Token | leaders |
Token ID | 2766 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
THING | +1.596 |
Cerberus | +1.453 |
IMAGES | +1.427 |
copyrighted | +1.398 |
inosaur | +1.383 |
Neg logit contributions | |
nesota | -2.141 |
olate | -2.013 |
vale | -1.961 |
lication | -1.935 |
jected | -1.922 |
Token | don |
Token ID | 836 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
THING | +1.853 |
Cerberus | +1.692 |
IMAGES | +1.659 |
inosaur | +1.657 |
copyrighted | +1.646 |
Neg logit contributions | |
nesota | -1.989 |
olate | -1.821 |
vale | -1.773 |
lication | -1.768 |
jected | -1.757 |
Token | � |
Token ID | 447 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
THING | +2.195 |
Cerberus | +1.993 |
inosaur | +1.990 |
IMAGES | +1.968 |
copyrighted | +1.948 |
Neg logit contributions | |
nesota | -1.915 |
olate | -1.774 |
lication | -1.702 |
vale | -1.696 |
jected | -1.692 |
Token | � |
Token ID | 247 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
THING | +4.749 |
inosaur | +4.212 |
Cerberus | +4.161 |
IMAGES | +4.160 |
copyrighted | +4.102 |
Neg logit contributions | |
nesota | -4.700 |
olate | -4.342 |
vale | -4.291 |
jected | -4.207 |
lication | -4.136 |
Token | t |
Token ID | 83 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
THING | +1.720 |
inosaur | +1.509 |
Cerberus | +1.497 |
IMAGES | +1.459 |
copyrighted | +1.423 |
Neg logit contributions | |
nesota | -2.819 |
olate | -2.618 |
vale | -2.568 |
jected | -2.549 |
lication | -2.548 |
Token | even |
Token ID | 772 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
THING | +4.307 |
Cerberus | +4.017 |
IMAGES | +3.999 |
copyrighted | +3.943 |
inosaur | +3.911 |
Neg logit contributions | |
nesota | -3.290 |
olate | -2.908 |
lication | -2.894 |
jected | -2.892 |
vale | -2.796 |
Token | talk |
Token ID | 1561 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
THING | +13.497 |
Cerberus | +12.508 |
copyrighted | +12.466 |
kidding | +12.386 |
IMAGES | +12.343 |
Neg logit contributions | |
nesota | -11.732 |
jected | -10.563 |
lication | -10.380 |
olate | -10.143 |
vale | -9.987 |
Token | about |
Token ID | 546 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
THING | +2.152 |
Cerberus | +1.936 |
IMAGES | +1.909 |
inosaur | +1.884 |
copyrighted | +1.854 |
Neg logit contributions | |
nesota | -2.818 |
olate | -2.627 |
vale | -2.551 |
jected | -2.517 |
lication | -2.515 |
Token | it |
Token ID | 340 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
THING | +4.156 |
Cerberus | +3.772 |
IMAGES | +3.661 |
copyrighted | +3.645 |
inosaur | +3.506 |
Neg logit contributions | |
nesota | -5.998 |
olate | -5.618 |
vale | -5.425 |
jected | -5.420 |
lication | -5.409 |
Token | . |
Token ID | 13 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
THING | +2.738 |
Cerberus | +2.475 |
IMAGES | +2.461 |
inosaur | +2.431 |
copyrighted | +2.385 |
Neg logit contributions | |
nesota | -3.228 |
olate | -3.017 |
vale | -2.923 |
lication | -2.908 |
jected | -2.885 |
Token |
|
Token ID | 198 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
THING | +2.468 |
Cerberus | +2.270 |
IMAGES | +2.268 |
inosaur | +2.188 |
copyrighted | +2.139 |
Neg logit contributions | |
nesota | -2.816 |
olate | -2.629 |
vale | -2.533 |
jected | -2.531 |
lication | -2.529 |
Token | I |
Token ID | 40 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
nesota | +1.678 |
olate | +1.564 |
vale | +1.505 |
jected | +1.478 |
lication | +1.472 |
Neg logit contributions | |
THING | -1.803 |
Cerberus | -1.652 |
IMAGES | -1.650 |
inosaur | -1.632 |
copyrighted | -1.596 |
Token | don |
Token ID | 836 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
THING | +3.342 |
Cerberus | +3.015 |
copyrighted | +3.010 |
inosaur | +2.991 |
IMAGES | +2.989 |
Neg logit contributions | |
nesota | -3.659 |
olate | -3.329 |
vale | -3.212 |
lication | -3.190 |
jected | -3.151 |
Token | � |
Token ID | 447 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
THING | +3.983 |
inosaur | +3.569 |
IMAGES | +3.540 |
Cerberus | +3.533 |
copyrighted | +3.511 |
Neg logit contributions | |
nesota | -3.784 |
olate | -3.490 |
lication | -3.370 |
jected | -3.352 |
vale | -3.328 |
Token | � |
Token ID | 247 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
THING | +5.721 |
inosaur | +5.060 |
IMAGES | +5.053 |
Cerberus | +4.978 |
copyrighted | +4.961 |
Neg logit contributions | |
nesota | -5.879 |
olate | -5.305 |
jected | -5.282 |
vale | -5.253 |
lication | -5.228 |
Token | t |
Token ID | 83 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
THING | +1.951 |
inosaur | +1.722 |
Cerberus | +1.719 |
IMAGES | +1.693 |
copyrighted | +1.657 |
Neg logit contributions | |
nesota | -2.862 |
olate | -2.638 |
vale | -2.563 |
jected | -2.551 |
lication | -2.537 |
Token | even |
Token ID | 772 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
THING | +3.524 |
Cerberus | +3.249 |
IMAGES | +3.238 |
copyrighted | +3.216 |
inosaur | +3.198 |
Neg logit contributions | |
nesota | -3.451 |
olate | -3.128 |
jected | -3.057 |
lication | -3.013 |
vale | -3.009 |
Token | have |
Token ID | 423 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
THING | +12.679 |
kidding | +12.047 |
copyrighted | +11.969 |
IMAGES | +11.827 |
Cerberus | +11.620 |
Neg logit contributions | |
nesota | -12.554 |
olate | -11.455 |
jected | -11.128 |
lication | -11.035 |
vale | -10.973 |
Token | words |
Token ID | 2456 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
THING | +4.955 |
Cerberus | +4.493 |
IMAGES | +4.442 |
copyrighted | +4.398 |
inosaur | +4.389 |
Neg logit contributions | |
nesota | -6.415 |
olate | -6.081 |
vale | -5.926 |
jected | -5.782 |
lication | -5.771 |
Token | for |
Token ID | 329 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
THING | +5.527 |
Cerberus | +4.834 |
inosaur | +4.830 |
copyrighted | +4.806 |
IMAGES | +4.685 |
Neg logit contributions | |
nesota | -6.992 |
olate | -6.641 |
vale | -6.457 |
jected | -6.291 |
lication | -6.281 |
Token | this |
Token ID | 428 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
THING | +1.942 |
Cerberus | +1.733 |
IMAGES | +1.677 |
inosaur | +1.665 |
copyrighted | +1.656 |
Neg logit contributions | |
nesota | -3.127 |
olate | -2.944 |
vale | -2.867 |
jected | -2.830 |
lication | -2.817 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
THING | +2.077 |
Cerberus | +1.863 |
inosaur | +1.837 |
IMAGES | +1.824 |
copyrighted | +1.817 |
Neg logit contributions | |
nesota | -2.289 |
olate | -2.152 |
vale | -2.054 |
lication | -2.044 |
jected | -2.034 |
Token | that |
Token ID | 326 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
nesota | +0.934 |
olate | +0.872 |
vale | +0.842 |
jected | +0.828 |
lication | +0.825 |
Neg logit contributions | |
THING | -0.898 |
Cerberus | -0.820 |
IMAGES | -0.817 |
inosaur | -0.809 |
copyrighted | -0.792 |
Token | don |
Token ID | 836 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
nesota | +5.453 |
olate | +5.190 |
vale | +4.999 |
onset | +4.912 |
jected | +4.903 |
Neg logit contributions | |
THING | -4.392 |
inosaur | -3.966 |
IMAGES | -3.949 |
Cerberus | -3.929 |
ModLoader | -3.833 |
Token | � |
Token ID | 447 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
THING | +0.074 |
Cerberus | +0.068 |
IMAGES | +0.068 |
inosaur | +0.067 |
copyrighted | +0.066 |
Neg logit contributions | |
nesota | -0.056 |
olate | -0.051 |
vale | -0.049 |
jected | -0.048 |
lication | -0.048 |
Token | � |
Token ID | 247 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
THING | +2.472 |
IMAGES | +2.221 |
Cerberus | +2.216 |
inosaur | +2.211 |
copyrighted | +2.167 |
Neg logit contributions | |
nesota | -2.149 |
olate | -1.979 |
vale | -1.925 |
jected | -1.901 |
lication | -1.890 |
Token | t |
Token ID | 83 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
THING | +0.403 |
Cerberus | +0.352 |
inosaur | +0.352 |
IMAGES | +0.351 |
copyrighted | +0.337 |
Neg logit contributions | |
nesota | -0.631 |
olate | -0.590 |
vale | -0.576 |
jected | -0.571 |
lication | -0.570 |
Token | even |
Token ID | 772 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
THING | +2.278 |
IMAGES | +2.082 |
Cerberus | +2.072 |
inosaur | +2.042 |
copyrighted | +2.038 |
Neg logit contributions | |
nesota | -2.340 |
olate | -2.144 |
lication | -2.097 |
jected | -2.069 |
vale | -2.052 |
Token | make |
Token ID | 787 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
THING | +12.980 |
IMAGES | +12.036 |
copyrighted | +11.958 |
Cerberus | +11.467 |
except | +11.209 |
Neg logit contributions | |
nesota | -12.497 |
lication | -11.655 |
olate | -11.245 |
jected | -11.153 |
vale | -10.777 |
Token | sense |
Token ID | 2565 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
THING | +2.992 |
Cerberus | +2.816 |
IMAGES | +2.789 |
inosaur | +2.758 |
copyrighted | +2.753 |
Neg logit contributions | |
nesota | -1.669 |
olate | -1.497 |
vale | -1.425 |
lication | -1.390 |
jected | -1.366 |
Token | when |
Token ID | 618 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
THING | +0.791 |
Cerberus | +0.716 |
IMAGES | +0.716 |
inosaur | +0.709 |
copyrighted | +0.697 |
Neg logit contributions | |
nesota | -0.811 |
olate | -0.753 |
vale | -0.729 |
lication | -0.718 |
jected | -0.717 |
Token | taken |
Token ID | 2077 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
THING | +0.079 |
Cerberus | +0.071 |
IMAGES | +0.070 |
inosaur | +0.069 |
copyrighted | +0.068 |
Neg logit contributions | |
nesota | -0.109 |
olate | -0.102 |
vale | -0.099 |
lication | -0.098 |
jected | -0.098 |
Token | at |
Token ID | 379 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
THING | +0.672 |
Cerberus | +0.601 |
IMAGES | +0.599 |
inosaur | +0.588 |
copyrighted | +0.576 |
Neg logit contributions | |
nesota | -1.047 |
olate | -0.983 |
vale | -0.961 |
lication | -0.947 |
jected | -0.943 |
Token | we |
Token ID | 356 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
THING | +2.074 |
Cerberus | +1.901 |
IMAGES | +1.866 |
copyrighted | +1.846 |
inosaur | +1.813 |
Neg logit contributions | |
nesota | -2.628 |
olate | -2.432 |
vale | -2.372 |
lication | -2.338 |
jected | -2.324 |
Token | don |
Token ID | 836 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
nesota | +0.586 |
olate | +0.545 |
vale | +0.526 |
jected | +0.517 |
lication | +0.516 |
Neg logit contributions | |
THING | -0.567 |
Cerberus | -0.517 |
IMAGES | -0.516 |
inosaur | -0.511 |
copyrighted | -0.503 |
Token | � |
Token ID | 447 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
THING | +3.671 |
inosaur | +3.269 |
Cerberus | +3.267 |
IMAGES | +3.263 |
copyrighted | +3.225 |
Neg logit contributions | |
nesota | -3.805 |
olate | -3.522 |
lication | -3.400 |
jected | -3.397 |
vale | -3.378 |
Token | � |
Token ID | 247 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
THING | +3.578 |
IMAGES | +3.192 |
inosaur | +3.178 |
Cerberus | +3.178 |
copyrighted | +3.131 |
Neg logit contributions | |
nesota | -3.345 |
olate | -3.058 |
vale | -3.005 |
jected | -2.962 |
lication | -2.927 |
Token | t |
Token ID | 83 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
THING | +1.381 |
Cerberus | +1.206 |
inosaur | +1.187 |
IMAGES | +1.182 |
copyrighted | +1.146 |
Neg logit contributions | |
nesota | -2.317 |
olate | -2.143 |
vale | -2.090 |
jected | -2.073 |
lication | -2.072 |
Token | even |
Token ID | 772 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
THING | +2.720 |
Cerberus | +2.529 |
IMAGES | +2.523 |
copyrighted | +2.486 |
inosaur | +2.448 |
Neg logit contributions | |
nesota | -2.264 |
olate | -2.047 |
lication | -1.993 |
jected | -1.985 |
vale | -1.972 |
Token | do |
Token ID | 466 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
THING | +12.671 |
copyrighted | +11.893 |
IMAGES | +11.817 |
Cerberus | +11.568 |
kidding | +11.537 |
Neg logit contributions | |
nesota | -12.160 |
lication | -10.920 |
olate | -10.814 |
jected | -10.806 |
vale | -10.586 |
Token | basic |
Token ID | 4096 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
THING | +4.285 |
Cerberus | +3.772 |
IMAGES | +3.760 |
copyrighted | +3.681 |
inosaur | +3.618 |
Neg logit contributions | |
nesota | -6.340 |
olate | -5.908 |
vale | -5.793 |
lication | -5.707 |
jected | -5.702 |
Token | due |
Token ID | 2233 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
nesota | +2.033 |
olate | +1.897 |
vale | +1.825 |
jected | +1.792 |
lication | +1.784 |
Neg logit contributions | |
THING | -2.174 |
Cerberus | -1.996 |
IMAGES | -1.994 |
inosaur | -1.977 |
copyrighted | -1.926 |
Token | diligence |
Token ID | 34136 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
nesota | +3.538 |
olate | +3.335 |
vale | +3.186 |
jected | +3.111 |
lication | +3.102 |
Neg logit contributions | |
THING | -4.591 |
IMAGES | -4.269 |
Cerberus | -4.243 |
inosaur | -4.194 |
copyrighted | -4.106 |
Token | in |
Token ID | 287 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
THING | +1.537 |
IMAGES | +1.380 |
Cerberus | +1.374 |
inosaur | +1.339 |
copyrighted | +1.325 |
Neg logit contributions | |
nesota | -2.067 |
olate | -1.927 |
vale | -1.874 |
jected | -1.861 |
lication | -1.836 |
Token | they |
Token ID | 484 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
nesota | +5.803 |
olate | +5.509 |
vale | +5.332 |
jected | +5.272 |
onset | +5.249 |
Neg logit contributions | |
THING | -4.776 |
inosaur | -4.346 |
IMAGES | -4.326 |
Cerberus | -4.201 |
ModLoader | -4.130 |
Token | don |
Token ID | 836 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
nesota | +1.861 |
olate | +1.737 |
vale | +1.675 |
jected | +1.647 |
lication | +1.642 |
Neg logit contributions | |
THING | -1.833 |
Cerberus | -1.679 |
IMAGES | -1.677 |
inosaur | -1.656 |
copyrighted | -1.623 |
Token | � |
Token ID | 447 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
THING | +0.647 |
Cerberus | +0.598 |
IMAGES | +0.597 |
inosaur | +0.593 |
copyrighted | +0.583 |
Neg logit contributions | |
nesota | -0.435 |
olate | -0.397 |
vale | -0.377 |
lication | -0.373 |
jected | -0.372 |
Token | � |
Token ID | 247 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
nesota | +0.532 |
olate | +0.497 |
vale | +0.480 |
jected | +0.472 |
lication | +0.471 |
Neg logit contributions | |
THING | -0.547 |
Cerberus | -0.498 |
IMAGES | -0.497 |
inosaur | -0.491 |
copyrighted | -0.482 |
Token | t |
Token ID | 83 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
THING | +2.431 |
Cerberus | +2.168 |
IMAGES | +2.166 |
inosaur | +2.150 |
copyrighted | +2.123 |
Neg logit contributions | |
nesota | -2.517 |
olate | -2.311 |
vale | -2.230 |
jected | -2.225 |
lication | -2.197 |
Token | even |
Token ID | 772 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
THING | +1.654 |
IMAGES | +1.545 |
Cerberus | +1.541 |
copyrighted | +1.518 |
inosaur | +1.505 |
Neg logit contributions | |
nesota | -1.438 |
olate | -1.321 |
jected | -1.270 |
lication | -1.262 |
vale | -1.253 |
Token | qualify |
Token ID | 12780 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
THING | +12.880 |
copyrighted | +12.531 |
IMAGES | +12.340 |
Cerberus | +12.202 |
except | +12.124 |
Neg logit contributions | |
nesota | -11.139 |
lication | -10.070 |
jected | -10.042 |
olate | -9.973 |
vale | -9.483 |
Token | as |
Token ID | 355 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
THING | +1.229 |
Cerberus | +1.092 |
IMAGES | +1.073 |
inosaur | +1.068 |
copyrighted | +1.051 |
Neg logit contributions | |
nesota | -1.940 |
olate | -1.829 |
vale | -1.773 |
jected | -1.749 |
lication | -1.742 |
Token | pork |
Token ID | 18128 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
THING | +1.627 |
Cerberus | +1.472 |
IMAGES | +1.449 |
inosaur | +1.418 |
copyrighted | +1.415 |
Neg logit contributions | |
nesota | -2.220 |
olate | -2.092 |
vale | -2.033 |
lication | -1.992 |
jected | -1.991 |
Token | . |
Token ID | 13 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
nesota | +0.171 |
olate | +0.160 |
vale | +0.153 |
jected | +0.151 |
lication | +0.150 |
Neg logit contributions | |
THING | -0.169 |
Cerberus | -0.155 |
IMAGES | -0.153 |
inosaur | -0.151 |
copyrighted | -0.149 |
Token | Lich |
Token ID | 35171 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
nesota | +0.185 |
olate | +0.173 |
vale | +0.166 |
jected | +0.164 |
lication | +0.164 |
Neg logit contributions | |
THING | -0.176 |
Cerberus | -0.161 |
IMAGES | -0.160 |
inosaur | -0.158 |
copyrighted | -0.154 |
Token | I |
Token ID | 314 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
THING | +2.787 |
Cerberus | +2.551 |
IMAGES | +2.478 |
copyrighted | +2.434 |
inosaur | +2.429 |
Neg logit contributions | |
nesota | -4.159 |
olate | -3.944 |
vale | -3.850 |
lication | -3.788 |
jected | -3.754 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
THING | +1.195 |
Cerberus | +1.082 |
IMAGES | +1.077 |
inosaur | +1.064 |
copyrighted | +1.061 |
Neg logit contributions | |
nesota | -1.510 |
olate | -1.398 |
vale | -1.365 |
lication | -1.339 |
jected | -1.321 |
Token | � |
Token ID | 447 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
THING | +0.473 |
Cerberus | +0.438 |
IMAGES | +0.437 |
inosaur | +0.434 |
copyrighted | +0.427 |
Neg logit contributions | |
nesota | -0.320 |
olate | -0.292 |
vale | -0.278 |
lication | -0.274 |
jected | -0.273 |
Token | � |
Token ID | 247 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
THING | +0.029 |
IMAGES | +0.026 |
Cerberus | +0.026 |
inosaur | +0.026 |
copyrighted | +0.025 |
Neg logit contributions | |
nesota | -0.028 |
olate | -0.026 |
vale | -0.025 |
jected | -0.025 |
lication | -0.025 |
Token | t |
Token ID | 83 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
THING | +1.351 |
inosaur | +1.204 |
IMAGES | +1.202 |
Cerberus | +1.195 |
copyrighted | +1.173 |
Neg logit contributions | |
nesota | -1.535 |
olate | -1.425 |
vale | -1.377 |
jected | -1.356 |
lication | -1.352 |
Token | even |
Token ID | 772 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
THING | +1.629 |
IMAGES | +1.512 |
Cerberus | +1.501 |
inosaur | +1.481 |
copyrighted | +1.477 |
Neg logit contributions | |
nesota | -1.485 |
olate | -1.362 |
vale | -1.312 |
jected | -1.299 |
lication | -1.295 |
Token | get |
Token ID | 651 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
THING | +12.191 |
IMAGES | +11.788 |
copyrighted | +11.529 |
kidding | +11.492 |
Cerberus | +11.328 |
Neg logit contributions | |
nesota | -12.078 |
olate | -11.023 |
lication | -10.749 |
vale | -10.718 |
jected | -10.579 |
Token | the |
Token ID | 262 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
THING | +1.584 |
Cerberus | +1.441 |
IMAGES | +1.425 |
inosaur | +1.405 |
copyrighted | +1.384 |
Neg logit contributions | |
nesota | -1.983 |
olate | -1.863 |
vale | -1.823 |
lication | -1.774 |
jected | -1.763 |
Token | one |
Token ID | 530 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
THING | +2.467 |
Cerberus | +2.291 |
IMAGES | +2.251 |
inosaur | +2.225 |
copyrighted | +2.209 |
Neg logit contributions | |
nesota | -2.338 |
olate | -2.231 |
vale | -2.148 |
lication | -2.082 |
jected | -2.046 |
Token | thing |
Token ID | 1517 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
THING | +4.093 |
Cerberus | +3.736 |
IMAGES | +3.681 |
inosaur | +3.634 |
copyrighted | +3.614 |
Neg logit contributions | |
nesota | -4.300 |
olate | -4.105 |
vale | -3.982 |
lication | -3.838 |
jected | -3.775 |
Token | I |
Token ID | 314 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
THING | +0.209 |
Cerberus | +0.190 |
IMAGES | +0.189 |
inosaur | +0.187 |
copyrighted | +0.184 |
Neg logit contributions | |
nesota | -0.237 |
olate | -0.222 |
vale | -0.216 |
jected | -0.211 |
lication | -0.211 |
Token | I |
Token ID | 314 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
nesota | +4.044 |
olate | +3.822 |
vale | +3.690 |
jected | +3.621 |
lication | +3.601 |
Neg logit contributions | |
THING | -3.696 |
IMAGES | -3.368 |
Cerberus | -3.355 |
inosaur | -3.320 |
copyrighted | -3.231 |
Token | � |
Token ID | 447 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
nesota | +1.529 |
olate | +1.438 |
vale | +1.387 |
jected | +1.366 |
lication | +1.359 |
Neg logit contributions | |
THING | -1.382 |
Cerberus | -1.257 |
IMAGES | -1.256 |
inosaur | -1.240 |
copyrighted | -1.207 |
Token | � |
Token ID | 247 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
nesota | +0.871 |
olate | +0.805 |
vale | +0.773 |
jected | +0.757 |
lication | +0.753 |
Neg logit contributions | |
THING | -1.115 |
Cerberus | -1.028 |
IMAGES | -1.027 |
inosaur | -1.016 |
copyrighted | -0.997 |
Token | m |
Token ID | 76 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
THING | +0.165 |
Cerberus | +0.151 |
IMAGES | +0.151 |
inosaur | +0.150 |
copyrighted | +0.147 |
Neg logit contributions | |
nesota | -0.134 |
olate | -0.123 |
vale | -0.118 |
lication | -0.115 |
jected | -0.115 |
Token | not |
Token ID | 407 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
nesota | +2.471 |
olate | +2.358 |
vale | +2.267 |
jected | +2.256 |
lication | +2.219 |
Neg logit contributions | |
THING | -1.950 |
IMAGES | -1.765 |
Cerberus | -1.745 |
inosaur | -1.743 |
ModLoader | -1.688 |
Token | even |
Token ID | 772 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
THING | +1.626 |
Cerberus | +1.459 |
IMAGES | +1.431 |
inosaur | +1.425 |
copyrighted | +1.394 |
Neg logit contributions | |
nesota | -2.771 |
olate | -2.609 |
vale | -2.539 |
lication | -2.504 |
jected | -2.497 |
Token | going |
Token ID | 1016 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
kidding | +9.031 |
THING | +8.977 |
Cerberus | +8.425 |
copyrighted | +8.280 |
IMAGES | +7.851 |
Neg logit contributions | |
nesota | -16.355 |
olate | -15.357 |
vale | -14.891 |
lication | -14.620 |
imester | -14.096 |
Token | to |
Token ID | 284 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
THING | +4.281 |
Cerberus | +3.934 |
inosaur | +3.904 |
IMAGES | +3.873 |
copyrighted | +3.775 |
Neg logit contributions | |
nesota | -4.850 |
olate | -4.490 |
vale | -4.399 |
lication | -4.343 |
jected | -4.279 |
Token | attempt |
Token ID | 2230 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
THING | +3.127 |
Cerberus | +2.899 |
IMAGES | +2.895 |
inosaur | +2.869 |
copyrighted | +2.850 |
Neg logit contributions | |
nesota | -2.633 |
olate | -2.411 |
lication | -2.334 |
vale | -2.306 |
jected | -2.298 |
Token | to |
Token ID | 284 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
THING | +3.274 |
Cerberus | +2.972 |
inosaur | +2.942 |
IMAGES | +2.904 |
copyrighted | +2.876 |
Neg logit contributions | |
nesota | -3.917 |
olate | -3.582 |
vale | -3.508 |
jected | -3.416 |
lication | -3.400 |
Token | do |
Token ID | 466 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
THING | +1.001 |
IMAGES | +0.929 |
Cerberus | +0.928 |
inosaur | +0.924 |
copyrighted | +0.917 |
Neg logit contributions | |
nesota | -0.713 |
olate | -0.646 |
vale | -0.625 |
lication | -0.618 |
jected | -0.612 |
Token | I |
Token ID | 40 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
nesota | +3.969 |
olate | +3.729 |
vale | +3.613 |
jected | +3.531 |
lication | +3.514 |
Neg logit contributions | |
THING | -4.257 |
IMAGES | -3.955 |
Cerberus | -3.948 |
inosaur | -3.862 |
copyrighted | -3.802 |
Token | don |
Token ID | 836 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
nesota | +0.903 |
olate | +0.839 |
vale | +0.810 |
lication | +0.794 |
jected | +0.794 |
Neg logit contributions | |
THING | -0.861 |
Cerberus | -0.784 |
IMAGES | -0.782 |
inosaur | -0.775 |
copyrighted | -0.761 |
Token | � |
Token ID | 447 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
THING | +1.996 |
Cerberus | +1.814 |
inosaur | +1.812 |
IMAGES | +1.810 |
copyrighted | +1.777 |
Neg logit contributions | |
nesota | -1.625 |
olate | -1.497 |
vale | -1.421 |
lication | -1.420 |
jected | -1.417 |
Token | � |
Token ID | 247 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
THING | +4.400 |
IMAGES | +3.918 |
Cerberus | +3.895 |
inosaur | +3.854 |
copyrighted | +3.823 |
Neg logit contributions | |
nesota | -4.258 |
olate | -3.888 |
vale | -3.827 |
lication | -3.780 |
jected | -3.771 |
Token | t |
Token ID | 83 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
THING | +0.860 |
Cerberus | +0.757 |
inosaur | +0.755 |
IMAGES | +0.748 |
copyrighted | +0.728 |
Neg logit contributions | |
nesota | -1.306 |
olate | -1.217 |
vale | -1.182 |
jected | -1.172 |
lication | -1.170 |
Token | even |
Token ID | 772 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
