Token | struggles |
Token ID | 12766 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
holiest | +2.122 |
saf | +1.940 |
cific | +1.910 |
Trivia | +1.892 |
Advantage | +1.877 |
Neg logit contributions | |
debates | -1.377 |
adoption | -1.335 |
birth | -1.334 |
Pg | -1.320 |
rons | -1.304 |
Token | against |
Token ID | 1028 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
holiest | +2.204 |
saf | +2.009 |
cific | +1.981 |
Trivia | +1.960 |
Advantage | +1.942 |
Neg logit contributions | |
debates | -1.506 |
adoption | -1.462 |
birth | -1.455 |
Pg | -1.441 |
rons | -1.426 |
Token | the |
Token ID | 262 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
debates | +0.412 |
adoption | +0.402 |
birth | +0.392 |
amounts | +0.389 |
Pg | +0.388 |
Neg logit contributions | |
holiest | -0.642 |
saf | -0.588 |
cific | -0.583 |
Trivia | -0.576 |
Advantage | -0.566 |
Token | catastrophic |
Token ID | 22694 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
holiest | +0.879 |
saf | +0.805 |
cific | +0.796 |
Trivia | +0.787 |
Advantage | +0.777 |
Neg logit contributions | |
debates | -0.561 |
adoption | -0.545 |
birth | -0.538 |
Pg | -0.533 |
rons | -0.527 |
Token | and |
Token ID | 290 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
holiest | +1.085 |
saf | +0.993 |
cific | +0.983 |
Trivia | +0.971 |
Advantage | +0.959 |
Neg logit contributions | |
debates | -0.690 |
adoption | -0.669 |
birth | -0.660 |
Pg | -0.652 |
amounts | -0.649 |
Token | explo |
Token ID | 6694 |
Feature activation | +1.75e+01 |
Pos logit contributions | |
holiest | +3.560 |
saf | +3.230 |
cific | +3.174 |
Trivia | +3.146 |
Advantage | +3.124 |
Neg logit contributions | |
debates | -2.329 |
birth | -2.262 |
adoption | -2.249 |
Pg | -2.236 |
rons | -2.224 |
Token | itative |
Token ID | 12464 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
holiest | +8.395 |
saf | +8.047 |
cific | +7.509 |
Advantage | +7.151 |
Trivia | +7.081 |
Neg logit contributions | |
rons | -13.755 |
adoption | -13.573 |
Lauder | -13.554 |
bathing | -13.317 |
croft | -13.305 |
Token | choices |
Token ID | 7747 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
holiest | +6.535 |
saf | +5.944 |
Advantage | +5.825 |
Trivia | +5.724 |
cific | +5.701 |
Neg logit contributions | |
birth | -4.501 |
Pg | -4.490 |
tumblr | -4.483 |
debates | -4.456 |
rons | -4.411 |
Token | of |
Token ID | 286 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
holiest | +0.916 |
saf | +0.838 |
cific | +0.830 |
Trivia | +0.822 |
Advantage | +0.811 |
Neg logit contributions | |
debates | -0.558 |
adoption | -0.540 |
birth | -0.534 |
Pg | -0.528 |
rons | -0.524 |
Token | the |
Token ID | 262 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
holiest | +3.669 |
saf | +3.341 |
cific | +3.280 |
Trivia | +3.249 |
Advantage | +3.239 |
Neg logit contributions | |
debates | -2.528 |
birth | -2.462 |
Pg | -2.449 |
adoption | -2.446 |
rons | -2.406 |
Token | state |
Token ID | 1181 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
holiest | +2.700 |
saf | +2.460 |
cific | +2.421 |
Trivia | +2.398 |
Advantage | +2.382 |
Neg logit contributions | |
debates | -1.798 |
birth | -1.743 |
adoption | -1.741 |
Pg | -1.727 |
rons | -1.704 |
Token | the |
Token ID | 262 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
debates | +0.588 |
adoption | +0.570 |
birth | +0.554 |
amounts | +0.549 |
Pg | +0.538 |
Neg logit contributions | |
holiest | -0.990 |
saf | -0.910 |
cific | -0.902 |
Trivia | -0.894 |
Advantage | -0.872 |
Token | donation |
Token ID | 13784 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
debates | +0.545 |
adoption | +0.532 |
amounts | +0.510 |
birth | +0.509 |
viewing | +0.496 |
Neg logit contributions | |
holiest | -0.874 |
saf | -0.805 |
cific | -0.801 |
Trivia | -0.791 |
INGTON | -0.774 |
Token | would |
Token ID | 561 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
debates | +1.840 |
amounts | +1.778 |
adoption | +1.771 |
Pg | +1.698 |
birth | +1.692 |
Neg logit contributions | |
holiest | -3.039 |
saf | -2.801 |
cific | -2.764 |
Trivia | -2.739 |
INGTON | -2.684 |
Token | have |
Token ID | 423 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
debates | +2.368 |
adoption | +2.341 |
amounts | +2.338 |
birth | +2.177 |
clam | +2.168 |
Neg logit contributions | |
holiest | -7.115 |
cific | -6.513 |
Trivia | -6.501 |
saf | -6.400 |
Advantage | -6.327 |
Token | on |
Token ID | 319 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
debates | +2.023 |
adoption | +1.993 |
amounts | +1.939 |
birth | +1.916 |
Pg | +1.866 |
Neg logit contributions | |
holiest | -3.771 |
saf | -3.408 |
Trivia | -3.407 |
cific | -3.395 |
Advantage | -3.322 |
Token | financially |
Token ID | 18786 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
debates | +1.607 |
adoption | +1.556 |
amounts | +1.469 |
birth | +1.467 |
breastfeeding | +1.443 |
Neg logit contributions | |
holiest | -3.248 |
saf | -3.006 |
cific | -2.972 |
Trivia | -2.951 |
INGTON | -2.883 |
Token | disadvantaged |
Token ID | 36327 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
holiest | +12.457 |
saf | +10.894 |
Advantage | +10.720 |
ever | +10.417 |
INGTON | +10.378 |
Neg logit contributions | |
xon | -10.236 |
rons | -9.792 |
Pg | -9.758 |
anamo | -9.653 |
croft | -9.548 |
Token | students |
Token ID | 2444 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
holiest | +3.888 |
saf | +3.612 |
cific | +3.555 |
Advantage | +3.540 |
Trivia | +3.530 |
Neg logit contributions | |
debates | -1.326 |
Pg | -1.276 |
birth | -1.276 |
adoption | -1.263 |
rons | -1.227 |
Token | by |
Token ID | 416 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
debates | +3.204 |
adoption | +3.082 |
viewing | +3.046 |
amounts | +3.041 |
birth | +3.021 |
Neg logit contributions | |
holiest | -5.393 |
saf | -4.974 |
cific | -4.871 |
Trivia | -4.849 |
INGTON | -4.805 |
Token | drawing |
Token ID | 8263 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
holiest | +1.527 |
saf | +1.410 |
cific | +1.395 |
Trivia | +1.382 |
Advantage | +1.368 |
Neg logit contributions | |
debates | -0.691 |
adoption | -0.666 |
birth | -0.656 |
Pg | -0.643 |
rons | -0.637 |
Token | from |
Token ID | 422 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
holiest | +0.279 |
saf | +0.259 |
cific | +0.255 |
Trivia | +0.253 |
Advantage | +0.251 |
Neg logit contributions | |
debates | -0.114 |
adoption | -0.109 |
birth | -0.107 |
Pg | -0.106 |
amounts | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | +9.05e+00 |
Pos logit contributions | |
holiest | +8.744 |
saf | +7.887 |
Advantage | +7.808 |
Trivia | +7.765 |
INGTON | +7.652 |
Neg logit contributions | |
Pg | -8.093 |
debates | -7.878 |
adoption | -7.596 |
tumblr | -7.586 |
Lauder | -7.561 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
holiest | +5.266 |
saf | +4.628 |
Advantage | +4.595 |
cific | +4.504 |
Trivia | +4.492 |
Neg logit contributions | |
debates | -7.322 |
Pg | -7.301 |
birth | -7.119 |
adoption | -7.052 |
xon | -6.971 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
holiest | +2.382 |
saf | +2.157 |
cific | +2.125 |
Trivia | +2.099 |
Advantage | +2.076 |
Neg logit contributions | |
debates | -1.894 |
adoption | -1.843 |
birth | -1.835 |
Pg | -1.816 |
rons | -1.802 |
Token | ( |
Token ID | 357 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
holiest | +0.193 |
saf | +0.177 |
cific | +0.175 |
Trivia | +0.173 |
Advantage | +0.171 |
Neg logit contributions | |
debates | -0.099 |
adoption | -0.096 |
birth | -0.096 |
Pg | -0.094 |
rons | -0.093 |
Token | Published |
Token ID | 24492 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
holiest | +2.700 |
saf | +2.466 |
cific | +2.415 |
Trivia | +2.409 |
Advantage | +2.379 |
Neg logit contributions | |
debates | -1.862 |
adoption | -1.797 |
birth | -1.789 |
Pg | -1.768 |
rons | -1.760 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +1.67e+01 |
Pos logit contributions | |
holiest | +4.003 |
saf | +3.618 |
cific | +3.512 |
Advantage | +3.511 |
Trivia | +3.486 |
Neg logit contributions | |
debates | -3.349 |
Pg | -3.308 |
birth | -3.267 |
adoption | -3.247 |
rons | -3.194 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
holiest | +9.311 |
Advantage | +9.201 |
saf | +8.822 |
Trivia | +8.577 |
gin | +8.520 |
Neg logit contributions | |
debates | -11.236 |
ritical | -11.069 |
adoption | -11.061 |
birth | -11.006 |
Pg | -10.985 |
Token | Dec |
Token ID | 4280 |
Feature activation | +8.81e+00 |
Pos logit contributions | |
holiest | +6.622 |
Advantage | +5.847 |
Trivia | +5.667 |
saf | +5.667 |
INGTON | +5.441 |
Neg logit contributions | |
debates | -9.003 |
Pg | -8.884 |
birth | -8.804 |
stret | -8.737 |
tumblr | -8.737 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
holiest | +5.594 |
saf | +5.278 |
cific | +5.180 |
Advantage | +5.097 |
Trivia | +4.979 |
Neg logit contributions | |
debates | -6.451 |
adoption | -6.260 |
Pg | -6.249 |
clam | -6.136 |
bathing | -6.135 |
Token | 27 |
Token ID | 2681 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
holiest | +2.900 |
saf | +2.593 |
cific | +2.506 |
Advantage | +2.500 |
Trivia | +2.494 |
Neg logit contributions | |
debates | -3.717 |
adoption | -3.628 |
Pg | -3.607 |
birth | -3.591 |
rons | -3.573 |
Token | , |
Token ID | 11 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
holiest | +7.469 |
saf | +7.440 |
Advantage | +7.204 |
Trivia | +7.124 |
INGTON | +7.041 |
Neg logit contributions | |
debates | -8.957 |
anamo | -8.732 |
clam | -8.679 |
stret | -8.618 |
ritical | -8.594 |
Token | in |
Token ID | 287 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
debates | +2.302 |
adoption | +2.285 |
amounts | +2.236 |
rons | +2.153 |
birth | +2.149 |
Neg logit contributions | |
holiest | -4.736 |
Trivia | -4.300 |
saf | -4.291 |
cific | -4.266 |
INGTON | -4.216 |
Token | their |
Token ID | 511 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
debates | +1.336 |
adoption | +1.311 |
amounts | +1.298 |
viewing | +1.230 |
clam | +1.220 |
Neg logit contributions | |
holiest | -2.226 |
cific | -2.038 |
Trivia | -2.024 |
saf | -2.017 |
INGTON | -1.979 |
Token | fine |
Token ID | 3734 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
holiest | +0.458 |
saf | +0.414 |
cific | +0.413 |
Trivia | +0.408 |
Advantage | +0.398 |
Neg logit contributions | |
debates | -0.347 |
adoption | -0.338 |
amounts | -0.332 |
birth | -0.329 |
Pg | -0.328 |
Token | because |
Token ID | 780 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
debates | +1.006 |
adoption | +0.972 |
amounts | +0.965 |
birth | +0.945 |
rons | +0.945 |
Neg logit contributions | |
holiest | -1.528 |
saf | -1.388 |
cific | -1.372 |
Trivia | -1.361 |
Advantage | -1.338 |
Token | they |
Token ID | 484 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
holiest | +1.656 |
saf | +1.512 |
cific | +1.491 |
Trivia | +1.477 |
Advantage | +1.458 |
Neg logit contributions | |
debates | -1.099 |
adoption | -1.066 |
birth | -1.055 |
Pg | -1.046 |
rons | -1.038 |
Token | cooper |
Token ID | 6788 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
holiest | +4.790 |
saf | +4.401 |
cific | +4.315 |
Trivia | +4.268 |
Advantage | +4.247 |
Neg logit contributions | |
debates | -3.095 |
birth | -3.025 |
adoption | -3.019 |
Pg | -2.982 |
rons | -2.922 |
Token | ated |
Token ID | 515 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
saf | +7.014 |
holiest | +6.615 |
rown | +6.439 |
cific | +6.350 |
Trivia | +5.769 |
Neg logit contributions | |
adoption | -14.209 |
birth | -14.205 |
Lauder | -14.005 |
viewing | -13.859 |
debates | -13.848 |
Token | with |
Token ID | 351 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
holiest | +6.867 |
saf | +6.415 |
cific | +6.181 |
Trivia | +6.113 |
Advantage | +6.094 |
Neg logit contributions | |
birth | -5.084 |
debates | -5.065 |
Pg | -5.017 |
adoption | -4.992 |
tumblr | -4.931 |
Token | investigators |
Token ID | 10093 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
holiest | +3.439 |
saf | +3.147 |
cific | +3.094 |
Trivia | +3.050 |
Advantage | +3.034 |
Neg logit contributions | |
debates | -2.385 |
birth | -2.327 |
adoption | -2.310 |
Pg | -2.297 |
rons | -2.268 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
holiest | +0.572 |
saf | +0.517 |
cific | +0.512 |
Trivia | +0.507 |
Advantage | +0.501 |
Neg logit contributions | |
debates | -0.404 |
adoption | -0.390 |
birth | -0.383 |
amounts | -0.382 |
rons | -0.381 |
Token |
|
Token ID | 198 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
debates | +1.097 |
adoption | +1.063 |
birth | +1.062 |
Pg | +1.049 |
rons | +1.045 |
Neg logit contributions | |
holiest | -1.522 |
saf | -1.368 |
cific | -1.352 |
Trivia | -1.337 |
Advantage | -1.308 |
Token | soon |
Token ID | 2582 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
holiest | +0.810 |
saf | +0.737 |
cific | +0.724 |
Trivia | +0.719 |
Advantage | +0.709 |
Neg logit contributions | |
debates | -0.620 |
adoption | -0.601 |
birth | -0.598 |
Pg | -0.590 |
rons | -0.587 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
debates | +0.173 |
adoption | +0.167 |
birth | +0.167 |
rons | +0.164 |
Pg | +0.164 |
Neg logit contributions | |
holiest | -0.254 |
saf | -0.230 |
cific | -0.227 |
Trivia | -0.224 |
Advantage | -0.222 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
holiest | +1.119 |
saf | +1.011 |
cific | +0.997 |
Trivia | +0.984 |
Advantage | +0.970 |
Neg logit contributions | |
debates | -0.846 |
adoption | -0.822 |
birth | -0.821 |
Pg | -0.813 |
rons | -0.802 |
Token |
|
Token ID | 198 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
holiest | +2.724 |
saf | +2.528 |
Trivia | +2.460 |
cific | +2.443 |
Advantage | +2.414 |
Neg logit contributions | |
debates | -2.517 |
adoption | -2.446 |
rons | -2.411 |
birth | -2.398 |
amounts | -2.373 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
holiest | +1.751 |
saf | +1.568 |
cific | +1.554 |
Advantage | +1.524 |
Trivia | +1.521 |
Neg logit contributions | |
debates | -1.366 |
birth | -1.337 |
adoption | -1.330 |
Pg | -1.327 |
rons | -1.302 |
Token | nd |
Token ID | 358 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
holiest | +2.142 |
saf | +1.943 |
cific | +1.912 |
Trivia | +1.891 |
Advantage | +1.870 |
Neg logit contributions | |
debates | -1.556 |
adoption | -1.506 |
birth | -1.496 |
Pg | -1.490 |
rons | -1.472 |
Token | and |
Token ID | 290 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
holiest | +12.716 |
Advantage | +11.409 |
cific | +11.170 |
saf | +11.103 |
Trivia | +10.955 |
Neg logit contributions | |
tumblr | -9.009 |
debates | -8.854 |
Lauder | -8.846 |
Pg | -8.608 |
birth | -8.580 |
Token | 6 |
Token ID | 718 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
holiest | +3.753 |
saf | +3.362 |
cific | +3.289 |
Trivia | +3.250 |
Advantage | +3.234 |
Neg logit contributions | |
debates | -3.735 |
adoption | -3.641 |
birth | -3.640 |
Pg | -3.614 |
rons | -3.591 |
Token | : |
Token ID | 25 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
debates | +0.530 |
adoption | +0.512 |
amounts | +0.499 |
birth | +0.499 |
Pg | +0.498 |
Neg logit contributions | |
holiest | -0.788 |
saf | -0.713 |
cific | -0.704 |
Trivia | -0.698 |
Advantage | -0.683 |
Token | B |
Token ID | 347 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
holiest | +1.177 |
saf | +1.060 |
cific | +1.051 |
Trivia | +1.039 |
Advantage | +1.021 |
Neg logit contributions | |
debates | -0.848 |
adoption | -0.824 |
birth | -0.821 |
Pg | -0.813 |
rons | -0.802 |
Token | ugg |
Token ID | 6837 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
holiest | +0.903 |
saf | +0.816 |
cific | +0.802 |
Trivia | +0.793 |
Advantage | +0.785 |
Neg logit contributions | |
debates | -0.752 |
adoption | -0.733 |
birth | -0.727 |
Pg | -0.723 |
rons | -0.716 |
Token | battling |
Token ID | 20581 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
debates | +0.368 |
adoption | +0.362 |
amounts | +0.350 |
birth | +0.350 |
viewing | +0.347 |
Neg logit contributions | |
holiest | -0.604 |
saf | -0.549 |
cific | -0.546 |
Trivia | -0.546 |
INGTON | -0.534 |
Token | display |
Token ID | 3359 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
holiest | +2.702 |
saf | +2.464 |
cific | +2.431 |
Trivia | +2.404 |
Advantage | +2.394 |
Neg logit contributions | |
debates | -1.765 |
birth | -1.709 |
adoption | -1.707 |
Pg | -1.695 |
rons | -1.671 |
Token | . |
Token ID | 13 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
debates | +0.792 |
adoption | +0.772 |
amounts | +0.758 |
rons | +0.752 |
birth | +0.745 |
Neg logit contributions | |
holiest | -1.268 |
saf | -1.159 |
cific | -1.152 |
Trivia | -1.141 |
INGTON | -1.114 |
Token |
|
Token ID | 198 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
debates | +0.408 |
birth | +0.396 |
Pg | +0.395 |
adoption | +0.395 |
amounts | +0.383 |
Neg logit contributions | |
holiest | -0.617 |
saf | -0.555 |
cific | -0.547 |
Trivia | -0.537 |
INGTON | -0.524 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
debates | +0.314 |
birth | +0.308 |
adoption | +0.306 |
Pg | +0.305 |
rons | +0.298 |
Neg logit contributions | |
holiest | -0.451 |
saf | -0.405 |
cific | -0.403 |
Trivia | -0.394 |
Advantage | -0.392 |
Token | Sl |
Token ID | 11122 |
Feature activation | +1.65e+01 |
Pos logit contributions | |
Pg | +1.357 |
birth | +1.332 |
debates | +1.301 |
adoption | +1.283 |
tumblr | +1.263 |
Neg logit contributions | |
holiest | -1.814 |
cific | -1.606 |
Advantage | -1.589 |
saf | -1.583 |
INGTON | -1.520 |
Token | ov |
Token ID | 709 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
holiest | +11.624 |
saf | +11.221 |
rown | +11.193 |
ever | +11.181 |
cific | +10.661 |
Neg logit contributions | |
Lauder | -9.729 |
tumblr | -9.146 |
adoption | -9.048 |
birth | -8.987 |
breastfeeding | -8.936 |
Token | akia |
Token ID | 21897 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
holiest | +1.610 |
saf | +1.447 |
cific | +1.420 |
Trivia | +1.400 |
Advantage | +1.382 |
Neg logit contributions | |
debates | -1.668 |
adoption | -1.627 |
birth | -1.622 |
Pg | -1.612 |
rons | -1.596 |
Token | � |
Token ID | 447 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
holiest | +6.560 |
saf | +5.993 |
Advantage | +5.935 |
Trivia | +5.827 |
cific | +5.772 |
Neg logit contributions | |
debates | -4.556 |
Pg | -4.498 |
tumblr | -4.462 |
birth | -4.438 |
adoption | -4.373 |
Token | � |
Token ID | 247 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
holiest | +3.823 |
saf | +3.456 |
cific | +3.391 |
Trivia | +3.369 |
Advantage | +3.333 |
Neg logit contributions | |
debates | -3.216 |
adoption | -3.120 |
birth | -3.104 |
Pg | -3.089 |
rons | -3.081 |
Token | s |
Token ID | 82 |
Feature activation | +8.87e+00 |
Pos logit contributions | |
holiest | +1.174 |
saf | +1.061 |
cific | +1.050 |
Trivia | +1.036 |
Advantage | +1.028 |
Neg logit contributions | |
debates | -0.851 |
birth | -0.829 |
adoption | -0.829 |
Pg | -0.820 |
rons | -0.810 |
Token | incident |
Token ID | 4519 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
holiest | +1.486 |
saf | +1.359 |
cific | +1.340 |
Trivia | +1.327 |
Advantage | +1.315 |
Neg logit contributions | |
debates | -0.941 |
adoption | -0.912 |
birth | -0.907 |
Pg | -0.898 |
rons | -0.888 |
Token | in |
Token ID | 287 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
holiest | +0.572 |
saf | +0.525 |
cific | +0.522 |
Trivia | +0.513 |
Advantage | +0.510 |
Neg logit contributions | |
debates | -0.341 |
adoption | -0.328 |
birth | -0.324 |
amounts | -0.320 |
rons | -0.319 |
Token | the |
Token ID | 262 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
holiest | +1.195 |
saf | +1.089 |
cific | +1.076 |
Trivia | +1.066 |
Advantage | +1.051 |
Neg logit contributions | |
debates | -0.854 |
adoption | -0.829 |
birth | -0.820 |
Pg | -0.809 |
amounts | -0.805 |
Token | revolution |
Token ID | 5854 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
debates | +0.334 |
adoption | +0.326 |
birth | +0.320 |
amounts | +0.316 |
Pg | +0.314 |
Neg logit contributions | |
holiest | -0.447 |
saf | -0.412 |
cific | -0.411 |
Trivia | -0.407 |
Advantage | -0.398 |
Token | - |
Token ID | 12 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
debates | +4.379 |
adoption | +4.103 |
amounts | +4.083 |
rons | +4.013 |
viewing | +3.971 |
Neg logit contributions | |
holiest | -6.552 |
Trivia | -6.200 |
cific | -6.151 |
Advantage | -6.050 |
saf | -6.025 |
Token | wr |
Token ID | 18351 |
Feature activation | +1.65e+01 |
Pos logit contributions | |
holiest | +1.223 |
saf | +1.101 |
cific | +1.091 |
Trivia | +1.079 |
Advantage | +1.071 |
Neg logit contributions | |
debates | -1.000 |
birth | -0.973 |
adoption | -0.969 |
Pg | -0.963 |
rons | -0.952 |
Token | acked |
Token ID | 6021 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
holiest | +4.420 |
rown | +3.995 |
saf | +3.812 |
cific | +3.650 |
cture | +3.388 |
Neg logit contributions | |
adoption | -16.568 |
Lauder | -16.264 |
birth | -16.157 |
tumblr | -16.003 |
debates | -15.910 |
Token | nation |
Token ID | 3277 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
holiest | +0.605 |
saf | +0.553 |
cific | +0.548 |
Trivia | +0.544 |
Advantage | +0.533 |
Neg logit contributions | |
debates | -0.453 |
adoption | -0.442 |
birth | -0.436 |
Pg | -0.429 |
amounts | -0.429 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
debates | +0.968 |
birth | +0.929 |
adoption | +0.927 |
amounts | +0.915 |
rons | +0.914 |
Neg logit contributions | |
holiest | -1.458 |
saf | -1.328 |
cific | -1.324 |
Trivia | -1.304 |
Advantage | -1.297 |
Token | a |
Token ID | 257 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
debates | +0.090 |
adoption | +0.088 |
birth | +0.086 |
amounts | +0.085 |
Pg | +0.084 |
Neg logit contributions | |
holiest | -0.128 |
saf | -0.117 |
cific | -0.116 |
Trivia | -0.115 |
Advantage | -0.113 |
Token | senior |
Token ID | 4664 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
debates | +0.117 |
adoption | +0.115 |
birth | +0.111 |
amounts | +0.110 |
Pg | +0.110 |
Neg logit contributions | |
holiest | -0.168 |
saf | -0.155 |
cific | -0.153 |
Trivia | -0.152 |
Advantage | -0.149 |
Token | De |
Token ID | 1024 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
debates | +0.669 |
adoption | +0.646 |
birth | +0.643 |
Pg | +0.638 |
rons | +0.629 |
Neg logit contributions | |
holiest | -1.181 |
saf | -1.081 |
cific | -1.067 |
Trivia | -1.053 |
INGTON | -1.039 |
Token | vers |
Token ID | 690 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
debates | +4.160 |
birth | +4.131 |
adoption | +4.070 |
Pg | +3.999 |
rons | +3.972 |
Neg logit contributions | |
holiest | -4.998 |
saf | -4.478 |
cific | -4.430 |
Advantage | -4.285 |
INGTON | -4.277 |
Token | . |
Token ID | 13 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
debates | +0.702 |
adoption | +0.678 |
birth | +0.678 |
Pg | +0.665 |
rons | +0.663 |
Neg logit contributions | |
holiest | -1.297 |
saf | -1.187 |
cific | -1.173 |
Trivia | -1.159 |
Advantage | -1.149 |
Token |
|
Token ID | 198 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
debates | +1.726 |
birth | +1.705 |
adoption | +1.701 |
Pg | +1.683 |
rons | +1.661 |
Neg logit contributions | |
holiest | -2.480 |
saf | -2.222 |
cific | -2.202 |
Trivia | -2.176 |
INGTON | -2.129 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
holiest | +0.590 |
saf | +0.535 |
cific | +0.527 |
Trivia | +0.522 |
Advantage | +0.516 |
Neg logit contributions | |
debates | -0.463 |
adoption | -0.450 |
birth | -0.448 |
Pg | -0.444 |
rons | -0.440 |
Token | Sl |
Token ID | 11122 |
Feature activation | +1.64e+01 |
Pos logit contributions | |
holiest | +0.161 |
