Token | first |
Token ID | 717 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Nice | +0.071 |
quiet | +0.067 |
zeb | +0.066 |
isexual | +0.063 |
� | +0.062 |
Neg logit contributions | |
welf | -0.104 |
weap | -0.096 |
scrut | -0.096 |
ingred | -0.094 |
unden | -0.092 |
Token | to |
Token ID | 284 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Nice | +0.226 |
quiet | +0.211 |
zeb | +0.208 |
isexual | +0.197 |
� | +0.192 |
Neg logit contributions | |
welf | -0.428 |
weap | -0.400 |
scrut | -0.400 |
ingred | -0.395 |
unden | -0.389 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
welf | +0.308 |
weap | +0.288 |
scrut | +0.285 |
ingred | +0.280 |
unden | +0.275 |
Neg logit contributions | |
Nice | -0.198 |
quiet | -0.188 |
zeb | -0.185 |
isexual | -0.176 |
� | -0.173 |
Token | about |
Token ID | 546 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Nice | +0.661 |
quiet | +0.625 |
zeb | +0.617 |
isexual | +0.583 |
� | +0.573 |
Neg logit contributions | |
welf | -1.027 |
weap | -0.946 |
ingred | -0.944 |
scrut | -0.944 |
unden | -0.940 |
Token | Nation |
Token ID | 8741 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
Nice | +0.106 |
quiet | +0.100 |
zeb | +0.099 |
isexual | +0.094 |
� | +0.093 |
Neg logit contributions | |
welf | -0.105 |
scrut | -0.096 |
ingred | -0.095 |
weap | -0.095 |
unden | -0.091 |
Token | Travels |
Token ID | 48899 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
welf | +0.405 |
scrut | +0.360 |
weap | +0.359 |
ingred | +0.350 |
unden | +0.335 |
Neg logit contributions | |
Nice | -0.645 |
quiet | -0.627 |
zeb | -0.622 |
isexual | -0.604 |
� | -0.592 |
Token | destinations |
Token ID | 23982 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
welf | +3.944 |
weap | +3.656 |
scrut | +3.574 |
ingred | +3.447 |
ships | +3.441 |
Neg logit contributions | |
Nice | -5.577 |
zeb | -5.432 |
quiet | -5.427 |
isexual | -5.240 |
� | -5.175 |
Token | , |
Token ID | 11 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
welf | +0.882 |
weap | +0.823 |
scrut | +0.818 |
ingred | +0.803 |
ships | +0.783 |
Neg logit contributions | |
Nice | -0.675 |
quiet | -0.643 |
zeb | -0.636 |
isexual | -0.613 |
� | -0.597 |
Token | and |
Token ID | 290 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
welf | +0.033 |
weap | +0.031 |
scrut | +0.031 |
ingred | +0.031 |
unden | +0.030 |
Neg logit contributions | |
Nice | -0.021 |
quiet | -0.020 |
zeb | -0.020 |
isexual | -0.019 |
� | -0.019 |
Token | explore |
Token ID | 7301 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Nice | +0.080 |
quiet | +0.077 |
zeb | +0.076 |
isexual | +0.073 |
� | +0.072 |
Neg logit contributions | |
welf | -0.093 |
weap | -0.086 |
scrut | -0.085 |
ingred | -0.084 |
unden | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
welf | +0.310 |
weap | +0.290 |
scrut | +0.289 |
ingred | +0.286 |
unden | +0.280 |
Neg logit contributions | |
Nice | -0.203 |
quiet | -0.191 |
zeb | -0.189 |
isexual | -0.180 |
� | -0.177 |
Token | first |
Token ID | 717 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
welf | +0.331 |
weap | +0.310 |
scrut | +0.306 |
ingred | +0.301 |
ships | +0.299 |
Neg logit contributions | |
Nice | -0.217 |
quiet | -0.202 |
zeb | -0.197 |
isexual | -0.185 |
� | -0.185 |
Token | to |
Token ID | 284 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
welf | +0.028 |
weap | +0.026 |
scrut | +0.026 |
ingred | +0.026 |
unden | +0.025 |
Neg logit contributions | |
Nice | -0.015 |
quiet | -0.014 |
zeb | -0.014 |
isexual | -0.013 |
� | -0.013 |
Token | hear |
Token ID | 3285 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
welf | +0.813 |
weap | +0.770 |
scrut | +0.756 |
ingred | +0.745 |
ships | +0.734 |
Neg logit contributions | |
Nice | -0.514 |
quiet | -0.485 |
zeb | -0.475 |
isexual | -0.449 |
� | -0.441 |
Token | about |
Token ID | 546 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Nice | +0.429 |
quiet | +0.399 |
zeb | +0.382 |
isexual | +0.363 |
igue | +0.349 |
Neg logit contributions | |
welf | -0.694 |
weap | -0.662 |
scrut | -0.652 |
ingred | -0.646 |
unden | -0.623 |
Token | Nation |
Token ID | 8741 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
welf | +0.221 |
scrut | +0.210 |
weap | +0.208 |
ingred | +0.204 |
ships | +0.193 |
Neg logit contributions | |
Nice | -0.215 |
quiet | -0.198 |
zeb | -0.193 |
isexual | -0.182 |
igue | -0.179 |
Token | Travels |
Token ID | 48899 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
welf | +0.869 |
weap | +0.786 |
scrut | +0.778 |
ingred | +0.774 |
unden | +0.729 |
Neg logit contributions | |
Nice | -1.370 |
quiet | -1.324 |
zeb | -1.311 |
isexual | -1.278 |
� | -1.255 |
Token | destinations |
Token ID | 23982 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
welf | +3.848 |
weap | +3.573 |
scrut | +3.473 |
ships | +3.358 |
ingred | +3.347 |
Neg logit contributions | |
Nice | -5.531 |
quiet | -5.397 |
zeb | -5.397 |
isexual | -5.204 |
� | -5.156 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
welf | +0.937 |
weap | +0.876 |
scrut | +0.870 |
ingred | +0.853 |
ships | +0.836 |
Neg logit contributions | |
Nice | -0.726 |
quiet | -0.690 |
zeb | -0.683 |
isexual | -0.659 |
� | -0.642 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
welf | +0.206 |
weap | +0.191 |
scrut | +0.191 |
ingred | +0.189 |
unden | +0.188 |
Neg logit contributions | |
Nice | -0.126 |
quiet | -0.117 |
zeb | -0.116 |
isexual | -0.107 |
igue | -0.107 |
Token | explore |
Token ID | 7301 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
welf | +0.169 |
weap | +0.152 |
ingred | +0.152 |
scrut | +0.152 |
unden | +0.151 |
Neg logit contributions | |
Nice | -0.121 |
quiet | -0.113 |
zeb | -0.111 |
isexual | -0.106 |
� | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
welf | +0.475 |
weap | +0.445 |
scrut | +0.443 |
ingred | +0.437 |
unden | +0.425 |
Neg logit contributions | |
Nice | -0.319 |
quiet | -0.298 |
zeb | -0.294 |
isexual | -0.281 |
� | -0.276 |
Token | ce |
Token ID | 344 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
welf | +0.552 |
scrut | +0.524 |
weap | +0.524 |
ingred | +0.502 |
unden | +0.498 |
Neg logit contributions | |
Nice | -0.577 |
quiet | -0.553 |
zeb | -0.548 |
isexual | -0.525 |
igue | -0.519 |
Token | / |
Token ID | 14 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
welf | +0.995 |
weap | +0.928 |
scrut | +0.921 |
ingred | +0.902 |
ships | +0.883 |
Neg logit contributions | |
Nice | -0.786 |
quiet | -0.746 |
zeb | -0.735 |
isexual | -0.710 |
� | -0.693 |
Token | edd |
Token ID | 6048 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
welf | +0.010 |
weap | +0.009 |
scrut | +0.009 |
ingred | +0.009 |
unden | +0.009 |
Neg logit contributions | |
Nice | -0.011 |
quiet | -0.011 |
zeb | -0.011 |
isexual | -0.010 |
� | -0.010 |
Token | 75 |
Token ID | 2425 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
welf | +0.729 |
weap | +0.671 |
scrut | +0.668 |
ingred | +0.650 |
ships | +0.631 |
Neg logit contributions | |
Nice | -0.802 |
quiet | -0.773 |
zeb | -0.767 |
isexual | -0.745 |
� | -0.728 |
Token | / |
Token ID | 14 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
welf | +0.027 |
weap | +0.025 |
scrut | +0.025 |
ingred | +0.025 |
unden | +0.024 |
Neg logit contributions | |
Nice | -0.021 |
quiet | -0.020 |
zeb | -0.020 |
isexual | -0.019 |
� | -0.019 |
Token | AUT |
Token ID | 39371 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
welf | +0.093 |
scrut | +0.088 |
weap | +0.087 |
ingred | +0.084 |
unden | +0.082 |
Neg logit contributions | |
Nice | -0.072 |
quiet | -0.070 |
zeb | -0.065 |
isexual | -0.063 |
� | -0.063 |
Token | OC |
Token ID | 4503 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
welf | +4.246 |
weap | +3.935 |
scrut | +3.897 |
ingred | +3.801 |
ships | +3.749 |
Neg logit contributions | |
Nice | -4.274 |
quiet | -4.093 |
zeb | -4.058 |
isexual | -3.941 |
� | -3.846 |
Token | R |
Token ID | 49 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Nice | +0.884 |
quiet | +0.832 |
zeb | +0.811 |
isexual | +0.763 |
� | +0.759 |
Neg logit contributions | |
welf | -1.900 |
scrut | -1.815 |
weap | -1.809 |
ingred | -1.766 |
unden | -1.733 |
Token | OP |
Token ID | 3185 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
Nice | +1.164 |
quiet | +1.103 |
zeb | +1.078 |
isexual | +1.052 |
igue | +1.025 |
Neg logit contributions | |
welf | -1.444 |
weap | -1.341 |
ingred | -1.330 |
scrut | -1.325 |
ships | -1.290 |
Token | / |
Token ID | 14 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
welf | +0.078 |
weap | +0.073 |
scrut | +0.073 |
ingred | +0.071 |
unden | +0.069 |
Neg logit contributions | |
Nice | -0.062 |
quiet | -0.059 |
zeb | -0.058 |
isexual | -0.057 |
� | -0.055 |
Token | h |
Token ID | 71 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
welf | +0.212 |
scrut | +0.201 |
weap | +0.195 |
ingred | +0.195 |
unden | +0.188 |
Neg logit contributions | |
Nice | -0.273 |
quiet | -0.272 |
zeb | -0.255 |
� | -0.253 |
isexual | -0.247 |
Token | acids |
Token ID | 17045 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
welf | +0.465 |
weap | +0.424 |
scrut | +0.423 |
ingred | +0.409 |
ships | +0.399 |
Neg logit contributions | |
Nice | -0.571 |
quiet | -0.545 |
zeb | -0.544 |
isexual | -0.528 |
� | -0.516 |
Token | for |
Token ID | 329 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
Nice | +0.908 |
quiet | +0.857 |
zeb | +0.854 |
isexual | +0.817 |
� | +0.802 |
Neg logit contributions | |
welf | -1.235 |
weap | -1.148 |
scrut | -1.145 |
ingred | -1.116 |
ships | -1.098 |
Token | fuel |
Token ID | 5252 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Nice | +0.058 |
quiet | +0.055 |
zeb | +0.055 |
isexual | +0.053 |
� | +0.052 |
Neg logit contributions | |
welf | -0.067 |
weap | -0.062 |
scrut | -0.062 |
ingred | -0.060 |
ships | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Nice | +1.377 |
quiet | +1.310 |
zeb | +1.307 |
isexual | +1.254 |
� | +1.238 |
Neg logit contributions | |
welf | -1.486 |
scrut | -1.374 |
weap | -1.372 |
ingred | -1.331 |
ships | -1.300 |
Token | Inter |
Token ID | 4225 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
Nice | +0.251 |
quiet | +0.231 |
zeb | +0.228 |
isexual | +0.219 |
� | +0.218 |
Neg logit contributions | |
welf | -0.310 |
scrut | -0.290 |
weap | -0.289 |
ingred | -0.286 |
unden | -0.276 |
Token | mitt |
Token ID | 20124 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
Nice | +0.960 |
quiet | +0.929 |
zeb | +0.924 |
isexual | +0.905 |
� | +0.889 |
Neg logit contributions | |
welf | -0.437 |
weap | -0.386 |
scrut | -0.381 |
ingred | -0.366 |
ships | -0.357 |
Token | ent |
Token ID | 298 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
welf | +4.080 |
weap | +3.881 |
scrut | +3.854 |
ships | +3.804 |
ingred | +3.767 |
Neg logit contributions | |
Nice | -3.127 |
zeb | -2.935 |
quiet | -2.898 |
isexual | -2.799 |
� | -2.751 |
Token | fasting |
Token ID | 24845 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
welf | +0.017 |
weap | +0.016 |
scrut | +0.016 |
ingred | +0.015 |
ships | +0.015 |
Neg logit contributions | |
Nice | -0.015 |
quiet | -0.015 |
zeb | -0.015 |
isexual | -0.014 |
� | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
welf | +1.804 |
weap | +1.681 |
scrut | +1.667 |
ingred | +1.631 |
ships | +1.603 |
Neg logit contributions | |
Nice | -1.551 |
quiet | -1.481 |
zeb | -1.466 |
isexual | -1.415 |
� | -1.385 |
Token | spending |
Token ID | 4581 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Nice | +0.203 |
quiet | +0.192 |
zeb | +0.189 |
isexual | +0.184 |
� | +0.179 |
Neg logit contributions | |
welf | -0.242 |
weap | -0.226 |
scrut | -0.225 |
ingred | -0.219 |
ships | -0.218 |
Token | more |
Token ID | 517 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Nice | +0.090 |
quiet | +0.085 |
zeb | +0.084 |
isexual | +0.081 |
� | +0.079 |
Neg logit contributions | |
welf | -0.121 |
weap | -0.113 |
scrut | -0.113 |
ingred | -0.110 |
ships | -0.109 |
Token | ar |
Token ID | 283 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
welf | +0.189 |
weap | +0.177 |
scrut | +0.176 |
ingred | +0.174 |
unden | +0.171 |
Neg logit contributions | |
Nice | -0.106 |
quiet | -0.101 |
zeb | -0.100 |
isexual | -0.095 |
� | -0.092 |
Token | ( |
Token ID | 357 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
Nice | +0.193 |
quiet | +0.183 |
zeb | +0.182 |
isexual | +0.175 |
� | +0.173 |
Neg logit contributions | |
welf | -0.212 |
weap | -0.195 |
scrut | -0.193 |
ingred | -0.190 |
ships | -0.186 |
Token | D |
Token ID | 35 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
welf | +0.036 |
weap | +0.034 |
scrut | +0.034 |
ingred | +0.033 |
ships | +0.032 |
Neg logit contributions | |
Nice | -0.022 |
quiet | -0.021 |
zeb | -0.020 |
isexual | -0.020 |
� | -0.019 |
Token | ish |
Token ID | 680 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
welf | +0.248 |
weap | +0.234 |
scrut | +0.233 |
ingred | +0.229 |
ships | +0.226 |
Neg logit contributions | |
Nice | -0.124 |
zeb | -0.116 |
quiet | -0.116 |
isexual | -0.110 |
� | -0.105 |
Token | ) |
Token ID | 8 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
welf | +0.236 |
weap | +0.220 |
scrut | +0.218 |
ingred | +0.214 |
ships | +0.210 |
Neg logit contributions | |
Nice | -0.194 |
quiet | -0.185 |
zeb | -0.183 |
isexual | -0.177 |
� | -0.173 |
Token | owes |
Token ID | 29264 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
Nice | +0.652 |
quiet | +0.616 |
zeb | +0.615 |
isexual | +0.590 |
� | +0.580 |
Neg logit contributions | |
welf | -0.724 |
weap | -0.667 |
scrut | -0.661 |
ingred | -0.652 |
ships | -0.636 |
Token | V |
Token ID | 569 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
welf | +3.899 |
weap | +3.639 |
scrut | +3.608 |
ingred | +3.537 |
ships | +3.478 |
Neg logit contributions | |
Nice | -3.376 |
quiet | -3.249 |
zeb | -3.210 |
isexual | -3.113 |
� | -3.024 |
Token | oom |
Token ID | 4207 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Nice | +0.308 |
quiet | +0.295 |
zeb | +0.294 |
isexual | +0.283 |
� | +0.275 |
Neg logit contributions | |
welf | -0.366 |
scrut | -0.340 |
weap | -0.335 |
ingred | -0.332 |
unden | -0.326 |
Token | ( |
Token ID | 357 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
Nice | +0.168 |
quiet | +0.157 |
zeb | +0.157 |
isexual | +0.152 |
� | +0.150 |
Neg logit contributions | |
welf | -0.196 |
weap | -0.182 |
scrut | -0.181 |
ingred | -0.176 |
ships | -0.173 |
Token | AM |
Token ID | 2390 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
welf | +0.022 |
weap | +0.020 |
scrut | +0.020 |
ingred | +0.020 |
unden | +0.019 |
Neg logit contributions | |
Nice | -0.014 |
quiet | -0.014 |
zeb | -0.013 |
isexual | -0.013 |
� | -0.013 |
Token | C |
Token ID | 34 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
welf | +0.320 |
weap | +0.294 |
scrut | +0.290 |
ingred | +0.283 |
ships | +0.277 |
Neg logit contributions | |
Nice | -0.419 |
quiet | -0.403 |
zeb | -0.400 |
isexual | -0.389 |
� | -0.382 |
Token | presidential |
Token ID | 4787 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
welf | +1.456 |
weap | +1.367 |
scrut | +1.356 |
ingred | +1.333 |
ships | +1.315 |
Neg logit contributions | |
Nice | -0.996 |
quiet | -0.940 |
zeb | -0.928 |
isexual | -0.896 |
� | -0.867 |
Token | nominee |
Token ID | 10429 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Nice | +0.539 |
quiet | +0.500 |
zeb | +0.490 |
isexual | +0.472 |
� | +0.455 |
Neg logit contributions | |
welf | -0.895 |
weap | -0.843 |
scrut | -0.824 |
ingred | -0.823 |
ships | -0.819 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Nice | +0.244 |
quiet | +0.222 |
zeb | +0.215 |
isexual | +0.202 |
� | +0.195 |
Neg logit contributions | |
welf | -0.551 |
weap | -0.523 |
scrut | -0.516 |
ingred | -0.511 |
ships | -0.507 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
welf | +1.023 |
weap | +0.960 |
scrut | +0.953 |
ingred | +0.941 |
unden | +0.923 |
Neg logit contributions | |
Nice | -0.603 |
quiet | -0.557 |
zeb | -0.551 |
isexual | -0.525 |
igue | -0.510 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
welf | +0.987 |
weap | +0.919 |
scrut | +0.909 |
ingred | +0.891 |
ships | +0.876 |
Neg logit contributions | |
Nice | -0.888 |
quiet | -0.848 |
zeb | -0.840 |
isexual | -0.812 |
� | -0.793 |
Token | Diane |
Token ID | 26542 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
welf | +1.024 |
weap | +0.936 |
scrut | +0.931 |
ingred | +0.917 |
unden | +0.909 |
Neg logit contributions | |
Nice | -1.039 |
quiet | -0.973 |
zeb | -0.951 |
isexual | -0.927 |
igue | -0.920 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
welf | +2.653 |
scrut | +2.385 |
weap | +2.384 |
ingred | +2.279 |
ships | +2.244 |
Neg logit contributions | |
Nice | -4.279 |
quiet | -4.157 |
zeb | -4.137 |
isexual | -4.059 |
� | -3.987 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
welf | +1.301 |
weap | +1.227 |
scrut | +1.218 |
ingred | +1.194 |
ships | +1.173 |
Neg logit contributions | |
Nice | -0.798 |
quiet | -0.750 |
zeb | -0.735 |
isexual | -0.703 |
� | -0.686 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
welf | +0.815 |
weap | +0.750 |
scrut | +0.742 |
ingred | +0.721 |
ships | +0.703 |
Neg logit contributions | |
Nice | -0.959 |
quiet | -0.925 |
zeb | -0.911 |
isexual | -0.887 |
� | -0.870 |
Token | : |
Token ID | 25 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
welf | +0.525 |
weap | +0.474 |
scrut | +0.462 |
ingred | +0.448 |
unden | +0.447 |
Neg logit contributions | |
Nice | -0.739 |
quiet | -0.698 |
zeb | -0.687 |
isexual | -0.668 |
igue | -0.658 |
Token | ' |
Token ID | 705 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
welf | +0.959 |
weap | +0.887 |
scrut | +0.879 |
ingred | +0.860 |
ships | +0.852 |
Neg logit contributions | |
Nice | -0.946 |
quiet | -0.918 |
zeb | -0.910 |
isexual | -0.877 |
� | -0.865 |
Token | mix |
Token ID | 5022 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
welf | +0.216 |
weap | +0.201 |
scrut | +0.199 |
ingred | +0.196 |
ships | +0.192 |
Neg logit contributions | |
Nice | -0.197 |
quiet | -0.188 |
zeb | -0.186 |
isexual | -0.180 |
� | -0.176 |
Token | of |
Token ID | 286 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Nice | +0.427 |
quiet | +0.407 |
zeb | +0.403 |
isexual | +0.391 |
� | +0.383 |
Neg logit contributions | |
welf | -0.460 |
weap | -0.428 |
scrut | -0.423 |
ingred | -0.414 |
ships | -0.405 |
Token | low |
Token ID | 1877 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
welf | +0.118 |
weap | +0.111 |
scrut | +0.110 |
ingred | +0.107 |
ships | +0.106 |
Neg logit contributions | |
Nice | -0.091 |
quiet | -0.085 |
zeb | -0.084 |
isexual | -0.082 |
� | -0.079 |
Token | - |
Token ID | 12 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
welf | +0.472 |
weap | +0.438 |
scrut | +0.434 |
ingred | +0.424 |
ships | +0.417 |
Neg logit contributions | |
Nice | -0.449 |
quiet | -0.429 |
zeb | -0.424 |
isexual | -0.412 |
� | -0.403 |
Token | s |
Token ID | 82 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
welf | +0.348 |
weap | +0.323 |
scrut | +0.320 |
ingred | +0.312 |
ships | +0.308 |
Neg logit contributions | |
Nice | -0.352 |
quiet | -0.337 |
zeb | -0.334 |
isexual | -0.324 |
� | -0.316 |
Token | ulf |
Token ID | 4754 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
Nice | +0.103 |
quiet | +0.100 |
zeb | +0.099 |
isexual | +0.097 |
� | +0.096 |
Neg logit contributions | |
welf | -0.043 |
weap | -0.038 |
scrut | -0.037 |
ingred | -0.035 |
ships | -0.034 |
Token | ur |
Token ID | 333 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
welf | +4.010 |
weap | +3.799 |
scrut | +3.796 |
ships | +3.762 |
ingred | +3.716 |
Neg logit contributions | |
Nice | -2.703 |
quiet | -2.549 |
zeb | -2.496 |
isexual | -2.399 |
� | -2.353 |
Token | fuel |
Token ID | 5252 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Nice | +0.478 |
quiet | +0.450 |
zeb | +0.445 |
isexual | +0.434 |
� | +0.420 |
Neg logit contributions | |
welf | -0.578 |
weap | -0.539 |
scrut | -0.536 |
ingred | -0.522 |
ships | -0.512 |
Token | oil |
Token ID | 3056 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
Nice | +0.840 |
quiet | +0.789 |
zeb | +0.787 |
isexual | +0.760 |
� | +0.740 |
Neg logit contributions | |
welf | -1.031 |
weap | -0.961 |
scrut | -0.957 |
ingred | -0.935 |
ships | -0.914 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Nice | +0.018 |
quiet | +0.017 |
zeb | +0.017 |
isexual | +0.016 |
� | +0.016 |
Neg logit contributions | |
welf | -0.020 |
weap | -0.018 |
scrut | -0.018 |
ingred | -0.018 |
ships | -0.017 |
Token | diesel |
Token ID | 21866 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
welf | +0.102 |
weap | +0.095 |
scrut | +0.094 |
ingred | +0.092 |
ships | +0.091 |
Neg logit contributions | |
Nice | -0.082 |
quiet | -0.077 |
zeb | -0.076 |
isexual | -0.074 |
� | -0.072 |
Token | MORE |
Token ID | 12011 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
welf | +0.268 |
weap | +0.250 |
scrut | +0.249 |
ingred | +0.242 |
ships | +0.241 |
Neg logit contributions | |
Nice | -0.234 |
zeb | -0.224 |
quiet | -0.224 |
isexual | -0.217 |
� | -0.211 |
Token | and |
Token ID | 290 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
Nice | +0.860 |
quiet | +0.818 |
zeb | +0.806 |
isexual | +0.780 |
� | +0.758 |
Neg logit contributions | |
welf | -1.141 |
weap | -1.068 |
scrut | -1.058 |
ingred | -1.037 |
ships | -1.023 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Nice | +0.419 |
quiet | +0.388 |
zeb | +0.378 |
isexual | +0.361 |
� | +0.353 |
Neg logit contributions | |
welf | -0.731 |
weap | -0.685 |
scrut | -0.676 |
ingred | -0.671 |
ships | -0.664 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
welf | +0.344 |
weap | +0.322 |
scrut | +0.320 |
ingred | +0.317 |
unden | +0.311 |
Neg logit contributions | |
Nice | -0.198 |
quiet | -0.183 |
zeb | -0.180 |
isexual | -0.171 |
� | -0.167 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
welf | +0.792 |
weap | +0.750 |
scrut | +0.743 |
ingred | +0.734 |
ships | +0.723 |
Neg logit contributions | |
Nice | -0.360 |
quiet | -0.336 |
zeb | -0.330 |
isexual | -0.309 |
� | -0.300 |
Token | Diane |
Token ID | 26542 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
welf | +0.595 |
weap | +0.543 |
scrut | +0.539 |
ingred | +0.532 |
unden | +0.524 |
Neg logit contributions | |
Nice | -0.624 |
quiet | -0.584 |
zeb | -0.575 |
isexual | -0.556 |
igue | -0.553 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
