Token | . |
Token ID | 13 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
eming | +1.984 |
atown | +1.498 |
toggle | +1.457 |
texting | +1.431 |
slowing | +1.418 |
Neg logit contributions | |
ought | -1.386 |
rightly | -1.367 |
rightfully | -1.278 |
BACK | -1.266 |
Parables | -1.252 |
Token | � |
Token ID | 564 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
rightly | +2.561 |
ought | +2.551 |
rightfully | +2.398 |
BACK | +2.362 |
Parables | +2.339 |
Neg logit contributions | |
eming | -3.079 |
atown | -2.255 |
toggle | -2.213 |
texting | -2.126 |
slowing | -2.095 |
Token | � |
Token ID | 250 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ought | +1.260 |
rightly | +1.257 |
rightfully | +1.190 |
BACK | +1.173 |
Parables | +1.157 |
Neg logit contributions | |
eming | -1.152 |
atown | -0.794 |
toggle | -0.784 |
texting | -0.740 |
slowing | -0.727 |
Token | There |
Token ID | 1858 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ought | +2.162 |
rightly | +2.155 |
rightfully | +1.989 |
BACK | +1.953 |
Parables | +1.906 |
Neg logit contributions | |
eming | -3.742 |
atown | -2.878 |
toggle | -2.846 |
texting | -2.744 |
slowing | -2.708 |
Token | are |
Token ID | 389 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
ought | +0.863 |
rightly | +0.859 |
rightfully | +0.800 |
BACK | +0.790 |
Parables | +0.781 |
Neg logit contributions | |
eming | -1.224 |
atown | -0.916 |
toggle | -0.906 |
texting | -0.869 |
slowing | -0.860 |
Token | far |
Token ID | 1290 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
rightly | +4.243 |
ought | +4.121 |
rightfully | +3.942 |
BACK | +3.767 |
suprem | +3.613 |
Neg logit contributions | |
eming | -6.402 |
atown | -4.858 |
toggle | -4.795 |
hyde | -4.551 |
alert | -4.491 |
Token | too |
Token ID | 1165 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
rightly | +8.243 |
ought | +7.724 |
rightfully | +7.249 |
BACK | +6.776 |
iors | +6.638 |
Neg logit contributions | |
eming | -17.299 |
atown | -13.695 |
toggle | -13.455 |
hyde | -13.069 |
Appears | -12.761 |
Token | many |
Token ID | 867 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
rightly | +4.599 |
ought | +4.406 |
rightfully | +4.104 |
BACK | +3.832 |
suprem | +3.655 |
Neg logit contributions | |
eming | -11.203 |
atown | -8.948 |
toggle | -8.853 |
hyde | -8.599 |
alert | -8.455 |
Token | questions |
Token ID | 2683 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
rightly | +2.599 |
ought | +2.573 |
rightfully | +2.422 |
BACK | +2.356 |
Parables | +2.295 |
Neg logit contributions | |
eming | -3.653 |
atown | -2.752 |
toggle | -2.689 |
texting | -2.549 |
hyde | -2.548 |
Token | left |
Token ID | 1364 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
rightly | +7.352 |
ought | +7.036 |
rightfully | +6.852 |
BACK | +6.362 |
suprem | +6.202 |
Neg logit contributions | |
eming | -9.030 |
toggle | -6.822 |
atown | -6.783 |
hyde | -6.320 |
Appears | -6.236 |
Token | unanswered |
Token ID | 34001 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
rightly | +2.908 |
ought | +2.885 |
rightfully | +2.706 |
BACK | +2.586 |
suprem | +2.523 |
Neg logit contributions | |
eming | -4.304 |
atown | -3.255 |
toggle | -3.240 |
texting | -3.053 |
hyde | -3.046 |
Token | , |
Token ID | 11 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
eming | +2.631 |
atown | +1.905 |
toggle | +1.892 |
texting | +1.862 |
slowing | +1.845 |
Neg logit contributions | |
ought | -2.126 |
rightly | -2.070 |
BACK | -1.975 |
rightfully | -1.939 |
Parables | -1.933 |
Token | Dallas |
Token ID | 8533 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
eming | +2.276 |
atown | +1.672 |
toggle | +1.656 |
texting | +1.622 |
slowing | +1.606 |
Neg logit contributions | |
ought | -1.765 |
rightly | -1.720 |
BACK | -1.630 |
rightfully | -1.608 |
Parables | -1.589 |
Token | has |
Token ID | 468 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
rightly | +2.341 |
ought | +2.321 |
rightfully | +2.180 |
BACK | +2.093 |
Parables | +2.037 |
Neg logit contributions | |
eming | -3.538 |
atown | -2.666 |
toggle | -2.648 |
texting | -2.515 |
hyde | -2.509 |
Token | to |
Token ID | 284 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ought | +1.119 |
rightly | +1.111 |
rightfully | +1.027 |
BACK | +1.016 |
Parables | +0.995 |
Neg logit contributions | |
eming | -1.873 |
atown | -1.429 |
toggle | -1.416 |
texting | -1.368 |
slowing | -1.353 |
Token | decide |
Token ID | 5409 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
eming | +2.114 |
atown | +1.557 |
toggle | +1.538 |
texting | +1.491 |
slowing | +1.489 |
Neg logit contributions | |
ought | -1.612 |
rightly | -1.560 |
BACK | -1.490 |
Parables | -1.459 |
rightfully | -1.453 |
Token | almost |
Token ID | 2048 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ought | +0.934 |
rightly | +0.931 |
rightfully | +0.866 |
BACK | +0.849 |
Parables | +0.834 |
Neg logit contributions | |
eming | -1.409 |
atown | -1.061 |
toggle | -1.052 |
texting | -1.010 |
slowing | -0.997 |
Token | immediately |
Token ID | 3393 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
rightly | +9.268 |
rightfully | +8.557 |
ought | +8.260 |
suprem | +7.490 |
fut | +7.463 |
Neg logit contributions | |
eming | -16.362 |
toggle | -12.699 |
atown | -12.546 |
hyde | -12.344 |
roma | -12.038 |
Token | into |
Token ID | 656 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
rightly | +4.275 |
ought | +4.163 |
rightfully | +3.946 |
BACK | +3.576 |
suprem | +3.564 |
Neg logit contributions | |
eming | -7.659 |
atown | -5.964 |
toggle | -5.850 |
hyde | -5.682 |
roma | -5.527 |
Token | the |
Token ID | 262 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
ought | +0.068 |
rightly | +0.067 |
rightfully | +0.063 |
BACK | +0.062 |
Parables | +0.061 |
Neg logit contributions | |
eming | -0.085 |
atown | -0.062 |
toggle | -0.062 |
texting | -0.060 |
slowing | -0.059 |
Token | offseason |
Token ID | 16349 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
rightly | +3.099 |
ought | +3.072 |
rightfully | +2.899 |
BACK | +2.804 |
Parables | +2.752 |
Neg logit contributions | |
eming | -4.401 |
atown | -3.316 |
toggle | -3.245 |
hyde | -3.106 |
alert | -3.073 |
Token | whether |
Token ID | 1771 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
rightly | +4.283 |
ought | +4.105 |
rightfully | +3.941 |
suprem | +3.583 |
BACK | +3.574 |
Neg logit contributions | |
eming | -7.806 |
atown | -6.055 |
toggle | -5.991 |
hyde | -5.760 |
alert | -5.621 |
Token | Israel |
Token ID | 2692 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
eming | +1.854 |
atown | +1.364 |
toggle | +1.364 |
texting | +1.317 |
slowing | +1.301 |
Neg logit contributions | |
ought | -1.380 |
rightly | -1.351 |
BACK | -1.272 |
rightfully | -1.265 |
Parables | -1.247 |
Token | on |
Token ID | 319 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
eming | +1.539 |
atown | +1.157 |
toggle | +1.145 |
texting | +1.114 |
slowing | +1.102 |
Neg logit contributions | |
ought | -1.010 |
rightly | -0.985 |
rightfully | -0.923 |
BACK | -0.921 |
Parables | -0.907 |
Token | what |
Token ID | 644 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
rightly | +3.149 |
ought | +3.136 |
rightfully | +2.916 |
BACK | +2.832 |
Parables | +2.786 |
Neg logit contributions | |
eming | -4.445 |
atown | -3.372 |
toggle | -3.306 |
hyde | -3.138 |
alert | -3.103 |
Token | they |
Token ID | 484 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
rightly | +5.262 |
ought | +5.181 |
rightfully | +4.883 |
BACK | +4.546 |
suprem | +4.523 |
Neg logit contributions | |
eming | -7.800 |
atown | -5.946 |
toggle | -5.788 |
hyde | -5.648 |
alert | -5.507 |
Token | can |
Token ID | 460 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
rightly | +2.555 |
ought | +2.516 |
rightfully | +2.344 |
BACK | +2.181 |
Parables | +2.157 |
Neg logit contributions | |
eming | -4.439 |
atown | -3.432 |
toggle | -3.402 |
hyde | -3.267 |
texting | -3.202 |
Token | and |
Token ID | 290 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
rightly | +1.514 |
ought | +1.507 |
rightfully | +1.417 |
BACK | +1.373 |
Parables | +1.351 |
Neg logit contributions | |
eming | -1.901 |
atown | -1.402 |
toggle | -1.391 |
texting | -1.319 |
hyde | -1.312 |
Token | cannot |
Token ID | 2314 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
rightly | +6.298 |
ought | +5.858 |
rightfully | +5.464 |
suprem | +4.155 |
learnt | +4.120 |
Neg logit contributions | |
eming | -18.446 |
atown | -15.613 |
toggle | -15.256 |
hyde | -15.196 |
alert | -14.722 |
Token | do |
Token ID | 466 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
rightly | +2.614 |
ought | +2.574 |
rightfully | +2.446 |
BACK | +2.333 |
Parables | +2.297 |
Neg logit contributions | |
eming | -3.238 |
atown | -2.408 |
toggle | -2.376 |
hyde | -2.259 |
texting | -2.233 |
Token | than |
Token ID | 621 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
eming | +0.209 |
atown | +0.156 |
toggle | +0.154 |
texting | +0.149 |
slowing | +0.147 |
Neg logit contributions | |
ought | -0.148 |
rightly | -0.147 |
rightfully | -0.137 |
BACK | -0.136 |
Parables | -0.134 |
Token | America |
Token ID | 2253 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
rightly | +3.129 |
ought | +3.097 |
rightfully | +2.878 |
BACK | +2.773 |
Parables | +2.761 |
Neg logit contributions | |
eming | -4.845 |
atown | -3.695 |
toggle | -3.622 |
hyde | -3.460 |
texting | -3.438 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ought | +0.647 |
rightly | +0.644 |
rightfully | +0.604 |
BACK | +0.593 |
Parables | +0.584 |
Neg logit contributions | |
eming | -0.831 |
atown | -0.612 |
toggle | -0.606 |
texting | -0.580 |
slowing | -0.572 |
Token | Butler |
Token ID | 17389 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
eming | +2.743 |
atown | +2.006 |
texting | +1.961 |
toggle | +1.953 |
slowing | +1.919 |
Neg logit contributions | |
ought | -2.221 |
rightly | -2.153 |
BACK | -2.067 |
Parables | -2.039 |
rightfully | -2.020 |
Token | write |
Token ID | 3551 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
rightly | +2.163 |
ought | +2.153 |
rightfully | +2.018 |
BACK | +1.968 |
Parables | +1.934 |
Neg logit contributions | |
eming | -3.059 |
atown | -2.284 |
toggle | -2.258 |
texting | -2.153 |
hyde | -2.126 |
Token | his |
Token ID | 465 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ought | +1.757 |
rightly | +1.753 |
rightfully | +1.634 |
BACK | +1.603 |
Parables | +1.576 |
Neg logit contributions | |
eming | -2.493 |
atown | -1.863 |
toggle | -1.845 |
texting | -1.766 |
hyde | -1.743 |
Token | r |
Token ID | 374 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
rightly | +5.300 |
ought | +5.194 |
rightfully | +4.980 |
Parables | +4.797 |
BACK | +4.767 |
Neg logit contributions | |
eming | -8.165 |
atown | -6.222 |
toggle | -6.150 |
hyde | -6.064 |
screenings | -5.880 |
Token | ags |
Token ID | 3775 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
eming | +0.688 |
toggle | +0.494 |
atown | +0.490 |
texting | +0.466 |
slowing | +0.460 |
Neg logit contributions | |
rightly | -0.549 |
ought | -0.536 |
rightfully | -0.517 |
BACK | -0.510 |
Parables | -0.498 |
Token | - |
Token ID | 12 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ought | +3.845 |
rightly | +3.817 |
rightfully | +3.522 |
BACK | +3.364 |
Parables | +3.308 |
Neg logit contributions | |
eming | -6.955 |
atown | -5.405 |
toggle | -5.376 |
hyde | -5.192 |
texting | -5.136 |
Token | to |
Token ID | 1462 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ought | +5.131 |
rightly | +4.716 |
rightfully | +4.246 |
fortune | +3.586 |
BACK | +3.510 |
Neg logit contributions | |
eming | -18.196 |
Archdemon | -15.877 |
screenings | -15.416 |
atown | -15.251 |
Weird | -14.831 |
Token | - |
Token ID | 12 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ought | +2.878 |
rightly | +2.864 |
rightfully | +2.620 |
BACK | +2.517 |
Vice | +2.353 |
Neg logit contributions | |
eming | -5.998 |
atown | -4.668 |
toggle | -4.622 |
hyde | -4.495 |
Archdemon | -4.451 |
Token | ric |
Token ID | 1173 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ought | +7.322 |
rightly | +6.925 |
rightfully | +6.526 |
BACK | +6.313 |
Vice | +6.109 |
Neg logit contributions | |
eming | -12.224 |
Archdemon | -9.325 |
atown | -9.245 |
screenings | -8.978 |
texting | -8.912 |
Token | hes |
Token ID | 956 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
eming | +5.357 |
toggle | +3.297 |
atown | +3.217 |
alert | +2.967 |
screenings | +2.956 |
Neg logit contributions | |
rightly | -8.999 |
ought | -8.969 |
BACK | -8.633 |
suprem | -8.524 |
rightfully | -8.508 |
Token | story |
Token ID | 1621 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ought | +0.805 |
rightly | +0.802 |
rightfully | +0.750 |
BACK | +0.738 |
Parables | +0.726 |
Neg logit contributions | |
eming | -1.014 |
atown | -0.743 |
toggle | -0.736 |
texting | -0.707 |
slowing | -0.696 |
Token | to |
Token ID | 284 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ought | +1.387 |
rightly | +1.382 |
rightfully | +1.269 |
BACK | +1.241 |
Parables | +1.215 |
Neg logit contributions | |
eming | -2.642 |
atown | -2.044 |
toggle | -2.028 |
texting | -1.957 |
slowing | -1.935 |
Token | learn |
Token ID | 2193 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
rightly | +0.782 |
ought | +0.778 |
rightfully | +0.732 |
BACK | +0.714 |
Parables | +0.701 |
Neg logit contributions | |
eming | -1.011 |
atown | -0.747 |
toggle | -0.738 |
texting | -0.701 |
hyde | -0.699 |
Token | all |
Token ID | 477 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
ought | +0.042 |
rightly | +0.041 |
rightfully | +0.039 |
BACK | +0.038 |
Parables | +0.038 |
Neg logit contributions | |
eming | -0.052 |
atown | -0.038 |
toggle | -0.038 |
texting | -0.037 |
slowing | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
rightly | +4.245 |
ought | +4.232 |
rightfully | +3.986 |
BACK | +3.903 |
Parables | +3.809 |
Neg logit contributions | |
eming | -4.925 |
atown | -3.598 |
toggle | -3.579 |
hyde | -3.387 |
texting | -3.335 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ought | +1.844 |
rightly | +1.843 |
rightfully | +1.716 |
BACK | +1.683 |
Parables | +1.656 |
Neg logit contributions | |
eming | -2.598 |
atown | -1.943 |
toggle | -1.923 |
texting | -1.832 |
hyde | -1.820 |
Token | ins |
Token ID | 1035 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
rightly | +1.868 |
ought | +1.860 |
rightfully | +1.735 |
BACK | +1.697 |
Parables | +1.669 |
Neg logit contributions | |
eming | -2.801 |
atown | -2.121 |
toggle | -2.091 |
hyde | -1.992 |
texting | -1.990 |
Token | and |
Token ID | 290 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ought | +8.343 |
rightly | +7.947 |
rightfully | +7.299 |
BACK | +7.294 |
Parables | +6.944 |
Neg logit contributions | |
eming | -15.294 |
atown | -11.996 |
toggle | -11.940 |
hyde | -11.600 |
Archdemon | -11.358 |
Token | outs |
Token ID | 12198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
rightly | +3.592 |
ought | +3.306 |
rightfully | +2.942 |
BACK | +2.483 |
tyre | +2.459 |
Neg logit contributions | |
eming | -18.225 |
Archdemon | -14.651 |
atown | -14.619 |
toggle | -14.444 |
alert | -14.337 |
Token | of |
Token ID | 286 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
rightly | +4.557 |
ought | +4.488 |
rightfully | +4.179 |
BACK | +4.013 |
suprem | +3.780 |
Neg logit contributions | |
eming | -8.610 |
toggle | -6.808 |
atown | -6.786 |
hyde | -6.426 |
alert | -6.371 |
Token | running |
Token ID | 2491 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
rightly | +2.299 |
ought | +2.295 |
rightfully | +2.148 |
BACK | +2.109 |
Parables | +2.071 |
Neg logit contributions | |
eming | -2.981 |
atown | -2.204 |
toggle | -2.180 |
texting | -2.057 |
hyde | -2.054 |
Token | a |
Token ID | 257 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
rightly | +2.789 |
ought | +2.761 |
rightfully | +2.575 |
BACK | +2.495 |
Parables | +2.448 |
Neg logit contributions | |
eming | -4.693 |
atown | -3.597 |
toggle | -3.557 |
hyde | -3.384 |
texting | -3.370 |
Token | 's |
Token ID | 338 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ought | +1.000 |
rightly | +0.994 |
rightfully | +0.934 |
BACK | +0.921 |
Parables | +0.908 |
Neg logit contributions | |
eming | -1.222 |
atown | -0.894 |
toggle | -0.884 |
texting | -0.844 |
slowing | -0.833 |
Token | science |
Token ID | 3783 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
rightly | +1.494 |
ought | +1.489 |
rightfully | +1.394 |
BACK | +1.359 |
Parables | +1.332 |
Neg logit contributions | |
eming | -1.944 |
atown | -1.445 |
toggle | -1.421 |
hyde | -1.348 |
texting | -1.343 |
Token | focus |
Token ID | 2962 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
eming | +4.181 |
atown | +3.038 |
toggle | +2.965 |
screenings | +2.960 |
texting | +2.938 |
Neg logit contributions | |
ought | -3.270 |
rightly | -3.188 |
Parables | -3.067 |
BACK | -3.030 |
rightfully | -3.012 |
Token | is |
Token ID | 318 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
eming | +2.477 |
atown | +1.877 |
toggle | +1.864 |
texting | +1.789 |
slowing | +1.788 |
Neg logit contributions | |
ought | -1.601 |
rightly | -1.549 |
rightfully | -1.451 |
BACK | -1.439 |
Parables | -1.427 |
Token | no |
Token ID | 645 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
rightly | +3.282 |
ought | +3.188 |
rightfully | +3.031 |
BACK | +2.855 |
Parables | +2.815 |
Neg logit contributions | |
eming | -5.347 |
atown | -4.089 |
toggle | -4.042 |
hyde | -3.862 |
alert | -3.846 |
Token | easy |
Token ID | 2562 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
rightly | +4.228 |
ought | +4.112 |
rightfully | +3.879 |
Parables | +3.719 |
BACK | +3.674 |
Neg logit contributions | |
eming | -7.067 |
atown | -5.401 |
toggle | -5.265 |
hyde | -5.083 |
alert | -5.033 |
Token | task |
Token ID | 4876 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
ought | +8.243 |
rightly | +8.180 |
rightfully | +7.492 |
suprem | +7.037 |
fut | +6.942 |
Neg logit contributions | |
eming | -15.375 |
atown | -11.640 |
toggle | -11.605 |
alert | -11.206 |
hyde | -11.180 |
Token | , |
Token ID | 11 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
rightly | +2.937 |
ought | +2.916 |
rightfully | +2.702 |
BACK | +2.617 |
Parables | +2.571 |
Neg logit contributions | |
eming | -5.006 |
atown | -3.823 |
toggle | -3.792 |
texting | -3.634 |
hyde | -3.598 |
Token | says |
Token ID | 1139 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
rightly | +3.005 |
ought | +2.941 |
rightfully | +2.795 |
BACK | +2.675 |
Parables | +2.656 |
Neg logit contributions | |
eming | -4.098 |
atown | -3.040 |
toggle | -3.001 |
hyde | -2.876 |
texting | -2.852 |
Token | Young |
Token ID | 6960 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
rightly | +2.049 |
ought | +2.046 |
rightfully | +1.915 |
BACK | +1.873 |
Parables | +1.846 |
Neg logit contributions | |
eming | -2.669 |
atown | -1.974 |
toggle | -1.950 |
texting | -1.856 |
hyde | -1.840 |
Token | ah |
Token ID | 993 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
eming | +2.419 |
atown | +1.741 |
toggle | +1.716 |
texting | +1.631 |
hyde | +1.620 |
Neg logit contributions | |
ought | -2.065 |
rightly | -2.055 |
rightfully | -1.940 |
BACK | -1.926 |
Parables | -1.878 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ought | +0.502 |
rightly | +0.499 |
rightfully | +0.469 |
BACK | +0.462 |
Parables | +0.459 |
Neg logit contributions | |
eming | -0.634 |
atown | -0.464 |
toggle | -0.461 |
texting | -0.444 |
slowing | -0.438 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ought | +1.303 |
rightly | +1.295 |
rightfully | +1.209 |
BACK | +1.190 |
Parables | +1.171 |
Neg logit contributions | |
eming | -1.853 |
atown | -1.385 |
toggle | -1.372 |
texting | -1.320 |
slowing | -1.303 |
Token | Ferguson |
Token ID | 15031 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
eming | +0.657 |
toggle | +0.468 |
atown | +0.467 |
hyde | +0.441 |
texting | +0.439 |
Neg logit contributions | |
rightly | -0.562 |
ought | -0.560 |
rightfully | -0.534 |
BACK | -0.533 |
Parables | -0.520 |
Token | was |
Token ID | 373 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
rightly | +4.392 |
ought | +4.311 |
rightfully | +4.042 |
BACK | +3.858 |
suprem | +3.745 |
Neg logit contributions | |
eming | -6.694 |
atown | -5.113 |
toggle | -5.103 |
texting | -4.834 |
hyde | -4.791 |
Token | appointed |
Token ID | 9899 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
ought | +1.072 |
rightly | +1.066 |
rightfully | +0.994 |
BACK | +0.980 |
Parables | +0.965 |
Neg logit contributions | |
eming | -1.487 |
atown | -1.107 |
toggle | -1.097 |
texting | -1.055 |
slowing | -1.039 |
Token | auditor |
Token ID | 30625 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
eming | +0.073 |
atown | +0.055 |
toggle | +0.054 |
texting | +0.054 |
slowing | +0.052 |
Neg logit contributions | |
ought | -0.050 |
rightly | -0.049 |
BACK | -0.046 |
rightfully | -0.046 |
Parables | -0.045 |
Token | general |
Token ID | 2276 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
rightly | +7.466 |
ought | +7.086 |
rightfully | +6.665 |
suprem | +6.376 |
extraord | +6.094 |
Neg logit contributions | |
eming | -15.731 |
atown | -12.683 |
toggle | -12.648 |
hyde | -11.957 |
roma | -11.782 |
Token | , |
Token ID | 11 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
rightly | +4.823 |
ought | +4.754 |
rightfully | +4.439 |
BACK | +4.161 |
suprem | +4.118 |
Neg logit contributions | |
eming | -8.377 |
atown | -6.508 |
toggle | -6.447 |
hyde | -6.124 |
texting | -6.089 |
Token | even |
Token ID | 772 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
rightly | +2.733 |
ought | +2.729 |
rightfully | +2.551 |
BACK | +2.493 |
Parables | +2.451 |
Neg logit contributions | |
eming | -3.636 |
atown | -2.695 |
toggle | -2.674 |
texting | -2.541 |
hyde | -2.513 |
Token | though |
Token ID | 996 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
eming | +0.473 |
atown | +0.340 |
toggle | +0.337 |
texting | +0.327 |
slowing | +0.323 |
Neg logit contributions | |
ought | -0.408 |
rightly | -0.403 |
rightfully | -0.379 |
BACK | -0.378 |
Parables | -0.371 |
Token | he |
Token ID | 339 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ought | +1.272 |
rightly | +1.267 |
rightfully | +1.178 |
BACK | +1.158 |
Parables | +1.136 |
Neg logit contributions | |
eming | -1.935 |
atown | -1.460 |
toggle | -1.447 |
texting | -1.390 |
slowing | -1.372 |
Token | � |
Token ID | 250 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
ought | +0.454 |
rightly | +0.453 |
rightfully | +0.427 |
BACK | +0.421 |
Parables | +0.415 |
Neg logit contributions | |
eming | -0.460 |
atown | -0.325 |
toggle | -0.321 |
texting | -0.304 |
slowing | -0.299 |
Token | we |
Token ID | 732 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ought | +1.390 |
rightly | +1.384 |
rightfully | +1.296 |
BACK | +1.276 |
Parables | +1.247 |
Neg logit contributions | |
eming | -1.745 |
atown | -1.288 |
toggle | -1.269 |
texting | -1.213 |
hyde | -1.196 |
Token | might |
Token ID | 1244 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
eming | +2.367 |
atown | +1.787 |
toggle | +1.770 |
texting | +1.720 |
screenings | +1.713 |
Neg logit contributions | |
ought | -1.472 |
rightly | -1.445 |
BACK | -1.385 |
Parables | -1.369 |
rightfully | -1.347 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
eming | +5.460 |
toggle | +4.031 |
slowing | +3.909 |
atown | +3.905 |
screenings | +3.847 |
Neg logit contributions | |
ought | -4.352 |
rightly | -4.110 |
Parables | -4.091 |
BACK | -4.054 |
Vice | -3.942 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
rightly | +1.306 |
ought | +1.296 |
rightfully | +1.215 |
BACK | +1.177 |
Parables | +1.154 |
Neg logit contributions | |
eming | -1.856 |
atown | -1.391 |
toggle | -1.375 |
texting | -1.312 |
hyde | -1.304 |
Token | likely |
Token ID | 1884 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
rightly | +6.109 |
ought | +5.673 |
rightfully | +5.637 |