saf | +0.140 |
cific | +0.138 |
Advantage | +0.136 |
Trivia | +0.134 |
Neg logit contributions | |
debates | -0.169 |
birth | -0.167 |
Pg | -0.166 |
adoption | -0.166 |
rons | -0.164 |
Token | ov |
Token ID | 709 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
saf | +11.243 |
ever | +11.136 |
holiest | +11.100 |
rown | +10.983 |
cific | +10.899 |
Neg logit contributions | |
Lauder | -9.519 |
breastfeeding | -8.934 |
bathing | -8.917 |
adoption | -8.687 |
birth | -8.686 |
Token | akia |
Token ID | 21897 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
holiest | +3.222 |
saf | +3.056 |
cific | +2.953 |
Trivia | +2.840 |
Advantage | +2.822 |
Neg logit contributions | |
debates | -4.168 |
Pg | -4.073 |
adoption | -4.060 |
birth | -4.034 |
amounts | -4.011 |
Token | : |
Token ID | 25 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
holiest | +6.597 |
saf | +6.024 |
Advantage | +5.919 |
cific | +5.842 |
Trivia | +5.834 |
Neg logit contributions | |
debates | -6.639 |
Pg | -6.540 |
tumblr | -6.438 |
adoption | -6.402 |
xon | -6.402 |
Token | Gre |
Token ID | 11955 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
holiest | +1.236 |
saf | +1.132 |
cific | +1.118 |
Trivia | +1.107 |
Advantage | +1.094 |
Neg logit contributions | |
debates | -0.725 |
adoption | -0.702 |
birth | -0.698 |
Pg | -0.690 |
rons | -0.682 |
Token | if |
Token ID | 361 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
holiest | +1.148 |
saf | +1.031 |
cific | +1.013 |
Trivia | +1.004 |
Advantage | +0.996 |
Neg logit contributions | |
debates | -0.972 |
birth | -0.947 |
adoption | -0.946 |
Pg | -0.936 |
rons | -0.930 |
Token | at |
Token ID | 379 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
holiest | +0.075 |
saf | +0.068 |
cific | +0.067 |
Trivia | +0.066 |
Advantage | +0.065 |
Neg logit contributions | |
debates | -0.059 |
adoption | -0.057 |
birth | -0.057 |
rons | -0.056 |
amounts | -0.056 |
Token | Wel |
Token ID | 22268 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
holiest | +2.630 |
saf | +2.420 |
cific | +2.390 |
Trivia | +2.367 |
Advantage | +2.348 |
Neg logit contributions | |
debates | -1.364 |
adoption | -1.316 |
birth | -1.308 |
Pg | -1.294 |
rons | -1.277 |
Token | ford |
Token ID | 3841 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
holiest | +4.551 |
saf | +4.351 |
cific | +4.203 |
Trivia | +4.165 |
rown | +4.023 |
Neg logit contributions | |
debates | -3.824 |
adoption | -3.726 |
clam | -3.671 |
amounts | -3.660 |
Pg | -3.658 |
Token | Road |
Token ID | 5567 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
holiest | +3.083 |
saf | +2.695 |
Advantage | +2.604 |
Trivia | +2.589 |
cific | +2.577 |
Neg logit contributions | |
debates | -5.479 |
adoption | -5.373 |
Pg | -5.367 |
birth | -5.330 |
bathing | -5.280 |
Token | , |
Token ID | 11 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
holiest | +5.692 |
saf | +5.192 |
cific | +5.075 |
Trivia | +5.073 |
Advantage | +5.073 |
Neg logit contributions | |
debates | -4.408 |
Pg | -4.364 |
adoption | -4.320 |
birth | -4.277 |
tumblr | -4.248 |
Token | Saturday |
Token ID | 3909 |
Feature activation | +1.61e+01 |
Pos logit contributions | |
holiest | +3.294 |
saf | +2.968 |
cific | +2.931 |
Trivia | +2.887 |
Advantage | +2.880 |
Neg logit contributions | |
debates | -2.734 |
Pg | -2.666 |
adoption | -2.653 |
birth | -2.650 |
rons | -2.614 |
Token | 21 |
Token ID | 2310 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
holiest | +9.970 |
Advantage | +9.270 |
saf | +9.220 |
cific | +8.934 |
Trivia | +8.703 |
Neg logit contributions | |
tumblr | -10.595 |
Pg | -10.535 |
debates | -10.280 |
xon | -10.076 |
adoption | -10.068 |
Token | January |
Token ID | 3269 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
holiest | +5.598 |
saf | +5.090 |
cific | +4.983 |
Trivia | +4.954 |
Advantage | +4.949 |
Neg logit contributions | |
debates | -5.367 |
Pg | -5.263 |
adoption | -5.260 |
birth | -5.226 |
tumblr | -5.165 |
Token | live |
Token ID | 2107 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
holiest | +7.692 |
Advantage | +7.063 |
saf | +6.981 |
Trivia | +6.853 |
cific | +6.812 |
Neg logit contributions | |
Pg | -7.720 |
debates | -7.673 |
adoption | -7.569 |
tumblr | -7.498 |
birth | -7.489 |
Token | on |
Token ID | 319 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
holiest | +0.609 |
saf | +0.555 |
cific | +0.547 |
Trivia | +0.542 |
Advantage | +0.537 |
Neg logit contributions | |
debates | -0.387 |
adoption | -0.374 |
birth | -0.372 |
Pg | -0.366 |
rons | -0.365 |
Token | BT |
Token ID | 22205 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
debates | +1.095 |
adoption | +1.047 |
birth | +1.032 |
viewing | +1.025 |
amounts | +1.017 |
Neg logit contributions | |
holiest | -1.882 |
saf | -1.742 |
cific | -1.715 |
Trivia | -1.710 |
INGTON | -1.679 |
Token | ! |
Token ID | 0 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
debates | +0.656 |
adoption | +0.632 |
birth | +0.627 |
Pg | +0.621 |
rons | +0.619 |
Neg logit contributions | |
holiest | -0.963 |
saf | -0.885 |
cific | -0.869 |
Trivia | -0.856 |
Advantage | -0.845 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
holiest | +2.428 |
saf | +2.205 |
cific | +2.170 |
Trivia | +2.155 |
Advantage | +2.140 |
Neg logit contributions | |
debates | -1.857 |
adoption | -1.809 |
birth | -1.799 |
Pg | -1.783 |
rons | -1.766 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
holiest | +2.944 |
saf | +2.722 |
Trivia | +2.681 |
cific | +2.642 |
Advantage | +2.612 |
Neg logit contributions | |
debates | -2.727 |
adoption | -2.650 |
rons | -2.600 |
birth | -2.588 |
amounts | -2.572 |
Token | When |
Token ID | 2215 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
holiest | +1.936 |
saf | +1.746 |
cific | +1.720 |
Trivia | +1.698 |
Advantage | +1.682 |
Neg logit contributions | |
debates | -1.652 |
adoption | -1.608 |
birth | -1.603 |
Pg | -1.590 |
rons | -1.575 |
Token | : |
Token ID | 25 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
holiest | +0.206 |
saf | +0.189 |
cific | +0.186 |
Trivia | +0.182 |
Advantage | +0.180 |
Neg logit contributions | |
debates | -0.150 |
adoption | -0.145 |
birth | -0.143 |
amounts | -0.141 |
rons | -0.141 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
holiest | +4.397 |
saf | +3.959 |
Advantage | +3.877 |
cific | +3.873 |
Trivia | +3.864 |
Neg logit contributions | |
debates | -3.619 |
adoption | -3.538 |
Pg | -3.533 |
birth | -3.530 |
rons | -3.486 |
Token | , |
Token ID | 11 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
holiest | +10.160 |
Advantage | +9.240 |
saf | +9.021 |
Trivia | +8.716 |
cific | +8.625 |
Neg logit contributions | |
Pg | -10.155 |
tumblr | -10.125 |
anamo | -10.021 |
debates | -9.909 |
birth | -9.821 |
Token | Jul |
Token ID | 5979 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
holiest | +6.149 |
Advantage | +5.443 |
saf | +5.437 |
Trivia | +5.329 |
cific | +5.324 |
Neg logit contributions | |
debates | -5.889 |
Pg | -5.782 |
birth | -5.721 |
adoption | -5.701 |
rons | -5.697 |
Token | 12 |
Token ID | 1105 |
Feature activation | +8.57e+00 |
Pos logit contributions | |
holiest | +6.739 |
saf | +6.267 |
cific | +5.974 |
Advantage | +5.960 |
Trivia | +5.824 |
Neg logit contributions | |
debates | -10.439 |
Pg | -10.197 |
adoption | -10.185 |
breastfeeding | -10.082 |
clam | -10.011 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
holiest | +6.370 |
saf | +5.813 |
Advantage | +5.703 |
cific | +5.602 |
Trivia | +5.588 |
Neg logit contributions | |
debates | -5.535 |
adoption | -5.442 |
Pg | -5.412 |
birth | -5.305 |
tumblr | -5.297 |
Token | : |
Token ID | 25 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
holiest | +1.248 |
saf | +1.118 |
cific | +1.099 |
Trivia | +1.082 |
Advantage | +1.065 |
Neg logit contributions | |
debates | -1.253 |
adoption | -1.223 |
birth | -1.221 |
Pg | -1.204 |
rons | -1.195 |
Token | a |
Token ID | 257 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
holiest | +2.175 |
saf | +1.991 |
cific | +1.969 |
Trivia | +1.945 |
Advantage | +1.913 |
Neg logit contributions | |
debates | -1.388 |
adoption | -1.353 |
birth | -1.334 |
Pg | -1.318 |
amounts | -1.308 |
Token | way |
Token ID | 835 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
holiest | +1.669 |
saf | +1.487 |
cific | +1.463 |
Trivia | +1.445 |
Advantage | +1.421 |
Neg logit contributions | |
debates | -1.810 |
adoption | -1.775 |
birth | -1.763 |
Pg | -1.752 |
rons | -1.734 |
Token | to |
Token ID | 284 |
Feature activation | +9.48e+00 |
Pos logit contributions | |
holiest | +6.217 |
saf | +5.750 |
cific | +5.629 |
Trivia | +5.573 |
Advantage | +5.518 |
Neg logit contributions | |
debates | -3.643 |
birth | -3.501 |
adoption | -3.497 |
Pg | -3.477 |
rons | -3.450 |
Token | make |
Token ID | 787 |
Feature activation | +8.30e+00 |
Pos logit contributions | |
holiest | +7.400 |
saf | +6.883 |
cific | +6.644 |
Advantage | +6.603 |
Trivia | +6.496 |
Neg logit contributions | |
debates | -5.697 |
birth | -5.638 |
Pg | -5.595 |
adoption | -5.488 |
rons | -5.469 |
Token | a |
Token ID | 257 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
holiest | +6.748 |
Advantage | +6.054 |
saf | +6.045 |
Trivia | +5.950 |
cific | +5.944 |
Neg logit contributions | |
debates | -4.805 |
birth | -4.760 |
Pg | -4.697 |
rons | -4.696 |
croft | -4.668 |
Token | profit |
Token ID | 7630 |
Feature activation | +1.58e+01 |
Pos logit contributions | |
holiest | +3.754 |
saf | +3.378 |
cific | +3.308 |
Trivia | +3.285 |
Advantage | +3.257 |
Neg logit contributions | |
debates | -3.308 |
birth | -3.196 |
adoption | -3.177 |
Pg | -3.167 |
rons | -3.165 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
holiest | +10.958 |
saf | +10.177 |
Advantage | +9.982 |
Trivia | +9.886 |
cific | +9.784 |
Neg logit contributions | |
debates | -9.018 |
tumblr | -8.827 |
Pg | -8.730 |
birth | -8.673 |
anamo | -8.628 |
Token | But |
Token ID | 887 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
debates | +0.065 |
birth | +0.064 |
adoption | +0.064 |
Pg | +0.063 |
rons | +0.062 |
Neg logit contributions | |
holiest | -0.090 |
saf | -0.080 |
cific | -0.080 |
Trivia | -0.078 |
INGTON | -0.077 |
Token | that |
Token ID | 326 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
holiest | +4.509 |
saf | +4.122 |
cific | +4.035 |
Advantage | +4.023 |
Trivia | +3.999 |
Neg logit contributions | |
debates | -3.070 |
Pg | -3.023 |
birth | -2.986 |
adoption | -2.960 |
rons | -2.925 |
Token | profit |
Token ID | 7630 |
Feature activation | +7.58e+00 |
Pos logit contributions | |
adoption | +1.008 |
debates | +1.008 |
amounts | +0.983 |
birth | +0.971 |
Pg | +0.953 |
Neg logit contributions | |
holiest | -1.406 |
cific | -1.284 |
saf | -1.276 |
Trivia | -1.263 |
INGTON | -1.245 |
Token | has |
Token ID | 468 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
holiest | +6.274 |
saf | +5.776 |
cific | +5.672 |
Trivia | +5.597 |
Advantage | +5.572 |
Neg logit contributions | |
debates | -4.382 |
Pg | -4.226 |
birth | -4.200 |
adoption | -4.178 |
rons | -4.163 |
Token | repeat |
Token ID | 9585 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
debates | +1.664 |
adoption | +1.643 |
birth | +1.604 |
Pg | +1.584 |
rons | +1.564 |
Neg logit contributions | |
holiest | -2.564 |
saf | -2.370 |
cific | -2.350 |
Trivia | -2.322 |
Advantage | -2.263 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
debates | +3.099 |
adoption | +3.074 |
amounts | +3.022 |
viewing | +3.019 |
birth | +2.967 |
Neg logit contributions | |
holiest | -4.897 |
saf | -4.532 |
cific | -4.489 |
Trivia | -4.415 |
Advantage | -4.309 |
Token | Posted |
Token ID | 12918 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
debates | +1.399 |
Pg | +1.377 |
birth | +1.374 |
adoption | +1.368 |
tumblr | +1.345 |
Neg logit contributions | |
holiest | -2.099 |
saf | -1.885 |
cific | -1.867 |
Trivia | -1.808 |
INGTON | -1.773 |
Token | on |
Token ID | 319 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
holiest | +3.157 |
saf | +2.862 |
cific | +2.820 |
Trivia | +2.788 |
Advantage | +2.761 |
Neg logit contributions | |
debates | -2.451 |
adoption | -2.382 |
birth | -2.374 |
Pg | -2.354 |
rons | -2.328 |
Token | August |
Token ID | 2932 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
debates | +0.517 |
adoption | +0.505 |
birth | +0.498 |
amounts | +0.486 |
rons | +0.482 |
Neg logit contributions | |
holiest | -0.743 |
cific | -0.679 |
saf | -0.675 |
Trivia | -0.661 |
INGTON | -0.654 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
holiest | +4.826 |
saf | +4.406 |
Advantage | +4.245 |
Trivia | +4.216 |
cific | +4.185 |
Neg logit contributions | |
debates | -6.803 |
adoption | -6.648 |
Pg | -6.607 |
birth | -6.547 |
rons | -6.540 |
Token | on |
Token ID | 319 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
holiest | +9.737 |
saf | +9.240 |
Advantage | +8.953 |
Trivia | +8.787 |
cific | +8.646 |
Neg logit contributions | |
debates | -10.409 |
Pg | -10.309 |
adoption | -10.150 |
birth | -10.059 |
bathing | -9.911 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
holiest | +1.297 |
saf | +1.179 |
cific | +1.172 |
Trivia | +1.151 |
Advantage | +1.136 |
Neg logit contributions | |
debates | -0.891 |
adoption | -0.868 |
birth | -0.854 |
Pg | -0.841 |
rons | -0.838 |
Token | , |
Token ID | 11 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
holiest | +5.348 |
saf | +4.842 |
Trivia | +4.767 |
cific | +4.758 |
Advantage | +4.705 |
Neg logit contributions | |
debates | -4.324 |
adoption | -4.207 |
birth | -4.205 |
Pg | -4.185 |
rons | -4.133 |
Token | the |
Token ID | 262 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
holiest | +4.077 |
saf | +3.708 |
cific | +3.665 |
Trivia | +3.627 |
Advantage | +3.604 |
Neg logit contributions | |
debates | -2.792 |
birth | -2.713 |
adoption | -2.704 |
Pg | -2.691 |
rons | -2.667 |
Token | video |
Token ID | 2008 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
holiest | +3.112 |
saf | +2.855 |
cific | +2.819 |
Trivia | +2.792 |
Advantage | +2.771 |
Neg logit contributions | |
debates | -1.702 |
adoption | -1.640 |
birth | -1.639 |
Pg | -1.621 |
rons | -1.604 |
Token | Fore |
Token ID | 4558 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
debates | +0.436 |
birth | +0.422 |
adoption | +0.421 |
Pg | +0.418 |
amounts | +0.413 |
Neg logit contributions | |
holiest | -0.603 |
saf | -0.540 |
cific | -0.536 |
Trivia | -0.529 |
Advantage | -0.514 |
Token | casters |
Token ID | 26248 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
holiest | +3.945 |
saf | +3.647 |
cific | +3.569 |
Trivia | +3.523 |
Advantage | +3.514 |
Neg logit contributions | |
debates | -2.701 |
adoption | -2.640 |
birth | -2.610 |
Pg | -2.596 |
rons | -2.560 |
Token | said |
Token ID | 531 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
holiest | +1.817 |
saf | +1.661 |
cific | +1.639 |
Trivia | +1.623 |
Advantage | +1.607 |
Neg logit contributions | |
debates | -1.141 |
adoption | -1.106 |
birth | -1.099 |
Pg | -1.087 |
rons | -1.077 |
Token | late |
Token ID | 2739 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
holiest | +1.065 |
saf | +0.977 |
cific | +0.963 |
Trivia | +0.955 |
Advantage | +0.940 |
Neg logit contributions | |
debates | -0.690 |
adoption | -0.669 |
birth | -0.658 |
Pg | -0.652 |
amounts | -0.650 |
Token | on |
Token ID | 319 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
holiest | +3.229 |
saf | +2.907 |
cific | +2.871 |
Trivia | +2.832 |
Advantage | +2.830 |
Neg logit contributions | |
debates | -2.439 |
birth | -2.386 |
adoption | -2.368 |
Pg | -2.363 |
rons | -2.328 |
Token | Monday |
Token ID | 3321 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
holiest | +0.140 |
saf | +0.129 |
Trivia | +0.126 |
cific | +0.126 |
Advantage | +0.123 |
Neg logit contributions | |
debates | -0.095 |
adoption | -0.092 |
birth | -0.091 |
amounts | -0.090 |
Pg | -0.089 |
Token | local |
Token ID | 1957 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
holiest | +11.037 |
Advantage | +9.751 |
saf | +9.689 |
cific | +9.515 |
INGTON | +9.262 |
Neg logit contributions | |
birth | -9.486 |
Pg | -9.295 |
tumblr | -9.246 |
rons | -9.025 |
debates | -9.018 |
Token | time |
Token ID | 640 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
holiest | +2.616 |
saf | +2.387 |
cific | +2.353 |
Trivia | +2.329 |
Advantage | +2.314 |
Neg logit contributions | |
debates | -1.693 |
birth | -1.644 |
adoption | -1.641 |
Pg | -1.628 |
rons | -1.605 |
Token | that |
Token ID | 326 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
holiest | +1.076 |
saf | +0.983 |
cific | +0.969 |
Trivia | +0.962 |
Advantage | +0.946 |
Neg logit contributions | |
debates | -0.704 |
adoption | -0.681 |
birth | -0.672 |
Pg | -0.666 |
amounts | -0.662 |
Token | Matthew |
Token ID | 9308 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
holiest | +0.476 |
saf | +0.436 |
cific | +0.430 |
Trivia | +0.426 |
Advantage | +0.419 |
Neg logit contributions | |
debates | -0.310 |
adoption | -0.302 |
birth | -0.295 |
amounts | -0.295 |
Pg | -0.293 |
Token | would |
Token ID | 561 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
debates | +2.705 |
adoption | +2.697 |
amounts | +2.692 |
viewing | +2.573 |
rons | +2.560 |
Neg logit contributions | |
holiest | -4.302 |
cific | -4.046 |
saf | -3.969 |
Trivia | -3.921 |
INGTON | -3.799 |
Token | an |
Token ID | 281 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
debates | +0.700 |
adoption | +0.683 |
amounts | +0.666 |
Pg | +0.660 |
birth | +0.659 |
Neg logit contributions | |
holiest | -0.972 |
saf | -0.889 |
Trivia | -0.877 |
cific | -0.871 |
Advantage | -0.863 |
Token | Israeli |
Token ID | 6085 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
holiest | +2.175 |
saf | +1.950 |
cific | +1.917 |
Trivia | +1.893 |
Advantage | +1.870 |
Neg logit contributions | |
debates | -2.159 |
adoption | -2.109 |
birth | -2.097 |
Pg | -2.081 |
rons | -2.063 |
Token | official |
Token ID | 1743 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
holiest | +1.752 |
saf | +1.561 |
cific | +1.534 |
Trivia | +1.514 |
Advantage | +1.496 |
Neg logit contributions | |
debates | -1.864 |
adoption | -1.820 |
birth | -1.815 |
Pg | -1.801 |
rons | -1.787 |
Token | confirmed |
Token ID | 4999 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
holiest | +4.084 |
saf | +3.712 |
cific | +3.639 |
Trivia | +3.608 |
Advantage | +3.554 |
Neg logit contributions | |
debates | -3.286 |
birth | -3.213 |
adoption | -3.207 |
Pg | -3.204 |
rons | -3.157 |
Token | on |
Token ID | 319 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
holiest | +2.288 |
saf | +2.091 |
cific | +2.062 |
Trivia | +2.041 |
Advantage | +2.022 |
Neg logit contributions | |
debates | -1.470 |
adoption | -1.424 |
birth | -1.418 |
Pg | -1.404 |
rons | -1.389 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
holiest | +0.477 |
saf | +0.433 |
cific | +0.429 |
Trivia | +0.425 |
Advantage | +0.418 |
Neg logit contributions | |
debates | -0.373 |
adoption | -0.364 |
birth | -0.360 |
Pg | -0.356 |
amounts | -0.352 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
holiest | +9.789 |
saf | +8.792 |
cific | +8.524 |
Advantage | +8.259 |
Trivia | +8.252 |
Neg logit contributions | |
tumblr | -10.512 |
Pg | -10.436 |
rons | -10.261 |
birth | -10.212 |
xon | -10.172 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
holiest | +0.462 |
saf | +0.419 |
cific | +0.413 |
Trivia | +0.408 |
Advantage | +0.402 |
Neg logit contributions | |
debates | -0.334 |
adoption | -0.324 |
birth | -0.322 |
Pg | -0.322 |
rons | -0.315 |
Token |
|
Token ID | 198 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
holiest | +1.252 |
saf | +1.140 |
cific | +1.118 |
Trivia | +1.110 |
Advantage | +1.097 |
Neg logit contributions | |
debates | -1.028 |
adoption | -0.999 |
birth | -0.990 |
Pg | -0.980 |
rons | -0.979 |
Token | Although |
Token ID | 7003 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
holiest | +0.254 |
saf | +0.225 |
cific | +0.225 |
Advantage | +0.224 |
Trivia | +0.216 |
Neg logit contributions | |
Pg | -0.208 |
debates | -0.207 |
birth | -0.205 |
adoption | -0.203 |
rons | -0.199 |
Token | there |
Token ID | 612 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
debates | +1.079 |
adoption | +1.039 |
Pg | +1.007 |
birth | +1.005 |
amounts | +1.002 |
Neg logit contributions | |
holiest | -1.733 |
saf | -1.598 |
cific | -1.572 |
Trivia | -1.569 |
Advantage | -1.546 |
Token | said |
Token ID | 531 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
holiest | +1.092 |
saf | +0.994 |
cific | +0.981 |
Trivia | +0.965 |
Advantage | +0.955 |
Neg logit contributions | |
debates | -0.807 |
adoption | -0.782 |
birth | -0.778 |
Pg | -0.766 |
rons | -0.761 |
Token | in |
Token ID | 287 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
holiest | +3.921 |
saf | +3.565 |
cific | +3.494 |
Trivia | +3.471 |
Advantage | +3.440 |
Neg logit contributions | |
debates | -2.691 |
Pg | -2.642 |
birth | -2.632 |
adoption | -2.630 |
rons | -2.566 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
holiest | +2.326 |
saf | +2.106 |
cific | +2.073 |
Trivia | +2.052 |
Advantage | +2.041 |
Neg logit contributions | |
debates | -1.718 |
adoption | -1.678 |
birth | -1.675 |
Pg | -1.673 |
rons | -1.645 |
Token | tweet |
Token ID | 6126 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
holiest | +1.388 |
saf | +1.262 |
cific | +1.244 |
Trivia | +1.231 |
Advantage | +1.219 |
Neg logit contributions | |
debates | -0.992 |
adoption | -0.963 |
birth | -0.959 |
Pg | -0.952 |
rons | -0.941 |
Token | on |
Token ID | 319 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
holiest | +5.784 |
saf | +5.236 |
cific | +5.109 |
Trivia | +5.078 |
Advantage | +5.033 |
Neg logit contributions | |
Pg | -4.160 |
debates | -4.142 |
birth | -4.073 |
adoption | -4.048 |
rons | -3.981 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
holiest | +1.679 |
saf | +1.525 |
cific | +1.503 |
Trivia | +1.487 |
Advantage | +1.472 |
Neg logit contributions | |
debates | -1.245 |
adoption | -1.210 |
birth | -1.205 |
Pg | -1.192 |
rons | -1.181 |
Token | , |
Token ID | 11 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
holiest | +10.910 |
saf | +9.644 |
Trivia | +9.381 |
Advantage | +9.366 |
cific | +9.187 |
Neg logit contributions | |
Pg | -9.513 |
tumblr | -8.935 |
birth | -8.932 |
xon | -8.889 |
adoption | -8.788 |
Token | echoing |
Token ID | 39915 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
holiest | +5.664 |
saf | +5.174 |
cific | +5.076 |
Trivia | +5.033 |
Advantage | +5.029 |
Neg logit contributions | |
debates | -3.121 |
Pg | -3.085 |
birth | -3.027 |
adoption | -3.017 |
rons | -3.006 |
Token | criticisms |
Token ID | 25094 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
holiest | +0.108 |
saf | +0.100 |
cific | +0.099 |
Trivia | +0.097 |
Advantage | +0.096 |
Neg logit contributions | |
debates | -0.064 |
adoption | -0.061 |
birth | -0.060 |
amounts | -0.059 |
rons | -0.058 |
Token | he |
Token ID | 339 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
debates | +0.147 |
adoption | +0.141 |
birth | +0.138 |
amounts | +0.137 |
rons | +0.136 |
Neg logit contributions | |
holiest | -0.271 |
saf | -0.250 |
cific | -0.247 |
Trivia | -0.245 |
Advantage | -0.241 |
Token | made |
Token ID | 925 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
holiest | +3.376 |
saf | +3.090 |
cific | +3.038 |
Trivia | +3.006 |
Advantage | +2.985 |
Neg logit contributions | |
debates | -2.222 |
adoption | -2.159 |
birth | -2.154 |
Pg | -2.138 |
rons | -2.108 |
Token | was |
Token ID | 373 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