welf | +2.408 |
scrut | +2.179 |
weap | +2.159 |
ingred | +2.042 |
ships | +2.031 |
Neg logit contributions | |
Nice | -4.327 |
quiet | -4.244 |
zeb | -4.232 |
isexual | -4.186 |
� | -4.109 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
welf | +1.385 |
weap | +1.307 |
scrut | +1.297 |
ingred | +1.273 |
ships | +1.250 |
Neg logit contributions | |
Nice | -0.847 |
quiet | -0.796 |
zeb | -0.777 |
isexual | -0.745 |
� | -0.728 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
welf | +0.803 |
weap | +0.739 |
scrut | +0.729 |
ingred | +0.707 |
ships | +0.690 |
Neg logit contributions | |
Nice | -0.970 |
quiet | -0.939 |
zeb | -0.923 |
isexual | -0.898 |
� | -0.882 |
Token | : |
Token ID | 25 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
welf | +0.443 |
weap | +0.401 |
scrut | +0.389 |
ingred | +0.379 |
unden | +0.379 |
Neg logit contributions | |
Nice | -0.630 |
quiet | -0.595 |
zeb | -0.586 |
isexual | -0.570 |
igue | -0.562 |
Token | ' |
Token ID | 705 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
welf | +1.073 |
weap | +0.989 |
scrut | +0.982 |
ingred | +0.953 |
ships | +0.952 |
Neg logit contributions | |
Nice | -1.094 |
quiet | -1.070 |
zeb | -1.062 |
isexual | -1.018 |
� | -1.010 |
Token | mandate |
Token ID | 14598 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
welf | +0.439 |
weap | +0.409 |
scrut | +0.407 |
ingred | +0.399 |
ships | +0.395 |
Neg logit contributions | |
Nice | -0.364 |
quiet | -0.344 |
zeb | -0.343 |
isexual | -0.327 |
� | -0.322 |
Token | . |
Token ID | 13 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
Nice | +0.694 |
quiet | +0.659 |
zeb | +0.656 |
isexual | +0.631 |
� | +0.617 |
Neg logit contributions | |
welf | -0.785 |
weap | -0.731 |
scrut | -0.727 |
ingred | -0.712 |
ships | -0.697 |
Token | The |
Token ID | 383 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
Nice | +0.055 |
quiet | +0.052 |
zeb | +0.052 |
isexual | +0.050 |
� | +0.049 |
Neg logit contributions | |
welf | -0.065 |
weap | -0.060 |
scrut | -0.060 |
ingred | -0.059 |
ships | -0.058 |
Token | Bush |
Token ID | 5511 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
welf | +0.038 |
weap | +0.036 |
scrut | +0.035 |
ingred | +0.034 |
ships | +0.034 |
Neg logit contributions | |
Nice | -0.035 |
quiet | -0.033 |
zeb | -0.032 |
isexual | -0.031 |
� | -0.031 |
Token | Administration |
Token ID | 8694 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Nice | +0.366 |
quiet | +0.347 |
zeb | +0.343 |
isexual | +0.329 |
� | +0.322 |
Neg logit contributions | |
welf | -0.424 |
weap | -0.398 |
scrut | -0.395 |
ingred | -0.386 |
ships | -0.382 |
Token | susp |
Token ID | 4012 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
welf | +1.018 |
weap | +0.947 |
scrut | +0.936 |
ingred | +0.917 |
ships | +0.898 |
Neg logit contributions | |
Nice | -0.990 |
quiet | -0.948 |
zeb | -0.937 |
isexual | -0.906 |
� | -0.884 |
Token | ends |
Token ID | 2412 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
welf | +2.137 |
weap | +1.884 |
scrut | +1.873 |
ships | +1.799 |
ingred | +1.768 |
Neg logit contributions | |
Nice | -4.696 |
quiet | -4.528 |
zeb | -4.514 |
isexual | -4.415 |
� | -4.331 |
Token | the |
Token ID | 262 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
welf | +0.603 |
weap | +0.565 |
scrut | +0.560 |
ingred | +0.550 |
ships | +0.543 |
Neg logit contributions | |
Nice | -0.479 |
quiet | -0.453 |
zeb | -0.447 |
isexual | -0.433 |
� | -0.421 |
Token | OR |
Token ID | 6375 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
welf | +0.240 |
weap | +0.224 |
scrut | +0.223 |
ingred | +0.218 |
ships | +0.215 |
Neg logit contributions | |
Nice | -0.215 |
quiet | -0.203 |
zeb | -0.200 |
isexual | -0.194 |
� | -0.189 |
Token | I |
Token ID | 40 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
welf | +0.438 |
weap | +0.404 |
scrut | +0.401 |
ingred | +0.393 |
unden | +0.380 |
Neg logit contributions | |
Nice | -0.465 |
quiet | -0.445 |
zeb | -0.440 |
isexual | -0.429 |
� | -0.419 |
Token | proposal |
Token ID | 6961 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Nice | +0.196 |
quiet | +0.186 |
zeb | +0.184 |
isexual | +0.178 |
� | +0.174 |
Neg logit contributions | |
welf | -0.204 |
weap | -0.190 |
scrut | -0.188 |
ingred | -0.184 |
ships | -0.181 |
Token | Los |
Token ID | 5401 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Nice | +0.404 |
quiet | +0.377 |
zeb | +0.371 |
isexual | +0.357 |
� | +0.346 |
Neg logit contributions | |
welf | -0.576 |
weap | -0.542 |
scrut | -0.538 |
ingred | -0.528 |
ships | -0.524 |
Token | Angeles |
Token ID | 5652 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Nice | +0.813 |
quiet | +0.759 |
zeb | +0.754 |
isexual | +0.716 |
� | +0.690 |
Neg logit contributions | |
welf | -1.436 |
weap | -1.354 |
scrut | -1.344 |
ingred | -1.324 |
ships | -1.299 |
Token | Times |
Token ID | 3782 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
welf | +0.367 |
weap | +0.346 |
scrut | +0.343 |
ingred | +0.337 |
ships | +0.332 |
Neg logit contributions | |
Nice | -0.197 |
quiet | -0.186 |
zeb | -0.183 |
isexual | -0.176 |
� | -0.170 |
Token | blogger |
Token ID | 23530 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
welf | +0.022 |
weap | +0.021 |
scrut | +0.021 |
ingred | +0.020 |
ships | +0.020 |
Neg logit contributions | |
Nice | -0.021 |
quiet | -0.020 |
zeb | -0.020 |
isexual | -0.019 |
� | -0.018 |
Token | Andrew |
Token ID | 6858 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
welf | +1.651 |
weap | +1.553 |
scrut | +1.543 |
ingred | +1.512 |
ships | +1.494 |
Neg logit contributions | |
Nice | -1.025 |
quiet | -0.975 |
zeb | -0.964 |
isexual | -0.928 |
� | -0.898 |
Token | Malcolm |
Token ID | 20002 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
welf | +1.270 |
weap | +1.192 |
scrut | +1.183 |
ingred | +1.154 |
ships | +1.142 |
Neg logit contributions | |
Nice | -0.917 |
quiet | -0.882 |
zeb | -0.867 |
isexual | -0.842 |
� | -0.814 |
Token | , |
Token ID | 11 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
welf | +3.595 |
weap | +3.344 |
scrut | +3.339 |
ingred | +3.244 |
ships | +3.203 |
Neg logit contributions | |
Nice | -2.968 |
quiet | -2.878 |
zeb | -2.817 |
isexual | -2.782 |
� | -2.667 |
Token | you |
Token ID | 345 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
welf | +0.235 |
weap | +0.219 |
scrut | +0.217 |
ingred | +0.213 |
ships | +0.210 |
Neg logit contributions | |
Nice | -0.202 |
quiet | -0.192 |
zeb | -0.188 |
isexual | -0.182 |
� | -0.178 |
Token | flip |
Token ID | 14283 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Nice | +0.344 |
quiet | +0.330 |
zeb | +0.323 |
isexual | +0.311 |
� | +0.305 |
Neg logit contributions | |
welf | -0.431 |
weap | -0.402 |
scrut | -0.397 |
ingred | -0.395 |
ships | -0.383 |
Token | the |
Token ID | 262 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
welf | +1.507 |
weap | +1.408 |
scrut | +1.397 |
ingred | +1.367 |
ships | +1.347 |
Neg logit contributions | |
Nice | -1.213 |
quiet | -1.157 |
zeb | -1.145 |
isexual | -1.107 |
� | -1.077 |
Token | script |
Token ID | 4226 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
welf | +0.159 |
weap | +0.149 |
scrut | +0.147 |
ingred | +0.144 |
ships | +0.143 |
Neg logit contributions | |
Nice | -0.119 |
quiet | -0.113 |
zeb | -0.112 |
isexual | -0.108 |
� | -0.105 |
Token | ) |
Token ID | 8 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
Nice | +0.130 |
quiet | +0.124 |
zeb | +0.121 |
isexual | +0.117 |
� | +0.115 |
Neg logit contributions | |
welf | -0.159 |
weap | -0.149 |
scrut | -0.147 |
ingred | -0.145 |
ships | -0.141 |
Token | is |
Token ID | 318 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Nice | +0.460 |
quiet | +0.439 |
zeb | +0.433 |
isexual | +0.417 |
� | +0.409 |
Neg logit contributions | |
welf | -0.532 |
weap | -0.497 |
scrut | -0.492 |
ingred | -0.484 |
unden | -0.469 |
Token | difficult |
Token ID | 2408 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
welf | +0.335 |
weap | +0.313 |
scrut | +0.310 |
ingred | +0.305 |
ships | +0.298 |
Neg logit contributions | |
Nice | -0.272 |
quiet | -0.258 |
zeb | -0.254 |
isexual | -0.245 |
� | -0.239 |
Token | ," |
Token ID | 553 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
welf | +0.219 |
weap | +0.205 |
scrut | +0.204 |
ingred | +0.200 |
ships | +0.196 |
Neg logit contributions | |
Nice | -0.156 |
quiet | -0.148 |
zeb | -0.146 |
isexual | -0.141 |
� | -0.137 |
Token | Lam |
Token ID | 10923 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
welf | +0.841 |
weap | +0.784 |
scrut | +0.779 |
ingred | +0.762 |
ships | +0.750 |
Neg logit contributions | |
Nice | -0.674 |
quiet | -0.642 |
zeb | -0.632 |
isexual | -0.611 |
� | -0.595 |
Token | orie |
Token ID | 19257 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
welf | +0.675 |
weap | +0.634 |
scrut | +0.630 |
ingred | +0.618 |
ships | +0.606 |
Neg logit contributions | |
Nice | -0.415 |
quiet | -0.393 |
zeb | -0.387 |
isexual | -0.371 |
� | -0.361 |
Token | llo |
Token ID | 18798 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
welf | +1.038 |
weap | +0.801 |
scrut | +0.769 |
ingred | +0.694 |
ships | +0.677 |
Neg logit contributions | |
Nice | -5.586 |
quiet | -5.437 |
zeb | -5.419 |
isexual | -5.341 |
� | -5.243 |
Token | said |
Token ID | 531 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
welf | +0.077 |
weap | +0.072 |
scrut | +0.071 |
ingred | +0.070 |
ships | +0.069 |
Neg logit contributions | |
Nice | -0.077 |
quiet | -0.074 |
zeb | -0.073 |
isexual | -0.071 |
� | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Nice | +0.491 |
quiet | +0.471 |
zeb | +0.466 |
isexual | +0.453 |
� | +0.442 |
Neg logit contributions | |
welf | -0.488 |
weap | -0.452 |
scrut | -0.448 |
ingred | -0.438 |
ships | -0.430 |
Token | " |
Token ID | 366 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
welf | +0.487 |
weap | +0.453 |
scrut | +0.449 |
ingred | +0.439 |
ships | +0.432 |
Neg logit contributions | |
Nice | -0.439 |
quiet | -0.419 |
zeb | -0.415 |
isexual | -0.403 |
� | -0.392 |
Token | But |
Token ID | 1537 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
welf | +0.055 |
weap | +0.051 |
scrut | +0.051 |
ingred | +0.050 |
unden | +0.048 |
Neg logit contributions | |
Nice | -0.051 |
quiet | -0.049 |
zeb | -0.048 |
isexual | -0.046 |
� | -0.046 |
Token | would |
Token ID | 561 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
welf | +0.154 |
weap | +0.143 |
scrut | +0.142 |
ingred | +0.140 |
ships | +0.137 |
Neg logit contributions | |
Nice | -0.122 |
quiet | -0.116 |
zeb | -0.114 |
isexual | -0.110 |
� | -0.107 |
Token | go |
Token ID | 467 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
welf | +0.008 |
weap | +0.007 |
scrut | +0.007 |
ingred | +0.007 |
ships | +0.007 |
Neg logit contributions | |
Nice | -0.007 |
quiet | -0.007 |
zeb | -0.007 |
isexual | -0.007 |
� | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
welf | +0.122 |
weap | +0.115 |
scrut | +0.114 |
ingred | +0.112 |
ships | +0.109 |
Neg logit contributions | |
Nice | -0.081 |
quiet | -0.077 |
zeb | -0.075 |
isexual | -0.072 |
� | -0.070 |
Token | cover |
Token ID | 3002 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
welf | +0.208 |
weap | +0.194 |
scrut | +0.192 |
ingred | +0.189 |
ships | +0.185 |
Neg logit contributions | |
Nice | -0.172 |
quiet | -0.163 |
zeb | -0.160 |
isexual | -0.154 |
� | -0.151 |
Token | debts |
Token ID | 20250 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
welf | +0.597 |
weap | +0.555 |
scrut | +0.549 |
ingred | +0.541 |
ships | +0.531 |
Neg logit contributions | |
Nice | -0.514 |
quiet | -0.488 |
zeb | -0.482 |
isexual | -0.464 |
� | -0.456 |
Token | owed |
Token ID | 21057 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
welf | +1.749 |
weap | +1.631 |
scrut | +1.620 |
ingred | +1.578 |
ships | +1.559 |
Neg logit contributions | |
Nice | -1.524 |
quiet | -1.461 |
zeb | -1.449 |
isexual | -1.409 |
� | -1.364 |
Token | the |
Token ID | 262 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
welf | +3.763 |
weap | +3.540 |
scrut | +3.515 |
ships | +3.438 |
ingred | +3.406 |
Neg logit contributions | |
Nice | -2.779 |
quiet | -2.673 |
zeb | -2.659 |
isexual | -2.596 |
� | -2.485 |
Token | City |
Token ID | 2254 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
welf | +0.660 |
weap | +0.618 |
scrut | +0.614 |
ingred | +0.603 |
ships | +0.592 |
Neg logit contributions | |
Nice | -0.476 |
quiet | -0.450 |
zeb | -0.445 |
isexual | -0.428 |
� | -0.416 |
Token | of |
Token ID | 286 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Nice | +0.083 |
quiet | +0.079 |
zeb | +0.079 |
isexual | +0.075 |
� | +0.074 |
Neg logit contributions | |
welf | -0.100 |
weap | -0.093 |
scrut | -0.092 |
ingred | -0.091 |
unden | -0.088 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
welf | +0.678 |
weap | +0.636 |
scrut | +0.631 |
ingred | +0.620 |
ships | +0.610 |
Neg logit contributions | |
Nice | -0.459 |
quiet | -0.434 |
zeb | -0.429 |
isexual | -0.413 |
� | -0.401 |
Token | and |
Token ID | 290 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
welf | +0.609 |
weap | +0.567 |
scrut | +0.563 |
ingred | +0.557 |
ships | +0.540 |
Neg logit contributions | |
Nice | -0.470 |
quiet | -0.446 |
zeb | -0.440 |
isexual | -0.422 |
� | -0.414 |
Token | this |
Token ID | 428 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
Nice | +0.045 |
quiet | +0.042 |
zeb | +0.042 |
isexual | +0.040 |
� | +0.039 |
Neg logit contributions | |
welf | -0.056 |
weap | -0.052 |
scrut | -0.052 |
ingred | -0.050 |
ships | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Nice | +0.015 |
quiet | +0.014 |
zeb | +0.014 |
isexual | +0.013 |
� | +0.013 |
Neg logit contributions | |
welf | -0.019 |
scrut | -0.018 |
weap | -0.018 |
ingred | -0.017 |
ships | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
welf | +0.228 |
weap | +0.213 |
scrut | +0.212 |
ingred | +0.207 |
ships | +0.202 |
Neg logit contributions | |
Nice | -0.191 |
quiet | -0.178 |
zeb | -0.177 |
isexual | -0.171 |
� | -0.167 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
welf | +0.188 |
weap | +0.174 |
scrut | +0.173 |
ingred | +0.173 |
unden | +0.170 |
Neg logit contributions | |
Nice | -0.142 |
quiet | -0.135 |
zeb | -0.133 |
isexual | -0.127 |
� | -0.125 |
Token | P |
Token ID | 47 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
welf | +0.223 |
weap | +0.207 |
scrut | +0.205 |
ingred | +0.200 |
unden | +0.195 |
Neg logit contributions | |
Nice | -0.208 |
quiet | -0.200 |
zeb | -0.197 |
isexual | -0.191 |
� | -0.188 |
Token | ump |
Token ID | 931 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
welf | +1.536 |
weap | +1.431 |
scrut | +1.419 |
ingred | +1.388 |
ships | +1.365 |
Neg logit contributions | |
Nice | -1.333 |
quiet | -1.273 |
zeb | -1.261 |
isexual | -1.221 |
� | -1.189 |
Token | kin |
Token ID | 5116 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
welf | +3.717 |
weap | +3.476 |
scrut | +3.466 |
ingred | +3.404 |
ships | +3.347 |
Neg logit contributions | |
Nice | -2.856 |
quiet | -2.730 |
zeb | -2.701 |
isexual | -2.598 |
� | -2.527 |
Token | Seed |
Token ID | 23262 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
welf | +0.159 |
weap | +0.148 |
scrut | +0.147 |
ingred | +0.144 |
ships | +0.141 |
Neg logit contributions | |
Nice | -0.129 |
quiet | -0.122 |
zeb | -0.121 |
isexual | -0.117 |
� | -0.114 |
Token | Fl |
Token ID | 1610 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Nice | +0.022 |
quiet | +0.021 |
zeb | +0.021 |
isexual | +0.020 |
� | +0.020 |
Neg logit contributions | |
welf | -0.026 |
weap | -0.024 |
scrut | -0.024 |
ingred | -0.023 |
ships | -0.023 |
Token | our |
Token ID | 454 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
welf | +1.422 |
weap | +1.343 |
scrut | +1.335 |
ingred | +1.316 |
unden | +1.286 |
Neg logit contributions | |
Nice | -0.682 |
quiet | -0.644 |
zeb | -0.631 |
isexual | -0.601 |
� | -0.583 |
Token | — |
Token ID | 960 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
welf | +0.122 |
weap | +0.110 |
scrut | +0.109 |
ingred | +0.106 |
ships | +0.103 |
Neg logit contributions | |
Nice | -0.197 |
quiet | -0.191 |
zeb | -0.189 |
isexual | -0.185 |
� | -0.181 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Nice | +0.527 |
quiet | +0.494 |
zeb | +0.492 |
isexual | +0.469 |
� | +0.463 |
Neg logit contributions | |
welf | -0.754 |
weap | -0.710 |
scrut | -0.706 |
ingred | -0.693 |
ships | -0.677 |
Token | ended |
Token ID | 4444 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
welf | +0.667 |
weap | +0.621 |
scrut | +0.614 |
ingred | +0.602 |
ships | +0.591 |
Neg logit contributions | |
Nice | -0.600 |
quiet | -0.574 |
zeb | -0.569 |
isexual | -0.548 |
� | -0.539 |
Token | � |
Token ID | 564 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
welf | +0.956 |
weap | +0.898 |
scrut | +0.891 |
ingred | +0.876 |
ships | +0.862 |
Neg logit contributions | |
Nice | -0.739 |
quiet | -0.699 |
zeb | -0.692 |
isexual | -0.667 |
� | -0.651 |
Token | � |
Token ID | 250 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Nice | +0.115 |
quiet | +0.110 |
zeb | +0.109 |
isexual | +0.105 |
� | +0.102 |
Neg logit contributions | |
welf | -0.144 |
weap | -0.135 |
scrut | -0.134 |
ingred | -0.131 |
ships | -0.129 |
Token | w |
Token ID | 86 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Nice | +0.078 |
quiet | +0.075 |
zeb | +0.074 |
isexual | +0.071 |
� | +0.070 |
Neg logit contributions | |
welf | -0.085 |
weap | -0.079 |
scrut | -0.079 |
ingred | -0.077 |
ships | -0.075 |
Token | elfare |
Token ID | 27122 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
welf | +0.993 |
weap | +0.922 |
scrut | +0.916 |
ingred | +0.895 |
ships | +0.878 |
Neg logit contributions | |
Nice | -0.975 |
quiet | -0.933 |
zeb | -0.925 |
isexual | -0.898 |
� | -0.878 |
Token | as |
Token ID | 355 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
welf | +3.750 |
weap | +3.498 |
scrut | +3.460 |
ingred | +3.393 |
ships | +3.347 |
Neg logit contributions | |
Nice | -2.857 |
quiet | -2.722 |
zeb | -2.686 |
isexual | -2.618 |
� | -2.532 |
Token | we |
Token ID | 356 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Nice | +0.043 |
quiet | +0.041 |
zeb | +0.041 |
isexual | +0.039 |
� | +0.039 |
Neg logit contributions | |
welf | -0.052 |
scrut | -0.049 |
weap | -0.049 |
ingred | -0.048 |
ships | -0.048 |
Token | know |
Token ID | 760 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Nice | +1.136 |
quiet | +1.106 |
zeb | +1.100 |
� | +1.052 |
isexual | +1.050 |
Neg logit contributions | |
welf | -0.863 |
weap | -0.797 |
scrut | -0.786 |
ingred | -0.781 |
ships | -0.759 |
Token | it |
Token ID | 340 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
welf | +0.421 |
weap | +0.393 |
scrut | +0.391 |
ingred | +0.382 |
ships | +0.376 |
Neg logit contributions | |
Nice | -0.361 |
quiet | -0.344 |
zeb | -0.341 |
isexual | -0.329 |
� | -0.322 |
Token | , |
Token ID | 11 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
welf | +0.014 |
weap | +0.013 |
scrut | +0.013 |
ingred | +0.013 |
ships | +0.013 |
Neg logit contributions | |
Nice | -0.015 |
quiet | -0.014 |
zeb | -0.014 |
isexual | -0.014 |
� | -0.014 |
Token | an |
Token ID | 281 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
welf | +0.649 |
weap | +0.607 |
scrut | +0.592 |
ingred | +0.587 |
unden | +0.573 |
Neg logit contributions | |
Nice | -0.591 |
zeb | -0.557 |
quiet | -0.552 |
isexual | -0.529 |
� | -0.519 |
Token | alternative |
Token ID | 5559 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Nice | +0.379 |
zeb | +0.360 |
quiet | +0.359 |
isexual | +0.347 |
� | +0.340 |
Neg logit contributions | |
welf | -0.359 |
weap | -0.334 |
scrut | -0.325 |
ingred | -0.318 |
ships | -0.315 |
Token | to |
Token ID | 284 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Nice | +0.499 |
zeb | +0.464 |
quiet | +0.460 |
isexual | +0.427 |
� | +0.416 |
Neg logit contributions | |
welf | -1.050 |
weap | -0.987 |
ingred | -0.984 |
scrut | -0.968 |
ships | -0.960 |
Token | The |
Token ID | 383 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
Nice | +0.104 |
zeb | +0.095 |
quiet | +0.091 |
Knox | +0.086 |
igue | +0.086 |
Neg logit contributions | |
welf | -0.165 |
weap | -0.156 |
scrut | -0.156 |
ingred | -0.155 |
unden | -0.154 |
Token | Ad |
Token ID | 1215 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Nice | +0.542 |
zeb | +0.507 |
quiet | +0.502 |
isexual | +0.481 |
� | +0.466 |
Neg logit contributions | |
welf | -0.807 |
weap | -0.755 |
scrut | -0.747 |
ingred | -0.740 |
ships | -0.721 |
Token | vertis |
Token ID | 3346 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
welf | +0.305 |
weap | +0.273 |
scrut | +0.269 |
ingred | +0.261 |
ships | +0.254 |
Neg logit contributions | |
Nice | -0.548 |
quiet | -0.531 |
zeb | -0.527 |
isexual | -0.514 |
� | -0.505 |
Token | er |
Token ID | 263 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
welf | +4.011 |
weap | +3.803 |
scrut | +3.767 |
ships | +3.689 |
ingred | +3.674 |
Neg logit contributions | |
Nice | -2.508 |
quiet | -2.369 |
zeb | -2.341 |
isexual | -2.289 |
� | -2.198 |
Token | , |
Token ID | 11 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
welf | +0.060 |
weap | +0.056 |
ingred | +0.056 |
scrut | +0.056 |
unden | +0.053 |
Neg logit contributions | |
Nice | -0.039 |
zeb | -0.037 |
quiet | -0.037 |
isexual | -0.035 |
� | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Nice | +0.041 |
zeb | +0.036 |
quiet | +0.035 |
igue | +0.034 |
� | +0.034 |
Neg logit contributions | |
welf | -0.056 |
ingred | -0.052 |
weap | -0.052 |
scrut | -0.051 |
unden | -0.051 |
Token | different |
Token ID | 1180 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
welf | +0.278 |
weap | +0.261 |
ingred | +0.256 |
scrut | +0.256 |
ships | +0.253 |
Neg logit contributions | |
Nice | -0.223 |
quiet | -0.208 |
zeb | -0.207 |
isexual | -0.194 |
� | -0.192 |
Token | voice |
Token ID | 3809 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
welf | +0.364 |
weap | +0.333 |
ingred | +0.333 |
scrut | +0.328 |
ships | +0.323 |
Neg logit contributions | |
Nice | -0.360 |
zeb | -0.340 |
quiet | -0.336 |
� | -0.319 |
isexual | -0.318 |
Token | MORE |
Token ID | 12011 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Nice | +0.552 |
quiet | +0.524 |
zeb | +0.519 |
isexual | +0.501 |
� | +0.487 |
Neg logit contributions | |