THING | +1.738 |
IMAGES | +1.589 |
Cerberus | +1.582 |
inosaur | +1.580 |
copyrighted | +1.558 |
Neg logit contributions | |
nesota | -1.762 |
olate | -1.623 |
vale | -1.555 |
jected | -1.551 |
lication | -1.538 |
Token | remember |
Token ID | 3505 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
THING | +12.141 |
kidding | +11.239 |
copyrighted | +11.184 |
IMAGES | +11.177 |
inosaur | +11.003 |
Neg logit contributions | |
nesota | -12.141 |
olate | -11.196 |
jected | -10.574 |
vale | -10.483 |
lication | -10.415 |
Token | when |
Token ID | 618 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
THING | +2.499 |
Cerberus | +2.219 |
inosaur | +2.176 |
IMAGES | +2.172 |
copyrighted | +2.126 |
Neg logit contributions | |
nesota | -3.733 |
olate | -3.518 |
vale | -3.401 |
jected | -3.358 |
lication | -3.337 |
Token | til |
Token ID | 21502 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
nesota | +0.024 |
olate | +0.022 |
vale | +0.022 |
jected | +0.021 |
lication | +0.021 |
Neg logit contributions | |
THING | -0.023 |
Cerberus | -0.020 |
IMAGES | -0.020 |
inosaur | -0.020 |
copyrighted | -0.020 |
Token | ap |
Token ID | 499 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
nesota | +1.527 |
olate | +1.412 |
vale | +1.349 |
jected | +1.321 |
lication | +1.315 |
Neg logit contributions | |
THING | -2.075 |
Cerberus | -1.928 |
IMAGES | -1.919 |
inosaur | -1.912 |
copyrighted | -1.863 |
Token | ia |
Token ID | 544 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
nesota | +3.100 |
olate | +2.861 |
vale | +2.717 |
jected | +2.667 |
lication | +2.663 |
Neg logit contributions | |
THING | -4.346 |
Cerberus | -4.023 |
IMAGES | -3.988 |
inosaur | -3.929 |
copyrighted | -3.876 |
Token | forget |
Token ID | 6044 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
THING | +2.563 |
IMAGES | +2.412 |
Cerberus | +2.407 |
copyrighted | +2.352 |
inosaur | +2.329 |
Neg logit contributions | |
nesota | -2.270 |
olate | -2.057 |
lication | -2.025 |
jected | -2.007 |
vale | -1.985 |
Token | that |
Token ID | 326 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
THING | +5.101 |
Cerberus | +4.571 |
copyrighted | +4.534 |
IMAGES | +4.526 |
inosaur | +4.444 |
Neg logit contributions | |
nesota | -6.526 |
olate | -5.919 |
vale | -5.784 |
jected | -5.764 |
lication | -5.714 |
Token | we |
Token ID | 356 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
nesota | +1.229 |
olate | +1.159 |
vale | +1.123 |
jected | +1.106 |
lication | +1.103 |
Neg logit contributions | |
THING | -0.895 |
Cerberus | -0.804 |
IMAGES | -0.803 |
inosaur | -0.790 |
copyrighted | -0.772 |
Token | do |
Token ID | 466 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
THING | +1.226 |
IMAGES | +1.117 |
Cerberus | +1.116 |
copyrighted | +1.102 |
inosaur | +1.097 |
Neg logit contributions | |
nesota | -1.302 |
olate | -1.204 |
vale | -1.165 |
jected | -1.151 |
lication | -1.140 |
Token | not |
Token ID | 407 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
THING | +2.034 |
Cerberus | +1.856 |
IMAGES | +1.850 |
copyrighted | +1.818 |
inosaur | +1.806 |
Neg logit contributions | |
nesota | -1.964 |
olate | -1.803 |
vale | -1.736 |
jected | -1.733 |
lication | -1.711 |
Token | even |
Token ID | 772 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
THING | +4.347 |
IMAGES | +4.119 |
copyrighted | +4.096 |
Cerberus | +4.026 |
inosaur | +3.938 |
Neg logit contributions | |
nesota | -4.396 |
olate | -3.974 |
jected | -3.939 |
lication | -3.821 |
vale | -3.786 |
Token | know |
Token ID | 760 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
copyrighted | +10.395 |
THING | +10.385 |
IMAGES | +10.238 |
except | +9.915 |
kidding | +9.778 |
Neg logit contributions | |
nesota | -12.855 |
jected | -11.851 |
olate | -11.528 |
lication | -11.373 |
vale | -11.139 |
Token | the |
Token ID | 262 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
THING | +5.870 |
copyrighted | +5.096 |
IMAGES | +5.017 |
Cerberus | +4.970 |
Hirosh | +4.805 |
Neg logit contributions | |
nesota | -10.612 |
olate | -9.905 |
vale | -9.626 |
jected | -9.571 |
lication | -9.488 |
Token | exact |
Token ID | 2748 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
THING | +2.157 |
Cerberus | +1.964 |
IMAGES | +1.959 |
copyrighted | +1.941 |
inosaur | +1.914 |
Neg logit contributions | |
nesota | -2.266 |
olate | -2.125 |
vale | -2.043 |
lication | -2.012 |
jected | -2.004 |
Token | birthday |
Token ID | 10955 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
THING | +8.588 |
copyrighted | +8.017 |
Cerberus | +7.907 |
IMAGES | +7.707 |
inosaur | +7.622 |
Neg logit contributions | |
nesota | -7.826 |
olate | -7.179 |
lication | -6.943 |
vale | -6.917 |
jected | -6.790 |
Token | of |
Token ID | 286 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
nesota | +2.034 |
olate | +1.928 |
vale | +1.876 |
jected | +1.848 |
lication | +1.843 |
Neg logit contributions | |
THING | -1.212 |
Cerberus | -1.075 |
IMAGES | -1.073 |
inosaur | -1.056 |
copyrighted | -1.020 |
Token | it |
Token ID | 340 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
THING | +0.106 |
Cerberus | +0.094 |
IMAGES | +0.094 |
inosaur | +0.092 |
copyrighted | +0.089 |
Neg logit contributions | |
nesota | -0.178 |
olate | -0.169 |
vale | -0.164 |
jected | -0.162 |
lication | -0.162 |
Token | � |
Token ID | 447 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
THING | +0.030 |
IMAGES | +0.027 |
Cerberus | +0.027 |
inosaur | +0.027 |
copyrighted | +0.027 |
Neg logit contributions | |
nesota | -0.030 |
olate | -0.028 |
vale | -0.027 |
lication | -0.026 |
jected | -0.026 |
Token | � |
Token ID | 247 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
THING | +3.851 |
IMAGES | +3.487 |
Cerberus | +3.459 |
inosaur | +3.380 |
copyrighted | +3.378 |
Neg logit contributions | |
nesota | -3.660 |
olate | -3.406 |
vale | -3.321 |
jected | -3.260 |
lication | -3.219 |
Token | s |
Token ID | 82 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
THING | +0.946 |
IMAGES | +0.857 |
Cerberus | +0.852 |
inosaur | +0.849 |
copyrighted | +0.827 |
Neg logit contributions | |
nesota | -1.129 |
olate | -1.059 |
vale | -1.022 |
lication | -1.005 |
jected | -1.001 |
Token | not |
Token ID | 407 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
THING | +0.052 |
Cerberus | +0.047 |
IMAGES | +0.047 |
inosaur | +0.047 |
copyrighted | +0.045 |
Neg logit contributions | |
nesota | -0.068 |
olate | -0.064 |
vale | -0.062 |
jected | -0.061 |
lication | -0.061 |
Token | even |
Token ID | 772 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
THING | +1.204 |
Cerberus | +1.082 |
IMAGES | +1.074 |
inosaur | +1.062 |
copyrighted | +1.041 |
Neg logit contributions | |
nesota | -1.751 |
olate | -1.653 |
vale | -1.604 |
jected | -1.581 |
lication | -1.579 |
Token | wild |
Token ID | 4295 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
THING | +9.811 |
Cerberus | +8.997 |
copyrighted | +8.959 |
IMAGES | +8.546 |
kidding | +8.516 |
Neg logit contributions | |
nesota | -13.361 |
olate | -12.889 |
vale | -12.403 |
lication | -12.389 |
jected | -12.200 |
Token | to |
Token ID | 284 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
THING | +3.930 |
Cerberus | +3.499 |
inosaur | +3.406 |
copyrighted | +3.354 |
IMAGES | +3.339 |
Neg logit contributions | |
nesota | -4.977 |
olate | -4.682 |
jected | -4.488 |
lication | -4.445 |
vale | -4.434 |
Token | make |
Token ID | 787 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
nesota | +1.109 |
olate | +1.028 |
vale | +0.982 |
jected | +0.967 |
lication | +0.966 |
Neg logit contributions | |
THING | -1.314 |
Cerberus | -1.215 |
IMAGES | -1.207 |
inosaur | -1.193 |
copyrighted | -1.178 |
Token | a |
Token ID | 257 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
nesota | +0.153 |
olate | +0.145 |
vale | +0.141 |
jected | +0.139 |
lication | +0.138 |
Neg logit contributions | |
THING | -0.092 |
Cerberus | -0.082 |
IMAGES | -0.081 |
inosaur | -0.080 |
copyrighted | -0.078 |
Token | statement |
Token ID | 2643 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
THING | +2.146 |
Cerberus | +2.024 |
copyrighted | +1.959 |
IMAGES | +1.955 |
inosaur | +1.927 |
Neg logit contributions | |
nesota | -1.720 |
olate | -1.591 |
vale | -1.538 |
lication | -1.480 |
jected | -1.458 |
Token | policies |
Token ID | 4788 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
nesota | +0.335 |
olate | +0.316 |
vale | +0.307 |
jected | +0.302 |
lication | +0.301 |
Neg logit contributions | |
THING | -0.237 |
Cerberus | -0.212 |
IMAGES | -0.212 |
inosaur | -0.209 |
copyrighted | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
nesota | +0.058 |
olate | +0.054 |
vale | +0.052 |
jected | +0.051 |
lication | +0.050 |
Neg logit contributions | |
THING | -0.058 |
Cerberus | -0.054 |
IMAGES | -0.053 |
inosaur | -0.052 |
copyrighted | -0.052 |
Token | That |
Token ID | 1320 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
nesota | +0.550 |
olate | +0.514 |
vale | +0.495 |
jected | +0.488 |
lication | +0.486 |
Neg logit contributions | |
THING | -0.546 |
Cerberus | -0.500 |
IMAGES | -0.499 |
inosaur | -0.491 |
copyrighted | -0.480 |
Token | is |
Token ID | 318 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
nesota | +3.621 |
olate | +3.381 |
vale | +3.265 |
jected | +3.223 |
lication | +3.211 |
Neg logit contributions | |
THING | -3.227 |
IMAGES | -2.951 |
Cerberus | -2.938 |
inosaur | -2.907 |
copyrighted | -2.820 |
Token | not |
Token ID | 407 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
nesota | +0.156 |
olate | +0.147 |
vale | +0.142 |
jected | +0.140 |
lication | +0.140 |
Neg logit contributions | |
THING | -0.123 |
Cerberus | -0.111 |
IMAGES | -0.110 |
inosaur | -0.109 |
copyrighted | -0.106 |
Token | even |
Token ID | 772 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
THING | +1.685 |
Cerberus | +1.528 |
IMAGES | +1.492 |
inosaur | +1.484 |
copyrighted | +1.469 |
Neg logit contributions | |
nesota | -2.374 |
olate | -2.226 |
vale | -2.168 |
lication | -2.149 |
jected | -2.134 |
Token | the |
Token ID | 262 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
THING | +9.831 |
Cerberus | +8.761 |
copyrighted | +8.518 |
kidding | +8.407 |
inosaur | +8.302 |
Neg logit contributions | |
nesota | -13.258 |
olate | -12.635 |
vale | -12.338 |
lication | -12.229 |
jected | -11.984 |
Token | worst |
Token ID | 5290 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
THING | +2.832 |
Cerberus | +2.593 |
copyrighted | +2.558 |
IMAGES | +2.556 |
inosaur | +2.512 |
Neg logit contributions | |
nesota | -2.203 |
olate | -2.014 |
vale | -1.967 |
lication | -1.908 |
jected | -1.886 |
Token | of |
Token ID | 286 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
THING | +1.795 |
Cerberus | +1.586 |
IMAGES | +1.551 |
inosaur | +1.549 |
copyrighted | +1.524 |
Neg logit contributions | |
nesota | -2.395 |
olate | -2.291 |
vale | -2.193 |
jected | -2.166 |
lication | -2.163 |
Token | it |
Token ID | 340 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
THING | +4.267 |
Cerberus | +3.846 |
IMAGES | +3.649 |
copyrighted | +3.644 |
inosaur | +3.592 |
Neg logit contributions | |
nesota | -6.264 |
olate | -6.011 |
vale | -5.770 |
lication | -5.714 |
jected | -5.689 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
THING | +2.480 |
Cerberus | +2.246 |
IMAGES | +2.222 |
inosaur | +2.195 |
copyrighted | +2.176 |
Neg logit contributions | |
nesota | -2.839 |
olate | -2.675 |
vale | -2.581 |
jected | -2.560 |
lication | -2.537 |
Token | of |
Token ID | 286 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
nesota | +3.198 |
olate | +3.028 |
vale | +2.938 |
jected | +2.901 |
lication | +2.886 |
Neg logit contributions | |
THING | -2.132 |
Cerberus | -1.899 |
IMAGES | -1.893 |
inosaur | -1.875 |
copyrighted | -1.811 |
Token | the |
Token ID | 262 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
THING | +2.040 |
Cerberus | +1.838 |
IMAGES | +1.738 |
copyrighted | +1.715 |
inosaur | +1.681 |
Neg logit contributions | |
nesota | -4.188 |
olate | -3.890 |
vale | -3.833 |
lication | -3.780 |
jected | -3.736 |
Token | crisis |
Token ID | 4902 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
nesota | +0.551 |
olate | +0.513 |
vale | +0.495 |
jected | +0.485 |
lication | +0.485 |
Neg logit contributions | |
THING | -0.551 |
Cerberus | -0.505 |
IMAGES | -0.503 |
inosaur | -0.495 |
copyrighted | -0.487 |
Token | has |
Token ID | 468 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
THING | +1.559 |
IMAGES | +1.418 |
Cerberus | +1.414 |
inosaur | +1.364 |
copyrighted | +1.350 |
Neg logit contributions | |
nesota | -2.206 |
olate | -2.075 |
vale | -2.024 |
lication | -1.985 |
jected | -1.975 |
Token | not |
Token ID | 407 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
nesota | +0.402 |
olate | +0.379 |
vale | +0.369 |
lication | +0.362 |
jected | +0.359 |
Neg logit contributions | |
THING | -0.310 |
Cerberus | -0.279 |
IMAGES | -0.277 |
inosaur | -0.272 |
copyrighted | -0.268 |
Token | even |
Token ID | 772 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
THING | +1.799 |
Cerberus | +1.574 |
IMAGES | +1.549 |
copyrighted | +1.530 |
inosaur | +1.511 |
Neg logit contributions | |
nesota | -3.473 |
olate | -3.312 |
vale | -3.234 |
lication | -3.175 |
jected | -3.144 |
Token | started |
Token ID | 2067 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
THING | +7.781 |
copyrighted | +6.796 |
Cerberus | +6.704 |
IMAGES | +6.344 |
inosaur | +6.231 |
Neg logit contributions | |
nesota | -14.946 |
olate | -14.615 |
vale | -14.429 |
lication | -13.987 |
jected | -13.402 |
Token | to |
Token ID | 284 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
nesota | +1.483 |
olate | +1.393 |
vale | +1.347 |
jected | +1.325 |
lication | +1.320 |
Neg logit contributions | |
THING | -1.255 |
Cerberus | -1.138 |
IMAGES | -1.136 |
inosaur | -1.121 |
copyrighted | -1.093 |
Token | be |
Token ID | 307 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
nesota | +1.041 |
olate | +0.950 |
vale | +0.910 |
lication | +0.891 |
jected | +0.886 |
Neg logit contributions | |
THING | -1.575 |
Cerberus | -1.463 |
IMAGES | -1.457 |
inosaur | -1.438 |
copyrighted | -1.419 |
Token | resolved |
Token ID | 12939 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
THING | +2.215 |
Cerberus | +2.016 |
inosaur | +1.956 |
IMAGES | +1.951 |
copyrighted | +1.945 |
Neg logit contributions | |
nesota | -3.059 |
olate | -2.827 |
vale | -2.797 |
lication | -2.725 |
jected | -2.685 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
THING | +3.878 |
Cerberus | +3.530 |
IMAGES | +3.510 |
copyrighted | +3.368 |
inosaur | +3.327 |
Neg logit contributions | |
nesota | -5.205 |
olate | -4.810 |
vale | -4.708 |
lication | -4.660 |
jected | -4.612 |
Token | now |
Token ID | 783 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
THING | +1.662 |
Cerberus | +1.507 |
IMAGES | +1.503 |
inosaur | +1.455 |
copyrighted | +1.451 |
Neg logit contributions | |
nesota | -2.241 |
olate | -2.077 |
vale | -2.038 |
lication | -2.009 |
jected | -1.986 |
Token | global |
Token ID | 3298 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
THING | +2.243 |
IMAGES | +2.053 |
Cerberus | +2.052 |
inosaur | +1.963 |
copyrighted | +1.960 |
Neg logit contributions | |
nesota | -2.970 |
olate | -2.732 |
vale | -2.699 |
lication | -2.649 |
jected | -2.639 |
Token | fragmentation |
Token ID | 42965 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
THING | +3.068 |
Cerberus | +2.824 |
IMAGES | +2.797 |
copyrighted | +2.743 |
inosaur | +2.741 |
Neg logit contributions | |
nesota | -3.036 |
olate | -2.763 |
vale | -2.724 |
lication | -2.682 |
jected | -2.609 |
Token | leading |
Token ID | 3756 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
THING | +3.106 |
IMAGES | +2.836 |
Cerberus | +2.828 |
copyrighted | +2.704 |
inosaur | +2.672 |
Neg logit contributions | |
nesota | -4.571 |
olate | -4.255 |
vale | -4.110 |
lication | -4.098 |
jected | -4.088 |
Token | to |
Token ID | 284 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
THING | +0.850 |
Cerberus | +0.778 |
IMAGES | +0.773 |
inosaur | +0.764 |
copyrighted | +0.746 |
Neg logit contributions | |
nesota | -0.955 |
olate | -0.890 |
vale | -0.863 |
lication | -0.848 |
jected | -0.845 |
Token | annihilation |
Token ID | 49972 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
THING | +2.554 |
Cerberus | +2.333 |
IMAGES | +2.282 |
inosaur | +2.242 |
copyrighted | +2.230 |
Neg logit contributions | |
nesota | -3.515 |
olate | -3.258 |
vale | -3.200 |
lication | -3.153 |
jected | -3.105 |
Token | of |
Token ID | 286 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
THING | +8.815 |
Cerberus | +8.111 |
IMAGES | +7.973 |
inosaur | +7.565 |
copyrighted | +7.495 |
Neg logit contributions | |
nesota | -13.593 |
olate | -12.619 |
jected | -12.355 |
lication | -12.263 |
vale | -12.242 |
Token | life |
Token ID | 1204 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
THING | +7.565 |
Cerberus | +6.815 |
IMAGES | +6.776 |
copyrighted | +6.775 |
inosaur | +6.366 |
Neg logit contributions | |
nesota | -10.341 |
olate | -9.505 |
vale | -9.483 |
lication | -9.152 |
jected | -9.048 |
Token | on |
Token ID | 319 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
THING | +4.715 |
IMAGES | +4.237 |
Cerberus | +4.194 |
copyrighted | +4.119 |
inosaur | +3.977 |
Neg logit contributions | |
nesota | -7.070 |
olate | -6.659 |
vale | -6.456 |
jected | -6.436 |
lication | -6.412 |
Token | earth |
Token ID | 4534 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
THING | +1.526 |
Cerberus | +1.363 |
IMAGES | +1.347 |
inosaur | +1.312 |
copyrighted | +1.301 |
Neg logit contributions | |
nesota | -2.671 |
olate | -2.514 |
vale | -2.468 |
lication | -2.407 |
jected | -2.406 |
Token | is |
Token ID | 318 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
THING | +7.656 |
IMAGES | +7.092 |
Cerberus | +6.984 |
copyrighted | +6.774 |
inosaur | +6.735 |
Neg logit contributions | |
nesota | -11.548 |
olate | -10.673 |
lication | -10.420 |
jected | -10.396 |
vale | -10.317 |
Token | world |
Token ID | 995 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
nesota | +2.948 |
olate | +2.753 |
vale | +2.648 |
jected | +2.619 |
lication | +2.591 |
Neg logit contributions | |
THING | -2.967 |
IMAGES | -2.722 |
Cerberus | -2.714 |
inosaur | -2.690 |
copyrighted | -2.605 |
Token | — |
Token ID | 851 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
THING | +0.816 |
IMAGES | +0.758 |
Cerberus | +0.746 |
inosaur | +0.738 |
copyrighted | +0.737 |
Neg logit contributions | |
nesota | -0.776 |
olate | -0.713 |
jected | -0.680 |
lication | -0.675 |
vale | -0.673 |
Token | even |
Token ID | 772 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
nesota | +0.074 |
olate | +0.070 |
vale | +0.068 |
jected | +0.067 |
lication | +0.067 |
Neg logit contributions | |
THING | -0.043 |
Cerberus | -0.038 |
IMAGES | -0.038 |
inosaur | -0.037 |
copyrighted | -0.036 |
Token | before |
Token ID | 878 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
THING | +7.480 |
IMAGES | +6.734 |
copyrighted | +6.709 |
Cerberus | +6.682 |
inosaur | +6.417 |
Neg logit contributions | |
nesota | -11.504 |
olate | -10.498 |
lication | -10.465 |
vale | -10.347 |
jected | -10.063 |
Token | we |
Token ID | 356 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
THING | +1.182 |
Cerberus | +1.073 |
IMAGES | +1.053 |
inosaur | +1.025 |
copyrighted | +1.021 |
Neg logit contributions | |
nesota | -1.738 |
olate | -1.633 |
vale | -1.584 |
jected | -1.569 |
lication | -1.563 |
Token | even |
Token ID | 772 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
THING | +1.633 |
Cerberus | +1.523 |
IMAGES | +1.509 |
copyrighted | +1.503 |
inosaur | +1.484 |
Neg logit contributions | |
nesota | -1.294 |
olate | -1.158 |
vale | -1.131 |
lication | -1.113 |
jected | -1.103 |
Token | know |
Token ID | 760 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
THING | +11.866 |
copyrighted | +11.594 |
Cerberus | +11.170 |
IMAGES | +11.019 |
except | +10.820 |
Neg logit contributions | |
nesota | -10.432 |
vale | -9.118 |
lication | -8.846 |
olate | -8.762 |
jected | -8.399 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
THING | +6.089 |
Cerberus | +5.409 |
IMAGES | +5.273 |
copyrighted | +5.160 |
inosaur | +4.999 |
Neg logit contributions | |
nesota | -9.674 |
olate | -9.053 |
vale | -8.818 |
jected | -8.705 |
lication | -8.693 |
Token | outcome |
Token ID | 8055 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
THING | +3.730 |
Cerberus | +3.392 |
IMAGES | +3.339 |
copyrighted | +3.336 |
inosaur | +3.249 |
Neg logit contributions | |
nesota | -3.916 |
olate | -3.694 |
vale | -3.571 |
lication | -3.541 |
jected | -3.485 |
Token | of |
Token ID | 286 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
THING | +2.638 |
IMAGES | +2.383 |
Cerberus | +2.379 |
inosaur | +2.353 |
copyrighted | +2.300 |
Neg logit contributions | |
nesota | -3.188 |
olate | -3.004 |
vale | -2.889 |
jected | -2.862 |
lication | -2.860 |
Token | the |
Token ID | 262 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
THING | +4.515 |
Cerberus | +3.983 |
IMAGES | +3.837 |
copyrighted | +3.795 |
inosaur | +3.693 |
Neg logit contributions | |
nesota | -8.507 |
vale | -7.993 |
olate | -7.975 |
lication | -7.821 |
jected | -7.721 |
Token | constructing |
Token ID | 30580 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
THING | +1.203 |
Cerberus | +1.104 |
IMAGES | +1.091 |
inosaur | +1.072 |
copyrighted | +1.065 |
Neg logit contributions | |
nesota | -1.324 |
olate | -1.240 |
vale | -1.192 |
jected | -1.171 |
lication | -1.170 |
Token | of |
Token ID | 286 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
THING | +2.092 |
Cerberus | +1.888 |
IMAGES | +1.885 |
inosaur | +1.841 |
copyrighted | +1.817 |
Neg logit contributions | |
nesota | -2.718 |
olate | -2.565 |
vale | -2.467 |
lication | -2.435 |
jected | -2.420 |
Token | housing |
Token ID | 5627 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
THING | +3.245 |
Cerberus | +2.961 |
IMAGES | +2.932 |
inosaur | +2.864 |
copyrighted | +2.842 |
Neg logit contributions | |
nesota | -4.047 |
olate | -3.813 |
vale | -3.656 |
lication | -3.618 |
jected | -3.575 |
Token | complexes |
Token ID | 42665 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
THING | +2.566 |
Cerberus | +2.347 |
IMAGES | +2.338 |
inosaur | +2.262 |
copyrighted | +2.260 |
Neg logit contributions | |
nesota | -2.952 |
olate | -2.768 |
vale | -2.628 |
lication | -2.627 |
jected | -2.595 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
THING | +2.307 |
Cerberus | +2.115 |
IMAGES | +2.084 |
inosaur | +2.044 |
copyrighted | +2.037 |
Neg logit contributions | |
nesota | -2.957 |
olate | -2.764 |
vale | -2.674 |
jected | -2.642 |
lication | -2.620 |
Token | Even |
Token ID | 3412 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
THING | +0.670 |
IMAGES | +0.612 |
Cerberus | +0.609 |
inosaur | +0.597 |
copyrighted | +0.583 |
Neg logit contributions | |
nesota | -0.771 |
olate | -0.723 |
vale | -0.692 |
jected | -0.685 |
lication | -0.683 |
Token | though |
Token ID | 996 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
THING | +10.712 |
Cerberus | +9.978 |
IMAGES | +9.817 |
copyrighted | +9.526 |
inosaur | +9.462 |
Neg logit contributions | |
nesota | -11.898 |
olate | -10.859 |
vale | -10.564 |
lication | -10.524 |
jected | -10.054 |
Token | residents |
Token ID | 5085 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
THING | +0.284 |
Cerberus | +0.257 |
IMAGES | +0.256 |
inosaur | +0.249 |
copyrighted | +0.246 |
Neg logit contributions | |
nesota | -0.405 |
olate | -0.382 |
vale | -0.369 |
lication | -0.364 |
jected | -0.363 |
Token | and |
Token ID | 290 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
THING | +0.039 |
Cerberus | +0.036 |
IMAGES | +0.035 |
inosaur | +0.035 |
copyrighted | +0.034 |
Neg logit contributions | |
nesota | -0.049 |
olate | -0.045 |
vale | -0.044 |
jected | -0.043 |
lication | -0.043 |
Token | environment |
Token ID | 2858 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
nesota | +1.500 |
olate | +1.409 |
vale | +1.359 |
jected | +1.335 |
lication | +1.332 |
Neg logit contributions | |
THING | -1.315 |
Cerberus | -1.195 |
IMAGES | -1.193 |
inosaur | -1.177 |
copyrighted | -1.151 |
Token | activists |
Token ID | 7941 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
nesota | +0.376 |
