Token | to |
Token ID | 284 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
enburg | +0.154 |
assic | +0.150 |
yden | +0.134 |
IDES | +0.134 |
wana | +0.132 |
Neg logit contributions | |
redes | -0.178 |
Shank | -0.175 |
Sew | -0.163 |
purge | -0.160 |
comprom | -0.159 |
Token | fly |
Token ID | 6129 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
redes | +0.103 |
Shank | +0.102 |
Sew | +0.094 |
purge | +0.092 |
comprom | +0.090 |
Neg logit contributions | |
enburg | -0.116 |
assic | -0.114 |
yden | -0.103 |
IDES | -0.103 |
wana | -0.102 |
Token | back |
Token ID | 736 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
redes | +0.494 |
Shank | +0.490 |
Sew | +0.456 |
purge | +0.448 |
comprom | +0.438 |
Neg logit contributions | |
enburg | -0.463 |
assic | -0.453 |
yden | -0.404 |
IDES | -0.404 |
wana | -0.400 |
Token | to |
Token ID | 284 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
redes | +0.712 |
Shank | +0.706 |
Sew | +0.658 |
purge | +0.645 |
comprom | +0.630 |
Neg logit contributions | |
enburg | -0.677 |
assic | -0.664 |
IDES | -0.592 |
yden | -0.592 |
wana | -0.585 |
Token | Che |
Token ID | 2580 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
enburg | +0.042 |
assic | +0.041 |
IDES | +0.037 |
yden | +0.037 |
wana | +0.037 |
Neg logit contributions | |
redes | -0.042 |
Shank | -0.042 |
Sew | -0.039 |
purge | -0.038 |
comprom | -0.037 |
Token | chn |
Token ID | 1349 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
enburg | +0.262 |
assic | +0.259 |
IDES | +0.235 |
yden | +0.232 |
wana | +0.229 |
Neg logit contributions | |
Shank | -0.223 |
redes | -0.221 |
Sew | -0.205 |
purge | -0.201 |
Sho | -0.194 |
Token | ya |
Token ID | 3972 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
enburg | +2.582 |
assic | +2.498 |
yden | +2.230 |
wana | +2.209 |
IDES | +2.131 |
Neg logit contributions | |
redes | -3.235 |
Shank | -3.063 |
Sew | -2.861 |
comprom | -2.855 |
purge | -2.839 |
Token | on |
Token ID | 319 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
enburg | +0.388 |
assic | +0.378 |
yden | +0.338 |
IDES | +0.338 |
wana | +0.335 |
Neg logit contributions | |
redes | -0.416 |
Shank | -0.411 |
Sew | -0.382 |
purge | -0.376 |
comprom | -0.369 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
enburg | +0.138 |
assic | +0.134 |
yden | +0.122 |
IDES | +0.122 |
wana | +0.121 |
Neg logit contributions | |
redes | -0.118 |
Shank | -0.116 |
Sew | -0.107 |
purge | -0.105 |
comprom | -0.103 |
Token | night |
Token ID | 1755 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
redes | +0.077 |
Shank | +0.076 |
Sew | +0.071 |
purge | +0.070 |
comprom | +0.069 |
Neg logit contributions | |
enburg | -0.071 |
assic | -0.069 |
yden | -0.062 |
IDES | -0.061 |
wana | -0.061 |
Token | with |
Token ID | 351 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
enburg | +0.153 |
assic | +0.148 |
yden | +0.133 |
IDES | +0.132 |
wana | +0.131 |
Neg logit contributions | |
redes | -0.182 |
Shank | -0.179 |
Sew | -0.167 |
purge | -0.165 |
comprom | -0.162 |
Token | ce |
Token ID | 344 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
enburg | +0.108 |
assic | +0.106 |
IDES | +0.094 |
wana | +0.094 |
yden | +0.094 |
Neg logit contributions | |
Shank | -0.100 |
redes | -0.100 |
Sew | -0.094 |
purge | -0.090 |
comprom | -0.089 |
Token | / |
Token ID | 14 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
Shank | +0.166 |
redes | +0.165 |
Sew | +0.157 |
purge | +0.154 |
Sho | +0.152 |
Neg logit contributions | |
enburg | -0.094 |
assic | -0.091 |
yden | -0.077 |
IDES | -0.077 |
wana | -0.076 |
Token | edd |
Token ID | 6048 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
enburg | +0.500 |
assic | +0.487 |
yden | +0.429 |
IDES | +0.428 |
wana | +0.423 |
Neg logit contributions | |
redes | -0.655 |
Shank | -0.650 |
Sew | -0.609 |
purge | -0.599 |
comprom | -0.588 |
Token | 75 |
Token ID | 2425 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
enburg | +0.375 |
assic | +0.366 |
IDES | +0.323 |
yden | +0.322 |
wana | +0.318 |
Neg logit contributions | |
redes | -0.488 |
Shank | -0.485 |
Sew | -0.455 |
purge | -0.447 |
comprom | -0.438 |
Token | / |
Token ID | 14 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
enburg | +0.238 |
assic | +0.231 |
IDES | +0.198 |
yden | +0.198 |
wana | +0.194 |
Neg logit contributions | |
redes | -0.420 |
Shank | -0.418 |
Sew | -0.395 |
purge | -0.390 |
comprom | -0.382 |
Token | AUT |
Token ID | 39371 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
enburg | +0.156 |
assic | +0.152 |
yden | +0.115 |
IDES | +0.115 |
wana | +0.112 |
Neg logit contributions | |
Shank | -0.530 |
redes | -0.528 |
Sew | -0.507 |
purge | -0.498 |
Sho | -0.494 |
Token | OC |
Token ID | 4503 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
enburg | +1.757 |
assic | +1.697 |
IDES | +1.456 |
yden | +1.437 |
wana | +1.397 |
Neg logit contributions | |
redes | -3.580 |
Shank | -3.534 |
Sew | -3.333 |
purge | -3.306 |
comprom | -3.244 |
Token | R |
Token ID | 49 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
enburg | +1.525 |
assic | +1.473 |
IDES | +1.421 |
yden | +1.358 |
wana | +1.326 |
Neg logit contributions | |
redes | -2.307 |
Shank | -2.154 |
purge | -2.065 |
comprom | -2.039 |
Sew | -2.007 |
Token | OP |
Token ID | 3185 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
enburg | +0.223 |
assic | +0.211 |
yden | +0.187 |
wana | +0.186 |
IDES | +0.182 |
Neg logit contributions | |
Shank | -0.351 |
redes | -0.342 |
Sew | -0.332 |
purge | -0.323 |
Sho | -0.320 |
Token | / |
Token ID | 14 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
enburg | +0.716 |
assic | +0.693 |
yden | +0.582 |
IDES | +0.580 |
wana | +0.576 |
Neg logit contributions | |
Shank | -1.239 |
redes | -1.223 |
Sew | -1.174 |
purge | -1.153 |
Sho | -1.135 |
Token | h |
Token ID | 71 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
assic | +0.515 |
enburg | +0.507 |
yden | +0.459 |
IDES | +0.458 |
wana | +0.447 |
Neg logit contributions | |
Shank | -0.427 |
redes | -0.419 |
Sew | -0.397 |
purge | -0.386 |
Sho | -0.377 |
Token | hex |
Token ID | 17910 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
enburg | +0.162 |
assic | +0.157 |
yden | +0.141 |
IDES | +0.140 |
wana | +0.139 |
Neg logit contributions | |
redes | -0.181 |
Shank | -0.179 |
Sew | -0.167 |
purge | -0.164 |
comprom | -0.160 |
Token | agon |
Token ID | 1840 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
enburg | +0.371 |
assic | +0.362 |
yden | +0.324 |
IDES | +0.322 |
wana | +0.320 |
Neg logit contributions | |
redes | -0.391 |
Shank | -0.387 |
Sew | -0.361 |
purge | -0.354 |
comprom | -0.346 |
Token | - |
Token ID | 12 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
redes | +0.319 |
Shank | +0.316 |
Sew | +0.294 |
purge | +0.289 |
comprom | +0.283 |
Neg logit contributions | |
enburg | -0.294 |
assic | -0.287 |
yden | -0.257 |
IDES | -0.256 |
wana | -0.253 |
Token | shaped |
Token ID | 16760 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
enburg | +0.137 |
assic | +0.135 |
yden | +0.125 |
IDES | +0.124 |
wana | +0.124 |
Neg logit contributions | |
redes | -0.063 |
Shank | -0.062 |
Sew | -0.055 |
purge | -0.053 |
comprom | -0.051 |
Token | ep |
Token ID | 2462 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
redes | +0.344 |
Shank | +0.341 |
Sew | +0.318 |
purge | +0.313 |
comprom | +0.307 |
Neg logit contributions | |
enburg | -0.314 |
assic | -0.307 |
yden | -0.274 |
IDES | -0.273 |
wana | -0.270 |
Token | oxy |
Token ID | 23536 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
enburg | +1.328 |
assic | +1.292 |
yden | +1.134 |
wana | +1.109 |
IDES | +1.104 |
Neg logit contributions | |
redes | -1.922 |
Shank | -1.871 |
Sew | -1.761 |
purge | -1.744 |
comprom | -1.695 |
Token | resin |
Token ID | 36536 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
enburg | +2.196 |
assic | +2.143 |
yden | +1.909 |
IDES | +1.888 |
wana | +1.873 |
Neg logit contributions | |
redes | -2.627 |
Shank | -2.596 |
Sew | -2.414 |
purge | -2.355 |
Sho | -2.315 |
Token | scaff |
Token ID | 41498 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
enburg | +0.588 |
assic | +0.572 |
yden | +0.510 |
IDES | +0.509 |
wana | +0.503 |
Neg logit contributions | |
redes | -0.664 |
Shank | -0.656 |
Sew | -0.610 |
purge | -0.599 |
comprom | -0.587 |
Token | old |
Token ID | 727 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
redes | +0.894 |
Shank | +0.873 |
Sew | +0.824 |
purge | +0.813 |
comprom | +0.804 |
Neg logit contributions | |
enburg | -0.583 |
assic | -0.566 |
yden | -0.494 |
wana | -0.490 |
IDES | -0.487 |
Token | that |
Token ID | 326 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
enburg | +0.013 |
assic | +0.013 |
yden | +0.011 |
IDES | +0.011 |
wana | +0.011 |
Neg logit contributions | |
redes | -0.015 |
Shank | -0.015 |
Sew | -0.014 |
purge | -0.013 |
comprom | -0.013 |
Token | measures |
Token ID | 5260 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
enburg | +0.006 |
assic | +0.006 |
yden | +0.005 |
IDES | +0.005 |
wana | +0.005 |
Neg logit contributions | |
redes | -0.006 |
Shank | -0.006 |
Sew | -0.006 |
purge | -0.006 |
comprom | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
enburg | +0.038 |
assic | +0.037 |
yden | +0.033 |
IDES | +0.033 |
wana | +0.032 |
Neg logit contributions | |
redes | -0.047 |
Shank | -0.047 |
Sew | -0.044 |
purge | -0.043 |
comprom | -0.042 |
Token | � |
Token ID | 247 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
enburg | +0.080 |
assic | +0.078 |
IDES | +0.069 |
yden | +0.069 |
wana | +0.068 |
Neg logit contributions | |
redes | -0.100 |
Shank | -0.100 |
Sew | -0.093 |
purge | -0.092 |
comprom | -0.090 |
Token | d |
Token ID | 67 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
enburg | +0.061 |
assic | +0.060 |
yden | +0.053 |
IDES | +0.053 |
wana | +0.052 |
Neg logit contributions | |
redes | -0.073 |
Shank | -0.072 |
Sew | -0.067 |
purge | -0.066 |
comprom | -0.065 |
Token | be |
Token ID | 307 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
redes | +0.168 |
Shank | +0.166 |
Sew | +0.154 |
purge | +0.151 |
comprom | +0.148 |
Neg logit contributions | |
enburg | -0.177 |
assic | -0.173 |
yden | -0.156 |
IDES | -0.156 |
wana | -0.154 |
Token | one |
Token ID | 530 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
enburg | +0.004 |
assic | +0.004 |
yden | +0.004 |
IDES | +0.004 |
wana | +0.004 |
Neg logit contributions | |
redes | -0.005 |
Shank | -0.005 |
Sew | -0.004 |
purge | -0.004 |
comprom | -0.004 |
Token | heck |
Token ID | 22574 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
redes | +0.319 |
Shank | +0.315 |
Sew | +0.294 |
purge | +0.289 |
comprom | +0.283 |
Neg logit contributions | |
enburg | -0.286 |
assic | -0.278 |
yden | -0.249 |
IDES | -0.248 |
wana | -0.245 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
enburg | +2.139 |
assic | +2.047 |
yden | +1.821 |
wana | +1.799 |
IDES | +1.786 |
Neg logit contributions | |
redes | -2.615 |
Shank | -2.536 |
Sew | -2.391 |
purge | -2.349 |
comprom | -2.328 |
Token | a |
Token ID | 257 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
enburg | +0.072 |
assic | +0.070 |
yden | +0.062 |
IDES | +0.062 |
wana | +0.062 |
Neg logit contributions | |
redes | -0.088 |
Shank | -0.087 |
Sew | -0.082 |
purge | -0.080 |
comprom | -0.079 |
Token | better |
Token ID | 1365 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
enburg | +0.269 |
assic | +0.262 |
yden | +0.237 |
IDES | +0.235 |
wana | +0.233 |
Neg logit contributions | |
redes | -0.264 |
Shank | -0.260 |
Sew | -0.241 |
purge | -0.236 |
comprom | -0.230 |
Token | President |
Token ID | 1992 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
enburg | +0.493 |
assic | +0.479 |
yden | +0.433 |
IDES | +0.432 |
wana | +0.426 |
Neg logit contributions | |
redes | -0.471 |
Shank | -0.463 |
Sew | -0.430 |
purge | -0.420 |
Sho | -0.409 |
Token | I |
Token ID | 314 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
enburg | +0.219 |
assic | +0.213 |
yden | +0.191 |
IDES | +0.190 |
wana | +0.189 |
Neg logit contributions | |
redes | -0.237 |
Shank | -0.233 |
Sew | -0.217 |
purge | -0.214 |
comprom | -0.209 |
Token | minerals |
Token ID | 21622 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
enburg | +1.002 |
assic | +0.977 |
yden | +0.868 |
IDES | +0.866 |
wana | +0.856 |
Neg logit contributions | |
redes | -1.185 |
Shank | -1.173 |
Sew | -1.095 |
purge | -1.076 |
comprom | -1.055 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
enburg | +0.675 |
assic | +0.659 |
yden | +0.592 |
IDES | +0.591 |
wana | +0.585 |
Neg logit contributions | |
redes | -0.665 |
Shank | -0.659 |
Sew | -0.612 |
purge | -0.600 |
comprom | -0.588 |
Token | especially |
Token ID | 2592 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
enburg | +0.169 |
assic | +0.165 |
yden | +0.149 |
IDES | +0.148 |
wana | +0.147 |
Neg logit contributions | |
redes | -0.168 |
Shank | -0.166 |
Sew | -0.154 |
purge | -0.151 |
comprom | -0.148 |
Token | since |
Token ID | 1201 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
enburg | +0.446 |
assic | +0.433 |
IDES | +0.381 |
yden | +0.381 |
wana | +0.376 |
Neg logit contributions | |
redes | -0.590 |
Shank | -0.586 |
Sew | -0.550 |
purge | -0.541 |
comprom | -0.531 |
Token | ep |
Token ID | 2462 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
enburg | +0.231 |
assic | +0.225 |
IDES | +0.200 |
yden | +0.200 |
wana | +0.198 |
Neg logit contributions | |
redes | -0.259 |
Shank | -0.257 |
Sew | -0.240 |
purge | -0.236 |
comprom | -0.231 |
Token | oxy |
Token ID | 23536 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
enburg | +1.062 |
assic | +1.031 |
yden | +0.906 |
IDES | +0.888 |
wana | +0.878 |
Neg logit contributions | |
redes | -1.645 |
Shank | -1.621 |
Sew | -1.517 |
purge | -1.503 |
comprom | -1.470 |
Token | resin |
Token ID | 36536 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
enburg | +2.267 |
assic | +2.221 |
yden | +1.985 |
IDES | +1.971 |
wana | +1.946 |
Neg logit contributions | |
redes | -2.405 |
Shank | -2.388 |
Sew | -2.210 |
purge | -2.161 |
comprom | -2.116 |
Token | is |
Token ID | 318 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
enburg | +0.460 |
assic | +0.449 |
yden | +0.403 |
IDES | +0.403 |
wana | +0.399 |
Neg logit contributions | |
redes | -0.464 |
Shank | -0.460 |
Sew | -0.427 |
purge | -0.419 |
comprom | -0.411 |
Token | " |
Token ID | 366 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
enburg | +0.083 |
assic | +0.081 |
yden | +0.073 |
IDES | +0.073 |
wana | +0.072 |
Neg logit contributions | |
redes | -0.086 |
Shank | -0.085 |
Sew | -0.079 |
purge | -0.078 |
comprom | -0.077 |
Token | res |
Token ID | 411 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
redes | +0.444 |
Shank | +0.440 |
Sew | +0.408 |
purge | +0.400 |
comprom | +0.392 |
Neg logit contributions | |
enburg | -0.462 |
assic | -0.452 |
yden | -0.407 |
IDES | -0.406 |
wana | -0.401 |
Token | il |
Token ID | 346 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
enburg | +0.550 |
assic | +0.535 |
yden | +0.474 |
IDES | +0.474 |
wana | +0.467 |
Neg logit contributions | |
redes | -0.682 |
Shank | -0.675 |
Sew | -0.629 |
purge | -0.619 |
comprom | -0.607 |
Token | and |
Token ID | 290 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
redes | +0.051 |
Shank | +0.051 |
Sew | +0.048 |
purge | +0.047 |
comprom | +0.046 |
Neg logit contributions | |
enburg | -0.049 |
assic | -0.048 |
IDES | -0.043 |
yden | -0.043 |
wana | -0.043 |
Token | my |
Token ID | 616 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
redes | +0.286 |
Shank | +0.285 |
Sew | +0.265 |
purge | +0.261 |
comprom | +0.255 |
Neg logit contributions | |
enburg | -0.252 |
assic | -0.246 |
yden | -0.219 |
IDES | -0.219 |
wana | -0.216 |
Token | mouth |
Token ID | 5422 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
redes | +0.201 |
Shank | +0.199 |
Sew | +0.186 |
purge | +0.183 |
comprom | +0.179 |
Neg logit contributions | |
enburg | -0.171 |
assic | -0.166 |
yden | -0.148 |
IDES | -0.148 |
wana | -0.146 |
Token | was |
Token ID | 373 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
redes | +0.118 |
Shank | +0.117 |
Sew | +0.109 |
purge | +0.108 |
comprom | +0.105 |
Neg logit contributions | |
enburg | -0.101 |
assic | -0.098 |
yden | -0.087 |
IDES | -0.087 |
wana | -0.086 |
Token | all |
Token ID | 477 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
redes | +0.103 |
Shank | +0.102 |
Sew | +0.094 |
purge | +0.093 |
comprom | +0.091 |
Neg logit contributions | |
enburg | -0.109 |
assic | -0.106 |
yden | -0.096 |
IDES | -0.095 |
wana | -0.094 |
Token | sore |
Token ID | 19597 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Shank | +0.495 |
redes | +0.492 |
Sew | +0.460 |
purge | +0.452 |
Sho | +0.439 |
Neg logit contributions | |
enburg | -0.530 |
assic | -0.520 |
IDES | -0.469 |
yden | -0.467 |
wana | -0.463 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
enburg | +2.048 |
assic | +1.946 |
yden | +1.757 |
wana | +1.717 |
IDES | +1.708 |
Neg logit contributions | |
redes | -2.599 |
Shank | -2.499 |
Sew | -2.342 |
purge | -2.305 |
comprom | -2.294 |
Token | swollen |
Token ID | 37327 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
enburg | +0.013 |
assic | +0.013 |
IDES | +0.012 |
yden | +0.012 |
wana | +0.011 |
Neg logit contributions | |
Shank | -0.015 |
redes | -0.015 |
Sew | -0.014 |
purge | -0.014 |
comprom | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
enburg | +0.836 |
assic | +0.809 |
yden | +0.723 |
IDES | +0.718 |
wana | +0.711 |
Neg logit contributions | |
redes | -0.966 |
Shank | -0.946 |
Sew | -0.882 |
purge | -0.866 |
comprom | -0.857 |
Token | and |
Token ID | 290 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
redes | +0.116 |
Shank | +0.115 |
Sew | +0.107 |
purge | +0.105 |
comprom | +0.103 |
Neg logit contributions | |
enburg | -0.105 |
assic | -0.102 |
yden | -0.091 |
IDES | -0.091 |
wana | -0.090 |
Token | I |
Token ID | 314 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
redes | +0.049 |
Shank | +0.049 |
Sew | +0.046 |
purge | +0.045 |
comprom | +0.044 |
Neg logit contributions | |
enburg | -0.043 |
assic | -0.042 |
yden | -0.037 |
IDES | -0.037 |
wana | -0.037 |
Token | year |
Token ID | 1941 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
Shank | +0.340 |
redes | +0.334 |
Sew | +0.320 |
purge | +0.312 |
Sho | +0.307 |
Neg logit contributions | |
enburg | -0.238 |
assic | -0.232 |
IDES | -0.205 |
yden | -0.203 |
wana | -0.197 |
Token | - |
Token ID | 12 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Shank | +0.508 |
redes | +0.498 |
Sew | +0.474 |
purge | +0.463 |
Sho | +0.453 |
Neg logit contributions | |
enburg | -0.449 |
assic | -0.437 |
IDES | -0.392 |
yden | -0.391 |
wana | -0.383 |
Token | old |
Token ID | 727 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
Shank | +0.173 |
redes | +0.168 |
Sew | +0.162 |
purge | +0.158 |
Sho | +0.155 |
Neg logit contributions | |
enburg | -0.141 |
assic | -0.138 |
IDES | -0.123 |
yden | -0.122 |
wana | -0.119 |
Token | cr |
Token ID | 1067 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
redes | +0.048 |
Shank | +0.047 |
Sew | +0.044 |
purge | +0.043 |
comprom | +0.042 |
Neg logit contributions | |
enburg | -0.047 |
assic | -0.046 |
yden | -0.041 |
IDES | -0.041 |
wana | -0.041 |
Token | ick |
Token ID | 624 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
enburg | +0.304 |
assic | +0.298 |
yden | +0.266 |
IDES | +0.264 |
wana | +0.263 |
Neg logit contributions | |
redes | -0.320 |
Shank | -0.315 |
Sew | -0.293 |
purge | -0.289 |
comprom | -0.284 |
Token | eter |
Token ID | 2357 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
enburg | +0.186 |
assic | +0.176 |
yden | +0.137 |
IDES | +0.137 |
wana | +0.133 |
Neg logit contributions | |
redes | -0.601 |
Shank | -0.596 |
Sew | -0.569 |
purge | -0.562 |
comprom | -0.555 |
Token | added |
Token ID | 2087 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
enburg | +2.085 |
assic | +2.006 |
wana | +1.819 |
yden | +1.813 |
IDES | +1.809 |
Neg logit contributions | |
redes | -2.387 |
Shank | -2.299 |
Sew | -2.179 |
purge | -2.174 |
comprom | -2.115 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
redes | +0.482 |
Shank | +0.473 |
Sew | +0.444 |
purge | +0.436 |
comprom | +0.427 |
Neg logit contributions | |
enburg | -0.431 |
assic | -0.421 |
yden | -0.377 |
IDES | -0.375 |
wana | -0.371 |
Token |
|
Token ID | 198 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
enburg | +0.288 |
assic | +0.280 |
yden | +0.248 |
IDES | +0.248 |
wana | +0.246 |
Neg logit contributions | |
redes | -0.346 |
Shank | -0.340 |
Sew | -0.318 |
purge | -0.315 |
comprom | -0.310 |
Token |
|
Token ID | 198 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
enburg | +0.281 |
assic | +0.276 |
yden | +0.246 |
IDES | +0.245 |
wana | +0.242 |
Neg logit contributions | |
Shank | -0.306 |
redes | -0.300 |
Sew | -0.286 |
purge | -0.278 |
Sho | -0.274 |
Token | Speaking |
Token ID | 13887 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
enburg | +0.198 |
assic | +0.193 |
yden | +0.170 |
IDES | +0.169 |
wana | +0.168 |
Neg logit contributions | |
redes | -0.249 |
Shank | -0.249 |
Sew | -0.233 |
purge | -0.228 |
comprom | -0.224 |
Token | membranes |
Token ID | 43447 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
redes | +0.174 |
Shank | +0.173 |
Sew | +0.161 |
purge | +0.158 |
comprom | +0.155 |
Neg logit contributions | |
enburg | -0.164 |
assic | -0.160 |
yden | -0.143 |
IDES | -0.143 |
wana | -0.141 |
Token | of |
Token ID | 286 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
redes | +0.130 |
Shank | +0.129 |
Sew | +0.120 |
purge | +0.117 |
comprom | +0.115 |
Neg logit contributions | |
enburg | -0.125 |
assic | -0.122 |
yden | -0.109 |
IDES | -0.109 |
wana | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
enburg | +0.037 |
assic | +0.036 |
yden | +0.033 |
IDES | +0.033 |
wana | +0.032 |
Neg logit contributions | |
redes | -0.040 |
Shank | -0.040 |
Sew | -0.037 |
purge | -0.036 |
comprom | -0.036 |
Token | upper |
Token ID | 6727 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
redes | +0.023 |
Shank | +0.023 |
Sew | +0.021 |
purge | +0.021 |
comprom | +0.021 |
Neg logit contributions | |
enburg | -0.021 |
assic | -0.020 |
yden | -0.018 |
IDES | -0.018 |
wana | -0.018 |
Token | respiratory |
Token ID | 22949 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
enburg | +0.374 |
assic | +0.366 |
yden | +0.326 |
IDES | +0.325 |
wana | +0.319 |
Neg logit contributions | |
redes | -0.429 |
Shank | -0.422 |
Sew | -0.393 |
purge | -0.387 |
comprom | -0.381 |
Token | tract |