welf | -0.685 |
weap | -0.641 |
scrut | -0.635 |
ingred | -0.622 |
ships | -0.612 |
Token | and |
Token ID | 290 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Nice | +0.819 |
quiet | +0.781 |
zeb | +0.772 |
isexual | +0.746 |
� | +0.726 |
Neg logit contributions | |
welf | -1.031 |
weap | -0.963 |
scrut | -0.955 |
ingred | -0.935 |
ships | -0.920 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
Nice | +0.560 |
quiet | +0.525 |
zeb | +0.522 |
isexual | +0.501 |
� | +0.486 |
Neg logit contributions | |
welf | -0.747 |
weap | -0.699 |
scrut | -0.694 |
ingred | -0.678 |
ships | -0.673 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
welf | +0.077 |
weap | +0.072 |
scrut | +0.072 |
ingred | +0.070 |
ships | +0.069 |
Neg logit contributions | |
Nice | -0.049 |
quiet | -0.046 |
zeb | -0.046 |
isexual | -0.044 |
� | -0.043 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
welf | +0.146 |
weap | +0.138 |
scrut | +0.137 |
ingred | +0.135 |
ships | +0.133 |
Neg logit contributions | |
Nice | -0.070 |
quiet | -0.066 |
zeb | -0.065 |
isexual | -0.062 |
� | -0.059 |
Token | Diane |
Token ID | 26542 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
welf | +0.445 |
weap | +0.407 |
scrut | +0.405 |
ingred | +0.398 |
unden | +0.395 |
Neg logit contributions | |
Nice | -0.460 |
quiet | -0.429 |
zeb | -0.423 |
isexual | -0.410 |
igue | -0.406 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
welf | +2.361 |
scrut | +2.115 |
weap | +2.113 |
ships | +1.999 |
ingred | +1.995 |
Neg logit contributions | |
Nice | -4.058 |
quiet | -3.962 |
zeb | -3.935 |
isexual | -3.890 |
� | -3.820 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
welf | +1.041 |
weap | +0.983 |
scrut | +0.975 |
ingred | +0.958 |
ships | +0.939 |
Neg logit contributions | |
Nice | -0.631 |
quiet | -0.592 |
zeb | -0.577 |
isexual | -0.552 |
� | -0.541 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
welf | +0.426 |
weap | +0.392 |
scrut | +0.387 |
ingred | +0.375 |
ships | +0.367 |
Neg logit contributions | |
Nice | -0.508 |
quiet | -0.491 |
zeb | -0.482 |
isexual | -0.470 |
� | -0.462 |
Token | : |
Token ID | 25 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
welf | +0.313 |
weap | +0.283 |
scrut | +0.275 |
ingred | +0.266 |
unden | +0.266 |
Neg logit contributions | |
Nice | -0.465 |
quiet | -0.441 |
zeb | -0.435 |
isexual | -0.422 |
igue | -0.417 |
Token | ' |
Token ID | 705 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
welf | +0.971 |
weap | +0.897 |
scrut | +0.886 |
ingred | +0.865 |
ships | +0.864 |
Neg logit contributions | |
Nice | -0.983 |
quiet | -0.962 |
zeb | -0.954 |
isexual | -0.915 |
� | -0.907 |
Token | � |
Token ID | 247 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
Nice | +0.253 |
quiet | +0.243 |
zeb | +0.240 |
� | +0.230 |
isexual | +0.230 |
Neg logit contributions | |
welf | -0.381 |
weap | -0.355 |
scrut | -0.351 |
ingred | -0.340 |
unden | -0.336 |
Token | s |
Token ID | 82 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
Nice | +0.010 |
quiet | +0.009 |
zeb | +0.009 |
isexual | +0.009 |
� | +0.009 |
Neg logit contributions | |
welf | -0.009 |
weap | -0.008 |
scrut | -0.008 |
ingred | -0.008 |
unden | -0.008 |
Token | been |
Token ID | 587 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Nice | +0.492 |
quiet | +0.466 |
zeb | +0.462 |
isexual | +0.446 |
� | +0.433 |
Neg logit contributions | |
welf | -0.641 |
weap | -0.600 |
scrut | -0.593 |
ingred | -0.582 |
ships | -0.573 |
Token | made |
Token ID | 925 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
Nice | +0.222 |
quiet | +0.211 |
zeb | +0.209 |
isexual | +0.202 |
� | +0.196 |
Neg logit contributions | |
welf | -0.283 |
weap | -0.265 |
scrut | -0.262 |
ingred | -0.257 |
ships | -0.253 |
Token | since |
Token ID | 1201 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
welf | +0.034 |
weap | +0.032 |
scrut | +0.032 |
ingred | +0.031 |
ships | +0.030 |
Neg logit contributions | |
Nice | -0.026 |
quiet | -0.025 |
zeb | -0.024 |
isexual | -0.024 |
� | -0.023 |
Token | owes |
Token ID | 29264 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
Nice | +1.324 |
quiet | +1.232 |
zeb | +1.218 |
isexual | +1.158 |
� | +1.137 |
Neg logit contributions | |
welf | -1.802 |
weap | -1.694 |
scrut | -1.673 |
ingred | -1.641 |
ships | -1.617 |
Token | something |
Token ID | 1223 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
welf | +3.452 |
weap | +3.221 |
scrut | +3.191 |
ingred | +3.127 |
ships | +3.085 |
Neg logit contributions | |
Nice | -2.982 |
quiet | -2.867 |
zeb | -2.838 |
isexual | -2.751 |
� | -2.671 |
Token | to |
Token ID | 284 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Nice | +0.721 |
quiet | +0.666 |
zeb | +0.647 |
isexual | +0.629 |
� | +0.614 |
Neg logit contributions | |
welf | -1.283 |
weap | -1.215 |
scrut | -1.199 |
ingred | -1.175 |
ships | -1.161 |
Token | Annie |
Token ID | 25860 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
Nice | +0.492 |
quiet | +0.462 |
zeb | +0.456 |
isexual | +0.441 |
� | +0.427 |
Neg logit contributions | |
welf | -0.673 |
weap | -0.634 |
scrut | -0.628 |
ingred | -0.615 |
ships | -0.604 |
Token | Hall |
Token ID | 4789 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
welf | +0.058 |
weap | +0.054 |
scrut | +0.053 |
ingred | +0.052 |
ships | +0.051 |
Neg logit contributions | |
Nice | -0.054 |
quiet | -0.052 |
zeb | -0.051 |
isexual | -0.050 |
� | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
welf | +0.521 |
weap | +0.481 |
scrut | +0.477 |
ingred | +0.464 |
ships | +0.455 |
Neg logit contributions | |
Nice | -0.573 |
quiet | -0.550 |
zeb | -0.546 |
isexual | -0.529 |
� | -0.519 |
Token | � |
Token ID | 447 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
welf | +0.492 |
weap | +0.460 |
scrut | +0.458 |
ingred | +0.449 |
ships | +0.440 |
Neg logit contributions | |
Nice | -0.360 |
quiet | -0.340 |
zeb | -0.335 |
isexual | -0.323 |
� | -0.316 |
Token | � |
Token ID | 251 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
welf | +0.520 |
weap | +0.483 |
scrut | +0.479 |
ingred | +0.468 |
unden | +0.456 |
Neg logit contributions | |
Nice | -0.396 |
quiet | -0.380 |
zeb | -0.374 |
isexual | -0.359 |
� | -0.354 |
Token | says |
Token ID | 1139 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
Nice | +0.172 |
quiet | +0.165 |
zeb | +0.161 |
isexual | +0.155 |
� | +0.152 |
Neg logit contributions | |
welf | -0.222 |
weap | -0.207 |
scrut | -0.205 |
ingred | -0.201 |
ships | -0.195 |
Token | NASA |
Token ID | 8884 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
welf | +0.079 |
weap | +0.074 |
scrut | +0.073 |
ingred | +0.072 |
ships | +0.071 |
Neg logit contributions | |
Nice | -0.053 |
quiet | -0.050 |
zeb | -0.050 |
isexual | -0.048 |
� | -0.047 |
Token | Goddard |
Token ID | 47386 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
welf | +0.522 |
weap | +0.479 |
scrut | +0.476 |
ingred | +0.464 |
ships | +0.455 |
Neg logit contributions | |
Nice | -0.596 |
quiet | -0.573 |
zeb | -0.567 |
isexual | -0.549 |
� | -0.539 |
Token | glac |
Token ID | 25169 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
Nice | +0.489 |
quiet | +0.461 |
zeb | +0.451 |
isexual | +0.437 |
igue | +0.430 |
Neg logit contributions | |
welf | -0.597 |
scrut | -0.552 |
weap | -0.552 |
ingred | -0.540 |
unden | -0.530 |
Token | iologist |
Token ID | 31599 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
welf | +3.298 |
weap | +3.134 |
scrut | +3.048 |
ships | +2.961 |
ingred | +2.957 |
Neg logit contributions | |
Nice | -3.110 |
quiet | -2.955 |
zeb | -2.919 |
isexual | -2.825 |
� | -2.755 |
Token | Kelly |
Token ID | 9077 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
welf | +0.912 |
weap | +0.859 |
scrut | +0.853 |
ingred | +0.838 |
ships | +0.827 |
Neg logit contributions | |
Nice | -0.540 |
quiet | -0.510 |
zeb | -0.503 |
isexual | -0.483 |
� | -0.467 |
Token | Br |
Token ID | 1709 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Nice | +0.153 |
quiet | +0.144 |
zeb | +0.143 |
isexual | +0.137 |
� | +0.134 |
Neg logit contributions | |
welf | -0.205 |
weap | -0.192 |
scrut | -0.191 |
ingred | -0.187 |
ships | -0.184 |
Token | unt |
Token ID | 2797 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Nice | +1.031 |
quiet | +0.986 |
zeb | +0.978 |
isexual | +0.945 |
� | +0.922 |
Neg logit contributions | |
welf | -1.207 |
weap | -1.123 |
scrut | -1.114 |
ingred | -1.091 |
ships | -1.070 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Nice | +1.392 |
quiet | +1.334 |
zeb | +1.329 |
isexual | +1.256 |
� | +1.254 |
Neg logit contributions | |
welf | -1.606 |
weap | -1.494 |
scrut | -1.479 |
ingred | -1.459 |
unden | -1.418 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
welf | +0.135 |
weap | +0.127 |
scrut | +0.126 |
ingred | +0.123 |
ships | +0.122 |
Neg logit contributions | |
Nice | -0.105 |
quiet | -0.098 |
zeb | -0.098 |
isexual | -0.094 |
� | -0.092 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
welf | +0.018 |
weap | +0.017 |
scrut | +0.017 |
ingred | +0.017 |
ships | +0.017 |
Neg logit contributions | |
Nice | -0.015 |
quiet | -0.014 |
zeb | -0.014 |
isexual | -0.013 |
� | -0.013 |
Token | Court |
Token ID | 3078 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
welf | +1.765 |
weap | +1.646 |
scrut | +1.628 |
ingred | +1.603 |
ships | +1.561 |
Neg logit contributions | |
Nice | -1.637 |
quiet | -1.551 |
zeb | -1.535 |
isexual | -1.481 |
� | -1.459 |
Token | Orders |
Token ID | 30689 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
welf | +0.559 |
weap | +0.521 |
scrut | +0.514 |
ingred | +0.503 |
ships | +0.495 |
Neg logit contributions | |
Nice | -0.547 |
quiet | -0.522 |
zeb | -0.517 |
isexual | -0.500 |
� | -0.490 |
Token | on |
Token ID | 319 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
welf | +1.136 |
weap | +1.061 |
scrut | +1.053 |
ingred | +1.030 |
ships | +1.015 |
Neg logit contributions | |
Nice | -0.928 |
quiet | -0.885 |
zeb | -0.876 |
isexual | -0.847 |
� | -0.824 |
Token | Aadhaar |
Token ID | 47727 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
welf | +0.574 |
weap | +0.538 |
scrut | +0.533 |
ingred | +0.523 |
ships | +0.515 |
Neg logit contributions | |
Nice | -0.440 |
quiet | -0.417 |
zeb | -0.412 |
isexual | -0.398 |
� | -0.387 |
Token |
|
Token ID | 198 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
welf | +3.471 |
weap | +3.222 |
scrut | +3.215 |
ingred | +3.131 |
ships | +3.085 |
Neg logit contributions | |
Nice | -2.966 |
quiet | -2.849 |
zeb | -2.821 |
isexual | -2.749 |
� | -2.660 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
welf | +0.532 |
weap | +0.496 |
scrut | +0.492 |
ingred | +0.482 |
ships | +0.472 |
Neg logit contributions | |
Nice | -0.460 |
quiet | -0.439 |
zeb | -0.434 |
isexual | -0.420 |
� | -0.410 |
Token | The |
Token ID | 464 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
welf | +0.342 |
weap | +0.319 |
scrut | +0.314 |
ingred | +0.308 |
unden | +0.299 |
Neg logit contributions | |
Nice | -0.344 |
quiet | -0.333 |
zeb | -0.327 |
isexual | -0.316 |
� | -0.312 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
welf | +0.031 |
weap | +0.029 |
scrut | +0.029 |
ingred | +0.028 |
ships | +0.028 |
Neg logit contributions | |
Nice | -0.029 |
quiet | -0.028 |
zeb | -0.027 |
isexual | -0.026 |
� | -0.026 |
Token | Court |
Token ID | 3078 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
welf | +1.702 |
weap | +1.585 |
scrut | +1.566 |
ingred | +1.540 |
ships | +1.503 |
Neg logit contributions | |
Nice | -1.588 |
quiet | -1.510 |
zeb | -1.494 |
isexual | -1.443 |
� | -1.413 |
Token | 23 |
Token ID | 2242 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
welf | +0.106 |
weap | +0.100 |
scrut | +0.099 |
ingred | +0.098 |
ships | +0.096 |
Neg logit contributions | |
Nice | -0.081 |
quiet | -0.075 |
zeb | -0.075 |
isexual | -0.072 |
� | -0.069 |
Token | Muslim |
Token ID | 3765 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Nice | +0.139 |
quiet | +0.132 |
zeb | +0.131 |
isexual | +0.127 |
� | +0.123 |
Neg logit contributions | |
welf | -0.164 |
weap | -0.154 |
scrut | -0.151 |
ingred | -0.149 |
ships | -0.146 |
Token | organisations |
Token ID | 16435 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
welf | +2.088 |
weap | +1.940 |
scrut | +1.935 |
ingred | +1.882 |
ships | +1.851 |
Neg logit contributions | |
Nice | -1.830 |
quiet | -1.763 |
zeb | -1.742 |
isexual | -1.691 |
� | -1.653 |
Token | in |
Token ID | 287 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
welf | +0.229 |
weap | +0.214 |
scrut | +0.211 |
ingred | +0.208 |
ships | +0.204 |
Neg logit contributions | |
Nice | -0.181 |
quiet | -0.172 |
zeb | -0.171 |
isexual | -0.164 |
� | -0.160 |
Token | Tamil |
Token ID | 32519 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
welf | +0.273 |
weap | +0.259 |
scrut | +0.254 |
ingred | +0.252 |
ships | +0.247 |
Neg logit contributions | |
Nice | -0.227 |
quiet | -0.211 |
zeb | -0.209 |
isexual | -0.202 |
� | -0.196 |
Token | Nadu |
Token ID | 46917 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
welf | +1.138 |
weap | +0.935 |
scrut | +0.910 |
ingred | +0.843 |
ships | +0.837 |
Neg logit contributions | |
Nice | -4.104 |
quiet | -4.009 |
zeb | -3.973 |
isexual | -3.911 |
� | -3.858 |
Token | before |
Token ID | 878 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
welf | +3.367 |
weap | +3.125 |
scrut | +3.116 |
ingred | +3.016 |
ships | +3.015 |
Neg logit contributions | |
Nice | -3.018 |
quiet | -2.899 |
zeb | -2.864 |
isexual | -2.800 |
� | -2.694 |
Token | its |
Token ID | 663 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
welf | +0.055 |
weap | +0.051 |
scrut | +0.051 |
ingred | +0.050 |
ships | +0.049 |
Neg logit contributions | |
Nice | -0.043 |
quiet | -0.040 |
zeb | -0.040 |
isexual | -0.038 |
� | -0.037 |
Token | release |
Token ID | 2650 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Nice | +0.526 |
quiet | +0.491 |
zeb | +0.491 |
isexual | +0.472 |
� | +0.458 |
Neg logit contributions | |
welf | -0.514 |
weap | -0.481 |
scrut | -0.471 |
ingred | -0.469 |
ships | -0.461 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
welf | +1.020 |
weap | +0.954 |
scrut | +0.946 |
ingred | +0.926 |
ships | +0.912 |
Neg logit contributions | |
Nice | -0.803 |
quiet | -0.765 |
zeb | -0.757 |
isexual | -0.731 |
� | -0.711 |
Token | before |
Token ID | 878 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
welf | +0.092 |
weap | +0.086 |
scrut | +0.085 |
ingred | +0.084 |
ships | +0.083 |
Neg logit contributions | |
Nice | -0.075 |
quiet | -0.070 |
zeb | -0.070 |
isexual | -0.067 |
� | -0.065 |
Token | ! |
Token ID | 0 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Nice | +2.017 |
quiet | +1.870 |
zeb | +1.826 |
� | +1.766 |
isexual | +1.758 |
Neg logit contributions | |
welf | -2.353 |
weap | -2.233 |
scrut | -2.150 |
ships | -2.146 |
ingred | -2.143 |
Token | If |
Token ID | 1002 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Nice | +0.543 |
quiet | +0.505 |
zeb | +0.497 |
isexual | +0.479 |
� | +0.470 |
Neg logit contributions | |
welf | -0.661 |
weap | -0.618 |
scrut | -0.612 |
ingred | -0.603 |
ships | -0.588 |
Token | you |
Token ID | 345 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
welf | +1.046 |
weap | +0.972 |
scrut | +0.963 |
ingred | +0.943 |
ships | +0.927 |
Neg logit contributions | |
Nice | -0.956 |
quiet | -0.912 |
zeb | -0.903 |
isexual | -0.875 |
� | -0.854 |
Token | need |
Token ID | 761 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Nice | +1.138 |
quiet | +1.074 |
zeb | +1.053 |
isexual | +1.007 |
� | +0.997 |
Neg logit contributions | |
welf | -1.419 |
weap | -1.306 |
scrut | -1.293 |
ingred | -1.286 |
CLASSIFIED | -1.274 |
Token | a |
Token ID | 257 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
welf | +0.170 |
weap | +0.160 |
scrut | +0.158 |
ingred | +0.155 |
ships | +0.153 |
Neg logit contributions | |
Nice | -0.117 |
quiet | -0.111 |
zeb | -0.110 |
isexual | -0.106 |
� | -0.102 |
Token | compound |
Token ID | 13061 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
Nice | +0.255 |
quiet | +0.239 |
zeb | +0.237 |
isexual | +0.228 |
� | +0.223 |
Neg logit contributions | |
welf | -0.297 |
weap | -0.277 |
scrut | -0.274 |
ingred | -0.270 |
ships | -0.268 |
Token | expression |
Token ID | 5408 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Nice | +3.939 |
quiet | +3.581 |
zeb | +3.517 |
� | +3.437 |
igue | +3.369 |
Neg logit contributions | |
welf | -4.228 |
weap | -3.916 |
ships | -3.893 |
scrut | -3.770 |
ingred | -3.758 |
Token | , |
Token ID | 11 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Nice | +0.948 |
quiet | +0.884 |
zeb | +0.865 |
isexual | +0.827 |
� | +0.820 |
Neg logit contributions | |
welf | -1.311 |
weap | -1.226 |
scrut | -1.203 |
ingred | -1.196 |
ships | -1.179 |
Token | use |
Token ID | 779 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Nice | +0.254 |
quiet | +0.238 |
zeb | +0.235 |
isexual | +0.226 |
� | +0.222 |
Neg logit contributions | |
welf | -0.277 |
weap | -0.256 |
scrut | -0.253 |
ingred | -0.249 |
ships | -0.248 |
Token | ng |
Token ID | 23370 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
welf | +0.495 |
weap | +0.462 |
scrut | +0.457 |
ingred | +0.449 |
ships | +0.443 |
Neg logit contributions | |
Nice | -0.409 |
quiet | -0.389 |
zeb | -0.384 |
isexual | -0.371 |
� | -0.362 |
Token | - |
Token ID | 12 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
Nice | +0.679 |
quiet | +0.648 |
zeb | +0.640 |
isexual | +0.618 |
� | +0.605 |
Neg logit contributions | |
welf | -0.705 |
weap | -0.654 |
scrut | -0.647 |
ingred | -0.634 |
ships | -0.627 |
Token | in |
Token ID | 287 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Nice | +1.454 |
quiet | +1.371 |
zeb | +1.351 |
isexual | +1.298 |
� | +1.259 |
Neg logit contributions | |
welf | -2.345 |
weap | -2.200 |
scrut | -2.190 |
ingred | -2.147 |
ships | -2.113 |
Token | clock |
Token ID | 8801 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Nice | +0.133 |
quiet | +0.127 |
zeb | +0.125 |
isexual | +0.121 |
� | +0.117 |
Neg logit contributions | |
welf | -0.180 |
weap | -0.169 |
scrut | -0.167 |
ingred | -0.164 |
ships | -0.162 |
Token | speeds |
Token ID | 12055 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Nice | +1.828 |
quiet | +1.744 |
zeb | +1.727 |
isexual | +1.640 |
� | +1.628 |
Neg logit contributions | |
welf | -2.076 |
weap | -1.927 |
scrut | -1.907 |
ingred | -1.880 |
ships | -1.837 |
Token | . |
Token ID | 13 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
welf | +0.277 |
weap | +0.258 |
scrut | +0.256 |
ingred | +0.251 |
ships | +0.246 |
Neg logit contributions | |
Nice | -0.245 |
quiet | -0.233 |
zeb | -0.231 |
isexual | -0.222 |
� | -0.218 |
Token | In |
Token ID | 554 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
welf | +0.253 |
weap | +0.236 |
scrut | +0.234 |
ingred | +0.231 |
ships | +0.225 |
Neg logit contributions | |
Nice | -0.207 |
quiet | -0.195 |
zeb | -0.192 |
isexual | -0.185 |
� | -0.181 |
Token | OC |
Token ID | 24775 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
welf | +0.558 |
weap | +0.520 |
scrut | +0.514 |
ingred | +0.506 |
ships | +0.498 |
Neg logit contributions | |
Nice | -0.479 |
quiet | -0.456 |
zeb | -0.449 |
isexual | -0.435 |
� | -0.424 |
Token | M |
Token ID | 337 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
Nice | +1.897 |
quiet | +1.737 |
zeb | +1.638 |
isexual | +1.509 |
� | +1.456 |
Neg logit contributions | |
welf | -5.760 |
weap | -5.443 |
scrut | -5.395 |
ingred | -5.363 |
unden | -5.248 |
Token | ODE |
Token ID | 16820 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Nice | +0.643 |
quiet | +0.613 |
zeb | +0.609 |
isexual | +0.588 |
� | +0.573 |
Neg logit contributions | |
welf | -0.750 |
weap | -0.699 |
scrut | -0.698 |
ingred | -0.680 |
ships | -0.666 |
Token | the |
Token ID | 262 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Nice | +0.757 |
quiet | +0.712 |
zeb | +0.694 |
isexual | +0.664 |
� | +0.648 |
Neg logit contributions | |
welf | -1.228 |
weap | -1.152 |
scrut | -1.143 |
ingred | -1.125 |
ships | -1.108 |
Token | core |
Token ID | 4755 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Nice | +0.187 |
quiet | +0.177 |
zeb | +0.175 |
isexual | +0.168 |
� | +0.165 |
Neg logit contributions | |
welf | -0.216 |
weap | -0.201 |
scrut | -0.199 |
ingred | -0.195 |
ships | -0.193 |
Token | increases |
Token ID | 5732 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Nice | +0.111 |
quiet | +0.106 |
zeb | +0.105 |
isexual | +0.102 |
� | +0.099 |
Neg logit contributions | |
welf | -0.118 |
weap | -0.109 |
scrut | -0.108 |
ingred | -0.106 |
ships | -0.104 |
Token | warm |
Token ID | 5814 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
welf | +0.784 |
weap | +0.731 |
scrut | +0.725 |
ingred | +0.709 |
ships | +0.698 |
Neg logit contributions | |
Nice | -0.682 |
quiet | -0.651 |
zeb | -0.645 |
isexual | -0.625 |
� | -0.608 |
Token | and |
Token ID | 290 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
welf | +0.154 |
weap | +0.143 |
scrut | +0.142 |
ingred | +0.139 |
ships | +0.136 |
Neg logit contributions | |
Nice | -0.135 |
quiet | -0.129 |
zeb | -0.128 |
isexual | -0.124 |
� | -0.121 |
Token | stubborn |
Token ID | 24444 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
Nice | +0.285 |
quiet | +0.271 |
zeb | +0.267 |
isexual | +0.257 |
� | +0.250 |
Neg logit contributions | |
welf | -0.392 |
weap | -0.367 |
scrut | -0.363 |
ingred | -0.357 |
ships | -0.352 |
Token | sonic |
Token ID | 36220 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
welf | +0.560 |
weap | +0.519 |
scrut | +0.514 |
ingred | +0.502 |
ships | +0.493 |
Neg logit contributions | |
Nice | -0.554 |
quiet | -0.530 |
zeb | -0.524 |
isexual | -0.508 |
� | -0.497 |
Token | imp |
Token ID | 848 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
welf | +0.080 |
weap | +0.074 |
scrut | +0.073 |
ingred | +0.071 |
ships | +0.070 |
Neg logit contributions | |
Nice | -0.084 |
quiet | -0.080 |
zeb | -0.080 |
isexual | -0.077 |
� | -0.075 |
Token | urities |
Token ID | 10886 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
welf | +0.602 |
weap | +0.560 |
scrut | +0.555 |
ingred | +0.543 |
ships | +0.533 |
Neg logit contributions | |
Nice | -0.534 |
quiet | -0.511 |
zeb | -0.505 |
isexual | -0.489 |
� | -0.477 |
Token | , |