suprem | +4.875 |
BACK | +4.799 |
Neg logit contributions | |
eming | -10.159 |
atown | -8.024 |
toggle | -7.730 |
hyde | -7.475 |
alert | -7.347 |
Token | will |
Token ID | 481 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
rightly | +7.686 |
rightfully | +7.078 |
ought | +6.865 |
suprem | +5.848 |
Vice | +5.784 |
Neg logit contributions | |
eming | -15.659 |
atown | -12.866 |
toggle | -12.672 |
roma | -11.988 |
hyde | -11.944 |
Token | � |
Token ID | 447 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ought | +1.737 |
rightly | +1.728 |
rightfully | +1.614 |
BACK | +1.590 |
Parables | +1.567 |
Neg logit contributions | |
eming | -2.349 |
atown | -1.739 |
toggle | -1.727 |
texting | -1.651 |
slowing | -1.630 |
Token | � |
Token ID | 251 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ought | +0.952 |
rightly | +0.946 |
rightfully | +0.888 |
BACK | +0.875 |
Parables | +0.854 |
Neg logit contributions | |
eming | -1.009 |
atown | -0.716 |
toggle | -0.703 |
texting | -0.674 |
screenings | -0.668 |
Token | apply |
Token ID | 4174 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
eming | +1.997 |
toggle | +1.441 |
atown | +1.411 |
texting | +1.351 |
screenings | +1.348 |
Neg logit contributions | |
ought | -1.756 |
rightly | -1.740 |
rightfully | -1.640 |
Parables | -1.635 |
BACK | -1.625 |
Token | the |
Token ID | 262 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
eming | +5.906 |
screenings | +4.309 |
toggle | +4.272 |
texting | +4.219 |
slowing | +4.201 |
Neg logit contributions | |
ought | -4.938 |
rightly | -4.803 |
Parables | -4.589 |
rightfully | -4.574 |
BACK | -4.524 |
Token | wood |
Token ID | 3822 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
eming | +0.021 |
atown | +0.016 |
toggle | +0.016 |
texting | +0.015 |
slowing | +0.015 |
Neg logit contributions | |
ought | -0.014 |
rightly | -0.014 |
rightfully | -0.013 |
BACK | -0.013 |
Parables | -0.013 |
Token | has |
Token ID | 468 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
eming | +2.311 |
atown | +1.738 |
toggle | +1.716 |
texting | +1.685 |
slowing | +1.671 |
Neg logit contributions | |
ought | -1.607 |
rightly | -1.574 |
Parables | -1.519 |
BACK | -1.491 |
rightfully | -1.460 |
Token | excellent |
Token ID | 6275 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
rightly | +1.556 |
ought | +1.555 |
rightfully | +1.441 |
BACK | +1.404 |
Parables | +1.373 |
Neg logit contributions | |
eming | -2.597 |
atown | -1.979 |
toggle | -1.963 |
texting | -1.880 |
hyde | -1.864 |
Token | size |
Token ID | 2546 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
rightly | +1.600 |
ought | +1.598 |
rightfully | +1.504 |
BACK | +1.479 |
Parables | +1.440 |
Neg logit contributions | |
eming | -1.878 |
atown | -1.362 |
toggle | -1.339 |
hyde | -1.271 |
texting | -1.268 |
Token | at |
Token ID | 379 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ought | +4.077 |
rightly | +4.066 |
rightfully | +3.789 |
BACK | +3.689 |
suprem | +3.538 |
Neg logit contributions | |
eming | -6.474 |
atown | -4.911 |
toggle | -4.866 |
hyde | -4.653 |
Archdemon | -4.587 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
rightly | +5.803 |
ought | +5.702 |
rightfully | +5.311 |
BACK | +4.774 |
suprem | +4.754 |
Neg logit contributions | |
eming | -13.069 |
atown | -10.504 |
toggle | -10.242 |
hyde | -10.009 |
Appears | -9.742 |
Token | - |
Token ID | 12 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ought | +6.380 |
rightly | +5.999 |
BACK | +5.696 |
rightfully | +5.284 |
suprem | +5.096 |
Neg logit contributions | |
eming | -16.228 |
atown | -13.514 |
toggle | -12.690 |
hyde | -12.612 |
texting | -12.533 |
Token | foot |
Token ID | 5898 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ought | +6.594 |
rightly | +6.220 |
BACK | +5.980 |
rightfully | +5.700 |
Vice | +5.553 |
Neg logit contributions | |
eming | -11.231 |
atown | -8.813 |
texting | -8.428 |
Archdemon | -8.384 |
slowing | -8.258 |
Token | - |
Token ID | 12 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ought | +4.354 |
rightly | +4.293 |
rightfully | +3.950 |
BACK | +3.906 |
suprem | +3.741 |
Neg logit contributions | |
eming | -8.485 |
atown | -6.720 |
toggle | -6.587 |
texting | -6.316 |
hyde | -6.275 |
Token | 6 |
Token ID | 21 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ought | +4.474 |
rightly | +4.233 |
BACK | +3.963 |
rightfully | +3.863 |
Vice | +3.742 |
Neg logit contributions | |
eming | -8.130 |
atown | -6.445 |
texting | -6.127 |
toggle | -6.074 |
Archdemon | -6.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ought | +5.056 |
rightly | +5.001 |
rightfully | +4.657 |
BACK | +4.572 |
suprem | +4.380 |
Neg logit contributions | |
eming | -7.950 |
atown | -6.137 |
toggle | -6.018 |
texting | -5.706 |
alert | -5.626 |
Token | commit |
Token ID | 41509 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
eming | +4.008 |
toggle | +3.016 |
atown | +2.890 |
alert | +2.863 |
texting | +2.822 |
Neg logit contributions | |
rightly | -2.930 |
ought | -2.866 |
rightfully | -2.731 |
Parables | -2.713 |
suprem | -2.649 |
Token | ) |
Token ID | 8 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
eming | +2.895 |
atown | +2.099 |
toggle | +2.074 |
texting | +2.045 |
slowing | +1.994 |
Neg logit contributions | |
rightly | -2.340 |
ought | -2.326 |
rightfully | -2.181 |
Parables | -2.175 |
BACK | -2.139 |
Token | Levi |
Token ID | 20196 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
ought | +0.228 |
rightly | +0.227 |
rightfully | +0.212 |
BACK | +0.209 |
Parables | +0.205 |
Neg logit contributions | |
eming | -0.289 |
atown | -0.211 |
toggle | -0.211 |
texting | -0.201 |
slowing | -0.198 |
Token | Jones |
Token ID | 5437 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
eming | +0.361 |
atown | +0.260 |
toggle | +0.258 |
texting | +0.245 |
slowing | +0.242 |
Neg logit contributions | |
ought | -0.312 |
rightly | -0.311 |
rightfully | -0.292 |
BACK | -0.289 |
Parables | -0.285 |
Token | LB |
Token ID | 22199 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ought | +5.480 |
rightly | +5.366 |
BACK | +5.026 |
rightfully | +4.921 |
Parables | +4.573 |
Neg logit contributions | |
eming | -10.595 |
atown | -8.419 |
toggle | -8.202 |
hyde | -7.946 |
texting | -7.893 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ought | +4.178 |
rightly | +4.081 |
BACK | +3.722 |
rightfully | +3.640 |
Parables | +3.427 |
Neg logit contributions | |
eming | -10.742 |
atown | -8.641 |
toggle | -8.424 |
hyde | -8.249 |
texting | -8.222 |
Token | ' |
Token ID | 6 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
ought | +5.214 |
rightly | +4.837 |
BACK | +4.624 |
Vice | +4.112 |
���� | +3.996 |
Neg logit contributions | |
eming | -16.899 |
rul | -14.518 |
atown | -14.392 |
hyde | -14.067 |
texting | -13.713 |
Token | 3 |
Token ID | 18 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ought | +3.698 |
rightly | +3.651 |
BACK | +3.397 |
rightfully | +3.308 |
Vice | +3.167 |
Neg logit contributions | |
eming | -7.118 |
atown | -5.649 |
texting | -5.391 |
toggle | -5.358 |
slowing | -5.320 |
Token | / |
Token ID | 14 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
ought | +1.019 |
rightly | +1.016 |
rightfully | +0.932 |
BACK | +0.920 |
Parables | +0.882 |
Neg logit contributions | |
eming | -1.824 |
atown | -1.408 |
toggle | -1.371 |
hyde | -1.343 |
texting | -1.336 |
Token | 215 |
Token ID | 23349 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
ought | +3.693 |
rightly | +3.571 |
BACK | +3.359 |
rightfully | +3.245 |
Vice | +3.180 |
Neg logit contributions | |
eming | -6.565 |
atown | -5.234 |
texting | -4.985 |
toggle | -4.911 |
screenings | -4.903 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
ought | +3.260 |
rightly | +3.244 |
rightfully | +2.932 |
BACK | +2.918 |
Parables | +2.790 |
Neg logit contributions | |
eming | -7.600 |
atown | -6.047 |
toggle | -5.893 |
hyde | -5.766 |
texting | -5.731 |
Token | , |
Token ID | 11 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
eming | +0.739 |
toggle | +0.536 |
atown | +0.535 |
texting | +0.514 |
slowing | +0.514 |
Neg logit contributions | |
ought | -0.605 |
rightly | -0.601 |
rightfully | -0.565 |
BACK | -0.559 |
Parables | -0.558 |
Token | but |
Token ID | 475 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
eming | +0.050 |
atown | +0.036 |
toggle | +0.036 |
texting | +0.034 |
slowing | +0.034 |
Neg logit contributions | |
ought | -0.042 |
rightly | -0.042 |
rightfully | -0.040 |
BACK | -0.039 |
Parables | -0.039 |
Token | also |
Token ID | 635 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
ought | +1.503 |
rightly | +1.500 |
rightfully | +1.400 |
BACK | +1.374 |
Parables | +1.350 |
Neg logit contributions | |
eming | -2.061 |
atown | -1.533 |
toggle | -1.519 |
texting | -1.453 |
slowing | -1.433 |
Token | in |
Token ID | 287 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
rightly | +4.204 |
ought | +4.054 |
rightfully | +3.886 |
suprem | +3.617 |
BACK | +3.608 |
Neg logit contributions | |
eming | -6.220 |
atown | -4.697 |
toggle | -4.657 |
hyde | -4.398 |
alert | -4.336 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
ought | +2.233 |
rightly | +2.228 |
rightfully | +2.079 |
BACK | +2.038 |
Parables | +2.002 |
Neg logit contributions | |
eming | -3.065 |
atown | -2.279 |
toggle | -2.258 |
texting | -2.159 |
hyde | -2.129 |
Token | long |
Token ID | 890 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
rightly | +1.540 |
ought | +1.539 |
rightfully | +1.384 |
BACK | +1.330 |
Parables | +1.289 |
Neg logit contributions | |
eming | -4.007 |
atown | -3.184 |
toggle | -3.159 |
texting | -3.048 |
hyde | -3.027 |
Token | term |
Token ID | 3381 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ought | +5.933 |
rightly | +5.929 |
rightfully | +5.153 |
BACK | +4.730 |
suprem | +4.668 |
Neg logit contributions | |
eming | -17.022 |
atown | -13.535 |
toggle | -13.490 |
hyde | -13.054 |
texting | -12.687 |
Token | : |
Token ID | 25 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ought | +1.085 |
rightly | +1.076 |
rightfully | +1.002 |
BACK | +0.990 |
Parables | +0.979 |
Neg logit contributions | |
eming | -1.707 |
atown | -1.291 |
toggle | -1.283 |
texting | -1.242 |
slowing | -1.233 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ought | +1.212 |
rightly | +1.206 |
rightfully | +1.128 |
BACK | +1.110 |
Parables | +1.091 |
Neg logit contributions | |
eming | -1.604 |
atown | -1.187 |
toggle | -1.177 |
texting | -1.127 |
slowing | -1.114 |
Token | costs |
Token ID | 3484 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
eming | +0.102 |
atown | +0.075 |
toggle | +0.075 |
texting | +0.073 |
slowing | +0.073 |
Neg logit contributions | |
ought | -0.077 |
rightly | -0.076 |
rightfully | -0.071 |
BACK | -0.071 |
Parables | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
eming | +1.152 |
toggle | +0.859 |
atown | +0.858 |
texting | +0.847 |
slowing | +0.846 |
Neg logit contributions | |
ought | -0.735 |
rightly | -0.719 |
BACK | -0.684 |
rightfully | -0.672 |
Parables | -0.669 |
Token | of |
Token ID | 286 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
ought | +0.633 |
rightly | +0.627 |
rightfully | +0.581 |
BACK | +0.572 |
Parables | +0.559 |
Neg logit contributions | |
eming | -1.040 |
atown | -0.792 |
toggle | -0.783 |
texting | -0.764 |
slowing | -0.755 |
Token | Israel |
Token ID | 2692 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
eming | +0.451 |
atown | +0.333 |
toggle | +0.328 |
texting | +0.319 |
screenings | +0.314 |
Neg logit contributions | |
ought | -0.349 |
rightly | -0.348 |
rightfully | -0.325 |
BACK | -0.321 |
Parables | -0.314 |
Token | , |
Token ID | 11 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
eming | +0.282 |
atown | +0.213 |
toggle | +0.208 |
texting | +0.203 |
screenings | +0.201 |
Neg logit contributions | |
ought | -0.191 |
rightly | -0.190 |
rightfully | -0.177 |
BACK | -0.175 |
Parables | -0.171 |
Token | which |
Token ID | 543 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
eming | +0.514 |
atown | +0.381 |
toggle | +0.377 |
texting | +0.368 |
slowing | +0.362 |
Neg logit contributions | |
ought | -0.384 |
rightly | -0.379 |
rightfully | -0.355 |
BACK | -0.353 |
Parables | -0.346 |
Token | cost |
Token ID | 1575 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
rightly | +2.391 |
ought | +2.377 |
rightfully | +2.219 |
BACK | +2.149 |
Parables | +2.108 |
Neg logit contributions | |
eming | -3.647 |
atown | -2.746 |
toggle | -2.723 |
texting | -2.592 |
hyde | -2.585 |
Token | nearly |
Token ID | 3016 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ought | +2.151 |
rightly | +2.148 |
rightfully | +1.995 |
BACK | +1.948 |
Parables | +1.915 |
Neg logit contributions | |
eming | -3.248 |
atown | -2.448 |
toggle | -2.431 |
texting | -2.315 |
hyde | -2.300 |
Token | $ |
Token ID | 720 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
rightly | +6.373 |
ought | +6.332 |
rightfully | +5.864 |
suprem | +5.369 |
fut | +5.176 |
Neg logit contributions | |
eming | -16.167 |
toggle | -12.810 |
atown | -12.711 |
hyde | -12.677 |
roma | -12.196 |
Token | 4 |
Token ID | 19 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
ought | +4.484 |
rightly | +4.294 |
BACK | +3.984 |
rightfully | +3.843 |
Vice | +3.798 |
Neg logit contributions | |
eming | -8.588 |
atown | -6.913 |
texting | -6.557 |
slowing | -6.502 |
screenings | -6.487 |
Token | , |
Token ID | 11 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
ought | +4.389 |
rightly | +4.357 |
rightfully | +4.031 |
BACK | +3.933 |
Parables | +3.814 |
Neg logit contributions | |
eming | -6.959 |
atown | -5.378 |
toggle | -5.247 |
hyde | -4.983 |
texting | -4.977 |
Token | 000 |
Token ID | 830 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ought | +1.666 |
rightly | +1.657 |
rightfully | +1.537 |
BACK | +1.504 |
Parables | +1.475 |
Neg logit contributions | |
eming | -2.562 |
atown | -1.943 |
toggle | -1.918 |
texting | -1.843 |
slowing | -1.821 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
rightly | +2.952 |
ought | +2.935 |
rightfully | +2.724 |
BACK | +2.650 |
Parables | +2.577 |
Neg logit contributions | |
eming | -5.075 |
atown | -3.882 |
toggle | -3.848 |
texting | -3.665 |
hyde | -3.657 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
eming | +0.263 |
atown | +0.196 |
toggle | +0.195 |
texting | +0.189 |
screenings | +0.187 |
Neg logit contributions | |
ought | -0.178 |
rightly | -0.177 |
rightfully | -0.164 |
BACK | -0.162 |
Parables | -0.160 |
Token | Cos |
Token ID | 10437 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
ought | +1.404 |
rightly | +1.400 |
rightfully | +1.308 |
BACK | +1.285 |
Parables | +1.263 |
Neg logit contributions | |
eming | -1.882 |
atown | -1.395 |
toggle | -1.382 |
texting | -1.322 |
slowing | -1.303 |
Token | player |
Token ID | 7829 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ought | +4.760 |
rightly | +4.721 |
rightfully | +4.469 |
BACK | +4.404 |
Parables | +4.307 |
Neg logit contributions | |
eming | -4.049 |
atown | -2.751 |
toggle | -2.698 |
texting | -2.547 |
slowing | -2.514 |
Token | and |
Token ID | 290 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
rightly | +5.474 |
ought | +5.412 |
rightfully | +5.107 |
BACK | +4.961 |
extraord | +4.849 |
Neg logit contributions | |
eming | -8.740 |
atown | -6.676 |
toggle | -6.593 |
hyde | -6.264 |
texting | -6.188 |
Token | figure |
Token ID | 3785 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
rightly | +5.018 |
ought | +4.933 |
rightfully | +4.711 |
BACK | +4.569 |
suprem | +4.503 |
Neg logit contributions | |
eming | -5.847 |
atown | -4.280 |
toggle | -4.165 |
hyde | -3.988 |
alert | -3.887 |
Token | model |
Token ID | 2746 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ought | +5.568 |
rightly | +5.495 |
rightfully | +5.110 |
BACK | +5.049 |
suprem | +4.881 |
Neg logit contributions | |
eming | -7.631 |
atown | -5.680 |
toggle | -5.556 |
hyde | -5.316 |
texting | -5.283 |
Token | . |
Token ID | 13 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
rightly | +8.204 |
ought | +7.925 |
rightfully | +7.709 |
extraord | +7.652 |
BACK | +7.208 |
Neg logit contributions | |
eming | -14.174 |
atown | -11.099 |
toggle | -10.947 |
hyde | -10.354 |
roma | -10.220 |
Token | Founder |
Token ID | 30153 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
rightly | +4.302 |
ought | +4.294 |
rightfully | +4.026 |
BACK | +3.972 |
Parables | +3.925 |
Neg logit contributions | |
eming | -5.354 |
atown | -3.939 |
toggle | -3.840 |
hyde | -3.664 |
texting | -3.658 |
Token | and |
Token ID | 290 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
rightly | +3.053 |
ought | +3.049 |
rightfully | +2.835 |
BACK | +2.766 |
Parables | +2.705 |
Neg logit contributions | |
eming | -4.841 |
atown | -3.678 |
toggle | -3.647 |
texting | -3.479 |
hyde | -3.449 |
Token | Editor |
Token ID | 12058 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
rightly | +4.591 |
ought | +4.520 |
rightfully | +4.299 |
BACK | +4.130 |
suprem | +4.121 |
Neg logit contributions | |
eming | -5.998 |
atown | -4.468 |
toggle | -4.377 |
hyde | -4.128 |
texting | -4.113 |
Token | - |
Token ID | 12 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
rightly | +5.191 |
ought | +5.058 |
rightfully | +4.759 |
BACK | +4.596 |
Parables | +4.476 |
Neg logit contributions | |
eming | -10.123 |
atown | -7.992 |
toggle | -7.980 |
texting | -7.478 |
hyde | -7.473 |
Token | be |
Token ID | 307 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ought | +1.167 |
rightly | +1.154 |
rightfully | +1.057 |
BACK | +1.041 |
Parables | +1.020 |
Neg logit contributions | |
eming | -2.385 |
atown | -1.854 |
toggle | -1.842 |
texting | -1.777 |
slowing | -1.761 |
Token | reversed |
Token ID | 17687 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ought | +1.009 |
rightly | +1.003 |
rightfully | +0.945 |
BACK | +0.931 |
Parables | +0.920 |
Neg logit contributions | |
eming | -1.116 |
atown | -0.798 |
toggle | -0.791 |
texting | -0.754 |
slowing | -0.744 |
Token | . |
Token ID | 13 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
ought | +1.219 |
rightly | +1.206 |
rightfully | +1.120 |
BACK | +1.106 |
Parables | +1.091 |
Neg logit contributions | |
eming | -1.980 |
atown | -1.503 |
toggle | -1.489 |
texting | -1.435 |
slowing | -1.422 |
Token | It |
Token ID | 632 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
rightly | +2.880 |
ought | +2.855 |
rightfully | +2.650 |
BACK | +2.607 |
Parables | +2.603 |
Neg logit contributions | |
eming | -4.141 |
atown | -3.130 |
toggle | -3.034 |
texting | -2.980 |
hyde | -2.955 |
Token | is |
Token ID | 318 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
ought | +1.752 |
rightly | +1.751 |
rightfully | +1.633 |
BACK | +1.595 |
Parables | +1.561 |
Neg logit contributions | |
eming | -2.439 |
atown | -1.821 |
toggle | -1.807 |
texting | -1.726 |
hyde | -1.703 |
Token | far |
Token ID | 1290 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
rightly | +3.048 |
ought | +3.006 |
rightfully | +2.817 |
BACK | +2.710 |
Parables | +2.651 |
Neg logit contributions | |
eming | -4.602 |
atown | -3.501 |
toggle | -3.467 |
hyde | -3.310 |
texting | -3.288 |
Token | from |
Token ID | 422 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
rightly | +8.340 |
ought | +7.885 |
rightfully | +7.483 |
BACK | +7.024 |
suprem | +6.879 |
Neg logit contributions | |
eming | -13.994 |
toggle | -10.985 |
atown | -10.951 |
hyde | -10.433 |
Archdemon | -10.428 |
Token | clear |
Token ID | 1598 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
rightly | +4.258 |
ought | +4.139 |
rightfully | +3.934 |
BACK | +3.787 |
suprem | +3.686 |
Neg logit contributions | |
eming | -6.322 |
toggle | -4.824 |
atown | -4.762 |
hyde | -4.558 |
alert | -4.523 |
Token | that |
Token ID | 326 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
rightly | +3.847 |
ought | +3.825 |
rightfully | +3.564 |
BACK | +3.453 |
Parables | +3.377 |
Neg logit contributions | |
eming | -5.391 |
atown | -4.067 |
toggle | -4.004 |
hyde | -3.810 |
texting | -3.809 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
rightly | +2.747 |
ought | +2.737 |
rightfully | +2.555 |
BACK | +2.476 |
Parables | +2.441 |
Neg logit contributions | |
eming | -3.885 |
atown | -2.915 |
toggle | -2.875 |
texting | -2.734 |
hyde | -2.733 |
Token | Governor |
Token ID | 10807 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
ought | +2.107 |
rightly | +2.101 |
rightfully | +1.969 |
BACK | +1.936 |
Parables | +1.905 |
Neg logit contributions | |
eming | -2.638 |
atown | -1.935 |
toggle | -1.916 |
texting | -1.830 |
slowing | -1.804 |
Token | Dev |
Token ID | 6245 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
ought | +1.190 |
rightly | +1.187 |
rightfully | +1.104 |
BACK | +1.082 |
Parables | +1.063 |
Neg logit contributions | |
eming | -1.790 |
atown | -1.346 |
toggle | -1.336 |
texting | -1.282 |
slowing | -1.266 |
Token | ont |
Token ID | 756 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ought | +1.967 |
rightly | +1.956 |
rightfully | +1.831 |
BACK | +1.801 |
Parables | +1.768 |
Neg logit contributions | |
eming | -2.563 |
atown | -1.904 |
toggle | -1.882 |
texting | -1.797 |
slowing | -1.780 |
Token | a |
Token ID | 64 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
rightly | +1.301 |
ought | +1.299 |
rightfully | +1.212 |
BACK | +1.191 |
Parables | +1.167 |
Neg logit contributions | |
eming | -1.864 |
atown | -1.396 |
toggle | -1.378 |
texting | -1.323 |
slowing | -1.305 |
Token | Smith |
Token ID | 4176 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ought | +1.107 |
rightly | +1.104 |
rightfully | +1.027 |
BACK | +1.010 |
Parables | +0.991 |
Neg logit contributions | |
eming | -1.630 |
atown | -1.223 |
toggle | -1.212 |
texting | -1.163 |
slowing | -1.148 |
Token | WR |
Token ID | 11342 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ought | +5.508 |
rightly | +5.382 |
BACK | +5.050 |
rightfully | +4.939 |
Parables | +4.588 |
Neg logit contributions | |
eming | -10.783 |
atown | -8.622 |
toggle | -8.362 |
hyde | -8.069 |
texting | -8.051 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ought | +4.476 |
rightly | +4.394 |
BACK | +4.078 |
rightfully | +3.936 |
Parables | +3.749 |
Neg logit contributions | |
eming | -11.506 |
atown | -9.342 |
toggle | -8.958 |
hyde | -8.886 |
texting | -8.813 |
Token | ' |
Token ID | 6 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ought | +5.815 |
rightly | +5.419 |
BACK | +5.391 |
rightfully | +4.608 |
Vice | +4.544 |
Neg logit contributions | |
eming | -16.091 |
atown | -13.351 |
hyde | -13.026 |
texting | -12.646 |
Archdemon | -12.462 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ought | +4.033 |
rightly | +4.015 |
BACK | +3.724 |
rightfully | +3.650 |
Vice | +3.482 |
Neg logit contributions | |
eming | -7.704 |
atown | -6.069 |
toggle | -5.776 |
texting | -5.769 |
slowing | -5.694 |
Token | / |
Token ID | 14 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
eming | +0.902 |
toggle | +0.666 |
atown | +0.662 |
texting | +0.636 |
slowing | +0.631 |
Neg logit contributions | |
rightly | -0.667 |
ought | -0.660 |
rightfully | -0.620 |
Parables | -0.604 |
BACK | -0.600 |
Token | 160 |
Token ID | 14198 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ought | +4.692 |
rightly | +4.466 |
BACK | +4.258 |
rightfully | +4.046 |
Vice | +3.990 |
Neg logit contributions | |
eming | -8.407 |
atown | -6.736 |
texting | -6.418 |
slowing | -6.319 |
screenings | -6.302 |
Token | 4 |
Token ID | 604 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ought | +1.900 |
rightly | +1.893 |
rightfully | +1.726 |
BACK | +1.702 |
Parables | +1.656 |
Neg logit contributions | |
eming | -3.917 |
atown | -3.070 |
toggle | -3.015 |
texting | -2.916 |
hyde | -2.908 |
Token | former |
Token ID | 1966 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
ought | +1.200 |
rightly | +1.196 |
rightfully | +1.116 |
BACK | +1.096 |
Parables | +1.078 |
Neg logit contributions | |