Token ID | 14998 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
enburg | +0.823 |
assic | +0.804 |
yden | +0.665 |
IDES | +0.658 |
wana | +0.644 |
Neg logit contributions | |
redes | -1.804 |
Shank | -1.780 |
Sew | -1.674 |
purge | -1.650 |
comprom | -1.641 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
enburg | +2.155 |
assic | +2.072 |
yden | +1.858 |
IDES | +1.852 |
wana | +1.828 |
Neg logit contributions | |
redes | -2.365 |
Shank | -2.299 |
Sew | -2.148 |
purge | -2.092 |
comprom | -2.067 |
Token | Because |
Token ID | 4362 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
redes | +0.029 |
Shank | +0.029 |
Sew | +0.027 |
purge | +0.026 |
comprom | +0.026 |
Neg logit contributions | |
enburg | -0.033 |
assic | -0.032 |
yden | -0.029 |
IDES | -0.029 |
wana | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
enburg | +0.123 |
assic | +0.120 |
yden | +0.107 |
IDES | +0.107 |
wana | +0.106 |
Neg logit contributions | |
redes | -0.138 |
Shank | -0.136 |
Sew | -0.127 |
purge | -0.125 |
comprom | -0.122 |
Token | arm |
Token ID | 3211 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
redes | +0.202 |
Shank | +0.200 |
Sew | +0.187 |
purge | +0.184 |
comprom | +0.180 |
Neg logit contributions | |
enburg | -0.174 |
assic | -0.169 |
yden | -0.150 |
IDES | -0.150 |
wana | -0.149 |
Token | ad |
Token ID | 324 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
redes | +0.938 |
Shank | +0.930 |
Sew | +0.873 |
purge | +0.857 |
comprom | +0.844 |
Neg logit contributions | |
enburg | -0.694 |
assic | -0.677 |
yden | -0.593 |
IDES | -0.590 |
wana | -0.584 |
Token | Pe |
Token ID | 2631 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
redes | +0.085 |
Shank | +0.085 |
Sew | +0.079 |
purge | +0.077 |
Sho | +0.075 |
Neg logit contributions | |
enburg | -0.089 |
assic | -0.087 |
IDES | -0.079 |
yden | -0.079 |
wana | -0.078 |
Token | pt |
Token ID | 457 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
enburg | +0.282 |
assic | +0.275 |
yden | +0.249 |
IDES | +0.246 |
wana | +0.245 |
Neg logit contributions | |
redes | -0.254 |
Shank | -0.249 |
Sew | -0.230 |
purge | -0.226 |
comprom | -0.222 |
Token | ost |
Token ID | 455 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
enburg | +0.778 |
assic | +0.757 |
yden | +0.645 |
IDES | +0.638 |
wana | +0.622 |
Neg logit contributions | |
redes | -1.510 |
Shank | -1.481 |
Sew | -1.397 |
purge | -1.376 |
comprom | -1.359 |
Token | re |
Token ID | 260 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
enburg | +1.215 |
assic | +1.188 |
yden | +1.045 |
wana | +1.031 |
IDES | +1.012 |
Neg logit contributions | |
redes | -1.473 |
Shank | -1.434 |
Sew | -1.344 |
purge | -1.334 |
comprom | -1.321 |
Token | pt |
Token ID | 457 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
enburg | +0.268 |
assic | +0.261 |
yden | +0.229 |
IDES | +0.229 |
wana | +0.226 |
Neg logit contributions | |
redes | -0.360 |
Shank | -0.357 |
Sew | -0.335 |
purge | -0.329 |
comprom | -0.324 |
Token | ococ |
Token ID | 34403 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
enburg | +0.832 |
assic | +0.800 |
yden | +0.692 |
IDES | +0.685 |
wana | +0.683 |
Neg logit contributions | |
redes | -1.411 |
Shank | -1.386 |
Sew | -1.300 |
purge | -1.290 |
comprom | -1.272 |
Token | cus |
Token ID | 9042 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
enburg | +1.569 |
assic | +1.558 |
yden | +1.349 |
IDES | +1.339 |
wana | +1.311 |
Neg logit contributions | |
redes | -2.851 |
Shank | -2.786 |
Sew | -2.612 |
purge | -2.594 |
comprom | -2.588 |
Token | , |
Token ID | 11 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
enburg | +0.870 |
assic | +0.846 |
yden | +0.746 |
IDES | +0.746 |
wana | +0.736 |
Neg logit contributions | |
redes | -1.138 |
Shank | -1.127 |
Sew | -1.056 |
purge | -1.039 |
comprom | -1.021 |
Token | Gard |
Token ID | 12790 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
redes | +0.194 |
Shank | +0.193 |
Sew | +0.179 |
purge | +0.175 |
Sho | +0.171 |
Neg logit contributions | |
enburg | -0.195 |
assic | -0.191 |
IDES | -0.171 |
yden | -0.171 |
wana | -0.170 |
Token | n |
Token ID | 77 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Shank | +0.451 |
redes | +0.451 |
Sew | +0.423 |
purge | +0.412 |
Sho | +0.402 |
Neg logit contributions | |
enburg | -0.436 |
assic | -0.429 |
IDES | -0.390 |
yden | -0.385 |
wana | -0.378 |
Token | erella |
Token ID | 36648 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
enburg | +0.427 |
assic | +0.414 |
yden | +0.361 |
IDES | +0.361 |
wana | +0.355 |
Neg logit contributions | |
redes | -0.672 |
Shank | -0.669 |
Sew | -0.630 |
purge | -0.619 |
comprom | -0.608 |
Token | night |
Token ID | 1755 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
enburg | +0.340 |
assic | +0.331 |
IDES | +0.299 |
yden | +0.299 |
wana | +0.295 |
Neg logit contributions | |
redes | -0.303 |
Shank | -0.298 |
Sew | -0.274 |
purge | -0.268 |
comprom | -0.264 |
Token | and |
Token ID | 290 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
redes | +0.422 |
Shank | +0.416 |
Sew | +0.388 |
purge | +0.382 |
comprom | +0.376 |
Neg logit contributions | |
enburg | -0.356 |
assic | -0.346 |
IDES | -0.308 |
yden | -0.307 |
wana | -0.304 |
Token | puts |
Token ID | 7584 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
enburg | +0.048 |
assic | +0.047 |
IDES | +0.043 |
yden | +0.043 |
wana | +0.042 |
Neg logit contributions | |
redes | -0.044 |
Shank | -0.043 |
Sew | -0.040 |
purge | -0.039 |
comprom | -0.038 |
Token | together |
Token ID | 1978 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
redes | +0.017 |
Shank | +0.016 |
Sew | +0.015 |
purge | +0.015 |
comprom | +0.015 |
Neg logit contributions | |
enburg | -0.015 |
assic | -0.014 |
yden | -0.013 |
IDES | -0.013 |
wana | -0.012 |
Token | one |
Token ID | 530 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
enburg | +0.249 |
assic | +0.242 |
IDES | +0.216 |
yden | +0.216 |
wana | +0.213 |
Neg logit contributions | |
redes | -0.278 |
Shank | -0.274 |
Sew | -0.255 |
purge | -0.251 |
comprom | -0.246 |
Token | heck |
Token ID | 22574 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
redes | +0.308 |
Shank | +0.304 |
Sew | +0.283 |
purge | +0.278 |
comprom | +0.273 |
Neg logit contributions | |
enburg | -0.282 |
assic | -0.275 |
yden | -0.245 |
IDES | -0.245 |
wana | -0.241 |
Token | of |
Token ID | 286 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
enburg | +1.941 |
assic | +1.889 |
yden | +1.648 |
IDES | +1.631 |
wana | +1.626 |
Neg logit contributions | |
redes | -2.464 |
Shank | -2.397 |
Sew | -2.246 |
purge | -2.210 |
comprom | -2.202 |
Token | a |
Token ID | 257 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
enburg | +0.188 |
assic | +0.184 |
yden | +0.162 |
IDES | +0.162 |
wana | +0.159 |
Neg logit contributions | |
redes | -0.237 |
Shank | -0.234 |
Sew | -0.219 |
purge | -0.215 |
comprom | -0.212 |
Token | sp |
Token ID | 599 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
enburg | +0.246 |
assic | +0.240 |
yden | +0.217 |
IDES | +0.217 |
wana | +0.214 |
Neg logit contributions | |
redes | -0.219 |
Shank | -0.215 |
Sew | -0.198 |
purge | -0.193 |
comprom | -0.190 |
Token | iced |
Token ID | 3711 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
redes | +0.103 |
Shank | +0.101 |
Sew | +0.095 |
purge | +0.093 |
comprom | +0.092 |
Neg logit contributions | |
enburg | -0.079 |
assic | -0.077 |
yden | -0.068 |
IDES | -0.068 |
wana | -0.067 |
Token | pear |
Token ID | 25286 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
enburg | +0.331 |
assic | +0.323 |
yden | +0.291 |
IDES | +0.291 |
wana | +0.287 |
Neg logit contributions | |
redes | -0.316 |
Shank | -0.312 |
Sew | -0.289 |
purge | -0.283 |
comprom | -0.277 |
Token | we |
Token ID | 356 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
redes | +0.057 |
Shank | +0.057 |
Sew | +0.053 |
purge | +0.052 |
comprom | +0.051 |
Neg logit contributions | |
enburg | -0.051 |
assic | -0.050 |
yden | -0.044 |
IDES | -0.044 |
wana | -0.044 |
Token | all |
Token ID | 477 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
enburg | +0.399 |
assic | +0.390 |
yden | +0.349 |
IDES | +0.348 |
wana | +0.345 |
Neg logit contributions | |
redes | -0.423 |
Shank | -0.418 |
Sew | -0.389 |
purge | -0.382 |
comprom | -0.374 |
Token | knew |
Token ID | 2993 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
redes | +0.253 |
Shank | +0.251 |
Sew | +0.233 |
purge | +0.229 |
comprom | +0.224 |
Neg logit contributions | |
enburg | -0.246 |
assic | -0.241 |
IDES | -0.216 |
yden | -0.216 |
wana | -0.213 |
Token | about |
Token ID | 546 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
enburg | +0.217 |
assic | +0.211 |
yden | +0.188 |
IDES | +0.188 |
wana | +0.185 |
Neg logit contributions | |
redes | -0.257 |
Shank | -0.253 |
Sew | -0.236 |
purge | -0.233 |
comprom | -0.228 |
Token | his |
Token ID | 465 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
redes | +0.280 |
Shank | +0.278 |
Sew | +0.260 |
purge | +0.256 |
comprom | +0.251 |
Neg logit contributions | |
enburg | -0.221 |
assic | -0.215 |
yden | -0.190 |
IDES | -0.189 |
wana | -0.187 |
Token | fond |
Token ID | 16245 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
enburg | +0.325 |
assic | +0.317 |
yden | +0.288 |
IDES | +0.288 |
wana | +0.284 |
Neg logit contributions | |
redes | -0.266 |
Shank | -0.262 |
Sew | -0.241 |
purge | -0.235 |
comprom | -0.230 |
Token | ness |
Token ID | 1108 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
enburg | +2.319 |
assic | +2.226 |
yden | +2.025 |
IDES | +2.003 |
wana | +2.002 |
Neg logit contributions | |
redes | -2.071 |
Shank | -2.062 |
Sew | -1.889 |
purge | -1.829 |
comprom | -1.814 |
Token | for |
Token ID | 329 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
enburg | +0.806 |
assic | +0.781 |
yden | +0.705 |
IDES | +0.702 |
wana | +0.699 |
Neg logit contributions | |
redes | -0.776 |
Shank | -0.766 |
Sew | -0.705 |
purge | -0.689 |
comprom | -0.678 |
Token | � |
Token ID | 564 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
enburg | +0.137 |
assic | +0.133 |
yden | +0.119 |
IDES | +0.119 |
wana | +0.118 |
Neg logit contributions | |
redes | -0.147 |
Shank | -0.145 |
Sew | -0.135 |
purge | -0.133 |
comprom | -0.130 |
Token | � |
Token ID | 247 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
enburg | +0.004 |
assic | +0.004 |
yden | +0.003 |
IDES | +0.003 |
wana | +0.003 |
Neg logit contributions | |
redes | -0.008 |
Shank | -0.008 |
Sew | -0.008 |
purge | -0.008 |
comprom | -0.007 |
Token | 60 |
Token ID | 1899 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
redes | +0.075 |
Shank | +0.074 |
Sew | +0.068 |
purge | +0.067 |
comprom | +0.066 |
Neg logit contributions | |
enburg | -0.084 |
assic | -0.082 |
yden | -0.074 |
IDES | -0.074 |
wana | -0.073 |
Token | badass |
Token ID | 37289 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
enburg | +0.262 |
assic | +0.252 |
IDES | +0.224 |
yden | +0.223 |
wana | +0.221 |
Neg logit contributions | |
redes | -0.329 |
Shank | -0.324 |
Sew | -0.302 |
purge | -0.298 |
comprom | -0.292 |
Token | ery |
Token ID | 1924 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
enburg | +0.800 |
assic | +0.779 |
yden | +0.696 |
IDES | +0.695 |
wana | +0.687 |
Neg logit contributions | |
redes | -0.889 |
Shank | -0.880 |
Sew | -0.820 |
purge | -0.807 |
comprom | -0.790 |
Token | , |
Token ID | 11 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
redes | +0.661 |
Shank | +0.655 |
Sew | +0.613 |
purge | +0.603 |
comprom | +0.591 |
Neg logit contributions | |
enburg | -0.527 |
assic | -0.513 |
yden | -0.454 |
IDES | -0.452 |
wana | -0.447 |
Token | and |
Token ID | 290 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
redes | +0.060 |
Shank | +0.060 |
Sew | +0.056 |
purge | +0.055 |
comprom | +0.054 |
Neg logit contributions | |
enburg | -0.052 |
assic | -0.051 |
yden | -0.045 |
IDES | -0.045 |
wana | -0.045 |
Token | one |
Token ID | 530 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
redes | +0.020 |
Shank | +0.020 |
Sew | +0.019 |
purge | +0.018 |
comprom | +0.018 |
Neg logit contributions | |
enburg | -0.019 |
assic | -0.018 |
IDES | -0.016 |
yden | -0.016 |
wana | -0.016 |
Token | hell |
Token ID | 5968 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
redes | +0.295 |
Shank | +0.292 |
Sew | +0.271 |
purge | +0.266 |
comprom | +0.260 |
Neg logit contributions | |
enburg | -0.294 |
assic | -0.287 |
yden | -0.258 |
IDES | -0.257 |
wana | -0.255 |
Token | of |
Token ID | 286 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
enburg | +1.916 |
assic | +1.875 |
yden | +1.629 |
IDES | +1.613 |
wana | +1.603 |
Neg logit contributions | |
redes | -2.453 |
Shank | -2.397 |
Sew | -2.239 |
purge | -2.198 |
comprom | -2.185 |
Token | an |
Token ID | 281 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
enburg | +0.162 |
assic | +0.158 |
IDES | +0.140 |
yden | +0.139 |
wana | +0.138 |
Neg logit contributions | |
redes | -0.199 |
Shank | -0.196 |
Sew | -0.184 |
purge | -0.181 |
comprom | -0.177 |
Token | epic |
Token ID | 12191 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
enburg | +0.074 |
assic | +0.072 |
yden | +0.064 |
IDES | +0.064 |
wana | +0.064 |
Neg logit contributions | |
redes | -0.080 |
Shank | -0.079 |
Sew | -0.074 |
purge | -0.073 |
comprom | -0.071 |
Token | superhero |
Token ID | 17343 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
enburg | +0.488 |
assic | +0.477 |
yden | +0.426 |
IDES | +0.426 |
wana | +0.422 |
Neg logit contributions | |
redes | -0.504 |
Shank | -0.499 |
Sew | -0.463 |
purge | -0.455 |
comprom | -0.446 |
Token | crossover |
Token ID | 27668 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
redes | +0.041 |
Shank | +0.041 |
Sew | +0.038 |
purge | +0.038 |
comprom | +0.037 |
Neg logit contributions | |
enburg | -0.034 |
assic | -0.033 |
yden | -0.029 |
IDES | -0.029 |
wana | -0.029 |
Token | oth |
Token ID | 849 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
enburg | +0.259 |
assic | +0.251 |
yden | +0.221 |
IDES | +0.220 |
wana | +0.218 |
Neg logit contributions | |
redes | -0.357 |
Shank | -0.354 |
Sew | -0.332 |
purge | -0.327 |
comprom | -0.321 |
Token | rix |
Token ID | 8609 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
redes | +0.331 |
Shank | +0.329 |
Sew | +0.310 |
purge | +0.306 |
comprom | +0.301 |
Neg logit contributions | |
enburg | -0.193 |
assic | -0.186 |
yden | -0.162 |
IDES | -0.161 |
wana | -0.158 |
Token | existed |
Token ID | 11196 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
enburg | +1.225 |
assic | +1.199 |
IDES | +1.071 |
yden | +1.068 |
wana | +1.060 |
Neg logit contributions | |
redes | -1.300 |
Shank | -1.286 |
Sew | -1.196 |
purge | -1.176 |
comprom | -1.151 |
Token | on |
Token ID | 319 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
Shank | +0.793 |
redes | +0.792 |
Sew | +0.733 |
purge | +0.720 |
comprom | +0.703 |
Neg logit contributions | |
enburg | -0.816 |
assic | -0.795 |
yden | -0.720 |
IDES | -0.718 |
wana | -0.704 |
Token | Hispan |
Token ID | 13600 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
redes | +0.007 |
Shank | +0.007 |
Sew | +0.007 |
purge | +0.006 |
comprom | +0.006 |
Neg logit contributions | |
enburg | -0.006 |
assic | -0.006 |
yden | -0.005 |
IDES | -0.005 |
wana | -0.005 |
Token | iola |
Token ID | 30292 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
enburg | +0.532 |
assic | +0.507 |
yden | +0.402 |
IDES | +0.401 |
wana | +0.391 |
Neg logit contributions | |
redes | -1.581 |
Shank | -1.573 |
Sew | -1.498 |
purge | -1.479 |
comprom | -1.459 |
Token | relatively |
Token ID | 5365 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
enburg | +2.159 |
assic | +2.111 |
IDES | +1.880 |
wana | +1.878 |
yden | +1.877 |
Neg logit contributions | |
redes | -2.187 |
Shank | -2.139 |
Sew | -1.991 |
purge | -1.959 |
comprom | -1.922 |
Token | morph |
Token ID | 17488 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
enburg | +0.212 |
assic | +0.207 |
yden | +0.186 |
IDES | +0.186 |
wana | +0.184 |
Neg logit contributions | |
redes | -0.197 |
Shank | -0.195 |
Sew | -0.180 |
purge | -0.177 |
comprom | -0.173 |
Token | ologically |
Token ID | 13437 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
enburg | +0.568 |
assic | +0.562 |
yden | +0.493 |
IDES | +0.490 |
wana | +0.487 |
Neg logit contributions | |
redes | -0.605 |
Shank | -0.583 |
Sew | -0.548 |
purge | -0.542 |
comprom | -0.527 |
Token | unchanged |
Token ID | 21588 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
enburg | +0.573 |
assic | +0.558 |
yden | +0.498 |
IDES | +0.498 |
wana | +0.493 |
Neg logit contributions | |
redes | -0.601 |
Shank | -0.590 |
Sew | -0.551 |
purge | -0.540 |
comprom | -0.530 |
Token | for |
Token ID | 329 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
redes | +0.100 |
Shank | +0.099 |
Sew | +0.092 |
purge | +0.090 |
comprom | +0.088 |
Neg logit contributions | |
enburg | -0.113 |
assic | -0.111 |
yden | -0.100 |
IDES | -0.100 |
wana | -0.099 |
Token | ied |
Token ID | 798 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
redes | +0.494 |
Shank | +0.491 |
Sew | +0.466 |
purge | +0.460 |
comprom | +0.452 |
Neg logit contributions | |
enburg | -0.231 |
assic | -0.223 |
IDES | -0.186 |
yden | -0.186 |
wana | -0.183 |
Token | them |
Token ID | 606 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
redes | +0.332 |
Shank | +0.330 |
Sew | +0.309 |
purge | +0.304 |
comprom | +0.297 |
Neg logit contributions | |
enburg | -0.267 |
assic | -0.260 |
IDES | -0.229 |
yden | -0.229 |
wana | -0.227 |
Token | up |
Token ID | 510 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
redes | +0.517 |
Shank | +0.514 |
Sew | +0.478 |
purge | +0.469 |
comprom | +0.457 |
Neg logit contributions | |
enburg | -0.520 |
assic | -0.507 |
IDES | -0.454 |
yden | -0.454 |
wana | -0.449 |
Token | with |
Token ID | 351 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
enburg | +0.072 |
assic | +0.071 |
yden | +0.063 |
IDES | +0.063 |
wana | +0.062 |
Neg logit contributions | |
redes | -0.075 |
Shank | -0.074 |
Sew | -0.069 |
purge | -0.068 |
comprom | -0.066 |
Token | two |
Token ID | 734 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
redes | +0.042 |
Shank | +0.042 |
Sew | +0.039 |
purge | +0.038 |
comprom | +0.037 |
Neg logit contributions | |
enburg | -0.037 |
assic | -0.036 |
yden | -0.032 |
IDES | -0.032 |
wana | -0.031 |
Token | flat |
Token ID | 6228 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
redes | +0.509 |
Shank | +0.506 |
Sew | +0.473 |
purge | +0.464 |
comprom | +0.454 |
Neg logit contributions | |
enburg | -0.459 |
assic | -0.446 |
IDES | -0.399 |
yden | -0.398 |
wana | -0.395 |
Token | head |
Token ID | 2256 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
enburg | +2.043 |
assic | +2.004 |
yden | +1.787 |
IDES | +1.781 |
wana | +1.759 |
Neg logit contributions | |
redes | -2.248 |
Shank | -2.210 |
Sew | -2.053 |
purge | -2.019 |
comprom | -1.994 |
Token | screw |
Token ID | 9580 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
redes | +0.428 |
Shank | +0.425 |
Sew | +0.398 |
purge | +0.391 |
comprom | +0.382 |
Neg logit contributions | |
enburg | -0.355 |
assic | -0.345 |
yden | -0.306 |
IDES | -0.306 |
wana | -0.303 |
Token | drivers |
Token ID | 36702 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
enburg | +0.699 |
assic | +0.677 |
yden | +0.570 |
IDES | +0.567 |
wana | +0.558 |
Neg logit contributions | |
redes | -1.406 |
Shank | -1.389 |
Sew | -1.316 |
purge | -1.295 |
comprom | -1.281 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
redes | +0.113 |
Shank | +0.112 |
Sew | +0.104 |
purge | +0.102 |
comprom | +0.100 |
Neg logit contributions | |
enburg | -0.104 |
assic | -0.101 |
yden | -0.090 |
IDES | -0.090 |
wana | -0.089 |
Token | It |
Token ID | 632 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
redes | +0.189 |
Shank | +0.187 |
Sew | +0.172 |
purge | +0.169 |
comprom | +0.165 |
Neg logit contributions | |
enburg | -0.221 |
assic | -0.216 |
yden | -0.196 |
IDES | -0.196 |
wana | -0.194 |
Token | / |
Token ID | 14 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
enburg | +0.244 |
assic | +0.237 |
yden | +0.201 |
IDES | +0.200 |
wana | +0.197 |
Neg logit contributions | |
redes | -0.458 |
Shank | -0.457 |
Sew | -0.432 |
purge | -0.425 |
comprom | -0.418 |
Token | index |
Token ID | 9630 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
enburg | +0.221 |
assic | +0.218 |
IDES | +0.191 |
yden | +0.190 |
wana | +0.189 |
Neg logit contributions | |
redes | -0.292 |
Shank | -0.291 |
Sew | -0.272 |
purge | -0.267 |
Sho | -0.264 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
enburg | +1.410 |
assic | +1.366 |
yden | +1.227 |
IDES | +1.223 |
wana | +1.204 |
Neg logit contributions | |
redes | -1.585 |
Shank | -1.545 |
Sew | -1.441 |
purge | -1.419 |
comprom | -1.397 |
Token | php |
Token ID | 10121 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
enburg | +0.168 |
assic | +0.164 |
IDES | +0.150 |
yden | +0.146 |
wana | +0.145 |
Neg logit contributions | |
Shank | -0.161 |
redes | -0.159 |
Sew | -0.150 |
Sho | -0.145 |
purge | -0.145 |
Token | ? |
Token ID | 30 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
enburg | +1.030 |
assic | +1.016 |
IDES | +0.859 |
yden | +0.857 |
wana | +0.842 |
Neg logit contributions | |
Shank | -1.748 |
redes | -1.744 |
Sew | -1.653 |
purge | -1.620 |
Sho | -1.597 |
Token | topic |
Token ID | 26652 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
redes | +0.890 |
Shank | +0.888 |
Sew | +0.842 |
purge | +0.830 |
Sho | +0.819 |
Neg logit contributions | |
enburg | -0.546 |
assic | -0.540 |
wana | -0.456 |
IDES | -0.454 |
yden | -0.451 |
Token | = |
Token ID | 28 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
enburg | +1.741 |
assic | +1.695 |
yden | +1.474 |
IDES | +1.472 |
wana | +1.459 |
Neg logit contributions | |
redes | -2.503 |
Shank | -2.503 |
Sew | -2.355 |
purge | -2.319 |
Sho | -2.276 |
Token | 28 |
Token ID | 2078 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
enburg | +1.200 |
assic | +1.158 |
yden | +1.022 |
IDES | +1.021 |
wana | +1.005 |
Neg logit contributions | |
redes | -1.647 |
Shank | -1.626 |
Sew | -1.523 |
purge | -1.505 |
comprom | -1.477 |
Token | 18 |
Token ID | 1507 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
enburg | +0.109 |
assic | +0.106 |
yden | +0.093 |
IDES | +0.093 |
wana | +0.092 |
Neg logit contributions | |
redes | -0.152 |
Shank | -0.151 |
Sew | -0.141 |
purge | -0.139 |
comprom | -0.137 |
Token | 48 |
Token ID | 2780 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
redes | +0.315 |
Shank | +0.313 |
Sew | +0.293 |