Token ID | 11 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Nice | +3.264 |
quiet | +3.140 |
zeb | +3.071 |
� | +2.973 |
isexual | +2.954 |
Neg logit contributions | |
welf | -4.126 |
weap | -3.798 |
ingred | -3.723 |
scrut | -3.698 |
CLASSIFIED | -3.655 |
Token | having |
Token ID | 1719 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Nice | +0.280 |
quiet | +0.266 |
zeb | +0.263 |
isexual | +0.254 |
� | +0.248 |
Neg logit contributions | |
welf | -0.359 |
weap | -0.336 |
scrut | -0.333 |
ingred | -0.326 |
ships | -0.321 |
Token | been |
Token ID | 587 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Nice | +1.031 |
quiet | +0.983 |
zeb | +0.970 |
isexual | +0.938 |
� | +0.917 |
Neg logit contributions | |
welf | -1.318 |
weap | -1.232 |
scrut | -1.215 |
ingred | -1.196 |
ships | -1.175 |
Token | encoded |
Token ID | 30240 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Nice | +0.155 |
quiet | +0.148 |
zeb | +0.147 |
isexual | +0.141 |
� | +0.139 |
Neg logit contributions | |
welf | -0.186 |
weap | -0.174 |
scrut | -0.172 |
ingred | -0.169 |
ships | -0.166 |
Token | in |
Token ID | 287 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Nice | +0.736 |
quiet | +0.704 |
zeb | +0.691 |
isexual | +0.667 |
� | +0.656 |
Neg logit contributions | |
welf | -1.027 |
weap | -0.953 |
scrut | -0.949 |
ingred | -0.929 |
ships | -0.917 |
Token | earlier |
Token ID | 2961 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
welf | +0.232 |
weap | +0.217 |
scrut | +0.216 |
ingred | +0.213 |
ships | +0.208 |
Neg logit contributions | |
Nice | -0.182 |
quiet | -0.173 |
zeb | -0.170 |
isexual | -0.164 |
� | -0.161 |
Token | works |
Token ID | 2499 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Nice | +0.484 |
quiet | +0.462 |
zeb | +0.454 |
isexual | +0.441 |
� | +0.431 |
Neg logit contributions | |
welf | -0.458 |
weap | -0.425 |
scrut | -0.424 |
ingred | -0.413 |
ships | -0.401 |
Token | like |
Token ID | 588 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
welf | +0.110 |
weap | +0.102 |
scrut | +0.101 |
ingred | +0.100 |
ships | +0.098 |
Neg logit contributions | |
Nice | -0.094 |
quiet | -0.090 |
zeb | -0.089 |
isexual | -0.086 |
� | -0.084 |
Token | The |
Token ID | 383 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Nice | +0.353 |
quiet | +0.332 |
zeb | +0.329 |
isexual | +0.316 |
� | +0.309 |
Neg logit contributions | |
welf | -0.462 |
weap | -0.432 |
scrut | -0.429 |
ingred | -0.422 |
ships | -0.413 |
Token | Cour |
Token ID | 2734 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Nice | +0.460 |
quiet | +0.436 |
zeb | +0.430 |
isexual | +0.415 |
� | +0.405 |
Neg logit contributions | |
welf | -0.584 |
weap | -0.545 |
scrut | -0.541 |
ingred | -0.531 |
ships | -0.520 |
Token | tyard |
Token ID | 30308 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
Nice | +0.694 |
quiet | +0.654 |
zeb | +0.645 |
isexual | +0.611 |
� | +0.595 |
Neg logit contributions | |
welf | -1.343 |
weap | -1.268 |
scrut | -1.260 |
ingred | -1.236 |
unden | -1.208 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Nice | +3.260 |
quiet | +3.020 |
zeb | +2.995 |
� | +2.855 |
isexual | +2.830 |
Neg logit contributions | |
welf | -4.126 |
weap | -3.839 |
scrut | -3.833 |
ingred | -3.812 |
unden | -3.664 |
Token | where |
Token ID | 810 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
welf | +0.174 |
weap | +0.163 |
scrut | +0.161 |
ingred | +0.159 |
ships | +0.156 |
Neg logit contributions | |
Nice | -0.132 |
quiet | -0.125 |
zeb | -0.124 |
isexual | -0.119 |
� | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Nice | +0.187 |
quiet | +0.175 |
zeb | +0.173 |
isexual | +0.167 |
� | +0.163 |
Neg logit contributions | |
welf | -0.260 |
weap | -0.243 |
scrut | -0.242 |
ingred | -0.238 |
ships | -0.234 |
Token | characters |
Token ID | 3435 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
welf | +0.203 |
weap | +0.188 |
scrut | +0.187 |
ingred | +0.183 |
ships | +0.180 |
Neg logit contributions | |
Nice | -0.183 |
quiet | -0.174 |
zeb | -0.172 |
isexual | -0.166 |
� | -0.163 |
Token | boast |
Token ID | 28020 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
welf | +0.442 |
weap | +0.411 |
scrut | +0.407 |
ingred | +0.401 |
ships | +0.393 |
Neg logit contributions | |
Nice | -0.374 |
quiet | -0.357 |
zeb | -0.353 |
isexual | -0.341 |
� | -0.334 |
Token | was |
Token ID | 373 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
welf | +0.208 |
weap | +0.194 |
scrut | +0.192 |
ingred | +0.188 |
ships | +0.185 |
Neg logit contributions | |
Nice | -0.179 |
quiet | -0.170 |
zeb | -0.169 |
isexual | -0.163 |
� | -0.160 |
Token | characterized |
Token ID | 16264 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Nice | +0.045 |
quiet | +0.042 |
zeb | +0.042 |
isexual | +0.040 |
� | +0.039 |
Neg logit contributions | |
welf | -0.061 |
weap | -0.057 |
scrut | -0.057 |
ingred | -0.056 |
ships | -0.055 |
Token | as |
Token ID | 355 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
welf | +0.185 |
weap | +0.173 |
scrut | +0.171 |
ingred | +0.168 |
ships | +0.165 |
Neg logit contributions | |
Nice | -0.146 |
quiet | -0.138 |
zeb | -0.137 |
isexual | -0.132 |
� | -0.129 |
Token | having |
Token ID | 1719 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Nice | +0.604 |
quiet | +0.566 |
zeb | +0.555 |
isexual | +0.545 |
� | +0.528 |
Neg logit contributions | |
welf | -0.760 |
weap | -0.712 |
scrut | -0.702 |
ingred | -0.690 |
ships | -0.683 |
Token | bacterial |
Token ID | 23462 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Nice | +1.438 |
quiet | +1.334 |
zeb | +1.301 |
isexual | +1.299 |
� | +1.249 |
Neg logit contributions | |
welf | -1.777 |
weap | -1.669 |
scrut | -1.622 |
ingred | -1.611 |
ships | -1.585 |
Token | vag |
Token ID | 14334 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
Nice | +1.812 |
quiet | +1.706 |
zeb | +1.688 |
isexual | +1.687 |
� | +1.591 |
Neg logit contributions | |
welf | -1.992 |
weap | -1.873 |
scrut | -1.828 |
ingred | -1.800 |
ships | -1.785 |
Token | in |
Token ID | 259 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
Nice | +2.009 |
quiet | +1.903 |
zeb | +1.823 |
isexual | +1.773 |
igue | +1.640 |
Neg logit contributions | |
welf | -5.151 |
weap | -4.870 |
scrut | -4.806 |
ingred | -4.789 |
unden | -4.713 |
Token | osis |
Token ID | 5958 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Nice | +0.032 |
quiet | +0.031 |
zeb | +0.030 |
isexual | +0.030 |
� | +0.029 |
Neg logit contributions | |
welf | -0.039 |
weap | -0.036 |
scrut | -0.036 |
ingred | -0.035 |
ships | -0.034 |
Token | ( |
Token ID | 357 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Nice | +1.323 |
quiet | +1.248 |
zeb | +1.233 |
isexual | +1.209 |
� | +1.174 |
Neg logit contributions | |
welf | -1.588 |
weap | -1.486 |
scrut | -1.454 |
ingred | -1.436 |
ships | -1.407 |
Token | B |
Token ID | 33 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Nice | +0.270 |
quiet | +0.259 |
zeb | +0.255 |
isexual | +0.249 |
� | +0.242 |
Neg logit contributions | |
welf | -0.298 |
weap | -0.277 |
scrut | -0.273 |
ingred | -0.268 |
ships | -0.260 |
Token | V |
Token ID | 53 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
welf | +0.179 |
weap | +0.166 |
scrut | +0.163 |
ingred | +0.160 |
ships | +0.156 |
Neg logit contributions | |
Nice | -0.174 |
quiet | -0.167 |
zeb | -0.165 |
isexual | -0.163 |
� | -0.159 |
Token | lot |
Token ID | 1256 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
welf | +0.112 |
weap | +0.104 |
scrut | +0.103 |
ingred | +0.102 |
ships | +0.100 |
Neg logit contributions | |
Nice | -0.096 |
quiet | -0.091 |
zeb | -0.090 |
isexual | -0.087 |
� | -0.084 |
Token | of |
Token ID | 286 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
welf | +0.577 |
weap | +0.536 |
scrut | +0.532 |
ingred | +0.516 |
ships | +0.510 |
Neg logit contributions | |
Nice | -0.563 |
quiet | -0.540 |
zeb | -0.538 |
isexual | -0.521 |
� | -0.509 |
Token | sense |
Token ID | 2565 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Nice | +0.044 |
quiet | +0.041 |
zeb | +0.039 |
isexual | +0.037 |
� | +0.036 |
Neg logit contributions | |
welf | -0.089 |
weap | -0.084 |
scrut | -0.083 |
ingred | -0.082 |
ships | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
welf | +0.985 |
weap | +0.916 |
scrut | +0.906 |
ingred | +0.883 |
ships | +0.872 |
Neg logit contributions | |
Nice | -0.982 |
quiet | -0.942 |
zeb | -0.937 |
isexual | -0.909 |
� | -0.887 |
Token | Its |
Token ID | 6363 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
Nice | +0.093 |
quiet | +0.086 |
zeb | +0.085 |
isexual | +0.081 |
� | +0.080 |
Neg logit contributions | |
welf | -0.112 |
scrut | -0.105 |
weap | -0.104 |
ingred | -0.104 |
unden | -0.100 |
Token | admittedly |
Token ID | 33603 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
Nice | +0.554 |
quiet | +0.525 |
zeb | +0.514 |
isexual | +0.493 |
� | +0.484 |
Neg logit contributions | |
welf | -0.642 |
weap | -0.598 |
scrut | -0.592 |
ingred | -0.585 |
ships | -0.579 |
Token | high |
Token ID | 1029 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
Nice | +2.980 |
quiet | +2.793 |
zeb | +2.687 |
isexual | +2.572 |
� | +2.524 |
Neg logit contributions | |
welf | -4.065 |
weap | -3.811 |
ingred | -3.779 |
CLASSIFIED | -3.736 |
scrut | -3.735 |
Token | fuel |
Token ID | 5252 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
welf | +0.055 |
weap | +0.051 |
scrut | +0.051 |
ingred | +0.050 |
ships | +0.049 |
Neg logit contributions | |
Nice | -0.052 |
quiet | -0.049 |
zeb | -0.049 |
isexual | -0.047 |
� | -0.046 |
Token | consumption |
Token ID | 7327 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Nice | +1.592 |
quiet | +1.522 |
zeb | +1.503 |
isexual | +1.447 |
igue | +1.435 |
Neg logit contributions | |
welf | -1.628 |
weap | -1.507 |
scrut | -1.488 |
ingred | -1.452 |
ships | -1.435 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
welf | +0.243 |
weap | +0.227 |
scrut | +0.225 |
ingred | +0.220 |
ships | +0.217 |
Neg logit contributions | |
Nice | -0.200 |
quiet | -0.190 |
zeb | -0.187 |
isexual | -0.180 |
� | -0.176 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Nice | +0.272 |
quiet | +0.258 |
zeb | +0.253 |
isexual | +0.245 |
� | +0.239 |
Neg logit contributions | |
welf | -0.334 |
weap | -0.312 |
scrut | -0.310 |
ingred | -0.305 |
ships | -0.300 |
Token | a |
Token ID | 257 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Nice | +0.022 |
quiet | +0.020 |
zeb | +0.020 |
isexual | +0.019 |
� | +0.019 |
Neg logit contributions | |
welf | -0.027 |
weap | -0.026 |
scrut | -0.025 |
ingred | -0.025 |
ships | -0.025 |
Token | Catalan |
Token ID | 31066 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
Nice | +0.322 |
quiet | +0.303 |
zeb | +0.296 |
isexual | +0.287 |
� | +0.282 |
Neg logit contributions | |
welf | -0.402 |
weap | -0.377 |
scrut | -0.369 |
ingred | -0.367 |
ships | -0.360 |
Token | town |
Token ID | 3240 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Nice | +0.036 |
quiet | +0.034 |
zeb | +0.033 |
isexual | +0.032 |
� | +0.032 |
Neg logit contributions | |
welf | -0.045 |
weap | -0.043 |
scrut | -0.042 |
ingred | -0.041 |
ships | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Nice | +1.390 |
quiet | +1.319 |
zeb | +1.291 |
isexual | +1.244 |
� | +1.219 |
Neg logit contributions | |
welf | -1.870 |
weap | -1.752 |
scrut | -1.726 |
ingred | -1.706 |
unden | -1.655 |
Token | a |
Token ID | 257 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
Nice | +0.244 |
quiet | +0.229 |
zeb | +0.223 |
isexual | +0.216 |
� | +0.213 |
Neg logit contributions | |
welf | -0.319 |
weap | -0.300 |
scrut | -0.295 |
ingred | -0.293 |
ships | -0.286 |
Token | bid |
Token ID | 8406 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
Nice | +0.482 |
quiet | +0.454 |
zeb | +0.445 |
isexual | +0.428 |
� | +0.420 |
Neg logit contributions | |
welf | -0.643 |
weap | -0.604 |
scrut | -0.593 |
ingred | -0.587 |
ships | -0.576 |
Token | to |
Token ID | 284 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
Nice | +2.128 |
quiet | +2.015 |
zeb | +1.917 |
isexual | +1.780 |
� | +1.775 |
Neg logit contributions | |
welf | -4.932 |
weap | -4.597 |
ingred | -4.551 |
scrut | -4.549 |
unden | -4.545 |
Token | sc |
Token ID | 629 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Nice | +0.376 |
quiet | +0.357 |
zeb | +0.348 |
isexual | +0.337 |
� | +0.330 |
Neg logit contributions | |
welf | -0.518 |
weap | -0.484 |
scrut | -0.474 |
ingred | -0.471 |
ships | -0.466 |
Token | upper |
Token ID | 45828 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
welf | +0.088 |
weap | +0.082 |
scrut | +0.082 |
ingred | +0.080 |
ships | +0.079 |
Neg logit contributions | |
Nice | -0.064 |
quiet | -0.061 |
zeb | -0.060 |
isexual | -0.058 |
� | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Nice | +0.143 |
quiet | +0.135 |
zeb | +0.132 |
isexual | +0.128 |
� | +0.126 |
Neg logit contributions | |
welf | -0.184 |
weap | -0.173 |
scrut | -0.170 |
ingred | -0.168 |
ships | -0.165 |
Token | referendum |
Token ID | 11467 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Nice | +0.322 |
quiet | +0.304 |
zeb | +0.297 |
isexual | +0.289 |
� | +0.284 |
Neg logit contributions | |
welf | -0.359 |
weap | -0.335 |
scrut | -0.329 |
ingred | -0.325 |
ships | -0.319 |
Token | tested |
Token ID | 6789 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
Nice | +0.222 |
quiet | +0.213 |
zeb | +0.210 |
isexual | +0.203 |
� | +0.198 |
Neg logit contributions | |
welf | -0.269 |
weap | -0.248 |
ingred | -0.244 |
scrut | -0.244 |
ships | -0.237 |
Token | the |
Token ID | 262 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
welf | +0.074 |
weap | +0.069 |
scrut | +0.068 |
ingred | +0.067 |
ships | +0.066 |
Neg logit contributions | |
Nice | -0.054 |
quiet | -0.051 |
zeb | -0.050 |
isexual | -0.048 |
� | -0.047 |
Token | single |
Token ID | 2060 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
welf | +0.122 |
weap | +0.114 |
scrut | +0.113 |
ingred | +0.110 |
ships | +0.109 |
Neg logit contributions | |
Nice | -0.094 |
quiet | -0.089 |
zeb | -0.087 |
isexual | -0.083 |
� | -0.082 |
Token | card |
Token ID | 2657 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
Nice | +0.294 |
quiet | +0.281 |
zeb | +0.277 |
isexual | +0.269 |
� | +0.263 |
Neg logit contributions | |
welf | -0.330 |
weap | -0.307 |
scrut | -0.304 |
ingred | -0.298 |
ships | -0.294 |
Token | in |
Token ID | 287 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Nice | +1.947 |
quiet | +1.834 |
zeb | +1.794 |
isexual | +1.695 |
� | +1.669 |
Neg logit contributions | |
welf | -2.707 |
weap | -2.516 |
scrut | -2.490 |
ingred | -2.470 |
ships | -2.428 |
Token | OC |
Token ID | 24775 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
welf | +0.281 |
weap | +0.263 |
scrut | +0.259 |
ingred | +0.257 |
ships | +0.253 |
Neg logit contributions | |
Nice | -0.212 |
quiet | -0.202 |
zeb | -0.197 |
isexual | -0.191 |
� | -0.186 |
Token | mode |
Token ID | 4235 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Nice | +2.021 |
quiet | +1.884 |
zeb | +1.809 |
isexual | +1.658 |
� | +1.622 |
Neg logit contributions | |
welf | -4.860 |
weap | -4.593 |
ingred | -4.532 |
scrut | -4.528 |
ships | -4.450 |
Token | , |
Token ID | 11 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
Nice | +1.270 |
quiet | +1.197 |
zeb | +1.166 |
isexual | +1.103 |
� | +1.099 |
Neg logit contributions | |
welf | -1.800 |
weap | -1.681 |
scrut | -1.655 |
ingred | -1.639 |
ships | -1.612 |
Token | but |
Token ID | 475 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
welf | +0.021 |
weap | +0.019 |
scrut | +0.019 |
ingred | +0.019 |
ships | +0.019 |
Neg logit contributions | |
Nice | -0.015 |
quiet | -0.014 |
zeb | -0.014 |
isexual | -0.013 |
� | -0.013 |
Token | we |
Token ID | 356 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
welf | +0.444 |
weap | +0.413 |
scrut | +0.407 |
ingred | +0.404 |
ships | +0.398 |
Neg logit contributions | |
Nice | -0.350 |
quiet | -0.332 |
zeb | -0.325 |
isexual | -0.310 |
� | -0.306 |
Token | are |
Token ID | 389 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Nice | +0.290 |
quiet | +0.278 |
zeb | +0.274 |
isexual | +0.263 |
� | +0.258 |
Neg logit contributions | |
welf | -0.349 |
weap | -0.322 |
ingred | -0.318 |
scrut | -0.316 |
CLASSIFIED | -0.309 |
Token | � |
Token ID | 447 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Nice | +0.385 |
quiet | +0.369 |
zeb | +0.363 |
isexual | +0.348 |
� | +0.346 |
Neg logit contributions | |
welf | -0.453 |
weap | -0.421 |
scrut | -0.417 |
ingred | -0.408 |
ships | -0.400 |
Token | � |
Token ID | 247 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Nice | +0.277 |
quiet | +0.266 |
zeb | +0.263 |
isexual | +0.250 |
� | +0.250 |
Neg logit contributions | |
welf | -0.395 |
weap | -0.368 |
scrut | -0.365 |
ingred | -0.355 |
unden | -0.350 |
Token | s |
Token ID | 82 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Nice | +0.118 |
quiet | +0.114 |
zeb | +0.112 |
isexual | +0.108 |
� | +0.107 |
Neg logit contributions | |
welf | -0.114 |
weap | -0.106 |
scrut | -0.104 |
ingred | -0.102 |
ships | -0.099 |
Token | where |
Token ID | 810 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
Nice | +0.076 |
quiet | +0.072 |
zeb | +0.071 |
isexual | +0.068 |
� | +0.067 |
Neg logit contributions | |
welf | -0.085 |
weap | -0.079 |
scrut | -0.078 |
ingred | -0.076 |
ships | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
Nice | +0.529 |
quiet | +0.502 |
zeb | +0.489 |
isexual | +0.471 |
� | +0.464 |
Neg logit contributions | |
welf | -0.662 |
weap | -0.617 |
scrut | -0.615 |
ingred | -0.602 |
ships | -0.589 |
Token | admittedly |
Token ID | 33603 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
welf | +0.052 |
weap | +0.049 |
scrut | +0.048 |
ingred | +0.047 |
ships | +0.046 |
Neg logit contributions | |
Nice | -0.050 |
quiet | -0.048 |
zeb | -0.047 |
isexual | -0.045 |
� | -0.045 |
Token | tiny |
Token ID | 7009 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Nice | +2.950 |
quiet | +2.784 |
zeb | +2.675 |
� | +2.551 |
isexual | +2.495 |
Neg logit contributions | |
welf | -3.801 |
weap | -3.545 |
ingred | -3.503 |
scrut | -3.464 |
ships | -3.455 |
Token | piece |
Token ID | 3704 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Nice | +0.362 |
quiet | +0.343 |
zeb | +0.337 |
isexual | +0.324 |
� | +0.323 |
Neg logit contributions | |
welf | -0.355 |
weap | -0.329 |
scrut | -0.328 |
ingred | -0.318 |
ships | -0.311 |
Token | of |
Token ID | 286 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Nice | +0.326 |
quiet | +0.312 |
zeb | +0.309 |
isexual | +0.299 |
� | +0.292 |
Neg logit contributions | |
welf | -0.355 |
weap | -0.330 |
scrut | -0.327 |
ingred | -0.320 |
ships | -0.314 |
Token | good |
Token ID | 922 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
welf | +0.192 |
weap | +0.177 |
scrut | +0.176 |
ingred | +0.171 |
ships | +0.169 |
Neg logit contributions | |
Nice | -0.217 |
quiet | -0.208 |
zeb | -0.205 |
isexual | -0.198 |
� | -0.195 |
Token | news |
Token ID | 1705 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
welf | +0.915 |
weap | +0.854 |
scrut | +0.847 |
ingred | +0.830 |
ships | +0.814 |
Neg logit contributions | |
Nice | -0.750 |
quiet | -0.716 |
zeb | -0.707 |
isexual | -0.681 |
� | -0.667 |
Token | be |
Token ID | 307 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Nice | +0.891 |
quiet | +0.863 |
zeb | +0.842 |
isexual | +0.819 |
� | +0.796 |
Neg logit contributions | |
welf | -1.070 |
weap | -0.989 |
scrut | -0.982 |
ingred | -0.965 |
ships | -0.959 |
Token | explained |
Token ID | 4893 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
welf | +0.323 |
weap | +0.301 |
scrut | +0.297 |
ingred | +0.294 |
ships | +0.290 |
Neg logit contributions | |
Nice | -0.269 |
quiet | -0.257 |
zeb | -0.254 |
isexual | -0.246 |
� | -0.238 |
Token | away |
Token ID | 1497 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Nice | +0.084 |
quiet | +0.080 |
zeb | +0.078 |
isexual | +0.074 |
� | +0.072 |
Neg logit contributions | |
welf | -0.146 |
weap | -0.138 |
scrut | -0.136 |
ingred | -0.135 |
ships | -0.132 |
Token | as |
Token ID | 355 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Nice | +1.009 |
quiet | +0.968 |
zeb | +0.953 |
isexual | +0.912 |
� | +0.897 |
Neg logit contributions | |
welf | -1.284 |
weap | -1.201 |
scrut | -1.182 |
ingred | -1.177 |
ships | -1.148 |
Token | an |
Token ID | 281 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
Nice | +0.146 |
quiet | +0.139 |
zeb | +0.137 |
isexual | +0.132 |
� | +0.129 |
Neg logit contributions | |
welf | -0.172 |
weap | -0.160 |
scrut | -0.159 |
ingred | -0.156 |
ships | -0.154 |
Token | aber |
Token ID | 42499 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Nice | +0.556 |
quiet | +0.527 |
zeb | +0.521 |
isexual | +0.505 |
� | +0.493 |
Neg logit contributions | |
welf | -0.686 |
weap | -0.641 |
scrut | -0.634 |
ingred | -0.622 |
ships | -0.615 |
Token | ration |
Token ID | 1358 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
Nice | +2.245 |
quiet | +2.164 |
zeb | +2.066 |
isexual | +2.002 |
igue | +1.932 |
Neg logit contributions | |
welf | -4.497 |
weap | -4.272 |
scrut | -4.215 |
ingred | -4.146 |
unden | -4.104 |
Token | of |
Token ID | 286 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Nice | +1.760 |
quiet | +1.658 |
zeb | +1.647 |
isexual | +1.579 |
� | +1.546 |
Neg logit contributions | |
welf | -2.199 |
weap | -2.060 |
scrut | -2.025 |
ingred | -2.015 |
ships | -1.954 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Nice | +0.216 |
quiet | +0.203 |
zeb | +0.202 |
isexual | +0.194 |
� | +0.190 |
Neg logit contributions | |
welf | -0.278 |
weap | -0.260 |
scrut | -0.258 |
ingred | -0.253 |
ships | -0.250 |
Token | primitive |
Token ID | 20049 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Nice | +0.087 |
quiet | +0.083 |
zeb | +0.082 |
isexual | +0.079 |
� | +0.077 |
Neg logit contributions | |
welf | -0.111 |
weap | -0.104 |
scrut | -0.103 |
ingred | -0.101 |
ships | -0.099 |
Token | mind |
Token ID | 2000 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Nice | +2.092 |
quiet | +1.925 |
zeb | +1.922 |
isexual | +1.828 |
� | +1.826 |
Neg logit contributions | |
welf | -2.446 |
weap | -2.275 |
scrut | -2.258 |
ingred | -2.232 |
ships | -2.189 |
Token | army |
Token ID | 5428 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
