributions | |
oaded | -0.653 |
indal | -0.631 |
atorial | -0.613 |
Moroc | -0.606 |
icion | -0.596 |
Token | li |
Token ID | 4528 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
oaded | +0.091 |
indal | +0.089 |
netic | +0.086 |
atorial | +0.085 |
icion | +0.083 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.152 |
theless | -0.151 |
lasting | -0.145 |
wonder | -0.144 |
™: | -0.143 |
Token | è |
Token ID | 14064 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
oaded | +0.591 |
indal | +0.590 |
atorial | +0.562 |
otle | +0.542 |
ornia | +0.539 |
Neg logit contributions | |
theless | -0.758 |
\\\\\\\\\\\\\\\\ | -0.738 |
wonder | -0.711 |
lasting | -0.709 |
longer | -0.692 |
Token | s |
Token ID | 82 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.816 |
lasting | +0.775 |
theless | +0.773 |
wonder | +0.764 |
livest | +0.760 |
Neg logit contributions | |
oaded | -0.445 |
indal | -0.438 |
atorial | -0.416 |
clusively | -0.410 |
swick | -0.408 |
Token | also |
Token ID | 635 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.476 |
lasting | +0.437 |
theless | +0.433 |
™: | +0.419 |
wonder | +0.418 |
Neg logit contributions | |
oaded | -0.616 |
indal | -0.582 |
atorial | -0.576 |
clusively | -0.574 |
ornia | -0.572 |
Token | referred |
Token ID | 6412 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
oaded | +0.343 |
indal | +0.321 |
atorial | +0.321 |
clusively | +0.320 |
ornia | +0.317 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.273 |
lasting | -0.248 |
theless | -0.247 |
quin | -0.239 |
livest | -0.239 |
Token | to |
Token ID | 284 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
oaded | +0.839 |
indal | +0.794 |
atorial | +0.778 |
clusively | +0.769 |
ornia | +0.768 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.750 |
lasting | -0.721 |
theless | -0.716 |
wonder | -0.694 |
livest | -0.676 |
Token | a |
Token ID | 257 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.596 |
lasting | +0.578 |
theless | +0.569 |
wonder | +0.557 |
™: | +0.542 |
Neg logit contributions | |
oaded | -0.614 |
indal | -0.583 |
atorial | -0.571 |
ornia | -0.563 |
clusively | -0.560 |
Token | C |
Token ID | 327 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.685 |
lasting | +0.660 |
theless | +0.659 |
wonder | +0.635 |
™: | +0.630 |
Neg logit contributions | |
oaded | -0.758 |
indal | -0.725 |
atorial | -0.710 |
ornia | -0.698 |
Moroc | -0.694 |
Token | AG |
Token ID | 4760 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
oaded | +2.281 |
indal | +2.176 |
ornia | +2.117 |
atorial | +2.098 |
icion | +2.079 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.590 |
lasting | -2.571 |
theless | -2.530 |
wonder | -2.460 |
™: | -2.383 |
Token | report |
Token ID | 989 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
oaded | +5.537 |
indal | +5.320 |
atorial | +5.225 |
ornia | +5.156 |
Moroc | +5.054 |
Neg logit contributions | |
theless | -4.812 |
\\\\\\\\\\\\\\\\ | -4.650 |
lasting | -4.469 |
™: | -4.255 |
wonder | -4.253 |
Token | which |
Token ID | 543 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.256 |
theless | +0.245 |
lasting | +0.240 |
wonder | +0.235 |
livest | +0.229 |
Neg logit contributions | |
oaded | -0.325 |
indal | -0.314 |
atorial | -0.309 |
ornia | -0.304 |
clusively | -0.302 |
Token | stated |
Token ID | 5081 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
oaded | +0.254 |
indal | +0.244 |
ornia | +0.242 |
atorial | +0.239 |
clusively | +0.239 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.176 |
lasting | -0.168 |
theless | -0.166 |
wonder | -0.159 |
™: | -0.157 |
Token | that |
Token ID | 326 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
oaded | +0.945 |
indal | +0.897 |
atorial | +0.880 |
ornia | +0.870 |
clusively | +0.866 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.768 |
lasting | -0.746 |
theless | -0.739 |
wonder | -0.718 |
livest | -0.692 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
oaded | +1.208 |
indal | +1.150 |
atorial | +1.122 |
ornia | +1.112 |
Moroc | +1.103 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.143 |
theless | -1.099 |
lasting | -1.089 |
wonder | -1.063 |
™: | -1.037 |
Token | , |
Token ID | 11 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
oaded | +0.070 |
indal | +0.067 |
atorial | +0.067 |
icion | +0.066 |
Moroc | +0.066 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.063 |
lasting | -0.062 |
theless | -0.060 |
wonder | -0.059 |
™: | -0.056 |
Token | le |
Token ID | 443 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.422 |
lasting | +0.414 |
theless | +0.406 |
wonder | +0.399 |
™: | +0.379 |
Neg logit contributions | |
oaded | -0.478 |
indal | -0.454 |
atorial | -0.448 |
Moroc | -0.445 |
clusively | -0.443 |
Token | Command |
Token ID | 9455 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.439 |
lasting | +1.417 |
theless | +1.385 |
wonder | +1.353 |
™: | +1.298 |
Neg logit contributions | |
oaded | -1.790 |
indal | -1.690 |
atorial | -1.665 |
ornia | -1.661 |
Moroc | -1.654 |
Token | ement |
Token ID | 972 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
oaded | +1.268 |
indal | +1.205 |
atorial | +1.203 |
icion | +1.171 |
ornia | +1.164 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.842 |
lasting | -1.796 |
theless | -1.774 |
wonder | -1.749 |
livest | -1.717 |
Token | a |
Token ID | 257 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.065 |
lasting | +0.064 |
theless | +0.063 |
wonder | +0.062 |
livest | +0.059 |
Neg logit contributions | |
oaded | -0.058 |
indal | -0.055 |
atorial | -0.054 |
Moroc | -0.054 |
ornia | -0.053 |
Token | ag |
Token ID | 556 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.120 |
theless | +0.117 |
lasting | +0.117 |
wonder | +0.114 |
livest | +0.109 |
Neg logit contributions | |
oaded | -0.080 |
indal | -0.075 |
atorial | -0.074 |
icion | -0.074 |
Moroc | -0.073 |
Token | i |
Token ID | 72 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
oaded | +4.892 |
icion | +4.801 |
atorial | +4.685 |
indal | +4.640 |
iov | +4.594 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.657 |
theless | -5.527 |
lasting | -5.374 |
wonder | -5.189 |
livest | -5.109 |
Token | comm |
Token ID | 725 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
oaded | +0.594 |
atorial | +0.570 |
indal | +0.568 |
ornia | +0.560 |
icion | +0.557 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.542 |
theless | -0.526 |
lasting | -0.523 |
wonder | -0.499 |
™: | -0.480 |
Token | e |
Token ID | 68 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
oaded | +0.253 |
indal | +0.241 |
icion | +0.239 |
atorial | +0.238 |
ornia | +0.236 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.245 |
lasting | -0.242 |
theless | -0.234 |
wonder | -0.228 |
livest | -0.224 |
Token | la |
Token ID | 8591 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
oaded | +0.885 |
indal | +0.855 |
atorial | +0.848 |
icion | +0.846 |
clusively | +0.840 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.794 |
lasting | -0.766 |
theless | -0.757 |
wonder | -0.735 |
™: | -0.710 |
Token | chart |
Token ID | 8262 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
oaded | +0.014 |
indal | +0.013 |
atorial | +0.013 |
icion | +0.013 |
ornia | +0.013 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.011 |
lasting | -0.011 |
theless | -0.011 |
wonder | -0.011 |
™: | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
oaded | +0.305 |
indal | +0.290 |
atorial | +0.282 |
icion | +0.282 |
ornia | +0.279 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.288 |
theless | -0.282 |
lasting | -0.279 |
wonder | -0.274 |
livest | -0.264 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.045 |
theless | +0.043 |
lasting | +0.043 |
wonder | +0.041 |
™: | +0.040 |
Neg logit contributions | |
oaded | -0.059 |
indal | -0.057 |
atorial | -0.056 |
clusively | -0.055 |
icion | -0.054 |
Token | that |
Token ID | 326 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
oaded | +0.757 |
indal | +0.723 |
atorial | +0.701 |
icion | +0.698 |
ornia | +0.692 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.701 |
theless | -0.686 |
lasting | -0.685 |
wonder | -0.668 |
livest | -0.649 |
Token | bas |
Token ID | 1615 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
oaded | +0.970 |
indal | +0.925 |
icion | +0.901 |
ornia | +0.899 |
atorial | +0.897 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.942 |
theless | -0.924 |
lasting | -0.916 |
wonder | -0.902 |
livest | -0.875 |
Token | ing |
Token ID | 278 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
oaded | +1.923 |
atorial | +1.879 |
indal | +1.832 |
clusively | +1.812 |
icion | +1.802 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.993 |
lasting | -1.959 |
theless | -1.934 |
wonder | -1.928 |
livest | -1.836 |
Token | fiscal |
Token ID | 9068 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
oaded | +0.419 |
indal | +0.401 |
atorial | +0.397 |
clusively | +0.391 |
ornia | +0.389 |
Neg logit contributions | |
theless | -0.427 |
\\\\\\\\\\\\\\\\ | -0.426 |
lasting | -0.413 |
wonder | -0.405 |
livest | -0.399 |
Token | policy |
Token ID | 2450 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
oaded | +4.090 |
ornia | +4.043 |
atorial | +3.965 |
indal | +3.950 |
clusively | +3.799 |
Neg logit contributions | |
theless | -5.827 |
\\\\\\\\\\\\\\\\ | -5.786 |
livest | -5.564 |
lasting | -5.521 |
hm | -5.431 |
Token | on |
Token ID | 319 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
oaded | +2.027 |
indal | +1.984 |
atorial | +1.962 |
ornia | +1.920 |
clusively | +1.914 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.013 |
theless | -2.009 |
wonder | -1.941 |
lasting | -1.939 |
livest | -1.875 |
Token | a |
Token ID | 257 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.068 |
theless | +0.067 |
lasting | +0.066 |
wonder | +0.064 |
livest | +0.062 |
Neg logit contributions | |
oaded | -0.074 |
indal | -0.070 |
clusively | -0.069 |
atorial | -0.068 |
ornia | -0.068 |
Token | growth |
Token ID | 3349 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
oaded | +0.373 |
indal | +0.360 |
clusively | +0.354 |
atorial | +0.351 |
ornia | +0.350 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.291 |
theless | -0.287 |
lasting | -0.279 |
wonder | -0.273 |
™: | -0.266 |
Token | figure |
Token ID | 3785 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
oaded | +2.050 |
indal | +1.958 |
atorial | +1.945 |
ornia | +1.929 |
icion | +1.909 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.089 |
theless | -2.062 |
lasting | -2.020 |
wonder | -1.946 |
livest | -1.932 |
Token | links |
Token ID | 6117 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.485 |
theless | +0.462 |
lasting | +0.454 |
wonder | +0.440 |
quin | +0.436 |
Neg logit contributions | |
oaded | -0.525 |
indal | -0.499 |
atorial | -0.492 |
icion | -0.484 |
clusively | -0.484 |
Token | of |
Token ID | 286 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
oaded | +1.046 |
indal | +0.975 |
atorial | +0.971 |
clusively | +0.946 |
icion | +0.945 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.840 |
theless | -0.796 |
lasting | -0.774 |
wonder | -0.758 |
livest | -0.750 |
Token | conversations |
Token ID | 10275 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
oaded | +0.800 |
indal | +0.751 |
atorial | +0.736 |
clusively | +0.735 |
icion | +0.731 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.741 |
theless | -0.716 |
lasting | -0.697 |
wonder | -0.673 |
quin | -0.669 |
Token | that |
Token ID | 326 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
oaded | +0.521 |
atorial | +0.490 |
clusively | +0.480 |
indal | +0.479 |
icion | +0.472 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.518 |
theless | -0.496 |
wonder | -0.467 |
lasting | -0.465 |
livest | -0.465 |
Token | say |
Token ID | 910 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.331 |
theless | +0.317 |
lasting | +0.313 |
wonder | +0.300 |
™: | +0.299 |
Neg logit contributions | |
oaded | -0.358 |
indal | -0.336 |
clusively | -0.333 |
icion | -0.331 |
atorial | -0.328 |
Token | otherwise |
Token ID | 4306 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
oaded | +1.800 |
indal | +1.685 |
atorial | +1.632 |
ornia | +1.630 |
clusively | +1.628 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.619 |
theless | -1.586 |
lasting | -1.560 |
wonder | -1.487 |
livest | -1.483 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
oaded | +5.126 |
indal | +4.770 |
clusively | +4.699 |
atorial | +4.646 |
ornia | +4.592 |
Neg logit contributions | |
theless | -4.862 |
\\\\\\\\\\\\\\\\ | -4.843 |
lasting | -4.703 |
livest | -4.586 |
wonder | -4.519 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
oaded | +0.719 |
atorial | +0.681 |
indal | +0.681 |
swick | +0.669 |
icion | +0.660 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.902 |
lasting | -0.893 |
theless | -0.890 |
livest | -0.882 |
wonder | -0.855 |
Token |
|
Token ID | 198 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
oaded | +0.022 |
atorial | +0.021 |
indal | +0.021 |
icion | +0.020 |
clusively | +0.020 |
Neg logit contributions | |
livest | -0.031 |
theless | -0.031 |
\\\\\\\\\\\\\\\\ | -0.031 |
lasting | -0.030 |
wonder | -0.029 |
Token | The |
Token ID | 464 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
oaded | +0.081 |
indal | +0.076 |
atorial | +0.075 |
icion | +0.074 |
clusively | +0.073 |
Neg logit contributions | |
lasting | -0.115 |
theless | -0.114 |
\\\\\\\\\\\\\\\\ | -0.111 |
livest | -0.110 |
wonder | -0.110 |
Token | ONE |
Token ID | 16329 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.294 |
theless | +0.283 |
lasting | +0.281 |
wonder | +0.270 |
™: | +0.267 |
Neg logit contributions | |
oaded | -0.320 |
indal | -0.300 |
atorial | -0.297 |
icion | -0.295 |
clusively | -0.293 |
Token | if |
Token ID | 611 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.941 |
theless | +0.886 |
lasting | +0.886 |
livest | +0.844 |
wonder | +0.842 |
Neg logit contributions | |
oaded | -1.421 |
indal | -1.352 |
atorial | -1.336 |
clusively | -1.325 |
ornia | -1.310 |
Token | congressional |
Token ID | 11702 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
oaded | +0.785 |
indal | +0.751 |
clusively | +0.722 |
atorial | +0.719 |
icion | +0.708 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.822 |
theless | -0.796 |
lasting | -0.784 |
wonder | -0.759 |
livest | -0.753 |
Token | Democrats |
Token ID | 4956 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
oaded | +0.713 |
indal | +0.671 |
atorial | +0.664 |
ornia | +0.657 |
clusively | +0.654 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.923 |
theless | -0.893 |
lasting | -0.875 |
livest | -0.857 |
™: | -0.840 |
Token | and |
Token ID | 290 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
oaded | +1.153 |
atorial | +1.108 |
indal | +1.101 |
swick | +1.066 |
clusively | +1.061 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.926 |
theless | -0.836 |
lasting | -0.833 |
™: | -0.810 |
ishable | -0.801 |
Token | their |
Token ID | 511 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.338 |
theless | +1.301 |
lasting | +1.290 |
wonder | +1.240 |
livest | +1.225 |
Neg logit contributions | |
oaded | -1.283 |
indal | -1.219 |
atorial | -1.184 |
icion | -1.176 |
ornia | -1.175 |
Token | allied |
Token ID | 22034 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
oaded | +0.405 |
indal | +0.382 |
atorial | +0.374 |
ornia | +0.365 |
icion | +0.364 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.608 |
theless | -0.588 |
lasting | -0.571 |
livest | -0.561 |
wonder | -0.556 |
Token | committees |
Token ID | 17460 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
oaded | +4.580 |
indal | +4.458 |
atorial | +4.416 |
icion | +4.301 |
ornia | +4.282 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.526 |
theless | -5.326 |
lasting | -5.078 |
livest | -5.033 |
™: | -4.933 |
Token | can |
Token ID | 460 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.171 |
lasting | +1.097 |
theless | +1.085 |
wonder | +1.038 |
™: | +1.028 |
Neg logit contributions | |
oaded | -1.585 |
indal | -1.509 |
atorial | -1.502 |
icion | -1.460 |
clusively | -1.456 |
Token | do |
Token ID | 466 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
oaded | +2.797 |
atorial | +2.743 |
clusively | +2.737 |
indal | +2.675 |
icion | +2.573 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.650 |
theless | -2.536 |
lasting | -2.439 |
quin | -2.378 |
livest | -2.360 |
Token | the |
Token ID | 262 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
oaded | +2.597 |
indal | +2.492 |
atorial | +2.485 |
clusively | +2.478 |
icion | +2.392 |
Neg logit contributions | |
theless | -2.205 |
\\\\\\\\\\\\\\\\ | -2.176 |
livest | -2.077 |
wonder | -1.994 |
™: | -1.968 |
Token | same |
Token ID | 976 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
oaded | +0.104 |
indal | +0.099 |
atorial | +0.098 |
clusively | +0.097 |
ornia | +0.096 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.117 |
theless | -0.115 |
lasting | -0.111 |
livest | -0.109 |
wonder | -0.109 |
Token | a |
Token ID | 64 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
oaded | +2.387 |
indal | +2.303 |
atorial | +2.232 |
icion | +2.221 |
ornia | +2.202 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.995 |
lasting | -1.972 |
theless | -1.927 |
wonder | -1.885 |
livest | -1.822 |
Token | l |
Token ID | 300 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
oaded | +0.741 |
indal | +0.707 |
atorial | +0.688 |
icion | +0.684 |
ornia | +0.682 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.657 |
lasting | -0.646 |
theless | -0.637 |
wonder | -0.619 |
livest | -0.600 |
Token | ah |
Token ID | 993 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
oaded | +1.038 |
indal | +0.983 |
atorial | +0.951 |
ornia | +0.939 |
icion | +0.933 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.190 |
lasting | -1.179 |
theless | -1.145 |
wonder | -1.128 |
livest | -1.103 |
Token | at |
Token ID | 265 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
oaded | +0.763 |
indal | +0.723 |
atorial | +0.692 |
ornia | +0.689 |
icion | +0.672 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.202 |
lasting | -1.194 |
theless | -1.173 |
wonder | -1.147 |
livest | -1.143 |
Token | ng |
Token ID | 23370 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
oaded | +2.400 |
indal | +2.301 |
atorial | +2.231 |
icion | +2.221 |
ornia | +2.214 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.164 |
lasting | -2.110 |
theless | -2.098 |
wonder | -2.009 |
livest | -1.986 |
Token | gin |
Token ID | 39733 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
oaded | +2.248 |
indal | +2.162 |
atorial | +2.106 |
ornia | +2.073 |
icion | +2.073 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.864 |
theless | -1.811 |
lasting | -1.803 |
wonder | -1.724 |
™: | -1.689 |
Token | ag |
Token ID | 363 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
oaded | +4.608 |
atorial | +4.421 |
indal | +4.305 |
clusively | +4.119 |
icion | +4.105 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -5.731 |
lasting | -5.638 |
theless | -5.571 |
livest | -5.367 |
™: | -5.315 |
Token | awa |
Token ID | 6909 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
oaded | +3.659 |
indal | +3.427 |
atorial | +3.378 |
ornia | +3.342 |
clusively | +3.241 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -4.667 |
lasting | -4.531 |
theless | -4.438 |
livest | -4.342 |
wonder | -4.328 |
Token | n |
Token ID | 299 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