purge | +0.288 |
comprom | +0.283 |
Neg logit contributions | |
enburg | -0.233 |
assic | -0.226 |
yden | -0.199 |
IDES | -0.198 |
wana | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
enburg | +0.249 |
assic | +0.242 |
yden | +0.217 |
IDES | +0.217 |
wana | +0.214 |
Neg logit contributions | |
redes | -0.272 |
Shank | -0.269 |
Sew | -0.250 |
purge | -0.246 |
comprom | -0.241 |
Token | z |
Token ID | 89 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
enburg | +0.380 |
assic | +0.366 |
yden | +0.315 |
IDES | +0.313 |
wana | +0.311 |
Neg logit contributions | |
redes | -0.651 |
Shank | -0.645 |
Sew | -0.609 |
purge | -0.601 |
comprom | -0.591 |
Token | ons |
Token ID | 684 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
enburg | +0.589 |
assic | +0.571 |
yden | +0.509 |
wana | +0.507 |
IDES | +0.506 |
Neg logit contributions | |
redes | -0.651 |
Shank | -0.643 |
Sew | -0.600 |
purge | -0.592 |
comprom | -0.579 |
Token | por |
Token ID | 1819 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
redes | +0.624 |
Shank | +0.619 |
Sew | +0.585 |
purge | +0.576 |
comprom | +0.565 |
Neg logit contributions | |
enburg | -0.389 |
assic | -0.380 |
yden | -0.328 |
IDES | -0.328 |
wana | -0.320 |
Token | and |
Token ID | 290 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
enburg | +0.437 |
assic | +0.426 |
yden | +0.381 |
IDES | +0.381 |
wana | +0.377 |
Neg logit contributions | |
redes | -0.462 |
Shank | -0.456 |
Sew | -0.425 |
purge | -0.417 |
comprom | -0.409 |
Token | Gen |
Token ID | 5215 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
redes | +0.190 |
Shank | +0.189 |
Sew | +0.175 |
purge | +0.172 |
comprom | +0.168 |
Neg logit contributions | |
enburg | -0.184 |
assic | -0.179 |
yden | -0.161 |
IDES | -0.160 |
wana | -0.159 |
Token | ç |
Token ID | 16175 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
redes | +0.324 |
Shank | +0.321 |
Sew | +0.302 |
purge | +0.297 |
comprom | +0.292 |
Neg logit contributions | |
enburg | -0.220 |
assic | -0.214 |
yden | -0.187 |
IDES | -0.187 |
wana | -0.184 |
Token | ler |
Token ID | 1754 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
enburg | +1.952 |
assic | +1.850 |
yden | +1.638 |
IDES | +1.622 |
wana | +1.610 |
Neg logit contributions | |
redes | -2.350 |
Shank | -2.298 |
Sew | -2.171 |
purge | -2.130 |
comprom | -2.090 |
Token | b |
Token ID | 65 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
redes | +0.254 |
Shank | +0.251 |
Sew | +0.235 |
purge | +0.230 |
comprom | +0.226 |
Neg logit contributions | |
enburg | -0.220 |
assic | -0.215 |
yden | -0.191 |
IDES | -0.191 |
wana | -0.189 |
Token | irl |
Token ID | 1901 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
redes | +0.071 |
Shank | +0.070 |
Sew | +0.065 |
purge | +0.064 |
comprom | +0.063 |
Neg logit contributions | |
enburg | -0.070 |
assic | -0.068 |
yden | -0.061 |
IDES | -0.061 |
wana | -0.061 |
Token | i |
Token ID | 72 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
redes | +0.003 |
Shank | +0.003 |
Sew | +0.003 |
purge | +0.003 |
comprom | +0.003 |
Neg logit contributions | |
enburg | -0.002 |
assic | -0.002 |
yden | -0.002 |
IDES | -0.002 |
wana | -0.002 |
Token | ğ |
Token ID | 33133 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
enburg | +0.455 |
assic | +0.442 |
yden | +0.395 |
IDES | +0.395 |
wana | +0.390 |
Neg logit contributions | |
redes | -0.495 |
Shank | -0.488 |
Sew | -0.456 |
purge | -0.448 |
comprom | -0.440 |
Token | � |
Token ID | 247 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
redes | +0.473 |
Shank | +0.472 |
Sew | +0.440 |
purge | +0.433 |
comprom | +0.423 |
Neg logit contributions | |
enburg | -0.393 |
assic | -0.384 |
IDES | -0.339 |
yden | -0.339 |
wana | -0.336 |
Token | d |
Token ID | 67 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
redes | +0.084 |
Shank | +0.083 |
Sew | +0.078 |
purge | +0.076 |
comprom | +0.075 |
Neg logit contributions | |
enburg | -0.077 |
assic | -0.075 |
yden | -0.067 |
IDES | -0.067 |
wana | -0.066 |
Token | be |
Token ID | 307 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
redes | +0.226 |
Shank | +0.224 |
Sew | +0.207 |
purge | +0.203 |
comprom | +0.199 |
Neg logit contributions | |
enburg | -0.235 |
assic | -0.229 |
yden | -0.206 |
IDES | -0.206 |
wana | -0.203 |
Token | worth |
Token ID | 2861 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
redes | +0.262 |
Shank | +0.260 |
Sew | +0.242 |
purge | +0.237 |
comprom | +0.233 |
Neg logit contributions | |
enburg | -0.254 |
assic | -0.248 |
IDES | -0.222 |
yden | -0.222 |
wana | -0.220 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
redes | +0.320 |
Shank | +0.319 |
Sew | +0.297 |
purge | +0.291 |
comprom | +0.287 |
Neg logit contributions | |
enburg | -0.304 |
assic | -0.297 |
IDES | -0.265 |
yden | -0.265 |
wana | -0.263 |
Token | hell |
Token ID | 5968 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
enburg | +0.093 |
assic | +0.090 |
IDES | +0.081 |
yden | +0.081 |
wana | +0.080 |
Neg logit contributions | |
redes | -0.100 |
Shank | -0.100 |
Sew | -0.093 |
purge | -0.092 |
comprom | -0.089 |
Token | of |
Token ID | 286 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
enburg | +1.857 |
assic | +1.818 |
yden | +1.587 |
IDES | +1.582 |
vant | +1.561 |
Neg logit contributions | |
redes | -2.377 |
Shank | -2.319 |
Sew | -2.171 |
purge | -2.120 |
comprom | -2.116 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
enburg | +0.021 |
assic | +0.020 |
yden | +0.018 |
IDES | +0.018 |
wana | +0.018 |
Neg logit contributions | |
redes | -0.025 |
Shank | -0.025 |
Sew | -0.023 |
purge | -0.023 |
comprom | -0.023 |
Token | lot |
Token ID | 1256 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
enburg | +0.124 |
assic | +0.121 |
yden | +0.110 |
IDES | +0.110 |
wana | +0.109 |
Neg logit contributions | |
redes | -0.097 |
Shank | -0.096 |
Sew | -0.088 |
purge | -0.087 |
comprom | -0.084 |
Token | more |
Token ID | 517 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
redes | +0.212 |
Shank | +0.210 |
Sew | +0.194 |
purge | +0.191 |
comprom | +0.187 |
Neg logit contributions | |
enburg | -0.220 |
assic | -0.215 |
yden | -0.193 |
IDES | -0.193 |
wana | -0.191 |
Token | than |
Token ID | 621 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
enburg | +0.025 |
assic | +0.025 |
yden | +0.022 |
IDES | +0.022 |
wana | +0.022 |
Neg logit contributions | |
redes | -0.024 |
Shank | -0.024 |
Sew | -0.022 |
purge | -0.022 |
comprom | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
enburg | +0.097 |
assic | +0.095 |
yden | +0.084 |
IDES | +0.084 |
wana | +0.083 |
Neg logit contributions | |
redes | -0.113 |
Shank | -0.112 |
Sew | -0.105 |
purge | -0.103 |
comprom | -0.101 |
Token | rat |
Token ID | 4227 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
enburg | +0.071 |
assic | +0.069 |
yden | +0.062 |
IDES | +0.061 |
wana | +0.061 |
Neg logit contributions | |
redes | -0.075 |
Shank | -0.074 |
Sew | -0.069 |
purge | -0.068 |
comprom | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
redes | +0.229 |
Shank | +0.227 |
Sew | +0.211 |
purge | +0.208 |
comprom | +0.203 |
Neg logit contributions | |
enburg | -0.207 |
assic | -0.202 |
yden | -0.180 |
IDES | -0.180 |
wana | -0.178 |
Token | get |
Token ID | 651 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
enburg | +0.111 |
assic | +0.109 |
yden | +0.098 |
IDES | +0.098 |
wana | +0.097 |
Neg logit contributions | |
redes | -0.105 |
Shank | -0.104 |
Sew | -0.097 |
purge | -0.095 |
comprom | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
redes | +0.272 |
Shank | +0.270 |
Sew | +0.251 |
purge | +0.247 |
comprom | +0.241 |
Neg logit contributions | |
enburg | -0.260 |
assic | -0.254 |
yden | -0.227 |
IDES | -0.227 |
wana | -0.224 |
Token | heck |
Token ID | 22574 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
enburg | +0.045 |
assic | +0.044 |
yden | +0.039 |
IDES | +0.039 |
wana | +0.039 |
Neg logit contributions | |
redes | -0.045 |
Shank | -0.045 |
Sew | -0.042 |
purge | -0.041 |
comprom | -0.040 |
Token | off |
Token ID | 572 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
enburg | +1.964 |
assic | +1.891 |
yden | +1.694 |
IDES | +1.680 |
wana | +1.678 |
Neg logit contributions | |
redes | -2.266 |
Shank | -2.198 |
Sew | -2.072 |
purge | -2.043 |
comprom | -2.028 |
Token | this |
Token ID | 428 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
enburg | +0.682 |
assic | +0.658 |
yden | +0.586 |
IDES | +0.585 |
wana | +0.577 |
Neg logit contributions | |
redes | -0.886 |
Shank | -0.869 |
Sew | -0.812 |
purge | -0.803 |
comprom | -0.789 |
Token | sinking |
Token ID | 27141 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
redes | +0.163 |
Shank | +0.161 |
Sew | +0.150 |
purge | +0.147 |
comprom | +0.144 |
Neg logit contributions | |
enburg | -0.154 |
assic | -0.151 |
yden | -0.135 |
IDES | -0.135 |
wana | -0.133 |
Token | ship |
Token ID | 4074 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
enburg | +1.102 |
assic | +1.080 |
yden | +0.992 |
IDES | +0.989 |
wana | +0.981 |
Neg logit contributions | |
redes | -0.705 |
Shank | -0.694 |
Sew | -0.627 |
purge | -0.614 |
comprom | -0.599 |
Token | of |
Token ID | 286 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
enburg | +0.210 |
assic | +0.204 |
yden | +0.183 |
IDES | +0.182 |
wana | +0.180 |
Neg logit contributions | |
redes | -0.234 |
Shank | -0.231 |
Sew | -0.215 |
purge | -0.211 |
comprom | -0.208 |
Token | St |
Token ID | 1273 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
enburg | +0.606 |
assic | +0.588 |
IDES | +0.519 |
yden | +0.517 |
wana | +0.509 |
Neg logit contributions | |
redes | -0.843 |
Shank | -0.830 |
Sew | -0.777 |
purge | -0.769 |
comprom | -0.756 |
Token | all |
Token ID | 439 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
enburg | +0.146 |
assic | +0.142 |
yden | +0.127 |
IDES | +0.126 |
wana | +0.125 |
Neg logit contributions | |
redes | -0.164 |
Shank | -0.161 |
Sew | -0.150 |
purge | -0.148 |
comprom | -0.146 |
Token | one |
Token ID | 505 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
redes | +0.799 |
Shank | +0.791 |
Sew | +0.736 |
purge | +0.722 |
comprom | +0.707 |
Neg logit contributions | |
enburg | -0.773 |
assic | -0.754 |
yden | -0.676 |
IDES | -0.675 |
wana | -0.668 |
Token | - |
Token ID | 12 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
redes | +0.697 |
Shank | +0.692 |
Sew | +0.643 |
purge | +0.630 |
comprom | +0.617 |
Neg logit contributions | |
enburg | -0.681 |
assic | -0.665 |
yden | -0.596 |
IDES | -0.596 |
wana | -0.589 |
Token | Tom |
Token ID | 13787 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
enburg | +0.964 |
assic | +0.935 |
IDES | +0.826 |
yden | +0.821 |
wana | +0.808 |
Neg logit contributions | |
redes | -1.343 |
Shank | -1.317 |
Sew | -1.232 |
purge | -1.223 |
comprom | -1.202 |
Token | Cruise |
Token ID | 29147 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
enburg | +0.232 |
assic | +0.226 |
yden | +0.202 |
IDES | +0.200 |
wana | +0.199 |
Neg logit contributions | |
redes | -0.265 |
Shank | -0.259 |
Sew | -0.241 |
purge | -0.240 |
comprom | -0.235 |
Token | Book |
Token ID | 4897 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
enburg | +1.950 |
assic | +1.865 |
IDES | +1.667 |
yden | +1.660 |
wana | +1.657 |
Neg logit contributions | |
redes | -2.287 |
Shank | -2.222 |
purge | -2.061 |
Sew | -2.052 |
comprom | -2.045 |
Token | - |
Token ID | 12 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
enburg | +0.225 |
assic | +0.218 |
yden | +0.195 |
wana | +0.194 |
IDES | +0.193 |
Neg logit contributions | |
redes | -0.237 |
Shank | -0.231 |
Sew | -0.213 |
purge | -0.212 |
comprom | -0.209 |
Token | M |
Token ID | 44 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
enburg | +0.628 |
assic | +0.610 |
IDES | +0.537 |
yden | +0.534 |
wana | +0.526 |
Neg logit contributions | |
redes | -0.883 |
Shank | -0.869 |
Sew | -0.814 |
purge | -0.806 |
comprom | -0.792 |
Token | unch |
Token ID | 3316 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
redes | +0.192 |
Shank | +0.190 |
Sew | +0.178 |
purge | +0.175 |
comprom | +0.172 |
Neg logit contributions | |
enburg | -0.155 |
assic | -0.151 |
yden | -0.134 |
IDES | -0.134 |
wana | -0.132 |
Token | kins |
Token ID | 5331 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
redes | +1.094 |
Shank | +1.086 |
Sew | +1.014 |
purge | +0.995 |
comprom | +0.975 |
Neg logit contributions | |
enburg | -0.952 |
assic | -0.928 |
yden | -0.826 |
IDES | -0.825 |
wana | -0.815 |
Token | rav |
Token ID | 4108 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
enburg | +0.481 |
assic | +0.467 |
IDES | +0.424 |
yden | +0.422 |
wana | +0.417 |
Neg logit contributions | |
Shank | -0.454 |
redes | -0.447 |
Sew | -0.422 |
purge | -0.407 |
Sho | -0.402 |
Token | olt |
Token ID | 5978 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
enburg | +0.667 |
assic | +0.633 |
yden | +0.531 |
IDES | +0.523 |
wana | +0.515 |
Neg logit contributions | |
redes | -1.541 |
Shank | -1.504 |
purge | -1.421 |
Sew | -1.421 |
comprom | -1.404 |
Token | a |
Token ID | 64 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
enburg | +0.152 |
assic | +0.149 |
IDES | +0.132 |
yden | +0.132 |
wana | +0.129 |
Neg logit contributions | |
redes | -0.187 |
Shank | -0.187 |
Sew | -0.175 |
purge | -0.171 |
comprom | -0.169 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
enburg | +0.046 |
assic | +0.044 |
IDES | +0.040 |
yden | +0.040 |
wana | +0.039 |
Neg logit contributions | |
redes | -0.047 |
Shank | -0.047 |
Sew | -0.043 |
purge | -0.043 |
comprom | -0.042 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
redes | +0.090 |
Shank | +0.089 |
Sew | +0.083 |
purge | +0.082 |
comprom | +0.081 |
Neg logit contributions | |
enburg | -0.075 |
assic | -0.073 |
yden | -0.064 |
IDES | -0.064 |
wana | -0.064 |
Token | Cruise |
Token ID | 29147 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
enburg | +0.480 |
assic | +0.468 |
yden | +0.417 |
IDES | +0.417 |
wana | +0.415 |
Neg logit contributions | |
redes | -0.512 |
Shank | -0.494 |
purge | -0.461 |
Sew | -0.457 |
comprom | -0.454 |
Token | ( |
Token ID | 357 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
enburg | +1.960 |
assic | +1.880 |
IDES | +1.686 |
yden | +1.677 |
wana | +1.669 |
Neg logit contributions | |
redes | -2.278 |
Shank | -2.221 |
Sew | -2.078 |
purge | -2.045 |
comprom | -2.014 |
Token | for |
Token ID | 1640 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
redes | +0.037 |
Shank | +0.036 |
Sew | +0.034 |
purge | +0.033 |
comprom | +0.032 |
Neg logit contributions | |
enburg | -0.041 |
assic | -0.040 |
yden | -0.036 |
IDES | -0.036 |
wana | -0.036 |
Token | their |
Token ID | 511 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
redes | +0.055 |
Shank | +0.054 |
Sew | +0.051 |
purge | +0.050 |
comprom | +0.049 |
Neg logit contributions | |
enburg | -0.045 |
assic | -0.044 |
yden | -0.038 |
IDES | -0.038 |
wana | -0.038 |
Token | Scientology |
Token ID | 24990 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
enburg | +0.034 |
assic | +0.033 |
yden | +0.030 |
IDES | +0.030 |
wana | +0.029 |
Neg logit contributions | |
redes | -0.037 |
Shank | -0.036 |
Sew | -0.034 |
purge | -0.033 |
comprom | -0.033 |
Token | ); |
Token ID | 1776 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
enburg | +0.500 |
assic | +0.485 |
yden | +0.431 |
IDES | +0.431 |
wana | +0.426 |
Neg logit contributions | |
redes | -0.592 |
Shank | -0.587 |
Sew | -0.549 |
purge | -0.535 |
comprom | -0.529 |
Token | surveillance |
Token ID | 8452 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
enburg | +0.403 |
assic | +0.388 |
yden | +0.352 |
IDES | +0.348 |
wana | +0.343 |
Neg logit contributions | |
redes | -0.467 |
Shank | -0.460 |
Sew | -0.430 |
purge | -0.418 |
comprom | -0.416 |
Token | litigation |
Token ID | 19284 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
enburg | +0.155 |
assic | +0.150 |
yden | +0.134 |
IDES | +0.132 |
wana | +0.131 |
Neg logit contributions | |
redes | -0.191 |
Shank | -0.188 |
Sew | -0.177 |
purge | -0.172 |
comprom | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
redes | +0.039 |
Shank | +0.038 |
Sew | +0.036 |
purge | +0.035 |
comprom | +0.035 |
Neg logit contributions | |
enburg | -0.028 |
assic | -0.027 |
yden | -0.024 |
IDES | -0.024 |
wana | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
redes | +0.155 |
Shank | +0.153 |
Sew | +0.142 |
purge | +0.139 |
comprom | +0.137 |
Neg logit contributions | |
enburg | -0.164 |
assic | -0.160 |
yden | -0.145 |
IDES | -0.144 |
wana | -0.143 |
Token | sp |
Token ID | 2777 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
redes | +0.144 |
Shank | +0.142 |
Sew | +0.132 |
purge | +0.130 |
comprom | +0.127 |
Neg logit contributions | |
enburg | -0.131 |
assic | -0.128 |
yden | -0.114 |
IDES | -0.114 |
wana | -0.113 |
Token | ent |
Token ID | 298 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
enburg | +0.138 |
assic | +0.132 |
yden | +0.115 |
IDES | +0.113 |
wana | +0.110 |
Neg logit contributions | |
redes | -0.264 |
Shank | -0.259 |
Sew | -0.243 |
purge | -0.241 |
comprom | -0.238 |
Token | $ |
Token ID | 720 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Shank | +3.338 |
redes | +3.329 |
Sew | +3.117 |
purge | +3.064 |
comprom | +3.004 |
Neg logit contributions | |
enburg | -3.140 |
assic | -3.058 |
IDES | -2.746 |
wana | -2.729 |
yden | -2.723 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
enburg | +0.358 |
assic | +0.348 |
yden | +0.306 |
IDES | +0.306 |
wana | +0.302 |
Neg logit contributions | |
redes | -0.478 |
Shank | -0.474 |
Sew | -0.444 |
purge | -0.437 |
comprom | -0.429 |
Token | . |
Token ID | 13 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
enburg | +0.098 |
assic | +0.095 |
yden | +0.084 |
IDES | +0.084 |
wana | +0.083 |
Neg logit contributions | |
redes | -0.120 |
Shank | -0.118 |
Sew | -0.111 |
purge | -0.109 |
comprom | -0.107 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
enburg | +0.290 |
assic | +0.281 |
IDES | +0.249 |
yden | +0.249 |
wana | +0.245 |
Neg logit contributions | |
redes | -0.379 |
Shank | -0.372 |
Sew | -0.348 |
purge | -0.344 |
comprom | -0.338 |
Token | million |
Token ID | 1510 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
redes | +0.004 |
Shank | +0.004 |
Sew | +0.004 |
purge | +0.004 |
comprom | +0.004 |
Neg logit contributions | |
enburg | -0.003 |
assic | -0.003 |
yden | -0.003 |
IDES | -0.003 |
wana | -0.003 |
Token | Jamaica |
Token ID | 31620 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
redes | +0.068 |
Shank | +0.067 |
Sew | +0.063 |
purge | +0.062 |
comprom | +0.061 |
Neg logit contributions | |
enburg | -0.060 |
assic | -0.058 |
IDES | -0.052 |
yden | -0.052 |
wana | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
enburg | +0.750 |
assic | +0.726 |
IDES | +0.652 |
yden | +0.646 |
wana | +0.640 |
Neg logit contributions | |
redes | -0.883 |
Shank | -0.865 |
Sew | -0.805 |
purge | -0.799 |
comprom | -0.785 |
Token | on |
Token ID | 319 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
redes | +0.045 |
Shank | +0.045 |
Sew | +0.042 |
purge | +0.041 |
comprom | +0.040 |
Neg logit contributions | |
enburg | -0.046 |
assic | -0.045 |
yden | -0.041 |
IDES | -0.041 |
wana | -0.040 |
Token | Monday |
Token ID | 3321 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
redes | +0.081 |
Shank | +0.080 |
Sew | +0.074 |
purge | +0.073 |
comprom | +0.071 |
Neg logit contributions | |
enburg | -0.095 |
assic | -0.093 |
yden | -0.084 |
IDES | -0.084 |
wana | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
redes | +0.066 |
Shank | +0.065 |
Sew | +0.061 |
purge | +0.060 |
comprom | +0.059 |
Neg logit contributions | |
enburg | -0.055 |
assic | -0.053 |
yden | -0.047 |
IDES | -0.047 |
wana | -0.047 |
Token | Credit |
Token ID | 10504 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
redes | +0.071 |
Shank | +0.069 |
purge | +0.064 |
Sew | +0.064 |
comprom | +0.063 |
Neg logit contributions | |
enburg | -0.073 |
assic | -0.070 |
IDES | -0.064 |
yden | -0.063 |
wana | -0.063 |
Token | : |
Token ID | 25 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Shank | +3.097 |
redes | +3.027 |
Sew | +2.893 |
purge | +2.790 |
Sho | +2.765 |
Neg logit contributions | |
enburg | -2.765 |
assic | -2.751 |
yden | -2.428 |
IDES | -2.408 |
wana | -2.380 |
Token | AP |
Token ID | 2969 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
enburg | +0.360 |
assic | +0.349 |
IDES | +0.313 |
yden | +0.311 |
wana | +0.308 |
Neg logit contributions | |
redes | -0.420 |
Shank | -0.412 |
Sew | -0.384 |
purge | -0.381 |
comprom | -0.374 |
Token | While |
Token ID | 2893 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
enburg | +0.983 |
assic | +0.954 |
IDES | +0.860 |
yden | +0.849 |
wana | +0.837 |
Neg logit contributions | |
redes | -1.143 |
Shank | -1.113 |
purge | -1.033 |
Sew | -1.030 |
comprom | -1.026 |
Token | fore |
Token ID | 1674 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
enburg | +0.182 |
assic | +0.177 |
IDES | +0.158 |
yden | +0.158 |
wana | +0.156 |
Neg logit contributions | |
redes | -0.200 |
Shank | -0.197 |
Sew | -0.183 |
purge | -0.181 |
comprom | -0.178 |
Token | casters |
Token ID | 26248 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
redes | +0.592 |
Shank | +0.586 |
Sew | +0.539 |
purge | +0.533 |
comprom | +0.525 |
Neg logit contributions | |
enburg | -0.667 |
assic | -0.646 |
yden | -0.584 |
wana | -0.578 |
IDES | -0.578 |
Token | > |
Token ID | 1875 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Shank | +1.083 |
redes | +1.082 |
Sew | +1.019 |
purge | +0.998 |
comprom | +0.977 |
Neg logit contributions | |
enburg | -0.884 |
assic | -0.861 |
yden | -0.759 |
IDES | -0.754 |
wana | -0.748 |
Token | & |
Token ID | 1222 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
enburg | +0.421 |
assic | +0.412 |
yden | +0.372 |
IDES | +0.370 |
wana | +0.367 |
Neg logit contributions | |
redes | -0.387 |
Shank | -0.384 |
Sew | -0.355 |
purge | -0.349 |
comprom | -0.341 |
Token | density |
Token ID | 12109 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
redes | +1.631 |
Shank | +1.622 |
Sew | +1.505 |
purge | +1.480 |
comprom | +1.440 |
Neg logit contributions | |
enburg | -1.768 |
assic | -1.746 |
yden | -1.564 |
IDES | -1.560 |
wana | -1.538 |
Token | Grid |
Token ID | 41339 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
enburg | +0.395 |
assic | +0.385 |
yden | +0.346 |
IDES | +0.346 |
wana | +0.342 |
Neg logit contributions | |
redes | -0.389 |
Shank | -0.385 |
Sew | -0.357 |
purge | -0.350 |
comprom | -0.343 |
Token | , |
Token ID | 837 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
