Token | in |
Token ID | 287 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
CARD | +4.164 |
infect | +3.493 |
foreskin | +3.232 |
beard | +3.191 |
giving | +3.171 |
Neg logit contributions | |
Seym | -4.893 |
Ham | -4.772 |
Pru | -4.501 |
slam | -4.293 |
encers | -4.279 |
Token | next |
Token ID | 1306 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Ham | +1.700 |
Pru | +1.537 |
Seym | +1.527 |
slam | +1.486 |
Corm | +1.460 |
Neg logit contributions | |
CARD | -2.499 |
infect | -2.173 |
foreskin | -2.089 |
helic | -2.069 |
beard | -2.021 |
Token | week |
Token ID | 1285 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Ham | +1.310 |
Pru | +1.194 |
Seym | +1.192 |
slam | +1.170 |
Corm | +1.152 |
Neg logit contributions | |
CARD | -1.433 |
infect | -1.215 |
foreskin | -1.159 |
helic | -1.150 |
beard | -1.118 |
Token | � |
Token ID | 447 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
Ham | +1.440 |
Seym | +1.292 |
Pru | +1.279 |
slam | +1.234 |
Ryan | +1.223 |
Neg logit contributions | |
CARD | -2.161 |
infect | -1.874 |
foreskin | -1.812 |
helic | -1.798 |
beard | -1.758 |
Token | � |
Token ID | 247 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
CARD | +0.594 |
infect | +0.508 |
foreskin | +0.482 |
helic | +0.474 |
beard | +0.469 |
Neg logit contributions | |
Ham | -0.531 |
Seym | -0.501 |
Pru | -0.490 |
slam | -0.471 |
Corm | -0.471 |
Token | s |
Token ID | 82 |
Feature activation | +2.25e+01 |
Pos logit contributions | |
Ham | +3.206 |
slam | +2.742 |
Pru | +2.739 |
Ryan | +2.727 |
encers | +2.626 |
Neg logit contributions | |
CARD | -4.727 |
infect | -3.978 |
helic | -3.962 |
foreskin | -3.934 |
beard | -3.788 |
Token | post |
Token ID | 1281 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Ham | +4.892 |
slam | +4.737 |
compliment | +4.223 |
abstract | +4.030 |
Ryan | +3.830 |
Neg logit contributions | |
CARD | -24.108 |
Dise | -22.043 |
helic | -21.874 |
infect | -21.333 |
foreskin | -21.051 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
CARD | +0.366 |
infect | +0.312 |
foreskin | +0.296 |
helic | +0.293 |
beard | +0.289 |
Neg logit contributions | |
Ham | -0.297 |
Seym | -0.278 |
Pru | -0.271 |
slam | -0.263 |
Corm | -0.258 |
Token | To |
Token ID | 1675 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
CARD | +0.901 |
infect | +0.772 |
foreskin | +0.739 |
helic | +0.731 |
beard | +0.715 |
Neg logit contributions | |
Ham | -0.713 |
Seym | -0.651 |
Pru | -0.646 |
slam | -0.627 |
Corm | -0.616 |
Token | be |
Token ID | 307 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
CARD | +0.858 |
infect | +0.714 |
foreskin | +0.674 |
helic | +0.662 |
beard | +0.659 |
Neg logit contributions | |
Ham | -0.934 |
Seym | -0.889 |
Pru | -0.864 |
slam | -0.833 |
Corm | -0.829 |
Token | notified |
Token ID | 17600 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Ham | +1.124 |
Pru | +1.006 |
Seym | +0.989 |
slam | +0.959 |
Corm | +0.950 |
Neg logit contributions | |
CARD | -1.978 |
infect | -1.731 |
foreskin | -1.677 |
helic | -1.670 |
beard | -1.634 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
CARD | +4.989 |
infect | +4.152 |
giving | +3.944 |
foreskin | +3.838 |
beard | +3.785 |
Neg logit contributions | |
Seym | -5.704 |
Ham | -5.258 |
Pru | -5.173 |
slam | -4.911 |
ouver | -4.860 |
Token | I |
Token ID | 314 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
CARD | +3.464 |
infect | +2.975 |
foreskin | +2.849 |
helic | +2.833 |
beard | +2.772 |
Neg logit contributions | |
Ham | -2.607 |
Seym | -2.399 |
Pru | -2.374 |
slam | -2.288 |
encers | -2.257 |
Token | 'm |
Token ID | 1101 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Ham | +0.312 |
Seym | +0.282 |
Pru | +0.280 |
slam | +0.270 |
Corm | +0.265 |
Neg logit contributions | |
CARD | -0.480 |
infect | -0.418 |
foreskin | -0.401 |
helic | -0.398 |
beard | -0.390 |
Token | glad |
Token ID | 9675 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
CARD | +3.405 |
infect | +2.896 |
foreskin | +2.761 |
helic | +2.728 |
beard | +2.696 |
Neg logit contributions | |
Ham | -3.302 |
Seym | -3.247 |
Pru | -3.036 |
Corm | -2.951 |
encers | -2.918 |
Token | nan |
Token ID | 15709 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Ham | +3.600 |
Pru | +3.390 |
slam | +3.327 |
Seym | +3.279 |
Corm | +3.216 |
Neg logit contributions | |
CARD | -3.870 |
infect | -3.322 |
foreskin | -3.105 |
helic | -3.064 |
beard | -2.974 |
Token | ocl |
Token ID | 38679 |
Feature activation | +1.96e+01 |
Pos logit contributions | |
Ham | +1.110 |
Pru | +0.930 |
slam | +0.922 |
Seym | +0.907 |
Corm | +0.891 |
Neg logit contributions | |
CARD | -2.535 |
infect | -2.221 |
foreskin | -2.156 |
helic | -2.148 |
beard | -2.111 |
Token | oud |
Token ID | 2778 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
Ham | +4.096 |
oud | +3.681 |
ownt | +3.577 |
ault | +3.048 |
encers | +2.768 |
Neg logit contributions | |
CARD | -23.994 |
helic | -21.704 |
foreskin | -21.011 |
Dise | -20.904 |
scrut | -20.467 |
Token | wasn |
Token ID | 2492 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Ham | +5.743 |
slam | +5.101 |
Ryan | +4.800 |
Pru | +4.789 |
compliment | +4.739 |
Neg logit contributions | |
CARD | -11.418 |
infect | -9.849 |
helic | -9.585 |
Dise | -9.358 |
foreskin | -9.319 |
Token | 't |
Token ID | 470 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Ham | +2.037 |
Pru | +1.776 |
slam | +1.744 |
Ryan | +1.739 |
Corm | +1.717 |
Neg logit contributions | |
CARD | -2.778 |
infect | -2.373 |
helic | -2.337 |
foreskin | -2.311 |
beard | -2.224 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Ham | +0.976 |
Pru | +0.874 |
Seym | +0.853 |
slam | +0.852 |
Corm | +0.837 |
Neg logit contributions | |
CARD | -1.392 |
infect | -1.209 |
foreskin | -1.161 |
helic | -1.154 |
beard | -1.120 |
Token | one |
Token ID | 530 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
CARD | +0.935 |
infect | +0.777 |
foreskin | +0.735 |
helic | +0.720 |
beard | +0.709 |
Neg logit contributions | |
Ham | -1.106 |
Seym | -1.051 |
Pru | -1.026 |
slam | -0.991 |
Corm | -0.986 |
Token | o |
Token ID | 78 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
CARD | +2.214 |
infect | +1.850 |
foreskin | +1.694 |
beard | +1.658 |
giving | +1.635 |
Neg logit contributions | |
Ham | -2.937 |
Seym | -2.908 |
Pru | -2.771 |
slam | -2.693 |
Corm | -2.670 |
Token | by |
Token ID | 416 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
Ham | +3.422 |
Pru | +3.120 |
Seym | +3.098 |
slam | +3.055 |
Corm | +2.970 |
Neg logit contributions | |
CARD | -4.659 |
infect | -4.056 |
foreskin | -3.877 |
helic | -3.845 |
beard | -3.733 |
Token | Sing |
Token ID | 5573 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
Ham | +3.056 |
Seym | +2.777 |
Pru | +2.756 |
slam | +2.682 |
Corm | +2.649 |
Neg logit contributions | |
CARD | -4.025 |
infect | -3.525 |
foreskin | -3.361 |
helic | -3.316 |
beard | -3.229 |
Token | , |
Token ID | 11 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
CARD | +3.592 |
infect | +3.069 |
foreskin | +2.896 |
helic | +2.878 |
beard | +2.833 |
Neg logit contributions | |
Ham | -3.120 |
Seym | -2.918 |
Pru | -2.884 |
slam | -2.794 |
Corm | -2.744 |
Token | Bird |
Token ID | 14506 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
CARD | +3.757 |
infect | +2.816 |
foreskin | +2.632 |
beard | +2.607 |
helic | +2.460 |
Neg logit contributions | |
Ham | -6.426 |
Seym | -6.323 |
Pru | -6.055 |
slam | -6.004 |
ouver | -5.950 |
Token | of |
Token ID | 286 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
Ham | +1.075 |
Seym | +0.973 |
Pru | +0.964 |
slam | +0.937 |
Corm | +0.923 |
Neg logit contributions | |
CARD | -1.490 |
infect | -1.293 |
foreskin | -1.238 |
helic | -1.227 |
beard | -1.198 |
Token | Pre |
Token ID | 3771 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
Ham | +5.924 |
Pru | +5.641 |
Corm | +5.217 |
Payne | +4.352 |
Painting | +4.328 |
Neg logit contributions | |
CARD | -19.140 |
helic | -17.937 |
infect | -17.746 |
scrut | -17.494 |
anwhile | -16.812 |
Token | y |
Token ID | 88 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Ham | +2.496 |
Pru | +2.234 |
slam | +2.215 |
Ryan | +2.173 |
Seym | +2.150 |
Neg logit contributions | |
CARD | -2.358 |
helic | -1.934 |
infect | -1.933 |
foreskin | -1.867 |
beard | -1.777 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Ham | +2.171 |
Seym | +1.968 |
Pru | +1.965 |
slam | +1.908 |
Corm | +1.876 |
Neg logit contributions | |
CARD | -2.895 |
infect | -2.515 |
foreskin | -2.405 |
helic | -2.384 |
beard | -2.320 |
Token |
|
Token ID | 198 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
Ham | +1.379 |
Pru | +1.217 |
slam | +1.181 |
Seym | +1.170 |
Corm | +1.166 |
Neg logit contributions | |
CARD | -2.045 |
infect | -1.779 |
helic | -1.719 |
foreskin | -1.717 |
beard | -1.663 |
Token | https |
Token ID | 5450 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Ham | +3.345 |
Pru | +2.870 |
Ryan | +2.855 |
Seym | +2.841 |
slam | +2.806 |
Neg logit contributions | |
CARD | -4.742 |
infect | -4.048 |
foreskin | -3.998 |
helic | -3.969 |
beard | -3.848 |
Token | all |
Token ID | 477 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
Ham | +4.012 |
Pru | +3.629 |
Seym | +3.609 |
slam | +3.526 |
Corm | +3.466 |
Neg logit contributions | |
CARD | -6.008 |
infect | -5.262 |
foreskin | -4.970 |
helic | -4.908 |
beard | -4.825 |
Token | nuclear |
Token ID | 4523 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
Ham | +2.222 |
Seym | +2.024 |
Pru | +2.014 |
slam | +1.950 |
Corm | +1.920 |
Neg logit contributions | |
CARD | -2.983 |
infect | -2.579 |
foreskin | -2.464 |
helic | -2.436 |
beard | -2.390 |
Token | powered |
Token ID | 13232 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
Ham | +3.619 |
Pru | +3.304 |
Seym | +3.293 |
slam | +3.235 |
Corm | +3.162 |
Neg logit contributions | |
CARD | -4.633 |
infect | -3.976 |
foreskin | -3.800 |
helic | -3.739 |
beard | -3.691 |
Token | ( |
Token ID | 357 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Ham | +3.906 |
Pru | +3.532 |
Seym | +3.526 |
slam | +3.436 |
Corm | +3.398 |
Neg logit contributions | |
CARD | -5.497 |
infect | -4.794 |
foreskin | -4.577 |
helic | -4.462 |
beard | -4.425 |
Token | 4 |
Token ID | 19 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Ham | +1.571 |
Seym | +1.420 |
Pru | +1.409 |
slam | +1.360 |
Corm | +1.338 |
Neg logit contributions | |
CARD | -2.270 |
infect | -1.966 |
foreskin | -1.890 |
helic | -1.871 |
beard | -1.834 |
Token | SS |
Token ID | 6723 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
Ham | +2.419 |
Seym | +2.197 |
Pru | +2.184 |
slam | +2.112 |
Corm | +2.090 |
Neg logit contributions | |
CARD | -3.305 |
infect | -2.865 |
foreskin | -2.742 |
helic | -2.704 |
beard | -2.657 |
Token | BN |
Token ID | 15766 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
Ham | +8.098 |
Ns | +7.768 |
Pru | +7.114 |
Seym | +6.796 |
Corm | +6.668 |
Neg logit contributions | |
CARD | -17.062 |
infect | -15.108 |
foreskin | -14.537 |
beard | -14.073 |
giving | -13.945 |
Token | , |
Token ID | 11 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
Ham | +6.454 |
Pru | +5.835 |
Seym | +5.817 |
slam | +5.680 |
Corm | +5.642 |
Neg logit contributions | |
CARD | -9.892 |
infect | -8.677 |
foreskin | -8.226 |
helic | -8.025 |
beard | -8.017 |
Token | 8 |
Token ID | 807 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
Ham | +3.032 |
Pru | +2.721 |
Seym | +2.707 |
slam | +2.627 |
Corm | +2.576 |
Neg logit contributions | |
CARD | -5.028 |
infect | -4.431 |
foreskin | -4.227 |
helic | -4.180 |
beard | -4.108 |