oaded | +0.730 |
indal | +0.701 |
atorial | +0.683 |
icion | +0.674 |
ornia | +0.669 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.633 |
lasting | -0.614 |
theless | -0.611 |
wonder | -0.592 |
livest | -0.573 |
Token | atin |
Token ID | 10680 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
oaded | +1.234 |
indal | +1.166 |
atorial | +1.155 |
ornia | +1.115 |
icion | +1.100 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.635 |
lasting | -1.614 |
theless | -1.598 |
wonder | -1.537 |
livest | -1.535 |
Token | ay |
Token ID | 38762 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
oaded | +2.558 |
indal | +2.448 |
atorial | +2.411 |
icion | +2.366 |
ornia | +2.343 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.275 |
theless | -2.207 |
lasting | -2.195 |
wonder | -2.114 |
livest | -2.086 |
Token | BLACK |
Token ID | 31963 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.138 |
lasting | +0.136 |
theless | +0.132 |
wonder | +0.131 |
livest | +0.127 |
Neg logit contributions | |
oaded | -0.149 |
indal | -0.142 |
atorial | -0.140 |
swick | -0.138 |
Moroc | -0.138 |
Token | FO |
Token ID | 6080 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
oaded | +0.323 |
indal | +0.300 |
atorial | +0.291 |
Moroc | +0.287 |
ornia | +0.287 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.500 |
lasting | -0.500 |
theless | -0.488 |
wonder | -0.486 |
livest | -0.465 |
Token | OT |
Token ID | 2394 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
theless | +0.036 |
lasting | +0.035 |
livest | +0.035 |
\\\\\\\\\\\\\\\\ | +0.035 |
wonder | +0.034 |
Neg logit contributions | |
oaded | -0.046 |
indal | -0.043 |
otle | -0.042 |
atorial | -0.042 |
icion | -0.042 |
Token | T |
Token ID | 309 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
oaded | +2.072 |
indal | +1.935 |
atorial | +1.888 |
Moroc | +1.865 |
clusively | +1.860 |
Neg logit contributions | |
lasting | -2.318 |
\\\\\\\\\\\\\\\\ | -2.308 |
theless | -2.263 |
wonder | -2.207 |
livest | -2.169 |
Token | OC |
Token ID | 4503 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
oaded | +1.587 |
indal | +1.412 |
atorial | +1.387 |
icion | +1.350 |
swick | +1.339 |
Neg logit contributions | |
theless | -2.908 |
livest | -2.777 |
lasting | -2.754 |
\\\\\\\\\\\\\\\\ | -2.749 |
wonder | -2.671 |
Token | AK |
Token ID | 15837 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
oaded | +3.022 |
indal | +2.866 |
atorial | +2.825 |
SON | +2.810 |
swick | +2.788 |
Neg logit contributions | |
lasting | -2.559 |
\\\\\\\\\\\\\\\\ | -2.540 |
theless | -2.536 |
wonder | -2.430 |
livest | -2.423 |
Token | NOW |
Token ID | 45669 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
oaded | +4.873 |
indal | +4.449 |
atorial | +4.338 |
SON | +4.319 |
clusively | +4.282 |
Neg logit contributions | |
lasting | -5.159 |
\\\\\\\\\\\\\\\\ | -5.152 |
theless | -5.133 |
wonder | -4.969 |
livest | -4.884 |
Token | LED |
Token ID | 30465 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
oaded | +1.653 |
indal | +1.445 |
SON | +1.388 |
ornia | +1.363 |
LIN | +1.349 |
Neg logit contributions | |
livest | -3.130 |
theless | -3.117 |
lasting | -3.115 |
\\\\\\\\\\\\\\\\ | -3.106 |
wonder | -3.006 |
Token | G |
Token ID | 38 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
oaded | +1.713 |
SON | +1.604 |
atorial | +1.545 |
otle | +1.530 |
indal | +1.521 |
Neg logit contributions | |
livest | -3.658 |
theless | -3.614 |
lasting | -3.494 |
\\\\\\\\\\\\\\\\ | -3.440 |
wonder | -3.383 |
Token | ED |
Token ID | 1961 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
oaded | +4.065 |
SON | +3.713 |
indal | +3.619 |
nell | +3.606 |
ERAL | +3.573 |
Neg logit contributions | |
livest | -5.466 |
theless | -5.350 |
\\\\\\\\\\\\\\\\ | -5.241 |
lasting | -5.150 |
wonder | -4.946 |
Token | NET |
Token ID | 30502 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
oaded | +1.917 |
indal | +1.828 |
atorial | +1.789 |
swick | +1.778 |
clusively | +1.776 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.783 |
lasting | -1.755 |
theless | -1.737 |
wonder | -1.711 |
livest | -1.674 |
Token | RANT |
Token ID | 32506 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
oaded | +2.989 |
indal | +2.778 |
atorial | +2.775 |
Moroc | +2.622 |
clusively | +2.617 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -4.536 |
theless | -4.486 |
lasting | -4.411 |
wonder | -4.360 |
quin | -4.280 |
Token | food |
Token ID | 2057 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.601 |
lasting | +0.599 |
theless | +0.595 |
wonder | +0.567 |
livest | +0.549 |
Neg logit contributions | |
oaded | -0.692 |
indal | -0.653 |
ornia | -0.638 |
atorial | -0.636 |
icion | -0.634 |
Token | from |
Token ID | 422 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
oaded | +1.201 |
indal | +1.143 |
ornia | +1.130 |
atorial | +1.130 |
icion | +1.106 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.885 |
theless | -0.881 |
lasting | -0.864 |
wonder | -0.814 |
livest | -0.797 |
Token | a |
Token ID | 257 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
oaded | +0.630 |
indal | +0.602 |
ornia | +0.591 |
atorial | +0.581 |
Moroc | +0.581 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.576 |
theless | -0.569 |
lasting | -0.569 |
wonder | -0.539 |
quin | -0.526 |
Token | good |
Token ID | 922 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
oaded | +0.136 |
indal | +0.130 |
atorial | +0.127 |
ornia | +0.127 |
clusively | +0.126 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.122 |
lasting | -0.120 |
theless | -0.119 |
wonder | -0.114 |
™: | -0.111 |
Token | Christian |
Token ID | 4302 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
oaded | +2.592 |
indal | +2.455 |
clusively | +2.443 |
ornia | +2.424 |
atorial | +2.411 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.584 |
theless | -2.553 |
lasting | -2.522 |
™: | -2.405 |
wonder | -2.395 |
Token | ! |
Token ID | 0 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
oaded | +5.329 |
indal | +5.100 |
otle | +4.952 |
clusively | +4.922 |
ornia | +4.910 |
Neg logit contributions | |
theless | -4.518 |
\\\\\\\\\\\\\\\\ | -4.431 |
lasting | -4.385 |
livest | -4.096 |
wonder | -4.046 |
Token | � |
Token ID | 447 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
oaded | +0.935 |
indal | +0.897 |
atorial | +0.882 |
ornia | +0.876 |
Moroc | +0.874 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.434 |
lasting | -0.433 |
theless | -0.412 |
wonder | -0.408 |
livest | -0.375 |
Token | � |
Token ID | 251 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
oaded | +0.886 |
ornia | +0.828 |
indal | +0.825 |
atorial | +0.821 |
icion | +0.812 |
Neg logit contributions | |
theless | -1.020 |
\\\\\\\\\\\\\\\\ | -0.995 |
lasting | -0.963 |
livest | -0.951 |
wonder | -0.936 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
oaded | +1.038 |
indal | +0.968 |
atorial | +0.964 |
swick | +0.939 |
icion | +0.937 |
Neg logit contributions | |
theless | -1.421 |
livest | -1.408 |
lasting | -1.392 |
\\\\\\\\\\\\\\\\ | -1.377 |
wonder | -1.338 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
oaded | +0.408 |
atorial | +0.391 |
indal | +0.387 |
icion | +0.376 |
clusively | +0.373 |
Neg logit contributions | |
livest | -0.605 |
theless | -0.595 |
\\\\\\\\\\\\\\\\ | -0.592 |
lasting | -0.576 |
wonder | -0.554 |
Token | Baker |
Token ID | 14372 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
oaded | +0.347 |
indal | +0.327 |
atorial | +0.321 |
ornia | +0.317 |
icion | +0.316 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.351 |
lasting | -0.351 |
theless | -0.344 |
wonder | -0.336 |
livest | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.609 |
theless | +0.597 |
lasting | +0.591 |
wonder | +0.574 |
livest | +0.550 |
Neg logit contributions | |
oaded | -0.825 |
indal | -0.786 |
atorial | -0.774 |
ornia | -0.770 |
icion | -0.757 |
Token | K |
Token ID | 509 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.683 |
lasting | +0.659 |
theless | +0.655 |
wonder | +0.634 |
™: | +0.614 |
Neg logit contributions | |
oaded | -0.801 |
indal | -0.763 |
ornia | -0.744 |
atorial | -0.743 |
Moroc | -0.742 |
Token | ed |
Token ID | 276 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
oaded | +0.896 |
indal | +0.843 |
atorial | +0.830 |
ornia | +0.825 |
icion | +0.807 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.958 |
lasting | -0.946 |
theless | -0.931 |
wonder | -0.909 |
livest | -0.881 |
Token | ric |
Token ID | 1173 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
oaded | +0.696 |
indal | +0.669 |
atorial | +0.643 |
ornia | +0.639 |
icion | +0.622 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.505 |
lasting | -1.503 |
theless | -1.495 |
wonder | -1.461 |
livest | -1.423 |
Token | Gol |
Token ID | 26849 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
oaded | +0.543 |
indal | +0.504 |
atorial | +0.493 |
ornia | +0.490 |
Moroc | +0.482 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.945 |
lasting | -0.937 |
theless | -0.924 |
wonder | -0.910 |
livest | -0.883 |
Token | ston |
Token ID | 3743 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
oaded | +3.109 |
indal | +2.967 |
ornia | +2.753 |
icion | +2.705 |
nell | +2.637 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -7.061 |
livest | -7.040 |
lasting | -6.866 |
wonder | -6.812 |
theless | -6.720 |
Token | and |
Token ID | 290 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
oaded | +0.569 |
indal | +0.542 |
atorial | +0.534 |
ornia | +0.530 |
Moroc | +0.527 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.373 |
lasting | -0.370 |
theless | -0.360 |
wonder | -0.355 |
livest | -0.333 |
Token | Kendall |
Token ID | 36779 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
oaded | +0.139 |
indal | +0.131 |
atorial | +0.128 |
ornia | +0.128 |
Moroc | +0.127 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.148 |
lasting | -0.143 |
theless | -0.142 |
wonder | -0.137 |
™: | -0.134 |
Token | Reyes |
Token ID | 40599 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.265 |
lasting | +0.262 |
theless | +0.258 |
wonder | +0.254 |
livest | +0.245 |
Neg logit contributions | |
oaded | -0.236 |
indal | -0.221 |
atorial | -0.220 |
ornia | -0.218 |
clusively | -0.218 |
Token | as |
Token ID | 355 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.233 |
theless | +0.229 |
lasting | +0.228 |
wonder | +0.220 |
livest | +0.213 |
Neg logit contributions | |
oaded | -0.292 |
indal | -0.279 |
atorial | -0.272 |
ornia | -0.269 |
icion | -0.268 |
Token | India |
Token ID | 3794 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
oaded | +1.547 |
indal | +1.523 |
atorial | +1.483 |
clusively | +1.458 |
icion | +1.449 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.690 |
lasting | -1.565 |
theless | -1.553 |
wonder | -1.488 |
quin | -1.479 |
Token | captain |
Token ID | 10654 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.718 |
lasting | +2.663 |
theless | +2.603 |
wonder | +2.558 |
quin | +2.454 |
Neg logit contributions | |
oaded | -2.698 |
indal | -2.577 |
atorial | -2.524 |
ornia | -2.493 |
icion | -2.484 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.755 |
lasting | +0.726 |
theless | +0.719 |
wonder | +0.702 |
livest | +0.681 |
Neg logit contributions | |
oaded | -0.698 |
indal | -0.673 |
atorial | -0.661 |
ornia | -0.645 |
icion | -0.645 |
Token | Rahul |
Token ID | 48543 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
oaded | +0.243 |
indal | +0.234 |
atorial | +0.232 |
icion | +0.228 |
ornia | +0.224 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.269 |
theless | -0.253 |
lasting | -0.253 |
wonder | -0.244 |
livest | -0.237 |
Token | D |
Token ID | 360 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
oaded | +0.104 |
indal | +0.100 |
atorial | +0.100 |
ornia | +0.099 |
icion | +0.096 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.138 |
theless | -0.132 |
lasting | -0.132 |
wonder | -0.127 |
livest | -0.124 |
Token | rav |
Token ID | 4108 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
oaded | +0.586 |
indal | +0.565 |
atorial | +0.531 |
icion | +0.522 |
ornia | +0.513 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.128 |
theless | -1.124 |
lasting | -1.114 |
wonder | -1.085 |
livest | -1.064 |
Token | id |
Token ID | 312 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
lasting | +5.636 |
\\\\\\\\\\\\\\\\ | +5.494 |
wonder | +5.435 |
hm | +5.131 |
ishable | +5.120 |
Neg logit contributions | |
oaded | -7.698 |
Moroc | -7.380 |
indal | -7.138 |
efficients | -6.986 |
ornia | -6.985 |
Token | who |
Token ID | 508 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
oaded | +2.464 |
indal | +2.400 |
atorial | +2.369 |
icion | +2.333 |
ornia | +2.305 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.109 |
theless | -2.062 |
lasting | -2.041 |
wonder | -1.975 |
livest | -1.891 |
Token | said |
Token ID | 531 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.087 |
theless | +0.082 |
lasting | +0.082 |
wonder | +0.078 |
quin | +0.075 |
Neg logit contributions | |
oaded | -0.120 |
indal | -0.115 |
atorial | -0.114 |
icion | -0.111 |
clusively | -0.110 |
Token | there |
Token ID | 612 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
oaded | +1.943 |
indal | +1.889 |
atorial | +1.855 |
icion | +1.804 |
clusively | +1.801 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.906 |
theless | -1.809 |
lasting | -1.772 |
wonder | -1.726 |
quin | -1.701 |
Token | should |
Token ID | 815 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
oaded | +4.253 |
atorial | +4.101 |
indal | +4.088 |
ornia | +3.937 |
clusively | +3.906 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -3.403 |
theless | -3.359 |
lasting | -3.287 |
quin | -3.145 |
™: | -3.114 |
Token | between |
Token ID | 1022 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.712 |
theless | +0.700 |
lasting | +0.694 |
wonder | +0.665 |
quin | +0.648 |
Neg logit contributions | |
oaded | -0.724 |
indal | -0.678 |
atorial | -0.677 |
ornia | -0.663 |
clusively | -0.660 |
Token | threads |
Token ID | 14390 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
oaded | +0.545 |
indal | +0.504 |
atorial | +0.504 |
clusively | +0.501 |
icion | +0.499 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.524 |
lasting | -0.513 |
theless | -0.509 |
wonder | -0.494 |
quin | -0.477 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.540 |
lasting | +0.525 |
theless | +0.523 |
wonder | +0.511 |
livest | +0.492 |
Neg logit contributions | |
oaded | -0.691 |
indal | -0.641 |
atorial | -0.640 |
icion | -0.631 |
ornia | -0.629 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
oaded | +0.598 |
indal | +0.558 |
atorial | +0.555 |
icion | +0.542 |
ornia | +0.539 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.689 |
lasting | -0.684 |
theless | -0.673 |
wonder | -0.652 |
livest | -0.639 |
Token |
|
Token ID | 198 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
oaded | +0.214 |
atorial | +0.205 |
indal | +0.203 |
icion | +0.197 |
clusively | +0.196 |
Neg logit contributions | |
livest | -0.303 |
\\\\\\\\\\\\\\\\ | -0.302 |
theless | -0.302 |
lasting | -0.294 |
wonder | -0.283 |
Token | Mod |
Token ID | 5841 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
oaded | +0.354 |
indal | +0.330 |
atorial | +0.329 |
ornia | +0.326 |
icion | +0.325 |
Neg logit contributions | |
lasting | -0.362 |
\\\\\\\\\\\\\\\\ | -0.356 |
theless | -0.355 |
wonder | -0.347 |
livest | -0.334 |
Token | ified |
Token ID | 1431 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +5.201 |
lasting | +5.170 |
wonder | +4.981 |
theless | +4.957 |
longer | +4.655 |
Neg logit contributions | |
oaded | -7.423 |
indal | -7.056 |
Moroc | -6.894 |
atorial | -6.878 |
ornia | -6.870 |
Token | , |
Token ID | 11 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.241 |
lasting | +2.231 |
theless | +2.187 |
wonder | +2.150 |
quin | +2.033 |
Neg logit contributions | |
oaded | -2.348 |
indal | -2.205 |
atorial | -2.180 |
ornia | -2.165 |
icion | -2.143 |
Token | our |
Token ID | 674 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.103 |
theless | +0.101 |
lasting | +0.099 |
wonder | +0.096 |
quin | +0.093 |
Neg logit contributions | |
oaded | -0.133 |
indal | -0.123 |
atorial | -0.122 |
ornia | -0.121 |
icion | -0.120 |
Token | Board |
Token ID | 5926 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
oaded | +2.158 |
atorial | +2.004 |
ornia | +1.984 |
clusively | +1.947 |
icion | +1.946 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.068 |
theless | -2.064 |
lasting | -2.015 |
wonder | -1.926 |
quin | -1.912 |
Token | looks |
Token ID | 3073 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
oaded | +0.242 |
indal | +0.227 |
atorial | +0.227 |
ornia | +0.226 |
icion | +0.223 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.181 |
lasting | -0.179 |
theless | -0.178 |
wonder | -0.172 |
livest | -0.163 |
Token | O |
Token ID | 440 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.162 |
theless | +0.156 |
lasting | +0.152 |
wonder | +0.149 |
quin | +0.145 |
Neg logit contributions | |
oaded | -0.174 |
indal | -0.166 |
atorial | -0.165 |
clusively | -0.162 |
icion | -0.161 |
Token | DI |
Token ID | 17931 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.145 |
lasting | +0.143 |
theless | +0.142 |
wonder | +0.140 |
livest | +0.136 |
Neg logit contributions | |
oaded | -0.059 |
indal | -0.053 |
atorial | -0.050 |
ornia | -0.050 |
icion | -0.050 |
Token | tournaments |
Token ID | 18130 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
oaded | +0.283 |
indal | +0.268 |
atorial | +0.266 |
clusively | +0.261 |
icion | +0.259 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.287 |
theless | -0.275 |
lasting | -0.272 |
wonder | -0.263 |
livest | -0.257 |
Token | ," |
Token ID | 553 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
oaded | +0.649 |
indal | +0.613 |
atorial | +0.613 |
clusively | +0.601 |
icion | +0.591 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.557 |
theless | -0.533 |
lasting | -0.507 |
wonder | -0.503 |
livest | -0.499 |
Token | D |
Token ID | 360 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.290 |
lasting | +0.281 |
theless | +0.274 |
wonder | +0.272 |
livest | +0.259 |
Neg logit contributions | |
oaded | -0.300 |
indal | -0.285 |
atorial | -0.281 |
icion | -0.276 |
ornia | -0.275 |
Token | rav |
Token ID | 4108 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
oaded | +0.736 |
indal | +0.721 |
atorial | +0.699 |
icion | +0.686 |
ornia | +0.660 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.762 |
theless | -1.743 |
lasting | -1.721 |
livest | -1.701 |
wonder | -1.667 |
Token | id |
Token ID | 312 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
lasting | +5.475 |
\\\\\\\\\\\\\\\\ | +5.414 |
wonder | +5.309 |
theless | +5.123 |
quin | +5.091 |
Neg logit contributions | |
oaded | -6.617 |
Moroc | -6.510 |
indal | -6.149 |
ornia | -6.083 |
icion | -6.019 |
Token | said |
Token ID | 531 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
oaded | +2.372 |
atorial | +2.252 |
indal | +2.247 |
ornia | +2.204 |
icion | +2.200 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.554 |
lasting | -1.478 |
theless | -1.465 |
wonder | -1.409 |
livest | -1.356 |
Token | . |
Token ID | 13 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.049 |
lasting | +0.047 |
theless | +0.046 |
wonder | +0.045 |
livest | +0.043 |
Neg logit contributions | |
oaded | -0.062 |
indal | -0.059 |
atorial | -0.058 |
icion | -0.057 |
ornia | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
oaded | +0.488 |