holiest | +0.191 |
saf | +0.175 |
cific | +0.174 |
Trivia | +0.172 |
Advantage | +0.169 |
Neg logit contributions | |
debates | -0.126 |
birth | -0.120 |
adoption | -0.120 |
amounts | -0.120 |
Pg | -0.119 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
holiest | +2.008 |
saf | +1.836 |
cific | +1.820 |
Trivia | +1.801 |
Advantage | +1.774 |
Neg logit contributions | |
debates | -1.286 |
adoption | -1.245 |
birth | -1.238 |
Pg | -1.225 |
rons | -1.209 |
Token | Caps |
Token ID | 23534 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
holiest | +2.185 |
saf | +1.994 |
cific | +1.975 |
Trivia | +1.958 |
Advantage | +1.923 |
Neg logit contributions | |
debates | -1.519 |
adoption | -1.475 |
birth | -1.457 |
Pg | -1.440 |
amounts | -1.431 |
Token | who |
Token ID | 508 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
debates | +2.438 |
adoption | +2.400 |
rons | +2.399 |
birth | +2.329 |
clam | +2.319 |
Neg logit contributions | |
holiest | -4.426 |
saf | -4.089 |
cific | -4.083 |
Trivia | -4.012 |
INGTON | -3.863 |
Token | struck |
Token ID | 7425 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
holiest | +4.141 |
saf | +3.785 |
cific | +3.721 |
Trivia | +3.684 |
Advantage | +3.660 |
Neg logit contributions | |
debates | -2.719 |
adoption | -2.639 |
birth | -2.628 |
Pg | -2.600 |
rons | -2.573 |
Token | first |
Token ID | 717 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
holiest | +6.409 |
saf | +5.790 |
Advantage | +5.691 |
cific | +5.655 |
Trivia | +5.588 |
Neg logit contributions | |
debates | -4.107 |
adoption | -3.980 |
birth | -3.979 |
Pg | -3.974 |
rons | -3.920 |
Token | when |
Token ID | 618 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
holiest | +10.355 |
Advantage | +9.277 |
saf | +8.855 |
cific | +8.828 |
Trivia | +8.611 |
Neg logit contributions | |
tumblr | -9.879 |
Pg | -9.668 |
debates | -9.580 |
catentry | -9.537 |
rons | -9.530 |
Token | Alex |
Token ID | 4422 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
holiest | +2.337 |
saf | +2.133 |
cific | +2.102 |
Trivia | +2.081 |
Advantage | +2.071 |
Neg logit contributions | |
debates | -1.542 |
adoption | -1.495 |
birth | -1.492 |
Pg | -1.478 |
rons | -1.461 |
Token | O |
Token ID | 440 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
debates | +3.155 |
birth | +3.080 |
Pg | +3.071 |
amounts | +3.049 |
adoption | +3.031 |
Neg logit contributions | |
holiest | -6.470 |
cific | -5.925 |
saf | -5.824 |
Trivia | -5.675 |
INGTON | -5.545 |
Token | ve |
Token ID | 303 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
debates | +1.172 |
birth | +1.126 |
Pg | +1.122 |
rons | +1.116 |
adoption | +1.107 |
Neg logit contributions | |
holiest | -1.224 |
saf | -1.092 |
cific | -1.059 |
Trivia | -1.054 |
Advantage | -1.037 |
Token | ch |
Token ID | 354 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
debates | +1.677 |
adoption | +1.607 |
birth | +1.599 |
Pg | +1.580 |
rons | +1.555 |
Neg logit contributions | |
holiest | -3.898 |
saf | -3.615 |
cific | -3.570 |
Trivia | -3.531 |
Advantage | -3.493 |
Token | be |
Token ID | 307 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
debates | +0.258 |
adoption | +0.247 |
birth | +0.246 |
amounts | +0.244 |
Pg | +0.242 |
Neg logit contributions | |
holiest | -0.625 |
saf | -0.574 |
cific | -0.572 |
Trivia | -0.570 |
Advantage | -0.563 |
Token | placed |
Token ID | 4624 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
holiest | +2.323 |
saf | +2.098 |
cific | +2.064 |
Trivia | +2.040 |
Advantage | +2.020 |
Neg logit contributions | |
debates | -1.969 |
adoption | -1.917 |
birth | -1.910 |
Pg | -1.893 |
rons | -1.876 |
Token | at |
Token ID | 379 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
holiest | +4.630 |
saf | +4.231 |
cific | +4.165 |
Trivia | +4.127 |
Advantage | +4.094 |
Neg logit contributions | |
debates | -3.016 |
adoption | -2.928 |
birth | -2.918 |
Pg | -2.892 |
rons | -2.849 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
holiest | +2.332 |
saf | +2.127 |
cific | +2.101 |
Trivia | +2.078 |
Advantage | +2.053 |
Neg logit contributions | |
debates | -1.542 |
adoption | -1.500 |
birth | -1.491 |
Pg | -1.472 |
rons | -1.458 |
Token | 0 |
Token ID | 657 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
holiest | +2.197 |
saf | +1.996 |
cific | +1.970 |
Trivia | +1.946 |
Advantage | +1.923 |
Neg logit contributions | |
debates | -1.669 |
adoption | -1.626 |
birth | -1.615 |
Pg | -1.599 |
rons | -1.582 |
Token | th |
Token ID | 400 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
holiest | +4.089 |
saf | +3.683 |
cific | +3.599 |
Trivia | +3.562 |
Advantage | +3.534 |
Neg logit contributions | |
debates | -3.492 |
adoption | -3.391 |
birth | -3.361 |
Pg | -3.351 |
rons | -3.345 |
Token | index |
Token ID | 6376 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
holiest | +11.546 |
saf | +10.216 |
Advantage | +9.980 |
cific | +9.744 |
Trivia | +9.549 |
Neg logit contributions | |
debates | -8.917 |
rons | -8.673 |
tumblr | -8.638 |
anamo | -8.525 |
Pg | -8.466 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
holiest | +1.418 |
saf | +1.294 |
cific | +1.280 |
Trivia | +1.269 |
Advantage | +1.249 |
Neg logit contributions | |
debates | -0.949 |
adoption | -0.926 |
birth | -0.919 |
Pg | -0.910 |
rons | -0.903 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
debates | +0.905 |
adoption | +0.882 |
birth | +0.882 |
Pg | +0.870 |
amounts | +0.862 |
Neg logit contributions | |
holiest | -1.318 |
saf | -1.186 |
cific | -1.170 |
Trivia | -1.145 |
INGTON | -1.137 |
Token |
|
Token ID | 198 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
holiest | +0.899 |
saf | +0.817 |
cific | +0.803 |
Trivia | +0.796 |
Advantage | +0.787 |
Neg logit contributions | |
debates | -0.714 |
adoption | -0.695 |
birth | -0.690 |
Pg | -0.684 |
rons | -0.680 |
Token | After |
Token ID | 3260 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
birth | +0.529 |
Pg | +0.528 |
debates | +0.527 |
adoption | +0.520 |
tumblr | +0.509 |
Neg logit contributions | |
holiest | -0.682 |
cific | -0.599 |
saf | -0.595 |
Advantage | -0.592 |
INGTON | -0.580 |
Token | phone |
Token ID | 3072 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
debates | +0.085 |
adoption | +0.083 |
birth | +0.081 |
Pg | +0.081 |
rons | +0.080 |
Neg logit contributions | |
holiest | -0.171 |
saf | -0.156 |
cific | -0.156 |
Trivia | -0.153 |
Advantage | -0.152 |
Token | in |
Token ID | 287 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
debates | +0.502 |
adoption | +0.487 |
birth | +0.478 |
amounts | +0.471 |
viewing | +0.470 |
Neg logit contributions | |
holiest | -0.765 |
saf | -0.700 |
cific | -0.689 |
Trivia | -0.678 |
Advantage | -0.669 |
Token | downtown |
Token ID | 9436 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
holiest | +1.007 |
saf | +0.913 |
cific | +0.901 |
Trivia | +0.887 |
Advantage | +0.875 |
Neg logit contributions | |
debates | -0.848 |
adoption | -0.826 |
birth | -0.818 |
Pg | -0.810 |
rons | -0.805 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
holiest | +2.369 |
saf | +2.097 |
cific | +2.053 |
Trivia | +2.035 |
Advantage | +2.015 |
Neg logit contributions | |
debates | -2.691 |
birth | -2.628 |
adoption | -2.624 |
Pg | -2.613 |
rons | -2.582 |
Token | on |
Token ID | 319 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
holiest | +2.963 |
saf | +2.693 |
cific | +2.651 |
Trivia | +2.634 |
Advantage | +2.607 |
Neg logit contributions | |
debates | -2.188 |
adoption | -2.127 |
birth | -2.122 |
Pg | -2.116 |
rons | -2.087 |
Token | Monday |
Token ID | 3321 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
debates | +0.685 |
adoption | +0.678 |
birth | +0.658 |
amounts | +0.648 |
viewing | +0.637 |
Neg logit contributions | |
holiest | -1.034 |
saf | -0.961 |
cific | -0.953 |
Trivia | -0.942 |
INGTON | -0.925 |
Token | . |
Token ID | 13 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
holiest | +10.120 |
saf | +9.029 |
Trivia | +8.912 |
Advantage | +8.832 |
cific | +8.736 |
Neg logit contributions | |
Pg | -9.707 |
debates | -9.551 |
tumblr | -9.459 |
birth | -9.447 |
xon | -9.408 |
Token | Liberal |
Token ID | 12266 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
holiest | +0.772 |
saf | +0.705 |
cific | +0.698 |
Trivia | +0.689 |
Advantage | +0.678 |
Neg logit contributions | |
debates | -0.455 |
adoption | -0.443 |
birth | -0.441 |
Pg | -0.434 |
rons | -0.429 |
Token | MP |
Token ID | 4904 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
debates | +0.105 |
adoption | +0.101 |
birth | +0.098 |
amounts | +0.098 |
rons | +0.097 |
Neg logit contributions | |
holiest | -0.146 |
saf | -0.135 |
cific | -0.134 |
Trivia | -0.131 |
Advantage | -0.128 |
Token | P |
Token ID | 47 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
debates | +2.632 |
adoption | +2.524 |
rons | +2.433 |
Pg | +2.431 |
birth | +2.422 |
Neg logit contributions | |
holiest | -4.370 |
saf | -4.008 |
cific | -3.907 |
Trivia | -3.860 |
INGTON | -3.852 |
Token | Y |
Token ID | 575 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
holiest | +0.142 |
saf | +0.130 |
cific | +0.129 |
Trivia | +0.127 |
Advantage | +0.125 |
Neg logit contributions | |
debates | -0.092 |
adoption | -0.088 |
birth | -0.087 |
Pg | -0.085 |
amounts | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
holiest | +5.091 |
saf | +4.619 |
cific | +4.570 |
Trivia | +4.499 |
Advantage | +4.495 |
Neg logit contributions | |
debates | -4.182 |
Pg | -4.158 |
birth | -4.140 |
adoption | -4.090 |
rons | -4.045 |
Token | in |
Token ID | 287 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
holiest | +0.872 |
saf | +0.800 |
cific | +0.787 |
Trivia | +0.785 |
Advantage | +0.773 |
Neg logit contributions | |
debates | -0.477 |
adoption | -0.460 |
birth | -0.454 |
rons | -0.443 |
amounts | -0.443 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
holiest | +2.898 |
saf | +2.628 |
cific | +2.603 |
Trivia | +2.562 |
Advantage | +2.551 |
Neg logit contributions | |
debates | -2.099 |
adoption | -2.047 |
birth | -2.046 |
Pg | -2.035 |
rons | -2.011 |
Token | statement |
Token ID | 2643 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
holiest | +1.333 |
saf | +1.215 |
cific | +1.197 |
Trivia | +1.186 |
Advantage | +1.174 |
Neg logit contributions | |
debates | -0.919 |
adoption | -0.892 |
birth | -0.887 |
Pg | -0.878 |
rons | -0.870 |
Token | on |
Token ID | 319 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
holiest | +2.656 |
saf | +2.407 |
cific | +2.371 |
Trivia | +2.338 |
Advantage | +2.320 |
Neg logit contributions | |
debates | -2.080 |
adoption | -2.024 |
birth | -2.021 |
Pg | -2.010 |
rons | -1.983 |
Token | Monday |
Token ID | 3321 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
holiest | +0.464 |
saf | +0.425 |
cific | +0.418 |
Trivia | +0.416 |
Advantage | +0.407 |
Neg logit contributions | |
debates | -0.320 |
adoption | -0.311 |
birth | -0.306 |
Pg | -0.301 |
rons | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
holiest | +9.179 |
saf | +8.153 |
cific | +8.046 |
Advantage | +7.979 |
Trivia | +7.738 |
Neg logit contributions | |
tumblr | -10.472 |
Pg | -10.419 |
debates | -10.207 |
birth | -10.201 |
rons | -10.133 |
Token |
|
Token ID | 198 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
debates | +0.135 |
adoption | +0.131 |
birth | +0.130 |
Pg | +0.129 |
rons | +0.128 |
Neg logit contributions | |
holiest | -0.183 |
saf | -0.166 |
cific | -0.163 |
Trivia | -0.162 |
Advantage | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
debates | +0.243 |
birth | +0.237 |
adoption | +0.236 |
Pg | +0.235 |
rons | +0.230 |
Neg logit contributions | |
holiest | -0.338 |
saf | -0.304 |
cific | -0.302 |
Trivia | -0.296 |
Advantage | -0.294 |
Token | But |
Token ID | 1537 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
Pg | +1.282 |
birth | +1.265 |
debates | +1.252 |
adoption | +1.217 |
tumblr | +1.206 |
Neg logit contributions | |
holiest | -1.832 |
cific | -1.634 |
saf | -1.610 |
Advantage | -1.600 |
INGTON | -1.538 |
Token | given |
Token ID | 1813 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
holiest | +3.148 |
saf | +2.889 |
cific | +2.861 |
Trivia | +2.830 |
Advantage | +2.819 |
Neg logit contributions | |
debates | -1.630 |
birth | -1.581 |
adoption | -1.579 |
Pg | -1.570 |
rons | -1.543 |
Token | okane |
Token ID | 41776 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
holiest | +4.582 |
saf | +4.357 |
cific | +4.337 |
Trivia | +3.973 |
INGTON | +3.756 |
Neg logit contributions | |
debates | -10.230 |
Lauder | -10.061 |
cort | -10.050 |
adoption | -10.024 |
bathing | -10.017 |
Token | police |
Token ID | 1644 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
holiest | +9.181 |
saf | +8.410 |
INGTON | +8.370 |
Advantage | +8.357 |
Trivia | +8.311 |
Neg logit contributions | |
debates | -7.045 |
birth | -7.041 |
tumblr | -7.025 |
rons | -7.013 |
Pg | -6.966 |
Token | arrested |
Token ID | 5169 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
holiest | +1.229 |
saf | +1.113 |
cific | +1.106 |
Trivia | +1.092 |
Advantage | +1.071 |
Neg logit contributions | |
debates | -0.880 |
adoption | -0.857 |
birth | -0.841 |
rons | -0.836 |
amounts | -0.828 |
Token | one |
Token ID | 530 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
holiest | +3.776 |
saf | +3.429 |
cific | +3.376 |
Trivia | +3.335 |
Advantage | +3.324 |
Neg logit contributions | |
debates | -2.795 |
birth | -2.719 |
adoption | -2.713 |
Pg | -2.704 |
rons | -2.660 |
Token | suspect |
Token ID | 4099 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
holiest | +7.385 |
saf | +6.552 |
cific | +6.520 |
Advantage | +6.514 |
Trivia | +6.402 |
Neg logit contributions | |
debates | -6.498 |
Pg | -6.336 |
birth | -6.256 |
rons | -6.183 |
adoption | -6.131 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
holiest | +4.183 |
saf | +3.796 |
cific | +3.750 |
Trivia | +3.711 |
Advantage | +3.683 |
Neg logit contributions | |
debates | -2.871 |
birth | -2.795 |
adoption | -2.781 |
Pg | -2.768 |
rons | -2.722 |
Token | night |
Token ID | 1755 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
holiest | +10.041 |
saf | +8.922 |
cific | +8.858 |
Advantage | +8.774 |
Trivia | +8.553 |
Neg logit contributions | |
Pg | -9.774 |
birth | -9.721 |
tumblr | -9.557 |
debates | -9.473 |
xon | -9.412 |
Token | and |
Token ID | 290 |
Feature activation | +6.79e+00 |
Pos logit contributions | |
holiest | +8.238 |
saf | +7.447 |
cific | +7.441 |
Advantage | +7.243 |
Trivia | +7.233 |
Neg logit contributions | |
birth | -6.727 |
Pg | -6.716 |
debates | -6.712 |
adoption | -6.578 |
tumblr | -6.520 |
Token | charged |
Token ID | 5047 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
holiest | +5.810 |
saf | +5.372 |
cific | +5.200 |
Advantage | +5.194 |
Trivia | +5.145 |
Neg logit contributions | |
debates | -3.765 |
Pg | -3.718 |
birth | -3.702 |
adoption | -3.630 |
rons | -3.549 |
Token | him |
Token ID | 683 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
holiest | +1.934 |
saf | +1.759 |
cific | +1.735 |
Trivia | +1.720 |
Advantage | +1.696 |
Neg logit contributions | |
debates | -1.358 |
adoption | -1.321 |
birth | -1.307 |
Pg | -1.291 |
rons | -1.287 |
Token | with |
Token ID | 351 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
holiest | +1.601 |
saf | +1.465 |
cific | +1.445 |
Trivia | +1.429 |
Advantage | +1.415 |
Neg logit contributions | |
debates | -0.999 |
adoption | -0.970 |
birth | -0.961 |
Pg | -0.947 |
rons | -0.945 |
Token | to |
Token ID | 284 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
birth | +5.114 |
viewing | +5.070 |
adoption | +5.062 |
crying | +4.969 |
debates | +4.929 |
Neg logit contributions | |
holiest | -10.476 |
cific | -9.717 |
saf | -9.562 |
Advantage | -9.466 |
INGTON | -9.415 |
Token | supposedly |
Token ID | 13519 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
holiest | +1.642 |
saf | +1.494 |
cific | +1.479 |
Trivia | +1.458 |
Advantage | +1.446 |
Neg logit contributions | |
debates | -1.161 |
adoption | -1.127 |
birth | -1.119 |
Pg | -1.100 |
amounts | -1.092 |
Token | kill |
Token ID | 1494 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
holiest | +3.753 |
saf | +3.424 |
cific | +3.361 |
Trivia | +3.330 |
Advantage | +3.301 |
Neg logit contributions | |
debates | -2.595 |
adoption | -2.520 |
birth | -2.509 |
Pg | -2.499 |
rons | -2.472 |
Token | actor |
Token ID | 8674 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
holiest | +2.674 |
saf | +2.455 |
cific | +2.420 |
Trivia | +2.398 |
Advantage | +2.379 |
Neg logit contributions | |
debates | -1.512 |
adoption | -1.463 |
birth | -1.457 |
Pg | -1.441 |
rons | -1.424 |
Token | Neil |
Token ID | 15929 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
holiest | +0.910 |
saf | +0.830 |
cific | +0.822 |
Trivia | +0.808 |
Advantage | +0.799 |
Neg logit contributions | |
debates | -0.588 |
adoption | -0.569 |
birth | -0.566 |
Pg | -0.558 |
rons | -0.555 |
Token | Patrick |
Token ID | 9925 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
debates | +2.790 |
birth | +2.747 |
rons | +2.741 |
Weiner | +2.707 |
croft | +2.663 |
Neg logit contributions | |
holiest | -4.726 |
cific | -4.384 |
saf | -4.372 |
Trivia | -4.267 |
INGTON | -4.256 |
Token | Harris |
Token ID | 10026 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
Weiner | +5.728 |
Bradley | +5.629 |
reading | +5.614 |
rons | +5.495 |
debates | +5.464 |
Neg logit contributions | |
holiest | -17.868 |
cific | -16.616 |
saf | -16.049 |
rown | -15.742 |
INGTON | -15.610 |
Token | , |
Token ID | 11 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
debates | +3.177 |
birth | +3.073 |
amounts | +3.053 |
adoption | +3.012 |
viewing | +2.989 |
Neg logit contributions | |
holiest | -5.630 |
saf | -5.119 |
cific | -5.105 |
Advantage | -5.029 |
Trivia | -4.883 |
Token | who |
Token ID | 508 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
debates | +1.272 |
adoption | +1.234 |
birth | +1.210 |
amounts | +1.200 |
viewing | +1.194 |
Neg logit contributions | |
holiest | -2.322 |
saf | -2.142 |
cific | -2.136 |
Trivia | -2.091 |
Advantage | -2.077 |
Token | is |
Token ID | 318 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
holiest | +1.018 |
saf | +0.928 |
cific | +0.925 |
Trivia | +0.906 |
Advantage | +0.903 |
Neg logit contributions | |
debates | -0.641 |
adoption | -0.614 |
birth | -0.609 |
amounts | -0.602 |
Pg | -0.601 |
Token | never |
Token ID | 1239 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
holiest | +0.457 |
saf | +0.419 |
cific | +0.419 |
Trivia | +0.409 |
Advantage | +0.408 |
Neg logit contributions | |
debates | -0.273 |
adoption | -0.264 |
birth | -0.263 |
Pg | -0.259 |
amounts | -0.256 |
Token | country |
Token ID | 1499 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
debates | +0.367 |
adoption | +0.352 |
birth | +0.349 |
amounts | +0.337 |
Pg | +0.336 |
Neg logit contributions | |
holiest | -0.840 |
saf | -0.783 |
cific | -0.782 |
Trivia | -0.773 |
Advantage | -0.756 |
Token | , |
Token ID | 11 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
debates | +1.071 |
birth | +1.036 |
adoption | +1.027 |
amounts | +1.005 |
rons | +1.001 |
Neg logit contributions | |
holiest | -1.677 |
saf | -1.538 |
cific | -1.526 |
Trivia | -1.502 |
Advantage | -1.486 |
Token | have |
Token ID | 423 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
debates | +0.431 |
adoption | +0.418 |
birth | +0.413 |
amounts | +0.404 |
viewing | +0.401 |
Neg logit contributions | |
holiest | -0.673 |
saf | -0.618 |
cific | -0.613 |
Trivia | -0.610 |
Advantage | -0.597 |
Token | to |
Token ID | 284 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
debates | +0.062 |
adoption | +0.060 |
birth | +0.059 |
rons | +0.058 |
Pg | +0.058 |
Neg logit contributions | |
holiest | -0.092 |
saf | -0.084 |
cific | -0.084 |
Trivia | -0.083 |
Advantage | -0.081 |
Token | accept |
Token ID | 2453 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
debates | +2.114 |
adoption | +2.035 |
birth | +1.989 |
clam | +1.976 |
amounts | +1.957 |
Neg logit contributions | |
holiest | -3.928 |
cific | -3.675 |
Trivia | -3.640 |
saf | -3.569 |
Advantage | -3.551 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.70e+01 |
Pos logit contributions | |
debates | +2.501 |
adoption | +2.454 |
birth | +2.337 |
amounts | +2.310 |
viewing | +2.273 |
Neg logit contributions | |
holiest | -4.093 |
cific | -3.875 |
saf | -3.836 |
Trivia | -3.784 |
INGTON | -3.650 |
Token | immigration |
Token ID | 6272 |
Feature activation | -9.35e+00 |
Pos logit contributions | |
adoption | +8.705 |
amounts | +8.353 |
debates | +7.966 |
birth | +7.903 |
viewing | +7.620 |
Neg logit contributions | |
holiest | -14.431 |
cific | -13.631 |
saf | -13.237 |
Trivia | -13.204 |
cture | -12.553 |
Token | from |
Token ID | 422 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
debates | +4.621 |
amounts | +4.424 |
adoption | +4.378 |
viewing | +4.177 |
birth | +4.126 |
Neg logit contributions | |
holiest | -8.549 |
saf | -8.046 |
cific | -8.007 |
Trivia | -7.760 |
cture | -7.580 |
Token | Africa |
Token ID | 5478 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
debates | +0.489 |
adoption | +0.476 |
birth | +0.470 |
amounts | +0.461 |
Pg | +0.457 |
Neg logit contributions | |
holiest | -0.717 |
saf | -0.656 |
cific | -0.650 |
Trivia | -0.642 |
Advantage | -0.630 |
Token | , |
Token ID | 11 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
holiest | +2.476 |
saf | +2.260 |
cific | +2.224 |
Trivia | +2.203 |
Advantage | +2.185 |
Neg logit contributions | |
debates | -1.647 |
adoption | -1.598 |
birth | -1.591 |
Pg | -1.576 |
rons | -1.561 |
Token | the |
Token ID | 262 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
debates | +1.671 |
adoption | +1.641 |
birth | +1.614 |
amounts | +1.572 |
viewing | +1.553 |
Neg logit contributions | |
holiest | -2.488 |
saf | -2.277 |
Trivia | -2.273 |
cific | -2.268 |
Advantage | -2.202 |
Token | dialect |
Token ID | 23637 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
holiest | +0.341 |
saf | +0.312 |
cific | +0.309 |
Trivia | +0.306 |
Advantage | +0.301 |
Neg logit contributions | |
debates | -0.220 |
adoption | -0.214 |
birth | -0.211 |
Pg | -0.209 |
rons | -0.207 |
Token | ic |
Token ID | 291 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
holiest | +0.945 |
saf | +0.841 |
cific | +0.827 |
Trivia | +0.819 |
Advantage | +0.808 |
Neg logit contributions | |
debates | -0.957 |
adoption | -0.933 |
birth | -0.932 |
Pg | -0.922 |
rons | -0.917 |
Token | of |
Token ID | 286 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
holiest | +0.187 |
saf | +0.171 |
cific | +0.169 |
Trivia | +0.167 |
Advantage | +0.165 |
Neg logit contributions | |
debates | -0.122 |
adoption | -0.118 |
birth | -0.117 |
Pg | -0.116 |
rons | -0.115 |
Token | an |
Token ID | 281 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
holiest | +0.831 |
saf | +0.761 |
cific | +0.751 |
Trivia | +0.743 |
Advantage | +0.729 |
Neg logit contributions | |
debates | -0.542 |
adoption | -0.525 |
birth | -0.517 |
Pg | -0.512 |
rons | -0.508 |
Token | extended |
Token ID | 7083 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
debates | +0.569 |
adoption | +0.561 |
birth | +0.545 |
Pg | +0.538 |
rons | +0.536 |
Neg logit contributions | |
holiest | -0.776 |
saf | -0.708 |
cific | -0.695 |
Trivia | -0.691 |
INGTON | -0.676 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
debates | +4.303 |
adoption | +4.205 |
clam | +3.976 |
amounts | +3.945 |
viewing | +3.941 |
Neg logit contributions | |
holiest | -6.613 |
saf | -6.190 |
