Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
roud | +0.907 |
rog | +0.778 |
utherland | +0.702 |
rite | +0.687 |
mia | +0.666 |
Neg logit contributions | |
unloaded | -0.600 |
Coy | -0.594 |
enegger | -0.592 |
withd | -0.554 |
thood | -0.547 |
Token | N |
Token ID | 399 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
roud | +0.919 |
rog | +0.789 |
utherland | +0.717 |
rite | +0.700 |
mia | +0.678 |
Neg logit contributions | |
unloaded | -0.582 |
Coy | -0.577 |
enegger | -0.571 |
withd | -0.536 |
perce | -0.527 |
Token | d |
Token ID | 67 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
roud | +1.066 |
rog | +0.898 |
utherland | +0.788 |
rite | +0.775 |
mia | +0.747 |
Neg logit contributions | |
unloaded | -0.939 |
enegger | -0.930 |
Coy | -0.929 |
withd | -0.880 |
thood | -0.868 |
Token | 4 |
Token ID | 19 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
roud | +1.380 |
rog | +1.148 |
utherland | +1.009 |
rite | +0.984 |
mia | +0.946 |
Neg logit contributions | |
unloaded | -1.338 |
Coy | -1.328 |
enegger | -1.324 |
withd | -1.256 |
thood | -1.243 |
Token | + |
Token ID | 10 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
roud | +1.445 |
rog | +1.233 |
utherland | +1.100 |
rite | +1.082 |
mia | +1.049 |
Neg logit contributions | |
unloaded | -1.023 |
enegger | -1.018 |
Coy | -1.012 |
withd | -0.950 |
thood | -0.945 |
Token | { |
Token ID | 1391 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
unloaded | +0.278 |
Coy | +0.275 |
enegger | +0.272 |
withd | +0.254 |
perce | +0.250 |
Neg logit contributions | |
roud | -0.493 |
rog | -0.426 |
utherland | -0.391 |
rite | -0.380 |
mia | -0.369 |
Token | ( |
Token ID | 7 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
roud | +5.082 |
rog | +4.345 |
utherland | +3.875 |
rite | +3.829 |
mia | +3.703 |
Neg logit contributions | |
unloaded | -3.610 |
enegger | -3.580 |
Coy | -3.566 |
withd | -3.344 |
thood | -3.330 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
roud | +1.304 |
rog | +1.076 |
utherland | +0.948 |
rite | +0.918 |
mia | +0.880 |
Neg logit contributions | |
unloaded | -1.326 |
Coy | -1.318 |
enegger | -1.314 |
withd | -1.243 |
thood | -1.235 |
Token | s |
Token ID | 82 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
unloaded | +0.034 |
Coy | +0.034 |
enegger | +0.034 |
withd | +0.032 |
perce | +0.031 |
Neg logit contributions | |
roud | -0.048 |
rog | -0.041 |
utherland | -0.037 |
rite | -0.036 |
mia | -0.035 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
roud | +0.742 |
rog | +0.592 |
utherland | +0.503 |
rite | +0.486 |
mia | +0.461 |
Neg logit contributions | |
unloaded | -1.019 |
Coy | -1.010 |
enegger | -1.006 |
withd | -0.964 |
thood | -0.957 |
Token | K |
Token ID | 509 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
roud | +1.859 |
rog | +1.595 |
utherland | +1.433 |
rite | +1.407 |
mia | +1.364 |
Neg logit contributions | |
unloaded | -1.231 |
enegger | -1.222 |
Coy | -1.217 |
withd | -1.139 |
thood | -1.131 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
roud | +0.366 |
rog | +0.316 |
utherland | +0.290 |
rite | +0.282 |
mia | +0.273 |
Neg logit contributions | |
unloaded | -0.214 |
Coy | -0.213 |
enegger | -0.208 |
perce | -0.193 |
withd | -0.193 |
Token | Q |
Token ID | 1195 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
roud | +1.139 |
rog | +0.981 |
utherland | +0.886 |
rite | +0.871 |
mia | +0.846 |
Neg logit contributions | |
unloaded | -0.695 |
enegger | -0.689 |
Coy | -0.687 |
withd | -0.640 |
thood | -0.635 |
Token | xf |
Token ID | 26152 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
roud | +1.283 |
rog | +1.095 |
utherland | +0.979 |
rite | +0.961 |
mia | +0.931 |
Neg logit contributions | |
unloaded | -0.928 |
Coy | -0.920 |
enegger | -0.918 |
withd | -0.863 |
thood | -0.851 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
roud | +0.033 |
rog | +0.027 |
utherland | +0.024 |
rite | +0.023 |
mia | +0.023 |
Neg logit contributions | |
unloaded | -0.031 |
Coy | -0.030 |
enegger | -0.030 |
withd | -0.029 |
thood | -0.028 |
Token | + |
Token ID | 10 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
roud | +0.453 |
rog | +0.381 |
utherland | +0.338 |
rite | +0.330 |
mia | +0.318 |
Neg logit contributions | |
unloaded | -0.393 |
Coy | -0.390 |
enegger | -0.388 |
withd | -0.367 |
thood | -0.363 |
Token | { |
Token ID | 1391 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
unloaded | +0.039 |
Coy | +0.039 |
enegger | +0.039 |
withd | +0.037 |
perce | +0.037 |
Neg logit contributions | |
roud | -0.038 |
rog | -0.031 |
utherland | -0.028 |
rite | -0.027 |
mia | -0.026 |
Token | ( |
Token ID | 7 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
roud | +4.834 |
rog | +4.154 |
utherland | +3.680 |
rite | +3.644 |
mia | +3.555 |
Neg logit contributions | |
unloaded | -3.311 |
Coy | -3.279 |
enegger | -3.275 |
withd | -3.085 |
perce | -3.061 |
Token | 113 |
Token ID | 16616 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
roud | +1.551 |
rog | +1.295 |
utherland | +1.151 |
rite | +1.119 |
mia | +1.076 |
Neg logit contributions | |
unloaded | -1.405 |
Coy | -1.396 |
enegger | -1.390 |
withd | -1.314 |
thood | -1.301 |
Token | s |
Token ID | 82 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
roud | +0.955 |
rog | +0.819 |
utherland | +0.745 |
rite | +0.727 |
mia | +0.705 |
Neg logit contributions | |
unloaded | -0.596 |
Coy | -0.591 |
enegger | -0.586 |
withd | -0.547 |
perce | -0.541 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
roud | +0.614 |
rog | +0.491 |
utherland | +0.423 |
rite | +0.407 |
mia | +0.387 |
Neg logit contributions | |
unloaded | -0.795 |
Coy | -0.790 |
enegger | -0.788 |
withd | -0.749 |
perce | -0.744 |
Token | R |
Token ID | 371 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
roud | +2.008 |
rog | +1.726 |
utherland | +1.550 |
rite | +1.526 |
mia | +1.482 |
Neg logit contributions | |
unloaded | -1.272 |
enegger | -1.267 |
Coy | -1.255 |
withd | -1.175 |
thood | -1.174 |
Token | also |
Token ID | 635 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
roud | +0.902 |
rog | +0.773 |
utherland | +0.695 |
rite | +0.681 |
mia | +0.660 |
Neg logit contributions | |
unloaded | -0.617 |
Coy | -0.613 |
enegger | -0.611 |
withd | -0.576 |
thood | -0.571 |
Token | said |
Token ID | 531 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
roud | +0.091 |
rog | +0.078 |
utherland | +0.071 |
rite | +0.069 |
mia | +0.067 |
Neg logit contributions | |
unloaded | -0.061 |
Coy | -0.061 |
enegger | -0.060 |
withd | -0.056 |
perce | -0.056 |
Token | Ross |
Token ID | 9847 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
roud | +0.793 |
rog | +0.680 |
utherland | +0.617 |
rite | +0.603 |
mia | +0.585 |
Neg logit contributions | |
unloaded | -0.509 |
Coy | -0.504 |
enegger | -0.500 |
withd | -0.467 |
perce | -0.462 |
Token | must |
Token ID | 1276 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
unloaded | +0.313 |
Coy | +0.310 |
enegger | +0.308 |
withd | +0.289 |
perce | +0.285 |
Neg logit contributions | |
roud | -0.454 |
rog | -0.388 |
utherland | -0.350 |
rite | -0.342 |
mia | -0.330 |
Token | rec |
Token ID | 664 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
roud | +0.142 |
rog | +0.123 |
utherland | +0.112 |
rite | +0.110 |
mia | +0.107 |
Neg logit contributions | |
unloaded | -0.078 |
Coy | -0.077 |
enegger | -0.077 |
withd | -0.071 |
thood | -0.070 |
Token | use |
Token ID | 1904 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
unloaded | +0.698 |
Coy | +0.690 |
enegger | +0.684 |
withd | +0.656 |
thood | +0.648 |
Neg logit contributions | |
roud | -0.581 |
rog | -0.467 |
utherland | -0.408 |
rite | -0.390 |
mia | -0.374 |
Token | himself |
Token ID | 2241 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
roud | +3.907 |
rog | +3.238 |
utherland | +2.779 |
rite | +2.688 |
Puppet | +2.604 |
Neg logit contributions | |
unloaded | -4.180 |
enegger | -4.156 |
Coy | -4.127 |
withd | -3.997 |
thood | -3.950 |
Token | from |
Token ID | 422 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
unloaded | +0.413 |
Coy | +0.408 |
enegger | +0.405 |
withd | +0.377 |
perce | +0.374 |
Neg logit contributions | |
roud | -0.678 |
rog | -0.582 |
utherland | -0.531 |
rite | -0.520 |
mia | -0.503 |
Token | all |
Token ID | 477 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
roud | +0.094 |
rog | +0.082 |
utherland | +0.074 |
rite | +0.073 |
mia | +0.071 |
Neg logit contributions | |
unloaded | -0.051 |
Coy | -0.050 |
enegger | -0.050 |
withd | -0.046 |
perce | -0.045 |
Token | Russia |
Token ID | 3284 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
unloaded | +0.322 |
Coy | +0.319 |
enegger | +0.314 |
withd | +0.294 |
perce | +0.293 |
Neg logit contributions | |
roud | -0.515 |
rog | -0.440 |
utherland | -0.401 |
rite | -0.392 |
mia | -0.382 |
Token | - |
Token ID | 12 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
unloaded | +0.515 |
Coy | +0.509 |
enegger | +0.499 |
perce | +0.473 |
withd | +0.471 |
Neg logit contributions | |
roud | -0.786 |
rog | -0.666 |
utherland | -0.610 |
rite | -0.595 |
mia | -0.579 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
roud | +0.334 |
rog | +0.288 |
utherland | +0.264 |
rite | +0.257 |
mia | +0.249 |
Neg logit contributions | |
unloaded | -0.195 |
Coy | -0.195 |
enegger | -0.191 |
perce | -0.176 |
thood | -0.176 |
Token | N |
Token ID | 399 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
roud | +1.088 |
rog | +0.935 |
utherland | +0.842 |
rite | +0.828 |
mia | +0.803 |
Neg logit contributions | |
unloaded | -0.689 |
enegger | -0.683 |
Coy | -0.681 |
withd | -0.636 |
thood | -0.631 |
Token | f |
Token ID | 69 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
roud | +0.976 |
rog | +0.819 |
utherland | +0.722 |
rite | +0.707 |
mia | +0.682 |
Neg logit contributions | |
unloaded | -0.870 |
Coy | -0.863 |
enegger | -0.861 |
withd | -0.816 |
thood | -0.804 |
Token | 5 |
Token ID | 20 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
roud | +0.386 |
rog | +0.322 |
utherland | +0.289 |
rite | +0.279 |
mia | +0.269 |
Neg logit contributions | |
unloaded | -0.347 |
Coy | -0.344 |
enegger | -0.341 |
withd | -0.323 |
thood | -0.320 |
Token | + |
Token ID | 10 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
roud | +0.571 |
rog | +0.469 |
utherland | +0.409 |
rite | +0.398 |
mia | +0.381 |
Neg logit contributions | |
unloaded | -0.617 |
Coy | -0.613 |
enegger | -0.612 |
withd | -0.582 |
thood | -0.576 |
Token | { |
Token ID | 1391 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
unloaded | +0.166 |
Coy | +0.165 |
enegger | +0.164 |
withd | +0.156 |
thood | +0.155 |
Neg logit contributions | |
roud | -0.149 |
rog | -0.122 |
utherland | -0.106 |
rite | -0.103 |
mia | -0.098 |
Token | ( |
Token ID | 7 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
roud | +4.599 |
rog | +3.964 |
utherland | +3.498 |
rite | +3.481 |
mia | +3.395 |
Neg logit contributions | |
unloaded | -3.096 |
enegger | -3.078 |
Coy | -3.042 |
withd | -3.018 |
proble | -2.952 |
Token | 43 |
Token ID | 3559 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
roud | +1.634 |
rog | +1.361 |
utherland | +1.207 |
rite | +1.174 |
mia | +1.128 |
Neg logit contributions | |
unloaded | -1.515 |
Coy | -1.505 |
enegger | -1.498 |
withd | -1.417 |
thood | -1.403 |
Token | s |
Token ID | 82 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
roud | +1.494 |
rog | +1.283 |
utherland | +1.165 |
rite | +1.138 |
mia | +1.103 |
Neg logit contributions | |
unloaded | -0.941 |
Coy | -0.932 |
enegger | -0.926 |
withd | -0.863 |
thood | -0.854 |
Token | )} |
Token ID | 38165 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
roud | +0.501 |
rog | +0.401 |
utherland | +0.347 |
rite | +0.333 |
mia | +0.318 |
Neg logit contributions | |
unloaded | -0.640 |
Coy | -0.637 |
enegger | -0.635 |
withd | -0.599 |
perce | -0.599 |
Token | K |
Token ID | 509 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
roud | +2.336 |
rog | +2.008 |
utherland | +1.797 |
rite | +1.777 |
mia | +1.727 |
Neg logit contributions | |
enegger | -1.474 |
unloaded | -1.474 |
Coy | -1.456 |
thood | -1.369 |
withd | -1.367 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
roud | +0.625 |
rog | +0.500 |
utherland | +0.428 |
rite | +0.413 |
mia | +0.392 |
Neg logit contributions | |
unloaded | -0.828 |
Coy | -0.822 |
enegger | -0.820 |
withd | -0.783 |
thood | -0.776 |
Token | 53 |
Token ID | 7192 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
roud | +1.734 |
rog | +1.439 |
utherland | +1.263 |
rite | +1.231 |
Puppet | +1.183 |
Neg logit contributions | |
unloaded | -1.682 |
enegger | -1.668 |
Coy | -1.663 |
withd | -1.578 |
thood | -1.570 |
Token | . |
Token ID | 13 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
roud | +0.502 |
rog | +0.433 |
utherland | +0.397 |
rite | +0.386 |
mia | +0.374 |
Neg logit contributions | |
unloaded | -0.296 |
Coy | -0.295 |
enegger | -0.290 |
perce | -0.268 |
withd | -0.267 |
Token | e |
Token ID | 304 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
roud | +1.383 |
rog | +1.190 |
utherland | +1.073 |
rite | +1.055 |
mia | +1.024 |
Neg logit contributions | |
unloaded | -0.857 |
enegger | -0.850 |
Coy | -0.847 |
withd | -0.790 |
thood | -0.785 |
Token | 6 |
Token ID | 21 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
roud | +1.128 |
rog | +0.932 |
utherland | +0.800 |
rite | +0.785 |
mia | +0.759 |
Neg logit contributions | |
unloaded | -1.158 |
enegger | -1.156 |
Coy | -1.146 |
withd | -1.102 |
thood | -1.087 |
Token | { |
Token ID | 1391 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
roud | +0.744 |
rog | +0.629 |
utherland | +0.560 |
rite | +0.548 |
mia | +0.530 |
Neg logit contributions | |
unloaded | -0.597 |
enegger | -0.592 |
Coy | -0.591 |
withd | -0.557 |
thood | -0.552 |
Token | ( |
Token ID | 7 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
roud | +4.293 |
rog | +3.689 |
utherland | +3.284 |
rite | +3.244 |
mia | +3.157 |
Neg logit contributions | |
unloaded | -2.904 |
Coy | -2.870 |
enegger | -2.859 |
withd | -2.682 |
thood | -2.665 |
Token | 8 |
Token ID | 23 |
Feature activation | -4.49e-04 |
Pos logit contributions | |
roud | +1.566 |
rog | +1.304 |
utherland | +1.157 |
rite | +1.124 |
mia | +1.080 |
Neg logit contributions | |
unloaded | -1.457 |
Coy | -1.448 |
enegger | -1.441 |
withd | -1.363 |
thood | -1.350 |
Token | s |
Token ID | 82 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
unloaded | +0.001 |
Coy | +0.001 |
enegger | +0.001 |
withd | +0.001 |
perce | +0.001 |
Neg logit contributions | |
roud | -0.001 |
rog | -0.001 |
utherland | -0.001 |
rite | -0.001 |
mia | -0.001 |
Token | )} |
Token ID | 38165 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
roud | +0.544 |
rog | +0.434 |
utherland | +0.368 |
rite | +0.356 |
mia | +0.337 |
Neg logit contributions | |
unloaded | -0.750 |
Coy | -0.744 |
enegger | -0.741 |
withd | -0.711 |
thood | -0.705 |
Token | R |
Token ID | 371 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
roud | +2.198 |
rog | +1.890 |
utherland | +1.695 |
rite | +1.670 |
mia | +1.623 |
Neg logit contributions | |
unloaded | -1.400 |
enegger | -1.399 |
Coy | -1.383 |
thood | -1.296 |
withd | -1.295 |
Token | is |
Token ID | 318 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
roud | +0.807 |
rog | +0.690 |
utherland | +0.623 |
rite | +0.610 |
mia | +0.592 |
Neg logit contributions | |
unloaded | -0.531 |
Coy | -0.528 |
enegger | -0.525 |
withd | -0.492 |
thood | -0.487 |
Token | perfectly |
Token ID | 7138 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
unloaded | +0.162 |
Coy | +0.160 |
enegger | +0.158 |
perce | +0.146 |
withd | +0.146 |
Neg logit contributions | |
roud | -0.297 |
rog | -0.258 |
utherland | -0.237 |
rite | -0.232 |
mia | -0.224 |
Token | positioned |
Token ID | 19378 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
unloaded | +0.955 |
Coy | +0.935 |
enegger | +0.907 |
perce | +0.872 |
withd | +0.850 |
Neg logit contributions | |
roud | -1.458 |
rog | -1.253 |
utherland | -1.140 |
rite | -1.122 |
mia | -1.075 |
Token | continue |
Token ID | 2555 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
roud | +0.032 |
rog | +0.027 |
utherland | +0.025 |
rite | +0.024 |
mia | +0.023 |
Neg logit contributions | |
unloaded | -0.020 |
Coy | -0.019 |
enegger | -0.019 |
withd | -0.018 |
perce | -0.018 |
Token | def |
Token ID | 825 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
roud | +0.247 |
rog | +0.212 |
utherland | +0.194 |
rite | +0.189 |
mia | +0.183 |
Neg logit contributions | |
unloaded | -0.152 |
Coy | -0.150 |
enegger | -0.149 |
withd | -0.140 |
perce | -0.138 |
Token | ying |
Token ID | 1112 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
roud | +1.319 |
rog | +1.137 |
utherland | +1.033 |
rite | +1.012 |
mia | +0.981 |
Neg logit contributions | |
unloaded | -0.795 |
Coy | -0.787 |
enegger | -0.783 |
withd | -0.730 |
thood | -0.720 |
Token | the |
Token ID | 262 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
roud | +4.211 |
rog | +3.608 |
utherland | +3.233 |
rite | +3.158 |
Puppet | +3.085 |
Neg logit contributions | |
enegger | -2.898 |
unloaded | -2.887 |
Coy | -2.843 |
withd | -2.738 |
thood | -2.697 |
Token | corporate |
Token ID | 6355 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
roud | +0.252 |
rog | +0.216 |
utherland | +0.195 |
rite | +0.191 |
mia | +0.185 |
Neg logit contributions | |
unloaded | -0.166 |
Coy | -0.165 |
enegger | -0.164 |
withd | -0.153 |
perce | -0.151 |
Token | interests |
Token ID | 5353 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
roud | +0.079 |
rog | +0.068 |
utherland | +0.061 |
rite | +0.060 |
mia | +0.058 |
Neg logit contributions | |
unloaded | -0.051 |
Coy | -0.050 |
enegger | -0.050 |
withd | -0.047 |
perce | -0.046 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
unloaded | +0.505 |
Coy | +0.496 |
enegger | +0.489 |
withd | +0.456 |
perce | +0.453 |
Neg logit contributions | |
roud | -0.914 |
rog | -0.792 |
utherland | -0.724 |
rite | -0.707 |
mia | -0.689 |
Token | the |
Token ID | 262 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
roud | +0.438 |
rog | +0.373 |
utherland | +0.335 |
rite | +0.327 |
mia | +0.316 |
Neg logit contributions | |
unloaded | -0.325 |
Coy | -0.322 |
enegger | -0.319 |
withd | -0.300 |
perce | -0.297 |
Token | s |
Token ID | 82 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
roud | +0.416 |
rog | +0.356 |
utherland | +0.323 |
rite | +0.316 |
mia | +0.305 |
Neg logit contributions | |
unloaded | -0.271 |
Coy | -0.269 |
enegger | -0.268 |
withd | -0.251 |
thood | -0.247 |
Token | )} |
Token ID | 38165 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
roud | +0.557 |
rog | +0.472 |
utherland | +0.423 |
rite | +0.413 |
mia | +0.398 |
Neg logit contributions | |
unloaded | -0.434 |
Coy | -0.431 |
enegger | -0.430 |
withd | -0.405 |
thood | -0.400 |
Token | Q |
Token ID | 1195 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
roud | +0.873 |
rog | +0.743 |
utherland | +0.670 |
rite | +0.652 |
mia | +0.633 |
Neg logit contributions | |
unloaded | -0.633 |
Coy | -0.628 |
enegger | -0.622 |
withd | -0.586 |
perce | -0.578 |
Token | xf |
Token ID | 26152 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
roud | +1.248 |
rog | +1.054 |
utherland | +0.939 |
rite | +0.917 |
mia | +0.885 |
Neg logit contributions | |
unloaded | -1.015 |
Coy | -1.006 |
enegger | -1.004 |
withd | -0.946 |
thood | -0.934 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
unloaded | +0.068 |
Coy | +0.067 |
enegger | +0.066 |
withd | +0.063 |
perce | +0.062 |
Neg logit contributions | |
roud | -0.075 |
rog | -0.063 |
utherland | -0.057 |
rite | -0.055 |
mia | -0.053 |
Token | { |
Token ID | 1391 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
roud | +0.346 |
rog | +0.292 |
utherland | +0.262 |
rite | +0.254 |
mia | +0.245 |
Neg logit contributions | |
unloaded | -0.283 |
Coy | -0.280 |
enegger | -0.278 |
withd | -0.263 |
perce | -0.260 |
Token | ( |
Token ID | 7 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
roud | +4.121 |
rog | +3.523 |
utherland | +3.140 |
rite | +3.094 |
mia | +2.994 |
Neg logit contributions | |
unloaded | -2.948 |
enegger | -2.923 |
Coy | -2.906 |
withd | -2.731 |
thood | -2.723 |
Token | 490 |
Token ID | 31503 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
roud | +0.806 |
rog | +0.662 |
utherland | +0.585 |
rite | +0.565 |
mia | +0.542 |
Neg logit contributions | |
unloaded | -0.841 |
Coy | -0.836 |
enegger | -0.832 |
withd | -0.790 |
thood | -0.783 |
Token | s |
Token ID | 82 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
roud | +1.250 |
rog | +1.058 |
utherland | +0.948 |
rite | +0.925 |
mia | +0.893 |
Neg logit contributions | |
unloaded | -0.978 |
Coy | -0.970 |
enegger | -0.966 |
withd | -0.910 |
thood | -0.899 |
Token | )} |
Token ID | 38165 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
roud | +0.476 |
rog | +0.382 |
utherland | +0.327 |
rite | +0.316 |
mia | +0.301 |
Neg logit contributions | |
unloaded | -0.619 |
Coy | -0.615 |
enegger | -0.613 |
withd | -0.585 |
thood | -0.580 |
Token | 51 |
Token ID | 6885 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
roud | +1.621 |
rog | +1.389 |
utherland | +1.247 |
rite | +1.223 |
mia | +1.185 |
Neg logit contributions | |
unloaded | -1.099 |
enegger | -1.090 |
Coy | -1.088 |
withd | -1.018 |
thood | -1.010 |
Token | } |
Token ID | 92 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
unloaded | +0.039 |
Coy | +0.038 |
enegger | +0.038 |
withd | +0.036 |
thood | +0.036 |
Neg logit contributions | |
roud | -0.050 |
rog | -0.042 |
utherland | -0.038 |
rite | -0.037 |
mia | -0.035 |
Token | -> |
Token ID | 4613 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
unloaded | +0.130 |
Coy | +0.129 |
enegger | +0.128 |
withd | +0.120 |
thood | +0.118 |
Neg logit contributions | |
roud | -0.204 |
rog | -0.175 |
utherland | -0.159 |
rite | -0.155 |
mia | -0.150 |
Token | " |
Token ID | 366 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
roud | +0.356 |
rog | +0.309 |
utherland | +0.282 |
rite | +0.277 |
mia | +0.270 |
Neg logit contributions | |
unloaded | -0.180 |
enegger | -0.178 |
Coy | -0.178 |
withd | -0.164 |
thood | -0.162 |
Token | E |
Token ID | 36 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
roud | +0.564 |
rog | +0.472 |
utherland | +0.420 |
rite | +0.409 |
mia | +0.394 |
Neg logit contributions | |
unloaded | -0.494 |
Coy | -0.491 |
enegger | -0.488 |
withd | -0.462 |
thood | -0.457 |
Token | ", |
Token ID | 1600 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
roud | +0.603 |
rog | +0.528 |
utherland | +0.481 |
rite | +0.475 |
mia | +0.462 |
Neg logit contributions | |
unloaded | -0.285 |
enegger | -0.280 |
Coy | -0.279 |
withd | -0.258 |
thood | -0.254 |
Token | { |
Token ID | 1391 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