indal | +0.459 |
ornia | +0.448 |
Moroc | +0.446 |
atorial | +0.445 |
Neg logit contributions | |
lasting | -0.447 |
\\\\\\\\\\\\\\\\ | -0.444 |
theless | -0.433 |
wonder | -0.431 |
longer | -0.410 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.420 |
livest | +0.418 |
theless | +0.416 |
lasting | +0.410 |
wonder | +0.395 |
Neg logit contributions | |
oaded | -0.317 |
indal | -0.302 |
atorial | -0.300 |
icion | -0.290 |
swick | -0.288 |
Token | You |
Token ID | 921 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.358 |
theless | +0.355 |
lasting | +0.355 |
livest | +0.350 |
wonder | +0.343 |
Neg logit contributions | |
oaded | -0.299 |
indal | -0.282 |
atorial | -0.281 |
icion | -0.272 |
swick | -0.272 |
Token | may |
Token ID | 743 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.461 |
theless | +0.460 |
lasting | +0.453 |
isite | +0.419 |
livest | +0.418 |
Neg logit contributions | |
oaded | -0.612 |
indal | -0.585 |
atorial | -0.582 |
icion | -0.566 |
iov | -0.559 |
Token | also |
Token ID | 635 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
oaded | +0.417 |
indal | +0.396 |
atorial | +0.390 |
icion | +0.376 |
clusively | +0.376 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.377 |
theless | -0.366 |
lasting | -0.357 |
livest | -0.336 |
quin | -0.334 |
Token | � |
Token ID | 564 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.449 |
theless | +0.439 |
lasting | +0.428 |
livest | +0.401 |
quin | +0.401 |
Neg logit contributions | |
oaded | -0.478 |
indal | -0.453 |
atorial | -0.448 |
clusively | -0.433 |
icion | -0.432 |
Token | � |
Token ID | 250 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.259 |
lasting | +2.241 |
theless | +2.215 |
wonder | +2.155 |
livest | +2.041 |
Neg logit contributions | |
oaded | -2.668 |
indal | -2.515 |
atorial | -2.484 |
ornia | -2.475 |
icion | -2.456 |
Token | rev |
Token ID | 18218 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
lasting | +3.019 |
\\\\\\\\\\\\\\\\ | +2.996 |
theless | +2.903 |
wonder | +2.863 |
livest | +2.751 |
Neg logit contributions | |
oaded | -2.965 |
indal | -2.785 |
atorial | -2.729 |
ornia | -2.703 |
icion | -2.680 |
Token | olt |
Token ID | 5978 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
lasting | +6.170 |
\\\\\\\\\\\\\\\\ | +6.166 |
wonder | +6.016 |
theless | +5.934 |
longer | +5.679 |
Neg logit contributions | |
oaded | -5.976 |
indal | -5.597 |
atorial | -5.505 |
Moroc | -5.504 |
ornia | -5.469 |
Token | � |
Token ID | 447 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.198 |
lasting | +0.197 |
theless | +0.194 |
wonder | +0.187 |
livest | +0.185 |
Neg logit contributions | |
oaded | -0.240 |
indal | -0.225 |
atorial | -0.222 |
ornia | -0.218 |
clusively | -0.218 |
Token | � |
Token ID | 251 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.369 |
lasting | +0.364 |
theless | +0.363 |
wonder | +0.352 |
quin | +0.334 |
Neg logit contributions | |
oaded | -0.442 |
indal | -0.416 |
ornia | -0.415 |
atorial | -0.414 |
icion | -0.410 |
Token | the |
Token ID | 262 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
oaded | +0.201 |
indal | +0.186 |
atorial | +0.184 |
icion | +0.180 |
ornia | +0.180 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.163 |
lasting | -0.160 |
theless | -0.158 |
wonder | -0.153 |
livest | -0.151 |
Token | players |
Token ID | 1938 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.455 |
theless | +0.446 |
lasting | +0.443 |
wonder | +0.424 |
livest | +0.415 |
Neg logit contributions | |
oaded | -0.483 |
indal | -0.450 |
atorial | -0.448 |
icion | -0.436 |
clusively | -0.435 |
Token | he |
Token ID | 339 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
oaded | +1.441 |
indal | +1.397 |
atorial | +1.349 |
ornia | +1.331 |
icion | +1.328 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.228 |
lasting | -1.210 |
theless | -1.182 |
wonder | -1.156 |
livest | -1.103 |
Token | said |
Token ID | 531 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.625 |
lasting | +0.606 |
theless | +0.592 |
wonder | +0.572 |
™: | +0.559 |
Neg logit contributions | |
oaded | -0.818 |
indal | -0.782 |
atorial | -0.767 |
icion | -0.752 |
ornia | -0.750 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
oaded | +0.309 |
indal | +0.298 |
icion | +0.287 |
atorial | +0.286 |
ornia | +0.284 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.247 |
lasting | -0.238 |
theless | -0.237 |
wonder | -0.226 |
livest | -0.220 |
Token |
|
Token ID | 198 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
oaded | +1.118 |
indal | +1.070 |
atorial | +1.041 |
Moroc | +1.026 |
icion | +1.024 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.112 |
lasting | -1.097 |
theless | -1.070 |
wonder | -1.059 |
livest | -1.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.148 |
livest | +0.148 |
theless | +0.146 |
lasting | +0.144 |
wonder | +0.139 |
Neg logit contributions | |
oaded | -0.109 |
indal | -0.104 |
atorial | -0.103 |
icion | -0.099 |
clusively | -0.099 |
Token | Mod |
Token ID | 5841 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
lasting | +0.039 |
\\\\\\\\\\\\\\\\ | +0.039 |
theless | +0.038 |
wonder | +0.037 |
livest | +0.037 |
Neg logit contributions | |
oaded | -0.033 |
indal | -0.032 |
atorial | -0.031 |
icion | -0.031 |
swick | -0.030 |
Token | i |
Token ID | 72 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +6.580 |
lasting | +6.496 |
theless | +6.381 |
wonder | +6.279 |
livest | +6.036 |
Neg logit contributions | |
oaded | -5.754 |
indal | -5.489 |
atorial | -5.355 |
icion | -5.281 |
ornia | -5.275 |
Token | first |
Token ID | 717 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.213 |
lasting | +1.127 |
theless | +1.101 |
wonder | +1.075 |
livest | +1.041 |
Neg logit contributions | |
oaded | -1.701 |
indal | -1.612 |
atorial | -1.590 |
icion | -1.566 |
clusively | -1.566 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.815 |
lasting | +2.661 |
theless | +2.575 |
wonder | +2.536 |
livest | +2.459 |
Neg logit contributions | |
oaded | -4.121 |
indal | -3.942 |
atorial | -3.842 |
clusively | -3.817 |
ornia | -3.808 |
Token | for |
Token ID | 329 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.937 |
lasting | +1.875 |
theless | +1.838 |
wonder | +1.802 |
livest | +1.731 |
Neg logit contributions | |
oaded | -2.056 |
indal | -1.964 |
atorial | -1.905 |
icion | -1.902 |
ornia | -1.887 |
Token | some |
Token ID | 617 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
oaded | +0.191 |
indal | +0.186 |
atorial | +0.180 |
icion | +0.179 |
clusively | +0.178 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.177 |
theless | -0.171 |
lasting | -0.167 |
wonder | -0.161 |
livest | -0.159 |
Token | � |
Token ID | 447 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.454 |
lasting | +0.448 |
theless | +0.445 |
livest | +0.436 |
wonder | +0.432 |
Neg logit contributions | |
oaded | -0.385 |
indal | -0.371 |
atorial | -0.369 |
swick | -0.356 |
icion | -0.354 |
Token | � |
Token ID | 251 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.674 |
lasting | +0.669 |
theless | +0.651 |
wonder | +0.646 |
longer | +0.607 |
Neg logit contributions | |
oaded | -0.824 |
indal | -0.781 |
atorial | -0.767 |
ornia | -0.763 |
Moroc | -0.758 |
Token |
|
Token ID | 198 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.554 |
lasting | +0.549 |
theless | +0.535 |
wonder | +0.529 |
livest | +0.519 |
Neg logit contributions | |
oaded | -0.528 |
indal | -0.504 |
atorial | -0.495 |
ornia | -0.482 |
icion | -0.480 |
Token |
|
Token ID | 198 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.210 |
theless | +1.200 |
lasting | +1.196 |
livest | +1.181 |
wonder | +1.151 |
Neg logit contributions | |
oaded | -0.986 |
indal | -0.936 |
atorial | -0.925 |
icion | -0.899 |
ornia | -0.897 |
Token | Prime |
Token ID | 26405 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
lasting | +1.014 |
theless | +1.002 |
\\\\\\\\\\\\\\\\ | +0.993 |
livest | +0.973 |
wonder | +0.971 |
Neg logit contributions | |
oaded | -0.789 |
indal | -0.753 |
atorial | -0.740 |
icion | -0.720 |
ornia | -0.710 |
Token | Minister |
Token ID | 4139 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
lasting | +3.436 |
\\\\\\\\\\\\\\\\ | +3.393 |
wonder | +3.368 |
theless | +3.304 |
longer | +3.201 |
Neg logit contributions | |
oaded | -2.607 |
indal | -2.380 |
ornia | -2.326 |
icion | -2.306 |
atorial | -2.305 |
Token | Trudeau |
Token ID | 17524 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
lasting | +5.333 |
\\\\\\\\\\\\\\\\ | +5.235 |
wonder | +5.177 |
theless | +5.071 |
longer | +4.851 |
Neg logit contributions | |
oaded | -6.739 |
indal | -6.369 |
Moroc | -6.275 |
atorial | -6.250 |
ornia | -6.221 |
Token | might |
Token ID | 1244 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.169 |
lasting | +2.117 |
theless | +2.067 |
wonder | +2.029 |
livest | +1.919 |
Neg logit contributions | |
oaded | -3.265 |
indal | -3.106 |
atorial | -3.060 |
ornia | -3.026 |
icion | -3.016 |
Token | agree |
Token ID | 4236 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
oaded | +1.138 |
indal | +1.068 |
atorial | +1.062 |
clusively | +1.033 |
icion | +1.019 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.116 |
theless | -1.068 |
lasting | -1.060 |
livest | -1.000 |
quin | -0.994 |
Token | with |
Token ID | 351 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
oaded | +1.401 |
indal | +1.334 |
atorial | +1.311 |
clusively | +1.290 |
icion | +1.286 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.214 |
lasting | -1.171 |
theless | -1.169 |
wonder | -1.128 |
livest | -1.104 |
Token | you |
Token ID | 345 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.891 |
lasting | +0.863 |
theless | +0.861 |
wonder | +0.833 |
livest | +0.811 |
Neg logit contributions | |
oaded | -0.940 |
indal | -0.886 |
atorial | -0.871 |
clusively | -0.860 |
icion | -0.855 |
Token | it |
Token ID | 340 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.729 |
lasting | +1.699 |
theless | +1.657 |
wonder | +1.634 |
livest | +1.555 |
Neg logit contributions | |
oaded | -2.049 |
indal | -1.939 |
atorial | -1.897 |
ornia | -1.877 |
icion | -1.876 |
Token | being |
Token ID | 852 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.783 |
lasting | +0.765 |
theless | +0.748 |
wonder | +0.742 |
livest | +0.699 |
Neg logit contributions | |
oaded | -1.295 |
indal | -1.234 |
atorial | -1.219 |
ornia | -1.203 |
clusively | -1.202 |
Token | fairly |
Token ID | 6547 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.287 |
lasting | +0.276 |
theless | +0.273 |
wonder | +0.267 |
hm | +0.256 |
Neg logit contributions | |
oaded | -0.349 |
indal | -0.327 |
clusively | -0.325 |
atorial | -0.323 |
ornia | -0.318 |
Token | simple |
Token ID | 2829 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.785 |
theless | +0.752 |
lasting | +0.751 |
wonder | +0.736 |
livest | +0.707 |
Neg logit contributions | |
oaded | -0.967 |
indal | -0.919 |
atorial | -0.919 |
clusively | -0.897 |
ornia | -0.895 |
Token | to |
Token ID | 284 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.182 |
lasting | +2.150 |
theless | +2.099 |
wonder | +2.047 |
livest | +1.937 |
Neg logit contributions | |
oaded | -3.337 |
indal | -3.178 |
atorial | -3.115 |
ornia | -3.079 |
icion | -3.078 |
Token | mod |
Token ID | 953 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.231 |
theless | +1.225 |
lasting | +1.211 |
wonder | +1.128 |
livest | +1.125 |
Neg logit contributions | |
oaded | -1.478 |
indal | -1.395 |
atorial | -1.373 |
clusively | -1.365 |
ornia | -1.349 |
Token | , |
Token ID | 11 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
lasting | +4.828 |
\\\\\\\\\\\\\\\\ | +4.809 |
wonder | +4.612 |
theless | +4.566 |
longer | +4.340 |
Neg logit contributions | |
oaded | -7.098 |
indal | -6.773 |
Moroc | -6.645 |
atorial | -6.629 |
ornia | -6.612 |
Token | and |
Token ID | 290 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.195 |
theless | +1.158 |
lasting | +1.139 |
wonder | +1.105 |
livest | +1.058 |
Neg logit contributions | |
oaded | -1.715 |
indal | -1.631 |
atorial | -1.604 |
icion | -1.583 |
clusively | -1.576 |
Token | partly |
Token ID | 11476 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.557 |
lasting | +0.542 |
theless | +0.529 |
wonder | +0.517 |
livest | +0.497 |
Neg logit contributions | |
oaded | -0.635 |
indal | -0.600 |
atorial | -0.587 |
icion | -0.586 |
ornia | -0.584 |
Token | due |
Token ID | 2233 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.346 |
lasting | +1.325 |
theless | +1.291 |
wonder | +1.264 |
livest | +1.197 |
Neg logit contributions | |
oaded | -2.424 |
indal | -2.305 |
atorial | -2.275 |
ornia | -2.262 |
icion | -2.243 |
Token | to |
Token ID | 284 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
oaded | +0.241 |
indal | +0.230 |
atorial | +0.227 |
ornia | +0.226 |
Moroc | +0.226 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.124 |
lasting | -0.124 |
wonder | -0.119 |
theless | -0.116 |
longer | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
oaded | +3.845 |
atorial | +3.674 |
indal | +3.564 |
clusively | +3.539 |
ornia | +3.532 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -3.525 |
theless | -3.397 |
lasting | -3.307 |
livest | -3.254 |
wonder | -3.205 |
Token |
|
Token ID | 198 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.065 |
lasting | +0.065 |
theless | +0.064 |
livest | +0.063 |
wonder | +0.062 |
Neg logit contributions | |
oaded | -0.054 |
atorial | -0.052 |
indal | -0.051 |
swick | -0.050 |
icion | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.879 |
theless | +0.870 |
livest | +0.869 |
lasting | +0.861 |
wonder | +0.828 |
Neg logit contributions | |
oaded | -0.678 |
indal | -0.642 |
atorial | -0.640 |
icion | -0.620 |
ornia | -0.617 |
Token | � |
Token ID | 447 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
lasting | +0.678 |
theless | +0.667 |
\\\\\\\\\\\\\\\\ | +0.664 |
wonder | +0.654 |
livest | +0.652 |
Neg logit contributions | |
oaded | -0.529 |
atorial | -0.500 |
indal | -0.497 |
icion | -0.485 |
ornia | -0.478 |
Token | � |
Token ID | 250 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.332 |
lasting | +0.330 |
theless | +0.320 |
wonder | +0.316 |
livest | +0.295 |
Neg logit contributions | |
oaded | -0.499 |
indal | -0.475 |
atorial | -0.468 |
ornia | -0.467 |
Moroc | -0.463 |
Token | Zero |
Token ID | 28667 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.945 |
lasting | +2.936 |
theless | +2.845 |
wonder | +2.845 |
livest | +2.701 |
Neg logit contributions | |
oaded | -2.762 |
indal | -2.603 |
atorial | -2.553 |
ornia | -2.527 |
icion | -2.511 |
Token | poverty |
Token ID | 8098 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
lasting | +5.342 |
\\\\\\\\\\\\\\\\ | +5.269 |
wonder | +5.209 |
theless | +5.073 |
longer | +4.855 |
Neg logit contributions | |
oaded | -6.305 |
indal | -5.930 |
atorial | -5.755 |
icion | -5.746 |
Moroc | -5.742 |
Token | in |
Token ID | 287 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.209 |
lasting | +1.178 |
theless | +1.158 |
wonder | +1.138 |
quin | +1.083 |
Neg logit contributions | |
oaded | -1.624 |
indal | -1.556 |
ornia | -1.526 |
atorial | -1.524 |
icion | -1.503 |
Token | four |
Token ID | 1440 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
oaded | +0.043 |
clusively | +0.041 |
indal | +0.041 |
ornia | +0.040 |
atorial | +0.040 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.032 |
theless | -0.031 |
lasting | -0.031 |
quin | -0.030 |
wonder | -0.030 |
Token | years |
Token ID | 812 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
oaded | +1.003 |
indal | +0.950 |
atorial | +0.928 |
ornia | +0.922 |
Moroc | +0.921 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.849 |
lasting | -0.847 |
wonder | -0.817 |
theless | -0.814 |
longer | -0.771 |
Token | � |
Token ID | 447 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.719 |
lasting | +0.698 |
theless | +0.691 |
wonder | +0.676 |
livest | +0.651 |
Neg logit contributions | |
oaded | -0.932 |
indal | -0.891 |
atorial | -0.877 |
ornia | -0.876 |
icion | -0.860 |
Token | think |
Token ID | 892 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.366 |
theless | +1.326 |
lasting | +1.299 |
™: | +1.235 |
livest | +1.217 |
Neg logit contributions | |
oaded | -1.675 |
indal | -1.604 |
atorial | -1.593 |
clusively | -1.565 |
icion | -1.534 |
Token | ," |
Token ID | 553 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
oaded | +1.463 |
atorial | +1.407 |
indal | +1.407 |
icion | +1.403 |
clusively | +1.399 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.234 |
theless | -1.230 |
lasting | -1.177 |
quin | -1.138 |
wonder | -1.136 |
Token | says |
Token ID | 1139 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.764 |
lasting | +0.743 |
theless | +0.726 |
wonder | +0.704 |
livest | +0.682 |
Neg logit contributions | |
oaded | -0.935 |
indal | -0.889 |
atorial | -0.883 |
Moroc | -0.872 |
clusively | -0.871 |
Token | Jo |
Token ID | 5302 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.429 |
lasting | +1.404 |
theless | +1.373 |
wonder | +1.341 |
™: | +1.290 |
Neg logit contributions | |
oaded | -1.467 |
indal | -1.390 |
atorial | -1.371 |
Moroc | -1.353 |
icion | -1.350 |
Token | - |
Token ID | 12 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.350 |
lasting | +0.348 |
theless | +0.339 |
wonder | +0.331 |
livest | +0.318 |
Neg logit contributions | |
oaded | -0.350 |
indal | -0.335 |
atorial | -0.327 |
ornia | -0.325 |
icion | -0.323 |
Token | Rem |
Token ID | 8413 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.414 |
lasting | +1.408 |
theless | +1.379 |
wonder | +1.357 |
livest | +1.310 |
Neg logit contributions | |
oaded | -1.170 |
indal | -1.094 |
atorial | -1.092 |
icion | -1.067 |
efficients | -1.057 |
Token | i |
Token ID | 72 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
lasting | +5.731 |
\\\\\\\\\\\\\\\\ | +5.701 |
wonder | +5.573 |
theless | +5.488 |
quin | +5.265 |
Neg logit contributions | |
oaded | -5.817 |
indal | -5.444 |
Moroc | -5.321 |
atorial | -5.290 |
ornia | -5.257 |
Token | Mad |
Token ID | 4627 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.653 |
lasting | +2.640 |
theless | +2.561 |
wonder | +2.548 |
longer | +2.413 |
Neg logit contributions | |
oaded | -2.777 |
indal | -2.627 |
atorial | -2.572 |
ornia | -2.550 |
Moroc | -2.546 |
Token | sen |
Token ID | 6248 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.169 |
lasting | +3.156 |
theless | +3.065 |
wonder | +3.054 |
longer | +2.902 |
Neg logit contributions | |
oaded | -2.871 |
indal | -2.700 |
atorial | -2.638 |
ornia | -2.617 |
icion | -2.601 |
Token | , |
Token ID | 11 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.251 |
lasting | +1.244 |
theless | +1.201 |
wonder | +1.195 |
longer | +1.119 |
Neg logit contributions | |
oaded | -1.752 |
indal | -1.669 |
atorial | -1.638 |
ornia | -1.625 |
Moroc | -1.623 |
Token | of |
Token ID | 286 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.307 |
lasting | +1.262 |
theless | +1.258 |
wonder | +1.215 |
™: | +1.177 |
Neg logit contributions | |
oaded | -1.347 |
indal | -1.279 |
atorial | -1.271 |
clusively | -1.252 |
icion | -1.247 |
Token | as |
Token ID | 355 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
oaded | +1.982 |
indal | +1.902 |
icion | +1.837 |
clusively | +1.835 |
atorial | +1.814 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.656 |
theless | -1.572 |
lasting | -1.544 |
wonder | -1.504 |
livest | -1.501 |
Token | change |
Token ID | 1487 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
oaded | +0.041 |