Token | SS |
Token ID | 6723 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Ham | +4.156 |
Seym | +3.790 |
Pru | +3.783 |
slam | +3.653 |
Corm | +3.650 |
Neg logit contributions | |
CARD | -5.332 |
infect | -4.659 |
foreskin | -4.434 |
helic | -4.334 |
beard | -4.281 |
Token | N |
Token ID | 45 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
Ham | +7.221 |
Ns | +6.401 |
Pru | +6.316 |
Seym | +6.283 |
Corm | +6.058 |
Neg logit contributions | |
CARD | -12.325 |
infect | -10.792 |
foreskin | -10.367 |
beard | -10.014 |
helic | -9.876 |
Token | � |
Token ID | 250 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
CARD | +0.470 |
infect | +0.407 |
foreskin | +0.390 |
helic | +0.385 |
beard | +0.379 |
Neg logit contributions | |
Ham | -0.337 |
Seym | -0.308 |
Pru | -0.304 |
slam | -0.294 |
Corm | -0.290 |
Token | We |
Token ID | 1135 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
Ham | +0.718 |
Seym | +0.660 |
Pru | +0.654 |
slam | +0.633 |
Corm | +0.622 |
Neg logit contributions | |
CARD | -0.928 |
infect | -0.799 |
foreskin | -0.763 |
helic | -0.755 |
beard | -0.740 |
Token | must |
Token ID | 1276 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
CARD | +4.290 |
infect | +3.667 |
foreskin | +3.415 |
helic | +3.411 |
beard | +3.372 |
Neg logit contributions | |
Ham | -4.118 |
Seym | -3.944 |
Pru | -3.833 |
Corm | -3.633 |
ouver | -3.565 |
Token | commit |
Token ID | 4589 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
Ham | +3.176 |
slam | +2.882 |
Pru | +2.841 |
Seym | +2.779 |
Corm | +2.711 |
Neg logit contributions | |
CARD | -4.714 |
infect | -4.053 |
foreskin | -3.910 |
helic | -3.855 |
beard | -3.766 |
Token | ourselves |
Token ID | 6731 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
Ham | +4.273 |
Pru | +3.928 |
Seym | +3.904 |
slam | +3.823 |
Ryan | +3.732 |
Neg logit contributions | |
CARD | -5.613 |
infect | -4.806 |
foreskin | -4.539 |
helic | -4.492 |
beard | -4.382 |
Token | very |
Token ID | 845 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
Ham | +7.708 |
slam | +7.178 |
Pru | +7.037 |
Ryan | +6.698 |
Corm | +6.653 |
Neg logit contributions | |
CARD | -14.324 |
infect | -12.429 |
foreskin | -11.911 |
helic | -11.725 |
Dise | -11.629 |
Token | res |
Token ID | 581 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
Ham | +4.267 |
slam | +4.072 |
Pru | +4.066 |
Corm | +3.327 |
Ryan | +3.300 |
Neg logit contributions | |
CARD | -20.527 |
infect | -18.152 |
Dise | -17.993 |
foreskin | -17.339 |
helic | -17.225 |
Token | olutely |
Token ID | 16780 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
Ham | +4.010 |
Pru | +3.757 |
slam | +3.710 |
Seym | +3.648 |
Corm | +3.646 |
Neg logit contributions | |
CARD | -2.471 |
infect | -1.891 |
foreskin | -1.818 |
helic | -1.764 |
beard | -1.656 |
Token | because |
Token ID | 780 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
Ham | +2.267 |
Seym | +1.994 |
Pru | +1.992 |
slam | +1.943 |
Corm | +1.891 |
Neg logit contributions | |
CARD | -4.245 |
infect | -3.739 |
foreskin | -3.613 |
helic | -3.579 |
beard | -3.485 |
Token | there |
Token ID | 612 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
Ham | +3.049 |
Pru | +2.698 |
Seym | +2.689 |
slam | +2.631 |
Corm | +2.562 |
Neg logit contributions | |
CARD | -5.558 |
infect | -4.877 |
foreskin | -4.733 |
helic | -4.672 |
beard | -4.554 |
Token | isn |
Token ID | 2125 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
Ham | +6.136 |
Pru | +5.429 |
slam | +5.367 |
Corm | +5.272 |
Ryan | +5.249 |
Neg logit contributions | |
CARD | -10.705 |
infect | -9.285 |
foreskin | -9.044 |
helic | -8.947 |
Dise | -8.706 |
Token | ten |
Token ID | 3478 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
Ham | +2.790 |
Seym | +2.527 |
Pru | +2.524 |
slam | +2.451 |
Corm | +2.412 |
Neg logit contributions | |
CARD | -3.902 |
infect | -3.394 |
foreskin | -3.234 |
helic | -3.195 |
beard | -3.137 |
Token | nuclear |
Token ID | 4523 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Ham | +5.435 |
Pru | +4.901 |
Seym | +4.855 |
slam | +4.840 |
Corm | +4.789 |
Neg logit contributions | |
CARD | -7.900 |
infect | -6.914 |
foreskin | -6.602 |
helic | -6.447 |
beard | -6.401 |
Token | submarines |
Token ID | 34031 |
Feature activation | +9.90e+00 |
Pos logit contributions | |
Ham | +2.058 |
Seym | +1.869 |
Pru | +1.862 |
slam | +1.823 |
Corm | +1.786 |
Neg logit contributions | |
CARD | -2.651 |
infect | -2.281 |
foreskin | -2.178 |
helic | -2.144 |
beard | -2.117 |
Token | ( |
Token ID | 357 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Ham | +5.926 |
Pru | +5.362 |
slam | +5.331 |
Seym | +5.207 |
Corm | +5.183 |
Neg logit contributions | |
CARD | -8.927 |
infect | -7.817 |
foreskin | -7.435 |
helic | -7.322 |
beard | -7.238 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Ham | +1.120 |
Seym | +1.008 |
Pru | +0.998 |
slam | +0.959 |
Corm | +0.941 |
Neg logit contributions | |
CARD | -1.943 |
infect | -1.704 |
foreskin | -1.637 |
helic | -1.624 |
beard | -1.594 |
Token | SS |
Token ID | 6723 |
Feature activation | +1.78e+01 |
Pos logit contributions | |
Ham | +0.937 |
Seym | +0.861 |
Pru | +0.854 |
slam | +0.828 |
Corm | +0.813 |
Neg logit contributions | |
CARD | -1.107 |
infect | -0.946 |
foreskin | -0.903 |
helic | -0.897 |
beard | -0.874 |
Token | BN |
Token ID | 15766 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Ham | +7.900 |
Ns | +7.650 |
Pru | +6.832 |
Seym | +6.700 |
Corm | +6.556 |
Neg logit contributions | |
CARD | -16.999 |
infect | -15.017 |
foreskin | -14.622 |
beard | -14.117 |
giving | -14.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Ham | +6.369 |
Seym | +5.776 |
Pru | +5.745 |
Corm | +5.665 |
slam | +5.646 |
Neg logit contributions | |
CARD | -9.330 |
infect | -8.160 |
foreskin | -7.764 |
beard | -7.569 |
giving | -7.498 |
Token | 6 |
Token ID | 718 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
Ham | +1.676 |
Seym | +1.517 |
Pru | +1.506 |
slam | +1.453 |
Corm | +1.428 |
Neg logit contributions | |
CARD | -2.550 |
infect | -2.221 |
foreskin | -2.130 |
helic | -2.110 |
beard | -2.070 |
Token | Rub |
Token ID | 6256 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
Ham | +3.036 |
Seym | +2.736 |
Pru | +2.717 |
slam | +2.615 |
Corm | +2.605 |
Neg logit contributions | |
CARD | -4.937 |
infect | -4.335 |
foreskin | -4.168 |
helic | -4.087 |
beard | -4.048 |
Token | is |
Token ID | 271 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Ham | +0.624 |
Seym | +0.571 |
Pru | +0.566 |
slam | +0.546 |
Corm | +0.537 |
Neg logit contributions | |
CARD | -0.863 |
infect | -0.747 |
foreskin | -0.713 |
helic | -0.708 |
beard | -0.693 |
Token | CPU |
Token ID | 9135 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
CARD | +0.827 |
infect | +0.704 |
foreskin | +0.672 |
helic | +0.667 |
beard | +0.652 |
Neg logit contributions | |
Ham | -0.677 |
Seym | -0.624 |
Pru | -0.614 |
slam | -0.596 |
Corm | -0.585 |
Token | ( |
Token ID | 7 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
Ham | +4.551 |
Pru | +3.859 |
Ryan | +3.761 |
Corm | +3.745 |
slam | +3.693 |
Neg logit contributions | |
CARD | -7.596 |
infect | -6.822 |
foreskin | -6.658 |
helic | -6.628 |
beard | -6.464 |
Token | ns |
Token ID | 5907 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Ham | +5.396 |
Ns | +4.698 |
Pru | +4.689 |
Ryan | +4.686 |
slam | +4.658 |
Neg logit contributions | |
CARD | -6.895 |
helic | -5.595 |
foreskin | -5.568 |
infect | -5.545 |
Dise | -5.333 |
Token | ) |
Token ID | 8 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
Ham | +0.514 |
Seym | +0.468 |
Pru | +0.467 |
slam | +0.454 |
Corm | +0.447 |
Neg logit contributions | |
CARD | -0.588 |
infect | -0.502 |
foreskin | -0.479 |
helic | -0.476 |
beard | -0.464 |
Token | Mem |
Token ID | 4942 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
Ham | +0.060 |
Seym | +0.055 |
Pru | +0.054 |
slam | +0.052 |
Corm | +0.051 |
Neg logit contributions | |
CARD | -0.084 |
infect | -0.072 |
foreskin | -0.069 |
helic | -0.069 |
beard | -0.067 |
Token | c |
Token ID | 66 |
Feature activation | +1.77e+01 |
Pos logit contributions | |
Ham | +2.670 |
Pru | +2.218 |
slam | +2.206 |
Ryan | +2.182 |
Corm | +2.160 |
Neg logit contributions | |
CARD | -5.339 |
infect | -4.668 |
foreskin | -4.640 |
helic | -4.609 |
beard | -4.474 |
Token | py |
Token ID | 9078 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
Ham | +3.812 |
Ryan | +2.357 |
7601 | +2.260 |
mine | +2.246 |
cv | +2.140 |
Neg logit contributions | |
CARD | -21.621 |
helic | -20.517 |
foreskin | -19.464 |
beard | -19.099 |
Dise | -19.065 |
Token | In |
Token ID | 818 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Ham | +3.900 |
Pru | +3.290 |
Ryan | +3.277 |
Seym | +3.177 |
Sent | +3.168 |
Neg logit contributions | |
CARD | -6.072 |
infect | -5.246 |
foreskin | -5.186 |
helic | -5.127 |
beard | -5.080 |
Token | Memory |
Token ID | 30871 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Ham | +1.019 |
Pru | +0.864 |
Seym | +0.856 |
slam | +0.826 |
Ryan | +0.818 |
Neg logit contributions | |
CARD | -2.114 |
infect | -1.867 |
foreskin | -1.814 |
helic | -1.807 |
beard | -1.770 |
Token | 4 |
Token ID | 604 |
Feature activation | -9.29e+00 |
Pos logit contributions | |
CARD | +0.692 |
infect | +0.594 |
foreskin | +0.570 |
helic | +0.564 |
beard | +0.555 |
Neg logit contributions | |
Ham | -0.479 |
Seym | -0.438 |
Pru | -0.432 |
slam | -0.418 |
Corm | -0.410 |
Token | 66 |
Token ID | 2791 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
CARD | +6.933 |
infect | +5.755 |
beard | +5.369 |
foreskin | +5.369 |
giving | +5.220 |
Neg logit contributions | |
Seym | -6.863 |
Ham | -6.823 |
Pru | -6.582 |
Corm | -6.306 |
ouver | -6.218 |
Token | LP |
Token ID | 18470 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
Ham | +2.402 |
Pru | +2.167 |
Seym | +2.153 |
slam | +2.116 |
Corm | +2.052 |
Neg logit contributions | |
CARD | -3.628 |
infect | -3.165 |
foreskin | -3.030 |
helic | -3.012 |
beard | -2.929 |
Token | for |
Token ID | 329 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
Ham | +2.787 |
Pru | +2.530 |
Seym | +2.516 |
slam | +2.472 |
Corm | +2.417 |
Neg logit contributions | |
CARD | -3.667 |
infect | -3.165 |
foreskin | -3.041 |
helic | -3.020 |
beard | -2.932 |
Token | Sing |
Token ID | 5573 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Ham | +2.600 |
Pru | +2.352 |
Seym | +2.350 |
slam | +2.285 |
Corm | +2.244 |
Neg logit contributions | |
CARD | -3.668 |
infect | -3.200 |
foreskin | -3.060 |
helic | -3.030 |
beard | -2.953 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
CARD | +0.973 |
infect | +0.835 |
foreskin | +0.796 |
helic | +0.790 |
beard | +0.773 |
Neg logit contributions | |
Ham | -0.785 |
Seym | -0.722 |
Pru | -0.714 |
slam | -0.693 |
Corm | -0.681 |
Token | Bird |
Token ID | 14506 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
CARD | +1.597 |
infect | +1.289 |
foreskin | +1.208 |
helic | +1.185 |
beard | +1.163 |
Neg logit contributions | |
Ham | -2.262 |
Seym | -2.118 |
Pru | -2.101 |
slam | -2.060 |
Corm | -2.027 |
Token | of |
Token ID | 286 |
Feature activation | +1.76e+01 |
Pos logit contributions | |
Ham | +2.393 |
Seym | +2.140 |
Pru | +2.136 |
slam | +2.079 |
Corm | +2.052 |
Neg logit contributions | |
CARD | -3.565 |
infect | -3.111 |
foreskin | -2.984 |
helic | -2.953 |
beard | -2.874 |
Token | Pre |
Token ID | 3771 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Pru | +5.703 |
Ham | +5.605 |
Corm | +5.145 |
Payne | +4.247 |
Painting | +4.205 |
Neg logit contributions | |
CARD | -18.119 |
helic | -16.766 |