roud | +0.450 |
rog | +0.368 |
utherland | +0.320 |
rite | +0.311 |
mia | +0.297 |
Neg logit contributions | |
unloaded | -0.500 |
Coy | -0.496 |
enegger | -0.495 |
withd | -0.471 |
thood | -0.467 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
roud | +3.351 |
rog | +2.753 |
utherland | +2.365 |
rite | +2.349 |
mia | +2.228 |
Neg logit contributions | |
unloaded | -3.712 |
enegger | -3.682 |
Coy | -3.666 |
withd | -3.512 |
perce | -3.455 |
Token | , |
Token ID | 11 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
roud | +0.560 |
rog | +0.485 |
utherland | +0.446 |
rite | +0.435 |
mia | +0.422 |
Neg logit contributions | |
unloaded | -0.295 |
Coy | -0.295 |
enegger | -0.291 |
perce | -0.265 |
thood | -0.265 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
roud | +0.762 |
rog | +0.650 |
utherland | +0.588 |
rite | +0.574 |
mia | +0.555 |
Neg logit contributions | |
unloaded | -0.528 |
Coy | -0.525 |
enegger | -0.520 |
withd | -0.487 |
perce | -0.482 |
Token | } |
Token ID | 92 |
Feature activation | +6.59e-03 |
Pos logit contributions | |
roud | +0.108 |
rog | +0.089 |
utherland | +0.080 |
rite | +0.077 |
mia | +0.074 |
Neg logit contributions | |
Coy | -0.108 |
unloaded | -0.107 |
enegger | -0.106 |
perce | -0.100 |
thood | -0.100 |
Token | -> |
Token ID | 4613 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
roud | +0.023 |
rog | +0.020 |
utherland | +0.019 |
rite | +0.018 |
mia | +0.018 |
Neg logit contributions | |
unloaded | -0.011 |
Coy | -0.010 |
enegger | -0.010 |
withd | -0.010 |
thood | -0.009 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
roud | +0.205 |
rog | +0.164 |
utherland | +0.142 |
rite | +0.137 |
mia | +0.130 |
Neg logit contributions | |
unloaded | -0.260 |
Coy | -0.259 |
enegger | -0.258 |
thood | -0.244 |
perce | -0.244 |
Token | Q |
Token ID | 1195 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
roud | +2.001 |
rog | +1.718 |
utherland | +1.536 |
rite | +1.519 |
Puppet | +1.478 |
Neg logit contributions | |
enegger | -1.281 |
unloaded | -1.279 |
Coy | -1.262 |
thood | -1.191 |
withd | -1.188 |
Token | f |
Token ID | 69 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
roud | +0.441 |
rog | +0.375 |
utherland | +0.338 |
rite | +0.330 |
mia | +0.319 |
Neg logit contributions | |
unloaded | -0.321 |
Coy | -0.318 |
enegger | -0.317 |
withd | -0.297 |
thood | -0.294 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
roud | +0.178 |
rog | +0.149 |
utherland | +0.135 |
rite | +0.131 |
mia | +0.126 |
Neg logit contributions | |
unloaded | -0.141 |
Coy | -0.140 |
enegger | -0.139 |
withd | -0.130 |
thood | -0.129 |
Token | + |
Token ID | 10 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
roud | +0.094 |
rog | +0.077 |
utherland | +0.069 |
rite | +0.066 |
foundation | +0.063 |
Neg logit contributions | |
unloaded | -0.098 |
Coy | -0.098 |
enegger | -0.097 |
perce | -0.091 |
thood | -0.091 |
Token | { |
Token ID | 1391 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
unloaded | +0.596 |
Coy | +0.592 |
enegger | +0.589 |
withd | +0.561 |
thood | +0.556 |
Neg logit contributions | |
roud | -0.534 |
rog | -0.436 |
utherland | -0.381 |
rite | -0.368 |
mia | -0.352 |
Token | ( |
Token ID | 7 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
roud | +4.229 |
rog | +3.650 |
utherland | +3.225 |
rite | +3.208 |
mia | +3.125 |
Neg logit contributions | |
unloaded | -2.827 |
enegger | -2.807 |
Coy | -2.775 |
withd | -2.753 |
proble | -2.687 |
Token | 19 |
Token ID | 1129 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
roud | +1.377 |
rog | +1.147 |
utherland | +1.017 |
rite | +0.989 |
mia | +0.950 |
Neg logit contributions | |
unloaded | -1.280 |
Coy | -1.273 |
enegger | -1.267 |
withd | -1.197 |
thood | -1.186 |
Token | s |
Token ID | 82 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
roud | +0.095 |
rog | +0.082 |
utherland | +0.074 |
rite | +0.072 |
mia | +0.070 |
Neg logit contributions | |
unloaded | -0.062 |
Coy | -0.062 |
enegger | -0.061 |
withd | -0.058 |
thood | -0.057 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
roud | +0.771 |
rog | +0.617 |
utherland | +0.531 |
rite | +0.511 |
mia | +0.486 |
Neg logit contributions | |
unloaded | -1.002 |
Coy | -0.997 |
enegger | -0.994 |
withd | -0.943 |
thood | -0.939 |
Token | 39 |
Token ID | 5014 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
roud | +1.802 |
rog | +1.487 |
utherland | +1.297 |
rite | +1.278 |
mia | +1.239 |
Neg logit contributions | |
unloaded | -1.766 |
enegger | -1.740 |
Coy | -1.733 |
withd | -1.667 |
thood | -1.642 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
roud | +0.473 |
rog | +0.379 |
utherland | +0.329 |
rite | +0.317 |
mia | +0.301 |
Neg logit contributions | |
unloaded | -0.593 |
Coy | -0.590 |
enegger | -0.588 |
perce | -0.555 |
thood | -0.554 |
Token | 54 |
Token ID | 7175 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
roud | +1.970 |
rog | +1.674 |
utherland | +1.491 |
rite | +1.463 |
mia | +1.418 |
Neg logit contributions | |
unloaded | -1.480 |
enegger | -1.470 |
Coy | -1.459 |
withd | -1.375 |
thood | -1.372 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
roud | +0.793 |
rog | +0.684 |
utherland | +0.628 |
rite | +0.611 |
mia | +0.591 |
Neg logit contributions | |
unloaded | -0.462 |
Coy | -0.461 |
enegger | -0.450 |
perce | -0.416 |
thood | -0.414 |
Token | f |
Token ID | 277 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
roud | +1.155 |
rog | +0.994 |
utherland | +0.898 |
rite | +0.882 |
mia | +0.856 |
Neg logit contributions | |
unloaded | -0.712 |
enegger | -0.706 |
Coy | -0.704 |
withd | -0.656 |
thood | -0.651 |
Token | 4 |
Token ID | 19 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
roud | +0.678 |
rog | +0.566 |
utherland | +0.504 |
rite | +0.490 |
mia | +0.471 |
Neg logit contributions | |
unloaded | -0.615 |
Coy | -0.610 |
enegger | -0.606 |
withd | -0.574 |
thood | -0.569 |
Token | { |
Token ID | 1391 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
roud | +1.512 |
rog | +1.253 |
utherland | +1.088 |
rite | +1.068 |
mia | +1.030 |
Neg logit contributions | |
unloaded | -1.507 |
enegger | -1.505 |
Coy | -1.495 |
withd | -1.420 |
thood | -1.414 |
Token | ( |
Token ID | 7 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
roud | +4.284 |
rog | +3.699 |
utherland | +3.301 |
rite | +3.258 |
mia | +3.171 |
Neg logit contributions | |
unloaded | -2.767 |
enegger | -2.739 |
Coy | -2.726 |
withd | -2.636 |
proble | -2.565 |
Token | 100 |
Token ID | 3064 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
roud | +1.605 |
rog | +1.340 |
utherland | +1.189 |
rite | +1.157 |
mia | +1.112 |
Neg logit contributions | |
unloaded | -1.464 |
Coy | -1.455 |
enegger | -1.448 |
withd | -1.369 |
thood | -1.356 |
Token | s |
Token ID | 82 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
unloaded | +0.036 |
Coy | +0.036 |
enegger | +0.035 |
perce | +0.033 |
withd | +0.032 |
Neg logit contributions | |
roud | -0.060 |
rog | -0.052 |
utherland | -0.047 |
rite | -0.046 |
mia | -0.045 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
roud | +0.502 |
rog | +0.402 |
utherland | +0.347 |
rite | +0.334 |
mia | +0.318 |
Neg logit contributions | |
unloaded | -0.639 |
Coy | -0.636 |
enegger | -0.634 |
withd | -0.599 |
perce | -0.599 |
Token | a |
Token ID | 257 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
roud | +2.055 |
rog | +1.767 |
utherland | +1.585 |
rite | +1.562 |
mia | +1.518 |
Neg logit contributions | |
unloaded | -1.314 |
enegger | -1.311 |
Coy | -1.298 |
withd | -1.216 |
thood | -1.214 |
Token | . |
Token ID | 13 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
roud | +0.125 |
rog | +0.108 |
utherland | +0.099 |
rite | +0.096 |
mia | +0.093 |
Neg logit contributions | |
unloaded | -0.074 |
Coy | -0.074 |
enegger | -0.073 |
perce | -0.067 |
thood | -0.067 |
Token | R |
Token ID | 371 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
roud | +1.174 |
rog | +1.009 |
utherland | +0.908 |
rite | +0.894 |
mia | +0.868 |
Neg logit contributions | |
unloaded | -0.740 |
enegger | -0.736 |
Coy | -0.732 |
withd | -0.684 |
thood | -0.680 |
Token | xd |
Token ID | 24954 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
roud | +0.540 |
rog | +0.458 |
utherland | +0.410 |
rite | +0.401 |
mia | +0.388 |
Neg logit contributions | |
unloaded | -0.411 |
Coy | -0.408 |
enegger | -0.406 |
withd | -0.383 |
thood | -0.378 |
Token | 8 |
Token ID | 23 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
unloaded | +0.335 |
Coy | +0.333 |
enegger | +0.328 |
withd | +0.312 |
perce | +0.310 |
Neg logit contributions | |
roud | -0.356 |
rog | -0.295 |
utherland | -0.264 |
rite | -0.255 |
Puppet | -0.244 |
Token | + |
Token ID | 10 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
roud | +0.091 |
rog | +0.075 |
utherland | +0.067 |
rite | +0.064 |
mia | +0.061 |
Neg logit contributions | |
unloaded | -0.098 |
Coy | -0.098 |
enegger | -0.096 |
withd | -0.092 |
perce | -0.091 |
Token | { |
Token ID | 1391 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
unloaded | +0.745 |
Coy | +0.739 |
enegger | +0.737 |
withd | +0.702 |
thood | +0.695 |
Neg logit contributions | |
roud | -0.661 |
rog | -0.540 |
utherland | -0.471 |
rite | -0.456 |
mia | -0.436 |
Token | ( |
Token ID | 7 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
roud | +4.207 |
rog | +3.632 |
utherland | +3.192 |
rite | +3.188 |
mia | +3.109 |
Neg logit contributions | |
unloaded | -2.845 |
enegger | -2.828 |
Coy | -2.789 |
withd | -2.786 |
proble | -2.723 |
Token | 71 |
Token ID | 4869 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
roud | +1.471 |
rog | +1.224 |
utherland | +1.084 |
rite | +1.054 |
mia | +1.013 |
Neg logit contributions | |
unloaded | -1.387 |
Coy | -1.378 |
enegger | -1.372 |
withd | -1.299 |
thood | -1.286 |
Token | s |
Token ID | 82 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
roud | +0.023 |
rog | +0.019 |
utherland | +0.018 |
rite | +0.017 |
Puppet | +0.017 |
Neg logit contributions | |
unloaded | -0.013 |
Coy | -0.013 |
enegger | -0.013 |
perce | -0.012 |
thood | -0.012 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
roud | +0.403 |
rog | +0.323 |
utherland | +0.280 |
rite | +0.269 |
mia | +0.256 |
Neg logit contributions | |
unloaded | -0.509 |
Coy | -0.506 |
enegger | -0.504 |
thood | -0.476 |
withd | -0.476 |
Token | Q |
Token ID | 1195 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
roud | +2.149 |
rog | +1.845 |
utherland | +1.643 |
rite | +1.632 |
Puppet | +1.587 |
Neg logit contributions | |
enegger | -1.387 |
unloaded | -1.381 |
Coy | -1.364 |
thood | -1.291 |
withd | -1.287 |
Token | "] |
Token ID | 8973 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
unloaded | +0.020 |
enegger | +0.020 |
Coy | +0.020 |
withd | +0.018 |
thood | +0.018 |
Neg logit contributions | |
roud | -0.032 |
rog | -0.028 |
utherland | -0.025 |
rite | -0.025 |
mia | -0.024 |
Token | 1 |
Token ID | 352 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
roud | +1.560 |
rog | +1.319 |
utherland | +1.180 |
rite | +1.151 |
mia | +1.111 |
Neg logit contributions | |
unloaded | -1.246 |
Coy | -1.236 |
enegger | -1.231 |
withd | -1.160 |
thood | -1.146 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
roud | +0.279 |
rog | +0.240 |
utherland | +0.218 |
rite | +0.213 |
mia | +0.207 |
Neg logit contributions | |
unloaded | -0.171 |
Coy | -0.170 |
enegger | -0.169 |
withd | -0.157 |
thood | -0.155 |
Token | d |
Token ID | 288 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
roud | +0.478 |
rog | +0.414 |
utherland | +0.379 |
rite | +0.370 |
mia | +0.360 |
Neg logit contributions | |
unloaded | -0.261 |
Coy | -0.258 |
enegger | -0.255 |
withd | -0.238 |
perce | -0.234 |
Token | 4 |
Token ID | 19 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
roud | +0.432 |
rog | +0.359 |
utherland | +0.312 |
rite | +0.305 |
mia | +0.293 |
Neg logit contributions | |
unloaded | -0.435 |
enegger | -0.434 |
Coy | -0.433 |
withd | -0.412 |
perce | -0.404 |
Token | { |
Token ID | 1391 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
roud | +0.281 |
rog | +0.238 |
utherland | +0.212 |
rite | +0.208 |
mia | +0.200 |
Neg logit contributions | |
unloaded | -0.223 |
Coy | -0.221 |
enegger | -0.221 |
withd | -0.208 |
thood | -0.205 |
Token | ( |
Token ID | 7 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
roud | +4.189 |
rog | +3.587 |
utherland | +3.197 |
rite | +3.170 |
mia | +3.074 |
Neg logit contributions | |
unloaded | -2.835 |
enegger | -2.807 |
Coy | -2.798 |
withd | -2.628 |
perce | -2.599 |
Token | 0 |
Token ID | 15 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
roud | +0.393 |
rog | +0.327 |
utherland | +0.291 |
rite | +0.282 |
mia | +0.270 |
Neg logit contributions | |
unloaded | -0.365 |
Coy | -0.364 |
enegger | -0.362 |
withd | -0.340 |
thood | -0.339 |
Token | s |
Token ID | 82 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
unloaded | +0.795 |
Coy | +0.793 |
enegger | +0.786 |
withd | +0.736 |
perce | +0.723 |
Neg logit contributions | |
roud | -1.272 |
rog | -1.092 |
utherland | -0.993 |
rite | -0.971 |
mia | -0.939 |
Token | )} |
Token ID | 38165 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
unloaded | +0.126 |
Coy | +0.125 |
enegger | +0.125 |
withd | +0.120 |
thood | +0.118 |
Neg logit contributions | |
roud | -0.097 |
rog | -0.078 |
utherland | -0.067 |
rite | -0.064 |
mia | -0.061 |
Token | N |
Token ID | 399 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
roud | +1.186 |
rog | +1.010 |
utherland | +0.906 |
rite | +0.887 |
mia | +0.857 |
Neg logit contributions | |
unloaded | -0.869 |
Coy | -0.861 |
enegger | -0.859 |
withd | -0.807 |
thood | -0.797 |
Token | s |
Token ID | 82 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
roud | +0.409 |
rog | +0.351 |
utherland | +0.317 |
rite | +0.311 |
mia | +0.301 |
Neg logit contributions | |
unloaded | -0.264 |
Coy | -0.262 |
enegger | -0.261 |
withd | -0.244 |
thood | -0.240 |
Token | request |
Token ID | 2581 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
roud | +0.191 |
rog | +0.163 |
utherland | +0.147 |
rite | +0.144 |
mia | +0.139 |
Neg logit contributions | |
unloaded | -0.131 |
Coy | -0.130 |
enegger | -0.130 |
withd | -0.122 |
thood | -0.120 |
Token | that |
Token ID | 326 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
roud | +0.051 |
rog | +0.044 |
utherland | +0.040 |
rite | +0.039 |
mia | +0.038 |
Neg logit contributions | |
unloaded | -0.030 |
Coy | -0.030 |
enegger | -0.030 |
withd | -0.028 |
thood | -0.028 |
Token | they |
Token ID | 484 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
unloaded | +0.137 |
Coy | +0.135 |
enegger | +0.134 |
withd | +0.126 |
perce | +0.123 |
Neg logit contributions | |
roud | -0.219 |
rog | -0.188 |
utherland | -0.171 |
rite | -0.167 |
mia | -0.162 |
Token | rec |
Token ID | 664 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
unloaded | +0.207 |
Coy | +0.204 |
enegger | +0.203 |
withd | +0.189 |
thood | +0.186 |
Neg logit contributions | |
roud | -0.365 |
rog | -0.316 |
utherland | -0.288 |
rite | -0.282 |
mia | -0.274 |
Token | use |
Token ID | 1904 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
unloaded | +0.446 |
Coy | +0.442 |
enegger | +0.439 |
withd | +0.423 |
thood | +0.419 |
Neg logit contributions | |
roud | -0.317 |
rog | -0.249 |
utherland | -0.213 |
rite | -0.203 |
mia | -0.194 |
Token | themselves |
Token ID | 2405 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
roud | +3.680 |
rog | +3.087 |
utherland | +2.706 |
rite | +2.640 |
Puppet | +2.552 |
Neg logit contributions | |
unloaded | -3.289 |
enegger | -3.280 |
Coy | -3.248 |
withd | -3.111 |
thood | -3.093 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
unloaded | +0.082 |
Coy | +0.082 |
enegger | +0.081 |
withd | +0.076 |
thood | +0.075 |
Neg logit contributions | |
roud | -0.128 |
rog | -0.110 |
utherland | -0.100 |
rite | -0.098 |
mia | -0.095 |
Token | giving |
Token ID | 3501 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
unloaded | +0.183 |
Coy | +0.181 |
enegger | +0.179 |
withd | +0.167 |
perce | +0.164 |
Neg logit contributions | |
roud | -0.344 |
rog | -0.298 |
utherland | -0.272 |
rite | -0.267 |
mia | -0.259 |
Token | rise |
Token ID | 4485 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
unloaded | +0.366 |
Coy | +0.365 |
enegger | +0.356 |
withd | +0.335 |
perce | +0.333 |
Neg logit contributions | |
roud | -0.526 |
rog | -0.450 |
utherland | -0.407 |
rite | -0.398 |
mia | -0.384 |
Token | to |
Token ID | 284 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
unloaded | +0.097 |
Coy | +0.097 |
enegger | +0.095 |
perce | +0.088 |
thood | +0.088 |
Neg logit contributions | |
roud | -0.164 |
rog | -0.141 |
utherland | -0.129 |
rite | -0.126 |
mia | -0.122 |
Token | camp |
Token ID | 1413 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
roud | +0.389 |
rog | +0.335 |
utherland | +0.304 |
rite | +0.297 |
mia | +0.288 |
Neg logit contributions | |
unloaded | -0.242 |
Coy | -0.240 |
enegger | -0.238 |
withd | -0.222 |
perce | -0.220 |
Token | lodge |
Token ID | 35362 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
roud | +0.071 |
rog | +0.062 |
utherland | +0.056 |
rite | +0.055 |
mia | +0.053 |
Neg logit contributions | |
unloaded | -0.042 |
Coy | -0.042 |
enegger | -0.041 |
withd | -0.038 |
perce | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
roud | +1.316 |
rog | +1.134 |
utherland | +1.029 |
rite | +1.008 |
mia | +0.978 |
Neg logit contributions | |
unloaded | -0.798 |
Coy | -0.790 |
enegger | -0.788 |
withd | -0.734 |
thood | -0.724 |
Token |
|
Token ID | 198 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
roud | +0.531 |
rog | +0.451 |
utherland | +0.405 |
rite | +0.395 |
mia | +0.382 |
Neg logit contributions | |
Coy | -0.404 |
unloaded | -0.401 |
enegger | -0.397 |
withd | -0.370 |
perce | -0.369 |
Token |
|
Token ID | 198 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
roud | +0.923 |
rog | +0.780 |
utherland | +0.703 |
rite | +0.681 |
mia | +0.657 |
Neg logit contributions | |
unloaded | -0.737 |
Coy | -0.734 |
enegger | -0.725 |
perce | -0.676 |
thood | -0.676 |
Token | 「 |
Token ID | 13697 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
roud | +1.056 |
rog | +0.887 |
utherland | +0.800 |
rite | +0.774 |
mia | +0.745 |
Neg logit contributions | |
Coy | -0.859 |
unloaded | -0.858 |
enegger | -0.847 |
thood | -0.796 |
withd | -0.790 |
Token | Ste |
Token ID | 7447 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
roud | +3.604 |
rog | +3.012 |
utherland | +2.653 |
rite | +2.599 |
mia | +2.505 |
Neg logit contributions | |
unloaded | -3.336 |
enegger | -3.300 |
Coy | -3.284 |
withd | -3.138 |
perce | -3.083 |
Token | lla |
Token ID | 8466 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
unloaded | +0.408 |
enegger | +0.401 |
Coy | +0.398 |
perce | +0.377 |
thood | +0.376 |
Neg logit contributions | |
roud | -0.429 |
rog | -0.354 |
utherland | -0.320 |
rite | -0.303 |
Puppet | -0.296 |
Token | - |
Token ID | 12 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
unloaded | +0.718 |
Coy | +0.711 |
enegger | +0.701 |
withd | +0.656 |
perce | +0.654 |
Neg logit contributions | |
roud | -1.190 |
rog | -1.026 |
utherland | -0.933 |
rite | -0.910 |
mia | -0.880 |
Token | san |
Token ID | 12807 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
roud | +0.061 |
rog | +0.050 |
utherland | +0.045 |
rite | +0.043 |
mia | +0.041 |
Neg logit contributions | |
unloaded | -0.059 |
Coy | -0.059 |
enegger | -0.059 |
withd | -0.056 |
thood | -0.055 |
Token | collapsed |
Token ID | 14707 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
roud | +1.183 |
rog | +1.018 |
utherland | +0.922 |
rite | +0.903 |
mia | +0.877 |
Neg logit contributions | |
unloaded | -0.733 |
Coy | -0.726 |
enegger | -0.723 |
withd | -0.675 |
thood | -0.666 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
roud | +0.439 |
rog | +0.351 |
utherland | +0.304 |
rite | +0.292 |
mia | +0.278 |
Neg logit contributions | |
unloaded | -0.560 |
Coy | -0.557 |
enegger | -0.555 |
withd | -0.526 |
perce | -0.524 |
Token | 55 |
Token ID | 5996 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
roud | +1.747 |
rog | +1.461 |
utherland | +1.290 |
rite | +1.260 |
mia | +1.212 |
Neg logit contributions | |
unloaded | -1.589 |
Coy | -1.574 |
enegger | -1.573 |
withd | -1.488 |
thood | -1.475 |
Token | . |
Token ID | 13 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
unloaded | +0.035 |
Coy | +0.035 |
enegger | +0.034 |
perce | +0.031 |
withd | +0.031 |
Neg logit contributions | |
roud | -0.060 |
rog | -0.052 |
utherland | -0.047 |
rite | -0.046 |
mia | -0.045 |
Token | Ra |
Token ID | 7567 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
roud | +1.109 |
rog | +0.953 |
utherland | +0.859 |
rite | +0.844 |
mia | +0.819 |
Neg logit contributions | |
unloaded | -0.698 |
enegger | -0.693 |
Coy | -0.691 |
withd | -0.644 |
thood | -0.640 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
roud | +1.541 |
rog | +1.290 |
utherland | +1.106 |
rite | +1.089 |
mia | +1.059 |
Neg logit contributions | |
enegger | -1.508 |
unloaded | -1.505 |
Coy | -1.503 |
withd | -1.433 |
thood | -1.409 |
Token | { |
Token ID | 1391 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
roud | +0.644 |
rog | +0.533 |
utherland | +0.467 |
rite | +0.455 |
mia | +0.438 |
Neg logit contributions | |
unloaded | -0.646 |
Coy | -0.641 |
enegger | -0.641 |
withd | -0.608 |
thood | -0.603 |
Token | ( |
Token ID | 7 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
roud | +4.199 |
rog | +3.621 |
utherland | +3.230 |
rite | +3.192 |
mia | +3.108 |
Neg logit contributions | |
unloaded | -2.715 |
enegger | -2.688 |
Coy | -2.671 |
withd | -2.587 |
proble | -2.517 |
Token | 55 |
Token ID | 2816 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
roud | +1.346 |
rog | +1.118 |
utherland | +0.992 |
rite | +0.963 |
mia | +0.924 |
Neg logit contributions | |
unloaded | -1.275 |
Coy | -1.268 |
enegger | -1.262 |
withd | -1.192 |
thood | -1.183 |
Token | s |
Token ID | 82 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
roud | +0.439 |
rog | +0.377 |
utherland | +0.341 |
rite | +0.334 |
mia | +0.323 |
Neg logit contributions | |
unloaded | -0.284 |
Coy | -0.281 |
enegger | -0.280 |
withd | -0.262 |
thood | -0.259 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
roud | +0.256 |
rog | +0.205 |
utherland | +0.177 |
rite | +0.171 |
mia | +0.162 |
Neg logit contributions | |
unloaded | -0.322 |
Coy | -0.320 |
enegger | -0.319 |
perce | -0.301 |
withd | -0.301 |
Token | Ra |
Token ID | 7567 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
roud | +2.003 |
rog | +1.719 |
utherland | +1.536 |
rite | +1.516 |
mia | +1.470 |
Neg logit contributions | |
enegger | -1.328 |
unloaded | -1.328 |
Coy | -1.312 |
thood | -1.234 |
withd | -1.232 |
Token | s |
