Token | millionaires |
Token ID | 48675 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ONY | +1.178 |
space | +1.074 |
Stall | +1.027 |
lust | +0.991 |
Goth | +0.989 |
Neg logit contributions | |
milo | -1.166 |
oried | -0.969 |
Choi | -0.918 |
bamboo | -0.897 |
Kw | -0.890 |
Token | , |
Token ID | 11 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
milo | +2.000 |
oried | +1.651 |
Choi | +1.570 |
Kw | +1.517 |
bamboo | +1.517 |
Neg logit contributions | |
ONY | -2.314 |
space | -2.132 |
Stall | -2.016 |
lust | -1.965 |
Goth | -1.937 |
Token | � |
Token ID | 447 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ONY | +3.800 |
space | +3.428 |
Stall | +3.315 |
Goth | +3.222 |
lust | +3.137 |
Neg logit contributions | |
milo | -4.110 |
oried | -3.518 |
Choi | -3.213 |
bamboo | -3.205 |
Hong | -3.175 |
Token | � |
Token ID | 251 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ONY | +0.399 |
space | +0.372 |
Stall | +0.356 |
lust | +0.348 |
Goth | +0.346 |
Neg logit contributions | |
milo | -0.225 |
oried | -0.173 |
Choi | -0.161 |
bamboo | -0.154 |
Kw | -0.153 |
Token | Ms |
Token ID | 6997 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
ONY | +2.325 |
space | +2.103 |
Stall | +1.995 |
Goth | +1.924 |
lust | +1.915 |
Neg logit contributions | |
milo | -2.594 |
oried | -2.213 |
Choi | -2.067 |
bamboo | -2.052 |
Hong | -1.998 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e+01 |
Pos logit contributions | |
ONY | +8.802 |
space | +8.147 |
lust | +7.661 |
Stall | +7.481 |
Goth | +7.322 |
Neg logit contributions | |
milo | -12.546 |
conclud | -11.116 |
bamboo | -10.397 |
challeng | -10.262 |
describ | -10.177 |
Token | Ole |
Token ID | 30093 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
ONY | +9.258 |
Stall | +8.547 |
Goth | +8.331 |
space | +8.279 |
Lys | +7.550 |
Neg logit contributions | |
milo | -14.017 |
oried | -12.007 |
bamboo | -11.437 |
sidx | -11.244 |
linkage | -11.232 |
Token | ch |
Token ID | 354 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ONY | +5.706 |
space | +5.593 |
lust | +5.057 |
Stall | +4.926 |
empt | +4.906 |
Neg logit contributions | |
milo | -6.847 |
oried | -5.791 |
conclud | -5.718 |
bamboo | -5.637 |
Choi | -5.513 |
Token | owski |
Token ID | 12079 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
milo | +2.539 |
oried | +2.143 |
Choi | +2.008 |
Kw | +1.981 |
Zhang | +1.959 |
Neg logit contributions | |
ONY | -2.621 |
space | -2.307 |
satell | -2.284 |
Stall | -2.271 |
Goth | -2.153 |
Token | said |
Token ID | 531 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ONY | +1.025 |
space | +0.919 |
Stall | +0.864 |
lust | +0.817 |
Goth | +0.816 |
Neg logit contributions | |
milo | -1.551 |
oried | -1.322 |
Choi | -1.260 |
bamboo | -1.243 |
Kw | -1.226 |
Token | . |
Token ID | 13 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
milo | +1.490 |
oried | +1.234 |
Choi | +1.167 |
Kw | +1.129 |
bamboo | +1.129 |
Neg logit contributions | |
ONY | -1.773 |
space | -1.632 |
Stall | -1.551 |
lust | -1.505 |
Goth | -1.490 |
Token | iking |
Token ID | 14132 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
milo | +1.967 |
oried | +1.659 |
Choi | +1.565 |
Kw | +1.525 |
bamboo | +1.518 |
Neg logit contributions | |
ONY | -1.995 |
space | -1.825 |
Stall | -1.735 |
lust | -1.672 |
satell | -1.663 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
milo | +1.372 |
oried | +1.133 |
Choi | +1.074 |
bamboo | +1.045 |
Kw | +1.042 |
Neg logit contributions | |
ONY | -1.578 |
space | -1.446 |
Stall | -1.370 |
lust | -1.334 |
Goth | -1.321 |
Token | 2006 |
Token ID | 4793 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
milo | +1.170 |
oried | +0.994 |
Choi | +0.955 |
bamboo | +0.932 |
Kw | +0.931 |
Neg logit contributions | |
ONY | -0.980 |
space | -0.884 |
Stall | -0.830 |
lust | -0.804 |
Goth | -0.792 |
Token | ). |
Token ID | 737 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
milo | +1.626 |
oried | +1.358 |
Choi | +1.291 |
bamboo | +1.260 |
Kw | +1.255 |
Neg logit contributions | |
ONY | -1.665 |
space | -1.513 |
Stall | -1.436 |
lust | -1.390 |
Goth | -1.377 |
Token | Ms |
Token ID | 6997 |
Feature activation | +7.57e+00 |
Pos logit contributions | |
ONY | +1.446 |
space | +1.307 |
Stall | +1.242 |
Goth | +1.194 |
lust | +1.188 |
Neg logit contributions | |
milo | -1.754 |
oried | -1.491 |
bamboo | -1.394 |
Choi | -1.392 |
Kw | -1.362 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+01 |
Pos logit contributions | |
ONY | +5.317 |
space | +5.000 |
Stall | +4.640 |
lust | +4.592 |
Goth | +4.535 |
Neg logit contributions | |
milo | -5.922 |
oried | -4.742 |
conclud | -4.603 |
bamboo | -4.601 |
Choi | -4.500 |
Token | Sand |
Token ID | 3837 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ONY | +6.969 |
Stall | +6.555 |
space | +6.549 |
Goth | +6.443 |
Span | +5.894 |
Neg logit contributions | |
milo | -15.384 |
oried | -13.077 |
� | -12.526 |
sidx | -12.343 |
arij | -12.213 |
Token | ler |
Token ID | 1754 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
milo | +0.341 |
oried | +0.276 |
Choi | +0.257 |
bamboo | +0.248 |
Kw | +0.248 |
Neg logit contributions | |
ONY | -0.473 |
space | -0.430 |
Stall | -0.416 |
satell | -0.409 |
Goth | -0.401 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
milo | +2.594 |
oried | +2.196 |
Choi | +2.103 |
bamboo | +2.052 |
Kw | +2.046 |
Neg logit contributions | |
ONY | -2.434 |
space | -2.199 |
Stall | -2.075 |
lust | -2.017 |
Goth | -1.982 |
Token | who |
Token ID | 508 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
milo | +0.884 |
oried | +0.724 |
Choi | +0.681 |
bamboo | +0.664 |
Kw | +0.660 |
Neg logit contributions | |
ONY | -1.040 |
space | -0.958 |
Stall | -0.912 |
lust | -0.884 |
Goth | -0.879 |
Token | calls |
Token ID | 3848 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
milo | +0.814 |
oried | +0.676 |
Choi | +0.639 |
bamboo | +0.624 |
Kw | +0.621 |
Neg logit contributions | |
ONY | -0.854 |
space | -0.783 |
Stall | -0.743 |
lust | -0.719 |
Goth | -0.714 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
ONY | +1.205 |
space | +1.104 |
Stall | +1.043 |
lust | +1.013 |
Goth | +1.003 |
Neg logit contributions | |
milo | -1.149 |
oried | -0.961 |
Choi | -0.904 |
bamboo | -0.885 |
Kw | -0.880 |
Token |
|
Token ID | 198 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
ONY | +2.476 |
space | +2.223 |
Stall | +2.128 |
Goth | +2.017 |
lust | +2.011 |
Neg logit contributions | |
milo | -3.126 |
oried | -2.677 |
Choi | -2.524 |
bamboo | -2.473 |
� | -2.455 |
Token |
|
Token ID | 198 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
ONY | +2.470 |
space | +2.255 |
Stall | +2.101 |
lust | +2.038 |
Goth | +2.002 |
Neg logit contributions | |
milo | -3.402 |
oried | -2.898 |
Choi | -2.752 |
bamboo | -2.721 |
arij | -2.681 |
Token | T |
Token ID | 51 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
ONY | +4.005 |
space | +3.623 |
Stall | +3.357 |
lust | +3.255 |
Goth | +3.197 |
Neg logit contributions | |
milo | -5.059 |
oried | -4.348 |
Choi | -4.214 |
bamboo | -4.145 |
Kw | -4.049 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ONY | +4.958 |
space | +4.649 |
Stall | +4.368 |
lust | +4.329 |
empt | +4.283 |
Neg logit contributions | |
milo | -4.101 |
oried | -3.310 |
Choi | -3.208 |
bamboo | -3.116 |
Kw | -3.110 |
Token | er |
Token ID | 263 |
Feature activation | +1.62e+01 |
Pos logit contributions | |
ONY | +3.533 |
space | +3.263 |
Stall | +3.100 |
lust | +3.012 |
Goth | +2.948 |
Neg logit contributions | |
milo | -3.446 |
oried | -2.814 |
Choi | -2.747 |
bamboo | -2.685 |
Kw | -2.658 |
Token | at |
Token ID | 265 |
Feature activation | +9.29e+00 |
Pos logit contributions | |
ONY | +7.139 |
space | +6.947 |
thus | +6.443 |
Stall | +6.246 |
ace | +6.231 |
Neg logit contributions | |
milo | -13.961 |
conclud | -12.787 |
� | -12.221 |
Choi | -12.156 |
referen | -12.023 |
Token | ops |
Token ID | 2840 |
Feature activation | +8.09e+00 |
Pos logit contributions | |
ONY | +4.428 |
space | +4.018 |
Stall | +3.523 |
lust | +3.510 |
empt | +3.454 |
Neg logit contributions | |
milo | -9.063 |
oried | -7.857 |
bamboo | -7.789 |
Choi | -7.744 |
conclud | -7.680 |
Token | # |
Token ID | 1303 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ONY | +4.674 |
space | +4.135 |
Stall | +4.063 |
Goth | +3.834 |
lust | +3.729 |
Neg logit contributions | |
milo | -7.107 |
oried | -6.204 |
Choi | -5.829 |
bamboo | -5.747 |
� | -5.722 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ONY | +1.010 |
space | +0.926 |
Stall | +0.875 |
lust | +0.850 |
Goth | +0.841 |
Neg logit contributions | |
milo | -0.956 |
oried | -0.799 |
Choi | -0.752 |
bamboo | -0.736 |
Kw | -0.731 |
Token |
|
Token ID | 198 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
ONY | +2.459 |
space | +2.206 |
Stall | +2.114 |
Goth | +2.007 |
lust | +1.999 |
Neg logit contributions | |
milo | -3.048 |
oried | -2.605 |
Choi | -2.458 |
bamboo | -2.404 |
Kw | -2.388 |
Token | ! |
Token ID | 0 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
milo | +0.726 |
oried | +0.596 |
Choi | +0.562 |
bamboo | +0.546 |
Kw | +0.544 |
Neg logit contributions | |
ONY | -0.895 |
space | -0.822 |
Stall | -0.783 |
lust | -0.762 |
Goth | -0.756 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
ONY | +1.638 |
space | +1.480 |
Stall | +1.404 |
lust | +1.336 |
Goth | +1.336 |
Neg logit contributions | |
milo | -2.119 |
oried | -1.796 |
Choi | -1.682 |
bamboo | -1.676 |
arij | -1.655 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
ONY | +1.303 |
space | +1.178 |
Stall | +1.106 |
lust | +1.068 |
Goth | +1.055 |
Neg logit contributions | |
milo | -1.602 |
oried | -1.364 |
Choi | -1.302 |
bamboo | -1.276 |
Kw | -1.270 |
Token | Your |
Token ID | 7120 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ONY | +0.379 |
space | +0.343 |
Stall | +0.320 |
lust | +0.311 |
Goth | +0.306 |
Neg logit contributions | |
milo | -0.460 |
oried | -0.392 |
Choi | -0.374 |
bamboo | -0.368 |
Kw | -0.364 |
Token | Inner |
Token ID | 24877 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
ONY | +0.659 |
space | +0.600 |
Stall | +0.565 |
lust | +0.548 |
Goth | +0.542 |
Neg logit contributions | |
milo | -0.723 |
oried | -0.609 |
Choi | -0.575 |
bamboo | -0.562 |
Kw | -0.558 |
Token | Ass |
Token ID | 2195 |
Feature activation | +1.61e+01 |
Pos logit contributions | |
ONY | +3.663 |
space | +3.345 |
Stall | +3.154 |
lust | +2.951 |
Goth | +2.917 |
Neg logit contributions | |
milo | -6.561 |
oried | -5.695 |
bamboo | -5.282 |
arij | -5.266 |
� | -5.256 |
Token | hole |
Token ID | 13207 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
space | +6.099 |
ONY | +5.664 |
lust | +4.937 |
hoe | +4.857 |
Stall | +4.757 |
Neg logit contributions | |
milo | -15.792 |
conclud | -14.141 |
oried | -13.552 |
bamboo | -13.523 |
� | -13.311 |
Token | is |
Token ID | 318 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
ONY | +0.658 |
space | +0.603 |
Stall | +0.572 |
lust | +0.553 |
Goth | +0.549 |
Neg logit contributions | |
milo | -0.649 |
oried | -0.541 |
Choi | -0.510 |
bamboo | -0.498 |
Kw | -0.494 |
Token | never |
Token ID | 1239 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
milo | +0.660 |
oried | +0.547 |
Choi | +0.518 |
bamboo | +0.504 |
Kw | +0.502 |
Neg logit contributions | |
ONY | -0.724 |
space | -0.664 |
Stall | -0.630 |
lust | -0.612 |
Goth | -0.606 |
Token | off |
Token ID | 572 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
ONY | +0.073 |
space | +0.067 |
Stall | +0.063 |
lust | +0.061 |
Goth | +0.061 |
Neg logit contributions | |
milo | -0.068 |
oried | -0.057 |
Choi | -0.054 |
bamboo | -0.052 |
Kw | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ONY | +3.349 |
space | +3.183 |
Stall | +2.992 |
lust | +2.902 |
empt | +2.836 |
Neg logit contributions | |
milo | -3.543 |
oried | -2.937 |
Choi | -2.773 |
� | -2.702 |
Hugo | -2.699 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ONY | +1.010 |
space | +0.926 |
Stall | +0.875 |
lust | +0.850 |
Goth | +0.841 |
Neg logit contributions | |
milo | -0.956 |
oried | -0.799 |
Choi | -0.752 |
bamboo | -0.736 |
Kw | -0.731 |
Token |
|
Token ID | 198 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
ONY | +2.459 |
space | +2.206 |
Stall | +2.114 |
Goth | +2.007 |
lust | +1.999 |
Neg logit contributions | |
milo | -3.048 |
oried | -2.605 |
Choi | -2.458 |
bamboo | -2.404 |
Kw | -2.388 |
Token |
|
Token ID | 198 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
ONY | +2.452 |
space | +2.237 |
Stall | +2.084 |
lust | +2.023 |
Goth | +1.986 |
Neg logit contributions | |
milo | -3.365 |
oried | -2.866 |
Choi | -2.723 |
bamboo | -2.691 |
arij | -2.650 |
Token | T |
Token ID | 51 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
ONY | +3.892 |
space | +3.524 |
Stall | +3.257 |
lust | +3.162 |
Goth | +3.102 |
Neg logit contributions | |
milo | -4.917 |
oried | -4.227 |
Choi | -4.096 |
bamboo | -4.024 |
Kw | -3.940 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
ONY | +5.175 |
space | +4.831 |
Stall | +4.549 |
lust | +4.505 |
empt | +4.463 |
Neg logit contributions | |
milo | -4.263 |
oried | -3.448 |
Choi | -3.343 |
Kw | -3.245 |
bamboo | -3.240 |
Token | er |
Token ID | 263 |
Feature activation | +1.61e+01 |
Pos logit contributions | |
ONY | +3.465 |
space | +3.203 |
Stall | +3.037 |
lust | +2.954 |
Goth | +2.887 |
Neg logit contributions | |
milo | -3.381 |
oried | -2.761 |
Choi | -2.693 |
bamboo | -2.634 |
Kw | -2.612 |
Token | at |
Token ID | 265 |
Feature activation | +8.88e+00 |
Pos logit contributions | |
ONY | +7.113 |
space | +7.005 |
thus | +6.410 |
ace | +6.236 |
Stall | +6.230 |
Neg logit contributions | |
milo | -13.839 |
conclud | -12.892 |
referen | -12.153 |
� | -12.116 |
Choi | -12.065 |
Token | ops |
Token ID | 2840 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
ONY | +4.316 |
space | +3.910 |
Stall | +3.419 |
lust | +3.410 |
empt | +3.342 |
Neg logit contributions | |
milo | -8.615 |
oried | -7.478 |
bamboo | -7.398 |
Choi | -7.377 |
conclud | -7.283 |
Token | # |
Token ID | 1303 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ONY | +4.355 |
space | +3.854 |
Stall | +3.763 |
Goth | +3.553 |
lust | +3.474 |
Neg logit contributions | |
milo | -6.583 |
oried | -5.735 |
Choi | -5.400 |
bamboo | -5.318 |
� | -5.289 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ONY | +0.873 |
space | +0.800 |
Stall | +0.756 |
lust | +0.734 |
Goth | +0.727 |
Neg logit contributions | |
milo | -0.818 |
oried | -0.683 |
Choi | -0.644 |
bamboo | -0.630 |
Kw | -0.626 |
Token |
|
Token ID | 198 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ONY | +0.382 |
space | +0.346 |
Stall | +0.326 |
lust | +0.315 |
Goth | +0.312 |
Neg logit contributions | |
milo | -0.446 |
oried | -0.378 |
Choi | -0.360 |
bamboo | -0.352 |
Kw | -0.351 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ONY | +2.236 |
space | +2.050 |
Stall | +1.935 |
lust | +1.874 |
Goth | +1.851 |
Neg logit contributions | |
milo | -2.186 |
oried | -1.831 |
Choi | -1.723 |
bamboo | -1.694 |
Kw | -1.680 |
Token |
|
Token ID | 198 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
ONY | +1.351 |
space | +1.218 |
Stall | +1.158 |
lust | +1.106 |
Goth | +1.102 |
Neg logit contributions | |
milo | -1.630 |
oried | -1.387 |
Choi | -1.314 |
bamboo | -1.286 |
Kw | -1.280 |
Token |
|
Token ID | 198 |
Feature activation | +6.79e+00 |
Pos logit contributions | |
ONY | +2.753 |
space | +2.516 |
Stall | +2.340 |
lust | +2.273 |
Goth | +2.227 |
Neg logit contributions | |
milo | -3.911 |
oried | -3.332 |
Choi | -3.158 |
bamboo | -3.135 |
arij | -3.100 |
Token | T |
Token ID | 51 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
ONY | +4.293 |
space | +3.896 |
Stall | +3.603 |
lust | +3.500 |
Goth | +3.413 |
Neg logit contributions | |
milo | -5.714 |
oried | -4.937 |
Choi | -4.795 |
bamboo | -4.729 |
Kw | -4.615 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ONY | +5.093 |
space | +4.802 |
Stall | +4.510 |
lust | +4.471 |
empt | +4.422 |
Neg logit contributions | |
milo | -4.298 |
oried | -3.469 |
Choi | -3.383 |
Kw | -3.295 |
bamboo | -3.285 |
Token | er |
Token ID | 263 |
Feature activation | +1.60e+01 |
Pos logit contributions | |
ONY | +3.235 |
space | +2.984 |
Stall | +2.834 |
lust | +2.752 |
Goth | +2.699 |
Neg logit contributions | |
milo | -3.102 |
oried | -2.532 |
Choi | -2.464 |
bamboo | -2.409 |
Kw | -2.385 |
Token | at |
Token ID | 265 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
ONY | +7.186 |
space | +6.910 |
thus | +6.453 |
Stall | +6.234 |
ace | +6.225 |
Neg logit contributions | |
milo | -13.925 |
conclud | -12.795 |
� | -12.185 |
Choi | -12.094 |
referen | -11.975 |
Token | ops |
Token ID | 2840 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
ONY | +4.267 |
space | +3.858 |
Stall | +3.402 |
lust | +3.365 |
empt | +3.350 |
Neg logit contributions | |
milo | -8.632 |
oried | -7.467 |
bamboo | -7.387 |
Choi | -7.334 |
conclud | -7.272 |
Token | # |
Token ID | 1303 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ONY | +4.680 |
space | +4.160 |
Stall | +4.080 |
Goth | +3.815 |
lust | +3.707 |
Neg logit contributions | |
milo | -7.838 |
oried | -6.868 |
bamboo | -6.447 |
Choi | -6.422 |
� | -6.372 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
ONY | +1.205 |
space | +1.104 |
Stall | +1.043 |
lust | +1.013 |
Goth | +1.003 |
Neg logit contributions | |
milo | -1.149 |
oried | -0.961 |
Choi | -0.904 |
bamboo | -0.885 |
Kw | -0.880 |
Token |
|
Token ID | 198 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
ONY | +2.476 |
space | +2.223 |
Stall | +2.128 |
Goth | +2.017 |
lust | +2.011 |
Neg logit contributions | |
milo | -3.126 |
oried | -2.677 |
Choi | -2.524 |
bamboo | -2.473 |
� | -2.455 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ONY | +4.141 |
space | +3.913 |
Stall | +3.678 |
lust | +3.567 |
Goth | +3.413 |
Neg logit contributions | |
milo | -4.444 |
oried | -3.776 |
Choi | -3.491 |
bamboo | -3.445 |
arij | -3.440 |
Token |
|
Token ID | 198 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
milo | +0.123 |
oried | +0.104 |
Choi | +0.099 |
bamboo | +0.098 |
Kw | +0.097 |
Neg logit contributions | |
ONY | -0.103 |
space | -0.093 |
Stall | -0.088 |
lust | -0.085 |
Goth | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
milo | +0.605 |
oried | +0.515 |
Choi | +0.493 |
Kw | +0.482 |
Zhang | +0.477 |
Neg logit contributions | |
ONY | -0.575 |
satell | -0.516 |
space | -0.513 |
Stall | -0.491 |
Goth | -0.469 |
Token | Your |
Token ID | 7120 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
milo | +0.922 |
oried | +0.782 |
Choi | +0.745 |
Kw | +0.727 |
bamboo | +0.727 |
Neg logit contributions | |
ONY | -0.783 |
space | -0.707 |
Stall | -0.669 |
lust | -0.643 |
satell | -0.641 |
Token | Inner |
Token ID | 24877 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
ONY | +0.119 |
space | +0.109 |
Stall | +0.103 |
lust | +0.100 |
Goth | +0.099 |
Neg logit contributions | |
milo | -0.119 |
oried | -0.099 |
Choi | -0.094 |
bamboo | -0.092 |
Kw | -0.091 |
Token | Ass |
Token ID | 2195 |
Feature activation | +1.60e+01 |
Pos logit contributions | |
ONY | +3.859 |
space | +3.565 |
Stall | +3.363 |
lust | +3.178 |
Goth | +3.161 |
Neg logit contributions | |
milo | -5.696 |
oried | -4.885 |
arij | -4.511 |
bamboo | -4.489 |
� | -4.468 |
Token | hole |
Token ID | 13207 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
space | +7.559 |
ONY | +7.501 |
Stall | +6.516 |
lust | +6.309 |
empt | +6.159 |
Neg logit contributions | |
milo | -13.966 |
oried | -11.725 |
bamboo | -11.427 |
� | -11.294 |
immigrants | -11.157 |
Token | never |
Token ID | 1239 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
ONY | +0.760 |
space | +0.696 |
Stall | +0.658 |
lust | +0.635 |
Goth | +0.629 |
Neg logit contributions | |
milo | -0.795 |
oried | -0.666 |
Choi | -0.627 |
bamboo | -0.614 |
Kw | -0.609 |
Token | gets |
Token ID | 3011 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
milo | +0.433 |
oried | +0.355 |
Choi | +0.334 |
bamboo | +0.325 |
Kw | +0.324 |
Neg logit contributions | |
ONY | -0.516 |
space | -0.476 |
Stall | -0.453 |
lust | -0.440 |
Goth | -0.436 |
Token | enough |
Token ID | 1576 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
milo | +0.712 |
oried | +0.591 |
Choi | +0.561 |
bamboo | +0.547 |
Kw | +0.544 |
Neg logit contributions | |
ONY | -0.771 |
space | -0.706 |
Stall | -0.669 |
lust | -0.650 |
Goth | -0.643 |
Token | data |
Token ID | 1366 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ONY | +1.819 |
space | +1.677 |
Stall | +1.580 |
lust | +1.530 |
Goth | +1.512 |
Neg logit contributions | |
milo | -1.896 |
oried | -1.576 |
Choi | -1.485 |
Kw | -1.444 |
bamboo | -1.443 |
Token | grades |
Token ID | 19051 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ONY | +1.673 |
space | +1.535 |
Stall | +1.453 |
lust | +1.412 |
Goth | +1.401 |
Neg logit contributions | |
milo | -1.677 |
oried | -1.400 |
Choi | -1.297 |
bamboo | -1.278 |
� | -1.276 |
Token | were |
Token ID | 547 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
milo | +0.241 |
oried | +0.201 |
Choi | +0.189 |
Kw | +0.185 |
bamboo | +0.185 |
Neg logit contributions | |
ONY | -0.246 |
space | -0.227 |
Stall | -0.214 |
lust | -0.208 |
Goth | -0.206 |
Token | put |
Token ID | 1234 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ONY | +0.307 |
space | +0.282 |
Stall | +0.268 |
lust | +0.260 |
Goth | +0.259 |
Neg logit contributions | |
milo | -0.292 |
oried | -0.240 |
Choi | -0.225 |
bamboo | -0.220 |
Kw | -0.220 |
Token | on |
Token ID | 319 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
milo | +0.209 |
oried | +0.175 |
Choi | +0.166 |
Kw | +0.162 |
bamboo | +0.162 |
Neg logit contributions | |
ONY | -0.206 |
space | -0.188 |
Stall | -0.177 |
lust | -0.172 |
Goth | -0.171 |
Token | the |
Token ID | 262 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
milo | +0.753 |
oried | +0.624 |
Choi | +0.590 |
bamboo | +0.574 |
Kw | +0.573 |
Neg logit contributions | |
ONY | -0.818 |
space | -0.751 |
Stall | -0.713 |
lust | -0.691 |
Goth | -0.685 |
Token | back |
Token ID | 736 |
Feature activation | +1.58e+01 |
Pos logit contributions | |
ONY | +2.704 |
space | +2.505 |
Stall | +2.408 |
Goth | +2.313 |
lust | +2.259 |
Neg logit contributions | |
milo | -2.803 |
oried | -2.347 |
Choi | -2.142 |
� | -2.114 |
arij | -2.113 |
Token | burner |