olate | +0.354 |
vale | +0.342 |
lication | +0.336 |
jected | +0.335 |
Neg logit contributions | |
THING | -0.318 |
IMAGES | -0.289 |
Cerberus | -0.289 |
inosaur | -0.283 |
copyrighted | -0.278 |
Token | for |
Token ID | 329 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
nesota | +2.252 |
olate | +2.109 |
vale | +2.036 |
jected | +2.002 |
lication | +1.994 |
Neg logit contributions | |
THING | -2.114 |
Cerberus | -1.927 |
IMAGES | -1.924 |
inosaur | -1.902 |
copyrighted | -1.857 |
Token | the |
Token ID | 262 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
THING | +1.310 |
Cerberus | +1.179 |
IMAGES | +1.163 |
inosaur | +1.128 |
copyrighted | +1.111 |
Neg logit contributions | |
nesota | -2.125 |
olate | -1.993 |
vale | -1.949 |
lication | -1.921 |
jected | -1.913 |
Token | full |
Token ID | 1336 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
THING | +0.214 |
Cerberus | +0.197 |
IMAGES | +0.196 |
inosaur | +0.192 |
copyrighted | +0.189 |
Neg logit contributions | |
nesota | -0.201 |
olate | -0.186 |
vale | -0.181 |
lication | -0.177 |
jected | -0.176 |
Token | tour |
Token ID | 4205 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
THING | +5.084 |
Cerberus | +4.755 |
IMAGES | +4.702 |
copyrighted | +4.583 |
inosaur | +4.542 |
Neg logit contributions | |
nesota | -4.185 |
olate | -3.810 |
vale | -3.712 |
lication | -3.645 |
jected | -3.574 |
Token | . |
Token ID | 13 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
THING | +0.388 |
Cerberus | +0.357 |
IMAGES | +0.355 |
inosaur | +0.352 |
copyrighted | +0.345 |
Neg logit contributions | |
nesota | -0.371 |
olate | -0.342 |
vale | -0.331 |
lication | -0.326 |
jected | -0.326 |
Token | Even |
Token ID | 3412 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
THING | +1.422 |
IMAGES | +1.303 |
Cerberus | +1.300 |
inosaur | +1.269 |
copyrighted | +1.234 |
Neg logit contributions | |
nesota | -1.517 |
olate | -1.412 |
vale | -1.369 |
lication | -1.354 |
jected | -1.350 |
Token | if |
Token ID | 611 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
THING | +10.163 |
Cerberus | +9.270 |
IMAGES | +9.134 |
copyrighted | +8.771 |
inosaur | +8.683 |
Neg logit contributions | |
nesota | -12.347 |
lication | -11.460 |
olate | -11.396 |
vale | -11.292 |
jected | -10.937 |
Token | the |
Token ID | 262 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
THING | +3.233 |
Cerberus | +2.983 |
IMAGES | +2.920 |
copyrighted | +2.817 |
inosaur | +2.780 |
Neg logit contributions | |
nesota | -4.353 |
olate | -4.020 |
vale | -3.945 |
lication | -3.925 |
jected | -3.857 |
Token | tunnel |
Token ID | 13275 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
THING | +0.009 |
Cerberus | +0.008 |
IMAGES | +0.008 |
inosaur | +0.008 |
copyrighted | +0.008 |
Neg logit contributions | |
nesota | -0.009 |
olate | -0.008 |
vale | -0.008 |
lication | -0.008 |
jected | -0.008 |
Token | stages |
Token ID | 9539 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
THING | +1.244 |
Cerberus | +1.134 |
IMAGES | +1.133 |
inosaur | +1.108 |
copyrighted | +1.082 |
Neg logit contributions | |
nesota | -1.486 |
olate | -1.382 |
vale | -1.343 |
lication | -1.319 |
jected | -1.307 |
Token | and |
Token ID | 290 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
nesota | +4.376 |
olate | +4.169 |
vale | +3.974 |
jected | +3.932 |
onset | +3.890 |
Neg logit contributions | |
THING | -4.320 |
Cerberus | -3.943 |
IMAGES | -3.929 |
inosaur | -3.921 |
ModLoader | -3.832 |
Token | 2019 |
Token ID | 13130 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
THING | +5.193 |
Cerberus | +4.848 |
copyrighted | +4.736 |
IMAGES | +4.666 |
inosaur | +4.580 |
Neg logit contributions | |
nesota | -6.569 |
olate | -6.323 |
lication | -6.176 |
jected | -5.943 |
onset | -5.899 |
Token | The |
Token ID | 383 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
THING | +1.833 |
Cerberus | +1.737 |
copyrighted | +1.647 |
IMAGES | +1.633 |
inosaur | +1.557 |
Neg logit contributions | |
nesota | -3.282 |
olate | -3.162 |
jected | -2.998 |
lication | -2.998 |
vale | -2.946 |
Token | Washington |
Token ID | 2669 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
THING | +2.833 |
IMAGES | +2.678 |
Cerberus | +2.662 |
copyrighted | +2.555 |
inosaur | +2.444 |
Neg logit contributions | |
nesota | -3.975 |
olate | -3.865 |
lication | -3.785 |
jected | -3.666 |
vale | -3.649 |
Token | Times |
Token ID | 3782 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
THING | +1.402 |
Cerberus | +1.286 |
IMAGES | +1.285 |
inosaur | +1.255 |
copyrighted | +1.240 |
Neg logit contributions | |
nesota | -1.625 |
olate | -1.517 |
vale | -1.465 |
jected | -1.451 |
lication | -1.450 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
THING | +1.673 |
Cerberus | +1.552 |
IMAGES | +1.530 |
copyrighted | +1.521 |
inosaur | +1.506 |
Neg logit contributions | |
nesota | -1.471 |
olate | -1.338 |
lication | -1.298 |
vale | -1.271 |
jected | -1.271 |
Token | LLC |
Token ID | 11419 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
THING | +1.483 |
Cerberus | +0.964 |
copyrighted | +0.907 |
inosaur | +0.696 |
IMAGES | +0.612 |
Neg logit contributions | |
nesota | -13.606 |
olate | -13.211 |
lication | -12.826 |
jected | -12.608 |
onset | -12.504 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
THING | +7.639 |
copyrighted | +6.931 |
Cerberus | +6.877 |
Osiris | +6.512 |
inosaur | +6.361 |
Neg logit contributions | |
nesota | -14.622 |
olate | -14.222 |
lication | -13.902 |
jected | -13.155 |
vale | -13.115 |
Token | Click |
Token ID | 6914 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
THING | +4.565 |
Cerberus | +4.195 |
IMAGES | +4.102 |
copyrighted | +4.049 |
inosaur | +4.028 |
Neg logit contributions | |
nesota | -4.221 |
olate | -4.069 |
lication | -3.833 |
jected | -3.777 |
vale | -3.757 |
Token | here |
Token ID | 994 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
THING | +1.985 |
IMAGES | +1.720 |
Cerberus | +1.714 |
inosaur | +1.697 |
copyrighted | +1.664 |
Neg logit contributions | |
nesota | -4.006 |
olate | -3.824 |
vale | -3.701 |
jected | -3.668 |
lication | -3.656 |
Token | for |
Token ID | 329 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
THING | +2.100 |
Cerberus | +1.901 |
IMAGES | +1.883 |
inosaur | +1.877 |
copyrighted | +1.853 |
Neg logit contributions | |
nesota | -3.502 |
olate | -3.289 |
vale | -3.178 |
lication | -3.149 |
jected | -3.149 |
Token | reprint |
Token ID | 26589 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
THING | +1.747 |
Cerberus | +1.502 |
copyrighted | +1.475 |
inosaur | +1.435 |
IMAGES | +1.416 |
Neg logit contributions | |
nesota | -5.336 |
olate | -5.125 |
vale | -4.961 |
lication | -4.911 |
jected | -4.895 |
Token | 2006 |
Token ID | 4793 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
THING | +1.382 |
IMAGES | +1.261 |
Cerberus | +1.260 |
inosaur | +1.226 |
copyrighted | +1.220 |
Neg logit contributions | |
nesota | -1.665 |
olate | -1.562 |
vale | -1.511 |
jected | -1.485 |
lication | -1.484 |
Token | - |
Token ID | 12 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
nesota | +1.674 |
olate | +1.541 |
vale | +1.464 |
jected | +1.437 |
lication | +1.433 |
Neg logit contributions | |
THING | -2.574 |
Cerberus | -2.383 |
IMAGES | -2.376 |
inosaur | -2.367 |
copyrighted | -2.313 |
Token | 2012 |
Token ID | 6999 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
nesota | +1.684 |
olate | +1.579 |
vale | +1.523 |
jected | +1.496 |
lication | +1.488 |
Neg logit contributions | |
THING | -1.649 |
Cerberus | -1.508 |
IMAGES | -1.500 |
inosaur | -1.492 |
copyrighted | -1.453 |
Token | ( |
Token ID | 357 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
THING | +1.878 |
IMAGES | +1.744 |
Cerberus | +1.739 |
inosaur | +1.708 |
copyrighted | +1.685 |
Neg logit contributions | |
nesota | -1.449 |
olate | -1.338 |
vale | -1.279 |
jected | -1.250 |
lication | -1.242 |
Token | and |
Token ID | 392 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
THING | +0.286 |
IMAGES | +0.261 |
Cerberus | +0.261 |
inosaur | +0.258 |
copyrighted | +0.253 |
Neg logit contributions | |
nesota | -0.283 |
olate | -0.264 |
vale | -0.253 |
lication | -0.249 |
jected | -0.248 |
Token | counting |
Token ID | 14143 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
THING | +3.030 |
IMAGES | +2.782 |
Cerberus | +2.761 |
copyrighted | +2.700 |
inosaur | +2.672 |
Neg logit contributions | |
nesota | -3.718 |
olate | -3.424 |
vale | -3.328 |
lication | -3.276 |
jected | -3.253 |
Token | )[ |
Token ID | 38381 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
THING | +9.205 |
IMAGES | +8.450 |
copyrighted | +8.178 |
Cerberus | +8.054 |
inosaur | +8.000 |
Neg logit contributions | |
nesota | -13.356 |
olate | -12.221 |
vale | -11.962 |
lication | -11.714 |
jected | -11.578 |
Token | h |
Token ID | 71 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
THING | +2.489 |
IMAGES | +2.275 |
Cerberus | +2.243 |
inosaur | +2.209 |
copyrighted | +2.199 |
Neg logit contributions | |
nesota | -2.555 |
olate | -2.360 |
vale | -2.256 |
lication | -2.232 |
jected | -2.209 |
Token | int |
Token ID | 600 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
THING | +2.446 |
inosaur | +2.305 |
IMAGES | +2.294 |
Cerberus | +2.254 |
copyrighted | +2.202 |
Neg logit contributions | |
nesota | -1.716 |
olate | -1.528 |
vale | -1.452 |
lication | -1.430 |
onset | -1.381 |
Token | : |
Token ID | 25 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
nesota | +4.393 |
olate | +4.159 |
vale | +4.031 |
jected | +3.947 |
onset | +3.895 |
Neg logit contributions | |
THING | -4.872 |
Cerberus | -4.462 |
inosaur | -4.456 |
IMAGES | -4.431 |
ModLoader | -4.329 |
Token | for |
Token ID | 329 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
nesota | +0.444 |
olate | +0.417 |
vale | +0.403 |
jected | +0.397 |
lication | +0.396 |
Neg logit contributions | |
THING | -0.361 |
Cerberus | -0.327 |
IMAGES | -0.327 |
inosaur | -0.322 |
copyrighted | -0.315 |
Token | start |
Token ID | 923 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
THING | +0.366 |
Cerberus | +0.334 |
IMAGES | +0.332 |
inosaur | +0.323 |
copyrighted | +0.321 |
Neg logit contributions | |
nesota | -0.410 |
olate | -0.381 |
vale | -0.371 |
jected | -0.364 |
lication | -0.362 |
Token | painting |
Token ID | 12036 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
nesota | +6.236 |
olate | +6.048 |
vale | +5.762 |
jected | +5.735 |
onset | +5.704 |
Neg logit contributions | |
THING | -5.588 |
inosaur | -5.127 |
IMAGES | -5.113 |
Cerberus | -5.039 |
ModLoader | -4.990 |
Token | . |
Token ID | 13 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
THING | +3.764 |
Cerberus | +3.429 |
IMAGES | +3.422 |
copyrighted | +3.290 |
inosaur | +3.215 |
Neg logit contributions | |
nesota | -5.155 |
olate | -4.773 |
vale | -4.705 |
jected | -4.600 |
lication | -4.595 |
Token | There |
Token ID | 1318 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
nesota | +0.248 |
olate | +0.230 |
vale | +0.223 |
jected | +0.219 |
lication | +0.219 |
Neg logit contributions | |
THING | -0.240 |
Cerberus | -0.220 |
IMAGES | -0.220 |
inosaur | -0.215 |
copyrighted | -0.211 |
Token | is |
Token ID | 318 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
THING | +1.540 |
IMAGES | +1.407 |
Cerberus | +1.383 |
inosaur | +1.373 |
copyrighted | +1.346 |
Neg logit contributions | |
nesota | -1.906 |
olate | -1.779 |
vale | -1.730 |
jected | -1.693 |
lication | -1.666 |
Token | literally |
Token ID | 7360 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
THING | +0.957 |
Cerberus | +0.867 |
IMAGES | +0.863 |
inosaur | +0.843 |
copyrighted | +0.839 |
Neg logit contributions | |
nesota | -1.175 |
olate | -1.094 |
vale | -1.062 |
jected | -1.044 |
lication | -1.042 |
Token | no |
Token ID | 645 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
THING | +9.481 |
IMAGES | +8.531 |
copyrighted | +8.467 |
Cerberus | +8.462 |
inosaur | +7.642 |
Neg logit contributions | |
nesota | -13.637 |
vale | -12.123 |
lication | -12.011 |
olate | -11.926 |
jected | -11.743 |
Token | technique |
Token ID | 8173 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
THING | +8.628 |
Cerberus | +7.860 |
copyrighted | +7.799 |
IMAGES | +7.653 |
kidding | +7.424 |
Neg logit contributions | |
nesota | -7.568 |
olate | -6.863 |
vale | -6.716 |
jected | -6.429 |
lication | -6.259 |
Token | for |
Token ID | 329 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
THING | +0.049 |
Cerberus | +0.044 |
IMAGES | +0.044 |
inosaur | +0.043 |
copyrighted | +0.043 |
Neg logit contributions | |
nesota | -0.069 |
olate | -0.064 |
vale | -0.063 |
jected | -0.061 |
lication | -0.061 |
Token | painting |
Token ID | 12036 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
nesota | +0.685 |
olate | +0.644 |
vale | +0.624 |
jected | +0.613 |
lication | +0.611 |
Neg logit contributions | |
THING | -0.545 |
Cerberus | -0.493 |
IMAGES | -0.490 |
inosaur | -0.482 |
copyrighted | -0.473 |
Token | . |
Token ID | 13 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
THING | +1.840 |
Cerberus | +1.656 |
IMAGES | +1.644 |
inosaur | +1.594 |
copyrighted | +1.586 |
Neg logit contributions | |
nesota | -2.677 |
olate | -2.516 |
vale | -2.455 |
lication | -2.408 |
jected | -2.406 |
Token | of |
Token ID | 286 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
THING | +5.083 |
Cerberus | +4.717 |
copyrighted | +4.712 |
IMAGES | +4.616 |
confiscated | +4.467 |
Neg logit contributions | |
nesota | -7.396 |
olate | -6.703 |
vale | -6.534 |
jected | -6.436 |
lication | -6.372 |
Token | ste |
Token ID | 2876 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
THING | +5.226 |
Cerberus | +4.818 |
IMAGES | +4.795 |
copyrighted | +4.737 |
inosaur | +4.432 |
Neg logit contributions | |
nesota | -6.644 |
olate | -6.144 |
vale | -6.081 |
lication | -5.913 |
jected | -5.733 |
Token | in |
Token ID | 259 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
THING | +0.904 |
inosaur | +0.834 |
IMAGES | +0.829 |
Cerberus | +0.827 |
copyrighted | +0.801 |
Neg logit contributions | |
nesota | -0.817 |
olate | -0.751 |
vale | -0.730 |
jected | -0.707 |
lication | -0.706 |
Token | supporters |
Token ID | 5941 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
nesota | +6.919 |
olate | +6.601 |
vale | +6.342 |
jected | +6.316 |
onset | +6.256 |
Neg logit contributions | |
THING | -5.086 |
Cerberus | -4.582 |
inosaur | -4.525 |
IMAGES | -4.497 |
ModLoader | -4.346 |
Token | never |
Token ID | 1239 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
nesota | +2.406 |
olate | +2.275 |
vale | +2.198 |
jected | +2.165 |
lication | +2.158 |
Neg logit contributions | |
THING | -1.949 |
Cerberus | -1.755 |
IMAGES | -1.755 |
inosaur | -1.740 |
copyrighted | -1.675 |
Token | even |
Token ID | 772 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
THING | +3.586 |
IMAGES | +3.336 |
Cerberus | +3.283 |
copyrighted | +3.274 |
inosaur | +3.181 |
Neg logit contributions | |
nesota | -4.498 |
olate | -4.185 |
vale | -4.041 |
lication | -3.945 |
jected | -3.934 |
Token | made |
Token ID | 925 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
THING | +9.801 |
IMAGES | +9.407 |
copyrighted | +9.374 |
Cerberus | +9.062 |
confiscated | +8.844 |
Neg logit contributions | |
nesota | -12.635 |
olate | -11.432 |
vale | -11.260 |
lication | -10.797 |
jected | -10.634 |
Token | it |
Token ID | 340 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
THING | +1.478 |
Cerberus | +1.337 |
IMAGES | +1.327 |
inosaur | +1.283 |
copyrighted | +1.282 |
Neg logit contributions | |
nesota | -2.050 |
olate | -1.905 |
vale | -1.860 |
jected | -1.815 |
lication | -1.814 |
Token | to |
Token ID | 284 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
THING | +3.614 |
IMAGES | +3.272 |
Cerberus | +3.241 |
copyrighted | +3.185 |
inosaur | +3.144 |
Neg logit contributions | |
nesota | -4.488 |
olate | -4.101 |
vale | -4.021 |
lication | -4.002 |
jected | -3.938 |
Token | the |
Token ID | 262 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
THING | +1.383 |
Cerberus | +1.217 |
IMAGES | +1.215 |
inosaur | +1.158 |
copyrighted | +1.155 |
Neg logit contributions | |
nesota | -2.508 |
olate | -2.361 |
vale | -2.308 |
lication | -2.277 |
jected | -2.268 |
Token | event |
Token ID | 1785 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
nesota | +0.961 |
olate | +0.898 |
vale | +0.866 |
jected | +0.850 |
lication | +0.849 |
Neg logit contributions | |
THING | -0.942 |
Cerberus | -0.860 |
IMAGES | -0.860 |
inosaur | -0.848 |
copyrighted | -0.831 |
Token | The |
Token ID | 464 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
nesota | +0.545 |
olate | +0.509 |
vale | +0.488 |
jected | +0.480 |
lication | +0.478 |
Neg logit contributions | |
THING | -0.558 |
Cerberus | -0.506 |
IMAGES | -0.505 |
inosaur | -0.502 |
copyrighted | -0.488 |
Token | young |
Token ID | 1862 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
THING | +0.119 |
Cerberus | +0.108 |
IMAGES | +0.107 |
inosaur | +0.106 |
copyrighted | +0.104 |
Neg logit contributions | |
nesota | -0.150 |
olate | -0.142 |
vale | -0.137 |
lication | -0.135 |
jected | -0.134 |
Token | man |
Token ID | 582 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
nesota | +3.604 |
olate | +3.398 |
vale | +3.298 |
jected | +3.253 |
lication | +3.224 |
Neg logit contributions | |
THING | -2.782 |
IMAGES | -2.508 |
Cerberus | -2.500 |
inosaur | -2.473 |
copyrighted | -2.406 |
Token | was |
Token ID | 373 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
THING | +0.028 |
Cerberus | +0.026 |
IMAGES | +0.026 |
inosaur | +0.025 |
copyrighted | +0.025 |
Neg logit contributions | |
nesota | -0.035 |
olate | -0.033 |
vale | -0.032 |
jected | -0.031 |
lication | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
nesota | +2.274 |
olate | +2.160 |
vale | +2.077 |
jected | +2.063 |
lication | +2.043 |
Neg logit contributions | |
THING | -1.733 |
IMAGES | -1.573 |
inosaur | -1.556 |
Cerberus | -1.544 |
copyrighted | -1.489 |
Token | junior |
Token ID | 13430 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
nesota | +0.126 |
olate | +0.118 |
vale | +0.114 |
lication | +0.112 |
jected | +0.111 |
Neg logit contributions | |
THING | -0.108 |
Cerberus | -0.098 |
IMAGES | -0.097 |
inosaur | -0.096 |
copyrighted | -0.094 |
Token | clerk |
Token ID | 21120 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
nesota | +13.445 |
onset | +13.103 |
olate | +12.919 |
vale | +12.765 |
jected | +12.677 |
Neg logit contributions | |
THING | -12.037 |
IMAGES | -11.342 |
inosaur | -11.325 |
ModLoader | -11.279 |
copyrighted | -10.605 |
Token | in |
Token ID | 287 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nesota | +4.463 |
olate | +4.228 |
vale | +4.087 |
jected | +4.034 |
lication | +4.003 |
Neg logit contributions | |
THING | -3.578 |
IMAGES | -3.288 |
inosaur | -3.206 |
Cerberus | -3.205 |
ModLoader | -3.113 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
nesota | +4.474 |
olate | +4.268 |
vale | +4.147 |
jected | +4.103 |
lication | +4.093 |
Neg logit contributions | |
THING | -2.740 |
IMAGES | -2.452 |
Cerberus | -2.386 |
inosaur | -2.384 |
copyrighted | -2.286 |
Token | ministry |
Token ID | 11957 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
nesota | +4.065 |
olate | +3.838 |
vale | +3.734 |
jected | +3.655 |
onset | +3.645 |
Neg logit contributions | |
THING | -3.542 |
IMAGES | -3.233 |
Cerberus | -3.182 |
inosaur | -3.177 |
copyrighted | -3.069 |
Token | of |
Token ID | 286 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
nesota | +1.140 |
olate | +1.073 |
vale | +1.039 |
jected | +1.024 |
lication | +1.020 |
Neg logit contributions | |
THING | -0.875 |
Cerberus | -0.789 |
IMAGES | -0.786 |
inosaur | -0.777 |
copyrighted | -0.756 |
Token | the |
Token ID | 262 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
THING | +1.379 |
Cerberus | +1.272 |
IMAGES | +1.233 |
inosaur | +1.197 |
copyrighted | +1.189 |
Neg logit contributions | |
nesota | -2.210 |
olate | -2.123 |
vale | -2.053 |
lication | -2.024 |
jected | -2.009 |
Token | Winter |
Token ID | 10633 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
nesota | +1.416 |
olate | +1.346 |
vale | +1.299 |
lication | +1.279 |
jected | +1.268 |
Neg logit contributions | |
THING | -1.122 |
Cerberus | -1.034 |
IMAGES | -1.018 |
inosaur | -1.001 |
copyrighted | -0.984 |
Token | hawks |
Token ID | 27221 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
nesota | +7.547 |
olate | +7.063 |
vale | +6.975 |
jected | +6.722 |
lication | +6.691 |
Neg logit contributions | |
THING | -6.524 |
IMAGES | -5.948 |
inosaur | -5.817 |
Cerberus | -5.812 |
copyrighted | -5.683 |
Token | in |
Token ID | 287 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
nesota | +0.007 |
olate | +0.006 |
vale | +0.006 |
lication | +0.006 |
jected | +0.006 |
Neg logit contributions | |
THING | -0.006 |
Cerberus | -0.005 |
IMAGES | -0.005 |
inosaur | -0.005 |
copyrighted | -0.005 |
Token | major |
Token ID | 1688 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
nesota | +2.607 |
olate | +2.476 |
vale | +2.406 |
jected | +2.373 |
lication | +2.367 |
Neg logit contributions | |
THING | -1.480 |
Cerberus | -1.306 |
IMAGES | -1.302 |
inosaur | -1.281 |
copyrighted | -1.240 |
Token | junior |
Token ID | 13430 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
nesota | +2.172 |
olate | +2.025 |
vale | +1.947 |
jected | +1.910 |
lication | +1.904 |
Neg logit contributions | |
THING | -2.395 |
Cerberus | -2.197 |
IMAGES | -2.197 |
inosaur | -2.169 |
copyrighted | -2.124 |
Token | hockey |
Token ID | 12217 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
nesota | +11.326 |
onset | +10.037 |
olate | +9.975 |
vale | +9.789 |
jected | +9.778 |
Neg logit contributions | |
THING | -13.454 |
ModLoader | -13.424 |
inosaur | -13.231 |
IMAGES | -12.514 |
Cerberus | -12.510 |
Token | 's |
Token ID | 338 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
nesota | +3.283 |
olate | +3.063 |
vale | +2.954 |
jected | +2.910 |
lication | +2.897 |
Neg logit contributions | |
THING | -3.223 |
Cerberus | -2.948 |
IMAGES | -2.944 |
inosaur | -2.915 |
copyrighted | -2.840 |
Token | import |
Token ID | 1330 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
nesota | +1.885 |
olate | +1.765 |
vale | +1.708 |
jected | +1.663 |
lication | +1.661 |
Neg logit contributions | |
THING | -1.963 |
Cerberus | -1.807 |
IMAGES | -1.800 |
inosaur | -1.772 |
copyrighted | -1.747 |
Token | draft |
Token ID | 4538 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
nesota | +1.358 |
olate | +1.251 |
vale | +1.204 |
lication | +1.172 |
jected | +1.157 |
Neg logit contributions | |
THING | -1.773 |
Cerberus | -1.649 |
IMAGES | -1.631 |
inosaur | -1.621 |
copyrighted | -1.595 |
Token | in |
Token ID | 287 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
nesota | +4.380 |
olate | +4.052 |
vale | +3.921 |
jected | +3.894 |
lication | +3.849 |
Neg logit contributions | |
THING | -4.205 |
IMAGES | -3.860 |
Cerberus | -3.831 |
inosaur | -3.804 |
ModLoader | -3.736 |
Token | putting |
Token ID | 5137 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
nesota | +4.412 |
olate | +4.209 |
vale | +4.045 |
jected | +4.002 |
lication | +3.974 |
Neg logit contributions | |
THING | -3.628 |
IMAGES | -3.319 |
Cerberus | -3.275 |
inosaur | -3.274 |
copyrighted | -3.146 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
THING | +0.862 |
Cerberus | +0.776 |
IMAGES | +0.771 |
inosaur | +0.755 |
copyrighted | +0.745 |
Neg logit contributions | |
nesota | -1.197 |
olate | -1.123 |
vale | -1.094 |
lication | -1.073 |
jected | -1.072 |
Token | fish |
Token ID | 5916 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
THING | +0.372 |
Cerberus | +0.339 |
IMAGES | +0.338 |
inosaur | +0.330 |
copyrighted | +0.327 |
Neg logit contributions | |
nesota | -0.400 |
olate | -0.373 |
vale | -0.362 |
jected | -0.354 |
lication | -0.354 |
Token | in |
Token ID | 287 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
THING | +0.765 |
IMAGES | +0.686 |
Cerberus | +0.686 |
inosaur | +0.671 |
copyrighted | +0.653 |
Neg logit contributions | |
nesota | -1.051 |
olate | -0.977 |
vale | -0.953 |
jected | -0.941 |
lication | -0.937 |
Token | their |
Token ID | 511 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
nesota | +1.389 |
olate | +1.310 |
vale | +1.271 |
jected | +1.251 |