welf | +0.902 |
weap | +0.840 |
scrut | +0.833 |
ingred | +0.814 |
ships | +0.801 |
Neg logit contributions | |
Nice | -0.810 |
quiet | -0.774 |
zeb | -0.766 |
isexual | -0.742 |
� | -0.723 |
Token | and |
Token ID | 290 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
welf | +0.483 |
weap | +0.449 |
scrut | +0.446 |
ingred | +0.438 |
ships | +0.429 |
Neg logit contributions | |
Nice | -0.406 |
quiet | -0.387 |
zeb | -0.385 |
isexual | -0.370 |
� | -0.362 |
Token | its |
Token ID | 663 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Nice | +0.208 |
quiet | +0.197 |
zeb | +0.195 |
isexual | +0.187 |
� | +0.183 |
Neg logit contributions | |
welf | -0.278 |
weap | -0.261 |
scrut | -0.259 |
ingred | -0.254 |
ships | -0.251 |
Token | allies |
Token ID | 7681 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Nice | +0.891 |
quiet | +0.834 |
zeb | +0.830 |
isexual | +0.795 |
� | +0.785 |
Neg logit contributions | |
welf | -0.920 |
weap | -0.854 |
scrut | -0.853 |
ingred | -0.837 |
ships | -0.825 |
Token | captured |
Token ID | 7907 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Nice | +0.222 |
quiet | +0.211 |
zeb | +0.209 |
isexual | +0.201 |
� | +0.197 |
Neg logit contributions | |
welf | -0.272 |
weap | -0.253 |
scrut | -0.251 |
ingred | -0.247 |
ships | -0.242 |
Token | turf |
Token ID | 29553 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
Nice | +0.070 |
quiet | +0.065 |
zeb | +0.065 |
isexual | +0.062 |
� | +0.061 |
Neg logit contributions | |
welf | -0.091 |
weap | -0.085 |
scrut | -0.085 |
ingred | -0.083 |
ships | -0.082 |
Token | around |
Token ID | 1088 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Nice | +2.742 |
quiet | +2.581 |
zeb | +2.512 |
� | +2.390 |
isexual | +2.358 |
Neg logit contributions | |
welf | -4.053 |
weap | -3.751 |
scrut | -3.748 |
ingred | -3.704 |
unden | -3.585 |
Token | the |
Token ID | 262 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Nice | +0.865 |
quiet | +0.808 |
zeb | +0.803 |
isexual | +0.768 |
� | +0.749 |
Neg logit contributions | |
welf | -1.281 |
weap | -1.203 |
scrut | -1.196 |
ingred | -1.171 |
ships | -1.152 |
Token | southern |
Token ID | 8372 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Nice | +0.311 |
quiet | +0.295 |
zeb | +0.291 |
isexual | +0.281 |
� | +0.273 |
Neg logit contributions | |
welf | -0.446 |
weap | -0.419 |
scrut | -0.416 |
ingred | -0.408 |
ships | -0.402 |
Token | edge |
Token ID | 5743 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
welf | +0.914 |
weap | +0.858 |
scrut | +0.852 |
ingred | +0.835 |
ships | +0.823 |
Neg logit contributions | |
Nice | -0.619 |
quiet | -0.589 |
zeb | -0.582 |
isexual | -0.561 |
� | -0.543 |
Token | of |
Token ID | 286 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
Nice | +0.971 |
quiet | +0.930 |
zeb | +0.921 |
isexual | +0.895 |
� | +0.871 |
Neg logit contributions | |
welf | -1.012 |
weap | -0.939 |
scrut | -0.931 |
ingred | -0.911 |
ships | -0.897 |
Token | amongst |
Token ID | 12077 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Nice | +1.371 |
quiet | +1.293 |
zeb | +1.273 |
isexual | +1.210 |
� | +1.175 |
Neg logit contributions | |
welf | -2.021 |
weap | -1.893 |
scrut | -1.885 |
ingred | -1.855 |
ships | -1.810 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Nice | +0.934 |
quiet | +0.872 |
zeb | +0.861 |
isexual | +0.826 |
� | +0.801 |
Neg logit contributions | |
welf | -1.252 |
weap | -1.179 |
scrut | -1.167 |
ingred | -1.152 |
ships | -1.141 |
Token | officers |
Token ID | 3790 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
Nice | +0.267 |
quiet | +0.251 |
zeb | +0.247 |
isexual | +0.239 |
� | +0.232 |
Neg logit contributions | |
welf | -0.332 |
weap | -0.312 |
scrut | -0.308 |
ingred | -0.303 |
ships | -0.301 |
Token | , |
Token ID | 11 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
welf | +0.036 |
weap | +0.034 |
scrut | +0.034 |
ingred | +0.033 |
ships | +0.033 |
Neg logit contributions | |
Nice | -0.026 |
quiet | -0.025 |
zeb | -0.025 |
isexual | -0.024 |
� | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Nice | +0.163 |
quiet | +0.154 |
zeb | +0.153 |
isexual | +0.147 |
� | +0.143 |
Neg logit contributions | |
welf | -0.205 |
weap | -0.192 |
scrut | -0.190 |
ingred | -0.187 |
ships | -0.184 |
Token | crude |
Token ID | 14897 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
welf | +0.242 |
weap | +0.226 |
scrut | +0.224 |
ingred | +0.220 |
ships | +0.217 |
Neg logit contributions | |
Nice | -0.199 |
quiet | -0.189 |
zeb | -0.187 |
isexual | -0.180 |
� | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Nice | +3.054 |
quiet | +2.826 |
zeb | +2.814 |
isexual | +2.698 |
� | +2.630 |
Neg logit contributions | |
welf | -3.637 |
scrut | -3.327 |
weap | -3.317 |
ships | -3.286 |
ingred | -3.259 |
Token | disgusting |
Token ID | 23374 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Nice | +0.329 |
quiet | +0.311 |
zeb | +0.308 |
isexual | +0.296 |
� | +0.287 |
Neg logit contributions | |
welf | -0.484 |
weap | -0.454 |
scrut | -0.450 |
ingred | -0.442 |
ships | -0.436 |
Token | comments |
Token ID | 3651 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Nice | +1.022 |
quiet | +0.952 |
zeb | +0.946 |
isexual | +0.908 |
� | +0.887 |
Neg logit contributions | |
welf | -1.259 |
weap | -1.163 |
scrut | -1.161 |
ships | -1.141 |
ingred | -1.133 |
Token | ."" |
Token ID | 32203 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Nice | +1.245 |
quiet | +1.178 |
zeb | +1.160 |
isexual | +1.112 |
� | +1.084 |
Neg logit contributions | |
welf | -1.702 |
weap | -1.589 |
scrut | -1.574 |
ingred | -1.543 |
ships | -1.527 |
Token | Oh |
Token ID | 5812 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Nice | +0.315 |
quiet | +0.299 |
zeb | +0.295 |
isexual | +0.286 |
� | +0.280 |
Neg logit contributions | |
welf | -0.314 |
weap | -0.290 |
scrut | -0.288 |
ingred | -0.284 |
unden | -0.274 |
Token | honey |
Token ID | 12498 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Nice | +0.396 |
quiet | +0.373 |
zeb | +0.369 |
isexual | +0.356 |
� | +0.347 |
Neg logit contributions | |
welf | -0.491 |
weap | -0.458 |
scrut | -0.454 |
ingred | -0.446 |
ships | -0.442 |
Token | comb |
Token ID | 24011 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Nice | +1.080 |
quiet | +1.025 |
zeb | +1.011 |
isexual | +0.962 |
� | +0.938 |
Neg logit contributions | |
welf | -1.609 |
weap | -1.507 |
scrut | -1.498 |
ingred | -1.471 |
ships | -1.442 |
Token | to |
Token ID | 284 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Nice | +1.143 |
quiet | +1.071 |
zeb | +1.059 |
isexual | +1.024 |
� | +1.004 |
Neg logit contributions | |
welf | -1.425 |
weap | -1.334 |
scrut | -1.313 |
ingred | -1.296 |
ships | -1.282 |
Token | mimic |
Token ID | 26332 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Nice | +0.265 |
quiet | +0.250 |
zeb | +0.246 |
isexual | +0.240 |
� | +0.234 |
Neg logit contributions | |
welf | -0.330 |
weap | -0.308 |
scrut | -0.303 |
ingred | -0.298 |
ships | -0.293 |
Token | the |
Token ID | 262 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Nice | +0.988 |
quiet | +0.924 |
zeb | +0.914 |
isexual | +0.884 |
� | +0.866 |
Neg logit contributions | |
welf | -1.260 |
weap | -1.179 |
scrut | -1.166 |
ingred | -1.145 |
ships | -1.135 |
Token | compound |
Token ID | 13061 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
Nice | +0.133 |
quiet | +0.125 |
zeb | +0.124 |
isexual | +0.120 |
� | +0.118 |
Neg logit contributions | |
welf | -0.145 |
weap | -0.136 |
scrut | -0.134 |
ingred | -0.131 |
ships | -0.130 |
Token | eye |
Token ID | 4151 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Nice | +3.035 |
quiet | +2.762 |
zeb | +2.719 |
� | +2.649 |
isexual | +2.638 |
Neg logit contributions | |
welf | -3.655 |
weap | -3.400 |
scrut | -3.353 |
CLASSIFIED | -3.277 |
ships | -3.269 |
Token | of |
Token ID | 286 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
welf | +1.004 |
weap | +0.934 |
scrut | +0.921 |
ingred | +0.900 |
ships | +0.884 |
Neg logit contributions | |
Nice | -0.999 |
quiet | -0.954 |
zeb | -0.948 |
isexual | -0.916 |
� | -0.896 |
Token | a |
Token ID | 257 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
welf | +0.026 |
weap | +0.024 |
scrut | +0.024 |
ingred | +0.024 |
ships | +0.023 |
Neg logit contributions | |
Nice | -0.023 |
quiet | -0.021 |
zeb | -0.021 |
isexual | -0.020 |
� | -0.020 |
Token | fly |
Token ID | 6129 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
Nice | +0.045 |
quiet | +0.042 |
zeb | +0.042 |
isexual | +0.041 |
� | +0.039 |
Neg logit contributions | |
welf | -0.058 |
weap | -0.055 |
scrut | -0.054 |
ingred | -0.053 |
ships | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
welf | +0.484 |
weap | +0.450 |
scrut | +0.446 |
ingred | +0.437 |
ships | +0.428 |
Neg logit contributions | |
Nice | -0.458 |
quiet | -0.438 |
zeb | -0.434 |
isexual | -0.421 |
� | -0.410 |
Token | since |
Token ID | 1201 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Nice | +1.154 |
quiet | +1.098 |
zeb | +1.077 |
isexual | +1.028 |
� | +1.009 |
Neg logit contributions | |
welf | -1.538 |
weap | -1.425 |
scrut | -1.424 |
ingred | -1.404 |
ships | -1.370 |
Token | March |
Token ID | 2805 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
Nice | +0.782 |
quiet | +0.713 |
zeb | +0.677 |
isexual | +0.639 |
� | +0.628 |
Neg logit contributions | |
welf | -1.796 |
weap | -1.696 |
scrut | -1.681 |
ingred | -1.674 |
ships | -1.645 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
welf | +0.646 |
weap | +0.602 |
scrut | +0.596 |
ingred | +0.586 |
ships | +0.574 |
Neg logit contributions | |
Nice | -0.546 |
quiet | -0.520 |
zeb | -0.512 |
isexual | -0.494 |
� | -0.484 |
Token | in |
Token ID | 287 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
welf | +0.363 |
weap | +0.337 |
scrut | +0.334 |
ingred | +0.326 |
ships | +0.321 |
Neg logit contributions | |
Nice | -0.354 |
quiet | -0.339 |
zeb | -0.336 |
isexual | -0.326 |
� | -0.318 |
Token | a |
Token ID | 257 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
welf | +0.212 |
weap | +0.199 |
scrut | +0.195 |
ingred | +0.194 |
ships | +0.190 |
Neg logit contributions | |
Nice | -0.181 |
quiet | -0.171 |
zeb | -0.167 |
isexual | -0.162 |
� | -0.159 |
Token | bid |
Token ID | 8406 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
Nice | +0.094 |
quiet | +0.087 |
zeb | +0.085 |
isexual | +0.081 |
� | +0.078 |
Neg logit contributions | |
welf | -0.196 |
weap | -0.186 |
scrut | -0.184 |
ingred | -0.182 |
ships | -0.180 |
Token | to |
Token ID | 284 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Nice | +2.154 |
quiet | +2.045 |
zeb | +1.975 |
isexual | +1.874 |
� | +1.821 |
Neg logit contributions | |
welf | -4.454 |
weap | -4.217 |
scrut | -4.166 |
ingred | -4.122 |
unden | -4.044 |
Token | help |
Token ID | 1037 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Nice | +0.153 |
quiet | +0.146 |
zeb | +0.143 |
isexual | +0.138 |
� | +0.135 |
Neg logit contributions | |
welf | -0.196 |
weap | -0.183 |
scrut | -0.181 |
ingred | -0.178 |
ships | -0.176 |
Token | economic |
Token ID | 3034 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Nice | +0.870 |
quiet | +0.828 |
zeb | +0.811 |
isexual | +0.786 |
� | +0.769 |
Neg logit contributions | |
welf | -1.105 |
weap | -1.035 |
scrut | -1.028 |
ingred | -1.006 |
ships | -0.991 |
Token | recovery |
Token ID | 7628 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
welf | +0.136 |
weap | +0.128 |
scrut | +0.127 |
ingred | +0.124 |
ships | +0.122 |
Neg logit contributions | |
Nice | -0.111 |
quiet | -0.106 |
zeb | -0.105 |
isexual | -0.101 |
� | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Nice | +0.472 |
quiet | +0.452 |
zeb | +0.445 |
isexual | +0.431 |
� | +0.422 |
Neg logit contributions | |
welf | -0.503 |
weap | -0.467 |
scrut | -0.463 |
ingred | -0.454 |
ships | -0.444 |
Token | in |
Token ID | 287 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
welf | +0.078 |
weap | +0.072 |
scrut | +0.072 |
ingred | +0.070 |
ships | +0.069 |
Neg logit contributions | |
Nice | -0.065 |
quiet | -0.061 |
zeb | -0.061 |
isexual | -0.058 |
� | -0.058 |
Token | turn |
Token ID | 1210 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
welf | +0.016 |
weap | +0.015 |
scrut | +0.015 |
ingred | +0.015 |
ships | +0.015 |
Neg logit contributions | |
Nice | -0.011 |
quiet | -0.010 |
zeb | -0.010 |
isexual | -0.010 |
� | -0.009 |
Token | results |
Token ID | 2482 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Nice | +1.359 |
quiet | +1.289 |
zeb | +1.281 |
isexual | +1.235 |
� | +1.224 |
Neg logit contributions | |
welf | -1.475 |
weap | -1.365 |
scrut | -1.351 |
ingred | -1.330 |
unden | -1.290 |
Token | in |
Token ID | 287 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Nice | +1.136 |
quiet | +1.070 |
zeb | +1.057 |
isexual | +1.013 |
� | +0.983 |
Neg logit contributions | |
welf | -1.929 |
weap | -1.817 |
scrut | -1.805 |
ingred | -1.768 |
ships | -1.744 |
Token | the |
Token ID | 262 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Nice | +0.272 |
quiet | +0.256 |
zeb | +0.252 |
isexual | +0.243 |
� | +0.239 |
Neg logit contributions | |
welf | -0.349 |
weap | -0.327 |
scrut | -0.325 |
ingred | -0.318 |
ships | -0.312 |
Token | dil |
Token ID | 11844 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
Nice | +0.460 |
quiet | +0.435 |
zeb | +0.431 |
isexual | +0.417 |
� | +0.410 |
Neg logit contributions | |
welf | -0.463 |
weap | -0.432 |
scrut | -0.427 |
ingred | -0.417 |
ships | -0.408 |
Token | ution |
Token ID | 1009 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Nice | +2.447 |
quiet | +2.354 |
zeb | +2.313 |
isexual | +2.215 |
igue | +2.164 |
Neg logit contributions | |
welf | -4.175 |
weap | -3.955 |
scrut | -3.871 |
ingred | -3.850 |
unden | -3.762 |
Token | of |
Token ID | 286 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
Nice | +1.489 |
quiet | +1.415 |
zeb | +1.401 |
isexual | +1.351 |
� | +1.329 |
Neg logit contributions | |
welf | -1.684 |
weap | -1.570 |
scrut | -1.555 |
ingred | -1.516 |
ships | -1.480 |
Token | talent |
Token ID | 7401 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Nice | +0.035 |
quiet | +0.033 |
zeb | +0.032 |
isexual | +0.031 |
� | +0.030 |
Neg logit contributions | |
welf | -0.047 |
weap | -0.044 |
scrut | -0.044 |
ingred | -0.043 |
ships | -0.042 |
Token | that |
Token ID | 326 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
Nice | +0.406 |
quiet | +0.381 |
zeb | +0.377 |
isexual | +0.360 |
� | +0.356 |
Neg logit contributions | |
welf | -0.527 |
weap | -0.493 |
scrut | -0.489 |
ingred | -0.478 |
ships | -0.468 |
Token | the |
Token ID | 262 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Nice | +0.350 |
quiet | +0.331 |
zeb | +0.326 |
isexual | +0.314 |
� | +0.312 |
Neg logit contributions | |
welf | -0.425 |
weap | -0.397 |
scrut | -0.394 |
ingred | -0.385 |
ships | -0.378 |
Token | passenger |
Token ID | 11849 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Nice | +0.106 |
quiet | +0.099 |
zeb | +0.097 |
isexual | +0.094 |
� | +0.091 |
Neg logit contributions | |
welf | -0.132 |
weap | -0.123 |
scrut | -0.123 |
ingred | -0.121 |
ships | -0.118 |
Token | planes |
Token ID | 13016 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
welf | +0.401 |
weap | +0.372 |
scrut | +0.371 |
ingred | +0.362 |
ships | +0.353 |
Neg logit contributions | |
Nice | -0.393 |
quiet | -0.375 |
zeb | -0.371 |
isexual | -0.359 |
� | -0.350 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
welf | +0.150 |
weap | +0.140 |
scrut | +0.139 |
ingred | +0.136 |
ships | +0.133 |
Neg logit contributions | |
Nice | -0.126 |
quiet | -0.120 |
zeb | -0.118 |
isexual | -0.114 |
� | -0.111 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
Nice | +0.100 |
quiet | +0.094 |
zeb | +0.093 |
isexual | +0.089 |
� | +0.087 |
Neg logit contributions | |
welf | -0.126 |
scrut | -0.118 |
weap | -0.118 |
ingred | -0.116 |
unden | -0.112 |
Token | An |
Token ID | 2025 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
welf | +0.589 |
weap | +0.546 |
scrut | +0.541 |
ingred | +0.528 |
ships | +0.516 |
Neg logit contributions | |
Nice | -0.595 |
quiet | -0.572 |
zeb | -0.566 |
isexual | -0.550 |
� | -0.537 |
Token | amateur |
Token ID | 18585 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
welf | +0.278 |
weap | +0.260 |
scrut | +0.258 |
ingred | +0.252 |
ships | +0.248 |
Neg logit contributions | |
Nice | -0.219 |
quiet | -0.209 |
zeb | -0.206 |
isexual | -0.200 |
� | -0.194 |
Token | football |
Token ID | 4346 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Nice | +2.955 |
quiet | +2.719 |
zeb | +2.692 |
isexual | +2.606 |
� | +2.538 |
Neg logit contributions | |
welf | -3.577 |
weap | -3.349 |
scrut | -3.304 |
ingred | -3.284 |
ships | -3.273 |
Token | match |
Token ID | 2872 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
welf | +0.474 |
weap | +0.443 |
scrut | +0.439 |
ingred | +0.430 |
ships | +0.423 |
Neg logit contributions | |
Nice | -0.399 |
quiet | -0.380 |
zeb | -0.377 |
isexual | -0.364 |
� | -0.355 |
Token | in |
Token ID | 287 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Nice | +1.337 |
quiet | +1.276 |
zeb | +1.270 |
isexual | +1.220 |
� | +1.197 |
Neg logit contributions | |
welf | -1.490 |
weap | -1.380 |
scrut | -1.357 |
ingred | -1.343 |
unden | -1.307 |
Token | Brazil |
Token ID | 7595 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
Nice | +0.356 |
quiet | +0.332 |
zeb | +0.328 |
isexual | +0.317 |
� | +0.309 |
Neg logit contributions | |
welf | -0.483 |
weap | -0.453 |
scrut | -0.448 |
ingred | -0.441 |
ships | -0.435 |
Token | turned |
Token ID | 2900 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Nice | +0.532 |
quiet | +0.503 |
zeb | +0.499 |
isexual | +0.480 |
� | +0.472 |
Neg logit contributions | |
welf | -0.643 |
weap | -0.599 |
scrut | -0.591 |
ingred | -0.582 |
ships | -0.570 |
Token | acquired |
Token ID | 9477 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Nice | +0.296 |
zeb | +0.278 |
quiet | +0.275 |
isexual | +0.260 |
� | +0.258 |
Neg logit contributions | |
welf | -0.359 |
weap | -0.334 |
scrut | -0.329 |
ingred | -0.327 |
ships | -0.323 |
Token | by |
Token ID | 416 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
welf | +0.548 |
weap | +0.511 |
scrut | +0.507 |
ingred | +0.499 |
ships | +0.491 |
Neg logit contributions | |
Nice | -0.427 |
quiet | -0.405 |
zeb | -0.403 |
isexual | -0.385 |
� | -0.377 |
Token | reading |
Token ID | 3555 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Nice | +0.277 |
zeb | +0.258 |
quiet | +0.257 |
isexual | +0.244 |
� | +0.240 |
Neg logit contributions | |
welf | -0.354 |
weap | -0.331 |
scrut | -0.327 |
ingred | -0.324 |
ships | -0.321 |
Token | from |
Token ID | 422 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Nice | +0.701 |
zeb | +0.655 |
quiet | +0.654 |
isexual | +0.620 |
� | +0.608 |
Neg logit contributions | |
welf | -0.999 |
weap | -0.934 |
scrut | -0.924 |
ingred | -0.914 |
ships | -0.902 |
Token | an |
Token ID | 281 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Nice | +0.310 |
quiet | +0.291 |
zeb | +0.290 |
isexual | +0.277 |
� | +0.272 |
Neg logit contributions | |
welf | -0.394 |
weap | -0.368 |
scrut | -0.365 |
ingred | -0.360 |
ships | -0.354 |
Token | Atomic |
Token ID | 28976 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
Nice | +0.419 |
quiet | +0.395 |
zeb | +0.393 |
isexual | +0.377 |
� | +0.370 |
Neg logit contributions | |
welf | -0.529 |
weap | -0.493 |
scrut | -0.489 |
ingred | -0.480 |
ships | -0.476 |
Token | , |
Token ID | 837 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Nice | +3.052 |
zeb | +2.872 |
quiet | +2.846 |
� | +2.723 |
isexual | +2.722 |
Neg logit contributions | |
welf | -3.465 |
weap | -3.217 |
ingred | -3.189 |
scrut | -3.177 |
ships | -3.105 |
Token | as |
Token ID | 355 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
Nice | +0.479 |
quiet | +0.445 |
zeb | +0.442 |
isexual | +0.421 |
� | +0.413 |
Neg logit contributions | |
welf | -0.654 |
weap | -0.610 |
scrut | -0.605 |
ingred | -0.599 |
ships | -0.589 |
Token | we |
Token ID | 356 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
welf | +0.030 |
weap | +0.028 |
scrut | +0.027 |
ingred | +0.027 |
ships | +0.027 |
Neg logit contributions | |
Nice | -0.027 |
quiet | -0.026 |
zeb | -0.025 |
isexual | -0.024 |
� | -0.024 |
Token | � |
Token ID | 447 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Nice | +0.880 |
quiet | +0.841 |
zeb | +0.827 |
� | +0.798 |
isexual | +0.790 |
Neg logit contributions | |
welf | -1.048 |
weap | -0.981 |
ingred | -0.962 |
scrut | -0.958 |
CLASSIFIED | -0.937 |
Token | � |
Token ID | 247 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Nice | +0.116 |
quiet | +0.111 |
zeb | +0.109 |
� | +0.105 |
isexual | +0.105 |
Neg logit contributions | |
welf | -0.162 |
weap | -0.150 |
scrut | -0.149 |
ingred | -0.145 |
unden | -0.143 |
Token | rather |
Token ID | 34330 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Nice | +0.280 |
quiet | +0.273 |
zeb | +0.268 |
isexual | +0.259 |
� | +0.252 |
Neg logit contributions | |
welf | -0.327 |
weap | -0.306 |
scrut | -0.302 |
ingred | -0.297 |
ships | -0.288 |
Token | - |
Token ID | 12 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
welf | +0.209 |
scrut | +0.193 |
weap | +0.192 |
ingred | +0.191 |
unden | +0.188 |
Neg logit contributions | |
Nice | -0.174 |
quiet | -0.171 |
zeb | -0.166 |
isexual | -0.159 |
� | -0.157 |
Token | than |
Token ID | 14813 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
quiet | +0.374 |
Nice | +0.372 |
zeb | +0.358 |
isexual | +0.347 |
� | +0.338 |
Neg logit contributions | |
welf | -0.501 |
weap | -0.474 |
scrut | -0.464 |
ingred | -0.459 |
unden | -0.448 |
Token | - |
Token ID | 12 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Nice | +0.583 |
quiet | +0.571 |
zeb | +0.550 |
isexual | +0.532 |
� | +0.525 |
Neg logit contributions | |
welf | -0.753 |
weap | -0.697 |
ingred | -0.697 |
scrut | -0.696 |
unden | -0.692 |
Token | bre |
Token ID | 4679 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
quiet | +0.463 |
Nice | +0.455 |
zeb | +0.439 |
isexual | +0.425 |
� | +0.416 |
Neg logit contributions | |
welf | -0.619 |
weap | -0.583 |
scrut | -0.572 |
ingred | -0.567 |
unden | -0.558 |
Token | xit |
Token ID | 10198 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