Token ID | 82 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
roud | +0.955 |
rog | +0.819 |
utherland | +0.745 |
rite | +0.727 |
mia | +0.705 |
Neg logit contributions | |
unloaded | -0.596 |
Coy | -0.591 |
enegger | -0.586 |
withd | -0.547 |
perce | -0.541 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
roud | +0.614 |
rog | +0.491 |
utherland | +0.423 |
rite | +0.407 |
mia | +0.387 |
Neg logit contributions | |
unloaded | -0.795 |
Coy | -0.790 |
enegger | -0.788 |
withd | -0.749 |
perce | -0.744 |
Token | R |
Token ID | 371 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
roud | +2.008 |
rog | +1.726 |
utherland | +1.550 |
rite | +1.526 |
mia | +1.482 |
Neg logit contributions | |
unloaded | -1.272 |
enegger | -1.267 |
Coy | -1.255 |
withd | -1.175 |
thood | -1.174 |
Token | xf |
Token ID | 26152 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
roud | +0.504 |
rog | +0.429 |
utherland | +0.383 |
rite | +0.375 |
mia | +0.363 |
Neg logit contributions | |
unloaded | -0.379 |
Coy | -0.376 |
enegger | -0.375 |
withd | -0.352 |
thood | -0.348 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
roud | +0.288 |
rog | +0.240 |
utherland | +0.213 |
rite | +0.207 |
mia | +0.199 |
Neg logit contributions | |
unloaded | -0.266 |
Coy | -0.264 |
enegger | -0.263 |
withd | -0.249 |
thood | -0.246 |
Token | { |
Token ID | 1391 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
roud | +0.428 |
rog | +0.353 |
utherland | +0.310 |
rite | +0.301 |
mia | +0.288 |
Neg logit contributions | |
unloaded | -0.448 |
Coy | -0.446 |
enegger | -0.443 |
withd | -0.422 |
perce | -0.417 |
Token | ( |
Token ID | 7 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
roud | +4.093 |
rog | +3.506 |
utherland | +3.142 |
rite | +3.089 |
mia | +3.007 |
Neg logit contributions | |
unloaded | -2.723 |
Coy | -2.696 |
enegger | -2.685 |
withd | -2.522 |
thood | -2.507 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
roud | +1.421 |
rog | +1.182 |
utherland | +1.047 |
rite | +1.017 |
mia | +0.977 |
Neg logit contributions | |
unloaded | -1.335 |
Coy | -1.328 |
enegger | -1.322 |
withd | -1.249 |
thood | -1.239 |
Token | s |
Token ID | 82 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
roud | +0.934 |
rog | +0.802 |
utherland | +0.725 |
rite | +0.710 |
mia | +0.688 |
Neg logit contributions | |
unloaded | -0.606 |
Coy | -0.600 |
enegger | -0.598 |
withd | -0.559 |
thood | -0.552 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
roud | +0.625 |
rog | +0.500 |
utherland | +0.428 |
rite | +0.413 |
mia | +0.392 |
Neg logit contributions | |
unloaded | -0.828 |
Coy | -0.822 |
enegger | -0.820 |
withd | -0.783 |
thood | -0.776 |
Token | 53 |
Token ID | 7192 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
roud | +1.734 |
rog | +1.439 |
utherland | +1.263 |
rite | +1.231 |
Puppet | +1.183 |
Neg logit contributions | |
unloaded | -1.682 |
enegger | -1.668 |
Coy | -1.663 |
withd | -1.578 |
thood | -1.570 |
Token | )" |
Token ID | 16725 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
roud | +0.267 |
rog | +0.222 |
utherland | +0.195 |
rite | +0.190 |
mia | +0.182 |
Neg logit contributions | |
unloaded | -0.265 |
Coy | -0.263 |
enegger | -0.261 |
withd | -0.249 |
thood | -0.247 |
Token | break |
Token ID | 2270 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
roud | +0.438 |
rog | +0.383 |
utherland | +0.354 |
rite | +0.345 |
mia | +0.337 |
Neg logit contributions | |
unloaded | -0.196 |
Coy | -0.194 |
enegger | -0.189 |
withd | -0.173 |
perce | -0.172 |
Token | } |
Token ID | 1782 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
roud | +0.506 |
rog | +0.386 |
utherland | +0.318 |
rite | +0.301 |
mia | +0.284 |
Neg logit contributions | |
unloaded | -0.887 |
Coy | -0.881 |
enegger | -0.876 |
withd | -0.837 |
perce | -0.835 |
Token | } |
Token ID | 1782 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
roud | +0.064 |
rog | +0.049 |
utherland | +0.040 |
rite | +0.038 |
mia | +0.036 |
Neg logit contributions | |
unloaded | -0.111 |
Coy | -0.111 |
enegger | -0.110 |
withd | -0.106 |
thood | -0.105 |
Token | End |
Token ID | 5268 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
roud | +0.341 |
rog | +0.284 |
utherland | +0.251 |
rite | +0.243 |
mia | +0.234 |
Neg logit contributions | |
unloaded | -0.331 |
Coy | -0.328 |
enegger | -0.325 |
withd | -0.310 |
perce | -0.306 |
Token | { |
Token ID | 1391 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
unloaded | +0.232 |
Coy | +0.231 |
enegger | +0.227 |
withd | +0.213 |
thood | +0.213 |
Neg logit contributions | |
roud | -0.337 |
rog | -0.287 |
utherland | -0.260 |
rite | -0.251 |
mia | -0.248 |
Token | Try |
Token ID | 9993 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
roud | +3.680 |
rog | +3.098 |
utherland | +2.751 |
rite | +2.734 |
Puppet | +2.622 |
Neg logit contributions | |
enegger | -3.011 |
unloaded | -2.979 |
Coy | -2.966 |
withd | -2.815 |
thood | -2.779 |
Token | { |
Token ID | 1391 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
unloaded | +0.273 |
Coy | +0.271 |
enegger | +0.270 |
withd | +0.257 |
thood | +0.254 |
Neg logit contributions | |
roud | -0.247 |
rog | -0.203 |
utherland | -0.177 |
rite | -0.171 |
mia | -0.164 |
Token | # |
Token ID | 1303 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
roud | +2.664 |
rog | +2.238 |
utherland | +1.992 |
rite | +1.973 |
Puppet | +1.896 |
Neg logit contributions | |
enegger | -2.175 |
unloaded | -2.162 |
Coy | -2.154 |
withd | -2.041 |
thood | -2.023 |
Token | Close |
Token ID | 13872 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
roud | +1.599 |
rog | +1.371 |
utherland | +1.239 |
rite | +1.215 |
mia | +1.175 |
Neg logit contributions | |
unloaded | -1.048 |
enegger | -1.037 |
Coy | -1.037 |
withd | -0.969 |
thood | -0.958 |
Token | Graphics |
Token ID | 19840 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
roud | +0.898 |
rog | +0.771 |
utherland | +0.699 |
rite | +0.683 |
mia | +0.664 |
Neg logit contributions | |
unloaded | -0.570 |
Coy | -0.563 |
enegger | -0.559 |
withd | -0.524 |
perce | -0.516 |
Token | s |
Token ID | 82 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
unloaded | +0.034 |
Coy | +0.034 |
enegger | +0.034 |
withd | +0.032 |
perce | +0.031 |
Neg logit contributions | |
roud | -0.048 |
rog | -0.041 |
utherland | -0.037 |
rite | -0.036 |
mia | -0.035 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
roud | +0.742 |
rog | +0.592 |
utherland | +0.503 |
rite | +0.486 |
mia | +0.461 |
Neg logit contributions | |
unloaded | -1.019 |
Coy | -1.010 |
enegger | -1.006 |
withd | -0.964 |
thood | -0.957 |
Token | K |
Token ID | 509 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
roud | +1.859 |
rog | +1.595 |
utherland | +1.433 |
rite | +1.407 |
mia | +1.364 |
Neg logit contributions | |
unloaded | -1.231 |
enegger | -1.222 |
Coy | -1.217 |
withd | -1.139 |
thood | -1.131 |
Token | b |
Token ID | 65 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
roud | +0.650 |
rog | +0.540 |
utherland | +0.481 |
rite | +0.466 |
mia | +0.447 |
Neg logit contributions | |
unloaded | -0.610 |
Coy | -0.606 |
enegger | -0.601 |
withd | -0.571 |
thood | -0.565 |
Token | 7 |
Token ID | 22 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
roud | +0.553 |
rog | +0.467 |
utherland | +0.415 |
rite | +0.405 |
mia | +0.392 |
Neg logit contributions | |
unloaded | -0.455 |
Coy | -0.451 |
enegger | -0.451 |
withd | -0.425 |
thood | -0.420 |
Token | { |
Token ID | 1391 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
roud | +0.206 |
rog | +0.172 |
utherland | +0.153 |
rite | +0.149 |
mia | +0.143 |
Neg logit contributions | |
unloaded | -0.186 |
Coy | -0.184 |
enegger | -0.183 |
withd | -0.174 |
thood | -0.172 |
Token | ( |
Token ID | 7 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
roud | +4.023 |
rog | +3.452 |
utherland | +3.103 |
rite | +3.045 |
mia | +2.961 |
Neg logit contributions | |
unloaded | -2.663 |
enegger | -2.629 |
Coy | -2.628 |
withd | -2.451 |
thood | -2.445 |
Token | 3 |
Token ID | 18 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
roud | +1.240 |
rog | +1.030 |
utherland | +0.911 |
rite | +0.885 |
mia | +0.849 |
Neg logit contributions | |
unloaded | -1.193 |
Coy | -1.186 |
enegger | -1.181 |
withd | -1.117 |
thood | -1.108 |
Token | s |
Token ID | 82 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
roud | +0.165 |
rog | +0.142 |
utherland | +0.129 |
rite | +0.126 |
mia | +0.122 |
Neg logit contributions | |
unloaded | -0.105 |
Coy | -0.104 |
enegger | -0.104 |
withd | -0.097 |
perce | -0.096 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
roud | +0.446 |
rog | +0.356 |
utherland | +0.302 |
rite | +0.292 |
mia | +0.277 |
Neg logit contributions | |
unloaded | -0.612 |
Coy | -0.607 |
enegger | -0.604 |
withd | -0.578 |
thood | -0.575 |
Token | 52 |
Token ID | 6740 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
roud | +1.850 |
rog | +1.582 |
utherland | +1.417 |
rite | +1.390 |
mia | +1.347 |
Neg logit contributions | |
unloaded | -1.279 |
enegger | -1.271 |
Coy | -1.264 |
withd | -1.185 |
thood | -1.181 |
Token | } |
Token ID | 92 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
roud | +0.044 |
rog | +0.038 |
utherland | +0.034 |
rite | +0.034 |
mia | +0.032 |
Neg logit contributions | |
unloaded | -0.030 |
Coy | -0.030 |
enegger | -0.030 |
withd | -0.028 |
thood | -0.028 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
unloaded | +0.429 |
Coy | +0.424 |
enegger | +0.420 |
withd | +0.393 |
perce | +0.391 |
Neg logit contributions | |
roud | -0.584 |
rog | -0.497 |
utherland | -0.450 |
rite | -0.437 |
mia | -0.424 |
Token | " |
Token ID | 366 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
unloaded | +0.594 |
Coy | +0.589 |
enegger | +0.581 |
withd | +0.548 |
perce | +0.542 |
Neg logit contributions | |
roud | -0.804 |
rog | -0.684 |
utherland | -0.617 |
rite | -0.600 |
mia | -0.580 |
Token | E |
Token ID | 36 |
Feature activation | -5.54e-05 |
Pos logit contributions | |
unloaded | +0.713 |
Coy | +0.708 |
enegger | +0.698 |
withd | +0.665 |
perce | +0.656 |
Neg logit contributions | |
roud | -0.766 |
rog | -0.635 |
utherland | -0.568 |
rite | -0.547 |
mia | -0.526 |
Token | ", |
Token ID | 1600 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
unloaded | +0.000 |
Coy | +0.000 |
enegger | +0.000 |
withd | +0.000 |
thood | +0.000 |
Neg logit contributions | |
roud | -0.000 |
rog | -0.000 |
utherland | -0.000 |
rite | -0.000 |
mia | -0.000 |
Token | { |
Token ID | 1391 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
roud | +0.218 |
rog | +0.187 |
utherland | +0.169 |
rite | +0.165 |
mia | +0.160 |
Neg logit contributions | |
unloaded | -0.145 |
Coy | -0.144 |
enegger | -0.142 |
withd | -0.134 |
perce | -0.132 |
Token | 1 |
Token ID | 16 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
roud | +3.776 |
rog | +3.215 |
utherland | +2.869 |
rite | +2.831 |
mia | +2.720 |
Neg logit contributions | |
unloaded | -2.857 |
enegger | -2.847 |
Coy | -2.823 |
withd | -2.670 |
thood | -2.633 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
roud | +0.246 |
rog | +0.212 |
utherland | +0.192 |
rite | +0.188 |
mia | +0.182 |
Neg logit contributions | |
unloaded | -0.156 |
Coy | -0.154 |
enegger | -0.153 |
withd | -0.143 |
thood | -0.141 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
roud | +0.622 |
rog | +0.525 |
utherland | +0.474 |
rite | +0.459 |
mia | +0.444 |
Neg logit contributions | |
unloaded | -0.489 |
Coy | -0.486 |
enegger | -0.482 |
withd | -0.454 |
thood | -0.450 |
Token | } |
Token ID | 92 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
unloaded | +0.039 |
Coy | +0.038 |
enegger | +0.038 |
withd | +0.036 |
thood | +0.036 |
Neg logit contributions | |
roud | -0.050 |
rog | -0.042 |
utherland | -0.038 |
rite | -0.037 |
mia | -0.035 |
Token | -> |
Token ID | 4613 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
unloaded | +0.130 |
Coy | +0.129 |
enegger | +0.128 |
withd | +0.120 |
thood | +0.118 |
Neg logit contributions | |
roud | -0.204 |
rog | -0.175 |
utherland | -0.159 |
rite | -0.155 |
mia | -0.150 |
Token | into |
Token ID | 656 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
roud | +0.129 |
rog | +0.111 |
utherland | +0.101 |
rite | +0.099 |
mia | +0.096 |
Neg logit contributions | |
unloaded | -0.075 |
Coy | -0.074 |
enegger | -0.074 |
withd | -0.069 |
thood | -0.068 |
Token | them |
Token ID | 606 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
unloaded | +0.095 |
Coy | +0.095 |
enegger | +0.094 |
withd | +0.088 |
perce | +0.087 |
Neg logit contributions | |
roud | -0.148 |
rog | -0.128 |
utherland | -0.115 |
rite | -0.113 |
mia | -0.110 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
roud | +0.144 |
rog | +0.124 |
utherland | +0.112 |
rite | +0.110 |
mia | +0.106 |
Neg logit contributions | |
unloaded | -0.092 |
Coy | -0.091 |
enegger | -0.091 |
withd | -0.085 |
thood | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
roud | +0.322 |
rog | +0.272 |
utherland | +0.245 |
rite | +0.238 |
mia | +0.230 |
Neg logit contributions | |
unloaded | -0.254 |
Coy | -0.253 |
enegger | -0.251 |
thood | -0.233 |
perce | -0.233 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
roud | +0.351 |
rog | +0.297 |
utherland | +0.270 |
rite | +0.261 |
mia | +0.251 |
Neg logit contributions | |
unloaded | -0.272 |
Coy | -0.271 |
enegger | -0.267 |
perce | -0.249 |
thood | -0.248 |
Token | Topics |
Token ID | 25902 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
roud | +0.473 |
rog | +0.397 |
utherland | +0.359 |
rite | +0.349 |
Puppet | +0.337 |
Neg logit contributions | |
unloaded | -0.382 |
Coy | -0.381 |
enegger | -0.377 |
thood | -0.354 |
withd | -0.353 |
Token | : |
Token ID | 25 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
roud | +3.961 |
rog | +3.406 |
utherland | +3.039 |
rite | +3.011 |
mia | +2.931 |
Neg logit contributions | |
enegger | -2.631 |
unloaded | -2.618 |
Coy | -2.600 |
withd | -2.538 |
proble | -2.460 |
Token | marine |
Token ID | 16050 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
unloaded | +0.136 |
Coy | +0.134 |
enegger | +0.133 |
withd | +0.123 |
perce | +0.121 |
Neg logit contributions | |
roud | -0.279 |
rog | -0.243 |
utherland | -0.223 |
rite | -0.219 |
mia | -0.213 |
Token | - |
Token ID | 12 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
unloaded | +0.657 |
Coy | +0.648 |
enegger | +0.642 |
withd | +0.603 |
perce | +0.600 |
Neg logit contributions | |
roud | -1.012 |
rog | -0.851 |
utherland | -0.784 |
rite | -0.762 |
Puppet | -0.745 |
Token | biology |
Token ID | 43592 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
unloaded | +0.228 |
Coy | +0.224 |
enegger | +0.223 |
thood | +0.213 |
withd | +0.212 |
Neg logit contributions | |
roud | -0.276 |
rog | -0.229 |
utherland | -0.211 |
Puppet | -0.203 |
rite | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
unloaded | +0.160 |
Coy | +0.158 |
enegger | +0.155 |
perce | +0.144 |
thood | +0.144 |
Neg logit contributions | |
roud | -0.299 |
rog | -0.257 |
utherland | -0.238 |
rite | -0.231 |
FANTASY | -0.224 |
Token | YOUR |
Token ID | 16592 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
unloaded | +0.191 |
Coy | +0.190 |
enegger | +0.187 |
withd | +0.177 |
perce | +0.175 |
Neg logit contributions | |
roud | -0.267 |
rog | -0.226 |
utherland | -0.205 |
rite | -0.200 |
mia | -0.192 |
Token | bed |
Token ID | 3996 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
roud | +0.053 |
rog | +0.044 |
utherland | +0.040 |
rite | +0.039 |
mia | +0.037 |
Neg logit contributions | |
unloaded | -0.044 |
Coy | -0.044 |
enegger | -0.043 |
withd | -0.041 |
perce | -0.040 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
roud | +1.345 |
rog | +1.151 |
utherland | +1.037 |
rite | +1.016 |
mia | +0.984 |
Neg logit contributions | |
unloaded | -0.920 |
Coy | -0.911 |
enegger | -0.908 |
withd | -0.851 |
thood | -0.840 |
Token | she |
Token ID | 673 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
roud | +0.485 |
rog | +0.410 |
utherland | +0.367 |
rite | +0.358 |
mia | +0.346 |
Neg logit contributions | |
unloaded | -0.382 |
Coy | -0.378 |
enegger | -0.378 |
withd | -0.357 |
thood | -0.352 |
Token | te |
Token ID | 573 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
unloaded | +0.224 |
Coy | +0.221 |
enegger | +0.220 |
withd | +0.205 |
perce | +0.201 |
Neg logit contributions | |
roud | -0.388 |
rog | -0.335 |
utherland | -0.305 |
rite | -0.299 |
mia | -0.290 |
Token | ases |
Token ID | 1386 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Coy | +1.612 |
unloaded | +1.611 |
enegger | +1.593 |
perce | +1.463 |
withd | +1.452 |
Neg logit contributions | |
roud | -2.634 |
rog | -2.239 |
utherland | -2.074 |
rite | -2.011 |
Puppet | -1.965 |
Token | . |
Token ID | 13 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
unloaded | +2.591 |
Coy | +2.566 |
enegger | +2.485 |
perce | +2.335 |
withd | +2.331 |
Neg logit contributions | |
roud | -4.876 |
rog | -4.230 |
utherland | -3.905 |
rite | -3.847 |
mia | -3.704 |
Token |
|
Token ID | 198 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
unloaded | +0.204 |
Coy | +0.202 |
enegger | +0.201 |
withd | +0.189 |
thood | +0.187 |
Neg logit contributions | |
roud | -0.297 |
rog | -0.253 |
utherland | -0.228 |
rite | -0.223 |
mia | -0.216 |
Token |
|
Token ID | 198 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
Coy | +0.140 |
unloaded | +0.140 |
enegger | +0.137 |
perce | +0.128 |
thood | +0.127 |
Neg logit contributions | |
roud | -0.185 |
rog | -0.157 |
utherland | -0.143 |
rite | -0.138 |
mia | -0.133 |
Token | I |
Token ID | 40 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
unloaded | +0.062 |
Coy | +0.062 |
enegger | +0.062 |
withd | +0.058 |
thood | +0.057 |
Neg logit contributions | |
roud | -0.096 |
rog | -0.082 |
utherland | -0.074 |
rite | -0.073 |
mia | -0.070 |
Token | tried |
Token ID | 3088 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
unloaded | +0.474 |
Coy | +0.466 |
enegger | +0.461 |
withd | +0.436 |
perce | +0.430 |
Neg logit contributions | |
roud | -0.675 |
rog | -0.576 |
utherland | -0.523 |
rite | -0.508 |
mia | -0.490 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Coy | +0.412 |
unloaded | +0.411 |
enegger | +0.406 |
withd | +0.377 |
perce | +0.374 |
Neg logit contributions | |
roud | -0.673 |
rog | -0.578 |
utherland | -0.526 |
rite | -0.514 |
mia | -0.498 |
Token | United |
Token ID | 1578 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Coy | +0.617 |
unloaded | +0.609 |
enegger | +0.606 |
withd | +0.560 |
perce | +0.559 |
Neg logit contributions | |
roud | -0.885 |
rog | -0.752 |
utherland | -0.684 |
rite | -0.666 |
mia | -0.643 |
Token | States |
Token ID | 1829 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Coy | +1.112 |
unloaded | +1.112 |
enegger | +1.097 |
withd | +1.020 |
perce | +1.004 |
Neg logit contributions | |
roud | -1.893 |
rog | -1.630 |
utherland | -1.495 |
rite | -1.454 |
mia | -1.407 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
Coy | +0.670 |
unloaded | +0.660 |
enegger | +0.653 |
perce | +0.609 |
withd | +0.607 |
Neg logit contributions | |
roud | -0.846 |
rog | -0.712 |
utherland | -0.645 |
rite | -0.626 |
mia | -0.600 |
Token | 240 |
Token ID | 16102 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Coy | +1.389 |
unloaded | +1.376 |
enegger | +1.370 |
perce | +1.289 |
withd | +1.286 |
Neg logit contributions | |
roud | -1.661 |
rog | -1.400 |
utherland | -1.257 |
rite | -1.223 |
mia | -1.172 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Coy | +0.362 |
unloaded | +0.359 |
enegger | +0.352 |
perce | +0.330 |
thood | +0.328 |
Neg logit contributions | |
roud | -0.568 |
rog | -0.484 |
utherland | -0.444 |
rite | -0.429 |
mia | -0.416 |
Token | # |
Token ID | 1303 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Coy | +3.221 |
unloaded | +3.207 |
enegger | +3.093 |
perce | +2.954 |
withd | +2.945 |
Neg logit contributions | |
roud | -3.907 |
rog | -3.274 |
utherland | -3.005 |
rite | -2.905 |
mia | -2.827 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Coy | +0.612 |
unloaded | +0.607 |
enegger | +0.601 |
thood | +0.564 |
perce | +0.559 |
Neg logit contributions | |
roud | -0.756 |
rog | -0.635 |
utherland | -0.575 |
rite | -0.556 |
mia | -0.538 |
Token | Happy |
Token ID | 14628 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
unloaded | +0.242 |
Coy | +0.241 |
enegger | +0.237 |
withd | +0.222 |
perce | +0.219 |
Neg logit contributions | |
roud | -0.382 |
rog | -0.327 |
utherland | -0.298 |
rite | -0.290 |
mia | -0.282 |
Token | it |
Token ID | 340 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
unloaded | +0.184 |
Coy | +0.183 |
enegger | +0.181 |
withd | +0.170 |
perce | +0.168 |
Neg logit contributions | |
roud | -0.273 |
rog | -0.233 |
utherland | -0.211 |
rite | -0.206 |
mia | -0.200 |
Token | worked |
Token ID | 3111 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
unloaded | +0.723 |
Coy | +0.714 |
enegger | +0.705 |
withd | +0.664 |
perce | +0.659 |
Neg logit contributions | |
roud | -0.988 |
rog | -0.844 |
utherland | -0.763 |
rite | -0.737 |
mia | -0.717 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Coy | +0.657 |
unloaded | +0.652 |
enegger | +0.639 |
perce | +0.592 |
thood | +0.588 |
Neg logit contributions | |
roud | -1.115 |
rog | -0.959 |
utherland | -0.878 |
rite | -0.856 |
mia | -0.829 |
Token | United |
Token ID | 1578 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
Coy | +0.747 |
unloaded | +0.735 |
enegger | +0.730 |
withd | +0.678 |
perce | +0.675 |
Neg logit contributions | |
roud | -1.038 |
rog | -0.880 |
utherland | -0.801 |
rite | -0.779 |
mia | -0.752 |
Token | States |
Token ID | 1829 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
unloaded | +1.125 |
Coy | +1.122 |
enegger | +1.111 |
withd | +1.031 |
thood | +1.019 |
Neg logit contributions | |
roud | -1.865 |
rog | -1.609 |
utherland | -1.469 |
rite | -1.432 |
mia | -1.386 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Coy | +0.486 |
unloaded | +0.480 |
enegger | +0.474 |
perce | +0.443 |
withd | +0.440 |
Neg logit contributions | |
roud | -0.613 |
rog | -0.516 |
utherland | -0.467 |
rite | -0.454 |
mia | -0.436 |
Token | 667 |
Token ID | 28933 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
Coy | +0.915 |
unloaded | +0.908 |
enegger | +0.908 |
perce | +0.851 |
thood | +0.851 |
Neg logit contributions | |
roud | -0.940 |
rog | -0.778 |
utherland | -0.689 |
rite | -0.670 |
mia | -0.643 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
roud | +0.118 |
rog | +0.101 |
utherland | +0.092 |
rite | +0.089 |
mia | +0.086 |
Neg logit contributions | |
Coy | -0.080 |
unloaded | -0.080 |
enegger | -0.079 |
perce | -0.073 |
thood | -0.073 |
Token | # |
Token ID | 1303 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
unloaded | +3.169 |
Coy | +3.162 |