infect | -16.579 |
scrut | -16.132 |
beard | -15.690 |
Token | y |
Token ID | 88 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Ham | +3.713 |
Pru | +3.289 |
slam | +3.284 |
Ryan | +3.220 |
ownt | +3.178 |
Neg logit contributions | |
CARD | -3.795 |
helic | -3.184 |
infect | -3.095 |
foreskin | -3.018 |
beard | -2.869 |
Token | ." |
Token ID | 526 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Ham | +2.005 |
Seym | +1.819 |
Pru | +1.817 |
slam | +1.764 |
Corm | +1.737 |
Neg logit contributions | |
CARD | -2.537 |
infect | -2.189 |
foreskin | -2.092 |
helic | -2.073 |
beard | -2.019 |
Token | " |
Token ID | 366 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
Ham | +1.536 |
Seym | +1.387 |
Pru | +1.377 |
slam | +1.335 |
Corm | +1.316 |
Neg logit contributions | |
CARD | -2.218 |
infect | -1.940 |
foreskin | -1.861 |
helic | -1.845 |
beard | -1.798 |
Token | Rating |
Token ID | 29321 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Ham | +3.324 |
Pru | +2.907 |
Seym | +2.886 |
Ryan | +2.835 |
slam | +2.812 |
Neg logit contributions | |
CARD | -4.580 |
infect | -3.957 |
foreskin | -3.860 |
helic | -3.811 |
beard | -3.717 |
Token | be |
Token ID | 307 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
CARD | +0.177 |
infect | +0.150 |
foreskin | +0.143 |
helic | +0.141 |
beard | +0.138 |
Neg logit contributions | |
Ham | -0.164 |
Seym | -0.152 |
Pru | -0.150 |
slam | -0.145 |
Corm | -0.144 |
Token | misinterpret |
Token ID | 40882 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
CARD | +2.194 |
infect | +1.874 |
foreskin | +1.798 |
helic | +1.754 |
beard | +1.737 |
Neg logit contributions | |
Ham | -2.045 |
Seym | -1.907 |
Pru | -1.860 |
slam | -1.787 |
Corm | -1.783 |
Token | ed |
Token ID | 276 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
CARD | +2.552 |
infect | +2.136 |
foreskin | +1.966 |
helic | +1.941 |
beard | +1.929 |
Neg logit contributions | |
Ham | -3.379 |
Seym | -3.215 |
Pru | -3.157 |
slam | -3.057 |
Corm | -3.028 |
Token | , |
Token ID | 11 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Ham | +0.131 |
Seym | +0.120 |
Pru | +0.119 |
slam | +0.115 |
Corm | +0.114 |
Neg logit contributions | |
CARD | -0.162 |
infect | -0.139 |
foreskin | -0.133 |
helic | -0.131 |
beard | -0.128 |
Token | I |
Token ID | 314 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
CARD | +0.407 |
infect | +0.351 |
foreskin | +0.337 |
helic | +0.332 |
beard | +0.328 |
Neg logit contributions | |
Ham | -0.302 |
Seym | -0.277 |
Pru | -0.272 |
slam | -0.262 |
Corm | -0.259 |
Token | take |
Token ID | 1011 |
Feature activation | +1.76e+01 |
Pos logit contributions | |
Ham | +3.599 |
slam | +3.346 |
Pru | +3.272 |
Seym | +3.151 |
Corm | +3.150 |
Neg logit contributions | |
CARD | -4.929 |
infect | -4.288 |
foreskin | -4.026 |
helic | -4.025 |
beard | -3.870 |
Token | full |
Token ID | 1336 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
Ham | +8.435 |
slam | +8.226 |
Pru | +8.086 |
Corm | +7.948 |
compliment | +7.780 |
Neg logit contributions | |
CARD | -15.303 |
infect | -14.068 |
Dise | -12.868 |
helic | -12.653 |
foreskin | -12.398 |
Token | responsibility |
Token ID | 5798 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
Ham | +3.198 |
Pru | +2.902 |
slam | +2.835 |
Corm | +2.728 |
compliment | +2.715 |
Neg logit contributions | |
CARD | -6.838 |
infect | -6.070 |
foreskin | -5.722 |
helic | -5.702 |
Dise | -5.577 |
Token | and |
Token ID | 290 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
Ham | +3.314 |
Pru | +2.943 |
Seym | +2.910 |
slam | +2.907 |
Corm | +2.855 |
Neg logit contributions | |
CARD | -5.314 |
infect | -4.642 |
helic | -4.449 |
foreskin | -4.425 |
beard | -4.299 |
Token | regret |
Token ID | 13721 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Ham | +2.776 |
Pru | +2.551 |
Seym | +2.517 |
slam | +2.514 |
Corm | +2.425 |
Neg logit contributions | |
CARD | -3.816 |
infect | -3.303 |
foreskin | -3.126 |
helic | -3.104 |
beard | -3.028 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Ham | +2.542 |
Pru | +2.302 |
Seym | +2.273 |
slam | +2.236 |
Corm | +2.198 |
Neg logit contributions | |
CARD | -3.457 |
infect | -2.991 |
foreskin | -2.844 |
helic | -2.833 |
beard | -2.766 |
Token | . |
Token ID | 13 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
Ham | +0.444 |
Seym | +0.404 |
Pru | +0.401 |
slam | +0.387 |
Corm | +0.381 |
Neg logit contributions | |
CARD | -0.628 |
infect | -0.544 |
foreskin | -0.521 |
helic | -0.517 |
beard | -0.506 |
Token | Dinosaur |
Token ID | 47808 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Ham | +3.760 |
Pru | +3.414 |
Seym | +3.327 |
Corm | +3.277 |
slam | +3.222 |
Neg logit contributions | |
CARD | -5.235 |
infect | -4.604 |
foreskin | -4.408 |
helic | -4.400 |
beard | -4.290 |
Token | bones |
Token ID | 11945 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
CARD | +0.926 |
infect | +0.778 |
foreskin | +0.741 |
helic | +0.730 |
beard | +0.717 |
Neg logit contributions | |
Ham | -0.979 |
Seym | -0.913 |
Pru | -0.902 |
slam | -0.871 |
Corm | -0.862 |
Token | with |
Token ID | 351 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Ham | +0.680 |
Seym | +0.622 |
Pru | +0.618 |
slam | +0.600 |
Corm | +0.590 |
Neg logit contributions | |
CARD | -0.842 |
infect | -0.723 |
foreskin | -0.690 |
helic | -0.683 |
beard | -0.668 |
Token | Carbon |
Token ID | 23699 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
CARD | +1.004 |
infect | +0.862 |
foreskin | +0.834 |
helic | +0.827 |
beard | +0.810 |
Neg logit contributions | |
Ham | -0.800 |
Seym | -0.731 |
Pru | -0.718 |
slam | -0.692 |
Ryan | -0.686 |
Token | - |
Token ID | 12 |
Feature activation | +1.74e+01 |
Pos logit contributions | |
Ham | +5.321 |
Seym | +4.857 |
Pru | +4.800 |
slam | +4.649 |
Corm | +4.641 |
Neg logit contributions | |
CARD | -6.717 |
infect | -5.789 |
foreskin | -5.584 |
helic | -5.340 |
beard | -5.310 |
Token | 14 |
Token ID | 1415 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Ham | +6.319 |
Ryan | +4.673 |
Seym | +4.368 |
Sent | +4.236 |
Sham | +4.066 |
Neg logit contributions | |
CARD | -18.930 |
foreskin | -16.722 |
beard | -16.029 |
infect | -15.970 |
helic | -15.564 |
Token | dates |
Token ID | 9667 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
Ham | +0.276 |
Seym | +0.252 |
Pru | +0.250 |
slam | +0.241 |
Corm | +0.238 |
Neg logit contributions | |
CARD | -0.351 |
infect | -0.302 |
foreskin | -0.289 |
helic | -0.287 |
beard | -0.281 |
Token | in |
Token ID | 287 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
CARD | +0.294 |
infect | +0.251 |
foreskin | +0.240 |
helic | +0.238 |
beard | +0.233 |
Neg logit contributions | |
Ham | -0.255 |
Seym | -0.235 |
Pru | -0.233 |
slam | -0.225 |
Corm | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
CARD | +4.927 |
infect | +4.198 |
foreskin | +4.114 |
helic | +4.031 |
beard | +4.012 |
Neg logit contributions | |
Ham | -4.278 |
Seym | -3.911 |
Pru | -3.763 |
encers | -3.699 |
Ryan | -3.653 |
Token | range |
Token ID | 2837 |
Feature activation | -8.24e+00 |
Pos logit contributions | |
CARD | +3.620 |
infect | +3.050 |
foreskin | +2.988 |
helic | +2.934 |
beard | +2.913 |
Neg logit contributions | |
Ham | -3.140 |
Seym | -2.845 |
Pru | -2.792 |
encers | -2.718 |
ouver | -2.717 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
CARD | +0.662 |
infect | +0.564 |
foreskin | +0.542 |
helic | +0.538 |
beard | +0.526 |
Neg logit contributions | |
Ham | -0.560 |
Seym | -0.519 |
Pru | -0.511 |
slam | -0.490 |
Corm | -0.487 |
Token | The |
Token ID | 383 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Ham | +1.902 |
Pru | +1.726 |
Seym | +1.722 |
slam | +1.662 |
Corm | +1.650 |
Neg logit contributions | |
CARD | -2.584 |
infect | -2.242 |
foreskin | -2.144 |
helic | -2.126 |
beard | -2.080 |
Token | data |
Token ID | 1366 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
Ham | +0.746 |
Seym | +0.683 |
Pru | +0.678 |
slam | +0.658 |
Corm | +0.648 |
Neg logit contributions | |
CARD | -0.923 |
infect | -0.793 |
foreskin | -0.757 |
helic | -0.750 |
beard | -0.733 |
Token | : |
Token ID | 25 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
CARD | +3.871 |
infect | +3.273 |
foreskin | +3.200 |
helic | +3.145 |
beard | +3.071 |
Neg logit contributions | |
Ham | -3.421 |
Seym | -3.219 |
Pru | -3.082 |
Ryan | -2.964 |
slam | -2.954 |
Token | Carbon |
Token ID | 23699 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
Ham | +1.857 |
Seym | +1.692 |
Pru | +1.683 |
slam | +1.629 |
Corm | +1.609 |
Neg logit contributions | |
CARD | -2.436 |
infect | -2.103 |
foreskin | -2.007 |
helic | -1.989 |
beard | -1.943 |
Token | - |
Token ID | 12 |
Feature activation | +1.73e+01 |
Pos logit contributions | |
Ham | +6.855 |
Seym | +6.087 |
slam | +5.917 |
Corm | +5.896 |
Pru | +5.884 |
Neg logit contributions | |
CARD | -9.563 |
infect | -8.350 |
foreskin | -8.044 |
helic | -7.669 |
beard | -7.574 |
Token | 14 |
Token ID | 1415 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
Ham | +5.835 |
Ryan | +4.221 |
Sent | +3.696 |
Sham | +3.620 |
Scale | +3.610 |
Neg logit contributions | |
CARD | -19.310 |
foreskin | -17.101 |
beard | -16.515 |
helic | -16.379 |
infect | -16.349 |
Token | in |
Token ID | 287 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Ham | +2.994 |
Seym | +2.696 |
Pru | +2.683 |
slam | +2.631 |
Corm | +2.595 |
Neg logit contributions | |
CARD | -4.245 |
infect | -3.694 |
foreskin | -3.537 |
helic | -3.472 |
beard | -3.393 |
Token | dinosaur |
Token ID | 28257 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
Ham | +1.083 |
Seym | +0.992 |
Pru | +0.985 |
slam | +0.955 |
Corm | +0.940 |
Neg logit contributions | |
CARD | -1.338 |
infect | -1.149 |
foreskin | -1.097 |
helic | -1.086 |
beard | -1.062 |
Token | bones |
Token ID | 11945 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
Ham | +0.793 |
Seym | +0.735 |
Pru | +0.730 |
slam | +0.711 |
Corm | +0.701 |
Neg logit contributions | |
CARD | -0.737 |
infect | -0.617 |
foreskin | -0.585 |
helic | -0.578 |
beard | -0.563 |
Token | ( |
Token ID | 357 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
Ham | +4.367 |
Pru | +3.996 |
Seym | +3.942 |
slam | +3.895 |
Corm | +3.847 |
Neg logit contributions | |
CARD | -5.680 |
infect | -4.969 |
foreskin | -4.709 |
helic | -4.647 |
beard | -4.536 |
Token | the |
Token ID | 262 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
Ham | +2.567 |
Pru | +2.329 |
Seym | +2.283 |
slam | +2.263 |
Corm | +2.214 |
Neg logit contributions | |
CARD | -3.856 |
infect | -3.388 |
foreskin | -3.191 |
helic | -3.188 |
beard | -3.101 |
Token | so |
Token ID | 523 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Ham | +3.209 |
Pru | +2.928 |
Seym | +2.875 |
slam | +2.855 |
Corm | +2.795 |
Neg logit contributions | |
CARD | -4.316 |
infect | -3.782 |
helic | -3.557 |
foreskin | -3.552 |
beard | -3.442 |
Token | - |
Token ID | 12 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
CARD | +0.681 |
infect | +0.579 |
foreskin | +0.551 |
helic | +0.542 |
beard | +0.535 |
Neg logit contributions | |
Ham | -0.644 |
Seym | -0.606 |
Pru | -0.591 |
slam | -0.573 |
Corm | -0.566 |
Token | called |
Token ID | 7174 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
Ham | +1.179 |
Pru | +1.059 |
Seym | +1.057 |
slam | +1.029 |
Corm | +1.014 |
Neg logit contributions | |
CARD | -1.466 |
infect | -1.251 |
foreskin | -1.205 |
helic | -1.193 |
beard | -1.166 |
Token | white |
Token ID | 2330 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
Ham | +2.891 |
Pru | +2.611 |
Seym | +2.588 |
slam | +2.556 |
Corm | +2.483 |