redes | +0.073 |
Shank | +0.073 |
Sew | +0.068 |
purge | +0.066 |
comprom | +0.065 |
Neg logit contributions | |
enburg | -0.072 |
assic | -0.071 |
yden | -0.063 |
IDES | -0.063 |
wana | -0.063 |
Token | const |
Token ID | 1500 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
enburg | +0.020 |
assic | +0.020 |
IDES | +0.018 |
yden | +0.018 |
wana | +0.017 |
Neg logit contributions | |
redes | -0.021 |
Shank | -0.021 |
Sew | -0.019 |
purge | -0.019 |
comprom | -0.019 |
Token | Vector |
Token ID | 20650 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
Shank | +2.807 |
redes | +2.782 |
Sew | +2.609 |
purge | +2.529 |
Sho | +2.468 |
Neg logit contributions | |
assic | -3.071 |
enburg | -3.064 |
yden | -2.742 |
IDES | -2.702 |
wana | -2.682 |
Token | < |
Token ID | 27 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
redes | +0.759 |
Shank | +0.758 |
Sew | +0.709 |
purge | +0.693 |
comprom | +0.682 |
Neg logit contributions | |
enburg | -0.620 |
assic | -0.604 |
yden | -0.534 |
IDES | -0.528 |
wana | -0.523 |
Token | Part |
Token ID | 2142 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
enburg | +0.120 |
assic | +0.117 |
yden | +0.106 |
IDES | +0.106 |
wana | +0.105 |
Neg logit contributions | |
redes | -0.097 |
Shank | -0.096 |
Sew | -0.089 |
purge | -0.087 |
comprom | -0.085 |
Token | icle |
Token ID | 1548 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
enburg | +0.168 |
assic | +0.164 |
yden | +0.149 |
IDES | +0.149 |
wana | +0.147 |
Neg logit contributions | |
redes | -0.134 |
Shank | -0.132 |
Sew | -0.122 |
purge | -0.119 |
comprom | -0.116 |
Token | > |
Token ID | 1875 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
enburg | +0.157 |
assic | +0.153 |
yden | +0.134 |
IDES | +0.133 |
wana | +0.133 |
Neg logit contributions | |
redes | -0.209 |
Shank | -0.208 |
Sew | -0.196 |
purge | -0.192 |
comprom | -0.188 |
Token | ) |
Token ID | 8 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
redes | +0.405 |
Shank | +0.402 |
Sew | +0.377 |
purge | +0.371 |
comprom | +0.365 |
Neg logit contributions | |
enburg | -0.284 |
assic | -0.276 |
yden | -0.242 |
IDES | -0.242 |
wana | -0.238 |
Token | { |
Token ID | 1391 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
redes | +0.631 |
Shank | +0.620 |
Sew | +0.557 |
purge | +0.539 |
comprom | +0.527 |
Neg logit contributions | |
enburg | -1.144 |
assic | -1.120 |
yden | -1.035 |
IDES | -1.035 |
wana | -1.025 |
Token | // |
Token ID | 3373 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
redes | +1.196 |
Shank | +1.186 |
Sew | +1.106 |
purge | +1.089 |
comprom | +1.066 |
Neg logit contributions | |
enburg | -1.051 |
assic | -1.026 |
yden | -0.913 |
IDES | -0.913 |
wana | -0.901 |
Token | Time |
Token ID | 3862 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
enburg | +0.390 |
assic | +0.379 |
yden | +0.342 |
IDES | +0.342 |
wana | +0.339 |
Neg logit contributions | |
redes | -0.375 |
Shank | -0.370 |
Sew | -0.342 |
purge | -0.334 |
comprom | -0.328 |
Token | component |
Token ID | 7515 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
redes | +0.272 |
Shank | +0.268 |
Sew | +0.249 |
purge | +0.244 |
comprom | +0.239 |
Neg logit contributions | |
enburg | -0.264 |
assic | -0.257 |
yden | -0.231 |
IDES | -0.231 |
wana | -0.228 |
Token | const |
Token ID | 1500 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
redes | +0.084 |
Shank | +0.083 |
Sew | +0.077 |
purge | +0.076 |
comprom | +0.074 |
Neg logit contributions | |
enburg | -0.079 |
assic | -0.077 |
yden | -0.069 |
IDES | -0.069 |
wana | -0.068 |
Token | float |
Token ID | 12178 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Shank | +2.792 |
redes | +2.785 |
Sew | +2.568 |
purge | +2.534 |
Sho | +2.484 |
Neg logit contributions | |
enburg | -3.043 |
assic | -3.001 |
yden | -2.682 |
IDES | -2.661 |
wana | -2.650 |
Token | TA |
Token ID | 21664 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
redes | +1.213 |
Shank | +1.204 |
Sew | +1.118 |
purge | +1.101 |
comprom | +1.077 |
Neg logit contributions | |
enburg | -1.162 |
assic | -1.138 |
yden | -1.014 |
IDES | -1.012 |
wana | -1.002 |
Token | U |
Token ID | 52 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
redes | +0.370 |
Shank | +0.365 |
Sew | +0.342 |
purge | +0.336 |
comprom | +0.329 |
Neg logit contributions | |
enburg | -0.308 |
assic | -0.301 |
yden | -0.267 |
IDES | -0.267 |
wana | -0.263 |
Token | = |
Token ID | 796 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
enburg | +0.916 |
assic | +0.889 |
IDES | +0.795 |
yden | +0.789 |
wana | +0.780 |
Neg logit contributions | |
redes | -1.145 |
Shank | -1.127 |
Sew | -1.050 |
purge | -1.036 |
comprom | -1.015 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
redes | +0.212 |
Shank | +0.210 |
Sew | +0.195 |
purge | +0.192 |
comprom | +0.188 |
Neg logit contributions | |
enburg | -0.211 |
assic | -0.206 |
yden | -0.184 |
IDES | -0.184 |
wana | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
enburg | +0.025 |
assic | +0.024 |
yden | +0.021 |
IDES | +0.021 |
wana | +0.021 |
Neg logit contributions | |
redes | -0.034 |
Shank | -0.033 |
Sew | -0.031 |
purge | -0.031 |
comprom | -0.030 |
Token | 25 |
Token ID | 1679 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
enburg | +0.010 |
assic | +0.009 |
IDES | +0.008 |
yden | +0.008 |
wana | +0.008 |
Neg logit contributions | |
redes | -0.010 |
Shank | -0.010 |
Sew | -0.010 |
purge | -0.009 |
comprom | -0.009 |
Token | th |
Token ID | 400 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
redes | +0.130 |
Shank | +0.127 |
Sew | +0.119 |
purge | +0.117 |
comprom | +0.115 |
Neg logit contributions | |
enburg | -0.116 |
assic | -0.113 |
IDES | -0.101 |
yden | -0.100 |
wana | -0.099 |
Token | partition |
Token ID | 18398 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
redes | +0.259 |
Shank | +0.255 |
Sew | +0.237 |
purge | +0.232 |
comprom | +0.227 |
Neg logit contributions | |
enburg | -0.270 |
assic | -0.263 |
yden | -0.237 |
IDES | -0.237 |
wana | -0.234 |
Token | (/ |
Token ID | 50247 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
enburg | +0.692 |
assic | +0.672 |
yden | +0.602 |
IDES | +0.602 |
wana | +0.593 |
Neg logit contributions | |
redes | -0.776 |
Shank | -0.765 |
Sew | -0.713 |
purge | -0.699 |
comprom | -0.689 |
Token | dev |
Token ID | 7959 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
redes | +0.720 |
Shank | +0.711 |
Sew | +0.662 |
purge | +0.649 |
comprom | +0.638 |
Neg logit contributions | |
enburg | -0.664 |
assic | -0.646 |
yden | -0.579 |
IDES | -0.579 |
wana | -0.571 |
Token | / |
Token ID | 14 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
Shank | +3.540 |
redes | +3.528 |
Sew | +3.330 |
purge | +3.290 |
Sho | +3.226 |
Neg logit contributions | |
enburg | -2.119 |
assic | -2.066 |
yden | -1.746 |
wana | -1.742 |
IDES | -1.733 |
Token | mm |
Token ID | 3020 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
redes | +0.637 |
Shank | +0.629 |
Sew | +0.587 |
purge | +0.576 |
comprom | +0.566 |
Neg logit contributions | |
enburg | -0.574 |
assic | -0.558 |
yden | -0.499 |
IDES | -0.497 |
wana | -0.491 |
Token | c |
Token ID | 66 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
redes | +0.093 |
Shank | +0.091 |
Sew | +0.085 |
purge | +0.084 |
comprom | +0.082 |
Neg logit contributions | |
enburg | -0.070 |
assic | -0.068 |
yden | -0.060 |
IDES | -0.059 |
wana | -0.058 |
Token | bl |
Token ID | 2436 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
redes | +0.340 |
Shank | +0.337 |
Sew | +0.312 |
purge | +0.306 |
comprom | +0.299 |
Neg logit contributions | |
enburg | -0.360 |
assic | -0.352 |
IDES | -0.317 |
yden | -0.317 |
wana | -0.313 |
Token | k |
Token ID | 74 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
enburg | +0.194 |
assic | +0.189 |
yden | +0.172 |
wana | +0.170 |
IDES | +0.170 |
Neg logit contributions | |
redes | -0.190 |
Shank | -0.184 |
Sew | -0.172 |
purge | -0.169 |
comprom | -0.165 |
Token | in |
Token ID | 287 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
enburg | +0.411 |
assic | +0.396 |
IDES | +0.355 |
yden | +0.354 |
wana | +0.351 |
Neg logit contributions | |
redes | -0.465 |
Shank | -0.457 |
Sew | -0.422 |
purge | -0.419 |
comprom | -0.413 |
Token | Kingston |
Token ID | 34612 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
redes | +0.098 |
Shank | +0.096 |
Sew | +0.089 |
purge | +0.088 |
comprom | +0.086 |
Neg logit contributions | |
enburg | -0.095 |
assic | -0.092 |
yden | -0.083 |
IDES | -0.083 |
wana | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
redes | +0.658 |
Shank | +0.650 |
Sew | +0.606 |
purge | +0.599 |
comprom | +0.587 |
Neg logit contributions | |
enburg | -0.547 |
assic | -0.530 |
yden | -0.471 |
IDES | -0.471 |
wana | -0.466 |
Token | Jamaica |
Token ID | 31620 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
redes | +0.120 |
Shank | +0.118 |
Sew | +0.110 |
purge | +0.108 |
comprom | +0.106 |
Neg logit contributions | |
enburg | -0.115 |
assic | -0.112 |
IDES | -0.100 |
yden | -0.100 |
wana | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
enburg | +0.359 |
assic | +0.347 |
IDES | +0.310 |
yden | +0.308 |
wana | +0.305 |
Neg logit contributions | |
redes | -0.428 |
Shank | -0.421 |
Sew | -0.392 |
purge | -0.389 |
comprom | -0.382 |
Token | Credit |
Token ID | 10504 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
enburg | +0.054 |
assic | +0.052 |
IDES | +0.048 |
yden | +0.048 |
wana | +0.047 |
Neg logit contributions | |
redes | -0.043 |
Shank | -0.042 |
purge | -0.039 |
Sew | -0.038 |
comprom | -0.038 |
Token | : |
Token ID | 25 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Shank | +2.823 |
Sew | +2.653 |
redes | +2.545 |
Sho | +2.524 |
purge | +2.465 |
Neg logit contributions | |
assic | -2.821 |
enburg | -2.792 |
yden | -2.498 |
wana | -2.449 |
IDES | -2.435 |
Token | AP |
Token ID | 2969 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
enburg | +0.313 |
assic | +0.304 |
IDES | +0.270 |
yden | +0.268 |
wana | +0.265 |
Neg logit contributions | |
redes | -0.409 |
Shank | -0.403 |
Sew | -0.377 |
purge | -0.373 |
comprom | -0.366 |
Token | Cuban |
Token ID | 18147 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
enburg | +1.029 |
assic | +0.990 |
IDES | +0.912 |
yden | +0.900 |
wana | +0.893 |
Neg logit contributions | |
redes | -0.920 |
Shank | -0.885 |
purge | -0.823 |
comprom | -0.808 |
Sew | -0.806 |
Token | authorities |
Token ID | 4773 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
enburg | +0.565 |
assic | +0.548 |
IDES | +0.492 |
yden | +0.489 |
wana | +0.487 |
Neg logit contributions | |
redes | -0.574 |
Shank | -0.565 |
Sew | -0.520 |
purge | -0.515 |
comprom | -0.506 |
Token | organised |
Token ID | 20325 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
enburg | +0.511 |
assic | +0.498 |
yden | +0.451 |
IDES | +0.450 |
wana | +0.450 |
Neg logit contributions | |
redes | -0.438 |
Shank | -0.433 |
Sew | -0.397 |
purge | -0.385 |
comprom | -0.383 |
Token | the |
Token ID | 262 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
redes | +0.115 |
Shank | +0.114 |
Sew | +0.107 |
purge | +0.105 |
comprom | +0.103 |
Neg logit contributions | |
enburg | -0.092 |
assic | -0.089 |
IDES | -0.079 |
yden | -0.079 |
wana | -0.078 |
Token | 19 |
Token ID | 678 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
redes | +0.043 |
Shank | +0.043 |
Sew | +0.040 |
purge | +0.039 |
comprom | +0.038 |
Neg logit contributions | |
enburg | -0.043 |
assic | -0.042 |
yden | -0.038 |
IDES | -0.038 |
wana | -0.038 |
Token | th |
Token ID | 400 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
redes | +0.368 |
Shank | +0.365 |
Sew | +0.336 |
purge | +0.329 |
comprom | +0.320 |
Neg logit contributions | |
enburg | -0.453 |
assic | -0.444 |
yden | -0.403 |
IDES | -0.402 |
wana | -0.399 |
Token | partition |
Token ID | 18398 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
redes | +0.244 |
Shank | +0.239 |
Sew | +0.221 |
purge | +0.216 |
comprom | +0.212 |
Neg logit contributions | |
enburg | -0.274 |
assic | -0.267 |
yden | -0.242 |
IDES | -0.242 |
wana | -0.239 |
Token | (/ |
Token ID | 50247 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
enburg | +0.599 |
assic | +0.581 |
IDES | +0.522 |
yden | +0.521 |
wana | +0.515 |
Neg logit contributions | |
redes | -0.645 |
Shank | -0.635 |
Sew | -0.591 |
purge | -0.580 |
comprom | -0.570 |
Token | dev |
Token ID | 7959 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
redes | +0.699 |
Shank | +0.688 |
Sew | +0.627 |
purge | +0.612 |
comprom | +0.599 |
Neg logit contributions | |
enburg | -0.964 |
assic | -0.942 |
yden | -0.862 |
IDES | -0.862 |
wana | -0.851 |
Token | / |
Token ID | 14 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
Shank | +3.326 |
Sew | +3.160 |
redes | +3.089 |
Sho | +3.050 |
purge | +3.037 |
Neg logit contributions | |
enburg | -2.227 |
assic | -2.201 |
yden | -1.888 |
IDES | -1.868 |
wana | -1.861 |
Token | block |
Token ID | 9967 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
redes | +0.773 |
Shank | +0.763 |
Sew | +0.711 |
purge | +0.696 |
comprom | +0.685 |
Neg logit contributions | |
enburg | -0.737 |
assic | -0.717 |
yden | -0.644 |
IDES | -0.641 |
wana | -0.633 |
Token | / |
Token ID | 14 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
redes | +0.163 |
Shank | +0.161 |
Sew | +0.151 |
purge | +0.148 |
comprom | +0.145 |
Neg logit contributions | |
enburg | -0.126 |
assic | -0.123 |
yden | -0.109 |
IDES | -0.109 |
wana | -0.107 |
Token | mm |
Token ID | 3020 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
redes | +0.575 |
Shank | +0.566 |
Sew | +0.525 |
purge | +0.516 |
comprom | +0.506 |
Neg logit contributions | |
enburg | -0.574 |
assic | -0.558 |
yden | -0.504 |
IDES | -0.502 |
wana | -0.497 |
Token | c |
Token ID | 66 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
redes | +0.287 |
Shank | +0.283 |
Sew | +0.265 |
purge | +0.260 |
comprom | +0.255 |
Neg logit contributions | |
enburg | -0.223 |
assic | -0.218 |
yden | -0.192 |
IDES | -0.191 |
wana | -0.188 |
Token | unexplained |
Token ID | 43286 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
redes | +0.140 |
Shank | +0.138 |
Sew | +0.129 |
purge | +0.126 |
comprom | +0.124 |
Neg logit contributions | |
enburg | -0.133 |
assic | -0.130 |
yden | -0.116 |
IDES | -0.116 |
wana | -0.115 |
Token | temperature |
Token ID | 5951 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
redes | +0.643 |
Shank | +0.634 |
Sew | +0.588 |
purge | +0.576 |
comprom | +0.564 |
Neg logit contributions | |
enburg | -0.676 |
assic | -0.660 |
yden | -0.594 |
IDES | -0.594 |
wana | -0.587 |
Token | dependence |
Token ID | 21403 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
enburg | +0.168 |
assic | +0.164 |
yden | +0.149 |
IDES | +0.149 |
wana | +0.148 |
Neg logit contributions | |
redes | -0.129 |
Shank | -0.128 |
Sew | -0.117 |
purge | -0.114 |
comprom | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
redes | +0.450 |
Shank | +0.445 |
Sew | +0.415 |
purge | +0.407 |
comprom | +0.399 |
Neg logit contributions | |
enburg | -0.422 |
assic | -0.412 |
yden | -0.369 |
IDES | -0.368 |
wana | -0.364 |
Token | Sach |
Token ID | 20678 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
redes | +0.196 |
Shank | +0.193 |
Sew | +0.178 |
purge | +0.175 |
comprom | +0.171 |
Neg logit contributions | |
enburg | -0.222 |
assic | -0.217 |
IDES | -0.196 |
yden | -0.196 |
wana | -0.194 |
Token | dev |
Token ID | 7959 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
enburg | +0.377 |
assic | +0.367 |
yden | +0.325 |
IDES | +0.324 |
wana | +0.323 |
Neg logit contributions | |
redes | -0.478 |
Shank | -0.471 |
Sew | -0.441 |
purge | -0.435 |
comprom | -0.428 |
Token | had |
Token ID | 550 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
Shank | +2.894 |
redes | +2.870 |
Sew | +2.690 |
purge | +2.615 |
Sho | +2.568 |
Neg logit contributions | |
enburg | -2.578 |
assic | -2.541 |
IDES | -2.257 |
yden | -2.244 |
wana | -2.204 |
Token | a |
Token ID | 257 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
enburg | +0.009 |
assic | +0.009 |
yden | +0.008 |
IDES | +0.008 |
wana | +0.008 |
Neg logit contributions | |
redes | -0.008 |
Shank | -0.008 |
Sew | -0.008 |
purge | -0.007 |
comprom | -0.007 |
Token | theory |
Token ID | 4583 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
redes | +0.043 |
Shank | +0.042 |
Sew | +0.039 |
purge | +0.038 |
comprom | +0.038 |
Neg logit contributions | |
enburg | -0.042 |
assic | -0.040 |
yden | -0.036 |
IDES | -0.036 |
wana | -0.036 |
Token | but |
Token ID | 475 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
redes | +0.649 |
Shank | +0.644 |
Sew | +0.600 |
purge | +0.589 |
comprom | +0.578 |
Neg logit contributions | |
enburg | -0.583 |
assic | -0.569 |
yden | -0.508 |
IDES | -0.507 |
wana | -0.501 |
Token | needed |
Token ID | 2622 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
redes | +0.309 |
Shank | +0.308 |
Sew | +0.287 |
purge | +0.281 |
comprom | +0.275 |
Neg logit contributions | |
enburg | -0.280 |
assic | -0.275 |
yden | -0.245 |
IDES | -0.245 |
wana | -0.242 |
Token | u |
Token ID | 334 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
redes | +0.239 |
Shank | +0.235 |
Sew | +0.221 |
purge | +0.216 |
comprom | +0.213 |
Neg logit contributions | |
enburg | -0.187 |
assic | -0.182 |
yden | -0.161 |
IDES | -0.161 |
wana | -0.159 |
Token | Part |
Token ID | 7841 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
redes | +1.310 |
Shank | +1.289 |
Sew | +1.213 |
purge | +1.196 |
comprom | +1.174 |
Neg logit contributions | |
enburg | -0.915 |
assic | -0.893 |
IDES | -0.782 |
yden | -0.780 |
wana | -0.766 |
Token | icle |
Token ID | 1548 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
Shank | +0.054 |
redes | +0.053 |
Sew | +0.049 |
purge | +0.048 |
Sho | +0.047 |
Neg logit contributions | |
enburg | -0.073 |
assic | -0.072 |
IDES | -0.065 |
yden | -0.065 |
wana | -0.065 |
Token | ] |
Token ID | 2361 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
enburg | +0.063 |
assic | +0.061 |
IDES | +0.056 |
yden | +0.056 |
wana | +0.055 |
Neg logit contributions | |
redes | -0.056 |
Shank | -0.054 |
Sew | -0.050 |
purge | -0.049 |
comprom | -0.048 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
redes | +0.614 |
Shank | +0.602 |
Sew | +0.553 |
purge | +0.539 |
comprom | +0.530 |
Neg logit contributions | |
enburg | -0.752 |
assic | -0.738 |
yden | -0.674 |
IDES | -0.673 |
wana | -0.657 |
Token | const |
Token ID | 1500 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
redes | +1.100 |
Shank | +1.089 |
Sew | +1.017 |
purge | +0.999 |
comprom | +0.980 |
Neg logit contributions | |
enburg | -0.944 |
assic | -0.919 |
yden | -0.818 |
IDES | -0.817 |
wana | -0.808 |
Token | Vec |
Token ID | 38692 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Shank | +2.547 |
redes | +2.530 |
Sew | +2.347 |
purge | +2.295 |
Sho | +2.244 |
Neg logit contributions | |
enburg | -2.948 |
assic | -2.902 |
yden | -2.614 |
IDES | -2.600 |
wana | -2.584 |
Token | 3 |
Token ID | 18 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
redes | +1.814 |
Shank | +1.808 |
Sew | +1.686 |
purge | +1.652 |
comprom | +1.621 |
Neg logit contributions | |
enburg | -1.606 |
assic | -1.565 |
yden | -1.389 |
IDES | -1.382 |
wana | -1.372 |
Token | & |
Token ID | 1222 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
enburg | +0.015 |
assic | +0.015 |
yden | +0.013 |
IDES | +0.013 |
wana | +0.013 |
Neg logit contributions | |
redes | -0.017 |
Shank | -0.017 |
Sew | -0.016 |
purge | -0.016 |
comprom | -0.015 |
Token | r |
Token ID | 374 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
redes | +1.243 |
Shank | +1.232 |
Sew | +1.146 |
purge | +1.129 |
comprom | +1.104 |
Neg logit contributions | |
enburg | -1.188 |
assic | -1.158 |
IDES | -1.036 |
yden | -1.035 |
wana | -1.025 |
Token | Position |
Token ID | 26545 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
redes | +0.208 |
Shank | +0.205 |
Sew | +0.193 |
purge | +0.190 |
comprom | +0.186 |
Neg logit contributions | |
enburg | -0.158 |
assic | -0.154 |
yden | -0.136 |
IDES | -0.136 |
wana | -0.134 |
Token | float |
Token ID | 12178 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
redes | +0.359 |
Shank | +0.356 |
Sew | +0.331 |
purge | +0.325 |
comprom | +0.318 |
Neg logit contributions | |
enburg | -0.337 |
assic | -0.329 |
yden | -0.294 |
IDES | -0.293 |
wana | -0.290 |
Token | ambient |
Token ID | 25237 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
redes | +0.860 |
Shank | +0.854 |
Sew | +0.787 |
purge | +0.773 |
comprom | +0.755 |
Neg logit contributions | |
enburg | -0.987 |
assic | -0.966 |
yden | -0.874 |
IDES | -0.870 |
wana | -0.863 |
Token | D |
Token ID | 35 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
redes | +0.403 |
Shank | +0.400 |
Sew | +0.373 |
purge | +0.367 |
comprom | +0.359 |
Neg logit contributions | |
enburg | -0.345 |
assic | -0.337 |
yden | -0.299 |
IDES | -0.298 |
wana | -0.296 |
Token | ensity |
Token ID | 6377 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
redes | +0.219 |
Shank | +0.217 |
Sew | +0.202 |
purge | +0.198 |
comprom | +0.193 |
Neg logit contributions | |
enburg | -0.223 |
assic | -0.219 |
IDES | -0.196 |
yden | -0.196 |
wana | -0.194 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
enburg | +0.344 |
assic | +0.336 |
yden | +0.298 |
IDES | +0.297 |
wana | +0.294 |
Neg logit contributions | |
redes | -0.415 |
Shank | -0.411 |
Sew | -0.385 |
purge | -0.378 |
comprom | -0.371 |
Token | const |
Token ID | 1500 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
redes | +0.269 |
Shank | +0.267 |
Sew | +0.244 |
purge | +0.239 |
Sho | +0.231 |
Neg logit contributions | |
enburg | -0.386 |
assic | -0.380 |
yden | -0.346 |
IDES | -0.344 |
wana | -0.342 |
Token | { |
Token ID | 1391 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Shank | +2.057 |
redes | +2.051 |
Sew | +1.853 |
purge | +1.803 |
Sho | +1.761 |
Neg logit contributions | |
enburg | -3.365 |
assic | -3.346 |
yden | -3.040 |
wana | -2.994 |
IDES | -2.969 |
Token | const |
Token ID | 1500 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
redes | +0.927 |
Shank | +0.920 |
Sew | +0.848 |
purge | +0.833 |
comprom | +0.809 |
Neg logit contributions | |
enburg | -1.086 |
assic | -1.066 |
yden | -0.962 |
IDES | -0.961 |
wana | -0.953 |
Token | float |
Token ID | 12178 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
redes | +2.398 |
Shank | +2.395 |
Sew | +2.201 |
purge | +2.167 |
Sho | +2.109 |
Neg logit contributions | |
enburg | -2.794 |
assic | -2.750 |
yden | -2.484 |
IDES | -2.464 |
wana | -2.454 |
Token | f |