enegger | +3.079 |
withd | +2.926 |
thood | +2.912 |
Neg logit contributions | |
roud | -3.734 |
rog | -3.130 |
utherland | -2.839 |
rite | -2.744 |
mia | -2.678 |
Token | 12 |
Token ID | 1065 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
unloaded | +0.610 |
Coy | +0.605 |
enegger | +0.599 |
withd | +0.561 |
thood | +0.558 |
Neg logit contributions | |
roud | -0.815 |
rog | -0.692 |
utherland | -0.624 |
rite | -0.607 |
mia | -0.587 |
Token | I |
Token ID | 314 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
unloaded | +0.378 |
Coy | +0.376 |
enegger | +0.371 |
withd | +0.349 |
perce | +0.343 |
Neg logit contributions | |
roud | -0.589 |
rog | -0.506 |
utherland | -0.459 |
rite | -0.448 |
mia | -0.435 |
Token | 'm |
Token ID | 1101 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
unloaded | +0.569 |
Coy | +0.559 |
enegger | +0.554 |
withd | +0.524 |
perce | +0.516 |
Neg logit contributions | |
roud | -0.799 |
rog | -0.681 |
utherland | -0.618 |
rite | -0.598 |
mia | -0.579 |
Token | glad |
Token ID | 9675 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
unloaded | +0.703 |
Coy | +0.694 |
enegger | +0.677 |
withd | +0.641 |
perce | +0.635 |
Neg logit contributions | |
roud | -1.231 |
rog | -1.069 |
utherland | -0.981 |
rite | -0.956 |
mia | -0.928 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Coy | +0.133 |
unloaded | +0.133 |
enegger | +0.131 |
withd | +0.121 |
perce | +0.121 |
Neg logit contributions | |
roud | -0.218 |
rog | -0.187 |
utherland | -0.170 |
rite | -0.167 |
mia | -0.162 |
Token | United |
Token ID | 1578 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Coy | +0.419 |
unloaded | +0.416 |
enegger | +0.413 |
withd | +0.384 |
perce | +0.381 |
Neg logit contributions | |
roud | -0.601 |
rog | -0.512 |
utherland | -0.465 |
rite | -0.453 |
mia | -0.438 |
Token | States |
Token ID | 1829 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
unloaded | +1.010 |
Coy | +1.008 |
enegger | +1.000 |
withd | +0.928 |
thood | +0.916 |
Neg logit contributions | |
roud | -1.658 |
rog | -1.430 |
utherland | -1.304 |
rite | -1.269 |
mia | -1.231 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Coy | +0.450 |
unloaded | +0.444 |
enegger | +0.439 |
perce | +0.410 |
withd | +0.408 |
Neg logit contributions | |
roud | -0.566 |
rog | -0.477 |
utherland | -0.432 |
rite | -0.419 |
mia | -0.402 |
Token | 53 |
Token ID | 4310 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Coy | +0.940 |
enegger | +0.927 |
unloaded | +0.927 |
perce | +0.870 |
withd | +0.867 |
Neg logit contributions | |
roud | -1.038 |
rog | -0.865 |
utherland | -0.767 |
rite | -0.747 |
mia | -0.718 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
roud | +0.075 |
rog | +0.064 |
utherland | +0.058 |
rite | +0.056 |
mia | +0.055 |
Neg logit contributions | |
Coy | -0.050 |
unloaded | -0.049 |
enegger | -0.049 |
perce | -0.045 |
thood | -0.045 |
Token | # |
Token ID | 1303 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
unloaded | +3.050 |
Coy | +3.042 |
enegger | +2.979 |
withd | +2.822 |
thood | +2.806 |
Neg logit contributions | |
roud | -3.547 |
rog | -2.971 |
utherland | -2.695 |
rite | -2.601 |
mia | -2.535 |
Token | 15 |
Token ID | 1314 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
unloaded | +0.612 |
Coy | +0.604 |
enegger | +0.592 |
thood | +0.567 |
perce | +0.562 |
Neg logit contributions | |
roud | -0.681 |
rog | -0.567 |
utherland | -0.524 |
rite | -0.488 |
FANTASY | -0.480 |
Token | honestly |
Token ID | 12698 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
unloaded | +0.446 |
Coy | +0.443 |
enegger | +0.437 |
withd | +0.410 |
perce | +0.405 |
Neg logit contributions | |
roud | -0.696 |
rog | -0.597 |
utherland | -0.542 |
rite | -0.529 |
mia | -0.514 |
Token | if |
Token ID | 611 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
unloaded | +1.093 |
Coy | +1.085 |
enegger | +1.063 |
withd | +1.001 |
perce | +0.993 |
Neg logit contributions | |
roud | -1.907 |
rog | -1.643 |
utherland | -1.515 |
rite | -1.472 |
mia | -1.431 |
Token | we |
Token ID | 356 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
roud | +0.021 |
rog | +0.018 |
utherland | +0.016 |
rite | +0.016 |
mia | +0.015 |
Neg logit contributions | |
unloaded | -0.013 |
Coy | -0.013 |
enegger | -0.013 |
withd | -0.012 |
perce | -0.012 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
unloaded | +0.372 |
Coy | +0.369 |
enegger | +0.367 |
withd | +0.343 |
thood | +0.338 |
Neg logit contributions | |
roud | -0.579 |
rog | -0.497 |
utherland | -0.450 |
rite | -0.440 |
mia | -0.427 |
Token | United |
Token ID | 1578 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Coy | +0.273 |
unloaded | +0.271 |
enegger | +0.269 |
withd | +0.252 |
perce | +0.249 |
Neg logit contributions | |
roud | -0.376 |
rog | -0.319 |
utherland | -0.289 |
rite | -0.282 |
mia | -0.272 |
Token | States |
Token ID | 1829 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
unloaded | +1.047 |
Coy | +1.044 |
enegger | +1.035 |
withd | +0.962 |
thood | +0.949 |
Neg logit contributions | |
roud | -1.731 |
rog | -1.491 |
utherland | -1.361 |
rite | -1.327 |
mia | -1.286 |
Token | 3 |
Token ID | 513 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Coy | +0.554 |
unloaded | +0.548 |
enegger | +0.541 |
perce | +0.506 |
withd | +0.505 |
Neg logit contributions | |
roud | -0.678 |
rog | -0.569 |
utherland | -0.514 |
rite | -0.499 |
mia | -0.480 |
Token | 472 |
Token ID | 37856 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Coy | +1.330 |
enegger | +1.318 |
unloaded | +1.316 |
withd | +1.242 |
thood | +1.241 |
Neg logit contributions | |
roud | -1.182 |
rog | -0.963 |
utherland | -0.846 |
rite | -0.819 |
mia | -0.780 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
roud | +0.471 |
rog | +0.402 |
utherland | +0.362 |
rite | +0.353 |
mia | +0.342 |
Neg logit contributions | |
unloaded | -0.328 |
Coy | -0.327 |
enegger | -0.324 |
withd | -0.301 |
thood | -0.300 |
Token | # |
Token ID | 1303 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Coy | +3.011 |
unloaded | +3.010 |
enegger | +2.923 |
withd | +2.780 |
perce | +2.773 |
Neg logit contributions | |
roud | -3.565 |
rog | -2.986 |
utherland | -2.724 |
rite | -2.627 |
mia | -2.557 |
Token | 11 |
Token ID | 1157 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
unloaded | +0.401 |
Coy | +0.399 |
enegger | +0.392 |
thood | +0.366 |
perce | +0.364 |
Neg logit contributions | |
roud | -0.574 |
rog | -0.488 |
utherland | -0.444 |
rite | -0.430 |
mia | -0.419 |
Token | On |
Token ID | 1550 |
Feature activation | -2.80e-03 |
Pos logit contributions | |
roud | +0.531 |
rog | +0.456 |
utherland | +0.412 |
rite | +0.403 |
mia | +0.390 |
Neg logit contributions | |
unloaded | -0.348 |
Coy | -0.345 |
enegger | -0.343 |
withd | -0.321 |
thood | -0.317 |
Token | September |
Token ID | 2693 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
unloaded | +0.005 |
Coy | +0.005 |
enegger | +0.005 |
withd | +0.004 |
thood | +0.004 |
Neg logit contributions | |
roud | -0.009 |
rog | -0.008 |
utherland | -0.007 |
rite | -0.007 |
mia | -0.007 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
roud | +0.732 |
rog | +0.630 |
utherland | +0.573 |
rite | +0.560 |
mia | +0.543 |
Neg logit contributions | |
unloaded | -0.450 |
Coy | -0.449 |
enegger | -0.442 |
withd | -0.410 |
perce | -0.407 |
Token | how |
Token ID | 703 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
unloaded | +0.097 |
Coy | +0.096 |
enegger | +0.095 |
withd | +0.089 |
perce | +0.088 |
Neg logit contributions | |
roud | -0.162 |
rog | -0.140 |
utherland | -0.127 |
rite | -0.125 |
mia | -0.121 |
Token | to |
Token ID | 284 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
unloaded | +0.713 |
Coy | +0.709 |
enegger | +0.699 |
withd | +0.656 |
perce | +0.645 |
Neg logit contributions | |
roud | -1.168 |
rog | -1.005 |
utherland | -0.913 |
rite | -0.896 |
mia | -0.866 |
Token | operate |
Token ID | 8076 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
unloaded | +0.535 |
Coy | +0.529 |
enegger | +0.522 |
withd | +0.492 |
perce | +0.485 |
Neg logit contributions | |
roud | -0.841 |
rog | -0.723 |
utherland | -0.657 |
rite | -0.641 |
mia | -0.621 |
Token | in |
Token ID | 287 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
unloaded | +0.414 |
Coy | +0.410 |
enegger | +0.408 |
withd | +0.381 |
perce | +0.375 |
Neg logit contributions | |
roud | -0.669 |
rog | -0.576 |
utherland | -0.522 |
rite | -0.511 |
mia | -0.496 |
Token | a |
Token ID | 257 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
unloaded | +0.123 |
Coy | +0.122 |
enegger | +0.122 |
withd | +0.114 |
thood | +0.112 |
Neg logit contributions | |
roud | -0.205 |
rog | -0.177 |
utherland | -0.160 |
rite | -0.157 |
mia | -0.152 |
Token | technical |
Token ID | 6276 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
unloaded | +0.126 |
Coy | +0.125 |
enegger | +0.123 |
withd | +0.114 |
perce | +0.113 |
Neg logit contributions | |
roud | -0.234 |
rog | -0.203 |
utherland | -0.186 |
rite | -0.182 |
mia | -0.176 |
Token | sprint |
Token ID | 18553 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
unloaded | +2.453 |
Coy | +2.437 |
enegger | +2.367 |
perce | +2.224 |
withd | +2.214 |
Neg logit contributions | |
roud | -4.067 |
rog | -3.518 |
utherland | -3.212 |
rite | -3.138 |
mia | -3.022 |
Token | like |
Token ID | 588 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
unloaded | +0.624 |
Coy | +0.618 |
enegger | +0.615 |
withd | +0.573 |
thood | +0.565 |
Neg logit contributions | |
roud | -1.045 |
rog | -0.901 |
utherland | -0.818 |
rite | -0.801 |
mia | -0.777 |
Token | that |
Token ID | 326 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
unloaded | +0.109 |
Coy | +0.108 |
enegger | +0.107 |
withd | +0.100 |
perce | +0.099 |
Neg logit contributions | |
roud | -0.165 |
rog | -0.141 |
utherland | -0.128 |
rite | -0.125 |
mia | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
unloaded | +0.453 |
Coy | +0.448 |
enegger | +0.446 |
withd | +0.416 |
thood | +0.410 |
Neg logit contributions | |
roud | -0.752 |
rog | -0.649 |
utherland | -0.589 |
rite | -0.577 |
mia | -0.559 |
Token | � |
Token ID | 447 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
unloaded | +0.069 |
Coy | +0.069 |
enegger | +0.068 |
withd | +0.064 |
perce | +0.063 |
Neg logit contributions | |
roud | -0.094 |
rog | -0.080 |
utherland | -0.072 |
rite | -0.071 |
mia | -0.068 |
Token | June |
Token ID | 2795 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Coy | +0.905 |
unloaded | +0.897 |
enegger | +0.865 |
perce | +0.807 |
withd | +0.804 |
Neg logit contributions | |
roud | -1.730 |
rog | -1.495 |
utherland | -1.374 |
rite | -1.345 |
mia | -1.307 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Coy | +0.857 |
unloaded | +0.848 |
enegger | +0.835 |
perce | +0.772 |
withd | +0.769 |
Neg logit contributions | |
roud | -1.457 |
rog | -1.251 |
utherland | -1.144 |
rite | -1.120 |
mia | -1.082 |
Token | Canada |
Token ID | 3340 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Coy | +0.722 |
unloaded | +0.710 |
enegger | +0.706 |
withd | +0.655 |
perce | +0.652 |
Neg logit contributions | |
roud | -1.030 |
rog | -0.875 |
utherland | -0.796 |
rite | -0.777 |
mia | -0.750 |
Token | 16 |
Token ID | 1467 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Coy | +0.716 |
unloaded | +0.709 |
enegger | +0.698 |
perce | +0.655 |
thood | +0.651 |
Neg logit contributions | |
roud | -0.879 |
rog | -0.741 |
utherland | -0.667 |
rite | -0.647 |
mia | -0.623 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Coy | +1.259 |
unloaded | +1.243 |
enegger | +1.237 |
perce | +1.167 |
thood | +1.162 |
Neg logit contributions | |
roud | -1.382 |
rog | -1.147 |
utherland | -1.019 |
rite | -0.996 |
mia | -0.953 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Coy | +0.443 |
unloaded | +0.437 |
enegger | +0.434 |
perce | +0.402 |
thood | +0.401 |
Neg logit contributions | |
roud | -0.664 |
rog | -0.567 |
utherland | -0.513 |
rite | -0.501 |
mia | -0.485 |
Token | # |
Token ID | 1303 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
unloaded | +2.914 |
Coy | +2.908 |
enegger | +2.847 |
withd | +2.699 |
thood | +2.684 |
Neg logit contributions | |
roud | -3.378 |
rog | -2.831 |
utherland | -2.557 |
rite | -2.475 |
mia | -2.409 |
Token | 14 |
Token ID | 1415 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
unloaded | +0.569 |
Coy | +0.565 |
enegger | +0.558 |
thood | +0.526 |
perce | +0.525 |
Neg logit contributions | |
roud | -0.644 |
rog | -0.540 |
utherland | -0.484 |
rite | -0.466 |
Puppet | -0.450 |
Token | On |
Token ID | 1550 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
unloaded | +0.022 |
Coy | +0.022 |
enegger | +0.022 |
withd | +0.021 |
thood | +0.020 |
Neg logit contributions | |
roud | -0.035 |
rog | -0.030 |
utherland | -0.027 |
rite | -0.026 |
mia | -0.025 |
Token | September |
Token ID | 2693 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
roud | +0.120 |
rog | +0.103 |
utherland | +0.094 |
rite | +0.092 |
mia | +0.089 |
Neg logit contributions | |
unloaded | -0.074 |
Coy | -0.074 |
enegger | -0.073 |
withd | -0.068 |
perce | -0.068 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
roud | +0.693 |
rog | +0.591 |
utherland | +0.529 |
rite | +0.517 |
Puppet | +0.502 |
Neg logit contributions | |
unloaded | -0.494 |
Coy | -0.489 |
enegger | -0.486 |
withd | -0.462 |
thood | -0.453 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Coy | +0.331 |
unloaded | +0.329 |
enegger | +0.324 |
perce | +0.299 |
withd | +0.298 |
Neg logit contributions | |
roud | -0.550 |
rog | -0.474 |
utherland | -0.432 |
rite | -0.421 |
mia | -0.409 |
Token | United |
Token ID | 1578 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
Coy | +0.507 |
unloaded | +0.503 |
enegger | +0.501 |
withd | +0.465 |
perce | +0.462 |
Neg logit contributions | |
roud | -0.726 |
rog | -0.619 |
utherland | -0.562 |
rite | -0.547 |
mia | -0.529 |
Token | States |
Token ID | 1829 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Coy | +0.928 |
enegger | +0.911 |
unloaded | +0.910 |
perce | +0.824 |
Inqu | +0.817 |
Neg logit contributions | |
roud | -1.617 |
rog | -1.399 |
utherland | -1.288 |
rite | -1.246 |
mia | -1.207 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Coy | +0.359 |
unloaded | +0.354 |
enegger | +0.350 |
perce | +0.327 |
withd | +0.326 |
Neg logit contributions | |
roud | -0.443 |
rog | -0.372 |
utherland | -0.336 |
rite | -0.326 |
mia | -0.314 |
Token | 83 |
Token ID | 5999 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
Coy | +0.524 |
unloaded | +0.521 |
enegger | +0.520 |
withd | +0.486 |
perce | +0.485 |
Neg logit contributions | |
roud | -0.578 |
rog | -0.481 |
utherland | -0.429 |
rite | -0.416 |
mia | -0.399 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Coy | +0.185 |
unloaded | +0.180 |
enegger | +0.180 |
perce | +0.167 |
thood | +0.166 |
Neg logit contributions | |
roud | -0.283 |
rog | -0.242 |
utherland | -0.219 |
rite | -0.213 |
mia | -0.207 |
Token | Last |
Token ID | 4586 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
unloaded | +2.844 |
Coy | +2.839 |
enegger | +2.788 |
withd | +2.636 |
thood | +2.619 |
Neg logit contributions | |
roud | -3.267 |
rog | -2.738 |
utherland | -2.471 |
rite | -2.391 |
mia | -2.324 |
Token | Edited |
Token ID | 34212 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
unloaded | +0.425 |
Coy | +0.422 |
enegger | +0.411 |
perce | +0.361 |
thood | +0.360 |
Neg logit contributions | |
roud | -1.362 |
rog | -1.205 |
utherland | -1.121 |
rite | -1.101 |
mia | -1.072 |
Token | : |
Token ID | 25 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
unloaded | +0.967 |
Coy | +0.966 |
enegger | +0.931 |
perce | +0.867 |
thood | +0.859 |
Neg logit contributions | |
roud | -1.836 |
rog | -1.583 |
utherland | -1.464 |
rite | -1.419 |
mia | -1.379 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Coy | +0.124 |
unloaded | +0.122 |
enegger | +0.120 |
perce | +0.113 |
thood | +0.111 |
Neg logit contributions | |
roud | -0.170 |
rog | -0.144 |
utherland | -0.131 |
rite | -0.128 |
mia | -0.124 |
Token | - |
Token ID | 12 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
Coy | +0.824 |
unloaded | +0.815 |
enegger | +0.804 |
perce | +0.745 |
thood | +0.739 |
Neg logit contributions | |
roud | -1.235 |
rog | -1.050 |
utherland | -0.962 |
rite | -0.936 |
mia | -0.906 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Coy | +0.502 |
unloaded | +0.501 |
enegger | +0.493 |
withd | +0.456 |
perce | +0.455 |
Neg logit contributions | |
roud | -0.834 |
rog | -0.717 |
utherland | -0.652 |
rite | -0.639 |
mia | -0.619 |
Token | United |
Token ID | 1578 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Coy | +0.441 |
unloaded | +0.438 |
enegger | +0.435 |
withd | +0.404 |
perce | +0.401 |
Neg logit contributions | |
roud | -0.641 |
rog | -0.546 |
utherland | -0.496 |
rite | -0.484 |
mia | -0.469 |
Token | States |
Token ID | 1829 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
unloaded | +1.131 |
Coy | +1.128 |
enegger | +1.118 |
withd | +1.039 |
thood | +1.028 |
Neg logit contributions | |
roud | -1.831 |
rog | -1.577 |
utherland | -1.435 |
rite | -1.400 |
mia | -1.356 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Coy | +0.470 |
unloaded | +0.464 |
enegger | +0.459 |
perce | +0.428 |
withd | +0.425 |
Neg logit contributions | |
roud | -0.597 |
rog | -0.504 |
utherland | -0.455 |
rite | -0.443 |
mia | -0.426 |
Token | 12 |
Token ID | 1065 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Coy | +0.746 |
unloaded | +0.741 |
enegger | +0.740 |
withd | +0.694 |
perce | +0.694 |
Neg logit contributions | |
roud | -0.759 |
rog | -0.627 |
utherland | -0.555 |
rite | -0.540 |
mia | -0.516 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Coy | +0.859 |
unloaded | +0.841 |
enegger | +0.838 |
perce | +0.777 |
thood | +0.776 |
Neg logit contributions | |
roud | -1.288 |
rog | -1.100 |
utherland | -0.993 |
rite | -0.974 |
mia | -0.940 |
Token | # |
Token ID | 1303 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
unloaded | +2.770 |
Coy | +2.764 |
enegger | +2.711 |
withd | +2.571 |
thood | +2.550 |
Neg logit contributions | |
roud | -3.189 |
rog | -2.673 |
utherland | -2.413 |
rite | -2.334 |
mia | -2.270 |
Token | 17 |
Token ID | 1558 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
unloaded | +0.364 |
Coy | +0.361 |
enegger | +0.357 |
perce | +0.338 |
thood | +0.336 |
Neg logit contributions | |
roud | -0.356 |
rog | -0.294 |
utherland | -0.261 |
rite | -0.252 |
Puppet | -0.242 |
Token | Good |
Token ID | 4599 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
roud | +0.041 |
rog | +0.035 |
utherland | +0.032 |
rite | +0.031 |
mia | +0.030 |
Neg logit contributions | |
unloaded | -0.027 |
Coy | -0.027 |
enegger | -0.026 |
withd | -0.025 |
thood | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
roud | +0.549 |
rog | +0.471 |
utherland | +0.426 |
rite | +0.417 |
mia | +0.404 |
Neg logit contributions | |
unloaded | -0.356 |
Coy | -0.353 |
enegger | -0.351 |
withd | -0.328 |
thood | -0.324 |
Token | hear |
Token ID | 3285 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
unloaded | +0.155 |
enegger | +0.154 |
Coy | +0.153 |
withd | +0.142 |
thood | +0.140 |
Neg logit contributions | |
roud | -0.271 |
rog | -0.234 |
utherland | -0.213 |
rite | -0.209 |
mia | -0.203 |
Token | assumed |
Token ID | 9672 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
unloaded | +0.433 |
Coy | +0.428 |
enegger | +0.424 |
perce | +0.398 |
withd | +0.398 |
Neg logit contributions | |
roud | -0.605 |
rog | -0.515 |
utherland | -0.466 |
rite | -0.454 |
mia | -0.438 |
Token | that |
Token ID | 326 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
unloaded | +1.051 |
Coy | +1.044 |
enegger | +1.020 |
perce | +0.952 |
withd | +0.952 |
Neg logit contributions | |
roud | -1.961 |
rog | -1.701 |
utherland | -1.567 |
rite | -1.522 |
foundation | -1.479 |
Token | women |
Token ID | 1466 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
unloaded | +0.382 |
Coy | +0.378 |
enegger | +0.375 |
withd | +0.350 |
perce | +0.346 |
Neg logit contributions | |
roud | -0.631 |
rog | -0.544 |
utherland | -0.494 |
rite | -0.483 |
mia | -0.469 |
Token | with |
Token ID | 351 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
unloaded | +0.868 |
Coy | +0.853 |
enegger | +0.841 |
withd | +0.798 |
perce | +0.793 |
Neg logit contributions | |
roud | -1.313 |
rog | -1.121 |
utherland | -1.021 |
rite | -0.991 |
mia | -0.958 |
Token | younger |
Token ID | 7099 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
roud | +0.192 |
rog | +0.167 |
utherland | +0.152 |
rite | +0.149 |
mia | +0.144 |
Neg logit contributions | |
unloaded | -0.106 |
Coy | -0.105 |
enegger | -0.105 |
withd | -0.097 |
thood | -0.096 |
Token | husbands |
Token ID | 27742 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
unloaded | +0.422 |
Coy | +0.418 |
enegger | +0.411 |
withd | +0.384 |
perce | +0.382 |
Neg logit contributions | |
roud | -0.731 |
rog | -0.632 |
utherland | -0.577 |
rite | -0.562 |
mia | -0.546 |
Token | also |
Token ID | 635 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
unloaded | +2.400 |
Coy | +2.313 |
enegger | +2.252 |
perce | +2.192 |
withd | +2.146 |
Neg logit contributions | |
roud | -3.522 |
rog | -2.997 |
utherland | -2.771 |
rite | -2.652 |
Puppet | -2.587 |
Token | live |
Token ID | 2107 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
unloaded | +0.375 |
Coy | +0.370 |
enegger | +0.367 |
withd | +0.346 |
perce | +0.342 |
Neg logit contributions | |
roud | -0.544 |
rog | -0.465 |
utherland | -0.421 |
rite | -0.410 |
mia | -0.397 |
Token | longer |
Token ID | 2392 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
roud | +0.658 |
rog | +0.588 |
utherland | +0.546 |
rite | +0.540 |
mia | +0.527 |
Neg logit contributions | |
unloaded | -0.159 |
enegger | -0.156 |
Coy | -0.156 |
withd | -0.135 |
thood | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
unloaded | +0.590 |
Coy | +0.583 |
enegger | +0.580 |
withd | +0.540 |
thood | +0.532 |
Neg logit contributions | |
roud | -1.021 |
rog | -0.883 |
utherland | -0.803 |
rite | -0.787 |
mia | -0.763 |
Token | in |
Token ID | 287 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
unloaded | +0.366 |
Coy | +0.363 |
enegger | +0.359 |
withd | +0.336 |
perce | +0.332 |
Neg logit contributions | |
roud | -0.601 |
rog | -0.518 |
utherland | -0.470 |
rite | -0.461 |
mia | -0.446 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Coy | +0.680 |
unloaded | +0.675 |
enegger | +0.664 |
perce | +0.612 |
withd | +0.609 |
Neg logit contributions | |
roud | -1.132 |
rog | -0.975 |
utherland | -0.890 |
rite | -0.869 |
mia | -0.844 |
Token | United |
Token ID | 1578 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Coy | +0.622 |
unloaded | +0.615 |
enegger | +0.612 |
withd | +0.567 |