eming | -1.655 |
atown | -1.233 |
toggle | -1.220 |
texting | -1.167 |
slowing | -1.151 |
Token | International |
Token ID | 4037 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
rightly | +3.439 |
ought | +3.420 |
rightfully | +3.175 |
suprem | +3.106 |
BACK | +3.082 |
Neg logit contributions | |
eming | -5.639 |
atown | -4.349 |
toggle | -4.246 |
hyde | -4.030 |
alert | -4.017 |
Token | Monetary |
Token ID | 34112 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ought | +1.056 |
rightly | +1.054 |
rightfully | +0.978 |
BACK | +0.960 |
Parables | +0.935 |
Neg logit contributions | |
eming | -1.788 |
atown | -1.366 |
toggle | -1.359 |
texting | -1.312 |
slowing | -1.293 |
Token | Fund |
Token ID | 7557 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
ought | +1.584 |
rightly | +1.580 |
rightfully | +1.462 |
BACK | +1.437 |
Parables | +1.410 |
Neg logit contributions | |
eming | -2.377 |
atown | -1.802 |
toggle | -1.770 |
texting | -1.698 |
hyde | -1.677 |
Token | chief |
Token ID | 4039 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
rightly | +3.130 |
ought | +3.120 |
rightfully | +2.858 |
suprem | +2.787 |
BACK | +2.769 |
Neg logit contributions | |
eming | -6.231 |
atown | -4.883 |
toggle | -4.753 |
hyde | -4.602 |
texting | -4.563 |
Token | Domin |
Token ID | 11817 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ought | +0.188 |
rightly | +0.186 |
rightfully | +0.172 |
BACK | +0.170 |
Parables | +0.169 |
Neg logit contributions | |
eming | -0.365 |
toggle | -0.281 |
atown | -0.278 |
texting | -0.274 |
slowing | -0.272 |
Token | ique |
Token ID | 2350 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
ought | +6.089 |
rightly | +5.194 |
suprem | +4.647 |
rightfully | +4.476 |
BACK | +4.197 |
Neg logit contributions | |
eming | -16.422 |
toggle | -13.473 |
atown | -13.086 |
Magikarp | -13.039 |
screenings | -13.021 |
Token | Strauss |
Token ID | 42971 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
rightly | +3.164 |
ought | +3.141 |
rightfully | +2.998 |
BACK | +2.914 |
Parables | +2.905 |
Neg logit contributions | |
eming | -2.564 |
atown | -1.762 |
toggle | -1.726 |
hyde | -1.594 |
texting | -1.569 |
Token | - |
Token ID | 12 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
rightly | +3.481 |
ought | +3.460 |
rightfully | +3.209 |
BACK | +3.152 |
Parables | +3.067 |
Neg logit contributions | |
eming | -5.683 |
atown | -4.358 |
toggle | -4.302 |
texting | -4.102 |
hyde | -4.095 |
Token | K |
Token ID | 42 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
rightly | +5.001 |
ought | +4.990 |
rightfully | +4.439 |
Vice | +4.434 |
BACK | +4.419 |
Neg logit contributions | |
eming | -7.579 |
atown | -6.311 |
texting | -5.837 |
toggle | -5.834 |
screenings | -5.739 |
Token | ahn |
Token ID | 15386 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ought | +3.313 |
rightly | +3.193 |
rightfully | +2.843 |
suprem | +2.767 |
BACK | +2.727 |
Neg logit contributions | |
eming | -4.883 |
atown | -3.880 |
texting | -3.876 |
screenings | -3.798 |
contagious | -3.789 |
Token | R |
Token ID | 371 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
eming | +3.218 |
atown | +2.312 |
toggle | +2.296 |
texting | +2.190 |
slowing | +2.186 |
Neg logit contributions | |
ought | -2.792 |
rightly | -2.790 |
BACK | -2.660 |
rightfully | -2.621 |
Parables | -2.617 |
Token | ugg |
Token ID | 6837 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
eming | +1.224 |
atown | +0.911 |
toggle | +0.904 |
texting | +0.866 |
hyde | +0.864 |
Neg logit contributions | |
rightly | -0.827 |
ought | -0.821 |
rightfully | -0.774 |
BACK | -0.759 |
Parables | -0.756 |
Token | s |
Token ID | 82 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ought | +2.638 |
rightly | +2.621 |
rightfully | +2.458 |
BACK | +2.423 |
Parables | +2.379 |
Neg logit contributions | |
eming | -3.155 |
atown | -2.304 |
toggle | -2.278 |
texting | -2.173 |
hyde | -2.147 |
Token | III |
Token ID | 6711 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ought | +5.281 |
rightly | +5.139 |
BACK | +4.769 |
rightfully | +4.746 |
Parables | +4.410 |
Neg logit contributions | |
eming | -10.293 |
atown | -8.154 |
toggle | -7.990 |
hyde | -7.729 |
texting | -7.669 |
Token | WR |
Token ID | 11342 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ought | +4.650 |
rightly | +4.632 |
rightfully | +4.241 |
BACK | +4.240 |
Parables | +3.938 |
Neg logit contributions | |
eming | -9.248 |
atown | -7.310 |
toggle | -7.085 |
hyde | -7.007 |
texting | -6.852 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ought | +4.434 |
rightly | +4.327 |
BACK | +4.072 |
rightfully | +3.854 |
Parables | +3.656 |
Neg logit contributions | |
eming | -12.144 |
atown | -9.884 |
hyde | -9.470 |
toggle | -9.467 |
texting | -9.347 |
Token | ' |
Token ID | 6 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ought | +5.283 |
rightly | +4.866 |
BACK | +4.674 |
Vice | +4.140 |
���� | +4.033 |
Neg logit contributions | |
eming | -16.451 |
atown | -13.941 |
rul | -13.873 |
hyde | -13.590 |
texting | -13.292 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ought | +4.032 |
rightly | +3.978 |
BACK | +3.698 |
rightfully | +3.601 |
Vice | +3.451 |
Neg logit contributions | |
eming | -7.922 |
atown | -6.295 |
texting | -6.004 |
toggle | -5.963 |
slowing | -5.913 |
Token | / |
Token ID | 14 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
ought | +0.615 |
rightly | +0.613 |
rightfully | +0.564 |
BACK | +0.557 |
Parables | +0.539 |
Neg logit contributions | |
eming | -1.060 |
atown | -0.815 |
toggle | -0.797 |
hyde | -0.773 |
texting | -0.773 |
Token | 175 |
Token ID | 17430 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
ought | +3.980 |
rightly | +3.836 |
BACK | +3.652 |
rightfully | +3.477 |
Vice | +3.413 |
Neg logit contributions | |
eming | -7.239 |
atown | -5.803 |
texting | -5.522 |
screenings | -5.435 |
slowing | -5.423 |
Token | 4 |
Token ID | 604 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
ought | +2.882 |
rightly | +2.879 |
rightfully | +2.601 |
BACK | +2.599 |
Parables | +2.478 |
Neg logit contributions | |
eming | -6.691 |
atown | -5.336 |
toggle | -5.168 |
hyde | -5.064 |
texting | -5.031 |
Token | disparate |
Token ID | 37433 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
eming | +2.762 |
toggle | +1.923 |
atown | +1.918 |
texting | +1.889 |
slowing | +1.866 |
Neg logit contributions | |
ought | -2.705 |
rightly | -2.649 |
Parables | -2.522 |
BACK | -2.518 |
rightfully | -2.507 |
Token | communities |
Token ID | 5348 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
eming | +4.327 |
toggle | +3.100 |
atown | +3.092 |
texting | +3.083 |
screenings | +3.076 |
Neg logit contributions | |
ought | -3.919 |
rightly | -3.859 |
BACK | -3.648 |
rightfully | -3.634 |
Parables | -3.609 |
Token | in |
Token ID | 287 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
ought | +0.079 |
rightly | +0.078 |
rightfully | +0.073 |
BACK | +0.072 |
Parables | +0.071 |
Neg logit contributions | |
eming | -0.112 |
atown | -0.084 |
toggle | -0.083 |
texting | -0.080 |
slowing | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
eming | +2.194 |
atown | +1.619 |
toggle | +1.599 |
texting | +1.561 |
slowing | +1.546 |
Neg logit contributions | |
ought | -1.735 |
rightly | -1.723 |
rightfully | -1.619 |
BACK | -1.607 |
Parables | -1.575 |
Token | " |
Token ID | 366 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
eming | +0.333 |
atown | +0.245 |
toggle | +0.243 |
texting | +0.233 |
slowing | +0.230 |
Neg logit contributions | |
ought | -0.264 |
rightly | -0.262 |
rightfully | -0.245 |
BACK | -0.242 |
Parables | -0.239 |
Token | near |
Token ID | 40093 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
eming | +1.639 |
toggle | +1.216 |
atown | +1.201 |
texting | +1.142 |
alert | +1.132 |
Neg logit contributions | |
rightly | -1.256 |
ought | -1.236 |
rightfully | -1.174 |
Parables | -1.156 |
BACK | -1.132 |
Token | future |
Token ID | 2003 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ought | +6.928 |
rightly | +6.908 |
rightfully | +6.351 |
fut | +6.019 |
suprem | +6.011 |
Neg logit contributions | |
eming | -15.437 |
toggle | -11.972 |
atown | -11.500 |
hyde | -11.422 |
alert | -11.336 |
Token | " |
Token ID | 1 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ought | +1.366 |
rightly | +1.362 |
rightfully | +1.259 |
BACK | +1.234 |
Parables | +1.212 |
Neg logit contributions | |
eming | -2.304 |
atown | -1.760 |
toggle | -1.746 |
texting | -1.681 |
slowing | -1.660 |
Token | because |
Token ID | 780 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
eming | +1.091 |
atown | +0.810 |
toggle | +0.804 |
texting | +0.780 |
slowing | +0.771 |
Neg logit contributions | |
ought | -0.792 |
rightly | -0.780 |
rightfully | -0.727 |
BACK | -0.724 |
Parables | -0.716 |
Token | he |
Token ID | 339 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
rightly | +1.172 |
ought | +1.171 |
rightfully | +1.092 |
BACK | +1.067 |
Parables | +1.048 |
Neg logit contributions | |
eming | -1.712 |
atown | -1.285 |
toggle | -1.272 |
texting | -1.215 |
hyde | -1.204 |
Token | feels |
Token ID | 5300 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
eming | +1.627 |
atown | +1.225 |
toggle | +1.204 |
texting | +1.168 |
screenings | +1.149 |
Neg logit contributions | |
ought | -1.148 |
rightly | -1.123 |
BACK | -1.066 |
Parables | -1.055 |
rightfully | -1.046 |
Token | would |
Token ID | 561 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
rightly | +2.200 |
ought | +2.164 |
rightfully | +2.041 |
BACK | +1.958 |
Parables | +1.913 |
Neg logit contributions | |
eming | -3.300 |
atown | -2.517 |
toggle | -2.463 |
texting | -2.359 |
hyde | -2.350 |
Token | make |
Token ID | 787 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
eming | +1.098 |
toggle | +0.791 |
atown | +0.790 |
slowing | +0.753 |
texting | +0.753 |
Neg logit contributions | |
ought | -0.919 |
rightly | -0.901 |
BACK | -0.847 |
rightfully | -0.845 |
Parables | -0.837 |
Token | bandwidth |
Token ID | 19484 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
eming | +0.461 |
atown | +0.335 |
toggle | +0.332 |
texting | +0.320 |
slowing | +0.316 |
Neg logit contributions | |
ought | -0.387 |
rightly | -0.383 |
rightfully | -0.360 |
BACK | -0.357 |
Parables | -0.352 |
Token | increases |
Token ID | 5732 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ought | +1.091 |
rightly | +1.090 |
rightfully | +1.021 |
BACK | +1.003 |
Parables | +0.987 |
Neg logit contributions | |
eming | -1.350 |
atown | -0.989 |
toggle | -0.979 |
texting | -0.933 |
hyde | -0.920 |
Token | safer |
Token ID | 14178 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
eming | +1.193 |
atown | +0.868 |
toggle | +0.867 |
texting | +0.839 |
slowing | +0.838 |
Neg logit contributions | |
ought | -0.940 |
rightly | -0.918 |
rightfully | -0.863 |
BACK | -0.860 |
Parables | -0.851 |
Token | long |
Token ID | 890 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
rightly | +6.361 |
ought | +6.084 |
rightfully | +5.868 |
BACK | +5.511 |
suprem | +5.317 |
Neg logit contributions | |
eming | -10.710 |
atown | -8.321 |
toggle | -8.235 |
hyde | -7.986 |
texting | -7.707 |
Token | term |
Token ID | 3381 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
rightly | +6.314 |
ought | +6.180 |
rightfully | +5.649 |
suprem | +5.114 |
BACK | +5.094 |
Neg logit contributions | |
eming | -16.075 |
toggle | -12.814 |
atown | -12.807 |
hyde | -12.478 |
texting | -12.031 |
Token | . |
Token ID | 13 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
rightly | +3.780 |
ought | +3.746 |
rightfully | +3.481 |
BACK | +3.375 |
suprem | +3.222 |
Neg logit contributions | |
eming | -6.702 |
atown | -5.175 |
toggle | -5.109 |
hyde | -4.892 |
texting | -4.877 |
Token | Further |
Token ID | 7735 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
rightly | +2.864 |
ought | +2.836 |
rightfully | +2.657 |
BACK | +2.628 |
Parables | +2.570 |
Neg logit contributions | |
eming | -3.987 |
atown | -2.986 |
toggle | -2.954 |
texting | -2.810 |
hyde | -2.798 |
Token | work |
Token ID | 670 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
rightly | +4.371 |
ought | +4.324 |
rightfully | +4.075 |
BACK | +4.009 |
Parables | +3.920 |
Neg logit contributions | |
eming | -4.971 |
atown | -3.637 |
toggle | -3.636 |
hyde | -3.397 |
texting | -3.309 |
Token | will |
Token ID | 481 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
ought | +0.012 |
rightly | +0.012 |
rightfully | +0.011 |
BACK | +0.011 |
Parables | +0.011 |
Neg logit contributions | |
eming | -0.018 |
atown | -0.013 |
toggle | -0.013 |
texting | -0.013 |
slowing | -0.013 |
Token | result |
Token ID | 1255 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
ought | +1.415 |
rightly | +1.412 |
rightfully | +1.316 |
BACK | +1.291 |
Parables | +1.268 |
Neg logit contributions | |
eming | -2.008 |
atown | -1.501 |
toggle | -1.486 |
texting | -1.424 |
hyde | -1.404 |
Token | of |
Token ID | 286 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
rightly | +2.414 |
ought | +2.343 |
rightfully | +2.181 |
BACK | +2.011 |
suprem | +1.935 |
Neg logit contributions | |
eming | -5.313 |
atown | -4.201 |
toggle | -4.125 |
hyde | -3.970 |
texting | -3.945 |
Token | supply |
Token ID | 5127 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ought | +1.401 |
rightly | +1.400 |
rightfully | +1.305 |
BACK | +1.278 |
Parables | +1.254 |
Neg logit contributions | |
eming | -1.967 |
atown | -1.468 |
toggle | -1.452 |
texting | -1.389 |
hyde | -1.372 |
Token | - |
Token ID | 12 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ought | +1.536 |
rightly | +1.533 |
rightfully | +1.432 |
BACK | +1.403 |
Parables | +1.377 |
Neg logit contributions | |
eming | -2.084 |
atown | -1.548 |
toggle | -1.530 |
texting | -1.459 |
hyde | -1.444 |
Token | and |
Token ID | 392 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
ought | +5.002 |
rightly | +4.868 |
rightfully | +4.544 |
BACK | +4.425 |
Parables | +4.374 |
Neg logit contributions | |
eming | -6.609 |
atown | -4.989 |
toggle | -4.747 |
texting | -4.715 |
Archdemon | -4.604 |
Token | - |
Token ID | 12 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
rightly | +2.246 |
ought | +2.223 |
rightfully | +2.048 |
BACK | +1.900 |
Vice | +1.841 |
Neg logit contributions | |
eming | -4.626 |
atown | -3.634 |
toggle | -3.540 |
hyde | -3.419 |
texting | -3.400 |
Token | demand |
Token ID | 28550 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ought | +6.052 |
rightly | +5.111 |
rightfully | +4.375 |
Vice | +4.355 |
fortune | +4.328 |
Neg logit contributions | |
eming | -15.862 |
Archdemon | -13.637 |
atown | -13.099 |
�� | -13.087 |
texting | -12.879 |
Token | fundamentals |
Token ID | 33099 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ought | +0.765 |
rightly | +0.761 |
rightfully | +0.713 |
BACK | +0.703 |
Parables | +0.695 |
Neg logit contributions | |
eming | -1.004 |
atown | -0.740 |
toggle | -0.737 |
texting | -0.709 |
slowing | -0.703 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
eming | +1.774 |
toggle | +1.302 |
atown | +1.298 |
slowing | +1.281 |
texting | +1.260 |
Neg logit contributions | |
ought | -1.356 |
rightly | -1.340 |
rightfully | -1.261 |
BACK | -1.255 |
Parables | -1.250 |
Token | More |
Token ID | 3125 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
rightly | +1.617 |
ought | +1.613 |
rightfully | +1.508 |
BACK | +1.483 |
Parables | +1.465 |
Neg logit contributions | |
eming | -2.150 |
atown | -1.599 |
toggle | -1.568 |
texting | -1.514 |
hyde | -1.496 |
Token | and |
Token ID | 290 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
rightly | +6.701 |
ought | +6.333 |
rightfully | +6.184 |
BACK | +5.818 |
cyn | +5.579 |
Neg logit contributions | |
eming | -9.418 |
atown | -7.028 |
toggle | -6.848 |
hyde | -6.755 |
Archdemon | -6.555 |
Token | . |
Token ID | 13 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
ought | +1.778 |
rightly | +1.751 |
BACK | +1.592 |
rightfully | +1.546 |
Vice | +1.496 |
Neg logit contributions | |
eming | -3.917 |
atown | -3.132 |
toggle | -3.008 |
texting | -2.999 |
screenings | -2.983 |
Token | S |
Token ID | 50 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
rightly | +0.258 |
ought | +0.257 |
rightfully | +0.242 |
BACK | +0.241 |
Parables | +0.234 |
Neg logit contributions | |
eming | -0.265 |
atown | -0.190 |
toggle | -0.184 |
texting | -0.179 |
screenings | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
ought | +2.639 |
rightly | +2.594 |
rightfully | +2.334 |
BACK | +2.268 |
Parables | +2.171 |
Neg logit contributions | |
eming | -6.028 |
toggle | -4.777 |
atown | -4.777 |
hyde | -4.600 |
texting | -4.586 |
Token | Congress |
Token ID | 3162 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
ought | +0.117 |
rightly | +0.117 |
rightfully | +0.109 |
BACK | +0.107 |
Parables | +0.106 |
Neg logit contributions | |
eming | -0.168 |
atown | -0.126 |
toggle | -0.124 |
slowing | -0.119 |
texting | -0.119 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
eming | +2.919 |
atown | +2.198 |
toggle | +2.193 |
texting | +2.127 |
slowing | +2.105 |
Neg logit contributions | |
ought | -1.759 |
rightly | -1.718 |
rightfully | -1.596 |
BACK | -1.594 |
Parables | -1.569 |
Token | broaden |
Token ID | 44870 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
eming | +1.244 |
atown | +0.908 |
toggle | +0.905 |
texting | +0.869 |
slowing | +0.860 |
Neg logit contributions | |
ought | -0.984 |
rightly | -0.966 |
rightfully | -0.905 |
BACK | -0.904 |
Parables | -0.888 |
Token | and |
Token ID | 290 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
eming | +12.380 |
authorizing | +9.194 |
screenings | +9.147 |
slowing | +9.004 |
texting | +8.922 |
Neg logit contributions | |
ought | -11.952 |
rightly | -11.383 |
Parables | -11.094 |
BACK | -10.983 |
Vice | -10.857 |
Token | leng |
Token ID | 40038 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
eming | +4.669 |
toggle | +3.339 |
atown | +3.296 |
texting | +3.236 |
slowing | +3.224 |
Neg logit contributions | |
ought | -4.140 |
rightly | -3.896 |
BACK | -3.775 |
Parables | -3.745 |
Vice | -3.700 |
Token | then |
Token ID | 8524 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
eming | +4.227 |
atown | +2.888 |
toggle | +2.861 |
alert | +2.674 |
texting | +2.646 |
Neg logit contributions | |
rightly | -4.615 |
ought | -4.604 |
BACK | -4.407 |
rightfully | -4.387 |
Parables | -4.362 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
eming | +6.971 |
toggle | +4.953 |
screenings | +4.933 |
texting | +4.885 |
slowing | +4.878 |
Neg logit contributions | |
ought | -6.159 |
rightly | -5.988 |
Parables | -5.712 |
BACK | -5.679 |
rightfully | -5.660 |
Token | tax |
Token ID | 1687 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
eming | +8.737 |
texting | +6.372 |
toggle | +6.367 |
slowing | +6.312 |
atown | +6.201 |
Neg logit contributions | |
ought | -7.177 |
rightly | -6.960 |
rightfully | -6.538 |
BACK | -6.439 |
fortune | -6.434 |
Token | Trump |
Token ID | 6170 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
eming | +1.085 |
toggle | +0.814 |
atown | +0.780 |
alert | +0.749 |
texting | +0.743 |
Neg logit contributions | |
rightly | -0.855 |
ought | -0.852 |
rightfully | -0.808 |
Parables | -0.792 |
suprem | -0.774 |
Token | threatened |
Token ID | 8556 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
eming | +2.143 |
atown | +1.619 |
toggle | +1.589 |
texting | +1.544 |
slowing | +1.532 |
Neg logit contributions | |
ought | -1.472 |
rightly | -1.430 |
Parables | -1.346 |
rightfully | -1.338 |
BACK | -1.332 |
Token | on |
Token ID | 319 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
eming | +1.672 |
toggle | +1.257 |
atown | +1.245 |
texting | +1.224 |
slowing | +1.219 |
Neg logit contributions | |
ought | -1.174 |
rightly | -1.146 |
rightfully | -1.079 |
BACK | -1.078 |
Parables | -1.073 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
rightly | +3.217 |
ought | +3.179 |
rightfully | +3.006 |
BACK | +2.913 |
suprem | +2.858 |
Neg logit contributions | |
eming | -3.931 |
atown | -2.932 |
toggle | -2.806 |
hyde | -2.703 |
alert | -2.626 |
Token | to |
Token ID | 284 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ought | +0.638 |
rightly | +0.635 |
rightfully | +0.589 |
BACK | +0.582 |
Parables | +0.572 |
Neg logit contributions | |
eming | -1.059 |
atown | -0.805 |
toggle | -0.801 |
texting | -0.777 |
slowing | -0.770 |
Token | shut |
Token ID | 4423 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
eming | +3.449 |
toggle | +2.514 |
atown | +2.464 |
slowing | +2.423 |
texting | +2.405 |
Neg logit contributions | |
ought | -3.028 |
rightly | -2.891 |
Parables | -2.775 |
BACK | -2.772 |
rightfully | -2.729 |
Token | down |
Token ID | 866 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
eming | +10.740 |
toggle | +7.125 |
screenings | +7.085 |
slowing | +7.084 |
atown | +7.073 |
Neg logit contributions | |
Parables | -13.659 |
ought | -13.639 |
rightly | -13.415 |
BACK | -13.199 |
rightfully | -12.965 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
eming | +9.942 |
screenings | +7.208 |
texting | +7.140 |
slowing | +7.121 |
toggle | +7.068 |
Neg logit contributions | |
ought | -10.361 |
Parables | -10.260 |
BACK | -10.003 |
rightly | -9.986 |
rightfully | -9.536 |
Token | government |
Token ID | 1230 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
eming | +6.661 |
toggle | +4.807 |
slowing | +4.738 |
texting | +4.685 |
screenings | +4.674 |
Neg logit contributions | |
ought | -6.635 |
rightly | -6.420 |
Parables | -6.298 |
BACK | -6.181 |
rightfully | -6.125 |
Token | if |
Token ID | 611 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
eming | +4.792 |
atown | +3.455 |
texting | +3.444 |
toggle | +3.434 |
slowing | +3.418 |
Neg logit contributions | |
ought | -4.104 |
rightly | -3.976 |
Parables | -3.864 |
BACK | -3.863 |
rightfully | -3.760 |
Token | Congress |
Token ID | 3162 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
eming | +1.468 |
toggle | +1.076 |
atown | +1.055 |
slowing | +1.043 |
texting | +1.041 |
Neg logit contributions | |
ought | -1.212 |
rightly | -1.191 |
Parables | -1.137 |
BACK | -1.137 |
rightfully | -1.123 |
Token | All |
Token ID | 1439 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
eming | +5.984 |
Appears | +3.785 |
atown | +3.421 |
Weird | +3.404 |
toggle | +3.400 |
Neg logit contributions | |
rightly | -11.042 |
ought | -10.845 |
rightfully | -10.756 |
suprem | -10.486 |
fortunately | -10.330 |
Token | Rights |
Token ID | 6923 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
eming | +7.318 |
texting | +5.214 |
screenings | +5.120 |
atown | +5.071 |
contagious | +5.032 |
Neg logit contributions | |
rightly | -5.442 |
ought | -5.346 |
rightfully | -4.991 |
suprem | -4.954 |
BACK | -4.873 |
Token | Reserved |
Token ID | 33876 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
eming | +5.185 |
atown | +3.288 |
toggle | +3.277 |
Appears | +3.171 |
hyde | +3.099 |
Neg logit contributions | |
rightly | -6.440 |
ought | -6.386 |
BACK | -6.187 |
rightfully | -6.099 |
suprem | -6.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
eming | +5.390 |
atown | +4.029 |
toggle | +3.999 |
texting | +3.835 |
alert | +3.779 |
Neg logit contributions | |
ought | -3.478 |
rightly | -3.475 |
rightfully | -3.246 |
BACK | -3.153 |
suprem | -3.140 |
Token | This |
Token ID | 770 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
eming | +8.331 |
Appears | +5.605 |
atown | +5.508 |
toggle | +5.506 |
Weird | +5.435 |
Neg logit contributions | |
ought | -8.985 |
rightly | -8.851 |
rightfully | -8.547 |
fortune | -8.329 |
suprem | -8.292 |
Token | material |
Token ID | 2587 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
eming | +9.279 |
texting | +6.607 |
slowing | +6.350 |
contagious | +6.290 |
atown | +6.262 |
Neg logit contributions | |
rightly | -8.329 |
ought | -8.263 |
BACK | -7.884 |
rightfully | -7.722 |
Parables | -7.697 |
Token | may |