Neg logit contributions | |
CARD | -4.194 |
infect | -3.689 |
helic | -3.472 |
foreskin | -3.466 |
beard | -3.358 |
Token | - |
Token ID | 12 |
Feature activation | +1.71e+01 |
Pos logit contributions | |
Ham | +7.844 |
slam | +7.452 |
Corm | +7.215 |
Pru | +7.211 |
Seym | +7.023 |
Neg logit contributions | |
CARD | -11.718 |
infect | -10.283 |
Dise | -9.295 |
helic | -9.202 |
giving | -9.175 |
Token | collar |
Token ID | 37676 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Ham | +7.921 |
Ryan | +6.500 |
mine | +6.470 |
ault | +6.432 |
ownt | +6.421 |
Neg logit contributions | |
CARD | -16.287 |
helic | -13.801 |
Dise | -13.630 |
foreskin | -13.612 |
beard | -13.246 |
Token | jobs |
Token ID | 3946 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
CARD | +2.061 |
infect | +1.782 |
foreskin | +1.733 |
helic | +1.719 |
beard | +1.699 |
Neg logit contributions | |
Ham | -1.317 |
Seym | -1.206 |
Pru | -1.180 |
slam | -1.122 |
Corm | -1.105 |
Token | of |
Token ID | 286 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Ham | +0.677 |
Seym | +0.620 |
Pru | +0.615 |
slam | +0.596 |
Corm | +0.587 |
Neg logit contributions | |
CARD | -0.836 |
infect | -0.718 |
foreskin | -0.686 |
helic | -0.679 |
beard | -0.664 |
Token | managers |
Token ID | 11663 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Ham | +1.386 |
Seym | +1.257 |
Pru | +1.254 |
slam | +1.214 |
Corm | +1.195 |
Neg logit contributions | |
CARD | -1.912 |
infect | -1.660 |
foreskin | -1.581 |
helic | -1.570 |
beard | -1.533 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Ham | +1.322 |
Seym | +1.204 |
Pru | +1.201 |
slam | +1.160 |
Corm | +1.143 |
Neg logit contributions | |
CARD | -1.689 |
infect | -1.454 |
foreskin | -1.390 |
helic | -1.376 |
beard | -1.345 |
Token | c |
Token ID | 66 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Ham | +2.584 |
Pru | +2.289 |
Seym | +2.267 |
slam | +2.241 |
Corm | +2.182 |
Neg logit contributions | |
CARD | -4.580 |
infect | -4.014 |
foreskin | -3.868 |
helic | -3.825 |
beard | -3.744 |
Token | , |
Token ID | 11 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
Ham | +3.461 |
Seym | +3.156 |
Pru | +3.135 |
slam | +3.054 |
Corm | +2.997 |
Neg logit contributions | |
CARD | -4.565 |
infect | -3.973 |
foreskin | -3.757 |
helic | -3.733 |
beard | -3.628 |
Token | d |
Token ID | 67 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
CARD | +2.683 |
infect | +2.305 |
foreskin | +2.148 |
helic | +2.113 |
beard | +2.084 |
Neg logit contributions | |
Ham | -2.825 |
Seym | -2.662 |
Pru | -2.630 |
slam | -2.548 |
Corm | -2.511 |
Token | ) |
Token ID | 8 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Ham | +0.368 |
Seym | +0.337 |
Pru | +0.335 |
slam | +0.325 |
Corm | +0.320 |
Neg logit contributions | |
CARD | -0.434 |
infect | -0.371 |
foreskin | -0.354 |
helic | -0.351 |
beard | -0.343 |
Token | C |
Token ID | 327 |
Feature activation | +8.59e+00 |
Pos logit contributions | |
Ham | +0.320 |
Seym | +0.293 |
Pru | +0.289 |
slam | +0.281 |
Corm | +0.275 |
Neg logit contributions | |
CARD | -0.422 |
infect | -0.363 |
foreskin | -0.348 |
helic | -0.344 |
beard | -0.337 |
Token | - |
Token ID | 12 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
Ham | +5.699 |
Seym | +5.012 |
Pru | +4.992 |
slam | +4.947 |
Corm | +4.874 |
Neg logit contributions | |
CARD | -7.415 |
infect | -6.430 |
foreskin | -6.198 |
helic | -5.951 |
giving | -5.805 |
Token | 14 |
Token ID | 1415 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Ham | +7.974 |
Ryan | +6.313 |
Seym | +5.989 |
slam | +5.792 |
Sham | +5.740 |
Neg logit contributions | |
CARD | -16.455 |
foreskin | -14.402 |
infect | -14.181 |
beard | -13.852 |
helic | -13.391 |
Token | Years |
Token ID | 13212 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
Ham | +0.926 |
Seym | +0.846 |
Pru | +0.841 |
slam | +0.816 |
Corm | +0.804 |
Neg logit contributions | |
CARD | -1.140 |
infect | -0.978 |
foreskin | -0.935 |
helic | -0.925 |
beard | -0.905 |
Token | B |
Token ID | 347 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
Ham | +2.171 |
Seym | +1.980 |
Pru | +1.974 |
slam | +1.915 |
Corm | +1.897 |
Neg logit contributions | |
CARD | -2.720 |
infect | -2.342 |
foreskin | -2.237 |
helic | -2.220 |
beard | -2.159 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
Ham | +5.931 |
Pru | +5.350 |
Seym | +5.258 |
Corm | +5.173 |
slam | +5.157 |
Neg logit contributions | |
CARD | -7.878 |
infect | -6.760 |
foreskin | -6.628 |
helic | -6.522 |
beard | -6.242 |
Token | P |
Token ID | 47 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Ham | +2.612 |
Seym | +2.377 |
Pru | +2.371 |
slam | +2.291 |
Corm | +2.274 |
Neg logit contributions | |
CARD | -3.222 |
infect | -2.771 |
foreskin | -2.649 |
helic | -2.608 |
beard | -2.555 |
Token | CPU |
Token ID | 9135 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
CARD | +0.716 |
infect | +0.608 |
foreskin | +0.581 |
helic | +0.577 |
beard | +0.563 |
Neg logit contributions | |
Ham | -0.587 |
Seym | -0.542 |
Pru | -0.532 |
slam | -0.516 |
Corm | -0.507 |
Token | ( |
Token ID | 7 |
Feature activation | +8.99e+00 |
Pos logit contributions | |
Ham | +4.352 |
Ryan | +3.622 |
Pru | +3.535 |
Corm | +3.468 |
slam | +3.417 |
Neg logit contributions | |
CARD | -7.543 |
infect | -6.722 |
helic | -6.652 |
foreskin | -6.622 |
beard | -6.431 |
Token | ns |
Token ID | 5907 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Ham | +5.927 |
Ns | +5.197 |
Ryan | +5.134 |
7601 | +5.071 |
slam | +5.064 |
Neg logit contributions | |
CARD | -8.064 |
helic | -6.575 |
foreskin | -6.506 |
infect | -6.424 |
Dise | -6.320 |
Token | ) |
Token ID | 8 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
Ham | +0.791 |
Pru | +0.714 |
Seym | +0.707 |
slam | +0.694 |
Corm | +0.685 |
Neg logit contributions | |
CARD | -0.927 |
infect | -0.794 |
foreskin | -0.761 |
helic | -0.758 |
beard | -0.735 |
Token | Mem |
Token ID | 4942 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
CARD | +0.025 |
infect | +0.022 |
foreskin | +0.021 |
helic | +0.021 |
beard | +0.020 |
Neg logit contributions | |
Ham | -0.018 |
Seym | -0.017 |
Pru | -0.016 |
slam | -0.016 |
Corm | -0.016 |
Token | c |
Token ID | 66 |
Feature activation | +1.69e+01 |
Pos logit contributions | |
Ham | +2.674 |
slam | +2.208 |
Pru | +2.205 |
Ryan | +2.187 |
Corm | +2.164 |
Neg logit contributions | |
CARD | -5.537 |
infect | -4.823 |
foreskin | -4.814 |
helic | -4.793 |
beard | -4.644 |
Token | py |
Token ID | 9078 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
Ham | +3.809 |
Ryan | +2.499 |
7601 | +2.362 |
mine | +2.291 |
cv | +2.251 |
Neg logit contributions | |
CARD | -20.602 |
helic | -19.458 |
foreskin | -18.448 |
Dise | -18.158 |
beard | -18.151 |
Token | In |
Token ID | 818 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Ham | +3.060 |
Pru | +2.609 |
Ryan | +2.578 |
Seym | +2.567 |
slam | +2.520 |
Neg logit contributions | |
CARD | -4.677 |
infect | -4.005 |
foreskin | -3.963 |
helic | -3.912 |
beard | -3.884 |
Token | Memory |
Token ID | 30871 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
Ham | +0.635 |
Seym | +0.551 |
Pru | +0.549 |
slam | +0.526 |
Corm | +0.515 |
Neg logit contributions | |
CARD | -1.293 |
infect | -1.142 |
foreskin | -1.104 |
helic | -1.097 |
beard | -1.077 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
CARD | +0.759 |
infect | +0.652 |
foreskin | +0.625 |
helic | +0.619 |
beard | +0.608 |
Neg logit contributions | |
Ham | -0.538 |
Seym | -0.489 |
Pru | -0.484 |
slam | -0.468 |
Corm | -0.461 |
Token | 66 |
Token ID | 2791 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
CARD | +6.869 |
infect | +5.590 |
beard | +5.246 |
foreskin | +5.199 |
helic | +5.099 |
Neg logit contributions | |
Ham | -8.184 |
Seym | -8.007 |
Pru | -7.912 |
Corm | -7.601 |
encers | -7.486 |
Token | les |
Token ID | 10287 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
Ham | +0.076 |
Seym | +0.069 |
Pru | +0.069 |
slam | +0.067 |
Corm | +0.066 |
Neg logit contributions | |
CARD | -0.084 |
infect | -0.071 |
foreskin | -0.068 |
helic | -0.067 |
beard | -0.066 |
Token | Mim |
Token ID | 39312 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
Ham | +4.593 |
Pru | +4.205 |
Seym | +4.169 |
Corm | +4.076 |
slam | +4.027 |
Neg logit contributions | |
CARD | -5.808 |
infect | -4.940 |
foreskin | -4.788 |
helic | -4.667 |
beard | -4.621 |
Token | os |
Token ID | 418 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
CARD | +2.558 |
infect | +2.182 |
helic | +2.022 |
foreskin | +2.013 |
beard | +1.966 |
Neg logit contributions | |
Ham | -2.678 |
Seym | -2.502 |
Pru | -2.439 |
slam | -2.397 |
Ryan | -2.344 |
Token | as |
Token ID | 292 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
CARD | +0.903 |
infect | +0.737 |
foreskin | +0.687 |
helic | +0.682 |
beard | +0.660 |
Neg logit contributions | |
Ham | -1.233 |
Seym | -1.155 |
Pru | -1.148 |
slam | -1.117 |
Corm | -1.106 |
Token | (@ |
Token ID | 4275 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
CARD | +2.746 |
infect | +2.314 |
helic | +2.191 |
foreskin | +2.186 |
beard | +2.139 |
Neg logit contributions | |
Ham | -2.568 |
Seym | -2.384 |
Pru | -2.336 |
slam | -2.279 |
Ryan | -2.231 |
Token | b |
Token ID | 65 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
CARD | +1.241 |
infect | +1.093 |
foreskin | +1.036 |
helic | +1.031 |
beard | +1.014 |
Neg logit contributions | |
Ham | -0.765 |
Seym | -0.701 |
Pru | -0.698 |
slam | -0.672 |
Corm | -0.656 |
Token | orm |
Token ID | 579 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
Ham | +8.620 |
Corm | +8.100 |
ownt | +7.943 |
ouver | +7.714 |
Ryan | +7.424 |
Neg logit contributions | |
CARD | -14.889 |
foreskin | -12.444 |
helic | -12.396 |
beard | -11.988 |
infect | -11.948 |
Token | est |
Token ID | 395 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Ham | +3.790 |
Seym | +3.260 |
encers | +3.218 |
ownt | +3.120 |
ouver | +3.092 |
Neg logit contributions | |
CARD | -8.731 |
foreskin | -7.375 |
infect | -7.289 |
helic | -7.227 |
beard | -7.119 |
Token | our |
Token ID | 454 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Ham | +0.143 |
Seym | +0.131 |
Pru | +0.130 |
slam | +0.125 |
Corm | +0.123 |
Neg logit contributions | |
CARD | -0.181 |
infect | -0.156 |
foreskin | -0.149 |
helic | -0.148 |
beard | -0.144 |
Token | ism |
Token ID | 1042 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
CARD | +0.152 |
infect | +0.130 |
foreskin | +0.124 |
helic | +0.123 |
beard | +0.120 |
Neg logit contributions | |
Ham | -0.127 |
Seym | -0.117 |
Pru | -0.116 |
slam | -0.112 |
Corm | -0.111 |
Token | e |
Token ID | 68 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
CARD | +1.851 |
infect | +1.593 |
foreskin | +1.496 |
helic | +1.488 |
beard | +1.457 |
Neg logit contributions | |
Ham | -1.662 |
Seym | -1.530 |
Pru | -1.528 |
slam | -1.478 |
Corm | -1.459 |
Token | pressed |
Token ID | 12070 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
Ham | +2.363 |
Pru | +2.155 |
Seym | +2.131 |
slam | +2.109 |
Corm | +2.057 |
Neg logit contributions | |
CARD | -3.010 |
infect | -2.579 |
foreskin | -2.463 |
helic | -2.443 |
beard | -2.373 |
Token | to |
Token ID | 284 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Ham | +0.629 |
Seym | +0.577 |
Pru | +0.572 |
slam | +0.554 |
Corm | +0.546 |
Neg logit contributions | |
CARD | -0.761 |
infect | -0.652 |
foreskin | -0.623 |
helic | -0.617 |
beard | -0.603 |
Token | cut |
Token ID | 2005 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Ham | +1.451 |
Seym | +1.327 |
Pru | +1.319 |
slam | +1.284 |
Corm | +1.260 |