Token ID | 277 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
redes | +1.259 |
Shank | +1.249 |
Sew | +1.150 |
purge | +1.131 |
comprom | +1.105 |
Neg logit contributions | |
enburg | -1.471 |
assic | -1.441 |
yden | -1.303 |
IDES | -1.299 |
wana | -1.289 |
Token | Mass |
Token ID | 20273 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
redes | +0.658 |
Shank | +0.652 |
Sew | +0.608 |
purge | +0.598 |
comprom | +0.586 |
Neg logit contributions | |
enburg | -0.569 |
assic | -0.555 |
yden | -0.494 |
IDES | -0.493 |
wana | -0.487 |
Token | generated |
Token ID | 7560 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
redes | +0.005 |
Shank | +0.005 |
Sew | +0.004 |
purge | +0.004 |
comprom | +0.004 |
Neg logit contributions | |
enburg | -0.005 |
assic | -0.004 |
yden | -0.004 |
IDES | -0.004 |
wana | -0.004 |
Token | by |
Token ID | 416 |
Feature activation | +4.99e-03 |
Pos logit contributions | |
enburg | +0.401 |
assic | +0.392 |
IDES | +0.355 |
yden | +0.354 |
wana | +0.352 |
Neg logit contributions | |
redes | -0.342 |
Shank | -0.337 |
Sew | -0.311 |
purge | -0.305 |
comprom | -0.298 |
Token | Hurricane |
Token ID | 16004 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
enburg | +0.004 |
assic | +0.004 |
IDES | +0.004 |
yden | +0.004 |
wana | +0.004 |
Neg logit contributions | |
redes | -0.004 |
Shank | -0.003 |
Sew | -0.003 |
purge | -0.003 |
comprom | -0.003 |
Token | Matthew |
Token ID | 9308 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
redes | +0.405 |
Shank | +0.399 |
Sew | +0.367 |
purge | +0.363 |
comprom | +0.356 |
Neg logit contributions | |
enburg | -0.451 |
assic | -0.438 |
IDES | -0.397 |
yden | -0.396 |
wana | -0.393 |
Token | . |
Token ID | 13 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
enburg | +0.288 |
assic | +0.280 |
IDES | +0.251 |
yden | +0.250 |
wana | +0.248 |
Neg logit contributions | |
redes | -0.313 |
Shank | -0.309 |
Sew | -0.287 |
purge | -0.283 |
comprom | -0.278 |
Token | Credit |
Token ID | 10504 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
redes | +0.041 |
Shank | +0.040 |
Sew | +0.036 |
purge | +0.036 |
comprom | +0.035 |
Neg logit contributions | |
enburg | -0.058 |
assic | -0.057 |
IDES | -0.052 |
yden | -0.052 |
wana | -0.052 |
Token | : |
Token ID | 25 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
Shank | +2.743 |
redes | +2.581 |
Sew | +2.569 |
Sho | +2.457 |
purge | +2.424 |
Neg logit contributions | |
assic | -2.610 |
enburg | -2.603 |
yden | -2.312 |
IDES | -2.273 |
wana | -2.255 |
Token | NO |
Token ID | 15285 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
enburg | +0.385 |
assic | +0.374 |
IDES | +0.336 |
yden | +0.332 |
wana | +0.330 |
Neg logit contributions | |
redes | -0.441 |
Shank | -0.435 |
Sew | -0.405 |
purge | -0.401 |
comprom | -0.392 |
Token | AA |
Token ID | 3838 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
enburg | +0.186 |
assic | +0.181 |
IDES | +0.164 |
yden | +0.163 |
wana | +0.162 |
Neg logit contributions | |
redes | -0.181 |
Shank | -0.179 |
Sew | -0.165 |
purge | -0.163 |
comprom | -0.159 |
Token | Around |
Token ID | 16824 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
redes | +0.034 |
Shank | +0.033 |
Sew | +0.031 |
purge | +0.030 |
comprom | +0.030 |
Neg logit contributions | |
enburg | -0.038 |
assic | -0.037 |
IDES | -0.033 |
yden | -0.033 |
wana | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
enburg | +0.203 |
assic | +0.197 |
IDES | +0.178 |
yden | +0.178 |
wana | +0.176 |
Neg logit contributions | |
redes | -0.204 |
Shank | -0.200 |
Sew | -0.185 |
purge | -0.183 |
comprom | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
enburg | +0.145 |
assic | +0.141 |
yden | +0.126 |
IDES | +0.126 |
wana | +0.124 |
Neg logit contributions | |
redes | -0.164 |
Shank | -0.162 |
Sew | -0.151 |
purge | -0.149 |
comprom | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
enburg | +0.324 |
assic | +0.322 |
yden | +0.286 |
IDES | +0.283 |
wana | +0.281 |
Neg logit contributions | |
Shank | -0.341 |
redes | -0.330 |
Sew | -0.321 |
purge | -0.309 |
Sho | -0.306 |
Token | Full |
Token ID | 13295 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
enburg | +0.258 |
assic | +0.255 |
yden | +0.227 |
IDES | +0.224 |
wana | +0.222 |
Neg logit contributions | |
Shank | -0.294 |
redes | -0.293 |
Sew | -0.278 |
purge | -0.272 |
comprom | -0.266 |
Token | Faith |
Token ID | 16463 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
enburg | +0.657 |
assic | +0.642 |
yden | +0.573 |
IDES | +0.572 |
wana | +0.566 |
Neg logit contributions | |
redes | -0.714 |
Shank | -0.708 |
Sew | -0.660 |
purge | -0.649 |
comprom | -0.634 |
Token | and |
Token ID | 290 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
enburg | +0.564 |
assic | +0.547 |
yden | +0.489 |
IDES | +0.487 |
wana | +0.481 |
Neg logit contributions | |
redes | -0.670 |
Shank | -0.663 |
Sew | -0.619 |
purge | -0.610 |
comprom | -0.596 |
Token | Credit |
Token ID | 10504 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
redes | +0.030 |
Shank | +0.030 |
Sew | +0.027 |
purge | +0.026 |
comprom | +0.025 |
Neg logit contributions | |
enburg | -0.055 |
assic | -0.054 |
yden | -0.049 |
IDES | -0.049 |
wana | -0.049 |
Token | shall |
Token ID | 2236 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
redes | +2.443 |
Shank | +2.417 |
Sew | +2.231 |
purge | +2.185 |
comprom | +2.131 |
Neg logit contributions | |
enburg | -2.889 |
assic | -2.829 |
yden | -2.562 |
IDES | -2.558 |
wana | -2.534 |
Token | be |
Token ID | 307 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
redes | +0.390 |
Shank | +0.387 |
Sew | +0.358 |
purge | +0.352 |
comprom | +0.349 |
Neg logit contributions | |
enburg | -0.353 |
assic | -0.339 |
yden | -0.306 |
IDES | -0.305 |
wana | -0.304 |
Token | given |
Token ID | 1813 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
enburg | +0.062 |
assic | +0.060 |
IDES | +0.053 |
yden | +0.053 |
wana | +0.052 |
Neg logit contributions | |
redes | -0.076 |
Shank | -0.075 |
Sew | -0.071 |
purge | -0.069 |
comprom | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
enburg | +1.050 |
assic | +1.018 |
yden | +0.925 |
IDES | +0.921 |
wana | +0.915 |
Neg logit contributions | |
redes | -1.007 |
Shank | -0.993 |
Sew | -0.914 |
purge | -0.904 |
comprom | -0.886 |
Token | each |
Token ID | 1123 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
enburg | +0.014 |
assic | +0.014 |
IDES | +0.013 |
yden | +0.013 |
wana | +0.013 |
Neg logit contributions | |
redes | -0.014 |
Shank | -0.014 |
Sew | -0.013 |
purge | -0.012 |
comprom | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
enburg | +0.561 |
assic | +0.546 |
IDES | +0.490 |
yden | +0.488 |
wana | +0.484 |
Neg logit contributions | |
redes | -0.628 |
Shank | -0.620 |
Sew | -0.577 |
purge | -0.566 |
comprom | -0.554 |
Token | grid |
Token ID | 10706 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
enburg | +0.022 |
assic | +0.021 |
IDES | +0.019 |
yden | +0.019 |
wana | +0.019 |
Neg logit contributions | |
redes | -0.023 |
Shank | -0.022 |
Sew | -0.021 |
purge | -0.020 |
comprom | -0.020 |
Token | cell |
Token ID | 3846 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
enburg | +0.160 |
assic | +0.156 |
yden | +0.141 |
IDES | +0.141 |
wana | +0.140 |
Neg logit contributions | |
redes | -0.136 |
Shank | -0.134 |
Sew | -0.123 |
purge | -0.120 |
comprom | -0.118 |
Token | volume |
Token ID | 6115 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
redes | +0.714 |
Shank | +0.703 |
Sew | +0.653 |
purge | +0.639 |
comprom | +0.626 |
Neg logit contributions | |
enburg | -0.697 |
assic | -0.679 |
IDES | -0.610 |
yden | -0.610 |
wana | -0.604 |
Token | . |
Token ID | 13 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
enburg | +0.460 |
assic | +0.447 |
IDES | +0.405 |
yden | +0.403 |
wana | +0.399 |
Neg logit contributions | |
redes | -0.487 |
Shank | -0.479 |
Sew | -0.444 |
purge | -0.435 |
comprom | -0.425 |
Token | const |
Token ID | 1500 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
redes | +0.314 |
Shank | +0.309 |
Sew | +0.286 |
purge | +0.280 |
comprom | +0.275 |
Neg logit contributions | |
enburg | -0.343 |
assic | -0.334 |
yden | -0.302 |
IDES | -0.302 |
wana | -0.300 |
Token | float |
Token ID | 12178 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Shank | +2.424 |
redes | +2.421 |
Sew | +2.234 |
purge | +2.190 |
comprom | +2.126 |
Neg logit contributions | |
enburg | -2.856 |
assic | -2.819 |
yden | -2.543 |
IDES | -2.532 |
wana | -2.510 |
Token | one |
Token ID | 530 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
redes | +1.264 |
Shank | +1.253 |
Sew | +1.161 |
purge | +1.140 |
comprom | +1.115 |
Neg logit contributions | |
enburg | -1.331 |
assic | -1.303 |
yden | -1.172 |
IDES | -1.169 |
wana | -1.158 |
Token | Over |
Token ID | 5886 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
redes | +0.475 |
Shank | +0.470 |
Sew | +0.438 |
purge | +0.431 |
comprom | +0.423 |
Neg logit contributions | |
enburg | -0.404 |
assic | -0.394 |
yden | -0.350 |
IDES | -0.350 |
wana | -0.345 |
Token | Cell |
Token ID | 28780 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
enburg | +0.668 |
assic | +0.650 |
yden | +0.592 |
IDES | +0.592 |
wana | +0.586 |
Neg logit contributions | |
redes | -0.566 |
Shank | -0.556 |
Sew | -0.512 |
purge | -0.502 |
comprom | -0.491 |
Token | Volume |
Token ID | 31715 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
redes | +0.173 |
Shank | +0.170 |
Sew | +0.158 |
purge | +0.156 |
comprom | +0.153 |
Neg logit contributions | |
enburg | -0.152 |
assic | -0.148 |
IDES | -0.132 |
yden | -0.132 |
wana | -0.131 |
Token | Center |
Token ID | 3337 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
enburg | +0.641 |
assic | +0.626 |
wana | +0.560 |
yden | +0.559 |
IDES | +0.559 |
Neg logit contributions | |
redes | -0.617 |
Shank | -0.596 |
Sew | -0.556 |
purge | -0.547 |
comprom | -0.534 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
redes | +0.582 |
Shank | +0.577 |
Sew | +0.537 |
purge | +0.528 |
comprom | +0.517 |
Neg logit contributions | |
enburg | -0.532 |
assic | -0.520 |
yden | -0.463 |
IDES | -0.463 |
wana | -0.458 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
redes | +0.023 |
Shank | +0.022 |
Sew | +0.021 |
purge | +0.021 |
comprom | +0.020 |
Neg logit contributions | |
enburg | -0.019 |
assic | -0.019 |
yden | -0.017 |
IDES | -0.017 |
wana | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
Shank | +0.101 |
redes | +0.097 |
Sew | +0.095 |
purge | +0.091 |
Sho | +0.090 |
Neg logit contributions | |
enburg | -0.096 |
assic | -0.095 |
yden | -0.084 |
IDES | -0.084 |
wana | -0.083 |
Token | M |
Token ID | 44 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Shank | +0.078 |
redes | +0.078 |
Sew | +0.073 |
purge | +0.071 |
comprom | +0.070 |
Neg logit contributions | |
enburg | -0.063 |
assic | -0.062 |
yden | -0.054 |
wana | -0.054 |
IDES | -0.054 |
Token | ood |
Token ID | 702 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
redes | +0.297 |
Shank | +0.293 |
Sew | +0.272 |
purge | +0.267 |
comprom | +0.261 |
Neg logit contributions | |
enburg | -0.306 |
assic | -0.299 |
yden | -0.270 |
IDES | -0.269 |
wana | -0.267 |
Token | y |
Token ID | 88 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
redes | +2.802 |
Shank | +2.783 |
Sew | +2.593 |
purge | +2.546 |
Sho | +2.502 |
Neg logit contributions | |
enburg | -2.417 |
assic | -2.377 |
yden | -2.106 |
IDES | -2.104 |
wana | -2.074 |
Token | � |
Token ID | 447 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
redes | +0.251 |
Shank | +0.247 |
Sew | +0.232 |
purge | +0.229 |
comprom | +0.226 |
Neg logit contributions | |
enburg | -0.178 |
assic | -0.173 |
IDES | -0.151 |
yden | -0.151 |
wana | -0.149 |
Token | � |
Token ID | 247 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
enburg | +0.013 |
assic | +0.012 |
yden | +0.011 |
IDES | +0.011 |
wana | +0.011 |
Neg logit contributions | |
redes | -0.019 |
Shank | -0.019 |
Sew | -0.018 |
purge | -0.018 |
comprom | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
enburg | +0.079 |
assic | +0.076 |
yden | +0.069 |
IDES | +0.068 |
wana | +0.067 |
Neg logit contributions | |
redes | -0.088 |
Shank | -0.087 |
Sew | -0.081 |
purge | -0.079 |
comprom | -0.078 |
Token | Investors |
Token ID | 38898 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
enburg | +0.120 |
assic | +0.117 |
IDES | +0.106 |
yden | +0.106 |
wana | +0.104 |
Neg logit contributions | |
redes | -0.111 |
Shank | -0.110 |
Sew | -0.102 |
purge | -0.100 |
comprom | -0.098 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Shank | +0.385 |
redes | +0.381 |
Sew | +0.356 |
purge | +0.348 |
Sho | +0.336 |
Neg logit contributions | |
enburg | -0.476 |
assic | -0.468 |
yden | -0.426 |
IDES | -0.424 |
wana | -0.421 |
Token | { |
Token ID | 1391 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Shank | +0.809 |
redes | +0.795 |
Sew | +0.726 |
purge | +0.695 |
Sho | +0.669 |
Neg logit contributions | |
enburg | -1.691 |
assic | -1.674 |
yden | -1.541 |
IDES | -1.539 |
wana | -1.532 |
Token | // |
Token ID | 3373 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
redes | +1.714 |
Shank | +1.709 |
Sew | +1.616 |
purge | +1.598 |
Sho | +1.564 |
Neg logit contributions | |
enburg | -0.983 |
assic | -0.957 |
yden | -0.819 |
IDES | -0.817 |
wana | -0.808 |
Token | Time |
Token ID | 3862 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
enburg | +0.416 |
assic | +0.402 |
yden | +0.364 |
IDES | +0.362 |
wana | +0.360 |
Neg logit contributions | |
redes | -0.396 |
Shank | -0.385 |
Sew | -0.355 |
purge | -0.351 |
comprom | -0.346 |
Token | component |
Token ID | 7515 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Shank | +0.390 |
redes | +0.389 |
Sew | +0.365 |
purge | +0.361 |
comprom | +0.354 |
Neg logit contributions | |
enburg | -0.290 |
assic | -0.282 |
IDES | -0.248 |
yden | -0.247 |
wana | -0.247 |
Token | const |
Token ID | 1500 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Shank | +0.169 |
redes | +0.168 |
Sew | +0.160 |
purge | +0.157 |
comprom | +0.154 |
Neg logit contributions | |
enburg | -0.111 |
assic | -0.109 |
IDES | -0.095 |
yden | -0.095 |
wana | -0.093 |
Token | float |
Token ID | 12178 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Shank | +1.980 |
redes | +1.841 |
Sew | +1.800 |
purge | +1.768 |
Sho | +1.730 |
Neg logit contributions | |
enburg | -3.301 |
assic | -3.259 |
yden | -2.965 |
wana | -2.958 |
IDES | -2.944 |
Token | TA |
Token ID | 21664 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
Shank | +1.116 |
redes | +1.109 |
Sew | +1.043 |
purge | +1.013 |
Sho | +1.003 |
Neg logit contributions | |
enburg | -1.281 |
assic | -1.259 |
yden | -1.125 |
IDES | -1.124 |
wana | -1.118 |
Token | U |
Token ID | 52 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Shank | +0.097 |
redes | +0.095 |
Sew | +0.092 |
purge | +0.090 |
Sho | +0.089 |
Neg logit contributions | |
enburg | -0.048 |
assic | -0.047 |
yden | -0.039 |
wana | -0.039 |
IDES | -0.039 |
Token | = |
Token ID | 796 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
enburg | +0.791 |
assic | +0.772 |
yden | +0.693 |
IDES | +0.693 |
wana | +0.685 |
Neg logit contributions | |
redes | -0.787 |
Shank | -0.779 |
Sew | -0.723 |
purge | -0.710 |
comprom | -0.695 |
Token | 6 |
Token ID | 718 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
redes | +0.289 |
Shank | +0.284 |
Sew | +0.259 |
purge | +0.252 |
comprom | +0.250 |
Neg logit contributions | |
enburg | -0.373 |
assic | -0.366 |
IDES | -0.334 |
yden | -0.332 |
wana | -0.329 |
Token | D |
Token ID | 35 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
redes | +0.403 |
Shank | +0.400 |
Sew | +0.373 |
purge | +0.367 |
comprom | +0.359 |
Neg logit contributions | |
enburg | -0.345 |
assic | -0.337 |
yden | -0.299 |
IDES | -0.298 |
wana | -0.296 |
Token | ensity |
Token ID | 6377 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
redes | +0.219 |
Shank | +0.217 |
Sew | +0.202 |
purge | +0.198 |
comprom | +0.193 |
Neg logit contributions | |
enburg | -0.223 |
assic | -0.219 |
IDES | -0.196 |
yden | -0.196 |
wana | -0.194 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
enburg | +0.344 |
assic | +0.336 |
yden | +0.298 |
IDES | +0.297 |
wana | +0.294 |
Neg logit contributions | |
redes | -0.415 |
Shank | -0.411 |
Sew | -0.385 |
purge | -0.378 |
comprom | -0.371 |
Token | const |
Token ID | 1500 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
redes | +0.269 |
Shank | +0.267 |
Sew | +0.244 |
purge | +0.239 |
Sho | +0.231 |
Neg logit contributions | |
enburg | -0.386 |
assic | -0.380 |
yden | -0.346 |
IDES | -0.344 |
wana | -0.342 |
Token | { |
Token ID | 1391 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Shank | +2.057 |
redes | +2.051 |
Sew | +1.853 |
purge | +1.803 |
Sho | +1.761 |
Neg logit contributions | |
enburg | -3.365 |
assic | -3.346 |
yden | -3.040 |
wana | -2.994 |
IDES | -2.969 |
Token | const |
Token ID | 1500 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
redes | +0.927 |
Shank | +0.920 |
Sew | +0.848 |
purge | +0.833 |
comprom | +0.809 |
Neg logit contributions | |
enburg | -1.086 |
assic | -1.066 |
yden | -0.962 |
IDES | -0.961 |
wana | -0.953 |
Token | float |
Token ID | 12178 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
redes | +2.398 |
Shank | +2.395 |
Sew | +2.201 |
purge | +2.167 |
Sho | +2.109 |
Neg logit contributions | |
enburg | -2.794 |
assic | -2.750 |
yden | -2.484 |
IDES | -2.464 |
wana | -2.454 |
Token | f |
Token ID | 277 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
redes | +1.259 |
Shank | +1.249 |
Sew | +1.150 |
purge | +1.131 |
comprom | +1.105 |
Neg logit contributions | |
enburg | -1.471 |
assic | -1.441 |
yden | -1.303 |
IDES | -1.299 |
wana | -1.289 |
Token | Mass |
Token ID | 20273 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
redes | +0.658 |
Shank | +0.652 |
Sew | +0.608 |
purge | +0.598 |
comprom | +0.586 |
Neg logit contributions | |
enburg | -0.569 |
assic | -0.555 |
yden | -0.494 |
IDES | -0.493 |
wana | -0.487 |
Token | = |
Token ID | 796 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
redes | +0.420 |
Shank | +0.416 |
Sew | +0.386 |
purge | +0.379 |
comprom | +0.371 |
Neg logit contributions | |
enburg | -0.413 |
assic | -0.403 |
yden | -0.361 |
IDES | -0.361 |
wana | -0.357 |
Token | ( |
Token ID | 357 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
redes | +0.450 |
Shank | +0.444 |
Sew | +0.410 |
purge | +0.401 |
comprom | +0.393 |
Neg logit contributions | |
enburg | -0.517 |
assic | -0.505 |
yden | -0.457 |
IDES | -0.457 |
wana | -0.452 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
enburg | +0.039 |
assic | +0.038 |
yden | +0.034 |
IDES | +0.034 |
wana | +0.034 |
Neg logit contributions | |
redes | -0.041 |
Shank | -0.041 |
Sew | -0.038 |
purge | -0.037 |
comprom | -0.036 |
Token | wind |
Token ID | 2344 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
redes | +0.101 |
Shank | +0.100 |
Sew | +0.093 |
purge | +0.092 |
comprom | +0.090 |
Neg logit contributions | |
enburg | -0.096 |
assic | -0.094 |
yden | -0.084 |
IDES | -0.084 |
wana | -0.083 |
Token | power |
Token ID | 1176 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
enburg | +0.070 |
assic | +0.069 |
yden | +0.062 |
IDES | +0.062 |
wana | +0.061 |
Neg logit contributions | |
redes | -0.069 |
Shank | -0.068 |
Sew | -0.064 |
purge | -0.062 |
comprom | -0.061 |
Token | production |
Token ID | 3227 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
enburg | +0.317 |
assic | +0.310 |
yden | +0.282 |
IDES | +0.282 |
wana | +0.279 |
Neg logit contributions | |
redes | -0.250 |
Shank | -0.247 |
Sew | -0.227 |
purge | -0.222 |
comprom | -0.217 |
Token | tax |
Token ID | 1687 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
enburg | +0.425 |
assic | +0.416 |
yden | +0.375 |
IDES | +0.375 |
wana | +0.371 |
Neg logit contributions | |
redes | -0.390 |
Shank | -0.387 |
Sew | -0.358 |
purge | -0.351 |
comprom | -0.343 |
Token | credit |
Token ID | 3884 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
enburg | +0.172 |
assic | +0.167 |
yden | +0.148 |
IDES | +0.148 |
wana | +0.147 |
Neg logit contributions | |
redes | -0.205 |
Shank | -0.203 |
Sew | -0.190 |
purge | -0.187 |
comprom | -0.183 |
Token | ), |
Token ID | 828 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Shank | +2.777 |
redes | +2.750 |
Sew | +2.597 |
purge | +2.565 |
comprom | +2.493 |
Neg logit contributions | |
enburg | -2.275 |
assic | -2.230 |
IDES | -1.980 |
yden | -1.964 |
wana | -1.947 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
enburg | +0.184 |
assic | +0.179 |
yden | +0.160 |
IDES | +0.160 |
wana | +0.158 |
Neg logit contributions | |
redes | -0.195 |
Shank | -0.192 |
Sew | -0.179 |
purge | -0.176 |
comprom | -0.172 |
Token | compared |
Token ID | 3688 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
redes | +0.162 |
Shank | +0.161 |
Sew | +0.150 |
purge | +0.147 |
comprom | +0.144 |
Neg logit contributions | |
enburg | -0.156 |
assic | -0.152 |
yden | -0.136 |
IDES | -0.136 |
wana | -0.134 |
Token | them |
Token ID | 606 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
enburg | +0.439 |
assic | +0.426 |
yden | +0.378 |
IDES | +0.377 |
wana | +0.373 |
Neg logit contributions | |
redes | -0.544 |
Shank | -0.537 |
Sew | -0.502 |
purge | -0.494 |
comprom | -0.485 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
redes | +0.305 |
Shank | +0.302 |
Sew | +0.281 |
purge | +0.276 |
comprom | +0.271 |
Neg logit contributions | |
enburg | -0.290 |
assic | -0.284 |
yden | -0.254 |
IDES | -0.253 |
wana | -0.251 |
Token | particle |
Token ID | 18758 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
enburg | +0.674 |
assic | +0.655 |
yden | +0.592 |
IDES | +0.590 |
wana | +0.585 |
Neg logit contributions | |
redes | -0.631 |
Shank | -0.620 |
Sew | -0.576 |
purge | -0.560 |
comprom | -0.549 |
Token | in |
Token ID | 287 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
enburg | +0.260 |
assic | +0.254 |
yden | +0.226 |
IDES | +0.226 |
wana | +0.223 |
Neg logit contributions | |
redes | -0.294 |
Shank | -0.291 |
Sew | -0.271 |
purge | -0.266 |
comprom | -0.261 |
Token | the |
Token ID | 262 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
redes | +0.053 |
Shank | +0.052 |
Sew | +0.049 |
purge | +0.048 |
comprom | +0.047 |
Neg logit contributions | |
enburg | -0.050 |
assic | -0.048 |
IDES | -0.043 |
yden | -0.043 |
wana | -0.043 |
Token | array |
Token ID | 7177 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
redes | +0.189 |
Shank | +0.187 |
Sew | +0.170 |
purge | +0.166 |
comprom | +0.162 |
Neg logit contributions | |
enburg | -0.266 |