Token ID | 46027 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
space | +6.236 |
ONY | +6.184 |
lust | +5.011 |
empt | +4.921 |
Stall | +4.865 |
Neg logit contributions | |
milo | -15.025 |
aukee | -13.205 |
oried | -13.028 |
arij | -12.868 |
Choi | -12.506 |
Token | , |
Token ID | 11 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
milo | +1.755 |
oried | +1.469 |
Choi | +1.400 |
bamboo | +1.363 |
Kw | +1.357 |
Neg logit contributions | |
ONY | -1.787 |
space | -1.624 |
Stall | -1.542 |
lust | -1.490 |
Goth | -1.477 |
Token | I |
Token ID | 314 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
milo | +2.392 |
oried | +1.989 |
Choi | +1.924 |
bamboo | +1.857 |
Kw | +1.855 |
Neg logit contributions | |
ONY | -2.596 |
space | -2.364 |
Stall | -2.236 |
lust | -2.180 |
satell | -2.160 |
Token | was |
Token ID | 373 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
milo | +0.339 |
oried | +0.279 |
Choi | +0.263 |
bamboo | +0.256 |
Kw | +0.255 |
Neg logit contributions | |
ONY | -0.377 |
space | -0.348 |
Stall | -0.329 |
lust | -0.320 |
Goth | -0.317 |
Token | freed |
Token ID | 13459 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ONY | +1.818 |
space | +1.673 |
Stall | +1.573 |
lust | +1.536 |
Goth | +1.529 |
Neg logit contributions | |
milo | -1.771 |
oried | -1.455 |
Choi | -1.352 |
bamboo | -1.321 |
Kw | -1.318 |
Token | the |
Token ID | 262 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
milo | +1.784 |
oried | +1.480 |
Choi | +1.403 |
bamboo | +1.368 |
Kw | +1.366 |
Neg logit contributions | |
ONY | -2.008 |
space | -1.841 |
Stall | -1.750 |
lust | -1.692 |
Goth | -1.681 |
Token | same |
Token ID | 976 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
milo | +0.343 |
oried | +0.285 |
Choi | +0.269 |
bamboo | +0.262 |
Kw | +0.261 |
Neg logit contributions | |
ONY | -0.364 |
space | -0.333 |
Stall | -0.317 |
lust | -0.307 |
Goth | -0.304 |
Token | instant |
Token ID | 9113 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
milo | +1.546 |
oried | +1.282 |
Choi | +1.220 |
bamboo | +1.192 |
Kw | +1.185 |
Neg logit contributions | |
ONY | -1.769 |
space | -1.619 |
Stall | -1.535 |
lust | -1.492 |
Goth | -1.477 |
Token | your |
Token ID | 534 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
milo | +2.492 |
oried | +2.018 |
Choi | +1.926 |
bamboo | +1.870 |
Kw | +1.860 |
Neg logit contributions | |
ONY | -3.296 |
space | -3.044 |
Stall | -2.899 |
lust | -2.816 |
satell | -2.815 |
Token | Inner |
Token ID | 24877 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
milo | +0.295 |
oried | +0.248 |
Choi | +0.237 |
bamboo | +0.231 |
Kw | +0.230 |
Neg logit contributions | |
ONY | -0.272 |
space | -0.247 |
Stall | -0.233 |
lust | -0.226 |
Goth | -0.223 |
Token | Ass |
Token ID | 2195 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
ONY | +3.151 |
space | +2.858 |
Stall | +2.689 |
lust | +2.530 |
Goth | +2.497 |
Neg logit contributions | |
milo | -5.482 |
oried | -4.760 |
bamboo | -4.421 |
Choi | -4.412 |
arij | -4.392 |
Token | hole |
Token ID | 13207 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
space | +4.742 |
ONY | +4.497 |
lust | +3.728 |
hoe | +3.657 |
Stall | +3.456 |
Neg logit contributions | |
milo | -16.491 |
conclud | -14.900 |
oried | -14.375 |
bamboo | -14.335 |
aukee | -14.146 |
Token | grabs |
Token ID | 22378 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
milo | +0.801 |
oried | +0.664 |
Choi | +0.631 |
bamboo | +0.615 |
Kw | +0.612 |
Neg logit contributions | |
ONY | -0.872 |
space | -0.799 |
Stall | -0.758 |
lust | -0.736 |
Goth | -0.728 |
Token | his |
Token ID | 465 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
milo | +2.973 |
oried | +2.431 |
Choi | +2.328 |
bamboo | +2.297 |
Kw | +2.273 |
Neg logit contributions | |
ONY | -3.694 |
space | -3.370 |
Stall | -3.213 |
lust | -3.125 |
satell | -3.106 |
Token | Ass |
Token ID | 2195 |
Feature activation | +9.19e+00 |
Pos logit contributions | |
ONY | +2.495 |
space | +2.313 |
Stall | +2.188 |
lust | +2.105 |
Goth | +2.090 |
Neg logit contributions | |
milo | -2.426 |
oried | -2.007 |
Choi | -1.886 |
arij | -1.840 |
� | -1.817 |
Token | hole |
Token ID | 13207 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ONY | +4.965 |
space | +4.825 |
Stall | +4.343 |
lust | +4.134 |
empt | +4.029 |
Neg logit contributions | |
milo | -8.291 |
oried | -7.056 |
Choi | -6.702 |
� | -6.687 |
bamboo | -6.649 |
Token | scenes |
Token ID | 8188 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
milo | +1.936 |
oried | +1.494 |
Choi | +1.371 |
Kw | +1.323 |
bamboo | +1.307 |
Neg logit contributions | |
ONY | -4.196 |
space | -3.866 |
Stall | -3.719 |
satell | -3.678 |
lust | -3.655 |
Token | . |
Token ID | 13 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
ONY | +1.566 |
space | +1.444 |
Stall | +1.369 |
lust | +1.333 |
Goth | +1.318 |
Neg logit contributions | |
milo | -1.368 |
oried | -1.121 |
Choi | -1.058 |
bamboo | -1.035 |
Kw | -1.022 |
Token | The |
Token ID | 383 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ONY | +2.924 |
space | +2.651 |
Stall | +2.483 |
lust | +2.324 |
Goth | +2.313 |
Neg logit contributions | |
milo | -5.419 |
oried | -4.665 |
bamboo | -4.432 |
arij | -4.377 |
Choi | -4.363 |
Token | new |
Token ID | 649 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
ONY | +0.300 |
space | +0.274 |
Stall | +0.255 |
lust | +0.245 |
Goth | +0.244 |
Neg logit contributions | |
milo | -0.372 |
oried | -0.315 |
Choi | -0.300 |
bamboo | -0.292 |
Kw | -0.290 |
Token | vehicle |
Token ID | 4038 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ONY | +3.698 |
space | +3.574 |
Stall | +3.218 |
lust | +2.965 |
empt | +2.925 |
Neg logit contributions | |
milo | -6.066 |
oried | -5.249 |
Choi | -4.997 |
� | -4.940 |
Hong | -4.919 |
Token | E |
Token ID | 412 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
ONY | +1.471 |
space | +1.355 |
Stall | +1.281 |
lust | +1.229 |
Goth | +1.221 |
Neg logit contributions | |
milo | -1.497 |
oried | -1.254 |
Choi | -1.186 |
bamboo | -1.171 |
Kw | -1.147 |
Token | ct |
Token ID | 310 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
space | +4.888 |
ONY | +4.533 |
empt | +3.975 |
thus | +3.568 |
lust | +3.566 |
Neg logit contributions | |
milo | -15.817 |
conclud | -14.587 |
bamboo | -14.472 |
oried | -14.440 |
Choi | -14.386 |
Token | o |
Token ID | 78 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ONY | +4.994 |
space | +4.712 |
Stall | +4.367 |
lust | +4.366 |
empt | +4.235 |
Neg logit contributions | |
milo | -4.436 |
oried | -3.583 |
Choi | -3.522 |
bamboo | -3.482 |
conclud | -3.401 |
Token | - |
Token ID | 12 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ONY | +3.434 |
space | +3.172 |
Stall | +2.983 |
lust | +2.910 |
Goth | +2.861 |
Neg logit contributions | |
milo | -3.578 |
oried | -2.970 |
Choi | -2.807 |
bamboo | -2.781 |
arij | -2.741 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
ONY | +1.369 |
space | +1.258 |
Stall | +1.191 |
lust | +1.159 |
Goth | +1.146 |
Neg logit contributions | |
milo | -1.228 |
oried | -1.016 |
Choi | -0.961 |
bamboo | -0.938 |
Kw | -0.932 |
Token | was |
Token ID | 373 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ONY | +2.378 |
space | +2.222 |
Stall | +2.082 |
lust | +2.050 |
Goth | +2.017 |
Neg logit contributions | |
milo | -2.108 |
oried | -1.719 |
Choi | -1.645 |
bamboo | -1.596 |
Kw | -1.578 |
Token | not |
Token ID | 407 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ONY | +4.141 |
space | +3.717 |
Stall | +3.604 |
Goth | +3.470 |
lust | +3.392 |
Neg logit contributions | |
milo | -4.702 |
oried | -4.053 |
Choi | -3.686 |
bamboo | -3.683 |
Hong | -3.642 |
Token | millionaires |
Token ID | 48675 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ONY | +1.178 |
space | +1.074 |
Stall | +1.027 |
lust | +0.991 |
Goth | +0.989 |
Neg logit contributions | |
milo | -1.166 |
oried | -0.969 |
Choi | -0.918 |
bamboo | -0.897 |
Kw | -0.890 |
Token | , |
Token ID | 11 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
milo | +2.000 |
oried | +1.651 |
Choi | +1.570 |
Kw | +1.517 |
bamboo | +1.517 |
Neg logit contributions | |
ONY | -2.314 |
space | -2.132 |
Stall | -2.016 |
lust | -1.965 |
Goth | -1.937 |
Token | � |
Token ID | 447 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ONY | +3.800 |
space | +3.428 |
Stall | +3.315 |
Goth | +3.222 |
lust | +3.137 |
Neg logit contributions | |
milo | -4.110 |
oried | -3.518 |
Choi | -3.213 |
bamboo | -3.205 |
Hong | -3.175 |
Token | � |
Token ID | 251 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ONY | +0.399 |
space | +0.372 |
Stall | +0.356 |
lust | +0.348 |
Goth | +0.346 |
Neg logit contributions | |
milo | -0.225 |
oried | -0.173 |
Choi | -0.161 |
bamboo | -0.154 |
Kw | -0.153 |
Token | Ms |
Token ID | 6997 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
ONY | +2.325 |
space | +2.103 |
Stall | +1.995 |
Goth | +1.924 |
lust | +1.915 |
Neg logit contributions | |
milo | -2.594 |
oried | -2.213 |
Choi | -2.067 |
bamboo | -2.052 |
Hong | -1.998 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e+01 |
Pos logit contributions | |
ONY | +8.802 |
space | +8.147 |
lust | +7.661 |
Stall | +7.481 |
Goth | +7.322 |
Neg logit contributions | |
milo | -12.546 |
conclud | -11.116 |
bamboo | -10.397 |
challeng | -10.262 |
describ | -10.177 |
Token | Ole |
Token ID | 30093 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
ONY | +9.258 |
Stall | +8.547 |
Goth | +8.331 |
space | +8.279 |
Lys | +7.550 |
Neg logit contributions | |
milo | -14.017 |
oried | -12.007 |
bamboo | -11.437 |
sidx | -11.244 |
linkage | -11.232 |
Token | ch |
Token ID | 354 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ONY | +5.706 |
space | +5.593 |
lust | +5.057 |
Stall | +4.926 |
empt | +4.906 |
Neg logit contributions | |
milo | -6.847 |
oried | -5.791 |
conclud | -5.718 |
bamboo | -5.637 |
Choi | -5.513 |
Token | owski |
Token ID | 12079 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
milo | +2.539 |
oried | +2.143 |
Choi | +2.008 |
Kw | +1.981 |
Zhang | +1.959 |
Neg logit contributions | |
ONY | -2.621 |
space | -2.307 |
satell | -2.284 |
Stall | -2.271 |
Goth | -2.153 |
Token | said |
Token ID | 531 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ONY | +1.025 |
space | +0.919 |
Stall | +0.864 |
lust | +0.817 |
Goth | +0.816 |
Neg logit contributions | |
milo | -1.551 |
oried | -1.322 |
Choi | -1.260 |
bamboo | -1.243 |
Kw | -1.226 |
Token | there |
Token ID | 612 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ONY | +3.279 |
space | +2.998 |
Stall | +2.892 |
Goth | +2.788 |
lust | +2.779 |
Neg logit contributions | |
milo | -3.472 |
oried | -2.843 |
Choi | -2.628 |
� | -2.608 |
arij | -2.596 |
Token | , |
Token ID | 11 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
milo | +1.494 |
oried | +1.246 |
Choi | +1.184 |
bamboo | +1.157 |
Kw | +1.151 |
Neg logit contributions | |
ONY | -1.587 |
space | -1.447 |
Stall | -1.372 |
lust | -1.331 |
Goth | -1.318 |
Token | waiting |
Token ID | 4953 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ONY | +3.219 |
space | +2.977 |
Stall | +2.840 |
lust | +2.728 |
Goth | +2.716 |
Neg logit contributions | |
milo | -3.273 |
oried | -2.730 |
Choi | -2.514 |
arij | -2.473 |
Kw | -2.428 |
Token | in |
Token ID | 287 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ONY | +1.899 |
space | +1.750 |
Stall | +1.645 |
lust | +1.606 |
Goth | +1.572 |
Neg logit contributions | |
milo | -2.194 |
oried | -1.836 |
Choi | -1.729 |
Kw | -1.686 |
arij | -1.683 |
Token | the |
Token ID | 262 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ONY | +1.133 |
space | +1.046 |
Stall | +1.002 |
lust | +0.968 |
Goth | +0.958 |
Neg logit contributions | |
milo | -0.930 |
oried | -0.756 |
Choi | -0.707 |
Kw | -0.681 |
bamboo | -0.679 |
Token | back |
Token ID | 736 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
ONY | +3.802 |
space | +3.515 |
Stall | +3.412 |
Goth | +3.247 |
lust | +3.216 |
Neg logit contributions | |
milo | -3.435 |
oried | -2.768 |
Choi | -2.561 |
arij | -2.542 |
� | -2.454 |
Token | of |
Token ID | 286 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
space | +9.513 |
ONY | +9.122 |
Stall | +8.150 |
lust | +8.010 |
empt | +7.578 |
Neg logit contributions | |
milo | -11.955 |
oried | -9.570 |
arij | -9.446 |
aukee | -9.336 |
Choi | -9.328 |
Token | an |
Token ID | 281 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ONY | +1.848 |
space | +1.703 |
Stall | +1.628 |
lust | +1.540 |
Goth | +1.540 |
Neg logit contributions | |
milo | -1.889 |
oried | -1.579 |
Choi | -1.472 |
� | -1.433 |
bamboo | -1.433 |
Token | SUV |
Token ID | 26763 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ONY | +2.337 |
space | +2.129 |
Stall | +2.021 |
Goth | +1.921 |
lust | +1.902 |
Neg logit contributions | |
milo | -2.493 |
oried | -2.099 |
Choi | -1.954 |
Kw | -1.908 |
arij | -1.894 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ONY | +0.102 |
space | +0.093 |
Stall | +0.088 |
lust | +0.085 |
Goth | +0.085 |
Neg logit contributions | |
milo | -0.098 |
oried | -0.082 |
Choi | -0.077 |
bamboo | -0.075 |
Kw | -0.075 |
Token | wearing |
Token ID | 5762 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
ONY | +1.641 |
space | +1.509 |
Stall | +1.434 |
lust | +1.385 |
Goth | +1.374 |
Neg logit contributions | |
milo | -1.607 |
oried | -1.339 |
Choi | -1.250 |
Kw | -1.211 |
bamboo | -1.209 |
Token | these |
Token ID | 777 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
ONY | +1.780 |
space | +1.630 |
Stall | +1.553 |
lust | +1.490 |
Goth | +1.489 |
Neg logit contributions | |
milo | -1.775 |
oried | -1.482 |
Choi | -1.394 |
bamboo | -1.351 |
Kw | -1.345 |
Token | checking |
Token ID | 10627 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ONY | +2.808 |
space | +2.611 |
Stall | +2.497 |
Goth | +2.385 |
lust | +2.374 |
Neg logit contributions | |
milo | -2.827 |
oried | -2.352 |
Choi | -2.203 |
arij | -2.120 |
bamboo | -2.109 |
Token | letters |
Token ID | 7475 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
milo | +0.376 |
oried | +0.313 |
Choi | +0.297 |
bamboo | +0.290 |
Kw | +0.289 |
Neg logit contributions | |
ONY | -0.387 |
space | -0.354 |
Stall | -0.335 |
lust | -0.325 |
Goth | -0.322 |
Token | TIT |
Token ID | 37977 |
Feature activation | +9.56e+00 |
Pos logit contributions | |
ONY | +2.154 |
space | +2.001 |
Stall | +1.887 |
lust | +1.807 |
Goth | +1.799 |
Neg logit contributions | |
milo | -2.211 |
oried | -1.853 |
Choi | -1.738 |
bamboo | -1.685 |
Kw | -1.678 |
Token | FOR |
Token ID | 7473 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ONY | +6.665 |
space | +5.957 |
Stall | +5.635 |
Goth | +5.357 |
lust | +5.296 |
Neg logit contributions | |
milo | -7.347 |
oried | -6.185 |
Choi | -5.868 |
Kw | -5.684 |
arij | -5.654 |
Token | T |
Token ID | 309 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
ONY | +6.145 |
space | +5.338 |
Stall | +5.163 |
Goth | +4.861 |
lust | +4.772 |
Neg logit contributions | |
milo | -8.494 |
oried | -7.315 |
Choi | -6.884 |
arij | -6.766 |
bamboo | -6.756 |
Token | AT |
Token ID | 1404 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
ONY | +7.789 |
space | +6.087 |
Stall | +5.224 |
empt | +5.213 |
lust | +5.152 |
Neg logit contributions | |
milo | -13.798 |
oried | -11.978 |
Choi | -11.926 |
bamboo | -11.767 |
Kw | -11.671 |
Token |
|
Token ID | 198 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ONY | +4.600 |
space | +4.243 |
Stall | +3.963 |
Goth | +3.784 |
lust | +3.777 |
Neg logit contributions | |
milo | -4.945 |
oried | -4.173 |
Choi | -3.940 |
bamboo | -3.801 |
Kw | -3.772 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ONY | +2.171 |
space | +1.980 |
Stall | +1.828 |
lust | +1.791 |
Goth | +1.747 |
Neg logit contributions | |
milo | -2.950 |
oried | -2.518 |
Choi | -2.403 |
bamboo | -2.369 |
Kw | -2.337 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
milo | +1.602 |
oried | +1.300 |
Choi | +1.218 |
Kw | +1.182 |
bamboo | +1.181 |
Neg logit contributions | |
ONY | -1.955 |
space | -1.781 |
Stall | -1.728 |
satell | -1.668 |
Goth | -1.664 |
Token | a |
Token ID | 64 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
milo | +2.470 |
oried | +1.981 |
Choi | +1.834 |
bamboo | +1.776 |
Kw | +1.774 |
Neg logit contributions | |
ONY | -3.964 |
space | -3.625 |
Stall | -3.495 |
satell | -3.419 |
Goth | -3.402 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ONY | +0.873 |
space | +0.800 |
Stall | +0.756 |
lust | +0.734 |
Goth | +0.727 |
Neg logit contributions | |
milo | -0.818 |
oried | -0.683 |
Choi | -0.644 |
bamboo | -0.630 |
Kw | -0.626 |
Token |
|
Token ID | 198 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ONY | +0.382 |
space | +0.346 |
Stall | +0.326 |
lust | +0.315 |
Goth | +0.312 |
Neg logit contributions | |
milo | -0.446 |
oried | -0.378 |
Choi | -0.360 |
bamboo | -0.352 |
Kw | -0.351 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
ONY | +2.026 |
space | +1.841 |
Stall | +1.720 |
lust | +1.666 |
Goth | +1.639 |
Neg logit contributions | |
milo | -2.671 |
oried | -2.275 |
Choi | -2.165 |
bamboo | -2.133 |
Kw | -2.106 |
Token | T |
Token ID | 51 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
ONY | +3.602 |
space | +3.258 |
Stall | +3.007 |
lust | +2.911 |
Goth | +2.859 |
Neg logit contributions | |
milo | -4.676 |
oried | -4.024 |
Choi | -3.899 |
bamboo | -3.833 |
Kw | -3.756 |
Token | ric |
Token ID | 1173 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ONY | +5.300 |
space | +4.973 |
Stall | +4.661 |
lust | +4.623 |
empt | +4.585 |
Neg logit contributions | |
milo | -4.382 |
oried | -3.541 |
Choi | -3.445 |
Kw | -3.363 |
bamboo | -3.340 |
Token | er |
Token ID | 263 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
ONY | +3.181 |
space | +2.938 |
Stall | +2.785 |
lust | +2.709 |
Goth | +2.649 |
Neg logit contributions | |
milo | -3.063 |
oried | -2.502 |
Choi | -2.431 |
bamboo | -2.379 |
Kw | -2.361 |
Token | at |
Token ID | 265 |
Feature activation | +8.22e+00 |
Pos logit contributions | |
ONY | +6.851 |
space | +6.781 |
thus | +6.106 |
Stall | +5.997 |
ace | +5.942 |
Neg logit contributions | |
milo | -13.124 |
conclud | -12.285 |
referen | -11.593 |
� | -11.429 |
Choi | -11.419 |
Token | ops |
Token ID | 2840 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
ONY | +4.109 |
space | +3.723 |
Stall | +3.258 |
lust | +3.235 |
empt | +3.163 |
Neg logit contributions | |
milo | -7.924 |
oried | -6.878 |
bamboo | -6.778 |
Choi | -6.768 |
Kw | -6.679 |
Token | # |
Token ID | 1303 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ONY | +3.951 |
space | +3.511 |
Stall | +3.403 |
Goth | +3.208 |
lust | +3.148 |
Neg logit contributions | |
milo | -6.054 |
oried | -5.274 |
Choi | -4.964 |
bamboo | -4.908 |
� | -4.869 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ONY | +0.977 |
space | +0.895 |
Stall | +0.845 |
lust | +0.822 |
Goth | +0.811 |
Neg logit contributions | |
milo | -0.933 |
oried | -0.780 |
Choi | -0.736 |
bamboo | -0.721 |
Kw | -0.715 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ONY | +1.676 |
space | +1.504 |
Stall | +1.430 |
lust | +1.361 |
Goth | +1.361 |
Neg logit contributions | |
milo | -2.096 |
oried | -1.793 |
Choi | -1.698 |
bamboo | -1.663 |
Kw | -1.652 |
Token | 47 |
Token ID | 2857 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
milo | +3.814 |
oried | +3.113 |
Zhang | +2.844 |
Kw | +2.812 |
Choi | +2.794 |
Neg logit contributions | |
ONY | -5.827 |
satell | -5.585 |
Stall | -5.216 |
space | -5.193 |
haps | -5.005 |
Token | ] |
Token ID | 60 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ONY | +0.006 |
space | +0.005 |
satell | +0.005 |
Stall | +0.004 |
Goth | +0.004 |
Neg logit contributions | |
milo | -0.011 |
oried | -0.009 |
Choi | -0.009 |
Kw | -0.009 |
Zhang | -0.009 |
Token | < |
Token ID | 1279 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
milo | +2.129 |
oried | +1.714 |
Choi | +1.622 |
bamboo | +1.580 |
Kw | +1.572 |
Neg logit contributions | |
ONY | -2.909 |
space | -2.702 |
Stall | -2.568 |
lust | -2.512 |
Goth | -2.480 |
Token | met |
Token ID | 4164 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ONY | +3.586 |
space | +3.387 |
lust | +3.098 |
Stall | +3.069 |
empt | +3.003 |
Neg logit contributions | |
milo | -3.341 |
oried | -2.845 |
Choi | -2.775 |
bamboo | -2.662 |
Kw | -2.647 |
Token | ros |
Token ID | 4951 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
milo | +0.961 |
oried | +0.829 |
Choi | +0.792 |
bamboo | +0.776 |
Kw | +0.775 |
Neg logit contributions | |
ONY | -0.664 |
space | -0.591 |
Stall | -0.554 |
lust | -0.529 |
Goth | -0.523 |
Token | xual |
Token ID | 5541 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
ONY | +2.727 |
space | +2.519 |
Stall | +2.332 |
lust | +2.321 |
empt | +2.239 |
Neg logit contributions | |
milo | -2.928 |
oried | -2.474 |
Choi | -2.400 |
bamboo | -2.334 |
Kw | -2.324 |
Token | th |
Token ID | 400 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
space | +6.071 |
lust | +5.824 |
thus | +5.541 |
ONY | +5.495 |
empt | +4.942 |
Neg logit contributions | |
milo | -14.021 |
conclud | -12.908 |
Choi | -12.823 |
referen | -12.626 |
Dai | -12.567 |
Token | ug |
Token ID | 1018 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
ONY | +3.120 |
space | +2.790 |
lust | +2.486 |
Stall | +2.371 |
empt | +2.312 |
Neg logit contributions | |
milo | -7.666 |
oried | -6.639 |
Choi | -6.631 |
bamboo | -6.541 |
conclud | -6.485 |
Token | > |
Token ID | 29 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ONY | +1.551 |
space | +1.380 |
Stall | +1.246 |
lust | +1.204 |
Goth | +1.162 |
Neg logit contributions | |
milo | -3.010 |
oried | -2.633 |
Choi | -2.543 |
bamboo | -2.503 |
Kw | -2.491 |
Token | le |
Token ID | 443 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
ONY | +2.119 |
space | +1.935 |
Stall | +1.854 |
Goth | +1.777 |
lust | +1.764 |
Neg logit contributions | |
milo | -2.249 |
oried | -1.905 |
Choi | -1.786 |
bamboo | -1.734 |
� | -1.730 |
Token | l |
Token ID | 75 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ONY | +0.305 |
space | +0.283 |
Stall | +0.270 |
lust | +0.264 |
Goth | +0.259 |
Neg logit contributions | |
milo | -0.222 |
oried | -0.180 |
Choi | -0.169 |
bamboo | -0.163 |
Kw | -0.162 |
Token | less |
Token ID | 1203 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
milo | +2.230 |
oried | +1.871 |
Choi | +1.772 |