welf | +0.812 |
weap | +0.747 |
scrut | +0.744 |
ships | +0.724 |
ingred | +0.719 |
Neg logit contributions | |
Nice | -0.928 |
zeb | -0.882 |
quiet | -0.881 |
isexual | -0.858 |
� | -0.831 |
Token | - |
Token ID | 12 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Nice | +2.704 |
quiet | +2.630 |
zeb | +2.544 |
isexual | +2.424 |
� | +2.416 |
Neg logit contributions | |
welf | -4.097 |
unden | -3.828 |
scrut | -3.771 |
ingred | -3.765 |
weap | -3.737 |
Token | is |
Token ID | 271 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Nice | +0.358 |
quiet | +0.348 |
zeb | +0.341 |
isexual | +0.332 |
� | +0.324 |
Neg logit contributions | |
welf | -0.367 |
weap | -0.340 |
scrut | -0.335 |
ingred | -0.328 |
unden | -0.318 |
Token | - |
Token ID | 12 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
Nice | +0.167 |
quiet | +0.163 |
zeb | +0.160 |
isexual | +0.153 |
� | +0.150 |
Neg logit contributions | |
welf | -0.203 |
weap | -0.186 |
scrut | -0.186 |
ingred | -0.185 |
unden | -0.182 |
Token | the |
Token ID | 1169 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Nice | +0.411 |
quiet | +0.400 |
zeb | +0.392 |
isexual | +0.378 |
� | +0.369 |
Neg logit contributions | |
welf | -0.517 |
weap | -0.482 |
scrut | -0.477 |
ingred | -0.469 |
unden | -0.458 |
Token | - |
Token ID | 12 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
Nice | +0.706 |
quiet | +0.683 |
zeb | +0.668 |
isexual | +0.638 |
� | +0.628 |
Neg logit contributions | |
welf | -0.847 |
scrut | -0.783 |
weap | -0.783 |
ingred | -0.771 |
unden | -0.758 |
Token | smell |
Token ID | 8508 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
welf | +0.307 |
weap | +0.284 |
scrut | +0.282 |
ingred | +0.278 |
ships | +0.274 |
Neg logit contributions | |
Nice | -0.240 |
quiet | -0.230 |
zeb | -0.225 |
isexual | -0.217 |
� | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
welf | +0.683 |
weap | +0.638 |
scrut | +0.632 |
ingred | +0.620 |
ships | +0.613 |
Neg logit contributions | |
Nice | -0.529 |
quiet | -0.501 |
zeb | -0.497 |
isexual | -0.476 |
� | -0.465 |
Token | scent |
Token ID | 21212 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
welf | +0.132 |
weap | +0.123 |
scrut | +0.122 |
ingred | +0.119 |
ships | +0.118 |
Neg logit contributions | |
Nice | -0.107 |
quiet | -0.102 |
zeb | -0.101 |
isexual | -0.097 |
� | -0.095 |
Token | of |
Token ID | 286 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
welf | +1.464 |
weap | +1.365 |
scrut | +1.356 |
ingred | +1.323 |
ships | +1.301 |
Neg logit contributions | |
Nice | -1.376 |
quiet | -1.320 |
zeb | -1.305 |
isexual | -1.271 |
� | -1.238 |
Token | burning |
Token ID | 9482 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
welf | +0.210 |
weap | +0.196 |
scrut | +0.194 |
ingred | +0.190 |
ships | +0.188 |
Neg logit contributions | |
Nice | -0.166 |
quiet | -0.158 |
zeb | -0.156 |
isexual | -0.150 |
� | -0.147 |
Token | flesh |
Token ID | 11222 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
Nice | +0.224 |
quiet | +0.211 |
zeb | +0.209 |
isexual | +0.200 |
� | +0.196 |
Neg logit contributions | |
welf | -0.323 |
weap | -0.303 |
scrut | -0.300 |
ingred | -0.294 |
ships | -0.292 |
Token | . |
Token ID | 13 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
Nice | +2.859 |
quiet | +2.728 |
zeb | +2.686 |
� | +2.533 |
isexual | +2.525 |
Neg logit contributions | |
welf | -3.685 |
weap | -3.375 |
scrut | -3.330 |
ingred | -3.284 |
ships | -3.222 |
Token | � |
Token ID | 447 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
welf | +0.070 |
weap | +0.064 |
scrut | +0.064 |
ingred | +0.063 |
unden | +0.061 |
Neg logit contributions | |
Nice | -0.067 |
quiet | -0.063 |
zeb | -0.062 |
isexual | -0.060 |
� | -0.059 |
Token | � |
Token ID | 251 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Nice | +0.380 |
quiet | +0.365 |
zeb | +0.362 |
isexual | +0.352 |
� | +0.344 |
Neg logit contributions | |
welf | -0.347 |
weap | -0.320 |
scrut | -0.317 |
ingred | -0.310 |
ships | -0.305 |
Token |
|
Token ID | 198 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Nice | +0.371 |
quiet | +0.356 |
zeb | +0.353 |
isexual | +0.343 |
� | +0.333 |
Neg logit contributions | |
welf | -0.412 |
weap | -0.384 |
scrut | -0.380 |
ingred | -0.372 |
ships | -0.366 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
welf | +0.031 |
weap | +0.029 |
scrut | +0.029 |
ingred | +0.029 |
unden | +0.028 |
Neg logit contributions | |
Nice | -0.024 |
quiet | -0.022 |
zeb | -0.022 |
isexual | -0.021 |
� | -0.021 |
Token | Audio |
Token ID | 13491 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
welf | +0.510 |
weap | +0.477 |
scrut | +0.473 |
ingred | +0.464 |
ships | +0.457 |
Neg logit contributions | |
Nice | -0.397 |
quiet | -0.379 |
zeb | -0.374 |
isexual | -0.362 |
� | -0.352 |
Token | To |
Token ID | 1675 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
welf | +1.060 |
weap | +0.987 |
scrut | +0.977 |
ingred | +0.957 |
ships | +0.942 |
Neg logit contributions | |
Nice | -0.948 |
quiet | -0.910 |
zeb | -0.901 |
isexual | -0.872 |
� | -0.851 |
Token | O |
Token ID | 440 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
Nice | +0.088 |
quiet | +0.084 |
zeb | +0.083 |
isexual | +0.081 |
� | +0.078 |
Neg logit contributions | |
welf | -0.111 |
weap | -0.104 |
scrut | -0.103 |
ingred | -0.101 |
ships | -0.099 |
Token | & |
Token ID | 5 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
welf | +0.521 |
weap | +0.486 |
scrut | +0.482 |
ingred | +0.472 |
ships | +0.465 |
Neg logit contributions | |
Nice | -0.436 |
quiet | -0.418 |
zeb | -0.413 |
isexual | -0.399 |
� | -0.389 |
Token | A |
Token ID | 32 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
Nice | +1.123 |
quiet | +1.048 |
zeb | +1.042 |
isexual | +1.002 |
� | +0.991 |
Neg logit contributions | |
welf | -1.337 |
ingred | -1.237 |
weap | -1.237 |
scrut | -1.237 |
unden | -1.204 |
Token | Bits |
Token ID | 44733 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
welf | +0.395 |
weap | +0.368 |
scrut | +0.364 |
ingred | +0.356 |
ships | +0.351 |
Neg logit contributions | |
Nice | -0.368 |
quiet | -0.354 |
zeb | -0.351 |
isexual | -0.340 |
� | -0.332 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Nice | +3.033 |
quiet | +2.861 |
zeb | +2.857 |
isexual | +2.738 |
� | +2.659 |
Neg logit contributions | |
welf | -3.511 |
weap | -3.277 |
scrut | -3.255 |
ingred | -3.170 |
ships | -3.107 |
Token | 01 |
Token ID | 486 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
welf | +0.575 |
weap | +0.507 |
scrut | +0.502 |
ingred | +0.482 |
ships | +0.462 |
Neg logit contributions | |
Nice | -1.271 |
quiet | -1.230 |
zeb | -1.221 |
isexual | -1.195 |
� | -1.178 |
Token | 11 |
Token ID | 1157 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Nice | +0.160 |
quiet | +0.155 |
zeb | +0.155 |
isexual | +0.151 |
� | +0.148 |
Neg logit contributions | |
welf | -0.090 |
weap | -0.081 |
scrut | -0.080 |
ingred | -0.077 |
ships | -0.076 |
Token | O |
Token ID | 440 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
welf | +0.852 |
weap | +0.786 |
scrut | +0.781 |
ingred | +0.770 |
unden | +0.748 |
Neg logit contributions | |
Nice | -0.813 |
quiet | -0.766 |
zeb | -0.755 |
isexual | -0.733 |
� | -0.715 |
Token | & |
Token ID | 5 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
welf | +0.910 |
weap | +0.848 |
scrut | +0.844 |
ingred | +0.831 |
unden | +0.813 |
Neg logit contributions | |
Nice | -0.694 |
quiet | -0.660 |
zeb | -0.653 |
isexual | -0.631 |
� | -0.614 |
Token | Neil |
Token ID | 29354 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
welf | +0.249 |
weap | +0.230 |
scrut | +0.228 |
ingred | +0.223 |
unden | +0.216 |
Neg logit contributions | |
Nice | -0.245 |
quiet | -0.236 |
zeb | -0.233 |
isexual | -0.225 |
� | -0.221 |
Token | Thomson |
Token ID | 32425 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Nice | +0.070 |
quiet | +0.066 |
zeb | +0.066 |
isexual | +0.063 |
� | +0.061 |
Neg logit contributions | |
welf | -0.095 |
weap | -0.089 |
scrut | -0.088 |
ingred | -0.087 |
ships | -0.085 |
Token | - |
Token ID | 532 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
Nice | +1.091 |
quiet | +1.031 |
zeb | +1.023 |
isexual | +0.980 |
� | +0.959 |
Neg logit contributions | |
welf | -1.386 |
weap | -1.289 |
scrut | -1.279 |
ingred | -1.255 |
ships | -1.225 |
Token | A |
Token ID | 317 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Nice | +0.638 |
quiet | +0.602 |
zeb | +0.596 |
isexual | +0.575 |
� | +0.560 |
Neg logit contributions | |
welf | -0.796 |
weap | -0.741 |
scrut | -0.736 |
ingred | -0.723 |
ships | -0.708 |
Token | Det |
Token ID | 4614 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
welf | +1.094 |
weap | +1.026 |
scrut | +1.017 |
ingred | +0.994 |
ships | +0.982 |
Neg logit contributions | |
Nice | -0.834 |
quiet | -0.799 |
zeb | -0.790 |
isexual | -0.765 |
� | -0.743 |
Token | ailed |
Token ID | 6255 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
Nice | +0.892 |
quiet | +0.860 |
zeb | +0.846 |
isexual | +0.825 |
� | +0.803 |
Neg logit contributions | |
welf | -0.942 |
weap | -0.874 |
scrut | -0.865 |
ingred | -0.847 |
ships | -0.826 |
Token | Review |
Token ID | 6602 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
welf | +3.122 |
weap | +2.927 |
scrut | +2.900 |
ingred | +2.803 |
ships | +2.782 |
Neg logit contributions | |
Nice | -2.748 |
quiet | -2.698 |
zeb | -2.678 |
isexual | -2.597 |
� | -2.502 |
Token |
|
Token ID | 198 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
welf | +0.385 |
weap | +0.359 |
scrut | +0.356 |
ingred | +0.348 |
ships | +0.342 |
Neg logit contributions | |
Nice | -0.350 |
quiet | -0.334 |
zeb | -0.331 |
isexual | -0.321 |
� | -0.313 |
Token |
|
Token ID | 198 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
welf | +0.696 |
weap | +0.645 |
scrut | +0.643 |
ingred | +0.636 |
unden | +0.622 |
Neg logit contributions | |
Nice | -0.558 |
quiet | -0.530 |
zeb | -0.524 |
isexual | -0.503 |
� | -0.493 |
Token | http |
Token ID | 4023 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
welf | +0.504 |
weap | +0.464 |
scrut | +0.460 |
ingred | +0.449 |
ships | +0.437 |
Neg logit contributions | |
Nice | -0.553 |
quiet | -0.533 |
zeb | -0.528 |
isexual | -0.511 |
� | -0.501 |
Token | :// |
Token ID | 1378 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Nice | +0.024 |
quiet | +0.023 |
zeb | +0.023 |
isexual | +0.022 |
� | +0.022 |
Neg logit contributions | |
welf | -0.019 |
scrut | -0.017 |
weap | -0.017 |
ingred | -0.017 |
unden | -0.017 |
Token | over |
Token ID | 625 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
welf | +0.504 |
weap | +0.469 |
scrut | +0.463 |
ingred | +0.458 |
ships | +0.445 |
Neg logit contributions | |
Nice | -0.451 |
quiet | -0.429 |
zeb | -0.423 |
isexual | -0.405 |
� | -0.399 |
Token | — |
Token ID | 851 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
welf | +0.497 |
weap | +0.465 |
scrut | +0.460 |
ingred | +0.454 |
ships | +0.444 |
Neg logit contributions | |
Nice | -0.351 |
quiet | -0.332 |
zeb | -0.328 |
isexual | -0.312 |
� | -0.305 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
Nice | +0.308 |
quiet | +0.291 |
zeb | +0.287 |
isexual | +0.275 |
� | +0.269 |
Neg logit contributions | |
welf | -0.367 |
weap | -0.339 |
scrut | -0.338 |
ingred | -0.336 |
unden | -0.323 |
Token | authority |
Token ID | 4934 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
welf | +0.269 |
weap | +0.249 |
scrut | +0.246 |
ingred | +0.243 |
ships | +0.236 |
Neg logit contributions | |
Nice | -0.258 |
quiet | -0.244 |
zeb | -0.241 |
isexual | -0.232 |
� | -0.227 |
Token | is |
Token ID | 318 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
welf | +0.559 |
weap | +0.519 |
scrut | +0.512 |
ingred | +0.504 |
ships | +0.493 |
Neg logit contributions | |
Nice | -0.533 |
quiet | -0.510 |
zeb | -0.505 |
isexual | -0.487 |
� | -0.478 |
Token | owed |
Token ID | 21057 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
welf | +0.658 |
weap | +0.619 |
scrut | +0.615 |
ingred | +0.604 |
ships | +0.595 |
Neg logit contributions | |
Nice | -0.404 |
quiet | -0.382 |
zeb | -0.377 |
isexual | -0.362 |
� | -0.350 |
Token | more |
Token ID | 517 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
welf | +2.971 |
weap | +2.744 |
scrut | +2.718 |
ingred | +2.647 |
ships | +2.603 |
Neg logit contributions | |
Nice | -3.288 |
quiet | -3.161 |
zeb | -3.134 |
isexual | -3.048 |
� | -2.976 |
Token | than |
Token ID | 621 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
welf | +0.064 |
weap | +0.059 |
scrut | +0.059 |
ingred | +0.058 |
ships | +0.057 |
Neg logit contributions | |
Nice | -0.048 |
quiet | -0.045 |
zeb | -0.045 |
isexual | -0.042 |
� | -0.042 |
Token | $ |
Token ID | 720 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Nice | +1.109 |
quiet | +1.048 |
zeb | +1.037 |
isexual | +1.004 |
� | +0.996 |
Neg logit contributions | |
welf | -0.670 |
weap | -0.602 |
scrut | -0.593 |
ingred | -0.586 |
CLASSIFIED | -0.566 |
Token | 251 |
Token ID | 28072 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Nice | +0.237 |
quiet | +0.228 |
zeb | +0.225 |
isexual | +0.218 |
� | +0.215 |
Neg logit contributions | |
welf | -0.210 |
scrut | -0.192 |
weap | -0.192 |
ingred | -0.189 |
unden | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Nice | +0.095 |
quiet | +0.091 |
zeb | +0.090 |
isexual | +0.087 |
� | +0.084 |
Neg logit contributions | |
welf | -0.118 |
weap | -0.111 |
scrut | -0.110 |
ingred | -0.107 |
ships | -0.106 |
Token | national |
Token ID | 2260 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
welf | +0.307 |
weap | +0.289 |
scrut | +0.285 |
ingred | +0.281 |
ships | +0.275 |
Neg logit contributions | |
Nice | -0.246 |
quiet | -0.233 |
zeb | -0.228 |
isexual | -0.220 |
� | -0.216 |
Token | cultures |
Token ID | 13817 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Nice | +1.179 |
quiet | +1.113 |
zeb | +1.098 |
isexual | +1.068 |
� | +1.043 |
Neg logit contributions | |
welf | -1.212 |
weap | -1.137 |
scrut | -1.124 |
ingred | -1.107 |
ships | -1.072 |
Token | within |
Token ID | 1626 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
welf | +1.081 |
weap | +1.008 |
scrut | +0.999 |
ingred | +0.978 |
ships | +0.963 |
Neg logit contributions | |
Nice | -0.918 |
quiet | -0.876 |
zeb | -0.867 |
isexual | -0.839 |
� | -0.818 |
Token | the |
Token ID | 262 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
welf | +0.122 |
weap | +0.115 |
scrut | +0.114 |
ingred | +0.112 |
ships | +0.110 |
Neg logit contributions | |
Nice | -0.092 |
quiet | -0.088 |
zeb | -0.086 |
isexual | -0.084 |
� | -0.082 |
Token | British |
Token ID | 3517 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Nice | +0.035 |
quiet | +0.033 |
zeb | +0.033 |
isexual | +0.032 |
� | +0.031 |
Neg logit contributions | |
welf | -0.051 |
weap | -0.048 |
scrut | -0.047 |
ingred | -0.046 |
ships | -0.046 |
Token | Isles |
Token ID | 36217 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
Nice | +0.370 |
quiet | +0.352 |
zeb | +0.347 |
isexual | +0.338 |
� | +0.331 |
Neg logit contributions | |
welf | -0.365 |
weap | -0.343 |
scrut | -0.338 |
ingred | -0.334 |
ships | -0.323 |
Token | can |
Token ID | 460 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
welf | +2.934 |
weap | +2.733 |
scrut | +2.719 |
ingred | +2.638 |
ships | +2.625 |
Neg logit contributions | |
Nice | -2.527 |
quiet | -2.412 |
zeb | -2.396 |
isexual | -2.321 |
� | -2.244 |
Token | claim |
Token ID | 1624 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
welf | +0.310 |
weap | +0.288 |
scrut | +0.285 |
ingred | +0.280 |
ships | +0.274 |
Neg logit contributions | |
Nice | -0.292 |
quiet | -0.281 |
zeb | -0.277 |
isexual | -0.269 |
� | -0.263 |
Token | to |
Token ID | 284 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
welf | +0.149 |
weap | +0.140 |
scrut | +0.139 |
ingred | +0.137 |
ships | +0.134 |
Neg logit contributions | |
Nice | -0.115 |
quiet | -0.108 |
zeb | -0.107 |
isexual | -0.103 |
� | -0.102 |
Token | be |
Token ID | 307 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
welf | +0.450 |
weap | +0.419 |
scrut | +0.415 |
ingred | +0.407 |
ships | +0.399 |
Neg logit contributions | |
Nice | -0.449 |
quiet | -0.429 |
zeb | -0.424 |
isexual | -0.413 |
� | -0.405 |
Token | literary |
Token ID | 16716 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
welf | +0.896 |
weap | +0.838 |
scrut | +0.831 |
ingred | +0.814 |
ships | +0.801 |
Neg logit contributions | |
Nice | -0.702 |
quiet | -0.669 |
zeb | -0.662 |
isexual | -0.639 |
� | -0.622 |
Token | Natural |
Token ID | 12068 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Nice | +0.051 |
quiet | +0.048 |
zeb | +0.047 |
isexual | +0.046 |
� | +0.044 |
Neg logit contributions | |
welf | -0.071 |
weap | -0.067 |
scrut | -0.066 |
ingred | -0.065 |
ships | -0.064 |
Token | Markets |
Token ID | 30251 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Nice | +1.028 |
quiet | +0.986 |
zeb | +0.978 |
isexual | +0.950 |
� | +0.928 |
Neg logit contributions | |
welf | -0.970 |
weap | -0.897 |
scrut | -0.889 |
ingred | -0.867 |
ships | -0.852 |
Token | will |
Token ID | 481 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
welf | +0.141 |
weap | +0.132 |
scrut | +0.130 |
ingred | +0.128 |
ships | +0.126 |
Neg logit contributions | |
Nice | -0.117 |
quiet | -0.111 |
zeb | -0.109 |
isexual | -0.106 |
� | -0.103 |
Token | open |
Token ID | 1280 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
welf | +0.843 |
weap | +0.788 |
scrut | +0.783 |
ingred | +0.766 |
ships | +0.756 |
Neg logit contributions | |
Nice | -0.596 |
quiet | -0.565 |
zeb | -0.556 |
isexual | -0.538 |
� | -0.522 |
Token | new |
Token ID | 649 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
welf | +0.540 |
weap | +0.499 |
scrut | +0.494 |
ingred | +0.483 |
ships | +0.474 |
Neg logit contributions | |
Nice | -0.554 |
quiet | -0.530 |
zeb | -0.524 |
isexual | -0.509 |
� | -0.497 |
Token | store |
Token ID | 3650 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
welf | +1.413 |
weap | +1.286 |
scrut | +1.271 |
ingred | +1.234 |
ships | +1.202 |
Neg logit contributions | |
Nice | -2.117 |
quiet | -2.056 |
zeb | -2.048 |
isexual | -1.997 |
� | -1.955 |
Token | at |
Token ID | 379 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
welf | +2.239 |
weap | +2.071 |
scrut | +2.049 |
ingred | +2.013 |
ships | +1.959 |
Neg logit contributions | |
Nice | -2.988 |
quiet | -2.907 |
zeb | -2.903 |
isexual | -2.831 |
� | -2.765 |
Token | Five |
Token ID | 10579 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
welf | +1.271 |
weap | +1.186 |
scrut | +1.179 |
ingred | +1.151 |
ships | +1.136 |
Neg logit contributions | |
Nice | -1.008 |
quiet | -0.973 |
zeb | -0.966 |
isexual | -0.930 |
� | -0.905 |
Token | Corn |
Token ID | 11424 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
welf | +0.242 |
weap | +0.220 |
scrut | +0.220 |
ingred | +0.217 |
unden | +0.209 |
Neg logit contributions | |
Nice | -0.308 |
quiet | -0.287 |
zeb | -0.285 |
isexual | -0.276 |
� | -0.272 |
Token | ers |
Token ID | 364 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
welf | +0.726 |
weap | +0.673 |
scrut | +0.669 |
ingred | +0.653 |
ships | +0.635 |
Neg logit contributions | |
Nice | -0.688 |
quiet | -0.658 |
zeb | -0.652 |
isexual | -0.631 |
� | -0.617 |
Token | in |
Token ID | 287 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
welf | +1.472 |
weap | +1.398 |
scrut | +1.375 |
ingred | +1.372 |
ships | +1.344 |
Neg logit contributions | |
Nice | -1.019 |
zeb | -0.980 |
quiet | -0.979 |
isexual | -0.949 |
� | -0.924 |
Token | Canadian |
Token ID | 5398 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
welf | +0.159 |
weap | +0.152 |
scrut | +0.149 |
ingred | +0.147 |
ships | +0.145 |
Neg logit contributions | |
Nice | -0.090 |
quiet | -0.083 |
zeb | -0.081 |
isexual | -0.078 |
� | -0.076 |
Token | public |
Token ID | 1171 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
welf | +0.950 |
weap | +0.896 |
scrut | +0.880 |
ingred | +0.868 |
ships | +0.858 |
Neg logit contributions | |
Nice | -0.713 |
quiet | -0.674 |
zeb | -0.659 |
isexual | -0.643 |
� | -0.626 |
Token | identify |
Token ID | 5911 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
welf | +0.441 |
weap | +0.413 |
scrut | +0.406 |
ingred | +0.402 |
ships | +0.391 |
Neg logit contributions | |
Nice | -0.386 |
quiet | -0.370 |
zeb | -0.364 |
isexual | -0.352 |
� | -0.344 |
Token | with |
Token ID | 351 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
welf | +1.053 |
weap | +0.990 |
scrut | +0.982 |
ingred | +0.964 |
ships | +0.950 |
Neg logit contributions | |
Nice | -0.707 |
quiet | -0.669 |
zeb | -0.661 |
isexual | -0.637 |
� | -0.618 |
Token | enough |
Token ID | 1576 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
welf | +0.611 |
weap | +0.581 |
scrut | +0.572 |
ingred | +0.566 |
ships | +0.551 |
Neg logit contributions | |
Nice | -0.459 |
quiet | -0.428 |
zeb | -0.422 |
isexual | -0.410 |
� | -0.401 |
Token | faces |
Token ID | 6698 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
welf | +0.834 |
weap | +0.791 |
scrut | +0.776 |
ingred | +0.764 |
ships | +0.746 |
Neg logit contributions | |
Nice | -0.709 |
quiet | -0.669 |
zeb | -0.660 |
isexual | -0.646 |
� | -0.630 |
Token | around |
Token ID | 1088 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
welf | +3.564 |
scrut | +3.341 |
weap | +3.341 |
ingred | +3.243 |
ships | +3.235 |
Neg logit contributions | |
Nice | -2.468 |
zeb | -2.360 |
quiet | -2.357 |
isexual | -2.256 |
� | -2.164 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Nice | +0.778 |
quiet | +0.727 |
zeb | +0.720 |
isexual | +0.692 |
� | +0.677 |
Neg logit contributions | |
welf | -1.112 |
weap | -1.046 |
scrut | -1.034 |
ingred | -1.015 |
ships | -0.997 |
Token | table |
Token ID | 3084 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
welf | +0.135 |
weap | +0.128 |
scrut | +0.126 |
ingred | +0.124 |
ships | +0.123 |
Neg logit contributions | |
Nice | -0.069 |
quiet | -0.064 |
zeb | -0.063 |
isexual | -0.060 |
� | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Nice | +0.438 |
quiet | +0.415 |
zeb | +0.405 |
isexual | +0.392 |
� | +0.383 |
Neg logit contributions | |
welf | -0.708 |
weap | -0.667 |
scrut | -0.658 |
ingred | -0.651 |
ships | -0.635 |
Token | If |
Token ID | 1002 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