assic | -0.261 |
yden | -0.238 |
IDES | -0.238 |
wana | -0.236 |
Token | ... |
Token ID | 986 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
redes | +0.335 |
Shank | +0.332 |
Sew | +0.310 |
purge | +0.305 |
comprom | +0.299 |
Neg logit contributions | |
enburg | -0.278 |
assic | -0.271 |
yden | -0.240 |
IDES | -0.240 |
wana | -0.237 |
Token | const |
Token ID | 1500 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
enburg | +0.283 |
assic | +0.273 |
yden | +0.244 |
IDES | +0.244 |
wana | +0.242 |
Neg logit contributions | |
redes | -0.326 |
Shank | -0.321 |
Sew | -0.300 |
purge | -0.293 |
comprom | -0.288 |
Token | Part |
Token ID | 2142 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
redes | +2.427 |
Shank | +2.425 |
Sew | +2.244 |
purge | +2.214 |
comprom | +2.155 |
Neg logit contributions | |
enburg | -2.658 |
assic | -2.611 |
yden | -2.350 |
IDES | -2.340 |
wana | -2.319 |
Token | icle |
Token ID | 1548 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
enburg | +0.049 |
assic | +0.048 |
yden | +0.043 |
IDES | +0.043 |
wana | +0.043 |
Neg logit contributions | |
redes | -0.040 |
Shank | -0.040 |
Sew | -0.037 |
purge | -0.036 |
comprom | -0.035 |
Token | & |
Token ID | 1222 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
enburg | +0.223 |
assic | +0.218 |
IDES | +0.194 |
yden | +0.194 |
wana | +0.191 |
Neg logit contributions | |
redes | -0.252 |
Shank | -0.249 |
Sew | -0.232 |
purge | -0.228 |
comprom | -0.223 |
Token | r |
Token ID | 374 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
redes | +1.154 |
Shank | +1.143 |
Sew | +1.057 |
purge | +1.040 |
comprom | +1.016 |
Neg logit contributions | |
enburg | -1.252 |
assic | -1.222 |
IDES | -1.102 |
yden | -1.102 |
wana | -1.090 |
Token | Part |
Token ID | 7841 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
redes | +0.236 |
Shank | +0.233 |
Sew | +0.217 |
purge | +0.214 |
comprom | +0.210 |
Neg logit contributions | |
enburg | -0.204 |
assic | -0.199 |
yden | -0.177 |
IDES | -0.177 |
wana | -0.174 |
Token | Getty |
Token ID | 6633 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
redes | +0.009 |
Shank | +0.009 |
Sew | +0.009 |
purge | +0.008 |
comprom | +0.008 |
Neg logit contributions | |
enburg | -0.006 |
assic | -0.006 |
IDES | -0.005 |
yden | -0.005 |
wana | -0.005 |
Token | images |
Token ID | 4263 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
redes | +1.347 |
Shank | +1.340 |
Sew | +1.261 |
purge | +1.242 |
comprom | +1.216 |
Neg logit contributions | |
enburg | -0.862 |
assic | -0.838 |
yden | -0.726 |
IDES | -0.723 |
wana | -0.717 |
Token | ] |
Token ID | 60 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
enburg | +0.461 |
assic | +0.450 |
IDES | +0.409 |
yden | +0.408 |
wana | +0.403 |
Neg logit contributions | |
redes | -0.392 |
Shank | -0.386 |
Sew | -0.357 |
purge | -0.349 |
comprom | -0.343 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
enburg | +0.177 |
assic | +0.171 |
IDES | +0.155 |
yden | +0.154 |
wana | +0.150 |
Neg logit contributions | |
redes | -0.181 |
Shank | -0.177 |
Sew | -0.165 |
purge | -0.162 |
comprom | -0.160 |
Token | Pl |
Token ID | 3646 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
redes | +0.056 |
Shank | +0.056 |
Sew | +0.052 |
purge | +0.052 |
comprom | +0.051 |
Neg logit contributions | |
enburg | -0.043 |
assic | -0.042 |
yden | -0.037 |
IDES | -0.037 |
wana | -0.036 |
Token | enty |
Token ID | 3787 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
enburg | +0.550 |
assic | +0.539 |
yden | +0.476 |
IDES | +0.472 |
wana | +0.470 |
Neg logit contributions | |
redes | -0.653 |
Shank | -0.638 |
Sew | -0.596 |
purge | -0.587 |
comprom | -0.580 |
Token | of |
Token ID | 286 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
redes | +2.611 |
Shank | +2.587 |
Sew | +2.408 |
purge | +2.362 |
comprom | +2.307 |
Neg logit contributions | |
enburg | -2.489 |
assic | -2.426 |
yden | -2.175 |
IDES | -2.171 |
wana | -2.147 |
Token | new |
Token ID | 649 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
redes | +0.157 |
Shank | +0.155 |
Sew | +0.144 |
purge | +0.142 |
comprom | +0.139 |
Neg logit contributions | |
enburg | -0.143 |
assic | -0.139 |
yden | -0.125 |
IDES | -0.124 |
wana | -0.123 |
Token | airports |
Token ID | 22600 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
redes | +0.323 |
Shank | +0.320 |
Sew | +0.299 |
purge | +0.294 |
comprom | +0.289 |
Neg logit contributions | |
enburg | -0.269 |
assic | -0.262 |
yden | -0.232 |
IDES | -0.232 |
wana | -0.229 |
Token | but |
Token ID | 475 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
enburg | +0.345 |
assic | +0.337 |
yden | +0.304 |
IDES | +0.303 |
wana | +0.300 |
Neg logit contributions | |
redes | -0.330 |
Shank | -0.327 |
Sew | -0.303 |
purge | -0.297 |
comprom | -0.291 |
Token | few |
Token ID | 1178 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
redes | +0.064 |
Shank | +0.063 |
Sew | +0.059 |
purge | +0.058 |
comprom | +0.057 |
Neg logit contributions | |
enburg | -0.057 |
assic | -0.056 |
yden | -0.049 |
IDES | -0.049 |
wana | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
redes | +0.121 |
Shank | +0.120 |
Sew | +0.111 |
purge | +0.110 |
comprom | +0.109 |
Neg logit contributions | |
enburg | -0.101 |
assic | -0.097 |
IDES | -0.087 |
yden | -0.087 |
wana | -0.085 |
Token | 10 |
Token ID | 838 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
redes | +0.230 |
Shank | +0.225 |
Sew | +0.209 |
purge | +0.207 |
comprom | +0.204 |
Neg logit contributions | |
enburg | -0.224 |
assic | -0.218 |
yden | -0.196 |
IDES | -0.196 |
wana | -0.193 |
Token | Thompson |
Token ID | 11654 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
enburg | +0.271 |
assic | +0.263 |
yden | +0.236 |
IDES | +0.236 |
wana | +0.234 |
Neg logit contributions | |
redes | -0.289 |
Shank | -0.283 |
Sew | -0.264 |
purge | -0.261 |
comprom | -0.256 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
redes | +0.228 |
Shank | +0.224 |
Sew | +0.206 |
purge | +0.203 |
comprom | +0.198 |
Neg logit contributions | |
enburg | -0.276 |
assic | -0.269 |
yden | -0.245 |
IDES | -0.244 |
wana | -0.242 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Shank | +0.098 |
redes | +0.096 |
Sew | +0.092 |
purge | +0.089 |
Sho | +0.088 |
Neg logit contributions | |
enburg | -0.091 |
assic | -0.090 |
yden | -0.080 |
IDES | -0.080 |
wana | -0.079 |
Token | Credit |
Token ID | 23690 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
Shank | +0.094 |
redes | +0.094 |
Sew | +0.089 |
purge | +0.086 |
Sho | +0.085 |
Neg logit contributions | |
enburg | -0.073 |
assic | -0.072 |
yden | -0.063 |
IDES | -0.063 |
wana | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Shank | +2.652 |
redes | +2.636 |
Sew | +2.489 |
purge | +2.424 |
Sho | +2.388 |
Neg logit contributions | |
enburg | -2.421 |
assic | -2.383 |
IDES | -2.122 |
yden | -2.111 |
wana | -2.085 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
redes | +0.118 |
Shank | +0.117 |
Sew | +0.109 |
purge | +0.107 |
comprom | +0.105 |
Neg logit contributions | |
enburg | -0.105 |
assic | -0.102 |
yden | -0.091 |
IDES | -0.091 |
wana | -0.090 |
Token | National |
Token ID | 2351 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
redes | +0.083 |
Shank | +0.082 |
Sew | +0.076 |
purge | +0.075 |
comprom | +0.073 |
Neg logit contributions | |
enburg | -0.081 |
assic | -0.079 |
yden | -0.071 |
IDES | -0.071 |
wana | -0.070 |
Token | Post |
Token ID | 2947 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
redes | +0.819 |
Shank | +0.813 |
Sew | +0.752 |
purge | +0.734 |
comprom | +0.717 |
Neg logit contributions | |
enburg | -0.924 |
assic | -0.905 |
yden | -0.817 |
IDES | -0.817 |
wana | -0.809 |
Token | for |
Token ID | 329 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
redes | +0.700 |
Shank | +0.693 |
Sew | +0.643 |
purge | +0.631 |
comprom | +0.617 |
Neg logit contributions | |
enburg | -0.714 |
assic | -0.698 |
yden | -0.627 |
IDES | -0.626 |
wana | -0.620 |
Token | ( |
Token ID | 357 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
redes | +0.169 |
Shank | +0.168 |
Sew | +0.156 |
purge | +0.152 |
comprom | +0.149 |
Neg logit contributions | |
enburg | -0.177 |
assic | -0.173 |
yden | -0.155 |
IDES | -0.155 |
wana | -0.154 |
Token | Steve |
Token ID | 19206 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
enburg | +0.141 |
assic | +0.136 |
IDES | +0.119 |
yden | +0.119 |
wana | +0.118 |
Neg logit contributions | |
redes | -0.201 |
Shank | -0.199 |
Sew | -0.187 |
purge | -0.184 |
comprom | -0.181 |
Token | Hel |
Token ID | 5053 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
enburg | +0.209 |
assic | +0.205 |
yden | +0.181 |
IDES | +0.180 |
wana | +0.180 |
Neg logit contributions | |
Shank | -0.250 |
redes | -0.248 |
Sew | -0.233 |
purge | -0.226 |
Sho | -0.223 |
Token | ber |
Token ID | 527 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
enburg | +0.053 |
assic | +0.051 |
yden | +0.045 |
wana | +0.045 |
IDES | +0.045 |
Neg logit contributions | |
redes | -0.065 |
Shank | -0.063 |
Sew | -0.059 |
purge | -0.058 |
comprom | -0.058 |
Token | / |
Token ID | 14 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
enburg | +0.144 |
assic | +0.139 |
yden | +0.118 |
IDES | +0.118 |
wana | +0.116 |
Neg logit contributions | |
redes | -0.273 |
Shank | -0.272 |
Sew | -0.257 |
purge | -0.253 |
comprom | -0.249 |
Token | AP |
Token ID | 2969 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
redes | +0.329 |
Shank | +0.323 |
Sew | +0.303 |
purge | +0.299 |
comprom | +0.294 |
Neg logit contributions | |
enburg | -0.233 |
assic | -0.224 |
IDES | -0.199 |
yden | -0.198 |
wana | -0.194 |
Token | ) |
Token ID | 8 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
enburg | +1.173 |
assic | +1.121 |
yden | +0.990 |
IDES | +0.984 |
wana | +0.954 |
Neg logit contributions | |
redes | -1.825 |
Shank | -1.788 |
Sew | -1.681 |
purge | -1.664 |
comprom | -1.661 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
redes | +0.033 |
Shank | +0.033 |
Sew | +0.031 |
purge | +0.030 |
comprom | +0.030 |
Neg logit contributions | |
enburg | -0.028 |
assic | -0.026 |
yden | -0.024 |
IDES | -0.024 |
wana | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
enburg | +0.161 |
assic | +0.158 |
yden | +0.140 |
IDES | +0.140 |
wana | +0.139 |
Neg logit contributions | |
Shank | -0.178 |
redes | -0.177 |
Sew | -0.167 |
purge | -0.163 |
Sho | -0.160 |
Token | Gil |
Token ID | 40747 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
enburg | +0.136 |
assic | +0.134 |
yden | +0.118 |
wana | +0.117 |
IDES | +0.116 |
Neg logit contributions | |
Shank | -0.165 |
redes | -0.164 |
Sew | -0.154 |
purge | -0.151 |
Sho | -0.148 |
Token | bert |
Token ID | 4835 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
enburg | +0.105 |
assic | +0.100 |
IDES | +0.073 |
yden | +0.072 |
wana | +0.069 |
Neg logit contributions | |
redes | -0.431 |
Shank | -0.430 |
Sew | -0.412 |
purge | -0.407 |
comprom | -0.400 |
Token | up |
Token ID | 510 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
redes | +0.109 |
Shank | +0.108 |
Sew | +0.100 |
purge | +0.098 |
comprom | +0.096 |
Neg logit contributions | |
enburg | -0.119 |
assic | -0.116 |
yden | -0.105 |
IDES | -0.105 |
wana | -0.103 |
Token | against |
Token ID | 1028 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
enburg | +0.163 |
assic | +0.158 |
yden | +0.141 |
IDES | +0.141 |
wana | +0.140 |
Neg logit contributions | |
redes | -0.187 |
Shank | -0.185 |
Sew | -0.172 |
purge | -0.170 |
comprom | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
redes | +0.407 |
Shank | +0.403 |
Sew | +0.376 |
purge | +0.369 |
comprom | +0.362 |
Neg logit contributions | |
enburg | -0.365 |
assic | -0.356 |
yden | -0.317 |
IDES | -0.317 |
wana | -0.314 |
Token | Give |
Token ID | 13786 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
enburg | +0.230 |
assic | +0.222 |
yden | +0.202 |
IDES | +0.202 |
wana | +0.199 |
Neg logit contributions | |
redes | -0.225 |
Shank | -0.218 |
Sew | -0.202 |
purge | -0.201 |
comprom | -0.197 |
Token | it |
Token ID | 340 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
enburg | +0.436 |
assic | +0.422 |
yden | +0.378 |
IDES | +0.376 |
wana | +0.371 |
Neg logit contributions | |
redes | -0.512 |
Shank | -0.506 |
Sew | -0.472 |
purge | -0.465 |
comprom | -0.456 |
Token | hell |
Token ID | 5968 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
redes | +0.076 |
Shank | +0.075 |
Sew | +0.070 |
purge | +0.069 |
comprom | +0.068 |
Neg logit contributions | |
enburg | -0.065 |
assic | -0.063 |
yden | -0.056 |
IDES | -0.056 |
wana | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
enburg | +1.748 |
assic | +1.686 |
yden | +1.531 |
IDES | +1.514 |
wana | +1.498 |
Neg logit contributions | |
redes | -1.911 |
Shank | -1.880 |
Sew | -1.747 |
purge | -1.722 |
comprom | -1.689 |
Token | John |
Token ID | 1757 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
enburg | +0.002 |
assic | +0.002 |
yden | +0.002 |
IDES | +0.002 |
wana | +0.002 |
Neg logit contributions | |
redes | -0.003 |
Shank | -0.003 |
Sew | -0.002 |
purge | -0.002 |
comprom | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
redes | +0.432 |
Shank | +0.425 |
Sew | +0.396 |
purge | +0.390 |
comprom | +0.381 |
Neg logit contributions | |
enburg | -0.417 |
assic | -0.405 |
yden | -0.365 |
IDES | -0.363 |
wana | -0.358 |
Token | � |
Token ID | 447 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
redes | +0.110 |
Shank | +0.108 |
Sew | +0.100 |
purge | +0.099 |
comprom | +0.097 |
Neg logit contributions | |
enburg | -0.110 |
assic | -0.106 |
yden | -0.096 |
IDES | -0.096 |
wana | -0.095 |
Token | � |
Token ID | 251 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
redes | +0.145 |
Shank | +0.144 |
Sew | +0.136 |
purge | +0.134 |
comprom | +0.132 |
Neg logit contributions | |
enburg | -0.092 |
assic | -0.089 |
yden | -0.079 |
IDES | -0.077 |
wana | -0.076 |
Token | an |
Token ID | 281 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
enburg | +0.254 |
assic | +0.247 |
yden | +0.220 |
IDES | +0.220 |
wana | +0.217 |
Neg logit contributions | |
redes | -0.294 |
Shank | -0.291 |
Sew | -0.272 |
purge | -0.267 |
comprom | -0.262 |
Token | aber |
Token ID | 42499 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
redes | +0.355 |
Shank | +0.351 |
Sew | +0.328 |
purge | +0.324 |
comprom | +0.317 |
Neg logit contributions | |
enburg | -0.300 |
assic | -0.292 |
yden | -0.262 |
IDES | -0.261 |
wana | -0.259 |
Token | ration |
Token ID | 1358 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
enburg | +0.433 |
assic | +0.426 |
yden | +0.382 |
IDES | +0.379 |
wana | +0.378 |
Neg logit contributions | |
redes | -0.395 |
Shank | -0.381 |
Sew | -0.355 |
purge | -0.345 |
comprom | -0.341 |
Token | of |
Token ID | 286 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
redes | +0.037 |
Shank | +0.036 |
Sew | +0.034 |
purge | +0.033 |
comprom | +0.033 |
Neg logit contributions | |
enburg | -0.033 |
assic | -0.032 |
yden | -0.029 |
IDES | -0.029 |
wana | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
redes | +0.114 |
Shank | +0.113 |
Sew | +0.106 |
purge | +0.104 |
comprom | +0.102 |
Neg logit contributions | |
enburg | -0.103 |
assic | -0.101 |
yden | -0.090 |
IDES | -0.090 |
wana | -0.089 |
Token | primitive |
Token ID | 20049 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
enburg | +0.079 |
assic | +0.077 |
IDES | +0.069 |
yden | +0.069 |
wana | +0.068 |
Neg logit contributions | |
redes | -0.084 |
Shank | -0.083 |
Sew | -0.077 |
purge | -0.076 |
comprom | -0.075 |
Token | mind |
Token ID | 2000 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
enburg | +1.233 |
assic | +1.200 |
IDES | +1.070 |
yden | +1.069 |
wana | +1.049 |
Neg logit contributions | |
redes | -1.378 |
Shank | -1.364 |
Sew | -1.268 |
purge | -1.247 |
comprom | -1.226 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
enburg | +0.653 |
assic | +0.635 |
yden | +0.565 |
IDES | +0.562 |
wana | +0.559 |
Neg logit contributions | |
redes | -0.749 |
Shank | -0.737 |
Sew | -0.689 |
purge | -0.674 |
comprom | -0.664 |
Token | Various |
Token ID | 26386 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
enburg | +0.002 |
assic | +0.002 |
yden | +0.001 |
IDES | +0.001 |
wana | +0.001 |
Neg logit contributions | |
Shank | -0.001 |
redes | -0.001 |
Sew | -0.001 |
purge | -0.001 |
Sho | -0.001 |
Token | schools |
Token ID | 4266 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
redes | +0.843 |
Shank | +0.839 |
Sew | +0.786 |
purge | +0.776 |
comprom | +0.761 |
Neg logit contributions | |
enburg | -0.578 |
assic | -0.562 |
yden | -0.492 |
IDES | -0.492 |
wana | -0.488 |
Token | all |
Token ID | 477 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
enburg | +0.997 |
assic | +0.974 |
yden | +0.865 |
IDES | +0.862 |
wana | +0.857 |
Neg logit contributions | |
redes | -1.116 |
Shank | -1.100 |
Sew | -1.027 |
purge | -1.004 |
comprom | -0.988 |
Token | at |
Token ID | 379 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
enburg | +0.794 |
assic | +0.772 |
yden | +0.702 |
IDES | +0.699 |
wana | +0.692 |
Neg logit contributions | |
redes | -0.719 |
Shank | -0.706 |
Sew | -0.654 |
purge | -0.639 |
comprom | -0.630 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
enburg | +0.015 |
assic | +0.015 |
yden | +0.013 |
IDES | +0.013 |
wana | +0.013 |
Neg logit contributions | |
redes | -0.017 |
Shank | -0.017 |
Sew | -0.015 |
purge | -0.015 |
comprom | -0.015 |
Token | � |
Token ID | 447 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
enburg | +0.085 |
assic | +0.082 |
IDES | +0.073 |
yden | +0.073 |
wana | +0.072 |
Neg logit contributions | |
redes | -0.097 |
Shank | -0.096 |
Sew | -0.089 |
purge | -0.088 |
comprom | -0.087 |
Token | � |
Token ID | 247 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
enburg | +0.005 |
assic | +0.005 |
yden | +0.004 |
IDES | +0.004 |
wana | +0.004 |
Neg logit contributions | |
redes | -0.006 |
Shank | -0.006 |
Sew | -0.005 |
purge | -0.005 |
comprom | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
enburg | +0.088 |
assic | +0.086 |
IDES | +0.077 |
yden | +0.077 |
wana | +0.077 |
Neg logit contributions | |
Shank | -0.091 |
redes | -0.091 |
Sew | -0.085 |
purge | -0.083 |
Sho | -0.081 |
Token | business |
Token ID | 1597 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
enburg | +0.097 |
assic | +0.094 |
IDES | +0.084 |
yden | +0.084 |
wana | +0.083 |
Neg logit contributions | |
redes | -0.099 |
Shank | -0.098 |
Sew | -0.090 |
purge | -0.088 |
comprom | -0.088 |
Token | associates |
Token ID | 20093 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
enburg | +1.051 |
assic | +0.999 |
wana | +0.871 |
yden | +0.870 |
IDES | +0.869 |
Neg logit contributions | |
redes | -1.628 |
Shank | -1.618 |
Sew | -1.521 |
comprom | -1.481 |
purge | -1.480 |
Token | both |
Token ID | 1111 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
enburg | +0.011 |
assic | +0.011 |
yden | +0.010 |
IDES | +0.010 |
wana | +0.010 |
Neg logit contributions | |
redes | -0.013 |
Shank | -0.013 |
Sew | -0.012 |
purge | -0.012 |
comprom | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
enburg | +0.621 |
assic | +0.598 |
yden | +0.535 |
IDES | +0.530 |
wana | +0.528 |
Neg logit contributions | |
redes | -0.672 |
Shank | -0.662 |
Sew | -0.616 |
purge | -0.602 |
comprom | -0.596 |
Token | the |
Token ID | 262 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
enburg | +0.078 |
assic | +0.076 |
yden | +0.068 |
IDES | +0.068 |
wana | +0.067 |
Neg logit contributions | |
redes | -0.084 |
Shank | -0.083 |
Sew | -0.077 |
purge | -0.076 |
comprom | -0.075 |
Token | US |
Token ID | 1294 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
enburg | +0.041 |
assic | +0.040 |
IDES | +0.036 |
yden | +0.036 |
wana | +0.036 |
Neg logit contributions | |
redes | -0.042 |
Shank | -0.041 |
Sew | -0.038 |
purge | -0.037 |
comprom | -0.037 |
Token | Ru |
Token ID | 11667 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
enburg | +0.199 |
assic | +0.194 |
yden | +0.176 |
IDES | +0.176 |
wana | +0.174 |
Neg logit contributions | |
redes | -0.170 |
Shank | -0.167 |
Sew | -0.154 |
purge | -0.151 |
comprom | -0.148 |
Token | iz |
Token ID | 528 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Shank | +0.101 |
redes | +0.099 |
Sew | +0.096 |
purge | +0.092 |
Sho | +0.091 |
Neg logit contributions | |
enburg | -0.092 |
assic | -0.090 |
IDES | -0.081 |
yden | -0.080 |
wana | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
enburg | +0.155 |
assic | +0.151 |
yden | +0.136 |
IDES | +0.136 |
wana | +0.134 |
Neg logit contributions | |
redes | -0.150 |
Shank | -0.148 |
Sew | -0.137 |
purge | -0.135 |
comprom | -0.132 |
Token | who |
Token ID | 508 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
enburg | +0.139 |
assic | +0.135 |
yden | +0.121 |
IDES | +0.121 |
wana | +0.120 |
Neg logit contributions | |
redes | -0.144 |
Shank | -0.142 |
Sew | -0.132 |
purge | -0.130 |
comprom | -0.127 |
Token | had |
Token ID | 550 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
redes | +0.189 |
Shank | +0.187 |
Sew | +0.173 |
purge | +0.170 |
comprom | +0.167 |
Neg logit contributions | |
enburg | -0.206 |
assic | -0.200 |
yden | -0.181 |
IDES | -0.180 |
wana | -0.178 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
enburg | +0.383 |
assic | +0.373 |
yden | +0.337 |
IDES | +0.336 |
wana | +0.332 |
Neg logit contributions | |
redes | -0.352 |
Shank | -0.347 |
Sew | -0.322 |
purge | -0.316 |
comprom | -0.309 |
Token | ized |
Token ID | 1143 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
enburg | +1.311 |
assic | +1.280 |
yden | +1.131 |
IDES | +1.126 |
wana | +1.110 |
Neg logit contributions | |
redes | -1.660 |
Shank | -1.642 |
Sew | -1.531 |
purge | -1.506 |
comprom | -1.479 |
Token | all |
Token ID | 477 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
enburg | +0.428 |
assic | +0.419 |
yden | +0.374 |
IDES | +0.374 |
wana | +0.370 |
Neg logit contributions | |
redes | -0.452 |
Shank | -0.449 |
Sew | -0.418 |
purge | -0.410 |
comprom | -0.401 |
Token | of |
Token ID | 286 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
redes | +0.222 |
Shank | +0.221 |
Sew | +0.206 |
purge | +0.201 |
Sho | +0.197 |
Neg logit contributions | |
enburg | -0.214 |
assic | -0.210 |
IDES | -0.187 |
yden | -0.187 |
wana | -0.186 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
enburg | +0.251 |
assic | +0.245 |
yden | +0.220 |
IDES | +0.219 |
wana | +0.217 |
Neg logit contributions | |
redes | -0.264 |
Shank | -0.262 |
Sew | -0.244 |
purge | -0.239 |
comprom | -0.234 |
Token | winners |
Token ID | 14591 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