cific | -6.127 |
Trivia | -6.085 |
INGTON | -5.813 |
Token | revolt |
Token ID | 27360 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
adoption | +8.631 |
debates | +8.336 |
clam | +8.120 |
birth | +8.102 |
discussion | +7.906 |
Neg logit contributions | |
holiest | -13.947 |
Trivia | -12.296 |
saf | -12.261 |
cific | -11.991 |
INGTON | -11.596 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
debates | +2.697 |
adoption | +2.560 |
Pg | +2.530 |
amounts | +2.517 |
rons | +2.510 |
Neg logit contributions | |
holiest | -5.138 |
saf | -4.645 |
Trivia | -4.606 |
cific | -4.597 |
Advantage | -4.554 |
Token | a |
Token ID | 257 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
debates | +0.840 |
adoption | +0.816 |
birth | +0.794 |
Pg | +0.789 |
rons | +0.777 |
Neg logit contributions | |
holiest | -1.297 |
saf | -1.191 |
cific | -1.168 |
Trivia | -1.166 |
Advantage | -1.148 |
Token | defeated |
Token ID | 9772 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
debates | +2.189 |
adoption | +2.130 |
Pg | +2.098 |
birth | +2.082 |
clam | +2.056 |
Neg logit contributions | |
holiest | -3.362 |
saf | -3.102 |
Trivia | -3.048 |
cific | -3.015 |
Advantage | -3.009 |
Token | proletarian |
Token ID | 47393 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
debates | +0.270 |
adoption | +0.263 |
birth | +0.257 |
Pg | +0.257 |
rons | +0.254 |
Neg logit contributions | |
holiest | -0.414 |
saf | -0.380 |
cific | -0.375 |
Trivia | -0.373 |
Advantage | -0.363 |
Token | dominated |
Token ID | 13354 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
holiest | +1.605 |
saf | +1.466 |
cific | +1.448 |
Trivia | +1.434 |
Advantage | +1.415 |
Neg logit contributions | |
debates | -1.061 |
adoption | -1.027 |
birth | -1.017 |
Pg | -1.008 |
rons | -1.000 |
Token | political |
Token ID | 1964 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
holiest | +0.481 |
saf | +0.442 |
cific | +0.436 |
Trivia | +0.432 |
Advantage | +0.426 |
Neg logit contributions | |
debates | -0.300 |
adoption | -0.289 |
birth | -0.285 |
Pg | -0.281 |
rons | -0.279 |
Token | institutions |
Token ID | 6712 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
debates | +0.257 |
adoption | +0.241 |
birth | +0.231 |
amounts | +0.229 |
rons | +0.227 |
Neg logit contributions | |
holiest | -0.562 |
cific | -0.520 |
saf | -0.520 |
Trivia | -0.514 |
Advantage | -0.505 |
Token | and |
Token ID | 290 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
debates | +0.203 |
adoption | +0.195 |
birth | +0.192 |
amounts | +0.189 |
rons | +0.188 |
Neg logit contributions | |
holiest | -0.333 |
saf | -0.307 |
cific | -0.305 |
Trivia | -0.303 |
Advantage | -0.298 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
debates | +0.050 |
adoption | +0.047 |
amounts | +0.046 |
birth | +0.046 |
rons | +0.045 |
Neg logit contributions | |
holiest | -0.083 |
saf | -0.077 |
cific | -0.076 |
Trivia | -0.075 |
Advantage | -0.074 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.65e+01 |
Pos logit contributions | |
debates | +1.079 |
adoption | +1.026 |
amounts | +0.983 |
rons | +0.976 |
birth | +0.972 |
Neg logit contributions | |
holiest | -1.932 |
cific | -1.806 |
saf | -1.798 |
Trivia | -1.770 |
Advantage | -1.746 |
Token | media |
Token ID | 2056 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
adoption | +6.236 |
debates | +6.225 |
amounts | +5.869 |
viewing | +5.676 |
discussion | +5.600 |
Neg logit contributions | |
holiest | -15.933 |
cific | -15.041 |
saf | -14.493 |
Advantage | -14.354 |
Trivia | -14.344 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
debates | +4.459 |
adoption | +4.210 |
amounts | +4.082 |
viewing | +4.031 |
clam | +3.961 |
Neg logit contributions | |
holiest | -7.362 |
cific | -6.875 |
saf | -6.863 |
Trivia | -6.735 |
INGTON | -6.726 |
Token | leading |
Token ID | 3756 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
debates | +1.118 |
adoption | +1.072 |
birth | +1.038 |
amounts | +1.037 |
viewing | +1.032 |
Neg logit contributions | |
holiest | -1.812 |
saf | -1.673 |
cific | -1.667 |
Trivia | -1.652 |
Advantage | -1.614 |
Token | to |
Token ID | 284 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
debates | +1.118 |
adoption | +1.054 |
Pg | +1.019 |
amounts | +1.019 |
birth | +1.016 |
Neg logit contributions | |
holiest | -2.329 |
saf | -2.166 |
cific | -2.136 |
Trivia | -2.121 |
Advantage | -2.090 |
Token | a |
Token ID | 257 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
debates | +1.442 |
adoption | +1.364 |
amounts | +1.317 |
birth | +1.306 |
viewing | +1.298 |
Neg logit contributions | |
holiest | -2.261 |
saf | -2.091 |
cific | -2.066 |
Trivia | -2.050 |
Advantage | -2.018 |
Token | United |
Token ID | 1578 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
debates | +0.008 |
adoption | +0.008 |
birth | +0.008 |
Pg | +0.008 |
amounts | +0.008 |
Neg logit contributions | |
holiest | -0.013 |
saf | -0.012 |
cific | -0.012 |
Trivia | -0.011 |
Advantage | -0.011 |
Token | Nations |
Token ID | 7973 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
debates | +1.687 |
adoption | +1.651 |
birth | +1.646 |
rons | +1.628 |
Pg | +1.627 |
Neg logit contributions | |
holiest | -1.088 |
saf | -0.949 |
cific | -0.928 |
Trivia | -0.912 |
Advantage | -0.897 |
Token | , |
Token ID | 11 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
debates | +3.776 |
adoption | +3.549 |
amounts | +3.427 |
birth | +3.403 |
viewing | +3.385 |
Neg logit contributions | |
holiest | -7.870 |
cific | -7.280 |
Advantage | -7.253 |
saf | -7.203 |
INGTON | -7.009 |
Token | Susan |
Token ID | 14919 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
debates | +2.404 |
adoption | +2.341 |
birth | +2.297 |
amounts | +2.241 |
Pg | +2.198 |
Neg logit contributions | |
holiest | -4.037 |
saf | -3.710 |
Trivia | -3.630 |
cific | -3.629 |
Advantage | -3.607 |
Token | E |
Token ID | 412 |
Feature activation | -9.59e+00 |
Pos logit contributions | |
debates | +2.634 |
birth | +2.526 |
Lauder | +2.486 |
adoption | +2.467 |
Weiner | +2.456 |
Neg logit contributions | |
holiest | -6.465 |
saf | -6.118 |
Trivia | -5.995 |
INGTON | -5.962 |
cific | -5.957 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e+01 |
Pos logit contributions | |
debates | +4.415 |
birth | +4.301 |
adoption | +4.128 |
amounts | +4.050 |
bell | +4.042 |
Neg logit contributions | |
holiest | -9.175 |
saf | -8.248 |
INGTON | -8.193 |
Advantage | -8.163 |
Trivia | -8.021 |
Token | Rice |
Token ID | 13823 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
Lauder | +4.522 |
Bradley | +4.085 |
Weiner | +4.045 |
birth | +3.887 |
Flynn | +3.808 |
Neg logit contributions | |
holiest | -18.153 |
saf | -17.129 |
INGTON | -16.382 |
Trivia | -16.293 |
cific | -16.023 |
Token | , |
Token ID | 11 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
debates | +3.361 |
birth | +3.205 |
adoption | +3.167 |
amounts | +3.093 |
rons | +3.091 |
Neg logit contributions | |
holiest | -6.813 |
saf | -6.134 |
cific | -6.089 |
Advantage | -6.087 |
Trivia | -6.013 |
Token | said |
Token ID | 531 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
debates | +2.221 |
adoption | +2.124 |
birth | +2.113 |
viewing | +2.081 |
amounts | +2.066 |
Neg logit contributions | |
holiest | -3.403 |
cific | -3.072 |
saf | -3.065 |
Advantage | -3.047 |
Trivia | -3.025 |
Token | Friday |
Token ID | 3217 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
holiest | +0.648 |
saf | +0.593 |
cific | +0.585 |
Trivia | +0.581 |
Advantage | +0.575 |
Neg logit contributions | |
debates | -0.411 |
adoption | -0.397 |
birth | -0.394 |
Pg | -0.388 |
rons | -0.386 |
Token | that |
Token ID | 326 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
holiest | +8.678 |
saf | +7.745 |
cific | +7.578 |
Advantage | +7.382 |
Trivia | +7.375 |
Neg logit contributions | |
Pg | -7.568 |
tumblr | -7.513 |
birth | -7.492 |
debates | -7.320 |
xon | -7.315 |
Token | her |
Token ID | 607 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
debates | +0.388 |
adoption | +0.376 |
birth | +0.364 |
amounts | +0.362 |
Pg | +0.357 |
Neg logit contributions | |
holiest | -0.596 |
saf | -0.545 |
cific | -0.538 |
Trivia | -0.533 |
Advantage | -0.519 |
Token | rival |
Token ID | 8976 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
debates | +0.904 |
adoption | +0.879 |
birth | +0.857 |
amounts | +0.847 |
rons | +0.840 |
Neg logit contributions | |
holiest | -1.075 |
saf | -0.983 |
cific | -0.975 |
Trivia | -0.957 |
INGTON | -0.932 |
Token | Sen |
Token ID | 2311 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
debates | +1.462 |
adoption | +1.398 |
amounts | +1.349 |
birth | +1.339 |
rons | +1.333 |
Neg logit contributions | |
holiest | -2.558 |
saf | -2.359 |
cific | -2.334 |
Trivia | -2.301 |
INGTON | -2.240 |
Token | . |
Token ID | 13 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
debates | +1.206 |
birth | +1.166 |
adoption | +1.161 |
Pg | +1.145 |
rons | +1.132 |
Neg logit contributions | |
holiest | -1.745 |
saf | -1.570 |
Trivia | -1.536 |
cific | -1.526 |
INGTON | -1.522 |
Token | Barbara |
Token ID | 16685 |
Feature activation | -8.94e+00 |
Pos logit contributions | |
debates | +3.092 |
adoption | +2.941 |
amounts | +2.891 |
Bradley | +2.799 |
bell | +2.793 |
Neg logit contributions | |
holiest | -6.751 |
saf | -6.313 |
cific | -6.184 |
INGTON | -6.030 |
Trivia | -5.992 |
Token | Box |
Token ID | 8315 |
Feature activation | -1.64e+01 |
Pos logit contributions | |
Bradley | +2.263 |
debates | +2.166 |
Weiner | +2.135 |
birth | +2.048 |
viewing | +2.019 |
Neg logit contributions | |
holiest | -10.874 |
saf | -9.856 |
cific | -9.621 |
Trivia | -9.571 |
INGTON | -9.457 |
Token | er |
Token ID | 263 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
birth | +4.992 |
debates | +4.760 |
xon | +4.683 |
amounts | +4.591 |
croft | +4.422 |
Neg logit contributions | |
holiest | -17.383 |
cific | -16.043 |
saf | -15.916 |
Trivia | -15.794 |
alties | -15.344 |
Token | , |
Token ID | 11 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
debates | +3.020 |
amounts | +2.800 |
adoption | +2.797 |
birth | +2.748 |
rons | +2.738 |
Neg logit contributions | |
holiest | -5.845 |
saf | -5.386 |
cific | -5.297 |
Trivia | -5.236 |
INGTON | -5.065 |
Token | D |
Token ID | 360 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
debates | +2.409 |
adoption | +2.309 |
amounts | +2.244 |
birth | +2.223 |
rons | +2.222 |
Neg logit contributions | |
holiest | -4.516 |
saf | -4.198 |
cific | -4.145 |
Trivia | -4.079 |
INGTON | -3.959 |
Token | - |
Token ID | 12 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
debates | +1.221 |
adoption | +1.180 |
birth | +1.178 |
Pg | +1.164 |
rons | +1.150 |
Neg logit contributions | |
holiest | -1.607 |
saf | -1.443 |
cific | -1.428 |
Trivia | -1.405 |
Advantage | -1.391 |
Token | California |
Token ID | 25284 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
debates | +1.443 |
birth | +1.430 |
Pg | +1.412 |
adoption | +1.385 |
rons | +1.370 |
Neg logit contributions | |
holiest | -2.342 |
cific | -2.124 |
saf | -2.123 |
Advantage | -2.052 |
Trivia | -2.045 |
Token | crisis |
Token ID | 4902 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
debates | +1.941 |
adoption | +1.798 |
amounts | +1.724 |
clam | +1.684 |
birth | +1.675 |
Neg logit contributions | |
holiest | -3.222 |
saf | -2.995 |
cific | -2.994 |
Trivia | -2.993 |
Advantage | -2.873 |
Token | of |
Token ID | 286 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
debates | +1.936 |
adoption | +1.814 |
viewing | +1.758 |
amounts | +1.757 |
birth | +1.755 |
Neg logit contributions | |
holiest | -2.954 |
saf | -2.713 |
Trivia | -2.679 |
cific | -2.666 |
Advantage | -2.621 |
Token | capitalism |
Token ID | 12129 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
holiest | +1.587 |
saf | +1.453 |
cific | +1.433 |
Trivia | +1.430 |
Advantage | +1.393 |
Neg logit contributions | |
debates | -1.030 |
adoption | -0.994 |
birth | -0.974 |
Pg | -0.959 |
amounts | -0.956 |
Token | , |
Token ID | 11 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
holiest | +0.547 |
saf | +0.500 |
cific | +0.493 |
Trivia | +0.488 |
Advantage | +0.480 |
Neg logit contributions | |
debates | -0.383 |
adoption | -0.370 |
birth | -0.366 |
Pg | -0.360 |
amounts | -0.359 |
Token | with |
Token ID | 351 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
debates | +2.116 |
adoption | +2.015 |
viewing | +1.941 |
amounts | +1.931 |
birth | +1.931 |
Neg logit contributions | |
holiest | -3.209 |
saf | -2.944 |
Trivia | -2.907 |
cific | -2.875 |
INGTON | -2.823 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
holiest | +0.895 |
saf | +0.823 |
cific | +0.812 |
Trivia | +0.807 |
Advantage | +0.791 |
Neg logit contributions | |
debates | -0.540 |
adoption | -0.521 |
birth | -0.509 |
Pg | -0.505 |
amounts | -0.502 |
Token | unemployment |
Token ID | 10681 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
adoption | +8.592 |
debates | +8.527 |
amounts | +8.082 |
clam | +7.600 |
viewing | +7.559 |
Neg logit contributions | |
holiest | -13.087 |
cific | -11.745 |
Trivia | -11.670 |
saf | -11.545 |
cture | -11.005 |
Token | at |
Token ID | 379 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
debates | +1.076 |
adoption | +1.017 |
amounts | +1.011 |
birth | +0.994 |
viewing | +0.990 |
Neg logit contributions | |
holiest | -1.750 |
saf | -1.621 |
cific | -1.615 |
Trivia | -1.579 |
Advantage | -1.560 |
Token | home |
Token ID | 1363 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
debates | +1.500 |
adoption | +1.457 |
amounts | +1.436 |
birth | +1.422 |
viewing | +1.368 |
Neg logit contributions | |
holiest | -2.278 |
cific | -2.117 |
saf | -2.113 |
Trivia | -2.090 |
INGTON | -2.071 |
Token | and |
Token ID | 290 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
debates | +0.811 |
adoption | +0.776 |
birth | +0.766 |
amounts | +0.765 |
Pg | +0.758 |
Neg logit contributions | |
holiest | -1.325 |
saf | -1.227 |
cific | -1.221 |
Trivia | -1.196 |
Advantage | -1.180 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
debates | +1.315 |
adoption | +1.269 |
amounts | +1.214 |
birth | +1.211 |
Pg | +1.196 |
Neg logit contributions | |
holiest | -2.130 |
saf | -1.976 |
cific | -1.924 |
Trivia | -1.924 |
INGTON | -1.875 |
Token | Car |
Token ID | 9914 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
holiest | +6.094 |
saf | +5.525 |
Trivia | +5.510 |
cific | +5.345 |
Advantage | +5.290 |
Neg logit contributions | |
debates | -6.171 |
adoption | -5.907 |
rons | -5.811 |
amounts | -5.805 |
birth | -5.791 |
Token | lo |
Token ID | 5439 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
debates | +0.089 |
adoption | +0.087 |
birth | +0.086 |
rons | +0.085 |
croft | +0.084 |
Neg logit contributions | |
holiest | -0.122 |
saf | -0.111 |
cific | -0.110 |
Trivia | -0.109 |
Advantage | -0.107 |
Token | Alleg |
Token ID | 26326 |
Feature activation | -8.01e+00 |
Pos logit contributions | |
holiest | +2.780 |
saf | +2.457 |
cific | +2.408 |
Trivia | +2.378 |
Advantage | +2.348 |
Neg logit contributions | |
debates | -3.388 |
adoption | -3.314 |
birth | -3.305 |
Pg | -3.285 |
rons | -3.254 |
Token | ri |
Token ID | 380 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
rons | +2.560 |
debates | +2.274 |
croft | +2.184 |
adoption | +2.143 |
birth | +2.103 |
Neg logit contributions | |
holiest | -9.090 |
cific | -8.475 |
Trivia | -8.311 |
INGTON | -8.288 |
Advantage | -8.249 |
Token | ) |
Token ID | 8 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
debates | +0.382 |
adoption | +0.371 |
birth | +0.369 |
Pg | +0.363 |
amounts | +0.363 |
Neg logit contributions | |
holiest | -0.490 |
saf | -0.443 |
cific | -0.441 |
Trivia | -0.431 |
INGTON | -0.422 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
holiest | +0.076 |
saf | +0.070 |
cific | +0.069 |
Trivia | +0.067 |
Advantage | +0.066 |
Neg logit contributions | |
debates | -0.057 |
adoption | -0.056 |
birth | -0.055 |
Pg | -0.054 |
amounts | -0.054 |
Token | Flynn |
Token ID | 14654 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
debates | +7.136 |
Weiner | +6.871 |
Bradley | +6.718 |
Flynn | +6.712 |
birth | +6.621 |
Neg logit contributions | |
holiest | -13.384 |
saf | -13.086 |
cific | -12.972 |
Trivia | -11.802 |
INGTON | -11.794 |
Token | The |
Token ID | 383 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
debates | +1.847 |
adoption | +1.792 |
birth | +1.731 |
amounts | +1.726 |
rons | +1.710 |
Neg logit contributions | |
holiest | -2.665 |
cific | -2.459 |
saf | -2.436 |
Trivia | -2.376 |
Advantage | -2.305 |
Token | 57 |
Token ID | 7632 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
holiest | +1.399 |
saf | +1.276 |
cific | +1.257 |
Trivia | +1.245 |
Advantage | +1.234 |
Neg logit contributions | |
debates | -0.925 |
adoption | -0.897 |
birth | -0.895 |
Pg | -0.886 |
rons | -0.876 |
Token | - |
Token ID | 12 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
debates | +0.598 |
adoption | +0.582 |
birth | +0.580 |
Pg | +0.574 |
rons | +0.570 |
Neg logit contributions | |
holiest | -0.714 |
saf | -0.645 |
cific | -0.636 |
Trivia | -0.628 |
Advantage | -0.621 |
Token | year |
Token ID | 1941 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
debates | +0.397 |
adoption | +0.385 |
birth | +0.385 |
Pg | +0.380 |
rons | +0.376 |
Neg logit contributions | |
holiest | -0.612 |
saf | -0.557 |
cific | -0.550 |
Trivia | -0.545 |
Advantage | -0.540 |
Token | years |
Token ID | 812 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
holiest | +5.106 |
saf | +4.645 |
cific | +4.608 |
Trivia | +4.562 |
Advantage | +4.533 |
Neg logit contributions | |
debates | -2.579 |
birth | -2.568 |
Pg | -2.543 |
adoption | -2.524 |
rons | -2.496 |
Token | ago |
Token ID | 2084 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
holiest | +2.048 |
saf | +1.856 |
cific | +1.825 |
Trivia | +1.803 |
Advantage | +1.785 |
Neg logit contributions | |
debates | -1.647 |
adoption | -1.597 |
birth | -1.591 |
Pg | -1.576 |
rons | -1.562 |
Token | Rolling |
Token ID | 21567 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
holiest | +2.071 |
saf | +1.896 |
cific | +1.867 |
Trivia | +1.849 |
Advantage | +1.835 |
Neg logit contributions | |
debates | -1.313 |
adoption | -1.280 |
birth | -1.280 |
Pg | -1.270 |
rons | -1.260 |
Token | Stone |
Token ID | 8026 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
debates | +0.839 |
adoption | +0.802 |
Pg | +0.798 |
birth | +0.797 |
amounts | +0.785 |
Neg logit contributions | |
holiest | -1.668 |
saf | -1.536 |
cific | -1.525 |
Trivia | -1.470 |
Advantage | -1.446 |
Token | reporter |
Token ID | 9095 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
holiest | +0.950 |
saf | +0.861 |
cific | +0.857 |
Trivia | +0.840 |
Advantage | +0.834 |
Neg logit contributions | |
debates | -0.664 |
adoption | -0.640 |
birth | -0.628 |
Pg | -0.625 |
amounts | -0.619 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
holiest | +0.095 |
saf | +0.087 |
cific | +0.086 |
Trivia | +0.085 |
INGTON | +0.083 |
Neg logit contributions | |
debates | -0.060 |
adoption | -0.058 |
birth | -0.058 |
amounts | -0.056 |
Pg | -0.056 |
Token | Hastings |
Token ID | 38330 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Weiner | +7.253 |
Kimmel | +6.937 |
Bradley | +6.899 |
Berk | +6.659 |
birth | +6.449 |
Neg logit contributions | |
holiest | -13.483 |
cific | -13.208 |
saf | -13.145 |
Trivia | -12.300 |
INGTON | -12.117 |
Token | writing |
Token ID | 3597 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
debates | +0.642 |
adoption | +0.608 |
birth | +0.603 |
amounts | +0.596 |
clam | +0.594 |
Neg logit contributions | |
holiest | -0.942 |
cific | -0.856 |
saf | -0.847 |
Advantage | -0.830 |
Trivia | -0.827 |
Token | in |
Token ID | 287 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
holiest | +4.245 |
saf | +3.878 |
cific | +3.833 |
Trivia | +3.783 |
Advantage | +3.773 |
Neg logit contributions | |
debates | -2.633 |
adoption | -2.557 |
birth | -2.555 |
Pg | -2.545 |
rons | -2.504 |
Token | America |
Token ID | 2253 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
debates | +0.615 |
adoption | +0.592 |
birth | +0.585 |
amounts | +0.574 |
Pg | +0.572 |
Neg logit contributions | |
holiest | -0.949 |
saf | -0.868 |
Trivia | -0.852 |
cific | -0.852 |
INGTON | -0.826 |
Token | � |
Token ID | 447 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
holiest | +1.480 |
saf | +1.343 |
cific | +1.326 |
Trivia | +1.306 |
Advantage | +1.286 |
Neg logit contributions | |
debates | -1.081 |
adoption | -1.042 |
birth | -1.036 |
Pg | -1.021 |
rons | -1.019 |
Token | July |
Token ID | 2901 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
holiest | +2.310 |
saf | +2.101 |
cific | +2.069 |
Trivia | +2.048 |
Advantage | +2.028 |
Neg logit contributions | |
debates | -1.663 |
adoption | -1.616 |
birth | -1.610 |
Pg | -1.595 |
rons | -1.579 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
holiest | +2.868 |
saf | +2.610 |
cific | +2.577 |
Trivia | +2.548 |
Advantage | +2.523 |
Neg logit contributions | |
debates | -2.045 |
adoption | -1.982 |
birth | -1.973 |
Pg | -1.951 |
rons | -1.934 |
Token |
|
Token ID | 198 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
debates | +1.149 |
birth | +1.118 |
Pg | +1.097 |
adoption | +1.092 |
rons | +1.079 |
Neg logit contributions | |
holiest | -1.670 |
cific | -1.505 |
saf | -1.501 |
Trivia | -1.476 |
INGTON | -1.438 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
debates | +0.365 |
birth | +0.357 |
adoption | +0.354 |
Pg | +0.353 |
rons | +0.346 |
Neg logit contributions | |
holiest | -0.513 |
saf | -0.461 |
cific | -0.457 |
Trivia | -0.450 |
Advantage | -0.446 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Pg | +1.449 |
birth | +1.447 |
debates | +1.406 |
adoption | +1.358 |
rons | +1.356 |
Neg logit contributions | |
holiest | -2.059 |
cific | -1.857 |
Advantage | -1.834 |
saf | -1.786 |
INGTON | -1.740 |
Token | Continue |
Token ID | 10054 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
debates | +0.876 |
adoption | +0.860 |
birth | +0.855 |
Pg | +0.849 |
rons | +0.834 |
Neg logit contributions | |
holiest | -0.971 |
saf | -0.865 |
cific | -0.855 |
Trivia | -0.844 |
Advantage | -0.825 |
Token | reading |
Token ID | 3555 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
reading | +1.838 |
viewing | +1.290 |
adoption | +0.586 |
debates | +0.548 |
crying | +0.487 |
Neg logit contributions | |
holiest | -19.662 |
saf | -19.092 |
Trivia | -19.030 |
Advantage | -18.785 |
cific | -18.774 |
Token | the |
Token ID | 262 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
debates | +2.492 |
adoption | +2.433 |
Pg | +2.431 |
birth | +2.408 |
amounts | +2.351 |
Neg logit contributions | |
holiest | -5.205 |
saf | -4.763 |
Trivia | -4.705 |
cific | -4.703 |
INGTON | -4.652 |
Token | main |
Token ID | 1388 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
debates | +4.248 |
adoption | +4.189 |
bell | +4.067 |
amounts | +4.062 |
clam | +4.034 |
Neg logit contributions | |
holiest | -5.338 |
saf | -4.972 |
cific | -4.933 |
Trivia | -4.854 |
INGTON | -4.840 |
Token | story |
Token ID | 1621 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
debates | +3.367 |
adoption | +3.311 |
bell | +3.165 |
amounts | +3.161 |
viewing | +3.158 |
Neg logit contributions | |
holiest | -6.188 |
cific | -5.717 |
saf | -5.716 |
Trivia | -5.593 |
Advantage | -5.572 |
Token |
|
Token ID | 198 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
debates | +0.063 |
adoption | +0.062 |
birth | +0.061 |
Pg | +0.061 |
rons | +0.060 |
Neg logit contributions | |
holiest | -0.088 |