Token ID | 743 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
eming | +10.829 |
Appears | +7.424 |
texting | +7.412 |
screenings | +7.202 |
toggle | +7.183 |
Neg logit contributions | |
ought | -13.555 |
BACK | -13.322 |
Parables | -13.228 |
rightly | -12.976 |
fortune | -12.922 |
Token | not |
Token ID | 407 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
eming | +8.840 |
toggle | +5.943 |
contagious | +5.673 |
Appears | +5.573 |
texting | +5.529 |
Neg logit contributions | |
ought | -10.557 |
rightly | -10.142 |
BACK | -9.947 |
rightfully | -9.591 |
suprem | -9.550 |
Token | be |
Token ID | 307 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
eming | +5.105 |
toggle | +3.579 |
atown | +3.572 |
texting | +3.476 |
screenings | +3.414 |
Neg logit contributions | |
ought | -4.654 |
rightly | -4.590 |
BACK | -4.431 |
rightfully | -4.300 |
suprem | -4.266 |
Token | published |
Token ID | 3199 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
eming | +3.845 |
atown | +2.733 |
toggle | +2.714 |
texting | +2.603 |
slowing | +2.580 |
Neg logit contributions | |
ought | -3.444 |
rightly | -3.410 |
BACK | -3.212 |
rightfully | -3.198 |
Parables | -3.128 |
Token | , |
Token ID | 11 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
eming | +5.020 |
atown | +3.611 |
toggle | +3.609 |
texting | +3.475 |
slowing | +3.405 |
Neg logit contributions | |
ought | -4.149 |
rightly | -4.123 |
rightfully | -3.881 |
BACK | -3.853 |
Parables | -3.755 |
Token | and |
Token ID | 290 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
eming | +2.054 |
atown | +1.521 |
toggle | +1.490 |
texting | +1.464 |
screenings | +1.452 |
Neg logit contributions | |
ought | -1.890 |
rightly | -1.835 |
BACK | -1.761 |
rightfully | -1.725 |
Parables | -1.715 |
Token | Count |
Token ID | 2764 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
eming | +2.575 |
atown | +1.791 |
texting | +1.753 |
toggle | +1.735 |
Weird | +1.676 |
Neg logit contributions | |
ought | -2.718 |
rightly | -2.705 |
BACK | -2.615 |
Parables | -2.584 |
rightfully | -2.536 |
Token | ing |
Token ID | 278 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
eming | +3.534 |
atown | +2.589 |
toggle | +2.558 |
texting | +2.510 |
slowing | +2.448 |
Neg logit contributions | |
rightly | -3.055 |
ought | -3.018 |
rightfully | -2.869 |
BACK | -2.787 |
Parables | -2.757 |
Token | from |
Token ID | 422 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
eming | +0.862 |
atown | +0.648 |
toggle | +0.641 |
texting | +0.617 |
screenings | +0.610 |
Neg logit contributions | |
ought | -0.589 |
rightly | -0.586 |
rightfully | -0.544 |
BACK | -0.536 |
Parables | -0.529 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
eming | +8.380 |
screenings | +5.992 |
toggle | +5.972 |
atown | +5.966 |
texting | +5.933 |
Neg logit contributions | |
ought | -8.390 |
rightly | -8.162 |
Parables | -7.804 |
BACK | -7.767 |
rightfully | -7.677 |
Token | air |
Token ID | 1633 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
eming | +6.428 |
toggle | +4.575 |
texting | +4.432 |
atown | +4.414 |
screenings | +4.376 |
Neg logit contributions | |
ought | -6.625 |
rightly | -6.506 |
Parables | -6.217 |
BACK | -6.193 |
rightfully | -6.189 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
eming | +11.878 |
toggle | +8.772 |
screenings | +8.685 |
atown | +8.248 |
slowing | +8.231 |
Neg logit contributions | |
ought | -11.716 |
Parables | -11.377 |
rightly | -11.046 |
rightfully | -10.701 |
BACK | -10.601 |
Token |
|
Token ID | 198 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
eming | +1.314 |
toggle | +0.980 |
atown | +0.976 |
texting | +0.926 |
screenings | +0.915 |
Neg logit contributions | |
ought | -0.944 |
rightly | -0.935 |
rightfully | -0.874 |
BACK | -0.857 |
Parables | -0.843 |
Token |
|
Token ID | 198 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ought | +0.257 |
rightly | +0.257 |
rightfully | +0.230 |
BACK | +0.225 |
Parables | +0.214 |
Neg logit contributions | |
eming | -0.642 |
atown | -0.512 |
toggle | -0.499 |
texting | -0.489 |
hyde | -0.487 |
Token | With |
Token ID | 3152 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
ought | +0.176 |
rightly | +0.176 |
rightfully | +0.165 |
BACK | +0.161 |
Parables | +0.160 |
Neg logit contributions | |
eming | -0.228 |
atown | -0.168 |
toggle | -0.167 |
texting | -0.159 |
slowing | -0.156 |
Token | some |
Token ID | 617 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
eming | +5.155 |
toggle | +3.778 |
atown | +3.764 |
texting | +3.672 |
screenings | +3.645 |
Neg logit contributions | |
ought | -4.164 |
rightly | -4.065 |
BACK | -3.897 |
Parables | -3.815 |
rightfully | -3.810 |
Token | co |
Token ID | 763 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
eming | +4.911 |
toggle | +3.509 |
screenings | +3.462 |
texting | +3.450 |
atown | +3.448 |
Neg logit contributions | |
ought | -4.592 |
rightly | -4.536 |
rightfully | -4.313 |
BACK | -4.260 |
Parables | -4.227 |
Token | - |
Token ID | 12 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
eming | +8.787 |
atown | +6.317 |
toggle | +6.305 |
screenings | +6.275 |
hyde | +6.062 |
Neg logit contributions | |
rightly | -8.090 |
ought | -7.835 |
rightfully | -7.665 |
Parables | -7.625 |
BACK | -7.393 |
Token | host |
Token ID | 4774 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
eming | +0.223 |
atown | +0.164 |
toggle | +0.162 |
texting | +0.155 |
slowing | +0.152 |
Neg logit contributions | |
ought | -0.177 |
rightly | -0.177 |
rightfully | -0.166 |
BACK | -0.163 |
Parables | -0.160 |
Token | ed |
Token ID | 276 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
eming | +7.584 |
screenings | +5.242 |
toggle | +5.227 |
texting | +5.157 |
atown | +5.003 |
Neg logit contributions | |
ought | -7.021 |
rightly | -6.908 |
rightfully | -6.629 |
BACK | -6.504 |
Parables | -6.455 |
Token | by |
Token ID | 416 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
eming | +2.245 |
toggle | +1.652 |
atown | +1.641 |
texting | +1.596 |
screenings | +1.587 |
Neg logit contributions | |
ought | -1.794 |
rightly | -1.777 |
rightfully | -1.677 |
BACK | -1.662 |
Parables | -1.637 |
Token | Steve |
Token ID | 6542 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
eming | +1.240 |
toggle | +0.897 |
atown | +0.897 |
texting | +0.859 |
screenings | +0.847 |
Neg logit contributions | |
ought | -1.048 |
rightly | -1.037 |
rightfully | -0.978 |
BACK | -0.973 |
Parables | -0.953 |
Token | Do |
Token ID | 2141 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
eming | +7.911 |
Archdemon | +4.490 |
contagious | +4.373 |
Chill | +4.368 |
Morning | +4.363 |
Neg logit contributions | |
ought | -15.720 |
BACK | -14.898 |
Parables | -14.778 |
rightly | -14.581 |
rightfully | -14.498 |
Token | ocy |
Token ID | 13733 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
eming | +2.837 |
toggle | +1.765 |
atown | +1.710 |
hyde | +1.705 |
alert | +1.692 |
Neg logit contributions | |
ought | -3.653 |
rightly | -3.614 |
Parables | -3.607 |
rightfully | -3.487 |
BACK | -3.464 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
eming | +3.006 |
atown | +2.239 |
toggle | +2.230 |
texting | +2.158 |
screenings | +2.148 |
Neg logit contributions | |
ought | -2.083 |
rightly | -2.058 |
rightfully | -1.931 |
BACK | -1.902 |
Parables | -1.897 |
Token | Brian |
Token ID | 8403 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
eming | +0.940 |
atown | +0.697 |
toggle | +0.692 |
texting | +0.670 |
slowing | +0.660 |
Neg logit contributions | |
ought | -0.691 |
rightly | -0.682 |
rightfully | -0.637 |
BACK | -0.632 |
Parables | -0.621 |
Token | Kil |
Token ID | 19902 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
eming | +7.439 |
atown | +4.751 |
texting | +4.682 |
toggle | +4.620 |
Weird | +4.487 |
Neg logit contributions | |
ought | -10.201 |
rightly | -9.781 |
BACK | -9.720 |
Parables | -9.600 |
rightfully | -9.512 |
Token | broaden |
Token ID | 44870 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
eming | +1.244 |
atown | +0.908 |
toggle | +0.905 |
texting | +0.869 |
slowing | +0.860 |
Neg logit contributions | |
ought | -0.984 |
rightly | -0.966 |
rightfully | -0.905 |
BACK | -0.904 |
Parables | -0.888 |
Token | and |
Token ID | 290 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
eming | +12.380 |
authorizing | +9.194 |
screenings | +9.147 |
slowing | +9.004 |
texting | +8.922 |
Neg logit contributions | |
ought | -11.952 |
rightly | -11.383 |
Parables | -11.094 |
BACK | -10.983 |
Vice | -10.857 |
Token | leng |
Token ID | 40038 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
eming | +4.669 |
toggle | +3.339 |
atown | +3.296 |
texting | +3.236 |
slowing | +3.224 |
Neg logit contributions | |
ought | -4.140 |
rightly | -3.896 |
BACK | -3.775 |
Parables | -3.745 |
Vice | -3.700 |
Token | then |
Token ID | 8524 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
eming | +4.227 |
atown | +2.888 |
toggle | +2.861 |
alert | +2.674 |
texting | +2.646 |
Neg logit contributions | |
rightly | -4.615 |
ought | -4.604 |
BACK | -4.407 |
rightfully | -4.387 |
Parables | -4.362 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
eming | +6.971 |
toggle | +4.953 |
screenings | +4.933 |
texting | +4.885 |
slowing | +4.878 |
Neg logit contributions | |
ought | -6.159 |
rightly | -5.988 |
Parables | -5.712 |
BACK | -5.679 |
rightfully | -5.660 |
Token | tax |
Token ID | 1687 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
eming | +8.737 |
texting | +6.372 |
toggle | +6.367 |
slowing | +6.312 |
atown | +6.201 |
Neg logit contributions | |
ought | -7.177 |
rightly | -6.960 |
rightfully | -6.538 |
BACK | -6.439 |
fortune | -6.434 |
Token | credits |
Token ID | 10824 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
eming | +11.177 |
screenings | +8.159 |
toggle | +8.035 |
texting | +7.877 |
slowing | +7.658 |
Neg logit contributions | |
ought | -11.602 |
rightly | -11.225 |
Parables | -11.056 |
BACK | -11.048 |
fortune | -11.026 |
Token | for |
Token ID | 329 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
eming | +6.334 |
toggle | +4.596 |
atown | +4.532 |
slowing | +4.524 |
authorizing | +4.508 |
Neg logit contributions | |
ought | -5.185 |
rightly | -5.018 |
Parables | -4.902 |
BACK | -4.857 |
Vice | -4.742 |
Token | renewable |
Token ID | 15713 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
eming | +1.671 |
toggle | +1.208 |
atown | +1.199 |
texting | +1.161 |
slowing | +1.157 |
Neg logit contributions | |
ought | -1.471 |
rightly | -1.459 |
rightfully | -1.372 |
BACK | -1.357 |
Parables | -1.354 |
Token | energy |
Token ID | 2568 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ought | +0.371 |
rightly | +0.369 |
rightfully | +0.347 |
BACK | +0.344 |
Parables | +0.342 |
Neg logit contributions | |
eming | -0.385 |
atown | -0.273 |
toggle | -0.270 |
texting | -0.259 |
slowing | -0.255 |
Token | production |
Token ID | 3227 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
eming | +1.701 |
atown | +1.266 |
toggle | +1.264 |
texting | +1.224 |
slowing | +1.216 |
Neg logit contributions | |
ought | -1.199 |
rightly | -1.186 |
rightfully | -1.105 |
Parables | -1.100 |
BACK | -1.097 |
Token |
|
Token ID | 198 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
eming | +1.267 |
atown | +0.966 |
toggle | +0.963 |
texting | +0.915 |
slowing | +0.905 |
Neg logit contributions | |
ought | -0.768 |
rightly | -0.766 |
rightfully | -0.715 |
BACK | -0.693 |
suprem | -0.674 |
Token |
|
Token ID | 198 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
rightly | +0.682 |
ought | +0.679 |
rightfully | +0.601 |
BACK | +0.595 |
Vice | +0.562 |
Neg logit contributions | |
eming | -1.799 |
atown | -1.453 |
toggle | -1.398 |
hyde | -1.383 |
texting | -1.383 |
Token | Another |
Token ID | 6610 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ought | +1.937 |
rightly | +1.925 |
rightfully | +1.793 |
BACK | +1.778 |
Parables | +1.725 |
Neg logit contributions | |
eming | -2.644 |
atown | -1.975 |
toggle | -1.937 |
texting | -1.872 |
slowing | -1.845 |
Token | change |
Token ID | 1487 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
ought | +0.810 |
rightly | +0.808 |
rightfully | +0.752 |
BACK | +0.737 |
Parables | +0.723 |
Neg logit contributions | |
eming | -1.169 |
atown | -0.876 |
toggle | -0.868 |
texting | -0.830 |
hyde | -0.821 |
Token | would |
Token ID | 561 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
eming | +3.903 |
atown | +2.855 |
toggle | +2.810 |
slowing | +2.778 |
texting | +2.755 |
Neg logit contributions | |
ought | -2.902 |
rightly | -2.885 |
Parables | -2.752 |
BACK | -2.722 |
rightfully | -2.703 |
Token | restrict |
Token ID | 4239 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
eming | +8.044 |
slowing | +5.572 |
toggle | +5.522 |
alert | +5.307 |
atown | +5.304 |
Neg logit contributions | |
ought | -7.764 |
BACK | -7.408 |
Vice | -7.242 |
Parables | -7.214 |
Past | -7.177 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
eming | +11.740 |
texting | +8.805 |
slowing | +8.716 |
authorizing | +8.545 |
toggle | +8.444 |
Neg logit contributions | |
ought | -10.727 |
Parables | -10.477 |
BACK | -10.404 |
rightly | -10.361 |
rightfully | -9.882 |
Token | ability |
Token ID | 2694 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
eming | +7.404 |
slowing | +5.303 |
toggle | +5.274 |
texting | +5.260 |
screenings | +5.128 |
Neg logit contributions | |
ought | -7.152 |
rightly | -6.902 |
BACK | -6.587 |
Parables | -6.541 |
rightfully | -6.522 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
eming | +5.032 |
atown | +3.744 |
toggle | +3.736 |
texting | +3.614 |
slowing | +3.582 |
Neg logit contributions | |
ought | -3.369 |
rightly | -3.292 |
Parables | -3.066 |
rightfully | -3.066 |
BACK | -3.058 |
Token | convert |
Token ID | 10385 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
eming | +1.156 |
atown | +0.842 |
toggle | +0.839 |
texting | +0.805 |
slowing | +0.797 |
Neg logit contributions | |
ought | -0.920 |
rightly | -0.905 |
BACK | -0.848 |
rightfully | -0.846 |
Parables | -0.830 |
Token | income |
Token ID | 3739 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
rightly | +3.337 |
ought | +3.320 |
rightfully | +3.128 |
BACK | +3.001 |
suprem | +2.945 |
Neg logit contributions | |
eming | -4.511 |
atown | -3.371 |
toggle | -3.307 |
hyde | -3.176 |
alert | -3.129 |
Token | on |
Token ID | 319 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
eming | +1.245 |
atown | +0.924 |
toggle | +0.914 |
texting | +0.878 |
slowing | +0.867 |
Neg logit contributions | |
ought | -0.925 |
rightly | -0.920 |
rightfully | -0.858 |
BACK | -0.846 |
Parables | -0.830 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
eming | +4.448 |
texting | +3.024 |
toggle | +2.944 |
slowing | +2.864 |
alert | +2.774 |
Neg logit contributions | |
ought | -5.326 |
rightly | -5.056 |
BACK | -4.945 |
Parables | -4.883 |
rightfully | -4.809 |
Token | of |
Token ID | 286 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
eming | +3.709 |
toggle | +2.821 |
atown | +2.758 |
texting | +2.685 |
slowing | +2.672 |
Neg logit contributions | |
ought | -2.264 |
rightly | -2.246 |
rightfully | -2.088 |
BACK | -2.040 |
suprem | -2.032 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
eming | +4.612 |
toggle | +3.247 |
slowing | +3.196 |
texting | +3.175 |
atown | +3.134 |
Neg logit contributions | |
ought | -3.896 |
Parables | -3.769 |
rightly | -3.748 |
BACK | -3.698 |
rightfully | -3.539 |
Token | - |
Token ID | 12 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
eming | +8.115 |
toggle | +5.783 |
atown | +5.749 |
slowing | +5.733 |
texting | +5.700 |
Neg logit contributions | |
ought | -6.565 |
rightly | -6.149 |
Parables | -6.101 |
BACK | -5.881 |
rightfully | -5.778 |
Token | Kim |
Token ID | 26374 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
eming | +6.586 |
atown | +4.697 |
toggle | +4.621 |
texting | +4.534 |
slowing | +4.480 |
Neg logit contributions | |
ought | -5.539 |
rightly | -5.426 |
Parables | -5.424 |
rightfully | -5.024 |
BACK | -4.972 |
Token | summit |
Token ID | 14237 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
eming | +13.078 |
interactions | +9.022 |
texting | +8.945 |
Appears | +8.761 |
ャ | +8.714 |
Neg logit contributions | |
odder | -10.893 |
ought | -10.860 |
BACK | -10.564 |
Parables | -10.375 |
fortunately | -10.036 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
eming | +7.090 |
atown | +5.209 |
Appears | +4.825 |
toggle | +4.807 |
texting | +4.669 |
Neg logit contributions | |
ought | -7.314 |
rightly | -7.032 |
rightfully | -6.708 |
extraord | -6.603 |
fortune | -6.596 |
Token | 's |
Token ID | 338 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
eming | +5.641 |
texting | +4.016 |
slowing | +3.923 |
toggle | +3.895 |
atown | +3.892 |
Neg logit contributions | |
ought | -5.792 |
rightly | -5.602 |
Parables | -5.393 |
BACK | -5.371 |
rightfully | -5.247 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
eming | +3.818 |
atown | +2.727 |
toggle | +2.714 |
texting | +2.700 |
slowing | +2.656 |
Neg logit contributions | |
ought | -3.423 |
rightly | -3.332 |
BACK | -3.177 |
rightfully | -3.132 |
Parables | -3.110 |
Token | say |
Token ID | 910 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
eming | +0.961 |
toggle | +0.696 |
atown | +0.690 |
texting | +0.678 |
slowing | +0.671 |
Neg logit contributions | |
ought | -0.799 |
rightly | -0.774 |
BACK | -0.736 |
rightfully | -0.732 |
Parables | -0.722 |
Token | map |
Token ID | 3975 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
eming | +0.904 |
toggle | +0.671 |
atown | +0.671 |
texting | +0.655 |
slowing | +0.651 |
Neg logit contributions | |
ought | -0.647 |
rightly | -0.631 |
rightfully | -0.597 |
BACK | -0.592 |
Parables | -0.571 |
Token | of |
Token ID | 286 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ought | +0.147 |
rightly | +0.146 |
rightfully | +0.136 |
BACK | +0.132 |
Parables | +0.129 |
Neg logit contributions | |
eming | -0.243 |
atown | -0.185 |
toggle | -0.185 |
texting | -0.177 |
slowing | -0.175 |
Token | affected |
Token ID | 5676 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ought | +0.050 |
rightly | +0.049 |
rightfully | +0.046 |
BACK | +0.045 |
Parables | +0.045 |
Neg logit contributions | |
eming | -0.068 |
atown | -0.050 |
toggle | -0.050 |
texting | -0.049 |
slowing | -0.048 |
Token | area |
Token ID | 1989 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
rightly | +1.444 |
ought | +1.438 |
rightfully | +1.350 |
BACK | +1.321 |
Parables | +1.294 |
Neg logit contributions | |
eming | -1.880 |
atown | -1.394 |
toggle | -1.372 |
texting | -1.305 |
hyde | -1.297 |
Token | Russia |
Token ID | 3284 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
rightly | +2.311 |
ought | +2.293 |
rightfully | +2.136 |
BACK | +2.098 |
Parables | +2.048 |
Neg logit contributions | |
eming | -3.739 |
atown | -2.840 |
toggle | -2.792 |
hyde | -2.681 |
texting | -2.676 |
Token | shut |
Token ID | 4423 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
eming | +3.598 |
atown | +2.682 |
toggle | +2.673 |
slowing | +2.613 |
texting | +2.600 |
Neg logit contributions | |
ought | -2.688 |
rightly | -2.613 |
Parables | -2.495 |
BACK | -2.470 |
rightfully | -2.442 |
Token | off |
Token ID | 572 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
eming | +12.354 |
toggle | +8.953 |
atown | +8.898 |
slowing | +8.839 |
texting | +8.771 |
Neg logit contributions | |
rightly | -10.210 |
Parables | -10.085 |
ought | -9.935 |
rightfully | -9.719 |
suprem | -9.707 |
Token | the |
Token ID | 262 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
eming | +7.058 |
slowing | +5.236 |
toggle | +5.191 |
texting | +5.183 |
screenings | +5.091 |
Neg logit contributions | |
ought | -5.826 |
rightly | -5.641 |
Parables | -5.596 |
BACK | -5.423 |
rightfully | -5.244 |
Token | gas |
Token ID | 3623 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
eming | +4.352 |
toggle | +3.193 |
slowing | +3.142 |
texting | +3.138 |
atown | +3.107 |
Neg logit contributions | |
ought | -3.547 |
rightly | -3.471 |
Parables | -3.289 |
BACK | -3.265 |
rightfully | -3.245 |
Token | to |
Token ID | 284 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
eming | +0.956 |
toggle | +0.689 |
atown | +0.685 |
texting | +0.661 |
slowing | +0.655 |
Neg logit contributions | |
ought | -0.797 |
rightly | -0.789 |
rightfully | -0.741 |
BACK | -0.740 |
Parables | -0.735 |
Token | Europe |
Token ID | 2031 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
eming | +2.151 |
atown | +1.618 |
toggle | +1.618 |
slowing | +1.571 |
texting | +1.568 |
Neg logit contributions | |
ought | -1.390 |
rightly | -1.362 |
Parables | -1.265 |
rightfully | -1.264 |
BACK | -1.257 |
Token | of |
Token ID | 286 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
eming | +2.364 |
atown | +1.748 |
toggle | +1.736 |
texting | +1.684 |
slowing | +1.667 |
Neg logit contributions | |
ought | -1.704 |
rightly | -1.674 |
BACK | -1.596 |
rightfully | -1.566 |
Parables | -1.559 |
Token | Nebraska |
Token ID | 18329 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
eming | +2.658 |
toggle | +1.795 |
atown | +1.728 |
texting | +1.703 |
slowing | +1.669 |
Neg logit contributions | |
ought | -3.104 |
rightly | -3.062 |
BACK | -2.935 |
rightfully | -2.921 |
Parables | -2.911 |
Token | currently |
Token ID | 3058 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
eming | +1.863 |
atown | +1.378 |
toggle | +1.366 |
texting | +1.314 |
slowing | +1.298 |
Neg logit contributions | |
ought | -1.396 |
rightly | -1.372 |
BACK | -1.296 |
rightfully | -1.284 |
Parables | -1.272 |
Token | has |
Token ID | 468 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
eming | +2.155 |
toggle | +1.516 |
atown | +1.513 |
texting | +1.449 |
slowing | +1.433 |
Neg logit contributions | |
ought | -2.056 |
rightly | -2.007 |
BACK | -1.927 |
Parables | -1.896 |
rightfully | -1.894 |
Token | a |
Token ID | 257 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
eming | +4.954 |
toggle | +3.682 |
atown | +3.591 |
texting | +3.585 |
screenings | +3.552 |
Neg logit contributions | |
ought | -3.747 |
rightly | -3.646 |
BACK | -3.531 |
rightfully | -3.437 |
Parables | -3.415 |
Token | ban |
Token ID | 3958 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
eming | +3.793 |
toggle | +2.700 |
atown | +2.634 |
texting | +2.629 |
slowing | +2.563 |
Neg logit contributions | |
ought | -3.451 |
rightly | -3.363 |
BACK | -3.241 |
rightfully | -3.183 |
Parables | -3.152 |
Token | against |
Token ID | 1028 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
eming | +10.628 |
authorizing | +6.969 |
texting | +6.784 |
slowing | +6.625 |
ordering | +6.545 |
Neg logit contributions | |
ought | -12.688 |
rightly | -12.313 |
Parables | -12.236 |
BACK | -12.159 |
fortune | -11.991 |
Token | gay |
Token ID | 5650 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
eming | +6.221 |
texting | +4.447 |
toggle | +4.389 |
authorizing | +4.375 |
slowing | +4.344 |
Neg logit contributions | |
ought | -6.240 |
rightly | -6.083 |
BACK | -5.878 |
Parables | -5.843 |
rightfully | -5.744 |
Token | marriage |
Token ID | 4845 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
ought | +0.609 |
rightly | +0.608 |
rightfully | +0.571 |
BACK | +0.560 |
Parables | +0.550 |
Neg logit contributions | |
eming | -0.707 |
atown | -0.513 |
toggle | -0.507 |
texting | -0.480 |
hyde | -0.478 |
Token | , |
Token ID | 11 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
eming | +3.645 |
atown | +2.656 |
toggle | +2.643 |
texting | +2.576 |
screenings | +2.543 |
Neg logit contributions | |
ought | -3.089 |
rightly | -3.028 |
BACK | -2.852 |
rightfully | -2.831 |
Parables | -2.831 |
Token | the |
Token ID | 262 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
eming | +4.369 |
toggle | +3.202 |
atown | +3.170 |
texting | +3.122 |
screenings | +3.071 |
Neg logit contributions | |
ought | -3.678 |
rightly | -3.555 |
BACK | -3.431 |
Parables | -3.380 |
rightfully | -3.348 |
Token | system |