perce | +0.564 |
Neg logit contributions | |
roud | -0.894 |
rog | -0.761 |
utherland | -0.692 |
rite | -0.675 |
mia | -0.653 |
Token | States |
Token ID | 1829 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
unloaded | +0.986 |
Coy | +0.983 |
enegger | +0.975 |
withd | +0.907 |
thood | +0.895 |
Neg logit contributions | |
roud | -1.595 |
rog | -1.373 |
utherland | -1.250 |
rite | -1.219 |
mia | -1.181 |
Token | 228 |
Token ID | 29041 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
Coy | +0.434 |
unloaded | +0.429 |
enegger | +0.423 |
perce | +0.396 |
withd | +0.393 |
Neg logit contributions | |
roud | -0.547 |
rog | -0.460 |
utherland | -0.417 |
rite | -0.405 |
mia | -0.389 |
Token | 65 |
Token ID | 2996 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
Coy | +0.220 |
unloaded | +0.218 |
enegger | +0.218 |
withd | +0.204 |
perce | +0.203 |
Neg logit contributions | |
roud | -0.251 |
rog | -0.210 |
utherland | -0.186 |
rite | -0.182 |
mia | -0.174 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Coy | +0.150 |
unloaded | +0.148 |
enegger | +0.147 |
perce | +0.135 |
thood | +0.135 |
Neg logit contributions | |
roud | -0.229 |
rog | -0.196 |
utherland | -0.178 |
rite | -0.174 |
mia | -0.168 |
Token | # |
Token ID | 1303 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
unloaded | +2.699 |
Coy | +2.691 |
enegger | +2.633 |
withd | +2.499 |
thood | +2.485 |
Neg logit contributions | |
roud | -3.114 |
rog | -2.608 |
utherland | -2.356 |
rite | -2.279 |
mia | -2.219 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
unloaded | +0.554 |
Coy | +0.549 |
enegger | +0.544 |
perce | +0.508 |
thood | +0.508 |
Neg logit contributions | |
roud | -0.710 |
rog | -0.601 |
utherland | -0.540 |
rite | -0.525 |
mia | -0.508 |
Token | On |
Token ID | 1550 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
unloaded | +0.243 |
Coy | +0.241 |
enegger | +0.239 |
withd | +0.224 |
perce | +0.220 |
Neg logit contributions | |
roud | -0.379 |
rog | -0.325 |
utherland | -0.295 |
rite | -0.288 |
mia | -0.279 |
Token | September |
Token ID | 2693 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
roud | +0.129 |
rog | +0.111 |
utherland | +0.101 |
rite | +0.098 |
mia | +0.095 |
Neg logit contributions | |
unloaded | -0.080 |
Coy | -0.080 |
enegger | -0.079 |
withd | -0.074 |
perce | -0.073 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
roud | +0.492 |
rog | +0.421 |
utherland | +0.378 |
rite | +0.370 |
mia | +0.358 |
Neg logit contributions | |
unloaded | -0.337 |
Coy | -0.333 |
enegger | -0.332 |
withd | -0.313 |
thood | -0.308 |
Token | June |
Token ID | 2795 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Coy | +1.006 |
unloaded | +0.996 |
enegger | +0.959 |
perce | +0.896 |
withd | +0.893 |
Neg logit contributions | |
roud | -1.904 |
rog | -1.645 |
utherland | -1.511 |
rite | -1.481 |
mia | -1.438 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Coy | +0.674 |
unloaded | +0.666 |
enegger | +0.655 |
perce | +0.605 |
withd | +0.602 |
Neg logit contributions | |
roud | -1.162 |
rog | -0.999 |
utherland | -0.914 |
rite | -0.895 |
mia | -0.864 |
Token | Germany |
Token ID | 4486 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Coy | +0.589 |
unloaded | +0.584 |
enegger | +0.580 |
withd | +0.542 |
perce | +0.538 |
Neg logit contributions | |
roud | -0.792 |
rog | -0.671 |
utherland | -0.608 |
rite | -0.593 |
mia | -0.571 |
Token | 247 |
Token ID | 30179 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
roud | +0.036 |
rog | +0.031 |
utherland | +0.028 |
rite | +0.027 |
mia | +0.026 |
Neg logit contributions | |
Coy | -0.029 |
unloaded | -0.029 |
enegger | -0.028 |
perce | -0.026 |
withd | -0.026 |
Token | 34 |
Token ID | 2682 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
Coy | +0.338 |
unloaded | +0.333 |
enegger | +0.333 |
perce | +0.310 |
withd | +0.309 |
Neg logit contributions | |
roud | -0.444 |
rog | -0.378 |
utherland | -0.337 |
rite | -0.329 |
mia | -0.319 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
roud | +0.148 |
rog | +0.126 |
utherland | +0.115 |
rite | +0.112 |
mia | +0.108 |
Neg logit contributions | |
Coy | -0.099 |
unloaded | -0.098 |
enegger | -0.097 |
perce | -0.090 |
thood | -0.090 |
Token | # |
Token ID | 1303 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
unloaded | +2.683 |
Coy | +2.674 |
enegger | +2.627 |
withd | +2.489 |
thood | +2.467 |
Neg logit contributions | |
roud | -3.099 |
rog | -2.596 |
utherland | -2.339 |
rite | -2.262 |
mia | -2.207 |
Token | 20 |
Token ID | 1238 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
unloaded | +0.317 |
Coy | +0.315 |
enegger | +0.311 |
thood | +0.293 |
perce | +0.290 |
Neg logit contributions | |
roud | -0.381 |
rog | -0.320 |
utherland | -0.290 |
rite | -0.279 |
Puppet | -0.269 |
Token | Nice |
Token ID | 18460 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
unloaded | +0.363 |
Coy | +0.360 |
enegger | +0.355 |
withd | +0.334 |
perce | +0.330 |
Neg logit contributions | |
roud | -0.547 |
rog | -0.468 |
utherland | -0.425 |
rite | -0.414 |
mia | -0.402 |
Token | , |
Token ID | 11 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
unloaded | +0.331 |
Coy | +0.328 |
enegger | +0.323 |
withd | +0.304 |
perce | +0.300 |
Neg logit contributions | |
roud | -0.542 |
rog | -0.467 |
utherland | -0.424 |
rite | -0.415 |
mia | -0.403 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
roud | +0.240 |
rog | +0.206 |
utherland | +0.188 |
rite | +0.183 |
mia | +0.178 |
Neg logit contributions | |
unloaded | -0.147 |
Coy | -0.146 |
enegger | -0.144 |
withd | -0.135 |
perce | -0.133 |
Token | momentum |
Token ID | 12858 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
roud | +0.446 |
rog | +0.384 |
utherland | +0.348 |
rite | +0.341 |
mia | +0.330 |
Neg logit contributions | |
unloaded | -0.280 |
Coy | -0.277 |
enegger | -0.275 |
withd | -0.257 |
perce | -0.254 |
Token | going |
Token ID | 1016 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
roud | +0.639 |
rog | +0.557 |
utherland | +0.509 |
rite | +0.500 |
mia | +0.486 |
Neg logit contributions | |
unloaded | -0.311 |
Coy | -0.308 |
enegger | -0.308 |
withd | -0.283 |
thood | -0.279 |
Token | ," |
Token ID | 553 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
unloaded | +0.286 |
Coy | +0.283 |
enegger | +0.282 |
withd | +0.262 |
thood | +0.260 |
Neg logit contributions | |
roud | -0.476 |
rog | -0.410 |
utherland | -0.372 |
rite | -0.364 |
mia | -0.354 |
Token | he |
Token ID | 339 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
unloaded | +0.614 |
Coy | +0.614 |
enegger | +0.602 |
withd | +0.567 |
perce | +0.560 |
Neg logit contributions | |
roud | -0.905 |
rog | -0.774 |
utherland | -0.701 |
rite | -0.685 |
mia | -0.663 |
Token | signs |
Token ID | 5895 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
unloaded | +0.210 |
Coy | +0.208 |
enegger | +0.207 |
withd | +0.194 |
thood | +0.191 |
Neg logit contributions | |
roud | -0.308 |
rog | -0.263 |
utherland | -0.238 |
rite | -0.232 |
mia | -0.225 |
Token | off |
Token ID | 572 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
unloaded | +0.022 |
Coy | +0.022 |
enegger | +0.022 |
withd | +0.020 |
thood | +0.019 |
Neg logit contributions | |
roud | -0.060 |
rog | -0.053 |
utherland | -0.049 |
rite | -0.048 |
mia | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
unloaded | +2.068 |
Coy | +2.055 |
enegger | +2.009 |
withd | +1.888 |
perce | +1.858 |
Neg logit contributions | |
roud | -3.729 |
rog | -3.225 |
utherland | -2.966 |
rite | -2.899 |
mia | -2.829 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
Coy | +0.729 |
unloaded | +0.721 |
enegger | +0.718 |
withd | +0.668 |
thood | +0.663 |
Neg logit contributions | |
roud | -0.998 |
rog | -0.845 |
utherland | -0.764 |
rite | -0.745 |
mia | -0.720 |
Token | The |
Token ID | 464 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
unloaded | +0.136 |
Coy | +0.136 |
enegger | +0.135 |
thood | +0.127 |
withd | +0.126 |
Neg logit contributions | |
roud | -0.140 |
rog | -0.115 |
utherland | -0.104 |
rite | -0.100 |
Puppet | -0.096 |
Token | city |
Token ID | 1748 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
unloaded | +0.213 |
Coy | +0.212 |
enegger | +0.210 |
withd | +0.196 |
perce | +0.194 |
Neg logit contributions | |
roud | -0.328 |
rog | -0.282 |
utherland | -0.255 |
rite | -0.249 |
mia | -0.241 |
Token | of |
Token ID | 286 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
unloaded | +0.116 |
Coy | +0.115 |
enegger | +0.114 |
withd | +0.107 |
thood | +0.105 |
Neg logit contributions | |
roud | -0.183 |
rog | -0.157 |
utherland | -0.142 |
rite | -0.139 |
mia | -0.135 |
Token | by |
Token ID | 416 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
unloaded | +0.066 |
Coy | +0.065 |
enegger | +0.065 |
withd | +0.060 |
thood | +0.059 |
Neg logit contributions | |
roud | -0.117 |
rog | -0.101 |
utherland | -0.092 |
rite | -0.091 |
mia | -0.088 |
Token | Buddhism |
Token ID | 25932 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
roud | +0.094 |
rog | +0.081 |
utherland | +0.074 |
rite | +0.073 |
mia | +0.070 |
Neg logit contributions | |
unloaded | -0.052 |
Coy | -0.052 |
enegger | -0.052 |
withd | -0.048 |
thood | -0.047 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
roud | +0.290 |
rog | +0.248 |
utherland | +0.223 |
rite | +0.218 |
mia | +0.211 |
Neg logit contributions | |
unloaded | -0.206 |
Coy | -0.204 |
enegger | -0.204 |
withd | -0.191 |
thood | -0.189 |
Token | " |
Token ID | 1 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
unloaded | +0.136 |
Coy | +0.135 |
enegger | +0.134 |
thood | +0.127 |
withd | +0.126 |
Neg logit contributions | |
roud | -0.140 |
rog | -0.115 |
utherland | -0.104 |
rite | -0.100 |
Puppet | -0.096 |
Token | Sec |
Token ID | 6558 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Coy | +0.571 |
unloaded | +0.568 |
enegger | +0.561 |
withd | +0.530 |
thood | +0.528 |
Neg logit contributions | |
roud | -0.624 |
rog | -0.516 |
utherland | -0.464 |
rite | -0.447 |
mia | -0.430 |
Token | rets |
Token ID | 8004 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
unloaded | +0.947 |
Coy | +0.943 |
enegger | +0.928 |
withd | +0.883 |
thood | +0.875 |
Neg logit contributions | |
roud | -1.116 |
rog | -0.937 |
utherland | -0.837 |
rite | -0.819 |
mia | -0.795 |
Token | of |
Token ID | 286 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
unloaded | +2.103 |
Coy | +2.079 |
enegger | +1.993 |
withd | +1.877 |
perce | +1.864 |
Neg logit contributions | |
roud | -3.689 |
rog | -3.166 |
utherland | -2.926 |
rite | -2.825 |
mia | -2.776 |
Token | Season |
Token ID | 7369 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
unloaded | +0.467 |
Coy | +0.465 |
enegger | +0.460 |
withd | +0.431 |
thood | +0.428 |
Neg logit contributions | |
roud | -0.660 |
rog | -0.563 |
utherland | -0.510 |
rite | -0.497 |
mia | -0.481 |
Token | One |
Token ID | 1881 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
unloaded | +0.295 |
Coy | +0.293 |
enegger | +0.291 |
withd | +0.274 |
thood | +0.271 |
Neg logit contributions | |
roud | -0.398 |
rog | -0.339 |
utherland | -0.304 |
rite | -0.297 |
mia | -0.287 |
Token | " |
Token ID | 366 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
roud | +0.636 |
rog | +0.549 |
utherland | +0.498 |
rite | +0.488 |
mia | +0.474 |
Neg logit contributions | |
unloaded | -0.375 |
enegger | -0.371 |
Coy | -0.370 |
withd | -0.344 |
thood | -0.339 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
unloaded | +0.767 |
Coy | +0.761 |
enegger | +0.750 |
withd | +0.710 |
perce | +0.698 |
Neg logit contributions | |
roud | -1.094 |
rog | -0.930 |
utherland | -0.843 |
rite | -0.820 |
mia | -0.797 |
Token | without |
Token ID | 1231 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
roud | +0.320 |
rog | +0.277 |
utherland | +0.252 |
rite | +0.248 |
mia | +0.241 |
Neg logit contributions | |
unloaded | -0.182 |
Coy | -0.180 |
enegger | -0.178 |
withd | -0.166 |
perce | -0.165 |
Token | knowing |
Token ID | 6970 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
unloaded | +0.554 |
Coy | +0.550 |
enegger | +0.541 |
perce | +0.506 |
withd | +0.501 |
Neg logit contributions | |
roud | -1.061 |
rog | -0.923 |
utherland | -0.842 |
rite | -0.827 |
mia | -0.804 |
Token | the |
Token ID | 262 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
roud | +0.008 |
rog | +0.007 |
utherland | +0.007 |
rite | +0.006 |
mia | +0.006 |
Neg logit contributions | |
unloaded | -0.005 |
Coy | -0.005 |
enegger | -0.005 |
withd | -0.004 |
perce | -0.004 |
Token | magnitude |
Token ID | 14735 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
roud | +0.229 |
rog | +0.198 |
utherland | +0.179 |
rite | +0.175 |
mia | +0.170 |
Neg logit contributions | |
unloaded | -0.144 |
Coy | -0.143 |
enegger | -0.141 |
perce | -0.132 |
withd | -0.131 |
Token | of |
Token ID | 286 |
Feature activation | +9.69e-02 |
Pos logit contributions | |
unloaded | +0.394 |
Coy | +0.390 |
enegger | +0.387 |
withd | +0.361 |
thood | +0.356 |
Neg logit contributions | |
roud | -0.681 |
rog | -0.589 |
utherland | -0.535 |
rite | -0.524 |
mia | -0.509 |
Token | signals |
Token ID | 10425 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
roud | +0.291 |
rog | +0.249 |
utherland | +0.224 |
rite | +0.220 |
mia | +0.213 |
Neg logit contributions | |
unloaded | -0.205 |
Coy | -0.203 |
enegger | -0.201 |
withd | -0.188 |
perce | -0.188 |
Token | in |
Token ID | 287 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
unloaded | +1.991 |
Coy | +1.962 |
enegger | +1.876 |
perce | +1.824 |
withd | +1.749 |
Neg logit contributions | |
roud | -3.791 |
rog | -3.307 |
utherland | -3.035 |
rite | -2.976 |
foundation | -2.884 |
Token | them |
Token ID | 606 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
roud | +0.063 |
rog | +0.054 |
utherland | +0.049 |
rite | +0.048 |
mia | +0.047 |
Neg logit contributions | |
unloaded | -0.036 |
Coy | -0.036 |
enegger | -0.036 |
withd | -0.033 |
perce | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
unloaded | +0.012 |
Coy | +0.012 |
enegger | +0.012 |
withd | +0.011 |
thood | +0.011 |
Neg logit contributions | |
roud | -0.019 |
rog | -0.016 |
utherland | -0.014 |
rite | -0.014 |
mia | -0.014 |
Token | � |
Token ID | 564 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
roud | +0.310 |
rog | +0.265 |
utherland | +0.240 |
rite | +0.235 |
mia | +0.228 |
Neg logit contributions | |
Coy | -0.205 |
unloaded | -0.205 |
enegger | -0.203 |
withd | -0.189 |
perce | -0.188 |
Token | � |
Token ID | 250 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
roud | +0.311 |
rog | +0.263 |
utherland | +0.239 |
rite | +0.232 |
mia | +0.224 |
Neg logit contributions | |
unloaded | -0.223 |
Coy | -0.220 |
enegger | -0.219 |
perce | -0.204 |
thood | -0.203 |
Token | ist |
Token ID | 396 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
roud | +1.051 |
rog | +0.880 |
utherland | +0.783 |
rite | +0.762 |
mia | +0.735 |
Neg logit contributions | |
unloaded | -0.939 |
Coy | -0.934 |
enegger | -0.924 |
withd | -0.878 |
perce | -0.870 |
Token | ," |
Token ID | 553 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
roud | +0.760 |
rog | +0.657 |
utherland | +0.598 |
rite | +0.586 |
mia | +0.569 |
Neg logit contributions | |
unloaded | -0.430 |
Coy | -0.426 |
enegger | -0.424 |
withd | -0.394 |
thood | -0.389 |
Token | according |
Token ID | 1864 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
roud | +0.815 |
rog | +0.697 |
utherland | +0.628 |
rite | +0.615 |
mia | +0.596 |
Neg logit contributions | |
unloaded | -0.550 |
Coy | -0.545 |
enegger | -0.544 |
withd | -0.509 |
thood | -0.505 |
Token | to |
Token ID | 284 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
unloaded | +0.011 |
Coy | +0.011 |
enegger | +0.011 |
perce | +0.010 |
thood | +0.010 |
Neg logit contributions | |
roud | -0.019 |
rog | -0.016 |
utherland | -0.015 |
rite | -0.014 |
mia | -0.014 |
Token | former |
Token ID | 1966 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
unloaded | +0.036 |
Coy | +0.036 |
enegger | +0.035 |
withd | +0.033 |
perce | +0.033 |
Neg logit contributions | |
roud | -0.052 |
rog | -0.044 |
utherland | -0.040 |
rite | -0.039 |
mia | -0.038 |
Token | Vice |
Token ID | 11079 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
roud | +0.864 |
rog | +0.736 |
utherland | +0.661 |
rite | +0.647 |
mia | +0.626 |
Neg logit contributions | |
unloaded | -0.615 |
enegger | -0.609 |
Coy | -0.608 |
withd | -0.572 |
thood | -0.566 |
Token | President |
Token ID | 1992 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Coy | +2.704 |
unloaded | +2.694 |
enegger | +2.661 |
perce | +2.523 |
thood | +2.494 |
Neg logit contributions | |
roud | -2.974 |
rog | -2.530 |
utherland | -2.284 |
rite | -2.196 |
mia | -2.104 |
Token | Dick |
Token ID | 11740 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
unloaded | +0.304 |
Coy | +0.302 |
enegger | +0.297 |
withd | +0.279 |
perce | +0.278 |
Neg logit contributions | |
roud | -0.409 |
rog | -0.349 |
utherland | -0.314 |
rite | -0.307 |
mia | -0.295 |
Token | Cheney |
Token ID | 31287 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
roud | +0.693 |
rog | +0.580 |
utherland | +0.513 |
rite | +0.502 |
mia | +0.484 |
Neg logit contributions | |
unloaded | -0.590 |
Coy | -0.583 |
enegger | -0.583 |
withd | -0.556 |
thood | -0.551 |
Token | , |
Token ID | 11 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
unloaded | +0.668 |
Coy | +0.661 |
enegger | +0.657 |
withd | +0.608 |
perce | +0.601 |
Neg logit contributions | |
roud | -1.155 |
rog | -1.001 |
utherland | -0.915 |
rite | -0.892 |
mia | -0.867 |
Token | who |
Token ID | 508 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
unloaded | +0.058 |
Coy | +0.057 |
enegger | +0.056 |
withd | +0.052 |
perce | +0.052 |
Neg logit contributions | |
roud | -0.110 |
rog | -0.095 |
utherland | -0.087 |
rite | -0.086 |
mia | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
unloaded | +0.026 |
Coy | +0.026 |
enegger | +0.026 |
withd | +0.024 |
thood | +0.024 |
Neg logit contributions | |
roud | -0.041 |
rog | -0.035 |
utherland | -0.032 |
rite | -0.031 |
mia | -0.030 |
Token | whose |
Token ID | 3025 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
unloaded | +0.173 |
Coy | +0.172 |
enegger | +0.171 |
withd | +0.158 |
perce | +0.157 |
Neg logit contributions | |
roud | -0.293 |
rog | -0.252 |
utherland | -0.231 |
rite | -0.226 |
mia | -0.219 |
Token | confid |
Token ID | 47830 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
unloaded | +0.135 |
Coy | +0.134 |
enegger | +0.133 |
withd | +0.124 |
perce | +0.122 |
Neg logit contributions | |
roud | -0.217 |
rog | -0.186 |
utherland | -0.170 |
rite | -0.166 |
mia | -0.160 |
Token | ant |
Token ID | 415 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
unloaded | +0.629 |
Coy | +0.626 |
enegger | +0.622 |
withd | +0.583 |
thood | +0.583 |
Neg logit contributions | |
roud | -0.744 |
rog | -0.623 |
utherland | -0.564 |
rite | -0.542 |
mia | -0.528 |
Token | and |
Token ID | 290 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
unloaded | +0.283 |
Coy | +0.281 |
enegger | +0.277 |
withd | +0.259 |
perce | +0.257 |
Neg logit contributions | |
roud | -0.431 |
rog | -0.370 |
utherland | -0.336 |
rite | -0.328 |
mia | -0.318 |
Token | vice |
Token ID | 7927 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
unloaded | +0.103 |
Coy | +0.103 |
enegger | +0.101 |
withd | +0.095 |
perce | +0.094 |
Neg logit contributions | |
roud | -0.152 |
rog | -0.130 |
utherland | -0.119 |
rite | -0.115 |
mia | -0.112 |
Token | president |
Token ID | 1893 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
unloaded | +2.472 |
Coy | +2.455 |
enegger | +2.440 |
perce | +2.320 |
withd | +2.294 |
Neg logit contributions | |
roud | -3.091 |
rog | -2.608 |
utherland | -2.394 |
rite | -2.305 |
mia | -2.247 |
Token | he |
Token ID | 339 |
Feature activation | -9.57e-05 |
Pos logit contributions | |
unloaded | +0.503 |
Coy | +0.499 |
enegger | +0.494 |
withd | +0.459 |
perce | +0.456 |
Neg logit contributions | |
roud | -0.763 |
rog | -0.653 |
utherland | -0.592 |
rite | -0.579 |
mia | -0.561 |
Token | was |
Token ID | 373 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
unloaded | +0.000 |
Coy | +0.000 |
enegger | +0.000 |
withd | +0.000 |
perce | +0.000 |
Neg logit contributions | |
roud | -0.000 |
rog | -0.000 |
utherland | -0.000 |
rite | -0.000 |
mia | -0.000 |
Token | ], |
Token ID | 4357 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
unloaded | +0.103 |
Coy | +0.102 |
enegger | +0.102 |
withd | +0.095 |
perce | +0.094 |
Neg logit contributions | |
roud | -0.162 |
rog | -0.139 |
utherland | -0.126 |
rite | -0.123 |
mia | -0.119 |
Token | and |
Token ID | 290 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
unloaded | +0.138 |
Coy | +0.137 |
enegger | +0.135 |
withd | +0.126 |
perce | +0.124 |
Neg logit contributions | |
roud | -0.263 |
rog | -0.228 |
utherland | -0.209 |
rite | -0.205 |
mia | -0.200 |
Token | signed |
Token ID | 4488 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
roud | +0.714 |
rog | +0.611 |
utherland | +0.550 |
rite | +0.540 |
mia | +0.524 |
Neg logit contributions | |
unloaded | -0.472 |
enegger | -0.471 |
Coy | -0.471 |
withd | -0.440 |
thood | -0.437 |
Token | a |
Token ID | 257 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
unloaded | +0.399 |
Coy | +0.395 |
enegger | +0.393 |
withd | +0.367 |
thood | +0.362 |
Neg logit contributions | |
roud | -0.647 |
rog | -0.557 |
utherland | -0.505 |
rite | -0.495 |
mia | -0.480 |
Token | two |
Token ID | 734 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
unloaded | +0.444 |
Coy | +0.440 |
enegger | +0.439 |
withd | +0.411 |
thood | +0.406 |
Neg logit contributions | |
roud | -0.632 |
rog | -0.540 |
utherland | -0.486 |
rite | -0.475 |
mia | -0.460 |
Token | - |
Token ID | 12 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
roud | +0.181 |
rog | +0.155 |
utherland | +0.138 |
rite | +0.135 |
mia | +0.130 |
Neg logit contributions | |
enegger | -0.141 |
unloaded | -0.141 |
Coy | -0.140 |
withd | -0.131 |
thood | -0.130 |
Token | year |
Token ID | 1941 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
unloaded | +1.064 |
Coy | +1.057 |
enegger | +1.042 |
withd | +1.006 |
thood | +0.994 |
Neg logit contributions | |
roud | -0.935 |
rog | -0.755 |
utherland | -0.668 |
rite | -0.634 |
Puppet | -0.614 |
Token | contract |
Token ID | 2775 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
unloaded | +0.370 |
Coy | +0.367 |
enegger | +0.364 |
withd | +0.342 |
thood | +0.338 |
Neg logit contributions | |
roud | -0.545 |
rog | -0.467 |
utherland | -0.421 |
rite | -0.412 |
mia | -0.399 |
Token | with |
Token ID | 351 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
unloaded | +1.834 |
Coy | +1.800 |
enegger | +1.740 |
withd | +1.684 |