enburg | +0.244 |
assic | +0.238 |
yden | +0.212 |
IDES | +0.212 |
wana | +0.209 |
Neg logit contributions | |
redes | -0.282 |
Shank | -0.279 |
Sew | -0.261 |
purge | -0.256 |
comprom | -0.251 |
Token | relationships |
Token ID | 6958 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
enburg | +0.403 |
assic | +0.390 |
yden | +0.348 |
IDES | +0.348 |
wana | +0.344 |
Neg logit contributions | |
redes | -0.462 |
Shank | -0.457 |
Sew | -0.427 |
purge | -0.418 |
comprom | -0.410 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
redes | +0.358 |
Shank | +0.354 |
Sew | +0.331 |
purge | +0.325 |
comprom | +0.319 |
Neg logit contributions | |
enburg | -0.314 |
assic | -0.306 |
yden | -0.273 |
IDES | -0.272 |
wana | -0.269 |
Token | the |
Token ID | 262 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
redes | +0.124 |
Shank | +0.122 |
Sew | +0.114 |
purge | +0.112 |
comprom | +0.110 |
Neg logit contributions | |
enburg | -0.112 |
assic | -0.110 |
yden | -0.098 |
IDES | -0.098 |
wana | -0.097 |
Token | sexual |
Token ID | 3206 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
redes | +0.032 |
Shank | +0.032 |
Sew | +0.030 |
purge | +0.029 |
comprom | +0.028 |
Neg logit contributions | |
enburg | -0.030 |
assic | -0.029 |
yden | -0.026 |
IDES | -0.026 |
wana | -0.026 |
Token | dynamics |
Token ID | 17262 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
enburg | +0.010 |
assic | +0.010 |
yden | +0.009 |
IDES | +0.009 |
wana | +0.009 |
Neg logit contributions | |
redes | -0.012 |
Shank | -0.012 |
Sew | -0.011 |
purge | -0.011 |
comprom | -0.010 |
Token | between |
Token ID | 1022 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
redes | +1.300 |
Shank | +1.296 |
Sew | +1.209 |
purge | +1.186 |
comprom | +1.164 |
Neg logit contributions | |
enburg | -1.155 |
assic | -1.132 |
yden | -1.004 |
IDES | -0.996 |
wana | -0.988 |
Token | a |
Token ID | 257 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
redes | +0.158 |
Shank | +0.156 |
Sew | +0.146 |
purge | +0.143 |
comprom | +0.141 |
Neg logit contributions | |
enburg | -0.133 |
assic | -0.129 |
yden | -0.115 |
IDES | -0.115 |
wana | -0.114 |
Token | man |
Token ID | 582 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
enburg | +0.055 |
assic | +0.054 |
yden | +0.048 |
IDES | +0.048 |
wana | +0.048 |
Neg logit contributions | |
redes | -0.061 |
Shank | -0.060 |
Sew | -0.056 |
purge | -0.055 |
comprom | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
redes | +0.430 |
Shank | +0.425 |
Sew | +0.397 |
purge | +0.390 |
comprom | +0.383 |
Neg logit contributions | |
enburg | -0.373 |
assic | -0.363 |
yden | -0.324 |
IDES | -0.323 |
wana | -0.320 |
Token | a |
Token ID | 257 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
redes | +0.112 |
Shank | +0.110 |
Sew | +0.103 |
purge | +0.101 |
comprom | +0.099 |
Neg logit contributions | |
enburg | -0.101 |
assic | -0.098 |
yden | -0.088 |
IDES | -0.088 |
wana | -0.087 |
Token | woman |
Token ID | 2415 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
redes | +0.093 |
Shank | +0.091 |
Sew | +0.083 |
purge | +0.081 |
comprom | +0.079 |
Neg logit contributions | |
enburg | -0.145 |
assic | -0.142 |
yden | -0.131 |
IDES | -0.131 |
wana | -0.129 |
Token | an |
Token ID | 281 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
Shank | +0.159 |
redes | +0.158 |
Sew | +0.148 |
purge | +0.145 |
Sho | +0.142 |
Neg logit contributions | |
enburg | -0.145 |
assic | -0.143 |
IDES | -0.127 |
yden | -0.127 |
wana | -0.126 |
Token | option |
Token ID | 3038 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
Shank | +0.073 |
redes | +0.073 |
Sew | +0.068 |
purge | +0.067 |
comprom | +0.066 |
Neg logit contributions | |
enburg | -0.056 |
assic | -0.055 |
IDES | -0.049 |
yden | -0.049 |
wana | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Shank | +0.529 |
redes | +0.524 |
Sew | +0.488 |
purge | +0.479 |
Sho | +0.469 |
Neg logit contributions | |
enburg | -0.537 |
assic | -0.531 |
IDES | -0.473 |
yden | -0.472 |
wana | -0.469 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
redes | +0.099 |
Shank | +0.098 |
Sew | +0.090 |
purge | +0.089 |
comprom | +0.087 |
Neg logit contributions | |
enburg | -0.105 |
assic | -0.103 |
yden | -0.093 |
IDES | -0.093 |
wana | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
enburg | +0.076 |
assic | +0.074 |
yden | +0.066 |
IDES | +0.066 |
wana | +0.065 |
Neg logit contributions | |
Shank | -0.083 |
redes | -0.082 |
Sew | -0.078 |
purge | -0.076 |
Sho | -0.075 |
Token | � |
Token ID | 447 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
enburg | +0.096 |
assic | +0.094 |
yden | +0.083 |
IDES | +0.083 |
wana | +0.082 |
Neg logit contributions | |
redes | -0.117 |
Shank | -0.116 |
Sew | -0.108 |
purge | -0.106 |
comprom | -0.104 |
Token | � |
Token ID | 250 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
enburg | +0.019 |
assic | +0.019 |
yden | +0.016 |
IDES | +0.016 |
wana | +0.016 |
Neg logit contributions | |
redes | -0.028 |
Shank | -0.028 |
Sew | -0.027 |
purge | -0.026 |
comprom | -0.026 |
Token | It |
Token ID | 1026 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
enburg | +0.007 |
assic | +0.006 |
yden | +0.006 |
IDES | +0.006 |
wana | +0.006 |
Neg logit contributions | |
redes | -0.009 |
Shank | -0.009 |
Sew | -0.008 |
purge | -0.008 |
comprom | -0.008 |
Token | 's |
Token ID | 338 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
enburg | +0.225 |
assic | +0.220 |
IDES | +0.195 |
yden | +0.195 |
wana | +0.192 |
Neg logit contributions | |
redes | -0.276 |
Shank | -0.274 |
Sew | -0.256 |
purge | -0.252 |
comprom | -0.247 |
Token | just |
Token ID | 655 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
enburg | +0.532 |
assic | +0.520 |
yden | +0.466 |
IDES | +0.465 |
wana | +0.461 |
Neg logit contributions | |
redes | -0.551 |
Shank | -0.547 |
Sew | -0.509 |
purge | -0.499 |
comprom | -0.489 |
Token | that |
Token ID | 326 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
enburg | +0.085 |
assic | +0.083 |
yden | +0.074 |
IDES | +0.074 |
wana | +0.073 |
Neg logit contributions | |
redes | -0.092 |
Shank | -0.092 |
Sew | -0.086 |
purge | -0.084 |
comprom | -0.082 |
Token | as |
Token ID | 355 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
redes | +0.023 |
Shank | +0.023 |
Sew | +0.021 |
purge | +0.021 |
comprom | +0.020 |
Neg logit contributions | |
enburg | -0.021 |
assic | -0.020 |
yden | -0.018 |
IDES | -0.018 |
wana | -0.018 |
Token | they |
Token ID | 484 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
enburg | +0.281 |
assic | +0.274 |
yden | +0.244 |
IDES | +0.244 |
wana | +0.241 |
Neg logit contributions | |
redes | -0.319 |
Shank | -0.315 |
Sew | -0.294 |
purge | -0.289 |
comprom | -0.283 |
Token | missed |
Token ID | 6825 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
redes | +0.309 |
Shank | +0.306 |
Sew | +0.283 |
purge | +0.276 |
comprom | +0.271 |
Neg logit contributions | |
enburg | -0.334 |
assic | -0.325 |
yden | -0.293 |
IDES | -0.292 |
wana | -0.290 |
Token | the |
Token ID | 262 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
enburg | +0.235 |
assic | +0.229 |
yden | +0.204 |
IDES | +0.204 |
wana | +0.202 |
Neg logit contributions | |
redes | -0.262 |
Shank | -0.258 |
Sew | -0.241 |
purge | -0.237 |
comprom | -0.232 |
Token | postseason |
Token ID | 22905 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
enburg | +0.073 |
assic | +0.072 |
yden | +0.065 |
IDES | +0.065 |
wana | +0.065 |
Neg logit contributions | |
redes | -0.054 |
Shank | -0.054 |
Sew | -0.049 |
purge | -0.048 |
comprom | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
enburg | +0.196 |
assic | +0.190 |
yden | +0.170 |
IDES | +0.170 |
wana | +0.168 |
Neg logit contributions | |
redes | -0.205 |
Shank | -0.202 |
Sew | -0.188 |
purge | -0.184 |
comprom | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
redes | +0.050 |
Shank | +0.050 |
Sew | +0.046 |
purge | +0.046 |
comprom | +0.045 |
Neg logit contributions | |
enburg | -0.044 |
assic | -0.043 |
yden | -0.039 |
IDES | -0.039 |
wana | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Shank | +0.209 |
redes | +0.203 |
Sew | +0.196 |
purge | +0.190 |
Sho | +0.187 |
Neg logit contributions | |
enburg | -0.198 |
assic | -0.195 |
yden | -0.174 |
IDES | -0.173 |
wana | -0.172 |
Token | Bron |
Token ID | 18760 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Shank | +0.186 |
redes | +0.184 |
Sew | +0.174 |
purge | +0.170 |
Sho | +0.167 |
Neg logit contributions | |
enburg | -0.147 |
assic | -0.144 |
yden | -0.127 |
wana | -0.126 |
IDES | -0.126 |
Token | cos |
Token ID | 6966 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
redes | +0.124 |
Shank | +0.123 |
Sew | +0.112 |
purge | +0.109 |
comprom | +0.106 |
Neg logit contributions | |
enburg | -0.194 |
assic | -0.191 |
IDES | -0.175 |
yden | -0.175 |
wana | -0.173 |
Token | coach |
Token ID | 3985 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
redes | +0.031 |
Shank | +0.031 |
Sew | +0.029 |
purge | +0.028 |
comprom | +0.027 |
Neg logit contributions | |
enburg | -0.026 |
assic | -0.026 |
yden | -0.023 |
IDES | -0.023 |
wana | -0.023 |
Token | enrol |
Token ID | 34311 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
redes | +1.239 |
Shank | +1.235 |
Sew | +1.153 |
purge | +1.136 |
comprom | +1.106 |
Neg logit contributions | |
enburg | -1.137 |
assic | -1.114 |
IDES | -0.994 |
yden | -0.991 |
wana | -0.981 |
Token | lees |
Token ID | 49410 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Shank | +0.723 |
redes | +0.706 |
Sew | +0.664 |
purge | +0.647 |
Sho | +0.635 |
Neg logit contributions | |
enburg | -0.886 |
assic | -0.876 |
IDES | -0.798 |
yden | -0.792 |
wana | -0.782 |
Token | (" |
Token ID | 5855 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
redes | +0.350 |
Shank | +0.347 |
Sew | +0.323 |
purge | +0.317 |
comprom | +0.311 |
Neg logit contributions | |
enburg | -0.321 |
assic | -0.313 |
yden | -0.280 |
IDES | -0.280 |
wana | -0.276 |
Token | Republicans |
Token ID | 28455 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
redes | +0.223 |
Shank | +0.220 |
Sew | +0.205 |
purge | +0.201 |
comprom | +0.198 |
Neg logit contributions | |
enburg | -0.201 |
assic | -0.195 |
yden | -0.174 |
IDES | -0.174 |
wana | -0.172 |
Token | ' |
Token ID | 6 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
enburg | +1.197 |
assic | +1.158 |
yden | +1.048 |
IDES | +1.043 |
wana | +1.035 |
Neg logit contributions | |
redes | -1.183 |
Shank | -1.164 |
Sew | -1.076 |
purge | -1.047 |
comprom | -1.032 |
Token | fingerprints |
Token ID | 34290 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
redes | +0.500 |
Shank | +0.494 |
Sew | +0.456 |
purge | +0.446 |
comprom | +0.439 |
Neg logit contributions | |
enburg | -0.513 |
assic | -0.500 |
yden | -0.450 |
IDES | -0.450 |
wana | -0.444 |
Token | are |
Token ID | 389 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
enburg | +0.390 |
assic | +0.381 |
yden | +0.346 |
IDES | +0.344 |
wana | +0.343 |
Neg logit contributions | |
redes | -0.344 |
Shank | -0.339 |
Sew | -0.311 |
purge | -0.301 |
comprom | -0.298 |
Token | all |
Token ID | 477 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
redes | +0.034 |
Shank | +0.034 |
Sew | +0.031 |
purge | +0.030 |
comprom | +0.030 |
Neg logit contributions | |
enburg | -0.038 |
assic | -0.037 |
yden | -0.033 |
IDES | -0.033 |
wana | -0.033 |
Token | over |
Token ID | 625 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
redes | +0.710 |
Shank | +0.706 |
Sew | +0.669 |
purge | +0.657 |
comprom | +0.647 |
Neg logit contributions | |
enburg | -0.427 |
assic | -0.416 |
IDES | -0.357 |
yden | -0.356 |
wana | -0.351 |
Token | Obamacare |
Token ID | 12439 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
enburg | +0.892 |
assic | +0.857 |
yden | +0.778 |
IDES | +0.777 |
wana | +0.762 |
Neg logit contributions | |
redes | -0.927 |
Shank | -0.908 |
Sew | -0.839 |
purge | -0.825 |
comprom | -0.809 |
Token | premium |
Token ID | 8683 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
redes | +0.823 |
Shank | +0.815 |
Sew | +0.763 |
purge | +0.750 |
comprom | +0.736 |
Neg logit contributions | |
enburg | -0.658 |
assic | -0.640 |
yden | -0.566 |
IDES | -0.566 |
wana | -0.559 |
Token | the |
Token ID | 262 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
redes | +0.206 |
Shank | +0.205 |
Sew | +0.191 |
purge | +0.187 |
comprom | +0.183 |
Neg logit contributions | |
enburg | -0.191 |
assic | -0.187 |
IDES | -0.167 |
yden | -0.167 |
wana | -0.165 |
Token | spirit |
Token ID | 4437 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
enburg | +0.036 |
assic | +0.035 |
yden | +0.032 |
IDES | +0.032 |
wana | +0.031 |
Neg logit contributions | |
redes | -0.035 |
Shank | -0.035 |
Sew | -0.032 |
purge | -0.032 |
comprom | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
redes | +0.062 |
Shank | +0.062 |
Sew | +0.057 |
purge | +0.056 |
comprom | +0.055 |
Neg logit contributions | |
enburg | -0.054 |
assic | -0.053 |
yden | -0.047 |
IDES | -0.047 |
wana | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
enburg | +0.110 |
assic | +0.107 |
yden | +0.095 |
IDES | +0.095 |
wana | +0.094 |
Neg logit contributions | |
redes | -0.116 |
Shank | -0.115 |
Sew | -0.107 |
purge | -0.105 |
comprom | -0.103 |
Token | games |
Token ID | 1830 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
enburg | +0.018 |
assic | +0.018 |
yden | +0.016 |
IDES | +0.016 |
wana | +0.016 |
Neg logit contributions | |
redes | -0.019 |
Shank | -0.019 |
Sew | -0.018 |
purge | -0.017 |
comprom | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
redes | +0.477 |
Shank | +0.472 |
Sew | +0.439 |
purge | +0.431 |
comprom | +0.423 |
Neg logit contributions | |
enburg | -0.450 |
assic | -0.438 |
yden | -0.392 |
IDES | -0.391 |
wana | -0.388 |
Token | Residents |
Token ID | 29602 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
redes | +0.081 |
Shank | +0.080 |
Sew | +0.074 |
purge | +0.073 |
comprom | +0.071 |
Neg logit contributions | |
enburg | -0.088 |
assic | -0.086 |
IDES | -0.078 |
yden | -0.078 |
wana | -0.077 |
Token | have |
Token ID | 423 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
redes | +0.667 |
Shank | +0.661 |
Sew | +0.614 |
purge | +0.603 |
comprom | +0.590 |
Neg logit contributions | |
enburg | -0.663 |
assic | -0.647 |
yden | -0.580 |
IDES | -0.580 |
wana | -0.573 |
Token | also |
Token ID | 635 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
enburg | +0.024 |
assic | +0.023 |
yden | +0.021 |
IDES | +0.021 |
wana | +0.021 |
Neg logit contributions | |
redes | -0.020 |
Shank | -0.020 |
Sew | -0.018 |
purge | -0.018 |
comprom | -0.018 |
Token | missed |
Token ID | 6825 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
enburg | +0.085 |
assic | +0.083 |
yden | +0.076 |
IDES | +0.076 |
wana | +0.075 |
Neg logit contributions | |
redes | -0.069 |
Shank | -0.068 |
Sew | -0.063 |
purge | -0.062 |
comprom | -0.060 |
Token | out |
Token ID | 503 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
enburg | +0.472 |
assic | +0.460 |
IDES | +0.411 |
yden | +0.411 |
wana | +0.406 |
Neg logit contributions | |
redes | -0.510 |
Shank | -0.504 |
Sew | -0.470 |
purge | -0.462 |
comprom | -0.454 |
Token | charges |
Token ID | 4530 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
enburg | +0.027 |
assic | +0.026 |
IDES | +0.023 |
yden | +0.023 |
wana | +0.023 |
Neg logit contributions | |
redes | -0.026 |
Shank | -0.026 |
Sew | -0.024 |
purge | -0.023 |
comprom | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
enburg | +0.717 |
assic | +0.700 |
yden | +0.619 |
IDES | +0.616 |
wana | +0.612 |
Neg logit contributions | |
redes | -0.821 |
Shank | -0.810 |
Sew | -0.755 |
purge | -0.742 |
comprom | -0.729 |
Token | em |
Token ID | 795 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
redes | +0.262 |
Shank | +0.259 |
Sew | +0.240 |
purge | +0.235 |
comprom | +0.230 |
Neg logit contributions | |
enburg | -0.268 |
assic | -0.261 |
IDES | -0.234 |
yden | -0.234 |
wana | -0.232 |
Token | be |
Token ID | 1350 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
enburg | +1.044 |
assic | +1.000 |
wana | +0.917 |
yden | +0.914 |
vant | +0.912 |
Neg logit contributions | |
redes | -0.756 |
Shank | -0.741 |
Sew | -0.665 |
purge | -0.651 |
comprom | -0.639 |
Token | zz |
Token ID | 3019 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
redes | +1.075 |
Shank | +1.071 |
Sew | +1.000 |
purge | +0.982 |
comprom | +0.962 |
Neg logit contributions | |
enburg | -0.933 |
assic | -0.910 |
IDES | -0.811 |
yden | -0.809 |
wana | -0.798 |
Token | lement |
Token ID | 1732 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
redes | +0.019 |
Shank | +0.018 |
Sew | +0.017 |
purge | +0.017 |
comprom | +0.017 |
Neg logit contributions | |
enburg | -0.012 |
assic | -0.012 |
yden | -0.010 |
IDES | -0.010 |
wana | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
redes | +1.359 |
Shank | +1.348 |
Sew | +1.257 |
purge | +1.235 |
comprom | +1.209 |
Neg logit contributions | |
enburg | -1.226 |
assic | -1.197 |
yden | -1.069 |
IDES | -1.067 |
wana | -1.054 |
Token | char |
Token ID | 1149 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
enburg | +0.046 |
assic | +0.045 |
IDES | +0.040 |
yden | +0.040 |
wana | +0.040 |
Neg logit contributions | |
redes | -0.044 |
Shank | -0.044 |
Sew | -0.040 |
purge | -0.039 |
comprom | -0.039 |
Token | lat |
Token ID | 15460 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
enburg | +0.409 |
assic | +0.395 |
wana | +0.349 |
IDES | +0.349 |
yden | +0.348 |
Neg logit contributions | |
redes | -0.502 |
Shank | -0.494 |
Sew | -0.458 |
purge | -0.449 |
comprom | -0.447 |
Token | anism |
Token ID | 48162 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
enburg | +0.312 |
assic | +0.306 |
yden | +0.281 |
IDES | +0.279 |
wana | +0.278 |
Neg logit contributions | |
redes | -0.172 |
Shank | -0.168 |
Sew | -0.150 |
purge | -0.147 |
comprom | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
redes | +0.272 |
Shank | +0.268 |
Sew | +0.250 |
purge | +0.245 |
comprom | +0.241 |
Neg logit contributions | |
enburg | -0.241 |
assic | -0.234 |
yden | -0.208 |
IDES | -0.208 |
wana | -0.207 |
Token | with |
Token ID | 351 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
enburg | +0.569 |
assic | +0.552 |
yden | +0.492 |
IDES | +0.491 |
wana | +0.486 |
Neg logit contributions | |
redes | -0.662 |
Shank | -0.655 |
Sew | -0.612 |
purge | -0.603 |
comprom | -0.592 |
Token | our |
Token ID | 674 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
enburg | +0.039 |
assic | +0.038 |
yden | +0.034 |
IDES | +0.034 |
wana | +0.033 |
Neg logit contributions | |
redes | -0.044 |
Shank | -0.044 |
Sew | -0.041 |
purge | -0.040 |
comprom | -0.040 |
Token | con |
Token ID | 369 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
enburg | +0.041 |
assic | +0.040 |
yden | +0.036 |
IDES | +0.036 |
wana | +0.035 |
Neg logit contributions | |
redes | -0.048 |
Shank | -0.047 |
Sew | -0.044 |
purge | -0.044 |
comprom | -0.043 |
Token | undrum |
Token ID | 46859 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
enburg | +0.134 |
assic | +0.131 |
yden | +0.119 |
IDES | +0.117 |
wana | +0.117 |
Neg logit contributions | |
redes | -0.112 |
Shank | -0.111 |
Sew | -0.102 |
purge | -0.100 |
comprom | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
redes | +1.355 |
Shank | +1.344 |
Sew | +1.255 |
purge | +1.232 |
comprom | +1.207 |
Neg logit contributions | |
enburg | -1.184 |
assic | -1.156 |
IDES | -1.027 |
yden | -1.027 |
wana | -1.016 |
Token | Within |
Token ID | 12511 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
enburg | +0.240 |
assic | +0.234 |
yden | +0.211 |
IDES | +0.211 |
wana | +0.209 |
Neg logit contributions | |
redes | -0.220 |
Shank | -0.218 |
Sew | -0.202 |
purge | -0.198 |
comprom | -0.193 |
Token | a |
Token ID | 257 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
redes | +0.239 |
Shank | +0.237 |
Sew | +0.221 |
purge | +0.217 |
comprom | +0.212 |
Neg logit contributions | |
enburg | -0.222 |
assic | -0.217 |
IDES | -0.194 |
yden | -0.193 |
wana | -0.191 |
Token | few |
Token ID | 1178 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
enburg | +0.249 |
assic | +0.242 |
yden | +0.214 |
IDES | +0.214 |
wana | +0.211 |
Neg logit contributions | |
redes | -0.310 |
Shank | -0.307 |
Sew | -0.287 |
purge | -0.282 |
comprom | -0.277 |
Token | hours |
Token ID | 2250 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
enburg | +0.590 |
assic | +0.575 |
yden | +0.515 |
IDES | +0.514 |
wana | +0.508 |
Neg logit contributions | |
redes | -0.630 |
Shank | -0.623 |
Sew | -0.580 |
purge | -0.570 |
comprom | -0.558 |
Token | we |
Token ID | 356 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
enburg | +0.153 |
assic | +0.149 |
yden | +0.133 |
IDES | +0.133 |
wana | +0.131 |
Neg logit contributions | |
redes | -0.179 |
Shank | -0.178 |
Sew | -0.167 |
purge | -0.164 |
comprom | -0.160 |
Token | received |
Token ID | 2722 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
redes | +0.010 |
Shank | +0.010 |
Sew | +0.009 |
purge | +0.009 |
comprom | +0.009 |
Neg logit contributions | |
enburg | -0.011 |
assic | -0.010 |
yden | -0.009 |
IDES | -0.009 |
wana | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
redes | +0.015 |
Shank | +0.015 |
Sew | +0.014 |
purge | +0.014 |
comprom | +0.013 |
Neg logit contributions | |
enburg | -0.013 |
assic | -0.013 |
yden | -0.012 |
IDES | -0.012 |
wana | -0.012 |
Token | Garden |
Token ID | 11652 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
redes | +0.222 |
Shank | +0.218 |
Sew | +0.203 |
purge | +0.200 |
comprom | +0.196 |
Neg logit contributions | |
enburg | -0.215 |
assic | -0.209 |
yden | -0.188 |
IDES | -0.188 |
wana | -0.186 |
Token | Grove |
Token ID | 24144 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
enburg | +0.259 |
assic | +0.250 |
yden | +0.226 |
IDES | +0.225 |
wana | +0.223 |
Neg logit contributions | |
redes | -0.254 |
Shank | -0.247 |
Sew | -0.230 |
purge | -0.228 |
comprom | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
enburg | +0.328 |
assic | +0.314 |
yden | +0.277 |
IDES | +0.274 |
wana | +0.273 |
Neg logit contributions | |
redes | -0.470 |
Shank | -0.460 |
Sew | -0.431 |
purge | -0.429 |
comprom | -0.421 |
Token | California |
Token ID | 3442 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
redes | +0.072 |
Shank | +0.072 |
Sew | +0.068 |
purge | +0.067 |
comprom | +0.066 |
Neg logit contributions | |
enburg | -0.040 |
assic | -0.039 |
yden | -0.033 |
IDES | -0.033 |
wana | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
enburg | +0.270 |