Token ID | 1080 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
eming | +1.209 |
atown | +0.858 |
toggle | +0.844 |
texting | +0.813 |
slowing | +0.799 |
Neg logit contributions | |
ought | -1.166 |
rightly | -1.154 |
rightfully | -1.088 |
BACK | -1.081 |
Parables | -1.064 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
eming | +0.988 |
atown | +0.738 |
toggle | +0.723 |
texting | +0.704 |
slowing | +0.702 |
Neg logit contributions | |
ought | -0.702 |
rightly | -0.691 |
rightfully | -0.646 |
BACK | -0.644 |
Parables | -0.641 |
Token | make |
Token ID | 787 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
rightly | +0.837 |
ought | +0.836 |
rightfully | +0.782 |
BACK | +0.765 |
Parables | +0.750 |
Neg logit contributions | |
eming | -1.157 |
atown | -0.862 |
toggle | -0.854 |
texting | -0.817 |
hyde | -0.805 |
Token | it |
Token ID | 340 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
eming | +0.847 |
atown | +0.614 |
toggle | +0.605 |
texting | +0.582 |
slowing | +0.574 |
Neg logit contributions | |
ought | -0.735 |
rightly | -0.730 |
rightfully | -0.686 |
BACK | -0.680 |
Parables | -0.670 |
Token | equally |
Token ID | 8603 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
eming | +2.770 |
atown | +2.105 |
toggle | +2.074 |
slowing | +2.026 |
texting | +2.025 |
Neg logit contributions | |
ought | -1.753 |
rightly | -1.703 |
Parables | -1.587 |
rightfully | -1.576 |
BACK | -1.565 |
Token | fair |
Token ID | 3148 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
eming | +11.295 |
slowing | +8.546 |
contagious | +8.484 |
atown | +8.398 |
texting | +8.394 |
Neg logit contributions | |
ought | -6.897 |
Parables | -6.643 |
rightly | -6.400 |
BACK | -6.160 |
Vice | -6.141 |
Token | for |
Token ID | 329 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
eming | +11.592 |
atown | +8.252 |
slowing | +8.127 |
texting | +7.981 |
favoring | +7.919 |
Neg logit contributions | |
ought | -10.775 |
Parables | -10.484 |
BACK | -10.131 |
rightly | -10.064 |
Vice | -9.992 |
Token | every |
Token ID | 790 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
eming | +3.061 |
atown | +2.184 |
toggle | +2.156 |
texting | +2.101 |
slowing | +2.072 |
Neg logit contributions | |
ought | -2.783 |
rightly | -2.726 |
BACK | -2.595 |
Parables | -2.560 |
rightfully | -2.555 |
Token | citizen |
Token ID | 9511 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
eming | +2.788 |
atown | +1.981 |
toggle | +1.947 |
texting | +1.884 |
slowing | +1.866 |
Neg logit contributions | |
ought | -2.642 |
rightly | -2.613 |
BACK | -2.483 |
Parables | -2.458 |
rightfully | -2.444 |
Token | . |
Token ID | 13 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
eming | +4.447 |
atown | +3.332 |
toggle | +3.234 |
texting | +3.221 |
slowing | +3.205 |
Neg logit contributions | |
ought | -3.069 |
rightly | -2.954 |
Parables | -2.821 |
BACK | -2.821 |
rightfully | -2.724 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
rightly | +2.833 |
ought | +2.810 |
rightfully | +2.604 |
BACK | +2.553 |
Parables | +2.499 |
Neg logit contributions | |
eming | -5.216 |
atown | -4.011 |
toggle | -3.984 |
texting | -3.845 |
slowing | -3.801 |
Token | information |
Token ID | 1321 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
rightly | +3.422 |
ought | +3.400 |
rightfully | +3.117 |
BACK | +3.066 |
Parables | +3.005 |
Neg logit contributions | |
eming | -6.078 |
atown | -4.674 |
toggle | -4.643 |
hyde | -4.406 |
texting | -4.389 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ought | +0.650 |
rightly | +0.645 |
rightfully | +0.602 |
BACK | +0.587 |
Parables | +0.581 |
Neg logit contributions | |
eming | -1.023 |
atown | -0.775 |
toggle | -0.766 |
texting | -0.743 |
screenings | -0.732 |
Token | CNN |
Token ID | 18474 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
ought | +0.807 |
rightly | +0.807 |
rightfully | +0.756 |
BACK | +0.739 |
Parables | +0.733 |
Neg logit contributions | |
eming | -1.006 |
atown | -0.735 |
toggle | -0.733 |
texting | -0.695 |
hyde | -0.685 |
Token | is |
Token ID | 318 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
eming | +3.686 |
toggle | +2.768 |
atown | +2.706 |
screenings | +2.604 |
Appears | +2.584 |
Neg logit contributions | |
ought | -2.841 |
rightly | -2.782 |
Parables | -2.667 |
BACK | -2.663 |
rightfully | -2.620 |
Token | not |
Token ID | 407 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
eming | +2.258 |
toggle | +1.592 |
atown | +1.586 |
texting | +1.565 |
slowing | +1.554 |
Neg logit contributions | |
ought | -2.170 |
rightly | -2.072 |
BACK | -1.990 |
Parables | -1.987 |
rightfully | -1.953 |
Token | renew |
Token ID | 6931 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
eming | +0.565 |
atown | +0.408 |
toggle | +0.403 |
texting | +0.389 |
slowing | +0.384 |
Neg logit contributions | |
ought | -0.493 |
rightly | -0.487 |
rightfully | -0.458 |
BACK | -0.454 |
Parables | -0.448 |
Token | ing |
Token ID | 278 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
eming | +10.743 |
texting | +7.265 |
authorizing | +7.149 |
screenings | +7.007 |
slowing | +7.000 |
Neg logit contributions | |
ought | -11.901 |
rightly | -11.769 |
BACK | -11.501 |
Parables | -11.413 |
rightfully | -11.150 |
Token | Re |
Token ID | 797 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
eming | +7.715 |
screenings | +5.545 |
texting | +5.470 |
toggle | +5.333 |
slowing | +5.330 |
Neg logit contributions | |
ought | -8.203 |
rightly | -8.002 |
BACK | -7.807 |
Parables | -7.645 |
rightfully | -7.542 |
Token | za |
Token ID | 4496 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
eming | +8.029 |
atown | +5.791 |
toggle | +5.657 |
alert | +5.559 |
roma | +5.519 |
Neg logit contributions | |
rightly | -5.475 |
ought | -5.357 |
Parables | -5.272 |
rightfully | -5.160 |
BACK | -5.088 |
Token | As |
Token ID | 1081 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
eming | +3.232 |
texting | +2.261 |
toggle | +2.259 |
atown | +2.218 |
slowing | +2.213 |
Neg logit contributions | |
ought | -3.223 |
rightly | -3.172 |
BACK | -3.046 |
Parables | -3.036 |
rightfully | -3.003 |
Token | lan |
Token ID | 9620 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
eming | +3.075 |
atown | +2.247 |
toggle | +2.245 |
alert | +2.133 |
hyde | +2.113 |
Neg logit contributions | |
ought | -2.131 |
rightly | -2.115 |
BACK | -2.005 |
rightfully | -2.001 |
Parables | -1.973 |
Token | on |
Token ID | 319 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
eming | +0.164 |
atown | +0.122 |
toggle | +0.121 |
texting | +0.115 |
hyde | +0.114 |
Neg logit contributions | |
rightly | -0.121 |
ought | -0.121 |
rightfully | -0.114 |
BACK | -0.111 |
Parables | -0.109 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
eming | +4.454 |
texting | +3.027 |
toggle | +2.965 |
slowing | +2.879 |
alert | +2.793 |
Neg logit contributions | |
ought | -5.201 |
rightly | -4.952 |
BACK | -4.832 |
Parables | -4.770 |
rightfully | -4.703 |
Token | of |
Token ID | 286 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
eming | +4.086 |
toggle | +3.105 |
atown | +3.037 |
texting | +2.961 |
slowing | +2.946 |
Neg logit contributions | |
ought | -2.487 |
rightly | -2.470 |
rightfully | -2.296 |
BACK | -2.245 |
Parables | -2.230 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
eming | +4.663 |
toggle | +3.264 |
slowing | +3.206 |
texting | +3.203 |
atown | +3.131 |
Neg logit contributions | |
ought | -4.111 |
Parables | -3.990 |
rightly | -3.960 |
BACK | -3.925 |
rightfully | -3.729 |
Token | - |
Token ID | 12 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
eming | +8.031 |
slowing | +5.669 |
toggle | +5.654 |
atown | +5.610 |
ordering | +5.601 |
Neg logit contributions | |
ought | -6.615 |
Parables | -6.274 |
rightly | -6.171 |
BACK | -5.927 |
rightfully | -5.791 |
Token | Kim |
Token ID | 26374 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
eming | +6.576 |
atown | +4.669 |
toggle | +4.640 |
texting | +4.525 |
slowing | +4.497 |
Neg logit contributions | |
ought | -5.350 |
rightly | -5.278 |
Parables | -5.216 |
rightfully | -4.866 |
suprem | -4.800 |
Token | summit |
Token ID | 14237 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
eming | +12.894 |
interactions | +8.880 |
texting | +8.781 |
Appears | +8.632 |
ャ | +8.541 |
Neg logit contributions | |
odder | -10.730 |
ought | -10.636 |
BACK | -10.448 |
Parables | -10.256 |
fortunately | -9.975 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
eming | +6.628 |
atown | +4.803 |
toggle | +4.383 |
Appears | +4.309 |
Archdemon | +4.287 |
Neg logit contributions | |
ought | -7.103 |
rightly | -6.849 |
rightfully | -6.561 |
BACK | -6.539 |
extraord | -6.533 |
Token | 's |
Token ID | 338 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
eming | +5.398 |
texting | +3.785 |
slowing | +3.721 |
toggle | +3.698 |
atown | +3.693 |
Neg logit contributions | |
ought | -5.587 |
rightly | -5.409 |
Parables | -5.185 |
BACK | -5.177 |
rightfully | -5.072 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
eming | +3.701 |
atown | +2.641 |
toggle | +2.622 |
texting | +2.612 |
slowing | +2.571 |
Neg logit contributions | |
ought | -3.326 |
rightly | -3.242 |
BACK | -3.106 |
Parables | -3.050 |
rightfully | -3.042 |
Token | say |
Token ID | 910 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
eming | +0.747 |
toggle | +0.538 |
atown | +0.534 |
texting | +0.526 |
slowing | +0.521 |
Neg logit contributions | |
ought | -0.621 |
rightly | -0.601 |
BACK | -0.575 |
rightfully | -0.569 |
Parables | -0.561 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
eming | +4.614 |
atown | +3.415 |
toggle | +3.404 |
texting | +3.299 |
slowing | +3.250 |
Neg logit contributions | |
ought | -3.486 |
rightly | -3.404 |
BACK | -3.239 |
Parables | -3.228 |
rightfully | -3.187 |
Token | � |
Token ID | 447 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ought | +1.422 |
rightly | +1.412 |
rightfully | +1.297 |
BACK | +1.285 |
Vice | +1.230 |
Neg logit contributions | |
eming | -2.379 |
atown | -1.828 |
toggle | -1.769 |
texting | -1.745 |
hyde | -1.724 |
Token | � |
Token ID | 247 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
eming | +1.388 |
atown | +0.977 |
toggle | +0.966 |
texting | +0.914 |
slowing | +0.900 |
Neg logit contributions | |
ought | -1.395 |
rightly | -1.393 |
rightfully | -1.316 |
BACK | -1.295 |
Parables | -1.278 |
Token | t |
Token ID | 83 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
eming | +0.888 |
atown | +0.653 |
toggle | +0.644 |
texting | +0.618 |
slowing | +0.608 |
Neg logit contributions | |
ought | -0.702 |
rightly | -0.698 |
rightfully | -0.653 |
BACK | -0.642 |
Parables | -0.630 |
Token | completely |
Token ID | 3190 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
eming | +0.294 |
atown | +0.220 |
toggle | +0.219 |
texting | +0.211 |
slowing | +0.208 |
Neg logit contributions | |
ought | -0.200 |
rightly | -0.198 |
rightfully | -0.184 |
BACK | -0.183 |
Parables | -0.179 |
Token | shut |
Token ID | 4423 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
eming | +1.602 |
atown | +1.190 |
toggle | +1.184 |
texting | +1.148 |
slowing | +1.135 |
Neg logit contributions | |
ought | -1.215 |
rightly | -1.194 |
BACK | -1.117 |
rightfully | -1.113 |
Parables | -1.100 |
Token | her |
Token ID | 607 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
eming | +10.556 |
atown | +7.723 |
toggle | +7.586 |
texting | +7.485 |
screenings | +7.298 |
Neg logit contributions | |
rightly | -11.468 |
ought | -11.233 |
Parables | -10.985 |
BACK | -10.834 |
rightfully | -10.791 |
Token | out |
Token ID | 503 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
eming | +5.502 |
atown | +4.004 |
toggle | +3.981 |
texting | +3.967 |
screenings | +3.900 |
Neg logit contributions | |
ought | -4.407 |
rightly | -4.319 |
Parables | -4.115 |
BACK | -4.060 |
rightfully | -4.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
eming | +8.000 |
atown | +6.010 |
texting | +5.936 |
toggle | +5.828 |
slowing | +5.785 |
Neg logit contributions | |
ought | -6.223 |
rightly | -5.880 |
BACK | -5.683 |
Parables | -5.674 |
rightfully | -5.500 |
Token | � |
Token ID | 564 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
eming | +1.972 |
toggle | +1.466 |
atown | +1.456 |
texting | +1.384 |
hyde | +1.358 |
Neg logit contributions | |
ought | -1.514 |
rightly | -1.490 |
rightfully | -1.399 |
BACK | -1.368 |
Parables | -1.346 |
Token | � |
Token ID | 250 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
eming | +0.580 |
atown | +0.397 |
toggle | +0.392 |
texting | +0.370 |
slowing | +0.363 |
Neg logit contributions | |
ought | -0.651 |
rightly | -0.650 |
rightfully | -0.616 |
BACK | -0.607 |
Parables | -0.599 |
Token | on |
Token ID | 319 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
rightly | +0.130 |
ought | +0.130 |
rightfully | +0.122 |
BACK | +0.119 |
Parables | +0.117 |
Neg logit contributions | |
eming | -0.165 |
atown | -0.121 |
toggle | -0.120 |
texting | -0.114 |
hyde | -0.113 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
eming | +4.438 |
texting | +2.989 |
toggle | +2.940 |
slowing | +2.847 |
alert | +2.747 |
Neg logit contributions | |
ought | -5.350 |
rightly | -5.118 |
BACK | -4.972 |
Parables | -4.915 |
rightfully | -4.862 |
Token | of |
Token ID | 286 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
eming | +3.557 |
toggle | +2.703 |
atown | +2.668 |
texting | +2.585 |
slowing | +2.570 |
Neg logit contributions | |
ought | -2.117 |
rightly | -2.104 |
rightfully | -1.951 |
BACK | -1.911 |
Parables | -1.889 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
eming | +4.815 |
toggle | +3.381 |
slowing | +3.324 |
texting | +3.310 |
atown | +3.240 |
Neg logit contributions | |
ought | -4.204 |
Parables | -4.102 |
rightly | -4.041 |
BACK | -3.998 |
rightfully | -3.802 |
Token | - |
Token ID | 12 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
eming | +8.194 |
atown | +5.863 |
toggle | +5.848 |
slowing | +5.804 |
texting | +5.713 |
Neg logit contributions | |
ought | -6.451 |
Parables | -6.083 |
rightly | -6.062 |
BACK | -5.719 |
rightfully | -5.706 |
Token | Kim |
Token ID | 26374 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
eming | +6.940 |
atown | +4.925 |
toggle | +4.896 |
texting | +4.772 |
slowing | +4.721 |
Neg logit contributions | |
ought | -5.471 |
rightly | -5.412 |
Parables | -5.313 |
rightfully | -5.001 |
suprem | -4.956 |
Token | summit |
Token ID | 14237 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
eming | +12.905 |
interactions | +8.818 |
texting | +8.789 |
ャ | +8.578 |
Appears | +8.474 |
Neg logit contributions | |
ought | -10.695 |
odder | -10.604 |
BACK | -10.270 |
Parables | -10.191 |
fortunately | -9.954 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
eming | +6.312 |
atown | +4.532 |
toggle | +4.127 |
Archdemon | +4.066 |
Appears | +4.048 |
Neg logit contributions | |
ought | -7.103 |
rightly | -6.771 |
rightfully | -6.513 |
extraord | -6.467 |
BACK | -6.467 |
Token | 's |
Token ID | 338 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
eming | +4.904 |
texting | +3.442 |
toggle | +3.387 |
slowing | +3.387 |
atown | +3.373 |
Neg logit contributions | |
ought | -5.024 |
rightly | -4.892 |
Parables | -4.672 |
BACK | -4.642 |
rightfully | -4.594 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
eming | +3.548 |
atown | +2.512 |
toggle | +2.512 |
texting | +2.465 |
slowing | +2.433 |
Neg logit contributions | |
ought | -3.262 |
rightly | -3.196 |
BACK | -3.035 |
rightfully | -3.000 |
Parables | -2.999 |
Token | say |
Token ID | 910 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
eming | +0.785 |
toggle | +0.567 |
atown | +0.564 |
texting | +0.552 |
slowing | +0.547 |
Neg logit contributions | |
ought | -0.644 |
rightly | -0.627 |
BACK | -0.595 |
rightfully | -0.592 |
Parables | -0.578 |
Token | reading |
Token ID | 3555 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
eming | +1.665 |
toggle | +1.196 |
atown | +1.184 |
texting | +1.160 |
screenings | +1.150 |
Neg logit contributions | |
ought | -1.470 |
rightly | -1.450 |
rightfully | -1.358 |
BACK | -1.349 |
Parables | -1.347 |
Token | privacy |
Token ID | 6782 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
eming | +2.028 |
toggle | +1.502 |
atown | +1.494 |
texting | +1.465 |
screenings | +1.445 |
Neg logit contributions | |
ought | -1.473 |
rightly | -1.457 |
rightfully | -1.359 |
Parables | -1.345 |
BACK | -1.342 |
Token | or |
Token ID | 393 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
rightly | +4.187 |
ought | +4.147 |
rightfully | +3.916 |
BACK | +3.785 |
suprem | +3.703 |
Neg logit contributions | |
eming | -5.387 |
atown | -3.992 |
toggle | -3.924 |
hyde | -3.749 |
Archdemon | -3.669 |
Token | require |
Token ID | 2421 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
eming | +2.420 |
atown | +1.737 |
toggle | +1.728 |
texting | +1.708 |
slowing | +1.673 |
Neg logit contributions | |
ought | -2.090 |
rightly | -2.055 |
BACK | -1.935 |
rightfully | -1.926 |
Parables | -1.915 |
Token | a |
Token ID | 257 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
eming | +6.724 |
texting | +4.965 |
screenings | +4.941 |
toggle | +4.850 |
atown | +4.821 |
Neg logit contributions | |
ought | -6.021 |
rightly | -5.817 |
Parables | -5.635 |
BACK | -5.535 |
rightfully | -5.462 |
Token | warrant |
Token ID | 8084 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
eming | +4.173 |
toggle | +2.994 |
atown | +2.991 |
texting | +2.959 |
slowing | +2.896 |
Neg logit contributions | |
ought | -3.605 |
rightly | -3.552 |
Parables | -3.321 |
rightfully | -3.320 |
BACK | -3.305 |
Token | to |
Token ID | 284 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
eming | +12.002 |
authorizing | +9.276 |
ordering | +8.479 |
slowing | +8.479 |
atown | +8.471 |
Neg logit contributions | |
rightly | -9.852 |
ought | -9.802 |
Parables | -9.729 |
fortune | -9.569 |
BACK | -9.533 |
Token | obtain |
Token ID | 7330 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
eming | +2.857 |
toggle | +2.015 |
atown | +2.003 |
texting | +1.930 |
screenings | +1.926 |
Neg logit contributions | |
ought | -2.807 |
rightly | -2.748 |
BACK | -2.594 |
Parables | -2.584 |
rightfully | -2.581 |
Token | book |
Token ID | 1492 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
eming | +0.531 |
atown | +0.391 |
toggle | +0.388 |
texting | +0.375 |
screenings | +0.370 |
Neg logit contributions | |
ought | -0.408 |
rightly | -0.406 |
rightfully | -0.380 |
BACK | -0.375 |
Parables | -0.371 |
Token | sales |
Token ID | 4200 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
eming | +3.868 |
toggle | +2.782 |
atown | +2.767 |
screenings | +2.753 |
texting | +2.711 |
Neg logit contributions | |
ought | -3.401 |
rightly | -3.348 |
rightfully | -3.133 |
Parables | -3.115 |
BACK | -3.084 |
Token | , |
Token ID | 11 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
eming | +1.479 |
atown | +1.094 |
toggle | +1.079 |
texting | +1.053 |
screenings | +1.044 |
Neg logit contributions | |
ought | -1.105 |
rightly | -1.095 |
rightfully | -1.018 |
BACK | -1.007 |
Parables | -0.998 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
eming | +1.099 |
atown | +0.784 |
toggle | +0.773 |
texting | +0.738 |
slowing | +0.727 |
Neg logit contributions | |
ought | -1.036 |
rightly | -1.030 |
rightfully | -0.973 |
BACK | -0.962 |
Parables | -0.950 |
Token | , |
Token ID | 11 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
rightly | +2.520 |
ought | +2.493 |
rightfully | +2.292 |
BACK | +2.231 |
Parables | +2.176 |
Neg logit contributions | |
eming | -4.792 |
atown | -3.699 |
toggle | -3.671 |
hyde | -3.516 |
texting | -3.513 |
Token | Georgia |
Token ID | 7859 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
eming | +4.515 |
toggle | +3.217 |
atown | +3.201 |
texting | +3.172 |
slowing | +3.165 |
Neg logit contributions | |
ought | -4.215 |
rightly | -3.997 |
BACK | -3.928 |
Parables | -3.928 |
rightfully | -3.825 |
Token | , |
Token ID | 11 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
ought | +1.331 |
rightly | +1.326 |
rightfully | +1.239 |
BACK | +1.217 |
Parables | +1.198 |
Neg logit contributions | |
eming | -1.827 |
atown | -1.360 |
toggle | -1.347 |
texting | -1.290 |
slowing | -1.274 |
Token | to |
Token ID | 284 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ought | +0.355 |
rightly | +0.352 |
rightfully | +0.325 |
BACK | +0.319 |
Parables | +0.313 |
Neg logit contributions | |
eming | -0.658 |
atown | -0.509 |
toggle | -0.506 |
texting | -0.488 |
slowing | -0.483 |
Token | halt |
Token ID | 17369 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
eming | +0.757 |
atown | +0.545 |
toggle | +0.545 |
texting | +0.521 |
slowing | +0.515 |
Neg logit contributions | |
ought | -0.658 |
rightly | -0.646 |
rightfully | -0.608 |
BACK | -0.606 |
Parables | -0.596 |
Token | its |
Token ID | 663 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
eming | +11.687 |
screenings | +9.208 |
texting | +8.782 |
contagious | +8.490 |
slowing | +8.462 |
Neg logit contributions | |
ought | -10.647 |
BACK | -10.022 |
rightly | -9.976 |
Parables | -9.969 |
rightfully | -9.797 |
Token | tracking |
Token ID | 9646 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
eming | +5.512 |
toggle | +3.979 |
screenings | +3.935 |
texting | +3.929 |
atown | +3.917 |
Neg logit contributions | |
ought | -4.667 |
rightly | -4.583 |
BACK | -4.359 |
rightfully | -4.357 |
Parables | -4.297 |
Token | of |
Token ID | 286 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
rightly | +2.243 |
ought | +2.241 |
rightfully | +2.045 |
BACK | +2.006 |
Parables | +1.948 |
Neg logit contributions | |
eming | -4.091 |
atown | -3.190 |
toggle | -3.141 |
texting | -2.998 |
hyde | -2.990 |
Token | influenza |
Token ID | 29491 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
ought | +0.038 |
rightly | +0.038 |
rightfully | +0.036 |
BACK | +0.035 |
Parables | +0.035 |
Neg logit contributions | |
eming | -0.043 |
atown | -0.031 |
toggle | -0.031 |
texting | -0.029 |
slowing | -0.029 |
Token | cases |
Token ID | 2663 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
rightly | +2.573 |
ought | +2.572 |
rightfully | +2.405 |
BACK | +2.363 |
Parables | +2.315 |
Neg logit contributions | |
eming | -3.201 |
atown | -2.355 |
toggle | -2.322 |
texting | -2.207 |
hyde | -2.189 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
eming | +2.323 |
toggle | +1.818 |
atown | +1.807 |
texting | +1.739 |
alert | +1.722 |
Neg logit contributions | |
ought | -1.093 |
rightly | -1.087 |
rightfully | -0.998 |
BACK | -0.967 |
Parables | -0.959 |
Token | The |
Token ID | 464 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
eming | +0.875 |
toggle | +0.660 |
atown | +0.633 |
alert | +0.607 |
texting | +0.603 |
Neg logit contributions | |
rightly | -0.673 |
ought | -0.666 |
rightfully | -0.633 |
Parables | -0.620 |
suprem | -0.605 |
Token | government |
Token ID | 1230 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
eming | +1.852 |
toggle | +1.342 |
atown | +1.334 |
texting | +1.299 |
slowing | +1.287 |
Neg logit contributions | |
ought | -1.547 |
rightly | -1.527 |
rightfully | -1.435 |
BACK | -1.423 |
Parables | -1.403 |
Token | had |
Token ID | 550 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
eming | +0.330 |
atown | +0.246 |
toggle | +0.245 |
texting | +0.235 |
slowing | +0.233 |
Neg logit contributions | |
ought | -0.231 |
rightly | -0.229 |
rightfully | -0.214 |
BACK | -0.211 |
Parables | -0.209 |
Token | largely |
Token ID | 5688 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
eming | +1.706 |
atown | +1.281 |
toggle | +1.280 |
texting | +1.249 |
slowing | +1.244 |
Neg logit contributions | |
ought | -1.145 |
rightly | -1.113 |
BACK | -1.062 |
Parables | -1.054 |
rightfully | -1.038 |
Token | halted |
Token ID | 27771 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
eming | +1.671 |
atown | +1.269 |
toggle | +1.265 |
texting | +1.228 |
slowing | +1.223 |
Neg logit contributions | |
ought | -1.055 |