lication | +1.248 |
Neg logit contributions | |
THING | -0.988 |
Cerberus | -0.886 |
IMAGES | -0.884 |
inosaur | -0.871 |
copyrighted | -0.848 |
Token | spring |
Token ID | 6076 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
nesota | +2.654 |
olate | +2.501 |
vale | +2.411 |
jected | +2.378 |
lication | +2.367 |
Neg logit contributions | |
THING | -2.300 |
IMAGES | -2.088 |
Cerberus | -2.088 |
inosaur | -2.067 |
copyrighted | -2.007 |
Token | rolls |
Token ID | 14088 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
nesota | +12.587 |
olate | +12.475 |
vale | +12.073 |
lication | +11.791 |
onset | +11.683 |
Neg logit contributions | |
THING | -11.583 |
IMAGES | -10.896 |
inosaur | -10.648 |
Cerberus | -10.529 |
ModLoader | -10.426 |
Token | — |
Token ID | 851 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
nesota | +1.482 |
olate | +1.388 |
vale | +1.340 |
jected | +1.318 |
lication | +1.312 |
Neg logit contributions | |
THING | -1.379 |
Cerberus | -1.256 |
IMAGES | -1.254 |
inosaur | -1.240 |
copyrighted | -1.210 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
nesota | +1.161 |
olate | +1.095 |
vale | +1.061 |
jected | +1.045 |
lication | +1.041 |
Neg logit contributions | |
THING | -0.852 |
Cerberus | -0.766 |
IMAGES | -0.764 |
inosaur | -0.754 |
copyrighted | -0.734 |
Token | that |
Token ID | 326 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
THING | +0.314 |
Cerberus | +0.285 |
IMAGES | +0.281 |
inosaur | +0.278 |
copyrighted | +0.273 |
Neg logit contributions | |
nesota | -0.405 |
olate | -0.377 |
vale | -0.368 |
jected | -0.360 |
lication | -0.360 |
Token | became |
Token ID | 2627 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
nesota | +3.104 |
olate | +2.915 |
vale | +2.816 |
jected | +2.770 |
lication | +2.759 |
Neg logit contributions | |
THING | -2.778 |
Cerberus | -2.528 |
IMAGES | -2.526 |
inosaur | -2.492 |
copyrighted | -2.430 |
Token | of |
Token ID | 286 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
THING | +0.529 |
Cerberus | +0.473 |
IMAGES | +0.469 |
inosaur | +0.460 |
copyrighted | +0.452 |
Neg logit contributions | |
nesota | -0.755 |
olate | -0.706 |
vale | -0.683 |
jected | -0.672 |
lication | -0.668 |
Token | English |
Token ID | 3594 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
THING | +2.757 |
Cerberus | +2.499 |
IMAGES | +2.436 |
copyrighted | +2.425 |
inosaur | +2.378 |
Neg logit contributions | |
nesota | -3.374 |
olate | -3.172 |
vale | -3.081 |
jected | -3.020 |
lication | -2.977 |
Token | he |
Token ID | 339 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
nesota | +2.790 |
olate | +2.620 |
vale | +2.530 |
jected | +2.490 |
lication | +2.481 |
Neg logit contributions | |
THING | -2.424 |
Cerberus | -2.201 |
IMAGES | -2.195 |
inosaur | -2.168 |
copyrighted | -2.120 |
Token | acquired |
Token ID | 9477 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
nesota | +3.289 |
olate | +3.103 |
vale | +2.997 |
jected | +2.953 |
lication | +2.944 |
Neg logit contributions | |
THING | -2.757 |
IMAGES | -2.492 |
Cerberus | -2.488 |
inosaur | -2.455 |
copyrighted | -2.380 |
Token | in |
Token ID | 287 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
THING | +0.469 |
Cerberus | +0.424 |
IMAGES | +0.421 |
inosaur | +0.413 |
copyrighted | +0.410 |
Neg logit contributions | |
nesota | -0.640 |
olate | -0.602 |
vale | -0.585 |
lication | -0.575 |
jected | -0.573 |
Token | junior |
Token ID | 13430 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
nesota | +3.434 |
olate | +3.226 |
vale | +3.124 |
jected | +3.077 |
lication | +3.062 |
Neg logit contributions | |
THING | -2.851 |
IMAGES | -2.578 |
Cerberus | -2.575 |
inosaur | -2.550 |
copyrighted | -2.474 |
Token | high |
Token ID | 1029 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
nesota | +9.611 |
jected | +8.490 |
onset | +8.425 |
vale | +8.407 |
iors | +8.319 |
Neg logit contributions | |
THING | -14.937 |
inosaur | -14.699 |
IMAGES | -14.047 |
Cerberus | -13.827 |
ModLoader | -13.788 |
Token | stayed |
Token ID | 9658 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
nesota | +2.172 |
olate | +2.043 |
vale | +1.969 |
jected | +1.938 |
lication | +1.934 |
Neg logit contributions | |
THING | -1.843 |
Cerberus | -1.674 |
IMAGES | -1.671 |
inosaur | -1.643 |
copyrighted | -1.613 |
Token | within |
Token ID | 1626 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
nesota | +1.540 |
olate | +1.456 |
vale | +1.413 |
jected | +1.394 |
lication | +1.387 |
Neg logit contributions | |
THING | -1.049 |
IMAGES | -0.941 |
Cerberus | -0.937 |
inosaur | -0.927 |
copyrighted | -0.891 |
Token | him |
Token ID | 683 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
THING | +1.160 |
Cerberus | +1.047 |
IMAGES | +1.031 |
copyrighted | +0.997 |
inosaur | +0.993 |
Neg logit contributions | |
nesota | -1.961 |
olate | -1.860 |
vale | -1.793 |
lication | -1.773 |
jected | -1.770 |
Token | enough |
Token ID | 1576 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
THING | +0.286 |
Cerberus | +0.258 |
IMAGES | +0.258 |
inosaur | +0.253 |
copyrighted | +0.250 |
Neg logit contributions | |
nesota | -0.355 |
olate | -0.332 |
vale | -0.321 |
jected | -0.318 |
lication | -0.316 |
Token | region |
Token ID | 3814 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
nesota | +3.101 |
olate | +2.898 |
vale | +2.794 |
jected | +2.742 |
lication | +2.726 |
Neg logit contributions | |
THING | -3.211 |
Cerberus | -2.940 |
IMAGES | -2.939 |
inosaur | -2.903 |
copyrighted | -2.837 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
nesota | +6.573 |
olate | +6.273 |
vale | +6.044 |
jected | +5.999 |
onset | +5.924 |
Neg logit contributions | |
THING | -5.110 |
IMAGES | -4.674 |
inosaur | -4.537 |
Cerberus | -4.530 |
ModLoader | -4.412 |
Token | about |
Token ID | 546 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
nesota | +5.098 |
olate | +4.826 |
vale | +4.704 |
jected | +4.587 |
lication | +4.582 |
Neg logit contributions | |
THING | -4.726 |
IMAGES | -4.336 |
Cerberus | -4.269 |
inosaur | -4.229 |
ModLoader | -4.149 |
Token | a |
Token ID | 257 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
nesota | +2.255 |
olate | +2.133 |
vale | +2.069 |
jected | +2.039 |
lication | +2.029 |
Neg logit contributions | |
THING | -1.503 |
IMAGES | -1.342 |
Cerberus | -1.337 |
inosaur | -1.323 |
copyrighted | -1.276 |
Token | warm |
Token ID | 5814 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
THING | +0.197 |
Cerberus | +0.179 |
IMAGES | +0.177 |
inosaur | +0.174 |
copyrighted | +0.172 |
Neg logit contributions | |
nesota | -0.244 |
olate | -0.229 |
vale | -0.222 |
lication | -0.219 |
jected | -0.217 |
Token | spring |
Token ID | 6076 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
nesota | +9.523 |
olate | +9.177 |
vale | +8.901 |
onset | +8.817 |
jected | +8.578 |
Neg logit contributions | |
THING | -9.827 |
IMAGES | -9.228 |
Cerberus | -9.162 |
inosaur | -8.916 |
ModLoader | -8.776 |
Token | and |
Token ID | 290 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
nesota | +12.015 |
onset | +11.672 |
olate | +11.503 |
vale | +11.241 |
occ | +10.926 |
Neg logit contributions | |
THING | -11.978 |
IMAGES | -11.181 |
Cerberus | -10.991 |
inosaur | -10.885 |
ModLoader | -10.586 |
Token | dreams |
Token ID | 10625 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
nesota | +3.332 |
olate | +3.135 |
vale | +3.014 |
jected | +2.972 |
onset | +2.953 |
Neg logit contributions | |
THING | -3.041 |
Cerberus | -2.756 |
IMAGES | -2.753 |
inosaur | -2.730 |
copyrighted | -2.641 |
Token | of |
Token ID | 286 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
THING | +1.053 |
Cerberus | +0.908 |
inosaur | +0.890 |
IMAGES | +0.887 |
copyrighted | +0.863 |
Neg logit contributions | |
nesota | -2.106 |
olate | -1.994 |
vale | -1.936 |
lication | -1.916 |
jected | -1.915 |
Token | a |
Token ID | 257 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
THING | +2.789 |
Cerberus | +2.525 |
IMAGES | +2.465 |
copyrighted | +2.448 |
inosaur | +2.448 |
Neg logit contributions | |
nesota | -3.484 |
olate | -3.285 |
vale | -3.196 |
lication | -3.147 |
jected | -3.139 |
Token | less |
Token ID | 1342 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
THING | +1.707 |
Cerberus | +1.561 |
IMAGES | +1.537 |
copyrighted | +1.516 |
inosaur | +1.515 |
Neg logit contributions | |
nesota | -1.817 |
olate | -1.695 |
vale | -1.643 |
lication | -1.628 |
jected | -1.604 |
Token | to |
Token ID | 284 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
nesota | +1.365 |
olate | +1.290 |
vale | +1.250 |
jected | +1.232 |
lication | +1.228 |
Neg logit contributions | |
THING | -0.962 |
Cerberus | -0.862 |
IMAGES | -0.861 |
inosaur | -0.849 |
copyrighted | -0.824 |
Token | sit |
Token ID | 1650 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
THING | +0.156 |
Cerberus | +0.146 |
IMAGES | +0.145 |
inosaur | +0.142 |
copyrighted | +0.142 |
Neg logit contributions | |
nesota | -0.113 |
olate | -0.103 |
lication | -0.099 |
vale | -0.099 |
jected | -0.097 |
Token | out |
Token ID | 503 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
nesota | +3.267 |
olate | +3.094 |
vale | +2.994 |
jected | +2.954 |
lication | +2.927 |
Neg logit contributions | |
THING | -2.438 |
IMAGES | -2.192 |
Cerberus | -2.188 |
inosaur | -2.167 |
copyrighted | -2.100 |
Token | during |
Token ID | 1141 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
nesota | +1.690 |
olate | +1.599 |
vale | +1.550 |
jected | +1.527 |
lication | +1.521 |
Neg logit contributions | |
THING | -1.170 |
Cerberus | -1.047 |
IMAGES | -1.047 |
inosaur | -1.033 |
copyrighted | -1.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
nesota | +3.306 |
olate | +3.136 |
vale | +3.035 |
jected | +2.992 |
lication | +2.981 |
Neg logit contributions | |
THING | -2.270 |
IMAGES | -2.030 |
Cerberus | -2.020 |
inosaur | -2.009 |
copyrighted | -1.939 |
Token | Spring |
Token ID | 8225 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
nesota | +4.744 |
olate | +4.471 |
vale | +4.275 |
jected | +4.209 |
onset | +4.192 |
Neg logit contributions | |
THING | -4.817 |
IMAGES | -4.408 |
inosaur | -4.387 |
Cerberus | -4.359 |
copyrighted | -4.256 |
Token | Split |
Token ID | 27758 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
nesota | +11.638 |
olate | +11.569 |
vale | +11.383 |
onset | +10.817 |
lication | +10.691 |
Neg logit contributions | |
THING | -11.879 |
IMAGES | -11.077 |
inosaur | -10.709 |
copyrighted | -10.640 |
ModLoader | -10.379 |
Token | due |
Token ID | 2233 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
nesota | +7.130 |
olate | +6.796 |
vale | +6.563 |
onset | +6.484 |
jected | +6.446 |
Neg logit contributions | |
THING | -6.158 |
IMAGES | -5.577 |
inosaur | -5.574 |
Cerberus | -5.514 |
ModLoader | -5.402 |
Token | to |
Token ID | 284 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
nesota | +2.664 |
olate | +2.486 |
vale | +2.391 |
jected | +2.343 |
lication | +2.333 |
Neg logit contributions | |
THING | -2.912 |
IMAGES | -2.672 |
Cerberus | -2.670 |
inosaur | -2.640 |
copyrighted | -2.580 |
Token | visa |
Token ID | 14552 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
nesota | +0.931 |
olate | +0.878 |
vale | +0.851 |
jected | +0.839 |
lication | +0.836 |
Neg logit contributions | |
THING | -0.673 |
Cerberus | -0.605 |
IMAGES | -0.603 |
inosaur | -0.593 |
copyrighted | -0.578 |
Token | issues |
Token ID | 2428 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
nesota | +3.684 |
olate | +3.470 |
vale | +3.342 |
jected | +3.285 |
lication | +3.282 |
Neg logit contributions | |
THING | -3.642 |
IMAGES | -3.359 |
Cerberus | -3.345 |
inosaur | -3.322 |
copyrighted | -3.221 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
nesota | +0.666 |
olate | +0.628 |
vale | +0.608 |
jected | +0.597 |
lication | +0.597 |
Neg logit contributions | |
THING | -0.497 |
Cerberus | -0.448 |
IMAGES | -0.445 |
inosaur | -0.439 |
copyrighted | -0.433 |
Token | a |
Token ID | 257 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
nesota | +1.503 |
olate | +1.421 |
vale | +1.378 |
jected | +1.359 |
lication | +1.356 |
Neg logit contributions | |
THING | -1.008 |
Cerberus | -0.902 |
IMAGES | -0.898 |
inosaur | -0.885 |
copyrighted | -0.863 |
Token | warm |
Token ID | 5814 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
nesota | +1.399 |
olate | +1.307 |
vale | +1.263 |
lication | +1.242 |
jected | +1.240 |
Neg logit contributions | |
THING | -1.282 |
Cerberus | -1.171 |
IMAGES | -1.163 |
inosaur | -1.147 |
copyrighted | -1.130 |
Token | , |
Token ID | 11 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
nesota | +8.471 |
olate | +8.086 |
onset | +7.880 |
vale | +7.851 |
jected | +7.553 |
Neg logit contributions | |
THING | -9.791 |
IMAGES | -9.158 |
Cerberus | -9.002 |
inosaur | -8.969 |
ModLoader | -8.756 |
Token | dry |
Token ID | 5894 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
nesota | +2.327 |
olate | +2.183 |
vale | +2.101 |
jected | +2.069 |
lication | +2.051 |
Neg logit contributions | |
THING | -2.282 |
IMAGES | -2.081 |
Cerberus | -2.080 |
inosaur | -2.058 |
copyrighted | -1.994 |
Token | spring |
Token ID | 6076 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
nesota | +2.332 |
olate | +2.160 |
vale | +2.075 |
lication | +2.046 |
jected | +2.045 |
Neg logit contributions | |
THING | -2.515 |
Cerberus | -2.305 |
IMAGES | -2.295 |
inosaur | -2.265 |
copyrighted | -2.234 |
Token | that |
Token ID | 326 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
nesota | +12.064 |
olate | +11.876 |
onset | +11.873 |
vale | +11.449 |
occ | +10.981 |
Neg logit contributions | |
THING | -11.683 |
IMAGES | -10.693 |
inosaur | -10.578 |
Cerberus | -10.553 |
ModLoader | -10.422 |
Token | has |
Token ID | 468 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
nesota | +5.749 |
olate | +5.380 |
vale | +5.269 |
jected | +5.161 |
onset | +5.160 |
Neg logit contributions | |
THING | -4.991 |
inosaur | -4.515 |
Cerberus | -4.477 |
IMAGES | -4.459 |
ModLoader | -4.298 |
Token | them |
Token ID | 606 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
nesota | +2.778 |
olate | +2.619 |
vale | +2.529 |
jected | +2.503 |
lication | +2.474 |
Neg logit contributions | |
THING | -2.270 |
IMAGES | -2.047 |
inosaur | -2.040 |
Cerberus | -2.037 |
ModLoader | -1.949 |
Token | well |
Token ID | 880 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
THING | +0.201 |
Cerberus | +0.182 |
IMAGES | +0.181 |
inosaur | +0.178 |
copyrighted | +0.176 |
Neg logit contributions | |
nesota | -0.244 |
olate | -0.229 |
vale | -0.221 |
lication | -0.218 |
jected | -0.218 |
Token | ahead |
Token ID | 4058 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
nesota | +2.451 |
olate | +2.309 |
vale | +2.240 |
jected | +2.205 |
lication | +2.194 |
Neg logit contributions | |
THING | -1.868 |
Cerberus | -1.685 |
IMAGES | -1.683 |
inosaur | -1.663 |
copyrighted | -1.608 |
Token | Huang |
Token ID | 31663 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
nesota | +2.958 |
olate | +2.797 |
vale | +2.713 |
jected | +2.661 |
lication | +2.649 |
Neg logit contributions | |
THING | -2.283 |
IMAGES | -2.050 |
Cerberus | -2.041 |
inosaur | -2.021 |
copyrighted | -1.972 |
Token | , |
Token ID | 11 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
nesota | +0.346 |
olate | +0.323 |
vale | +0.310 |
jected | +0.306 |
lication | +0.305 |
Neg logit contributions | |
THING | -0.341 |
Cerberus | -0.312 |
IMAGES | -0.310 |
inosaur | -0.307 |
copyrighted | -0.300 |
Token | a |
Token ID | 257 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
THING | +1.693 |
Cerberus | +1.516 |
IMAGES | +1.480 |
inosaur | +1.455 |
copyrighted | +1.424 |
Neg logit contributions | |
nesota | -3.019 |
olate | -2.879 |
vale | -2.787 |
lication | -2.757 |
jected | -2.745 |
Token | junior |
Token ID | 13430 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
THING | +0.132 |
Cerberus | +0.122 |
IMAGES | +0.121 |
inosaur | +0.119 |
copyrighted | +0.117 |
Neg logit contributions | |
nesota | -0.131 |
olate | -0.122 |
vale | -0.117 |
lication | -0.116 |
jected | -0.115 |
Token | computer |
Token ID | 3644 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
nesota | +11.526 |
onset | +10.986 |
olate | +10.600 |
vale | +10.535 |
jected | +10.368 |
Neg logit contributions | |
THING | -11.444 |
inosaur | -10.817 |
IMAGES | -10.474 |
ModLoader | -10.332 |
Cerberus | -10.070 |
Token | science |
Token ID | 3783 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
nesota | +3.845 |
olate | +3.589 |
vale | +3.462 |
jected | +3.395 |
lication | +3.363 |
Neg logit contributions | |
THING | -3.890 |
IMAGES | -3.555 |
Cerberus | -3.553 |
inosaur | -3.518 |
copyrighted | -3.416 |
Token | major |
Token ID | 1688 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
nesota | +10.339 |
olate | +9.673 |
onset | +9.622 |
jected | +9.353 |
vale | +9.173 |
Neg logit contributions | |
THING | -12.998 |
inosaur | -12.443 |
IMAGES | -12.103 |
ModLoader | -12.033 |
Cerberus | -11.736 |
Token | ; |
Token ID | 26 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
nesota | +5.165 |
olate | +4.879 |
vale | +4.702 |
jected | +4.628 |
onset | +4.564 |
Neg logit contributions | |
THING | -4.669 |
IMAGES | -4.266 |
inosaur | -4.224 |
Cerberus | -4.211 |
ModLoader | -4.102 |
Token | Michael |
Token ID | 3899 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
THING | +0.546 |
Cerberus | +0.498 |
IMAGES | +0.492 |
inosaur | +0.483 |
copyrighted | +0.474 |
Neg logit contributions | |
nesota | -0.743 |
olate | -0.705 |
vale | -0.678 |
jected | -0.672 |
lication | -0.670 |
Token | Shin |
Token ID | 11466 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
THING | +0.492 |
Cerberus | +0.453 |
IMAGES | +0.446 |
inosaur | +0.441 |
copyrighted | +0.426 |
Neg logit contributions | |
nesota | -0.645 |
olate | -0.600 |
vale | -0.579 |
jected | -0.576 |
lication | -0.575 |
Token | , |
Token ID | 11 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
nesota | +2.844 |
olate | +2.630 |
vale | +2.534 |
jected | +2.485 |
lication | +2.467 |
Neg logit contributions | |
THING | -3.376 |
IMAGES | -3.116 |
Cerberus | -3.100 |
inosaur | -3.069 |
copyrighted | -3.004 |
Token | ; |
Token ID | 26 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
nesota | +5.811 |
olate | +5.518 |
vale | +5.327 |
jected | +5.263 |
onset | +5.189 |
Neg logit contributions | |
THING | -4.700 |
IMAGES | -4.281 |
inosaur | -4.238 |
Cerberus | -4.200 |
ModLoader | -4.111 |
Token | Kevin |
Token ID | 7939 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
THING | +0.408 |
Cerberus | +0.372 |
IMAGES | +0.368 |
inosaur | +0.362 |
copyrighted | +0.355 |
Neg logit contributions | |
nesota | -0.554 |
olate | -0.525 |
vale | -0.505 |
jected | -0.500 |
lication | -0.499 |
Token | Huang |
Token ID | 31663 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
nesota | +2.958 |
olate | +2.797 |
vale | +2.713 |
jected | +2.661 |
lication | +2.649 |
Neg logit contributions | |
THING | -2.283 |
IMAGES | -2.050 |
Cerberus | -2.041 |
inosaur | -2.021 |
copyrighted | -1.972 |
Token | , |
Token ID | 11 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
nesota | +0.346 |
olate | +0.323 |
vale | +0.310 |
jected | +0.306 |
lication | +0.305 |
Neg logit contributions | |
THING | -0.341 |
Cerberus | -0.312 |
IMAGES | -0.310 |
inosaur | -0.307 |
copyrighted | -0.300 |
Token | a |
Token ID | 257 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
THING | +1.693 |
Cerberus | +1.516 |
IMAGES | +1.480 |
inosaur | +1.455 |
copyrighted | +1.424 |
Neg logit contributions | |
nesota | -3.019 |
olate | -2.879 |
vale | -2.787 |
lication | -2.757 |
jected | -2.745 |
Token | junior |
Token ID | 13430 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
THING | +0.132 |
Cerberus | +0.122 |
IMAGES | +0.121 |
inosaur | +0.119 |
copyrighted | +0.117 |
Neg logit contributions | |
nesota | -0.131 |
olate | -0.122 |
vale | -0.117 |
lication | -0.116 |
jected | -0.115 |
Token | computer |
Token ID | 3644 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
nesota | +11.526 |
onset | +10.986 |
olate | +10.600 |
vale | +10.535 |
jected | +10.368 |
Neg logit contributions | |
THING | -11.444 |
inosaur | -10.817 |
IMAGES | -10.474 |
ModLoader | -10.332 |
Cerberus | -10.070 |
Token | science |
Token ID | 3783 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
nesota | +3.845 |
olate | +3.589 |
vale | +3.462 |
jected | +3.395 |
lication | +3.363 |
Neg logit contributions | |
THING | -3.890 |
IMAGES | -3.555 |
Cerberus | -3.553 |
inosaur | -3.518 |
copyrighted | -3.416 |
Token | major |
Token ID | 1688 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
nesota | +10.339 |
olate | +9.673 |
onset | +9.622 |
jected | +9.353 |
vale | +9.173 |
Neg logit contributions | |
THING | -12.998 |
inosaur | -12.443 |
IMAGES | -12.103 |
ModLoader | -12.033 |
Cerberus | -11.736 |
Token | ; |
Token ID | 26 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
nesota | +5.165 |
olate | +4.879 |
vale | +4.702 |
jected | +4.628 |
onset | +4.564 |
Neg logit contributions | |
THING | -4.669 |
IMAGES | -4.266 |
inosaur | -4.224 |
Cerberus | -4.211 |
ModLoader | -4.102 |
Token | Michael |
Token ID | 3899 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
THING | +0.546 |
Cerberus | +0.498 |
IMAGES | +0.492 |
inosaur | +0.483 |
copyrighted | +0.474 |
Neg logit contributions | |
nesota | -0.743 |
olate | -0.705 |
vale | -0.678 |
jected | -0.672 |
lication | -0.670 |
Token | superb |
Token ID | 21840 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
nesota | +2.019 |
olate | +1.917 |
vale | +1.848 |
jected | +1.826 |
lication | +1.813 |
Neg logit contributions | |
THING | -1.485 |
IMAGES | -1.336 |
Cerberus | -1.331 |
inosaur | -1.320 |
copyrighted | -1.268 |
Token | ; |
Token ID | 26 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
nesota | +0.494 |
olate | +0.458 |
vale | +0.445 |
jected | +0.435 |
lication | +0.432 |
Neg logit contributions | |
THING | -0.485 |
Cerberus | -0.443 |
IMAGES | -0.441 |
inosaur | -0.435 |
copyrighted | -0.428 |
Token | a |
Token ID | 257 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
nesota | +4.508 |
olate | +4.276 |
vale | +4.104 |
jected | +4.062 |
onset | +4.026 |
Neg logit contributions | |
THING | -3.470 |
IMAGES | -3.146 |
inosaur | -3.096 |
Cerberus | -3.079 |
copyrighted | -2.990 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
nesota | +1.428 |
olate | +1.338 |
vale | +1.294 |
jected | +1.270 |
lication | +1.269 |
Neg logit contributions | |
THING | -1.253 |
Cerberus | -1.140 |
IMAGES | -1.133 |
inosaur | -1.120 |
copyrighted | -1.096 |
Token | of |
Token ID | 286 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
nesota | +5.370 |
olate | +5.080 |
vale | +4.992 |
lication | +4.937 |
jected | +4.909 |
Neg logit contributions | |
THING | -3.269 |
IMAGES | -2.988 |
Cerberus | -2.894 |
inosaur | -2.859 |
copyrighted | -2.766 |
Token | spring |
Token ID | 6076 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
THING | +1.450 |
Cerberus | +1.338 |
IMAGES | +1.298 |
inosaur | +1.291 |
copyrighted | +1.279 |
Neg logit contributions | |
nesota | -1.643 |
olate | -1.534 |
vale | -1.489 |
lication | -1.458 |
jected | -1.456 |
Token | roll |
Token ID | 4836 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
nesota | +12.528 |
olate | +12.234 |
vale | +12.047 |
lication | +11.543 |
onset | +11.471 |
Neg logit contributions | |
THING | -10.883 |
IMAGES | -10.555 |
inosaur | -9.819 |
Cerberus | -9.703 |
copyrighted | -9.586 |
Token | — |
Token ID | 851 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
nesota | +3.655 |
olate | +3.468 |
vale | +3.348 |
jected | +3.304 |
lication | +3.302 |
Neg logit contributions | |
THING | -2.631 |
IMAGES | -2.369 |
Cerberus | -2.346 |
inosaur | -2.322 |
copyrighted | -2.252 |
Token | � |
Token ID | 564 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
nesota | +3.800 |
olate | +3.602 |
vale | +3.466 |
jected | +3.439 |
lication | +3.412 |
Neg logit contributions | |
THING | -2.713 |
IMAGES | -2.458 |
Cerberus | -2.413 |
inosaur | -2.397 |
copyrighted | -2.313 |
Token | � |
Token ID | 250 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
nesota | +2.705 |
olate | +2.533 |
vale | +2.428 |
jected | +2.402 |
lication | +2.374 |
Neg logit contributions | |
THING | -2.716 |
Cerberus | -2.482 |
IMAGES | -2.479 |