saf | -0.079 |
cific | -0.079 |
Trivia | -0.077 |
Advantage | -0.076 |
Token | for |
Token ID | 329 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
debates | +2.543 |
adoption | +2.402 |
amounts | +2.379 |
Pg | +2.354 |
birth | +2.345 |
Neg logit contributions | |
holiest | -5.520 |
saf | -5.219 |
cific | -5.108 |
Trivia | -5.068 |
Advantage | -4.991 |
Token | the |
Token ID | 262 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
debates | +0.565 |
adoption | +0.549 |
birth | +0.533 |
Pg | +0.531 |
amounts | +0.527 |
Neg logit contributions | |
holiest | -0.863 |
saf | -0.796 |
cific | -0.784 |
Trivia | -0.775 |
Advantage | -0.757 |
Token | flight |
Token ID | 5474 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
holiest | +0.167 |
saf | +0.155 |
cific | +0.152 |
Trivia | +0.151 |
Advantage | +0.147 |
Neg logit contributions | |
debates | -0.100 |
adoption | -0.097 |
birth | -0.094 |
Pg | -0.093 |
amounts | -0.093 |
Token | home |
Token ID | 1363 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
debates | +1.031 |
adoption | +0.995 |
birth | +0.974 |
Pg | +0.969 |
rons | +0.967 |
Neg logit contributions | |
holiest | -1.682 |
saf | -1.544 |
cific | -1.533 |
Trivia | -1.510 |
Advantage | -1.498 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
holiest | +0.246 |
saf | +0.227 |
cific | +0.224 |
Trivia | +0.222 |
Advantage | +0.219 |
Neg logit contributions | |
debates | -0.143 |
adoption | -0.137 |
birth | -0.136 |
Pg | -0.135 |
rons | -0.134 |
Token | Expect |
Token ID | 23600 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
debates | +0.926 |
Pg | +0.893 |
adoption | +0.892 |
birth | +0.891 |
rons | +0.876 |
Neg logit contributions | |
holiest | -1.420 |
saf | -1.289 |
cific | -1.271 |
Trivia | -1.245 |
Advantage | -1.214 |
Token | ing |
Token ID | 278 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
debates | +7.156 |
rons | +6.912 |
adoption | +6.780 |
Pg | +6.635 |
reading | +6.567 |
Neg logit contributions | |
holiest | -12.694 |
saf | -12.112 |
cific | -11.821 |
Trivia | -11.705 |
Advantage | -11.293 |
Token | another |
Token ID | 1194 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
debates | +2.304 |
adoption | +2.236 |
Pg | +2.131 |
birth | +2.125 |
amounts | +2.124 |
Neg logit contributions | |
holiest | -4.034 |
saf | -3.772 |
cific | -3.742 |
Trivia | -3.687 |
Advantage | -3.560 |
Token | tired |
Token ID | 10032 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
holiest | +1.736 |
saf | +1.592 |
cific | +1.570 |
Trivia | +1.554 |
Advantage | +1.535 |
Neg logit contributions | |
debates | -1.082 |
adoption | -1.053 |
birth | -1.042 |
Pg | -1.030 |
rons | -1.018 |
Token | clone |
Token ID | 17271 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
debates | +2.200 |
adoption | +2.138 |
birth | +2.084 |
Pg | +2.072 |
clam | +2.058 |
Neg logit contributions | |
holiest | -3.429 |
saf | -3.197 |
cific | -3.139 |
Trivia | -3.075 |
Advantage | -3.003 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
debates | +2.155 |
adoption | +2.101 |
birth | +2.059 |
Pg | +2.043 |
clam | +2.021 |
Neg logit contributions | |
holiest | -3.751 |
saf | -3.517 |
cific | -3.423 |
Trivia | -3.372 |
Advantage | -3.313 |
Token |
|
Token ID | 198 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
debates | +0.587 |
adoption | +0.568 |
birth | +0.565 |
Pg | +0.559 |
amounts | +0.552 |
Neg logit contributions | |
holiest | -0.819 |
saf | -0.742 |
cific | -0.731 |
Trivia | -0.722 |
Advantage | -0.705 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
debates | +0.152 |
birth | +0.148 |
adoption | +0.148 |
Pg | +0.147 |
rons | +0.144 |
Neg logit contributions | |
holiest | -0.208 |
saf | -0.188 |
cific | -0.186 |
Trivia | -0.183 |
Advantage | -0.182 |
Token | F |
Token ID | 37 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
debates | +0.753 |
birth | +0.750 |
Pg | +0.748 |
adoption | +0.735 |
tumblr | +0.716 |
Neg logit contributions | |
holiest | -0.991 |
cific | -0.882 |
saf | -0.874 |
Advantage | -0.862 |
Trivia | -0.835 |
Token | inance |
Token ID | 14149 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
holiest | +5.125 |
saf | +4.603 |
cific | +4.544 |
Trivia | +4.507 |
INGTON | +4.421 |
Neg logit contributions | |
debates | -4.350 |
birth | -4.277 |
Pg | -4.251 |
adoption | -4.244 |
amounts | -4.138 |
Token | Minister |
Token ID | 4139 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
holiest | +2.790 |
saf | +2.502 |
cific | +2.448 |
Trivia | +2.429 |
Advantage | +2.416 |
Neg logit contributions | |
debates | -2.668 |
birth | -2.617 |
adoption | -2.613 |
Pg | -2.597 |
rons | -2.571 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
debates | +1.816 |
amounts | +1.738 |
birth | +1.704 |
adoption | +1.696 |
viewing | +1.657 |
Neg logit contributions | |
holiest | -2.928 |
saf | -2.664 |
cific | -2.658 |
INGTON | -2.593 |
Trivia | -2.591 |
Token | Noon |
Token ID | 41035 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
debates | +5.362 |
Lauder | +5.073 |
Bradley | +5.023 |
Fallon | +4.982 |
Weiner | +4.847 |
Neg logit contributions | |
holiest | -14.921 |
saf | -14.205 |
INGTON | -13.646 |
cific | -13.530 |
Trivia | -13.168 |
Token | an |
Token ID | 272 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
debates | +4.460 |
adoption | +4.354 |
clam | +4.114 |
birth | +4.105 |
rons | +4.075 |
Neg logit contributions | |
holiest | -7.139 |
cific | -6.436 |
saf | -6.395 |
Trivia | -6.151 |
Advantage | -5.989 |
Token | said |
Token ID | 531 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
debates | +1.470 |
adoption | +1.391 |
birth | +1.381 |
amounts | +1.379 |
rons | +1.353 |
Neg logit contributions | |
holiest | -2.196 |
saf | -1.986 |
cific | -1.978 |
Trivia | -1.940 |
Advantage | -1.938 |
Token | on |
Token ID | 319 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
holiest | +1.898 |
saf | +1.734 |
cific | +1.710 |
Trivia | +1.693 |
Advantage | +1.676 |
Neg logit contributions | |
debates | -1.238 |
adoption | -1.200 |
birth | -1.191 |
Pg | -1.177 |
rons | -1.168 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
debates | +2.641 |
adoption | +2.550 |
birth | +2.500 |
amounts | +2.449 |
viewing | +2.447 |
Neg logit contributions | |
holiest | -4.109 |
saf | -3.771 |
cific | -3.768 |
Trivia | -3.749 |
Advantage | -3.637 |
Token | the |
Token ID | 262 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
holiest | +1.559 |
saf | +1.412 |
cific | +1.392 |
Trivia | +1.378 |
Advantage | +1.362 |
Neg logit contributions | |
debates | -1.239 |
adoption | -1.206 |
birth | -1.198 |
Pg | -1.187 |
rons | -1.175 |
Token | induction |
Token ID | 28471 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
debates | +0.441 |
adoption | +0.432 |
birth | +0.418 |
Pg | +0.414 |
amounts | +0.412 |
Neg logit contributions | |
holiest | -0.636 |
saf | -0.590 |
cific | -0.585 |
Trivia | -0.581 |
Advantage | -0.568 |
Token | of |
Token ID | 286 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
debates | +2.796 |
adoption | +2.577 |
viewing | +2.495 |
amounts | +2.458 |
cort | +2.438 |
Neg logit contributions | |
holiest | -5.217 |
saf | -4.885 |
cific | -4.846 |
Trivia | -4.763 |
Advantage | -4.727 |
Token | President |
Token ID | 1992 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
debates | +0.260 |
adoption | +0.254 |
birth | +0.248 |
Pg | +0.246 |
amounts | +0.244 |
Neg logit contributions | |
holiest | -0.372 |
saf | -0.341 |
cific | -0.338 |
Trivia | -0.334 |
Advantage | -0.329 |
Token | William |
Token ID | 3977 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
debates | +2.482 |
adoption | +2.346 |
birth | +2.309 |
Pg | +2.279 |
Lauder | +2.263 |
Neg logit contributions | |
holiest | -5.107 |
saf | -4.690 |
Trivia | -4.655 |
cific | -4.640 |
INGTON | -4.584 |
Token | V |
Token ID | 569 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
debates | +1.831 |
birth | +1.771 |
Lauder | +1.766 |
adoption | +1.760 |
rons | +1.703 |
Neg logit contributions | |
holiest | -3.540 |
saf | -3.244 |
cific | -3.151 |
Trivia | -3.148 |
INGTON | -3.079 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
debates | +8.860 |
rons | +8.846 |
adoption | +8.557 |
Pg | +8.212 |
Lauder | +8.144 |
Neg logit contributions | |
holiest | -10.941 |
saf | -10.187 |
cific | -10.016 |
Trivia | -9.673 |
Advantage | -9.555 |
Token | S |
Token ID | 50 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Lauder | +5.418 |
Weiner | +5.384 |
debates | +5.375 |
birth | +5.270 |
Bradley | +5.243 |
Neg logit contributions | |
holiest | -11.865 |
saf | -11.082 |
Trivia | -10.639 |
cific | -10.618 |
onyms | -10.524 |
Token | . |
Token ID | 13 |
Feature activation | -8.08e+00 |
Pos logit contributions | |
debates | +0.507 |
adoption | +0.493 |
birth | +0.492 |
Pg | +0.485 |
rons | +0.482 |
Neg logit contributions | |
holiest | -0.648 |
saf | -0.588 |
cific | -0.577 |
Trivia | -0.574 |
Advantage | -0.566 |
Token | Tub |
Token ID | 42850 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
debates | +3.779 |
Lauder | +3.634 |
adoption | +3.604 |
birth | +3.553 |
Pg | +3.478 |
Neg logit contributions | |
holiest | -7.772 |
saf | -7.305 |
cific | -7.028 |
Trivia | -6.972 |
INGTON | -6.967 |
Token | man |
Token ID | 805 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
debates | +2.562 |
birth | +2.547 |
adoption | +2.468 |
rons | +2.468 |
croft | +2.462 |
Neg logit contributions | |
holiest | -3.840 |
saf | -3.438 |
cific | -3.386 |
Trivia | -3.343 |
Advantage | -3.325 |
Token | to |
Token ID | 284 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
holiest | +0.276 |
saf | +0.254 |
cific | +0.250 |
Trivia | +0.247 |
Advantage | +0.244 |
Neg logit contributions | |
debates | -0.175 |
adoption | -0.169 |
birth | -0.167 |
Pg | -0.164 |
amounts | -0.164 |
Token | NBC |
Token ID | 9716 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
debates | +1.572 |
adoption | +1.499 |
rons | +1.453 |
birth | +1.452 |
viewing | +1.447 |
Neg logit contributions | |
holiest | -2.704 |
saf | -2.494 |
Trivia | -2.465 |
cific | -2.450 |
INGTON | -2.372 |
Token | � |
Token ID | 447 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
debates | +3.311 |
adoption | +3.094 |
viewing | +3.024 |
amounts | +3.021 |
birth | +2.969 |
Neg logit contributions | |
holiest | -5.803 |
saf | -5.346 |
cific | -5.286 |
Trivia | -5.114 |
Advantage | -4.961 |
Token | � |
Token ID | 247 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
holiest | +1.539 |
saf | +1.407 |
cific | +1.387 |
Trivia | +1.373 |
Advantage | +1.360 |
Neg logit contributions | |
debates | -0.984 |
adoption | -0.953 |
birth | -0.949 |
Pg | -0.939 |
rons | -0.928 |
Token | s |
Token ID | 82 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
holiest | +0.176 |
saf | +0.159 |
cific | +0.157 |
Trivia | +0.156 |
Advantage | +0.154 |
Neg logit contributions | |
debates | -0.125 |
birth | -0.121 |
adoption | -0.121 |
Pg | -0.119 |
rons | -0.119 |
Token | Matt |
Token ID | 4705 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
debates | +0.216 |
adoption | +0.208 |
birth | +0.205 |
Pg | +0.202 |
rons | +0.201 |
Neg logit contributions | |
holiest | -0.331 |
saf | -0.305 |
cific | -0.302 |
Trivia | -0.298 |
Advantage | -0.293 |
Token | L |
Token ID | 406 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Weiner | +5.149 |
debates | +5.021 |
Boyle | +4.892 |
Bradley | +4.830 |
rons | +4.643 |
Neg logit contributions | |
holiest | -14.556 |
cific | -13.941 |
saf | -13.777 |
Trivia | -13.585 |
INGTON | -13.583 |
Token | auer |
Token ID | 16261 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
debates | +0.986 |
birth | +0.948 |
rons | +0.936 |
adoption | +0.933 |
Pg | +0.916 |
Neg logit contributions | |
holiest | -1.925 |
saf | -1.797 |
cific | -1.741 |
Trivia | -1.721 |
Advantage | -1.717 |
Token | that |
Token ID | 326 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
debates | +1.711 |
adoption | +1.616 |
birth | +1.592 |
amounts | +1.585 |
viewing | +1.570 |
Neg logit contributions | |
holiest | -2.746 |
saf | -2.515 |
cific | -2.443 |
Trivia | -2.421 |
Advantage | -2.394 |
Token | he |
Token ID | 339 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
holiest | +1.486 |
saf | +1.362 |
cific | +1.342 |
Trivia | +1.329 |
Advantage | +1.314 |
Neg logit contributions | |
debates | -0.927 |
adoption | -0.896 |
birth | -0.888 |
Pg | -0.878 |
rons | -0.869 |
Token | he |
Token ID | 339 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
holiest | +2.680 |
saf | +2.437 |
cific | +2.400 |
Trivia | +2.375 |
Advantage | +2.352 |
Neg logit contributions | |
debates | -1.942 |
adoption | -1.888 |
birth | -1.880 |
Pg | -1.863 |
rons | -1.844 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
holiest | +3.430 |
saf | +3.129 |
cific | +3.078 |
Advantage | +3.046 |
Trivia | +3.043 |
Neg logit contributions | |
debates | -3.151 |
birth | -3.064 |
Pg | -3.054 |
adoption | -3.050 |
rons | -3.028 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
holiest | +1.417 |
saf | +1.285 |
cific | +1.265 |
Trivia | +1.253 |
Advantage | +1.241 |
Neg logit contributions | |
debates | -1.140 |
adoption | -1.109 |
birth | -1.106 |
Pg | -1.100 |
rons | -1.085 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
holiest | +1.783 |
saf | +1.633 |
cific | +1.594 |
Trivia | +1.588 |
Advantage | +1.567 |
Neg logit contributions | |
debates | -1.513 |
adoption | -1.471 |
birth | -1.454 |
rons | -1.444 |
Pg | -1.442 |
Token | We |
Token ID | 1135 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
debates | +0.851 |
Pg | +0.846 |
birth | +0.839 |
adoption | +0.829 |
rons | +0.821 |
Neg logit contributions | |
holiest | -1.088 |
cific | -0.957 |
saf | -0.945 |
Advantage | -0.943 |
INGTON | -0.910 |
Token | will |
Token ID | 481 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
debates | +1.742 |
rons | +1.685 |
birth | +1.677 |
adoption | +1.662 |
Pg | +1.637 |
Neg logit contributions | |
holiest | -2.415 |
saf | -2.149 |
cific | -2.140 |
Trivia | -2.120 |
Advantage | -2.100 |
Token | continue |
Token ID | 2555 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
debates | +4.194 |
viewing | +3.902 |
adoption | +3.875 |
clam | +3.866 |
rons | +3.862 |
Neg logit contributions | |
holiest | -7.717 |
cific | -7.103 |
Trivia | -6.916 |
Advantage | -6.800 |
saf | -6.738 |
Token | to |
Token ID | 284 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
debates | +6.014 |
viewing | +5.777 |
reading | +5.732 |
adoption | +5.537 |
discussion | +5.427 |
Neg logit contributions | |
holiest | -14.321 |
Trivia | -13.181 |
cific | -13.170 |
saf | -12.954 |
Advantage | -12.856 |
Token | keep |
Token ID | 1394 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
debates | +3.871 |
clam | +3.595 |
adoption | +3.557 |
viewing | +3.529 |
amounts | +3.449 |
Neg logit contributions | |
holiest | -5.977 |
cific | -5.528 |
Trivia | -5.461 |
saf | -5.330 |
Advantage | -5.286 |
Token | a |
Token ID | 257 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
debates | +2.506 |
adoption | +2.386 |
viewing | +2.345 |
breastfeeding | +2.244 |
reading | +2.236 |
Neg logit contributions | |
holiest | -5.577 |
cific | -5.225 |
Trivia | -5.171 |
saf | -5.158 |
Advantage | -4.963 |
Token | close |
Token ID | 1969 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
debates | +3.049 |
viewing | +2.958 |
adoption | +2.929 |
reading | +2.865 |
clam | +2.855 |
Neg logit contributions | |
holiest | -4.557 |
saf | -4.271 |
cific | -4.263 |
Trivia | -4.201 |
Advantage | -4.157 |
Token | eye |
Token ID | 4151 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
debates | +1.798 |
adoption | +1.759 |
reading | +1.733 |
viewing | +1.732 |
clam | +1.569 |
Neg logit contributions | |
holiest | -7.735 |
saf | -7.394 |
cific | -7.352 |
INGTON | -7.161 |
Trivia | -7.143 |
Token |
|
Token ID | 198 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
debates | +0.065 |
adoption | +0.063 |
birth | +0.063 |
Pg | +0.062 |
rons | +0.061 |
Neg logit contributions | |
holiest | -0.086 |
saf | -0.078 |
cific | -0.077 |
Trivia | -0.076 |
Advantage | -0.075 |
Token | Take |
Token ID | 12322 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
debates | +0.553 |
birth | +0.550 |
Pg | +0.544 |
adoption | +0.539 |
rons | +0.529 |
Neg logit contributions | |
holiest | -0.641 |
cific | -0.566 |
saf | -0.562 |
Advantage | -0.556 |
INGTON | -0.548 |
Token | mankind |
Token ID | 18019 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
holiest | +2.023 |
saf | +1.851 |
cific | +1.826 |
Trivia | +1.808 |
Advantage | +1.792 |
Neg logit contributions | |
debates | -1.240 |
adoption | -1.201 |
birth | -1.195 |
Pg | -1.183 |
rons | -1.170 |
Token | in |
Token ID | 287 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
debates | +1.838 |
adoption | +1.777 |
birth | +1.744 |
amounts | +1.738 |
bathing | +1.721 |
Neg logit contributions | |
holiest | -3.086 |
cific | -2.872 |
saf | -2.856 |
Trivia | -2.810 |
INGTON | -2.768 |
Token | the |
Token ID | 262 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
debates | +2.191 |
adoption | +2.139 |
amounts | +2.057 |
birth | +2.040 |
bathing | +2.031 |
Neg logit contributions | |
holiest | -3.446 |
cific | -3.232 |
saf | -3.230 |
Trivia | -3.169 |
INGTON | -3.113 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
debates | +1.470 |
adoption | +1.436 |
amounts | +1.378 |
birth | +1.375 |
Pg | +1.360 |
Neg logit contributions | |
holiest | -2.196 |
cific | -2.080 |
saf | -2.054 |
Trivia | -2.030 |
INGTON | -2.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
adoption | +8.051 |
debates | +7.905 |
birth | +7.760 |
amounts | +7.743 |
clam | +7.665 |
Neg logit contributions | |
holiest | -11.443 |
cific | -10.651 |
saf | -10.402 |
Trivia | -10.332 |
Advantage | -10.036 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
debates | +0.623 |
adoption | +0.611 |
birth | +0.597 |
Pg | +0.590 |
amounts | +0.585 |
Neg logit contributions | |
holiest | -0.934 |
saf | -0.864 |
cific | -0.856 |
Trivia | -0.847 |
Advantage | -0.829 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
holiest | +0.179 |
saf | +0.161 |
cific | +0.159 |
Trivia | +0.157 |
Advantage | +0.156 |
Neg logit contributions | |
debates | -0.135 |
adoption | -0.131 |
birth | -0.131 |
Pg | -0.130 |
rons | -0.128 |
Token | and |
Token ID | 392 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
birth | +0.732 |
debates | +0.730 |
Pg | +0.721 |
adoption | +0.719 |
rons | +0.708 |
Neg logit contributions | |
holiest | -0.715 |
cific | -0.629 |
saf | -0.620 |
Advantage | -0.614 |
Trivia | -0.607 |
Token | for |
Token ID | 329 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
debates | +1.418 |
adoption | +1.377 |
birth | +1.344 |
amounts | +1.328 |
rons | +1.324 |
Neg logit contributions | |
holiest | -2.148 |
saf | -1.987 |
cific | -1.981 |
Trivia | -1.961 |
INGTON | -1.916 |
Token | If |
Token ID | 1532 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
holiest | +0.437 |
cific | +0.381 |
saf | +0.379 |
Advantage | +0.373 |
INGTON | +0.362 |
Neg logit contributions | |
birth | -0.358 |
Pg | -0.357 |
debates | -0.357 |
adoption | -0.350 |
tumblr | -0.345 |
Token | Dallas |
Token ID | 8533 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
debates | +1.299 |
adoption | +1.250 |
amounts | +1.227 |
birth | +1.209 |
viewing | +1.206 |
Neg logit contributions | |
holiest | -2.138 |
saf | -1.959 |
cific | -1.934 |
Trivia | -1.907 |
INGTON | -1.850 |
Token | ren |
Token ID | 8851 |
Feature activation | +8.79e+00 |
Pos logit contributions | |
holiest | +5.748 |
saf | +5.189 |
Trivia | +5.137 |
cific | +5.129 |
Advantage | +5.122 |
Neg logit contributions | |
debates | -4.100 |
birth | -4.085 |
Pg | -4.031 |
adoption | -4.011 |
rons | -3.983 |
Token | ounces |
Token ID | 45982 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
holiest | +5.919 |
cific | +5.455 |
saf | +5.429 |
Trivia | +5.342 |
Advantage | +5.152 |
Neg logit contributions | |
adoption | -6.224 |
debates | -6.107 |
birth | -6.082 |
breastfeeding | -6.010 |
Pg | -5.996 |
Token | Charlie |
Token ID | 11526 |
Feature activation | -9.06e+00 |
Pos logit contributions | |
holiest | +1.221 |
saf | +1.119 |
cific | +1.106 |
Trivia | +1.093 |
Advantage | +1.073 |
Neg logit contributions | |
debates | -0.795 |
adoption | -0.771 |
birth | -0.759 |
amounts | -0.751 |
Pg | -0.749 |
Token | V |
Token ID | 569 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
Pg | +6.788 |
adoption | +6.787 |
debates | +6.717 |
amounts | +6.617 |
breastfeeding | +6.519 |
Neg logit contributions | |
holiest | -6.037 |
saf | -5.193 |
cific | -5.125 |
INGTON | -5.011 |
Trivia | -4.932 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
rons | +8.618 |
debates | +8.468 |
ogue | +8.261 |
Pg | +8.064 |
Weiner | +7.989 |
Neg logit contributions | |
holiest | -10.941 |
Advantage | -10.122 |
saf | -10.061 |
cific | -9.630 |
alties | -9.383 |
Token | Greg |
Token ID | 8547 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
debates | +1.277 |
adoption | +1.242 |
amounts | +1.225 |
birth | +1.196 |
viewing | +1.187 |
Neg logit contributions | |
holiest | -2.110 |
saf | -1.936 |
cific | -1.891 |
Trivia | -1.884 |
Advantage | -1.826 |
Token | Smith |
Token ID | 4176 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
debates | +2.272 |
adoption | +2.138 |
rons | +2.099 |
amounts | +2.084 |
Pg | +2.084 |
Neg logit contributions | |
holiest | -5.655 |
saf | -5.310 |
cific | -5.215 |
Trivia | -5.072 |
INGTON | -5.033 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
debates | +1.788 |
amounts | +1.713 |
adoption | +1.705 |
Pg | +1.685 |
birth | +1.684 |
Neg logit contributions | |
holiest | -3.206 |
saf | -2.924 |
cific | -2.888 |
Trivia | -2.832 |
Advantage | -2.814 |
Token | Richard |
Token ID | 6219 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
debates | +1.197 |
adoption | +1.171 |
amounts | +1.139 |
birth | +1.128 |
Pg | +1.125 |
Neg logit contributions | |
holiest | -1.815 |
saf | -1.663 |
cific | -1.637 |
Trivia | -1.613 |
INGTON | -1.583 |
Token | topical |
Token ID | 39867 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
debates | +0.105 |
adoption | +0.102 |
birth | +0.101 |
Pg | +0.100 |
amounts | +0.099 |
Neg logit contributions | |
holiest | -0.170 |
saf | -0.158 |
cific | -0.156 |
Trivia | -0.153 |
Advantage | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
holiest | +0.211 |
saf | +0.194 |
cific | +0.191 |
Trivia | +0.189 |
Advantage | +0.187 |
Neg logit contributions | |
debates | -0.129 |
adoption | -0.123 |
birth | -0.121 |
Pg | -0.120 |
amounts | -0.120 |
Token | Trey |
Token ID | 36085 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
holiest | +0.440 |
saf | +0.401 |
cific | +0.398 |
Trivia | +0.393 |
Advantage | +0.388 |
Neg logit contributions | |
debates | -0.288 |
adoption | -0.279 |
birth | -0.276 |
Pg | -0.272 |
rons | -0.270 |
Token | Parker |
Token ID | 13612 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
debates | +1.429 |
adoption | +1.312 |
Pg | +1.295 |
rons | +1.280 |
viewing | +1.278 |
Neg logit contributions | |
holiest | -2.722 |
saf | -2.509 |
cific | -2.491 |
Trivia | -2.427 |
INGTON | -2.420 |
Token | and |
Token ID | 290 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
debates | +0.581 |
adoption | +0.553 |
birth | +0.546 |
amounts | +0.541 |
Pg | +0.536 |
Neg logit contributions | |
holiest | -0.899 |
cific | -0.822 |
saf | -0.821 |
Advantage | -0.795 |
Trivia | -0.792 |
Token | Matt |
Token ID | 4705 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
debates | +0.538 |
adoption | +0.528 |
birth | +0.510 |
amounts | +0.506 |
rons | +0.504 |