rightly | -1.036 |
rightfully | -0.963 |
BACK | -0.960 |
Parables | -0.958 |
Token | street |
Token ID | 4675 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
eming | +10.915 |
screenings | +8.509 |
slowing | +8.387 |
texting | +8.387 |
authorizing | +8.142 |
Neg logit contributions | |
ought | -10.753 |
Parables | -10.420 |
rightly | -10.367 |
BACK | -10.293 |
fortune | -10.177 |
Token | protests |
Token ID | 8536 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
eming | +2.077 |
toggle | +1.502 |
atown | +1.483 |
screenings | +1.445 |
texting | +1.434 |
Neg logit contributions | |
ought | -1.966 |
rightly | -1.950 |
rightfully | -1.835 |
Parables | -1.821 |
BACK | -1.816 |
Token | in |
Token ID | 287 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
eming | +0.298 |
atown | +0.221 |
toggle | +0.219 |
texting | +0.210 |
slowing | +0.207 |
Neg logit contributions | |
ought | -0.224 |
rightly | -0.223 |
rightfully | -0.208 |
BACK | -0.205 |
Parables | -0.202 |
Token | July |
Token ID | 2901 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
eming | +1.658 |
atown | +1.212 |
toggle | +1.208 |
texting | +1.165 |
slowing | +1.155 |
Neg logit contributions | |
ought | -1.340 |
rightly | -1.330 |
rightfully | -1.246 |
BACK | -1.238 |
Parables | -1.211 |
Token | , |
Token ID | 11 |
Feature activation | -7.58e-03 |
Pos logit contributions | |
eming | +0.098 |
atown | +0.073 |
toggle | +0.072 |
texting | +0.069 |
slowing | +0.068 |
Neg logit contributions | |
ought | -0.073 |
rightly | -0.073 |
rightfully | -0.068 |
BACK | -0.067 |
Parables | -0.066 |
Token | 30 |
Token ID | 1542 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
rightly | +1.946 |
ought | +1.940 |
rightfully | +1.805 |
BACK | +1.745 |
suprem | +1.702 |
Neg logit contributions | |
eming | -2.868 |
atown | -2.122 |
toggle | -2.091 |
hyde | -2.018 |
alert | -1.982 |
Token | . |
Token ID | 13 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
eming | +3.133 |
toggle | +2.329 |
atown | +2.329 |
texting | +2.231 |
screenings | +2.196 |
Neg logit contributions | |
ought | -2.471 |
rightly | -2.444 |
rightfully | -2.306 |
BACK | -2.288 |
Parables | -2.279 |
Token | After |
Token ID | 2293 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
eming | +2.490 |
toggle | +1.872 |
atown | +1.844 |
texting | +1.769 |
hyde | +1.730 |
Neg logit contributions | |
ought | -1.798 |
rightly | -1.790 |
rightfully | -1.684 |
BACK | -1.642 |
Parables | -1.630 |
Token | I |
Token ID | 314 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
rightly | +1.164 |
ought | +1.161 |
rightfully | +1.084 |
BACK | +1.055 |
Parables | +1.033 |
Neg logit contributions | |
eming | -1.655 |
atown | -1.240 |
toggle | -1.223 |
texting | -1.162 |
hyde | -1.162 |
Token | joined |
Token ID | 5399 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
rightly | +2.196 |
ought | +2.174 |
rightfully | +2.030 |
BACK | +1.917 |
suprem | +1.834 |
Neg logit contributions | |
eming | -4.037 |
atown | -3.094 |
toggle | -3.072 |
hyde | -2.948 |
texting | -2.947 |
Token | Pf |
Token ID | 38477 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
eming | +4.049 |
atown | +2.964 |
toggle | +2.925 |
texting | +2.884 |
slowing | +2.793 |
Neg logit contributions | |
ought | -3.430 |
rightly | -3.383 |
BACK | -3.207 |
rightfully | -3.177 |
Parables | -3.176 |
Token | izer |
Token ID | 7509 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
eming | +6.605 |
atown | +3.054 |
toggle | +2.244 |
slowing | +2.181 |
alert | +2.105 |
Neg logit contributions | |
rightly | -15.902 |
BACK | -15.739 |
Parables | -15.728 |
rightfully | -15.360 |
Lenin | -15.320 |
Token | Pharmaceutical |
Token ID | 37175 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
eming | +3.226 |
atown | +2.379 |
toggle | +2.347 |
texting | +2.262 |
slowing | +2.250 |
Neg logit contributions | |
ought | -2.557 |
rightly | -2.536 |
Parables | -2.388 |
rightfully | -2.379 |
BACK | -2.370 |
Token | s |
Token ID | 82 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
eming | +4.949 |
toggle | +3.063 |
atown | +2.981 |
slowing | +2.931 |
alert | +2.899 |
Neg logit contributions | |
rightly | -6.774 |
ought | -6.750 |
BACK | -6.585 |
Parables | -6.550 |
rightfully | -6.462 |
Token | , |
Token ID | 11 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
eming | +1.416 |
atown | +1.045 |
toggle | +1.035 |
texting | +0.995 |
slowing | +0.989 |
Neg logit contributions | |
ought | -1.094 |
rightly | -1.085 |
rightfully | -1.016 |
BACK | -1.013 |
Parables | -1.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
eming | +2.894 |
atown | +2.166 |
toggle | +2.157 |
texting | +2.096 |
slowing | +2.072 |
Neg logit contributions | |
ought | -2.042 |
rightly | -1.999 |
BACK | -1.879 |
Parables | -1.873 |
rightfully | -1.860 |
Token | company |
Token ID | 1664 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
eming | +3.935 |
toggle | +2.626 |
texting | +2.608 |
slowing | +2.519 |
atown | +2.504 |
Neg logit contributions | |
ought | -5.472 |
rightly | -5.421 |
Parables | -5.311 |
BACK | -5.191 |
rightfully | -5.139 |
Token | , |
Token ID | 11 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
eming | +1.907 |
toggle | +1.381 |
atown | +1.381 |
texting | +1.343 |
slowing | +1.318 |
Neg logit contributions | |
ought | -1.566 |
rightly | -1.550 |
Parables | -1.462 |
BACK | -1.457 |
rightfully | -1.453 |
Token | is |
Token ID | 318 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
eming | +2.041 |
atown | +1.504 |
toggle | +1.493 |
texting | +1.448 |
slowing | +1.433 |
Neg logit contributions | |
ought | -1.597 |
rightly | -1.559 |
BACK | -1.486 |
Parables | -1.477 |
rightfully | -1.460 |
Token | going |
Token ID | 1016 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
eming | +1.415 |
atown | +1.019 |
toggle | +1.013 |
texting | +0.985 |
slowing | +0.973 |
Neg logit contributions | |
ought | -1.227 |
rightly | -1.205 |
BACK | -1.131 |
rightfully | -1.131 |
Parables | -1.123 |
Token | to |
Token ID | 284 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
eming | +0.246 |
atown | +0.182 |
toggle | +0.181 |
texting | +0.174 |
slowing | +0.171 |
Neg logit contributions | |
ought | -0.191 |
rightly | -0.189 |
rightfully | -0.177 |
BACK | -0.175 |
Parables | -0.173 |
Token | ban |
Token ID | 3958 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
eming | +1.513 |
toggle | +1.092 |
atown | +1.088 |
texting | +1.045 |
slowing | +1.039 |
Neg logit contributions | |
ought | -1.290 |
rightly | -1.259 |
BACK | -1.185 |
Parables | -1.183 |
rightfully | -1.179 |
Token | most |
Token ID | 749 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
eming | +11.886 |
texting | +9.008 |
screenings | +8.590 |
filtering | +8.511 |
slowing | +8.506 |
Neg logit contributions | |
ought | -9.796 |
rightly | -9.482 |
Parables | -9.425 |
BACK | -9.250 |
rightfully | -9.010 |
Token | nude |
Token ID | 26349 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
eming | +2.670 |
toggle | +1.961 |
atown | +1.950 |
texting | +1.931 |
screenings | +1.888 |
Neg logit contributions | |
ought | -1.987 |
rightly | -1.943 |
BACK | -1.824 |
rightfully | -1.814 |
Parables | -1.808 |
Token | photos |
Token ID | 5205 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ought | +1.331 |
rightly | +1.326 |
rightfully | +1.235 |
BACK | +1.205 |
suprem | +1.174 |
Neg logit contributions | |
eming | -1.956 |
atown | -1.484 |
toggle | -1.461 |
hyde | -1.387 |
texting | -1.376 |
Token | and |
Token ID | 290 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
eming | +1.705 |
atown | +1.257 |
toggle | +1.244 |
texting | +1.207 |
slowing | +1.189 |
Neg logit contributions | |
ought | -1.270 |
rightly | -1.257 |
rightfully | -1.172 |
BACK | -1.170 |
Parables | -1.157 |
Token | video |
Token ID | 2008 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
eming | +0.133 |
atown | +0.098 |
toggle | +0.098 |
texting | +0.095 |
slowing | +0.094 |
Neg logit contributions | |
ought | -0.097 |
rightly | -0.096 |
rightfully | -0.089 |
BACK | -0.089 |
Parables | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ought | +0.652 |
rightly | +0.649 |
rightfully | +0.605 |
BACK | +0.596 |
Parables | +0.587 |
Neg logit contributions | |
eming | -0.947 |
atown | -0.710 |
toggle | -0.701 |
texting | -0.676 |
slowing | -0.670 |
Token |
|
Token ID | 198 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
eming | +1.551 |
atown | +1.213 |
toggle | +1.210 |
texting | +1.166 |
slowing | +1.154 |
Neg logit contributions | |
ought | -0.706 |
rightly | -0.703 |
rightfully | -0.642 |
BACK | -0.624 |
Parables | -0.613 |
Token | ' |
Token ID | 6 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
eming | +2.901 |
toggle | +2.158 |
atown | +2.044 |
alert | +1.992 |
texting | +1.958 |
Neg logit contributions | |
rightly | -2.476 |
ought | -2.441 |
rightfully | -2.341 |
Parables | -2.318 |
suprem | -2.257 |
Token | You |
Token ID | 1639 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ought | +0.447 |
rightly | +0.446 |
rightfully | +0.418 |
BACK | +0.412 |
Parables | +0.405 |
Neg logit contributions | |
eming | -0.532 |
atown | -0.387 |
toggle | -0.383 |
texting | -0.365 |
slowing | -0.360 |
Token | could |
Token ID | 714 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
ought | +1.018 |
rightly | +1.016 |
rightfully | +0.945 |
BACK | +0.924 |
Parables | +0.908 |
Neg logit contributions | |
eming | -1.527 |
atown | -1.150 |
toggle | -1.140 |
texting | -1.092 |
hyde | -1.079 |
Token | tell |
Token ID | 1560 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ought | +0.456 |
rightly | +0.449 |
rightfully | +0.419 |
BACK | +0.417 |
Parables | +0.410 |
Neg logit contributions | |
eming | -0.657 |
atown | -0.491 |
toggle | -0.487 |
texting | -0.469 |
slowing | -0.462 |
Token | she |
Token ID | 673 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
rightly | +5.894 |
ought | +5.554 |
rightfully | +5.451 |
suprem | +4.921 |
tyre | +4.862 |
Neg logit contributions | |
eming | -9.433 |
atown | -7.157 |
toggle | -6.811 |
hyde | -6.715 |
alert | -6.542 |
Token | was |
Token ID | 373 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
eming | +0.070 |
atown | +0.052 |
toggle | +0.052 |
texting | +0.050 |
slowing | +0.049 |
Neg logit contributions | |
ought | -0.051 |
rightly | -0.051 |
rightfully | -0.047 |
BACK | -0.047 |
Parables | -0.047 |
Token | hurting |
Token ID | 21530 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
eming | +2.037 |
atown | +1.475 |
toggle | +1.464 |
texting | +1.455 |
slowing | +1.437 |
Neg logit contributions | |
ought | -1.693 |
rightly | -1.636 |
BACK | -1.558 |
Parables | -1.545 |
rightfully | -1.534 |
Token | , |
Token ID | 11 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
rightly | +1.630 |
ought | +1.619 |
rightfully | +1.515 |
BACK | +1.471 |
Parables | +1.434 |
Neg logit contributions | |
eming | -2.373 |
atown | -1.779 |
toggle | -1.766 |
texting | -1.671 |
hyde | -1.666 |
Token | but |
Token ID | 475 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
eming | +2.423 |
atown | +1.746 |
toggle | +1.740 |
texting | +1.729 |
slowing | +1.713 |
Neg logit contributions | |
ought | -2.071 |
rightly | -2.010 |
BACK | -1.925 |
Parables | -1.925 |
rightfully | -1.888 |
Token | having |
Token ID | 1719 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ought | +0.782 |
rightly | +0.779 |
rightfully | +0.735 |
BACK | +0.725 |
Parables | +0.715 |
Neg logit contributions | |
eming | -0.777 |
atown | -0.546 |
toggle | -0.540 |
texting | -0.513 |
slowing | -0.505 |
Token | a |
Token ID | 257 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
rightly | +2.746 |
ought | +2.745 |
rightfully | +2.540 |
BACK | +2.475 |
Parables | +2.418 |
Neg logit contributions | |
eming | -4.371 |
atown | -3.310 |
toggle | -3.281 |
texting | -3.131 |
hyde | -3.118 |
Token | tax |
Token ID | 1687 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
eming | +0.301 |
atown | +0.223 |
toggle | +0.222 |
texting | +0.215 |
slowing | +0.212 |
Neg logit contributions | |
ought | -0.215 |
rightly | -0.214 |
rightfully | -0.200 |
BACK | -0.197 |
Parables | -0.195 |
Token | - |
Token ID | 12 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
eming | +5.581 |
slowing | +3.982 |
toggle | +3.965 |
texting | +3.961 |
atown | +3.958 |
Neg logit contributions | |
ought | -4.549 |
rightly | -4.447 |
Parables | -4.264 |
BACK | -4.264 |
rightfully | -4.193 |
Token | and |
Token ID | 392 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ought | +3.795 |
rightly | +3.737 |
rightfully | +3.510 |
BACK | +3.467 |
suprem | +3.353 |
Neg logit contributions | |
eming | -4.585 |
atown | -3.427 |
toggle | -3.281 |
texting | -3.182 |
screenings | -3.152 |
Token | - |
Token ID | 12 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
rightly | +0.992 |
ought | +0.988 |
rightfully | +0.910 |
BACK | +0.881 |
Parables | +0.848 |
Neg logit contributions | |
eming | -1.801 |
atown | -1.396 |
toggle | -1.369 |
hyde | -1.313 |
texting | -1.313 |
Token | sp |
Token ID | 2777 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ought | +5.827 |
rightly | +5.495 |
BACK | +5.117 |
rightfully | +5.112 |
Vice | +4.867 |
Neg logit contributions | |
eming | -8.572 |
atown | -6.856 |
Archdemon | -6.529 |
screenings | -6.341 |
texting | -6.313 |
Token | end |
Token ID | 437 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
rightly | +0.787 |
ought | +0.784 |
rightfully | +0.747 |
BACK | +0.738 |
Parables | +0.733 |
Neg logit contributions | |
eming | -0.673 |
atown | -0.456 |
toggle | -0.449 |
texting | -0.420 |
slowing | -0.410 |
Token | philosophy |
Token ID | 8876 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
eming | +1.097 |
atown | +0.818 |
toggle | +0.811 |
texting | +0.795 |
slowing | +0.783 |
Neg logit contributions | |
ought | -0.743 |
rightly | -0.738 |
rightfully | -0.688 |
BACK | -0.680 |
Parables | -0.676 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
eming | +0.532 |
atown | +0.400 |
toggle | +0.395 |
texting | +0.382 |
slowing | +0.379 |
Neg logit contributions | |
ought | -0.356 |
rightly | -0.351 |
rightfully | -0.328 |
BACK | -0.325 |
Parables | -0.321 |
Token | The |
Token ID | 383 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
rightly | +1.655 |
ought | +1.655 |
rightfully | +1.533 |
BACK | +1.503 |
Parables | +1.477 |
Neg logit contributions | |
eming | -2.622 |
atown | -1.989 |
toggle | -1.967 |
texting | -1.893 |
slowing | -1.870 |
Token | his |
Token ID | 465 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
eming | +1.554 |
atown | +1.149 |
toggle | +1.135 |
texting | +1.113 |
slowing | +1.097 |
Neg logit contributions | |
ought | -1.175 |
rightly | -1.156 |
BACK | -1.090 |
rightfully | -1.083 |
Parables | -1.063 |
Token | descend |
Token ID | 15350 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
eming | +1.844 |
atown | +1.324 |
toggle | +1.321 |
texting | +1.301 |
slowing | +1.288 |
Neg logit contributions | |
ought | -1.498 |
rightly | -1.464 |
BACK | -1.386 |
rightfully | -1.373 |
Parables | -1.338 |
Token | ents |
Token ID | 658 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
eming | +0.716 |
atown | +0.485 |
toggle | +0.465 |
texting | +0.438 |
alert | +0.432 |
Neg logit contributions | |
rightly | -0.836 |
ought | -0.832 |
rightfully | -0.787 |
BACK | -0.785 |
Parables | -0.782 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
eming | +2.349 |
atown | +1.717 |
toggle | +1.694 |
texting | +1.675 |
slowing | +1.653 |
Neg logit contributions | |
ought | -1.707 |
rightly | -1.679 |
rightfully | -1.575 |
BACK | -1.561 |
Parables | -1.522 |
Token | Pict |
Token ID | 10780 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
ought | +0.823 |
rightly | +0.819 |
rightfully | +0.753 |
BACK | +0.732 |
Parables | +0.713 |
Neg logit contributions | |
eming | -1.620 |
atown | -1.256 |
toggle | -1.251 |
texting | -1.200 |
slowing | -1.187 |
Token | ured |
Token ID | 1522 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ought | +4.025 |
rightly | +4.012 |
rightfully | +3.692 |
BACK | +3.594 |
Parables | +3.502 |
Neg logit contributions | |
eming | -6.204 |
atown | -4.749 |
toggle | -4.663 |
texting | -4.446 |
hyde | -4.439 |
Token | are |
Token ID | 389 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
rightly | +6.028 |
ought | +5.852 |
rightfully | +5.541 |
BACK | +5.366 |
suprem | +5.194 |
Neg logit contributions | |
eming | -9.876 |
atown | -7.545 |
toggle | -7.363 |
hyde | -7.118 |
alert | -7.114 |
Token | soldiers |
Token ID | 5795 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ought | +1.538 |
rightly | +1.533 |
rightfully | +1.430 |
BACK | +1.404 |
Parables | +1.380 |
Neg logit contributions | |
eming | -2.177 |
atown | -1.627 |
toggle | -1.612 |
texting | -1.545 |
slowing | -1.524 |
Token | marking |
Token ID | 18730 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
rightly | +2.485 |
ought | +2.475 |
rightfully | +2.329 |
BACK | +2.278 |
Parables | +2.233 |
Neg logit contributions | |
eming | -3.039 |
atown | -2.240 |
toggle | -2.204 |
hyde | -2.080 |
texting | -2.071 |
Token | the |
Token ID | 262 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
rightly | +4.451 |
ought | +4.424 |
rightfully | +4.135 |
BACK | +4.018 |
Parables | +3.986 |
Neg logit contributions | |
eming | -6.447 |
atown | -4.832 |
toggle | -4.791 |
hyde | -4.527 |
texting | -4.487 |
Token | 65 |
Token ID | 6135 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
rightly | +3.279 |
ought | +3.242 |
rightfully | +3.049 |
BACK | +2.976 |
Parables | +2.946 |
Neg logit contributions | |
eming | -4.535 |
atown | -3.419 |
toggle | -3.351 |
hyde | -3.185 |
texting | -3.163 |
Token | t |
Token ID | 83 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
ought | +2.643 |
rightly | +2.610 |
rightfully | +2.430 |
BACK | +2.375 |
Parables | +2.330 |
Neg logit contributions | |
eming | -3.488 |
atown | -2.604 |
toggle | -2.558 |
texting | -2.478 |
screenings | -2.440 |
Token | find |
Token ID | 1064 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
rightly | +2.618 |
ought | +2.552 |
rightfully | +2.430 |
BACK | +2.315 |
Parables | +2.283 |
Neg logit contributions | |
eming | -3.622 |
atown | -2.713 |
toggle | -2.681 |
hyde | -2.524 |
texting | -2.522 |
Token | an |
Token ID | 281 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ought | +0.732 |
rightly | +0.730 |
rightfully | +0.681 |
BACK | +0.670 |
Parables | +0.659 |
Neg logit contributions | |
eming | -1.015 |
atown | -0.756 |
toggle | -0.748 |
texting | -0.719 |
slowing | -0.710 |
Token | answer |
Token ID | 3280 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
ought | +0.667 |
rightly | +0.665 |
rightfully | +0.620 |
BACK | +0.605 |
Parables | +0.598 |
Neg logit contributions | |
eming | -0.906 |
atown | -0.672 |
toggle | -0.666 |
texting | -0.633 |
hyde | -0.628 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ought | +0.413 |
rightly | +0.410 |
rightfully | +0.381 |
BACK | +0.375 |
Parables | +0.370 |
Neg logit contributions | |
eming | -0.643 |
atown | -0.487 |
toggle | -0.481 |
texting | -0.465 |
slowing | -0.459 |
Token | this |
Token ID | 428 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
rightly | +4.539 |
ought | +4.456 |
rightfully | +4.178 |
BACK | +3.953 |
Parables | +3.889 |
Neg logit contributions | |
eming | -7.417 |
atown | -5.695 |
toggle | -5.571 |
hyde | -5.351 |
roma | -5.287 |
Token | question |
Token ID | 1808 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
rightly | +5.882 |
ought | +5.709 |
rightfully | +5.457 |
BACK | +5.108 |
suprem | +5.097 |
Neg logit contributions | |
eming | -8.999 |
atown | -6.841 |
toggle | -6.771 |
screenings | -6.332 |
alert | -6.293 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
rightly | +4.118 |
ought | +4.004 |
rightfully | +3.798 |
BACK | +3.582 |
suprem | +3.492 |
Neg logit contributions | |
eming | -6.345 |
toggle | -4.851 |
atown | -4.839 |
hyde | -4.549 |
screenings | -4.517 |
Token |
|
Token ID | 198 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
ought | +0.877 |
rightly | +0.875 |
rightfully | +0.810 |
BACK | +0.794 |
Parables | +0.779 |
Neg logit contributions | |
eming | -1.430 |
atown | -1.089 |
toggle | -1.078 |
texting | -1.036 |
hyde | -1.024 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
rightly | +1.527 |
ought | +1.524 |
BACK | +1.316 |
rightfully | +1.302 |
Vice | +1.241 |
Neg logit contributions | |
eming | -4.622 |
atown | -3.799 |
hyde | -3.618 |
texting | -3.599 |
toggle | -3.579 |
Token | D |
Token ID | 35 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ought | +1.849 |
rightly | +1.836 |
rightfully | +1.714 |
BACK | +1.707 |
Parables | +1.645 |
Neg logit contributions | |
eming | -2.338 |
atown | -1.738 |
toggle | -1.692 |
texting | -1.639 |
screenings | -1.618 |
Token | ort |
Token ID | 419 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
eming | +0.697 |
atown | +0.498 |
toggle | +0.494 |
texting | +0.466 |
alert | +0.462 |
Neg logit contributions | |
rightly | -0.623 |
ought | -0.618 |
rightfully | -0.590 |
BACK | -0.575 |
Parables | -0.568 |
Token | iculture |
Token ID | 47428 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
eming | +3.486 |
atown | +2.413 |
toggle | +2.327 |
texting | +2.222 |
alert | +2.217 |
Neg logit contributions | |
ought | -3.774 |
rightly | -3.742 |
BACK | -3.576 |
rightfully | -3.558 |
Parables | -3.478 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ought | +2.633 |
rightly | +2.630 |
rightfully | +2.442 |
BACK | +2.392 |
Parables | +2.346 |
Neg logit contributions | |
eming | -4.018 |
atown | -3.032 |
toggle | -3.007 |
texting | -2.875 |
hyde | -2.848 |
Token | Land |
Token ID | 6379 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ought | +1.198 |
rightly | +1.193 |
rightfully | +1.122 |
BACK | +1.105 |
Parables | +1.088 |
Neg logit contributions | |
eming | -1.345 |
atown | -0.968 |
toggle | -0.958 |
texting | -0.913 |
slowing | -0.899 |
Token | sc |
Token ID | 1416 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
eming | +5.291 |
toggle | +3.811 |
atown | +3.756 |
alert | +3.644 |
slowing | +3.624 |
Neg logit contributions | |
ought | -3.964 |
rightly | -3.921 |
rightfully | -3.704 |
Parables | -3.690 |
BACK | -3.650 |
Token | aping |
Token ID | 9269 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
eming | +2.897 |
atown | +1.821 |
toggle | +1.782 |
screenings | +1.674 |
texting | +1.648 |
Neg logit contributions | |
ought | -3.788 |
rightly | -3.779 |
rightfully | -3.641 |
BACK | -3.623 |
Parables | -3.577 |
Token | blog |
Token ID | 4130 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
rightly | +5.846 |
ought | +5.739 |
rightfully | +5.441 |
BACK | +5.304 |
Parables | +5.214 |
Neg logit contributions | |
eming | -8.515 |
atown | -6.454 |
toggle | -6.422 |
hyde | -6.069 |
texting | -5.968 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
rightly | +4.546 |
ought | +4.408 |
rightfully | +4.152 |
BACK | +4.099 |
Parables | +3.959 |
Neg logit contributions | |
eming | -7.852 |
toggle | -6.030 |
atown | -5.971 |
texting | -5.687 |
hyde | -5.671 |
Token |
|
Token ID | 198 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
rightly | +0.543 |
ought | +0.542 |
rightfully | +0.481 |
BACK | +0.475 |
Vice | +0.445 |
Neg logit contributions | |
eming | -1.399 |
atown | -1.123 |
toggle | -1.089 |
texting | -1.070 |
hyde | -1.069 |
Token | For |
Token ID | 1890 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ought | +1.685 |
rightly | +1.675 |
rightfully | +1.565 |
BACK | +1.556 |
Parables | +1.506 |
Neg logit contributions | |
eming | -2.205 |
atown | -1.635 |
toggle | -1.605 |
texting | -1.549 |
slowing | -1.529 |
Token | more |
Token ID | 517 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
ought | +0.964 |
rightly | +0.961 |
rightfully | +0.898 |
BACK | +0.882 |
Parables | +0.867 |
Neg logit contributions | |
eming | -1.297 |
atown | -0.962 |
toggle | -0.953 |
texting | -0.912 |
slowing | -0.899 |
Token | ?) |
Token ID | 10091 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