indal | +0.039 |
atorial | +0.038 |
icion | +0.038 |
ornia | +0.038 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.037 |
theless | -0.035 |
lasting | -0.035 |
wonder | -0.033 |
™: | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.859 |
lasting | +0.823 |
theless | +0.813 |
wonder | +0.804 |
livest | +0.775 |
Neg logit contributions | |
oaded | -1.169 |
indal | -1.118 |
atorial | -1.092 |
icion | -1.085 |
clusively | -1.078 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
oaded | +0.933 |
indal | +0.896 |
atorial | +0.866 |
icion | +0.853 |
Moroc | +0.848 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.052 |
lasting | -1.019 |
theless | -0.997 |
wonder | -0.991 |
livest | -0.962 |
Token |
|
Token ID | 198 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
oaded | +0.066 |
indal | +0.063 |
atorial | +0.063 |
icion | +0.061 |
clusively | +0.060 |
Neg logit contributions | |
livest | -0.092 |
\\\\\\\\\\\\\\\\ | -0.092 |
theless | -0.091 |
lasting | -0.089 |
wonder | -0.086 |
Token | Mod |
Token ID | 5841 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
oaded | +0.058 |
indal | +0.056 |
atorial | +0.054 |
icion | +0.053 |
swick | +0.052 |
Neg logit contributions | |
lasting | -0.070 |
\\\\\\\\\\\\\\\\ | -0.070 |
theless | -0.069 |
wonder | -0.068 |
livest | -0.067 |
Token | i |
Token ID | 72 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +6.006 |
lasting | +5.979 |
theless | +5.806 |
wonder | +5.785 |
longer | +5.495 |
Neg logit contributions | |
oaded | -5.659 |
indal | -5.339 |
atorial | -5.214 |
ornia | -5.167 |
icion | -5.140 |
Token | had |
Token ID | 550 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.213 |
lasting | +1.129 |
theless | +1.112 |
wonder | +1.083 |
livest | +1.045 |
Neg logit contributions | |
oaded | -1.718 |
indal | -1.639 |
atorial | -1.611 |
icion | -1.590 |
clusively | -1.582 |
Token | three |
Token ID | 1115 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.842 |
lasting | +0.770 |
theless | +0.764 |
wonder | +0.744 |
™: | +0.735 |
Neg logit contributions | |
oaded | -1.031 |
indal | -0.972 |
clusively | -0.959 |
atorial | -0.957 |
icion | -0.951 |
Token | MPs |
Token ID | 14952 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
oaded | +0.875 |
indal | +0.855 |
atorial | +0.821 |
icion | +0.805 |
clusively | +0.802 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.800 |
theless | -0.750 |
lasting | -0.715 |
livest | -0.705 |
™: | -0.704 |
Token | for |
Token ID | 329 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
oaded | +0.216 |
indal | +0.208 |
atorial | +0.203 |
clusively | +0.197 |
swick | +0.197 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.195 |
theless | -0.183 |
lasting | -0.179 |
wonder | -0.173 |
livest | -0.170 |
Token | laid |
Token ID | 8104 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.176 |
theless | +0.164 |
lasting | +0.157 |
quin | +0.152 |
wonder | +0.152 |
Neg logit contributions | |
oaded | -0.260 |
clusively | -0.250 |
ornia | -0.243 |
indal | -0.243 |
atorial | -0.241 |
Token | fresh |
Token ID | 4713 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
theless | +1.156 |
\\\\\\\\\\\\\\\\ | +1.134 |
lasting | +1.123 |
wonder | +1.085 |
livest | +1.033 |
Neg logit contributions | |
oaded | -2.006 |
indal | -1.887 |
clusively | -1.878 |
ornia | -1.874 |
atorial | -1.870 |
Token | charges |
Token ID | 4530 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
theless | +0.041 |
\\\\\\\\\\\\\\\\ | +0.040 |
lasting | +0.038 |
livest | +0.036 |
hm | +0.036 |
Neg logit contributions | |
oaded | -0.076 |
ornia | -0.073 |
atorial | -0.072 |
indal | -0.072 |
clusively | -0.071 |
Token | against |
Token ID | 1028 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.591 |
theless | +0.575 |
lasting | +0.567 |
wonder | +0.560 |
livest | +0.554 |
Neg logit contributions | |
oaded | -0.484 |
indal | -0.455 |
atorial | -0.444 |
ornia | -0.441 |
clusively | -0.437 |
Token | former |
Token ID | 1966 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
oaded | +1.269 |
indal | +1.187 |
clusively | +1.183 |
atorial | +1.170 |
ornia | +1.169 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.165 |
theless | -1.109 |
lasting | -1.091 |
wonder | -1.048 |
livest | -1.034 |
Token | Reserve |
Token ID | 12224 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
oaded | +0.753 |
indal | +0.719 |
atorial | +0.716 |
clusively | +0.716 |
ornia | +0.714 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.714 |
lasting | -0.676 |
theless | -0.671 |
wonder | -0.643 |
™: | -0.636 |
Token | Bank |
Token ID | 5018 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
lasting | +5.240 |
\\\\\\\\\\\\\\\\ | +5.217 |
wonder | +5.088 |
theless | +4.986 |
longer | +4.771 |
Neg logit contributions | |
oaded | -6.347 |
indal | -6.007 |
atorial | -5.861 |
ornia | -5.809 |
Moroc | -5.809 |
Token | currency |
Token ID | 7395 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.557 |
lasting | +1.549 |
theless | +1.494 |
wonder | +1.480 |
longer | +1.378 |
Neg logit contributions | |
oaded | -2.480 |
indal | -2.372 |
atorial | -2.329 |
ornia | -2.321 |
Moroc | -2.315 |
Token | executives |
Token ID | 12353 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
oaded | +1.090 |
indal | +1.034 |
icion | +1.018 |
atorial | +1.014 |
ornia | +1.006 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.263 |
theless | -1.252 |
lasting | -1.243 |
wonder | -1.192 |
livest | -1.175 |
Token | involving |
Token ID | 7411 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
oaded | +1.092 |
indal | +1.041 |
atorial | +1.027 |
ornia | +1.018 |
Moroc | +1.007 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.110 |
theless | -1.092 |
lasting | -1.053 |
livest | -1.021 |
wonder | -1.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.633 |
theless | +0.615 |
lasting | +0.611 |
wonder | +0.592 |
livest | +0.580 |
Neg logit contributions | |
oaded | -0.683 |
indal | -0.645 |
atorial | -0.639 |
clusively | -0.629 |
ornia | -0.628 |
Token | file |
Token ID | 2393 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.110 |
theless | +0.107 |
lasting | +0.106 |
wonder | +0.103 |
livest | +0.100 |
Neg logit contributions | |
oaded | -0.104 |
indal | -0.097 |
atorial | -0.097 |
clusively | -0.093 |
icion | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.663 |
lasting | +0.648 |
theless | +0.634 |
wonder | +0.626 |
livest | +0.601 |
Neg logit contributions | |
oaded | -0.840 |
indal | -0.786 |
atorial | -0.772 |
clusively | -0.764 |
ornia | -0.761 |
Token | and |
Token ID | 290 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.130 |
lasting | +0.128 |
theless | +0.126 |
wonder | +0.123 |
quin | +0.118 |
Neg logit contributions | |
oaded | -0.127 |
indal | -0.119 |
atorial | -0.116 |
icion | -0.115 |
clusively | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
oaded | +0.616 |
indal | +0.578 |
atorial | +0.566 |
icion | +0.562 |
clusively | +0.560 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.590 |
theless | -0.567 |
lasting | -0.566 |
quin | -0.534 |
wonder | -0.534 |
Token | ' |
Token ID | 705 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
oaded | +0.047 |
indal | +0.044 |
atorial | +0.043 |
icion | +0.042 |
clusively | +0.042 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.047 |
lasting | -0.046 |
theless | -0.046 |
wonder | -0.044 |
quin | -0.043 |
Token | mod |
Token ID | 4666 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
lasting | +0.375 |
\\\\\\\\\\\\\\\\ | +0.374 |
theless | +0.363 |
wonder | +0.359 |
livest | +0.342 |
Neg logit contributions | |
oaded | -0.393 |
indal | -0.370 |
atorial | -0.364 |
ornia | -0.357 |
icion | -0.357 |
Token | eline |
Token ID | 4470 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +5.709 |
lasting | +5.692 |
theless | +5.521 |
wonder | +5.511 |
longer | +5.242 |
Neg logit contributions | |
oaded | -5.817 |
indal | -5.470 |
Moroc | -5.350 |
ornia | -5.330 |
atorial | -5.310 |
Token | ' |
Token ID | 6 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.854 |
lasting | +1.845 |
wonder | +1.770 |
theless | +1.767 |
longer | +1.651 |
Neg logit contributions | |
oaded | -2.920 |
indal | -2.787 |
atorial | -2.734 |
ornia | -2.721 |
Moroc | -2.717 |
Token | option |
Token ID | 3038 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.036 |
lasting | +0.036 |
theless | +0.035 |
wonder | +0.034 |
livest | +0.033 |
Neg logit contributions | |
oaded | -0.043 |
indal | -0.041 |
atorial | -0.040 |
icion | -0.040 |
clusively | -0.039 |
Token | is |
Token ID | 318 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.607 |
lasting | +0.595 |
theless | +0.582 |
wonder | +0.567 |
livest | +0.539 |
Neg logit contributions | |
oaded | -0.879 |
indal | -0.834 |
atorial | -0.818 |
ornia | -0.805 |
icion | -0.804 |
Token | on |
Token ID | 319 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.077 |
lasting | +1.058 |
theless | +1.043 |
wonder | +1.013 |
™: | +0.960 |
Neg logit contributions | |
oaded | -1.562 |
indal | -1.465 |
atorial | -1.451 |
ornia | -1.434 |
clusively | -1.432 |
Token | " |
Token ID | 366 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.348 |
lasting | +1.342 |
theless | +1.309 |
wonder | +1.288 |
quin | +1.233 |
Neg logit contributions | |
oaded | -1.381 |
indal | -1.303 |
atorial | -1.275 |
ornia | -1.263 |
clusively | -1.259 |
Token | example |
Token ID | 20688 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
oaded | +0.580 |
indal | +0.540 |
atorial | +0.529 |
ornia | +0.529 |
icion | +0.525 |
Neg logit contributions | |
lasting | -0.736 |
\\\\\\\\\\\\\\\\ | -0.730 |
theless | -0.714 |
wonder | -0.708 |
livest | -0.679 |
Token | : |
Token ID | 25 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
lasting | +0.639 |
\\\\\\\\\\\\\\\\ | +0.639 |
theless | +0.620 |
wonder | +0.610 |
livest | +0.581 |
Neg logit contributions | |
oaded | -0.831 |
indal | -0.790 |
atorial | -0.774 |
ornia | -0.771 |
clusively | -0.765 |
Token | "). |
Token ID | 11074 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
lasting | +1.107 |
\\\\\\\\\\\\\\\\ | +1.106 |
theless | +1.075 |
wonder | +1.061 |
livest | +1.007 |
Neg logit contributions | |
oaded | -1.228 |
indal | -1.158 |
atorial | -1.135 |
ornia | -1.132 |
icion | -1.123 |
Token | * |
Token ID | 1635 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.064 |
lasting | +0.064 |
theless | +0.063 |
wonder | +0.062 |
livest | +0.059 |
Neg logit contributions | |
oaded | -0.067 |
indal | -0.063 |
atorial | -0.062 |
clusively | -0.062 |
icion | -0.061 |
Token | mod |
Token ID | 4666 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.141 |
lasting | +2.135 |
theless | +2.076 |
wonder | +2.073 |
longer | +1.978 |
Neg logit contributions | |
oaded | -1.588 |
indal | -1.482 |
atorial | -1.442 |
ornia | -1.429 |
Moroc | -1.424 |
Token | eline |
Token ID | 4470 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +6.075 |
lasting | +6.038 |
wonder | +5.929 |
theless | +5.920 |
quin | +5.711 |
Neg logit contributions | |
oaded | -5.163 |
Moroc | -4.819 |
indal | -4.716 |
ornia | -4.631 |
atorial | -4.559 |
Token | - |
Token ID | 12 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.360 |
lasting | +2.339 |
wonder | +2.265 |
theless | +2.241 |
longer | +2.138 |
Neg logit contributions | |
oaded | -2.983 |
indal | -2.830 |
ornia | -2.769 |
atorial | -2.766 |
Moroc | -2.757 |
Token | local |
Token ID | 12001 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
lasting | +0.918 |
\\\\\\\\\\\\\\\\ | +0.917 |
theless | +0.888 |
wonder | +0.885 |
livest | +0.844 |
Neg logit contributions | |
oaded | -0.893 |
indal | -0.841 |
atorial | -0.821 |
icion | -0.811 |
ornia | -0.810 |
Token | * |
Token ID | 9 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
oaded | +1.264 |
indal | +1.190 |
atorial | +1.162 |
icion | +1.157 |
clusively | +1.150 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.195 |
lasting | -1.190 |
theless | -1.155 |
wonder | -1.141 |
livest | -1.089 |
Token | The |
Token ID | 383 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
oaded | +0.360 |
indal | +0.338 |
atorial | +0.333 |
Moroc | +0.330 |
clusively | +0.328 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.317 |
lasting | -0.314 |
theless | -0.309 |
wonder | -0.302 |
livest | -0.288 |
Token | � |
Token ID | 447 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.942 |
theless | +0.907 |
lasting | +0.903 |
wonder | +0.868 |
livest | +0.837 |
Neg logit contributions | |
oaded | -1.159 |
indal | -1.091 |
clusively | -1.089 |
ornia | -1.081 |
atorial | -1.071 |
Token | � |
Token ID | 247 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
oaded | +0.222 |
ornia | +0.214 |
icion | +0.213 |
atorial | +0.213 |
indal | +0.206 |
Neg logit contributions | |
theless | -0.274 |
\\\\\\\\\\\\\\\\ | -0.266 |
lasting | -0.259 |
wonder | -0.258 |
livest | -0.251 |
Token | s |
Token ID | 82 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
oaded | +1.277 |
indal | +1.216 |
ornia | +1.209 |
atorial | +1.192 |
clusively | +1.188 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.057 |
lasting | -1.031 |
theless | -1.014 |
wonder | -1.001 |
livest | -0.967 |
Token | old |
Token ID | 1468 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.052 |
lasting | +1.033 |
theless | +1.018 |
wonder | +0.987 |
livest | +0.949 |
Neg logit contributions | |
oaded | -1.246 |
indal | -1.183 |
atorial | -1.172 |
ornia | -1.155 |
clusively | -1.153 |
Token | Federal |
Token ID | 5618 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
oaded | +0.712 |
indal | +0.683 |
atorial | +0.676 |
clusively | +0.674 |
ornia | +0.672 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.594 |
lasting | -0.576 |
theless | -0.573 |
wonder | -0.543 |
livest | -0.537 |
Token | Reserve |
Token ID | 12224 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.894 |
lasting | +1.881 |
theless | +1.813 |
wonder | +1.783 |
livest | +1.718 |
Neg logit contributions | |
oaded | -2.504 |
indal | -2.381 |
ornia | -2.347 |
atorial | -2.347 |
icion | -2.324 |
Token | Building |
Token ID | 11819 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +5.189 |
lasting | +5.185 |
wonder | +5.024 |
theless | +4.883 |
longer | +4.692 |
Neg logit contributions | |
oaded | -6.336 |
indal | -6.012 |
atorial | -5.903 |
Moroc | -5.859 |
icion | -5.806 |
Token | with |
Token ID | 351 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.699 |
lasting | +1.671 |
theless | +1.644 |
wonder | +1.608 |
livest | +1.527 |
Neg logit contributions | |
oaded | -2.181 |
indal | -2.072 |
atorial | -2.028 |
ornia | -2.027 |
icion | -2.013 |
Token | a |
Token ID | 257 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.061 |
theless | +0.060 |
lasting | +0.059 |
wonder | +0.057 |
livest | +0.056 |
Neg logit contributions | |
oaded | -0.067 |
indal | -0.063 |
atorial | -0.062 |
clusively | -0.062 |
ornia | -0.062 |
Token | 31 |
Token ID | 3261 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.045 |
theless | +0.044 |
lasting | +0.043 |
wonder | +0.042 |
™: | +0.042 |
Neg logit contributions | |
oaded | -0.055 |
atorial | -0.053 |
indal | -0.052 |
clusively | -0.052 |
icion | -0.052 |
Token | - |
Token ID | 12 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
oaded | +2.604 |
indal | +2.502 |
atorial | +2.481 |
icion | +2.480 |
clusively | +2.461 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.297 |
theless | -2.257 |
lasting | -2.244 |
wonder | -2.108 |
livest | -2.105 |
Token | suggest |
Token ID | 1950 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.026 |
lasting | +0.994 |
theless | +0.992 |
quin | +0.908 |
isite | +0.894 |
Neg logit contributions | |
oaded | -1.541 |
indal | -1.482 |
ornia | -1.464 |
atorial | -1.464 |
clusively | -1.430 |
Token | you |
Token ID | 345 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
oaded | +0.362 |
indal | +0.343 |
ornia | +0.336 |
atorial | +0.333 |
icion | +0.332 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.339 |
theless | -0.332 |
lasting | -0.328 |
wonder | -0.320 |
quin | -0.315 |
Token | ask |
Token ID | 1265 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
oaded | +0.510 |
indal | +0.495 |
ornia | +0.478 |
atorial | +0.476 |
clusively | +0.472 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.445 |
theless | -0.435 |
lasting | -0.431 |
isite | -0.404 |
quin | -0.400 |
Token | [ |
Token ID | 685 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.825 |
lasting | +1.792 |
theless | +1.773 |
wonder | +1.719 |
livest | +1.648 |
Neg logit contributions | |
oaded | -2.278 |
indal | -2.179 |
atorial | -2.142 |
ornia | -2.134 |
clusively | -2.107 |
Token | Prime |
Token ID | 26405 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
lasting | +1.652 |
\\\\\\\\\\\\\\\\ | +1.641 |
theless | +1.612 |
wonder | +1.597 |
livest | +1.517 |
Neg logit contributions | |
oaded | -1.682 |
indal | -1.608 |
atorial | -1.582 |
ornia | -1.576 |
icion | -1.571 |
Token | Minister |
Token ID | 4139 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.772 |
lasting | +3.750 |
wonder | +3.632 |
theless | +3.605 |
longer | +3.417 |
Neg logit contributions | |
oaded | -4.711 |
indal | -4.420 |
atorial | -4.350 |
ornia | -4.332 |
icion | -4.317 |
Token | Benjamin |
Token ID | 14533 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
lasting | +4.379 |
\\\\\\\\\\\\\\\\ | +4.330 |
wonder | +4.226 |
theless | +4.088 |
longer | +3.980 |
Neg logit contributions | |
oaded | -6.931 |
indal | -6.604 |
atorial | -6.454 |
swick | -6.451 |
icion | -6.444 |
Token | ] |
Token ID | 60 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.020 |
lasting | +1.008 |
theless | +0.982 |
wonder | +0.976 |
livest | +0.956 |
Neg logit contributions | |
oaded | -1.100 |
indal | -1.043 |
atorial | -1.029 |
ornia | -1.005 |
icion | -1.001 |
Token | Netanyahu |
Token ID | 17104 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.943 |
lasting | +0.928 |
theless | +0.922 |
wonder | +0.897 |
quin | +0.865 |
Neg logit contributions | |
oaded | -1.092 |
indal | -1.030 |
atorial | -1.018 |
clusively | -1.014 |
Moroc | -1.009 |
Token | a |
Token ID | 257 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.497 |
lasting | +0.489 |
theless | +0.484 |
wonder | +0.466 |
livest | +0.448 |
Neg logit contributions | |
oaded | -0.748 |
indal | -0.710 |
atorial | -0.703 |
ornia | -0.697 |
icion | -0.691 |
Token | lot |
Token ID | 1256 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.253 |
theless | +0.252 |
lasting | +0.239 |
wonder | +0.229 |
™: | +0.223 |
Neg logit contributions | |
oaded | -0.402 |
atorial | -0.387 |
indal | -0.382 |
ornia | -0.378 |
icion | -0.378 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.333 |
lasting | +0.326 |
theless | +0.322 |
wonder | +0.317 |
livest | +0.307 |
Neg logit contributions | |
oaded | -0.349 |
indal | -0.328 |
atorial | -0.322 |
ornia | -0.321 |
Moroc | -0.319 |
Token | creation |
Token ID | 6282 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.047 |
theless | +0.046 |
lasting | +0.046 |
wonder | +0.044 |
livest | +0.044 |
Neg logit contributions | |
oaded | -0.065 |
indal | -0.061 |
atorial | -0.060 |
ornia | -0.060 |
icion | -0.060 |
Token | of |
Token ID | 286 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
lasting | +0.625 |
\\\\\\\\\\\\\\\\ | +0.622 |
wonder | +0.586 |
theless | +0.576 |
longer | +0.536 |
Neg logit contributions | |
oaded | -1.520 |
indal | -1.456 |
atorial | -1.426 |
ornia | -1.424 |
icion | -1.423 |
Token | the |
Token ID | 262 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
oaded | +0.485 |
indal | +0.457 |
ornia | +0.448 |
atorial | +0.447 |