perce | +1.627 |
Neg logit contributions | |
roud | -3.792 |
rog | -3.302 |
utherland | -3.038 |
rite | -2.950 |
mia | -2.892 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
unloaded | +0.231 |
Coy | +0.229 |
enegger | +0.227 |
withd | +0.214 |
thood | +0.211 |
Neg logit contributions | |
roud | -0.311 |
rog | -0.264 |
utherland | -0.237 |
rite | -0.232 |
mia | -0.224 |
Token | 76 |
Token ID | 8684 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
unloaded | +0.216 |
enegger | +0.214 |
Coy | +0.213 |
withd | +0.200 |
thood | +0.197 |
Neg logit contributions | |
roud | -0.333 |
rog | -0.285 |
utherland | -0.258 |
rite | -0.253 |
mia | -0.245 |
Token | ers |
Token ID | 364 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
unloaded | +0.564 |
Coy | +0.561 |
enegger | +0.550 |
perce | +0.510 |
thood | +0.503 |
Neg logit contributions | |
roud | -1.060 |
rog | -0.919 |
utherland | -0.842 |
rite | -0.825 |
mia | -0.799 |
Token | on |
Token ID | 319 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
unloaded | +0.602 |
Coy | +0.595 |
enegger | +0.589 |
withd | +0.550 |
perce | +0.540 |
Neg logit contributions | |
roud | -1.105 |
rog | -0.958 |
utherland | -0.874 |
rite | -0.856 |
mia | -0.831 |
Token | signed |
Token ID | 4488 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
unloaded | +0.113 |
Coy | +0.111 |
enegger | +0.110 |
withd | +0.103 |
perce | +0.102 |
Neg logit contributions | |
roud | -0.177 |
rog | -0.152 |
utherland | -0.138 |
rite | -0.135 |
mia | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
unloaded | +0.214 |
Coy | +0.212 |
enegger | +0.209 |
withd | +0.197 |
perce | +0.193 |
Neg logit contributions | |
roud | -0.345 |
rog | -0.296 |
utherland | -0.268 |
rite | -0.262 |
mia | -0.254 |
Token | five |
Token ID | 1936 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
unloaded | +0.450 |
Coy | +0.447 |
enegger | +0.438 |
withd | +0.416 |
perce | +0.409 |
Neg logit contributions | |
roud | -0.666 |
rog | -0.570 |
utherland | -0.516 |
rite | -0.504 |
mia | -0.487 |
Token | - |
Token ID | 12 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
unloaded | +0.482 |
Coy | +0.477 |
enegger | +0.475 |
withd | +0.447 |
thood | +0.441 |
Neg logit contributions | |
roud | -0.662 |
rog | -0.563 |
utherland | -0.507 |
rite | -0.495 |
mia | -0.479 |
Token | year |
Token ID | 1941 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
unloaded | +1.088 |
Coy | +1.083 |
enegger | +1.059 |
withd | +1.021 |
thood | +1.016 |
Neg logit contributions | |
roud | -1.000 |
rog | -0.804 |
utherland | -0.718 |
rite | -0.675 |
Puppet | -0.662 |
Token | contract |
Token ID | 2775 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
unloaded | +0.583 |
Coy | +0.578 |
enegger | +0.565 |
withd | +0.533 |
thood | +0.524 |
Neg logit contributions | |
roud | -1.017 |
rog | -0.879 |
utherland | -0.803 |
rite | -0.784 |
mia | -0.758 |
Token | that |
Token ID | 326 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
unloaded | +1.850 |
Coy | +1.814 |
enegger | +1.729 |
withd | +1.661 |
perce | +1.620 |
Neg logit contributions | |
roud | -3.783 |
rog | -3.285 |
utherland | -3.028 |
rite | -2.945 |
mia | -2.872 |
Token | offseason |
Token ID | 16349 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
unloaded | +0.498 |
Coy | +0.489 |
enegger | +0.476 |
withd | +0.454 |
perce | +0.449 |
Neg logit contributions | |
roud | -0.729 |
rog | -0.622 |
utherland | -0.566 |
rite | -0.552 |
foundation | -0.533 |
Token | , |
Token ID | 11 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
unloaded | +0.037 |
Coy | +0.036 |
enegger | +0.036 |
withd | +0.034 |
thood | +0.033 |
Neg logit contributions | |
roud | -0.066 |
rog | -0.057 |
utherland | -0.052 |
rite | -0.051 |
mia | -0.049 |
Token | worth |
Token ID | 2861 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
unloaded | +0.176 |
Coy | +0.173 |
enegger | +0.168 |
withd | +0.159 |
perce | +0.157 |
Neg logit contributions | |
roud | -0.333 |
rog | -0.288 |
utherland | -0.264 |
rite | -0.259 |
mia | -0.251 |
Token | a |
Token ID | 257 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
unloaded | +1.342 |
Coy | +1.335 |
enegger | +1.276 |
perce | +1.226 |
withd | +1.221 |
Neg logit contributions | |
roud | -1.557 |
rog | -1.292 |
utherland | -1.168 |
rite | -1.140 |
foundation | -1.084 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Coy | +0.463 |
unloaded | +0.462 |
enegger | +0.455 |
withd | +0.422 |
perce | +0.421 |
Neg logit contributions | |
roud | -0.739 |
rog | -0.634 |
utherland | -0.576 |
rite | -0.564 |
mia | -0.546 |
Token | United |
Token ID | 1578 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
Coy | +0.452 |
unloaded | +0.448 |
enegger | +0.445 |
withd | +0.415 |
perce | +0.412 |
Neg logit contributions | |
roud | -0.623 |
rog | -0.530 |
utherland | -0.480 |
rite | -0.468 |
mia | -0.453 |
Token | States |
Token ID | 1829 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Coy | +1.145 |
unloaded | +1.145 |
enegger | +1.132 |
withd | +1.050 |
thood | +1.038 |
Neg logit contributions | |
roud | -1.896 |
rog | -1.637 |
utherland | -1.493 |
rite | -1.454 |
mia | -1.409 |
Token | 21 |
Token ID | 2310 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Coy | +0.522 |
unloaded | +0.516 |
enegger | +0.509 |
perce | +0.476 |
withd | +0.473 |
Neg logit contributions | |
roud | -0.668 |
rog | -0.563 |
utherland | -0.509 |
rite | -0.496 |
mia | -0.477 |
Token | 50 |
Token ID | 1120 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
Coy | +0.773 |
unloaded | +0.757 |
enegger | +0.753 |
perce | +0.706 |
withd | +0.703 |
Neg logit contributions | |
roud | -1.014 |
rog | -0.855 |
utherland | -0.774 |
rite | -0.748 |
mia | -0.726 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
roud | +0.104 |
rog | +0.089 |
utherland | +0.081 |
rite | +0.078 |
mia | +0.076 |
Neg logit contributions | |
Coy | -0.070 |
unloaded | -0.070 |
enegger | -0.069 |
perce | -0.064 |
thood | -0.064 |
Token | # |
Token ID | 1303 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
unloaded | +2.579 |
Coy | +2.570 |
enegger | +2.524 |
withd | +2.395 |
thood | +2.372 |
Neg logit contributions | |
roud | -2.948 |
rog | -2.468 |
utherland | -2.226 |
rite | -2.154 |
mia | -2.096 |
Token | 16 |
Token ID | 1433 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
unloaded | +0.358 |
Coy | +0.354 |
enegger | +0.351 |
withd | +0.330 |
perce | +0.329 |
Neg logit contributions | |
roud | -0.415 |
rog | -0.348 |
utherland | -0.313 |
rite | -0.302 |
Puppet | -0.292 |
Token | Glad |
Token ID | 28442 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
unloaded | +0.209 |
Coy | +0.207 |
enegger | +0.205 |
withd | +0.192 |
perce | +0.190 |
Neg logit contributions | |
roud | -0.325 |
rog | -0.279 |
utherland | -0.253 |
rite | -0.247 |
mia | -0.240 |
Token | to |
Token ID | 284 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
roud | +0.079 |
rog | +0.068 |
utherland | +0.062 |
rite | +0.060 |
mia | +0.059 |
Neg logit contributions | |
unloaded | -0.049 |
Coy | -0.049 |
enegger | -0.049 |
withd | -0.045 |
perce | -0.045 |
Token | hear |
Token ID | 3285 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
unloaded | +0.117 |
enegger | +0.116 |
Coy | +0.116 |
withd | +0.107 |
thood | +0.106 |
Neg logit contributions | |
roud | -0.215 |
rog | -0.186 |
utherland | -0.169 |
rite | -0.167 |
mia | -0.162 |
Token | 22 |
Token ID | 2534 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
roud | +1.902 |
rog | +1.585 |
utherland | +1.391 |
rite | +1.380 |
Puppet | +1.339 |
Neg logit contributions | |
enegger | -1.603 |
unloaded | -1.600 |
Coy | -1.584 |
thood | -1.519 |
withd | -1.518 |
Token | . |
Token ID | 13 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
unloaded | +0.028 |
Coy | +0.028 |
enegger | +0.027 |
perce | +0.025 |
thood | +0.025 |
Neg logit contributions | |
roud | -0.048 |
rog | -0.042 |
utherland | -0.038 |
rite | -0.037 |
mia | -0.036 |
Token | R |
Token ID | 371 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
roud | +1.276 |
rog | +1.099 |
utherland | +0.989 |
rite | +0.974 |
mia | +0.946 |
Neg logit contributions | |
unloaded | -0.794 |
enegger | -0.789 |
Coy | -0.785 |
withd | -0.733 |
thood | -0.729 |
Token | c |
Token ID | 66 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
roud | +0.351 |
rog | +0.302 |
utherland | +0.274 |
rite | +0.268 |
mia | +0.260 |
Neg logit contributions | |
unloaded | -0.217 |
Coy | -0.214 |
enegger | -0.213 |
withd | -0.199 |
thood | -0.197 |
Token | 3 |
Token ID | 18 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
roud | +0.447 |
rog | +0.370 |
utherland | +0.327 |
rite | +0.317 |
mia | +0.304 |
Neg logit contributions | |
unloaded | -0.441 |
Coy | -0.437 |
enegger | -0.435 |
withd | -0.413 |
thood | -0.409 |
Token | { |
Token ID | 1391 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
roud | +0.625 |
rog | +0.510 |
utherland | +0.439 |
rite | +0.430 |
mia | +0.411 |
Neg logit contributions | |
unloaded | -0.712 |
enegger | -0.707 |
Coy | -0.706 |
withd | -0.672 |
thood | -0.666 |
Token | ( |
Token ID | 7 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
roud | +3.450 |
rog | +2.976 |
utherland | +2.643 |
rite | +2.622 |
mia | +2.553 |
Neg logit contributions | |
unloaded | -2.245 |
enegger | -2.224 |
Coy | -2.206 |
withd | -2.160 |
proble | -2.102 |
Token | 270 |
Token ID | 20233 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
roud | +1.181 |
rog | +0.983 |
utherland | +0.872 |
rite | +0.848 |
mia | +0.814 |
Neg logit contributions | |
unloaded | -1.105 |
Coy | -1.099 |
enegger | -1.094 |
withd | -1.034 |
thood | -1.024 |
Token | s |
Token ID | 82 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
roud | +0.580 |
rog | +0.497 |
utherland | +0.455 |
rite | +0.442 |
mia | +0.429 |
Neg logit contributions | |
unloaded | -0.353 |
Coy | -0.350 |
enegger | -0.346 |
perce | -0.320 |
withd | -0.319 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
roud | +0.321 |
rog | +0.258 |
utherland | +0.224 |
rite | +0.215 |
mia | +0.204 |
Neg logit contributions | |
unloaded | -0.405 |
Coy | -0.403 |
enegger | -0.402 |
perce | -0.379 |
thood | -0.379 |
Token | Rac |
Token ID | 24746 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
roud | +2.101 |
rog | +1.808 |
utherland | +1.614 |
rite | +1.600 |
Puppet | +1.556 |
Neg logit contributions | |
enegger | -1.324 |
unloaded | -1.323 |
Coy | -1.304 |
thood | -1.229 |
withd | -1.228 |
Token | { |
Token ID | 1391 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
roud | +1.367 |
rog | +1.118 |
utherland | +0.977 |
rite | +0.946 |
mia | +0.905 |
Neg logit contributions | |
unloaded | -1.515 |
Coy | -1.506 |
enegger | -1.498 |
withd | -1.421 |
perce | -1.411 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
roud | +3.316 |
rog | +2.843 |
utherland | +2.520 |
rite | +2.487 |
mia | +2.435 |
Neg logit contributions | |
unloaded | -2.394 |
Coy | -2.343 |
enegger | -2.341 |
withd | -2.256 |
perce | -2.186 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
unloaded | +0.190 |
Coy | +0.189 |
enegger | +0.186 |
perce | +0.169 |
thood | +0.169 |
Neg logit contributions | |
roud | -0.361 |
rog | -0.313 |
utherland | -0.288 |
rite | -0.280 |
mia | -0.272 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
roud | +0.300 |
rog | +0.254 |
utherland | +0.227 |
rite | +0.223 |
mia | +0.214 |
Neg logit contributions | |
unloaded | -0.233 |
Coy | -0.230 |
enegger | -0.230 |
withd | -0.217 |
thood | -0.214 |
Token | }, |
Token ID | 5512 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
unloaded | +0.304 |
Coy | +0.302 |
enegger | +0.300 |
withd | +0.281 |
perce | +0.280 |
Neg logit contributions | |
roud | -0.360 |
rog | -0.303 |
utherland | -0.271 |
rite | -0.263 |
mia | -0.255 |
Token | { |
Token ID | 1391 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
roud | +1.392 |
rog | +1.139 |
utherland | +0.996 |
rite | +0.964 |
mia | +0.922 |
Neg logit contributions | |
unloaded | -1.540 |
Coy | -1.530 |
enegger | -1.522 |
withd | -1.442 |
perce | -1.433 |
Token | 9 |
Token ID | 24 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
roud | +3.100 |
rog | +2.638 |
utherland | +2.312 |
rite | +2.289 |
mia | +2.241 |
Neg logit contributions | |
unloaded | -2.466 |
enegger | -2.422 |
Coy | -2.416 |
withd | -2.318 |
perce | -2.274 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
unloaded | +0.073 |
Coy | +0.073 |
enegger | +0.072 |
perce | +0.065 |
thood | +0.065 |
Neg logit contributions | |
roud | -0.139 |
rog | -0.120 |
utherland | -0.111 |
rite | -0.108 |
mia | -0.105 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
roud | +0.533 |
rog | +0.450 |
utherland | +0.402 |
rite | +0.394 |
mia | +0.378 |
Neg logit contributions | |
unloaded | -0.420 |
Coy | -0.415 |
enegger | -0.414 |
withd | -0.393 |
thood | -0.387 |
Token | }, |
Token ID | 5512 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
roud | +0.307 |
rog | +0.257 |
utherland | +0.229 |
rite | +0.223 |
mia | +0.215 |
Neg logit contributions | |
unloaded | -0.264 |
Coy | -0.262 |
enegger | -0.261 |
withd | -0.246 |
thood | -0.244 |
Token | { |
Token ID | 1391 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
roud | +1.445 |
rog | +1.183 |
utherland | +1.034 |
rite | +1.001 |
mia | +0.957 |
Neg logit contributions | |
unloaded | -1.601 |
Coy | -1.591 |
enegger | -1.582 |
withd | -1.500 |
perce | -1.490 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
roud | +0.211 |
rog | +0.179 |
utherland | +0.160 |
rite | +0.156 |
mia | +0.151 |
Neg logit contributions | |
unloaded | -0.160 |
Coy | -0.159 |
enegger | -0.158 |
withd | -0.149 |
thood | -0.147 |
Token | site |
Token ID | 2524 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
roud | +0.039 |
rog | +0.033 |
utherland | +0.030 |
rite | +0.029 |
mia | +0.028 |
Neg logit contributions | |
unloaded | -0.028 |
Coy | -0.028 |
enegger | -0.028 |
withd | -0.026 |
perce | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
roud | +0.716 |
rog | +0.609 |
utherland | +0.547 |
rite | +0.535 |
mia | +0.516 |
Neg logit contributions | |
unloaded | -0.529 |
Coy | -0.524 |
enegger | -0.522 |
withd | -0.491 |
thood | -0.485 |
Token | magn |
Token ID | 7842 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
unloaded | +0.382 |
Coy | +0.380 |
enegger | +0.376 |
withd | +0.351 |
perce | +0.347 |
Neg logit contributions | |
roud | -0.580 |
rog | -0.498 |
utherland | -0.450 |
rite | -0.440 |
mia | -0.427 |
Token | ifying |
Token ID | 4035 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
unloaded | +1.120 |
Coy | +1.105 |
enegger | +1.095 |
withd | +1.034 |
thood | +1.028 |
Neg logit contributions | |
roud | -1.272 |
rog | -1.062 |
utherland | -0.959 |
rite | -0.923 |
mia | -0.897 |
Token | glass |
Token ID | 5405 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
roud | +0.638 |
rog | +0.516 |
utherland | +0.446 |
rite | +0.431 |
mia | +0.415 |
Neg logit contributions | |
unloaded | -0.771 |
Coy | -0.766 |
enegger | -0.756 |
withd | -0.728 |
perce | -0.724 |
Token | function |
Token ID | 2163 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
roud | +3.234 |
rog | +2.787 |
utherland | +2.491 |
rite | +2.445 |
mia | +2.354 |
Neg logit contributions | |
enegger | -2.218 |
unloaded | -2.217 |
Coy | -2.194 |
withd | -2.076 |
thood | -2.040 |
Token | to |
Token ID | 284 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
roud | +0.664 |
rog | +0.572 |
utherland | +0.516 |
rite | +0.506 |
mia | +0.490 |
Neg logit contributions | |
unloaded | -0.424 |
Coy | -0.421 |
enegger | -0.419 |
withd | -0.392 |
thood | -0.387 |
Token | extract |
Token ID | 7925 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
roud | +0.059 |
rog | +0.051 |
utherland | +0.046 |
rite | +0.045 |
mia | +0.044 |
Neg logit contributions | |
unloaded | -0.035 |
Coy | -0.034 |
enegger | -0.034 |
withd | -0.032 |
perce | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
unloaded | +0.176 |
Coy | +0.174 |
enegger | +0.173 |
withd | +0.162 |
perce | +0.160 |
Neg logit contributions | |
roud | -0.258 |
rog | -0.221 |
utherland | -0.199 |
rite | -0.195 |
mia | -0.189 |
Token | high |
Token ID | 1029 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
roud | +0.340 |
rog | +0.291 |
utherland | +0.263 |
rite | +0.257 |
mia | +0.249 |
Neg logit contributions | |
unloaded | -0.235 |
Coy | -0.233 |
enegger | -0.232 |
withd | -0.217 |
perce | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
roud | +0.345 |
rog | +0.299 |
utherland | +0.276 |
rite | +0.269 |
mia | +0.261 |
Neg logit contributions | |
unloaded | -0.180 |
Coy | -0.179 |
enegger | -0.176 |
thood | -0.161 |
perce | -0.161 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
roud | +0.884 |
rog | +0.757 |
utherland | +0.682 |
rite | +0.667 |
mia | +0.645 |
Neg logit contributions | |
unloaded | -0.604 |
Coy | -0.596 |
enegger | -0.596 |
withd | -0.560 |
thood | -0.551 |
Token | } |
Token ID | 92 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
roud | +0.720 |
rog | +0.602 |
utherland | +0.530 |
rite | +0.520 |
Puppet | +0.496 |
Neg logit contributions | |
unloaded | -0.676 |
Coy | -0.668 |
enegger | -0.666 |
withd | -0.633 |
thood | -0.625 |
Token | < |
Token ID | 1279 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
roud | +0.262 |
rog | +0.215 |
utherland | +0.189 |
rite | +0.183 |
mia | +0.176 |
Neg logit contributions | |
unloaded | -0.277 |
Coy | -0.275 |
enegger | -0.274 |
withd | -0.261 |
thood | -0.258 |
Token | -> |
Token ID | 3784 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
roud | +1.594 |
rog | +1.379 |
utherland | +1.253 |
rite | +1.237 |
mia | +1.191 |
Neg logit contributions | |
unloaded | -0.927 |
Coy | -0.913 |
enegger | -0.905 |
withd | -0.848 |
thood | -0.837 |
Token | { |
Token ID | 1391 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
roud | +0.483 |
rog | +0.396 |
utherland | +0.346 |
rite | +0.337 |
mia | +0.321 |
Neg logit contributions | |
unloaded | -0.527 |
Coy | -0.524 |
enegger | -0.523 |
withd | -0.496 |
thood | -0.492 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
roud | +2.715 |
rog | +2.210 |
utherland | +1.872 |
rite | +1.846 |
mia | +1.755 |
Neg logit contributions | |
unloaded | -3.396 |
Coy | -3.357 |
enegger | -3.351 |
withd | -3.194 |
perce | -3.166 |
Token | , |
Token ID | 11 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
roud | +0.998 |
rog | +0.865 |
utherland | +0.789 |
rite | +0.773 |
mia | +0.750 |
Neg logit contributions | |
unloaded | -0.550 |
Coy | -0.546 |
enegger | -0.542 |
withd | -0.500 |
thood | -0.495 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
roud | +0.900 |
rog | +0.769 |
utherland | +0.690 |
rite | +0.676 |
mia | +0.652 |
Neg logit contributions | |
unloaded | -0.643 |
Coy | -0.635 |
enegger | -0.634 |
withd | -0.597 |
thood | -0.588 |
Token | } |
Token ID | 92 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
roud | +0.787 |
rog | +0.657 |
utherland | +0.578 |
rite | +0.566 |
mia | +0.541 |
Neg logit contributions | |
unloaded | -0.746 |
Coy | -0.736 |
enegger | -0.733 |
withd | -0.697 |
thood | -0.690 |
Token | ... |
Token ID | 2644 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
roud | +0.251 |
rog | +0.200 |
utherland | +0.171 |
rite | +0.165 |
mia | +0.156 |
Neg logit contributions | |
unloaded | -0.337 |
Coy | -0.335 |
enegger | -0.334 |
withd | -0.319 |
thood | -0.317 |
Token | } |
Token ID | 92 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
roud | +0.433 |
rog | +0.356 |
utherland | +0.315 |
rite | +0.304 |
mia | +0.292 |
Neg logit contributions | |
unloaded | -0.441 |
Coy | -0.441 |
enegger | -0.437 |
thood | -0.410 |
perce | -0.410 |
Token | -> |
Token ID | 4613 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
unloaded | +0.007 |
Coy | +0.007 |
enegger | +0.007 |
perce | +0.006 |
withd | +0.006 |
Neg logit contributions | |
roud | -0.017 |
rog | -0.015 |
utherland | -0.014 |
rite | -0.013 |
mia | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
roud | +0.232 |
rog | +0.203 |
utherland | +0.187 |
rite | +0.183 |
mia | +0.178 |
Neg logit contributions | |
unloaded | -0.105 |
Coy | -0.104 |
enegger | -0.103 |
withd | -0.093 |
perce | -0.093 |
Token | S |
Token ID | 50 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
roud | +0.751 |
rog | +0.629 |
utherland | +0.556 |
rite | +0.544 |
mia | +0.524 |
Neg logit contributions | |
unloaded | -0.670 |
enegger | -0.665 |
Coy | -0.664 |
withd | -0.628 |
thood | -0.622 |
Token | ", |
Token ID | 1600 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
roud | +0.687 |
rog | +0.600 |
utherland | +0.548 |
rite | +0.539 |
mia | +0.526 |
Neg logit contributions | |
unloaded | -0.327 |
Coy | -0.320 |
enegger | -0.318 |
withd | -0.293 |
thood | -0.292 |
Token | { |
Token ID | 1391 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
roud | +0.687 |
rog | +0.563 |
utherland | +0.496 |
rite | +0.478 |
mia | +0.458 |
Neg logit contributions | |
unloaded | -0.741 |
Coy | -0.736 |
enegger | -0.730 |
withd | -0.690 |
perce | -0.689 |
Token | 5 |
Token ID | 20 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
roud | +2.771 |
rog | +2.312 |
utherland | +2.015 |
rite | +1.977 |
mia | +1.900 |
Neg logit contributions | |
unloaded | -2.723 |
enegger | -2.696 |
Coy | -2.686 |
withd | -2.577 |
perce | -2.527 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
unloaded | +0.140 |
Coy | +0.140 |
enegger | +0.138 |
perce | +0.125 |
thood | +0.125 |
Neg logit contributions | |
roud | -0.275 |
rog | -0.238 |
utherland | -0.221 |
rite | -0.214 |
mia | -0.208 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
roud | +0.516 |
rog | +0.443 |
utherland | +0.400 |
rite | +0.392 |
mia | +0.379 |
Neg logit contributions | |
unloaded | -0.336 |
enegger | -0.333 |
Coy | -0.332 |
withd | -0.312 |
thood | -0.307 |
Token | } |
Token ID | 92 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
roud | +0.418 |
rog | +0.344 |
utherland | +0.305 |
rite | +0.294 |
mia | +0.283 |
Neg logit contributions | |
Coy | -0.420 |
unloaded | -0.419 |
enegger | -0.415 |
perce | -0.390 |
thood | -0.389 |
Token | -> |
Token ID | 4613 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
roud | +0.068 |
rog | +0.060 |
utherland | +0.055 |
rite | +0.054 |
mia | +0.052 |
Neg logit contributions | |
unloaded | -0.029 |
Coy | -0.029 |
enegger | -0.029 |
perce | -0.026 |
withd | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
unloaded | +0.710 |
Coy | +0.704 |
enegger | +0.701 |
withd | +0.660 |
thood | +0.652 |
Neg logit contributions | |
roud | -0.920 |
rog | -0.780 |
utherland | -0.699 |
rite | -0.682 |
mia | -0.659 |
Token | fact |
Token ID | 1109 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
roud | +0.102 |
rog | +0.086 |
utherland | +0.076 |
rite | +0.074 |
Puppet | +0.071 |
Neg logit contributions | |
unloaded | -0.090 |
enegger | -0.090 |
Coy | -0.089 |
withd | -0.085 |