Neg logit contributions | |
holiest | -0.846 |
saf | -0.774 |
cific | -0.770 |
Trivia | -0.755 |
Advantage | -0.743 |
Token | Stone |
Token ID | 8026 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
Weiner | +5.174 |
debates | +5.015 |
adoption | +4.796 |
Bradley | +4.694 |
viewing | +4.557 |
Neg logit contributions | |
holiest | -14.643 |
cific | -14.506 |
saf | -14.091 |
Trivia | -13.707 |
abouts | -13.430 |
Token | 's |
Token ID | 338 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
debates | +2.837 |
birth | +2.693 |
adoption | +2.653 |
rons | +2.609 |
amounts | +2.594 |
Neg logit contributions | |
holiest | -4.968 |
cific | -4.508 |
saf | -4.479 |
Trivia | -4.393 |
Advantage | -4.342 |
Token | news |
Token ID | 1705 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
holiest | +2.174 |
saf | +1.985 |
cific | +1.957 |
Trivia | +1.937 |
Advantage | +1.920 |
Neg logit contributions | |
debates | -1.409 |
adoption | -1.365 |
birth | -1.361 |
Pg | -1.347 |
rons | -1.333 |
Token | y |
Token ID | 88 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
debates | +2.727 |
adoption | +2.645 |
birth | +2.632 |
viewing | +2.612 |
amounts | +2.585 |
Neg logit contributions | |
holiest | -4.352 |
cific | -4.022 |
saf | -3.900 |
Trivia | -3.865 |
Advantage | -3.860 |
Token | cartoon |
Token ID | 16251 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
holiest | +1.980 |
saf | +1.815 |
cific | +1.790 |
Trivia | +1.773 |
Advantage | +1.758 |
Neg logit contributions | |
debates | -1.168 |
adoption | -1.130 |
birth | -1.126 |
Pg | -1.115 |
rons | -1.102 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
debates | +1.486 |
Pg | +1.446 |
birth | +1.443 |
adoption | +1.424 |
amounts | +1.385 |
Neg logit contributions | |
holiest | -2.311 |
cific | -2.089 |
saf | -2.074 |
Advantage | -2.026 |
INGTON | -1.996 |
Token | : |
Token ID | 25 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
debates | +2.233 |
adoption | +2.150 |
birth | +2.108 |
amounts | +2.104 |
Pg | +2.103 |
Neg logit contributions | |
holiest | -3.155 |
saf | -2.866 |
cific | -2.852 |
Trivia | -2.758 |
Advantage | -2.728 |
Token | ' |
Token ID | 705 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
debates | +2.749 |
adoption | +2.679 |
birth | +2.602 |
amounts | +2.569 |
rons | +2.556 |
Neg logit contributions | |
holiest | -4.294 |
cific | -3.987 |
saf | -3.918 |
Trivia | -3.898 |
INGTON | -3.688 |
Token | I |
Token ID | 40 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
birth | +3.072 |
debates | +3.005 |
adoption | +2.976 |
rons | +2.897 |
Pg | +2.857 |
Neg logit contributions | |
holiest | -4.960 |
cific | -4.531 |
saf | -4.422 |
INGTON | -4.308 |
Advantage | -4.289 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
debates | +1.460 |
adoption | +1.412 |
birth | +1.403 |
Pg | +1.382 |
rons | +1.377 |
Neg logit contributions | |
holiest | -2.416 |
saf | -2.214 |
cific | -2.186 |
Trivia | -2.161 |
Advantage | -2.141 |
Token | expect |
Token ID | 1607 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
debates | +5.275 |
adoption | +5.172 |
birth | +5.130 |
rons | +5.096 |
croft | +4.945 |
Neg logit contributions | |
holiest | -11.117 |
cific | -10.889 |
Advantage | -10.458 |
saf | -10.432 |
INGTON | -10.416 |
Token | ' |
Token ID | 6 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
debates | +8.264 |
amounts | +7.773 |
Weiner | +7.556 |
croft | +7.387 |
adoption | +7.291 |
Neg logit contributions | |
holiest | -12.607 |
saf | -12.173 |
Trivia | -11.859 |
cific | -11.535 |
INGTON | -11.489 |
Token | fair |
Token ID | 3148 |
Feature activation | -8.57e+00 |
Pos logit contributions | |
debates | +4.222 |
adoption | +4.167 |
amounts | +4.095 |
birth | +4.028 |
viewing | +3.928 |
Neg logit contributions | |
holiest | -8.423 |
saf | -8.033 |
cific | -7.644 |
Trivia | -7.636 |
Advantage | -7.418 |
Token | treatment |
Token ID | 3513 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
debates | +5.080 |
adoption | +4.707 |
amounts | +4.663 |
viewing | +4.472 |
breastfeeding | +4.433 |
Neg logit contributions | |
holiest | -7.664 |
cific | -7.055 |
saf | -6.935 |
Trivia | -6.842 |
Advantage | -6.579 |
Token | by |
Token ID | 416 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
debates | +3.200 |
adoption | +3.034 |
amounts | +2.999 |
rons | +2.920 |
viewing | +2.894 |
Neg logit contributions | |
holiest | -5.184 |
saf | -4.856 |
cific | -4.782 |
Trivia | -4.699 |
INGTON | -4.554 |
Token | DNC |
Token ID | 17824 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
debates | +2.690 |
adoption | +2.595 |
birth | +2.579 |
Pg | +2.546 |
rons | +2.527 |
Neg logit contributions | |
holiest | -4.440 |
saf | -4.067 |
cific | -4.019 |
Trivia | -3.980 |
Advantage | -3.937 |
Token | finance |
Token ID | 9604 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
debates | +4.659 |
adoption | +4.587 |
amounts | +4.343 |
viewing | +4.260 |
clam | +4.182 |
Neg logit contributions | |
holiest | -5.764 |
cific | -5.338 |
saf | -5.291 |
Trivia | -5.233 |
INGTON | -5.162 |
Token | and |
Token ID | 290 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
holiest | +3.401 |
saf | +3.077 |
cific | +3.017 |
Advantage | +2.988 |
Trivia | +2.983 |
Neg logit contributions | |
debates | -2.434 |
birth | -2.410 |
Pg | -2.397 |
adoption | -2.372 |
rons | -2.351 |
Token | ro |
Token ID | 686 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
debates | +0.038 |
adoption | +0.037 |
birth | +0.036 |
amounts | +0.035 |
Pg | +0.035 |
Neg logit contributions | |
holiest | -0.059 |
saf | -0.054 |
cific | -0.053 |
Trivia | -0.053 |
Advantage | -0.052 |
Token | iled |
Token ID | 3902 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
holiest | +1.071 |
saf | +0.947 |
Trivia | +0.940 |
cific | +0.939 |
Advantage | +0.924 |
Neg logit contributions | |
debates | -0.890 |
birth | -0.873 |
Pg | -0.863 |
adoption | -0.861 |
rons | -0.858 |
Token | by |
Token ID | 416 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
debates | +1.436 |
adoption | +1.354 |
amounts | +1.301 |
Pg | +1.293 |
rons | +1.293 |
Neg logit contributions | |
holiest | -2.084 |
saf | -1.949 |
cific | -1.910 |
Trivia | -1.895 |
Advantage | -1.869 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
debates | +0.113 |
adoption | +0.109 |
birth | +0.105 |
amounts | +0.105 |
Pg | +0.103 |
Neg logit contributions | |
holiest | -0.172 |
saf | -0.159 |
cific | -0.156 |
Trivia | -0.155 |
Advantage | -0.153 |
Token | street |
Token ID | 4675 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
adoption | +7.958 |
debates | +7.950 |
amounts | +7.662 |
clam | +7.197 |
viewing | +6.981 |
Neg logit contributions | |
holiest | -12.327 |
cific | -11.450 |
saf | -11.307 |
Trivia | -11.163 |
Advantage | -10.972 |
Token | protests |
Token ID | 8536 |
Feature activation | -7.64e+00 |
Pos logit contributions | |
debates | +1.183 |
adoption | +1.091 |
amounts | +1.032 |
birth | +1.030 |
Pg | +1.024 |
Neg logit contributions | |
holiest | -3.512 |
cific | -3.249 |
saf | -3.247 |
Trivia | -3.206 |
Advantage | -3.192 |
Token | . |
Token ID | 13 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
debates | +3.833 |
clam | +3.649 |
amounts | +3.599 |
adoption | +3.598 |
viewing | +3.547 |
Neg logit contributions | |
holiest | -6.913 |
cific | -6.495 |
saf | -6.483 |
Trivia | -6.430 |
Advantage | -6.365 |
Token | These |
Token ID | 2312 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
debates | +2.239 |
birth | +2.167 |
Pg | +2.155 |
adoption | +2.136 |
Lauder | +2.107 |
Neg logit contributions | |
holiest | -3.417 |
saf | -3.058 |
cific | -3.023 |
Trivia | -2.957 |
INGTON | -2.899 |
Token | were |
Token ID | 547 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
debates | +2.360 |
adoption | +2.212 |
amounts | +2.165 |
clam | +2.109 |
birth | +2.099 |
Neg logit contributions | |
holiest | -3.536 |
saf | -3.250 |
cific | -3.241 |
Trivia | -3.186 |
Advantage | -3.161 |
Token | no |
Token ID | 645 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
holiest | +0.345 |
saf | +0.315 |
cific | +0.313 |
Trivia | +0.310 |
Advantage | +0.305 |
Neg logit contributions | |
debates | -0.197 |
adoption | -0.189 |
birth | -0.188 |
rons | -0.186 |
Pg | -0.185 |
Token | one |
Token ID | 530 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
holiest | +2.092 |
saf | +1.862 |
cific | +1.829 |
Trivia | +1.805 |
Advantage | +1.783 |
Neg logit contributions | |
debates | -2.279 |
adoption | -2.226 |
birth | -2.218 |
Pg | -2.201 |
rons | -2.184 |
Token | can |
Token ID | 460 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
holiest | +4.352 |
saf | +3.902 |
cific | +3.838 |
Trivia | +3.825 |
Advantage | +3.806 |
Neg logit contributions | |
debates | -3.334 |
birth | -3.304 |
Pg | -3.298 |
adoption | -3.273 |
rons | -3.225 |
Token | take |
Token ID | 1011 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
holiest | +3.520 |
saf | +3.201 |
cific | +3.142 |
Trivia | +3.105 |
Advantage | +3.083 |
Neg logit contributions | |
debates | -2.687 |
adoption | -2.628 |
birth | -2.627 |
Pg | -2.600 |
rons | -2.564 |
Token | any |
Token ID | 597 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
holiest | +2.391 |
saf | +2.174 |
cific | +2.143 |
Trivia | +2.123 |
Advantage | +2.118 |
Neg logit contributions | |
debates | -1.610 |
birth | -1.565 |
adoption | -1.562 |
Pg | -1.549 |
rons | -1.533 |
Token | risks |
Token ID | 7476 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
holiest | +5.040 |
saf | +4.520 |
Advantage | +4.451 |
cific | +4.436 |
Trivia | +4.380 |
Neg logit contributions | |
debates | -3.825 |
birth | -3.804 |
Pg | -3.767 |
adoption | -3.734 |
rons | -3.724 |
Token | with |
Token ID | 351 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
holiest | +8.065 |
saf | +7.317 |
Trivia | +7.101 |
Advantage | +7.064 |
cific | +7.037 |
Neg logit contributions | |
Pg | -5.852 |
birth | -5.777 |
debates | -5.721 |
tumblr | -5.659 |
adoption | -5.628 |
Token | this |
Token ID | 428 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
holiest | +3.094 |
saf | +2.828 |
cific | +2.789 |
Trivia | +2.764 |
Advantage | +2.745 |
Neg logit contributions | |
debates | -1.871 |
birth | -1.812 |
adoption | -1.811 |
Pg | -1.795 |
rons | -1.773 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
debates | +2.233 |
adoption | +2.214 |
amounts | +2.145 |
viewing | +2.085 |
clam | +2.049 |
Neg logit contributions | |
holiest | -3.337 |
cific | -3.136 |
saf | -3.134 |
Trivia | -3.092 |
INGTON | -3.005 |
Token | Everything |
Token ID | 11391 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
holiest | +0.219 |
saf | +0.198 |
cific | +0.195 |
Trivia | +0.191 |
INGTON | +0.187 |
Neg logit contributions | |
debates | -0.154 |
adoption | -0.149 |
birth | -0.148 |
Pg | -0.146 |
amounts | -0.144 |
Token | must |
Token ID | 1276 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
holiest | +1.674 |
saf | +1.534 |
cific | +1.515 |
Trivia | +1.493 |
Advantage | +1.478 |
Neg logit contributions | |
debates | -1.066 |
adoption | -1.030 |
birth | -1.016 |
amounts | -1.007 |
Pg | -1.004 |
Token | recession |
Token ID | 16457 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
debates | +0.846 |
adoption | +0.818 |
viewing | +0.781 |
amounts | +0.781 |
Pg | +0.775 |
Neg logit contributions | |
holiest | -1.354 |
saf | -1.255 |
cific | -1.243 |
Trivia | -1.238 |
INGTON | -1.201 |
Token | . |
Token ID | 13 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
holiest | +3.263 |
saf | +2.960 |
cific | +2.906 |
Trivia | +2.869 |
Advantage | +2.858 |
Neg logit contributions | |
debates | -2.548 |
adoption | -2.485 |
birth | -2.482 |
Pg | -2.459 |
rons | -2.430 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
debates | +1.733 |
birth | +1.664 |
adoption | +1.648 |
Pg | +1.629 |
rons | +1.615 |
Neg logit contributions | |
holiest | -2.617 |
saf | -2.369 |
cific | -2.339 |
Trivia | -2.299 |
Advantage | -2.227 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
debates | +0.926 |
birth | +0.913 |
Pg | +0.903 |
adoption | +0.900 |
amounts | +0.876 |
Neg logit contributions | |
holiest | -1.396 |
cific | -1.249 |
saf | -1.246 |
Trivia | -1.217 |
Advantage | -1.212 |
Token | On |
Token ID | 2202 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
Pg | +2.426 |
birth | +2.387 |
debates | +2.305 |
tumblr | +2.270 |
adoption | +2.241 |
Neg logit contributions | |
holiest | -3.352 |
cific | -2.983 |
Advantage | -2.966 |
saf | -2.881 |
INGTON | -2.757 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
debates | +2.545 |
adoption | +2.457 |
birth | +2.409 |
viewing | +2.367 |
amounts | +2.353 |
Neg logit contributions | |
holiest | -3.882 |
saf | -3.564 |
cific | -3.561 |
Trivia | -3.554 |
INGTON | -3.452 |
Token | , |
Token ID | 11 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
holiest | +9.613 |
saf | +8.554 |
Advantage | +8.467 |
cific | +8.410 |
INGTON | +8.386 |
Neg logit contributions | |
Pg | -7.658 |
birth | -7.516 |
tumblr | -7.460 |
adoption | -7.230 |
anamo | -7.214 |
Token | Carney |
Token ID | 40775 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
holiest | +3.680 |
saf | +3.349 |
cific | +3.312 |
Trivia | +3.271 |
Advantage | +3.265 |
Neg logit contributions | |
debates | -2.333 |
Pg | -2.295 |
birth | -2.291 |
adoption | -2.278 |
rons | -2.245 |
Token | said |
Token ID | 531 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
debates | +0.046 |
adoption | +0.044 |
birth | +0.044 |
amounts | +0.043 |
rons | +0.043 |
Neg logit contributions | |
holiest | -0.068 |
saf | -0.062 |
cific | -0.062 |
Trivia | -0.061 |
Advantage | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
holiest | +1.920 |
saf | +1.753 |
cific | +1.728 |
Trivia | +1.711 |
Advantage | +1.694 |
Neg logit contributions | |
debates | -1.274 |
adoption | -1.234 |
birth | -1.228 |
Pg | -1.214 |
rons | -1.204 |
Token | independent |
Token ID | 4795 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
holiest | +0.034 |
saf | +0.031 |
cific | +0.031 |
Trivia | +0.031 |
Advantage | +0.030 |
Neg logit contributions | |
debates | -0.021 |
adoption | -0.020 |
birth | -0.019 |
amounts | -0.019 |
Pg | -0.019 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
birth | +3.040 |
Pg | +3.002 |
Weiner | +2.935 |
debates | +2.926 |
Lauder | +2.852 |
Neg logit contributions | |
holiest | -11.685 |
cific | -10.882 |
saf | -10.866 |
alties | -10.292 |
challeng | -10.247 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
debates | +1.423 |
adoption | +1.385 |
birth | +1.378 |
amounts | +1.351 |
Pg | +1.344 |
Neg logit contributions | |
holiest | -1.491 |
saf | -1.341 |
cific | -1.324 |
Trivia | -1.285 |
Advantage | -1.271 |
Token | realDonaldTrump |
Token ID | 28024 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
holiest | +1.036 |
saf | +0.909 |
cific | +0.884 |
Trivia | +0.875 |
Advantage | +0.850 |
Neg logit contributions | |
debates | -1.542 |
adoption | -1.506 |
birth | -1.502 |
Pg | -1.491 |
rons | -1.478 |
Token | ) |
Token ID | 8 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
debates | +0.373 |
birth | +0.363 |
adoption | +0.362 |
Pg | +0.357 |
amounts | +0.351 |
Neg logit contributions | |
holiest | -0.590 |
saf | -0.533 |
cific | -0.529 |
Trivia | -0.519 |
Advantage | -0.518 |
Token | June |
Token ID | 2795 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
holiest | +2.367 |
saf | +2.142 |
cific | +2.110 |
Trivia | +2.085 |
Advantage | +2.063 |
Neg logit contributions | |
debates | -1.929 |
adoption | -1.877 |
birth | -1.870 |
Pg | -1.852 |
rons | -1.835 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
holiest | +4.426 |
saf | +3.944 |
Advantage | +3.829 |
Trivia | +3.799 |
cific | +3.750 |
Neg logit contributions | |
debates | -6.093 |
Pg | -5.954 |
adoption | -5.933 |
rons | -5.924 |
birth | -5.892 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
holiest | +7.188 |
saf | +6.917 |
Advantage | +6.738 |
Trivia | +6.721 |
cific | +6.559 |
Neg logit contributions | |
debates | -7.585 |
stret | -7.437 |
adoption | -7.418 |
bathing | -7.377 |
clam | -7.356 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
holiest | +5.162 |
saf | +4.162 |
Advantage | +4.011 |
Trivia | +3.870 |
cific | +3.818 |
Neg logit contributions | |
Pg | -10.573 |
debates | -10.500 |
rons | -10.225 |
tumblr | -10.102 |
birth | -10.078 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
holiest | +3.347 |
saf | +3.021 |
cific | +2.944 |
Trivia | +2.943 |
Advantage | +2.941 |
Neg logit contributions | |
debates | -3.033 |
birth | -2.959 |
Pg | -2.957 |
adoption | -2.956 |
rons | -2.942 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
holiest | +2.594 |
saf | +2.392 |
Trivia | +2.329 |
cific | +2.315 |
Advantage | +2.287 |
Neg logit contributions | |
debates | -2.393 |
adoption | -2.329 |
rons | -2.294 |
birth | -2.285 |
Pg | -2.260 |
Token | Shortly |
Token ID | 30513 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
holiest | +1.012 |
saf | +0.905 |
cific | +0.901 |
Advantage | +0.885 |
Trivia | +0.875 |
Neg logit contributions | |
debates | -0.840 |
birth | -0.823 |
Pg | -0.819 |
adoption | -0.818 |
rons | -0.802 |
Token | three |
Token ID | 1115 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
holiest | +3.925 |
saf | +3.524 |
cific | +3.445 |
Trivia | +3.401 |
Advantage | +3.386 |
Neg logit contributions | |
debates | -3.959 |
birth | -3.876 |
Pg | -3.858 |
adoption | -3.858 |
rons | -3.813 |
Token | games |
Token ID | 1830 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
holiest | +3.997 |
saf | +3.624 |
cific | +3.569 |
Trivia | +3.524 |
Advantage | +3.516 |
Neg logit contributions | |
debates | -2.929 |
birth | -2.900 |
adoption | -2.879 |
Pg | -2.861 |
rons | -2.821 |
Token | with |
Token ID | 351 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
holiest | +0.359 |
saf | +0.328 |
cific | +0.324 |
Trivia | +0.320 |
Advantage | +0.315 |
Neg logit contributions | |
debates | -0.234 |
adoption | -0.227 |
birth | -0.224 |
Pg | -0.222 |
rons | -0.221 |
Token | their |
Token ID | 511 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
holiest | +3.131 |
saf | +2.846 |
cific | +2.806 |
Trivia | +2.775 |
Advantage | +2.743 |
Neg logit contributions | |
debates | -2.310 |
adoption | -2.243 |
birth | -2.229 |
Pg | -2.208 |
rons | -2.189 |
Token | 14 |
Token ID | 1478 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
holiest | +3.846 |
saf | +3.500 |
cific | +3.443 |
Trivia | +3.404 |
Advantage | +3.388 |
Neg logit contributions | |
debates | -2.522 |
birth | -2.443 |
adoption | -2.441 |
Pg | -2.427 |
rons | -2.400 |
Token | th |
Token ID | 400 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
holiest | +1.921 |
saf | +1.739 |
cific | +1.713 |
Trivia | +1.695 |
Advantage | +1.675 |
Neg logit contributions | |
debates | -1.557 |
adoption | -1.510 |
birth | -1.504 |
Pg | -1.489 |
rons | -1.476 |
Token | defeat |
Token ID | 7433 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
holiest | +9.825 |
Advantage | +8.683 |
saf | +8.607 |
cific | +8.476 |
INGTON | +8.315 |
Neg logit contributions | |
debates | -7.954 |
Pg | -7.943 |
rons | -7.817 |
tumblr | -7.686 |
croft | -7.666 |
Token | in |
Token ID | 287 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
holiest | +5.422 |
saf | +4.950 |
cific | +4.830 |
Trivia | +4.801 |
Advantage | +4.774 |
Neg logit contributions | |
debates | -3.991 |
adoption | -3.883 |
birth | -3.871 |
Pg | -3.856 |
tumblr | -3.766 |
Token | 16 |
Token ID | 1467 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
holiest | +4.105 |
saf | +3.669 |
cific | +3.594 |
Trivia | +3.565 |
Advantage | +3.555 |
Neg logit contributions | |
debates | -3.874 |
birth | -3.792 |
Pg | -3.774 |
adoption | -3.762 |
rons | -3.720 |
Token | outings |
Token ID | 47280 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
holiest | +0.573 |
saf | +0.524 |
cific | +0.519 |
Trivia | +0.514 |
INGTON | +0.505 |
Neg logit contributions | |
debates | -0.351 |
adoption | -0.336 |
birth | -0.330 |
amounts | -0.324 |
Pg | -0.322 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
holiest | +3.541 |
saf | +3.213 |
cific | +3.161 |
Trivia | +3.132 |
Advantage | +3.104 |
Neg logit contributions | |
debates | -2.706 |
adoption | -2.633 |
birth | -2.623 |
Pg | -2.603 |
rons | -2.569 |
Token | dispute |
Token ID | 11047 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
debates | +1.768 |
adoption | +1.690 |
amounts | +1.633 |
birth | +1.560 |
viewing | +1.556 |
Neg logit contributions | |
holiest | -3.776 |
cific | -3.498 |
saf | -3.458 |
Trivia | -3.454 |
INGTON | -3.393 |
Token | in |
Token ID | 287 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
holiest | +0.081 |
saf | +0.074 |
cific | +0.073 |
Trivia | +0.073 |
Advantage | +0.071 |
Neg logit contributions | |
debates | -0.054 |
adoption | -0.052 |
amounts | -0.051 |
birth | -0.051 |
rons | -0.050 |
Token | its |
Token ID | 663 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
holiest | +1.224 |
saf | +1.118 |
cific | +1.099 |
Trivia | +1.094 |
Advantage | +1.073 |
Neg logit contributions | |
debates | -0.874 |
adoption | -0.845 |
birth | -0.834 |
amounts | -0.819 |
Pg | -0.815 |
Token | statement |
Token ID | 2643 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
holiest | +2.730 |
saf | +2.486 |
cific | +2.449 |
Trivia | +2.424 |
Advantage | +2.402 |
Neg logit contributions | |
debates | -1.872 |
adoption | -1.815 |
birth | -1.812 |
Pg | -1.796 |
rons | -1.778 |
Token | on |
Token ID | 319 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
holiest | +0.004 |
saf | +0.004 |
cific | +0.004 |
Trivia | +0.004 |
Advantage | +0.004 |
Neg logit contributions | |
debates | -0.003 |
adoption | -0.003 |
birth | -0.002 |
amounts | -0.002 |
rons | -0.002 |
Token | Monday |
Token ID | 3321 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
holiest | +0.368 |
saf | +0.337 |
cific | +0.334 |
Trivia | +0.332 |
Advantage | +0.325 |
Neg logit contributions | |
debates | -0.264 |
adoption | -0.258 |
birth | -0.254 |
amounts | -0.247 |
Pg | -0.247 |
Token | , |
Token ID | 11 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
holiest | +8.690 |
saf | +7.867 |
cific | +7.595 |
Advantage | +7.551 |
Trivia | +7.498 |
Neg logit contributions | |
Pg | -7.999 |
tumblr | -7.872 |
debates | -7.849 |
rons | -7.838 |
birth | -7.806 |
Token | but |
Token ID | 475 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
holiest | +4.323 |
saf | +3.979 |
cific | +3.932 |
Trivia | +3.890 |
Advantage | +3.865 |
Neg logit contributions | |
debates | -2.025 |
birth | -1.946 |
adoption | -1.944 |
Pg | -1.938 |
rons | -1.909 |
Token | said |
Token ID | 531 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
holiest | +4.451 |
saf | +4.036 |
cific | +3.974 |
Trivia | +3.913 |
Advantage | +3.903 |
Neg logit contributions | |
debates | -3.312 |
Pg | -3.270 |
birth | -3.250 |
adoption | -3.227 |
rons | -3.181 |
Token | it |
Token ID | 340 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
holiest | +4.076 |
saf | +3.677 |
cific | +3.626 |
Trivia | +3.579 |
Advantage | +3.575 |
Neg logit contributions | |
debates | -2.978 |
Pg | -2.935 |
birth | -2.922 |
adoption | -2.899 |
rons | -2.859 |
Token | would |
Token ID | 561 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
holiest | +3.836 |
saf | +3.474 |
cific | +3.400 |
Trivia | +3.370 |
Advantage | +3.353 |
Neg logit contributions | |
debates | -2.913 |
birth | -2.863 |
adoption | -2.853 |
Pg | -2.840 |
rons | -2.798 |
Token | though |
Token ID | 996 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
debates | +0.526 |
adoption | +0.517 |
birth | +0.497 |
amounts | +0.495 |