Kw | +1.739 |
bamboo | +1.725 |
Neg logit contributions | |
ONY | -2.316 |
space | -2.095 |
Stall | -1.983 |
satell | -1.938 |
Goth | -1.903 |
Token | Apprentice |
Token ID | 31581 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
milo | +0.117 |
oried | +0.098 |
Choi | +0.094 |
bamboo | +0.091 |
Kw | +0.091 |
Neg logit contributions | |
ONY | -0.110 |
space | -0.100 |
Stall | -0.094 |
lust | -0.091 |
Goth | -0.090 |
Token | " |
Token ID | 1 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ONY | +3.031 |
space | +2.812 |
Stall | +2.671 |
lust | +2.609 |
Goth | +2.589 |
Neg logit contributions | |
milo | -3.049 |
oried | -2.533 |
Choi | -2.351 |
bamboo | -2.332 |
� | -2.300 |
Token | from |
Token ID | 422 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
milo | +0.784 |
oried | +0.651 |
Choi | +0.619 |
bamboo | +0.606 |
Kw | +0.604 |
Neg logit contributions | |
ONY | -0.830 |
space | -0.757 |
Stall | -0.718 |
lust | -0.698 |
satell | -0.689 |
Token | In |
Token ID | 554 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
ONY | +3.506 |
space | +3.195 |
Stall | +3.007 |
Goth | +2.914 |
lust | +2.898 |
Neg logit contributions | |
milo | -3.881 |
oried | -3.297 |
Choi | -3.103 |
bamboo | -3.012 |
arij | -3.001 |
Token | U |
Token ID | 471 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
ONY | +0.431 |
space | +0.396 |
Stall | +0.376 |
lust | +0.366 |
Goth | +0.362 |
Neg logit contributions | |
milo | -0.368 |
oried | -0.303 |
Choi | -0.286 |
bamboo | -0.278 |
Kw | -0.277 |
Token | ter |
Token ID | 353 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
space | +8.596 |
ONY | +8.269 |
Stall | +7.175 |
thus | +7.157 |
lust | +7.142 |
Neg logit contributions | |
milo | -11.975 |
conclud | -10.560 |
oried | -10.012 |
bamboo | -9.849 |
challeng | -9.716 |
Token | o |
Token ID | 78 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ONY | +4.295 |
space | +4.049 |
Stall | +3.784 |
lust | +3.759 |
Goth | +3.676 |
Neg logit contributions | |
milo | -3.587 |
oried | -2.860 |
Choi | -2.769 |
bamboo | -2.720 |
Kw | -2.686 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
ONY | +1.661 |
space | +1.513 |
Stall | +1.435 |
lust | +1.384 |
Goth | +1.383 |
Neg logit contributions | |
milo | -1.736 |
oried | -1.456 |
Choi | -1.374 |
bamboo | -1.338 |
Kw | -1.329 |
Token | The |
Token ID | 383 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ONY | +2.498 |
space | +2.264 |
Stall | +2.159 |
Goth | +2.079 |
lust | +2.049 |
Neg logit contributions | |
milo | -2.942 |
oried | -2.487 |
Choi | -2.320 |
bamboo | -2.308 |
arij | -2.273 |
Token | book |
Token ID | 1492 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
milo | +0.115 |
oried | +0.096 |
Choi | +0.091 |
bamboo | +0.088 |
Kw | +0.088 |
Neg logit contributions | |
ONY | -0.122 |
space | -0.112 |
Stall | -0.106 |
lust | -0.103 |
Goth | -0.102 |
Token | have |
Token ID | 423 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
milo | +1.643 |
oried | +1.379 |
Choi | +1.327 |
bamboo | +1.293 |
Kw | +1.284 |
Neg logit contributions | |
ONY | -1.622 |
space | -1.474 |
Stall | -1.393 |
lust | -1.350 |
Goth | -1.339 |
Token | any |
Token ID | 597 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
milo | +2.018 |
oried | +1.685 |
Choi | +1.620 |
bamboo | +1.571 |
Kw | +1.569 |
Neg logit contributions | |
ONY | -2.235 |
space | -2.038 |
Stall | -1.927 |
lust | -1.885 |
Goth | -1.857 |
Token | statistics |
Token ID | 7869 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
milo | +2.543 |
oried | +2.108 |
Choi | +2.044 |
Kw | +2.001 |
bamboo | +1.993 |
Neg logit contributions | |
ONY | -2.846 |
space | -2.573 |
Stall | -2.451 |
lust | -2.373 |
satell | -2.366 |
Token | your |
Token ID | 534 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
milo | +2.602 |
oried | +2.136 |
Choi | +2.058 |
bamboo | +1.998 |
Kw | +1.996 |
Neg logit contributions | |
ONY | -3.015 |
space | -2.756 |
Stall | -2.617 |
lust | -2.546 |
Goth | -2.530 |
Token | Inner |
Token ID | 24877 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
milo | +0.465 |
oried | +0.393 |
Choi | +0.373 |
bamboo | +0.365 |
Kw | +0.363 |
Neg logit contributions | |
ONY | -0.424 |
space | -0.385 |
Stall | -0.363 |
lust | -0.351 |
Goth | -0.348 |
Token | Ass |
Token ID | 2195 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
ONY | +2.760 |
space | +2.493 |
Stall | +2.335 |
lust | +2.197 |
Goth | +2.179 |
Neg logit contributions | |
milo | -4.826 |
oried | -4.200 |
bamboo | -3.914 |
Choi | -3.897 |
� | -3.872 |
Token | hole |
Token ID | 13207 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
space | +5.441 |
ONY | +5.276 |
lust | +4.579 |
hoe | +4.427 |
Stall | +4.339 |
Neg logit contributions | |
milo | -14.701 |
conclud | -13.087 |
bamboo | -12.583 |
oried | -12.556 |
aukee | -12.284 |
Token | can |
Token ID | 460 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ONY | +0.233 |
space | +0.213 |
Stall | +0.201 |
lust | +0.194 |
Goth | +0.193 |
Neg logit contributions | |
milo | -0.241 |
oried | -0.202 |
Choi | -0.189 |
bamboo | -0.185 |
Kw | -0.185 |
Token | use |
Token ID | 779 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
milo | +0.128 |
oried | +0.105 |
Choi | +0.099 |
bamboo | +0.096 |
Kw | +0.096 |
Neg logit contributions | |
ONY | -0.144 |
space | -0.133 |
Stall | -0.126 |
lust | -0.122 |
Goth | -0.121 |
Token | against |
Token ID | 1028 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
milo | +0.979 |
oried | +0.810 |
Choi | +0.767 |
bamboo | +0.747 |
Kw | +0.743 |
Neg logit contributions | |
ONY | -1.091 |
space | -1.001 |
Stall | -0.951 |
lust | -0.923 |
Goth | -0.915 |
Token | you |
Token ID | 345 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
milo | +3.246 |
oried | +2.524 |
Choi | +2.407 |
Kw | +2.328 |
bamboo | +2.319 |
Neg logit contributions | |
ONY | -6.472 |
space | -6.060 |
Stall | -5.823 |
lust | -5.715 |
satell | -5.684 |
Token | obvious |
Token ID | 3489 |
Feature activation | +7.85e+00 |
Pos logit contributions | |
ONY | +0.781 |
space | +0.704 |
Stall | +0.664 |
lust | +0.639 |
Goth | +0.635 |
Neg logit contributions | |
milo | -0.913 |
oried | -0.759 |
Choi | -0.726 |
Kw | -0.706 |
bamboo | -0.705 |
Token | ( |
Token ID | 357 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
ONY | +4.867 |
space | +4.600 |
Stall | +4.307 |
lust | +4.136 |
Goth | +4.029 |
Neg logit contributions | |
milo | -6.571 |
oried | -5.594 |
bamboo | -5.330 |
Choi | -5.315 |
aukee | -5.200 |
Token | as |
Token ID | 292 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
ONY | +3.692 |
space | +3.539 |
lust | +3.238 |
Stall | +3.183 |
thus | +3.163 |
Neg logit contributions | |
milo | -3.180 |
oried | -2.623 |
Choi | -2.553 |
bamboo | -2.498 |
Kw | -2.476 |
Token | opposed |
Token ID | 6886 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ONY | +4.326 |
space | +4.092 |
lust | +3.702 |
Stall | +3.643 |
Goth | +3.641 |
Neg logit contributions | |
milo | -5.830 |
oried | -5.003 |
Choi | -4.778 |
bamboo | -4.707 |
� | -4.669 |
Token | to |
Token ID | 284 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
ONY | +0.267 |
space | +0.243 |
Stall | +0.232 |
satell | +0.228 |
lust | +0.224 |
Neg logit contributions | |
milo | -0.226 |
oried | -0.187 |
Choi | -0.176 |
bamboo | -0.171 |
Kw | -0.171 |
Token | back |
Token ID | 736 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
milo | +3.275 |
oried | +2.706 |
bamboo | +2.460 |
Zhang | +2.459 |
fabricated | +2.407 |
Neg logit contributions | |
ONY | -6.081 |
space | -5.520 |
satell | -5.414 |
Stall | -5.322 |
lust | -5.153 |
Token | in |
Token ID | 287 |
Feature activation | +7.84e+00 |
Pos logit contributions | |
space | +5.993 |
ONY | +5.796 |
lust | +5.146 |
Stall | +4.947 |
Goth | +4.767 |
Neg logit contributions | |
milo | -14.270 |
arij | -12.470 |
conclud | -12.469 |
challeng | -12.446 |
aukee | -12.442 |
Token | the |
Token ID | 262 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
ONY | +4.766 |
space | +4.519 |
Stall | +4.138 |
lust | +4.099 |
Goth | +3.991 |
Neg logit contributions | |
milo | -6.719 |
oried | -5.696 |
arij | -5.406 |
conclud | -5.398 |
Choi | -5.386 |
Token | day |
Token ID | 1110 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
milo | +0.065 |
oried | +0.055 |
Choi | +0.052 |
bamboo | +0.050 |
Kw | +0.050 |
Neg logit contributions | |
ONY | -0.070 |
space | -0.064 |
Stall | -0.061 |
lust | -0.059 |
satell | -0.059 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
milo | +3.883 |
oried | +3.338 |
Choi | +3.102 |
Zhang | +3.040 |
Kw | +3.040 |
Neg logit contributions | |
ONY | -3.882 |
space | -3.483 |
satell | -3.389 |
Stall | -3.343 |
lust | -3.231 |
Token | at |
Token ID | 379 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
ONY | +3.077 |
space | +2.834 |
Stall | +2.647 |
lust | +2.559 |
Goth | +2.516 |
Neg logit contributions | |
milo | -3.797 |
oried | -3.235 |
Choi | -3.095 |
bamboo | -3.022 |
� | -3.006 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ONY | +0.085 |
space | +0.078 |
Stall | +0.074 |
lust | +0.072 |
Goth | +0.071 |
Neg logit contributions | |
milo | -0.083 |
oried | -0.069 |
Choi | -0.065 |
bamboo | -0.064 |
Kw | -0.063 |
Token | - |
Token ID | 12 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
milo | +0.972 |
oried | +0.803 |
Choi | +0.758 |
bamboo | +0.739 |
Kw | +0.736 |
Neg logit contributions | |
ONY | -1.103 |
space | -1.011 |
Stall | -0.960 |
lust | -0.931 |
Goth | -0.924 |
Token | 1 |
Token ID | 16 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
milo | +1.611 |
oried | +1.325 |
Choi | +1.246 |
bamboo | +1.213 |
Kw | +1.209 |
Neg logit contributions | |
ONY | -1.887 |
space | -1.726 |
Stall | -1.649 |
lust | -1.595 |
Goth | -1.588 |
Token | on |
Token ID | 319 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
milo | +0.478 |
oried | +0.399 |
Choi | +0.380 |
bamboo | +0.371 |
Kw | +0.369 |
Neg logit contributions | |
ONY | -0.464 |
space | -0.425 |
Stall | -0.401 |
lust | -0.390 |
Goth | -0.385 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
milo | +2.024 |
oried | +1.688 |
Choi | +1.623 |
Kw | +1.583 |
bamboo | +1.569 |
Neg logit contributions | |
ONY | -2.330 |
space | -2.119 |
Stall | -2.008 |
lust | -1.946 |
satell | -1.936 |
Token | back |
Token ID | 736 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
ONY | +1.440 |
space | +1.350 |
Stall | +1.297 |
lust | +1.264 |
Goth | +1.259 |
Neg logit contributions | |
milo | -0.901 |
oried | -0.690 |
Choi | -0.645 |
bamboo | -0.610 |
Hong | -0.606 |
Token | of |
Token ID | 286 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
space | +7.725 |
ONY | +7.544 |
lust | +7.157 |
Stall | +6.745 |
empt | +6.641 |
Neg logit contributions | |
milo | -12.304 |
aukee | -10.216 |
Choi | -10.135 |
oried | -10.101 |
Collider | -9.940 |
Token | goals |
Token ID | 4661 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ONY | +0.757 |
space | +0.700 |
Stall | +0.665 |
lust | +0.644 |
Goth | +0.639 |
Neg logit contributions | |
milo | -0.702 |
oried | -0.578 |
Choi | -0.541 |
bamboo | -0.533 |
Kw | -0.522 |
Token | to |
Token ID | 284 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
milo | +1.816 |
oried | +1.485 |
Choi | +1.409 |
Kw | +1.369 |
bamboo | +1.359 |
Neg logit contributions | |
ONY | -2.350 |
space | -2.164 |
Stall | -2.056 |
lust | -1.998 |
Goth | -1.987 |
Token | Justin |
Token ID | 10799 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
ONY | +0.105 |
space | +0.097 |
Stall | +0.092 |
lust | +0.089 |
Goth | +0.088 |
Neg logit contributions | |
milo | -0.099 |
oried | -0.081 |
Choi | -0.076 |
bamboo | -0.075 |
Kw | -0.074 |
Token | Williams |
Token ID | 6484 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
milo | +3.230 |
Choi | +2.452 |
oried | +2.408 |
Kw | +2.348 |
Hugo | +2.236 |
Neg logit contributions | |
ONY | -7.578 |
space | -7.022 |
satell | -6.782 |
Stall | -6.660 |
lust | -6.588 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ONY | +2.273 |
space | +2.087 |
Stall | +1.962 |
lust | +1.928 |
Goth | +1.878 |
Neg logit contributions | |
milo | -2.390 |
oried | -2.000 |
Choi | -1.886 |
bamboo | -1.835 |
� | -1.834 |
Token | And |
Token ID | 843 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ONY | +1.686 |
space | +1.540 |
Stall | +1.470 |
lust | +1.408 |
Goth | +1.398 |
Neg logit contributions | |
milo | -1.916 |
oried | -1.610 |
bamboo | -1.492 |
Choi | -1.487 |
arij | -1.479 |
Token | while |
Token ID | 981 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ONY | +3.226 |
space | +2.974 |
Stall | +2.818 |
lust | +2.715 |
Goth | +2.692 |
Neg logit contributions | |
milo | -3.111 |
oried | -2.568 |
Choi | -2.379 |
� | -2.367 |
arij | -2.366 |
Token | your |
Token ID | 534 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ONY | +1.083 |
space | +0.998 |
Stall | +0.951 |
lust | +0.922 |
Goth | +0.914 |
Neg logit contributions | |
milo | -0.918 |
oried | -0.757 |
Choi | -0.701 |
bamboo | -0.685 |
� | -0.680 |
Token | Inner |
Token ID | 24877 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
ONY | +0.253 |
space | +0.231 |
Stall | +0.219 |
lust | +0.212 |
Goth | +0.210 |
Neg logit contributions | |
milo | -0.256 |
oried | -0.214 |
Choi | -0.202 |
bamboo | -0.197 |
Kw | -0.196 |
Token | Ass |
Token ID | 2195 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
ONY | +2.708 |
space | +2.454 |
Stall | +2.291 |
lust | +2.157 |
Goth | +2.129 |
Neg logit contributions | |
milo | -4.635 |
oried | -4.030 |
Choi | -3.746 |
bamboo | -3.743 |
arij | -3.723 |
Token | hole |
Token ID | 13207 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
space | +5.326 |
ONY | +5.172 |
lust | +4.278 |
Stall | +4.199 |
hoe | +4.118 |
Neg logit contributions | |
milo | -14.671 |
oried | -12.677 |
conclud | -12.614 |
bamboo | -12.458 |
� | -12.305 |
Token | is |
Token ID | 318 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ONY | +0.255 |
space | +0.233 |
Stall | +0.221 |
lust | +0.214 |
Goth | +0.212 |
Neg logit contributions | |
milo | -0.250 |
oried | -0.208 |
Choi | -0.197 |
bamboo | -0.192 |
Kw | -0.191 |
Token | confused |
Token ID | 10416 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
milo | +1.722 |
oried | +1.426 |
Choi | +1.361 |
bamboo | +1.325 |
Kw | +1.316 |
Neg logit contributions | |
ONY | -1.962 |
space | -1.800 |
Stall | -1.706 |
lust | -1.659 |
Goth | -1.641 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
milo | +0.709 |
oried | +0.589 |
Choi | +0.558 |
bamboo | +0.544 |
Kw | +0.542 |
Neg logit contributions | |
ONY | -0.761 |
space | -0.697 |
Stall | -0.661 |
lust | -0.641 |
Goth | -0.635 |
Token | your |
Token ID | 534 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
ONY | +0.991 |
space | +0.909 |
Stall | +0.862 |
lust | +0.836 |
Goth | +0.825 |
Neg logit contributions | |
milo | -0.961 |
oried | -0.799 |
Choi | -0.747 |
bamboo | -0.730 |
Kw | -0.726 |
Token | ), |
Token ID | 828 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ONY | +0.929 |
space | +0.847 |
Stall | +0.800 |
lust | +0.776 |
Goth | +0.766 |
Neg logit contributions | |
milo | -0.958 |
oried | -0.802 |
Choi | -0.762 |
bamboo | -0.744 |
Kw | -0.741 |
Token | reduce |
Token ID | 4646 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
milo | +0.988 |
oried | +0.807 |
Choi | +0.770 |
bamboo | +0.748 |
Kw | +0.740 |
Neg logit contributions | |
ONY | -1.231 |
space | -1.120 |
Stall | -1.068 |
lust | -1.036 |
satell | -1.033 |
Token | heat |
Token ID | 4894 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
milo | +2.867 |
oried | +2.297 |
Choi | +2.251 |
Kw | +2.187 |
bamboo | +2.185 |
Neg logit contributions | |
ONY | -4.051 |
space | -3.563 |
satell | -3.528 |
Stall | -3.435 |
Goth | -3.317 |
Token | to |
Token ID | 284 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
milo | +2.224 |
oried | +1.826 |
Choi | +1.752 |
Kw | +1.694 |
Hugo | +1.676 |
Neg logit contributions | |
ONY | -3.242 |
satell | -3.006 |
space | -2.881 |
Stall | -2.790 |
haps | -2.705 |
Token | low |
Token ID | 1877 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
milo | +2.426 |
Choi | +1.634 |
bamboo | +1.576 |
oried | +1.554 |
immigrants | +1.358 |
Neg logit contributions | |
ONY | -9.761 |
satell | -9.001 |
space | -8.932 |
Stall | -8.498 |
lust | -8.401 |
Token | and |
Token ID | 290 |
Feature activation | -1.78e+01 |
Pos logit contributions | |
milo | +3.594 |
oried | +2.923 |
Choi | +2.890 |
Kw | +2.784 |
Zhang | +2.762 |
Neg logit contributions | |
ONY | -5.687 |
satell | -5.513 |
space | -4.950 |
Stall | -4.857 |
haps | -4.724 |
Token | cook |
Token ID | 4255 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
milo | +4.229 |
oried | +3.329 |
Choi | +3.093 |
cooking | +2.808 |
immigrants | +2.756 |
Neg logit contributions | |
ONY | -19.144 |
satell | -18.211 |
space | -17.129 |
Stall | -17.053 |
ACTED | -16.871 |
Token | f |
Token ID | 277 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
milo | +3.645 |
oried | +2.928 |
bamboo | +2.868 |
Choi | +2.814 |
fabricated | +2.773 |
Neg logit contributions | |
ONY | -5.275 |
space | -4.660 |
satell | -4.563 |
Stall | -4.458 |
ACTED | -4.298 |
Token | rit |
Token ID | 799 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
milo | +3.879 |
oried | +2.765 |
ru | +2.535 |
Zhang | +2.001 |
arov | +1.991 |
Neg logit contributions | |
ONY | -10.305 |
satell | -9.811 |
Stall | -9.059 |
space | -8.881 |
ACTED | -8.816 |
Token | ters |
Token ID | 1010 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
ONY | +2.578 |
space | +2.429 |
Stall | +2.293 |
lust | +2.254 |
Goth | +2.211 |
Neg logit contributions | |
milo | -1.960 |
oried | -1.578 |
Choi | -1.497 |
bamboo | -1.464 |
Kw | -1.455 |
Token | on |
Token ID | 319 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
milo | +1.692 |
oried | +1.380 |
Choi | +1.319 |
Kw | +1.281 |
bamboo | +1.271 |
Neg logit contributions | |
ONY | -2.295 |
space | -2.076 |
satell | -2.058 |
Stall | -1.990 |
Goth | -1.930 |
Token | side |
Token ID | 1735 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ONY | +3.614 |
space | +3.383 |
Stall | +3.120 |
lust | +2.996 |
empt | +2.992 |
Neg logit contributions | |
milo | -4.562 |
oried | -3.955 |
Choi | -3.661 |
arij | -3.646 |
Hong | -3.623 |
Token | for |
Token ID | 329 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
milo | +1.138 |
oried | +0.942 |
Choi | +0.896 |
bamboo | +0.874 |
Kw | +0.867 |
Neg logit contributions | |
ONY | -1.258 |
space | -1.148 |
Stall | -1.093 |
lust | -1.060 |
Goth | -1.052 |
Token | about |
Token ID | 546 |
Feature activation | -8.87e+00 |
Pos logit contributions | |
milo | +5.579 |
Choi | +4.644 |
bamboo | +4.545 |
oried | +4.439 |
Kw | +4.355 |
Neg logit contributions | |
ONY | -8.808 |
space | -8.014 |
Stall | -7.617 |
ヘ | -7.594 |
lust | -7.560 |
Token | 2 |
Token ID | 362 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
milo | +5.050 |
Choi | +4.116 |
oried | +4.052 |
bamboo | +4.020 |
Kw | +3.885 |
Neg logit contributions | |
ONY | -7.756 |
space | -7.033 |
Stall | -6.692 |
satell | -6.646 |
lust | -6.605 |
Token | / |
Token ID | 14 |
Feature activation | -7.04e+00 |
Pos logit contributions | |
milo | +5.931 |
oried | +4.805 |
bamboo | +4.724 |
Choi | +4.707 |
Kw | +4.549 |
Neg logit contributions | |
ONY | -7.180 |
space | -6.610 |
Stall | -6.306 |
satell | -6.192 |
lust | -6.176 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
milo | +3.835 |
oried | +2.987 |
Choi | +2.771 |
Zhang | +2.658 |
bamboo | +2.646 |
Neg logit contributions | |
ONY | -6.560 |
Stall | -5.895 |
space | -5.884 |
Goth | -5.747 |
satell | -5.732 |
Token | minutes |
Token ID | 2431 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
milo | +9.268 |
Choi | +7.638 |
bamboo | +7.445 |
oried | +7.395 |
Kw | +7.292 |
Neg logit contributions | |
ONY | -12.419 |
satell | -10.886 |
space | -10.674 |
Stall | -10.572 |
ヘ | -10.384 |
Token | until |
Token ID | 1566 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
milo | +6.119 |
Choi | +5.004 |
oried | +4.937 |
bamboo | +4.859 |
── | +4.715 |
Neg logit contributions | |
ONY | -8.980 |
space | -8.207 |
Stall | -7.905 |
satell | -7.772 |
Goth | -7.743 |
Token | golden |
Token ID | 10861 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
milo | +2.470 |
oried | +2.046 |
Choi | +2.009 |
bamboo | +1.990 |
Kw | +1.910 |
Neg logit contributions | |
ONY | -2.712 |
space | -2.480 |
Stall | -2.349 |
Goth | -2.242 |
satell | -2.236 |
Token | brown |
Token ID | 7586 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
milo | +2.583 |
oried | +2.069 |
Choi | +1.957 |
bamboo | +1.909 |
Kw | +1.832 |
Neg logit contributions | |
ONY | -3.905 |
space | -3.635 |
Stall | -3.471 |
Goth | -3.361 |
lust | -3.360 |
Token | . |
Token ID | 13 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
milo | +3.328 |
oried | +2.771 |
Choi | +2.633 |
bamboo | +2.585 |
── | +2.510 |
Neg logit contributions | |
ONY | -4.299 |
space | -3.936 |
Stall | -3.769 |
satell | -3.654 |
Goth | -3.652 |
Token | ache |
Token ID | 4891 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ONY | +2.161 |
space | +1.917 |
Stall | +1.709 |
lust | +1.670 |
empt | +1.626 |
Neg logit contributions | |
milo | -4.262 |
oried | -3.709 |
Choi | -3.630 |
Kw | -3.570 |
bamboo | -3.569 |
Token | and |
Token ID | 290 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
ONY | +0.382 |
space | +0.349 |
Stall | +0.331 |
lust | +0.321 |
Goth | +0.317 |
Neg logit contributions | |
milo | -0.379 |
oried | -0.316 |
Choi | -0.299 |
bamboo | -0.292 |
Kw | -0.290 |
Token | a |
Token ID | 257 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
milo | +3.196 |
oried | +2.618 |
Choi | +2.496 |
Kw | +2.440 |
Zhang | +2.415 |
Neg logit contributions | |
ONY | -5.932 |
space | -5.395 |
satell | -5.290 |
Stall | -5.149 |
lust | -5.027 |
Token | bit |
Token ID | 1643 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
milo | +1.263 |
oried | +1.011 |
Choi | +0.943 |
bamboo | +0.922 |
Kw | +0.921 |
Neg logit contributions | |
ONY | -1.908 |
space | -1.762 |
Stall | -1.681 |
lust | -1.638 |
satell | -1.628 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
milo | +0.075 |
oried | +0.063 |
Choi | +0.061 |
Kw | +0.059 |
bamboo | +0.059 |
Neg logit contributions | |
ONY | -0.077 |
space | -0.070 |
Stall | -0.066 |
satell | -0.066 |
lust | -0.064 |
Token | Paul |
Token ID | 3362 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