clusively | +0.443 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.433 |
theless | -0.425 |
lasting | -0.419 |
wonder | -0.406 |
™: | -0.405 |
Token | Federal |
Token ID | 5618 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
oaded | +0.458 |
indal | +0.435 |
ornia | +0.431 |
atorial | +0.428 |
Moroc | +0.421 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.366 |
theless | -0.358 |
lasting | -0.346 |
™: | -0.337 |
livest | -0.337 |
Token | Reserve |
Token ID | 12224 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.195 |
lasting | +1.156 |
theless | +1.127 |
wonder | +1.077 |
livest | +1.037 |
Neg logit contributions | |
oaded | -3.256 |
indal | -3.126 |
ornia | -3.088 |
atorial | -3.074 |
icion | -3.036 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
lasting | +4.938 |
\\\\\\\\\\\\\\\\ | +4.891 |
wonder | +4.718 |
theless | +4.579 |
longer | +4.451 |
Neg logit contributions | |
oaded | -6.483 |
indal | -6.217 |
atorial | -6.071 |
icion | -6.014 |
Moroc | -5.994 |
Token | and |
Token ID | 290 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.129 |
lasting | +0.126 |
theless | +0.125 |
wonder | +0.121 |
™: | +0.117 |
Neg logit contributions | |
oaded | -0.189 |
indal | -0.179 |
atorial | -0.177 |
ornia | -0.175 |
Moroc | -0.174 |
Token | how |
Token ID | 703 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
oaded | +0.773 |
indal | +0.735 |
atorial | +0.723 |
clusively | +0.715 |
ornia | +0.712 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.608 |
theless | -0.579 |
lasting | -0.577 |
™: | -0.552 |
quin | -0.544 |
Token | its |
Token ID | 663 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.913 |
lasting | +0.887 |
theless | +0.881 |
wonder | +0.861 |
livest | +0.833 |
Neg logit contributions | |
oaded | -1.037 |
indal | -0.980 |
ornia | -0.961 |
atorial | -0.959 |
clusively | -0.951 |
Token | destruction |
Token ID | 8166 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
oaded | +2.542 |
atorial | +2.452 |
ornia | +2.398 |
indal | +2.386 |
clusively | +2.371 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.477 |
theless | -2.405 |
livest | -2.341 |
hm | -2.322 |
™: | -2.304 |
Token | to |
Token ID | 284 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
oaded | +0.635 |
indal | +0.607 |
atorial | +0.594 |
icion | +0.592 |
clusively | +0.590 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.480 |
theless | -0.461 |
lasting | -0.447 |
wonder | -0.443 |
livest | -0.433 |
Token | him |
Token ID | 683 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
oaded | +0.348 |
indal | +0.332 |
icion | +0.323 |
atorial | +0.322 |
Moroc | +0.320 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.348 |
lasting | -0.334 |
theless | -0.331 |
wonder | -0.320 |
livest | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
oaded | +0.987 |
indal | +0.930 |
atorial | +0.919 |
clusively | +0.914 |
icion | +0.911 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.907 |
theless | -0.854 |
lasting | -0.818 |
wonder | -0.814 |
livest | -0.807 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
oaded | +0.707 |
indal | +0.671 |
atorial | +0.659 |
swick | +0.651 |
icion | +0.644 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.818 |
lasting | -0.804 |
theless | -0.790 |
wonder | -0.781 |
livest | -0.772 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
oaded | +0.161 |
indal | +0.153 |
atorial | +0.153 |
icion | +0.147 |
swick | +0.147 |
Neg logit contributions | |
livest | -0.227 |
\\\\\\\\\\\\\\\\ | -0.225 |
theless | -0.223 |
lasting | -0.219 |
wonder | -0.211 |
Token | Mod |
Token ID | 5841 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
oaded | +0.181 |
indal | +0.172 |
atorial | +0.168 |
icion | +0.164 |
swick | +0.162 |
Neg logit contributions | |
lasting | -0.218 |
\\\\\\\\\\\\\\\\ | -0.217 |
theless | -0.215 |
wonder | -0.210 |
livest | -0.210 |
Token | i |
Token ID | 72 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +5.926 |
lasting | +5.899 |
theless | +5.729 |
wonder | +5.708 |
longer | +5.422 |
Neg logit contributions | |
oaded | -5.575 |
indal | -5.259 |
atorial | -5.137 |
ornia | -5.091 |
icion | -5.064 |
Token | wrote |
Token ID | 2630 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.189 |
lasting | +1.106 |
theless | +1.082 |
wonder | +1.060 |
™: | +1.027 |
Neg logit contributions | |
oaded | -1.662 |
indal | -1.573 |
atorial | -1.561 |
icion | -1.532 |
clusively | -1.531 |
Token | : |
Token ID | 25 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.297 |
theless | +1.257 |
lasting | +1.249 |
wonder | +1.210 |
livest | +1.191 |
Neg logit contributions | |
oaded | -1.523 |
indal | -1.455 |
atorial | -1.418 |
clusively | -1.404 |
icion | -1.388 |
Token | " |
Token ID | 366 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.667 |
lasting | +0.666 |
wonder | +0.642 |
theless | +0.640 |
longer | +0.603 |
Neg logit contributions | |
oaded | -0.848 |
indal | -0.804 |
atorial | -0.788 |
ornia | -0.784 |
Moroc | -0.782 |
Token | ann |
Token ID | 1236 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
oaded | +1.713 |
indal | +1.654 |
icion | +1.576 |
atorial | +1.569 |
swick | +1.534 |
Neg logit contributions | |
lasting | -2.286 |
theless | -2.280 |
\\\\\\\\\\\\\\\\ | -2.273 |
wonder | -2.209 |
livest | -2.194 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.433 |
lasting | +1.413 |
theless | +1.389 |
wonder | +1.362 |
livest | +1.304 |
Neg logit contributions | |
oaded | -1.986 |
indal | -1.905 |
atorial | -1.865 |
ornia | -1.841 |
clusively | -1.840 |
Token | Ad |
Token ID | 1215 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
oaded | +0.191 |
indal | +0.183 |
atorial | +0.180 |
swick | +0.176 |
icion | +0.176 |
Neg logit contributions | |
lasting | -0.231 |
\\\\\\\\\\\\\\\\ | -0.230 |
theless | -0.229 |
livest | -0.225 |
wonder | -0.221 |
Token | Policy |
Token ID | 7820 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
oaded | +1.012 |
indal | +0.959 |
atorial | +0.926 |
icion | +0.925 |
ornia | +0.919 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.298 |
lasting | -1.275 |
theless | -1.250 |
wonder | -1.228 |
livest | -1.196 |
Token |
|
Token ID | 198 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.273 |
lasting | +0.270 |
theless | +0.262 |
wonder | +0.260 |
livest | +0.250 |
Neg logit contributions | |
oaded | -0.253 |
indal | -0.239 |
atorial | -0.232 |
ornia | -0.231 |
icion | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
oaded | +0.046 |
indal | +0.044 |
atorial | +0.044 |
icion | +0.042 |
swick | +0.042 |
Neg logit contributions | |
livest | -0.063 |
theless | -0.063 |
\\\\\\\\\\\\\\\\ | -0.063 |
lasting | -0.062 |
wonder | -0.059 |
Token | Mod |
Token ID | 5841 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
oaded | +0.241 |
indal | +0.231 |
atorial | +0.225 |
icion | +0.222 |
ornia | +0.217 |
Neg logit contributions | |
lasting | -0.297 |
theless | -0.294 |
\\\\\\\\\\\\\\\\ | -0.290 |
livest | -0.286 |
wonder | -0.282 |
Token | er |
Token ID | 263 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +4.708 |
lasting | +4.673 |
theless | +4.502 |
wonder | +4.437 |
longer | +4.214 |
Neg logit contributions | |
oaded | -6.715 |
indal | -6.463 |
atorial | -6.331 |
ornia | -6.297 |
icion | -6.267 |
Token | ator |
Token ID | 1352 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.709 |
lasting | +2.690 |
theless | +2.632 |
wonder | +2.625 |
livest | +2.515 |
Neg logit contributions | |
oaded | -1.639 |
indal | -1.546 |
atorial | -1.531 |
ornia | -1.470 |
clusively | -1.463 |
Token | Elaine |
Token ID | 41463 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.577 |
theless | +1.541 |
lasting | +1.528 |
wonder | +1.454 |
livest | +1.406 |
Neg logit contributions | |
oaded | -1.951 |
indal | -1.872 |
atorial | -1.836 |
Moroc | -1.821 |
ornia | -1.819 |
Token | Qu |
Token ID | 2264 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.855 |
lasting | +0.845 |
theless | +0.828 |
wonder | +0.809 |
livest | +0.774 |
Neg logit contributions | |
oaded | -1.023 |
indal | -0.965 |
atorial | -0.945 |
clusively | -0.935 |
Moroc | -0.932 |
Token | ij |
Token ID | 2926 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.988 |
lasting | +1.945 |
theless | +1.864 |
livest | +1.819 |
wonder | +1.799 |
Neg logit contributions | |
oaded | -1.858 |
indal | -1.807 |
atorial | -1.760 |
ornia | -1.745 |
icion | -1.709 |
Token | deal |
Token ID | 1730 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
oaded | +3.032 |
atorial | +2.858 |
indal | +2.833 |
clusively | +2.792 |
ornia | +2.785 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.228 |
theless | -2.218 |
livest | -2.060 |
lasting | -2.058 |
wonder | -2.041 |
Token | -- |
Token ID | 1377 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
oaded | +0.528 |
atorial | +0.498 |
indal | +0.493 |
clusively | +0.485 |
icion | +0.482 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.452 |
theless | -0.427 |
wonder | -0.411 |
livest | -0.407 |
quin | -0.399 |
Token | although |
Token ID | 3584 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
oaded | +0.159 |
indal | +0.150 |
atorial | +0.149 |
clusively | +0.148 |
ornia | +0.148 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.121 |
theless | -0.116 |
wonder | -0.110 |
lasting | -0.110 |
™: | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
oaded | +0.690 |
indal | +0.643 |
ornia | +0.635 |
atorial | +0.635 |
clusively | +0.633 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.775 |
theless | -0.741 |
lasting | -0.726 |
wonder | -0.710 |
quin | -0.708 |
Token | European |
Token ID | 3427 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.013 |
theless | +0.012 |
livest | +0.012 |
lasting | +0.012 |
™: | +0.012 |
Neg logit contributions | |
oaded | -0.014 |
atorial | -0.013 |
indal | -0.013 |
clusively | -0.013 |
icion | -0.013 |
Token | Commission |
Token ID | 4513 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.075 |
lasting | +1.044 |
theless | +1.043 |
wonder | +0.988 |
™: | +0.968 |
Neg logit contributions | |
oaded | -1.511 |
indal | -1.426 |
atorial | -1.422 |
icion | -1.389 |
ornia | -1.388 |
Token | pointed |
Token ID | 6235 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
lasting | +4.336 |
\\\\\\\\\\\\\\\\ | +4.236 |
wonder | +4.182 |
theless | +4.083 |
longer | +3.904 |
Neg logit contributions | |
oaded | -6.946 |
indal | -6.627 |
Moroc | -6.509 |
ornia | -6.487 |
atorial | -6.482 |
Token | out |
Token ID | 503 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.108 |
lasting | +0.106 |
theless | +0.102 |
wonder | +0.101 |
livest | +0.096 |
Neg logit contributions | |
oaded | -0.170 |
indal | -0.162 |
atorial | -0.159 |
ornia | -0.158 |
icion | -0.157 |
Token | that |
Token ID | 326 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
oaded | +1.968 |
indal | +1.817 |
clusively | +1.811 |
atorial | +1.807 |
ornia | +1.797 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.906 |
theless | -1.842 |
lasting | -1.779 |
livest | -1.771 |
wonder | -1.736 |
Token | Britain |
Token ID | 5491 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
oaded | +0.024 |
indal | +0.022 |
atorial | +0.022 |
clusively | +0.022 |
ornia | +0.022 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.023 |
theless | -0.022 |
lasting | -0.021 |
wonder | -0.021 |
livest | -0.021 |
Token | cannot |
Token ID | 2314 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.534 |
theless | +0.519 |
lasting | +0.509 |
wonder | +0.494 |
livest | +0.479 |
Neg logit contributions | |
oaded | -0.752 |
atorial | -0.718 |
indal | -0.717 |
ornia | -0.700 |
icion | -0.697 |
Token | Japan |
Token ID | 2869 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.994 |
lasting | +0.964 |
theless | +0.946 |
wonder | +0.931 |
livest | +0.897 |
Neg logit contributions | |
oaded | -0.956 |
indal | -0.899 |
atorial | -0.885 |
icion | -0.874 |
Moroc | -0.873 |
Token | as |
Token ID | 355 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.487 |
lasting | +1.458 |
theless | +1.431 |
wonder | +1.400 |
livest | +1.318 |
Neg logit contributions | |
oaded | -2.238 |
indal | -2.133 |
atorial | -2.105 |
ornia | -2.082 |
icion | -2.075 |
Token | he |
Token ID | 339 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.481 |
lasting | +0.464 |
theless | +0.461 |
wonder | +0.449 |
livest | +0.434 |
Neg logit contributions | |
oaded | -0.520 |
indal | -0.493 |
atorial | -0.487 |
ornia | -0.479 |
icion | -0.478 |
Token | and |
Token ID | 290 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.843 |
lasting | +0.788 |
theless | +0.776 |
wonder | +0.746 |
hm | +0.735 |
Neg logit contributions | |
oaded | -1.137 |
atorial | -1.069 |
indal | -1.067 |
clusively | -1.044 |
ornia | -1.040 |
Token | Prime |
Token ID | 5537 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.543 |
lasting | +0.515 |
theless | +0.514 |
wonder | +0.498 |
livest | +0.486 |
Neg logit contributions | |
oaded | -0.542 |
indal | -0.506 |
atorial | -0.501 |
icion | -0.492 |
clusively | -0.490 |
Token | Minister |
Token ID | 4139 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.923 |
lasting | +3.864 |
theless | +3.819 |
wonder | +3.736 |
livest | +3.629 |
Neg logit contributions | |
oaded | -4.066 |
indal | -3.878 |
atorial | -3.796 |
icion | -3.733 |
ornia | -3.719 |
Token | Shinzo |
Token ID | 43531 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
lasting | +5.541 |
\\\\\\\\\\\\\\\\ | +5.409 |
wonder | +5.310 |
theless | +5.196 |
longer | +5.048 |
Neg logit contributions | |
oaded | -5.698 |
indal | -5.404 |
ornia | -5.320 |
Moroc | -5.309 |
swick | -5.302 |
Token | Abe |
Token ID | 22257 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
oaded | +0.692 |
indal | +0.664 |
atorial | +0.657 |
ornia | +0.645 |
icion | +0.634 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.064 |
theless | -1.056 |
livest | -1.008 |
lasting | -0.995 |
wonder | -0.993 |
Token | issued |
Token ID | 4884 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
oaded | +0.501 |
indal | +0.476 |
atorial | +0.469 |
ornia | +0.461 |
clusively | +0.459 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.380 |
lasting | -0.355 |
theless | -0.352 |
wonder | -0.338 |
™: | -0.332 |
Token | a |
Token ID | 257 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.376 |
theless | +0.369 |
lasting | +0.355 |
wonder | +0.345 |
™: | +0.341 |
Neg logit contributions | |
oaded | -0.415 |
indal | -0.394 |
atorial | -0.389 |
icion | -0.378 |
clusively | -0.378 |
Token | joint |
Token ID | 6466 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
oaded | +0.503 |
indal | +0.481 |
atorial | +0.480 |
clusively | +0.469 |
ornia | +0.468 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.478 |
theless | -0.469 |
™: | -0.435 |
lasting | -0.432 |
wonder | -0.426 |
Token | syntax |
Token ID | 15582 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
oaded | +0.449 |
indal | +0.411 |
atorial | +0.402 |
clusively | +0.396 |
icion | +0.394 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.699 |
lasting | -0.693 |
theless | -0.685 |
wonder | -0.671 |
livest | -0.654 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
oaded | +2.322 |
indal | +2.190 |
atorial | +2.142 |
clusively | +2.128 |
icion | +2.122 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.805 |
theless | -1.776 |
lasting | -1.743 |
wonder | -1.693 |
livest | -1.663 |
Token | the |
Token ID | 262 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
oaded | +0.400 |
indal | +0.375 |
atorial | +0.369 |
clusively | +0.367 |
icion | +0.367 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.328 |
theless | -0.320 |
lasting | -0.319 |
wonder | -0.304 |
quin | -0.297 |
Token | curly |
Token ID | 45731 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
oaded | +1.078 |
indal | +1.011 |
atorial | +1.002 |
clusively | +0.991 |
icion | +0.985 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.943 |
theless | -0.922 |
lasting | -0.918 |
wonder | -0.880 |
quin | -0.862 |
Token | brace |
Token ID | 22581 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
oaded | +1.447 |
indal | +1.361 |
atorial | +1.341 |
ornia | +1.327 |
Moroc | +1.304 |
Neg logit contributions | |
theless | -1.525 |
\\\\\\\\\\\\\\\\ | -1.523 |
lasting | -1.510 |
wonder | -1.441 |
livest | -1.418 |
Token | syntax |
Token ID | 15582 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
oaded | +3.222 |
indal | +3.065 |
atorial | +3.032 |
icion | +2.971 |
ornia | +2.942 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.656 |
theless | -2.652 |
lasting | -2.622 |
wonder | -2.499 |
livest | -2.488 |
Token | e |
Token ID | 304 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
oaded | +2.989 |
indal | +2.850 |
atorial | +2.782 |
icion | +2.774 |
clusively | +2.723 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.268 |
theless | -2.233 |
lasting | -2.198 |
wonder | -2.150 |
livest | -2.100 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
oaded | +2.659 |
indal | +2.532 |
atorial | +2.494 |
ornia | +2.467 |
icion | +2.463 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.853 |
lasting | -1.844 |
theless | -1.776 |
wonder | -1.765 |
longer | -1.658 |
Token | g |
Token ID | 70 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
oaded | +0.555 |
atorial | +0.498 |
indal | +0.495 |
icion | +0.482 |
clusively | +0.469 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.211 |
lasting | -1.204 |
theless | -1.194 |
livest | -1.184 |
wonder | -1.159 |
Token | .: |
Token ID | 11207 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
oaded | +4.448 |
indal | +4.241 |
atorial | +4.164 |
ornia | +4.123 |
icion | +4.118 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -3.200 |
lasting | -3.177 |
theless | -3.104 |
wonder | -3.051 |
livest | -2.855 |
Token |
|
Token ID | 198 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
oaded | +0.925 |
indal | +0.870 |
atorial | +0.853 |
ornia | +0.842 |
clusively | +0.839 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.998 |
lasting | -0.988 |
theless | -0.974 |
wonder | -0.949 |
livest | -0.912 |
Token | had |
Token ID | 550 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.435 |
lasting | +0.413 |
theless | +0.412 |
wonder | +0.395 |
livest | +0.386 |
Neg logit contributions | |
oaded | -0.629 |
indal | -0.600 |
atorial | -0.599 |
ornia | -0.590 |
icion | -0.584 |
Token | clearly |
Token ID | 4084 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.585 |
theless | +0.551 |
lasting | +0.543 |
wonder | +0.537 |
quin | +0.534 |
Neg logit contributions | |
oaded | -0.673 |
indal | -0.637 |
clusively | -0.635 |
atorial | -0.634 |
ornia | -0.627 |
Token | gained |
Token ID | 8618 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
oaded | +0.214 |
atorial | +0.205 |
clusively | +0.204 |
indal | +0.199 |
ornia | +0.199 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.171 |
theless | -0.160 |
quin | -0.156 |
lasting | -0.154 |
wonder | -0.154 |
Token | from |
Token ID | 422 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
oaded | +1.808 |
indal | +1.727 |
atorial | +1.703 |
clusively | +1.689 |
ornia | +1.655 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.828 |
theless | -1.808 |
livest | -1.732 |
quin | -1.689 |
hm | -1.678 |
Token | its |
Token ID | 663 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.402 |
theless | +0.393 |
lasting | +0.378 |
wonder | +0.375 |
livest | +0.371 |
Neg logit contributions | |
oaded | -0.390 |
clusively | -0.364 |
indal | -0.364 |
atorial | -0.363 |
ornia | -0.362 |
Token | membership |
Token ID | 9931 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