Neg logit contributions | |
CARD | -1.771 |
infect | -1.519 |
foreskin | -1.449 |
helic | -1.435 |
beard | -1.403 |
Token | $ |
Token ID | 720 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
CARD | +1.054 |
infect | +0.897 |
foreskin | +0.870 |
helic | +0.866 |
beard | +0.845 |
Neg logit contributions | |
Ham | -0.846 |
Seym | -0.786 |
Pru | -0.764 |
slam | -0.738 |
Corm | -0.729 |
Token | 5 |
Token ID | 20 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
Ham | +0.546 |
Seym | +0.492 |
Pru | +0.487 |
slam | +0.468 |
Corm | +0.460 |
Neg logit contributions | |
CARD | -0.918 |
infect | -0.803 |
foreskin | -0.772 |
helic | -0.766 |
beard | -0.752 |
Token | b |
Token ID | 275 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
Ham | +3.835 |
Pru | +3.498 |
Seym | +3.486 |
slam | +3.426 |
Corm | +3.355 |
Neg logit contributions | |
CARD | -4.652 |
infect | -4.051 |
foreskin | -3.816 |
helic | -3.792 |
beard | -3.685 |
Token | n |
Token ID | 77 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
Ham | +6.992 |
Ns | +6.201 |
slam | +5.923 |
nai | +5.905 |
Pru | +5.851 |
Neg logit contributions | |
CARD | -17.522 |
helic | -14.903 |
Dise | -14.455 |
foreskin | -14.139 |
infect | -14.093 |
Token | in |
Token ID | 287 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
Ham | +4.510 |
Pru | +4.042 |
Seym | +3.966 |
slam | +3.953 |
Corm | +3.860 |
Neg logit contributions | |
CARD | -6.483 |
infect | -5.641 |
foreskin | -5.351 |
helic | -5.341 |
beard | -5.200 |
Token | food |
Token ID | 2057 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Ham | +2.809 |
Pru | +2.574 |
Seym | +2.535 |
slam | +2.496 |
Corm | +2.445 |
Neg logit contributions | |
CARD | -3.735 |
infect | -3.252 |
foreskin | -3.063 |
helic | -3.049 |
beard | -2.974 |
Token | stamps |
Token ID | 25560 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Ham | +0.546 |
Seym | +0.489 |
Pru | +0.484 |
slam | +0.465 |
Corm | +0.456 |
Neg logit contributions | |
CARD | -0.981 |
infect | -0.862 |
foreskin | -0.829 |
helic | -0.822 |
beard | -0.808 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Ham | +1.933 |
Seym | +1.755 |
Pru | +1.751 |
slam | +1.701 |
Corm | +1.670 |
Neg logit contributions | |
CARD | -2.546 |
infect | -2.204 |
foreskin | -2.104 |
helic | -2.084 |
beard | -2.036 |
Token | the |
Token ID | 262 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Ham | +0.349 |
Seym | +0.319 |
Pru | +0.316 |
slam | +0.306 |
Corm | +0.301 |
Neg logit contributions | |
CARD | -0.467 |
infect | -0.403 |
foreskin | -0.386 |
helic | -0.382 |
beard | -0.374 |
Token | so |
Token ID | 523 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Ham | +1.879 |
Pru | +1.710 |
Seym | +1.704 |
slam | +1.659 |
Corm | +1.625 |
Neg logit contributions | |
CARD | -2.515 |
infect | -2.186 |
foreskin | -2.079 |
helic | -2.064 |
beard | -2.008 |
Token | - |
Token ID | 12 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
CARD | +0.232 |
infect | +0.197 |
foreskin | +0.187 |
helic | +0.185 |
beard | +0.182 |
Neg logit contributions | |
Ham | -0.212 |
Seym | -0.198 |
Pru | -0.194 |
slam | -0.188 |
Corm | -0.186 |
Token | called |
Token ID | 7174 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Ham | +2.194 |
Pru | +1.921 |
Seym | +1.873 |
slam | +1.873 |
Ryan | +1.858 |
Neg logit contributions | |
CARD | -2.906 |
infect | -2.470 |
foreskin | -2.412 |
helic | -2.394 |
beard | -2.334 |
Token | white |
Token ID | 2330 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
Ham | +2.335 |
Pru | +2.115 |
Seym | +2.110 |
slam | +2.054 |
Corm | +2.006 |
Neg logit contributions | |
CARD | -3.325 |
infect | -2.907 |
foreskin | -2.761 |
helic | -2.750 |
beard | -2.668 |
Token | - |
Token ID | 12 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
Ham | +7.348 |
slam | +6.910 |
Pru | +6.800 |
Corm | +6.712 |
Seym | +6.632 |
Neg logit contributions | |
CARD | -11.198 |
infect | -9.875 |
foreskin | -8.925 |
helic | -8.917 |
Dise | -8.880 |
Token | collar |
Token ID | 37676 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Ham | +7.835 |
ownt | +6.370 |
Ryan | +6.358 |
mine | +6.343 |
ault | +6.322 |
Neg logit contributions | |
CARD | -16.039 |
helic | -13.524 |
foreskin | -13.370 |
Dise | -13.299 |
beard | -13.018 |
Token | jobs |
Token ID | 3946 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
CARD | +2.015 |
infect | +1.744 |
foreskin | +1.691 |
helic | +1.683 |
beard | +1.658 |
Neg logit contributions | |
Ham | -1.273 |
Seym | -1.162 |
Pru | -1.142 |
slam | -1.087 |
Corm | -1.070 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Ham | +0.765 |
Seym | +0.700 |
Pru | +0.694 |
slam | +0.672 |
Corm | +0.662 |
Neg logit contributions | |
CARD | -0.968 |
infect | -0.832 |
foreskin | -0.795 |
helic | -0.788 |
beard | -0.771 |
Token | while |
Token ID | 981 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Ham | +1.510 |
Seym | +1.381 |
Pru | +1.373 |
slam | +1.331 |
Corm | +1.310 |
Neg logit contributions | |
CARD | -1.866 |
infect | -1.604 |
foreskin | -1.533 |
helic | -1.515 |
beard | -1.483 |
Token | jobs |
Token ID | 3946 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Ham | +1.461 |
Seym | +1.319 |
Pru | +1.316 |
slam | +1.271 |
Corm | +1.251 |
Neg logit contributions | |
CARD | -2.188 |
infect | -1.909 |
foreskin | -1.826 |
helic | -1.806 |
beard | -1.767 |
Token | CPU |
Token ID | 9135 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
CARD | +0.749 |
infect | +0.628 |
foreskin | +0.601 |
helic | +0.596 |
beard | +0.584 |
Neg logit contributions | |
Ham | -0.631 |
Seym | -0.594 |
Pru | -0.572 |
slam | -0.557 |
encers | -0.546 |
Token | ( |
Token ID | 7 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
Ham | +4.436 |
Ryan | +3.705 |
Pru | +3.519 |
Corm | +3.482 |
7601 | +3.441 |
Neg logit contributions | |
CARD | -7.858 |
infect | -6.995 |
helic | -6.976 |
foreskin | -6.925 |
beard | -6.717 |
Token | ns |
Token ID | 5907 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Ham | +5.465 |
Ns | +4.760 |
Ryan | +4.746 |
slam | +4.705 |
ownt | +4.684 |
Neg logit contributions | |
CARD | -7.239 |
helic | -5.883 |
foreskin | -5.813 |
infect | -5.780 |
Dise | -5.634 |
Token | ) |
Token ID | 8 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
Ham | +1.190 |
Pru | +1.067 |
Seym | +1.045 |
slam | +1.038 |
Corm | +1.026 |
Neg logit contributions | |
CARD | -1.426 |
infect | -1.227 |
foreskin | -1.177 |
helic | -1.177 |
beard | -1.137 |
Token | Mem |
Token ID | 4942 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
Ham | +0.522 |
Seym | +0.477 |
Pru | +0.470 |
slam | +0.455 |
Corm | +0.446 |
Neg logit contributions | |
CARD | -0.728 |
infect | -0.628 |
foreskin | -0.602 |
helic | -0.596 |
beard | -0.584 |
Token | c |
Token ID | 66 |
Feature activation | +1.67e+01 |
Pos logit contributions | |
Ham | +2.905 |
slam | +2.380 |
Ryan | +2.377 |
Pru | +2.355 |
Corm | +2.345 |
Neg logit contributions | |
CARD | -6.258 |
foreskin | -5.461 |
helic | -5.450 |
infect | -5.447 |
beard | -5.260 |
Token | py |
Token ID | 9078 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
Ham | +3.697 |
Ryan | +2.494 |
7601 | +2.286 |
mine | +2.226 |
cv | +2.198 |
Neg logit contributions | |
CARD | -20.565 |
helic | -19.377 |
foreskin | -18.321 |
Dise | -18.104 |
beard | -18.070 |
Token | In |
Token ID | 818 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Ham | +2.818 |
Pru | +2.395 |
Ryan | +2.387 |
Seym | +2.329 |
slam | +2.302 |
Neg logit contributions | |
CARD | -4.320 |
infect | -3.729 |
foreskin | -3.664 |
helic | -3.646 |
beard | -3.606 |
Token | Memory |
Token ID | 30871 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Ham | +0.388 |
Seym | +0.343 |
Pru | +0.340 |
slam | +0.325 |
Corm | +0.318 |
Neg logit contributions | |
CARD | -0.780 |
infect | -0.688 |
foreskin | -0.664 |
helic | -0.659 |
beard | -0.648 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Ham | +0.259 |
Seym | +0.235 |
Pru | +0.232 |
slam | +0.224 |
Corm | +0.221 |
Neg logit contributions | |
CARD | -0.384 |
infect | -0.334 |
foreskin | -0.320 |
helic | -0.317 |
beard | -0.311 |
Token | 66 |
Token ID | 2791 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
CARD | +6.411 |
infect | +4.975 |
beard | +4.664 |
foreskin | +4.580 |
giving | +4.572 |
Neg logit contributions | |
Seym | -9.278 |
Pru | -8.500 |
Ham | -8.461 |
Corm | -8.109 |
ouver | -8.099 |
Token | 95 |
Token ID | 3865 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
Ham | +2.903 |
Pru | +2.500 |
Seym | +2.461 |
Ryan | +2.414 |
slam | +2.399 |
Neg logit contributions | |
CARD | -4.870 |
infect | -4.242 |
foreskin | -4.148 |
helic | -4.099 |
beard | -4.016 |
Token | , |
Token ID | 11 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Ham | +5.413 |
Pru | +5.000 |
Seym | +4.967 |
Corm | +4.817 |
slam | +4.745 |
Neg logit contributions | |
CARD | -7.005 |
infect | -6.134 |
foreskin | -5.876 |
helic | -5.735 |
beard | -5.645 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Ham | +1.583 |
Seym | +1.448 |
Pru | +1.435 |
slam | +1.390 |
Corm | +1.368 |
Neg logit contributions | |
CARD | -1.998 |
infect | -1.716 |
foreskin | -1.641 |
helic | -1.627 |
beard | -1.591 |
Token | - |
Token ID | 12 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Ham | +1.592 |
Seym | +1.459 |
Pru | +1.449 |
slam | +1.405 |
Corm | +1.385 |
Neg logit contributions | |
CARD | -1.908 |
infect | -1.634 |
foreskin | -1.561 |
helic | -1.544 |
beard | -1.511 |
Token | 5 |
Token ID | 20 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
CARD | +1.264 |
infect | +1.121 |
helic | +1.066 |
foreskin | +1.066 |
beard | +1.040 |
Neg logit contributions | |
Ham | -0.642 |
Seym | -0.588 |
Pru | -0.577 |
slam | -0.551 |
Corm | -0.536 |
Token | SS |
Token ID | 6723 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
Ham | +2.815 |
Seym | +2.548 |
Pru | +2.522 |
slam | +2.430 |
Corm | +2.416 |
Neg logit contributions | |
CARD | -4.515 |
infect | -3.967 |
foreskin | -3.809 |
helic | -3.741 |
beard | -3.688 |
Token | BN |
Token ID | 15766 |
Feature activation | +9.74e+00 |
Pos logit contributions | |
Ham | +7.034 |
Ns | +6.761 |
Pru | +5.942 |
Seym | +5.904 |
Corm | +5.827 |
Neg logit contributions | |
CARD | -16.596 |
infect | -14.785 |
foreskin | -14.351 |
giving | -13.846 |
beard | -13.815 |
Token | type |
Token ID | 2099 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
Ham | +6.108 |
Pru | +5.556 |
Seym | +5.544 |
Corm | +5.450 |
slam | +5.429 |
Neg logit contributions | |
CARD | -8.651 |
infect | -7.526 |
foreskin | -7.185 |
beard | -6.934 |
helic | -6.905 |
Token | - |
Token ID | 12 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
Ham | +4.789 |
Seym | +4.418 |
Pru | +4.394 |
Corm | +4.292 |
slam | +4.243 |
Neg logit contributions | |
CARD | -6.762 |
infect | -5.837 |
foreskin | -5.601 |
beard | -5.399 |
helic | -5.395 |
Token | 94 |
Token ID | 5824 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
Ham | +3.471 |
Pru | +2.953 |
Seym | +2.882 |
Ryan | +2.878 |
Corm | +2.843 |
Neg logit contributions | |
CARD | -5.960 |
infect | -5.202 |
foreskin | -5.107 |
helic | -5.044 |
beard | -4.953 |
Token | Jin |
Token ID | 17297 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Ham | +4.811 |
Seym | +4.434 |
Pru | +4.414 |
Corm | +4.261 |
slam | +4.230 |
Neg logit contributions | |
CARD | -6.296 |
infect | -5.469 |
foreskin | -5.249 |
helic | -5.110 |
beard | -5.049 |
Token | im |
Token ID | 545 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
Ham | +5.163 |
slam | +4.793 |
Pru | +4.548 |
Seym | +4.410 |
abstract | +4.387 |
Neg logit contributions | |
CARD | -13.766 |