viewing | +0.487 |
Neg logit contributions | |
holiest | -0.846 |
saf | -0.781 |
cific | -0.776 |
Trivia | -0.759 |
Advantage | -0.746 |
Token | I |
Token ID | 314 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
debates | +1.696 |
adoption | +1.677 |
birth | +1.609 |
amounts | +1.592 |
breastfeeding | +1.572 |
Neg logit contributions | |
holiest | -2.821 |
saf | -2.617 |
cific | -2.586 |
Trivia | -2.553 |
INGTON | -2.469 |
Token | knew |
Token ID | 2993 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
debates | +1.251 |
adoption | +1.198 |
rons | +1.191 |
birth | +1.189 |
clam | +1.186 |
Neg logit contributions | |
holiest | -1.796 |
cific | -1.629 |
saf | -1.627 |
Trivia | -1.599 |
Advantage | -1.579 |
Token | I |
Token ID | 314 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
debates | +2.366 |
adoption | +2.345 |
amounts | +2.231 |
birth | +2.213 |
breastfeeding | +2.172 |
Neg logit contributions | |
holiest | -4.001 |
cific | -3.721 |
saf | -3.695 |
Trivia | -3.632 |
INGTON | -3.509 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
holiest | +1.327 |
saf | +1.198 |
cific | +1.195 |
Trivia | +1.176 |
Advantage | +1.162 |
Neg logit contributions | |
debates | -1.031 |
adoption | -1.002 |
birth | -0.997 |
rons | -0.989 |
Pg | -0.982 |
Token | to |
Token ID | 284 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
debates | +1.582 |
adoption | +1.566 |
birth | +1.504 |
amounts | +1.444 |
Pg | +1.439 |
Neg logit contributions | |
holiest | -3.527 |
saf | -3.279 |
Trivia | -3.207 |
cific | -3.200 |
Advantage | -3.117 |
Token | get |
Token ID | 651 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
holiest | +0.441 |
saf | +0.402 |
cific | +0.399 |
Trivia | +0.395 |
Advantage | +0.391 |
Neg logit contributions | |
debates | -0.260 |
adoption | -0.254 |
birth | -0.248 |
amounts | -0.244 |
rons | -0.243 |
Token | � |
Token ID | 564 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
debates | +1.097 |
adoption | +1.092 |
birth | +1.042 |
amounts | +1.024 |
breastfeeding | +1.024 |
Neg logit contributions | |
holiest | -1.859 |
saf | -1.740 |
cific | -1.697 |
Trivia | -1.693 |
INGTON | -1.636 |
Token | � |
Token ID | 250 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
holiest | +0.178 |
saf | +0.161 |
cific | +0.159 |
Trivia | +0.157 |
Advantage | +0.154 |
Neg logit contributions | |
debates | -0.143 |
adoption | -0.139 |
birth | -0.138 |
Pg | -0.138 |
amounts | -0.135 |
Token | into |
Token ID | 20424 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
holiest | +2.062 |
saf | +1.878 |
cific | +1.850 |
Trivia | +1.831 |
Advantage | +1.813 |
Neg logit contributions | |
debates | -1.460 |
adoption | -1.417 |
birth | -1.411 |
Pg | -1.397 |
rons | -1.384 |
Token | tech |
Token ID | 7261 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
debates | +0.687 |
adoption | +0.667 |
birth | +0.655 |
amounts | +0.639 |
Pg | +0.635 |
Neg logit contributions | |
holiest | -1.127 |
saf | -1.028 |
cific | -1.024 |
Trivia | -1.001 |
Advantage | -0.984 |
Token | with |
Token ID | 351 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
debates | +1.484 |
adoption | +1.371 |
amounts | +1.370 |
birth | +1.358 |
rons | +1.353 |
Neg logit contributions | |
holiest | -2.506 |
saf | -2.320 |
cific | -2.269 |
Trivia | -2.267 |
Advantage | -2.238 |
Token | leadership |
Token ID | 5531 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
holiest | +0.918 |
saf | +0.843 |
cific | +0.830 |
Trivia | +0.824 |
Advantage | +0.813 |
Neg logit contributions | |
debates | -0.561 |
adoption | -0.541 |
birth | -0.532 |
Pg | -0.525 |
amounts | -0.524 |
Token | earlier |
Token ID | 2961 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
holiest | +2.942 |
saf | +2.687 |
cific | +2.649 |
Trivia | +2.623 |
Advantage | +2.601 |
Neg logit contributions | |
debates | -1.915 |
adoption | -1.866 |
birth | -1.866 |
Pg | -1.851 |
rons | -1.817 |
Token | this |
Token ID | 428 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
holiest | +1.607 |
saf | +1.468 |
cific | +1.448 |
Trivia | +1.441 |
Advantage | +1.418 |
Neg logit contributions | |
debates | -1.068 |
adoption | -1.030 |
birth | -1.017 |
Pg | -1.005 |
rons | -1.000 |
Token | year |
Token ID | 614 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
holiest | +0.788 |
saf | +0.719 |
cific | +0.708 |
Trivia | +0.703 |
Advantage | +0.693 |
Neg logit contributions | |
debates | -0.603 |
adoption | -0.586 |
birth | -0.576 |
Pg | -0.569 |
amounts | -0.566 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
holiest | +4.540 |
saf | +4.136 |
cific | +4.091 |
Trivia | +4.029 |
Advantage | +3.992 |
Neg logit contributions | |
debates | -3.248 |
adoption | -3.196 |
Pg | -3.193 |
birth | -3.187 |
rons | -3.118 |
Token | pushed |
Token ID | 7121 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
holiest | +1.986 |
saf | +1.820 |
cific | +1.795 |
Trivia | +1.780 |
Advantage | +1.762 |
Neg logit contributions | |
debates | -1.179 |
adoption | -1.140 |
birth | -1.131 |
Pg | -1.116 |
rons | -1.108 |
Token | to |
Token ID | 284 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
debates | +1.658 |
adoption | +1.610 |
amounts | +1.557 |
birth | +1.516 |
Pg | +1.516 |
Neg logit contributions | |
holiest | -2.893 |
saf | -2.669 |
Trivia | -2.614 |
cific | -2.601 |
Advantage | -2.561 |
Token | trim |
Token ID | 15797 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
holiest | +1.655 |
saf | +1.504 |
cific | +1.484 |
Trivia | +1.471 |
Advantage | +1.460 |
Neg logit contributions | |
debates | -1.152 |
adoption | -1.121 |
birth | -1.102 |
Pg | -1.087 |
rons | -1.080 |
Token | a |
Token ID | 257 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
debates | +0.527 |
adoption | +0.503 |
amounts | +0.496 |
birth | +0.492 |
Pg | +0.489 |
Neg logit contributions | |
holiest | -0.925 |
saf | -0.856 |
cific | -0.842 |
Trivia | -0.834 |
Advantage | -0.820 |
Token | spending |
Token ID | 4581 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
debates | +0.531 |
adoption | +0.517 |
birth | +0.507 |
amounts | +0.505 |
Pg | +0.503 |
Neg logit contributions | |
holiest | -0.758 |
saf | -0.697 |
cific | -0.685 |
Trivia | -0.679 |
Advantage | -0.669 |
Token | endi |
Token ID | 43109 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
holiest | +1.772 |
saf | +1.630 |
cific | +1.610 |
Trivia | +1.595 |
Advantage | +1.578 |
Neg logit contributions | |
debates | -0.973 |
adoption | -0.939 |
birth | -0.934 |
Pg | -0.921 |
rons | -0.913 |
Token | st |
Token ID | 336 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
holiest | +0.059 |
saf | +0.054 |
cific | +0.054 |
Advantage | +0.052 |
Trivia | +0.052 |
Neg logit contributions | |
debates | -0.040 |
adoption | -0.039 |
birth | -0.038 |
amounts | -0.038 |
Pg | -0.038 |
Token | rolled |
Token ID | 8375 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
holiest | +5.740 |
saf | +5.301 |
cific | +5.242 |
Trivia | +5.179 |
rown | +5.020 |
Neg logit contributions | |
adoption | -3.792 |
debates | -3.753 |
birth | -3.728 |
Pg | -3.677 |
amounts | -3.593 |
Token | off |
Token ID | 572 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
debates | +0.298 |
adoption | +0.289 |
birth | +0.283 |
amounts | +0.281 |
rons | +0.278 |
Neg logit contributions | |
holiest | -0.385 |
saf | -0.353 |
cific | -0.349 |
Trivia | -0.342 |
Advantage | -0.339 |
Token | to |
Token ID | 284 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
debates | +3.019 |
crying | +2.910 |
adoption | +2.889 |
viewing | +2.871 |
Pg | +2.826 |
Neg logit contributions | |
holiest | -5.611 |
saf | -5.182 |
cific | -5.133 |
Advantage | -5.099 |
INGTON | -4.978 |
Token | entertain |
Token ID | 8204 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
holiest | +2.422 |
saf | +2.219 |
cific | +2.191 |
Trivia | +2.168 |
Advantage | +2.151 |
Neg logit contributions | |
debates | -1.421 |
adoption | -1.374 |
birth | -1.365 |
Pg | -1.349 |
rons | -1.336 |
Token | ( |
Token ID | 357 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
holiest | +1.297 |
saf | +1.185 |
cific | +1.170 |
Trivia | +1.155 |
Advantage | +1.145 |
Neg logit contributions | |
debates | -0.803 |
adoption | -0.778 |
birth | -0.771 |
Pg | -0.764 |
rons | -0.756 |
Token | or |
Token ID | 273 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
holiest | +0.791 |
saf | +0.703 |
cific | +0.702 |
Advantage | +0.686 |
Trivia | +0.683 |
Neg logit contributions | |
debates | -0.686 |
birth | -0.675 |
Pg | -0.669 |
adoption | -0.668 |
rons | -0.654 |
Token | be |
Token ID | 307 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
holiest | +3.986 |
saf | +3.622 |
cific | +3.560 |
Trivia | +3.537 |
Advantage | +3.504 |
Neg logit contributions | |
debates | -2.750 |
birth | -2.685 |
adoption | -2.678 |
Pg | -2.667 |
rons | -2.633 |
Token | entertained |
Token ID | 34988 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
holiest | +0.406 |
saf | +0.374 |
cific | +0.368 |
Trivia | +0.364 |
Advantage | +0.362 |
Neg logit contributions | |
debates | -0.236 |
adoption | -0.229 |
birth | -0.229 |
Pg | -0.225 |
rons | -0.221 |
Token | ) |
Token ID | 8 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
holiest | +1.867 |
saf | +1.699 |
cific | +1.677 |
Trivia | +1.656 |
Advantage | +1.644 |
Neg logit contributions | |
debates | -1.271 |
adoption | -1.230 |
birth | -1.225 |
Pg | -1.212 |
rons | -1.202 |
Token | in |
Token ID | 287 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
debates | +0.506 |
adoption | +0.488 |
birth | +0.480 |
viewing | +0.472 |
amounts | +0.471 |
Neg logit contributions | |
holiest | -0.819 |
saf | -0.756 |
cific | -0.748 |
Trivia | -0.736 |
Advantage | -0.726 |
Token | his |
Token ID | 465 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
holiest | +1.222 |
saf | +1.116 |
cific | +1.102 |
Trivia | +1.090 |
Advantage | +1.078 |
Neg logit contributions | |
debates | -0.803 |
adoption | -0.774 |
birth | -0.769 |
Pg | -0.758 |
rons | -0.752 |
Token | infinite |
Token ID | 15541 |
Feature activation | -8.67e+00 |
Pos logit contributions | |
holiest | +0.465 |
saf | +0.428 |
cific | +0.424 |
Trivia | +0.420 |
Advantage | +0.413 |
Neg logit contributions | |
debates | -0.312 |
adoption | -0.301 |
birth | -0.295 |
amounts | -0.289 |
Pg | -0.289 |
Token | wisdom |
Token ID | 11501 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
debates | +4.315 |
amounts | +4.090 |
adoption | +4.032 |
viewing | +3.884 |
clam | +3.841 |
Neg logit contributions | |
holiest | -7.754 |
cific | -7.525 |
saf | -7.401 |
Trivia | -7.298 |
INGTON | -7.140 |
Token | , |
Token ID | 11 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
holiest | +1.763 |
saf | +1.608 |
cific | +1.593 |
Trivia | +1.571 |
Advantage | +1.559 |
Neg logit contributions | |
debates | -1.136 |
adoption | -1.096 |
birth | -1.087 |
Pg | -1.076 |
rons | -1.064 |
Token | tweeted |
Token ID | 10830 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
holiest | +0.084 |
saf | +0.076 |
cific | +0.076 |
Trivia | +0.074 |
Advantage | +0.074 |
Neg logit contributions | |
debates | -0.057 |
adoption | -0.055 |
birth | -0.054 |
amounts | -0.054 |
Pg | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
holiest | +5.575 |
saf | +5.043 |
cific | +5.006 |
Trivia | +4.952 |
Advantage | +4.909 |
Neg logit contributions | |
debates | -3.945 |
birth | -3.871 |
Pg | -3.870 |
adoption | -3.855 |
rons | -3.784 |
Token | following |
Token ID | 1708 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
holiest | +3.669 |
saf | +3.332 |
cific | +3.285 |
Trivia | +3.254 |
Advantage | +3.225 |
Neg logit contributions | |
debates | -2.570 |
adoption | -2.494 |
birth | -2.491 |
Pg | -2.469 |
rons | -2.443 |
Token | at |
Token ID | 379 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
holiest | +4.146 |
saf | +3.745 |
cific | +3.696 |
Trivia | +3.659 |
Advantage | +3.624 |
Neg logit contributions | |
debates | -3.092 |
birth | -3.013 |
Pg | -3.001 |
adoption | -2.998 |
rons | -2.953 |
Token | Ham |
Token ID | 4345 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
holiest | +1.613 |
saf | +1.473 |
cific | +1.454 |
Trivia | +1.439 |
Advantage | +1.422 |
Neg logit contributions | |
debates | -1.058 |
adoption | -1.026 |
birth | -1.019 |
Pg | -1.006 |
rons | -0.997 |
Token | ill |
Token ID | 359 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
holiest | +1.704 |
saf | +1.522 |
cific | +1.483 |
Trivia | +1.463 |
Advantage | +1.431 |
Neg logit contributions | |
debates | -2.247 |
adoption | -2.212 |
birth | -2.179 |
Pg | -2.162 |
rons | -2.150 |
Token | a |
Token ID | 257 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
holiest | +1.583 |
saf | +1.448 |
cific | +1.431 |
Trivia | +1.416 |
Advantage | +1.399 |
Neg logit contributions | |
debates | -1.065 |
adoption | -1.037 |
birth | -1.025 |
Pg | -1.009 |
rons | -1.002 |
Token | meltdown |
Token ID | 37824 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
holiest | +0.976 |
saf | +0.894 |
cific | +0.882 |
Trivia | +0.872 |
Advantage | +0.865 |
Neg logit contributions | |
debates | -0.695 |
adoption | -0.677 |
birth | -0.670 |
Pg | -0.664 |
rons | -0.656 |
Token | or |
Token ID | 393 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
holiest | +2.158 |
saf | +1.959 |
cific | +1.933 |
Trivia | +1.909 |
Advantage | +1.892 |
Neg logit contributions | |
debates | -1.627 |
adoption | -1.582 |
birth | -1.574 |
Pg | -1.557 |
rons | -1.546 |
Token | other |
Token ID | 584 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
holiest | +2.392 |
saf | +2.181 |
cific | +2.150 |
Trivia | +2.128 |
Advantage | +2.108 |
Neg logit contributions | |
debates | -1.630 |
adoption | -1.582 |
birth | -1.573 |
Pg | -1.557 |
rons | -1.542 |
Token | releases |
Token ID | 10050 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
holiest | +4.891 |
saf | +4.418 |
cific | +4.319 |
Trivia | +4.281 |
Advantage | +4.228 |
Neg logit contributions | |
debates | -3.644 |
birth | -3.565 |
Pg | -3.546 |
adoption | -3.515 |
rons | -3.508 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
holiest | +1.405 |
saf | +1.284 |
cific | +1.263 |
Trivia | +1.253 |
Advantage | +1.243 |
Neg logit contributions | |
debates | -0.975 |
adoption | -0.943 |
birth | -0.936 |
Pg | -0.928 |
rons | -0.923 |
Token | for |
Token ID | 329 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
holiest | +0.483 |
saf | +0.443 |
cific | +0.437 |
Trivia | +0.434 |
Advantage | +0.428 |
Neg logit contributions | |
debates | -0.314 |
adoption | -0.304 |
birth | -0.301 |
Pg | -0.297 |
amounts | -0.297 |
Token | instance |
Token ID | 4554 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
holiest | +0.246 |
saf | +0.224 |
cific | +0.223 |
Trivia | +0.221 |
Advantage | +0.216 |
Neg logit contributions | |
debates | -0.161 |
adoption | -0.158 |
birth | -0.154 |
amounts | -0.152 |
Pg | -0.152 |
Token | from |
Token ID | 422 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
holiest | +1.850 |
saf | +1.679 |
cific | +1.654 |
Trivia | +1.637 |
Advantage | +1.621 |
Neg logit contributions | |
debates | -1.413 |
adoption | -1.374 |
birth | -1.366 |
Pg | -1.353 |
rons | -1.341 |
Token | spent |
Token ID | 3377 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
holiest | +1.181 |
saf | +1.079 |
cific | +1.067 |
Trivia | +1.054 |
Advantage | +1.042 |
Neg logit contributions | |
debates | -0.791 |
adoption | -0.766 |
birth | -0.757 |
Pg | -0.748 |
amounts | -0.743 |
Token | fuel |
Token ID | 5252 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
debates | +1.667 |
adoption | +1.619 |
amounts | +1.603 |
rons | +1.569 |
birth | +1.563 |
Neg logit contributions | |
holiest | -3.305 |
cific | -3.077 |
saf | -3.053 |
Trivia | -3.001 |
INGTON | -2.954 |
Token | the |
Token ID | 262 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
debates | +2.628 |
adoption | +2.558 |
amounts | +2.472 |
birth | +2.452 |
Pg | +2.412 |
Neg logit contributions | |
holiest | -4.348 |
cific | -4.027 |
Trivia | -4.010 |
saf | -3.982 |
Advantage | -3.879 |
Token | beginning |
Token ID | 3726 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
debates | +1.571 |
adoption | +1.539 |
birth | +1.481 |
amounts | +1.460 |
viewing | +1.454 |
Neg logit contributions | |
holiest | -2.128 |
cific | -2.031 |
Trivia | -2.008 |
saf | -1.998 |
INGTON | -1.964 |
Token | of |
Token ID | 286 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
debates | +0.321 |
adoption | +0.311 |
birth | +0.309 |
Pg | +0.305 |
rons | +0.302 |
Neg logit contributions | |
holiest | -0.478 |
saf | -0.436 |
cific | -0.431 |
Trivia | -0.427 |
Advantage | -0.422 |
Token | the |
Token ID | 262 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
debates | +0.532 |
adoption | +0.513 |
birth | +0.500 |
amounts | +0.493 |
Pg | +0.492 |
Neg logit contributions | |
holiest | -0.857 |
saf | -0.783 |
cific | -0.781 |
Trivia | -0.779 |
Advantage | -0.763 |
Token | catastrophic |
Token ID | 22694 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
debates | +1.620 |
adoption | +1.577 |
amounts | +1.504 |
clam | +1.497 |
birth | +1.491 |
Neg logit contributions | |
holiest | -2.300 |
cific | -2.159 |
Trivia | -2.139 |
saf | -2.126 |
INGTON | -2.087 |
Token | phase |
Token ID | 7108 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
debates | +0.287 |
adoption | +0.278 |
birth | +0.271 |
amounts | +0.271 |
rons | +0.265 |
Neg logit contributions | |
holiest | -0.440 |
cific | -0.405 |
saf | -0.402 |
Trivia | -0.397 |
Advantage | -0.391 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
debates | +1.180 |
adoption | +1.150 |
birth | +1.129 |
amounts | +1.106 |
Pg | +1.101 |
Neg logit contributions | |
holiest | -1.871 |
saf | -1.695 |
cific | -1.693 |
Trivia | -1.676 |
Advantage | -1.645 |
Token | � |
Token ID | 447 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
holiest | +0.196 |
saf | +0.178 |
cific | +0.177 |
Trivia | +0.175 |
Advantage | +0.173 |
Neg logit contributions | |
debates | -0.138 |
adoption | -0.134 |
birth | -0.133 |
Pg | -0.131 |
amounts | -0.130 |
Token | � |
Token ID | 251 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
holiest | +2.489 |
saf | +2.281 |
cific | +2.251 |
Trivia | +2.229 |
Advantage | +2.209 |
Neg logit contributions | |
debates | -1.471 |
adoption | -1.423 |
birth | -1.416 |
Pg | -1.401 |
rons | -1.385 |
Token | Sebastian |
Token ID | 26190 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
holiest | +1.497 |
saf | +1.357 |
cific | +1.340 |
Trivia | +1.325 |
Advantage | +1.311 |
Neg logit contributions | |
debates | -1.159 |
adoption | -1.125 |
birth | -1.122 |
Pg | -1.110 |
rons | -1.096 |
Token | P |
Token ID | 350 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
debates | +0.796 |
birth | +0.763 |
adoption | +0.762 |
Pg | +0.753 |
rons | +0.753 |
Neg logit contributions | |
holiest | -1.278 |
saf | -1.164 |
cific | -1.154 |
Trivia | -1.138 |
INGTON | -1.122 |
Token | voluntary |
Token ID | 16171 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
debates | +1.503 |
adoption | +1.500 |
birth | +1.424 |
amounts | +1.415 |
viewing | +1.395 |
Neg logit contributions | |
holiest | -2.423 |
cific | -2.203 |
saf | -2.198 |
Trivia | -2.183 |
Advantage | -2.138 |
Token | filter |
Token ID | 8106 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
adoption | +2.493 |
debates | +2.476 |
viewing | +2.304 |
amounts | +2.259 |
breastfeeding | +2.242 |
Neg logit contributions | |
holiest | -5.985 |
cific | -5.533 |
Trivia | -5.485 |
saf | -5.441 |
Advantage | -5.373 |
Token | , |
Token ID | 11 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
adoption | +3.386 |
debates | +3.380 |
amounts | +3.142 |
birth | +3.106 |
viewing | +3.105 |
Neg logit contributions | |
holiest | -5.090 |
cific | -4.608 |
saf | -4.551 |
Trivia | -4.536 |
Advantage | -4.433 |
Token | stating |
Token ID | 12316 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
holiest | +0.806 |
saf | +0.743 |
cific | +0.734 |
Trivia | +0.730 |
Advantage | +0.722 |
Neg logit contributions | |
debates | -0.370 |
adoption | -0.357 |
birth | -0.352 |
Pg | -0.346 |
amounts | -0.341 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
holiest | +2.803 |
saf | +2.544 |
cific | +2.506 |
Trivia | +2.475 |
Advantage | +2.451 |
Neg logit contributions | |
debates | -2.177 |
birth | -2.121 |
Pg | -2.116 |
adoption | -2.111 |
rons | -2.086 |
Token | plan |
Token ID | 1410 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
holiest | +1.665 |
saf | +1.519 |
cific | +1.499 |
Trivia | +1.484 |
Advantage | +1.470 |
Neg logit contributions | |
debates | -1.091 |
adoption | -1.059 |
birth | -1.051 |
Pg | -1.041 |
rons | -1.029 |
Token | lacked |
Token ID | 19989 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
amounts | +4.033 |
debates | +4.005 |
adoption | +3.816 |
Pg | +3.718 |
reflected | +3.686 |
Neg logit contributions | |
holiest | -6.652 |
Trivia | -5.942 |
saf | -5.914 |
cific | -5.895 |
Advantage | -5.831 |
Token | transparency |
Token ID | 13902 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
holiest | +3.132 |
saf | +2.875 |
cific | +2.827 |
Trivia | +2.786 |
Advantage | +2.761 |
Neg logit contributions | |
debates | -2.104 |
birth | -2.052 |
Pg | -2.040 |
adoption | -2.029 |
rons | -2.022 |
Token | in |
Token ID | 287 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
holiest | +3.713 |
saf | +3.404 |
cific | +3.343 |
Trivia | +3.304 |
Advantage | +3.275 |
Neg logit contributions | |
debates | -2.713 |
birth | -2.655 |
Pg | -2.638 |
adoption | -2.632 |
rons | -2.594 |
Token | the |
Token ID | 262 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
holiest | +0.485 |
saf | +0.440 |
cific | +0.435 |
Trivia | +0.432 |
Advantage | +0.427 |
Neg logit contributions | |
debates | -0.345 |
adoption | -0.336 |
birth | -0.329 |
amounts | -0.325 |
Pg | -0.323 |
Token | selection |
Token ID | 6356 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
debates | +0.592 |
adoption | +0.581 |
amounts | +0.561 |
birth | +0.556 |
Pg | +0.548 |
Neg logit contributions | |
holiest | -0.834 |
saf | -0.754 |
cific | -0.752 |
Trivia | -0.750 |
Advantage | -0.738 |
Token | ILL |
Token ID | 8267 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
holiest | +1.979 |
saf | +1.795 |
cific | +1.771 |
Trivia | +1.748 |
Advantage | +1.731 |
Neg logit contributions | |
debates | -1.527 |
adoption | -1.486 |
birth | -1.479 |
Pg | -1.467 |
rons | -1.453 |
Token | NOT |
Token ID | 11929 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
debates | +1.552 |
adoption | +1.505 |
birth | +1.484 |
Pg | +1.474 |
amounts | +1.464 |
Neg logit contributions | |
holiest | -2.157 |
cific | -1.991 |
saf | -1.960 |
Trivia | -1.922 |
Advantage | -1.914 |
Token | DIV |
Token ID | 33569 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
debates | +1.236 |
birth | +1.201 |
adoption | +1.198 |
Pg | +1.197 |
rons | +1.174 |
Neg logit contributions | |
holiest | -2.073 |
cific | -1.899 |
saf | -1.894 |
Advantage | -1.852 |
Trivia | -1.838 |
Token | IDE |
Token ID | 14114 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
holiest | +1.736 |
saf | +1.396 |
cific | +1.345 |
Trivia | +1.339 |
Advantage | +1.303 |
Neg logit contributions | |
debates | -4.506 |
adoption | -4.419 |
birth | -4.419 |
rons | -4.391 |
Pg | -4.386 |
Token | . |
Token ID | 13 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
holiest | +0.345 |
saf | +0.314 |
cific | +0.310 |
Trivia | +0.305 |
Advantage | +0.303 |
Neg logit contributions | |
debates | -0.256 |
adoption | -0.250 |
birth | -0.248 |
Pg | -0.246 |
amounts | -0.243 |
Token | US |
Token ID | 2937 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
debates | +0.399 |