oaded | +1.170 |
atorial | +1.105 |
clusively | +1.091 |
indal | +1.091 |
ornia | +1.086 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.326 |
theless | -1.291 |
livest | -1.255 |
lasting | -1.227 |
hm | -1.221 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
oaded | +3.218 |
indal | +3.086 |
atorial | +3.039 |
ornia | +3.027 |
clusively | +3.009 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.687 |
theless | -2.635 |
livest | -2.490 |
lasting | -2.468 |
wonder | -2.436 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.421 |
theless | +0.408 |
lasting | +0.398 |
wonder | +0.390 |
livest | +0.384 |
Neg logit contributions | |
oaded | -0.426 |
atorial | -0.397 |
indal | -0.396 |
ornia | -0.394 |
clusively | -0.391 |
Token | EU |
Token ID | 4576 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
oaded | +0.310 |
atorial | +0.292 |
indal | +0.292 |
clusively | +0.290 |
icion | +0.284 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.289 |
theless | -0.282 |
livest | -0.270 |
™: | -0.267 |
lasting | -0.267 |
Token | has |
Token ID | 468 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
oaded | +0.536 |
atorial | +0.514 |
indal | +0.514 |
ornia | +0.502 |
efficients | +0.501 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.359 |
theless | -0.347 |
lasting | -0.344 |
™: | -0.325 |
wonder | -0.323 |
Token | benefited |
Token ID | 25050 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.179 |
theless | +1.116 |
lasting | +1.099 |
wonder | +1.089 |
livest | +1.071 |
Neg logit contributions | |
oaded | -1.431 |
atorial | -1.355 |
indal | -1.350 |
clusively | -1.345 |
ornia | -1.327 |
Token | is |
Token ID | 318 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
oaded | +1.603 |
indal | +1.519 |
atorial | +1.495 |
clusively | +1.482 |
ornia | +1.474 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.119 |
lasting | -1.100 |
theless | -1.074 |
wonder | -1.045 |
livest | -1.037 |
Token | now |
Token ID | 783 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.330 |
theless | +0.315 |
lasting | +0.312 |
wonder | +0.304 |
livest | +0.295 |
Neg logit contributions | |
oaded | -0.392 |
indal | -0.371 |
clusively | -0.366 |
atorial | -0.362 |
ornia | -0.360 |
Token | a |
Token ID | 257 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
oaded | +2.088 |
clusively | +1.992 |
indal | +1.982 |
Moroc | +1.935 |
swick | +1.929 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.867 |
theless | -1.804 |
lasting | -1.767 |
wonder | -1.720 |
quin | -1.685 |
Token | " |
Token ID | 366 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.910 |
lasting | +0.868 |
theless | +0.864 |
wonder | +0.830 |
™: | +0.815 |
Neg logit contributions | |
oaded | -1.022 |
indal | -0.976 |
clusively | -0.968 |
atorial | -0.963 |
ornia | -0.951 |
Token | social |
Token ID | 14557 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
oaded | +0.828 |
indal | +0.787 |
clusively | +0.780 |
ornia | +0.777 |
atorial | +0.771 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.804 |
lasting | -0.796 |
wonder | -0.777 |
theless | -0.777 |
livest | -0.739 |
Token | justice |
Token ID | 5316 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
oaded | +1.777 |
atorial | +1.682 |
indal | +1.670 |
clusively | +1.669 |
ornia | +1.667 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.708 |
theless | -1.619 |
lasting | -1.592 |
™: | -1.554 |
livest | -1.540 |
Token | magnet |
Token ID | 19972 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
oaded | +2.842 |
atorial | +2.777 |
indal | +2.731 |
clusively | +2.720 |
ornia | +2.716 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.739 |
theless | -2.613 |
lasting | -2.592 |
livest | -2.447 |
wonder | -2.445 |
Token | school |
Token ID | 1524 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
oaded | +1.338 |
indal | +1.269 |
atorial | +1.260 |
ornia | +1.250 |
clusively | +1.243 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.124 |
theless | -1.101 |
lasting | -1.076 |
wonder | -1.030 |
livest | -1.027 |
Token | ." |
Token ID | 526 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
oaded | +1.623 |
indal | +1.523 |
clusively | +1.511 |
atorial | +1.508 |
ornia | +1.488 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.406 |
theless | -1.349 |
lasting | -1.302 |
wonder | -1.283 |
livest | -1.273 |
Token | As |
Token ID | 1081 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
oaded | +0.210 |
indal | +0.197 |
atorial | +0.193 |
swick | +0.192 |
ornia | +0.187 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.232 |
lasting | -0.229 |
theless | -0.226 |
livest | -0.222 |
wonder | -0.221 |
Token | a |
Token ID | 257 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
oaded | +1.116 |
indal | +1.049 |
atorial | +1.025 |
clusively | +1.021 |
icion | +1.018 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.966 |
theless | -0.915 |
lasting | -0.898 |
wonder | -0.871 |
livest | -0.850 |
Token |
|
Token ID | 198 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
lasting | +0.486 |
\\\\\\\\\\\\\\\\ | +0.482 |
wonder | +0.472 |
theless | +0.464 |
longer | +0.448 |
Neg logit contributions | |
oaded | -0.580 |
indal | -0.547 |
ornia | -0.527 |
efficients | -0.524 |
icion | -0.523 |
Token |
|
Token ID | 198 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.925 |
theless | +0.917 |
livest | +0.911 |
lasting | +0.908 |
wonder | +0.876 |
Neg logit contributions | |
oaded | -0.734 |
indal | -0.698 |
atorial | -0.692 |
icion | -0.672 |
clusively | -0.670 |
Token | Action |
Token ID | 12502 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
lasting | +0.815 |
theless | +0.803 |
\\\\\\\\\\\\\\\\ | +0.798 |
wonder | +0.781 |
livest | +0.773 |
Neg logit contributions | |
oaded | -0.695 |
indal | -0.657 |
atorial | -0.652 |
icion | -0.641 |
ornia | -0.631 |
Token | News |
Token ID | 3000 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.865 |
lasting | +1.840 |
theless | +1.799 |
wonder | +1.745 |
livest | +1.650 |
Neg logit contributions | |
oaded | -3.042 |
indal | -2.877 |
atorial | -2.833 |
Moroc | -2.827 |
ornia | -2.824 |
Token | J |
Token ID | 449 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.879 |
lasting | +1.832 |
theless | +1.808 |
wonder | +1.762 |
livest | +1.676 |
Neg logit contributions | |
oaded | -2.633 |
indal | -2.500 |
atorial | -2.447 |
Moroc | -2.438 |
clusively | -2.435 |
Token | ax |
Token ID | 897 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
oaded | +1.257 |
indal | +1.179 |
atorial | +1.092 |
ornia | +1.081 |
clusively | +1.064 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.741 |
lasting | -2.710 |
theless | -2.675 |
wonder | -2.609 |
livest | -2.563 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
oaded | +4.394 |
indal | +4.073 |
clusively | +4.049 |
atorial | +3.989 |
ornia | +3.982 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -3.025 |
theless | -2.933 |
lasting | -2.898 |
wonder | -2.749 |
livest | -2.743 |
Token | J |
Token ID | 449 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.795 |
lasting | +1.751 |
theless | +1.724 |
wonder | +1.678 |
livest | +1.617 |
Neg logit contributions | |
oaded | -1.869 |
indal | -1.770 |
atorial | -1.745 |
icion | -1.728 |
Moroc | -1.720 |
Token | SO |
Token ID | 15821 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
oaded | +2.250 |
indal | +2.140 |
atorial | +2.037 |
ornia | +2.001 |
clusively | +1.968 |
Neg logit contributions | |
lasting | -4.112 |
\\\\\\\\\\\\\\\\ | -4.108 |
theless | -4.074 |
wonder | -3.949 |
livest | -3.889 |
Token | why |
Token ID | 1521 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
oaded | +3.619 |
indal | +3.428 |
clusively | +3.361 |
icion | +3.355 |
ornia | +3.353 |
Neg logit contributions | |
theless | -3.007 |
\\\\\\\\\\\\\\\\ | -2.964 |
lasting | -2.920 |
wonder | -2.790 |
livest | -2.749 |
Token | the |
Token ID | 262 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.660 |
lasting | +0.645 |
theless | +0.638 |
wonder | +0.619 |
livest | +0.600 |
Neg logit contributions | |
oaded | -0.681 |
indal | -0.643 |
atorial | -0.639 |
icion | -0.634 |
ornia | -0.628 |
Token | 's |
Token ID | 338 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.790 |
theless | +0.766 |
lasting | +0.752 |
wonder | +0.720 |
livest | +0.707 |
Neg logit contributions | |
oaded | -1.102 |
indal | -1.041 |
atorial | -1.035 |
ornia | -1.028 |
clusively | -1.027 |
Token | rav |
Token ID | 24343 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
oaded | +0.915 |
clusively | +0.867 |
indal | +0.864 |
atorial | +0.855 |
ornia | +0.843 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.805 |
theless | -0.764 |
lasting | -0.744 |
hm | -0.720 |
™: | -0.720 |
Token | ines |
Token ID | 1127 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.452 |
lasting | +1.416 |
theless | +1.400 |
wonder | +1.349 |
livest | +1.294 |
Neg logit contributions | |
oaded | -1.931 |
indal | -1.844 |
atorial | -1.826 |
icion | -1.791 |
clusively | -1.788 |
Token | . |
Token ID | 13 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
oaded | +0.833 |
indal | +0.774 |
atorial | +0.773 |
clusively | +0.761 |
ornia | +0.760 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.714 |
theless | -0.693 |
lasting | -0.662 |
livest | -0.651 |
wonder | -0.644 |
Token | The |
Token ID | 383 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
oaded | +0.902 |
atorial | +0.844 |
indal | +0.830 |
swick | +0.824 |
icion | +0.803 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.043 |
theless | -1.019 |
livest | -1.006 |
lasting | -1.000 |
wonder | -0.979 |
Token | result |
Token ID | 1255 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
oaded | +0.596 |
indal | +0.563 |
atorial | +0.560 |
clusively | +0.556 |
ornia | +0.551 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.503 |
theless | -0.470 |
lasting | -0.460 |
™: | -0.446 |
livest | -0.446 |
Token | gr |
Token ID | 1036 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
oaded | +3.435 |
atorial | +3.280 |
indal | +3.278 |
clusively | +3.183 |
ornia | +3.179 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.783 |
theless | -2.691 |
lasting | -2.589 |
livest | -2.546 |
wonder | -2.504 |
Token | aces |
Token ID | 2114 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.541 |
lasting | +0.539 |
theless | +0.527 |
wonder | +0.514 |
livest | +0.493 |
Neg logit contributions | |
oaded | -0.591 |
indal | -0.553 |
atorial | -0.548 |
ornia | -0.537 |
icion | -0.537 |
Token | the |
Token ID | 262 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
oaded | +0.671 |
indal | +0.629 |
clusively | +0.623 |
atorial | +0.617 |
icion | +0.607 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.639 |
theless | -0.605 |
lasting | -0.603 |
wonder | -0.587 |
livest | -0.568 |
Token | underside |
Token ID | 44929 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.038 |
theless | +0.036 |
lasting | +0.036 |
wonder | +0.034 |
livest | +0.034 |
Neg logit contributions | |
oaded | -0.044 |
indal | -0.042 |
atorial | -0.041 |
clusively | -0.041 |
icion | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
oaded | +0.346 |
indal | +0.331 |
atorial | +0.326 |
Moroc | +0.324 |
ornia | +0.324 |
Neg logit contributions | |
lasting | -0.135 |
\\\\\\\\\\\\\\\\ | -0.132 |
wonder | -0.128 |
theless | -0.123 |
longer | -0.115 |
Token | is |
Token ID | 318 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
oaded | +2.682 |
indal | +2.571 |
atorial | +2.567 |
icion | +2.510 |
clusively | +2.507 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.389 |
lasting | -2.260 |
theless | -2.246 |
™: | -2.160 |
ishable | -2.152 |
Token | about |
Token ID | 546 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.427 |
theless | +0.404 |
lasting | +0.392 |
™: | +0.387 |
quin | +0.386 |
Neg logit contributions | |
oaded | -0.509 |
clusively | -0.484 |
atorial | -0.479 |
indal | -0.479 |
ornia | -0.474 |
Token | 6 |
Token ID | 718 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.197 |
theless | +0.186 |
lasting | +0.183 |
livest | +0.179 |
wonder | +0.176 |
Neg logit contributions | |
oaded | -0.271 |
clusively | -0.259 |
indal | -0.253 |
atorial | -0.253 |
ornia | -0.250 |
Token | , |
Token ID | 11 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
oaded | +0.092 |
indal | +0.087 |
atorial | +0.085 |
clusively | +0.084 |
icion | +0.084 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.076 |
lasting | -0.075 |
theless | -0.075 |
wonder | -0.071 |
livest | -0.070 |
Token | 000 |
Token ID | 830 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.673 |
lasting | +0.665 |
theless | +0.652 |
wonder | +0.638 |
livest | +0.599 |
Neg logit contributions | |
oaded | -1.009 |
indal | -0.956 |
atorial | -0.940 |
ornia | -0.936 |
Moroc | -0.928 |
Token | Western |
Token ID | 4885 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.689 |
theless | +0.673 |
lasting | +0.666 |
wonder | +0.648 |
™: | +0.624 |
Neg logit contributions | |
oaded | -0.853 |
indal | -0.804 |
atorial | -0.786 |
Moroc | -0.785 |
ornia | -0.780 |
Token | ers |
Token ID | 364 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
oaded | +0.903 |
indal | +0.841 |
atorial | +0.832 |
icion | +0.829 |
ornia | +0.825 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.718 |
theless | -0.684 |
lasting | -0.676 |
wonder | -0.650 |
livest | -0.646 |
Token | and |
Token ID | 290 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.671 |
theless | +1.615 |
lasting | +1.590 |
wonder | +1.546 |
livest | +1.495 |
Neg logit contributions | |
oaded | -2.015 |
indal | -1.917 |
atorial | -1.874 |
ornia | -1.855 |
Moroc | -1.849 |
Token | 30 |
Token ID | 1542 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.853 |
theless | +0.797 |
lasting | +0.779 |
wonder | +0.772 |
quin | +0.764 |
Neg logit contributions | |
oaded | -1.091 |
indal | -1.043 |
atorial | -1.024 |
ornia | -1.017 |
clusively | -1.013 |
Token | , |
Token ID | 11 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.545 |
lasting | +0.540 |
theless | +0.526 |
wonder | +0.518 |
™: | +0.489 |
Neg logit contributions | |
oaded | -0.748 |
indal | -0.711 |
atorial | -0.696 |
Moroc | -0.692 |
ornia | -0.690 |
Token | 000 |
Token ID | 830 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.071 |
theless | +1.051 |
lasting | +1.037 |
wonder | +1.007 |
livest | +0.988 |
Neg logit contributions | |
oaded | -1.364 |
indal | -1.281 |
atorial | -1.261 |
ornia | -1.259 |
icion | -1.248 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.482 |
theless | +0.470 |
lasting | +0.463 |
wonder | +0.458 |
livest | +0.438 |
Neg logit contributions | |
oaded | -0.619 |
indal | -0.593 |
ornia | -0.581 |
atorial | -0.580 |
efficients | -0.576 |
Token | said |
Token ID | 531 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.585 |
theless | +0.572 |
lasting | +0.549 |
wonder | +0.549 |
quin | +0.528 |
Neg logit contributions | |
oaded | -0.681 |
indal | -0.661 |
atorial | -0.655 |
ornia | -0.653 |
clusively | -0.641 |
Token | Dr |
Token ID | 1583 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
oaded | +0.638 |
indal | +0.606 |
ornia | +0.594 |
atorial | +0.592 |
Moroc | +0.589 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.681 |
lasting | -0.659 |
theless | -0.650 |
wonder | -0.635 |
™: | -0.618 |
Token | . |
Token ID | 13 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.406 |
lasting | +0.399 |
theless | +0.396 |
wonder | +0.381 |
livest | +0.366 |
Neg logit contributions | |
oaded | -0.536 |
indal | -0.514 |
atorial | -0.504 |
ornia | -0.501 |
icion | -0.499 |
Token | Colt |
Token ID | 37360 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
oaded | +1.358 |
atorial | +1.278 |
indal | +1.275 |
ornia | +1.254 |
clusively | +1.238 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.555 |
theless | -1.526 |
lasting | -1.523 |
livest | -1.461 |
wonder | -1.450 |
Token | Ke |
Token ID | 3873 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
oaded | +3.905 |
indal | +3.715 |
atorial | +3.622 |
ornia | +3.611 |
icion | +3.598 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -3.724 |
lasting | -3.662 |
theless | -3.555 |
livest | -3.515 |
wonder | -3.481 |
Token | o |
Token ID | 78 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
oaded | +0.554 |
indal | +0.534 |
atorial | +0.526 |
ornia | +0.512 |
icion | +0.510 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.556 |
lasting | -0.554 |
theless | -0.546 |
wonder | -0.527 |
livest | -0.519 |
Token | - |
Token ID | 12 |
Feature activation | -7.85e-03 |
Pos logit contributions | |
oaded | +0.302 |
indal | +0.288 |
atorial | +0.284 |
ornia | +0.282 |
icion | +0.277 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.278 |
lasting | -0.276 |
theless | -0.273 |
wonder | -0.265 |
livest | -0.258 |
Token | Me |
Token ID | 5308 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
lasting | +0.012 |
\\\\\\\\\\\\\\\\ | +0.012 |
theless | +0.012 |
wonder | +0.012 |
livest | +0.012 |
Neg logit contributions | |
oaded | -0.011 |
indal | -0.010 |
atorial | -0.010 |
ornia | -0.010 |
icion | -0.010 |
Token | ier |
Token ID | 959 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.007 |
lasting | +1.990 |
theless | +1.936 |
wonder | +1.894 |
livest | +1.831 |
Neg logit contributions | |
oaded | -2.173 |
indal | -2.068 |
atorial | -2.030 |
ornia | -2.009 |
icion | -2.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.079 |
lasting | +0.078 |
theless | +0.076 |
wonder | +0.075 |
livest | +0.071 |
Neg logit contributions | |
oaded | -0.110 |
indal | -0.105 |
atorial | -0.103 |
ornia | -0.102 |
Moroc | -0.102 |
Token | deals |
Token ID | 7529 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
oaded | +0.351 |
atorial | +0.333 |
ornia | +0.328 |
indal | +0.328 |
clusively | +0.323 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.355 |
theless | -0.341 |
lasting | -0.337 |
™: | -0.323 |
wonder | -0.320 |
Token | with |
Token ID | 351 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.495 |
theless | +0.486 |
lasting | +0.475 |
livest | +0.463 |
wonder | +0.461 |
Neg logit contributions | |
oaded | -0.440 |
indal | -0.407 |
clusively | -0.402 |
ornia | -0.401 |
atorial | -0.398 |
Token | the |
Token ID | 262 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.719 |
theless | +0.701 |
lasting | +0.688 |
wonder | +0.671 |
™: | +0.664 |
Neg logit contributions | |
oaded | -0.739 |
indal | -0.688 |
ornia | -0.683 |
atorial | -0.678 |
clusively | -0.677 |
Token | fires |
Token ID | 12252 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.468 |
theless | +0.458 |
™: | +0.433 |
lasting | +0.433 |
livest | +0.424 |
Neg logit contributions | |
oaded | -0.559 |
indal | -0.530 |
ornia | -0.529 |
clusively | -0.524 |
atorial | -0.522 |
Token | , |
Token ID | 11 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.769 |
theless | +1.718 |
lasting | +1.681 |
wonder | +1.651 |
livest | +1.603 |
Neg logit contributions | |
oaded | -2.309 |
indal | -2.175 |
ornia | -2.161 |
atorial | -2.142 |
clusively | -2.129 |
Token | with |
Token ID | 351 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.957 |
theless | +0.925 |
lasting | +0.885 |
wonder | +0.873 |
™: | +0.858 |
Neg logit contributions | |
oaded | -1.232 |
indal | -1.159 |
atorial | -1.151 |
ornia | -1.143 |
Moroc | -1.130 |
Token | two |
Token ID | 734 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.457 |
theless | +0.438 |
lasting | +0.434 |
wonder | +0.423 |
™: | +0.417 |
Neg logit contributions | |
oaded | -0.467 |
indal | -0.433 |
atorial | -0.428 |
ornia | -0.423 |
clusively | -0.420 |