infect | -12.372 |
giving | -11.744 |
foreskin | -11.732 |
helic | -11.665 |
Token | utils |
Token ID | 26791 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
Ham | +3.394 |
encers | +2.902 |
slam | +2.882 |
Pru | +2.848 |
Ryan | +2.806 |
Neg logit contributions | |
CARD | -5.879 |
infect | -4.944 |
helic | -4.940 |
foreskin | -4.936 |
beard | -4.777 |
Token | import |
Token ID | 1330 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
Ham | +3.716 |
slam | +3.251 |
Pru | +3.091 |
Corm | +2.975 |
compliment | +2.942 |
Neg logit contributions | |
CARD | -9.234 |
infect | -8.274 |
helic | -8.036 |
foreskin | -7.998 |
beard | -7.874 |
Token | paths |
Token ID | 13532 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
Ham | +3.572 |
Pru | +3.359 |
Corm | +3.267 |
Seym | +3.228 |
slam | +3.212 |
Neg logit contributions | |
CARD | -5.236 |
infect | -4.592 |
foreskin | -4.401 |
helic | -4.317 |
giving | -4.263 |
Token | import |
Token ID | 1330 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
Ham | +3.768 |
slam | +3.370 |
Pru | +3.250 |
Corm | +3.156 |
Ryan | +3.069 |
Neg logit contributions | |
CARD | -9.145 |
infect | -8.234 |
helic | -7.960 |
foreskin | -7.942 |
beard | -7.826 |
Token | n |
Token ID | 299 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
Ham | +3.146 |
Pru | +2.847 |
Seym | +2.795 |
Corm | +2.791 |
slam | +2.775 |
Neg logit contributions | |
CARD | -7.446 |
infect | -6.655 |
foreskin | -6.364 |
helic | -6.340 |
giving | -6.244 |
Token | umpy |
Token ID | 32152 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
Ham | +9.081 |
ats | +8.101 |
cv | +7.805 |
Ryan | +7.655 |
ownt | +7.644 |
Neg logit contributions | |
CARD | -14.739 |
helic | -13.081 |
foreskin | -12.203 |
Dise | -11.915 |
beard | -11.880 |
Token | as |
Token ID | 355 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
Ham | +5.059 |
slam | +4.451 |
Pru | +4.299 |
Corm | +4.196 |
Ryan | +4.196 |
Neg logit contributions | |
CARD | -8.521 |
infect | -7.477 |
foreskin | -7.311 |
helic | -7.240 |
Dise | -7.106 |
Token | np |
Token ID | 45941 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
Ham | +0.770 |
Pru | +0.567 |
slam | +0.511 |
Corm | +0.343 |
compliment | +0.272 |
Neg logit contributions | |
CARD | -13.845 |
infect | -12.870 |
helic | -12.575 |
giving | -12.195 |
foreskin | -12.159 |
Token | import |
Token ID | 1330 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Ham | +3.751 |
slam | +3.397 |
Pru | +3.260 |
Corm | +3.175 |
Ryan | +3.018 |
Neg logit contributions | |
CARD | -9.209 |
infect | -8.431 |
foreskin | -8.039 |
helic | -7.996 |
giving | -7.877 |
Token | arg |
Token ID | 1822 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
Ham | +1.436 |
Seym | +1.321 |
Pru | +1.320 |
slam | +1.290 |
Corm | +1.280 |
Neg logit contributions | |
CARD | -1.638 |
infect | -1.405 |
foreskin | -1.342 |
helic | -1.318 |
beard | -1.289 |
Token | x |
Token ID | 2124 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
CARD | +1.119 |
infect | +0.937 |
foreskin | +0.897 |
helic | +0.884 |
beard | +0.870 |
Neg logit contributions | |
Ham | -1.069 |
Seym | -1.014 |
Pru | -0.984 |
slam | -0.949 |
Corm | -0.935 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
Ham | +0.107 |
Seym | +0.098 |
Pru | +0.097 |
slam | +0.094 |
Corm | +0.093 |
Neg logit contributions | |
CARD | -0.138 |
infect | -0.119 |
foreskin | -0.113 |
helic | -0.112 |
beard | -0.110 |
Token | x |
Token ID | 87 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
CARD | +4.789 |
infect | +4.085 |
giving | +3.834 |
foreskin | +3.546 |
sters | +3.509 |
Neg logit contributions | |
Seym | -7.182 |
Pru | -6.611 |
Ham | -6.564 |
slam | -6.244 |
Corm | -6.211 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
CARD | +5.484 |
infect | +4.558 |
giving | +4.394 |
foreskin | +4.188 |
beard | +4.122 |
Neg logit contributions | |
Seym | -6.708 |
Ham | -6.015 |
Pru | -5.895 |
oun | -5.636 |
slam | -5.620 |
Token | x |
Token ID | 87 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
CARD | +6.417 |
infect | +5.689 |
giving | +5.488 |
sters | +4.809 |
iov | +4.509 |
Neg logit contributions | |
Seym | -12.945 |
oun | -11.677 |
Pru | -11.611 |
Ham | -11.148 |
exha | -10.910 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e+01 |
Pos logit contributions | |
CARD | +8.341 |
infect | +7.150 |
giving | +6.825 |
iov | +5.967 |
foreskin | +5.917 |
Neg logit contributions | |
Seym | -14.890 |
oun | -13.556 |
Pru | -12.742 |
exha | -12.495 |
ThumbnailImage | -12.459 |
Token | 168 |
Token ID | 14656 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
infect | +7.143 |
CARD | +6.960 |
iov | +5.441 |
giving | +5.296 |
iris | +5.089 |
Neg logit contributions | |
Seym | -20.264 |
Pru | -19.792 |
Corm | -19.289 |
Ham | -18.680 |
oun | -18.428 |
Token | 100 |
Token ID | 1802 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
CARD | +3.122 |
infect | +2.688 |
foreskin | +2.611 |
helic | +2.583 |
beard | +2.536 |
Neg logit contributions | |
Ham | -1.870 |
Seym | -1.744 |
Pru | -1.647 |
slam | -1.610 |
ouver | -1.565 |
Token | 24 |
Token ID | 1731 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Ham | +2.479 |
Pru | +2.149 |
Seym | +2.071 |
Ryan | +2.055 |
slam | +2.052 |
Neg logit contributions | |
CARD | -4.150 |
infect | -3.663 |
foreskin | -3.555 |
helic | -3.545 |
beard | -3.452 |
Token | 80 |
Token ID | 1795 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
Ham | +2.562 |
Pru | +2.196 |
Ryan | +2.137 |
slam | +2.131 |
Corm | +2.125 |
Neg logit contributions | |
CARD | -4.215 |
infect | -3.718 |
foreskin | -3.611 |
helic | -3.607 |
beard | -3.500 |
Token | x |
Token ID | 2124 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
CARD | +3.018 |
infect | +2.447 |
foreskin | +2.358 |
helic | +2.303 |
beard | +2.302 |
Neg logit contributions | |
Ham | -3.169 |
Seym | -3.120 |
Pru | -2.947 |
slam | -2.827 |
ouver | -2.807 |
Token | was |
Token ID | 373 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
Ham | +0.073 |
Seym | +0.067 |
Pru | +0.066 |
slam | +0.064 |
Corm | +0.064 |
Neg logit contributions | |
CARD | -0.085 |
infect | -0.072 |
foreskin | -0.069 |
helic | -0.068 |
beard | -0.067 |
Token | p |
Token ID | 79 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
CARD | +4.863 |
infect | +4.334 |
foreskin | +4.073 |
helic | +4.027 |
beard | +4.010 |
Neg logit contributions | |
Ham | -2.630 |
Seym | -2.455 |
Pru | -2.355 |
slam | -2.233 |
Corm | -2.191 |
Token | from |
Token ID | 422 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Ham | +2.228 |
Pru | +2.022 |
Seym | +2.004 |
slam | +1.989 |
Corm | +1.944 |
Neg logit contributions | |
CARD | -2.725 |
infect | -2.318 |
helic | -2.219 |
foreskin | -2.218 |
beard | -2.139 |
Token | under |
Token ID | 739 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
CARD | +2.757 |
infect | +2.352 |
foreskin | +2.257 |
helic | +2.228 |
beard | +2.218 |
Neg logit contributions | |
Ham | -2.338 |
Seym | -2.189 |
Pru | -2.105 |
slam | -2.032 |
encers | -2.009 |
Token | his |
Token ID | 465 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
CARD | +3.183 |
infect | +2.675 |
foreskin | +2.531 |
helic | +2.455 |
beard | +2.448 |
Neg logit contributions | |
Ham | -3.443 |
Seym | -3.275 |
Pru | -3.171 |
slam | -3.102 |
encers | -3.045 |
Token | eyel |
Token ID | 29708 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
CARD | +7.798 |
foreskin | +6.846 |
beard | +6.619 |
infect | +6.421 |
helic | +6.234 |
Neg logit contributions | |
Ham | -8.031 |
Seym | -7.548 |
Pru | -7.211 |
encers | -7.160 |
ouver | -7.090 |
Token | id |
Token ID | 312 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
CARD | +9.830 |
infect | +9.276 |
beard | +8.298 |
foreskin | +8.242 |
iov | +7.774 |
Neg logit contributions | |
Seym | -16.293 |
Ham | -15.161 |
Pru | -14.954 |
Corm | -14.751 |
slam | -14.027 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
CARD | +7.384 |
infect | +6.121 |
foreskin | +6.040 |
beard | +5.941 |
helic | +5.778 |
Neg logit contributions | |
Ham | -7.366 |
Seym | -7.043 |
Pru | -6.944 |
encers | -6.577 |
ownt | -6.537 |
Token |
|
Token ID | 198 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
CARD | +2.543 |
infect | +2.119 |
foreskin | +2.020 |
helic | +1.978 |
beard | +1.963 |
Neg logit contributions | |
Ham | -2.032 |
Seym | -1.938 |
Pru | -1.835 |
slam | -1.834 |
ouver | -1.781 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Ham | +0.329 |
Seym | +0.297 |
Pru | +0.296 |
slam | +0.286 |
Corm | +0.282 |
Neg logit contributions | |
CARD | -0.452 |
infect | -0.391 |
foreskin | -0.374 |
helic | -0.371 |
beard | -0.363 |
Token | These |
Token ID | 4711 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
CARD | +1.227 |
infect | +1.065 |
foreskin | +1.002 |
helic | +0.987 |
beard | +0.975 |
Neg logit contributions | |
Ham | -0.892 |
Seym | -0.857 |
Pru | -0.833 |
slam | -0.805 |
Corm | -0.785 |
Token | x |
Token ID | 2124 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
CARD | +2.680 |
infect | +2.194 |
foreskin | +2.116 |
helic | +2.072 |
beard | +2.067 |
Neg logit contributions | |
Ham | -2.781 |
Seym | -2.707 |
Pru | -2.571 |
slam | -2.467 |
ouver | -2.453 |
Token | . |
Token ID | 13 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
Ham | +0.695 |
Pru | +0.623 |
Seym | +0.616 |
slam | +0.604 |
Corm | +0.596 |
Neg logit contributions | |
CARD | -0.930 |
infect | -0.803 |
foreskin | -0.771 |
helic | -0.766 |
beard | -0.746 |
Token | x |
Token ID | 87 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
CARD | +3.753 |
infect | +3.194 |
giving | +2.933 |
foreskin | +2.852 |
beard | +2.781 |
Neg logit contributions | |
Seym | -4.938 |
Ham | -4.719 |
Pru | -4.635 |
slam | -4.415 |
Corm | -4.379 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
CARD | +3.146 |
infect | +2.655 |
foreskin | +2.498 |
giving | +2.474 |
beard | +2.442 |
Neg logit contributions | |
Seym | -3.015 |
Ham | -2.932 |
Pru | -2.778 |
slam | -2.664 |
Corm | -2.608 |
Token | x |
Token ID | 87 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
CARD | +5.697 |
infect | +4.950 |
giving | +4.689 |
sters | +4.240 |
foreskin | +4.099 |
Neg logit contributions | |
Seym | -10.108 |
Pru | -9.181 |
Ham | -8.964 |
oun | -8.927 |
slam | -8.651 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
CARD | +7.310 |
infect | +6.001 |
giving | +5.937 |
foreskin | +5.368 |
beard | +5.364 |
Neg logit contributions | |
Seym | -11.136 |
oun | -9.986 |
Ham | -9.640 |
Pru | -9.550 |
slam | -9.147 |
Token | 155 |
Token ID | 18742 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
CARD | +7.641 |
infect | +7.589 |
giving | +6.291 |
iov | +5.983 |
beard | +5.916 |
Neg logit contributions | |
Seym | -18.346 |
Corm | -17.801 |
Pru | -17.778 |
Ham | -17.772 |
ouver | -17.307 |
Token | 10 |
Token ID | 838 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
CARD | +5.563 |
infect | +4.710 |
foreskin | +4.596 |
helic | +4.543 |
beard | +4.461 |
Neg logit contributions | |
Ham | -3.714 |
Seym | -3.534 |
Pru | -3.298 |
slam | -3.210 |
ouver | -3.205 |
Token | 384 |
Token ID | 22842 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
CARD | +3.933 |
infect | +3.311 |
foreskin | +3.142 |
giving | +3.130 |
beard | +3.079 |
Neg logit contributions | |
Seym | -2.921 |
Ham | -2.890 |
Pru | -2.722 |
slam | -2.620 |
Corm | -2.554 |
Token | 38 |
Token ID | 2548 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
Ham | +3.742 |
Ryan | +3.123 |
Pru | +3.080 |
Corm | +3.077 |
7601 | +3.039 |
Neg logit contributions | |
CARD | -6.522 |
infect | -5.872 |
helic | -5.762 |
foreskin | -5.727 |