inosaur | -2.446 |
copyrighted | -2.379 |
Token | t |
Token ID | 83 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
nesota | +4.112 |
olate | +3.863 |
vale | +3.746 |
jected | +3.677 |
lication | +3.647 |
Neg logit contributions | |
THING | -3.644 |
IMAGES | -3.363 |
Cerberus | -3.328 |
inosaur | -3.267 |
copyrighted | -3.198 |
Token | Fall |
Token ID | 7218 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
nesota | +5.289 |
olate | +5.003 |
vale | +4.809 |
onset | +4.737 |
jected | +4.731 |
Neg logit contributions | |
THING | -5.387 |
inosaur | -4.919 |
IMAGES | -4.880 |
Cerberus | -4.857 |
ModLoader | -4.720 |
Token | , |
Token ID | 11 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
nesota | +7.707 |
olate | +7.509 |
vale | +7.331 |
onset | +7.071 |
jected | +7.031 |
Neg logit contributions | |
THING | -6.372 |
Cerberus | -5.744 |
IMAGES | -5.683 |
inosaur | -5.670 |
copyrighted | -5.484 |
Token | Winter |
Token ID | 10633 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
THING | +0.248 |
Cerberus | +0.226 |
IMAGES | +0.224 |
inosaur | +0.221 |
copyrighted | +0.217 |
Neg logit contributions | |
nesota | -0.314 |
olate | -0.294 |
vale | -0.285 |
jected | -0.281 |
lication | -0.281 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
nesota | +6.859 |
olate | +6.560 |
vale | +6.438 |
onset | +6.106 |
lication | +5.940 |
Neg logit contributions | |
THING | -9.784 |
IMAGES | -9.052 |
inosaur | -8.992 |
Cerberus | -8.968 |
copyrighted | -8.825 |
Token | and |
Token ID | 290 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
THING | +0.041 |
Cerberus | +0.037 |
IMAGES | +0.037 |
inosaur | +0.037 |
copyrighted | +0.036 |
Neg logit contributions | |
nesota | -0.055 |
olate | -0.052 |
vale | -0.050 |
jected | -0.050 |
lication | -0.050 |
Token | Spring |
Token ID | 8225 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
nesota | +3.097 |
olate | +2.928 |
vale | +2.832 |
jected | +2.786 |
lication | +2.776 |
Neg logit contributions | |
THING | -2.372 |
IMAGES | -2.132 |
Cerberus | -2.131 |
inosaur | -2.108 |
copyrighted | -2.046 |
Token | , |
Token ID | 11 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
olate | +11.870 |
nesota | +11.734 |
vale | +11.718 |
onset | +11.381 |
occ | +10.858 |
Neg logit contributions | |
THING | -10.865 |
inosaur | -9.799 |
Cerberus | -9.630 |
IMAGES | -9.490 |
ModLoader | -9.392 |
Token | and |
Token ID | 290 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
nesota | +0.385 |
olate | +0.365 |
vale | +0.354 |
jected | +0.349 |
lication | +0.348 |
Neg logit contributions | |
THING | -0.252 |
Cerberus | -0.225 |
IMAGES | -0.225 |
inosaur | -0.221 |
copyrighted | -0.215 |
Token | lead |
Token ID | 1085 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
nesota | +2.188 |
olate | +2.061 |
vale | +1.992 |
jected | +1.959 |
lication | +1.950 |
Neg logit contributions | |
THING | -1.833 |
IMAGES | -1.659 |
Cerberus | -1.657 |
inosaur | -1.642 |
copyrighted | -1.593 |
Token | up |
Token ID | 510 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
nesota | +1.981 |
olate | +1.856 |
vale | +1.791 |
jected | +1.762 |
lication | +1.754 |
Neg logit contributions | |
THING | -1.851 |
Cerberus | -1.686 |
IMAGES | -1.684 |
inosaur | -1.664 |
copyrighted | -1.625 |
Token | to |
Token ID | 284 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
THING | +1.392 |
Cerberus | +1.273 |
inosaur | +1.266 |
IMAGES | +1.266 |
copyrighted | +1.226 |
Neg logit contributions | |
nesota | -1.410 |
olate | -1.312 |
vale | -1.264 |
lication | -1.241 |
jected | -1.240 |
Token | was |
Token ID | 373 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
nesota | +0.821 |
olate | +0.772 |
vale | +0.747 |
jected | +0.735 |
lication | +0.731 |
Neg logit contributions | |
THING | -0.655 |
Cerberus | -0.591 |
IMAGES | -0.587 |
inosaur | -0.582 |
copyrighted | -0.569 |
Token | an |
Token ID | 281 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
nesota | +1.322 |
olate | +1.236 |
vale | +1.195 |
jected | +1.173 |
lication | +1.169 |
Neg logit contributions | |
THING | -1.227 |
Cerberus | -1.120 |
IMAGES | -1.114 |
inosaur | -1.102 |
copyrighted | -1.079 |
Token | all |
Token ID | 477 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
nesota | +1.024 |
olate | +0.955 |
vale | +0.921 |
jected | +0.903 |
lication | +0.898 |
Neg logit contributions | |
THING | -1.036 |
Cerberus | -0.947 |
IMAGES | -0.939 |
inosaur | -0.935 |
copyrighted | -0.914 |
Token | ogene |
Token ID | 20878 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
THING | +5.408 |
Cerberus | +5.087 |
inosaur | +5.021 |
IMAGES | +4.957 |
copyrighted | +4.874 |
Neg logit contributions | |
nesota | -4.812 |
vale | -4.366 |
olate | -4.349 |
lication | -4.241 |
jected | -4.163 |
Token | ic |
Token ID | 291 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
nesota | +1.605 |
olate | +1.463 |
vale | +1.389 |
jected | +1.355 |
lication | +1.347 |
Neg logit contributions | |
THING | -2.771 |
Cerberus | -2.583 |
IMAGES | -2.580 |
inosaur | -2.558 |
copyrighted | -2.512 |
Token | stem |
Token ID | 10717 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
nesota | +4.748 |
olate | +4.440 |
vale | +4.267 |
jected | +4.236 |
lication | +4.206 |
Neg logit contributions | |
THING | -4.724 |
IMAGES | -4.356 |
Cerberus | -4.309 |
inosaur | -4.280 |
copyrighted | -4.157 |
Token | cell |
Token ID | 2685 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
nesota | +9.265 |
olate | +8.842 |
jected | +8.666 |
jection | +8.559 |
lication | +8.421 |
Neg logit contributions | |
IMAGES | -14.186 |
THING | -14.072 |
ModLoader | -13.329 |
inosaur | -13.016 |
Cerberus | -12.928 |
Token | transplant |
Token ID | 23319 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
nesota | +2.364 |
olate | +2.186 |
vale | +2.093 |
jected | +2.041 |
lication | +2.040 |
Neg logit contributions | |
THING | -3.073 |
Cerberus | -2.844 |
IMAGES | -2.820 |
inosaur | -2.802 |
copyrighted | -2.757 |
Token | — |
Token ID | 851 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
nesota | +4.125 |
olate | +3.859 |
vale | +3.696 |
jected | +3.672 |
lication | +3.650 |
Neg logit contributions | |
THING | -4.300 |
IMAGES | -3.979 |
Cerberus | -3.918 |
inosaur | -3.901 |
ModLoader | -3.811 |
Token | a |
Token ID | 257 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
nesota | +1.605 |
olate | +1.518 |
vale | +1.472 |
jected | +1.452 |
lication | +1.446 |
Neg logit contributions | |
THING | -1.094 |
IMAGES | -0.980 |
Cerberus | -0.978 |
inosaur | -0.964 |
copyrighted | -0.933 |
Token | donation |
Token ID | 13784 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
THING | +0.884 |
Cerberus | +0.817 |
copyrighted | +0.798 |
inosaur | +0.798 |
IMAGES | +0.796 |
Neg logit contributions | |
nesota | -0.722 |
olate | -0.663 |
vale | -0.644 |
lication | -0.623 |
jected | -0.615 |
Token | he |
Token ID | 339 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
THING | +0.980 |
Cerberus | +0.896 |
IMAGES | +0.889 |
copyrighted | +0.863 |
inosaur | +0.862 |
Neg logit contributions | |
nesota | -1.314 |
olate | -1.234 |
vale | -1.194 |
jected | -1.177 |
lication | -1.169 |
Token | should |
Token ID | 815 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
THING | +0.004 |
IMAGES | +0.004 |
Cerberus | +0.004 |
inosaur | +0.004 |
copyrighted | +0.004 |
Neg logit contributions | |
nesota | -0.005 |
olate | -0.005 |
vale | -0.004 |
jected | -0.004 |
lication | -0.004 |
Token | be |
Token ID | 307 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
nesota | +4.834 |
olate | +4.490 |
vale | +4.303 |
jected | +4.183 |
lication | +4.183 |
Neg logit contributions | |
THING | -6.736 |
Cerberus | -6.218 |
IMAGES | -6.199 |
inosaur | -6.158 |
ModLoader | -6.003 |
Token | in |
Token ID | 287 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
nesota | +1.378 |
olate | +1.304 |
vale | +1.264 |
jected | +1.246 |
lication | +1.242 |
Neg logit contributions | |
THING | -0.934 |
Cerberus | -0.834 |
IMAGES | -0.833 |
inosaur | -0.822 |
copyrighted | -0.797 |
Token | a |
Token ID | 257 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
nesota | +2.540 |
olate | +2.400 |
vale | +2.327 |
jected | +2.294 |
lication | +2.286 |
Neg logit contributions | |
THING | -1.765 |
Cerberus | -1.580 |
IMAGES | -1.578 |
inosaur | -1.555 |
copyrighted | -1.511 |
Token | provincial |
Token ID | 15818 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
nesota | +1.862 |
olate | +1.741 |
vale | +1.678 |
jected | +1.648 |
lication | +1.642 |
Neg logit contributions | |
THING | -1.866 |
Cerberus | -1.707 |
IMAGES | -1.704 |
inosaur | -1.684 |
copyrighted | -1.646 |
Token | jail |
Token ID | 7356 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
nesota | +9.923 |
olate | +9.541 |
onset | +9.062 |
vale | +9.059 |
jected | +8.980 |
Neg logit contributions | |
THING | -12.870 |
inosaur | -12.084 |
ModLoader | -11.963 |
IMAGES | -11.838 |
Cerberus | -11.648 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
THING | +0.318 |
Cerberus | +0.290 |
IMAGES | +0.288 |
inosaur | +0.285 |
copyrighted | +0.282 |
Neg logit contributions | |
nesota | -0.350 |
olate | -0.326 |
vale | -0.316 |
jected | -0.311 |
lication | -0.309 |
Token |
|
Token ID | 198 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
nesota | +0.943 |
olate | +0.884 |
vale | +0.851 |
jected | +0.839 |
lication | +0.834 |
Neg logit contributions | |
THING | -0.861 |
IMAGES | -0.785 |
Cerberus | -0.784 |
inosaur | -0.771 |
copyrighted | -0.754 |
Token |
|
Token ID | 198 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
THING | +0.111 |
IMAGES | +0.101 |
Cerberus | +0.101 |
inosaur | +0.099 |
copyrighted | +0.097 |
Neg logit contributions | |
nesota | -0.124 |
olate | -0.116 |
vale | -0.111 |
jected | -0.110 |
lication | -0.110 |
Token | Law |
Token ID | 16966 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
nesota | +0.222 |
olate | +0.206 |
vale | +0.197 |
jected | +0.194 |
onset | +0.192 |
Neg logit contributions | |
THING | -0.223 |
IMAGES | -0.201 |
inosaur | -0.198 |
Cerberus | -0.198 |
copyrighted | -0.194 |
Token | for |
Token ID | 329 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
nesota | +4.473 |
olate | +4.203 |
vale | +4.092 |
lication | +4.046 |
jected | +4.031 |
Neg logit contributions | |
THING | -4.154 |
IMAGES | -3.820 |
Cerberus | -3.798 |
inosaur | -3.730 |
ModLoader | -3.627 |
Token | a |
Token ID | 257 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
nesota | +0.817 |
olate | +0.766 |
vale | +0.738 |
jected | +0.726 |
lication | +0.723 |
Neg logit contributions | |
THING | -0.741 |
Cerberus | -0.675 |
IMAGES | -0.673 |
inosaur | -0.663 |
copyrighted | -0.650 |
Token | transfer |
Token ID | 4351 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
nesota | +0.551 |
olate | +0.515 |
vale | +0.496 |
jected | +0.487 |
lication | +0.487 |
Neg logit contributions | |
THING | -0.505 |
Cerberus | -0.462 |
IMAGES | -0.459 |
inosaur | -0.449 |
copyrighted | -0.445 |
Token | to |
Token ID | 284 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
nesota | +1.927 |
olate | +1.808 |
vale | +1.746 |
jected | +1.717 |
lication | +1.711 |
Neg logit contributions | |
THING | -1.721 |
Cerberus | -1.565 |
IMAGES | -1.562 |
inosaur | -1.543 |
copyrighted | -1.506 |
Token | a |
Token ID | 257 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
nesota | +3.381 |
olate | +3.204 |
vale | +3.102 |
jected | +3.053 |
lication | +3.041 |
Neg logit contributions | |
THING | -2.429 |
IMAGES | -2.168 |
Cerberus | -2.164 |
inosaur | -2.156 |
copyrighted | -2.074 |
Token | provincial |
Token ID | 15818 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
nesota | +1.631 |
olate | +1.526 |
vale | +1.471 |
jected | +1.447 |
lication | +1.439 |
Neg logit contributions | |
THING | -1.606 |
Cerberus | -1.464 |
IMAGES | -1.464 |
inosaur | -1.450 |
copyrighted | -1.412 |
Token | jail |
Token ID | 7356 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
nesota | +9.807 |
olate | +9.332 |
onset | +9.000 |
vale | +8.977 |
jected | +8.899 |
Neg logit contributions | |
THING | -13.055 |
inosaur | -12.286 |
ModLoader | -12.130 |
IMAGES | -12.019 |
Cerberus | -11.613 |
Token | last |
Token ID | 938 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
THING | +0.077 |
Cerberus | +0.069 |
IMAGES | +0.068 |
inosaur | +0.067 |
copyrighted | +0.066 |
Neg logit contributions | |
nesota | -0.108 |
olate | -0.102 |
vale | -0.099 |
jected | -0.097 |
lication | -0.097 |
Token | fall |
Token ID | 2121 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
nesota | +1.104 |
olate | +1.035 |
vale | +0.997 |
jected | +0.979 |
lication | +0.977 |
Neg logit contributions | |
THING | -1.046 |
Cerberus | -0.956 |
IMAGES | -0.953 |
inosaur | -0.939 |
copyrighted | -0.924 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
nesota | +6.211 |
olate | +5.830 |
vale | +5.712 |
jected | +5.614 |
lication | +5.560 |
Neg logit contributions | |
THING | -6.702 |
IMAGES | -6.161 |
Cerberus | -6.064 |
inosaur | -6.038 |
ModLoader | -6.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
nesota | +0.437 |
olate | +0.408 |
vale | +0.392 |
jected | +0.386 |
lication | +0.385 |
Neg logit contributions | |
THING | -0.419 |
Cerberus | -0.386 |
IMAGES | -0.385 |
inosaur | -0.375 |
copyrighted | -0.367 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
nesota | +1.848 |
olate | +1.732 |
vale | +1.670 |
jected | +1.643 |
lication | +1.636 |
Neg logit contributions | |
THING | -1.748 |
Cerberus | -1.592 |
IMAGES | -1.592 |
inosaur | -1.573 |
copyrighted | -1.535 |
Token | annoy |
Token ID | 10072 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
nesota | +5.127 |
olate | +4.909 |
onset | +4.727 |
jected | +4.694 |
vale | +4.680 |
Neg logit contributions | |
THING | -4.457 |
IMAGES | -4.034 |
inosaur | -3.981 |
Cerberus | -3.954 |
ModLoader | -3.821 |
Token | ingly |
Token ID | 4420 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
nesota | +0.556 |
olate | +0.525 |
vale | +0.510 |
lication | +0.503 |
jected | +0.503 |
Neg logit contributions | |
THING | -0.296 |
Cerberus | -0.260 |
IMAGES | -0.258 |
inosaur | -0.256 |
copyrighted | -0.247 |
Token | self |
Token ID | 2116 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
nesota | +0.888 |
olate | +0.834 |
vale | +0.806 |
jected | +0.793 |
lication | +0.790 |
Neg logit contributions | |
THING | -0.765 |
Cerberus | -0.694 |
IMAGES | -0.693 |
inosaur | -0.684 |
copyrighted | -0.667 |
Token | - |
Token ID | 12 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
THING | +0.388 |
Cerberus | +0.361 |
IMAGES | +0.358 |
inosaur | +0.356 |
copyrighted | +0.352 |
Neg logit contributions | |
nesota | -0.290 |
olate | -0.263 |
vale | -0.254 |
lication | -0.248 |
jected | -0.246 |
Token | conf |
Token ID | 10414 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
nesota | +3.107 |
olate | +2.926 |
jected | +2.799 |
vale | +2.786 |
lication | +2.722 |
Neg logit contributions | |
THING | -3.656 |
IMAGES | -3.387 |
Cerberus | -3.368 |
inosaur | -3.306 |
copyrighted | -3.253 |
Token | ident |
Token ID | 738 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
olate | +5.933 |
nesota | +5.649 |
jected | +5.433 |
lication | +4.993 |
dn | +4.876 |
Neg logit contributions | |
THING | -17.791 |
ModLoader | -16.991 |
IMAGES | -16.802 |
Cerberus | -16.505 |
ドラゴン | -16.091 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
nesota | +5.181 |
olate | +4.917 |
vale | +4.657 |
jected | +4.583 |
onset | +4.564 |
Neg logit contributions | |
THING | -6.501 |
IMAGES | -5.979 |
inosaur | -5.954 |
Cerberus | -5.878 |
ModLoader | -5.761 |
Token | Stephen |
Token ID | 7970 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
nesota | +0.669 |
olate | +0.632 |
vale | +0.613 |
jected | +0.604 |
lication | +0.603 |
Neg logit contributions | |
THING | -0.455 |
Cerberus | -0.408 |
IMAGES | -0.406 |
inosaur | -0.400 |
copyrighted | -0.389 |
Token | is |
Token ID | 318 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
nesota | +6.237 |
olate | +5.900 |
vale | +5.681 |
onset | +5.529 |
jected | +5.525 |
Neg logit contributions | |
THING | -5.789 |
IMAGES | -5.259 |
inosaur | -5.194 |
Cerberus | -5.155 |
ModLoader | -5.022 |
Token | divided |
Token ID | 9086 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
nesota | +2.853 |
olate | +2.713 |
vale | +2.593 |
jected | +2.575 |
onset | +2.557 |
Neg logit contributions | |
THING | -2.389 |
IMAGES | -2.177 |
Cerberus | -2.146 |
inosaur | -2.146 |
copyrighted | -2.061 |
Token | health |
Token ID | 1535 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
THING | +1.714 |
IMAGES | +1.562 |
Cerberus | +1.556 |
copyrighted | +1.535 |
inosaur | +1.474 |
Neg logit contributions | |
nesota | -2.275 |
olate | -2.135 |
vale | -2.092 |
lication | -2.044 |
jected | -2.029 |
Token | care |
Token ID | 1337 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
nesota | +0.991 |
olate | +0.932 |
vale | +0.898 |
jected | +0.882 |
lication | +0.879 |
Neg logit contributions | |
THING | -0.954 |
IMAGES | -0.874 |
Cerberus | -0.873 |
inosaur | -0.858 |
copyrighted | -0.844 |
Token | is |
Token ID | 318 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
THING | +0.280 |
Cerberus | +0.253 |
IMAGES | +0.252 |
inosaur | +0.245 |
copyrighted | +0.244 |
Neg logit contributions | |
nesota | -0.370 |
olate | -0.349 |
vale | -0.338 |
jected | -0.334 |
lication | -0.331 |
Token | primarily |
Token ID | 7525 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
nesota | +1.305 |
olate | +1.234 |
vale | +1.189 |
jected | +1.174 |
lication | +1.167 |
Neg logit contributions | |
THING | -1.025 |
IMAGES | -0.927 |
Cerberus | -0.923 |
inosaur | -0.915 |
copyrighted | -0.882 |
Token | a |
Token ID | 257 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
THING | +1.867 |
Cerberus | +1.685 |
copyrighted | +1.644 |
IMAGES | +1.630 |
inosaur | +1.603 |
Neg logit contributions | |
nesota | -2.780 |
olate | -2.603 |
vale | -2.562 |
jected | -2.503 |
lication | -2.503 |
Token | provincial |
Token ID | 15818 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
THING | +0.598 |
Cerberus | +0.547 |
copyrighted | +0.532 |
IMAGES | +0.531 |
inosaur | +0.523 |
Neg logit contributions | |
nesota | -0.646 |
olate | -0.597 |
vale | -0.582 |
lication | -0.569 |
jected | -0.568 |
Token | responsibility |
Token ID | 5798 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
nesota | +9.970 |
olate | +9.723 |
onset | +9.556 |
vale | +9.280 |
lication | +9.232 |
Neg logit contributions | |
THING | -12.005 |
IMAGES | -11.848 |
inosaur | -11.731 |
ModLoader | -11.463 |
Cerberus | -11.354 |
Token | delivered |
Token ID | 6793 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
nesota | +1.334 |
olate | +1.237 |
vale | +1.192 |
jected | +1.169 |
lication | +1.161 |
Neg logit contributions | |
THING | -1.523 |
Cerberus | -1.401 |
IMAGES | -1.396 |
inosaur | -1.380 |
copyrighted | -1.361 |
Token | at |
Token ID | 379 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
THING | +2.009 |
Cerberus | +1.778 |
IMAGES | +1.761 |
copyrighted | +1.747 |
inosaur | +1.707 |
Neg logit contributions | |
nesota | -3.587 |
olate | -3.413 |
vale | -3.319 |
lication | -3.271 |
jected | -3.255 |
Token | the |
Token ID | 262 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
nesota | +0.036 |
olate | +0.034 |
vale | +0.033 |
jected | +0.033 |
lication | +0.033 |
Neg logit contributions | |
THING | -0.026 |
Cerberus | -0.024 |
IMAGES | -0.023 |
inosaur | -0.023 |
copyrighted | -0.023 |
Token | regional |
Token ID | 7915 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
nesota | +2.081 |
olate | +1.934 |
vale | +1.856 |
jected | +1.821 |
lication | +1.815 |
Neg logit contributions | |
THING | -2.428 |
Cerberus | -2.240 |
IMAGES | -2.234 |
inosaur | -2.206 |
copyrighted | -2.168 |
Token | of |
Token ID | 286 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
THING | +3.754 |
Cerberus | +3.425 |
IMAGES | +3.363 |
inosaur | +3.229 |
copyrighted | +3.212 |
Neg logit contributions | |
nesota | -5.756 |
olate | -5.390 |
vale | -5.243 |
lication | -5.199 |
jected | -5.158 |
Token | white |
Token ID | 2330 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
THING | +1.168 |
Cerberus | +1.079 |
IMAGES | +1.058 |
copyrighted | +1.028 |
inosaur | +1.027 |
Neg logit contributions | |
nesota | -1.417 |
olate | -1.316 |
vale | -1.284 |
lication | -1.267 |
jected | -1.257 |
Token | sugar |
Token ID | 7543 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
nesota | +1.384 |
olate | +1.292 |
vale | +1.243 |
jected | +1.230 |
lication | +1.226 |
Neg logit contributions | |
THING | -1.195 |
Cerberus | -1.095 |
IMAGES | -1.077 |
inosaur | -1.065 |
copyrighted | -1.043 |
Token |
|
Token ID | 198 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
nesota | +5.153 |
olate | +4.926 |
vale | +4.705 |
jected | +4.624 |
lication | +4.583 |
Neg logit contributions | |
THING | -5.944 |
IMAGES | -5.476 |
inosaur | -5.464 |
Cerberus | -5.377 |
copyrighted | -5.272 |
Token |
|
Token ID | 198 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
THING | +0.240 |
Cerberus | +0.219 |
IMAGES | +0.218 |
inosaur | +0.215 |
copyrighted | +0.211 |
Neg logit contributions | |
nesota | -0.263 |
olate | -0.246 |
vale | -0.237 |
jected | -0.234 |
lication | -0.233 |
Token | Jun |
Token ID | 22396 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
THING | +0.244 |
Cerberus | +0.220 |
IMAGES | +0.218 |
inosaur | +0.217 |
copyrighted | +0.210 |
Neg logit contributions | |
nesota | -0.257 |
olate | -0.238 |
vale | -0.229 |
jected | -0.225 |
lication | -0.225 |
Token | iper |
Token ID | 9346 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
nesota | +8.718 |
olate | +8.140 |
vale | +7.954 |
ior | +7.799 |
iors | +7.739 |
Neg logit contributions | |
THING | -14.445 |
IMAGES | -13.979 |
ModLoader | -13.240 |
inosaur | -13.192 |
Cerberus | -13.187 |
Token | branches |
Token ID | 13737 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
nesota | +4.810 |
olate | +4.563 |
vale | +4.426 |
jected | +4.330 |
lication | +4.323 |
Neg logit contributions | |
THING | -4.128 |
IMAGES | -3.785 |
Cerberus | -3.720 |
inosaur | -3.716 |
copyrighted | -3.597 |
Token | ( |
Token ID | 357 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
nesota | +6.036 |
olate | +5.873 |
vale | +5.536 |
jected | +5.445 |
lication | +5.377 |
Neg logit contributions | |
THING | -6.695 |
IMAGES | -6.158 |
inosaur | -6.053 |
Cerberus | -6.004 |
ModLoader | -5.898 |
Token | this |
Token ID | 5661 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
nesota | +1.023 |
olate | +0.945 |
vale | +0.909 |
lication | +0.893 |
jected | +0.893 |
Neg logit contributions | |
THING | -1.127 |
Cerberus | -1.033 |
IMAGES | -1.027 |
inosaur | -1.021 |
copyrighted | -0.995 |
Token | is |
Token ID | 318 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
nesota | +1.770 |
olate | +1.660 |
vale | +1.610 |
jected | +1.588 |
lication | +1.582 |
Neg logit contributions | |
THING | -1.363 |
Cerberus | -1.230 |
IMAGES | -1.228 |
inosaur | -1.206 |
copyrighted | -1.180 |
Token | stir |
Token ID | 11240 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
THING | +0.258 |
Cerberus | +0.236 |
IMAGES | +0.235 |
inosaur | +0.230 |
copyrighted | +0.227 |
Neg logit contributions | |
nesota | -0.275 |
olate | -0.255 |
vale | -0.246 |
lication | -0.244 |
jected | -0.244 |
Token | thoroughly |
Token ID | 13770 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
nesota | +2.903 |
olate | +2.758 |
vale | +2.666 |
jected | +2.622 |
lication | +2.612 |
Neg logit contributions | |
THING | -2.233 |
IMAGES | -2.019 |
Cerberus | -2.014 |
inosaur | -1.988 |
copyrighted | -1.931 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
THING | +4.509 |
Cerberus | +4.113 |
IMAGES | +3.988 |
inosaur | +3.907 |
copyrighted | +3.876 |
Neg logit contributions | |
nesota | -6.144 |
olate | -5.533 |
vale | -5.447 |
lication | -5.389 |
jected | -5.352 |
Token | Add |
Token ID | 3060 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
nesota | +0.527 |
olate | +0.486 |
vale | +0.470 |
jected | +0.465 |
lication | +0.464 |
Neg logit contributions | |
THING | -0.526 |
Cerberus | -0.484 |
IMAGES | -0.481 |
inosaur | -0.470 |
copyrighted | -0.460 |
Token | more |
Token ID | 517 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
THING | +1.753 |
Cerberus | +1.571 |
IMAGES | +1.549 |