milo | +1.055 |
oried | +0.905 |
Choi | +0.868 |
bamboo | +0.849 |
Kw | +0.848 |
Neg logit contributions | |
ONY | -0.824 |
space | -0.743 |
Stall | -0.693 |
lust | -0.671 |
Goth | -0.662 |
Token | Newman |
Token ID | 27698 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
milo | +1.430 |
Hugo | +1.102 |
Friedman | +0.901 |
Kw | +0.837 |
Zhang | +0.753 |
Neg logit contributions | |
satell | -19.025 |
ONY | -18.930 |
space | -17.837 |
ヘ | -17.452 |
Stall | -17.250 |
Token | about |
Token ID | 546 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
milo | +1.575 |
oried | +1.287 |
Choi | +1.215 |
bamboo | +1.180 |
Kw | +1.178 |
Neg logit contributions | |
ONY | -1.935 |
space | -1.775 |
Stall | -1.692 |
lust | -1.644 |
Goth | -1.629 |
Token | him |
Token ID | 683 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
milo | +0.524 |
oried | +0.431 |
Choi | +0.409 |
bamboo | +0.397 |
Kw | +0.396 |
Neg logit contributions | |
ONY | -0.654 |
space | -0.600 |
Stall | -0.569 |
satell | -0.555 |
lust | -0.554 |
Token | . |
Token ID | 13 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
milo | +2.661 |
oried | +2.174 |
Choi | +2.071 |
Kw | +2.012 |
bamboo | +2.010 |
Neg logit contributions | |
ONY | -3.228 |
space | -2.954 |
Stall | -2.813 |
lust | -2.731 |
satell | -2.712 |
Token | Coll |
Token ID | 7778 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
ONY | +0.641 |
space | +0.584 |
Stall | +0.555 |
lust | +0.534 |
Goth | +0.531 |
Neg logit contributions | |
milo | -0.706 |
oried | -0.595 |
Choi | -0.560 |
bamboo | -0.553 |
Kw | -0.543 |
Token | oil |
Token ID | 3056 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
milo | +3.591 |
oried | +2.954 |
bamboo | +2.828 |
Choi | +2.779 |
Kw | +2.714 |
Neg logit contributions | |
ONY | -5.932 |
space | -5.349 |
satell | -5.214 |
Stall | -5.197 |
Goth | -4.986 |
Token | in |
Token ID | 287 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
ONY | +0.694 |
space | +0.623 |
Stall | +0.585 |
lust | +0.563 |
satell | +0.557 |
Neg logit contributions | |
milo | -0.888 |
oried | -0.760 |
Choi | -0.727 |
bamboo | -0.712 |
Kw | -0.709 |
Token | a |
Token ID | 257 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
milo | +3.475 |
oried | +2.864 |
Choi | +2.667 |
bamboo | +2.608 |
Kw | +2.583 |
Neg logit contributions | |
ONY | -7.188 |
satell | -6.663 |
space | -6.478 |
Stall | -6.346 |
ヘ | -6.155 |
Token | skillet |
Token ID | 41306 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
milo | +2.534 |
oried | +2.052 |
Choi | +1.961 |
bamboo | +1.920 |
Kw | +1.891 |
Neg logit contributions | |
ONY | -3.300 |
space | -2.980 |
Stall | -2.842 |
satell | -2.822 |
Goth | -2.816 |
Token | over |
Token ID | 625 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
milo | +2.249 |
oried | +1.873 |
Choi | +1.754 |
bamboo | +1.717 |
Kw | +1.710 |
Neg logit contributions | |
ONY | -3.736 |
space | -3.354 |
satell | -3.290 |
Stall | -3.270 |
lust | -3.155 |
Token | medium |
Token ID | 7090 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
milo | +1.523 |
oried | +0.932 |
bamboo | +0.877 |
Choi | +0.875 |
immigrants | +0.745 |
Neg logit contributions | |
ONY | -5.914 |
space | -5.442 |
satell | -5.338 |
Stall | -5.270 |
lust | -5.197 |
Token | - |
Token ID | 12 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
milo | +5.545 |
oried | +4.526 |
bamboo | +4.291 |
Zhang | +4.167 |
Choi | +4.146 |
Neg logit contributions | |
satell | -15.910 |
ONY | -15.567 |
space | -13.451 |
swer | -13.247 |
Stall | -13.202 |
Token | high |
Token ID | 8929 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
milo | +2.830 |
oried | +1.069 |
Hong | +0.843 |
lights | +0.811 |
ru | +0.695 |
Neg logit contributions | |
ONY | -16.620 |
satell | -16.316 |
Stall | -15.044 |
Goth | -14.533 |
Orbit | -14.302 |
Token | heat |
Token ID | 4894 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
milo | +5.332 |
oried | +4.246 |
Choi | +4.168 |
bamboo | +4.101 |
Kw | +3.942 |
Neg logit contributions | |
ONY | -9.840 |
satell | -9.036 |
space | -8.390 |
Stall | -8.207 |
ヘ | -8.071 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
milo | +3.392 |
oried | +2.840 |
Choi | +2.724 |
Kw | +2.596 |
Zhang | +2.546 |
Neg logit contributions | |
ONY | -6.238 |
satell | -6.155 |
space | -5.566 |
Stall | -5.479 |
haps | -5.359 |
Token | Place |
Token ID | 8474 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
milo | +1.138 |
oried | +0.978 |
Choi | +0.959 |
Kw | +0.931 |
bamboo | +0.922 |
Neg logit contributions | |
ONY | -0.907 |
space | -0.806 |
Stall | -0.746 |
satell | -0.741 |
lust | -0.729 |
Token | vegetables |
Token ID | 13701 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
milo | +1.983 |
oried | +1.546 |
Choi | +1.490 |
bamboo | +1.463 |
Kw | +1.410 |
Neg logit contributions | |
ONY | -3.323 |
space | -3.078 |
Stall | -2.931 |
lust | -2.883 |
satell | -2.841 |
Token | on |
Token ID | 319 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
milo | +3.570 |
oried | +2.948 |
Choi | +2.881 |
bamboo | +2.844 |
Kw | +2.777 |
Neg logit contributions | |
ONY | -3.931 |
space | -3.544 |
Stall | -3.378 |
satell | -3.300 |
lust | -3.247 |
Token | the |
Token ID | 262 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
milo | +3.958 |
oried | +3.281 |
Choi | +3.219 |
bamboo | +3.170 |
Kw | +3.079 |
Neg logit contributions | |
ONY | -4.450 |
space | -4.093 |
Stall | -3.849 |
lust | -3.772 |
Goth | -3.698 |
Token | stove |
Token ID | 27635 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
milo | +0.220 |
oried | +0.184 |
Choi | +0.173 |
Kw | +0.169 |
bamboo | +0.168 |
Neg logit contributions | |
ONY | -0.216 |
space | -0.197 |
Stall | -0.187 |
lust | -0.181 |
Goth | -0.179 |
Token | on |
Token ID | 319 |
Feature activation | -7.86e+00 |
Pos logit contributions | |
milo | +0.397 |
oried | +0.333 |
Choi | +0.316 |
bamboo | +0.309 |
Kw | +0.307 |
Neg logit contributions | |
ONY | -0.389 |
space | -0.354 |
Stall | -0.335 |
lust | -0.325 |
Goth | -0.321 |
Token | medium |
Token ID | 7090 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
milo | +4.327 |
Choi | +3.442 |
oried | +3.404 |
bamboo | +3.385 |
Kw | +3.199 |
Neg logit contributions | |
ONY | -7.011 |
space | -6.559 |
Stall | -6.242 |
lust | -6.137 |
satell | -6.062 |
Token | heat |
Token ID | 4894 |
Feature activation | -7.52e+00 |
Pos logit contributions | |
milo | +8.095 |
oried | +6.481 |
bamboo | +6.416 |
Choi | +6.311 |
── | +5.958 |
Neg logit contributions | |
ONY | -12.625 |
space | -11.315 |
satell | -10.885 |
Stall | -10.658 |
ヘ | -10.564 |
Token | . |
Token ID | 13 |
Feature activation | -8.40e+00 |
Pos logit contributions | |
milo | +4.752 |
oried | +3.922 |
Choi | +3.834 |
bamboo | +3.729 |
Kw | +3.593 |
Neg logit contributions | |
ONY | -6.237 |
space | -5.641 |
Stall | -5.435 |
satell | -5.332 |
lust | -5.268 |
Token | Add |
Token ID | 3060 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
milo | +5.766 |
Choi | +5.050 |
oried | +4.817 |
Kw | +4.808 |
Dai | +4.703 |
Neg logit contributions | |
ONY | -6.258 |
space | -5.637 |
satell | -5.626 |
empt | -5.231 |
haps | -5.195 |
Token | the |
Token ID | 262 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
milo | +1.030 |
oried | +0.852 |
Choi | +0.815 |
bamboo | +0.797 |
Kw | +0.788 |
Neg logit contributions | |
ONY | -1.110 |
space | -1.016 |
Stall | -0.962 |
lust | -0.934 |
Goth | -0.925 |
Token | coconut |
Token ID | 20132 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
milo | +2.818 |
oried | +2.281 |
Choi | +2.253 |
bamboo | +2.234 |
Kw | +2.155 |
Neg logit contributions | |
ONY | -3.403 |
space | -3.102 |
Stall | -2.939 |
lust | -2.874 |
Goth | -2.823 |
Token | AC |
Token ID | 2246 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
ONY | +2.780 |
space | +2.414 |
lust | +2.000 |
Stall | +1.983 |
Goth | +1.880 |
Neg logit contributions | |
milo | -6.369 |
oried | -5.615 |
Choi | -5.534 |
bamboo | -5.477 |
Kw | -5.445 |
Token | LU |
Token ID | 41596 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
milo | +3.172 |
oried | +2.627 |
Choi | +2.448 |
Hong | +2.382 |
ru | +2.368 |
Neg logit contributions | |
ONY | -3.570 |
satell | -3.405 |
space | -3.300 |
Stall | -3.287 |
Goth | -3.134 |
Token | _ |
Token ID | 62 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
ONY | +0.692 |
space | +0.629 |
Stall | +0.597 |
satell | +0.583 |
lust | +0.573 |
Neg logit contributions | |
milo | -0.769 |
oried | -0.650 |
Choi | -0.618 |
Kw | -0.602 |
bamboo | -0.601 |
Token | OR |
Token ID | 1581 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ONY | +3.899 |
space | +3.241 |
lust | +2.793 |
Stall | +2.787 |
Goth | +2.746 |
Neg logit contributions | |
milo | -6.891 |
oried | -5.960 |
Choi | -5.747 |
bamboo | -5.715 |
Kw | -5.702 |
Token | ) |
Token ID | 8 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
milo | +1.032 |
oried | +0.873 |
Choi | +0.825 |
Kw | +0.806 |
Zhang | +0.801 |
Neg logit contributions | |
ONY | -1.114 |
satell | -1.022 |
space | -1.007 |
Stall | -0.966 |
Goth | -0.924 |
Token | May |
Token ID | 1737 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
milo | +2.923 |
oried | +2.499 |
Choi | +2.495 |
Kw | +2.404 |
Zhang | +2.378 |
Neg logit contributions | |
ONY | -2.914 |
satell | -2.714 |
space | -2.613 |
Stall | -2.393 |
lust | -2.377 |
Token | 29 |
Token ID | 2808 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
milo | +7.229 |
Choi | +5.795 |
Hugo | +5.684 |
Zhang | +5.434 |
oried | +5.419 |
Neg logit contributions | |
ONY | -13.244 |
space | -12.206 |
satell | -11.828 |
Stall | -11.756 |
lust | -11.472 |
Token | , |
Token ID | 11 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
milo | +3.065 |
oried | +2.548 |
Choi | +2.441 |
Kw | +2.408 |
Zhang | +2.384 |
Neg logit contributions | |
ONY | -4.123 |
satell | -4.111 |
space | -3.665 |
Stall | -3.565 |
haps | -3.436 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
milo | +2.726 |
oried | +2.217 |
Choi | +2.110 |
Kw | +2.096 |
Zhang | +2.066 |
Neg logit contributions | |
ONY | -4.762 |
satell | -4.570 |
space | -4.293 |
Stall | -4.218 |
empt | -4.059 |
Token |
|
Token ID | 198 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
milo | +1.913 |
oried | +1.618 |
Choi | +1.548 |
Kw | +1.506 |
bamboo | +1.496 |
Neg logit contributions | |
ONY | -1.724 |
space | -1.559 |
satell | -1.472 |
Stall | -1.470 |
lust | -1.427 |
Token |
|
Token ID | 198 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
milo | +0.343 |
oried | +0.291 |
Choi | +0.278 |
Kw | +0.272 |
bamboo | +0.270 |
Neg logit contributions | |
ONY | -0.309 |
space | -0.277 |
satell | -0.268 |
Stall | -0.263 |
lust | -0.252 |
Token | AC |
Token ID | 2246 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
ONY | +3.234 |
space | +2.777 |
lust | +2.273 |
Stall | +2.207 |
empt | +2.104 |
Neg logit contributions | |
milo | -7.908 |
oried | -6.995 |
Choi | -6.981 |
Kw | -6.887 |
bamboo | -6.875 |
Token | LU |
Token ID | 41596 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
milo | +2.233 |
oried | +1.857 |
Choi | +1.729 |
Hong | +1.680 |
Kw | +1.676 |
Neg logit contributions | |
ONY | -2.401 |
satell | -2.229 |
space | -2.223 |
Stall | -2.188 |
Goth | -2.092 |
Token | _ |
Token ID | 62 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
ONY | +1.033 |
space | +0.939 |
Stall | +0.890 |
satell | +0.864 |
lust | +0.855 |
Neg logit contributions | |
milo | -1.153 |
oried | -0.974 |
Choi | -0.926 |
Kw | -0.901 |
bamboo | -0.901 |
Token | OR |
Token ID | 1581 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ONY | +4.379 |
space | +3.538 |
lust | +3.025 |
Goth | +2.945 |
Stall | +2.939 |
Neg logit contributions | |
milo | -8.098 |
oried | -7.042 |
Choi | -6.842 |
conclud | -6.813 |
bamboo | -6.811 |
Token | ) |
Token ID | 8 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
milo | +1.458 |
oried | +1.236 |
Choi | +1.163 |
Kw | +1.139 |
Zhang | +1.130 |
Neg logit contributions | |
ONY | -1.618 |
satell | -1.508 |
space | -1.467 |
Stall | -1.405 |
Goth | -1.349 |
Token | May |
Token ID | 1737 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
milo | +3.258 |
oried | +2.755 |
Choi | +2.669 |
Kw | +2.594 |
bamboo | +2.573 |
Neg logit contributions | |
ONY | -2.807 |
space | -2.550 |
Stall | -2.353 |
lust | -2.314 |
satell | -2.306 |
Token | 29 |
Token ID | 2808 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
milo | +6.995 |
Choi | +5.669 |
Hugo | +5.606 |
Zhang | +5.357 |
oried | +5.330 |
Neg logit contributions | |
ONY | -13.190 |
satell | -12.161 |
space | -12.141 |
Stall | -11.689 |
ACTED | -11.443 |
Token | , |
Token ID | 11 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
milo | +3.273 |
oried | +2.709 |
Choi | +2.597 |
Kw | +2.561 |
Zhang | +2.543 |
Neg logit contributions | |
satell | -4.540 |
ONY | -4.508 |
space | -4.006 |
Stall | -3.906 |
haps | -3.760 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
milo | +2.918 |
oried | +2.358 |
Choi | +2.250 |
Kw | +2.238 |
Zhang | +2.202 |
Neg logit contributions | |
ONY | -5.221 |
satell | -5.063 |
space | -4.701 |
Stall | -4.636 |
empt | -4.448 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
milo | +1.386 |
oried | +1.173 |
Choi | +1.122 |
bamboo | +1.095 |
Kw | +1.095 |
Neg logit contributions | |
ONY | -1.179 |
space | -1.066 |
Stall | -1.001 |
lust | -0.970 |
Goth | -0.955 |
Token |
|
Token ID | 198 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
milo | +1.077 |
oried | +0.915 |
Choi | +0.873 |
Kw | +0.855 |
Zhang | +0.845 |
Neg logit contributions | |
ONY | -1.032 |
satell | -0.933 |
space | -0.919 |
Stall | -0.880 |
Goth | -0.839 |
Token | AC |
Token ID | 2246 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
ONY | +3.085 |
space | +2.659 |
lust | +2.176 |
Stall | +2.125 |
empt | +2.017 |
Neg logit contributions | |
milo | -7.385 |
oried | -6.531 |
Choi | -6.474 |
bamboo | -6.395 |
Kw | -6.383 |
Token | LU |
Token ID | 41596 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
milo | +2.743 |
oried | +2.272 |
Choi | +2.123 |
Hong | +2.063 |
Kw | +2.050 |
Neg logit contributions | |
ONY | -3.026 |
satell | -2.859 |
space | -2.802 |
Stall | -2.782 |
Goth | -2.652 |
Token | _ |
Token ID | 62 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
ONY | +1.300 |
space | +1.179 |
Stall | +1.111 |
lust | +1.073 |
Goth | +1.062 |
Neg logit contributions | |
milo | -1.490 |
oried | -1.261 |
Choi | -1.202 |
bamboo | -1.175 |
Kw | -1.171 |
Token | OR |
Token ID | 1581 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ONY | +4.105 |
space | +3.381 |
lust | +2.901 |
Stall | +2.870 |
Goth | +2.839 |
Neg logit contributions | |
milo | -7.404 |
oried | -6.415 |
Choi | -6.196 |
bamboo | -6.163 |
Kw | -6.149 |
Token | ) |
Token ID | 8 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
milo | +1.344 |
oried | +1.137 |
Choi | +1.074 |
Kw | +1.049 |
Zhang | +1.043 |
Neg logit contributions | |
ONY | -1.464 |
satell | -1.348 |
space | -1.326 |
Stall | -1.271 |
Goth | -1.218 |
Token | May |
Token ID | 1737 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
milo | +3.132 |
oried | +2.669 |
Choi | +2.665 |
Kw | +2.560 |
Zhang | +2.530 |
Neg logit contributions | |
ONY | -3.114 |
satell | -2.872 |
space | -2.794 |
Stall | -2.561 |
lust | -2.548 |
Token | 29 |
Token ID | 2808 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
milo | +7.114 |
Choi | +5.730 |
Hugo | +5.620 |
Zhang | +5.371 |
oried | +5.350 |
Neg logit contributions | |
ONY | -13.064 |
space | -12.019 |
satell | -11.751 |
Stall | -11.583 |
lust | -11.322 |
Token | , |
Token ID | 11 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
milo | +3.130 |
oried | +2.603 |
Choi | +2.492 |
Kw | +2.462 |
Zhang | +2.435 |
Neg logit contributions | |
satell | -4.270 |
ONY | -4.259 |
space | -3.785 |
Stall | -3.688 |
haps | -3.556 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
milo | +2.801 |
oried | +2.278 |
Choi | +2.165 |
Kw | +2.157 |
Zhang | +2.126 |
Neg logit contributions | |
ONY | -4.949 |
satell | -4.767 |
space | -4.456 |
Stall | -4.389 |
empt | -4.220 |
Token |
|
Token ID | 198 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
milo | +2.402 |
oried | +2.027 |
Choi | +1.938 |
bamboo | +1.888 |
Kw | +1.886 |
Neg logit contributions | |
ONY | -2.125 |
space | -1.925 |
Stall | -1.816 |
lust | -1.761 |
satell | -1.738 |
Token |
|
Token ID | 198 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
ONY | +0.368 |
space | +0.331 |
Stall | +0.313 |
satell | +0.306 |
lust | +0.301 |
Neg logit contributions | |
milo | -0.430 |
oried | -0.365 |
Choi | -0.349 |
Kw | -0.341 |
bamboo | -0.340 |
Token | AC |
Token ID | 2246 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ONY | +2.856 |
space | +2.483 |
lust | +2.055 |
Stall | +2.037 |
Goth | +1.929 |
Neg logit contributions | |
milo | -6.579 |
oried | -5.800 |
Choi | -5.715 |
bamboo | -5.662 |
Kw | -5.622 |
Token | LU |
Token ID | 41596 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
milo | +2.962 |
oried | +2.451 |
Choi | +2.293 |
Hong | +2.228 |
── | +2.211 |
Neg logit contributions | |
ONY | -3.298 |
satell | -3.146 |
space | -3.048 |
Stall | -3.031 |
Goth | -2.893 |
Token | _ |
Token ID | 62 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
ONY | +0.770 |
space | +0.700 |
Stall | +0.664 |
satell | +0.650 |
lust | +0.638 |
Neg logit contributions | |
milo | -0.855 |
oried | -0.722 |
Choi | -0.687 |
Kw | -0.669 |
bamboo | -0.668 |
Token | OR |
Token ID | 1581 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
ONY | +3.685 |
space | +3.099 |
Stall | +2.700 |
lust | +2.684 |
Goth | +2.645 |
Neg logit contributions | |
milo | -6.335 |
oried | -5.475 |
Choi | -5.272 |
bamboo | -5.241 |
Kw | -5.223 |
Token | ) |
Token ID | 8 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
milo | +0.590 |
oried | +0.499 |
Choi | +0.472 |
Kw | +0.461 |
Zhang | +0.457 |
Neg logit contributions | |
ONY | -0.620 |
space | -0.561 |
satell | -0.558 |
Stall | -0.537 |
Goth | -0.513 |
Token | May |
Token ID | 1737 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
milo | +2.844 |
oried | +2.431 |
Choi | +2.429 |
Kw | +2.336 |
Zhang | +2.314 |
Neg logit contributions | |
ONY | -2.844 |
satell | -2.663 |
space | -2.549 |
Stall | -2.336 |
lust | -2.320 |
Token | 29 |
Token ID | 2808 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
milo | +6.397 |
Choi | +5.589 |
Hugo | +5.417 |
Zhang | +5.255 |
ru | +5.028 |
Neg logit contributions | |
satell | -13.485 |
ONY | -13.396 |
space | -12.260 |
Stall | -11.788 |
egal | -11.667 |
Token | , |
Token ID | 11 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
milo | +2.999 |
oried | +2.497 |
Choi | +2.395 |
Kw | +2.363 |
Zhang | +2.336 |
Neg logit contributions | |
ONY | -4.024 |
satell | -4.012 |
space | -3.577 |
Stall | -3.474 |
haps | -3.354 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
milo | +2.865 |
oried | +2.331 |
Choi | +2.219 |
Kw | +2.208 |
Zhang | +2.180 |
Neg logit contributions | |
ONY | -5.124 |
satell | -4.964 |
space | -4.613 |
Stall | -4.542 |
empt | -4.376 |
Token |
|
Token ID | 198 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
milo | +1.824 |
oried | +1.546 |
Choi | +1.480 |
Kw | +1.442 |
Zhang | +1.427 |
Neg logit contributions | |
ONY | -1.687 |
space | -1.525 |
satell | -1.479 |
Stall | -1.441 |
lust | -1.397 |
Token |
|
Token ID | 198 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
milo | +0.632 |
oried | +0.537 |
Choi | +0.514 |
Kw | +0.502 |
bamboo | +0.497 |
Neg logit contributions | |
ONY | -0.585 |
space | -0.523 |
satell | -0.517 |
Stall | -0.499 |
lust | -0.476 |
Token | fry |
Token ID | 32959 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
milo | +3.825 |
oried | +3.089 |
Choi | +3.066 |
bamboo | +3.007 |
Kw | +2.902 |
Neg logit contributions | |
ONY | -4.983 |
space | -4.577 |
Stall | -4.310 |
lust | -4.265 |
Goth | -4.208 |
Token | it |
Token ID | 340 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
milo | +4.174 |
oried | +3.421 |
Choi | +3.352 |
bamboo | +3.305 |
Kw | +3.177 |
Neg logit contributions | |
ONY | -4.941 |
space | -4.514 |
Stall | -4.278 |
satell | -4.185 |
lust | -4.182 |
Token | at |
Token ID | 379 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
milo | +4.546 |
oried | +3.751 |
Choi | +3.688 |
bamboo | +3.647 |
Kw | +3.513 |
Neg logit contributions | |
ONY | -5.809 |
space | -5.302 |
Stall | -5.015 |
lust | -4.941 |
satell | -4.920 |
Token | medium |
Token ID | 7090 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
milo | +2.140 |
oried | +1.787 |
Choi | +1.724 |
bamboo | +1.686 |
Kw | +1.660 |
Neg logit contributions | |
ONY | -2.216 |
space | -2.031 |
Stall | -1.933 |
lust | -1.867 |
Goth | -1.845 |
Token | - |
Token ID | 12 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
milo | +7.098 |
oried | +5.923 |
bamboo | +5.679 |
Choi | +5.644 |
── | +5.295 |
Neg logit contributions | |
ONY | -11.513 |
space | -10.345 |
satell | -9.869 |
Stall | -9.739 |
ヘ | -9.625 |
Token | high |
Token ID | 8929 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
milo | +4.044 |
oried | +2.608 |
lights | +2.200 |
ru | +2.144 |
Choi | +2.131 |
Neg logit contributions | |
ONY | -12.102 |
satell | -11.107 |
Stall | -11.016 |
space | -10.888 |
Goth | -10.748 |
Token | heat |
Token ID | 4894 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
milo | +7.864 |
oried | +6.468 |
Choi | +6.426 |
bamboo | +6.363 |
lights | +6.226 |
Neg logit contributions | |
ONY | -12.286 |
space | -10.712 |
ヘ | -10.482 |
Stall | -10.449 |
satell | -10.447 |
Token | until |
Token ID | 1566 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
milo | +5.798 |
oried | +4.797 |
Choi | +4.790 |
bamboo | +4.662 |
Kw | +4.468 |
Neg logit contributions | |
ONY | -8.472 |
space | -7.668 |
Stall | -7.417 |
satell | -7.335 |
ヘ | -7.223 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
milo | +2.098 |
oried | +1.730 |
Choi | +1.677 |
bamboo | +1.649 |
Kw | +1.601 |
Neg logit contributions | |
ONY | -2.549 |
space | -2.359 |
Stall | -2.231 |
lust | -2.147 |
Goth | -2.137 |
Token | onion |
Token ID | 21670 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
milo | +2.706 |
oried | +2.252 |
Choi | +2.199 |
bamboo | +2.174 |
Kw | +2.111 |
Neg logit contributions | |
ONY | -2.951 |
space | -2.708 |
Stall | -2.566 |
lust | -2.463 |
satell | -2.450 |
Token | is |
Token ID | 318 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
milo | +2.890 |
oried | +2.405 |