beard | -5.552 |
Token | x |
Token ID | 2124 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
CARD | +3.795 |
infect | +3.046 |
foreskin | +2.964 |
beard | +2.898 |
helic | +2.879 |
Neg logit contributions | |
Ham | -4.199 |
Seym | -4.171 |
Pru | -3.907 |
ouver | -3.779 |
encers | -3.752 |
Token | two |
Token ID | 734 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
CARD | +4.083 |
infect | +3.450 |
helic | +3.375 |
foreskin | +3.343 |
beard | +3.281 |
Neg logit contributions | |
Ham | -3.730 |
Seym | -3.476 |
Pru | -3.358 |
Ryan | -3.234 |
encers | -3.232 |
Token | ? |
Token ID | 30 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
CARD | +2.776 |
infect | +2.334 |
helic | +2.268 |
foreskin | +2.247 |
beard | +2.196 |
Neg logit contributions | |
Ham | -2.591 |
Seym | -2.421 |
Pru | -2.365 |
slam | -2.271 |
Ryan | -2.250 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Ham | +3.080 |
Pru | +2.785 |
Seym | +2.711 |
Corm | +2.673 |
Ryan | +2.601 |
Neg logit contributions | |
CARD | -4.559 |
infect | -4.109 |
foreskin | -3.945 |
helic | -3.902 |
beard | -3.816 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
CARD | +0.186 |
infect | +0.161 |
foreskin | +0.154 |
helic | +0.152 |
beard | +0.149 |
Neg logit contributions | |
Ham | -0.139 |
Seym | -0.129 |
Pru | -0.127 |
slam | -0.122 |
Corm | -0.120 |
Token | T |
Token ID | 51 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
CARD | +1.656 |
infect | +1.408 |
foreskin | +1.319 |
helic | +1.307 |
beard | +1.286 |
Neg logit contributions | |
Ham | -1.425 |
Seym | -1.370 |
Pru | -1.344 |
slam | -1.304 |
Corm | -1.275 |
Token | OM |
Token ID | 2662 |
Feature activation | -1.96e+01 |
Pos logit contributions | |
CARD | +7.960 |
infect | +6.152 |
helic | +5.744 |
foreskin | +5.699 |
beard | +5.654 |
Neg logit contributions | |
Seym | -8.819 |
Ham | -8.550 |
Pru | -8.401 |
encers | -8.163 |
slam | -8.064 |
Token | KING |
Token ID | 32957 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
CARD | +10.598 |
DATA | +5.984 |
LEG | +5.791 |
DISTR | +5.630 |
helic | +5.467 |
Neg logit contributions | |
Seym | -19.278 |
Ham | -16.942 |
encers | -16.838 |
ownt | -16.766 |
ouver | -16.539 |
Token | : |
Token ID | 25 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
CARD | +3.024 |
infect | +2.438 |
foreskin | +2.306 |
helic | +2.291 |
beard | +2.241 |
Neg logit contributions | |
Ham | -3.639 |
Seym | -3.422 |
Pru | -3.386 |
slam | -3.295 |
Corm | -3.245 |
Token | Well |
Token ID | 3894 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
CARD | +0.956 |
infect | +0.805 |
foreskin | +0.775 |
helic | +0.765 |
beard | +0.753 |
Neg logit contributions | |
Ham | -0.743 |
Seym | -0.694 |
Pru | -0.670 |
slam | -0.660 |
encers | -0.643 |
Token | , |
Token ID | 11 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Ham | +3.069 |
Pru | +2.755 |
Seym | +2.724 |
slam | +2.688 |
Corm | +2.683 |
Neg logit contributions | |
CARD | -4.436 |
infect | -3.921 |
foreskin | -3.703 |
helic | -3.671 |
beard | -3.559 |
Token | that |
Token ID | 326 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
CARD | +1.824 |
infect | +1.550 |
foreskin | +1.502 |
helic | +1.490 |
beard | +1.464 |
Neg logit contributions | |
Ham | -1.421 |
Seym | -1.315 |
Pru | -1.281 |
slam | -1.234 |
encers | -1.229 |
Token | x |
Token ID | 2124 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
CARD | +0.327 |
infect | +0.277 |
foreskin | +0.264 |
helic | +0.261 |
beard | +0.256 |
Neg logit contributions | |
Ham | -0.295 |
Seym | -0.275 |
Pru | -0.270 |
slam | -0.262 |
Corm | -0.258 |
Token | . |
Token ID | 13 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
Ham | +1.344 |
Pru | +1.187 |
slam | +1.156 |
Seym | +1.148 |
Corm | +1.143 |
Neg logit contributions | |
CARD | -1.884 |
infect | -1.634 |
foreskin | -1.573 |
helic | -1.571 |
beard | -1.521 |
Token | x |
Token ID | 87 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
CARD | +3.899 |
infect | +3.316 |
giving | +3.058 |
foreskin | +2.945 |
beard | +2.879 |
Neg logit contributions | |
Seym | -5.211 |
Ham | -4.936 |
Pru | -4.871 |
slam | -4.628 |
Corm | -4.597 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
CARD | +3.155 |
infect | +2.668 |
foreskin | +2.504 |
giving | +2.487 |
beard | +2.445 |
Neg logit contributions | |
Seym | -3.039 |
Ham | -2.948 |
Pru | -2.799 |
slam | -2.686 |
Corm | -2.630 |
Token | x |
Token ID | 87 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
CARD | +6.095 |
infect | +5.439 |
giving | +5.034 |
foreskin | +4.421 |
sters | +4.406 |
Neg logit contributions | |
Seym | -10.818 |
Pru | -9.906 |
Ham | -9.635 |
oun | -9.427 |
Corm | -9.372 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e+01 |
Pos logit contributions | |
CARD | +8.395 |
infect | +7.311 |
giving | +6.814 |
foreskin | +6.080 |
iov | +5.918 |
Neg logit contributions | |
Seym | -13.589 |
oun | -11.853 |
Pru | -11.629 |
Ham | -11.367 |
Corm | -11.190 |
Token | 166 |
Token ID | 23055 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
infect | +4.966 |
CARD | +4.710 |
giving | +2.880 |
translation | +2.473 |
iov | +2.376 |
Neg logit contributions | |
Seym | -21.991 |
Pru | -21.088 |
Corm | -20.746 |
Ham | -20.470 |
slam | -20.110 |
Token | 108 |
Token ID | 15495 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
CARD | +0.453 |
infect | +0.395 |
foreskin | +0.381 |
helic | +0.378 |
beard | +0.371 |
Neg logit contributions | |
Ham | -0.257 |
Seym | -0.233 |
Pru | -0.227 |
slam | -0.219 |
Corm | -0.213 |
Token | 67 |
Token ID | 3134 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
CARD | +0.287 |
infect | +0.248 |
foreskin | +0.236 |
helic | +0.234 |
beard | +0.230 |
Neg logit contributions | |
Ham | -0.196 |
Seym | -0.185 |
Pru | -0.179 |
slam | -0.174 |
Corm | -0.169 |
Token | 26 |
Token ID | 2075 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Ham | +3.197 |
Pru | +2.675 |
Ryan | +2.649 |
Corm | +2.615 |
slam | +2.602 |
Neg logit contributions | |
CARD | -5.563 |
infect | -4.949 |
helic | -4.846 |
foreskin | -4.819 |
beard | -4.670 |
Token | x |
Token ID | 2124 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
CARD | +0.474 |
infect | +0.400 |
foreskin | +0.382 |
helic | +0.377 |
beard | +0.370 |
Neg logit contributions | |
Ham | -0.437 |
Seym | -0.410 |
Pru | -0.401 |
slam | -0.388 |
Corm | -0.382 |
Token | x |
Token ID | 2124 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
CARD | +0.331 |
infect | +0.280 |
foreskin | +0.268 |
helic | +0.264 |
beard | +0.259 |
Neg logit contributions | |
Ham | -0.302 |
Seym | -0.282 |
Pru | -0.277 |
slam | -0.268 |
Corm | -0.264 |
Token | . |
Token ID | 13 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
CARD | +0.296 |
infect | +0.254 |
foreskin | +0.243 |
helic | +0.240 |
beard | +0.236 |
Neg logit contributions | |
Ham | -0.235 |
Seym | -0.218 |
Pru | -0.214 |
slam | -0.207 |
Corm | -0.204 |
Token | x |
Token ID | 87 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
CARD | +4.350 |
infect | +3.710 |
giving | +3.441 |
foreskin | +3.265 |
beard | +3.191 |
Neg logit contributions | |
Seym | -6.145 |
Ham | -5.727 |
Pru | -5.702 |
slam | -5.408 |
Corm | -5.376 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
CARD | +4.377 |
infect | +3.669 |
giving | +3.464 |
foreskin | +3.409 |
beard | +3.342 |
Neg logit contributions | |
Seym | -4.768 |
Ham | -4.435 |
Pru | -4.280 |
slam | -4.092 |
Corm | -4.007 |
Token | x |
Token ID | 87 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
CARD | +6.077 |
infect | +5.431 |
giving | +5.087 |
sters | +4.474 |
foreskin | +4.467 |
Neg logit contributions | |
Seym | -10.755 |
Pru | -9.835 |
Ham | -9.557 |
oun | -9.428 |
Corm | -9.295 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e+01 |
Pos logit contributions | |
CARD | +7.630 |
infect | +6.535 |
giving | +6.349 |
foreskin | +5.661 |
beard | +5.472 |
Neg logit contributions | |
Seym | -12.395 |
oun | -10.815 |
Pru | -10.618 |
Ham | -10.427 |
Corm | -10.090 |
Token | 170 |
Token ID | 17279 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
infect | +6.496 |
CARD | +6.329 |
giving | +5.361 |
iov | +4.822 |
translation | +4.807 |
Neg logit contributions | |
Seym | -19.868 |
Pru | -18.273 |
Corm | -18.009 |
Ham | -17.781 |
compliment | -17.234 |
Token | 108 |
Token ID | 15495 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
CARD | +4.796 |
infect | +4.117 |
foreskin | +4.007 |
helic | +3.978 |
beard | +3.898 |
Neg logit contributions | |
Ham | -2.924 |
Seym | -2.748 |
Pru | -2.565 |
slam | -2.509 |
ouver | -2.467 |
Token | 76 |
Token ID | 4304 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
CARD | +2.119 |
infect | +1.813 |
foreskin | +1.712 |
giving | +1.684 |
helic | +1.683 |
Neg logit contributions | |
Ham | -1.528 |
Seym | -1.511 |
Pru | -1.428 |
slam | -1.384 |
Corm | -1.341 |
Token | 25 |
Token ID | 1495 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Ham | +2.355 |
Pru | +2.018 |
Ryan | +1.961 |
Corm | +1.951 |
slam | +1.928 |
Neg logit contributions | |
CARD | -3.984 |
infect | -3.533 |
helic | -3.432 |
foreskin | -3.430 |
beard | -3.333 |
Token | x |
Token ID | 2124 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
CARD | +1.819 |
infect | +1.508 |
foreskin | +1.449 |
helic | +1.424 |
beard | +1.407 |
Neg logit contributions | |
Ham | -1.790 |
Seym | -1.712 |
Pru | -1.645 |
slam | -1.587 |
Corm | -1.561 |
Token | x |
Token ID | 2124 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
CARD | +1.866 |
infect | +1.546 |
foreskin | +1.487 |
helic | +1.460 |
beard | +1.445 |
Neg logit contributions | |
Ham | -1.835 |
Seym | -1.759 |
Pru | -1.692 |
slam | -1.632 |
Corm | -1.607 |
Token | . |
Token ID | 13 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
Ham | +1.286 |
Pru | +1.137 |
slam | +1.107 |
Seym | +1.104 |
Corm | +1.094 |
Neg logit contributions | |
CARD | -1.792 |
infect | -1.554 |
foreskin | -1.495 |
helic | -1.492 |
beard | -1.446 |
Token | x |
Token ID | 87 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
CARD | +4.237 |
infect | +3.605 |
giving | +3.346 |
foreskin | +3.195 |
beard | +3.122 |
Neg logit contributions | |
Seym | -5.928 |
Ham | -5.551 |
Pru | -5.516 |
slam | -5.227 |
Corm | -5.205 |
Token | . |
Token ID | 13 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
CARD | +3.404 |
infect | +2.867 |
foreskin | +2.693 |
giving | +2.682 |
beard | +2.631 |
Neg logit contributions | |
Seym | -3.347 |
Ham | -3.220 |
Pru | -3.068 |
slam | -2.943 |
Corm | -2.877 |
Token | x |
Token ID | 87 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
CARD | +5.004 |
infect | +4.279 |
giving | +4.019 |
foreskin | +3.708 |
sters | +3.664 |
Neg logit contributions | |
Seym | -7.763 |
Pru | -7.154 |
Ham | -7.115 |
slam | -6.775 |
Corm | -6.742 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e+01 |
Pos logit contributions | |
CARD | +7.733 |
infect | +6.361 |
giving | +6.301 |
foreskin | +5.495 |
sters | +5.430 |
Neg logit contributions | |
Seym | -12.858 |
oun | -11.294 |
Pru | -10.827 |
Ham | -10.700 |
exha | -10.576 |
Token | 165 |
Token ID | 20986 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
CARD | +6.471 |
infect | +6.111 |
giving | +4.712 |
iov | +4.281 |
translation | +4.098 |
Neg logit contributions | |
Seym | -20.375 |
Corm | -18.781 |
Ham | -18.642 |
Pru | -18.554 |
slam | -18.088 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
CARD | +3.843 |
infect | +3.278 |
foreskin | +3.191 |
helic | +3.158 |
beard | +3.096 |
Neg logit contributions | |
Ham | -2.432 |
Seym | -2.297 |
Pru | -2.157 |
slam | -2.102 |
ouver | -2.065 |
Token | 92 |