welf | +0.158 |
weap | +0.148 |
scrut | +0.147 |
ingred | +0.146 |
unden | +0.141 |
Neg logit contributions | |
Nice | -0.129 |
quiet | -0.120 |
zeb | -0.119 |
isexual | -0.114 |
� | -0.114 |
Token | office |
Token ID | 2607 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Nice | +1.380 |
quiet | +1.275 |
zeb | +1.261 |
isexual | +1.198 |
� | +1.143 |
Neg logit contributions | |
welf | -2.607 |
scrut | -2.466 |
weap | -2.451 |
ingred | -2.404 |
ships | -2.384 |
Token | secretary |
Token ID | 7705 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
welf | +0.317 |
weap | +0.295 |
scrut | +0.292 |
ingred | +0.285 |
ships | +0.282 |
Neg logit contributions | |
Nice | -0.297 |
quiet | -0.284 |
zeb | -0.280 |
isexual | -0.271 |
� | -0.264 |
Token | who |
Token ID | 508 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
Nice | +0.025 |
quiet | +0.024 |
zeb | +0.024 |
isexual | +0.023 |
� | +0.022 |
Neg logit contributions | |
welf | -0.029 |
weap | -0.027 |
scrut | -0.027 |
ingred | -0.026 |
ships | -0.026 |
Token | steals |
Token ID | 28052 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Nice | +0.475 |
quiet | +0.456 |
zeb | +0.449 |
isexual | +0.435 |
� | +0.425 |
Neg logit contributions | |
welf | -0.506 |
weap | -0.469 |
scrut | -0.465 |
ingred | -0.456 |
ships | -0.445 |
Token | $ |
Token ID | 720 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
welf | +1.696 |
weap | +1.582 |
scrut | +1.567 |
ingred | +1.534 |
ships | +1.510 |
Neg logit contributions | |
Nice | -1.439 |
quiet | -1.375 |
zeb | -1.362 |
isexual | -1.318 |
� | -1.284 |
Token | 40 |
Token ID | 1821 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Nice | +0.682 |
quiet | +0.660 |
zeb | +0.650 |
isexual | +0.627 |
� | +0.619 |
Neg logit contributions | |
welf | -0.617 |
scrut | -0.567 |
weap | -0.567 |
ingred | -0.557 |
unden | -0.545 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
welf | +0.487 |
weap | +0.455 |
scrut | +0.453 |
ingred | +0.443 |
ships | +0.436 |
Neg logit contributions | |
Nice | -0.366 |
quiet | -0.348 |
zeb | -0.344 |
isexual | -0.331 |
� | -0.323 |
Token | 000 |
Token ID | 830 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
welf | +0.011 |
weap | +0.010 |
scrut | +0.010 |
ingred | +0.010 |
ships | +0.010 |
Neg logit contributions | |
Nice | -0.014 |
quiet | -0.014 |
zeb | -0.014 |
isexual | -0.013 |
� | -0.013 |
Token | from |
Token ID | 422 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
Nice | +0.069 |
quiet | +0.065 |
zeb | +0.064 |
isexual | +0.061 |
� | +0.060 |
Neg logit contributions | |
welf | -0.106 |
weap | -0.100 |
scrut | -0.099 |
ingred | -0.097 |
ships | -0.095 |
Token | her |
Token ID | 607 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
welf | +0.004 |
weap | +0.004 |
scrut | +0.004 |
ingred | +0.004 |
ships | +0.004 |
Neg logit contributions | |
Nice | -0.003 |
quiet | -0.003 |
zeb | -0.003 |
isexual | -0.003 |
� | -0.003 |
Token | boss |
Token ID | 6478 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
welf | +0.669 |
weap | +0.627 |
scrut | +0.623 |
ingred | +0.610 |
ships | +0.602 |
Neg logit contributions | |
Nice | -0.479 |
quiet | -0.454 |
zeb | -0.448 |
isexual | -0.432 |
� | -0.420 |
Token | registration |
Token ID | 9352 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
welf | +0.460 |
weap | +0.430 |
scrut | +0.426 |
ingred | +0.419 |
ships | +0.413 |
Neg logit contributions | |
Nice | -0.391 |
quiet | -0.367 |
zeb | -0.363 |
isexual | -0.353 |
� | -0.345 |
Token | will |
Token ID | 481 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
welf | +1.500 |
weap | +1.390 |
scrut | +1.381 |
ingred | +1.346 |
ships | +1.325 |
Neg logit contributions | |
Nice | -1.466 |
quiet | -1.409 |
zeb | -1.397 |
isexual | -1.354 |
� | -1.318 |
Token | expire |
Token ID | 24264 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
welf | +0.558 |
weap | +0.514 |
scrut | +0.509 |
ingred | +0.498 |
ships | +0.488 |
Neg logit contributions | |
Nice | -0.590 |
quiet | -0.568 |
zeb | -0.561 |
isexual | -0.547 |
� | -0.534 |
Token | , |
Token ID | 11 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
Nice | +0.229 |
quiet | +0.216 |
zeb | +0.212 |
isexual | +0.205 |
� | +0.202 |
Neg logit contributions | |
welf | -0.313 |
weap | -0.292 |
scrut | -0.289 |
ingred | -0.287 |
ships | -0.281 |
Token | and |
Token ID | 290 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
welf | +0.600 |
weap | +0.561 |
scrut | +0.554 |
ingred | +0.545 |
ships | +0.538 |
Neg logit contributions | |
Nice | -0.474 |
quiet | -0.451 |
zeb | -0.445 |
isexual | -0.429 |
� | -0.422 |
Token | the |
Token ID | 262 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
welf | +0.357 |
weap | +0.335 |
scrut | +0.329 |
ingred | +0.323 |
ships | +0.321 |
Neg logit contributions | |
Nice | -0.300 |
quiet | -0.285 |
zeb | -0.281 |
isexual | -0.270 |
� | -0.267 |
Token | date |
Token ID | 3128 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
welf | +0.650 |
weap | +0.607 |
scrut | +0.602 |
ingred | +0.590 |
ships | +0.583 |
Neg logit contributions | |
Nice | -0.533 |
quiet | -0.505 |
zeb | -0.500 |
isexual | -0.483 |
� | -0.472 |
Token | of |
Token ID | 286 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
welf | +0.866 |
weap | +0.808 |
scrut | +0.801 |
ingred | +0.784 |
ships | +0.772 |
Neg logit contributions | |
Nice | -0.742 |
quiet | -0.708 |
zeb | -0.701 |
isexual | -0.678 |
� | -0.662 |
Token | that |
Token ID | 326 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
welf | +0.771 |
weap | +0.719 |
scrut | +0.714 |
ingred | +0.698 |
ships | +0.686 |
Neg logit contributions | |
Nice | -0.634 |
quiet | -0.606 |
zeb | -0.600 |
isexual | -0.581 |
� | -0.564 |
Token | exp |
Token ID | 1033 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
welf | +0.231 |
weap | +0.214 |
scrut | +0.212 |
ingred | +0.207 |
ships | +0.205 |
Neg logit contributions | |
Nice | -0.215 |
quiet | -0.206 |
zeb | -0.204 |
isexual | -0.198 |
� | -0.194 |
Token | iry |
Token ID | 9045 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
welf | +0.336 |
weap | +0.318 |
scrut | +0.316 |
ingred | +0.312 |
ships | +0.306 |
Neg logit contributions | |
Nice | -0.130 |
quiet | -0.122 |
zeb | -0.119 |
isexual | -0.113 |
� | -0.109 |
Token | give |
Token ID | 1577 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
welf | +0.496 |
weap | +0.463 |
scrut | +0.457 |
ingred | +0.450 |
ships | +0.442 |
Neg logit contributions | |
Nice | -0.446 |
quiet | -0.421 |
zeb | -0.416 |
isexual | -0.401 |
� | -0.390 |
Token | back |
Token ID | 736 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Nice | +0.136 |
quiet | +0.127 |
zeb | +0.125 |
isexual | +0.119 |
� | +0.116 |
Neg logit contributions | |
welf | -0.193 |
weap | -0.180 |
scrut | -0.179 |
ingred | -0.175 |
ships | -0.172 |
Token | to |
Token ID | 284 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
welf | +0.172 |
weap | +0.161 |
scrut | +0.160 |
ingred | +0.157 |
ships | +0.154 |
Neg logit contributions | |
Nice | -0.113 |
quiet | -0.106 |
zeb | -0.104 |
isexual | -0.100 |
� | -0.097 |
Token | them |
Token ID | 606 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
welf | +0.375 |
weap | +0.352 |
scrut | +0.350 |
ingred | +0.342 |
ships | +0.337 |
Neg logit contributions | |
Nice | -0.269 |
quiet | -0.253 |
zeb | -0.250 |
isexual | -0.240 |
� | -0.233 |
Token | and |
Token ID | 290 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
welf | +1.498 |
weap | +1.397 |
scrut | +1.387 |
ingred | +1.358 |
ships | +1.335 |
Neg logit contributions | |
Nice | -1.228 |
quiet | -1.167 |
zeb | -1.155 |
isexual | -1.117 |
� | -1.087 |
Token | use |
Token ID | 779 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
welf | +0.200 |
weap | +0.188 |
scrut | +0.186 |
ingred | +0.183 |
ships | +0.179 |
Neg logit contributions | |
Nice | -0.156 |
quiet | -0.147 |
zeb | -0.145 |
isexual | -0.140 |
� | -0.136 |
Token | that |
Token ID | 326 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
welf | +0.983 |
weap | +0.920 |
scrut | +0.913 |
ingred | +0.893 |
ships | +0.880 |
Neg logit contributions | |
Nice | -0.737 |
quiet | -0.693 |
zeb | -0.688 |
isexual | -0.661 |
� | -0.644 |
Token | to |
Token ID | 284 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
welf | +0.096 |
weap | +0.089 |
scrut | +0.088 |
ingred | +0.086 |
ships | +0.085 |
Neg logit contributions | |
Nice | -0.087 |
quiet | -0.082 |
zeb | -0.082 |
isexual | -0.078 |
� | -0.077 |
Token | improve |
Token ID | 2987 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
welf | +0.250 |
weap | +0.232 |
scrut | +0.231 |
ingred | +0.226 |
ships | +0.222 |
Neg logit contributions | |
Nice | -0.209 |
quiet | -0.196 |
zeb | -0.194 |
isexual | -0.187 |
� | -0.182 |
Token | their |
Token ID | 511 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
welf | +0.013 |
weap | +0.012 |
scrut | +0.012 |
ingred | +0.011 |
ships | +0.011 |
Neg logit contributions | |
Nice | -0.009 |
quiet | -0.009 |
zeb | -0.009 |
isexual | -0.008 |
� | -0.008 |
Token | experience |
Token ID | 1998 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
welf | +0.313 |
weap | +0.294 |
scrut | +0.291 |
ingred | +0.285 |
ships | +0.278 |
Neg logit contributions | |
Nice | -0.270 |
quiet | -0.253 |
zeb | -0.248 |
isexual | -0.238 |
� | -0.236 |
Token | not |
Token ID | 407 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Nice | +1.318 |
quiet | +1.229 |
zeb | +1.209 |
isexual | +1.152 |
� | +1.144 |
Neg logit contributions | |
welf | -1.665 |
weap | -1.553 |
scrut | -1.527 |
ingred | -1.513 |
ships | -1.492 |
Token | impossible |
Token ID | 5340 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Nice | +0.265 |
quiet | +0.249 |
zeb | +0.246 |
isexual | +0.235 |
� | +0.231 |
Neg logit contributions | |
welf | -0.342 |
weap | -0.321 |
scrut | -0.315 |
ingred | -0.311 |
ships | -0.307 |
Token | that |
Token ID | 326 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
welf | +1.132 |
weap | +1.061 |
scrut | +1.052 |
ingred | +1.033 |
ships | +1.015 |
Neg logit contributions | |
Nice | -0.897 |
quiet | -0.861 |
zeb | -0.850 |
isexual | -0.825 |
� | -0.796 |
Token | this |
Token ID | 428 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
welf | +0.111 |
weap | +0.103 |
scrut | +0.103 |
ingred | +0.101 |
ships | +0.100 |
Neg logit contributions | |
Nice | -0.077 |
quiet | -0.072 |
zeb | -0.071 |
isexual | -0.068 |
� | -0.066 |
Token | could |
Token ID | 714 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Nice | +0.087 |
quiet | +0.083 |
zeb | +0.082 |
isexual | +0.079 |
� | +0.077 |
Neg logit contributions | |
welf | -0.107 |
weap | -0.100 |
scrut | -0.099 |
ingred | -0.097 |
ships | -0.096 |
Token | happen |
Token ID | 1645 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
Nice | +0.681 |
quiet | +0.651 |
zeb | +0.638 |
isexual | +0.618 |
� | +0.607 |
Neg logit contributions | |
welf | -0.867 |
weap | -0.805 |
scrut | -0.798 |
ingred | -0.781 |
ships | -0.770 |
Token | again |
Token ID | 757 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
welf | +0.470 |
weap | +0.437 |
scrut | +0.433 |
ingred | +0.423 |
ships | +0.416 |
Neg logit contributions | |
Nice | -0.434 |
quiet | -0.415 |
zeb | -0.411 |
isexual | -0.399 |
� | -0.389 |
Token | . |
Token ID | 13 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Nice | +1.349 |
quiet | +1.284 |
zeb | +1.266 |
isexual | +1.222 |
� | +1.210 |
Neg logit contributions | |
welf | -1.478 |
weap | -1.360 |
scrut | -1.351 |
ingred | -1.325 |
ships | -1.290 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
welf | +0.325 |
weap | +0.302 |
scrut | +0.300 |
ingred | +0.296 |
ships | +0.288 |
Neg logit contributions | |
Nice | -0.273 |
quiet | -0.256 |
zeb | -0.255 |
isexual | -0.245 |
� | -0.240 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
Nice | +0.078 |
quiet | +0.074 |
zeb | +0.073 |
isexual | +0.070 |
� | +0.069 |
Neg logit contributions | |
welf | -0.104 |
weap | -0.096 |
scrut | -0.096 |
ingred | -0.096 |
unden | -0.094 |
Token | If |
Token ID | 1532 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Nice | +0.001 |
quiet | +0.001 |
zeb | +0.001 |
isexual | +0.001 |
� | +0.001 |
Neg logit contributions | |
welf | -0.001 |
weap | -0.001 |
scrut | -0.001 |
ingred | -0.001 |
unden | -0.001 |
Token | price |
Token ID | 2756 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
welf | +0.059 |
weap | +0.054 |
scrut | +0.053 |
ingred | +0.053 |
ships | +0.052 |
Neg logit contributions | |
Nice | -0.062 |
quiet | -0.058 |
zeb | -0.058 |
isexual | -0.055 |
� | -0.055 |
Token | they |
Token ID | 484 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
welf | +0.299 |
weap | +0.279 |
scrut | +0.276 |
ingred | +0.271 |
ships | +0.266 |
Neg logit contributions | |
Nice | -0.255 |
quiet | -0.242 |
zeb | -0.240 |
isexual | -0.231 |
� | -0.227 |
Token | will |
Token ID | 481 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
welf | +0.498 |
weap | +0.463 |
scrut | +0.458 |
ingred | +0.453 |
ships | +0.442 |
Neg logit contributions | |
Nice | -0.452 |
quiet | -0.431 |
zeb | -0.427 |
isexual | -0.411 |
� | -0.405 |
Token | want |
Token ID | 765 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
welf | +0.605 |
weap | +0.557 |
scrut | +0.554 |
ingred | +0.543 |
ships | +0.533 |
Neg logit contributions | |
Nice | -0.625 |
quiet | -0.595 |
zeb | -0.589 |
isexual | -0.572 |
� | -0.563 |
Token | , |
Token ID | 11 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
Nice | +0.141 |
quiet | +0.133 |
zeb | +0.132 |
isexual | +0.126 |
� | +0.124 |
Neg logit contributions | |
welf | -0.194 |
weap | -0.182 |
scrut | -0.181 |
ingred | -0.177 |
ships | -0.174 |
Token | so |
Token ID | 523 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
welf | +0.623 |
weap | +0.582 |
scrut | +0.577 |
ingred | +0.570 |
ships | +0.558 |
Neg logit contributions | |
Nice | -0.494 |
quiet | -0.467 |
zeb | -0.459 |
isexual | -0.442 |
� | -0.434 |
Token | factories |
Token ID | 17590 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
welf | +0.458 |
weap | +0.428 |
scrut | +0.422 |
ingred | +0.417 |
ships | +0.410 |
Neg logit contributions | |
Nice | -0.358 |
quiet | -0.336 |
zeb | -0.328 |
isexual | -0.316 |
� | -0.313 |
Token | will |
Token ID | 481 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
welf | +1.016 |
weap | +0.947 |
scrut | +0.939 |
ingred | +0.920 |
ships | +0.905 |
Neg logit contributions | |
Nice | -0.866 |
quiet | -0.825 |
zeb | -0.816 |
isexual | -0.789 |
� | -0.770 |
Token | close |
Token ID | 1969 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
welf | +0.686 |
weap | +0.636 |
scrut | +0.632 |
ingred | +0.619 |
ships | +0.610 |
Neg logit contributions | |
Nice | -0.608 |
quiet | -0.582 |
zeb | -0.573 |
isexual | -0.556 |
� | -0.541 |
Token | down |
Token ID | 866 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
welf | +1.662 |
weap | +1.547 |
scrut | +1.534 |
ingred | +1.497 |
ships | +1.474 |
Neg logit contributions | |
Nice | -1.554 |
quiet | -1.489 |
zeb | -1.478 |
isexual | -1.437 |
� | -1.395 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Nice | +0.243 |
quiet | +0.231 |
zeb | +0.228 |
isexual | +0.219 |
� | +0.215 |
Neg logit contributions | |
welf | -0.301 |
weap | -0.281 |
scrut | -0.278 |
ingred | -0.273 |
ships | -0.268 |
Token | formidable |
Token ID | 24599 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
welf | +0.240 |
weap | +0.225 |
scrut | +0.223 |
ingred | +0.218 |
ships | +0.215 |
Neg logit contributions | |
Nice | -0.178 |
quiet | -0.169 |
zeb | -0.167 |
isexual | -0.161 |
� | -0.157 |
Token | Diana |
Token ID | 25752 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
welf | +2.816 |
weap | +2.649 |
scrut | +2.631 |
ingred | +2.566 |
ships | +2.524 |
Neg logit contributions | |
Nice | -1.834 |
quiet | -1.765 |
zeb | -1.749 |
isexual | -1.691 |
� | -1.636 |
Token | Vill |
Token ID | 9757 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Nice | +0.223 |
quiet | +0.211 |
zeb | +0.210 |
isexual | +0.202 |
� | +0.197 |
Neg logit contributions | |
welf | -0.276 |
weap | -0.258 |
scrut | -0.256 |
ingred | -0.250 |
ships | -0.247 |
Token | iers |
Token ID | 3183 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
Nice | +1.383 |
quiet | +1.335 |
zeb | +1.326 |
isexual | +1.286 |
� | +1.259 |
Neg logit contributions | |
welf | -1.259 |
weap | -1.168 |
scrut | -1.151 |
ingred | -1.128 |
ships | -1.093 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Nice | +0.591 |
quiet | +0.560 |
zeb | +0.555 |
isexual | +0.531 |
� | +0.522 |
Neg logit contributions | |
welf | -0.706 |
weap | -0.658 |
scrut | -0.653 |
ingred | -0.641 |
ships | -0.629 |
Token | She |
Token ID | 1375 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
welf | +0.089 |
weap | +0.084 |
scrut | +0.083 |
ingred | +0.082 |
unden | +0.080 |
Neg logit contributions | |
Nice | -0.067 |
quiet | -0.063 |
zeb | -0.062 |
isexual | -0.060 |
� | -0.058 |
Token | is |
Token ID | 318 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
Nice | +0.259 |
quiet | +0.248 |
zeb | +0.245 |
isexual | +0.237 |
� | +0.231 |
Neg logit contributions | |
welf | -0.294 |
weap | -0.273 |
scrut | -0.271 |
ingred | -0.266 |
ships | -0.260 |
Token | too |
Token ID | 1165 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
welf | +0.027 |
weap | +0.026 |
scrut | +0.025 |
ingred | +0.025 |
ships | +0.024 |
Neg logit contributions | |
Nice | -0.021 |
quiet | -0.020 |
zeb | -0.020 |
isexual | -0.020 |
� | -0.019 |
Token | much |
Token ID | 881 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Nice | +0.986 |
quiet | +0.921 |
zeb | +0.910 |
isexual | +0.866 |
� | +0.842 |
Neg logit contributions | |
welf | -1.618 |
weap | -1.522 |
scrut | -1.501 |
ingred | -1.490 |
ships | -1.469 |
Token | for |
Token ID | 329 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
welf | +0.877 |
weap | +0.818 |
scrut | +0.811 |
ingred | +0.794 |
ships | +0.781 |
Neg logit contributions | |
Nice | -0.735 |
quiet | -0.701 |
zeb | -0.694 |
isexual | -0.671 |
� | -0.653 |
Token | Jack |
Token ID | 3619 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
Nice | +0.514 |
quiet | +0.488 |
zeb | +0.483 |
isexual | +0.467 |
� | +0.454 |
Neg logit contributions | |
welf | -0.641 |
weap | -0.599 |
scrut | -0.594 |
ingred | -0.583 |
ships | -0.573 |
Token | and |
Token ID | 290 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
welf | +0.109 |
weap | +0.102 |
scrut | +0.101 |
ingred | +0.099 |
ships | +0.097 |
Neg logit contributions | |
Nice | -0.083 |
quiet | -0.079 |
zeb | -0.078 |
isexual | -0.076 |
� | -0.074 |
Token | vegetables |
Token ID | 13701 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Nice | +0.247 |
quiet | +0.232 |
zeb | +0.230 |
isexual | +0.224 |
� | +0.218 |
Neg logit contributions | |
welf | -0.238 |
weap | -0.221 |
scrut | -0.221 |
ingred | -0.214 |
CLASSIFIED | -0.211 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
welf | +0.376 |
weap | +0.351 |
scrut | +0.349 |
ingred | +0.341 |
ships | +0.336 |
Neg logit contributions | |
Nice | -0.287 |
quiet | -0.273 |
zeb | -0.269 |
isexual | -0.260 |
� | -0.253 |
Token | keeps |
Token ID | 7622 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Nice | +0.165 |
quiet | +0.156 |
zeb | +0.153 |
isexual | +0.149 |
� | +0.146 |
Neg logit contributions | |
welf | -0.187 |
weap | -0.175 |
scrut | -0.173 |
ingred | -0.170 |
CLASSIFIED | -0.167 |
Token | honey |
Token ID | 12498 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
welf | +1.364 |
weap | +1.275 |
scrut | +1.265 |
ingred | +1.237 |
ships | +1.219 |
Neg logit contributions | |
Nice | -1.087 |
quiet | -1.037 |
zeb | -1.028 |
isexual | -0.994 |
� | -0.966 |
Token | bees |
Token ID | 41712 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Nice | +0.041 |
quiet | +0.039 |
zeb | +0.039 |
isexual | +0.037 |
� | +0.036 |
Neg logit contributions | |
welf | -0.056 |
weap | -0.052 |
scrut | -0.051 |
ingred | -0.050 |
ships | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Nice | +0.084 |
quiet | +0.080 |
zeb | +0.080 |
isexual | +0.076 |
� | +0.073 |
Neg logit contributions | |
welf | -0.126 |
weap | -0.119 |
scrut | -0.117 |
ingred | -0.115 |
ships | -0.113 |
Token | cultiv |
Token ID | 11229 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Nice | +0.111 |
quiet | +0.105 |
zeb | +0.104 |
isexual | +0.100 |
� | +0.098 |
Neg logit contributions | |
welf | -0.125 |
weap | -0.117 |
scrut | -0.115 |
ingred | -0.114 |
ships | -0.111 |
Token | ates |
Token ID | 689 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
welf | +1.673 |
weap | +1.558 |
scrut | +1.545 |
ingred | +1.511 |
ships | +1.488 |
Neg logit contributions | |
Nice | -1.481 |
quiet | -1.414 |
zeb | -1.401 |
isexual | -1.356 |
� | -1.322 |
Token | mushrooms |
Token ID | 23452 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
welf | +1.137 |
weap | +1.060 |
scrut | +1.052 |
ingred | +1.030 |
ships | +1.014 |
Neg logit contributions | |
Nice | -0.970 |
quiet | -0.922 |
zeb | -0.913 |
isexual | -0.884 |
� | -0.861 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
welf | +0.397 |
weap | +0.371 |
scrut | +0.368 |
ingred | +0.361 |
ships | +0.355 |
Neg logit contributions | |
Nice | -0.311 |
quiet | -0.296 |
zeb | -0.293 |
isexual | -0.283 |
� | -0.275 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
welf | +0.620 |
weap | +0.576 |
scrut | +0.571 |
ingred | +0.559 |
ships | +0.550 |
Neg logit contributions | |
Nice | -0.575 |
quiet | -0.550 |
zeb | -0.545 |
isexual | -0.528 |
� | -0.515 |
Token | books |
Token ID | 3835 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
welf | +0.009 |
weap | +0.009 |
scrut | +0.009 |
ingred | +0.009 |
ships | +0.008 |
Neg logit contributions | |
Nice | -0.009 |
quiet | -0.008 |
zeb | -0.008 |
isexual | -0.008 |
� | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
Nice | +0.475 |
quiet | +0.452 |
zeb | +0.444 |
isexual | +0.428 |
� | +0.420 |
Neg logit contributions | |
welf | -0.630 |
weap | -0.589 |
scrut | -0.584 |
ingred | -0.573 |
ships | -0.561 |
Token | you |
Token ID | 345 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
Nice | +0.369 |
quiet | +0.351 |
zeb | +0.343 |
isexual | +0.332 |
� | +0.329 |
Neg logit contributions | |
welf | -0.431 |
weap | -0.401 |
scrut | -0.396 |
ingred | -0.389 |
ships | -0.383 |
Token | want |
Token ID | 765 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
Nice | +0.598 |
quiet | +0.574 |