Choi | +2.329 |
bamboo | +2.312 |
Kw | +2.233 |
Neg logit contributions | |
ONY | -3.252 |
space | -2.978 |
Stall | -2.832 |
satell | -2.726 |
Goth | -2.702 |
Token | AC |
Token ID | 2246 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
ONY | +2.979 |
space | +2.590 |
lust | +2.136 |
Stall | +2.105 |
Goth | +1.998 |
Neg logit contributions | |
milo | -6.942 |
oried | -6.119 |
Choi | -6.033 |
bamboo | -5.987 |
Kw | -5.936 |
Token | LU |
Token ID | 41596 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
milo | +2.975 |
oried | +2.462 |
Choi | +2.307 |
Hong | +2.238 |
── | +2.225 |
Neg logit contributions | |
ONY | -3.308 |
satell | -3.144 |
space | -3.052 |
Stall | -3.035 |
Goth | -2.897 |
Token | _ |
Token ID | 62 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
ONY | +1.094 |
space | +0.992 |
Stall | +0.937 |
lust | +0.904 |
satell | +0.895 |
Neg logit contributions | |
milo | -1.247 |
oried | -1.055 |
Choi | -1.006 |
bamboo | -0.982 |
Kw | -0.980 |
Token | OR |
Token ID | 1581 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ONY | +3.601 |
space | +3.037 |
Stall | +2.648 |
lust | +2.627 |
Goth | +2.591 |
Neg logit contributions | |
milo | -6.186 |
oried | -5.346 |
Choi | -5.136 |
bamboo | -5.113 |
Kw | -5.094 |
Token | ) |
Token ID | 8 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
milo | +0.283 |
oried | +0.239 |
Choi | +0.227 |
Kw | +0.221 |
Zhang | +0.219 |
Neg logit contributions | |
ONY | -0.289 |
space | -0.261 |
satell | -0.255 |
Stall | -0.249 |
lust | -0.239 |
Token | May |
Token ID | 1737 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
milo | +2.529 |
oried | +2.165 |
Choi | +2.151 |
Kw | +2.071 |
Zhang | +2.052 |
Neg logit contributions | |
ONY | -2.462 |
satell | -2.277 |
space | -2.203 |
Stall | -2.027 |
lust | -2.002 |
Token | 29 |
Token ID | 2808 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
milo | +5.976 |
Choi | +5.463 |
Hugo | +5.314 |
Zhang | +5.159 |
Kw | +4.986 |
Neg logit contributions | |
satell | -14.105 |
ONY | -13.555 |
space | -12.355 |
egal | -11.940 |
ACTED | -11.865 |
Token | , |
Token ID | 11 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
milo | +2.840 |
oried | +2.366 |
Choi | +2.267 |
Kw | +2.234 |
Zhang | +2.209 |
Neg logit contributions | |
ONY | -3.732 |
satell | -3.687 |
space | -3.322 |
Stall | -3.222 |
haps | -3.103 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
milo | +2.712 |
oried | +2.207 |
Choi | +2.098 |
Kw | +2.080 |
Zhang | +2.056 |
Neg logit contributions | |
ONY | -4.711 |
satell | -4.523 |
space | -4.253 |
Stall | -4.184 |
empt | -4.020 |
Token |
|
Token ID | 198 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
milo | +1.332 |
oried | +1.131 |
Choi | +1.083 |
Kw | +1.055 |
bamboo | +1.046 |
Neg logit contributions | |
ONY | -1.215 |
space | -1.097 |
satell | -1.056 |
Stall | -1.036 |
lust | -1.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
milo | +0.474 |
oried | +0.403 |
Choi | +0.385 |
Kw | +0.376 |
bamboo | +0.373 |
Neg logit contributions | |
ONY | -0.432 |
space | -0.387 |
satell | -0.377 |
Stall | -0.368 |
lust | -0.352 |
Token | 107 |
Token ID | 16226 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ONY | +0.601 |
space | +0.546 |
Stall | +0.514 |
lust | +0.495 |
Goth | +0.492 |
Neg logit contributions | |
milo | -0.716 |
oried | -0.608 |
Choi | -0.578 |
bamboo | -0.566 |
Kw | -0.562 |
Token | P |
Token ID | 47 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
milo | +1.171 |
oried | +0.993 |
Choi | +0.949 |
bamboo | +0.927 |
Kw | +0.927 |
Neg logit contributions | |
ONY | -1.004 |
space | -0.908 |
Stall | -0.857 |
lust | -0.828 |
Goth | -0.817 |
Token | / |
Token ID | 14 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
milo | +2.934 |
oried | +2.320 |
Choi | +2.198 |
Kw | +2.164 |
bamboo | +2.090 |
Neg logit contributions | |
ONY | -4.809 |
space | -4.427 |
Stall | -4.231 |
lust | -4.191 |
satell | -4.106 |
Token | Wilson |
Token ID | 37349 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
milo | +4.470 |
oried | +3.755 |
Choi | +3.598 |
Kw | +3.536 |
Hong | +3.535 |
Neg logit contributions | |
ONY | -4.300 |
space | -3.806 |
Stall | -3.742 |
satell | -3.698 |
Goth | -3.558 |
Token | – |
Token ID | 1906 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
milo | +2.983 |
oried | +2.449 |
Choi | +2.318 |
Kw | +2.267 |
bamboo | +2.258 |
Neg logit contributions | |
ONY | -4.127 |
space | -3.728 |
Stall | -3.570 |
lust | -3.518 |
satell | -3.470 |
Token | Har |
Token ID | 13587 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
milo | +1.622 |
oried | +1.281 |
Choi | +1.189 |
Kw | +1.142 |
bamboo | +1.142 |
Neg logit contributions | |
ONY | -2.660 |
space | -2.449 |
Stall | -2.367 |
satell | -2.314 |
lust | -2.299 |
Token | rington |
Token ID | 24833 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
milo | +5.751 |
oried | +5.083 |
Dixon | +4.274 |
ru | +4.180 |
ville | +4.049 |
Neg logit contributions | |
satell | -14.762 |
ONY | -14.076 |
Stall | -12.742 |
ヘ | -12.384 |
Goth | -12.365 |
Token | . |
Token ID | 13 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
milo | +0.159 |
oried | +0.133 |
Choi | +0.126 |
bamboo | +0.123 |
Kw | +0.123 |
Neg logit contributions | |
ONY | -0.158 |
space | -0.144 |
Stall | -0.136 |
lust | -0.132 |
Goth | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
milo | +0.202 |
oried | +0.171 |
Choi | +0.163 |
bamboo | +0.159 |
Kw | +0.159 |
Neg logit contributions | |
ONY | -0.178 |
space | -0.162 |
Stall | -0.152 |
lust | -0.147 |
Goth | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
milo | +0.205 |
oried | +0.175 |
Choi | +0.167 |
Kw | +0.163 |
Zhang | +0.161 |
Neg logit contributions | |
ONY | -0.191 |
space | -0.170 |
satell | -0.168 |
Stall | -0.162 |
lust | -0.155 |
Token | The |
Token ID | 464 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ONY | +0.226 |
space | +0.205 |
Stall | +0.192 |
lust | +0.186 |
Goth | +0.183 |
Neg logit contributions | |
milo | -0.270 |
oried | -0.229 |
Choi | -0.219 |
bamboo | -0.215 |
Kw | -0.213 |
Token | Gram |
Token ID | 20159 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
milo | +2.191 |
oried | +1.844 |
Choi | +1.831 |
Kw | +1.772 |
Zhang | +1.751 |
Neg logit contributions | |
ONY | -2.508 |
satell | -2.259 |
space | -2.258 |
empt | -2.073 |
lust | -2.073 |
Token | mer |
Token ID | 647 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
ONY | +1.050 |
space | +0.935 |
Stall | +0.873 |
lust | +0.838 |
Goth | +0.829 |
Neg logit contributions | |
milo | -1.536 |
oried | -1.324 |
Choi | -1.269 |
bamboo | -1.244 |
Kw | -1.240 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ONY | +3.173 |
space | +2.889 |
Stall | +2.689 |
lust | +2.598 |
Goth | +2.568 |
Neg logit contributions | |
milo | -4.484 |
oried | -3.837 |
Choi | -3.629 |
bamboo | -3.615 |
arij | -3.581 |
Token |
|
Token ID | 198 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
ONY | +1.198 |
space | +1.081 |
Stall | +1.017 |
lust | +0.981 |
Goth | +0.971 |
Neg logit contributions | |
milo | -1.442 |
oried | -1.227 |
Choi | -1.173 |
bamboo | -1.146 |
Kw | -1.144 |
Token | 2004 |
Token ID | 15724 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
ONY | +3.486 |
space | +3.039 |
lust | +2.618 |
Stall | +2.556 |
Goth | +2.476 |
Neg logit contributions | |
milo | -7.057 |
oried | -6.216 |
Choi | -6.061 |
bamboo | -6.040 |
Kw | -5.959 |
Token | Larry |
Token ID | 13633 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
milo | +3.482 |
oried | +2.874 |
Choi | +2.845 |
Kw | +2.783 |
Hugo | +2.760 |
Neg logit contributions | |
ONY | -3.816 |
space | -3.488 |
satell | -3.302 |
Stall | -3.250 |
lust | -3.226 |
Token | David |
Token ID | 3271 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
milo | +4.012 |
Dixon | +3.958 |
Kw | +3.865 |
Choi | +3.832 |
Friedman | +3.767 |
Neg logit contributions | |
satell | -16.337 |
ONY | -15.347 |
haps | -14.200 |
space | -13.709 |
ople | -13.385 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ONY | +3.026 |
space | +2.767 |
Stall | +2.577 |
lust | +2.481 |
Goth | +2.468 |
Neg logit contributions | |
milo | -4.285 |
oried | -3.645 |
Choi | -3.454 |
bamboo | -3.442 |
arij | -3.413 |
Token |
|
Token ID | 198 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
ONY | +0.121 |
space | +0.108 |
satell | +0.105 |
Stall | +0.103 |
lust | +0.098 |
Neg logit contributions | |
milo | -0.132 |
oried | -0.112 |
Choi | -0.107 |
Kw | -0.105 |
bamboo | -0.104 |
Token | 2004 |
Token ID | 15724 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
ONY | +3.064 |
space | +2.703 |
lust | +2.342 |
Stall | +2.315 |
Goth | +2.225 |
Neg logit contributions | |
milo | -5.945 |
oried | -5.203 |
Choi | -5.097 |
bamboo | -5.053 |
Kw | -5.004 |
Token | Matt |
Token ID | 4705 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
milo | +3.756 |
oried | +3.089 |
Choi | +3.065 |
Kw | +3.009 |
Hugo | +2.996 |
Neg logit contributions | |
ONY | -4.334 |
space | -3.952 |
satell | -3.774 |
Stall | -3.680 |
lust | -3.657 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
milo | +2.982 |
oried | +2.455 |
Choi | +2.311 |
bamboo | +2.258 |
Kw | +2.252 |
Neg logit contributions | |
ONY | -3.593 |
space | -3.251 |
Stall | -3.084 |
lust | -3.030 |
satell | -3.010 |
Token | in |
Token ID | 287 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
milo | +1.725 |
oried | +1.461 |
Choi | +1.394 |
bamboo | +1.365 |
Kw | +1.357 |
Neg logit contributions | |
ONY | -1.553 |
space | -1.400 |
Stall | -1.326 |
lust | -1.284 |
Goth | -1.269 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ONY | +1.227 |
space | +1.126 |
Stall | +1.066 |
Goth | +1.020 |
lust | +1.018 |
Neg logit contributions | |
milo | -1.389 |
oried | -1.163 |
Choi | -1.100 |
bamboo | -1.073 |
Kw | -1.068 |
Token | Hard |
Token ID | 6912 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
ONY | +1.647 |
space | +1.520 |
Stall | +1.447 |
Goth | +1.389 |
lust | +1.365 |
Neg logit contributions | |
milo | -1.719 |
oried | -1.425 |
Choi | -1.336 |
� | -1.297 |
bamboo | -1.297 |
Token | - |
Token ID | 12 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
milo | +3.616 |
oried | +2.976 |
Choi | +2.854 |
bamboo | +2.778 |
Kw | +2.757 |
Neg logit contributions | |
ONY | -4.498 |
space | -3.931 |
satell | -3.748 |
Stall | -3.745 |
lust | -3.739 |
Token | Light |
Token ID | 15047 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
milo | +2.232 |
oried | +1.843 |
Choi | +1.737 |
bamboo | +1.691 |
Kw | +1.671 |
Neg logit contributions | |
ONY | -2.634 |
space | -2.357 |
Stall | -2.271 |
Goth | -2.223 |
satell | -2.213 |
Token | Sur |
Token ID | 4198 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
milo | +9.610 |
oried | +8.860 |
Choi | +8.339 |
Kw | +8.311 |
bamboo | +8.239 |
Neg logit contributions | |
ONY | -10.225 |
space | -8.537 |
satell | -8.393 |
lust | -8.310 |
haps | -8.059 |
Token | faces |
Token ID | 32186 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
milo | +1.843 |
oried | +1.559 |
Choi | +1.478 |
Kw | +1.446 |
bamboo | +1.438 |
Neg logit contributions | |
ONY | -1.768 |
space | -1.570 |
Stall | -1.500 |
lust | -1.450 |
Goth | -1.450 |
Token | co |
Token ID | 763 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
milo | +1.007 |
oried | +0.833 |
Choi | +0.789 |
bamboo | +0.769 |
Kw | +0.765 |
Neg logit contributions | |
ONY | -1.150 |
space | -1.052 |
Stall | -0.999 |
lust | -0.974 |
Goth | -0.963 |
Token | - |
Token ID | 12 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
ONY | +0.314 |
space | +0.289 |
Stall | +0.273 |
lust | +0.265 |
Goth | +0.262 |
Neg logit contributions | |
milo | -0.296 |
oried | -0.245 |
Choi | -0.233 |
bamboo | -0.227 |
Kw | -0.227 |
Token | op |
Token ID | 404 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
ONY | +2.547 |
space | +2.342 |
Stall | +2.030 |
lust | +2.006 |
empt | +1.941 |
Neg logit contributions | |
milo | -4.901 |
oried | -4.228 |
Choi | -4.138 |
Kw | -4.099 |
bamboo | -4.079 |
Token | oil |
Token ID | 3056 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
milo | +2.590 |
oried | +2.110 |
Choi | +2.044 |
bamboo | +2.003 |
Kw | +1.954 |
Neg logit contributions | |
ONY | -3.171 |
space | -2.919 |
Stall | -2.769 |
lust | -2.702 |
satell | -2.656 |
Token | in |
Token ID | 287 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
milo | +2.162 |
oried | +1.832 |
Choi | +1.758 |
bamboo | +1.722 |
Kw | +1.706 |
Neg logit contributions | |
ONY | -1.932 |
space | -1.747 |
Stall | -1.648 |
lust | -1.593 |
Goth | -1.579 |
Token | a |
Token ID | 257 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
milo | +4.129 |
oried | +3.313 |
bamboo | +3.257 |
Choi | +3.255 |
Kw | +3.084 |
Neg logit contributions | |
ONY | -6.656 |
space | -6.151 |
Stall | -5.879 |
lust | -5.751 |
Goth | -5.713 |
Token | skillet |
Token ID | 41306 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
milo | +4.391 |
bamboo | +3.612 |
Choi | +3.554 |
oried | +3.524 |
Kw | +3.392 |
Neg logit contributions | |
ONY | -7.164 |
space | -6.519 |
Stall | -6.141 |
lust | -6.101 |
satell | -5.993 |
Token | over |
Token ID | 625 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
milo | +4.593 |
oried | +3.748 |
Choi | +3.638 |
bamboo | +3.595 |
Kw | +3.414 |
Neg logit contributions | |
ONY | -6.814 |
space | -6.266 |
Stall | -5.973 |
satell | -5.854 |
lust | -5.830 |
Token | medium |
Token ID | 7090 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
milo | +2.395 |
oried | +1.539 |
Choi | +1.523 |
bamboo | +1.463 |
Kw | +1.333 |
Neg logit contributions | |
ONY | -7.459 |
space | -7.011 |
Stall | -6.751 |
lust | -6.608 |
Goth | -6.566 |
Token | - |
Token ID | 12 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
milo | +7.428 |
oried | +6.052 |
Choi | +5.944 |
bamboo | +5.828 |
── | +5.534 |
Neg logit contributions | |
ONY | -12.671 |
space | -11.453 |
satell | -10.807 |
Stall | -10.601 |
lust | -10.551 |
Token | high |
Token ID | 8929 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
milo | +3.061 |
oried | +1.857 |
Choi | +1.540 |
ru | +1.392 |
lights | +1.373 |
Neg logit contributions | |
ONY | -10.417 |
satell | -9.553 |
Stall | -9.491 |
space | -9.487 |
Goth | -9.223 |
Token | heat |
Token ID | 4894 |
Feature activation | -9.33e+00 |
Pos logit contributions | |
milo | +7.077 |
Choi | +5.686 |
oried | +5.563 |
bamboo | +5.542 |
lights | +5.196 |
Neg logit contributions | |
ONY | -11.580 |
space | -10.282 |
satell | -9.831 |
ヘ | -9.741 |
Stall | -9.699 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
milo | +5.162 |
Choi | +4.233 |
oried | +4.229 |
bamboo | +4.056 |
── | +3.853 |
Neg logit contributions | |
ONY | -8.146 |
space | -7.420 |
Stall | -7.131 |
satell | -7.066 |
Goth | -6.936 |
Token | Place |
Token ID | 8474 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
milo | +6.786 |
Choi | +6.261 |
Kw | +5.884 |
Dai | +5.811 |
Zhang | +5.727 |
Neg logit contributions | |
ONY | -8.526 |
satell | -8.091 |
space | -7.745 |
haps | -7.277 |
empt | -7.229 |
Token | at |
Token ID | 379 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
milo | +0.886 |
oried | +0.746 |
Choi | +0.711 |
bamboo | +0.695 |
Kw | +0.694 |
Neg logit contributions | |
ONY | -0.863 |
space | -0.784 |
Stall | -0.742 |
lust | -0.724 |
Goth | -0.713 |
Token | Five |
Token ID | 10579 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
ONY | +0.431 |
space | +0.391 |
Stall | +0.370 |
Goth | +0.353 |
lust | +0.353 |
Neg logit contributions | |
milo | -0.523 |
oried | -0.444 |
Choi | -0.421 |
bamboo | -0.413 |
Kw | -0.411 |
Token | Corn |
Token ID | 11424 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
milo | +4.350 |
oried | +3.774 |
Choi | +3.684 |
Dixon | +3.662 |
Kw | +3.639 |
Neg logit contributions | |
ONY | -5.200 |
satell | -4.995 |
space | -4.635 |
haps | -4.316 |
lust | -4.314 |
Token | ers |
Token ID | 364 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
milo | +0.284 |
oried | +0.213 |
Choi | +0.187 |
Kw | +0.177 |
bamboo | +0.173 |
Neg logit contributions | |
ONY | -0.692 |
space | -0.644 |
satell | -0.627 |
Stall | -0.625 |
lust | -0.608 |
Token | in |
Token ID | 287 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
ONY | +1.480 |
space | +1.332 |
Stall | +1.249 |
Goth | +1.192 |
lust | +1.186 |
Neg logit contributions | |
milo | -2.097 |
oried | -1.790 |
Choi | -1.701 |
bamboo | -1.667 |
Kw | -1.665 |
Token | Bur |
Token ID | 5481 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
milo | +2.979 |
oried | +2.404 |
Choi | +2.382 |
Kw | +2.268 |
Hugo | +2.257 |
Neg logit contributions | |
ONY | -5.155 |
satell | -4.653 |
space | -4.609 |
Stall | -4.392 |
lust | -4.343 |
Token | ien |
Token ID | 2013 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
milo | +2.364 |
oried | +1.228 |
ru | +1.105 |
iane | +0.644 |
Hugo | +0.618 |
Neg logit contributions | |
satell | -17.834 |
ONY | -17.401 |
Stall | -16.784 |
ヘ | -16.432 |
space | -15.781 |
Token |
|
Token ID | 198 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
milo | +0.509 |
oried | +0.425 |
Choi | +0.403 |
bamboo | +0.393 |
Kw | +0.392 |
Neg logit contributions | |
ONY | -0.518 |
space | -0.474 |
Stall | -0.448 |
lust | -0.435 |
Goth | -0.431 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
milo | +2.755 |
oried | +2.359 |
Choi | +2.264 |
Kw | +2.227 |
Zhang | +2.216 |
Neg logit contributions | |
ONY | -3.133 |
satell | -3.124 |
space | -2.773 |
Stall | -2.711 |
haps | -2.597 |
Token | 4 |
Token ID | 19 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
milo | +2.363 |
oried | +2.003 |
Choi | +1.904 |
bamboo | +1.855 |
� | +1.851 |
Neg logit contributions | |
ONY | -2.130 |
space | -1.924 |
Stall | -1.848 |
satell | -1.793 |
lust | -1.767 |
Token | Comments |
Token ID | 19502 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ONY | +1.524 |
space | +1.383 |
Stall | +1.311 |
lust | +1.263 |
Goth | +1.256 |
Neg logit contributions | |
milo | -1.627 |
oried | -1.349 |
Choi | -1.270 |
bamboo | -1.234 |
Kw | -1.227 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ONY | +0.487 |
space | +0.447 |
Stall | +0.424 |
lust | +0.413 |
Goth | +0.408 |
Neg logit contributions | |
milo | -0.436 |
oried | -0.360 |
Choi | -0.341 |
bamboo | -0.332 |
Kw | -0.330 |
Token |
|
Token ID | 198 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
milo | +1.722 |
oried | +1.458 |
Choi | +1.411 |
Kw | +1.376 |
Hugo | +1.366 |
Neg logit contributions | |
ONY | -1.541 |
space | -1.400 |
Stall | -1.307 |
satell | -1.290 |
lust | -1.270 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ONY | +0.629 |
space | +0.566 |
Stall | +0.535 |
satell | +0.524 |
lust | +0.514 |
Neg logit contributions | |
milo | -0.733 |
oried | -0.623 |
Choi | -0.596 |
Kw | -0.581 |
bamboo | -0.580 |
Token | Further |
Token ID | 13518 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
milo | +1.287 |
oried | +1.095 |
Choi | +1.041 |
Kw | +1.017 |
bamboo | +1.015 |
Neg logit contributions | |
ONY | -1.055 |
space | -0.952 |
Stall | -0.902 |
satell | -0.864 |
lust | -0.861 |
Token | on |
Token ID | 319 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
milo | +0.786 |
oried | +0.661 |
Choi | +0.629 |
bamboo | +0.615 |
Kw | +0.612 |
Neg logit contributions | |
ONY | -0.736 |
space | -0.670 |
Stall | -0.633 |
lust | -0.613 |
Goth | -0.606 |
Token | Hugo |
Token ID | 25930 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
milo | +4.458 |
oried | +3.762 |
Hugo | +3.609 |
Choi | +3.590 |
Kw | +3.469 |
Neg logit contributions | |
ONY | -4.747 |
space | -4.335 |
Stall | -4.100 |
lust | -3.998 |
Goth | -3.959 |
Token | Brady |
Token ID | 15260 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
milo | +8.469 |
Hugo | +7.261 |
oried | +7.249 |
Friedman | +7.099 |
Choi | +6.934 |
Neg logit contributions | |
ONY | -11.269 |
space | -10.318 |
lust | -9.615 |
satell | -9.386 |
Stall | -9.355 |
Token | writes |
Token ID | 6797 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
milo | +3.323 |
oried | +2.787 |
Choi | +2.652 |
bamboo | +2.598 |
Kw | +2.586 |
Neg logit contributions | |
ONY | -3.866 |
space | -3.513 |
Stall | -3.313 |
lust | -3.242 |
satell | -3.208 |
Token | that |
Token ID | 326 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ONY | +0.837 |
space | +0.761 |
Stall | +0.719 |
lust | +0.694 |
Goth | +0.689 |
Neg logit contributions | |
milo | -0.931 |
oried | -0.782 |
Choi | -0.747 |
bamboo | -0.730 |
Kw | -0.724 |
Token | given |
Token ID | 1813 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
ONY | +0.276 |
space | +0.252 |
Stall | +0.239 |
lust | +0.232 |
Goth | +0.230 |
Neg logit contributions | |
milo | -0.278 |
oried | -0.232 |
Choi | -0.220 |
bamboo | -0.215 |
Kw | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
milo | +0.709 |
oried | +0.592 |
Choi | +0.563 |
bamboo | +0.549 |
Kw | +0.548 |
Neg logit contributions | |
ONY | -0.722 |
space | -0.659 |
Stall | -0.623 |
lust | -0.604 |
Goth | -0.598 |
Token | " |
Token ID | 366 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ONY | +1.850 |
space | +1.691 |
Stall | +1.621 |
lust | +1.562 |
Goth | +1.561 |
Neg logit contributions | |
milo | -1.586 |
oried | -1.310 |
Choi | -1.213 |
bamboo | -1.202 |
� | -1.177 |
Token | 9 |
Token ID | 24 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ONY | +0.161 |
space | +0.147 |
Stall | +0.138 |
lust | +0.134 |
Goth | +0.132 |
Neg logit contributions | |
milo | -0.167 |
oried | -0.140 |
Choi | -0.134 |
bamboo | -0.131 |
Kw | -0.130 |
Token | - |
Token ID | 12 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ONY | +0.495 |
space | +0.454 |
Stall | +0.432 |
lust | +0.418 |
Goth | +0.415 |
Neg logit contributions | |
milo | -0.447 |
oried | -0.370 |
Choi | -0.350 |
bamboo | -0.341 |
Kw | -0.338 |
Token | to |
Token ID | 1462 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
ONY | +1.234 |
space | +1.143 |
Stall | +1.083 |
lust | +1.052 |
Goth | +1.041 |
Neg logit contributions | |
milo | -0.920 |
oried | -0.747 |
Choi | -0.705 |
bamboo | -0.687 |
Kw | -0.680 |
Token | - |
Token ID | 12 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
milo | +2.778 |
oried | +2.277 |
Choi | +2.126 |
Kw | +2.046 |
Zhang | +2.019 |
Neg logit contributions | |
ONY | -3.929 |
satell | -3.777 |
space | -3.581 |
Stall | -3.467 |
Goth | -3.382 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
milo | +1.801 |
oried | +1.433 |
Choi | +1.326 |
Hong | +1.283 |
bamboo | +1.277 |