thood | -0.084 |
Token | that |
Token ID | 326 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
unloaded | +0.373 |
Coy | +0.367 |
enegger | +0.361 |
perce | +0.333 |
withd | +0.332 |
Neg logit contributions | |
roud | -0.675 |
rog | -0.585 |
utherland | -0.536 |
rite | -0.521 |
mia | -0.506 |
Token | one |
Token ID | 530 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
unloaded | +0.203 |
enegger | +0.201 |
Coy | +0.201 |
withd | +0.187 |
thood | +0.186 |
Neg logit contributions | |
roud | -0.298 |
rog | -0.255 |
utherland | -0.230 |
rite | -0.226 |
mia | -0.218 |
Token | is |
Token ID | 318 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
roud | +0.185 |
rog | +0.159 |
utherland | +0.143 |
rite | +0.141 |
mia | +0.136 |
Neg logit contributions | |
unloaded | -0.122 |
enegger | -0.121 |
Coy | -0.121 |
withd | -0.113 |
thood | -0.112 |
Token | predominantly |
Token ID | 20736 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
roud | +0.168 |
rog | +0.139 |
utherland | +0.122 |
rite | +0.118 |
mia | +0.114 |
Neg logit contributions | |
unloaded | -0.174 |
Coy | -0.172 |
enegger | -0.170 |
withd | -0.163 |
perce | -0.162 |
Token | used |
Token ID | 973 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
roud | +0.342 |
rog | +0.283 |
utherland | +0.249 |
rite | +0.241 |
mia | +0.231 |
Neg logit contributions | |
unloaded | -0.355 |
Coy | -0.349 |
enegger | -0.346 |
perce | -0.328 |
withd | -0.328 |
Token | for |
Token ID | 329 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
roud | +0.862 |
rog | +0.752 |
utherland | +0.686 |
rite | +0.676 |
mia | +0.658 |
Neg logit contributions | |
unloaded | -0.419 |
enegger | -0.415 |
Coy | -0.414 |
withd | -0.386 |
thood | -0.376 |
Token | single |
Token ID | 2060 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
roud | +0.070 |
rog | +0.060 |
utherland | +0.055 |
rite | +0.053 |
mia | +0.052 |
Neg logit contributions | |
unloaded | -0.041 |
Coy | -0.041 |
enegger | -0.040 |
withd | -0.038 |
perce | -0.037 |
Token | line |
Token ID | 1627 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
roud | +1.462 |
rog | +1.278 |
utherland | +1.167 |
rite | +1.151 |
mia | +1.118 |
Neg logit contributions | |
unloaded | -0.706 |
enegger | -0.703 |
Coy | -0.697 |
withd | -0.653 |
thood | -0.637 |
Token | blocks |
Token ID | 7021 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
unloaded | +0.159 |
Coy | +0.155 |
enegger | +0.151 |
perce | +0.133 |
withd | +0.133 |
Neg logit contributions | |
roud | -0.555 |
rog | -0.493 |
utherland | -0.459 |
rite | -0.450 |
mia | -0.440 |
Token | this |
Token ID | 428 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
roud | +0.002 |
rog | +0.002 |
utherland | +0.002 |
rite | +0.002 |
mia | +0.002 |
Neg logit contributions | |
unloaded | -0.001 |
Coy | -0.001 |
enegger | -0.001 |
withd | -0.001 |
thood | -0.001 |
Token | far |
Token ID | 1290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
roud | +0.680 |
rog | +0.585 |
utherland | +0.532 |
rite | +0.520 |
mia | +0.505 |
Neg logit contributions | |
unloaded | -0.405 |
enegger | -0.400 |
Coy | -0.400 |
withd | -0.373 |
thood | -0.368 |
Token | , |
Token ID | 11 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
roud | +1.021 |
rog | +0.879 |
utherland | +0.796 |
rite | +0.779 |
mia | +0.757 |
Neg logit contributions | |
unloaded | -0.621 |
Coy | -0.612 |
enegger | -0.610 |
withd | -0.571 |
thood | -0.563 |
Token | I |
Token ID | 314 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
roud | +0.254 |
rog | +0.215 |
utherland | +0.193 |
rite | +0.189 |
mia | +0.183 |
Neg logit contributions | |
unloaded | -0.191 |
Coy | -0.189 |
enegger | -0.188 |
withd | -0.177 |
thood | -0.175 |
Token | � |
Token ID | 447 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
roud | +0.198 |
rog | +0.170 |
utherland | +0.154 |
rite | +0.150 |
mia | +0.146 |
Neg logit contributions | |
unloaded | -0.128 |
Coy | -0.127 |
enegger | -0.126 |
withd | -0.118 |
thood | -0.117 |
Token | � |
Token ID | 247 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
roud | +0.260 |
rog | +0.226 |
utherland | +0.207 |
rite | +0.202 |
mia | +0.197 |
Neg logit contributions | |
unloaded | -0.138 |
Coy | -0.136 |
enegger | -0.135 |
withd | -0.125 |
thood | -0.123 |
Token | d |
Token ID | 67 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
roud | +0.422 |
rog | +0.354 |
utherland | +0.315 |
rite | +0.307 |
mia | +0.295 |
Neg logit contributions | |
unloaded | -0.371 |
Coy | -0.368 |
enegger | -0.366 |
withd | -0.346 |
thood | -0.343 |
Token | love |
Token ID | 1842 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
roud | +0.034 |
rog | +0.030 |
utherland | +0.027 |
rite | +0.027 |
mia | +0.026 |
Neg logit contributions | |
unloaded | -0.018 |
Coy | -0.017 |
enegger | -0.017 |
withd | -0.016 |
thood | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
roud | +0.040 |
rog | +0.035 |
utherland | +0.031 |
rite | +0.030 |
mia | +0.030 |
Neg logit contributions | |
unloaded | -0.027 |
Coy | -0.027 |
enegger | -0.027 |
withd | -0.025 |
thood | -0.025 |
Token | if |
Token ID | 611 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
roud | +0.053 |
rog | +0.046 |
utherland | +0.041 |
rite | +0.041 |
mia | +0.039 |
Neg logit contributions | |
unloaded | -0.032 |
Coy | -0.032 |
enegger | -0.032 |
withd | -0.029 |
thood | -0.029 |
Token | you |
Token ID | 345 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
roud | +0.185 |
rog | +0.156 |
utherland | +0.140 |
rite | +0.136 |
mia | +0.131 |
Neg logit contributions | |
unloaded | -0.150 |
Coy | -0.150 |
enegger | -0.148 |
withd | -0.140 |
perce | -0.139 |
Token | K |
Token ID | 42 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
roud | +0.217 |
rog | +0.180 |
utherland | +0.161 |
rite | +0.155 |
Puppet | +0.148 |
Neg logit contributions | |
unloaded | -0.214 |
Coy | -0.213 |
enegger | -0.211 |
withd | -0.199 |
thood | -0.199 |
Token | ob |
Token ID | 672 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
roud | +0.013 |
rog | +0.011 |
utherland | +0.010 |
rite | +0.010 |
Puppet | +0.009 |
Neg logit contributions | |
unloaded | -0.010 |
Coy | -0.009 |
enegger | -0.009 |
withd | -0.009 |
thood | -0.009 |
Token | ay |
Token ID | 323 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
roud | +0.184 |
rog | +0.159 |
utherland | +0.144 |
rite | +0.141 |
mia | +0.137 |
Neg logit contributions | |
unloaded | -0.110 |
Coy | -0.109 |
enegger | -0.108 |
withd | -0.101 |
thood | -0.099 |
Token | ashi |
Token ID | 12144 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
roud | +1.134 |
rog | +0.944 |
utherland | +0.834 |
rite | +0.811 |
mia | +0.780 |
Neg logit contributions | |
unloaded | -1.077 |
Coy | -1.069 |
enegger | -1.065 |
withd | -1.010 |
thood | -0.999 |
Token | was |
Token ID | 373 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
unloaded | +0.049 |
Coy | +0.049 |
enegger | +0.049 |
withd | +0.046 |
perce | +0.045 |
Neg logit contributions | |
roud | -0.070 |
rog | -0.060 |
utherland | -0.054 |
rite | -0.053 |
mia | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
roud | +0.085 |
rog | +0.073 |
utherland | +0.067 |
rite | +0.066 |
mia | +0.063 |
Neg logit contributions | |
unloaded | -0.051 |
Coy | -0.050 |
enegger | -0.050 |
withd | -0.047 |
perce | -0.046 |
Token | great |
Token ID | 1049 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
roud | +0.912 |
rog | +0.781 |
utherland | +0.708 |
rite | +0.689 |
mia | +0.667 |
Neg logit contributions | |
unloaded | -0.638 |
Coy | -0.636 |
enegger | -0.628 |
withd | -0.591 |
perce | -0.585 |
Token | champion |
Token ID | 8783 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
unloaded | +0.258 |
Coy | +0.257 |
enegger | +0.255 |
withd | +0.240 |
perce | +0.238 |
Neg logit contributions | |
roud | -0.336 |
rog | -0.286 |
utherland | -0.257 |
rite | -0.250 |
mia | -0.242 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
roud | +1.356 |
rog | +1.169 |
utherland | +1.060 |
rite | +1.041 |
mia | +1.010 |
Neg logit contributions | |
unloaded | -0.780 |
Coy | -0.768 |
enegger | -0.766 |
withd | -0.715 |
thood | -0.706 |
Token | we |
Token ID | 356 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
roud | +0.369 |
rog | +0.316 |
utherland | +0.286 |
rite | +0.279 |
mia | +0.270 |
Neg logit contributions | |
unloaded | -0.249 |
Coy | -0.247 |
enegger | -0.245 |
withd | -0.230 |
perce | -0.227 |
Token | hope |
Token ID | 2911 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
roud | +0.447 |
rog | +0.384 |
utherland | +0.348 |
rite | +0.340 |
mia | +0.330 |
Neg logit contributions | |
unloaded | -0.282 |
Coy | -0.279 |
enegger | -0.278 |
withd | -0.260 |
thood | -0.256 |
Token | of |
Token ID | 286 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
unloaded | +0.144 |
Coy | +0.143 |
enegger | +0.140 |
withd | +0.132 |
perce | +0.131 |
Neg logit contributions | |
roud | -0.207 |
rog | -0.176 |
utherland | -0.159 |
rite | -0.155 |
mia | -0.151 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
roud | +0.840 |
rog | +0.718 |
utherland | +0.649 |
rite | +0.634 |
mia | +0.613 |
Neg logit contributions | |
unloaded | -0.583 |
Coy | -0.578 |
enegger | -0.573 |
withd | -0.538 |
perce | -0.530 |
Token | bonded |
Token ID | 40270 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
roud | +0.477 |
rog | +0.408 |
utherland | +0.370 |
rite | +0.361 |
mia | +0.350 |
Neg logit contributions | |
unloaded | -0.324 |
Coy | -0.323 |
enegger | -0.317 |
withd | -0.299 |
perce | -0.294 |
Token | aluminum |
Token ID | 15955 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
roud | +0.549 |
rog | +0.468 |
utherland | +0.423 |
rite | +0.412 |
mia | +0.401 |
Neg logit contributions | |
unloaded | -0.386 |
Coy | -0.384 |
enegger | -0.379 |
withd | -0.356 |
perce | -0.351 |
Token | frame |
Token ID | 5739 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
roud | +0.439 |
rog | +0.373 |
utherland | +0.336 |
rite | +0.328 |
mia | +0.318 |
Neg logit contributions | |
unloaded | -0.321 |
Coy | -0.318 |
enegger | -0.316 |
withd | -0.298 |
perce | -0.293 |
Token | with |
Token ID | 351 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
unloaded | +0.025 |
Coy | +0.024 |
enegger | +0.024 |
withd | +0.022 |
thood | +0.022 |
Neg logit contributions | |
roud | -0.044 |
rog | -0.038 |
utherland | -0.035 |
rite | -0.034 |
mia | -0.033 |
Token | an |
Token ID | 281 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
roud | +0.592 |
rog | +0.507 |
utherland | +0.458 |
rite | +0.448 |
mia | +0.433 |
Neg logit contributions | |
unloaded | -0.397 |
Coy | -0.393 |
enegger | -0.391 |
withd | -0.366 |
thood | -0.361 |
Token | od |
Token ID | 375 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
unloaded | +0.134 |
Coy | +0.133 |
enegger | +0.133 |
withd | +0.124 |
thood | +0.122 |
Neg logit contributions | |
roud | -0.212 |
rog | -0.182 |
utherland | -0.165 |
rite | -0.161 |
mia | -0.156 |
Token | ized |
Token ID | 1143 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
unloaded | +0.145 |
Coy | +0.143 |
enegger | +0.140 |
withd | +0.131 |
thood | +0.130 |
Neg logit contributions | |
roud | -0.296 |
rog | -0.256 |
utherland | -0.237 |
rite | -0.229 |
Puppet | -0.226 |
Token | tubing |
Token ID | 43128 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
unloaded | +0.124 |
Coy | +0.123 |
enegger | +0.122 |
withd | +0.115 |
perce | +0.114 |
Neg logit contributions | |
roud | -0.159 |
rog | -0.134 |
utherland | -0.120 |
rite | -0.117 |
mia | -0.113 |
Token | , |
Token ID | 11 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
roud | +0.185 |
rog | +0.160 |
utherland | +0.145 |
rite | +0.143 |
mia | +0.139 |
Neg logit contributions | |
unloaded | -0.105 |
enegger | -0.105 |
Coy | -0.104 |
withd | -0.097 |
thood | -0.096 |
Token | probably |
Token ID | 2192 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
roud | +0.305 |
rog | +0.263 |
utherland | +0.240 |
rite | +0.234 |
mia | +0.228 |
Neg logit contributions | |
unloaded | -0.177 |
Coy | -0.174 |
enegger | -0.172 |
withd | -0.160 |
perce | -0.158 |
Token | earned |
Token ID | 7366 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
unloaded | +0.181 |
Coy | +0.176 |
enegger | +0.172 |
withd | +0.161 |
perce | +0.161 |
Neg logit contributions | |
roud | -0.311 |
rog | -0.268 |
utherland | -0.245 |
rite | -0.240 |
mia | -0.232 |
Token | the |
Token ID | 262 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
roud | +0.767 |
rog | +0.660 |
utherland | +0.601 |
rite | +0.585 |
mia | +0.567 |
Neg logit contributions | |
unloaded | -0.481 |
Coy | -0.478 |
enegger | -0.464 |
perce | -0.435 |
withd | -0.433 |
Token | right |
Token ID | 826 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
unloaded | +0.127 |
Coy | +0.126 |
enegger | +0.124 |
withd | +0.116 |
perce | +0.116 |
Neg logit contributions | |
roud | -0.185 |
rog | -0.159 |
utherland | -0.144 |
rite | -0.141 |
mia | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
roud | +0.395 |
rog | +0.340 |
utherland | +0.309 |
rite | +0.301 |
mia | +0.292 |
Neg logit contributions | |
unloaded | -0.244 |
Coy | -0.243 |
enegger | -0.238 |
withd | -0.222 |
perce | -0.221 |
Token | hold |
Token ID | 1745 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
unloaded | +0.243 |
Coy | +0.240 |
enegger | +0.237 |
withd | +0.222 |
perce | +0.219 |
Neg logit contributions | |
roud | -0.404 |
rog | -0.348 |
utherland | -0.316 |
rite | -0.308 |
mia | -0.300 |
Token | those |
Token ID | 883 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
roud | +0.447 |
rog | +0.381 |
utherland | +0.344 |
rite | +0.335 |
mia | +0.326 |
Neg logit contributions | |
unloaded | -0.311 |
Coy | -0.309 |
enegger | -0.301 |
withd | -0.285 |
perce | -0.283 |
Token | titles |
Token ID | 8714 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
unloaded | +0.419 |
Coy | +0.418 |
enegger | +0.403 |
withd | +0.382 |
perce | +0.378 |
Neg logit contributions | |
roud | -0.673 |
rog | -0.580 |
utherland | -0.524 |
rite | -0.515 |
mia | -0.498 |
Token | by |
Token ID | 416 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
unloaded | +0.494 |
Coy | +0.487 |
enegger | +0.479 |
withd | +0.448 |
perce | +0.442 |
Neg logit contributions | |
roud | -0.864 |
rog | -0.747 |
utherland | -0.683 |
rite | -0.669 |
mia | -0.647 |
Token | himself |
Token ID | 2241 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
roud | +0.131 |
rog | +0.113 |
utherland | +0.103 |
rite | +0.100 |
mia | +0.097 |
Neg logit contributions | |
unloaded | -0.079 |
Coy | -0.078 |
enegger | -0.077 |
perce | -0.072 |
withd | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
unloaded | +0.821 |
Coy | +0.811 |
enegger | +0.803 |
withd | +0.749 |
perce | +0.739 |
Neg logit contributions | |
roud | -1.426 |
rog | -1.230 |
utherland | -1.126 |
rite | -1.103 |
mia | -1.067 |
Token | : |
Token ID | 25 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
roud | +0.578 |
rog | +0.499 |
utherland | +0.454 |
rite | +0.445 |
mia | +0.431 |
Neg logit contributions | |
unloaded | -0.336 |
Coy | -0.333 |
enegger | -0.331 |
withd | -0.307 |
thood | -0.304 |
Token | You |
Token ID | 921 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Coy | +0.507 |
unloaded | +0.506 |
enegger | +0.497 |
withd | +0.460 |
perce | +0.454 |
Neg logit contributions | |
roud | -0.919 |
rog | -0.798 |
utherland | -0.730 |
rite | -0.715 |
mia | -0.691 |
Token | know |
Token ID | 760 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
unloaded | +0.351 |
Coy | +0.346 |
enegger | +0.344 |
withd | +0.321 |
perce | +0.316 |
Neg logit contributions | |
roud | -0.603 |
rog | -0.521 |
utherland | -0.474 |
rite | -0.464 |
mia | -0.449 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
unloaded | +0.465 |
Coy | +0.461 |
enegger | +0.455 |
withd | +0.421 |
perce | +0.418 |
Neg logit contributions | |
roud | -0.850 |
rog | -0.739 |
utherland | -0.676 |
rite | -0.663 |
mia | -0.640 |
Token | it |
Token ID | 340 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
unloaded | +0.379 |
Coy | +0.375 |
enegger | +0.368 |
withd | +0.344 |
perce | +0.341 |
Neg logit contributions | |
roud | -0.668 |
rog | -0.578 |
utherland | -0.528 |
rite | -0.519 |
mia | -0.502 |
Token | � |
Token ID | 447 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
unloaded | +0.152 |
Coy | +0.150 |
enegger | +0.149 |
withd | +0.140 |
perce | +0.139 |
Neg logit contributions | |
roud | -0.197 |
rog | -0.167 |
utherland | -0.150 |
rite | -0.146 |
mia | -0.141 |
Token | � |
Token ID | 247 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
unloaded | +0.305 |
Coy | +0.295 |
enegger | +0.289 |
thood | +0.268 |
withd | +0.267 |
Neg logit contributions | |
roud | -0.623 |
rog | -0.539 |
utherland | -0.503 |
rite | -0.485 |
mia | -0.475 |
Token | s |
Token ID | 82 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
roud | +0.131 |
rog | +0.113 |
utherland | +0.102 |
rite | +0.100 |
mia | +0.097 |
Neg logit contributions | |
unloaded | -0.086 |
Coy | -0.085 |
enegger | -0.085 |
withd | -0.079 |
thood | -0.078 |
Token | not |
Token ID | 407 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
unloaded | +0.067 |
Coy | +0.067 |
enegger | +0.066 |
withd | +0.062 |
perce | +0.061 |
Neg logit contributions | |
roud | -0.110 |
rog | -0.095 |
utherland | -0.086 |
rite | -0.085 |
mia | -0.082 |
Token | just |
Token ID | 655 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
unloaded | +0.049 |
Coy | +0.048 |
enegger | +0.048 |
withd | +0.045 |
perce | +0.044 |
Neg logit contributions | |
roud | -0.084 |
rog | -0.073 |
utherland | -0.066 |
rite | -0.065 |
mia | -0.063 |
Token | brown |
Token ID | 7586 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
roud | +0.502 |
rog | +0.432 |
utherland | +0.391 |
rite | +0.383 |
mia | +0.371 |
Neg logit contributions | |
unloaded | -0.318 |
Coy | -0.315 |
enegger | -0.313 |
withd | -0.292 |
perce | -0.288 |
Token | reaction |
Token ID | 6317 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
unloaded | +0.177 |
Coy | +0.175 |
enegger | +0.174 |
withd | +0.163 |
perce | +0.162 |
Neg logit contributions | |
roud | -0.256 |
rog | -0.219 |
utherland | -0.198 |
rite | -0.193 |
mia | -0.187 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
unloaded | +0.148 |
Coy | +0.146 |
enegger | +0.146 |
withd | +0.136 |
thood | +0.134 |
Neg logit contributions | |
roud | -0.246 |
rog | -0.212 |
utherland | -0.192 |
rite | -0.188 |
mia | -0.183 |
Token | as |
Token ID | 355 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
roud | +0.433 |
rog | +0.373 |
utherland | +0.339 |
rite | +0.332 |
mia | +0.322 |
Neg logit contributions | |
unloaded | -0.261 |
Coy | -0.258 |
enegger | -0.257 |
withd | -0.239 |
thood | -0.236 |
Token | it |
Token ID | 340 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
roud | +0.374 |
rog | +0.325 |
utherland | +0.296 |
rite | +0.291 |
mia | +0.283 |
Neg logit contributions | |
unloaded | -0.196 |
Coy | -0.194 |
enegger | -0.193 |
withd | -0.179 |
thood | -0.176 |
Token | is |
Token ID | 318 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
unloaded | +0.100 |
Coy | +0.099 |
enegger | +0.099 |
withd | +0.092 |
perce | +0.092 |
Neg logit contributions | |
roud | -0.147 |
rog | -0.126 |
utherland | -0.114 |
rite | -0.111 |
mia | -0.108 |
Token | none |
Token ID | 4844 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
unloaded | +0.270 |
Coy | +0.266 |
enegger | +0.261 |
withd | +0.245 |
perce | +0.244 |
Neg logit contributions | |
roud | -0.454 |
rog | -0.390 |
utherland | -0.357 |
rite | -0.349 |
mia | -0.338 |
Token | of |
Token ID | 286 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
unloaded | +0.369 |
Coy | +0.364 |
enegger | +0.362 |
withd | +0.338 |
perce | +0.334 |
Neg logit contributions | |
roud | -0.608 |
rog | -0.524 |
utherland | -0.475 |
rite | -0.466 |
mia | -0.452 |
Token | their |
Token ID | 511 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
roud | +0.174 |
rog | +0.150 |
utherland | +0.136 |
rite | +0.134 |
mia | +0.129 |
Neg logit contributions | |
unloaded | -0.106 |
Coy | -0.106 |
enegger | -0.105 |
withd | -0.097 |
perce | -0.097 |
Token | business |
Token ID | 1597 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
unloaded | +0.026 |
Coy | +0.026 |
enegger | +0.025 |
perce | +0.024 |
withd | +0.024 |
Neg logit contributions | |
roud | -0.037 |
rog | -0.032 |
utherland | -0.029 |
rite | -0.028 |
mia | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
roud | +0.237 |
rog | +0.204 |
utherland | +0.185 |
rite | +0.180 |
mia | +0.175 |
Neg logit contributions | |
unloaded | -0.147 |
Coy | -0.146 |
enegger | -0.146 |
withd | -0.136 |
thood | -0.135 |
Token | Rather |
Token ID | 11317 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Coy | +0.255 |
unloaded | +0.254 |
enegger | +0.251 |
withd | +0.233 |
thood | +0.233 |
Neg logit contributions | |
roud | -0.351 |
rog | -0.298 |
utherland | -0.270 |
rite | -0.263 |
mia | -0.254 |
Token | will |
Token ID | 481 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
roud | +0.602 |
rog | +0.519 |
utherland | +0.470 |
rite | +0.460 |
mia | +0.446 |
Neg logit contributions | |
unloaded | -0.373 |
Coy | -0.369 |
enegger | -0.368 |
withd | -0.343 |
thood | -0.339 |
Token | walk |
Token ID | 2513 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
roud | +0.310 |
rog | +0.269 |
utherland | +0.245 |
rite | +0.240 |
mia | +0.234 |
Neg logit contributions | |
unloaded | -0.169 |
Coy | -0.167 |
enegger | -0.166 |
withd | -0.154 |
thood | -0.152 |
Token | right |
Token ID | 826 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
roud | +0.517 |
rog | +0.441 |
utherland | +0.395 |
rite | +0.387 |
mia | +0.374 |
Neg logit contributions | |
unloaded | -0.376 |
Coy | -0.373 |
enegger | -0.372 |
withd | -0.349 |
thood | -0.345 |
Token | past |
Token ID | 1613 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
roud | +0.935 |
rog | +0.811 |
utherland | +0.734 |
rite | +0.719 |
mia | +0.700 |
Neg logit contributions | |
enegger | -0.517 |
unloaded | -0.515 |
Coy | -0.512 |
withd | -0.477 |
thood | -0.472 |
Token | these |
Token ID | 777 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
roud | +0.267 |
rog | +0.229 |
utherland | +0.208 |
rite | +0.203 |
mia | +0.197 |
Neg logit contributions | |
unloaded | -0.174 |
Coy | -0.172 |
enegger | -0.171 |
withd | -0.160 |
perce | -0.158 |
Token | tasty |
Token ID | 25103 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
unloaded | +0.246 |
Coy | +0.242 |
enegger | +0.240 |
withd | +0.225 |
perce | +0.222 |
Neg logit contributions | |
roud | -0.399 |
rog | -0.343 |
utherland | -0.312 |
rite | -0.306 |
mia | -0.296 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
roud | +0.108 |
rog | +0.093 |
utherland | +0.084 |
rite | +0.083 |
mia | +0.080 |
Neg logit contributions | |
unloaded | -0.067 |
Coy | -0.066 |
enegger | -0.066 |
withd | -0.062 |