adoption | +0.389 |
Pg | +0.389 |
birth | +0.388 |
rons | +0.379 |
Neg logit contributions | |
holiest | -0.595 |
saf | -0.536 |
cific | -0.535 |
Trivia | -0.526 |
Advantage | -0.524 |
Token | due |
Token ID | 2233 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
debates | +0.887 |
adoption | +0.866 |
Pg | +0.851 |
birth | +0.846 |
amounts | +0.835 |
Neg logit contributions | |
holiest | -1.488 |
saf | -1.380 |
cific | -1.359 |
Trivia | -1.333 |
Advantage | -1.329 |
Token | to |
Token ID | 284 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
holiest | +0.302 |
saf | +0.278 |
cific | +0.275 |
Trivia | +0.272 |
Advantage | +0.270 |
Neg logit contributions | |
debates | -0.147 |
adoption | -0.142 |
birth | -0.141 |
Pg | -0.140 |
rons | -0.138 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
debates | +0.094 |
adoption | +0.092 |
amounts | +0.089 |
birth | +0.088 |
Pg | +0.088 |
Neg logit contributions | |
holiest | -0.131 |
saf | -0.120 |
cific | -0.118 |
Trivia | -0.117 |
Advantage | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
holiest | +1.396 |
saf | +1.272 |
cific | +1.258 |
Trivia | +1.243 |
Advantage | +1.234 |
Neg logit contributions | |
debates | -0.923 |
adoption | -0.894 |
birth | -0.880 |
Pg | -0.875 |
rons | -0.869 |
Token | illegal |
Token ID | 5293 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
holiest | +1.884 |
saf | +1.717 |
cific | +1.691 |
Trivia | +1.673 |
Advantage | +1.658 |
Neg logit contributions | |
debates | -1.337 |
adoption | -1.297 |
birth | -1.290 |
Pg | -1.278 |
rons | -1.265 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
debates | +0.523 |
adoption | +0.506 |
birth | +0.497 |
amounts | +0.491 |
rons | +0.491 |
Neg logit contributions | |
holiest | -0.763 |
saf | -0.700 |
cific | -0.686 |
INGTON | -0.673 |
Trivia | -0.672 |
Token | The |
Token ID | 383 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
debates | +0.764 |
adoption | +0.740 |
birth | +0.739 |
Pg | +0.738 |
amounts | +0.721 |
Neg logit contributions | |
holiest | -1.125 |
saf | -1.017 |
cific | -1.004 |
INGTON | -0.969 |
Trivia | -0.967 |
Token | game |
Token ID | 983 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
holiest | +2.092 |
saf | +1.909 |
cific | +1.882 |
Trivia | +1.863 |
Advantage | +1.846 |
Neg logit contributions | |
debates | -1.388 |
adoption | -1.346 |
birth | -1.341 |
Pg | -1.328 |
rons | -1.314 |
Token | also |
Token ID | 635 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
debates | +2.274 |
adoption | +2.177 |
amounts | +2.164 |
birth | +2.096 |
Pg | +2.072 |
Neg logit contributions | |
holiest | -3.646 |
saf | -3.357 |
cific | -3.303 |
INGTON | -3.266 |
Trivia | -3.233 |
Token | includes |
Token ID | 3407 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
debates | +0.068 |
adoption | +0.065 |
birth | +0.064 |
amounts | +0.064 |
Pg | +0.063 |
Neg logit contributions | |
holiest | -0.101 |
saf | -0.091 |
cific | -0.090 |
Trivia | -0.090 |
Advantage | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
debates | +0.427 |
adoption | +0.411 |
birth | +0.402 |
amounts | +0.401 |
viewing | +0.397 |
Neg logit contributions | |
holiest | -0.639 |
saf | -0.583 |
cific | -0.578 |
Trivia | -0.565 |
INGTON | -0.564 |
Token | character |
Token ID | 2095 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
debates | +1.758 |
adoption | +1.712 |
viewing | +1.688 |
birth | +1.674 |
bathing | +1.659 |
Neg logit contributions | |
holiest | -2.535 |
saf | -2.315 |
cific | -2.297 |
INGTON | -2.256 |
Trivia | -2.247 |
Token | creation |
Token ID | 6282 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
holiest | +2.798 |
saf | +2.542 |
cific | +2.512 |
Trivia | +2.489 |
Advantage | +2.469 |
Neg logit contributions | |
debates | -1.918 |
birth | -1.855 |
adoption | -1.854 |
Pg | -1.841 |
rons | -1.819 |
Token | system |
Token ID | 1080 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
holiest | +3.704 |
saf | +3.378 |
cific | +3.324 |
Trivia | +3.304 |
Advantage | +3.304 |
Neg logit contributions | |
debates | -2.222 |
birth | -2.174 |
adoption | -2.147 |
Pg | -2.140 |
rons | -2.119 |
Token | for |
Token ID | 329 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
debates | +1.287 |
adoption | +1.256 |
amounts | +1.216 |
viewing | +1.215 |
birth | +1.211 |
Neg logit contributions | |
holiest | -2.065 |
saf | -1.900 |
cific | -1.873 |
Trivia | -1.847 |
INGTON | -1.835 |
Token | making |
Token ID | 1642 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
debates | +0.053 |
adoption | +0.052 |
birth | +0.050 |
amounts | +0.050 |
viewing | +0.049 |
Neg logit contributions | |
holiest | -0.087 |
saf | -0.080 |
cific | -0.079 |
Trivia | -0.078 |
INGTON | -0.077 |
Token | I |
Token ID | 314 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
holiest | +0.142 |
saf | +0.129 |
cific | +0.127 |
Trivia | +0.126 |
Advantage | +0.125 |
Neg logit contributions | |
debates | -0.095 |
adoption | -0.092 |
birth | -0.091 |
Pg | -0.090 |
amounts | -0.089 |
Token | jab |
Token ID | 33896 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
holiest | +1.034 |
saf | +0.939 |
cific | +0.931 |
Trivia | +0.920 |
Advantage | +0.911 |
Neg logit contributions | |
debates | -0.677 |
adoption | -0.656 |
birth | -0.652 |
Pg | -0.644 |
rons | -0.642 |
Token | all |
Token ID | 477 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
holiest | +4.628 |
saf | +4.232 |
cific | +4.178 |
Trivia | +4.126 |
Advantage | +4.100 |
Neg logit contributions | |
debates | -2.971 |
adoption | -2.888 |
birth | -2.875 |
Pg | -2.855 |
rons | -2.795 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
debates | +0.509 |
adoption | +0.487 |
amounts | +0.481 |
Pg | +0.474 |
rons | +0.474 |
Neg logit contributions | |
holiest | -0.860 |
saf | -0.782 |
Trivia | -0.773 |
cific | -0.764 |
INGTON | -0.758 |
Token | time |
Token ID | 640 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
holiest | +0.874 |
saf | +0.793 |
cific | +0.779 |
Trivia | +0.777 |
Advantage | +0.764 |
Neg logit contributions | |
debates | -0.636 |
adoption | -0.611 |
birth | -0.604 |
amounts | -0.602 |
Pg | -0.601 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
holiest | +0.039 |
saf | +0.035 |
cific | +0.035 |
Trivia | +0.034 |
Advantage | +0.034 |
Neg logit contributions | |
debates | -0.025 |
adoption | -0.024 |
birth | -0.024 |
amounts | -0.023 |
Pg | -0.023 |
Token | It |
Token ID | 632 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
debates | +0.896 |
birth | +0.865 |
Pg | +0.862 |
adoption | +0.859 |
amounts | +0.841 |
Neg logit contributions | |
holiest | -1.295 |
saf | -1.163 |
cific | -1.147 |
Trivia | -1.123 |
INGTON | -1.109 |
Token | seems |
Token ID | 2331 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
debates | +1.957 |
amounts | +1.902 |
birth | +1.862 |
adoption | +1.840 |
Pg | +1.830 |
Neg logit contributions | |
holiest | -3.036 |
saf | -2.723 |
cific | -2.711 |
Trivia | -2.699 |
INGTON | -2.692 |
Token | I |
Token ID | 314 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
holiest | +2.268 |
saf | +2.072 |
cific | +2.043 |
Trivia | +2.023 |
Advantage | +2.004 |
Neg logit contributions | |
debates | -1.449 |
adoption | -1.404 |
birth | -1.399 |
Pg | -1.385 |
rons | -1.370 |
Token | � |
Token ID | 447 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
holiest | +2.814 |
saf | +2.565 |
cific | +2.528 |
Trivia | +2.502 |
Advantage | +2.478 |
Neg logit contributions | |
debates | -1.942 |
adoption | -1.885 |
birth | -1.876 |
Pg | -1.858 |
rons | -1.839 |
Token | � |
Token ID | 247 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
debates | +0.231 |
adoption | +0.224 |
birth | +0.223 |
Pg | +0.221 |
amounts | +0.216 |
Neg logit contributions | |
holiest | -0.410 |
saf | -0.376 |
cific | -0.372 |
Trivia | -0.367 |
Advantage | -0.363 |
Token | which |
Token ID | 543 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
holiest | +2.080 |
saf | +1.901 |
cific | +1.874 |
Trivia | +1.856 |
Advantage | +1.838 |
Neg logit contributions | |
debates | -1.332 |
adoption | -1.290 |
birth | -1.285 |
Pg | -1.271 |
rons | -1.258 |
Token | were |
Token ID | 547 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
holiest | +0.543 |
saf | +0.498 |
cific | +0.491 |
Trivia | +0.488 |
Advantage | +0.481 |
Neg logit contributions | |
debates | -0.316 |
adoption | -0.305 |
birth | -0.304 |
Pg | -0.299 |
amounts | -0.297 |
Token | discovered |
Token ID | 5071 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
holiest | +0.183 |
saf | +0.168 |
cific | +0.165 |
Trivia | +0.164 |
Advantage | +0.162 |
Neg logit contributions | |
debates | -0.123 |
adoption | -0.119 |
birth | -0.119 |
Pg | -0.117 |
rons | -0.116 |
Token | on |
Token ID | 319 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
holiest | +2.530 |
saf | +2.310 |
cific | +2.278 |
Trivia | +2.254 |
Advantage | +2.234 |
Neg logit contributions | |
debates | -1.664 |
adoption | -1.612 |
birth | -1.605 |
Pg | -1.587 |
rons | -1.572 |
Token | the |
Token ID | 262 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
debates | +0.098 |
adoption | +0.096 |
birth | +0.095 |
Pg | +0.093 |
amounts | +0.093 |
Neg logit contributions | |
holiest | -0.143 |
saf | -0.131 |
cific | -0.130 |
Trivia | -0.128 |
Advantage | -0.126 |
Token | infant |
Token ID | 11212 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
holiest | +1.462 |
saf | +1.348 |
cific | +1.331 |
Trivia | +1.316 |
Advantage | +1.295 |
Neg logit contributions | |
debates | -0.981 |
adoption | -0.953 |
birth | -0.941 |
Pg | -0.928 |
amounts | -0.922 |
Token | dated |
Token ID | 14567 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
birth | +5.458 |
adoption | +5.394 |
debates | +5.351 |
breastfeeding | +5.340 |
stret | +5.311 |
Neg logit contributions | |
holiest | -9.437 |
saf | -8.752 |
cific | -8.600 |
INGTON | -8.585 |
Trivia | -8.376 |
Token | three |
Token ID | 1115 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
holiest | +1.463 |
saf | +1.345 |
cific | +1.327 |
Trivia | +1.315 |
Advantage | +1.303 |
Neg logit contributions | |
debates | -0.786 |
adoption | -0.758 |
birth | -0.754 |
Pg | -0.746 |
rons | -0.736 |
Token | to |
Token ID | 284 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
holiest | +5.347 |
saf | +4.846 |
cific | +4.832 |
Trivia | +4.774 |
Advantage | +4.700 |
Neg logit contributions | |
debates | -2.618 |
birth | -2.528 |
adoption | -2.521 |
rons | -2.505 |
tumblr | -2.478 |
Token | four |
Token ID | 1440 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
holiest | +5.030 |
saf | +4.510 |
cific | +4.402 |
Trivia | +4.337 |
Advantage | +4.326 |
Neg logit contributions | |
debates | -4.991 |
Pg | -4.876 |
birth | -4.854 |
adoption | -4.845 |
rons | -4.798 |
Token | weeks |
Token ID | 2745 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
debates | +0.143 |
adoption | +0.138 |
birth | +0.136 |
Pg | +0.134 |
amounts | +0.131 |
Neg logit contributions | |
holiest | -0.321 |
saf | -0.299 |
cific | -0.294 |
Trivia | -0.292 |
Advantage | -0.290 |
Token | ys |
Token ID | 893 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
debates | +4.672 |
birth | +4.609 |
adoption | +4.504 |
rons | +4.495 |
tumblr | +4.490 |
Neg logit contributions | |
holiest | -4.820 |
Advantage | -4.060 |
saf | -4.028 |
Trivia | -4.026 |
cific | -4.009 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
debates | +1.976 |
birth | +1.929 |
adoption | +1.896 |
rons | +1.848 |
Pg | +1.843 |
Neg logit contributions | |
holiest | -2.457 |
saf | -2.241 |
cific | -2.215 |
Trivia | -2.160 |
INGTON | -2.149 |
Token | way |
Token ID | 1014 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
debates | +1.120 |
birth | +1.080 |
adoption | +1.066 |
Pg | +1.058 |
rons | +1.048 |
Neg logit contributions | |
holiest | -1.427 |
saf | -1.308 |
cific | -1.276 |
Trivia | -1.250 |
INGTON | -1.249 |
Token | Dream |
Token ID | 7610 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
debates | +0.141 |
adoption | +0.137 |
birth | +0.136 |
Pg | +0.133 |
rons | +0.133 |
Neg logit contributions | |
holiest | -0.184 |
saf | -0.167 |
cific | -0.165 |
Trivia | -0.162 |
INGTON | -0.159 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
debates | +2.148 |
birth | +2.121 |
adoption | +2.053 |
rons | +2.017 |
amounts | +2.009 |
Neg logit contributions | |
holiest | -2.801 |
cific | -2.515 |
saf | -2.488 |
INGTON | -2.420 |
Trivia | -2.391 |
Token | Ant |
Token ID | 13217 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
debates | +0.806 |
birth | +0.805 |
Pg | +0.798 |
adoption | +0.781 |
rons | +0.764 |
Neg logit contributions | |
holiest | -1.044 |
cific | -0.931 |
saf | -0.924 |
Advantage | -0.903 |
INGTON | -0.887 |
Token | @ |
Token ID | 2488 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
debates | +6.420 |
rons | +6.175 |
birth | +6.116 |
Weiner | +6.076 |
adoption | +5.978 |
Neg logit contributions | |
holiest | -7.713 |
cific | -6.831 |
INGTON | -6.762 |
saf | -6.735 |
Trivia | -6.484 |
Token | Casino |
Token ID | 32802 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
debates | +0.820 |
birth | +0.795 |
adoption | +0.787 |
Pg | +0.781 |
rons | +0.771 |
Neg logit contributions | |
holiest | -1.149 |
saf | -1.037 |
cific | -1.030 |
Trivia | -1.012 |
INGTON | -0.996 |
Token | Recap |
Token ID | 46585 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
holiest | +2.568 |
saf | +2.324 |
cific | +2.284 |
Trivia | +2.266 |
Advantage | +2.244 |
Neg logit contributions | |
debates | -2.107 |
adoption | -2.056 |
birth | -2.042 |
Pg | -2.028 |
rons | -2.008 |
Token | - |
Token ID | 12 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
debates | +0.009 |
birth | +0.008 |
adoption | +0.008 |
Pg | +0.008 |
rons | +0.008 |
Neg logit contributions | |
holiest | -0.011 |
saf | -0.010 |
cific | -0.009 |
Trivia | -0.009 |
Advantage | -0.009 |
Token | Sports |
Token ID | 18153 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
debates | +1.056 |
birth | +1.055 |
Pg | +1.048 |
adoption | +1.020 |
tumblr | +0.998 |
Neg logit contributions | |
holiest | -1.372 |
cific | -1.223 |
saf | -1.213 |
Advantage | -1.183 |
INGTON | -1.161 |
Token | pornography |
Token ID | 18384 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
birth | +2.288 |
viewing | +2.269 |
debates | +2.249 |
adoption | +2.199 |
breastfeeding | +2.060 |
Neg logit contributions | |
holiest | -8.053 |
cific | -7.485 |
saf | -7.385 |
INGTON | -7.260 |
Advantage | -7.249 |
Token | or |
Token ID | 393 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
debates | +0.148 |
adoption | +0.143 |
birth | +0.141 |
Pg | +0.139 |
rons | +0.138 |
Neg logit contributions | |
holiest | -0.213 |
saf | -0.196 |
cific | -0.194 |
Trivia | -0.190 |
Advantage | -0.189 |
Token | spam |
Token ID | 18084 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
debates | +0.601 |
adoption | +0.584 |
birth | +0.570 |
amounts | +0.563 |
Pg | +0.560 |
Neg logit contributions | |
holiest | -0.982 |
saf | -0.908 |
cific | -0.899 |
Trivia | -0.886 |
Advantage | -0.878 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
holiest | +1.871 |
saf | +1.687 |
cific | +1.660 |
Trivia | +1.640 |
Advantage | +1.624 |
Neg logit contributions | |
debates | -1.622 |
adoption | -1.579 |
birth | -1.571 |
Pg | -1.558 |
rons | -1.545 |
Token | The |
Token ID | 383 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
debates | +0.909 |
adoption | +0.876 |
birth | +0.874 |
Pg | +0.869 |
rons | +0.854 |
Neg logit contributions | |
holiest | -1.364 |
saf | -1.234 |
cific | -1.229 |
Trivia | -1.207 |
INGTON | -1.183 |
Token | change |
Token ID | 1487 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
holiest | +1.739 |
saf | +1.583 |
cific | +1.555 |
Trivia | +1.537 |
Advantage | +1.529 |
Neg logit contributions | |
debates | -1.218 |
birth | -1.187 |
adoption | -1.182 |
Pg | -1.177 |
rons | -1.162 |
Token | comes |
Token ID | 2058 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
amounts | +5.456 |
debates | +5.353 |
adoption | +5.191 |
reflected | +5.089 |
birth | +4.953 |
Neg logit contributions | |
holiest | -10.323 |
Trivia | -9.483 |
cific | -9.441 |
saf | -9.210 |
INGTON | -9.208 |
Token | about |
Token ID | 546 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
holiest | +1.317 |
saf | +1.198 |
cific | +1.177 |
Trivia | +1.168 |
Advantage | +1.155 |
Neg logit contributions | |
debates | -0.986 |
adoption | -0.955 |
birth | -0.943 |
Pg | -0.934 |
rons | -0.927 |
Token | six |
Token ID | 2237 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
holiest | +2.691 |
saf | +2.440 |
cific | +2.404 |
Trivia | +2.378 |
Advantage | +2.354 |
Neg logit contributions | |
debates | -2.073 |
adoption | -2.015 |
birth | -2.006 |
Pg | -1.988 |
rons | -1.969 |
Token | months |
Token ID | 1933 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
holiest | +3.395 |
saf | +3.116 |
cific | +3.081 |
Trivia | +3.058 |
Advantage | +3.027 |
Neg logit contributions | |
debates | -1.742 |
birth | -1.685 |
adoption | -1.683 |
Pg | -1.663 |
rons | -1.646 |
Token | after |
Token ID | 706 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
holiest | +2.822 |
saf | +2.499 |
cific | +2.459 |
Trivia | +2.424 |
Advantage | +2.395 |
Neg logit contributions | |
debates | -3.229 |
adoption | -3.157 |
birth | -3.152 |
Pg | -3.132 |
rons | -3.104 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
holiest | +1.740 |
saf | +1.583 |
cific | +1.557 |
Trivia | +1.540 |
Advantage | +1.527 |
Neg logit contributions | |
debates | -1.507 |
adoption | -1.465 |
birth | -1.455 |
Pg | -1.446 |
rons | -1.435 |
Token |
|
Token ID | 198 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
debates | +1.755 |
adoption | +1.727 |
birth | +1.717 |
Pg | +1.673 |
amounts | +1.655 |
Neg logit contributions | |
holiest | -2.696 |
saf | -2.422 |
cific | -2.408 |
Trivia | -2.338 |
INGTON | -2.317 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
holiest | +0.234 |
saf | +0.211 |
cific | +0.209 |
Trivia | +0.206 |
Advantage | +0.204 |
Neg logit contributions | |
debates | -0.174 |
birth | -0.169 |
adoption | -0.169 |
Pg | -0.168 |
rons | -0.165 |
Token | 2014 |
Token ID | 4967 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
birth | +0.862 |
Pg | +0.857 |
debates | +0.847 |
adoption | +0.841 |
tumblr | +0.830 |
Neg logit contributions | |
holiest | -0.864 |
cific | -0.752 |
saf | -0.736 |
Advantage | -0.729 |
INGTON | -0.709 |
Token | Don |
Token ID | 2094 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
debates | +1.117 |
adoption | +1.063 |
birth | +1.052 |
amounts | +1.047 |
rons | +1.040 |
Neg logit contributions | |
holiest | -1.587 |
saf | -1.434 |
cific | -1.426 |
Trivia | -1.389 |
INGTON | -1.379 |
Token | C |
Token ID | 327 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
debates | +0.810 |
birth | +0.784 |
adoption | +0.778 |
Pg | +0.771 |
rons | +0.762 |
Neg logit contributions | |
holiest | -1.477 |
saf | -1.350 |
cific | -1.328 |
Trivia | -1.314 |
Advantage | -1.302 |
Token | head |
Token ID | 2256 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
birth | +4.499 |
croft | +4.258 |
Pg | +4.065 |
tumblr | +4.057 |
debates | +3.997 |
Neg logit contributions | |
holiest | -8.319 |
Advantage | -7.359 |
INGTON | -7.206 |
cific | -7.139 |
Trivia | -7.083 |
Token | le |
Token ID | 293 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
debates | +1.079 |
birth | +1.065 |
Pg | +1.049 |
adoption | +1.043 |
rons | +1.026 |
Neg logit contributions | |
holiest | -1.981 |
saf | -1.786 |
cific | -1.775 |
Trivia | -1.761 |
Advantage | -1.760 |
Token |
|
Token ID | 198 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
debates | +1.029 |
adoption | +1.005 |
birth | +0.999 |
Pg | +0.975 |
rons | +0.972 |
Neg logit contributions | |
holiest | -1.428 |
saf | -1.290 |
cific | -1.282 |
Trivia | -1.251 |
Advantage | -1.237 |
Token |
|
Token ID | 198 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
debates | +0.192 |
birth | +0.188 |
adoption | +0.186 |
Pg | +0.186 |
rons | +0.182 |
Neg logit contributions | |
holiest | -0.271 |
saf | -0.243 |
cific | -0.241 |
Trivia | -0.237 |
Advantage | -0.235 |
Token | 2014 |
Token ID | 4967 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
birth | +0.478 |
Pg | +0.475 |
debates | +0.474 |
adoption | +0.469 |
tumblr | +0.460 |
Neg logit contributions | |
holiest | -0.467 |
cific | -0.406 |
saf | -0.400 |
Advantage | -0.393 |
INGTON | -0.384 |
Token | no |
Token ID | 645 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
holiest | +3.697 |
saf | +3.365 |
cific | +3.308 |
Trivia | +3.268 |
Advantage | +3.249 |
Neg logit contributions | |
debates | -2.530 |
birth | -2.469 |
Pg | -2.456 |
adoption | -2.444 |
rons | -2.427 |
Token | distinction |
Token ID | 12941 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
holiest | +1.508 |
saf | +1.385 |
cific | +1.367 |
Trivia | +1.355 |
Advantage | +1.343 |
Neg logit contributions | |
debates | -0.829 |
adoption | -0.802 |
birth | -0.793 |
Pg | -0.784 |
rons | -0.776 |
Token | between |
Token ID | 1022 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
holiest | +0.893 |
saf | +0.798 |
cific | +0.786 |
Trivia | +0.780 |
Advantage | +0.771 |
Neg logit contributions | |
debates | -0.761 |
adoption | -0.738 |
birth | -0.734 |
amounts | -0.727 |
Pg | -0.722 |
Token | youth |
Token ID | 6205 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
holiest | +1.055 |
saf | +0.968 |
cific | +0.957 |
Trivia | +0.947 |
Advantage | +0.936 |
Neg logit contributions | |
debates | -0.600 |
adoption | -0.582 |
birth | -0.572 |
Pg | -0.565 |
amounts | -0.561 |
Token | and |
Token ID | 290 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
debates | +2.109 |
adoption | +2.063 |
amounts | +2.007 |
viewing | +1.972 |
rons | +1.963 |
Neg logit contributions | |
holiest | -3.551 |
saf | -3.213 |
cific | -3.192 |
Trivia | -3.150 |
INGTON | -3.113 |
Token | adult |
Token ID | 4044 |
Feature activation | -9.27e+00 |
Pos logit contributions | |
holiest | +0.923 |
saf | +0.856 |
cific | +0.846 |
Trivia | +0.838 |
Advantage | +0.830 |
Neg logit contributions | |
debates | -0.357 |
adoption | -0.343 |
birth | -0.336 |
Pg | -0.330 |
rons | -0.327 |
Token | punishment |
Token ID | 9837 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
debates | +4.531 |
adoption | +4.427 |
amounts | +4.329 |
viewing | +4.192 |
cort | +4.049 |
Neg logit contributions | |
holiest | -8.668 |
saf | -8.028 |
cific | -7.968 |
INGTON | -7.869 |
Trivia | -7.786 |
Token | or |
Token ID | 393 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
holiest | +0.703 |
saf | +0.642 |
cific | +0.630 |
Trivia | +0.624 |
Advantage | +0.617 |
Neg logit contributions | |
debates | -0.476 |
adoption | -0.460 |
birth | -0.452 |
amounts | -0.452 |
Pg | -0.448 |
Token | between |
Token ID | 1022 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
holiest | +1.412 |
saf | +1.297 |
cific | +1.281 |
Trivia | +1.269 |
Advantage | +1.258 |
Neg logit contributions | |
debates | -0.760 |
adoption | -0.735 |
birth | -0.728 |
Pg | -0.719 |
rons | -0.711 |
Token | consecutive |
Token ID | 12785 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
holiest | +0.683 |
saf | +0.629 |
cific | +0.622 |
Trivia | +0.616 |
Advantage | +0.608 |
Neg logit contributions | |
debates | -0.365 |
adoption | -0.353 |
birth | -0.346 |
Pg | -0.341 |
amounts | -0.340 |
Token | and |
Token ID | 290 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
debates | +0.076 |
adoption | +0.073 |
birth | +0.072 |
amounts | +0.071 |
Pg | +0.070 |
Neg logit contributions | |
holiest | -0.157 |
saf | -0.145 |
cific | -0.144 |
Trivia | -0.143 |
Advantage | -0.141 |