Neg logit contributions | |
ONY | -2.540 |
space | -2.328 |
Stall | -2.265 |
satell | -2.251 |
Goth | -2.204 |
Token | Working |
Token ID | 14594 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
milo | +7.055 |
Kw | +5.556 |
oried | +5.507 |
Zhang | +5.364 |
Choi | +5.287 |
Neg logit contributions | |
ONY | -12.698 |
space | -11.731 |
satell | -11.274 |
ヘ | -10.997 |
lust | -10.984 |
Token | Women |
Token ID | 6926 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
milo | +1.029 |
oried | +0.841 |
Choi | +0.795 |
Kw | +0.772 |
bamboo | +0.768 |
Neg logit contributions | |
ONY | -1.333 |
space | -1.225 |
Stall | -1.164 |
lust | -1.138 |
satell | -1.130 |
Token | Education |
Token ID | 7868 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
milo | +0.320 |
oried | +0.250 |
Choi | +0.233 |
bamboo | +0.225 |
Kw | +0.223 |
Neg logit contributions | |
ONY | -0.524 |
space | -0.487 |
Stall | -0.467 |
lust | -0.456 |
Goth | -0.452 |
Token | Fund |
Token ID | 7557 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ONY | +0.013 |
space | +0.012 |
Stall | +0.011 |
lust | +0.011 |
Goth | +0.011 |
Neg logit contributions | |
milo | -0.017 |
oried | -0.014 |
Choi | -0.014 |
bamboo | -0.013 |
Kw | -0.013 |
Token | : |
Token ID | 25 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
milo | +1.022 |
oried | +0.856 |
Choi | +0.816 |
bamboo | +0.794 |
Kw | +0.793 |
Neg logit contributions | |
ONY | -1.013 |
space | -0.924 |
Stall | -0.873 |
lust | -0.850 |
Goth | -0.839 |
Token | Iran |
Token ID | 4068 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
ONY | +3.546 |
space | +3.245 |
Stall | +3.124 |
Goth | +2.993 |
lust | +2.956 |
Neg logit contributions | |
milo | -3.640 |
oried | -3.119 |
Choi | -2.845 |
bamboo | -2.829 |
arij | -2.788 |
Token | had |
Token ID | 550 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
milo | +2.376 |
oried | +1.960 |
Choi | +1.877 |
bamboo | +1.819 |
Kw | +1.814 |
Neg logit contributions | |
ONY | -2.810 |
space | -2.587 |
Stall | -2.452 |
lust | -2.391 |
Goth | -2.355 |
Token | Reagan |
Token ID | 12823 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
milo | +2.292 |
oried | +1.877 |
Choi | +1.807 |
bamboo | +1.758 |
Kw | +1.738 |
Neg logit contributions | |
ONY | -2.862 |
space | -2.640 |
Stall | -2.505 |
lust | -2.441 |
Goth | -2.406 |
Token | by |
Token ID | 416 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
milo | +0.679 |
oried | +0.565 |
Choi | +0.535 |
bamboo | +0.522 |
Kw | +0.520 |
Neg logit contributions | |
ONY | -0.717 |
space | -0.656 |
Stall | -0.622 |
lust | -0.603 |
Goth | -0.598 |
Token | the |
Token ID | 262 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
milo | +4.149 |
oried | +3.441 |
Choi | +3.310 |
bamboo | +3.214 |
Kw | +3.213 |
Neg logit contributions | |
ONY | -4.437 |
space | -4.076 |
Stall | -3.860 |
lust | -3.749 |
Goth | -3.677 |
Token | chain |
Token ID | 6333 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
milo | +0.182 |
oried | +0.152 |
Choi | +0.144 |
bamboo | +0.141 |
Kw | +0.140 |
Neg logit contributions | |
ONY | -0.182 |
space | -0.166 |
Stall | -0.158 |
lust | -0.153 |
Goth | -0.151 |
Token | because |
Token ID | 780 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
milo | +8.845 |
oried | +7.362 |
linking | +7.330 |
linkage | +7.162 |
bamboo | +7.123 |
Neg logit contributions | |
ONY | -10.901 |
space | -9.738 |
Stall | -9.561 |
satell | -9.327 |
haps | -9.280 |
Token | he |
Token ID | 339 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
milo | +1.746 |
oried | +1.463 |
Choi | +1.404 |
bamboo | +1.365 |
Kw | +1.365 |
Neg logit contributions | |
ONY | -1.666 |
space | -1.516 |
Stall | -1.424 |
lust | -1.387 |
Goth | -1.366 |
Token | did |
Token ID | 750 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
milo | +0.996 |
oried | +0.819 |
Choi | +0.773 |
bamboo | +0.752 |
Kw | +0.749 |
Neg logit contributions | |
ONY | -1.167 |
space | -1.073 |
Stall | -1.020 |
lust | -0.991 |
Goth | -0.983 |
Token | a |
Token ID | 257 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
ONY | +0.699 |
space | +0.635 |
Stall | +0.605 |
lust | +0.585 |
Goth | +0.580 |
Neg logit contributions | |
milo | -0.716 |
oried | -0.598 |
Choi | -0.561 |
bamboo | -0.547 |
Kw | -0.546 |
Token | dirty |
Token ID | 11841 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
milo | +0.362 |
oried | +0.299 |
Choi | +0.282 |
bamboo | +0.274 |
Kw | +0.273 |
Neg logit contributions | |
ONY | -0.410 |
space | -0.377 |
Stall | -0.358 |
lust | -0.348 |
Goth | -0.345 |
Token | m |
Token ID | 285 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ONY | +0.047 |
space | +0.043 |
Stall | +0.041 |
lust | +0.040 |
Goth | +0.040 |
Neg logit contributions | |
milo | -0.045 |
oried | -0.038 |
Choi | -0.036 |
bamboo | -0.035 |
Kw | -0.034 |
Token | ogg |
Token ID | 10332 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
ONY | +0.389 |
space | +0.353 |
Stall | +0.332 |
lust | +0.322 |
Goth | +0.318 |
Neg logit contributions | |
milo | -0.440 |
oried | -0.371 |
Choi | -0.355 |
bamboo | -0.346 |
Kw | -0.344 |
Token | ies |
Token ID | 444 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
ONY | +0.654 |
space | +0.602 |
Stall | +0.571 |
lust | +0.553 |
Goth | +0.546 |
Neg logit contributions | |
milo | -0.666 |
oried | -0.557 |
Choi | -0.536 |
Kw | -0.514 |
bamboo | -0.513 |
Token | . |
Token ID | 13 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
milo | +1.235 |
oried | +1.024 |
Choi | +0.971 |
bamboo | +0.948 |
Kw | +0.943 |
Neg logit contributions | |
ONY | -1.342 |
space | -1.229 |
Stall | -1.164 |
lust | -1.131 |
Goth | -1.119 |
Token | Did |
Token ID | 7731 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
milo | +2.808 |
oried | +2.364 |
Choi | +2.324 |
Kw | +2.282 |
Zhang | +2.252 |
Neg logit contributions | |
ONY | -2.736 |
space | -2.489 |
satell | -2.418 |
Stall | -2.293 |
lust | -2.270 |
Token | sp |
Token ID | 599 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
milo | +1.993 |
oried | +1.668 |
Choi | +1.585 |
bamboo | +1.550 |
Kw | +1.548 |
Neg logit contributions | |
ONY | -2.097 |
space | -1.921 |
Stall | -1.795 |
lust | -1.752 |
satell | -1.734 |
Token | arrow |
Token ID | 6018 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
milo | +6.118 |
oried | +5.384 |
ru | +5.270 |
iky | +5.178 |
ars | +4.873 |
Neg logit contributions | |
ONY | -13.307 |
Stall | -12.128 |
satell | -12.009 |
space | -11.942 |
ヘ | -11.394 |
Token | slaying |
Token ID | 45183 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
milo | +3.481 |
oried | +2.951 |
Choi | +2.810 |
bamboo | +2.799 |
Kw | +2.764 |
Neg logit contributions | |
ONY | -3.053 |
space | -2.738 |
Stall | -2.584 |
satell | -2.476 |
Goth | -2.452 |
Token | bows |
Token ID | 37469 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
milo | +5.313 |
oried | +4.547 |
bamboo | +4.449 |
Choi | +4.374 |
Zhang | +4.326 |
Neg logit contributions | |
ONY | -5.226 |
space | -4.701 |
Stall | -4.396 |
satell | -4.232 |
empt | -4.184 |
Token | have |
Token ID | 423 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
milo | +0.403 |
oried | +0.335 |
Choi | +0.317 |
bamboo | +0.309 |
Kw | +0.308 |
Neg logit contributions | |
ONY | -0.425 |
space | -0.389 |
Stall | -0.369 |
lust | -0.358 |
Goth | -0.354 |
Token | lines |
Token ID | 3951 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
milo | +2.287 |
oried | +1.911 |
Choi | +1.831 |
bamboo | +1.815 |
Kw | +1.777 |
Neg logit contributions | |
ONY | -2.651 |
space | -2.422 |
Stall | -2.276 |
lust | -2.222 |
satell | -2.187 |
Token | in |
Token ID | 259 |
Feature activation | +8.43e+00 |
Pos logit contributions | |
ONY | +2.112 |
space | +1.974 |
lust | +1.807 |
Stall | +1.806 |
empt | +1.748 |
Neg logit contributions | |
milo | -2.292 |
oried | -1.912 |
Choi | -1.864 |
bamboo | -1.810 |
Kw | -1.799 |
Token | possession |
Token ID | 7797 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ONY | +5.745 |
space | +5.392 |
Stall | +4.963 |
lust | +4.959 |
empt | +4.749 |
Neg logit contributions | |
milo | -6.665 |
oried | -5.435 |
Choi | -5.195 |
� | -5.153 |
Kw | -5.112 |
Token | of |
Token ID | 286 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
milo | +1.238 |
oried | +1.041 |
Choi | +0.989 |
bamboo | +0.966 |
Kw | +0.962 |
Neg logit contributions | |
ONY | -1.210 |
space | -1.100 |
Stall | -1.043 |
lust | -1.006 |
Goth | -0.999 |
Token | � |
Token ID | 564 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ONY | +1.520 |
space | +1.396 |
Stall | +1.317 |
lust | +1.286 |
Goth | +1.269 |
Neg logit contributions | |
milo | -1.579 |
oried | -1.305 |
Choi | -1.225 |
bamboo | -1.196 |
� | -1.193 |
Token | � |
Token ID | 250 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
ONY | +0.660 |
space | +0.605 |
Stall | +0.571 |
lust | +0.557 |
Goth | +0.550 |
Neg logit contributions | |
milo | -0.592 |
oried | -0.489 |
Choi | -0.464 |
bamboo | -0.451 |
Kw | -0.451 |
Token | each |
Token ID | 1123 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ONY | +4.796 |
space | +4.605 |
lust | +4.225 |
Stall | +3.978 |
thus | +3.955 |
Neg logit contributions | |
milo | -5.622 |
oried | -4.752 |
Choi | -4.649 |
bamboo | -4.522 |
Kw | -4.465 |
Token | other |
Token ID | 584 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
ONY | +6.705 |
space | +6.208 |
lust | +5.660 |
Stall | +5.644 |
Goth | +5.543 |
Neg logit contributions | |
milo | -7.906 |
oried | -6.463 |
Choi | -6.174 |
arij | -6.145 |
Hong | -6.047 |
Token | � |
Token ID | 447 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ONY | +4.874 |
space | +4.658 |
lust | +4.323 |
Stall | +4.253 |
Goth | +4.115 |
Neg logit contributions | |
milo | -4.698 |
oried | -3.819 |
Choi | -3.638 |
arij | -3.547 |
Kw | -3.532 |
Token | � |
Token ID | 247 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ONY | +1.520 |
space | +1.415 |
Stall | +1.350 |
lust | +1.326 |
Goth | +1.314 |
Neg logit contributions | |
milo | -0.914 |
oried | -0.705 |
Choi | -0.657 |
bamboo | -0.630 |
Kw | -0.628 |
Token | s |
Token ID | 82 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
ONY | +2.183 |
space | +2.038 |
Stall | +1.865 |
lust | +1.855 |
Goth | +1.779 |
Neg logit contributions | |
milo | -2.720 |
oried | -2.264 |
Choi | -2.184 |
bamboo | -2.129 |
Kw | -2.125 |
Token | � |
Token ID | 564 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
ONY | +4.368 |
space | +4.118 |
Stall | +3.856 |
lust | +3.850 |
Goth | +3.740 |
Neg logit contributions | |
milo | -4.595 |
oried | -3.603 |
Choi | -3.452 |
arij | -3.403 |
� | -3.330 |
Token | and |
Token ID | 290 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
milo | +2.870 |
oried | +2.380 |
Choi | +2.250 |
bamboo | +2.204 |
Kw | +2.188 |
Neg logit contributions | |
ONY | -3.291 |
space | -2.998 |
Stall | -2.861 |
lust | -2.766 |
satell | -2.749 |
Token | p |
Token ID | 279 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
milo | +2.015 |
oried | +1.675 |
Choi | +1.587 |
bamboo | +1.556 |
Kw | +1.539 |
Neg logit contributions | |
ONY | -2.242 |
space | -2.053 |
Stall | -1.942 |
lust | -1.882 |
Goth | -1.865 |
Token | atted |
Token ID | 16898 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
milo | +5.481 |
oried | +4.874 |
ru | +4.403 |
Choi | +4.386 |
bamboo | +4.342 |
Neg logit contributions | |
ONY | -4.548 |
space | -4.160 |
Stall | -4.009 |
satell | -3.967 |
Goth | -3.769 |
Token | himself |
Token ID | 2241 |
Feature activation | +8.81e+00 |
Pos logit contributions | |
ONY | +1.913 |
space | +1.788 |
Stall | +1.707 |
lust | +1.669 |
Goth | +1.668 |
Neg logit contributions | |
milo | -1.194 |
oried | -0.929 |
Choi | -0.881 |
bamboo | -0.834 |
Kw | -0.828 |
Token | on |
Token ID | 319 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ONY | +5.627 |
space | +5.132 |
Stall | +4.690 |
empt | +4.678 |
Goth | +4.678 |
Neg logit contributions | |
milo | -7.093 |
oried | -5.901 |
Choi | -5.788 |
Hong | -5.574 |
linkage | -5.558 |
Token | the |
Token ID | 262 |
Feature activation | +8.86e+00 |
Pos logit contributions | |
ONY | +2.192 |
space | +1.982 |
Stall | +1.861 |
lust | +1.808 |
Goth | +1.797 |
Neg logit contributions | |
milo | -2.550 |
oried | -2.148 |
Choi | -2.056 |
bamboo | -1.990 |
Kw | -1.973 |
Token | back |
Token ID | 736 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
ONY | +5.815 |
space | +5.225 |
Stall | +4.904 |
Goth | +4.848 |
empt | +4.828 |
Neg logit contributions | |
milo | -7.184 |
oried | -5.928 |
Choi | -5.648 |
aukee | -5.410 |
Puzzles | -5.410 |
Token | for |
Token ID | 329 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
ONY | +8.124 |
space | +7.900 |
lust | +7.211 |
empt | +6.814 |
Goth | +6.799 |
Neg logit contributions | |
milo | -11.421 |
oried | -9.256 |
arij | -9.205 |
Choi | -9.087 |
linkage | -8.884 |
Token | � |
Token ID | 564 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
milo | +2.703 |
oried | +2.250 |
Choi | +2.150 |
bamboo | +2.109 |
Kw | +2.094 |
Neg logit contributions | |
ONY | -3.005 |
space | -2.747 |
Stall | -2.599 |
lust | -2.512 |
satell | -2.500 |
Token | � |
Token ID | 250 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
milo | +1.785 |
oried | +1.433 |
Choi | +1.338 |
bamboo | +1.300 |
Kw | +1.289 |
Neg logit contributions | |
ONY | -2.515 |
space | -2.328 |
Stall | -2.223 |
lust | -2.164 |
Goth | -2.147 |
Token | public |
Token ID | 11377 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ONY | +1.081 |
space | +0.997 |
Stall | +0.924 |
lust | +0.911 |
empt | +0.889 |
Neg logit contributions | |
milo | -1.159 |
oried | -0.982 |
Choi | -0.941 |
bamboo | -0.917 |
Kw | -0.911 |
Token | strength |
Token ID | 4202 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ONY | +1.376 |
space | +1.263 |
Stall | +1.216 |
lust | +1.179 |
Goth | +1.172 |
Neg logit contributions | |
milo | -1.181 |
oried | -0.965 |
Choi | -0.900 |
Kw | -0.868 |
bamboo | -0.868 |
Token | . |
Token ID | 13 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
milo | +1.435 |
oried | +1.199 |
Choi | +1.140 |
bamboo | +1.111 |
Kw | +1.107 |
Neg logit contributions | |
ONY | -1.594 |
space | -1.463 |
Stall | -1.385 |
lust | -1.344 |
satell | -1.331 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ONY | +0.348 |
space | +0.314 |
Stall | +0.296 |
lust | +0.285 |
Goth | +0.282 |
Neg logit contributions | |
milo | -0.426 |
oried | -0.363 |
Choi | -0.345 |
bamboo | -0.339 |
Kw | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ONY | +1.378 |
space | +1.249 |
Stall | +1.168 |
lust | +1.132 |
Goth | +1.114 |
Neg logit contributions | |
milo | -1.742 |
oried | -1.483 |
Choi | -1.415 |
bamboo | -1.391 |
Kw | -1.378 |
Token | Thousands |
Token ID | 37482 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ONY | +1.101 |
space | +0.998 |
Stall | +0.929 |
lust | +0.906 |
Goth | +0.887 |
Neg logit contributions | |
milo | -1.319 |
oried | -1.122 |
Choi | -1.073 |
bamboo | -1.055 |
Kw | -1.046 |
Token | of |
Token ID | 286 |
Feature activation | +9.51e+00 |
Pos logit contributions | |
ONY | +2.895 |
space | +2.707 |
Stall | +2.547 |
lust | +2.490 |
Goth | +2.424 |
Neg logit contributions | |
milo | -3.416 |
oried | -2.901 |
Choi | -2.699 |
Kw | -2.625 |
bamboo | -2.619 |
Token | people |
Token ID | 661 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ONY | +6.701 |
space | +6.389 |
Stall | +6.224 |
Goth | +5.931 |
lust | +5.907 |
Neg logit contributions | |
milo | -6.912 |
oried | -5.716 |
� | -5.212 |
Choi | -5.188 |
thood | -5.168 |
Token | gather |
Token ID | 6431 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
ONY | +2.279 |
space | +2.141 |
Stall | +2.016 |
lust | +1.977 |
Goth | +1.935 |
Neg logit contributions | |
milo | -2.335 |
oried | -1.937 |
Choi | -1.832 |
Kw | -1.777 |
� | -1.768 |
Token | at |
Token ID | 379 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
ONY | +1.755 |
space | +1.607 |
Stall | +1.505 |
lust | +1.468 |
Goth | +1.450 |
Neg logit contributions | |
milo | -1.966 |
oried | -1.663 |
Choi | -1.574 |
bamboo | -1.538 |
Kw | -1.534 |
Token | the |
Token ID | 262 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
ONY | +2.808 |
space | +2.604 |
Stall | +2.461 |
Goth | +2.378 |
lust | +2.362 |
Neg logit contributions | |
milo | -2.875 |
oried | -2.401 |
Choi | -2.238 |
� | -2.186 |
bamboo | -2.181 |
Token | final |
Token ID | 2457 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ONY | +3.269 |
space | +3.042 |
Stall | +2.920 |
Goth | +2.814 |
lust | +2.777 |
Neg logit contributions | |
milo | -3.174 |
oried | -2.603 |
Choi | -2.408 |
� | -2.363 |
Hong | -2.343 |
Token | adoption |
Token ID | 12695 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
ONY | +0.063 |
space | +0.054 |
Stall | +0.049 |
lust | +0.046 |
Goth | +0.046 |
Neg logit contributions | |
milo | -0.143 |
oried | -0.126 |
Choi | -0.121 |
bamboo | -0.119 |
Kw | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
milo | +2.811 |
oried | +2.318 |
Choi | +2.196 |
bamboo | +2.138 |
Kw | +2.121 |
Neg logit contributions | |
ONY | -3.447 |
space | -3.134 |
Stall | -2.997 |
satell | -2.904 |
lust | -2.899 |
Token | And |
Token ID | 843 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
milo | +0.276 |
oried | +0.233 |
Choi | +0.221 |
bamboo | +0.216 |
Kw | +0.215 |
Neg logit contributions | |
ONY | -0.251 |
space | -0.228 |
Stall | -0.215 |
lust | -0.208 |
Goth | -0.206 |
Token | nothing |
Token ID | 2147 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ONY | +0.979 |
space | +0.903 |
Stall | +0.855 |
Goth | +0.826 |
lust | +0.821 |
Neg logit contributions | |
milo | -0.937 |
oried | -0.769 |
Choi | -0.720 |
bamboo | -0.707 |
� | -0.705 |
Token | you |
Token ID | 345 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
milo | +0.832 |
oried | +0.687 |
Choi | +0.650 |
bamboo | +0.633 |
Kw | +0.630 |
Neg logit contributions | |
ONY | -0.928 |
space | -0.851 |
Stall | -0.808 |
lust | -0.785 |
Goth | -0.777 |
Token | guys |
Token ID | 3730 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ONY | +2.783 |
space | +2.536 |
Stall | +2.379 |
lust | +2.314 |
empt | +2.282 |
Neg logit contributions | |
milo | -2.703 |
oried | -2.225 |
Choi | -2.091 |
Kw | -2.045 |
bamboo | -2.035 |
Token | do |
Token ID | 466 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ONY | +6.907 |
space | +6.266 |
Stall | +5.742 |
empt | +5.582 |
lust | +5.507 |
Neg logit contributions | |
milo | -7.762 |
oried | -6.389 |
Choi | -5.997 |
Hong | -5.915 |
arij | -5.799 |
Token | ever |
Token ID | 1683 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ONY | +1.703 |
space | +1.571 |
Stall | +1.473 |
lust | +1.438 |
Goth | +1.413 |
Neg logit contributions | |
milo | -1.717 |
oried | -1.424 |
Choi | -1.347 |
Kw | -1.314 |
bamboo | -1.308 |
Token | seems |
Token ID | 2331 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ONY | +0.374 |
space | +0.346 |
Stall | +0.327 |
lust | +0.319 |
Goth | +0.315 |
Neg logit contributions | |
milo | -0.333 |
oried | -0.274 |
Choi | -0.257 |
Kw | -0.250 |
bamboo | -0.249 |
Token | to |
Token ID | 284 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ONY | +1.245 |
space | +1.138 |
Stall | +1.065 |
lust | +1.049 |
Goth | +1.026 |
Neg logit contributions | |
milo | -1.310 |
oried | -1.081 |
Choi | -1.007 |
Kw | -0.987 |
bamboo | -0.984 |
Token | be |
Token ID | 307 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
ONY | +1.272 |
space | +1.172 |
Stall | +1.112 |
lust | +1.078 |
Goth | +1.060 |
Neg logit contributions | |
milo | -1.260 |
oried | -1.039 |
Choi | -0.973 |
Kw | -0.953 |
arij | -0.945 |
Token | , |
Token ID | 11 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
milo | +0.618 |
oried | +0.519 |
Choi | +0.493 |
bamboo | +0.482 |
Kw | +0.480 |
Neg logit contributions | |
ONY | -0.597 |
space | -0.544 |
Stall | -0.514 |
lust | -0.498 |
Goth | -0.493 |
Token | Vil |
Token ID | 34037 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
milo | +0.700 |
oried | +0.583 |
Choi | +0.552 |
bamboo | +0.539 |
Kw | +0.536 |
Neg logit contributions | |
ONY | -0.729 |
space | -0.666 |
Stall | -0.632 |
lust | -0.612 |
Goth | -0.607 |
Token | ma |
Token ID | 2611 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ONY | +0.446 |
space | +0.402 |
Stall | +0.378 |
lust | +0.364 |
Goth | +0.361 |
Neg logit contributions | |
milo | -0.553 |
oried | -0.472 |
Choi | -0.450 |
bamboo | -0.440 |
Kw | -0.439 |
Token | and |
Token ID | 290 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
milo | +1.879 |
oried | +1.566 |
Choi | +1.490 |
bamboo | +1.452 |
Kw | +1.448 |
Neg logit contributions | |
ONY | -2.008 |
space | -1.839 |
Stall | -1.733 |
lust | -1.692 |
Goth | -1.664 |
Token | the |
Token ID | 262 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
milo | +0.702 |
oried | +0.577 |
Choi | +0.543 |
bamboo | +0.530 |
Kw | +0.526 |
Neg logit contributions | |
ONY | -0.802 |
space | -0.736 |
Stall | -0.702 |
lust | -0.679 |
Goth | -0.676 |
Token | NFL |
Token ID | 5134 |
Feature activation | +9.12e+00 |
Pos logit contributions | |
milo | +0.758 |
oried | +0.631 |
Choi | +0.599 |
bamboo | +0.585 |
Kw | +0.582 |
Neg logit contributions | |
ONY | -0.748 |
space | -0.682 |
Stall | -0.648 |
lust | -0.624 |
Goth | -0.621 |
Token | PA |
Token ID | 4537 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ONY | +5.978 |
space | +5.263 |
Stall | +4.958 |
empt | +4.645 |
Goth | +4.643 |
Neg logit contributions | |
milo | -7.534 |
oried | -6.093 |
bamboo | -5.760 |
Choi | -5.756 |
� | -5.714 |
Token | aren |
Token ID | 3588 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ONY | +1.099 |
space | +0.999 |
Stall | +0.952 |
Goth | +0.914 |
lust | +0.911 |
Neg logit contributions | |
milo | -1.137 |
oried | -0.945 |
Choi | -0.887 |
bamboo | -0.867 |
� | -0.865 |
Token | 't |
Token ID | 470 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ONY | +0.162 |
space | +0.150 |
Stall | +0.144 |
satell | +0.142 |
lust | +0.140 |
Neg logit contributions | |
milo | -0.095 |
oried | -0.075 |
Choi | -0.069 |
Kw | -0.066 |
bamboo | -0.066 |
Token | arguing |
Token ID | 11810 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
milo | +1.780 |
oried | +1.482 |
Choi | +1.416 |
bamboo | +1.381 |
Kw | +1.372 |
Neg logit contributions | |
ONY | -1.936 |
space | -1.774 |
Stall | -1.668 |
lust | -1.630 |
satell | -1.603 |
Token | against |
Token ID | 1028 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
milo | +0.516 |