eming | +1.458 |
atown | +1.087 |
toggle | +1.077 |
texting | +1.038 |
slowing | +1.034 |
Neg logit contributions | |
ought | -1.059 |
rightly | -1.049 |
rightfully | -0.980 |
BACK | -0.970 |
Parables | -0.969 |
Token | but |
Token ID | 475 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
eming | +0.341 |
atown | +0.255 |
toggle | +0.252 |
texting | +0.243 |
slowing | +0.240 |
Neg logit contributions | |
ought | -0.241 |
rightly | -0.239 |
rightfully | -0.223 |
BACK | -0.220 |
Parables | -0.217 |
Token | you |
Token ID | 345 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
eming | +2.214 |
toggle | +1.632 |
atown | +1.630 |
texting | +1.585 |
slowing | +1.584 |
Neg logit contributions | |
ought | -1.720 |
rightly | -1.686 |
BACK | -1.586 |
rightfully | -1.578 |
Parables | -1.571 |
Token | could |
Token ID | 714 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
rightly | +2.555 |
ought | +2.536 |
rightfully | +2.373 |
BACK | +2.265 |
suprem | +2.215 |
Neg logit contributions | |
eming | -3.918 |
atown | -2.982 |
toggle | -2.941 |
hyde | -2.812 |
texting | -2.787 |
Token | still |
Token ID | 991 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
ought | +0.956 |
rightly | +0.954 |
rightfully | +0.892 |
BACK | +0.876 |
Parables | +0.861 |
Neg logit contributions | |
eming | -1.270 |
atown | -0.940 |
toggle | -0.931 |
texting | -0.890 |
slowing | -0.877 |
Token | see |
Token ID | 766 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
rightly | +2.247 |
ought | +2.209 |
rightfully | +2.092 |
BACK | +2.007 |
Parables | +1.972 |
Neg logit contributions | |
eming | -3.161 |
atown | -2.373 |
toggle | -2.331 |
hyde | -2.231 |
texting | -2.224 |
Token | the |
Token ID | 262 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
rightly | +2.022 |
ought | +2.018 |
rightfully | +1.885 |
BACK | +1.843 |
Parables | +1.811 |
Neg logit contributions | |
eming | -2.792 |
atown | -2.077 |
toggle | -2.056 |
texting | -1.959 |
hyde | -1.944 |
Token | screen |
Token ID | 3159 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
ought | +1.532 |
rightly | +1.530 |
rightfully | +1.430 |
BACK | +1.401 |
Parables | +1.379 |
Neg logit contributions | |
eming | -2.069 |
atown | -1.535 |
toggle | -1.519 |
texting | -1.451 |
hyde | -1.434 |
Token | door |
Token ID | 3420 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
ought | +0.337 |
rightly | +0.333 |
rightfully | +0.311 |
BACK | +0.308 |
Parables | +0.303 |
Neg logit contributions | |
eming | -0.461 |
atown | -0.345 |
toggle | -0.341 |
texting | -0.328 |
slowing | -0.325 |
Token | effect |
Token ID | 1245 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
eming | +0.011 |
atown | +0.007 |
toggle | +0.007 |
texting | +0.006 |
slowing | +0.006 |
Neg logit contributions | |
ought | -0.018 |
rightly | -0.018 |
rightfully | -0.018 |
BACK | -0.017 |
Parables | -0.017 |
Token | as |
Token ID | 355 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
rightly | +1.160 |
ought | +1.154 |
rightfully | +1.082 |
BACK | +1.053 |
Parables | +1.033 |
Neg logit contributions | |
eming | -1.592 |
atown | -1.186 |
toggle | -1.172 |
texting | -1.114 |
hyde | -1.108 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ought | +0.863 |
rightly | +0.858 |
rightfully | +0.803 |
BACK | +0.791 |
Parables | +0.774 |
Neg logit contributions | |
eming | -1.140 |
atown | -0.843 |
toggle | -0.835 |
texting | -0.800 |
slowing | -0.791 |
Token | National |
Token ID | 2351 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ought | +1.296 |
rightly | +1.293 |
rightfully | +1.206 |
BACK | +1.184 |
Parables | +1.164 |
Neg logit contributions | |
eming | -1.792 |
atown | -1.335 |
toggle | -1.322 |
texting | -1.266 |
slowing | -1.248 |
Token | Defense |
Token ID | 5947 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
ought | +1.988 |
rightly | +1.982 |
rightfully | +1.829 |
BACK | +1.790 |
Parables | +1.763 |
Neg logit contributions | |
eming | -3.329 |
atown | -2.549 |
toggle | -2.524 |
texting | -2.423 |
hyde | -2.396 |
Token | Commission |
Token ID | 4513 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
rightly | +3.385 |
ought | +3.347 |
rightfully | +3.093 |
BACK | +2.992 |
Parables | +2.944 |
Neg logit contributions | |
eming | -5.938 |
atown | -4.674 |
toggle | -4.636 |
texting | -4.388 |
hyde | -4.373 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
rightly | +4.305 |
ought | +4.270 |
rightfully | +3.979 |
BACK | +3.839 |
Parables | +3.800 |
Neg logit contributions | |
eming | -6.848 |
atown | -5.291 |
toggle | -5.232 |
texting | -4.953 |
hyde | -4.895 |
Token | [ |
Token ID | 685 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ought | +1.714 |
rightly | +1.712 |
rightfully | +1.591 |
BACK | +1.563 |
Parables | +1.536 |
Neg logit contributions | |
eming | -2.558 |
atown | -1.926 |
toggle | -1.906 |
texting | -1.831 |
slowing | -1.806 |
Token | 60 |
Token ID | 1899 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ought | +1.936 |
rightly | +1.936 |
rightfully | +1.812 |
BACK | +1.789 |
Parables | +1.753 |
Neg logit contributions | |
eming | -2.365 |
atown | -1.727 |
toggle | -1.699 |
texting | -1.630 |
slowing | -1.606 |
Token | ] |
Token ID | 60 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
eming | +3.188 |
toggle | +1.933 |
atown | +1.846 |
alert | +1.672 |
texting | +1.667 |
Neg logit contributions | |
ought | -5.622 |
rightly | -5.503 |
rightfully | -5.297 |
suprem | -5.226 |
BACK | -5.201 |
Token | The |
Token ID | 383 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
ought | +0.216 |
rightly | +0.214 |
rightfully | +0.199 |
BACK | +0.194 |
Parables | +0.190 |
Neg logit contributions | |
eming | -0.328 |
atown | -0.247 |
toggle | -0.247 |
texting | -0.235 |
slowing | -0.233 |
Token | DPRK |
Token ID | 48363 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
eming | +0.337 |
atown | +0.249 |
toggle | +0.249 |
texting | +0.240 |
slowing | +0.238 |
Neg logit contributions | |
ought | -0.251 |
rightly | -0.248 |
rightfully | -0.232 |
BACK | -0.229 |
Parables | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
eming | +1.361 |
atown | +1.020 |
toggle | +1.007 |
texting | +0.970 |
slowing | +0.968 |
Neg logit contributions | |
ought | -0.952 |
rightly | -0.929 |
rightfully | -0.867 |
BACK | -0.866 |
Parables | -0.857 |
Token | after |
Token ID | 706 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ought | +0.071 |
rightly | +0.071 |
rightfully | +0.066 |
BACK | +0.065 |
Parables | +0.064 |
Neg logit contributions | |
eming | -0.103 |
atown | -0.077 |
toggle | -0.076 |
texting | -0.074 |
slowing | -0.073 |
Token | such |
Token ID | 884 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
rightly | +1.583 |
ought | +1.583 |
rightfully | +1.483 |
BACK | +1.455 |
Parables | +1.431 |
Neg logit contributions | |
eming | -1.968 |
atown | -1.445 |
toggle | -1.429 |
texting | -1.357 |
hyde | -1.344 |
Token | a |
Token ID | 257 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
eming | +1.623 |
toggle | +1.225 |
slowing | +1.219 |
atown | +1.217 |
texting | +1.214 |
Neg logit contributions | |
ought | -1.011 |
rightly | -0.987 |
BACK | -0.929 |
Parables | -0.926 |
rightfully | -0.923 |
Token | performance |
Token ID | 2854 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
eming | +2.556 |
toggle | +1.869 |
slowing | +1.866 |
texting | +1.857 |
atown | +1.846 |
Neg logit contributions | |
ought | -1.946 |
rightly | -1.879 |
Parables | -1.794 |
BACK | -1.774 |
rightfully | -1.765 |
Token | - |
Token ID | 532 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ought | +0.975 |
rightly | +0.972 |
rightfully | +0.902 |
BACK | +0.885 |
Parables | +0.870 |
Neg logit contributions | |
eming | -1.545 |
atown | -1.171 |
toggle | -1.162 |
texting | -1.117 |
slowing | -1.104 |
Token | not |
Token ID | 407 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
eming | +0.281 |
atown | +0.206 |
toggle | +0.206 |
texting | +0.200 |
slowing | +0.198 |
Neg logit contributions | |
ought | -0.207 |
rightly | -0.204 |
rightfully | -0.191 |
BACK | -0.190 |
Parables | -0.187 |
Token | least |
Token ID | 1551 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ought | +0.700 |
rightly | +0.693 |
rightfully | +0.646 |
BACK | +0.641 |
Parables | +0.630 |
Neg logit contributions | |
eming | -1.045 |
atown | -0.782 |
toggle | -0.776 |
texting | -0.751 |
slowing | -0.743 |
Token | because |
Token ID | 780 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
eming | +3.247 |
texting | +2.306 |
slowing | +2.299 |
toggle | +2.275 |
atown | +2.236 |
Neg logit contributions | |
ought | -3.016 |
rightly | -2.904 |
BACK | -2.848 |
Parables | -2.836 |
rightfully | -2.749 |
Token | he |
Token ID | 339 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
rightly | +2.058 |
ought | +2.049 |
rightfully | +1.913 |
BACK | +1.863 |
Parables | +1.830 |
Neg logit contributions | |
eming | -3.029 |
atown | -2.291 |
toggle | -2.257 |
texting | -2.140 |
hyde | -2.138 |
Token | would |
Token ID | 561 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ought | +1.090 |
rightly | +1.083 |
rightfully | +1.007 |
BACK | +0.997 |
Parables | +0.984 |
Neg logit contributions | |
eming | -1.672 |
atown | -1.260 |
toggle | -1.248 |
texting | -1.207 |
slowing | -1.192 |
Token | rely |
Token ID | 8814 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ought | +0.903 |
rightly | +0.886 |
BACK | +0.829 |
rightfully | +0.826 |
Parables | +0.819 |
Neg logit contributions | |
eming | -1.342 |
atown | -0.998 |
toggle | -0.994 |
texting | -0.961 |
slowing | -0.953 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
rightly | +4.474 |
ought | +4.372 |
rightfully | +4.119 |
BACK | +3.845 |
suprem | +3.845 |
Neg logit contributions | |
eming | -7.060 |
atown | -5.425 |
toggle | -5.349 |
hyde | -5.129 |
alert | -5.050 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
rightly | +1.212 |
ought | +1.200 |
rightfully | +1.127 |
BACK | +1.089 |
Parables | +1.074 |
Neg logit contributions | |
eming | -1.679 |
atown | -1.258 |
toggle | -1.240 |
texting | -1.179 |
hyde | -1.177 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
rightly | +1.772 |
ought | +1.766 |
rightfully | +1.658 |
BACK | +1.612 |
Parables | +1.591 |
Neg logit contributions | |
eming | -2.294 |
atown | -1.695 |
toggle | -1.679 |
texting | -1.596 |
hyde | -1.585 |
Token | little |
Token ID | 1310 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
ought | +0.723 |
rightly | +0.719 |
rightfully | +0.676 |
BACK | +0.669 |
Parables | +0.659 |
Neg logit contributions | |
eming | -0.813 |
atown | -0.584 |
toggle | -0.578 |
texting | -0.553 |
slowing | -0.545 |
Token | ones |
Token ID | 3392 |
Feature activation | +3.10e-03 |
Pos logit contributions | |
eming | +0.486 |
atown | +0.357 |
toggle | +0.353 |
texting | +0.343 |
slowing | +0.339 |
Neg logit contributions | |
ought | -0.367 |
rightly | -0.361 |
BACK | -0.339 |
rightfully | -0.337 |
Parables | -0.332 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ought | +0.015 |
rightly | +0.015 |
rightfully | +0.014 |
BACK | +0.014 |
Parables | +0.014 |
Neg logit contributions | |
eming | -0.021 |
atown | -0.016 |
toggle | -0.016 |
texting | -0.015 |
slowing | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
ought | +0.736 |
rightly | +0.734 |
rightfully | +0.682 |
BACK | +0.669 |
Parables | +0.657 |
Neg logit contributions | |
eming | -1.112 |
atown | -0.838 |
toggle | -0.831 |
texting | -0.796 |
slowing | -0.786 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
eming | +0.286 |
atown | +0.210 |
toggle | +0.207 |
texting | +0.200 |
slowing | +0.197 |
Neg logit contributions | |
ought | -0.231 |
rightly | -0.228 |
rightfully | -0.214 |
BACK | -0.213 |
Parables | -0.209 |
Token | cattle |
Token ID | 17025 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
eming | +0.786 |
atown | +0.576 |
toggle | +0.570 |
texting | +0.551 |
slowing | +0.546 |
Neg logit contributions | |
ought | -0.622 |
rightly | -0.612 |
BACK | -0.575 |
rightfully | -0.573 |
Parables | -0.565 |
Token | , |
Token ID | 11 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
ought | +0.958 |
rightly | +0.955 |
rightfully | +0.891 |
BACK | +0.876 |
Parables | +0.861 |
Neg logit contributions | |
eming | -1.340 |
atown | -0.999 |
toggle | -0.990 |
texting | -0.948 |
slowing | -0.936 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ought | +0.035 |
rightly | +0.035 |
rightfully | +0.033 |
BACK | +0.032 |
Parables | +0.032 |
Neg logit contributions | |
eming | -0.047 |
atown | -0.035 |
toggle | -0.034 |
texting | -0.033 |
slowing | -0.033 |
Token | Bill |
Token ID | 3941 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ought | +0.337 |
rightly | +0.335 |
rightfully | +0.315 |
BACK | +0.311 |
Parables | +0.306 |
Neg logit contributions | |
eming | -0.378 |
atown | -0.271 |
toggle | -0.268 |
texting | -0.258 |
slowing | -0.254 |
Token | proposes |
Token ID | 26017 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
eming | +3.372 |
atown | +2.511 |
toggle | +2.471 |
texting | +2.452 |
slowing | +2.414 |
Neg logit contributions | |
ought | -2.284 |
rightly | -2.201 |
BACK | -2.100 |
Parables | -2.071 |
rightfully | -2.067 |
Token | offences |
Token ID | 20819 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
ought | +0.384 |
rightly | +0.380 |
rightfully | +0.355 |
BACK | +0.350 |
Parables | +0.343 |
Neg logit contributions | |
eming | -0.554 |
atown | -0.413 |
toggle | -0.408 |
texting | -0.397 |
slowing | -0.392 |
Token | committed |
Token ID | 5364 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
ought | +0.232 |
rightly | +0.229 |
rightfully | +0.214 |
BACK | +0.211 |
Parables | +0.206 |
Neg logit contributions | |
eming | -0.370 |
atown | -0.279 |
toggle | -0.276 |
texting | -0.269 |
slowing | -0.266 |
Token | by |
Token ID | 416 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
rightly | +2.466 |
ought | +2.435 |
rightfully | +2.268 |
BACK | +2.188 |
Parables | +2.132 |
Neg logit contributions | |
eming | -4.195 |
atown | -3.206 |
toggle | -3.196 |
hyde | -3.026 |
texting | -3.010 |
Token | Juven |
Token ID | 48113 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
rightly | +1.712 |
ought | +1.701 |
rightfully | +1.598 |
BACK | +1.563 |
Parables | +1.535 |
Neg logit contributions | |
eming | -2.273 |
atown | -1.687 |
toggle | -1.667 |
hyde | -1.574 |
texting | -1.569 |
Token | iles |
Token ID | 2915 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ought | +2.473 |
rightly | +2.468 |
rightfully | +2.300 |
BACK | +2.257 |
Parables | +2.222 |
Neg logit contributions | |
eming | -3.341 |
atown | -2.487 |
toggle | -2.466 |
texting | -2.357 |
slowing | -2.320 |
Token | . |
Token ID | 13 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
rightly | +1.668 |
ought | +1.668 |
rightfully | +1.547 |
BACK | +1.516 |
Parables | +1.487 |
Neg logit contributions | |
eming | -2.618 |
atown | -1.984 |
toggle | -1.970 |
texting | -1.884 |
hyde | -1.863 |
Token | The |
Token ID | 383 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
ought | +0.477 |
rightly | +0.475 |
rightfully | +0.445 |
BACK | +0.437 |
Parables | +0.429 |
Neg logit contributions | |
eming | -0.614 |
atown | -0.452 |
toggle | -0.447 |
texting | -0.428 |
hyde | -0.422 |
Token | Guardian |
Token ID | 8283 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
eming | +0.354 |
atown | +0.257 |
toggle | +0.254 |
texting | +0.246 |
slowing | +0.242 |
Neg logit contributions | |
ought | -0.293 |
rightly | -0.291 |
rightfully | -0.274 |
BACK | -0.270 |
Parables | -0.265 |
Token | / |
Token ID | 1220 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
rightly | +5.632 |
ought | +5.379 |
rightfully | +5.181 |
BACK | +4.898 |
Parables | +4.895 |
Neg logit contributions | |
eming | -7.833 |
atown | -5.925 |
toggle | -5.914 |
hyde | -5.625 |
texting | -5.516 |
Token | free |
Token ID | 1479 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
eming | +2.735 |
atown | +1.999 |
toggle | +1.958 |
texting | +1.883 |
screenings | +1.881 |
Neg logit contributions | |
ought | -2.264 |
rightly | -2.258 |
rightfully | -2.108 |
Parables | -2.107 |
BACK | -2.106 |
Token | � |
Token ID | 447 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ought | +3.652 |
rightly | +3.641 |
rightfully | +3.431 |
BACK | +3.357 |
suprem | +3.292 |
Neg logit contributions | |
eming | -3.934 |
atown | -2.808 |
toggle | -2.776 |
texting | -2.619 |
slowing | -2.599 |
Token | � |
Token ID | 251 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ought | +1.032 |
rightly | +1.027 |
rightfully | +0.970 |
BACK | +0.958 |
Parables | +0.942 |
Neg logit contributions | |
eming | -0.982 |
atown | -0.683 |
toggle | -0.675 |
texting | -0.639 |
screenings | -0.628 |
Token | zone |
Token ID | 6516 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
eming | +1.126 |
atown | +0.804 |
toggle | +0.793 |
texting | +0.757 |
screenings | +0.752 |
Neg logit contributions | |
ought | -1.035 |
rightly | -1.035 |
rightfully | -0.975 |
BACK | -0.964 |
Parables | -0.958 |
Token | , |
Token ID | 11 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
ought | +1.296 |
rightly | +1.295 |
rightfully | +1.204 |
BACK | +1.179 |
Parables | +1.157 |
Neg logit contributions | |
eming | -1.949 |
atown | -1.468 |
toggle | -1.456 |
texting | -1.395 |
hyde | -1.378 |
Token | making |
Token ID | 1642 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
ought | +0.425 |
rightly | +0.423 |
rightfully | +0.396 |
BACK | +0.390 |
Parables | +0.384 |
Neg logit contributions | |
eming | -0.549 |
atown | -0.405 |
toggle | -0.400 |
texting | -0.383 |
slowing | -0.378 |
Token | it |
Token ID | 340 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
eming | +3.119 |
atown | +2.275 |
toggle | +2.245 |
texting | +2.188 |
screenings | +2.163 |
Neg logit contributions | |
ought | -2.705 |
rightly | -2.665 |
BACK | -2.500 |
rightfully | -2.493 |
Parables | -2.474 |
Token | illegal |
Token ID | 5293 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
eming | +4.136 |
atown | +3.040 |
toggle | +3.032 |
texting | +2.965 |
contagious | +2.889 |
Neg logit contributions | |
ought | -3.120 |
rightly | -2.976 |
Parables | -2.862 |
BACK | -2.818 |
rightfully | -2.758 |
Token | for |
Token ID | 329 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
eming | +7.502 |
atown | +5.594 |
texting | +5.546 |
screenings | +5.452 |
toggle | +5.449 |
Neg logit contributions | |
ought | -5.723 |
rightly | -5.575 |
Parables | -5.360 |
BACK | -5.300 |
rightfully | -5.215 |
Token | them |
Token ID | 606 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
eming | +5.937 |
toggle | +4.382 |
atown | +4.379 |
texting | +4.323 |
screenings | +4.287 |
Neg logit contributions | |
ought | -4.972 |
rightly | -4.812 |
BACK | -4.655 |
Parables | -4.645 |
rightfully | -4.478 |
Token | to |
Token ID | 284 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
eming | +1.300 |
atown | +1.004 |
toggle | +0.993 |
texting | +0.958 |
screenings | +0.949 |
Neg logit contributions | |
ought | -0.725 |
rightly | -0.717 |
rightfully | -0.658 |
BACK | -0.652 |
Parables | -0.644 |
Token | to |
Token ID | 284 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
eming | +0.888 |
toggle | +0.658 |
atown | +0.653 |
texting | +0.627 |
slowing | +0.617 |
Neg logit contributions | |
ought | -0.660 |
rightly | -0.653 |
rightfully | -0.612 |
BACK | -0.600 |
Parables | -0.600 |
Token | a |
Token ID | 257 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
eming | +2.171 |
toggle | +1.624 |
atown | +1.586 |
texting | +1.534 |
alert | +1.509 |
Neg logit contributions | |
ought | -1.647 |
rightly | -1.634 |
rightfully | -1.529 |
Parables | -1.518 |
BACK | -1.504 |
Token | different |
Token ID | 1180 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
ought | +1.665 |
rightly | +1.664 |
rightfully | +1.560 |
BACK | +1.533 |
Parables | +1.501 |
Neg logit contributions | |
eming | -2.052 |
atown | -1.505 |
toggle | -1.483 |
texting | -1.415 |
hyde | -1.397 |
Token | value |
Token ID | 1988 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ought | +0.413 |
rightly | +0.412 |
rightfully | +0.383 |
BACK | +0.376 |
Parables | +0.370 |
Neg logit contributions | |
eming | -0.615 |
atown | -0.462 |
toggle | -0.459 |
texting | -0.440 |
slowing | -0.434 |
Token | , |
Token ID | 11 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
eming | +3.635 |
toggle | +2.663 |
atown | +2.602 |
texting | +2.551 |
slowing | +2.490 |
Neg logit contributions | |
ought | -2.972 |
rightly | -2.909 |
Parables | -2.760 |
rightfully | -2.743 |
BACK | -2.726 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
eming | +4.620 |
toggle | +3.342 |
texting | +3.214 |
atown | +3.185 |
slowing | +3.182 |
Neg logit contributions | |
ought | -4.196 |
rightly | -4.025 |
Parables | -3.892 |
BACK | -3.891 |
rightfully | -3.828 |
Token | result |
Token ID | 1255 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
eming | +0.728 |
toggle | +0.538 |
atown | +0.536 |
texting | +0.515 |
slowing | +0.508 |
Neg logit contributions | |
ought | -0.542 |
rightly | -0.538 |
rightfully | -0.503 |
BACK | -0.496 |
Parables | -0.492 |
Token | depends |
Token ID | 8338 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
eming | +3.886 |
toggle | +2.929 |
atown | +2.872 |
slowing | +2.846 |
texting | +2.839 |
Neg logit contributions | |
ought | -2.383 |
rightly | -2.340 |
Parables | -2.249 |
BACK | -2.206 |
rightfully | -2.181 |
Token | on |
Token ID | 319 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
eming | +2.627 |
toggle | +1.830 |
atown | +1.804 |
texting | +1.764 |
slowing | +1.746 |
Neg logit contributions | |
ought | -2.700 |
rightly | -2.581 |
Parables | -2.539 |
BACK | -2.519 |
rightfully | -2.467 |
Token | which |
Token ID | 543 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
rightly | +2.201 |
ought | +2.185 |
rightfully | +2.030 |
BACK | +1.985 |
Parables | +1.933 |
Neg logit contributions | |
eming | -3.344 |
atown | -2.550 |
toggle | -2.503 |
hyde | -2.404 |
texting | -2.381 |
Token | one |
Token ID | 530 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ought | +1.508 |
rightly | +1.506 |
rightfully | +1.399 |
BACK | +1.370 |
Parables | +1.341 |
Neg logit contributions | |
eming | -2.324 |
atown | -1.759 |
toggle | -1.736 |
texting | -1.664 |
hyde | -1.653 |
Token | think |
Token ID | 892 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
rightly | +0.963 |
ought | +0.963 |
rightfully | +0.896 |
BACK | +0.875 |
Parables | +0.859 |
Neg logit contributions | |
eming | -1.417 |
atown | -1.065 |
toggle | -1.054 |
texting | -1.007 |
hyde | -0.998 |
Token | this |
Token ID | 428 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
rightly | +3.541 |
ought | +3.482 |
rightfully | +3.297 |
BACK | +3.151 |
Parables | +3.109 |
Neg logit contributions | |
eming | -4.726 |
atown | -3.507 |
toggle | -3.481 |
hyde | -3.321 |
alert | -3.254 |
Token | is |
Token ID | 318 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
eming | +1.384 |
atown | +1.017 |
toggle | +1.008 |
texting | +0.987 |
slowing | +0.974 |
Neg logit contributions | |
ought | -1.107 |
rightly | -1.101 |
BACK | -1.033 |
rightfully | -1.030 |
Parables | -1.025 |
Token | normal |
Token ID | 3487 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
eming | +1.801 |
atown | +1.343 |
toggle | +1.322 |
texting | +1.310 |
slowing | +1.288 |
Neg logit contributions | |
ought | -1.294 |
rightly | -1.267 |
BACK | -1.184 |
rightfully | -1.178 |
Parables | -1.169 |
Token | because |
Token ID | 780 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
eming | +0.390 |
atown | +0.292 |
toggle | +0.287 |
texting | +0.282 |
slowing | +0.277 |
Neg logit contributions | |
ought | -0.273 |
rightly | -0.271 |
rightfully | -0.253 |
BACK | -0.251 |
Parables | -0.247 |
Token | we |
Token ID | 356 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ought | +0.477 |
rightly | +0.475 |
rightfully | +0.445 |
BACK | +0.438 |
Parables | +0.431 |
Neg logit contributions | |
eming | -0.586 |
atown | -0.429 |