inosaur | +1.504 |
copyrighted | +1.485 |
Neg logit contributions | |
nesota | -2.997 |
olate | -2.782 |
vale | -2.732 |
jected | -2.699 |
lication | -2.693 |
Token | jun |
Token ID | 10891 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
THING | +2.424 |
Cerberus | +2.233 |
IMAGES | +2.201 |
copyrighted | +2.127 |
inosaur | +2.120 |
Neg logit contributions | |
nesota | -2.676 |
olate | -2.470 |
vale | -2.385 |
lication | -2.372 |
jected | -2.359 |
Token | iper |
Token ID | 9346 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
nesota | +4.864 |
olate | +4.161 |
iors | +3.858 |
vale | +3.732 |
jected | +3.661 |
Neg logit contributions | |
THING | -18.794 |
ModLoader | -18.083 |
IMAGES | -17.911 |
Cerberus | -17.474 |
copyrighted | -17.263 |
Token | infusion |
Token ID | 35547 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
nesota | +5.212 |
olate | +4.923 |
vale | +4.765 |
jected | +4.634 |
lication | +4.629 |
Neg logit contributions | |
THING | -5.080 |
IMAGES | -4.616 |
inosaur | -4.601 |
Cerberus | -4.599 |
copyrighted | -4.467 |
Token | if |
Token ID | 611 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
nesota | +3.875 |
olate | +3.673 |
vale | +3.540 |
jected | +3.456 |
lication | +3.444 |
Neg logit contributions | |
THING | -3.856 |
IMAGES | -3.508 |
inosaur | -3.507 |
Cerberus | -3.498 |
copyrighted | -3.402 |
Token | necessary |
Token ID | 3306 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
nesota | +1.987 |
olate | +1.880 |
vale | +1.827 |
jected | +1.803 |
lication | +1.797 |
Neg logit contributions | |
THING | -1.178 |
Cerberus | -1.045 |
IMAGES | -1.039 |
inosaur | -1.019 |
copyrighted | -0.991 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
nesota | +0.820 |
olate | +0.761 |
vale | +0.735 |
jected | +0.723 |
lication | +0.719 |
Neg logit contributions | |
THING | -0.814 |
Cerberus | -0.747 |
IMAGES | -0.745 |
inosaur | -0.734 |
copyrighted | -0.716 |
Token |
|
Token ID | 198 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
nesota | +1.865 |
olate | +1.751 |
vale | +1.690 |
jected | +1.655 |
lication | +1.640 |
Neg logit contributions | |
THING | -1.916 |
Cerberus | -1.754 |
IMAGES | -1.753 |
inosaur | -1.737 |
ModLoader | -1.726 |
Token | - |
Token ID | 12 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
nesota | +1.702 |
olate | +1.573 |
vale | +1.507 |
jected | +1.475 |
lication | +1.465 |
Neg logit contributions | |
THING | -2.421 |
Cerberus | -2.256 |
IMAGES | -2.254 |
inosaur | -2.225 |
copyrighted | -2.188 |
Token | Rest |
Token ID | 8324 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
nesota | +2.847 |
olate | +2.698 |
vale | +2.602 |
jected | +2.561 |
lication | +2.538 |
Neg logit contributions | |
THING | -2.393 |
IMAGES | -2.164 |
Cerberus | -2.152 |
inosaur | -2.136 |
copyrighted | -2.082 |
Token | less |
Token ID | 1203 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
nesota | +3.918 |
olate | +3.698 |
vale | +3.537 |
jected | +3.502 |
lication | +3.448 |
Neg logit contributions | |
THING | -4.053 |
IMAGES | -3.701 |
Cerberus | -3.700 |
inosaur | -3.620 |
copyrighted | -3.550 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
THING | +1.561 |
Cerberus | +1.453 |
IMAGES | +1.444 |
inosaur | +1.430 |
copyrighted | +1.401 |
Neg logit contributions | |
nesota | -1.300 |
olate | -1.190 |
vale | -1.151 |
lication | -1.126 |
jected | -1.126 |
Token | Quick |
Token ID | 12029 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
nesota | +0.747 |
olate | +0.700 |
vale | +0.678 |
jected | +0.666 |
lication | +0.666 |
Neg logit contributions | |
THING | -0.626 |
Cerberus | -0.569 |
IMAGES | -0.567 |
inosaur | -0.560 |
copyrighted | -0.546 |
Token | to |
Token ID | 284 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
nesota | +11.246 |
olate | +11.095 |
jected | +10.592 |
onset | +10.468 |
vale | +10.329 |
Neg logit contributions | |
THING | -11.601 |
IMAGES | -10.635 |
inosaur | -10.218 |
Cerberus | -10.156 |
ModLoader | -9.988 |
Token | anger |
Token ID | 8993 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
nesota | +6.391 |
olate | +6.179 |
onset | +5.855 |
vale | +5.842 |
jected | +5.747 |
Neg logit contributions | |
THING | -6.784 |
IMAGES | -6.273 |
inosaur | -6.145 |
Cerberus | -6.114 |
ModLoader | -6.066 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
THING | +1.018 |
Cerberus | +0.947 |
IMAGES | +0.935 |
inosaur | +0.923 |
copyrighted | +0.905 |
Neg logit contributions | |
nesota | -0.959 |
olate | -0.876 |
vale | -0.847 |
lication | -0.838 |
jected | -0.830 |
Token | Unt |
Token ID | 26970 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
THING | +0.475 |
Cerberus | +0.436 |
IMAGES | +0.430 |
inosaur | +0.425 |
copyrighted | +0.415 |
Neg logit contributions | |
nesota | -0.562 |
olate | -0.521 |
vale | -0.507 |
lication | -0.501 |
jected | -0.497 |
Token | rust |
Token ID | 11469 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
THING | +2.299 |
inosaur | +2.171 |
Cerberus | +2.122 |
IMAGES | +2.104 |
copyrighted | +2.041 |
Neg logit contributions | |
nesota | -2.175 |
olate | -1.934 |
vale | -1.906 |
onset | -1.845 |
lication | -1.838 |
Token | Dug |
Token ID | 27436 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
nesota | +3.185 |
olate | +3.001 |
vale | +2.901 |
jected | +2.827 |
lication | +2.802 |
Neg logit contributions | |
THING | -3.252 |
inosaur | -2.959 |
IMAGES | -2.957 |
Cerberus | -2.932 |
ModLoader | -2.922 |
Token | gan |
Token ID | 1030 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
THING | +5.233 |
Cerberus | +4.876 |
inosaur | +4.873 |
IMAGES | +4.867 |
copyrighted | +4.589 |
Neg logit contributions | |
nesota | -9.261 |
olate | -8.562 |
lication | -8.342 |
vale | -8.256 |
jected | -8.144 |
Token | Middle |
Token ID | 6046 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nesota | +0.211 |
olate | +0.198 |
vale | +0.190 |
lication | +0.188 |
jected | +0.188 |
Neg logit contributions | |
THING | -0.190 |
Cerberus | -0.174 |
IMAGES | -0.173 |
inosaur | -0.170 |
copyrighted | -0.168 |
Token | School |
Token ID | 3961 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
nesota | +3.735 |
olate | +3.505 |
vale | +3.416 |
jected | +3.344 |
lication | +3.314 |
Neg logit contributions | |
THING | -3.373 |
IMAGES | -3.054 |
Cerberus | -3.052 |
inosaur | -3.040 |
copyrighted | -2.935 |
Token | 's |
Token ID | 338 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
THING | +0.611 |
Cerberus | +0.560 |
IMAGES | +0.557 |
inosaur | +0.541 |
copyrighted | +0.540 |
Neg logit contributions | |
nesota | -0.709 |
olate | -0.668 |
vale | -0.641 |
lication | -0.633 |
jected | -0.632 |
Token | junior |
Token ID | 13430 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
THING | +0.017 |
Cerberus | +0.016 |
IMAGES | +0.016 |
inosaur | +0.015 |
copyrighted | +0.015 |
Neg logit contributions | |
nesota | -0.017 |
olate | -0.016 |
vale | -0.015 |
jected | -0.015 |
lication | -0.015 |
Token | lobbying |
Token ID | 17502 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
nesota | +11.668 |
onset | +10.671 |
vale | +10.586 |
olate | +10.531 |
iors | +10.423 |
Neg logit contributions | |
THING | -10.805 |
inosaur | -10.406 |
ModLoader | -10.169 |
IMAGES | -9.916 |
Cerberus | -9.566 |
Token | factory |
Token ID | 8860 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
nesota | +2.311 |
olate | +2.156 |
vale | +2.077 |
jected | +2.042 |
lication | +2.027 |
Neg logit contributions | |
THING | -2.416 |
IMAGES | -2.207 |
Cerberus | -2.205 |
inosaur | -2.190 |
copyrighted | -2.126 |
Token | is |
Token ID | 318 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
THING | +3.575 |
Cerberus | +3.321 |
IMAGES | +3.259 |
copyrighted | +3.239 |
inosaur | +3.178 |
Neg logit contributions | |
nesota | -4.335 |
olate | -4.067 |
lication | -3.874 |
vale | -3.849 |
jected | -3.836 |
Token | " |
Token ID | 366 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
THING | +1.082 |
Cerberus | +0.987 |
IMAGES | +0.969 |
inosaur | +0.957 |
copyrighted | +0.948 |
Neg logit contributions | |
nesota | -1.414 |
olate | -1.323 |
vale | -1.285 |
jected | -1.266 |
lication | -1.266 |
Token | serious |
Token ID | 34009 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
nesota | +0.643 |
olate | +0.596 |
vale | +0.571 |
jected | +0.561 |
lication | +0.561 |
Neg logit contributions | |
THING | -0.709 |
Cerberus | -0.649 |
IMAGES | -0.646 |
inosaur | -0.642 |
copyrighted | -0.628 |
Token | the |
Token ID | 1169 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
nesota | +0.781 |
olate | +0.729 |
vale | +0.700 |
jected | +0.688 |
lication | +0.686 |
Neg logit contributions | |
THING | -0.800 |
Cerberus | -0.727 |
IMAGES | -0.726 |
inosaur | -0.719 |
copyrighted | -0.703 |
Token | killer |
Token ID | 11868 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
THING | +0.538 |
Cerberus | +0.491 |
IMAGES | +0.485 |
inosaur | +0.477 |
copyrighted | +0.471 |
Neg logit contributions | |
nesota | -0.660 |
olate | -0.621 |
vale | -0.605 |
jected | -0.591 |
lication | -0.590 |
Token | ] |
Token ID | 60 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
THING | +6.003 |
Cerberus | +5.442 |
copyrighted | +5.355 |
inosaur | +5.240 |
IMAGES | +5.199 |
Neg logit contributions | |
nesota | -8.039 |
olate | -7.585 |
vale | -7.481 |
jected | -7.216 |
lication | -7.043 |
Token | is |
Token ID | 318 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
THING | +2.471 |
Cerberus | +2.235 |
IMAGES | +2.203 |
inosaur | +2.183 |
copyrighted | +2.163 |
Neg logit contributions | |
nesota | -3.270 |
olate | -3.088 |
vale | -2.985 |
jected | -2.936 |
lication | -2.903 |
Token | probably |
Token ID | 2192 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
THING | +1.373 |
Cerberus | +1.250 |
IMAGES | +1.209 |
copyrighted | +1.194 |
inosaur | +1.189 |
Neg logit contributions | |
nesota | -2.026 |
olate | -1.899 |
vale | -1.867 |
jected | -1.823 |
lication | -1.819 |
Token | dead |
Token ID | 2636 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
nesota | +0.510 |
olate | +0.482 |
vale | +0.468 |
jected | +0.461 |
lication | +0.460 |
Neg logit contributions | |
THING | -0.347 |
Cerberus | -0.310 |
IMAGES | -0.310 |
inosaur | -0.305 |
copyrighted | -0.296 |
Token | or |
Token ID | 393 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
THING | +6.987 |
copyrighted | +6.209 |
Cerberus | +6.196 |
inosaur | +6.079 |
IMAGES | +5.927 |
Neg logit contributions | |
nesota | -9.478 |
olate | -8.757 |
vale | -8.658 |
lication | -8.518 |
jected | -8.456 |
Token | in |
Token ID | 287 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
nesota | +0.578 |
olate | +0.546 |
vale | +0.530 |
jected | +0.522 |
lication | +0.520 |
Neg logit contributions | |
THING | -0.395 |
Cerberus | -0.353 |
IMAGES | -0.352 |
inosaur | -0.347 |
copyrighted | -0.338 |
Token | prison |
Token ID | 3770 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
nesota | +1.285 |
olate | +1.211 |
vale | +1.174 |
jected | +1.154 |
lication | +1.151 |
Neg logit contributions | |
THING | -0.973 |
Cerberus | -0.876 |
IMAGES | -0.874 |
inosaur | -0.862 |
copyrighted | -0.839 |
Token | . |
Token ID | 13 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
THING | +1.822 |
Cerberus | +1.651 |
IMAGES | +1.647 |
inosaur | +1.615 |
copyrighted | +1.603 |
Neg logit contributions | |
nesota | -2.094 |
olate | -1.963 |
vale | -1.909 |
jected | -1.880 |
lication | -1.860 |
Token | But |
Token ID | 887 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
THING | +0.237 |
Cerberus | +0.217 |
IMAGES | +0.216 |
inosaur | +0.213 |
copyrighted | +0.207 |
Neg logit contributions | |
nesota | -0.246 |
olate | -0.230 |
vale | -0.221 |
jected | -0.219 |
lication | -0.217 |
Token | no |
Token ID | 645 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
nesota | +5.000 |
olate | +4.775 |
vale | +4.599 |
jected | +4.553 |
lication | +4.531 |
Neg logit contributions | |
THING | -3.929 |
inosaur | -3.519 |
IMAGES | -3.511 |
Cerberus | -3.506 |
ModLoader | -3.403 |
Token | interaction |
Token ID | 10375 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
THING | +4.026 |
IMAGES | +3.695 |
Cerberus | +3.651 |
inosaur | +3.551 |
copyrighted | +3.533 |
Neg logit contributions | |
nesota | -3.633 |
olate | -3.362 |
vale | -3.215 |
jected | -3.159 |
lication | -3.122 |
Token | with |
Token ID | 351 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
nesota | +1.186 |
olate | +1.116 |
vale | +1.081 |
jected | +1.063 |
lication | +1.059 |
Neg logit contributions | |
THING | -0.963 |
IMAGES | -0.870 |
Cerberus | -0.870 |
inosaur | -0.857 |
copyrighted | -0.836 |
Token | GUI |
Token ID | 25757 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
THING | +0.677 |
Cerberus | +0.602 |
IMAGES | +0.601 |
inosaur | +0.583 |
copyrighted | +0.570 |
Neg logit contributions | |
nesota | -1.166 |
olate | -1.097 |
vale | -1.070 |
jected | -1.050 |
lication | -1.050 |
Token | or |
Token ID | 393 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
THING | +1.483 |
IMAGES | +1.344 |
Cerberus | +1.339 |
inosaur | +1.311 |
copyrighted | +1.282 |
Neg logit contributions | |
nesota | -1.644 |
olate | -1.533 |
vale | -1.475 |
jected | -1.444 |
lication | -1.428 |
Token | whatsoever |
Token ID | 16014 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
nesota | +1.135 |
olate | +1.065 |
vale | +1.029 |
jected | +1.011 |
lication | +1.008 |
Neg logit contributions | |
THING | -0.994 |
Cerberus | -0.903 |
IMAGES | -0.902 |
inosaur | -0.889 |
copyrighted | -0.868 |
Token | without |
Token ID | 1231 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
THING | +8.067 |
IMAGES | +7.247 |
Cerberus | +7.002 |
copyrighted | +6.916 |
inosaur | +6.822 |
Neg logit contributions | |
nesota | -9.310 |
olate | -8.591 |
vale | -8.424 |
jected | -8.092 |
lication | -7.975 |
Token | breaking |
Token ID | 7163 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
THING | +2.609 |
IMAGES | +2.382 |
Cerberus | +2.373 |
copyrighted | +2.276 |
inosaur | +2.263 |
Neg logit contributions | |
nesota | -3.541 |
olate | -3.313 |
vale | -3.231 |
jected | -3.140 |
lication | -3.117 |
Token | game |
Token ID | 983 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
THING | +0.924 |
IMAGES | +0.834 |
Cerberus | +0.827 |
inosaur | +0.811 |
copyrighted | +0.793 |
Neg logit contributions | |
nesota | -1.278 |
olate | -1.195 |
vale | -1.169 |
lication | -1.145 |
jected | -1.144 |
Token | input |
Token ID | 5128 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
THING | +3.078 |
IMAGES | +2.828 |
inosaur | +2.760 |
Cerberus | +2.760 |
copyrighted | +2.731 |
Neg logit contributions | |
nesota | -2.927 |
olate | -2.715 |
vale | -2.642 |
jected | -2.558 |
lication | -2.536 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
nesota | +2.672 |
olate | +2.500 |
vale | +2.410 |
jected | +2.368 |
lication | +2.359 |
Neg logit contributions | |
THING | -2.632 |
Cerberus | -2.405 |
IMAGES | -2.400 |
inosaur | -2.376 |
copyrighted | -2.318 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
THING | +0.588 |
Cerberus | +0.538 |
IMAGES | +0.533 |
inosaur | +0.524 |
copyrighted | +0.519 |
Neg logit contributions | |
nesota | -0.606 |
olate | -0.561 |
vale | -0.544 |
lication | -0.536 |
jected | -0.535 |
Token | some |
Token ID | 617 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
nesota | +5.077 |
olate | +4.844 |
vale | +4.682 |
onset | +4.635 |
jected | +4.626 |
Neg logit contributions | |
THING | -3.812 |
inosaur | -3.420 |
IMAGES | -3.414 |
Cerberus | -3.356 |
ModLoader | -3.251 |
Token | , |
Token ID | 11 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
nesota | +5.977 |
olate | +5.687 |
vale | +5.404 |
jected | +5.387 |
onset | +5.364 |
Neg logit contributions | |
THING | -6.004 |
inosaur | -5.479 |
Cerberus | -5.438 |
IMAGES | -5.434 |
ModLoader | -5.298 |
Token | but |
Token ID | 475 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
nesota | +1.631 |
olate | +1.553 |
vale | +1.508 |
jected | +1.492 |
lication | +1.484 |
Neg logit contributions | |
THING | -0.854 |
IMAGES | -0.745 |
Cerberus | -0.745 |
inosaur | -0.733 |
copyrighted | -0.705 |
Token | all |
Token ID | 477 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
nesota | +3.895 |
olate | +3.702 |
vale | +3.554 |
jected | +3.502 |
lication | +3.468 |
Neg logit contributions | |
THING | -3.093 |
inosaur | -2.778 |
Cerberus | -2.772 |
IMAGES | -2.764 |
ModLoader | -2.665 |
Token | of |
Token ID | 286 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
THING | +6.589 |
IMAGES | +6.150 |
Cerberus | +5.920 |
copyrighted | +5.864 |
inosaur | +5.794 |
Neg logit contributions | |
nesota | -8.214 |
vale | -7.707 |
olate | -7.685 |
lication | -7.564 |
jected | -7.422 |
Token | what |
Token ID | 644 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
THING | +5.431 |
Cerberus | +4.846 |
IMAGES | +4.735 |
copyrighted | +4.574 |
inosaur | +4.207 |
Neg logit contributions | |
nesota | -10.701 |
lication | -10.060 |
olate | -10.053 |
vale | -10.029 |
jected | -9.792 |
Token | was |
Token ID | 373 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
THING | +2.790 |
IMAGES | +2.571 |
Cerberus | +2.570 |
copyrighted | +2.450 |
inosaur | +2.439 |
Neg logit contributions | |
nesota | -3.270 |
olate | -3.092 |
vale | -3.005 |
lication | -2.974 |
jected | -2.956 |
Token | listed |
Token ID | 5610 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
THING | +0.576 |
Cerberus | +0.516 |
IMAGES | +0.510 |
inosaur | +0.502 |
copyrighted | +0.497 |
Neg logit contributions | |
nesota | -0.888 |
olate | -0.838 |
vale | -0.817 |
lication | -0.806 |
jected | -0.802 |
Token | above |
Token ID | 2029 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
THING | +1.434 |
IMAGES | +1.273 |
Cerberus | +1.271 |
inosaur | +1.235 |
copyrighted | +1.230 |
Neg logit contributions | |
nesota | -2.428 |
olate | -2.299 |
vale | -2.234 |
lication | -2.214 |
jected | -2.202 |
Token | was |
Token ID | 373 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
THING | +4.603 |
IMAGES | +4.238 |
Cerberus | +4.193 |
copyrighted | +4.129 |
inosaur | +3.997 |
Neg logit contributions | |
nesota | -6.489 |
olate | -6.100 |
lication | -5.891 |
vale | -5.887 |
jected | -5.809 |
Token | hub |
Token ID | 12575 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
THING | +5.723 |
Cerberus | +5.307 |
IMAGES | +5.166 |
copyrighted | +5.014 |
inosaur | +4.965 |
Neg logit contributions | |
nesota | -5.587 |
olate | -5.071 |
lication | -4.906 |
vale | -4.814 |
jected | -4.810 |
Token | of |
Token ID | 286 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
THING | +0.302 |
Cerberus | +0.272 |
IMAGES | +0.271 |
inosaur | +0.268 |
copyrighted | +0.261 |
Neg logit contributions | |
nesota | -0.418 |
olate | -0.392 |
vale | -0.378 |
jected | -0.373 |
lication | -0.371 |
Token | activity |
Token ID | 3842 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
THING | +3.992 |
Cerberus | +3.628 |
IMAGES | +3.588 |
copyrighted | +3.526 |
inosaur | +3.437 |
Neg logit contributions | |
nesota | -4.722 |
olate | -4.437 |
vale | -4.294 |
lication | -4.215 |
jected | -4.186 |
Token | will |
Token ID | 481 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
THING | +0.005 |
Cerberus | +0.004 |
IMAGES | +0.004 |
inosaur | +0.004 |
copyrighted | +0.004 |
Neg logit contributions | |
nesota | -0.006 |
olate | -0.006 |
vale | -0.005 |
jected | -0.005 |
lication | -0.005 |
Token | be |
Token ID | 307 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
nesota | +1.411 |
olate | +1.293 |
vale | +1.240 |
lication | +1.228 |
jected | +1.228 |
Neg logit contributions | |
THING | -1.827 |
IMAGES | -1.701 |
Cerberus | -1.694 |
inosaur | -1.664 |
copyrighted | -1.647 |
Token | absolutely |
Token ID | 5543 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
THING | +1.456 |
Cerberus | +1.314 |
IMAGES | +1.304 |
inosaur | +1.275 |
copyrighted | +1.264 |
Neg logit contributions | |
nesota | -2.006 |
olate | -1.870 |
vale | -1.828 |
jected | -1.796 |
lication | -1.793 |
Token | packed |
Token ID | 11856 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
THING | +8.546 |
copyrighted | +7.571 |
Cerberus | +7.507 |
IMAGES | +7.499 |
Osiris | +7.153 |
Neg logit contributions | |
nesota | -11.909 |
vale | -10.523 |
lication | -10.483 |
olate | -10.152 |
jected | -10.101 |
Token | for |
Token ID | 329 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
THING | +4.728 |
IMAGES | +4.232 |
Cerberus | +4.216 |
copyrighted | +4.082 |
inosaur | +4.065 |
Neg logit contributions | |
nesota | -7.185 |
olate | -6.624 |
vale | -6.450 |
lication | -6.443 |
jected | -6.418 |
Token | every |
Token ID | 790 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
THING | +0.385 |
Cerberus | +0.346 |
IMAGES | +0.346 |
inosaur | +0.336 |
copyrighted | +0.331 |
Neg logit contributions | |
nesota | -0.566 |
olate | -0.533 |
vale | -0.518 |
jected | -0.510 |
lication | -0.509 |
Token | minute |
Token ID | 5664 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
THING | +5.445 |
Cerberus | +4.774 |
IMAGES | +4.750 |
copyrighted | +4.600 |
inosaur | +4.540 |
Neg logit contributions | |
nesota | -4.619 |
olate | -4.382 |
vale | -4.173 |
lication | -4.159 |
jected | -4.102 |
Token | it |
Token ID | 340 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
nesota | +1.578 |
olate | +1.500 |
vale | +1.457 |
jected | +1.439 |
lication | +1.432 |
Neg logit contributions | |
THING | -0.937 |
Cerberus | -0.824 |
IMAGES | -0.823 |
inosaur | -0.807 |
copyrighted | -0.785 |
Token | 's |
Token ID | 338 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
THING | +2.153 |
Cerberus | +2.021 |
IMAGES | +1.929 |
inosaur | +1.926 |
copyrighted | +1.921 |
Neg logit contributions | |
nesota | -2.696 |
olate | -2.520 |
vale | -2.422 |
lication | -2.395 |
jected | -2.394 |
Token | founder |
Token ID | 9119 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
THING | +0.629 |
Cerberus | +0.571 |
IMAGES | +0.553 |
inosaur | +0.548 |
copyrighted | +0.545 |
Neg logit contributions | |
nesota | -1.030 |
olate | -0.973 |
vale | -0.946 |
lication | -0.931 |
jected | -0.930 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
THING | +3.302 |
Cerberus | +3.106 |
copyrighted | +3.005 |
inosaur | +2.978 |
IMAGES | +2.951 |
Neg logit contributions | |
nesota | -3.564 |
olate | -3.332 |
vale | -3.166 |
lication | -3.144 |
jected | -3.131 |
Token | with |
Token ID | 351 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
THING | +4.308 |
Cerberus | +4.053 |
copyrighted | +3.900 |
inosaur | +3.799 |
IMAGES | +3.784 |
Neg logit contributions | |
nesota | -6.685 |
olate | -6.359 |
vale | -6.108 |
lication | -6.030 |
jected | -5.943 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
THING | +0.848 |
Cerberus | +0.759 |
IMAGES | +0.746 |
inosaur | +0.736 |
copyrighted | +0.723 |
Neg logit contributions | |
nesota | -1.473 |
olate | -1.396 |
vale | -1.357 |
jected | -1.335 |
lication | -1.333 |
Token | Cly |
Token ID | 29133 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
THING | +0.406 |
Cerberus | +0.378 |
IMAGES | +0.366 |
inosaur | +0.364 |
copyrighted | +0.361 |
Neg logit contributions | |
nesota | -0.459 |
olate | -0.431 |
vale | -0.412 |
jected | -0.405 |
lication | -0.402 |
Token | des |
Token ID | 8906 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
THING | +7.248 |
inosaur | +6.688 |
Cerberus | +6.652 |
copyrighted | +6.546 |
IMAGES | +6.322 |
Neg logit contributions | |
nesota | -7.379 |
olate | -6.895 |
onset | -6.427 |
lication | -6.333 |
jected | -6.188 |
Token | d |
Token ID | 67 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
THING | +3.425 |
inosaur | +3.174 |
Cerberus | +3.151 |
copyrighted | +3.098 |
IMAGES | +3.079 |
Neg logit contributions | |
nesota | -3.292 |
olate | -2.997 |
lication | -2.874 |
jected | -2.862 |
vale | -2.848 |
Token | ales |
Token ID | 2040 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
THING | +6.594 |
Cerberus | +6.401 |
inosaur | +6.390 |
IMAGES | +6.269 |
copyrighted | +6.153 |
Neg logit contributions | |
nesota | -2.784 |
olate | -2.462 |
jected | -2.322 |
lication | -2.293 |
onset | -2.282 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
THING | +3.293 |
Cerberus | +3.052 |
copyrighted | +2.961 |
inosaur | +2.953 |
IMAGES | +2.945 |
Neg logit contributions | |
nesota | -3.937 |
olate | -3.620 |
vale | -3.458 |
jected | -3.451 |
lication | -3.450 |
Token | He |