oried | +0.430 |
Choi | +0.408 |
bamboo | +0.398 |
Kw | +0.396 |
Neg logit contributions | |
ONY | -0.539 |
space | -0.493 |
Stall | -0.466 |
lust | -0.453 |
Goth | -0.448 |
Token | Notes |
Token ID | 11822 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
milo | +0.154 |
oried | +0.130 |
Choi | +0.124 |
bamboo | +0.122 |
Kw | +0.121 |
Neg logit contributions | |
ONY | -0.132 |
space | -0.120 |
Stall | -0.113 |
lust | -0.109 |
Goth | -0.108 |
Token | that |
Token ID | 326 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ONY | +2.312 |
space | +2.142 |
Stall | +2.040 |
lust | +1.964 |
Goth | +1.955 |
Neg logit contributions | |
milo | -2.111 |
oried | -1.712 |
Choi | -1.602 |
bamboo | -1.575 |
Kw | -1.550 |
Token | Group |
Token ID | 4912 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ONY | +1.780 |
space | +1.626 |
Stall | +1.553 |
Goth | +1.473 |
lust | +1.469 |
Neg logit contributions | |
milo | -1.943 |
oried | -1.631 |
Choi | -1.533 |
bamboo | -1.494 |
� | -1.488 |
Token | on |
Token ID | 261 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
milo | +2.685 |
oried | +2.188 |
Choi | +2.037 |
Kw | +1.970 |
bamboo | +1.968 |
Neg logit contributions | |
ONY | -3.626 |
space | -3.313 |
Stall | -3.212 |
satell | -3.147 |
lust | -3.136 |
Token | later |
Token ID | 1568 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
milo | +2.177 |
oried | +1.827 |
Choi | +1.761 |
bamboo | +1.708 |
Kw | +1.708 |
Neg logit contributions | |
ONY | -2.446 |
space | -2.222 |
Stall | -2.109 |
lust | -2.072 |
Goth | -2.025 |
Token | clarified |
Token ID | 28464 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
milo | +0.798 |
oried | +0.674 |
Choi | +0.643 |
bamboo | +0.628 |
Kw | +0.625 |
Neg logit contributions | |
ONY | -0.724 |
space | -0.657 |
Stall | -0.620 |
lust | -0.600 |
Goth | -0.593 |
Token | its |
Token ID | 663 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ONY | +2.109 |
space | +1.931 |
Stall | +1.845 |
Goth | +1.756 |
lust | +1.755 |
Neg logit contributions | |
milo | -2.267 |
oried | -1.886 |
Choi | -1.772 |
bamboo | -1.729 |
� | -1.715 |
Token | Firefox |
Token ID | 16802 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
milo | +1.423 |
oried | +1.188 |
Choi | +1.139 |
bamboo | +1.115 |
Kw | +1.110 |
Neg logit contributions | |
ONY | -1.558 |
space | -1.415 |
Stall | -1.343 |
lust | -1.312 |
Goth | -1.293 |
Token | stance |
Token ID | 12046 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
milo | +1.248 |
oried | +1.007 |
Choi | +0.942 |
bamboo | +0.920 |
Kw | +0.914 |
Neg logit contributions | |
ONY | -1.800 |
space | -1.659 |
Stall | -1.584 |
lust | -1.549 |
Goth | -1.535 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ONY | +0.539 |
space | +0.494 |
Stall | +0.469 |
lust | +0.452 |
Goth | +0.449 |
Neg logit contributions | |
milo | -0.543 |
oried | -0.450 |
Choi | -0.426 |
bamboo | -0.414 |
Kw | -0.413 |
Token | saying |
Token ID | 2282 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
ONY | +1.442 |
space | +1.321 |
Stall | +1.262 |
Goth | +1.210 |
lust | +1.202 |
Neg logit contributions | |
milo | -1.435 |
oried | -1.186 |
Choi | -1.110 |
bamboo | -1.081 |
Kw | -1.072 |
Token | '. |
Token ID | 4458 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ONY | +1.194 |
space | +1.099 |
Stall | +1.012 |
lust | +0.981 |
Goth | +0.952 |
Neg logit contributions | |
milo | -1.572 |
oried | -1.333 |
Choi | -1.283 |
bamboo | -1.258 |
Kw | -1.245 |
Token | The |
Token ID | 383 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ONY | +1.059 |
space | +0.972 |
Stall | +0.918 |
lust | +0.881 |
Goth | +0.874 |
Neg logit contributions | |
milo | -1.169 |
oried | -0.983 |
Choi | -0.923 |
bamboo | -0.908 |
Kw | -0.903 |
Token | back |
Token ID | 736 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
ONY | +1.304 |
space | +1.202 |
Stall | +1.137 |
Goth | +1.094 |
lust | +1.094 |
Neg logit contributions | |
milo | -1.191 |
oried | -0.981 |
Choi | -0.922 |
bamboo | -0.896 |
Kw | -0.894 |
Token | sl |
Token ID | 6649 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
space | +6.124 |
ONY | +5.362 |
Stall | +4.352 |
empt | +4.342 |
lust | +4.187 |
Neg logit contributions | |
milo | -11.837 |
aukee | -10.047 |
oried | -9.982 |
Choi | -9.545 |
iane | -9.321 |
Token | ash |
Token ID | 1077 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ONY | +1.182 |
space | +1.105 |
Stall | +1.046 |
lust | +1.024 |
Goth | +1.012 |
Neg logit contributions | |
milo | -0.812 |
oried | -0.643 |
Choi | -0.600 |
bamboo | -0.586 |
Kw | -0.579 |
Token | in |
Token ID | 287 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
ONY | +1.665 |
space | +1.551 |
Stall | +1.444 |
lust | +1.398 |
Goth | +1.384 |
Neg logit contributions | |
milo | -1.730 |
oried | -1.430 |
Choi | -1.348 |
bamboo | -1.315 |
Kw | -1.309 |
Token | front |
Token ID | 2166 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
ONY | +3.320 |
space | +3.102 |
Stall | +2.903 |
Goth | +2.799 |
lust | +2.776 |
Neg logit contributions | |
milo | -3.600 |
oried | -2.986 |
Choi | -2.771 |
� | -2.745 |
Hong | -2.724 |
Token | of |
Token ID | 286 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
space | +5.345 |
ONY | +5.287 |
Stall | +4.535 |
lust | +4.461 |
empt | +4.336 |
Neg logit contributions | |
milo | -7.544 |
oried | -6.298 |
Choi | -6.035 |
Kw | -5.860 |
fabricated | -5.850 |
Token | the |
Token ID | 262 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
ONY | +4.051 |
space | +3.816 |
Stall | +3.534 |
Goth | +3.381 |
lust | +3.341 |
Neg logit contributions | |
milo | -4.541 |
oried | -3.716 |
Choi | -3.441 |
� | -3.416 |
Hong | -3.402 |
Token | ' |
Token ID | 705 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
ONY | +5.075 |
space | +4.834 |
Stall | +4.460 |
Goth | +4.256 |
lust | +4.158 |
Neg logit contributions | |
milo | -5.173 |
oried | -4.186 |
Choi | -3.863 |
� | -3.847 |
aukee | -3.787 |
Token | :' |
Token ID | 32105 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ONY | +5.576 |
space | +5.492 |
Stall | +4.825 |
lust | +4.730 |
empt | +4.602 |
Neg logit contributions | |
milo | -6.606 |
oried | -5.460 |
Choi | -5.286 |
bamboo | -5.200 |
Kw | -5.165 |
Token | party |
Token ID | 2151 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ONY | +3.669 |
space | +3.408 |
Stall | +3.165 |
Goth | +3.125 |
lust | +3.059 |
Neg logit contributions | |
milo | -5.315 |
oried | -4.702 |
Choi | -4.408 |
atown | -4.334 |
arij | -4.327 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ONY | +1.223 |
space | +1.120 |
Stall | +1.059 |
Goth | +1.025 |
lust | +1.022 |
Neg logit contributions | |
milo | -1.260 |
oried | -1.060 |
Choi | -0.998 |
bamboo | -0.980 |
Kw | -0.971 |
Token |
|
Token ID | 198 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
milo | +1.755 |
oried | +1.490 |
Choi | +1.435 |
Kw | +1.398 |
bamboo | +1.389 |
Neg logit contributions | |
ONY | -1.511 |
space | -1.371 |
Stall | -1.289 |
lust | -1.249 |
satell | -1.248 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
milo | +0.675 |
oried | +0.576 |
Choi | +0.552 |
Kw | +0.538 |
Zhang | +0.534 |
Neg logit contributions | |
ONY | -0.635 |
space | -0.570 |
satell | -0.570 |
Stall | -0.547 |
Goth | -0.521 |
Token | The |
Token ID | 464 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
milo | +1.400 |
oried | +1.186 |
Choi | +1.128 |
Kw | +1.100 |
bamboo | +1.096 |
Neg logit contributions | |
ONY | -1.225 |
space | -1.109 |
Stall | -1.056 |
satell | -1.014 |
lust | -1.012 |
Token | row |
Token ID | 5752 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
milo | +1.476 |
oried | +1.222 |
Choi | +1.160 |
bamboo | +1.131 |
Kw | +1.124 |
Neg logit contributions | |
ONY | -1.667 |
space | -1.528 |
Stall | -1.452 |
lust | -1.412 |
Goth | -1.389 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ONY | +0.541 |
space | +0.503 |
Stall | +0.475 |
lust | +0.466 |
Goth | +0.461 |
Neg logit contributions | |
milo | -0.464 |
oried | -0.376 |
Choi | -0.359 |
bamboo | -0.350 |
Kw | -0.347 |
Token | which |
Token ID | 543 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
ONY | +0.935 |
space | +0.855 |
Stall | +0.811 |
lust | +0.781 |
Goth | +0.779 |
Neg logit contributions | |
milo | -0.983 |
oried | -0.820 |
Choi | -0.773 |
bamboo | -0.759 |
Kw | -0.750 |
Token | erupted |
Token ID | 23681 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ONY | +1.920 |
space | +1.767 |
Stall | +1.700 |
Goth | +1.650 |
lust | +1.633 |
Neg logit contributions | |
milo | -1.784 |
oried | -1.473 |
Choi | -1.374 |
bamboo | -1.351 |
Kw | -1.340 |
Token | at |
Token ID | 379 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ONY | +0.163 |
space | +0.149 |
Stall | +0.142 |
lust | +0.138 |
Goth | +0.137 |
Neg logit contributions | |
milo | -0.156 |
oried | -0.130 |
Choi | -0.122 |
bamboo | -0.119 |
Kw | -0.118 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
ONY | +0.278 |
space | +0.254 |
Stall | +0.242 |
lust | +0.234 |
Goth | +0.234 |
Neg logit contributions | |
milo | -0.263 |
oried | -0.218 |
Choi | -0.205 |
bamboo | -0.201 |
Kw | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ONY | +0.673 |
space | +0.606 |
Stall | +0.572 |
satell | +0.557 |
lust | +0.550 |
Neg logit contributions | |
milo | -0.788 |
oried | -0.671 |
Choi | -0.641 |
Kw | -0.625 |
bamboo | -0.625 |
Token | Later |
Token ID | 18602 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
milo | +1.303 |
oried | +1.103 |
Choi | +1.046 |
Kw | +1.021 |
bamboo | +1.018 |
Neg logit contributions | |
ONY | -1.115 |
space | -1.008 |
Stall | -0.960 |
satell | -0.928 |
lust | -0.920 |
Token | , |
Token ID | 11 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
ONY | +0.153 |
space | +0.139 |
Stall | +0.132 |
lust | +0.127 |
Goth | +0.126 |
Neg logit contributions | |
milo | -0.165 |
oried | -0.139 |
Choi | -0.132 |
bamboo | -0.129 |
Kw | -0.128 |
Token | Sy |
Token ID | 1632 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
milo | +2.832 |
oried | +2.350 |
Choi | +2.271 |
Kw | +2.209 |
Zhang | +2.178 |
Neg logit contributions | |
ONY | -3.041 |
space | -2.787 |
Stall | -2.616 |
lust | -2.592 |
Goth | -2.542 |
Token | kes |
Token ID | 5209 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
milo | +0.439 |
oried | +0.352 |
Choi | +0.323 |
Kw | +0.312 |
bamboo | +0.307 |
Neg logit contributions | |
ONY | -0.704 |
space | -0.644 |
Stall | -0.626 |
satell | -0.613 |
Goth | -0.607 |
Token | tweeted |
Token ID | 10830 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
milo | +2.751 |
oried | +2.332 |
Choi | +2.224 |
bamboo | +2.178 |
Kw | +2.173 |
Neg logit contributions | |
ONY | -2.670 |
space | -2.418 |
Stall | -2.274 |
lust | -2.232 |
satell | -2.195 |
Token | , |
Token ID | 11 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ONY | +0.143 |
space | +0.130 |
Stall | +0.123 |
lust | +0.119 |
Goth | +0.118 |
Neg logit contributions | |
milo | -0.145 |
oried | -0.121 |
Choi | -0.114 |
bamboo | -0.112 |
Kw | -0.111 |
Token | " |
Token ID | 366 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
milo | +0.340 |
oried | +0.278 |
Choi | +0.262 |
bamboo | +0.254 |
Kw | +0.253 |
Neg logit contributions | |
ONY | -0.419 |
space | -0.386 |
Stall | -0.368 |
lust | -0.358 |
Goth | -0.354 |
Token | I |
Token ID | 40 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
milo | +0.093 |
oried | +0.079 |
Choi | +0.076 |
bamboo | +0.074 |
Kw | +0.074 |
Neg logit contributions | |
ONY | -0.074 |
space | -0.067 |
Stall | -0.062 |
lust | -0.060 |
Goth | -0.059 |
Token | thanked |
Token ID | 26280 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
milo | +2.280 |
oried | +1.916 |
Choi | +1.827 |
Kw | +1.787 |
bamboo | +1.781 |
Neg logit contributions | |
ONY | -2.347 |
space | -2.146 |
Stall | -2.031 |
lust | -1.976 |
satell | -1.962 |
Token | [ |
Token ID | 685 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
milo | +2.466 |
oried | +2.037 |
Choi | +1.961 |
Kw | +1.913 |
bamboo | +1.896 |
Neg logit contributions | |
ONY | -2.640 |
space | -2.424 |
Stall | -2.275 |
lust | -2.246 |
satell | -2.209 |
Token | and |
Token ID | 290 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
ONY | +3.975 |
space | +3.707 |
Stall | +3.524 |
Goth | +3.424 |
lust | +3.406 |
Neg logit contributions | |
milo | -3.968 |
oried | -3.227 |
Choi | -2.988 |
� | -2.958 |
arij | -2.957 |
Token | dad |
Token ID | 9955 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
milo | +0.596 |
oried | +0.495 |
Choi | +0.470 |
bamboo | +0.458 |
Kw | +0.456 |
Neg logit contributions | |
ONY | -0.639 |
space | -0.585 |
Stall | -0.554 |
lust | -0.538 |
Goth | -0.532 |
Token | were |
Token ID | 547 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
ONY | +6.095 |
space | +5.675 |
Stall | +5.387 |
Goth | +5.281 |
lust | +5.173 |
Neg logit contributions | |
milo | -7.088 |
oried | -5.696 |
� | -5.424 |
arij | -5.309 |
Choi | -5.283 |
Token | speech |
Token ID | 4046 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
milo | +0.328 |
oried | +0.273 |
Choi | +0.259 |
bamboo | +0.253 |
Kw | +0.252 |
Neg logit contributions | |
ONY | -0.341 |
space | -0.312 |
Stall | -0.296 |
lust | -0.287 |
Goth | -0.284 |
Token | less |
Token ID | 1203 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
milo | +1.434 |
oried | +1.070 |
Choi | +0.969 |
bamboo | +0.929 |
Kw | +0.924 |
Neg logit contributions | |
ONY | -3.277 |
space | -3.047 |
Stall | -2.937 |
lust | -2.859 |
satell | -2.850 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
milo | +1.963 |
oried | +1.635 |
Choi | +1.552 |
bamboo | +1.507 |
Kw | +1.505 |
Neg logit contributions | |
ONY | -2.360 |
space | -2.150 |
Stall | -2.038 |
satell | -1.985 |
lust | -1.977 |
Token | They |
Token ID | 1119 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ONY | +1.465 |
space | +1.335 |
Stall | +1.269 |
Goth | +1.221 |
lust | +1.220 |
Neg logit contributions | |
milo | -1.613 |
oried | -1.349 |
Choi | -1.258 |
bamboo | -1.253 |
� | -1.230 |
Token | were |
Token ID | 547 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
milo | +0.631 |
oried | +0.519 |
Choi | +0.490 |
bamboo | +0.477 |
Kw | +0.475 |
Neg logit contributions | |
ONY | -0.735 |
space | -0.676 |
Stall | -0.642 |
lust | -0.624 |
Goth | -0.618 |
Token | looking |
Token ID | 2045 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
ONY | +1.383 |
space | +1.268 |
Stall | +1.207 |
Goth | +1.171 |
lust | +1.168 |
Neg logit contributions | |
milo | -1.321 |
oried | -1.089 |
Choi | -1.013 |
bamboo | -0.992 |
� | -0.992 |
Token | at |
Token ID | 379 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
milo | +0.529 |
oried | +0.444 |
Choi | +0.423 |
bamboo | +0.412 |
Kw | +0.410 |
Neg logit contributions | |
ONY | -0.534 |
space | -0.487 |
Stall | -0.461 |
lust | -0.446 |
Goth | -0.442 |
Token | Anna |
Token ID | 11735 |
Feature activation | +9.27e+00 |
Pos logit contributions | |
ONY | +0.082 |
space | +0.075 |
Stall | +0.071 |
lust | +0.069 |
Goth | +0.069 |
Neg logit contributions | |
milo | -0.078 |
oried | -0.065 |
Choi | -0.062 |
bamboo | -0.060 |
Kw | -0.060 |
Token | Mr |
Token ID | 1770 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
milo | +0.346 |
oried | +0.292 |
Choi | +0.278 |
bamboo | +0.272 |
Kw | +0.271 |
Neg logit contributions | |
ONY | -0.315 |
space | -0.286 |
Stall | -0.270 |
lust | -0.261 |
Goth | -0.258 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ONY | +3.330 |
space | +3.100 |
Stall | +2.927 |
lust | +2.869 |
Goth | +2.815 |
Neg logit contributions | |
milo | -3.282 |
oried | -2.674 |
bamboo | -2.530 |
Choi | -2.494 |
arij | -2.466 |
Token | Lu |
Token ID | 6026 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
milo | +1.033 |
oried | +0.858 |
Choi | +0.818 |
bamboo | +0.792 |
Kw | +0.792 |
Neg logit contributions | |
ONY | -1.113 |
space | -1.017 |
Stall | -0.962 |
lust | -0.936 |
Goth | -0.925 |
Token | ce |
Token ID | 344 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ONY | +3.710 |
space | +3.484 |
Stall | +3.152 |
lust | +3.146 |
empt | +3.050 |
Neg logit contributions | |
milo | -5.008 |
oried | -4.290 |
bamboo | -4.118 |
Choi | -4.081 |
Kw | -4.061 |
Token | asserted |
Token ID | 21635 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
milo | +2.613 |
oried | +2.235 |
Choi | +2.134 |
bamboo | +2.085 |
Kw | +2.083 |
Neg logit contributions | |
ONY | -2.146 |
space | -1.929 |
Stall | -1.806 |
lust | -1.757 |
Goth | -1.730 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
milo | +2.802 |
oried | +2.340 |
Choi | +2.193 |
Kw | +2.129 |
bamboo | +2.123 |
Neg logit contributions | |
ONY | -3.347 |
space | -3.073 |
Stall | -2.914 |
lust | -2.818 |
satell | -2.801 |
Token | before |
Token ID | 878 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
milo | +0.777 |
oried | +0.628 |
Choi | +0.590 |
bamboo | +0.572 |
Kw | +0.569 |
Neg logit contributions | |
ONY | -1.041 |
space | -0.961 |
Stall | -0.917 |
lust | -0.893 |
Goth | -0.885 |
Token | bound |
Token ID | 5421 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
milo | +0.985 |
oried | +0.814 |
Choi | +0.771 |
bamboo | +0.751 |
Kw | +0.747 |
Neg logit contributions | |
ONY | -1.104 |
space | -1.012 |
Stall | -0.960 |
lust | -0.933 |
Goth | -0.924 |
Token | ing |
Token ID | 278 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
milo | +0.482 |
oried | +0.387 |
Choi | +0.365 |
bamboo | +0.353 |
Kw | +0.351 |
Neg logit contributions | |
ONY | -0.654 |
space | -0.606 |
Stall | -0.577 |
lust | -0.565 |
Goth | -0.558 |
Token | onstage |
Token ID | 38500 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
ONY | +2.104 |
space | +1.953 |
Stall | +1.855 |
lust | +1.813 |
Goth | +1.782 |
Neg logit contributions | |
milo | -2.049 |
oried | -1.697 |
Choi | -1.588 |
� | -1.536 |
bamboo | -1.535 |
Token | for |
Token ID | 329 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
ONY | +4.027 |
space | +3.748 |
Stall | +3.540 |
lust | +3.477 |
Goth | +3.429 |
Neg logit contributions | |
milo | -4.696 |
oried | -3.877 |
Choi | -3.651 |
arij | -3.583 |
Hong | -3.572 |
Token | sey |
Token ID | 4397 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
milo | +1.891 |
oried | +1.570 |
Choi | +1.510 |
Kw | +1.467 |
Zhang | +1.451 |
Neg logit contributions | |
ONY | -1.940 |
satell | -1.725 |
space | -1.702 |
Stall | -1.645 |
Goth | -1.594 |
Token | Gram |
Token ID | 20159 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
milo | +1.895 |
oried | +1.601 |
Choi | +1.575 |
Kw | +1.517 |
Zhang | +1.500 |
Neg logit contributions | |
ONY | -2.109 |
space | -1.913 |
satell | -1.869 |
Stall | -1.757 |
lust | -1.751 |
Token | mer |
Token ID | 647 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
ONY | +1.536 |
space | +1.381 |
Stall | +1.274 |
lust | +1.233 |
Goth | +1.204 |
Neg logit contributions | |
milo | -2.329 |
oried | -2.010 |
Choi | -1.935 |
bamboo | -1.898 |
Kw | -1.891 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ONY | +3.676 |
space | +3.342 |
Stall | +3.160 |
lust | +3.007 |
Goth | +2.967 |
Neg logit contributions | |
milo | -5.518 |
oried | -4.747 |
bamboo | -4.522 |
arij | -4.469 |
Choi | -4.455 |
Token |
|
Token ID | 198 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
ONY | +1.529 |
space | +1.385 |
Stall | +1.297 |
lust | +1.255 |
Goth | +1.238 |
Neg logit contributions | |
milo | -1.911 |
oried | -1.626 |
Choi | -1.552 |
bamboo | -1.523 |
Kw | -1.513 |
Token | 1996 |
Token ID | 22288 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
ONY | +2.989 |
space | +2.721 |
lust | +2.363 |
Stall | +2.262 |
thus | +2.211 |
Neg logit contributions | |
milo | -7.140 |
oried | -6.479 |
bamboo | -6.335 |
arij | -6.264 |
Choi | -6.239 |
Token | Paul |
Token ID | 3362 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
milo | +2.554 |
oried | +2.127 |
Choi | +2.070 |
Kw | +2.036 |
Hugo | +1.995 |
Neg logit contributions | |
ONY | -2.972 |
space | -2.718 |
Stall | -2.528 |
satell | -2.524 |
lust | -2.505 |
Token | Re |
Token ID | 797 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
milo | +3.870 |
Choi | +3.373 |
oried | +3.369 |
Kw | +3.327 |
Zhang | +3.285 |
Neg logit contributions | |
ONY | -3.197 |
satell | -2.866 |
space | -2.826 |
lust | -2.531 |
Stall | -2.501 |
Token | iser |
Token ID | 5847 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
ONY | +0.676 |
space | +0.583 |
Stall | +0.532 |
lust | +0.504 |
Goth | +0.496 |
Neg logit contributions | |
milo | -1.423 |
oried | -1.252 |
Choi | -1.208 |
bamboo | -1.186 |
Kw | -1.183 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ONY | +3.660 |
space | +3.341 |
Stall | +3.171 |
lust | +3.021 |
Goth | +2.974 |
Neg logit contributions | |
milo | -5.590 |
oried | -4.784 |
bamboo | -4.546 |
arij | -4.536 |
� | -4.480 |
Token |
|
Token ID | 198 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
ONY | +1.018 |
space | +0.917 |
Stall | +0.864 |
satell | +0.835 |
lust | +0.832 |
Neg logit contributions | |
milo | -1.206 |
oried | -1.027 |
Choi | -0.981 |
bamboo | -0.957 |
Kw | -0.957 |
Token | ty |
Token ID | 774 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ONY | +3.067 |
space | +2.831 |
Stall | +2.669 |
lust | +2.618 |
Goth | +2.582 |
Neg logit contributions | |
milo | -2.887 |
oried | -2.389 |
Choi | -2.261 |
bamboo | -2.245 |
� | -2.219 |
Token | a |
Token ID | 64 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ONY | +1.180 |
space | +1.083 |
Stall | +1.027 |
lust | +0.998 |
Goth | +0.987 |
Neg logit contributions | |
milo | -1.127 |
oried | -0.933 |
Choi | -0.883 |
bamboo | -0.868 |
� | -0.853 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ONY | +0.845 |
space | +0.770 |
Stall | +0.730 |
lust | +0.705 |
Goth | +0.702 |
Neg logit contributions | |
milo | -0.886 |
oried | -0.739 |
Choi | -0.698 |
bamboo | -0.687 |
Kw | -0.677 |
Token | is |
Token ID | 318 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
milo | +1.119 |
oried | +0.948 |
Choi | +0.907 |
bamboo | +0.886 |
Kw | +0.883 |
Neg logit contributions | |
ONY | -0.992 |
space | -0.900 |
Stall | -0.846 |
lust | -0.820 |
Goth | -0.808 |
Token | a |
Token ID | 257 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
milo | +2.572 |
oried | +2.152 |
Choi | +2.064 |
bamboo | +2.004 |
Kw | +1.994 |
Neg logit contributions | |
ONY | -2.950 |
space | -2.709 |
Stall | -2.542 |
lust | -2.487 |
satell | -2.451 |
Token | recipient |
Token ID | 17800 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