toggle | -0.425 |
texting | -0.406 |
slowing | -0.400 |
Token | are |
Token ID | 389 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
eming | +2.186 |
atown | +1.626 |
toggle | +1.595 |
texting | +1.565 |
slowing | +1.535 |
Neg logit contributions | |
ought | -1.637 |
rightly | -1.609 |
BACK | -1.535 |
rightfully | -1.503 |
Parables | -1.499 |
Token | in |
Token ID | 287 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
eming | +3.327 |
atown | +2.434 |
toggle | +2.407 |
texting | +2.398 |
slowing | +2.363 |
Neg logit contributions | |
ought | -2.656 |
rightly | -2.571 |
BACK | -2.457 |
Parables | -2.416 |
rightfully | -2.411 |
Token | a |
Token ID | 257 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ought | +0.327 |
rightly | +0.326 |
rightfully | +0.305 |
BACK | +0.299 |
Parables | +0.294 |
Neg logit contributions | |
eming | -0.467 |
atown | -0.350 |
toggle | -0.345 |
texting | -0.332 |
slowing | -0.327 |
Token | way |
Token ID | 835 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
eming | +1.292 |
atown | +0.943 |
toggle | +0.930 |
texting | +0.902 |
slowing | +0.890 |
Neg logit contributions | |
ought | -1.063 |
rightly | -1.051 |
rightfully | -0.985 |
BACK | -0.979 |
Parables | -0.967 |
Token | brain |
Token ID | 3632 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
eming | +3.518 |
atown | +2.562 |
texting | +2.533 |
toggle | +2.511 |
slowing | +2.510 |
Neg logit contributions | |
ought | -2.805 |
rightly | -2.732 |
BACK | -2.601 |
Parables | -2.593 |
rightfully | -2.552 |
Token | py |
Token ID | 9078 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
eming | +0.955 |
atown | +0.670 |
toggle | +0.661 |
texting | +0.627 |
slowing | +0.616 |
Neg logit contributions | |
ought | -0.973 |
rightly | -0.970 |
rightfully | -0.916 |
BACK | -0.903 |
Parables | -0.890 |
Token | Reading |
Token ID | 36120 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
eming | +1.315 |
atown | +0.879 |
toggle | +0.874 |
texting | +0.817 |
slowing | +0.800 |
Neg logit contributions | |
ought | -1.591 |
rightly | -1.590 |
rightfully | -1.511 |
BACK | -1.480 |
Parables | -1.473 |
Token | 55 |
Token ID | 5996 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
rightly | +2.672 |
ought | +2.644 |
rightfully | +2.456 |
BACK | +2.395 |
Parables | +2.324 |
Neg logit contributions | |
eming | -4.621 |
atown | -3.550 |
toggle | -3.519 |
texting | -3.384 |
hyde | -3.377 |
Token | 80 |
Token ID | 1795 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
eming | +4.723 |
toggle | +3.241 |
atown | +3.134 |
alert | +3.022 |
texting | +2.888 |
Neg logit contributions | |
ought | -5.351 |
rightly | -5.336 |
suprem | -5.144 |
rightfully | -5.129 |
Parables | -5.123 |
Token | 953 |
Token ID | 49649 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
eming | +3.215 |
toggle | +2.276 |
atown | +2.243 |
texting | +2.115 |
screenings | +2.089 |
Neg logit contributions | |
ought | -3.195 |
rightly | -3.184 |
rightfully | -3.026 |
BACK | -2.977 |
Parables | -2.940 |
Token | 16 |
Token ID | 1467 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
rightly | +0.506 |
ought | +0.502 |
rightfully | +0.456 |
BACK | +0.442 |
Parables | +0.429 |
Neg logit contributions | |
eming | -1.244 |
atown | -0.985 |
toggle | -0.976 |
texting | -0.945 |
hyde | -0.939 |
Token | 27 |
Token ID | 1983 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
eming | +3.389 |
toggle | +2.517 |
atown | +2.456 |
texting | +2.326 |
alert | +2.321 |
Neg logit contributions | |
ought | -2.705 |
rightly | -2.694 |
rightfully | -2.546 |
Parables | -2.496 |
suprem | -2.478 |
Token | 145 |
Token ID | 18781 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
eming | +0.849 |
atown | +0.662 |
toggle | +0.654 |
texting | +0.634 |
slowing | +0.627 |
Neg logit contributions | |
ought | -0.419 |
rightly | -0.414 |
rightfully | -0.378 |
BACK | -0.372 |
Parables | -0.362 |
Token | Flat |
Token ID | 21939 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
eming | +3.996 |
atown | +2.574 |
toggle | +2.566 |
slowing | +2.476 |
Weird | +2.438 |
Neg logit contributions | |
ought | -5.797 |
rightly | -5.645 |
rightfully | -5.396 |
Vice | -5.299 |
BACK | -5.291 |
Token | buff |
Token ID | 36873 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
eming | +0.447 |
atown | +0.313 |
toggle | +0.309 |
texting | +0.293 |
slowing | +0.288 |
Neg logit contributions | |
ought | -0.458 |
rightly | -0.456 |
rightfully | -0.430 |
BACK | -0.425 |
Parables | -0.417 |
Token | ers |
Token ID | 364 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
eming | +2.505 |
toggle | +1.676 |
atown | +1.673 |
texting | +1.545 |
alert | +1.531 |
Neg logit contributions | |
rightly | -3.010 |
ought | -2.997 |
rightfully | -2.867 |
Parables | -2.809 |
BACK | -2.806 |
Token | individual |
Token ID | 1981 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
eming | +0.457 |
atown | +0.342 |
toggle | +0.341 |
texting | +0.329 |
slowing | +0.329 |
Neg logit contributions | |
ought | -0.311 |
rightly | -0.310 |
rightfully | -0.289 |
BACK | -0.284 |
Parables | -0.279 |
Token | market |
Token ID | 1910 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
eming | +2.323 |
toggle | +1.815 |
atown | +1.799 |
texting | +1.783 |
slowing | +1.777 |
Neg logit contributions | |
ought | -1.111 |
rightly | -1.102 |
rightfully | -1.017 |
Parables | -1.016 |
BACK | -1.002 |
Token | is |
Token ID | 318 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
eming | +1.523 |
atown | +1.146 |
toggle | +1.133 |
slowing | +1.099 |
texting | +1.096 |
Neg logit contributions | |
ought | -1.080 |
rightly | -1.066 |
rightfully | -0.996 |
Parables | -0.988 |
BACK | -0.981 |
Token | stabil |
Token ID | 14349 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ought | +0.666 |
rightly | +0.665 |
rightfully | +0.624 |
BACK | +0.614 |
Parables | +0.604 |
Neg logit contributions | |
eming | -0.797 |
atown | -0.580 |
toggle | -0.575 |
texting | -0.547 |
slowing | -0.539 |
Token | izing |
Token ID | 2890 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
eming | +1.557 |
atown | +0.982 |
toggle | +0.967 |
slowing | +0.896 |
texting | +0.895 |
Neg logit contributions | |
rightly | -2.300 |
ought | -2.293 |
rightfully | -2.193 |
BACK | -2.183 |
Parables | -2.158 |
Token | and |
Token ID | 290 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ought | +0.258 |
rightly | +0.255 |
rightfully | +0.238 |
BACK | +0.236 |
Parables | +0.232 |
Neg logit contributions | |
eming | -0.358 |
atown | -0.267 |
toggle | -0.265 |
texting | -0.254 |
slowing | -0.252 |
Token | insurers |
Token ID | 24668 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
eming | +1.434 |
atown | +1.048 |
toggle | +1.043 |
slowing | +1.007 |
texting | +1.006 |
Neg logit contributions | |
ought | -1.164 |
rightly | -1.145 |
rightfully | -1.072 |
BACK | -1.070 |
Parables | -1.061 |
Token | in |
Token ID | 287 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
eming | +1.719 |
atown | +1.281 |
toggle | +1.274 |
texting | +1.240 |
slowing | +1.238 |
Neg logit contributions | |
ought | -1.159 |
rightly | -1.144 |
BACK | -1.076 |
rightfully | -1.064 |
Parables | -1.053 |
Token | this |
Token ID | 428 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ought | +0.026 |
rightly | +0.026 |
rightfully | +0.024 |
BACK | +0.024 |
Parables | +0.023 |
Neg logit contributions | |
eming | -0.035 |
atown | -0.026 |
toggle | -0.026 |
texting | -0.025 |
slowing | -0.024 |
Token | market |
Token ID | 1910 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
eming | +1.513 |
atown | +1.172 |
toggle | +1.165 |
texting | +1.137 |
slowing | +1.136 |
Neg logit contributions | |
ought | -0.811 |
rightly | -0.806 |
rightfully | -0.743 |
BACK | -0.730 |
Parables | -0.728 |
Token | are |
Token ID | 389 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
eming | +3.955 |
atown | +2.963 |
toggle | +2.932 |
slowing | +2.894 |
texting | +2.876 |
Neg logit contributions | |
ought | -2.719 |
rightly | -2.656 |
BACK | -2.520 |
Parables | -2.503 |
rightfully | -2.477 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ought | +0.166 |
rightly | +0.164 |
rightfully | +0.152 |
BACK | +0.146 |
suprem | +0.141 |
Neg logit contributions | |
eming | -0.318 |
toggle | -0.246 |
atown | -0.245 |
texting | -0.234 |
alert | -0.232 |
Token |
|
Token ID | 198 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
eming | +1.093 |
atown | +0.859 |
toggle | +0.853 |
texting | +0.824 |
slowing | +0.815 |
Neg logit contributions | |
ought | -0.486 |
rightly | -0.484 |
rightfully | -0.440 |
BACK | -0.429 |
Parables | -0.419 |
Token | Newsletter |
Token ID | 33031 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
rightly | +0.154 |
ought | +0.154 |
rightfully | +0.144 |
Parables | +0.139 |
BACK | +0.138 |
Neg logit contributions | |
eming | -0.226 |
toggle | -0.170 |
atown | -0.168 |
texting | -0.160 |
alert | -0.159 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
rightly | +3.864 |
ought | +3.647 |
rightfully | +3.392 |
Parables | +3.376 |
BACK | +3.309 |
Neg logit contributions | |
eming | -9.326 |
atown | -7.599 |
toggle | -7.376 |
hyde | -7.356 |
contagious | -7.039 |
Token | Up |
Token ID | 3205 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
eming | +1.446 |
atown | +1.020 |
toggle | +1.008 |
texting | +0.955 |
slowing | +0.939 |
Neg logit contributions | |
ought | -1.430 |
rightly | -1.427 |
rightfully | -1.346 |
BACK | -1.326 |
Parables | -1.307 |
Token | Continue |
Token ID | 10054 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
eming | +4.649 |
toggle | +3.242 |
atown | +3.198 |
texting | +3.071 |
slowing | +3.023 |
Neg logit contributions | |
ought | -4.803 |
rightly | -4.798 |
rightfully | -4.544 |
BACK | -4.462 |
suprem | -4.428 |
Token | reading |
Token ID | 3555 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
eming | +5.269 |
texting | +3.260 |
slowing | +3.106 |
toggle | +3.013 |
screenings | +2.942 |
Neg logit contributions | |
ought | -10.824 |
rightly | -10.445 |
BACK | -10.383 |
Parables | -10.172 |
rightfully | -10.085 |
Token | the |
Token ID | 262 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
eming | +4.582 |
toggle | +3.355 |
atown | +3.312 |
texting | +3.238 |
slowing | +3.186 |
Neg logit contributions | |
ought | -3.928 |
rightly | -3.882 |
rightfully | -3.677 |
BACK | -3.627 |
Parables | -3.624 |
Token | main |
Token ID | 1388 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
eming | +4.008 |
toggle | +2.885 |
atown | +2.839 |
texting | +2.768 |
slowing | +2.739 |
Neg logit contributions | |
ought | -3.705 |
rightly | -3.678 |
rightfully | -3.479 |
BACK | -3.466 |
Parables | -3.431 |
Token | story |
Token ID | 1621 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
eming | +5.986 |
toggle | +4.282 |
slowing | +4.155 |
texting | +4.152 |
atown | +4.058 |
Neg logit contributions | |
ought | -6.798 |
rightly | -6.682 |
Parables | -6.490 |
BACK | -6.448 |
rightfully | -6.399 |
Token | Please |
Token ID | 4222 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
eming | +0.056 |
atown | +0.044 |
toggle | +0.043 |
texting | +0.042 |
hyde | +0.041 |
Neg logit contributions | |
ought | -0.026 |
rightly | -0.026 |
rightfully | -0.024 |
BACK | -0.023 |
Parables | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ought | +0.043 |
rightly | +0.042 |
rightfully | +0.039 |
BACK | +0.038 |
Parables | +0.038 |
Neg logit contributions | |
eming | -0.079 |
atown | -0.061 |
toggle | -0.061 |
texting | -0.059 |
slowing | -0.058 |
Token | have |
Token ID | 423 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
eming | +0.886 |
atown | +0.649 |
toggle | +0.643 |
texting | +0.616 |
slowing | +0.612 |
Neg logit contributions | |
ought | -0.708 |
rightly | -0.698 |
rightfully | -0.653 |
BACK | -0.649 |
Parables | -0.640 |
Token | a |
Token ID | 257 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
ought | +0.196 |
rightly | +0.196 |
rightfully | +0.183 |
BACK | +0.180 |
Parables | +0.177 |
Neg logit contributions | |
eming | -0.250 |
atown | -0.184 |
toggle | -0.182 |
texting | -0.174 |
slowing | -0.172 |
Token | transparent |
Token ID | 13245 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
eming | +4.162 |
toggle | +3.023 |
atown | +3.018 |
texting | +3.014 |
slowing | +2.996 |
Neg logit contributions | |
ought | -3.228 |
rightly | -3.138 |
Parables | -2.954 |
BACK | -2.924 |
rightfully | -2.918 |
Token | , |
Token ID | 11 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ought | +0.430 |
rightly | +0.430 |
rightfully | +0.403 |
BACK | +0.396 |
Parables | +0.389 |
Neg logit contributions | |
eming | -0.528 |
atown | -0.387 |
toggle | -0.383 |
texting | -0.364 |
hyde | -0.359 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
eming | +2.061 |
atown | +1.499 |
toggle | +1.491 |
texting | +1.452 |
slowing | +1.439 |
Neg logit contributions | |
ought | -1.648 |
rightly | -1.622 |
BACK | -1.515 |
Parables | -1.515 |
rightfully | -1.514 |
Token | licensing |
Token ID | 15665 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
eming | +10.157 |
texting | +7.293 |
filtering | +7.227 |
slowing | +7.195 |
toggle | +7.140 |
Neg logit contributions | |
ought | -8.687 |
rightly | -8.666 |
Parables | -8.613 |
rightfully | -8.128 |
BACK | -8.097 |
Token | agreement |
Token ID | 4381 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
eming | +4.526 |
toggle | +3.094 |
texting | +3.093 |
slowing | +3.034 |
atown | +3.007 |
Neg logit contributions | |
ought | -4.548 |
rightly | -4.432 |
Parables | -4.270 |
BACK | -4.249 |
rightfully | -4.199 |
Token | for |
Token ID | 329 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
eming | +1.775 |
atown | +1.346 |
toggle | +1.341 |
texting | +1.311 |
slowing | +1.298 |
Neg logit contributions | |
ought | -1.034 |
rightly | -1.012 |
rightfully | -0.937 |
BACK | -0.932 |
Parables | -0.931 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
eming | +2.715 |
toggle | +1.925 |
atown | +1.925 |
texting | +1.882 |
slowing | +1.852 |
Neg logit contributions | |
ought | -2.434 |
rightly | -2.401 |
rightfully | -2.251 |
BACK | -2.247 |
Parables | -2.230 |
Token | e |
Token ID | 304 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
eming | +1.084 |
atown | +0.763 |
toggle | +0.763 |
texting | +0.733 |
slowing | +0.722 |
Neg logit contributions | |
ought | -1.023 |
rightly | -1.014 |
rightfully | -0.953 |
BACK | -0.944 |
Parables | -0.934 |
Token | an |
Token ID | 281 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ought | +1.441 |
rightly | +1.432 |
rightfully | +1.334 |
BACK | +1.314 |
Parables | +1.296 |
Neg logit contributions | |
eming | -2.012 |
atown | -1.502 |
toggle | -1.482 |
texting | -1.427 |
slowing | -1.414 |
Token | accurate |
Token ID | 7187 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
ought | +3.409 |
rightly | +3.404 |
rightfully | +3.171 |
BACK | +3.058 |
Parables | +3.028 |
Neg logit contributions | |
eming | -5.033 |
atown | -3.779 |
toggle | -3.738 |
hyde | -3.567 |
texting | -3.564 |
Token | representation |
Token ID | 10552 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
rightly | +2.619 |
ought | +2.608 |
rightfully | +2.421 |
BACK | +2.366 |
Parables | +2.322 |
Neg logit contributions | |
eming | -4.254 |
atown | -3.234 |
toggle | -3.205 |
hyde | -3.060 |
texting | -3.048 |
Token | of |
Token ID | 286 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
rightly | +3.041 |
ought | +3.003 |
rightfully | +2.780 |
BACK | +2.690 |
Parables | +2.614 |
Neg logit contributions | |
eming | -6.061 |
toggle | -4.747 |
atown | -4.743 |
texting | -4.541 |
hyde | -4.504 |
Token | his |
Token ID | 465 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ought | +2.940 |
rightly | +2.935 |
rightfully | +2.738 |
BACK | +2.682 |
Parables | +2.635 |
Neg logit contributions | |
eming | -4.084 |
atown | -3.043 |
toggle | -3.020 |
texting | -2.884 |
hyde | -2.849 |
Token | worth |
Token ID | 2861 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ought | +0.978 |
rightly | +0.975 |
rightfully | +0.911 |
BACK | +0.896 |
Parables | +0.881 |
Neg logit contributions | |
eming | -1.292 |
atown | -0.955 |
toggle | -0.946 |
texting | -0.906 |
slowing | -0.894 |
Token | to |
Token ID | 284 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
eming | +8.630 |
atown | +6.473 |
texting | +6.026 |
slowing | +6.009 |
toggle | +5.955 |
Neg logit contributions | |
rightly | -6.924 |
ought | -6.912 |
BACK | -6.607 |
Parables | -6.560 |
Vice | -6.487 |
Token | an |
Token ID | 281 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
eming | +4.111 |
atown | +2.982 |
toggle | +2.880 |
slowing | +2.808 |
texting | +2.801 |
Neg logit contributions | |
ought | -3.620 |
rightly | -3.525 |
BACK | -3.374 |
Parables | -3.366 |
rightfully | -3.285 |
Token | NHL |
Token ID | 9481 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
eming | +1.712 |
atown | +1.232 |
toggle | +1.194 |
texting | +1.149 |
slowing | +1.135 |
Neg logit contributions | |
ought | -1.556 |
rightly | -1.550 |
BACK | -1.468 |
rightfully | -1.459 |
Parables | -1.434 |
Token | team |
Token ID | 1074 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ought | +0.301 |
rightly | +0.300 |
rightfully | +0.280 |
BACK | +0.277 |
Parables | +0.274 |
Neg logit contributions | |
eming | -0.385 |
atown | -0.282 |
toggle | -0.278 |
texting | -0.267 |
slowing | -0.265 |
Token | . |
Token ID | 13 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
eming | +1.359 |
atown | +1.028 |
toggle | +0.997 |
texting | +0.977 |
slowing | +0.970 |
Neg logit contributions | |
ought | -0.898 |
rightly | -0.876 |
BACK | -0.818 |
Parables | -0.813 |
rightfully | -0.813 |
Token | 1 |
Token ID | 352 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
rightly | +2.074 |
ought | +2.073 |
rightfully | +1.936 |
BACK | +1.900 |
Parables | +1.867 |
Neg logit contributions | |
eming | -2.774 |
atown | -2.055 |
toggle | -2.031 |
texting | -1.927 |
hyde | -1.917 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
eming | +4.202 |
atown | +3.126 |
toggle | +3.079 |
texting | +3.037 |
alert | +2.961 |
Neg logit contributions | |
ought | -3.158 |
rightly | -3.147 |
rightfully | -2.969 |
BACK | -2.940 |
Parables | -2.926 |
Token | 800 |
Token ID | 7410 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
eming | +1.409 |
atown | +1.062 |
toggle | +1.059 |
texting | +1.022 |
alert | +1.005 |
Neg logit contributions | |
ought | -0.904 |
rightly | -0.901 |
rightfully | -0.840 |
BACK | -0.821 |
Parables | -0.812 |
Token | . |
Token ID | 13 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
eming | +0.891 |
atown | +0.674 |
toggle | +0.672 |
texting | +0.655 |
alert | +0.640 |
Neg logit contributions | |
ought | -0.561 |
rightly | -0.558 |
rightfully | -0.523 |
Parables | -0.511 |
BACK | -0.506 |
Token | 366 |
Token ID | 32459 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
eming | +6.432 |
toggle | +4.911 |
atown | +4.659 |
alert | +4.598 |
texting | +4.498 |
Neg logit contributions | |
ought | -4.457 |
rightly | -4.452 |
rightfully | -4.216 |
suprem | -4.175 |
Parables | -4.134 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
eming | +1.546 |
toggle | +1.181 |
atown | +1.181 |
texting | +1.132 |
slowing | +1.117 |
Neg logit contributions | |
ought | -0.881 |
rightly | -0.878 |
rightfully | -0.813 |
BACK | -0.792 |
Parables | -0.783 |
Token | 44 |
Token ID | 2598 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
eming | +8.474 |
toggle | +6.670 |
alert | +6.170 |
Enlarge | +5.747 |
Alert | +5.682 |
Neg logit contributions | |
suprem | -7.185 |
ought | -7.022 |
rightly | -6.887 |
rightfully | -6.681 |
Parables | -6.600 |
Token | 84 |
Token ID | 5705 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
eming | +0.475 |
toggle | +0.353 |
atown | +0.352 |
texting | +0.339 |
alert | +0.335 |
Neg logit contributions | |
ought | -0.330 |
rightly | -0.327 |
rightfully | -0.306 |
BACK | -0.299 |
Parables | -0.297 |
Token | or |
Token ID | 393 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
eming | +2.216 |
atown | +1.667 |
toggle | +1.647 |
texting | +1.618 |
alert | +1.573 |
Neg logit contributions | |
ought | -1.532 |
rightly | -1.516 |
rightfully | -1.419 |
BACK | -1.387 |
Parables | -1.373 |
Token | by |
Token ID | 416 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
rightly | +2.280 |
ought | +2.278 |
rightfully | +2.158 |
BACK | +2.122 |
Parables | +2.095 |
Neg logit contributions | |
eming | -2.098 |
atown | -1.447 |
toggle | -1.430 |
hyde | -1.329 |
texting | -1.326 |
Token | using |
Token ID | 1262 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
rightly | +2.598 |
ought | +2.588 |
rightfully | +2.482 |
BACK | +2.444 |
Parables | +2.416 |
Neg logit contributions | |
eming | -1.502 |
atown | -0.896 |
toggle | -0.882 |
hyde | -0.786 |
screenings | -0.764 |
Token | Canada |
Token ID | 3340 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
rightly | +2.419 |
ought | +2.373 |
rightfully | +2.250 |
BACK | +2.156 |
Parables | +2.121 |
Neg logit contributions | |
eming | -3.479 |
atown | -2.606 |
toggle | -2.592 |
hyde | -2.457 |
texting | -2.451 |
Token | � |
Token ID | 447 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ought | +1.664 |
rightly | +1.660 |
rightfully | +1.562 |
BACK | +1.538 |
Parables | +1.515 |
Neg logit contributions | |
eming | -1.849 |
atown | -1.329 |
toggle | -1.314 |
texting | -1.250 |
slowing | -1.231 |
Token | � |
Token ID | 247 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
eming | +0.619 |
atown | +0.434 |
toggle | +0.427 |
texting | +0.404 |
slowing | +0.398 |
Neg logit contributions | |
ought | -0.643 |
rightly | -0.641 |
rightfully | -0.607 |
BACK | -0.598 |
Parables | -0.590 |
Token | s |
Token ID | 82 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
eming | +1.324 |
atown | +0.907 |
toggle | +0.875 |
texting | +0.816 |
screenings | +0.809 |
Neg logit contributions | |
ought | -1.589 |
rightly | -1.586 |
rightfully | -1.507 |
BACK | -1.490 |
Parables | -1.480 |
Token | first |
Token ID | 717 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
eming | +0.990 |
atown | +0.731 |
toggle | +0.728 |
texting | +0.705 |
slowing | +0.699 |
Neg logit contributions | |
ought | -0.708 |
rightly | -0.694 |
rightfully | -0.649 |
BACK | -0.648 |
Parables | -0.631 |
Token | legal |
Token ID | 2742 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
eming | +2.838 |
atown | +2.058 |
toggle | +2.057 |
texting | +2.021 |
screenings | +1.988 |
Neg logit contributions | |
ought | -2.154 |
rightly | -2.114 |
BACK | -2.001 |
rightfully | -1.989 |
Parables | -1.954 |
Token | same |
Token ID | 976 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
eming | +7.858 |
texting | +5.832 |
toggle | +5.767 |
slowing | +5.659 |
screenings | +5.616 |
Neg logit contributions | |
ought | -6.778 |
rightly | -6.679 |
Parables | -6.580 |
BACK | -6.470 |
rightfully | -6.309 |
Token | - |
Token ID | 12 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
eming | +7.739 |
atown | +5.424 |
texting | +5.423 |
toggle | +5.355 |
screenings | +5.278 |
Neg logit contributions | |
ought | -6.162 |
rightly | -6.087 |
Parables | -5.912 |
BACK | -5.805 |
rightfully | -5.758 |
Token | sex |
Token ID | 8044 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
eming | +6.399 |
toggle | +4.413 |
atown | +4.215 |
alert | +3.976 |
texting | +3.946 |
Neg logit contributions | |
rightly | -7.099 |
ought | -6.961 |
rightfully | -6.790 |
Parables | -6.781 |
BACK | -6.615 |
Token | marriage |
Token ID | 4845 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
eming | +3.485 |
toggle | +2.307 |
atown | +2.298 |
texting | +2.248 |
screenings | +2.204 |
Neg logit contributions | |
ought | -4.078 |
rightly | -4.030 |
BACK | -3.887 |
Parables | -3.875 |
rightfully | -3.841 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ought | +0.017 |
rightly | +0.017 |
rightfully | +0.016 |
BACK | +0.015 |
Parables | +0.015 |
Neg logit contributions | |
eming | -0.023 |
atown | -0.017 |
toggle | -0.017 |
texting | -0.016 |
slowing | -0.016 |