Token ID | 679 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
THING | +0.958 |
Cerberus | +0.882 |
IMAGES | +0.876 |
inosaur | +0.856 |
copyrighted | +0.839 |
Neg logit contributions | |
nesota | -1.120 |
olate | -1.046 |
vale | -1.008 |
jected | -0.997 |
lication | -0.992 |
Token | continue |
Token ID | 2555 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
THING | +0.467 |
Cerberus | +0.428 |
IMAGES | +0.422 |
inosaur | +0.413 |
copyrighted | +0.412 |
Neg logit contributions | |
nesota | -0.554 |
olate | -0.516 |
vale | -0.500 |
lication | -0.495 |
jected | -0.493 |
Token | to |
Token ID | 284 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
THING | +1.470 |
Cerberus | +1.354 |
inosaur | +1.321 |
IMAGES | +1.319 |
copyrighted | +1.302 |
Neg logit contributions | |
nesota | -1.668 |
olate | -1.549 |
vale | -1.494 |
lication | -1.484 |
jected | -1.472 |
Token | give |
Token ID | 1577 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
THING | +2.362 |
Cerberus | +2.203 |
IMAGES | +2.185 |
copyrighted | +2.171 |
inosaur | +2.161 |
Neg logit contributions | |
nesota | -1.955 |
olate | -1.770 |
lication | -1.744 |
jected | -1.705 |
vale | -1.697 |
Token | her |
Token ID | 607 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
THING | +2.563 |
Cerberus | +2.331 |
IMAGES | +2.282 |
copyrighted | +2.250 |
inosaur | +2.248 |
Neg logit contributions | |
nesota | -3.672 |
olate | -3.440 |
vale | -3.326 |
lication | -3.324 |
jected | -3.259 |
Token | large |
Token ID | 1588 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
THING | +1.076 |
Cerberus | +0.971 |
IMAGES | +0.969 |
inosaur | +0.955 |
copyrighted | +0.947 |
Neg logit contributions | |
nesota | -1.397 |
olate | -1.310 |
vale | -1.263 |
lication | -1.251 |
jected | -1.240 |
Token | platforms |
Token ID | 9554 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
THING | +3.709 |
Cerberus | +3.470 |
IMAGES | +3.440 |
copyrighted | +3.422 |
inosaur | +3.392 |
Neg logit contributions | |
nesota | -3.850 |
olate | -3.544 |
vale | -3.363 |
lication | -3.324 |
jected | -3.306 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
THING | +2.415 |
Cerberus | +2.175 |
inosaur | +2.165 |
IMAGES | +2.155 |
copyrighted | +2.148 |
Neg logit contributions | |
nesota | -3.200 |
olate | -3.003 |
vale | -2.872 |
lication | -2.842 |
jected | -2.832 |
Token | make |
Token ID | 787 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
nesota | +0.479 |
olate | +0.441 |
vale | +0.424 |
lication | +0.420 |
jected | +0.420 |
Neg logit contributions | |
THING | -0.559 |
Cerberus | -0.515 |
IMAGES | -0.513 |
inosaur | -0.507 |
copyrighted | -0.503 |
Token | them |
Token ID | 606 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
nesota | +2.724 |
olate | +2.590 |
vale | +2.497 |
jected | +2.479 |
lication | +2.454 |
Neg logit contributions | |
THING | -1.785 |
IMAGES | -1.586 |
Cerberus | -1.585 |
inosaur | -1.572 |
copyrighted | -1.500 |
Token | — |
Token ID | 960 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
THING | +0.117 |
IMAGES | +0.105 |
Cerberus | +0.105 |
inosaur | +0.103 |
copyrighted | +0.102 |
Neg logit contributions | |
nesota | -0.129 |
olate | -0.120 |
vale | -0.116 |
lication | -0.116 |
jected | -0.115 |
Token | it |
Token ID | 270 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
THING | +0.545 |
Cerberus | +0.493 |
IMAGES | +0.489 |
inosaur | +0.486 |
copyrighted | +0.476 |
Neg logit contributions | |
nesota | -0.522 |
olate | -0.483 |
vale | -0.463 |
lication | -0.458 |
jected | -0.455 |
Token | people |
Token ID | 661 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
THING | +2.905 |
Cerberus | +2.625 |
IMAGES | +2.560 |
copyrighted | +2.535 |
inosaur | +2.498 |
Neg logit contributions | |
nesota | -3.434 |
olate | -3.213 |
vale | -3.128 |
lication | -3.049 |
jected | -3.027 |
Token | realize |
Token ID | 6537 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
nesota | +0.635 |
olate | +0.574 |
vale | +0.551 |
jected | +0.542 |
lication | +0.534 |
Neg logit contributions | |
THING | -1.031 |
Cerberus | -0.959 |
IMAGES | -0.957 |
inosaur | -0.950 |
copyrighted | -0.939 |
Token | -- |
Token ID | 438 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
THING | +0.586 |
Cerberus | +0.539 |
IMAGES | +0.534 |
inosaur | +0.528 |
copyrighted | +0.519 |
Neg logit contributions | |
nesota | -0.582 |
olate | -0.541 |
vale | -0.522 |
lication | -0.514 |
jected | -0.513 |
Token | dating |
Token ID | 38734 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
THING | +0.395 |
Cerberus | +0.364 |
IMAGES | +0.360 |
inosaur | +0.358 |
copyrighted | +0.350 |
Neg logit contributions | |
nesota | -0.360 |
olate | -0.332 |
vale | -0.320 |
lication | -0.313 |
jected | -0.312 |
Token | back |
Token ID | 736 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
nesota | +0.065 |
olate | +0.060 |
vale | +0.058 |
lication | +0.057 |
jected | +0.057 |
Neg logit contributions | |
THING | -0.069 |
Cerberus | -0.064 |
IMAGES | -0.064 |
inosaur | -0.063 |
copyrighted | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
THING | +0.656 |
Cerberus | +0.601 |
IMAGES | +0.595 |
inosaur | +0.592 |
copyrighted | +0.578 |
Neg logit contributions | |
nesota | -0.739 |
olate | -0.688 |
vale | -0.666 |
lication | -0.655 |
jected | -0.652 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
THING | +1.033 |
Cerberus | +0.931 |
IMAGES | +0.915 |
inosaur | +0.908 |
copyrighted | +0.884 |
Neg logit contributions | |
nesota | -1.651 |
olate | -1.554 |
vale | -1.512 |
lication | -1.484 |
jected | -1.478 |
Token | 1950 |
Token ID | 11445 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
THING | +0.427 |
Cerberus | +0.396 |
IMAGES | +0.390 |
inosaur | +0.388 |
copyrighted | +0.381 |
Neg logit contributions | |
nesota | -0.414 |
olate | -0.385 |
vale | -0.370 |
lication | -0.362 |
jected | -0.359 |
Token | s |
Token ID | 82 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
THING | +0.919 |
Cerberus | +0.828 |
inosaur | +0.823 |
IMAGES | +0.816 |
copyrighted | +0.799 |
Neg logit contributions | |
nesota | -1.196 |
olate | -1.120 |
vale | -1.071 |
jected | -1.062 |
lication | -1.061 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
THING | +0.308 |
Cerberus | +0.282 |
IMAGES | +0.279 |
inosaur | +0.277 |
copyrighted | +0.271 |
Neg logit contributions | |
nesota | -0.354 |
olate | -0.329 |
vale | -0.319 |
lication | -0.314 |
jected | -0.313 |
Token | The |
Token ID | 383 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
THING | +0.443 |
Cerberus | +0.409 |
IMAGES | +0.406 |
inosaur | +0.396 |
copyrighted | +0.386 |
Neg logit contributions | |
nesota | -0.461 |
olate | -0.427 |
vale | -0.413 |
lication | -0.407 |
jected | -0.405 |
Token | , |
Token ID | 11 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
nesota | +0.838 |
olate | +0.779 |
lication | +0.746 |
vale | +0.744 |
jected | +0.744 |
Neg logit contributions | |
THING | -0.858 |
IMAGES | -0.788 |
Cerberus | -0.788 |
inosaur | -0.771 |
copyrighted | -0.760 |
Token | who |
Token ID | 508 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
THING | +1.746 |
Cerberus | +1.594 |
IMAGES | +1.560 |
inosaur | +1.508 |
copyrighted | +1.505 |
Neg logit contributions | |
nesota | -2.717 |
olate | -2.574 |
vale | -2.487 |
lication | -2.471 |
jected | -2.449 |
Token | has |
Token ID | 468 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
nesota | +2.060 |
olate | +1.941 |
vale | +1.877 |
jected | +1.849 |
lication | +1.844 |
Neg logit contributions | |
THING | -1.612 |
Cerberus | -1.456 |
IMAGES | -1.453 |
inosaur | -1.433 |
copyrighted | -1.397 |
Token | his |
Token ID | 465 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
nesota | +3.521 |
olate | +3.336 |
vale | +3.232 |
jected | +3.199 |
lication | +3.174 |
Neg logit contributions | |
THING | -2.136 |
IMAGES | -1.897 |
Cerberus | -1.876 |
inosaur | -1.867 |
ModLoader | -1.786 |
Token | own |
Token ID | 898 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
THING | +0.681 |
Cerberus | +0.634 |
IMAGES | +0.620 |
copyrighted | +0.615 |
inosaur | +0.610 |
Neg logit contributions | |
nesota | -0.598 |
olate | -0.553 |
vale | -0.534 |
lication | -0.522 |
jected | -0.516 |
Token | housing |
Token ID | 5627 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
THING | +3.684 |
Cerberus | +3.406 |
copyrighted | +3.322 |
IMAGES | +3.293 |
inosaur | +3.196 |
Neg logit contributions | |
nesota | -3.393 |
olate | -3.169 |
vale | -3.009 |
lication | -2.997 |
jected | -2.887 |
Token | research |
Token ID | 2267 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
THING | +1.941 |
Cerberus | +1.785 |
IMAGES | +1.767 |
copyrighted | +1.730 |
inosaur | +1.713 |
Neg logit contributions | |
nesota | -1.958 |
olate | -1.811 |
lication | -1.756 |
vale | -1.737 |
jected | -1.697 |
Token | business |
Token ID | 1597 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
nesota | +3.004 |
olate | +2.810 |
vale | +2.698 |
jected | +2.658 |
lication | +2.633 |
Neg logit contributions | |
THING | -3.190 |
Cerberus | -2.915 |
IMAGES | -2.913 |
inosaur | -2.893 |
copyrighted | -2.809 |
Token | and |
Token ID | 290 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
THING | +0.550 |
Cerberus | +0.508 |
IMAGES | +0.497 |
inosaur | +0.491 |
copyrighted | +0.487 |
Neg logit contributions | |
nesota | -0.658 |
olate | -0.607 |
vale | -0.588 |
jected | -0.582 |
lication | -0.581 |
Token | is |
Token ID | 318 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
nesota | +1.384 |
olate | +1.306 |
vale | +1.264 |
jected | +1.245 |
lication | +1.241 |
Neg logit contributions | |
THING | -1.051 |
Cerberus | -0.948 |
IMAGES | -0.946 |
inosaur | -0.931 |
copyrighted | -0.909 |
Token | also |
Token ID | 635 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
nesota | +1.503 |
olate | +1.419 |
vale | +1.375 |
jected | +1.355 |
lication | +1.350 |
Neg logit contributions | |
THING | -1.078 |
Cerberus | -0.967 |
IMAGES | -0.966 |
inosaur | -0.953 |
copyrighted | -0.925 |
Token | will |
Token ID | 481 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
THING | +1.344 |
Cerberus | +1.203 |
IMAGES | +1.201 |
inosaur | +1.187 |
copyrighted | +1.165 |
Neg logit contributions | |
nesota | -1.761 |
olate | -1.665 |
vale | -1.611 |
jected | -1.583 |
lication | -1.561 |
Token | be |
Token ID | 307 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
nesota | +0.332 |
olate | +0.305 |
vale | +0.291 |
jected | +0.284 |
lication | +0.283 |
Neg logit contributions | |
THING | -0.511 |
Cerberus | -0.475 |
IMAGES | -0.475 |
inosaur | -0.470 |
copyrighted | -0.462 |
Token | a |
Token ID | 257 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
THING | +2.899 |
Cerberus | +2.577 |
IMAGES | +2.458 |
copyrighted | +2.429 |
inosaur | +2.387 |
Neg logit contributions | |
nesota | -5.288 |
olate | -5.017 |
vale | -4.842 |
jected | -4.781 |
lication | -4.753 |
Token | full |
Token ID | 1336 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
THING | +2.062 |
Cerberus | +1.899 |
IMAGES | +1.839 |
copyrighted | +1.820 |
inosaur | +1.785 |
Neg logit contributions | |
nesota | -2.361 |
olate | -2.170 |
vale | -2.118 |
lication | -2.059 |
jected | -2.057 |
Token | rescue |
Token ID | 9992 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
THING | +2.456 |
Cerberus | +2.271 |
IMAGES | +2.193 |
copyrighted | +2.175 |
inosaur | +2.143 |
Neg logit contributions | |
nesota | -2.870 |
olate | -2.642 |
vale | -2.553 |
jected | -2.512 |
lication | -2.471 |
Token | for |
Token ID | 329 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
THING | +0.081 |
Cerberus | +0.074 |
IMAGES | +0.073 |
inosaur | +0.073 |
copyrighted | +0.072 |
Neg logit contributions | |
nesota | -0.086 |
olate | -0.080 |
vale | -0.077 |
jected | -0.076 |
lication | -0.075 |
Token | Spain |
Token ID | 8602 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
THING | +1.457 |
Cerberus | +1.330 |
IMAGES | +1.293 |
copyrighted | +1.257 |
inosaur | +1.243 |
Neg logit contributions | |
nesota | -2.274 |
olate | -2.122 |
vale | -2.048 |
lication | -2.017 |
jected | -2.012 |
Token | , |
Token ID | 11 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
nesota | +1.254 |
olate | +1.174 |
vale | +1.129 |
jected | +1.113 |
lication | +1.110 |
Neg logit contributions | |
THING | -1.186 |
Cerberus | -1.082 |
IMAGES | -1.078 |
inosaur | -1.068 |
copyrighted | -1.045 |
Token | to |
Token ID | 284 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
THING | +2.124 |
Cerberus | +1.959 |
IMAGES | +1.906 |
inosaur | +1.877 |
copyrighted | +1.876 |
Neg logit contributions | |
nesota | -2.626 |
olate | -2.453 |
vale | -2.379 |
lication | -2.333 |
jected | -2.314 |
Token | � |
Token ID | 564 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
nesota | +2.332 |
olate | +2.206 |
vale | +2.136 |
jected | +2.103 |
lication | +2.094 |
Neg logit contributions | |
THING | -1.767 |
IMAGES | -1.592 |
Cerberus | -1.587 |
inosaur | -1.574 |
copyrighted | -1.520 |
Token | � |
Token ID | 250 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
nesota | +2.739 |
olate | +2.564 |
vale | +2.449 |
jected | +2.419 |
lication | +2.379 |
Neg logit contributions | |
THING | -3.026 |
IMAGES | -2.787 |
Cerberus | -2.787 |
inosaur | -2.736 |
copyrighted | -2.679 |
Token | physical |
Token ID | 3518 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
nesota | +2.500 |
olate | +2.342 |
vale | +2.262 |
jected | +2.223 |
lication | +2.216 |
Neg logit contributions | |
THING | -2.303 |
Cerberus | -2.097 |
IMAGES | -2.094 |
inosaur | -2.068 |
copyrighted | -2.021 |
Token | transition |
Token ID | 6801 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
THING | +3.775 |
IMAGES | +3.484 |
Cerberus | +3.441 |
copyrighted | +3.394 |
inosaur | +3.340 |
Neg logit contributions | |
nesota | -2.961 |
olate | -2.762 |
vale | -2.638 |
jected | -2.577 |
lication | -2.480 |
Token | (" |
Token ID | 5855 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
nesota | +8.575 |
olate | +8.014 |
onset | +7.928 |
vale | +7.808 |
lication | +7.763 |
Neg logit contributions | |
THING | -7.695 |
Cerberus | -7.060 |
inosaur | -7.003 |
IMAGES | -6.953 |
ModLoader | -6.821 |
Token | trans |
Token ID | 7645 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
nesota | +2.048 |
olate | +1.904 |
vale | +1.829 |
jected | +1.794 |
lication | +1.788 |
Neg logit contributions | |
THING | -2.319 |
Cerberus | -2.128 |
IMAGES | -2.127 |
inosaur | -2.104 |
copyrighted | -2.058 |
Token | sexual |
Token ID | 18338 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
nesota | +3.617 |
olate | +3.366 |
vale | +3.237 |
jected | +3.189 |
lication | +3.162 |
Neg logit contributions | |
THING | -4.285 |
Cerberus | -3.962 |
IMAGES | -3.955 |
inosaur | -3.897 |
copyrighted | -3.829 |
Token | " |
Token ID | 1 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
THING | +0.484 |
IMAGES | +0.439 |
Cerberus | +0.438 |
inosaur | +0.429 |
copyrighted | +0.420 |
Neg logit contributions | |
nesota | -0.577 |
olate | -0.539 |
vale | -0.524 |
lication | -0.513 |
jected | -0.512 |
Token | people |
Token ID | 661 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
THING | +0.391 |
IMAGES | +0.352 |
Cerberus | +0.350 |
inosaur | +0.344 |
copyrighted | +0.337 |
Neg logit contributions | |
nesota | -0.568 |
olate | -0.534 |
vale | -0.520 |
jected | -0.511 |
lication | -0.510 |
Token | ) |
Token ID | 8 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
nesota | +2.014 |
olate | +1.885 |
vale | +1.822 |
jected | +1.795 |
lication | +1.786 |
Neg logit contributions | |
THING | -1.817 |
IMAGES | -1.653 |
Cerberus | -1.651 |
inosaur | -1.630 |
copyrighted | -1.594 |
Token | and |
Token ID | 290 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
nesota | +1.039 |
olate | +0.979 |
vale | +0.948 |
jected | +0.934 |
lication | +0.931 |
Neg logit contributions | |
THING | -0.795 |
Cerberus | -0.717 |
IMAGES | -0.716 |
inosaur | -0.706 |
copyrighted | -0.687 |
Token | other |
Token ID | 584 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
nesota | +2.154 |
olate | +2.042 |
vale | +1.986 |
jected | +1.959 |
lication | +1.955 |
Neg logit contributions | |
THING | -1.202 |
Cerberus | -1.057 |
IMAGES | -1.057 |
inosaur | -1.037 |
copyrighted | -1.006 |
Token | gender |
Token ID | 5279 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
THING | +0.245 |
IMAGES | +0.222 |
Cerberus | +0.219 |
inosaur | +0.215 |
copyrighted | +0.215 |
Neg logit contributions | |
nesota | -0.325 |
olate | -0.305 |
vale | -0.296 |
lication | -0.291 |
jected | -0.289 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
THING | +3.498 |
IMAGES | +3.185 |
inosaur | +3.170 |
Cerberus | +3.164 |
copyrighted | +3.067 |
Neg logit contributions | |
nesota | -4.508 |
olate | -4.129 |
jected | -3.940 |
vale | -3.936 |
lication | -3.905 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
THING | +3.304 |
Cerberus | +3.051 |
IMAGES | +2.984 |
inosaur | +2.936 |
copyrighted | +2.906 |
Neg logit contributions | |
nesota | -4.235 |
olate | -3.942 |
lication | -3.781 |
vale | -3.763 |
jected | -3.755 |
Token | , |
Token ID | 11 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
nesota | +0.969 |
olate | +0.908 |
vale | +0.876 |
jected | +0.865 |
lication | +0.859 |
Neg logit contributions | |
THING | -0.834 |
Cerberus | -0.758 |
IMAGES | -0.754 |
inosaur | -0.746 |
copyrighted | -0.729 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
THING | +2.509 |
Cerberus | +2.298 |
IMAGES | +2.272 |
inosaur | +2.231 |
copyrighted | +2.198 |
Neg logit contributions | |
nesota | -3.314 |
olate | -3.078 |
vale | -2.991 |
jected | -2.970 |
lication | -2.958 |
Token | ). |
Token ID | 737 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
THING | +2.712 |
Cerberus | +2.455 |
IMAGES | +2.428 |
inosaur | +2.405 |
copyrighted | +2.362 |
Neg logit contributions | |
nesota | -3.407 |
olate | -3.165 |
jected | -3.056 |
vale | -3.029 |
lication | -3.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
nesota | +1.205 |
olate | +1.126 |
vale | +1.086 |
jected | +1.069 |
lication | +1.066 |
Neg logit contributions | |
THING | -1.158 |
Cerberus | -1.059 |
IMAGES | -1.057 |
inosaur | -1.042 |
copyrighted | -1.018 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
nesota | +0.985 |
olate | +0.923 |
vale | +0.890 |
jected | +0.874 |
lication | +0.870 |
Neg logit contributions | |
THING | -0.965 |
Cerberus | -0.882 |
IMAGES | -0.881 |
inosaur | -0.872 |
copyrighted | -0.850 |
Token | Temperature |
Token ID | 42492 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
nesota | +1.348 |
olate | +1.252 |
vale | +1.204 |
jected | +1.183 |
lication | +1.181 |
Neg logit contributions | |
THING | -1.426 |
Cerberus | -1.297 |
IMAGES | -1.294 |
inosaur | -1.286 |
copyrighted | -1.253 |
Token | feedback |
Token ID | 7538 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
nesota | +6.059 |
olate | +5.732 |
onset | +5.497 |
vale | +5.470 |
jected | +5.348 |
Neg logit contributions | |
THING | -7.322 |
IMAGES | -6.757 |
inosaur | -6.744 |
Cerberus | -6.665 |
ModLoader | -6.494 |
Token | s |
Token ID | 82 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
nesota | +3.997 |
olate | +3.760 |
vale | +3.624 |
jected | +3.554 |
lication | +3.530 |
Neg logit contributions | |
THING | -3.817 |
IMAGES | -3.473 |
Cerberus | -3.469 |
inosaur | -3.447 |
copyrighted | -3.334 |
Token | – |
Token ID | 784 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
nesota | +3.489 |
olate | +3.288 |
vale | +3.152 |
jected | +3.107 |
lication | +3.085 |
Neg logit contributions | |
THING | -3.344 |
IMAGES | -3.047 |
Cerberus | -3.044 |
inosaur | -3.019 |
copyrighted | -2.925 |
Token | the |
Token ID | 262 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
nesota | +0.659 |
olate | +0.623 |
vale | +0.606 |
jected | +0.597 |
lication | +0.596 |
Neg logit contributions | |
THING | -0.423 |
Cerberus | -0.378 |
IMAGES | -0.376 |
inosaur | -0.367 |
copyrighted | -0.360 |
Token | field |
Token ID | 2214 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
nesota | +2.953 |
olate | +2.751 |
vale | +2.641 |
jected | +2.595 |
lication | +2.579 |
Neg logit contributions | |
THING | -3.343 |
Cerberus | -3.071 |
IMAGES | -3.069 |
inosaur | -3.041 |
copyrighted | -2.969 |
Token | of |
Token ID | 286 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
THING | +0.532 |
Cerberus | +0.480 |
IMAGES | +0.476 |
inosaur | +0.472 |
copyrighted | +0.462 |
Neg logit contributions | |
nesota | -0.684 |
olate | -0.640 |
vale | -0.619 |
jected | -0.611 |
lication | -0.609 |
Token | competitors |
Token ID | 13861 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
THING | +7.620 |
IMAGES | +7.199 |
Cerberus | +7.136 |
inosaur | +6.876 |
copyrighted | +6.847 |
Neg logit contributions | |
nesota | -5.276 |
vale | -4.788 |
olate | -4.746 |
lication | -4.373 |
jected | -4.315 |
Token | . |
Token ID | 13 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
nesota | +1.268 |
olate | +1.190 |
vale | +1.150 |
jected | +1.133 |
lication | +1.129 |
Neg logit contributions | |
THING | -1.065 |
Cerberus | -0.964 |
IMAGES | -0.961 |
inosaur | -0.949 |
copyrighted | -0.928 |
Token |
|
Token ID | 198 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
nesota | +0.154 |
olate | +0.144 |
vale | +0.139 |
jected | +0.137 |
lication | +0.137 |
Neg logit contributions | |
THING | -0.139 |
IMAGES | -0.127 |
Cerberus | -0.127 |
inosaur | -0.124 |
copyrighted | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
nesota | +0.343 |
olate | +0.320 |
vale | +0.309 |
jected | +0.304 |
lication | +0.304 |
Neg logit contributions | |
THING | -0.319 |
Cerberus | -0.291 |
IMAGES | -0.291 |
inosaur | -0.286 |
copyrighted | -0.280 |
Token | Since |
Token ID | 6385 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
THING | +0.333 |
IMAGES | +0.300 |
Cerberus | +0.298 |
inosaur | +0.296 |
copyrighted | +0.289 |
Neg logit contributions | |
nesota | -0.338 |
olate | -0.316 |
vale | -0.302 |
jected | -0.298 |
lication | -0.297 |
Token | Coach |
Token ID | 16393 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
nesota | +0.117 |
olate | +0.111 |
vale | +0.107 |
jected | +0.106 |
lication | +0.105 |
Neg logit contributions | |
THING | -0.082 |
Cerberus | -0.074 |
IMAGES | -0.074 |
inosaur | -0.072 |
copyrighted | -0.071 |
Token | never |
Token ID | 1239 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
THING | +0.556 |
Cerberus | +0.504 |
IMAGES | +0.501 |
inosaur | +0.495 |
copyrighted | +0.491 |
Neg logit contributions | |
nesota | -0.698 |
olate | -0.652 |
vale | -0.629 |
lication | -0.621 |
jected | -0.620 |
Token | played |
Token ID | 2826 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
THING | +3.794 |
IMAGES | +3.534 |
Cerberus | +3.461 |
copyrighted | +3.435 |
inosaur | +3.323 |
Neg logit contributions | |
nesota | -5.215 |
olate | -4.932 |
vale | -4.742 |
lication | -4.677 |
jected | -4.609 |
Token | in |
Token ID | 287 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
THING | +0.808 |
Cerberus | +0.728 |
IMAGES | +0.726 |
inosaur | +0.717 |
copyrighted | +0.701 |
Neg logit contributions | |
nesota | -1.055 |
olate | -0.992 |
vale | -0.962 |
jected | -0.949 |
lication | -0.944 |
Token | fish |
Token ID | 5916 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
nesota | +4.477 |
olate | +4.290 |
vale | +4.127 |
jected | +4.121 |
lication | +4.084 |
Neg logit contributions | |
THING | -2.876 |
IMAGES | -2.569 |
Cerberus | -2.531 |
inosaur | -2.505 |
copyrighted | -2.406 |
Token | exc |
Token ID | 2859 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
THING | +1.046 |
Cerberus | +0.950 |
IMAGES | +0.945 |
inosaur | +0.931 |
copyrighted | +0.917 |
Neg logit contributions | |
nesota | -1.051 |
olate | -0.960 |
vale | -0.923 |
jected | -0.916 |
lication | -0.905 |
Token | re |
Token ID | 260 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
nesota | +2.687 |
olate | +2.472 |
vale | +2.358 |
jected | +2.311 |
lication | +2.299 |
Neg logit contributions | |
THING | -3.858 |
Cerberus | -3.579 |
IMAGES | -3.576 |
inosaur | -3.541 |
copyrighted | -3.472 |
Token | ment |
Token ID | 434 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
nesota | +5.472 |
olate | +5.150 |
vale | +4.917 |
jected | +4.890 |
lication | +4.756 |
Neg logit contributions | |
THING | -6.003 |
IMAGES | -5.568 |
inosaur | -5.473 |
Cerberus | -5.465 |
ModLoader | -5.357 |
Token | or |