milo | +1.071 |
oried | +0.891 |
Choi | +0.847 |
bamboo | +0.825 |
Kw | +0.823 |
Neg logit contributions | |
ONY | -1.161 |
space | -1.063 |
Stall | -1.005 |
lust | -0.977 |
Goth | -0.965 |
Token | of |
Token ID | 286 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
milo | +4.570 |
oried | +3.853 |
Choi | +3.729 |
Kw | +3.592 |
Zhang | +3.586 |
Neg logit contributions | |
ONY | -5.193 |
space | -4.760 |
Stall | -4.482 |
lust | -4.351 |
Goth | -4.324 |
Token | $ |
Token ID | 720 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
milo | +4.186 |
Choi | +3.482 |
oried | +3.477 |
Kw | +3.419 |
bamboo | +3.317 |
Neg logit contributions | |
ONY | -4.833 |
space | -4.389 |
Stall | -4.055 |
lust | -4.007 |
empt | -3.981 |
Token | 154 |
Token ID | 21526 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
milo | +1.921 |
oried | +1.604 |
Choi | +1.533 |
Kw | +1.485 |
bamboo | +1.479 |
Neg logit contributions | |
ONY | -1.984 |
space | -1.812 |
Stall | -1.735 |
satell | -1.706 |
Goth | -1.665 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
milo | +1.500 |
oried | +1.276 |
Choi | +1.223 |
bamboo | +1.198 |
Kw | +1.196 |
Neg logit contributions | |
ONY | -1.231 |
space | -1.112 |
Stall | -1.046 |
lust | -1.008 |
Goth | -0.999 |
Token | 4 |
Token ID | 19 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
ONY | +2.793 |
space | +2.550 |
Stall | +2.409 |
lust | +2.341 |
Goth | +2.308 |
Neg logit contributions | |
milo | -2.713 |
oried | -2.252 |
bamboo | -2.074 |
Choi | -2.055 |
arij | -2.028 |
Token | A |
Token ID | 32 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ONY | +2.338 |
space | +2.095 |
Stall | +1.897 |
lust | +1.878 |
Goth | +1.808 |
Neg logit contributions | |
milo | -3.298 |
oried | -2.856 |
Choi | -2.739 |
bamboo | -2.723 |
Kw | -2.665 |
Token | movement |
Token ID | 3356 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ONY | +0.753 |
space | +0.692 |
Stall | +0.655 |
lust | +0.637 |
Goth | +0.630 |
Neg logit contributions | |
milo | -0.694 |
oried | -0.573 |
Choi | -0.544 |
bamboo | -0.529 |
Kw | -0.526 |
Token | is |
Token ID | 318 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
milo | +1.254 |
oried | +1.048 |
Choi | +0.995 |
bamboo | +0.971 |
Kw | +0.967 |
Neg logit contributions | |
ONY | -1.298 |
space | -1.185 |
Stall | -1.121 |
lust | -1.086 |
Goth | -1.076 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
milo | +3.032 |
oried | +2.528 |
Choi | +2.433 |
bamboo | +2.385 |
Kw | +2.377 |
Neg logit contributions | |
ONY | -3.577 |
space | -3.273 |
Stall | -3.071 |
satell | -3.001 |
lust | -2.998 |
Token | foot |
Token ID | 5898 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
ONY | +1.134 |
space | +1.035 |
Stall | +0.978 |
lust | +0.947 |
Goth | +0.933 |
Neg logit contributions | |
milo | -1.242 |
oried | -1.044 |
Choi | -0.995 |
bamboo | -0.966 |
Kw | -0.962 |
Token | that |
Token ID | 326 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
milo | +0.361 |
oried | +0.301 |
Choi | +0.285 |
bamboo | +0.278 |
Kw | +0.277 |
Neg logit contributions | |
ONY | -0.373 |
space | -0.341 |
Stall | -0.323 |
lust | -0.314 |
Goth | -0.311 |
Token | must |
Token ID | 1276 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
milo | +2.609 |
oried | +2.170 |
Choi | +2.104 |
Kw | +2.046 |
bamboo | +2.046 |
Neg logit contributions | |
ONY | -2.866 |
space | -2.617 |
Stall | -2.448 |
lust | -2.394 |
satell | -2.370 |
Token | not |
Token ID | 407 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
milo | +1.013 |
oried | +0.843 |
Choi | +0.798 |
bamboo | +0.779 |
Kw | +0.775 |
Neg logit contributions | |
ONY | -1.082 |
space | -0.990 |
Stall | -0.938 |
lust | -0.910 |
Goth | -0.903 |
Token | fade |
Token ID | 22100 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
ONY | +0.975 |
space | +0.895 |
Stall | +0.852 |
lust | +0.826 |
Goth | +0.812 |
Neg logit contributions | |
milo | -0.961 |
oried | -0.794 |
Choi | -0.758 |
Kw | -0.739 |
bamboo | -0.737 |
Token | away |
Token ID | 1497 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ONY | +0.440 |
space | +0.405 |
Stall | +0.384 |
lust | +0.374 |
Goth | +0.370 |
Neg logit contributions | |
milo | -0.397 |
oried | -0.327 |
Choi | -0.309 |
bamboo | -0.302 |
Kw | -0.300 |
Token | ," |
Token ID | 553 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ONY | +0.107 |
space | +0.098 |
Stall | +0.093 |
lust | +0.090 |
Goth | +0.089 |
Neg logit contributions | |
milo | -0.096 |
oried | -0.079 |
Choi | -0.075 |
bamboo | -0.073 |
Kw | -0.073 |
Token | That |
Token ID | 2504 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ONY | +1.022 |
space | +0.925 |
Stall | +0.855 |
lust | +0.841 |
Goth | +0.819 |
Neg logit contributions | |
milo | -1.247 |
oried | -1.063 |
Choi | -1.021 |
bamboo | -1.006 |
Kw | -0.993 |
Token | sucks |
Token ID | 22523 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
ONY | +2.126 |
space | +1.948 |
Stall | +1.848 |
lust | +1.813 |
Goth | +1.794 |
Neg logit contributions | |
milo | -2.012 |
oried | -1.669 |
Choi | -1.559 |
� | -1.524 |
bamboo | -1.513 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ONY | +0.423 |
space | +0.389 |
Stall | +0.367 |
lust | +0.358 |
Goth | +0.353 |
Neg logit contributions | |
milo | -0.395 |
oried | -0.328 |
Choi | -0.311 |
bamboo | -0.302 |
Kw | -0.301 |
Token |
|
Token ID | 198 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ONY | +1.152 |
space | +1.045 |
Stall | +0.993 |
lust | +0.950 |
Goth | +0.946 |
Neg logit contributions | |
milo | -1.378 |
oried | -1.174 |
Choi | -1.104 |
bamboo | -1.093 |
arij | -1.076 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ONY | +2.113 |
space | +1.922 |
Stall | +1.781 |
lust | +1.738 |
Goth | +1.697 |
Neg logit contributions | |
milo | -2.863 |
oried | -2.439 |
Choi | -2.328 |
bamboo | -2.304 |
Kw | -2.266 |
Token | What |
Token ID | 2061 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ONY | +1.076 |
space | +0.976 |
Stall | +0.900 |
lust | +0.884 |
Goth | +0.861 |
Neg logit contributions | |
milo | -1.335 |
oried | -1.142 |
Choi | -1.097 |
bamboo | -1.082 |
Kw | -1.067 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
milo | +2.781 |
oried | +2.279 |
Choi | +2.195 |
Kw | +2.140 |
bamboo | +2.136 |
Neg logit contributions | |
ONY | -3.433 |
space | -3.120 |
Stall | -2.961 |
lust | -2.885 |
satell | -2.871 |
Token | horrible |
Token ID | 12361 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
ONY | +0.079 |
space | +0.072 |
Stall | +0.069 |
lust | +0.066 |
Goth | +0.066 |
Neg logit contributions | |
milo | -0.078 |
oried | -0.065 |
Choi | -0.062 |
bamboo | -0.060 |
Kw | -0.060 |
Token | way |
Token ID | 835 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
milo | +0.502 |
oried | +0.413 |
Choi | +0.390 |
bamboo | +0.379 |
Kw | +0.378 |
Neg logit contributions | |
ONY | -0.578 |
space | -0.532 |
Stall | -0.505 |
lust | -0.491 |
Goth | -0.487 |
Token | to |
Token ID | 284 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
ONY | +0.930 |
space | +0.853 |
Stall | +0.808 |
lust | +0.784 |
Goth | +0.776 |
Neg logit contributions | |
milo | -0.892 |
oried | -0.742 |
Choi | -0.701 |
bamboo | -0.685 |
Kw | -0.683 |
Token | spend |
Token ID | 4341 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
milo | +2.061 |
oried | +1.718 |
Choi | +1.625 |
bamboo | +1.591 |
Kw | +1.585 |
Neg logit contributions | |
ONY | -2.441 |
space | -2.233 |
Stall | -2.107 |
lust | -2.063 |
satell | -2.045 |
Token |
|
Token ID | 198 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
milo | +0.789 |
oried | +0.670 |
Choi | +0.643 |
Kw | +0.628 |
Zhang | +0.622 |
Neg logit contributions | |
ONY | -0.752 |
satell | -0.673 |
space | -0.671 |
Stall | -0.643 |
Goth | -0.614 |
Token | Sm |
Token ID | 7556 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
milo | +3.193 |
oried | +2.659 |
Choi | +2.490 |
Hong | +2.486 |
� | +2.449 |
Neg logit contributions | |
ONY | -3.155 |
space | -2.859 |
Stall | -2.805 |
satell | -2.762 |
Goth | -2.690 |
Token | oke |
Token ID | 2088 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
milo | +3.066 |
oried | +2.565 |
Choi | +2.378 |
Kw | +2.318 |
bamboo | +2.282 |
Neg logit contributions | |
ONY | -3.920 |
space | -3.601 |
Stall | -3.442 |
satell | -3.349 |
lust | -3.337 |
Token | Music |
Token ID | 7849 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
milo | +5.341 |
oried | +4.472 |
Choi | +4.206 |
Kw | +4.114 |
bamboo | +4.111 |
Neg logit contributions | |
ONY | -6.038 |
space | -5.381 |
Stall | -5.117 |
satell | -5.000 |
lust | -4.943 |
Token | manager |
Token ID | 4706 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
milo | +1.939 |
oried | +1.611 |
Choi | +1.539 |
bamboo | +1.496 |
Kw | +1.493 |
Neg logit contributions | |
ONY | -2.083 |
space | -1.903 |
Stall | -1.804 |
lust | -1.755 |
Goth | -1.733 |
Token | Mark |
Token ID | 2940 |
Feature activation | -9.63e+00 |
Pos logit contributions | |
ONY | +1.284 |
space | +1.183 |
Stall | +1.134 |
Goth | +1.089 |
lust | +1.087 |
Neg logit contributions | |
milo | -1.219 |
oried | -1.011 |
Choi | -0.934 |
bamboo | -0.927 |
� | -0.916 |
Token | de |
Token ID | 390 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
milo | +6.573 |
Choi | +5.794 |
Kw | +5.768 |
oried | +5.716 |
Zhang | +5.588 |
Neg logit contributions | |
ONY | -7.089 |
satell | -6.242 |
space | -6.230 |
haps | -5.732 |
lust | -5.721 |
Token | Jong |
Token ID | 17960 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
milo | +4.064 |
oried | +3.375 |
Choi | +3.354 |
Kw | +3.288 |
Zhang | +3.198 |
Neg logit contributions | |
ONY | -4.150 |
space | -3.781 |
satell | -3.484 |
Stall | -3.481 |
lust | -3.472 |
Token | , |
Token ID | 11 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
ONY | +0.668 |
space | +0.612 |
Stall | +0.574 |
lust | +0.554 |
Goth | +0.547 |
Neg logit contributions | |
milo | -0.780 |
oried | -0.656 |
Choi | -0.622 |
bamboo | -0.611 |
Kw | -0.604 |
Token | who |
Token ID | 508 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
milo | +0.535 |
oried | +0.438 |
Choi | +0.413 |
bamboo | +0.401 |
Kw | +0.399 |
Neg logit contributions | |
ONY | -0.661 |
space | -0.608 |
Stall | -0.579 |
lust | -0.563 |
Goth | -0.558 |
Token | has |
Token ID | 468 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
ONY | +0.706 |
space | +0.648 |
Stall | +0.617 |
lust | +0.595 |
Goth | +0.592 |
Neg logit contributions | |
milo | -0.662 |
oried | -0.546 |
Choi | -0.515 |
bamboo | -0.503 |
Kw | -0.499 |
Token | : |
Token ID | 25 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ONY | +2.172 |
space | +1.964 |
Stall | +1.877 |
lust | +1.791 |
Goth | +1.774 |
Neg logit contributions | |
milo | -2.753 |
oried | -2.277 |
Choi | -2.156 |
bamboo | -2.121 |
arij | -2.114 |
Token | passengers |
Token ID | 10405 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ONY | +4.105 |
space | +3.844 |
Stall | +3.670 |
lust | +3.508 |
Goth | +3.446 |
Neg logit contributions | |
milo | -4.125 |
oried | -3.340 |
Choi | -3.126 |
arij | -3.063 |
� | -3.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ONY | +0.205 |
space | +0.188 |
Stall | +0.179 |
lust | +0.174 |
Goth | +0.173 |
Neg logit contributions | |
milo | -0.174 |
oried | -0.143 |
Choi | -0.135 |
bamboo | -0.132 |
Kw | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
milo | +1.532 |
oried | +1.302 |
Choi | +1.257 |
Kw | +1.227 |
bamboo | +1.217 |
Neg logit contributions | |
ONY | -1.375 |
space | -1.245 |
Stall | -1.163 |
satell | -1.141 |
lust | -1.133 |
Token |
|
Token ID | 198 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
ONY | +0.050 |
space | +0.045 |
satell | +0.043 |
Stall | +0.043 |
lust | +0.041 |
Neg logit contributions | |
milo | -0.056 |
oried | -0.047 |
Choi | -0.045 |
Kw | -0.044 |
bamboo | -0.044 |
Token | Sp |
Token ID | 4561 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
milo | +3.165 |
oried | +2.690 |
Hong | +2.571 |
Choi | +2.530 |
� | +2.504 |
Neg logit contributions | |
ONY | -2.902 |
space | -2.618 |
Stall | -2.545 |
satell | -2.535 |
Goth | -2.447 |
Token | urred |
Token ID | 12808 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
milo | +7.272 |
oried | +6.761 |
ru | +6.304 |
iky | +6.279 |
Choi | +6.015 |
Neg logit contributions | |
ONY | -6.913 |
satell | -6.018 |
space | -6.013 |
Stall | -5.753 |
Goth | -5.642 |
Token | by |
Token ID | 416 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
milo | +1.995 |
oried | +1.644 |
Choi | +1.567 |
bamboo | +1.526 |
Kw | +1.513 |
Neg logit contributions | |
ONY | -2.439 |
space | -2.237 |
Stall | -2.115 |
lust | -2.057 |
Goth | -2.046 |
Token | federal |
Token ID | 2717 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
milo | +0.487 |
oried | +0.401 |
Choi | +0.379 |
bamboo | +0.369 |
Kw | +0.367 |
Neg logit contributions | |
ONY | -0.565 |
space | -0.520 |
Stall | -0.494 |
lust | -0.480 |
Goth | -0.475 |
Token | infrastructure |
Token ID | 6884 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ONY | +0.328 |
space | +0.302 |
Stall | +0.286 |
lust | +0.277 |
Goth | +0.274 |
Neg logit contributions | |
milo | -0.317 |
oried | -0.263 |
Choi | -0.247 |
bamboo | -0.241 |
Kw | -0.240 |
Token | money |
Token ID | 1637 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
milo | +1.805 |
oried | +1.541 |
Choi | +1.476 |
bamboo | +1.450 |
Kw | +1.439 |
Neg logit contributions | |
ONY | -1.646 |
space | -1.476 |
Stall | -1.393 |
lust | -1.335 |
Goth | -1.334 |
Token | likely |
Token ID | 1884 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
milo | +1.264 |
oried | +1.051 |
Choi | +1.002 |
bamboo | +0.977 |
Kw | +0.971 |
Neg logit contributions | |
ONY | -1.472 |
space | -1.349 |
Stall | -1.280 |
lust | -1.245 |
Goth | -1.228 |
Token | related |
Token ID | 3519 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
milo | +0.662 |
oried | +0.548 |
Choi | +0.518 |
bamboo | +0.505 |
Kw | +0.503 |
Neg logit contributions | |
ONY | -0.726 |
space | -0.666 |
Stall | -0.632 |
lust | -0.613 |
Goth | -0.608 |
Token | to |
Token ID | 284 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
milo | +1.444 |
oried | +1.192 |
Choi | +1.134 |
bamboo | +1.108 |
Kw | +1.098 |
Neg logit contributions | |
ONY | -1.734 |
space | -1.586 |
Stall | -1.512 |
lust | -1.463 |
Goth | -1.453 |
Token | our |
Token ID | 674 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
milo | +0.027 |
oried | +0.022 |
Choi | +0.021 |
bamboo | +0.021 |
Kw | +0.021 |
Neg logit contributions | |
ONY | -0.028 |
space | -0.025 |
Stall | -0.024 |
lust | -0.023 |
Goth | -0.023 |
Token | recent |
Token ID | 2274 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
milo | +1.120 |
oried | +0.926 |
Choi | +0.883 |
bamboo | +0.862 |
Kw | +0.857 |
Neg logit contributions | |
ONY | -1.272 |
space | -1.162 |
Stall | -1.105 |
lust | -1.073 |
Goth | -1.059 |
Token | demonic |
Token ID | 33739 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
milo | +1.207 |
oried | +1.002 |
Choi | +0.955 |
bamboo | +0.936 |
Kw | +0.928 |
Neg logit contributions | |
ONY | -1.355 |
space | -1.238 |
Stall | -1.175 |
lust | -1.142 |
Goth | -1.126 |
Token | explorer |
Token ID | 39349 |
Feature activation | -8.07e+00 |
Pos logit contributions | |
milo | +6.976 |
oried | +5.851 |
immigrants | +5.826 |
Choi | +5.816 |
bamboo | +5.813 |
Neg logit contributions | |
ONY | -8.054 |
space | -7.059 |
Stall | -6.618 |
lust | -6.456 |
satell | -6.439 |
Token | problem |
Token ID | 1917 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
milo | +5.293 |
oried | +4.402 |
Choi | +4.367 |
Zhang | +4.235 |
Kw | +4.227 |
Neg logit contributions | |
ONY | -6.421 |
space | -5.816 |
Stall | -5.470 |
satell | -5.326 |
lust | -5.310 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ONY | +0.094 |
space | +0.085 |
Stall | +0.080 |
lust | +0.078 |
Goth | +0.077 |
Neg logit contributions | |
milo | -0.105 |
oried | -0.089 |
Choi | -0.085 |
bamboo | -0.083 |
Kw | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ONY | +0.716 |
space | +0.653 |
Stall | +0.620 |
lust | +0.594 |
Goth | +0.594 |
Neg logit contributions | |
milo | -0.796 |
oried | -0.670 |
Choi | -0.630 |
bamboo | -0.621 |
Kw | -0.614 |
Token |
|
Token ID | 198 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
ONY | +1.242 |
space | +1.124 |
Stall | +1.053 |
lust | +1.019 |
Goth | +1.005 |
Neg logit contributions | |
milo | -1.545 |
oried | -1.315 |
Choi | -1.255 |
bamboo | -1.231 |
Kw | -1.224 |
Token | � |
Token ID | 251 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
milo | +0.940 |
oried | +0.713 |
Choi | +0.652 |
bamboo | +0.625 |
Kw | +0.621 |
Neg logit contributions | |
ONY | -1.922 |
space | -1.797 |
Stall | -1.727 |
lust | -1.690 |
satell | -1.678 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ONY | +0.341 |
space | +0.308 |
Stall | +0.290 |
lust | +0.280 |
Goth | +0.277 |
Neg logit contributions | |
milo | -0.421 |
oried | -0.359 |
Choi | -0.341 |
bamboo | -0.335 |
Kw | -0.332 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ONY | +1.555 |
space | +1.410 |
Stall | +1.317 |
lust | +1.278 |
Goth | +1.258 |
Neg logit contributions | |
milo | -1.982 |
oried | -1.686 |
Choi | -1.610 |
bamboo | -1.582 |
Kw | -1.568 |
Token | � |
Token ID | 447 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ONY | +1.049 |
space | +0.955 |
Stall | +0.887 |
lust | +0.868 |
Goth | +0.849 |
Neg logit contributions | |
milo | -1.234 |
oried | -1.047 |
Choi | -1.000 |
bamboo | -0.984 |
Kw | -0.971 |
Token | � |
Token ID | 250 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
milo | +0.764 |
oried | +0.598 |
Choi | +0.556 |
bamboo | +0.537 |
Kw | +0.533 |
Neg logit contributions | |
ONY | -1.259 |
space | -1.172 |
Stall | -1.122 |
lust | -1.095 |
Goth | -1.086 |
Token | Who |
Token ID | 8241 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
ONY | +1.864 |
space | +1.709 |
Stall | +1.592 |
lust | +1.546 |
Goth | +1.511 |
Neg logit contributions | |
milo | -2.238 |
oried | -1.914 |
Choi | -1.827 |
bamboo | -1.806 |
Kw | -1.778 |
Token | is |
Token ID | 318 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
milo | +6.491 |
Choi | +5.409 |
oried | +5.408 |
── | +5.272 |
Zhang | +5.219 |
Neg logit contributions | |
ONY | -7.841 |
space | -7.016 |
Stall | -6.716 |
satell | -6.632 |
Goth | -6.494 |
Token | this |
Token ID | 428 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
milo | +2.700 |
oried | +2.234 |
Choi | +2.190 |
Kw | +2.116 |
Zhang | +2.110 |
Neg logit contributions | |
ONY | -2.816 |
space | -2.577 |
Stall | -2.408 |
lust | -2.378 |
satell | -2.313 |
Token | young |
Token ID | 1862 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
milo | +2.144 |
oried | +1.783 |
Choi | +1.726 |
bamboo | +1.685 |
Kw | +1.673 |
Neg logit contributions | |
ONY | -2.244 |
space | -2.040 |
Stall | -1.919 |
lust | -1.887 |
Goth | -1.845 |
Token | man |
Token ID | 582 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ONY | +2.663 |
space | +2.419 |
Stall | +2.336 |
Goth | +2.209 |
lust | +2.181 |
Neg logit contributions | |
milo | -3.499 |
oried | -2.987 |
Choi | -2.760 |
arij | -2.703 |
� | -2.699 |
Token | ? |
Token ID | 30 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
milo | +2.041 |
oried | +1.640 |
Choi | +1.571 |
Kw | +1.512 |
bamboo | +1.507 |
Neg logit contributions | |
ONY | -2.811 |
space | -2.590 |
Stall | -2.457 |
lust | -2.413 |
satell | -2.383 |
Token | could |
Token ID | 714 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
milo | +1.282 |
oried | +1.059 |
Choi | +1.000 |
bamboo | +0.976 |
Kw | +0.971 |
Neg logit contributions | |
ONY | -1.487 |
space | -1.364 |
Stall | -1.294 |
lust | -1.259 |
Goth | -1.246 |
Token | impact |
Token ID | 2928 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ONY | +0.788 |
space | +0.721 |
Stall | +0.684 |
lust | +0.660 |
Goth | +0.655 |
Neg logit contributions | |
milo | -0.775 |
oried | -0.638 |
Choi | -0.609 |
bamboo | -0.589 |
Kw | -0.587 |
Token | traditional |
Token ID | 4569 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
milo | +0.383 |
oried | +0.320 |
Choi | +0.304 |
bamboo | +0.297 |
Kw | +0.296 |
Neg logit contributions | |
ONY | -0.387 |
space | -0.354 |
Stall | -0.335 |
lust | -0.325 |
Goth | -0.321 |
Token | cable |
Token ID | 7862 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
milo | +0.505 |
oried | +0.415 |
Choi | +0.392 |
bamboo | +0.381 |
Kw | +0.379 |
Neg logit contributions | |
ONY | -0.583 |
space | -0.536 |
Stall | -0.509 |
lust | -0.495 |
Goth | -0.490 |
Token | providers |
Token ID | 9549 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
milo | +0.555 |
oried | +0.460 |
Choi | +0.435 |
bamboo | +0.424 |
Kw | +0.423 |
Neg logit contributions | |
ONY | -0.635 |
space | -0.582 |
Stall | -0.553 |
lust | -0.537 |
Goth | -0.532 |
Token | , |
Token ID | 11 |
Feature activation | -9.54e+00 |
Pos logit contributions | |
ONY | +0.647 |
space | +0.590 |
Stall | +0.556 |
lust | +0.538 |
Goth | +0.533 |
Neg logit contributions | |
milo | -0.697 |
oried | -0.580 |
Choi | -0.552 |
bamboo | -0.539 |
Kw | -0.537 |
Token | be |
Token ID | 307 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
milo | +5.553 |
oried | +4.637 |
Choi | +4.425 |
Hugo | +4.393 |
Kw | +4.391 |
Neg logit contributions | |
ONY | -7.982 |
space | -7.238 |
Stall | -6.887 |
satell | -6.852 |
lust | -6.731 |
Token | sure |
Token ID | 1654 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ONY | +1.074 |
space | +0.992 |
Stall | +0.940 |
lust | +0.919 |
Goth | +0.915 |
Neg logit contributions | |
milo | -0.875 |
oried | -0.708 |
Choi | -0.668 |
bamboo | -0.648 |
Kw | -0.646 |
Token | to |
Token ID | 284 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ONY | +0.158 |
space | +0.145 |
Stall | +0.137 |
lust | +0.133 |
Goth | +0.132 |
Neg logit contributions | |
milo | -0.145 |
oried | -0.120 |
Choi | -0.114 |
bamboo | -0.111 |
Kw | -0.110 |
Token | read |
Token ID | 1100 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
milo | +2.076 |
oried | +1.737 |
Choi | +1.632 |
bamboo | +1.602 |
Kw | +1.596 |
Neg logit contributions | |
ONY | -2.682 |
space | -2.452 |
Stall | -2.333 |
lust | -2.280 |
satell | -2.272 |
Token | Game |
Token ID | 3776 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
milo | +2.477 |
oried | +2.079 |
Choi | +1.957 |
Kw | +1.920 |
bamboo | +1.901 |
Neg logit contributions | |
ONY | -2.978 |
space | -2.741 |
Stall | -2.575 |
lust | -2.557 |
satell | -2.525 |