assic | +0.263 |
yden | +0.235 |
IDES | +0.234 |
wana | +0.231 |
Neg logit contributions | |
redes | -0.305 |
Shank | -0.300 |
Sew | -0.279 |
purge | -0.275 |
comprom | -0.271 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
redes | +0.321 |
Shank | +0.317 |
Sew | +0.288 |
purge | +0.281 |
comprom | +0.273 |
Neg logit contributions | |
enburg | -0.500 |
assic | -0.491 |
yden | -0.450 |
IDES | -0.449 |
wana | -0.445 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Shank | +0.166 |
redes | +0.166 |
Sew | +0.155 |
purge | +0.150 |
Sho | +0.147 |
Neg logit contributions | |
enburg | -0.175 |
assic | -0.172 |
yden | -0.154 |
IDES | -0.153 |
wana | -0.152 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
Shank | +0.879 |
Sew | +0.821 |
redes | +0.797 |
Sho | +0.777 |
purge | +0.756 |
Neg logit contributions | |
enburg | -1.020 |
assic | -1.005 |
yden | -0.918 |
wana | -0.909 |
IDES | -0.890 |
Token | of |
Token ID | 286 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
enburg | +0.637 |
assic | +0.625 |
yden | +0.558 |
IDES | +0.555 |
wana | +0.552 |
Neg logit contributions | |
Shank | -0.653 |
redes | -0.647 |
Sew | -0.609 |
purge | -0.593 |
Sho | -0.580 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
Shank | +0.049 |
redes | +0.048 |
Sew | +0.046 |
purge | +0.044 |
Sho | +0.044 |
Neg logit contributions | |
enburg | -0.051 |
assic | -0.051 |
yden | -0.045 |
IDES | -0.045 |
wana | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
redes | +1.009 |
Shank | +0.998 |
Sew | +0.935 |
purge | +0.922 |
comprom | +0.904 |
Neg logit contributions | |
enburg | -0.776 |
assic | -0.754 |
yden | -0.666 |
IDES | -0.665 |
wana | -0.658 |
Token | now |
Token ID | 783 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
enburg | +0.083 |
assic | +0.080 |
yden | +0.072 |
IDES | +0.072 |
wana | +0.071 |
Neg logit contributions | |
redes | -0.086 |
Shank | -0.084 |
Sew | -0.079 |
purge | -0.078 |
comprom | -0.076 |
Token | you |
Token ID | 345 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
redes | +0.531 |
Shank | +0.525 |
Sew | +0.491 |
purge | +0.483 |
comprom | +0.474 |
Neg logit contributions | |
enburg | -0.443 |
assic | -0.431 |
yden | -0.383 |
IDES | -0.383 |
wana | -0.379 |
Token | understand |
Token ID | 1833 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
enburg | +0.242 |
assic | +0.235 |
yden | +0.212 |
IDES | +0.211 |
wana | +0.211 |
Neg logit contributions | |
redes | -0.240 |
Shank | -0.236 |
Sew | -0.220 |
purge | -0.215 |
comprom | -0.212 |
Token | the |
Token ID | 262 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
redes | +0.306 |
Shank | +0.301 |
Sew | +0.281 |
purge | +0.276 |
comprom | +0.272 |
Neg logit contributions | |
enburg | -0.268 |
assic | -0.259 |
yden | -0.232 |
IDES | -0.232 |
wana | -0.229 |
Token | differences |
Token ID | 5400 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
redes | +0.045 |
Shank | +0.045 |
Sew | +0.042 |
purge | +0.041 |
comprom | +0.040 |
Neg logit contributions | |
enburg | -0.037 |
assic | -0.036 |
yden | -0.032 |
IDES | -0.032 |
wana | -0.032 |
Token | between |
Token ID | 1022 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
redes | +0.368 |
Shank | +0.366 |
Sew | +0.342 |
purge | +0.335 |
comprom | +0.329 |
Neg logit contributions | |
enburg | -0.311 |
assic | -0.303 |
yden | -0.269 |
IDES | -0.268 |
wana | -0.265 |
Token | these |
Token ID | 777 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
redes | +0.102 |
Shank | +0.099 |
Sew | +0.090 |
purge | +0.088 |
comprom | +0.085 |
Neg logit contributions | |
enburg | -0.168 |
assic | -0.165 |
IDES | -0.151 |
yden | -0.151 |
wana | -0.150 |
Token | three |
Token ID | 1115 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
enburg | +0.442 |
assic | +0.430 |
yden | +0.387 |
IDES | +0.386 |
wana | +0.382 |
Neg logit contributions | |
redes | -0.446 |
Shank | -0.441 |
Sew | -0.410 |
purge | -0.402 |
comprom | -0.394 |
Token | management |
Token ID | 4542 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
enburg | +0.071 |
assic | +0.069 |
yden | +0.061 |
IDES | +0.061 |
wana | +0.060 |
Neg logit contributions | |
redes | -0.090 |
Shank | -0.089 |
Sew | -0.083 |
purge | -0.082 |
comprom | -0.080 |
Token | approaches |
Token ID | 10581 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
enburg | +0.110 |
assic | +0.108 |
yden | +0.095 |
IDES | +0.095 |
wana | +0.094 |
Neg logit contributions | |
redes | -0.139 |
Shank | -0.138 |
Sew | -0.129 |
purge | -0.127 |
comprom | -0.125 |
Token | Gas |
Token ID | 14345 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
enburg | +0.184 |
assic | +0.180 |
yden | +0.162 |
IDES | +0.162 |
wana | +0.160 |
Neg logit contributions | |
redes | -0.171 |
Shank | -0.169 |
Sew | -0.156 |
purge | -0.153 |
comprom | -0.150 |
Token | Commission |
Token ID | 4513 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
enburg | +0.361 |
assic | +0.352 |
IDES | +0.317 |
yden | +0.317 |
wana | +0.316 |
Neg logit contributions | |
redes | -0.317 |
Shank | -0.311 |
Sew | -0.285 |
purge | -0.281 |
comprom | -0.278 |
Token | . |
Token ID | 13 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
redes | +0.164 |
Shank | +0.163 |
Sew | +0.152 |
purge | +0.149 |
comprom | +0.146 |
Neg logit contributions | |
enburg | -0.145 |
assic | -0.141 |
yden | -0.126 |
IDES | -0.126 |
wana | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
redes | +0.036 |
Shank | +0.036 |
Sew | +0.033 |
purge | +0.033 |
comprom | +0.032 |
Neg logit contributions | |
enburg | -0.036 |
assic | -0.035 |
yden | -0.031 |
IDES | -0.031 |
wana | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
enburg | +0.160 |
assic | +0.158 |
yden | +0.140 |
IDES | +0.140 |
wana | +0.138 |
Neg logit contributions | |
Shank | -0.172 |
redes | -0.167 |
Sew | -0.161 |
purge | -0.156 |
Sho | -0.154 |
Token | However |
Token ID | 4864 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
enburg | +0.132 |
assic | +0.128 |
yden | +0.114 |
IDES | +0.113 |
wana | +0.113 |
Neg logit contributions | |
redes | -0.157 |
Shank | -0.157 |
Sew | -0.147 |
purge | -0.144 |
Sho | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
redes | +0.337 |
Shank | +0.334 |
Sew | +0.313 |
purge | +0.308 |
comprom | +0.302 |
Neg logit contributions | |
enburg | -0.257 |
assic | -0.250 |
yden | -0.220 |
IDES | -0.220 |
wana | -0.217 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
redes | +0.102 |
Shank | +0.101 |
Sew | +0.094 |
purge | +0.093 |
Sho | +0.091 |
Neg logit contributions | |
enburg | -0.093 |
assic | -0.091 |
IDES | -0.081 |
yden | -0.081 |
wana | -0.080 |
Token | report |
Token ID | 989 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
redes | +0.097 |
Shank | +0.097 |
Sew | +0.090 |
purge | +0.088 |
comprom | +0.086 |
Neg logit contributions | |
enburg | -0.092 |
assic | -0.090 |
yden | -0.081 |
IDES | -0.080 |
wana | -0.080 |
Token | says |
Token ID | 1139 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
enburg | +0.204 |
assic | +0.199 |
yden | +0.179 |
IDES | +0.179 |
wana | +0.177 |
Neg logit contributions | |
redes | -0.192 |
Shank | -0.189 |
Sew | -0.175 |
purge | -0.172 |
comprom | -0.168 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
enburg | +0.315 |
assic | +0.307 |
yden | +0.272 |
IDES | +0.272 |
wana | +0.268 |
Neg logit contributions | |
redes | -0.376 |
Shank | -0.374 |
Sew | -0.350 |
purge | -0.344 |
comprom | -0.336 |
Token | B |
Token ID | 33 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
redes | +0.460 |
Shank | +0.456 |
Sew | +0.428 |
purge | +0.421 |
comprom | +0.414 |
Neg logit contributions | |
enburg | -0.331 |
assic | -0.322 |
yden | -0.283 |
IDES | -0.282 |
wana | -0.278 |
Token | old |
Token ID | 727 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
redes | +0.577 |
Shank | +0.574 |
Sew | +0.537 |
purge | +0.527 |
comprom | +0.516 |
Neg logit contributions | |
enburg | -0.481 |
assic | -0.468 |
yden | -0.415 |
IDES | -0.415 |
wana | -0.409 |
Token | ) |
Token ID | 8 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
redes | +1.505 |
Shank | +1.495 |
Sew | +1.402 |
purge | +1.377 |
comprom | +1.352 |
Neg logit contributions | |
enburg | -1.166 |
assic | -1.135 |
yden | -1.002 |
IDES | -0.999 |
wana | -0.987 |
Token | $ |
Token ID | 720 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
redes | +1.188 |
Shank | +1.172 |
Sew | +1.082 |
purge | +1.060 |
comprom | +1.041 |
Neg logit contributions | |
enburg | -1.307 |
assic | -1.277 |
IDES | -1.155 |
yden | -1.154 |
wana | -1.142 |
Token | Br |
Token ID | 9414 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
enburg | +0.166 |
assic | +0.161 |
yden | +0.140 |
IDES | +0.140 |
wana | +0.138 |
Neg logit contributions | |
redes | -0.245 |
Shank | -0.243 |
Sew | -0.229 |
purge | -0.225 |
comprom | -0.221 |
Token | ush |
Token ID | 1530 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
enburg | +0.265 |
assic | +0.259 |
yden | +0.229 |
IDES | +0.229 |
wana | +0.227 |
Neg logit contributions | |
redes | -0.316 |
Shank | -0.311 |
Sew | -0.291 |
purge | -0.285 |
comprom | -0.281 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
redes | +2.221 |
Shank | +2.211 |
Sew | +2.073 |
purge | +2.038 |
comprom | +1.998 |
Neg logit contributions | |
enburg | -1.803 |
assic | -1.756 |
yden | -1.557 |
IDES | -1.546 |
wana | -1.533 |
Token | = |
Token ID | 796 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
enburg | +0.195 |
assic | +0.189 |
yden | +0.170 |
IDES | +0.170 |
wana | +0.168 |
Neg logit contributions | |
redes | -0.211 |
Shank | -0.207 |
Sew | -0.192 |
purge | -0.189 |
comprom | -0.186 |
Token | New |
Token ID | 968 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
redes | +0.161 |
Shank | +0.159 |
Sew | +0.149 |
purge | +0.146 |
comprom | +0.144 |
Neg logit contributions | |
enburg | -0.138 |
assic | -0.134 |
IDES | -0.120 |
yden | -0.120 |
wana | -0.118 |
Token | - |
Token ID | 12 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
Shank | +0.344 |
redes | +0.335 |
Sew | +0.323 |
purge | +0.312 |
Sho | +0.309 |
Neg logit contributions | |
enburg | -0.300 |
assic | -0.295 |
yden | -0.261 |
IDES | -0.260 |
wana | -0.259 |
Token | Object |
Token ID | 10267 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Shank | +0.469 |
redes | +0.451 |
Sew | +0.443 |
Sho | +0.424 |
purge | +0.422 |
Neg logit contributions | |
enburg | -0.410 |
assic | -0.403 |
yden | -0.355 |
wana | -0.353 |
IDES | -0.351 |
Token | language |
Token ID | 3303 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
redes | +0.724 |
Shank | +0.717 |
Sew | +0.668 |
purge | +0.656 |
comprom | +0.646 |
Neg logit contributions | |
enburg | -0.642 |
assic | -0.624 |
yden | -0.556 |
IDES | -0.555 |
wana | -0.550 |
Token | 's |
Token ID | 338 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
redes | +0.514 |
Shank | +0.509 |
Sew | +0.476 |
purge | +0.468 |
comprom | +0.459 |
Neg logit contributions | |
enburg | -0.430 |
assic | -0.419 |
yden | -0.372 |
IDES | -0.372 |
wana | -0.367 |
Token | recommendation |
Token ID | 15602 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
redes | +0.270 |
Shank | +0.267 |
Sew | +0.248 |
purge | +0.243 |
comprom | +0.240 |
Neg logit contributions | |
enburg | -0.251 |
assic | -0.244 |
yden | -0.218 |
IDES | -0.218 |
wana | -0.216 |
Token | that |
Token ID | 326 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
redes | +0.894 |
Shank | +0.886 |
Sew | +0.828 |
purge | +0.813 |
comprom | +0.797 |
Neg logit contributions | |
enburg | -0.772 |
assic | -0.753 |
yden | -0.669 |
IDES | -0.669 |
wana | -0.661 |
Token | all |
Token ID | 477 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
redes | +0.391 |
Shank | +0.388 |
Sew | +0.362 |
purge | +0.355 |
comprom | +0.348 |
Neg logit contributions | |
enburg | -0.342 |
assic | -0.333 |
yden | -0.297 |
IDES | -0.296 |
wana | -0.293 |
Token | senior |
Token ID | 4664 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
redes | +0.692 |
Shank | +0.686 |
Sew | +0.645 |
purge | +0.633 |
comprom | +0.618 |
Neg logit contributions | |
enburg | -0.550 |
assic | -0.539 |
yden | -0.476 |
IDES | -0.474 |
wana | -0.468 |
Token | civil |
Token ID | 3026 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
redes | +1.959 |
Shank | +1.955 |
Sew | +1.831 |
purge | +1.796 |
Sho | +1.745 |
Neg logit contributions | |
enburg | -1.715 |
assic | -1.692 |
yden | -1.510 |
IDES | -1.488 |
wana | -1.476 |
Token | servants |
Token ID | 17523 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
redes | +0.011 |
Shank | +0.011 |
Sew | +0.011 |
purge | +0.010 |
comprom | +0.010 |
Neg logit contributions | |
enburg | -0.012 |
assic | -0.012 |
yden | -0.010 |
IDES | -0.010 |
wana | -0.010 |
Token | be |
Token ID | 307 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
redes | +0.319 |
Shank | +0.316 |
Sew | +0.294 |
purge | +0.289 |
comprom | +0.282 |
Neg logit contributions | |
enburg | -0.312 |
assic | -0.305 |
yden | -0.274 |
IDES | -0.274 |
wana | -0.270 |
Token | bilingual |
Token ID | 48116 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
redes | +0.413 |
Shank | +0.409 |
Sew | +0.379 |
purge | +0.373 |
comprom | +0.364 |
Neg logit contributions | |
enburg | -0.435 |
assic | -0.425 |
yden | -0.383 |
IDES | -0.382 |
wana | -0.378 |
Token | by |
Token ID | 416 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
redes | +1.194 |
Shank | +1.184 |
Sew | +1.105 |
purge | +1.087 |
comprom | +1.060 |
Neg logit contributions | |
enburg | -1.098 |
assic | -1.075 |
yden | -0.959 |
IDES | -0.957 |
wana | -0.944 |
Token | around |
Token ID | 1088 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
redes | +0.265 |
Shank | +0.262 |
Sew | +0.242 |
purge | +0.238 |
comprom | +0.233 |
Neg logit contributions | |
enburg | -0.272 |
assic | -0.265 |
yden | -0.239 |
IDES | -0.238 |
wana | -0.236 |
Token | pesky |
Token ID | 49109 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
enburg | +0.016 |
assic | +0.016 |
yden | +0.014 |
IDES | +0.014 |
wana | +0.014 |
Neg logit contributions | |
redes | -0.017 |
Shank | -0.017 |
Sew | -0.016 |
purge | -0.016 |
comprom | -0.015 |
Token | � |
Token ID | 564 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
enburg | +0.132 |
assic | +0.128 |
yden | +0.117 |
IDES | +0.116 |
wana | +0.115 |
Neg logit contributions | |
redes | -0.111 |
Shank | -0.109 |
Sew | -0.100 |
purge | -0.098 |
comprom | -0.096 |
Token | � |
Token ID | 250 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
redes | +0.198 |
Shank | +0.197 |
Sew | +0.186 |
purge | +0.183 |
comprom | +0.180 |
Neg logit contributions | |
enburg | -0.112 |
assic | -0.108 |
yden | -0.093 |
IDES | -0.093 |
wana | -0.091 |
Token | c |
Token ID | 66 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
redes | +0.373 |
Shank | +0.369 |
Sew | +0.346 |
purge | +0.341 |
comprom | +0.334 |
Neg logit contributions | |
enburg | -0.269 |
assic | -0.261 |
yden | -0.230 |
IDES | -0.229 |
wana | -0.226 |
Token | annot |
Token ID | 34574 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
redes | +0.159 |
Shank | +0.157 |
Sew | +0.146 |
purge | +0.144 |
comprom | +0.141 |
Neg logit contributions | |
enburg | -0.130 |
assic | -0.126 |
yden | -0.112 |
IDES | -0.111 |
wana | -0.110 |
Token | be |
Token ID | 307 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
redes | +1.873 |
Shank | +1.855 |
Sew | +1.733 |
purge | +1.704 |
comprom | +1.667 |
Neg logit contributions | |
enburg | -1.697 |
assic | -1.659 |
yden | -1.479 |
IDES | -1.479 |
wana | -1.462 |
Token | destroyed |
Token ID | 6572 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
redes | +0.552 |
Shank | +0.546 |
Sew | +0.501 |
purge | +0.490 |
comprom | +0.478 |
Neg logit contributions | |
enburg | -0.706 |
assic | -0.690 |
yden | -0.629 |
IDES | -0.627 |
wana | -0.622 |
Token | � |
Token ID | 447 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
enburg | +0.493 |
assic | +0.479 |
yden | +0.430 |
IDES | +0.430 |
wana | +0.426 |
Neg logit contributions | |
redes | -0.501 |
Shank | -0.494 |
Sew | -0.458 |
purge | -0.449 |
comprom | -0.442 |
Token | � |
Token ID | 251 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
redes | +0.109 |
Shank | +0.108 |
Sew | +0.101 |
purge | +0.100 |
comprom | +0.098 |
Neg logit contributions | |
enburg | -0.085 |
assic | -0.083 |
yden | -0.073 |
IDES | -0.073 |
wana | -0.072 |
Token | effects |
Token ID | 3048 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
redes | +0.087 |
Shank | +0.086 |
Sew | +0.080 |
purge | +0.078 |
comprom | +0.077 |
Neg logit contributions | |
enburg | -0.083 |
assic | -0.081 |
yden | -0.072 |
IDES | -0.072 |
wana | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
redes | +0.226 |
Shank | +0.224 |
Sew | +0.210 |
purge | +0.206 |
comprom | +0.202 |
Neg logit contributions | |
enburg | -0.194 |
assic | -0.189 |
IDES | -0.168 |
yden | -0.168 |
wana | -0.166 |
Token | presentation |
Token ID | 10470 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
redes | +0.107 |
Shank | +0.106 |
Sew | +0.099 |
purge | +0.097 |
comprom | +0.096 |
Neg logit contributions | |
enburg | -0.086 |
assic | -0.083 |
yden | -0.074 |
IDES | -0.073 |
wana | -0.072 |
Token | to |
Token ID | 284 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
redes | +0.924 |
Shank | +0.917 |
Sew | +0.851 |
purge | +0.834 |
comprom | +0.815 |
Neg logit contributions | |
enburg | -0.932 |
assic | -0.912 |
IDES | -0.818 |
yden | -0.816 |
wana | -0.809 |
Token | the |
Token ID | 262 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
redes | +0.152 |
Shank | +0.150 |
Sew | +0.140 |
purge | +0.138 |
comprom | +0.135 |
Neg logit contributions | |
enburg | -0.131 |
assic | -0.127 |
yden | -0.113 |
IDES | -0.113 |
wana | -0.112 |
Token | NASA |
Token ID | 8884 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
redes | +0.244 |
Shank | +0.242 |
Sew | +0.224 |
purge | +0.219 |
comprom | +0.214 |
Neg logit contributions | |
enburg | -0.269 |
assic | -0.263 |
yden | -0.237 |
IDES | -0.237 |
wana | -0.235 |
Token | Advisory |
Token ID | 23943 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
redes | +0.126 |
Shank | +0.124 |
Sew | +0.115 |
purge | +0.112 |
comprom | +0.110 |
Neg logit contributions | |
enburg | -0.148 |
assic | -0.144 |
IDES | -0.131 |
yden | -0.131 |
wana | -0.130 |
Token | Council |
Token ID | 4281 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
redes | +1.461 |
Shank | +1.456 |
Sew | +1.336 |
purge | +1.291 |
Sho | +1.268 |
Neg logit contributions | |
enburg | -2.040 |
assic | -2.012 |
yden | -1.827 |
IDES | -1.822 |
wana | -1.802 |
Token | � |
Token ID | 447 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
redes | +0.819 |
Shank | +0.813 |
Sew | +0.756 |
purge | +0.741 |
comprom | +0.725 |
Neg logit contributions | |
enburg | -0.782 |
assic | -0.765 |
yden | -0.684 |
IDES | -0.683 |
wana | -0.676 |
Token | � |
Token ID | 247 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
redes | +0.081 |
Shank | +0.080 |
Sew | +0.075 |
purge | +0.074 |
comprom | +0.073 |
Neg logit contributions | |
enburg | -0.049 |
assic | -0.047 |
yden | -0.041 |
IDES | -0.041 |
wana | -0.040 |
Token | s |
Token ID | 82 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
redes | +0.016 |
Shank | +0.016 |
Sew | +0.015 |
purge | +0.014 |
comprom | +0.014 |
Neg logit contributions | |
enburg | -0.015 |
assic | -0.015 |
IDES | -0.013 |
yden | -0.013 |
wana | -0.013 |
Token | Human |
Token ID | 5524 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
redes | +0.103 |
Shank | +0.102 |
Sew | +0.095 |
purge | +0.093 |
comprom | +0.091 |
Neg logit contributions | |
enburg | -0.106 |
assic | -0.103 |
yden | -0.093 |
IDES | -0.093 |
wana | -0.092 |
Token | ven |
Token ID | 574 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
enburg | +0.251 |
assic | +0.245 |
yden | +0.220 |
IDES | +0.218 |
wana | +0.217 |
Neg logit contributions | |
redes | -0.253 |
Shank | -0.248 |
Sew | -0.230 |
purge | -0.227 |
comprom | -0.222 |
Token | Miner |
Token ID | 29295 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
enburg | +0.046 |
assic | +0.045 |
yden | +0.041 |
IDES | +0.040 |
wana | +0.040 |
Neg logit contributions | |
redes | -0.040 |
Shank | -0.039 |
Sew | -0.036 |
purge | -0.036 |
comprom | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
enburg | +0.473 |
assic | +0.461 |
IDES | +0.411 |
yden | +0.410 |
wana | +0.407 |
Neg logit contributions | |
redes | -0.539 |
Shank | -0.527 |
Sew | -0.489 |
purge | -0.484 |
comprom | -0.476 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Shank | +0.181 |
redes | +0.176 |
Sew | +0.170 |
purge | +0.165 |
Sho | +0.163 |
Neg logit contributions | |
enburg | -0.171 |
assic | -0.168 |
yden | -0.150 |
IDES | -0.149 |
wana | -0.148 |
Token | Fab |
Token ID | 43957 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
redes | +0.188 |
Shank | +0.187 |
Sew | +0.176 |
purge | +0.172 |
comprom | +0.169 |
Neg logit contributions | |
enburg | -0.145 |
assic | -0.141 |
yden | -0.125 |
IDES | -0.124 |
wana | -0.123 |
Token | ric |
Token ID | 1173 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
redes | +0.203 |
Shank | +0.201 |
Sew | +0.188 |
purge | +0.185 |
comprom | +0.182 |
Neg logit contributions | |
enburg | -0.158 |
assic | -0.154 |
yden | -0.136 |
IDES | -0.135 |
wana | -0.134 |
Token | ate |
Token ID | 378 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Shank | +2.386 |
redes | +2.385 |
Sew | +2.240 |
purge | +2.189 |
Sho | +2.151 |
Neg logit contributions | |
enburg | -2.045 |
assic | -1.989 |
yden | -1.776 |
IDES | -1.761 |
wana | -1.749 |
Token | vs |
Token ID | 3691 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
redes | +0.449 |
Shank | +0.444 |
Sew | +0.416 |
purge | +0.410 |
comprom | +0.403 |
Neg logit contributions | |
enburg | -0.319 |
assic | -0.310 |
yden | -0.272 |
IDES | -0.271 |
wana | -0.268 |
Token | Ever |
Token ID | 10776 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
redes | +0.420 |
Shank | +0.412 |
Sew | +0.379 |
purge | +0.375 |
comprom | +0.366 |
Neg logit contributions | |
enburg | -0.456 |
assic | -0.445 |
yden | -0.402 |
IDES | -0.401 |
wana | -0.397 |
Token | gl |
Token ID | 4743 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
redes | +0.574 |
Shank | +0.566 |
Sew | +0.522 |
purge | +0.512 |
comprom | +0.501 |
Neg logit contributions | |
enburg | -0.645 |
assic | -0.630 |
yden | -0.571 |
IDES | -0.568 |
wana | -0.564 |
Token | ove |
Token ID | 659 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
enburg | +0.133 |
assic | +0.129 |
yden | +0.114 |
IDES | +0.113 |
wana | +0.113 |
Neg logit contributions | |
redes | -0.167 |
Shank | -0.163 |
Sew | -0.152 |
purge | -0.150 |
comprom | -0.148 |