Token ID | 393 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
THING | +0.755 |
Cerberus | +0.686 |
IMAGES | +0.683 |
inosaur | +0.668 |
copyrighted | +0.660 |
Neg logit contributions | |
nesota | -0.919 |
olate | -0.857 |
vale | -0.829 |
jected | -0.817 |
lication | -0.815 |
Token | sending |
Token ID | 7216 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
nesota | +0.954 |
olate | +0.896 |
vale | +0.869 |
jected | +0.854 |
lication | +0.851 |
Neg logit contributions | |
THING | -0.746 |
Cerberus | -0.674 |
IMAGES | -0.672 |
inosaur | -0.662 |
copyrighted | -0.647 |
Token | so |
Token ID | 523 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
THING | +0.972 |
Cerberus | +0.865 |
IMAGES | +0.862 |
inosaur | +0.845 |
copyrighted | +0.828 |
Neg logit contributions | |
nesota | -1.566 |
olate | -1.477 |
vale | -1.441 |
lication | -1.413 |
jected | -1.413 |
Token | apy |
Token ID | 12826 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
nesota | +1.275 |
olate | +1.181 |
vale | +1.139 |
lication | +1.114 |
jected | +1.112 |
Neg logit contributions | |
THING | -1.378 |
Cerberus | -1.264 |
IMAGES | -1.261 |
inosaur | -1.250 |
copyrighted | -1.224 |
Token | water |
Token ID | 1660 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
nesota | +1.980 |
olate | +1.862 |
vale | +1.801 |
jected | +1.770 |
lication | +1.767 |
Neg logit contributions | |
THING | -1.589 |
Cerberus | -1.436 |
IMAGES | -1.434 |
inosaur | -1.412 |
copyrighted | -1.380 |
Token | back |
Token ID | 736 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
THING | +1.193 |
Cerberus | +1.083 |
IMAGES | +1.082 |
inosaur | +1.057 |
copyrighted | +1.041 |
Neg logit contributions | |
nesota | -1.444 |
olate | -1.344 |
vale | -1.305 |
lication | -1.284 |
jected | -1.279 |
Token | Just |
Token ID | 5703 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
nesota | +0.875 |
olate | +0.816 |
vale | +0.784 |
jected | +0.772 |
lication | +0.770 |
Neg logit contributions | |
THING | -0.882 |
IMAGES | -0.802 |
Cerberus | -0.801 |
inosaur | -0.793 |
copyrighted | -0.774 |
Token | generally |
Token ID | 4143 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
THING | +2.499 |
Cerberus | +2.282 |
inosaur | +2.252 |
IMAGES | +2.234 |
copyrighted | +2.177 |
Neg logit contributions | |
nesota | -2.887 |
olate | -2.633 |
vale | -2.569 |
lication | -2.560 |
jected | -2.518 |
Token | speaking |
Token ID | 5486 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
nesota | +1.719 |
olate | +1.615 |
vale | +1.559 |
jected | +1.533 |
lication | +1.527 |
Neg logit contributions | |
THING | -1.541 |
Cerberus | -1.401 |
IMAGES | -1.400 |
inosaur | -1.383 |
copyrighted | -1.348 |
Token | , |
Token ID | 11 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
THING | +0.286 |
Cerberus | +0.263 |
IMAGES | +0.262 |
inosaur | +0.258 |
copyrighted | +0.254 |
Neg logit contributions | |
nesota | -0.256 |
olate | -0.236 |
vale | -0.228 |
jected | -0.224 |
lication | -0.223 |
Token | what |
Token ID | 644 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
THING | +1.786 |
Cerberus | +1.626 |
IMAGES | +1.609 |
inosaur | +1.564 |
copyrighted | +1.551 |
Neg logit contributions | |
nesota | -2.375 |
olate | -2.212 |
vale | -2.152 |
lication | -2.117 |
jected | -2.114 |
Token | was |
Token ID | 373 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
THING | +0.249 |
Cerberus | +0.226 |
IMAGES | +0.225 |
inosaur | +0.220 |
copyrighted | +0.218 |
Neg logit contributions | |
nesota | -0.285 |
olate | -0.268 |
vale | -0.258 |
jected | -0.254 |
lication | -0.253 |
Token | the |
Token ID | 262 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
nesota | +2.013 |
olate | +1.921 |
vale | +1.851 |
jected | +1.832 |
lication | +1.818 |
Neg logit contributions | |
THING | -1.289 |
IMAGES | -1.150 |
Cerberus | -1.143 |
inosaur | -1.137 |
copyrighted | -1.085 |
Token | experience |
Token ID | 1998 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
nesota | +2.026 |
olate | +1.877 |
vale | +1.802 |
jected | +1.764 |
lication | +1.758 |
Neg logit contributions | |
THING | -2.497 |
Cerberus | -2.304 |
IMAGES | -2.298 |
inosaur | -2.274 |
copyrighted | -2.232 |
Token | like |
Token ID | 588 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
nesota | +2.277 |
olate | +2.162 |
vale | +2.100 |
jected | +2.071 |
lication | +2.063 |
Neg logit contributions | |
THING | -1.338 |
IMAGES | -1.184 |
Cerberus | -1.182 |
inosaur | -1.166 |
copyrighted | -1.124 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
nesota | +2.753 |
olate | +2.597 |
vale | +2.512 |
jected | +2.474 |
lication | +2.462 |
Neg logit contributions | |
THING | -2.191 |
IMAGES | -1.979 |
Cerberus | -1.979 |
inosaur | -1.954 |
copyrighted | -1.896 |
Token | working |
Token ID | 1762 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
THING | +0.365 |
Cerberus | +0.333 |
IMAGES | +0.328 |
inosaur | +0.320 |
copyrighted | +0.319 |
Neg logit contributions | |
nesota | -0.469 |
olate | -0.438 |
vale | -0.422 |
jected | -0.417 |
lication | -0.417 |
Token | � |
Token ID | 247 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
THING | +0.386 |
Cerberus | +0.355 |
IMAGES | +0.355 |
inosaur | +0.351 |
copyrighted | +0.345 |
Neg logit contributions | |
nesota | -0.305 |
olate | -0.282 |
vale | -0.272 |
jected | -0.266 |
lication | -0.265 |
Token | s |
Token ID | 82 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
THING | +0.340 |
Cerberus | +0.307 |
IMAGES | +0.307 |
inosaur | +0.305 |
copyrighted | +0.296 |
Neg logit contributions | |
nesota | -0.397 |
olate | -0.371 |
vale | -0.360 |
jected | -0.353 |
lication | -0.353 |
Token | a |
Token ID | 257 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
THING | +1.006 |
Cerberus | +0.906 |
IMAGES | +0.899 |
inosaur | +0.886 |
copyrighted | +0.874 |
Neg logit contributions | |
nesota | -1.399 |
olate | -1.319 |
vale | -1.283 |
jected | -1.262 |
lication | -1.254 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
THING | +0.539 |
Cerberus | +0.491 |
IMAGES | +0.483 |
inosaur | +0.474 |
copyrighted | +0.473 |
Neg logit contributions | |
nesota | -0.685 |
olate | -0.642 |
vale | -0.622 |
lication | -0.612 |
jected | -0.609 |
Token | of |
Token ID | 286 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
THING | +2.686 |
Cerberus | +2.302 |
IMAGES | +2.254 |
inosaur | +2.253 |
copyrighted | +2.218 |
Neg logit contributions | |
nesota | -5.608 |
olate | -5.332 |
vale | -5.252 |
jected | -5.171 |
lication | -5.113 |
Token | other |
Token ID | 584 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
THING | +2.624 |
Cerberus | +2.401 |
IMAGES | +2.364 |
copyrighted | +2.340 |
inosaur | +2.295 |
Neg logit contributions | |
nesota | -3.231 |
olate | -3.018 |
vale | -2.962 |
lication | -2.878 |
jected | -2.876 |
Token | ways |
Token ID | 2842 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
nesota | +0.968 |
olate | +0.911 |
vale | +0.881 |
jected | +0.867 |
lication | +0.864 |
Neg logit contributions | |
THING | -0.794 |
Cerberus | -0.718 |
IMAGES | -0.717 |
inosaur | -0.707 |
copyrighted | -0.692 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
nesota | +3.849 |
olate | +3.635 |
vale | +3.505 |
jected | +3.458 |
lication | +3.442 |
Neg logit contributions | |
THING | -3.165 |
IMAGES | -2.872 |
Cerberus | -2.858 |
inosaur | -2.819 |
copyrighted | -2.731 |
Token | use |
Token ID | 779 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
nesota | +3.356 |
olate | +3.101 |
vale | +2.965 |
jected | +2.898 |
lication | +2.879 |
Neg logit contributions | |
THING | -4.676 |
Cerberus | -4.332 |
IMAGES | -4.325 |
inosaur | -4.287 |
copyrighted | -4.194 |
Token | cannabis |
Token ID | 9499 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
nesota | +0.137 |
olate | +0.129 |
vale | +0.125 |
jected | +0.123 |
lication | +0.123 |
Neg logit contributions | |
THING | -0.095 |
Cerberus | -0.086 |
IMAGES | -0.085 |
inosaur | -0.084 |
copyrighted | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
THING | +1.068 |
Cerberus | +0.967 |
IMAGES | +0.967 |
inosaur | +0.953 |
copyrighted | +0.944 |
Neg logit contributions | |
nesota | -1.295 |
olate | -1.210 |
vale | -1.178 |
lication | -1.159 |
jected | -1.159 |
Token | { |
Token ID | 1391 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
THING | +0.326 |
Cerberus | +0.292 |
IMAGES | +0.292 |
inosaur | +0.288 |
copyrighted | +0.279 |
Neg logit contributions | |
nesota | -0.467 |
olate | -0.441 |
vale | -0.427 |
jected | -0.421 |
lication | -0.420 |
Token | 2 |
Token ID | 17 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
nesota | +3.053 |
olate | +2.855 |
vale | +2.763 |
lication | +2.694 |
jected | +2.689 |
Neg logit contributions | |
THING | -3.329 |
Cerberus | -3.077 |
IMAGES | -3.074 |
inosaur | -3.043 |
copyrighted | -2.984 |
Token | , |
Token ID | 11 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
nesota | +2.614 |
olate | +2.418 |
vale | +2.327 |
jected | +2.248 |
lication | +2.211 |
Neg logit contributions | |
THING | -3.967 |
ModLoader | -3.754 |
IMAGES | -3.705 |
Cerberus | -3.700 |
inosaur | -3.673 |
Token | 14 |
Token ID | 1478 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
THING | +0.193 |
Cerberus | +0.175 |
IMAGES | +0.174 |
inosaur | +0.172 |
copyrighted | +0.169 |
Neg logit contributions | |
nesota | -0.222 |
olate | -0.208 |
vale | -0.201 |
lication | -0.198 |
jected | -0.198 |
Token | } |
Token ID | 92 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
nesota | +1.132 |
olate | +1.076 |
vale | +1.047 |
jected | +1.031 |
lication | +1.025 |
Neg logit contributions | |
THING | -0.671 |
Cerberus | -0.597 |
IMAGES | -0.597 |
inosaur | -0.585 |
ModLoader | -0.568 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
nesota | +0.945 |
olate | +0.878 |
vale | +0.843 |
jected | +0.827 |
lication | +0.823 |
Neg logit contributions | |
THING | -1.123 |
Cerberus | -1.034 |
IMAGES | -1.033 |
inosaur | -1.023 |
copyrighted | -1.001 |
Token | " |
Token ID | 366 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
nesota | +6.314 |
olate | +5.881 |
vale | +5.637 |
onset | +5.422 |
jected | +5.378 |
Neg logit contributions | |
ModLoader | -9.666 |
THING | -9.437 |
inosaur | -8.831 |
IMAGES | -8.672 |
Cerberus | -8.593 |
Token | D |
Token ID | 35 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
nesota | +4.621 |
olate | +4.337 |
vale | +4.202 |
jected | +4.102 |
lication | +4.023 |
Neg logit contributions | |
THING | -5.956 |
IMAGES | -5.634 |
Cerberus | -5.592 |
inosaur | -5.550 |
copyrighted | -5.443 |
Token | ", |
Token ID | 1600 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
THING | +0.098 |
Cerberus | +0.090 |
IMAGES | +0.089 |
inosaur | +0.089 |
copyrighted | +0.086 |
Neg logit contributions | |
nesota | -0.097 |
olate | -0.091 |
vale | -0.088 |
jected | -0.086 |
lication | -0.086 |
Token | { |
Token ID | 1391 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
THING | +0.831 |
Cerberus | +0.745 |
IMAGES | +0.743 |
inosaur | +0.734 |
copyrighted | +0.712 |
Neg logit contributions | |
nesota | -1.196 |
olate | -1.130 |
vale | -1.097 |
jected | -1.080 |
lication | -1.076 |
Token | 1 |
Token ID | 16 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
nesota | +2.137 |
olate | +1.996 |
vale | +1.937 |
jected | +1.892 |
lication | +1.891 |
Neg logit contributions | |
THING | -2.276 |
IMAGES | -2.101 |
Cerberus | -2.100 |
inosaur | -2.070 |
copyrighted | -2.031 |
Token | of |
Token ID | 286 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
nesota | +3.071 |
olate | +2.906 |
vale | +2.819 |
jected | +2.805 |
lication | +2.772 |
Neg logit contributions | |
THING | -1.834 |
inosaur | -1.613 |
Cerberus | -1.611 |
IMAGES | -1.591 |
copyrighted | -1.535 |
Token | f |
Token ID | 277 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
nesota | +0.197 |
olate | +0.185 |
vale | +0.179 |
lication | +0.176 |
jected | +0.176 |
Neg logit contributions | |
THING | -0.163 |
IMAGES | -0.148 |
Cerberus | -0.148 |
inosaur | -0.145 |
copyrighted | -0.142 |
Token | ift |
Token ID | 2135 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
nesota | +0.662 |
olate | +0.568 |
vale | +0.529 |
jected | +0.508 |
lication | +0.502 |
Neg logit contributions | |
THING | -1.822 |
IMAGES | -1.730 |
inosaur | -1.717 |
Cerberus | -1.707 |
copyrighted | -1.682 |
Token | ies |
Token ID | 444 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nesota | +4.840 |
olate | +4.443 |
vale | +4.279 |
jected | +4.145 |
lication | +4.118 |
Neg logit contributions | |
THING | -7.230 |
Cerberus | -6.645 |
inosaur | -6.490 |
IMAGES | -6.479 |
copyrighted | -6.453 |
Token | in |
Token ID | 287 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
nesota | +3.975 |
olate | +3.743 |
vale | +3.625 |
jected | +3.587 |
onset | +3.559 |
Neg logit contributions | |
THING | -3.258 |
Cerberus | -2.930 |
IMAGES | -2.909 |
inosaur | -2.901 |
ModLoader | -2.839 |
Token | that |
Token ID | 326 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
nesota | +6.103 |
olate | +5.782 |
vale | +5.568 |
jected | +5.555 |
onset | +5.479 |
Neg logit contributions | |
THING | -4.538 |
inosaur | -4.051 |
Cerberus | -4.009 |
IMAGES | -3.992 |
ModLoader | -3.843 |
Token | game |
Token ID | 983 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
nesota | +6.805 |
olate | +6.301 |
vale | +6.033 |
jected | +5.992 |
onset | +5.978 |
Neg logit contributions | |
THING | -8.294 |
inosaur | -7.718 |
Cerberus | -7.603 |
IMAGES | -7.601 |
ModLoader | -7.436 |
Token | and |
Token ID | 290 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
nesota | +2.472 |
olate | +2.330 |
vale | +2.253 |
jected | +2.222 |
lication | +2.206 |
Neg logit contributions | |
THING | -2.007 |
Cerberus | -1.808 |
IMAGES | -1.808 |
inosaur | -1.786 |
copyrighted | -1.732 |
Token | I |
Token ID | 314 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
nesota | +3.193 |
olate | +3.027 |
vale | +2.915 |
jected | +2.880 |
lication | +2.839 |
Neg logit contributions | |
THING | -2.796 |
inosaur | -2.528 |
IMAGES | -2.528 |
Cerberus | -2.514 |
ModLoader | -2.433 |
Token | think |
Token ID | 892 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
THING | +0.830 |
Cerberus | +0.761 |
IMAGES | +0.757 |
copyrighted | +0.741 |
inosaur | +0.740 |
Neg logit contributions | |
nesota | -1.009 |
olate | -0.937 |
vale | -0.909 |
lication | -0.896 |
jected | -0.887 |
Token | only |
Token ID | 691 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
nesota | +4.076 |
olate | +3.870 |
vale | +3.730 |
jected | +3.674 |
lication | +3.648 |
Neg logit contributions | |
THING | -3.287 |
inosaur | -2.962 |
IMAGES | -2.946 |
Cerberus | -2.936 |
ModLoader | -2.850 |
Token | , |
Token ID | 11 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
nesota | +3.474 |
olate | +3.297 |
vale | +3.188 |
jected | +3.137 |
lication | +3.131 |
Neg logit contributions | |
THING | -2.582 |
IMAGES | -2.336 |
Cerberus | -2.319 |
inosaur | -2.289 |
ModLoader | -2.212 |
Token | and |
Token ID | 290 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
THING | +1.429 |
Cerberus | +1.296 |
IMAGES | +1.276 |
inosaur | +1.259 |
copyrighted | +1.234 |
Neg logit contributions | |
nesota | -2.165 |
olate | -2.049 |
vale | -1.988 |
jected | -1.957 |
lication | -1.956 |
Token | she |
Token ID | 673 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
nesota | +1.567 |
olate | +1.472 |
vale | +1.422 |
jected | +1.398 |
lication | +1.392 |
Neg logit contributions | |
THING | -1.383 |
IMAGES | -1.256 |
Cerberus | -1.254 |
inosaur | -1.241 |
copyrighted | -1.206 |
Token | seems |
Token ID | 2331 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
nesota | +0.195 |
olate | +0.184 |
vale | +0.176 |
jected | +0.174 |
lication | +0.174 |
Neg logit contributions | |
THING | -0.163 |
Cerberus | -0.148 |
IMAGES | -0.148 |
inosaur | -0.147 |
copyrighted | -0.144 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
nesota | +3.858 |
olate | +3.655 |
vale | +3.524 |
jected | +3.479 |
lication | +3.452 |
Neg logit contributions | |
THING | -3.290 |
IMAGES | -3.004 |
Cerberus | -2.981 |
inosaur | -2.937 |
copyrighted | -2.862 |
Token | comfortable |
Token ID | 6792 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
nesota | +4.651 |
olate | +4.424 |
vale | +4.254 |
jected | +4.222 |
onset | +4.166 |
Neg logit contributions | |
THING | -4.093 |
IMAGES | -3.769 |
inosaur | -3.717 |
Cerberus | -3.710 |
ModLoader | -3.622 |
Token | with |
Token ID | 351 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
nesota | +9.791 |
olate | +9.425 |
vale | +8.974 |
onset | +8.931 |
lication | +8.882 |
Neg logit contributions | |
THING | -8.473 |
IMAGES | -8.122 |
inosaur | -7.858 |
ModLoader | -7.757 |
Cerberus | -7.624 |
Token | both |
Token ID | 1111 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
nesota | +2.019 |
olate | +1.903 |
vale | +1.842 |
jected | +1.814 |
lication | +1.808 |
Neg logit contributions | |
THING | -1.569 |
Cerberus | -1.414 |
IMAGES | -1.414 |
inosaur | -1.395 |
copyrighted | -1.356 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
THING | +1.511 |
Cerberus | +1.379 |
IMAGES | +1.375 |
inosaur | +1.349 |
copyrighted | +1.333 |
Neg logit contributions | |
nesota | -1.583 |
olate | -1.485 |
vale | -1.430 |
lication | -1.403 |
jected | -1.400 |
Token | I |
Token ID | 314 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
nesota | +1.181 |
olate | +1.103 |
vale | +1.062 |
jected | +1.044 |
lication | +1.039 |
Neg logit contributions | |
THING | -1.218 |
Cerberus | -1.116 |
IMAGES | -1.114 |
inosaur | -1.101 |
copyrighted | -1.076 |
Token | mean |
Token ID | 1612 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
THING | +1.012 |
Cerberus | +0.922 |
inosaur | +0.919 |
IMAGES | +0.914 |
copyrighted | +0.910 |
Neg logit contributions | |
nesota | -1.018 |
olate | -0.934 |
vale | -0.909 |
lication | -0.892 |
jected | -0.885 |
Token | fall |
Token ID | 2121 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
nesota | +5.113 |
olate | +4.877 |
vale | +4.618 |
jected | +4.524 |
onset | +4.517 |
Neg logit contributions | |
THING | -6.061 |
inosaur | -5.562 |
Cerberus | -5.532 |
IMAGES | -5.521 |
ModLoader | -5.447 |
Token | back |
Token ID | 736 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
nesota | +4.099 |
olate | +3.899 |
vale | +3.739 |
jected | +3.677 |
onset | +3.614 |
Neg logit contributions | |
THING | -3.694 |
Cerberus | -3.359 |
IMAGES | -3.347 |
inosaur | -3.322 |
copyrighted | -3.250 |
Token | on |
Token ID | 319 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
nesota | +4.784 |
olate | +4.583 |
vale | +4.425 |
jected | +4.351 |
lication | +4.301 |
Neg logit contributions | |
THING | -3.775 |
IMAGES | -3.398 |
Cerberus | -3.377 |
inosaur | -3.366 |
copyrighted | -3.260 |
Token | your |
Token ID | 534 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
THING | +0.061 |
Cerberus | +0.055 |
IMAGES | +0.054 |
inosaur | +0.053 |
copyrighted | +0.052 |
Neg logit contributions | |
nesota | -0.088 |
olate | -0.082 |
vale | -0.080 |
lication | -0.079 |
jected | -0.079 |
Token | Deep |
Token ID | 10766 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
nesota | +1.749 |
olate | +1.632 |
vale | +1.577 |
jected | +1.547 |
lication | +1.543 |
Neg logit contributions | |
THING | -1.677 |
Cerberus | -1.532 |
IMAGES | -1.527 |
inosaur | -1.507 |
copyrighted | -1.478 |
Token | Conf |
Token ID | 7326 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
nesota | +0.349 |
olate | +0.328 |
vale | +0.319 |
lication | +0.315 |
jected | +0.314 |
Neg logit contributions | |
THING | -0.196 |
Cerberus | -0.177 |
IMAGES | -0.173 |
inosaur | -0.171 |
copyrighted | -0.165 |
Token | idence |
Token ID | 1704 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
olate | +5.237 |
nesota | +5.217 |
jected | +4.856 |
lication | +4.497 |
jection | +4.490 |
Neg logit contributions | |
THING | -13.891 |
ModLoader | -13.603 |
IMAGES | -13.078 |
Cerberus | -12.907 |
copyrighted | -12.641 |
Token | while |
Token ID | 981 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
nesota | +6.158 |
olate | +5.930 |
vale | +5.694 |
jected | +5.602 |
onset | +5.563 |
Neg logit contributions | |
THING | -5.855 |
inosaur | -5.393 |
IMAGES | -5.383 |
Cerberus | -5.358 |
ModLoader | -5.287 |
Token | getting |
Token ID | 1972 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
nesota | +3.171 |
olate | +2.993 |
vale | +2.889 |
jected | +2.853 |
lication | +2.836 |
Neg logit contributions | |
THING | -2.542 |
IMAGES | -2.296 |
Cerberus | -2.292 |
inosaur | -2.279 |
copyrighted | -2.202 |
Token | lazy |
Token ID | 16931 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
nesota | +3.006 |
olate | +2.850 |
vale | +2.731 |
jected | +2.726 |
lication | +2.680 |
Neg logit contributions | |
THING | -2.410 |
Cerberus | -2.171 |
inosaur | -2.168 |
IMAGES | -2.166 |
copyrighted | -2.086 |
Token | and |
Token ID | 290 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
nesota | +0.856 |
olate | +0.803 |
vale | +0.775 |
lication | +0.762 |
jected | +0.762 |
Neg logit contributions | |
THING | -0.744 |
Cerberus | -0.676 |
IMAGES | -0.674 |
inosaur | -0.661 |
copyrighted | -0.649 |
Token | most |
Token ID | 749 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
nesota | +1.465 |
olate | +1.349 |
vale | +1.289 |
jected | +1.262 |
lication | +1.254 |
Neg logit contributions | |
THING | -2.093 |
Cerberus | -1.940 |
IMAGES | -1.940 |
inosaur | -1.921 |
copyrighted | -1.883 |
Token | valuable |
Token ID | 8119 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
THING | +1.128 |
Cerberus | +0.976 |
copyrighted | +0.938 |
IMAGES | +0.936 |
inosaur | +0.924 |
Neg logit contributions | |
nesota | -2.601 |
olate | -2.467 |
vale | -2.417 |
lication | -2.397 |
jected | -2.378 |
Token | , |
Token ID | 11 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
THING | +1.706 |
Cerberus | +1.551 |
IMAGES | +1.528 |
copyrighted | +1.496 |
inosaur | +1.495 |
Neg logit contributions | |
nesota | -1.975 |
olate | -1.855 |
vale | -1.787 |
jected | -1.761 |
lication | -1.760 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
THING | +1.596 |
Cerberus | +1.449 |
IMAGES | +1.423 |
inosaur | +1.405 |
copyrighted | +1.386 |
Neg logit contributions | |
nesota | -2.432 |
olate | -2.286 |
vale | -2.226 |
lication | -2.196 |
jected | -2.186 |
Token | 1000 |
Token ID | 8576 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
THING | +0.705 |
Cerberus | +0.646 |
IMAGES | +0.636 |
inosaur | +0.629 |
copyrighted | +0.621 |
Neg logit contributions | |
nesota | -0.869 |
olate | -0.817 |
vale | -0.790 |
lication | -0.776 |
jected | -0.774 |
Token | Swiss |
Token ID | 14780 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
THING | +5.255 |
Cerberus | +4.751 |
IMAGES | +4.745 |
inosaur | +4.662 |
copyrighted | +4.592 |
Neg logit contributions | |
nesota | -5.823 |
olate | -5.448 |
vale | -5.168 |
jected | -5.162 |
lication | -5.161 |
Token | franc |
Token ID | 46754 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
nesota | +7.600 |
olate | +7.101 |
vale | +6.988 |
lication | +6.684 |
jected | +6.627 |
Neg logit contributions | |
THING | -7.930 |
IMAGES | -7.328 |
ModLoader | -7.244 |
inosaur | -7.209 |
Cerberus | -7.012 |
Token | note |
Token ID | 3465 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
nesota | +7.135 |
olate | +6.786 |
vale | +6.641 |
jected | +6.378 |
onset | +6.346 |
Neg logit contributions | |
THING | -7.043 |
IMAGES | -6.486 |
ModLoader | -6.397 |
Cerberus | -6.356 |
inosaur | -6.353 |
Token | ( |
Token ID | 357 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
nesota | +2.689 |
olate | +2.535 |
vale | +2.444 |
jected | +2.405 |
lication | +2.386 |
Neg logit contributions | |
THING | -2.498 |
IMAGES | -2.279 |
Cerberus | -2.262 |
inosaur | -2.244 |
copyrighted | -2.178 |
Token | USD |
Token ID | 29072 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
nesota | +0.363 |
olate | +0.338 |
vale | +0.326 |
lication | +0.321 |
jected | +0.320 |
Neg logit contributions | |
THING | -0.327 |
Cerberus | -0.297 |
IMAGES | -0.295 |
inosaur | -0.293 |
copyrighted | -0.286 |
Token | 10 |
Token ID | 838 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
THING | +1.438 |
Cerberus | +1.295 |
IMAGES | +1.281 |
inosaur | +1.263 |
copyrighted | +1.228 |
Neg logit contributions | |
nesota | -2.040 |
olate | -1.906 |
vale | -1.841 |
lication | -1.834 |
jected | -1.820 |