Token | fire |
Token ID | 2046 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.822 |
theless | +0.791 |
lasting | +0.781 |
wonder | +0.756 |
™: | +0.739 |
Neg logit contributions | |
oaded | -0.883 |
indal | -0.836 |
atorial | -0.827 |
ornia | -0.814 |
Moroc | -0.812 |
Token | fighting |
Token ID | 26594 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.049 |
lasting | +1.037 |
theless | +1.021 |
wonder | +0.997 |
™: | +0.964 |
Neg logit contributions | |
oaded | -1.001 |
indal | -0.935 |
atorial | -0.932 |
Moroc | -0.917 |
ornia | -0.912 |
Token | planes |
Token ID | 13016 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.323 |
theless | +0.310 |
lasting | +0.308 |
wonder | +0.295 |
livest | +0.291 |
Neg logit contributions | |
oaded | -0.307 |
indal | -0.288 |
atorial | -0.286 |
ornia | -0.282 |
Moroc | -0.279 |
Token | sent |
Token ID | 1908 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
oaded | +1.122 |
clusively | +1.075 |
indal | +1.074 |
atorial | +1.062 |
ornia | +1.060 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.985 |
theless | -0.918 |
isite | -0.869 |
wonder | -0.858 |
livest | -0.856 |
Token | War |
Token ID | 13195 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
oaded | +0.363 |
indal | +0.343 |
icion | +0.336 |
atorial | +0.335 |
clusively | +0.330 |
Neg logit contributions | |
lasting | -0.368 |
\\\\\\\\\\\\\\\\ | -0.366 |
theless | -0.362 |
wonder | -0.354 |
livest | -0.335 |
Token | riors |
Token ID | 8657 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
oaded | +0.263 |
atorial | +0.257 |
indal | +0.252 |
swick | +0.241 |
icion | +0.238 |
Neg logit contributions | |
theless | -0.576 |
\\\\\\\\\\\\\\\\ | -0.574 |
lasting | -0.566 |
wonder | -0.559 |
livest | -0.550 |
Token | . |
Token ID | 13 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.387 |
theless | +0.380 |
lasting | +0.379 |
wonder | +0.370 |
livest | +0.347 |
Neg logit contributions | |
oaded | -0.496 |
indal | -0.471 |
atorial | -0.463 |
clusively | -0.457 |
icion | -0.452 |
Token | Glasgow |
Token ID | 23995 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
oaded | +0.579 |
indal | +0.545 |
atorial | +0.539 |
clusively | +0.526 |
icion | +0.526 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.589 |
lasting | -0.583 |
theless | -0.573 |
wonder | -0.563 |
livest | -0.539 |
Token | Warriors |
Token ID | 12090 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
oaded | +0.292 |
indal | +0.278 |
atorial | +0.271 |
swick | +0.269 |
icion | +0.268 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.269 |
lasting | -0.265 |
theless | -0.263 |
wonder | -0.255 |
quin | -0.243 |
Token | appearances |
Token ID | 11057 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
oaded | +0.866 |
indal | +0.837 |
atorial | +0.823 |
clusively | +0.817 |
icion | +0.803 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.749 |
theless | -0.728 |
lasting | -0.716 |
wonder | -0.688 |
isite | -0.664 |
Token | and |
Token ID | 290 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
oaded | +0.430 |
indal | +0.409 |
atorial | +0.397 |
clusively | +0.397 |
icion | +0.394 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.328 |
theless | -0.316 |
lasting | -0.303 |
wonder | -0.300 |
hm | -0.288 |
Token | European |
Token ID | 3427 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
oaded | +0.278 |
indal | +0.260 |
atorial | +0.260 |
clusively | +0.258 |
icion | +0.254 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.306 |
theless | -0.294 |
lasting | -0.291 |
wonder | -0.283 |
hm | -0.276 |
Token | appearances |
Token ID | 11057 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
oaded | +0.275 |
indal | +0.262 |
atorial | +0.259 |
ornia | +0.255 |
icion | +0.254 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.176 |
lasting | -0.171 |
theless | -0.167 |
wonder | -0.163 |
livest | -0.154 |
Token | in |
Token ID | 287 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
oaded | +0.117 |
indal | +0.111 |
atorial | +0.109 |
clusively | +0.108 |
icion | +0.108 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.093 |
theless | -0.089 |
lasting | -0.086 |
wonder | -0.085 |
hm | -0.082 |
Token | brackets |
Token ID | 28103 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
oaded | +0.639 |
clusively | +0.605 |
indal | +0.599 |
atorial | +0.596 |
efficients | +0.581 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.663 |
theless | -0.642 |
lasting | -0.638 |
wonder | -0.611 |
™: | -0.595 |
Token | Wil |
Token ID | 5187 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.161 |
lasting | +0.155 |
theless | +0.153 |
wonder | +0.149 |
™: | +0.144 |
Neg logit contributions | |
oaded | -0.194 |
indal | -0.185 |
Moroc | -0.182 |
atorial | -0.181 |
ornia | -0.180 |
Token | kins |
Token ID | 5331 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
oaded | +0.482 |
indal | +0.457 |
atorial | +0.446 |
icion | +0.442 |
ornia | +0.440 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.425 |
lasting | -0.424 |
wonder | -0.408 |
theless | -0.408 |
livest | -0.387 |
Token | � |
Token ID | 447 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.200 |
lasting | +0.193 |
theless | +0.192 |
wonder | +0.184 |
livest | +0.180 |
Neg logit contributions | |
oaded | -0.238 |
indal | -0.233 |
ornia | -0.226 |
atorial | -0.225 |
icion | -0.222 |
Token | � |
Token ID | 247 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
theless | +0.174 |
\\\\\\\\\\\\\\\\ | +0.172 |
lasting | +0.167 |
wonder | +0.166 |
livest | +0.162 |
Neg logit contributions | |
oaded | -0.144 |
ornia | -0.139 |
atorial | -0.137 |
indal | -0.136 |
icion | -0.133 |
Token | rock |
Token ID | 3881 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
oaded | +0.775 |
indal | +0.751 |
ornia | +0.733 |
atorial | +0.728 |
Moroc | +0.716 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.651 |
lasting | -0.628 |
theless | -0.620 |
wonder | -0.607 |
livest | -0.590 |
Token | - |
Token ID | 12 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
lasting | +0.060 |
\\\\\\\\\\\\\\\\ | +0.059 |
wonder | +0.057 |
theless | +0.057 |
longer | +0.054 |
Neg logit contributions | |
oaded | -0.082 |
indal | -0.077 |
atorial | -0.076 |
ornia | -0.075 |
Moroc | -0.075 |
Token | wall |
Token ID | 11930 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
oaded | +0.067 |
indal | +0.064 |
atorial | +0.063 |
Moroc | +0.063 |
ornia | +0.063 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.040 |
lasting | -0.040 |
theless | -0.039 |
wonder | -0.038 |
longer | -0.036 |
Token | aby |
Token ID | 3930 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
oaded | +0.968 |
indal | +0.920 |
atorial | +0.898 |
ornia | +0.894 |
icion | +0.882 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.945 |
lasting | -0.940 |
theless | -0.912 |
wonder | -0.904 |
livest | -0.862 |
Token | ( |
Token ID | 357 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
oaded | +0.653 |
indal | +0.632 |
ornia | +0.617 |
atorial | +0.611 |
Moroc | +0.606 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.497 |
theless | -0.484 |
lasting | -0.479 |
wonder | -0.464 |
livest | -0.453 |
Token | Pet |
Token ID | 25803 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.966 |
lasting | +0.960 |
theless | +0.937 |
wonder | +0.929 |
livest | +0.885 |
Neg logit contributions | |
oaded | -0.986 |
indal | -0.935 |
atorial | -0.912 |
ornia | -0.911 |
Moroc | -0.899 |
Token | rog |
Token ID | 3828 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
oaded | +0.606 |
indal | +0.557 |
atorial | +0.541 |
ornia | +0.535 |
icion | +0.531 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.167 |
lasting | -1.159 |
theless | -1.134 |
wonder | -1.128 |
longer | -1.086 |
Token | for |
Token ID | 329 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
oaded | +0.185 |
indal | +0.176 |
atorial | +0.173 |
ornia | +0.172 |
Moroc | +0.172 |
Neg logit contributions | |
lasting | -0.103 |
\\\\\\\\\\\\\\\\ | -0.103 |
wonder | -0.098 |
theless | -0.098 |
longer | -0.091 |
Token | them |
Token ID | 606 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.422 |
theless | +0.406 |
lasting | +0.396 |
livest | +0.389 |
wonder | +0.384 |
Neg logit contributions | |
oaded | -0.416 |
indal | -0.392 |
clusively | -0.385 |
atorial | -0.384 |
icion | -0.384 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
oaded | +0.815 |
indal | +0.783 |
ornia | +0.769 |
atorial | +0.768 |
Moroc | +0.767 |
Neg logit contributions | |
lasting | -0.411 |
\\\\\\\\\\\\\\\\ | -0.403 |
wonder | -0.391 |
theless | -0.383 |
longer | -0.362 |
Token | appeal |
Token ID | 5198 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.202 |
lasting | +0.192 |
theless | +0.191 |
livest | +0.179 |
™: | +0.177 |
Neg logit contributions | |
oaded | -0.233 |
indal | -0.222 |
atorial | -0.219 |
clusively | -0.216 |
icion | -0.213 |
Token | to |
Token ID | 284 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.834 |
lasting | +0.815 |
theless | +0.799 |
wonder | +0.780 |
livest | +0.742 |
Neg logit contributions | |
oaded | -1.336 |
indal | -1.276 |
atorial | -1.251 |
icion | -1.244 |
clusively | -1.244 |
Token | millennial |
Token ID | 46451 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.761 |
theless | +0.733 |
lasting | +0.713 |
livest | +0.694 |
wonder | +0.692 |
Neg logit contributions | |
oaded | -0.774 |
indal | -0.726 |
clusively | -0.723 |
icion | -0.714 |
atorial | -0.712 |
Token | voters |
Token ID | 4446 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.430 |
theless | +1.378 |
lasting | +1.373 |
livest | +1.318 |
wonder | +1.315 |
Neg logit contributions | |
oaded | -1.308 |
indal | -1.229 |
ornia | -1.202 |
atorial | -1.201 |
icion | -1.201 |
Token | . |
Token ID | 13 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.312 |
theless | +0.301 |
lasting | +0.299 |
wonder | +0.288 |
livest | +0.284 |
Neg logit contributions | |
oaded | -0.400 |
indal | -0.375 |
atorial | -0.372 |
icion | -0.367 |
clusively | -0.364 |
Token | And |
Token ID | 843 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
oaded | +0.112 |
atorial | +0.106 |
indal | +0.106 |
swick | +0.104 |
icion | +0.103 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.135 |
theless | -0.134 |
lasting | -0.133 |
livest | -0.132 |
wonder | -0.127 |
Token | a |
Token ID | 257 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
oaded | +2.601 |
indal | +2.475 |
icion | +2.441 |
atorial | +2.395 |
ornia | +2.389 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.496 |
theless | -2.361 |
lasting | -2.278 |
livest | -2.258 |
™: | -2.223 |
Token | lot |
Token ID | 1256 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.503 |
theless | +0.484 |
lasting | +0.479 |
wonder | +0.461 |
™: | +0.457 |
Neg logit contributions | |
oaded | -0.558 |
indal | -0.529 |
atorial | -0.524 |
icion | -0.518 |
clusively | -0.517 |
Token | users |
Token ID | 2985 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.796 |
theless | +0.783 |
lasting | +0.771 |
wonder | +0.747 |
quin | +0.731 |
Neg logit contributions | |
oaded | -0.905 |
indal | -0.857 |
icion | -0.856 |
atorial | -0.850 |
clusively | -0.847 |
Token | of |
Token ID | 286 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.832 |
lasting | +0.824 |
theless | +0.794 |
wonder | +0.787 |
livest | +0.727 |
Neg logit contributions | |
oaded | -1.502 |
indal | -1.437 |
atorial | -1.413 |
ornia | -1.402 |
Moroc | -1.399 |
Token | cannabis |
Token ID | 9499 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.127 |
lasting | +1.104 |
theless | +1.093 |
wonder | +1.061 |
livest | +1.024 |
Neg logit contributions | |
oaded | -1.168 |
indal | -1.109 |
atorial | -1.080 |
ornia | -1.072 |
icion | -1.070 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
oaded | +0.772 |
indal | +0.734 |
atorial | +0.725 |
icion | +0.723 |
ornia | +0.720 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.618 |
theless | -0.599 |
lasting | -0.596 |
wonder | -0.570 |
livest | -0.562 |
Token | Not |
Token ID | 1892 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
oaded | +0.197 |
indal | +0.186 |
atorial | +0.186 |
icion | +0.182 |
swick | +0.182 |
Neg logit contributions | |
lasting | -0.261 |
theless | -0.257 |
\\\\\\\\\\\\\\\\ | -0.256 |
livest | -0.255 |
wonder | -0.249 |
Token | necessarily |
Token ID | 6646 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
oaded | +0.106 |
indal | +0.101 |
icion | +0.099 |
clusively | +0.099 |
ornia | +0.099 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.094 |
lasting | -0.091 |
theless | -0.091 |
quin | -0.088 |
wonder | -0.088 |
Token | smoking |
Token ID | 9216 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.723 |
lasting | +0.704 |
theless | +0.704 |
wonder | +0.681 |
quin | +0.665 |
Neg logit contributions | |
oaded | -0.816 |
indal | -0.777 |
icion | -0.768 |
atorial | -0.767 |
clusively | -0.767 |
Token | a |
Token ID | 257 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.320 |
lasting | +1.288 |
theless | +1.281 |
wonder | +1.238 |
livest | +1.185 |
Neg logit contributions | |
oaded | -1.714 |
indal | -1.625 |
atorial | -1.601 |
icion | -1.586 |
clusively | -1.583 |
Token | joint |
Token ID | 6466 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.824 |
theless | +0.789 |
lasting | +0.788 |
wonder | +0.762 |
™: | +0.737 |
Neg logit contributions | |
oaded | -0.962 |
indal | -0.920 |
atorial | -0.912 |
icion | -0.899 |
clusively | -0.897 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
oaded | +2.442 |
atorial | +2.287 |
indal | +2.271 |
icion | +2.267 |
clusively | +2.248 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.081 |
theless | -1.995 |
lasting | -1.960 |
livest | -1.912 |
wonder | -1.881 |
Token | but |
Token ID | 475 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
oaded | +0.204 |
indal | +0.198 |
atorial | +0.193 |
icion | +0.192 |
ornia | +0.191 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.127 |
theless | -0.124 |
lasting | -0.121 |
wonder | -0.117 |
quin | -0.113 |
Token | Mc |
Token ID | 1982 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.451 |
lasting | +0.450 |
theless | +0.434 |
wonder | +0.431 |
livest | +0.407 |
Neg logit contributions | |
oaded | -0.531 |
indal | -0.505 |
atorial | -0.494 |
Moroc | -0.490 |
ornia | -0.490 |
Token | le |
Token ID | 293 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
oaded | +0.540 |
indal | +0.498 |
ornia | +0.463 |
clusively | +0.457 |
icion | +0.452 |
Neg logit contributions | |
lasting | -1.252 |
\\\\\\\\\\\\\\\\ | -1.246 |
theless | -1.241 |
livest | -1.222 |
wonder | -1.221 |
Token | od |
Token ID | 375 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.383 |
lasting | +2.370 |
theless | +2.275 |
wonder | +2.246 |
livest | +2.163 |
Neg logit contributions | |
oaded | -2.942 |
indal | -2.796 |
ornia | -2.720 |
atorial | -2.715 |
icion | -2.670 |
Token | Beth |
Token ID | 19223 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.265 |
lasting | +0.261 |
theless | +0.253 |
wonder | +0.251 |
livest | +0.243 |
Neg logit contributions | |
oaded | -0.313 |
indal | -0.301 |
atorial | -0.290 |
ornia | -0.290 |
swick | -0.287 |
Token | une |
Token ID | 1726 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
oaded | +0.865 |
indal | +0.847 |
ornia | +0.776 |
atorial | +0.740 |
icion | +0.730 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -3.074 |
livest | -3.047 |
theless | -3.036 |
lasting | -3.014 |
wonder | -2.926 |
Token | Boulevard |
Token ID | 23889 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
oaded | +0.882 |
indal | +0.852 |
atorial | +0.830 |
ornia | +0.827 |
Moroc | +0.819 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.676 |
lasting | -0.668 |
theless | -0.657 |
wonder | -0.631 |
livest | -0.612 |
Token | . |
Token ID | 13 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.379 |
lasting | +2.343 |
theless | +2.295 |
wonder | +2.263 |
livest | +2.137 |
Neg logit contributions | |
oaded | -3.214 |
indal | -3.061 |
atorial | -2.988 |
ornia | -2.981 |
Moroc | -2.972 |
Token | The |
Token ID | 383 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
oaded | +0.568 |
indal | +0.539 |
atorial | +0.532 |
swick | +0.528 |
icion | +0.515 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.619 |
lasting | -0.611 |
theless | -0.599 |
wonder | -0.595 |
livest | -0.586 |
Token | university |
Token ID | 6403 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
oaded | +0.575 |
indal | +0.551 |
atorial | +0.542 |
clusively | +0.538 |
ornia | +0.531 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.543 |
lasting | -0.518 |
theless | -0.513 |
wonder | -0.494 |
™: | -0.493 |
Token | 's |
Token ID | 338 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
oaded | +0.438 |
indal | +0.422 |
atorial | +0.411 |
clusively | +0.410 |
ornia | +0.406 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.318 |
lasting | -0.300 |
theless | -0.300 |
wonder | -0.290 |
livest | -0.285 |
Token | website |
Token ID | 3052 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
oaded | +0.164 |
indal | +0.157 |
atorial | +0.155 |
clusively | +0.152 |
ornia | +0.151 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.154 |
lasting | -0.148 |
theless | -0.148 |
wonder | -0.143 |
™: | -0.140 |
Token | technique |
Token ID | 8173 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.761 |
theless | +0.740 |
lasting | +0.700 |
™: | +0.678 |
quin | +0.675 |
Neg logit contributions | |
oaded | -0.925 |
atorial | -0.874 |
indal | -0.867 |
clusively | -0.855 |
icion | -0.849 |
Token | for |
Token ID | 329 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.205 |
theless | +0.196 |
lasting | +0.192 |
livest | +0.185 |
wonder | +0.184 |
Neg logit contributions | |
oaded | -0.317 |
indal | -0.302 |
atorial | -0.299 |
clusively | -0.294 |
icion | -0.294 |
Token | painting |
Token ID | 12036 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.914 |
theless | +0.877 |
lasting | +0.857 |
wonder | +0.847 |
livest | +0.825 |
Neg logit contributions | |
oaded | -1.060 |
indal | -1.004 |
clusively | -0.997 |
atorial | -0.995 |
icion | -0.980 |
Token | . |
Token ID | 13 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.116 |
lasting | +2.042 |
theless | +2.022 |
wonder | +1.986 |
livest | +1.890 |
Neg logit contributions | |
oaded | -2.443 |
indal | -2.310 |
atorial | -2.288 |
clusively | -2.269 |
Moroc | -2.251 |
Token | I |
Token ID | 314 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
oaded | +0.066 |
indal | +0.062 |
atorial | +0.061 |
swick | +0.061 |
icion | +0.060 |
Neg logit contributions | |
lasting | -0.075 |
\\\\\\\\\\\\\\\\ | -0.075 |
theless | -0.074 |
livest | -0.072 |
wonder | -0.071 |
Token | just |
Token ID | 655 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.894 |
theless | +1.818 |
lasting | +1.782 |
™: | +1.694 |
livest | +1.683 |
Neg logit contributions | |
oaded | -2.371 |
indal | -2.260 |
atorial | -2.240 |
clusively | -2.227 |
ornia | -2.189 |
Token | gl |
Token ID | 1278 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.697 |
theless | +1.595 |
lasting | +1.585 |
™: | +1.503 |
livest | +1.485 |
Neg logit contributions | |
oaded | -2.085 |
atorial | -1.972 |
indal | -1.966 |
clusively | -1.932 |
ornia | -1.905 |
Token | opped |
Token ID | 38333 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.156 |
lasting | +2.138 |
theless | +2.088 |
wonder | +2.060 |
livest | +1.984 |
Neg logit contributions | |
oaded | -1.850 |
indal | -1.708 |
atorial | -1.678 |
ornia | -1.668 |
icion | -1.656 |
Token | on |
Token ID | 319 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