perce | -0.061 |
Token | super |
Token ID | 2208 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
unloaded | +0.223 |
Coy | +0.220 |
enegger | +0.218 |
withd | +0.204 |
perce | +0.201 |
Neg logit contributions | |
roud | -0.359 |
rog | -0.308 |
utherland | -0.280 |
rite | -0.275 |
mia | -0.266 |
Token | - |
Token ID | 12 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
roud | +0.572 |
rog | +0.486 |
utherland | +0.439 |
rite | +0.429 |
mia | +0.414 |
Neg logit contributions | |
unloaded | -0.412 |
Coy | -0.408 |
enegger | -0.406 |
withd | -0.382 |
thood | -0.377 |
Token | nut |
Token ID | 14930 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
roud | +0.435 |
rog | +0.361 |
utherland | +0.322 |
rite | +0.312 |
mia | +0.300 |
Neg logit contributions | |
unloaded | -0.407 |
Coy | -0.403 |
enegger | -0.401 |
withd | -0.379 |
thood | -0.376 |
Token | rit |
Token ID | 799 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
roud | +0.257 |
rog | +0.194 |
utherland | +0.160 |
rite | +0.149 |
mia | +0.141 |
Neg logit contributions | |
unloaded | -0.477 |
Coy | -0.473 |
enegger | -0.472 |
withd | -0.453 |
thood | -0.451 |
Token | Bulgaria |
Token ID | 27902 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
unloaded | +0.003 |
Coy | +0.003 |
enegger | +0.003 |
withd | +0.003 |
thood | +0.002 |
Neg logit contributions | |
roud | -0.004 |
rog | -0.003 |
utherland | -0.003 |
rite | -0.003 |
mia | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
unloaded | +0.887 |
Coy | +0.879 |
enegger | +0.872 |
withd | +0.820 |
perce | +0.811 |
Neg logit contributions | |
roud | -1.275 |
rog | -1.088 |
utherland | -0.983 |
rite | -0.960 |
mia | -0.928 |
Token | EU |
Token ID | 4576 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
unloaded | +0.185 |
Coy | +0.183 |
enegger | +0.182 |
withd | +0.169 |
thood | +0.167 |
Neg logit contributions | |
roud | -0.323 |
rog | -0.279 |
utherland | -0.254 |
rite | -0.249 |
mia | -0.242 |
Token | membership |
Token ID | 9931 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
roud | +0.471 |
rog | +0.409 |
utherland | +0.371 |
rite | +0.365 |
mia | +0.354 |
Neg logit contributions | |
unloaded | -0.259 |
Coy | -0.256 |
enegger | -0.255 |
withd | -0.236 |
thood | -0.232 |
Token | you |
Token ID | 345 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
roud | +0.221 |
rog | +0.190 |
utherland | +0.172 |
rite | +0.169 |
mia | +0.164 |
Neg logit contributions | |
unloaded | -0.139 |
Coy | -0.138 |
enegger | -0.138 |
withd | -0.128 |
thood | -0.127 |
Token | could |
Token ID | 714 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
unloaded | +0.409 |
Coy | +0.405 |
enegger | +0.403 |
withd | +0.374 |
perce | +0.369 |
Neg logit contributions | |
roud | -0.698 |
rog | -0.602 |
utherland | -0.546 |
rite | -0.535 |
mia | -0.520 |
Token | read |
Token ID | 1100 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
unloaded | +0.556 |
Coy | +0.548 |
enegger | +0.545 |
withd | +0.508 |
perce | +0.500 |
Neg logit contributions | |
roud | -1.059 |
rog | -0.918 |
utherland | -0.840 |
rite | -0.821 |
mia | -0.799 |
Token | on |
Token ID | 319 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
unloaded | +0.965 |
Coy | +0.955 |
enegger | +0.945 |
withd | +0.884 |
perce | +0.879 |
Neg logit contributions | |
roud | -1.500 |
rog | -1.281 |
utherland | -1.166 |
rite | -1.143 |
mia | -1.102 |
Token | e |
Token ID | 304 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
roud | +0.145 |
rog | +0.124 |
utherland | +0.112 |
rite | +0.110 |
mia | +0.106 |
Neg logit contributions | |
unloaded | -0.099 |
Coy | -0.099 |
enegger | -0.098 |
withd | -0.092 |
perce | -0.091 |
Token | u |
Token ID | 84 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
roud | +0.277 |
rog | +0.227 |
utherland | +0.197 |
rite | +0.192 |
mia | +0.183 |
Neg logit contributions | |
unloaded | -0.308 |
Coy | -0.306 |
enegger | -0.305 |
withd | -0.290 |
thood | -0.287 |
Token | inside |
Token ID | 48787 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
unloaded | +0.292 |
Coy | +0.290 |
enegger | +0.289 |
withd | +0.273 |
thood | +0.270 |
Neg logit contributions | |
roud | -0.348 |
rog | -0.293 |
utherland | -0.261 |
rite | -0.255 |
mia | -0.246 |
Token | t |
Token ID | 83 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
roud | +0.313 |
rog | +0.265 |
utherland | +0.239 |
rite | +0.232 |
mia | +0.224 |
Neg logit contributions | |
unloaded | -0.244 |
Coy | -0.244 |
enegger | -0.240 |
withd | -0.226 |
thood | -0.225 |
Token | / |
Token ID | 14 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
roud | +1.363 |
rog | +1.181 |
utherland | +1.080 |
rite | +1.058 |
mia | +1.025 |
Neg logit contributions | |
unloaded | -0.751 |
Coy | -0.747 |
enegger | -0.738 |
withd | -0.682 |
thood | -0.675 |
Token | W |
Token ID | 54 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
roud | +0.524 |
rog | +0.440 |
utherland | +0.401 |
rite | +0.391 |
Puppet | +0.377 |
Neg logit contributions | |
unloaded | -0.384 |
Coy | -0.381 |
enegger | -0.373 |
thood | -0.350 |
perce | -0.350 |
Token | t |
Token ID | 83 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
roud | +1.308 |
rog | +1.080 |
utherland | +0.971 |
rite | +0.929 |
foundation | +0.890 |
Neg logit contributions | |
unloaded | -1.263 |
Coy | -1.257 |
enegger | -1.237 |
perce | -1.172 |
withd | -1.171 |
Token | Comp |
Token ID | 3082 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
roud | +0.862 |
rog | +0.723 |
utherland | +0.642 |
rite | +0.626 |
mia | +0.602 |
Neg logit contributions | |
unloaded | -0.761 |
Coy | -0.755 |
enegger | -0.752 |
withd | -0.711 |
thood | -0.703 |
Token | . |
Token ID | 13 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
unloaded | +0.073 |
Coy | +0.072 |
enegger | +0.072 |
withd | +0.066 |
thood | +0.065 |
Neg logit contributions | |
roud | -0.131 |
rog | -0.113 |
utherland | -0.103 |
rite | -0.101 |
mia | -0.098 |
Token | Rating |
Token ID | 12028 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Coy | +0.092 |
unloaded | +0.092 |
enegger | +0.090 |
perce | +0.085 |
thood | +0.084 |
Neg logit contributions | |
roud | -0.115 |
rog | -0.097 |
utherland | -0.088 |
rite | -0.085 |
mia | -0.082 |
Token | 247 |
Token ID | 30179 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
roud | +0.844 |
rog | +0.720 |
utherland | +0.650 |
rite | +0.634 |
mia | +0.613 |
Neg logit contributions | |
unloaded | -0.597 |
Coy | -0.594 |
enegger | -0.587 |
withd | -0.550 |
perce | -0.545 |
Token | ESPN |
Token ID | 10409 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
unloaded | +0.063 |
Coy | +0.062 |
enegger | +0.061 |
perce | +0.057 |
withd | +0.057 |
Neg logit contributions | |
roud | -0.084 |
rog | -0.072 |
utherland | -0.065 |
rite | -0.063 |
mia | -0.061 |
Token | Rivals |
Token ID | 42307 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
roud | +0.150 |
rog | +0.128 |
utherland | +0.116 |
rite | +0.112 |
mia | +0.109 |
Neg logit contributions | |
unloaded | -0.110 |
Coy | -0.109 |
enegger | -0.108 |
withd | -0.101 |
thood | -0.100 |
Token | Scout |
Token ID | 22529 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
roud | +0.996 |
rog | +0.824 |
utherland | +0.724 |
rite | +0.704 |
mia | +0.675 |
Neg logit contributions | |
unloaded | -1.010 |
Coy | -1.003 |
enegger | -0.997 |
withd | -0.947 |
thood | -0.938 |
Token | in |
Token ID | 287 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
Coy | +0.443 |
unloaded | +0.443 |
enegger | +0.433 |
withd | +0.406 |
perce | +0.401 |
Neg logit contributions | |
roud | -0.773 |
rog | -0.668 |
utherland | -0.608 |
rite | -0.596 |
mia | -0.576 |
Token | its |
Token ID | 663 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
roud | +0.169 |
rog | +0.146 |
utherland | +0.132 |
rite | +0.129 |
mia | +0.125 |
Neg logit contributions | |
unloaded | -0.109 |
Coy | -0.108 |
enegger | -0.107 |
withd | -0.100 |
thood | -0.099 |
Token | episode |
Token ID | 4471 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
roud | +0.216 |
rog | +0.186 |
utherland | +0.168 |
rite | +0.165 |
mia | +0.160 |
Neg logit contributions | |
unloaded | -0.137 |
Coy | -0.136 |
enegger | -0.135 |
withd | -0.126 |
thood | -0.125 |
Token | " |
Token ID | 366 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
roud | +1.037 |
rog | +0.900 |
utherland | +0.818 |
rite | +0.804 |
mia | +0.783 |
Neg logit contributions | |
unloaded | -0.554 |
enegger | -0.546 |
Coy | -0.543 |
withd | -0.504 |
thood | -0.496 |
Token | Sil |
Token ID | 15086 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
Coy | +0.482 |
unloaded | +0.481 |
enegger | +0.475 |
withd | +0.450 |
thood | +0.449 |
Neg logit contributions | |
roud | -0.473 |
rog | -0.389 |
utherland | -0.345 |
rite | -0.333 |
mia | -0.317 |
Token | ent |
Token ID | 298 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
Coy | +1.820 |
unloaded | +1.816 |
enegger | +1.771 |
thood | +1.715 |
withd | +1.685 |
Neg logit contributions | |
roud | -1.613 |
rog | -1.307 |
utherland | -1.165 |
rite | -1.120 |
Puppet | -1.065 |
Token | Ro |
Token ID | 5564 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Coy | +1.327 |
unloaded | +1.307 |
enegger | +1.273 |
withd | +1.195 |
thood | +1.195 |
Neg logit contributions | |
roud | -2.163 |
rog | -1.865 |
utherland | -1.713 |
rite | -1.666 |
mia | -1.610 |
Token | ar |
Token ID | 283 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
unloaded | +0.676 |
Coy | +0.671 |
enegger | +0.667 |
withd | +0.627 |
thood | +0.619 |
Neg logit contributions | |
roud | -0.924 |
rog | -0.787 |
utherland | -0.708 |
rite | -0.691 |
mia | -0.668 |
Token | : |
Token ID | 25 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
unloaded | +0.097 |
Coy | +0.096 |
enegger | +0.096 |
withd | +0.089 |
thood | +0.087 |
Neg logit contributions | |
roud | -0.184 |
rog | -0.160 |
utherland | -0.146 |
rite | -0.143 |
mia | -0.139 |
Token | Search |
Token ID | 11140 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
roud | +0.063 |
rog | +0.055 |
utherland | +0.050 |
rite | +0.048 |
mia | +0.047 |
Neg logit contributions | |
unloaded | -0.039 |
Coy | -0.039 |
enegger | -0.039 |
withd | -0.036 |
thood | -0.036 |
Token | ing |
Token ID | 278 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
roud | +0.464 |
rog | +0.406 |
utherland | +0.370 |
rite | +0.364 |
mia | +0.355 |
Neg logit contributions | |
unloaded | -0.218 |
enegger | -0.214 |
Coy | -0.213 |
withd | -0.197 |
thood | -0.193 |
Token | presumably |
Token ID | 14572 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
unloaded | +0.514 |
Coy | +0.507 |
enegger | +0.499 |
withd | +0.470 |
perce | +0.465 |
Neg logit contributions | |
roud | -0.812 |
rog | -0.696 |
utherland | -0.633 |
rite | -0.620 |
mia | -0.599 |
Token | minim |
Token ID | 10356 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
unloaded | +0.127 |
Coy | +0.126 |
enegger | +0.124 |
withd | +0.117 |
perce | +0.115 |
Neg logit contributions | |
roud | -0.200 |
rog | -0.172 |
utherland | -0.156 |
rite | -0.153 |
mia | -0.148 |
Token | ise |
Token ID | 786 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
unloaded | +0.471 |
Coy | +0.466 |
enegger | +0.462 |
withd | +0.428 |
thood | +0.422 |
Neg logit contributions | |
roud | -0.918 |
rog | -0.798 |
utherland | -0.730 |
rite | -0.715 |
mia | -0.696 |
Token | any |
Token ID | 597 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
roud | +1.013 |
rog | +0.868 |
utherland | +0.781 |
rite | +0.764 |
mia | +0.740 |
Neg logit contributions | |
unloaded | -0.697 |
Coy | -0.690 |
enegger | -0.690 |
withd | -0.647 |
thood | -0.638 |
Token | potential |
Token ID | 2785 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
unloaded | +0.540 |
Coy | +0.535 |
enegger | +0.530 |
withd | +0.496 |
perce | +0.492 |
Neg logit contributions | |
roud | -0.865 |
rog | -0.743 |
utherland | -0.673 |
rite | -0.660 |
mia | -0.639 |
Token | technical |
Token ID | 6276 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
unloaded | +0.269 |
Coy | +0.266 |
enegger | +0.265 |
withd | +0.248 |
thood | +0.244 |
Neg logit contributions | |
roud | -0.425 |
rog | -0.366 |
utherland | -0.331 |
rite | -0.324 |
mia | -0.314 |
Token | interference |
Token ID | 14517 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
unloaded | +1.506 |
Coy | +1.494 |
enegger | +1.458 |
perce | +1.365 |
withd | +1.357 |
Neg logit contributions | |
roud | -2.785 |
rog | -2.401 |
utherland | -2.207 |
rite | -2.156 |
mia | -2.088 |
Token | - |
Token ID | 532 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
unloaded | +0.265 |
Coy | +0.263 |
enegger | +0.261 |
withd | +0.243 |
thood | +0.239 |
Neg logit contributions | |
roud | -0.453 |
rog | -0.391 |
utherland | -0.356 |
rite | -0.348 |
mia | -0.338 |
Token | LOC |
Token ID | 37347 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
unloaded | +0.326 |
Coy | +0.323 |
enegger | +0.317 |
withd | +0.299 |
perce | +0.294 |
Neg logit contributions | |
roud | -0.551 |
rog | -0.475 |
utherland | -0.433 |
rite | -0.424 |
mia | -0.412 |
Token | OG |
Token ID | 7730 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
unloaded | +0.488 |
Coy | +0.484 |
enegger | +0.480 |
withd | +0.452 |
perce | +0.447 |
Neg logit contributions | |
roud | -0.653 |
rog | -0.554 |
utherland | -0.499 |
rite | -0.487 |
mia | -0.470 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
unloaded | +0.175 |
Coy | +0.174 |
enegger | +0.173 |
withd | +0.162 |
perce | +0.160 |
Neg logit contributions | |
roud | -0.247 |
rog | -0.211 |
utherland | -0.190 |
rite | -0.185 |
mia | -0.179 |
Token | s |
Token ID | 82 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
roud | +0.711 |
rog | +0.612 |
utherland | +0.554 |
rite | +0.542 |
mia | +0.526 |
Neg logit contributions | |
unloaded | -0.448 |
Coy | -0.443 |
enegger | -0.441 |
withd | -0.411 |
perce | -0.406 |
Token | are |
Token ID | 389 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
roud | +0.464 |
rog | +0.394 |
utherland | +0.355 |
rite | +0.346 |
mia | +0.334 |
Neg logit contributions | |
unloaded | -0.349 |
Coy | -0.344 |
enegger | -0.343 |
withd | -0.322 |
perce | -0.318 |
Token | CPU |
Token ID | 9135 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
roud | +0.157 |
rog | +0.135 |
utherland | +0.123 |
rite | +0.120 |
mia | +0.117 |
Neg logit contributions | |
unloaded | -0.093 |
Coy | -0.092 |
enegger | -0.092 |
withd | -0.085 |
thood | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
unloaded | +0.212 |
Coy | +0.209 |
enegger | +0.208 |
withd | +0.195 |
thood | +0.192 |
Neg logit contributions | |
roud | -0.325 |
rog | -0.279 |
utherland | -0.253 |
rite | -0.247 |
mia | -0.239 |
Token | memory |
Token ID | 4088 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
roud | +0.690 |
rog | +0.602 |
utherland | +0.551 |
rite | +0.541 |
mia | +0.526 |
Neg logit contributions | |
unloaded | -0.331 |
enegger | -0.328 |
Coy | -0.328 |
withd | -0.302 |
thood | -0.298 |
Token | bound |
Token ID | 5421 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
unloaded | +0.441 |
Coy | +0.436 |
enegger | +0.433 |
withd | +0.405 |
perce | +0.399 |
Neg logit contributions | |
roud | -0.697 |
rog | -0.600 |
utherland | -0.543 |
rite | -0.531 |
mia | -0.515 |
Token | , |
Token ID | 11 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
unloaded | +1.312 |
Coy | +1.286 |
enegger | +1.270 |
withd | +1.186 |
perce | +1.169 |
Neg logit contributions | |
roud | -2.319 |
rog | -2.014 |
utherland | -1.839 |
rite | -1.788 |
mia | -1.749 |
Token | which |
Token ID | 543 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
roud | +0.290 |
rog | +0.252 |
utherland | +0.230 |
rite | +0.226 |
mia | +0.220 |
Neg logit contributions | |
unloaded | -0.150 |
Coy | -0.148 |
enegger | -0.147 |
withd | -0.137 |
perce | -0.134 |
Token | were |
Token ID | 547 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
roud | +0.301 |
rog | +0.258 |
utherland | +0.234 |
rite | +0.229 |
mia | +0.222 |
Neg logit contributions | |
unloaded | -0.192 |
Coy | -0.190 |
enegger | -0.190 |
withd | -0.177 |
thood | -0.175 |
Token | already |
Token ID | 1541 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
unloaded | +0.026 |
Coy | +0.026 |
enegger | +0.025 |
withd | +0.024 |
perce | +0.023 |
Neg logit contributions | |
roud | -0.046 |
rog | -0.040 |
utherland | -0.036 |
rite | -0.035 |
mia | -0.034 |
Token | virtual |
Token ID | 7166 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
roud | +0.329 |
rog | +0.285 |
utherland | +0.259 |
rite | +0.254 |
mia | +0.247 |
Neg logit contributions | |
unloaded | -0.185 |
Coy | -0.183 |
enegger | -0.181 |
withd | -0.169 |
perce | -0.166 |
Token | sim |
Token ID | 985 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
unloaded | +0.247 |
Coy | +0.245 |
enegger | +0.239 |
withd | +0.227 |
perce | +0.224 |
Neg logit contributions | |
roud | -0.369 |
rog | -0.316 |
utherland | -0.286 |
rite | -0.279 |
mia | -0.271 |
Token | ulators |
Token ID | 24325 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
roud | +0.687 |
rog | +0.579 |
utherland | +0.518 |
rite | +0.506 |
mia | +0.487 |
Neg logit contributions | |
unloaded | -0.559 |
Coy | -0.554 |
enegger | -0.552 |
withd | -0.521 |
thood | -0.515 |
Token | , |
Token ID | 11 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
unloaded | +0.357 |
Coy | +0.353 |
enegger | +0.352 |
withd | +0.326 |
thood | +0.321 |
Neg logit contributions | |
roud | -0.681 |
rog | -0.592 |
utherland | -0.540 |
rite | -0.529 |
mia | -0.515 |
Token | publications |
Token ID | 16125 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
unloaded | +0.206 |
Coy | +0.204 |
enegger | +0.202 |
withd | +0.190 |
perce | +0.188 |
Neg logit contributions | |
roud | -0.295 |
rog | -0.252 |
utherland | -0.227 |
rite | -0.222 |
mia | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
unloaded | +0.063 |
enegger | +0.062 |
Coy | +0.062 |
withd | +0.058 |
thood | +0.057 |
Neg logit contributions | |
roud | -0.119 |
rog | -0.103 |
utherland | -0.094 |
rite | -0.093 |
mia | -0.090 |
Token | technical |
Token ID | 6276 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
unloaded | +0.246 |
Coy | +0.243 |
enegger | +0.239 |
withd | +0.225 |
perce | +0.223 |
Neg logit contributions | |
roud | -0.373 |
rog | -0.319 |
utherland | -0.290 |
rite | -0.283 |
mia | -0.274 |
Token | documentation |
Token ID | 10314 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
unloaded | +1.802 |
Coy | +1.790 |
enegger | +1.737 |
withd | +1.642 |
perce | +1.636 |
Neg logit contributions | |
roud | -2.888 |
rog | -2.484 |
utherland | -2.266 |
rite | -2.214 |
mia | -2.141 |
Token | , |
Token ID | 11 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
unloaded | +1.007 |
Coy | +0.995 |
enegger | +0.978 |
withd | +0.916 |
perce | +0.902 |
Neg logit contributions | |
roud | -1.831 |
rog | -1.589 |
utherland | -1.452 |
rite | -1.419 |
mia | -1.380 |
Token | cybersecurity |
Token ID | 31335 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
unloaded | +0.509 |
Coy | +0.503 |
enegger | +0.489 |
withd | +0.465 |
perce | +0.458 |
Neg logit contributions | |
roud | -0.838 |
rog | -0.723 |
utherland | -0.656 |
rite | -0.642 |
mia | -0.626 |
Token | , |
Token ID | 11 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
unloaded | +0.134 |
Coy | +0.133 |
enegger | +0.130 |
withd | +0.123 |
perce | +0.121 |
Neg logit contributions | |
roud | -0.209 |
rog | -0.180 |
utherland | -0.163 |
rite | -0.159 |
mia | -0.155 |
Token | critical |
Token ID | 4688 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
unloaded | +0.457 |
Coy | +0.453 |
enegger | +0.442 |
withd | +0.420 |
perce | +0.415 |
Neg logit contributions | |
roud | -0.695 |
rog | -0.597 |
utherland | -0.541 |
rite | -0.528 |
mia | -0.512 |
Token | first |
Token ID | 717 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
roud | +0.342 |
rog | +0.290 |
utherland | +0.262 |
rite | +0.254 |
mia | +0.247 |
Neg logit contributions | |
unloaded | -0.256 |
Coy | -0.254 |
enegger | -0.251 |
withd | -0.236 |
perce | -0.235 |
Token | rock |
Token ID | 3881 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
unloaded | +0.161 |
Coy | +0.159 |
enegger | +0.159 |
withd | +0.148 |
perce | +0.146 |
Neg logit contributions | |
roud | -0.249 |
rog | -0.214 |
utherland | -0.194 |
rite | -0.189 |
mia | -0.183 |
Token | analyzed |
Token ID | 15475 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
unloaded | +0.509 |
Coy | +0.504 |
enegger | +0.500 |
withd | +0.466 |
perce | +0.460 |
Neg logit contributions | |
roud | -0.853 |
rog | -0.734 |
utherland | -0.669 |
rite | -0.653 |
mia | -0.635 |
Token | by |
Token ID | 416 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
unloaded | +0.295 |
Coy | +0.291 |
enegger | +0.288 |
withd | +0.268 |
perce | +0.265 |
Neg logit contributions | |
roud | -0.526 |
rog | -0.455 |
utherland | -0.416 |
rite | -0.406 |
mia | -0.396 |
Token | the |
Token ID | 262 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
roud | +0.215 |
rog | +0.184 |
utherland | +0.166 |
rite | +0.162 |
mia | +0.157 |
Neg logit contributions | |
unloaded | -0.152 |
Coy | -0.151 |
enegger | -0.150 |
withd | -0.141 |
perce | -0.139 |
Token | rover |
Token ID | 35761 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
roud | +0.116 |
rog | +0.099 |
utherland | +0.090 |
rite | +0.088 |
mia | +0.085 |
Neg logit contributions | |
unloaded | -0.082 |
Coy | -0.081 |
enegger | -0.080 |
withd | -0.076 |
thood | -0.075 |
Token | 's |
Token ID | 338 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
unloaded | +1.353 |
Coy | +1.345 |
enegger | +1.299 |
withd | +1.236 |
perce | +1.235 |
Neg logit contributions | |
roud | -2.250 |
rog | -1.938 |
utherland | -1.791 |
rite | -1.719 |
mia | -1.692 |
Token | arm |
Token ID | 3211 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
unloaded | +0.098 |
Coy | +0.098 |
enegger | +0.097 |
withd | +0.091 |
perce | +0.090 |
Neg logit contributions | |
roud | -0.138 |
rog | -0.117 |
utherland | -0.106 |
rite | -0.103 |
mia | -0.100 |
Token | - |
Token ID | 12 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
roud | +0.250 |
rog | +0.215 |
utherland | +0.196 |
rite | +0.191 |
mia | +0.186 |
Neg logit contributions | |
unloaded | -0.153 |
Coy | -0.152 |
enegger | -0.151 |
withd | -0.141 |
perce | -0.139 |
Token | mounted |
Token ID | 29728 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
roud | +0.338 |
rog | +0.273 |
utherland | +0.230 |
rite | +0.225 |
mia | +0.212 |
Neg logit contributions | |
unloaded | -0.454 |
Coy | -0.452 |
enegger | -0.452 |
withd | -0.433 |
thood | -0.427 |
Token | Alpha |
Token ID | 12995 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
roud | +0.063 |
rog | +0.054 |
utherland | +0.048 |
rite | +0.047 |
mia | +0.046 |
Neg logit contributions | |
unloaded | -0.042 |
Coy | -0.042 |
enegger | -0.042 |
withd | -0.039 |
thood | -0.038 |