zeb | +0.558 |
isexual | +0.546 |
� | +0.538 |
Neg logit contributions | |
welf | -0.731 |
weap | -0.676 |
scrut | -0.668 |
ingred | -0.662 |
ships | -0.644 |
Token | to |
Token ID | 284 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
Nice | +0.399 |
quiet | +0.377 |
zeb | +0.369 |
isexual | +0.354 |
� | +0.345 |
Neg logit contributions | |
welf | -0.675 |
weap | -0.637 |
scrut | -0.630 |
ingred | -0.621 |
ships | -0.609 |
Token | read |
Token ID | 1100 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
welf | +0.093 |
weap | +0.088 |
scrut | +0.086 |
ingred | +0.085 |
ships | +0.084 |
Neg logit contributions | |
Nice | -0.056 |
quiet | -0.053 |
zeb | -0.052 |
isexual | -0.050 |
� | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
Nice | +0.603 |
quiet | +0.575 |
zeb | +0.559 |
isexual | +0.543 |
� | +0.532 |
Neg logit contributions | |
welf | -0.856 |
weap | -0.798 |
scrut | -0.792 |
ingred | -0.781 |
ships | -0.765 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Nice | +0.011 |
quiet | +0.010 |
zeb | +0.010 |
isexual | +0.010 |
� | +0.010 |
Neg logit contributions | |
welf | -0.012 |
weap | -0.011 |
scrut | -0.011 |
ingred | -0.011 |
ships | -0.011 |
Token | Kindle |
Token ID | 27114 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
welf | +0.080 |
weap | +0.075 |
scrut | +0.074 |
ingred | +0.072 |
ships | +0.071 |
Neg logit contributions | |
Nice | -0.075 |
quiet | -0.072 |
zeb | -0.071 |
isexual | -0.069 |
� | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Nice | +0.688 |
quiet | +0.654 |
zeb | +0.642 |
isexual | +0.616 |
� | +0.611 |
Neg logit contributions | |
welf | -0.891 |
weap | -0.835 |
scrut | -0.825 |
ingred | -0.820 |
ships | -0.801 |
Token | mind |
Token ID | 2000 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Nice | +0.112 |
quiet | +0.108 |
zeb | +0.106 |
isexual | +0.103 |
� | +0.101 |
Neg logit contributions | |
welf | -0.134 |
weap | -0.125 |
scrut | -0.123 |
ingred | -0.122 |
ships | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
welf | +1.625 |
weap | +1.515 |
scrut | +1.502 |
ingred | +1.470 |
ships | +1.446 |
Neg logit contributions | |
Nice | -1.398 |
quiet | -1.334 |
zeb | -1.321 |
isexual | -1.279 |
� | -1.246 |
Token | we |
Token ID | 356 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
welf | +0.242 |
weap | +0.225 |
scrut | +0.223 |
ingred | +0.220 |
ships | +0.215 |
Neg logit contributions | |
Nice | -0.196 |
quiet | -0.186 |
zeb | -0.182 |
isexual | -0.176 |
� | -0.173 |
Token | do |
Token ID | 466 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
welf | +0.129 |
weap | +0.120 |
scrut | +0.118 |
ingred | +0.117 |
ships | +0.114 |
Neg logit contributions | |
Nice | -0.111 |
quiet | -0.106 |
zeb | -0.105 |
isexual | -0.101 |
� | -0.100 |
Token | realize |
Token ID | 6537 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
welf | +0.863 |
weap | +0.798 |
scrut | +0.791 |
ingred | +0.777 |
ships | +0.764 |
Neg logit contributions | |
Nice | -0.796 |
quiet | -0.760 |
zeb | -0.750 |
isexual | -0.727 |
� | -0.713 |
Token | that |
Token ID | 326 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
welf | +0.330 |
weap | +0.309 |
scrut | +0.305 |
ingred | +0.301 |
ships | +0.295 |
Neg logit contributions | |
Nice | -0.251 |
quiet | -0.237 |
zeb | -0.233 |
isexual | -0.226 |
� | -0.221 |
Token | some |
Token ID | 617 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Nice | +0.035 |
quiet | +0.033 |
zeb | +0.033 |
isexual | +0.031 |
� | +0.031 |
Neg logit contributions | |
welf | -0.045 |
weap | -0.042 |
scrut | -0.041 |
ingred | -0.041 |
ships | -0.040 |
Token | are |
Token ID | 389 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
welf | +0.213 |
weap | +0.198 |
scrut | +0.195 |
ingred | +0.192 |
ships | +0.188 |
Neg logit contributions | |
Nice | -0.194 |
quiet | -0.185 |
zeb | -0.183 |
isexual | -0.176 |
� | -0.173 |
Token | more |
Token ID | 517 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Nice | +0.289 |
quiet | +0.273 |
zeb | +0.268 |
isexual | +0.259 |
� | +0.253 |
Neg logit contributions | |
welf | -0.387 |
weap | -0.361 |
scrut | -0.357 |
ingred | -0.351 |
ships | -0.346 |
Token | exciting |
Token ID | 7895 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Nice | +0.335 |
quiet | +0.316 |
zeb | +0.310 |
isexual | +0.300 |
� | +0.292 |
Neg logit contributions | |
welf | -0.437 |
weap | -0.407 |
scrut | -0.401 |
ingred | -0.396 |
ships | -0.391 |
Token | than |
Token ID | 621 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
welf | +0.249 |
weap | +0.232 |
scrut | +0.231 |
ingred | +0.226 |
ships | +0.222 |
Neg logit contributions | |
Nice | -0.197 |
quiet | -0.187 |
zeb | -0.185 |
isexual | -0.178 |
� | -0.174 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Nice | +0.569 |
quiet | +0.540 |
zeb | +0.536 |
isexual | +0.515 |
� | +0.503 |
Neg logit contributions | |
welf | -0.649 |
weap | -0.604 |
scrut | -0.599 |
ingred | -0.588 |
ships | -0.574 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Nice | +0.143 |
quiet | +0.134 |
zeb | +0.132 |
isexual | +0.128 |
� | +0.124 |
Neg logit contributions | |
welf | -0.185 |
weap | -0.173 |
scrut | -0.172 |
ingred | -0.169 |
ships | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Nice | +0.091 |
quiet | +0.086 |
zeb | +0.085 |
isexual | +0.083 |
� | +0.079 |
Neg logit contributions | |
welf | -0.117 |
weap | -0.110 |
scrut | -0.109 |
ingred | -0.107 |
ships | -0.106 |
Token | continue |
Token ID | 2555 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Nice | +0.015 |
quiet | +0.014 |
zeb | +0.014 |
isexual | +0.014 |
� | +0.013 |
Neg logit contributions | |
welf | -0.017 |
weap | -0.016 |
scrut | -0.015 |
ingred | -0.015 |
ships | -0.015 |
Token | paying |
Token ID | 5989 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
Nice | +0.275 |
quiet | +0.259 |
zeb | +0.255 |
isexual | +0.247 |
� | +0.237 |
Neg logit contributions | |
welf | -0.406 |
weap | -0.383 |
scrut | -0.378 |
ingred | -0.372 |
ships | -0.368 |
Token | my |
Token ID | 616 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Nice | +0.008 |
quiet | +0.007 |
zeb | +0.007 |
isexual | +0.007 |
� | +0.007 |
Neg logit contributions | |
welf | -0.008 |
weap | -0.007 |
scrut | -0.007 |
ingred | -0.007 |
ships | -0.007 |
Token | tit |
Token ID | 5259 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Nice | +0.213 |
quiet | +0.201 |
zeb | +0.200 |
isexual | +0.193 |
� | +0.188 |
Neg logit contributions | |
welf | -0.225 |
weap | -0.210 |
scrut | -0.207 |
ingred | -0.203 |
ships | -0.201 |
Token | hes |
Token ID | 956 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Nice | +1.177 |
quiet | +1.123 |
zeb | +1.118 |
isexual | +1.066 |
� | +1.051 |
Neg logit contributions | |
welf | -1.354 |
weap | -1.268 |
scrut | -1.263 |
ingred | -1.234 |
ships | -1.208 |
Token | to |
Token ID | 284 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
Nice | +0.711 |
quiet | +0.675 |
zeb | +0.667 |
isexual | +0.642 |
� | +0.623 |
Neg logit contributions | |
welf | -0.891 |
weap | -0.833 |
scrut | -0.828 |
ingred | -0.814 |
ships | -0.798 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
welf | +0.073 |
weap | +0.069 |
scrut | +0.068 |
ingred | +0.067 |
ships | +0.066 |
Neg logit contributions | |
Nice | -0.059 |
quiet | -0.056 |
zeb | -0.055 |
isexual | -0.054 |
� | -0.052 |
Token | church |
Token ID | 4928 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Nice | +0.073 |
quiet | +0.069 |
zeb | +0.068 |
isexual | +0.066 |
� | +0.063 |
Neg logit contributions | |
welf | -0.104 |
weap | -0.098 |
scrut | -0.097 |
ingred | -0.095 |
ships | -0.094 |
Token | aine |
Token ID | 5718 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
welf | +0.058 |
weap | +0.054 |
scrut | +0.053 |
ingred | +0.053 |
ships | +0.052 |
Neg logit contributions | |
Nice | -0.041 |
quiet | -0.039 |
zeb | -0.038 |
isexual | -0.036 |
� | -0.036 |
Token | also |
Token ID | 635 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
welf | +0.016 |
weap | +0.015 |
scrut | +0.014 |
ingred | +0.014 |
ships | +0.014 |
Neg logit contributions | |
Nice | -0.014 |
quiet | -0.013 |
zeb | -0.013 |
isexual | -0.013 |
� | -0.013 |
Token | did |
Token ID | 750 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Nice | +0.418 |
quiet | +0.398 |
zeb | +0.398 |
isexual | +0.378 |
� | +0.374 |
Neg logit contributions | |
welf | -0.452 |
weap | -0.419 |
scrut | -0.411 |
ingred | -0.410 |
ships | -0.399 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
welf | +0.216 |
weap | +0.202 |
scrut | +0.199 |
ingred | +0.197 |
ships | +0.195 |
Neg logit contributions | |
Nice | -0.185 |
quiet | -0.175 |
zeb | -0.174 |
isexual | -0.166 |
� | -0.164 |
Token | good |
Token ID | 922 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Nice | +0.106 |
quiet | +0.100 |
zeb | +0.099 |
isexual | +0.094 |
� | +0.092 |
Neg logit contributions | |
welf | -0.149 |
weap | -0.140 |
scrut | -0.138 |
ingred | -0.137 |
ships | -0.135 |
Token | job |
Token ID | 1693 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
welf | +0.510 |
weap | +0.475 |
scrut | +0.468 |
ingred | +0.459 |
ships | +0.451 |
Neg logit contributions | |
Nice | -0.511 |
quiet | -0.488 |
zeb | -0.484 |
isexual | -0.469 |
� | -0.459 |
Token | repeatedly |
Token ID | 7830 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Nice | +1.673 |
quiet | +1.582 |
zeb | +1.562 |
isexual | +1.484 |
� | +1.468 |
Neg logit contributions | |
welf | -2.110 |
weap | -1.987 |
ingred | -1.921 |
scrut | -1.914 |
ships | -1.886 |
Token | pressing |
Token ID | 12273 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
welf | +0.977 |
weap | +0.914 |
scrut | +0.904 |
ingred | +0.888 |
ships | +0.874 |
Neg logit contributions | |
Nice | -0.756 |
quiet | -0.720 |
zeb | -0.712 |
isexual | -0.686 |
� | -0.669 |
Token | on |
Token ID | 319 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Nice | +0.072 |
quiet | +0.067 |
zeb | +0.066 |
isexual | +0.063 |
� | +0.062 |
Neg logit contributions | |
welf | -0.101 |
weap | -0.095 |
scrut | -0.094 |
ingred | -0.092 |
ships | -0.091 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Nice | +0.267 |
quiet | +0.249 |
zeb | +0.246 |
isexual | +0.236 |
� | +0.230 |
Neg logit contributions | |
welf | -0.386 |
weap | -0.363 |
scrut | -0.361 |
ingred | -0.354 |
ships | -0.349 |
Token | � |
Token ID | 447 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Nice | +0.943 |
quiet | +0.897 |
zeb | +0.886 |
isexual | +0.847 |
� | +0.831 |
Neg logit contributions | |
welf | -1.394 |
weap | -1.305 |
scrut | -1.293 |
ingred | -1.274 |
ships | -1.247 |
Token | especially |
Token ID | 2592 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
welf | +0.074 |
weap | +0.069 |
scrut | +0.068 |
ingred | +0.067 |
ships | +0.066 |
Neg logit contributions | |
Nice | -0.061 |
quiet | -0.058 |
zeb | -0.057 |
isexual | -0.055 |
� | -0.054 |
Token | when |
Token ID | 618 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
Nice | +0.791 |
quiet | +0.749 |
zeb | +0.737 |
isexual | +0.708 |
� | +0.694 |
Neg logit contributions | |
welf | -1.090 |
weap | -1.018 |
scrut | -1.010 |
ingred | -0.992 |
ships | -0.975 |
Token | you |
Token ID | 345 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
welf | +0.072 |
weap | +0.066 |
scrut | +0.066 |
ingred | +0.065 |
ships | +0.064 |
Neg logit contributions | |
Nice | -0.060 |
quiet | -0.057 |
zeb | -0.056 |
isexual | -0.054 |
� | -0.053 |
Token | consider |
Token ID | 2074 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
Nice | +0.899 |
quiet | +0.863 |
zeb | +0.843 |
isexual | +0.814 |
� | +0.812 |
Neg logit contributions | |
welf | -1.036 |
weap | -0.958 |
scrut | -0.945 |
ingred | -0.938 |
ships | -0.915 |
Token | the |
Token ID | 262 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Nice | +0.470 |
quiet | +0.441 |
zeb | +0.434 |
isexual | +0.418 |
� | +0.412 |
Neg logit contributions | |
welf | -0.592 |
weap | -0.552 |
scrut | -0.548 |
ingred | -0.539 |
ships | -0.530 |
Token | Las |
Token ID | 10123 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Nice | +0.146 |
quiet | +0.138 |
zeb | +0.137 |
isexual | +0.131 |
� | +0.130 |
Neg logit contributions | |
welf | -0.144 |
weap | -0.133 |
scrut | -0.132 |
ingred | -0.129 |
ships | -0.128 |
Token | Vegas |
Token ID | 9621 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Nice | +1.769 |
quiet | +1.663 |
zeb | +1.653 |
isexual | +1.569 |
igue | +1.554 |
Neg logit contributions | |
welf | -2.347 |
scrut | -2.196 |
weap | -2.175 |
ingred | -2.164 |
unden | -2.147 |
Token | case |
Token ID | 1339 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Nice | +1.683 |
zeb | +1.563 |
quiet | +1.549 |
isexual | +1.471 |
� | +1.442 |
Neg logit contributions | |
welf | -2.113 |
scrut | -1.976 |
weap | -1.971 |
ingred | -1.924 |
ships | -1.915 |
Token | in |
Token ID | 287 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
welf | +1.562 |
weap | +1.454 |
scrut | +1.442 |
ingred | +1.408 |
ships | +1.389 |
Neg logit contributions | |
Nice | -1.426 |
quiet | -1.364 |
zeb | -1.350 |
isexual | -1.314 |
� | -1.274 |
Token | its |
Token ID | 663 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
welf | +0.102 |
weap | +0.095 |
scrut | +0.094 |
ingred | +0.092 |
ships | +0.091 |
Neg logit contributions | |
Nice | -0.101 |
quiet | -0.097 |
zeb | -0.095 |
isexual | -0.092 |
� | -0.090 |
Token | larger |
Token ID | 4025 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Nice | +1.331 |
quiet | +1.274 |
zeb | +1.271 |
isexual | +1.222 |
� | +1.207 |
Neg logit contributions | |
welf | -0.915 |
weap | -0.839 |
scrut | -0.826 |
ingred | -0.809 |
ships | -0.788 |
Token | pest |
Token ID | 28064 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
Nice | +0.316 |
quiet | +0.300 |
zeb | +0.297 |
isexual | +0.285 |
� | +0.277 |
Neg logit contributions | |
welf | -0.447 |
weap | -0.419 |
scrut | -0.415 |
ingred | -0.408 |
ships | -0.403 |
Token | il |
Token ID | 346 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
Nice | +0.059 |
quiet | +0.056 |
zeb | +0.056 |
isexual | +0.054 |
� | +0.053 |
Neg logit contributions | |
welf | -0.057 |
weap | -0.053 |
scrut | -0.052 |
ingred | -0.051 |
ships | -0.050 |
Token | ent |
Token ID | 298 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
welf | +0.803 |
weap | +0.757 |
scrut | +0.750 |
ingred | +0.736 |
ships | +0.728 |
Neg logit contributions | |
Nice | -0.520 |
quiet | -0.490 |
zeb | -0.486 |
isexual | -0.467 |
� | -0.453 |
Token | congregation |
Token ID | 28862 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
Nice | +0.938 |
quiet | +0.888 |
zeb | +0.879 |
isexual | +0.843 |
� | +0.827 |
Neg logit contributions | |
welf | -1.143 |
weap | -1.069 |
scrut | -1.056 |
ingred | -1.039 |
ships | -1.029 |
Token | of |
Token ID | 286 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Nice | +0.608 |
quiet | +0.581 |
zeb | +0.575 |
isexual | +0.552 |
� | +0.541 |
Neg logit contributions | |
welf | -0.728 |
weap | -0.681 |
scrut | -0.675 |
ingred | -0.662 |
ships | -0.647 |
Token | vap |
Token ID | 38187 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Nice | +0.095 |
quiet | +0.090 |
zeb | +0.089 |
isexual | +0.086 |
� | +0.084 |
Neg logit contributions | |
welf | -0.117 |
weap | -0.109 |
scrut | -0.108 |
ingred | -0.106 |
ships | -0.105 |
Token | ors |
Token ID | 669 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Nice | +1.585 |
quiet | +1.515 |
zeb | +1.498 |
isexual | +1.447 |
� | +1.407 |
Neg logit contributions | |
welf | -2.122 |
weap | -1.988 |
scrut | -1.962 |
ingred | -1.917 |
unden | -1.879 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Nice | +1.103 |
quiet | +1.053 |
zeb | +1.042 |
isexual | +0.996 |
� | +0.977 |
Neg logit contributions | |
welf | -1.383 |
weap | -1.291 |
scrut | -1.279 |
ingred | -1.256 |
ships | -1.229 |
Token |
|
Token ID | 198 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Nice | +0.294 |
quiet | +0.282 |
zeb | +0.280 |
isexual | +0.272 |
� | +0.264 |
Neg logit contributions | |
welf | -0.324 |
weap | -0.302 |
scrut | -0.298 |
ingred | -0.292 |
ships | -0.288 |
Token |
|
Token ID | 198 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
Nice | +0.368 |
quiet | +0.348 |
zeb | +0.343 |
isexual | +0.326 |
� | +0.323 |
Neg logit contributions | |
welf | -0.491 |
ingred | -0.455 |
weap | -0.455 |
scrut | -0.454 |
unden | -0.447 |
Token | What |
Token ID | 2061 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
Nice | +0.455 |
quiet | +0.439 |
zeb | +0.431 |
isexual | +0.415 |
� | +0.412 |
Neg logit contributions | |
welf | -0.442 |
weap | -0.410 |
scrut | -0.407 |
ingred | -0.400 |
unden | -0.386 |
Token | stock |
Token ID | 4283 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Nice | +0.680 |
quiet | +0.645 |
zeb | +0.628 |
isexual | +0.603 |
� | +0.591 |
Neg logit contributions | |
welf | -0.806 |
weap | -0.742 |
scrut | -0.728 |
ingred | -0.726 |
ships | -0.710 |
Token | was |
Token ID | 373 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Nice | +0.434 |
quiet | +0.414 |
zeb | +0.410 |
isexual | +0.396 |
� | +0.386 |
Neg logit contributions | |
welf | -0.494 |
weap | -0.459 |
scrut | -0.457 |
ingred | -0.447 |
ships | -0.437 |
Token | trading |
Token ID | 7313 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
welf | +0.115 |
weap | +0.107 |
scrut | +0.105 |
ingred | +0.104 |
ships | +0.101 |
Neg logit contributions | |
Nice | -0.109 |
quiet | -0.104 |
zeb | -0.102 |
isexual | -0.099 |
� | -0.097 |
Token | when |
Token ID | 618 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
welf | +0.360 |
weap | +0.337 |
scrut | +0.335 |
ingred | +0.329 |
ships | +0.323 |
Neg logit contributions | |
Nice | -0.256 |
quiet | -0.243 |
zeb | -0.238 |
isexual | -0.229 |
� | -0.223 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
welf | +0.206 |
weap | +0.192 |
scrut | +0.190 |
ingred | +0.187 |
ships | +0.184 |
Neg logit contributions | |
Nice | -0.156 |
quiet | -0.148 |
zeb | -0.144 |
isexual | -0.140 |
� | -0.137 |
Token | bid |
Token ID | 8406 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
Nice | +0.029 |
quiet | +0.028 |
zeb | +0.027 |
isexual | +0.026 |
� | +0.026 |
Neg logit contributions | |
welf | -0.028 |
weap | -0.026 |
scrut | -0.026 |
ingred | -0.026 |
ships | -0.025 |
Token | approach |
Token ID | 3164 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Nice | +2.644 |
quiet | +2.511 |
zeb | +2.503 |
isexual | +2.379 |
� | +2.299 |
Neg logit contributions | |
welf | -3.335 |
weap | -3.079 |
ingred | -3.028 |
scrut | -3.021 |
unden | -2.953 |
Token | was |
Token ID | 373 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
Nice | +0.492 |
quiet | +0.469 |
zeb | +0.464 |
isexual | +0.449 |
� | +0.437 |
Neg logit contributions | |
welf | -0.550 |
weap | -0.511 |
scrut | -0.505 |
ingred | -0.498 |
ships | -0.486 |
Token | made |
Token ID | 925 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
welf | +0.021 |
weap | +0.020 |
scrut | +0.019 |
ingred | +0.019 |
ships | +0.019 |
Neg logit contributions | |
Nice | -0.018 |
quiet | -0.017 |
zeb | -0.017 |
isexual | -0.016 |
� | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Nice | +0.078 |
quiet | +0.075 |
zeb | +0.073 |
isexual | +0.071 |
� | +0.069 |
Neg logit contributions | |
welf | -0.088 |
weap | -0.081 |
scrut | -0.080 |
ingred | -0.079 |
ships | -0.078 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Nice | +0.113 |
quiet | +0.104 |
zeb | +0.102 |
isexual | +0.097 |
� | +0.094 |
Neg logit contributions | |
welf | -0.208 |
weap | -0.196 |
scrut | -0.194 |
ingred | -0.192 |
ships | -0.189 |
Token | a |
Token ID | 257 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
welf | +0.268 |
weap | +0.252 |
scrut | +0.249 |
ingred | +0.244 |
ships | +0.240 |
Neg logit contributions | |
Nice | -0.231 |
quiet | -0.220 |
zeb | -0.217 |
isexual | -0.210 |
� | -0.204 |
Token | week |
Token ID | 1285 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Nice | +0.118 |
quiet | +0.113 |
zeb | +0.112 |
isexual | +0.108 |
� | +0.105 |
Neg logit contributions | |
welf | -0.144 |
weap | -0.134 |
scrut | -0.133 |
ingred | -0.130 |
ships | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
welf | +0.046 |
weap | +0.043 |
scrut | +0.043 |
ingred | +0.042 |
ships | +0.041 |
Neg logit contributions | |
Nice | -0.040 |
quiet | -0.038 |
zeb | -0.038 |
isexual | -0.037 |
� | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
welf | +0.209 |
weap | +0.195 |
scrut | +0.194 |
ingred | +0.190 |
ships | +0.185 |
Neg logit contributions | |
Nice | -0.174 |
quiet | -0.163 |
zeb | -0.162 |
isexual | -0.156 |
� | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
welf | +0.089 |
weap | +0.083 |
scrut | +0.083 |
ingred | +0.082 |
unden | +0.079 |
Neg logit contributions | |
Nice | -0.073 |
quiet | -0.069 |
zeb | -0.068 |
isexual | -0.066 |
� | -0.065 |
Token | Still |
Token ID | 9590 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
welf | +0.068 |
weap | +0.063 |
scrut | +0.063 |
ingred | +0.062 |
unden | +0.060 |
Neg logit contributions | |
Nice | -0.069 |
quiet | -0.067 |
zeb | -0.066 |
isexual | -0.064 |
� | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Nice | +2.017 |
quiet | +1.893 |
zeb | +1.845 |
isexual | +1.789 |
� | +1.741 |
Neg logit contributions | |
welf | -2.664 |
weap | -2.486 |
scrut | -2.470 |
ingred | -2.428 |
ships | -2.375 |
Token | there |
Token ID | 612 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
Nice | +0.333 |
quiet | +0.311 |
zeb | +0.307 |
isexual | +0.296 |
� | +0.290 |
Neg logit contributions | |
welf | -0.413 |
weap | -0.387 |
scrut | -0.384 |
ingred | -0.377 |
ships | -0.371 |
Token | is |
Token ID | 318 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
welf | +0.006 |
weap | +0.005 |
scrut | +0.005 |
ingred | +0.005 |
ships | +0.005 |
Neg logit contributions | |
Nice | -0.005 |
quiet | -0.005 |
zeb | -0.005 |
isexual | -0.004 |
� | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
welf | +0.080 |
weap | +0.075 |
scrut | +0.074 |
ingred | +0.072 |
ships | +0.071 |
Neg logit contributions | |
Nice | -0.069 |
quiet | -0.065 |
zeb | -0.064 |
isexual | -0.062 |
� | -0.060 |
Token | right |
Token ID | 826 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Nice | +0.119 |
quiet | +0.112 |
zeb | +0.111 |
isexual | +0.107 |
� | +0.104 |
Neg logit contributions | |
welf | -0.138 |
weap | -0.129 |
scrut | -0.127 |
ingred | -0.125 |
ships | -0.124 |