oaded | +0.651 |
indal | +0.603 |
atorial | +0.603 |
clusively | +0.599 |
ornia | +0.592 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.596 |
theless | -0.575 |
lasting | -0.570 |
wonder | -0.547 |
livest | -0.536 |
Token | a |
Token ID | 257 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.414 |
lasting | +0.402 |
theless | +0.399 |
wonder | +0.388 |
™: | +0.374 |
Neg logit contributions | |
oaded | -0.436 |
indal | -0.412 |
atorial | -0.403 |
Moroc | -0.401 |
clusively | -0.399 |
Token | bunch |
Token ID | 7684 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.046 |
theless | +0.044 |
lasting | +0.044 |
wonder | +0.043 |
™: | +0.042 |
Neg logit contributions | |
oaded | -0.052 |
indal | -0.049 |
atorial | -0.049 |
Moroc | -0.048 |
icion | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
oaded | +1.288 |
indal | +1.225 |
atorial | +1.204 |
ornia | +1.195 |
Moroc | +1.191 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.927 |
lasting | -0.922 |
theless | -0.890 |
wonder | -0.885 |
longer | -0.829 |
Token | would |
Token ID | 561 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
oaded | +1.462 |
atorial | +1.404 |
indal | +1.389 |
icion | +1.387 |
ornia | +1.376 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.205 |
theless | -1.185 |
lasting | -1.155 |
wonder | -1.119 |
livest | -1.110 |
Token | be |
Token ID | 307 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
oaded | +1.876 |
atorial | +1.760 |
indal | +1.754 |
clusively | +1.733 |
icion | +1.707 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -2.013 |
theless | -1.968 |
lasting | -1.922 |
quin | -1.851 |
livest | -1.835 |
Token | what |
Token ID | 644 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
oaded | +2.155 |
atorial | +2.048 |
clusively | +2.033 |
indal | +2.007 |
ornia | +1.975 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.871 |
theless | -1.801 |
lasting | -1.766 |
™: | -1.753 |
livest | -1.714 |
Token | he |
Token ID | 339 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.513 |
lasting | +3.483 |
theless | +3.392 |
wonder | +3.367 |
livest | +3.179 |
Neg logit contributions | |
oaded | -4.118 |
indal | -3.904 |
atorial | -3.828 |
ornia | -3.796 |
icion | -3.783 |
Token | was |
Token ID | 373 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.983 |
lasting | +0.968 |
theless | +0.939 |
wonder | +0.927 |
livest | +0.892 |
Neg logit contributions | |
oaded | -1.511 |
atorial | -1.443 |
indal | -1.423 |
ornia | -1.391 |
otle | -1.381 |
Token | doing |
Token ID | 1804 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.249 |
theless | +1.202 |
lasting | +1.194 |
wonder | +1.157 |
livest | +1.134 |
Neg logit contributions | |
oaded | -1.336 |
atorial | -1.254 |
indal | -1.246 |
clusively | -1.220 |
efficients | -1.212 |
Token | . |
Token ID | 13 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.044 |
theless | +0.042 |
lasting | +0.041 |
wonder | +0.040 |
livest | +0.040 |
Neg logit contributions | |
oaded | -0.051 |
indal | -0.047 |
atorial | -0.047 |
clusively | -0.047 |
ornia | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
oaded | +0.040 |
indal | +0.039 |
atorial | +0.038 |
swick | +0.038 |
icion | +0.037 |
Neg logit contributions | |
theless | -0.052 |
lasting | -0.051 |
livest | -0.051 |
\\\\\\\\\\\\\\\\ | -0.051 |
wonder | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
theless | +0.817 |
\\\\\\\\\\\\\\\\ | +0.815 |
livest | +0.812 |
lasting | +0.810 |
wonder | +0.782 |
Neg logit contributions | |
oaded | -0.638 |
indal | -0.604 |
atorial | -0.599 |
icion | -0.581 |
swick | -0.581 |
Token | Beyond |
Token ID | 24102 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
lasting | +0.575 |
theless | +0.569 |
\\\\\\\\\\\\\\\\ | +0.560 |
wonder | +0.549 |
livest | +0.541 |
Neg logit contributions | |
oaded | -0.500 |
indal | -0.477 |
atorial | -0.468 |
icion | -0.459 |
ornia | -0.455 |
Token | ogue |
Token ID | 5119 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.862 |
lasting | +0.856 |
theless | +0.841 |
wonder | +0.824 |
livest | +0.792 |
Neg logit contributions | |
oaded | -0.837 |
indal | -0.798 |
atorial | -0.774 |
ornia | -0.770 |
icion | -0.761 |
Token | at |
Token ID | 379 |
Feature activation | -9.16e-03 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.044 |
lasting | +1.036 |
theless | +1.000 |
wonder | +0.993 |
longer | +0.928 |
Neg logit contributions | |
oaded | -1.522 |
indal | -1.451 |
atorial | -1.427 |
ornia | -1.417 |
Moroc | -1.413 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.014 |
lasting | +0.013 |
theless | +0.013 |
wonder | +0.013 |
™: | +0.012 |
Neg logit contributions | |
oaded | -0.013 |
indal | -0.013 |
atorial | -0.012 |
icion | -0.012 |
clusively | -0.012 |
Token | New |
Token ID | 968 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
oaded | +0.294 |
indal | +0.278 |
icion | +0.275 |
atorial | +0.274 |
clusively | +0.272 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.291 |
lasting | -0.279 |
theless | -0.272 |
wonder | -0.265 |
™: | -0.261 |
Token | York |
Token ID | 1971 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.737 |
lasting | +1.730 |
theless | +1.667 |
wonder | +1.648 |
livest | +1.543 |
Neg logit contributions | |
oaded | -2.734 |
indal | -2.611 |
atorial | -2.572 |
ornia | -2.554 |
icion | -2.546 |
Token | Times |
Token ID | 3782 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.826 |
lasting | +2.799 |
theless | +2.695 |
wonder | +2.676 |
longer | +2.473 |
Neg logit contributions | |
oaded | -4.930 |
indal | -4.710 |
atorial | -4.642 |
ornia | -4.603 |
icion | -4.590 |
Token | as |
Token ID | 355 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.221 |
lasting | +3.219 |
wonder | +3.095 |
theless | +3.062 |
longer | +2.907 |
Neg logit contributions | |
oaded | -4.692 |
indal | -4.469 |
atorial | -4.368 |
Moroc | -4.338 |
ornia | -4.333 |
Token | well |
Token ID | 880 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.173 |
theless | +0.170 |
lasting | +0.168 |
wonder | +0.163 |
™: | +0.157 |
Neg logit contributions | |
oaded | -0.221 |
indal | -0.212 |
atorial | -0.208 |
clusively | -0.208 |
ornia | -0.207 |
Token | as |
Token ID | 355 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
oaded | +1.740 |
indal | +1.629 |
icion | +1.602 |
clusively | +1.599 |
atorial | +1.591 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.881 |
theless | -1.841 |
lasting | -1.774 |
livest | -1.757 |
wonder | -1.749 |
Token | by |
Token ID | 416 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
oaded | +0.618 |
indal | +0.587 |
atorial | +0.576 |
icion | +0.574 |
ornia | +0.574 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.577 |
lasting | -0.550 |
theless | -0.546 |
wonder | -0.529 |
™: | -0.517 |
Token | this |
Token ID | 428 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.895 |
lasting | +0.873 |
theless | +0.855 |
wonder | +0.839 |
™: | +0.809 |
Neg logit contributions | |
oaded | -0.905 |
indal | -0.860 |
icion | -0.843 |
atorial | -0.842 |
Moroc | -0.833 |
Token | situation |
Token ID | 3074 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.967 |
theless | +0.942 |
lasting | +0.934 |
wonder | +0.907 |
™: | +0.897 |
Neg logit contributions | |
oaded | -1.074 |
indal | -1.010 |
atorial | -0.997 |
clusively | -0.989 |
ornia | -0.986 |
Token | is |
Token ID | 318 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
oaded | +0.610 |
indal | +0.580 |
atorial | +0.579 |
swick | +0.567 |
icion | +0.567 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.503 |
theless | -0.482 |
livest | -0.463 |
lasting | -0.462 |
wonder | -0.457 |
Token | very |
Token ID | 845 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.471 |
theless | +1.396 |
lasting | +1.388 |
wonder | +1.370 |
™: | +1.335 |
Neg logit contributions | |
oaded | -1.866 |
clusively | -1.754 |
indal | -1.753 |
atorial | -1.752 |
icion | -1.731 |
Token | different |
Token ID | 1180 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.644 |
lasting | +2.565 |
theless | +2.516 |
wonder | +2.479 |
™: | +2.397 |
Neg logit contributions | |
oaded | -3.437 |
indal | -3.261 |
atorial | -3.250 |
clusively | -3.216 |
Moroc | -3.213 |
Token | from |
Token ID | 422 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
oaded | +0.615 |
indal | +0.585 |
atorial | +0.575 |
ornia | +0.575 |
clusively | +0.571 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.538 |
theless | -0.517 |
lasting | -0.505 |
wonder | -0.501 |
livest | -0.488 |
Token | what |
Token ID | 644 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.123 |
lasting | +1.093 |
theless | +1.087 |
wonder | +1.058 |
quin | +1.020 |
Neg logit contributions | |
oaded | -1.241 |
indal | -1.156 |
atorial | -1.153 |
clusively | -1.138 |
Moroc | -1.136 |
Token | it |
Token ID | 340 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.769 |
lasting | +3.763 |
wonder | +3.614 |
theless | +3.614 |
longer | +3.394 |
Neg logit contributions | |
oaded | -5.076 |
indal | -4.835 |
atorial | -4.733 |
ornia | -4.704 |
Moroc | -4.693 |
Token | was |
Token ID | 373 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
oaded | +0.934 |
atorial | +0.888 |
indal | +0.870 |
ornia | +0.864 |
swick | +0.853 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.651 |
theless | -0.626 |
lasting | -0.617 |
livest | -0.606 |
wonder | -0.592 |
Token | in |
Token ID | 287 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
oaded | +0.023 |
atorial | +0.021 |
indal | +0.021 |
clusively | +0.021 |
ornia | +0.021 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.020 |
theless | -0.019 |
lasting | -0.018 |
wonder | -0.018 |
livest | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
oaded | +0.536 |
clusively | +0.506 |
atorial | +0.500 |
Moroc | +0.498 |
indal | +0.497 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.548 |
lasting | -0.527 |
theless | -0.524 |
wonder | -0.512 |
™: | -0.503 |
Token | ' |
Token ID | 705 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.032 |
theless | +0.031 |
lasting | +0.031 |
wonder | +0.030 |
™: | +0.030 |
Neg logit contributions | |
oaded | -0.034 |
atorial | -0.032 |
indal | -0.032 |
clusively | -0.032 |
Moroc | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.000 |
theless | +0.000 |
lasting | +0.000 |
wonder | +0.000 |
livest | +0.000 |
Neg logit contributions | |
oaded | -0.000 |
indal | -0.000 |
atorial | -0.000 |
ornia | -0.000 |
icion | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
oaded | +0.388 |
indal | +0.362 |
atorial | +0.361 |
swick | +0.358 |
ornia | +0.348 |
Neg logit contributions | |
theless | -0.471 |
\\\\\\\\\\\\\\\\ | -0.470 |
lasting | -0.469 |
livest | -0.466 |
wonder | -0.456 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
livest | +0.393 |
theless | +0.390 |
\\\\\\\\\\\\\\\\ | +0.389 |
lasting | +0.379 |
wonder | +0.366 |
Neg logit contributions | |
oaded | -0.278 |
atorial | -0.266 |
indal | -0.265 |
icion | -0.256 |
swick | -0.255 |
Token | � |
Token ID | 447 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
lasting | +0.301 |
theless | +0.297 |
\\\\\\\\\\\\\\\\ | +0.297 |
wonder | +0.290 |
livest | +0.284 |
Neg logit contributions | |
oaded | -0.309 |
indal | -0.293 |
atorial | -0.288 |
ornia | -0.283 |
icion | -0.282 |
Token | � |
Token ID | 250 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.644 |
lasting | +0.640 |
theless | +0.632 |
wonder | +0.615 |
livest | +0.587 |
Neg logit contributions | |
oaded | -0.855 |
indal | -0.811 |
ornia | -0.801 |
atorial | -0.801 |
icion | -0.790 |
Token | What |
Token ID | 2061 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
lasting | +3.176 |
\\\\\\\\\\\\\\\\ | +3.160 |
theless | +3.121 |
wonder | +3.092 |
livest | +3.004 |
Neg logit contributions | |
oaded | -2.526 |
indal | -2.358 |
atorial | -2.310 |
icion | -2.268 |
ornia | -2.263 |
Token | we |
Token ID | 356 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +4.504 |
lasting | +4.444 |
theless | +4.350 |
wonder | +4.281 |
livest | +4.079 |
Neg logit contributions | |
oaded | -5.233 |
indal | -4.943 |
atorial | -4.841 |
ornia | -4.815 |
clusively | -4.782 |
Token | all |
Token ID | 477 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
oaded | +0.692 |
atorial | +0.642 |
clusively | +0.639 |
indal | +0.638 |
swick | +0.627 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.645 |
theless | -0.627 |
lasting | -0.607 |
™: | -0.607 |
livest | -0.604 |
Token | want |
Token ID | 765 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.141 |
™: | +0.132 |
theless | +0.132 |
lasting | +0.131 |
livest | +0.127 |
Neg logit contributions | |
oaded | -0.166 |
atorial | -0.156 |
indal | -0.155 |
swick | -0.154 |
clusively | -0.152 |
Token | is |
Token ID | 318 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.741 |
theless | +0.729 |
lasting | +0.710 |
wonder | +0.694 |
livest | +0.673 |
Neg logit contributions | |
oaded | -1.003 |
indal | -0.955 |
atorial | -0.937 |
ornia | -0.924 |
clusively | -0.917 |
Token | peace |
Token ID | 4167 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.797 |
theless | +0.779 |
lasting | +0.744 |
wonder | +0.736 |
livest | +0.726 |
Neg logit contributions | |
oaded | -0.946 |
indal | -0.898 |
clusively | -0.889 |
atorial | -0.885 |
ornia | -0.870 |
Token | star |
Token ID | 3491 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
oaded | +0.659 |
indal | +0.634 |
atorial | +0.626 |
ornia | +0.620 |
icion | +0.618 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.475 |
lasting | -0.454 |
theless | -0.447 |
livest | -0.432 |
wonder | -0.424 |
Token | ), |
Token ID | 828 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.377 |
theless | +0.367 |
lasting | +0.364 |
wonder | +0.353 |
livest | +0.349 |
Neg logit contributions | |
oaded | -0.415 |
indal | -0.397 |
atorial | -0.388 |
ornia | -0.384 |
icion | -0.382 |
Token | supporting |
Token ID | 6493 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.277 |
theless | +0.263 |
lasting | +0.260 |
wonder | +0.252 |
™: | +0.250 |
Neg logit contributions | |
oaded | -0.271 |
indal | -0.259 |
atorial | -0.258 |
clusively | -0.252 |
icion | -0.251 |
Token | actress |
Token ID | 14549 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
oaded | +1.602 |
indal | +1.532 |
atorial | +1.520 |
clusively | +1.511 |
icion | +1.501 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.731 |
theless | -1.658 |
lasting | -1.607 |
hm | -1.539 |
wonder | -1.538 |
Token | and |
Token ID | 290 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
lasting | +1.841 |
\\\\\\\\\\\\\\\\ | +1.823 |
wonder | +1.766 |
theless | +1.736 |
longer | +1.649 |
Neg logit contributions | |
oaded | -2.706 |
indal | -2.576 |
atorial | -2.515 |
Moroc | -2.510 |
ornia | -2.508 |
Token | original |
Token ID | 2656 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.143 |
theless | +1.091 |
lasting | +1.075 |
wonder | +1.046 |
hm | +1.028 |
Neg logit contributions | |
oaded | -1.166 |
indal | -1.117 |
atorial | -1.108 |
icion | -1.095 |
clusively | -1.090 |
Token | screenplay |
Token ID | 39769 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.498 |
lasting | +3.370 |
theless | +3.340 |
wonder | +3.259 |
™: | +3.113 |
Neg logit contributions | |
oaded | -4.325 |
indal | -4.133 |
atorial | -4.092 |
clusively | -4.013 |
icion | -4.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +2.263 |
lasting | +2.236 |
theless | +2.197 |
wonder | +2.146 |
livest | +2.057 |
Neg logit contributions | |
oaded | -2.773 |
indal | -2.633 |
atorial | -2.586 |
icion | -2.558 |
ornia | -2.551 |
Token | Of |
Token ID | 3226 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
oaded | +0.024 |
indal | +0.023 |
atorial | +0.023 |
icion | +0.022 |
swick | +0.022 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.027 |
lasting | -0.027 |
theless | -0.027 |
livest | -0.026 |
wonder | -0.026 |
Token | course |
Token ID | 1781 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
oaded | +0.814 |
indal | +0.776 |
atorial | +0.759 |
icion | +0.757 |
ornia | +0.755 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.673 |
lasting | -0.656 |
theless | -0.652 |
wonder | -0.632 |
livest | -0.617 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
oaded | +0.996 |
indal | +0.948 |
icion | +0.937 |
atorial | +0.935 |
ornia | +0.926 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.825 |
lasting | -0.798 |
theless | -0.791 |
wonder | -0.771 |
livest | -0.744 |
Token | of |
Token ID | 286 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
oaded | +1.136 |
indal | +1.094 |
atorial | +1.079 |
icion | +1.063 |
ornia | +1.058 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.789 |
theless | -0.778 |
lasting | -0.757 |
wonder | -0.717 |
quin | -0.698 |
Token | assassination |
Token ID | 18898 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
oaded | +1.013 |
indal | +0.968 |
atorial | +0.953 |
clusively | +0.948 |
ornia | +0.930 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.863 |
theless | -0.847 |
lasting | -0.820 |
wonder | -0.797 |
quin | -0.796 |
Token | . |
Token ID | 13 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
oaded | +1.160 |
atorial | +1.090 |
indal | +1.077 |
ornia | +1.069 |
clusively | +1.067 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.990 |
theless | -0.976 |
lasting | -0.942 |
wonder | -0.913 |
quin | -0.881 |
Token | But |
Token ID | 887 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
oaded | +0.482 |
atorial | +0.470 |
swick | +0.466 |
indal | +0.463 |
icion | +0.447 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -0.628 |
livest | -0.623 |
theless | -0.622 |
lasting | -0.618 |
wonder | -0.604 |
Token | he |
Token ID | 339 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
oaded | +1.733 |
indal | +1.674 |
atorial | +1.654 |
icion | +1.633 |
ornia | +1.616 |
Neg logit contributions | |
\\\\\\\\\\\\\\\\ | -1.738 |
theless | -1.672 |
™: | -1.600 |
lasting | -1.598 |
quin | -1.581 |
Token | never |
Token ID | 1239 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +1.099 |
lasting | +1.037 |
theless | +1.013 |
™: | +0.997 |
quin | +0.985 |
Neg logit contributions | |
oaded | -1.535 |
atorial | -1.471 |
indal | -1.442 |
clusively | -1.424 |
ornia | -1.403 |
Token | forgot |
Token ID | 16453 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +3.125 |
lasting | +2.933 |
wonder | +2.810 |
™: | +2.772 |
theless | +2.770 |
Neg logit contributions | |
oaded | -4.874 |
atorial | -4.662 |
clusively | -4.611 |
indal | -4.573 |
ornia | -4.519 |
Token | his |
Token ID | 465 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +4.045 |
lasting | +3.922 |
theless | +3.850 |
wonder | +3.778 |
livest | +3.622 |
Neg logit contributions | |
oaded | -4.852 |
indal | -4.658 |
atorial | -4.560 |
Moroc | -4.507 |
clusively | -4.493 |
Token | goal |
Token ID | 3061 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.775 |
theless | +0.740 |
lasting | +0.721 |
livest | +0.706 |
™: | +0.699 |
Neg logit contributions | |
oaded | -0.810 |
indal | -0.765 |
atorial | -0.760 |
clusively | -0.750 |
Moroc | -0.749 |
Token | , |
Token ID | 11 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.785 |
theless | +0.760 |
lasting | +0.737 |
wonder | +0.723 |
livest | +0.712 |
Neg logit contributions | |
oaded | -1.015 |
indal | -0.973 |
atorial | -0.960 |
clusively | -0.948 |
ornia | -0.936 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
\\\\\\\\\\\\\\\\ | +0.946 |
theless | +0.913 |
lasting | +0.867 |
wonder | +0.860 |
quin | +0.848 |
Neg logit contributions | |
oaded | -1.262 |
indal | -1.210 |
atorial | -1.208 |
clusively | -1.183 |
Moroc | -1.174 |