Token ID | 5892 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
CARD | +2.902 |
infect | +2.459 |
foreskin | +2.345 |
giving | +2.301 |
helic | +2.299 |
Neg logit contributions | |
Ham | -2.114 |
Seym | -2.077 |
Pru | -1.968 |
slam | -1.890 |
Corm | -1.852 |
Token | 194 |
Token ID | 22913 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
CARD | +2.075 |
infect | +1.776 |
helic | +1.692 |
foreskin | +1.686 |
beard | +1.646 |
Neg logit contributions | |
Ham | -1.558 |
Seym | -1.471 |
Pru | -1.431 |
slam | -1.392 |
Corm | -1.346 |
Token | x |
Token ID | 2124 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
CARD | +0.327 |
infect | +0.277 |
foreskin | +0.264 |
helic | +0.261 |
beard | +0.256 |
Neg logit contributions | |
Ham | -0.295 |
Seym | -0.275 |
Pru | -0.270 |
slam | -0.262 |
Corm | -0.258 |
Token | x |
Token ID | 2124 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
CARD | +0.134 |
infect | +0.113 |
foreskin | +0.108 |
helic | +0.107 |
beard | +0.105 |
Neg logit contributions | |
Ham | -0.121 |
Seym | -0.113 |
Pru | -0.111 |
slam | -0.108 |
Corm | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | -7.55e+00 |
Pos logit contributions | |
Ham | +1.060 |
Pru | +0.942 |
Seym | +0.922 |
slam | +0.916 |
Corm | +0.904 |
Neg logit contributions | |
CARD | -1.451 |
infect | -1.256 |
foreskin | -1.207 |
helic | -1.203 |
beard | -1.168 |
Token | x |
Token ID | 87 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
CARD | +4.725 |
infect | +4.032 |
giving | +3.763 |
foreskin | +3.515 |
sters | +3.453 |
Neg logit contributions | |
Seym | -7.009 |
Pru | -6.455 |
Ham | -6.433 |
slam | -6.110 |
Corm | -6.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
CARD | +4.003 |
infect | +3.359 |
giving | +3.164 |
foreskin | +3.136 |
beard | +3.073 |
Neg logit contributions | |
Seym | -4.197 |
Ham | -3.950 |
Pru | -3.791 |
slam | -3.627 |
Corm | -3.551 |
Token | x |
Token ID | 87 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
CARD | +6.174 |
infect | +5.419 |
giving | +5.174 |
sters | +4.622 |
foreskin | +4.348 |
Neg logit contributions | |
Seym | -11.883 |
Pru | -10.729 |
oun | -10.711 |
Ham | -10.334 |
Corm | -10.074 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e+01 |
Pos logit contributions | |
CARD | +7.558 |
infect | +6.204 |
giving | +6.139 |
foreskin | +5.422 |
sters | +5.405 |
Neg logit contributions | |
Seym | -12.017 |
oun | -10.934 |
Ham | -10.314 |
Pru | -10.269 |
ThumbnailImage | -9.978 |
Token | 154 |
Token ID | 21526 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
CARD | +8.717 |
infect | +8.587 |
giving | +7.570 |
conce | +7.060 |
iris | +6.868 |
Neg logit contributions | |
Seym | -16.310 |
Ham | -16.140 |
oun | -16.105 |
Pru | -16.035 |
Corm | -15.937 |
Token | 109 |
Token ID | 16003 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
CARD | +5.125 |
infect | +4.355 |
foreskin | +4.240 |
helic | +4.189 |
beard | +4.117 |
Neg logit contributions | |
Ham | -3.286 |
Seym | -3.135 |
Pru | -2.897 |
slam | -2.840 |
ouver | -2.821 |
Token | 77 |
Token ID | 3324 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Ham | +0.235 |
Seym | +0.217 |
Pru | +0.212 |
slam | +0.205 |
Corm | +0.201 |
Neg logit contributions | |
CARD | -0.360 |
infect | -0.313 |
foreskin | -0.299 |
helic | -0.296 |
beard | -0.291 |
Token | 39 |
Token ID | 2670 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Ham | +1.637 |
Pru | +1.429 |
Seym | +1.400 |
slam | +1.382 |
Corm | +1.367 |
Neg logit contributions | |
CARD | -2.622 |
infect | -2.299 |
foreskin | -2.222 |
helic | -2.217 |
beard | -2.157 |
Token | x |
Token ID | 2124 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
CARD | +2.680 |
infect | +2.194 |
foreskin | +2.116 |
helic | +2.072 |
beard | +2.067 |
Neg logit contributions | |
Ham | -2.781 |
Seym | -2.707 |
Pru | -2.571 |
slam | -2.467 |
ouver | -2.453 |
Token | x |
Token ID | 2124 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
CARD | +0.474 |
infect | +0.400 |
foreskin | +0.382 |
helic | +0.377 |
beard | +0.370 |
Neg logit contributions | |
Ham | -0.437 |
Seym | -0.410 |
Pru | -0.401 |
slam | -0.388 |
Corm | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
Ham | +0.989 |
Pru | +0.882 |
Seym | +0.865 |
slam | +0.856 |
Corm | +0.846 |
Neg logit contributions | |
CARD | -1.348 |
infect | -1.166 |
foreskin | -1.120 |
helic | -1.116 |
beard | -1.084 |
Token | x |
Token ID | 87 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
CARD | +4.154 |
infect | +3.545 |
giving | +3.278 |
foreskin | +3.131 |
beard | +3.050 |
Neg logit contributions | |
Seym | -5.807 |
Ham | -5.460 |
Pru | -5.413 |
slam | -5.136 |
Corm | -5.105 |
Token | . |
Token ID | 13 |
Feature activation | -9.60e+00 |
Pos logit contributions | |
CARD | +4.204 |
infect | +3.530 |
giving | +3.331 |
foreskin | +3.286 |
beard | +3.215 |
Neg logit contributions | |
Seym | -4.498 |
Ham | -4.215 |
Pru | -4.055 |
slam | -3.880 |
Corm | -3.795 |
Token | x |
Token ID | 87 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
CARD | +5.492 |
infect | +4.763 |
giving | +4.486 |
sters | +4.039 |
foreskin | +3.996 |
Neg logit contributions | |
Seym | -9.269 |
Pru | -8.491 |
Ham | -8.343 |
oun | -8.116 |
slam | -7.994 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
CARD | +8.067 |
infect | +6.850 |
giving | +6.578 |
foreskin | +5.777 |
sters | +5.687 |
Neg logit contributions | |
Seym | -13.477 |
oun | -12.064 |
Pru | -11.546 |
exha | -11.243 |
Ham | -11.150 |
Token | 167 |
Token ID | 21940 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
CARD | +5.750 |
infect | +5.529 |
iov | +4.037 |
foreskin | +3.685 |
giving | +3.623 |
Neg logit contributions | |
Seym | -20.259 |
Pru | -19.459 |
Corm | -18.735 |
Ham | -18.549 |
Shea | -17.821 |
Token | 101 |
Token ID | 8949 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
CARD | +3.874 |
infect | +3.328 |
foreskin | +3.235 |
helic | +3.201 |
beard | +3.144 |
Neg logit contributions | |
Ham | -2.396 |
Seym | -2.252 |
Pru | -2.115 |
slam | -2.062 |
ouver | -2.025 |
Token | 320 |
Token ID | 19504 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
Ham | +1.461 |
Pru | +1.284 |
Seym | +1.271 |
slam | +1.232 |
Corm | +1.216 |
Neg logit contributions | |
CARD | -2.469 |
infect | -2.170 |
foreskin | -2.095 |
helic | -2.084 |
beard | -2.037 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Ham | +4.293 |
Pru | +3.529 |
Corm | +3.407 |
slam | +3.356 |
Ryan | +3.347 |
Neg logit contributions | |
CARD | -12.264 |
infect | -11.590 |
foreskin | -11.196 |
helic | -11.168 |
beard | -10.809 |
Token | x |
Token ID | 2124 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
CARD | +1.119 |
infect | +0.937 |
foreskin | +0.897 |
helic | +0.884 |
beard | +0.870 |
Neg logit contributions | |
Ham | -1.069 |
Seym | -1.014 |
Pru | -0.984 |
slam | -0.949 |
Corm | -0.935 |
Token | x |
Token ID | 2124 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
CARD | +3.795 |
infect | +3.046 |
foreskin | +2.964 |
beard | +2.898 |
helic | +2.879 |
Neg logit contributions | |
Ham | -4.199 |
Seym | -4.171 |
Pru | -3.907 |
ouver | -3.779 |
encers | -3.752 |
Token | . |
Token ID | 13 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
Ham | +0.365 |
Seym | +0.329 |
Pru | +0.329 |
slam | +0.319 |
Corm | +0.314 |
Neg logit contributions | |
CARD | -0.477 |
infect | -0.411 |
foreskin | -0.393 |
helic | -0.390 |
beard | -0.381 |
Token | x |
Token ID | 87 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
CARD | +4.377 |
infect | +3.735 |
giving | +3.473 |
foreskin | +3.285 |
beard | +3.214 |
Neg logit contributions | |
Seym | -6.253 |
Ham | -5.827 |
Pru | -5.807 |
slam | -5.507 |
Corm | -5.460 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
CARD | +4.958 |
infect | +4.145 |
giving | +3.959 |
foreskin | +3.828 |
beard | +3.772 |
Neg logit contributions | |
Seym | -5.737 |
Ham | -5.253 |
Pru | -5.110 |
slam | -4.875 |
Corm | -4.781 |
Token | x |
Token ID | 87 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
CARD | +6.839 |
infect | +6.514 |
giving | +5.992 |
sters | +5.235 |
iov | +5.133 |
Neg logit contributions | |
Seym | -13.748 |
Pru | -12.913 |
oun | -12.711 |
Ham | -12.257 |
Corm | -12.138 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
CARD | +8.586 |
infect | +8.310 |
giving | +7.382 |
foreskin | +6.835 |
beard | +6.795 |
Neg logit contributions | |
Seym | -15.122 |
oun | -14.579 |
Pru | -14.038 |
Corm | -13.402 |
Ham | -13.375 |
Token | 156 |
Token ID | 21599 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
infect | +8.442 |
CARD | +7.467 |
helic | +6.634 |
giving | +6.628 |
foreskin | +6.249 |
Neg logit contributions | |
Pru | -17.008 |
Seym | -16.656 |
oun | -16.564 |
Corm | -16.383 |
Ham | -16.190 |
Token | 10 |
Token ID | 838 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
CARD | +3.786 |
infect | +3.238 |
foreskin | +3.158 |
helic | +3.114 |
beard | +3.062 |
Neg logit contributions | |
Ham | -2.397 |
Seym | -2.258 |
Pru | -2.121 |
slam | -2.071 |
ouver | -2.030 |
Token | 23 |
Token ID | 1954 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
CARD | +4.432 |
infect | +3.734 |
giving | +3.543 |
foreskin | +3.521 |
beard | +3.459 |
Neg logit contributions | |
Seym | -3.453 |
Ham | -3.379 |
Pru | -3.208 |
slam | -3.084 |
Corm | -3.004 |
Token | 688 |
Token ID | 34427 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
CARD | +2.359 |
infect | +2.044 |
foreskin | +1.946 |
helic | +1.939 |
beard | +1.905 |
Neg logit contributions | |
Ham | -1.556 |
Seym | -1.455 |
Pru | -1.422 |
slam | -1.366 |
Corm | -1.337 |
Token | x |
Token ID | 2124 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
CARD | +2.620 |
infect | +2.147 |
foreskin | +2.070 |
helic | +2.025 |
beard | +2.011 |
Neg logit contributions | |
Ham | -2.755 |
Seym | -2.685 |
Pru | -2.542 |
slam | -2.452 |
ouver | -2.432 |
Token | x |
Token ID | 2124 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
CARD | +3.018 |
infect | +2.447 |
foreskin | +2.358 |
helic | +2.303 |
beard | +2.302 |
Neg logit contributions | |
Ham | -3.169 |
Seym | -3.120 |
Pru | -2.947 |
slam | -2.827 |
ouver | -2.807 |
Token | . |
Token ID | 13 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
Ham | +1.468 |
Pru | +1.293 |
slam | +1.260 |
Corm | +1.246 |
Ryan | +1.245 |
Neg logit contributions | |
CARD | -2.079 |
infect | -1.806 |
foreskin | -1.739 |
helic | -1.738 |
beard | -1.681 |
Token | x |
Token ID | 87 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
CARD | +4.239 |
infect | +3.614 |
giving | +3.351 |
foreskin | +3.187 |
beard | +3.115 |
Neg logit contributions | |
Seym | -5.899 |
Ham | -5.529 |
Pru | -5.479 |
slam | -5.200 |
Corm | -5.173 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
CARD | +4.605 |
infect | +3.870 |
giving | +3.675 |
foreskin | +3.585 |
beard | +3.511 |
Neg logit contributions | |
Seym | -5.109 |
Ham | -4.726 |
Pru | -4.577 |
slam | -4.368 |
Corm | -4.281 |
Token | x |
Token ID | 87 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
CARD | +5.824 |
infect | +5.100 |
giving | +4.824 |
sters | +4.296 |
foreskin | +4.198 |
Neg logit contributions | |
Seym | -10.491 |
Pru | -9.520 |
Ham | -9.318 |
oun | -9.253 |
Corm | -8.977 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e+01 |
Pos logit contributions | |
CARD | +6.854 |
infect | +5.789 |
giving | +5.525 |
foreskin | +5.109 |
beard | +4.943 |
Neg logit contributions | |
Seym | -9.877 |
Pru | -8.565 |
Ham | -8.504 |
oun | -8.496 |
Corm | -8.112 |
Token | 169 |
Token ID | 22172 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
CARD | +7.569 |
infect | +7.324 |
iov | +6.022 |
giving | +5.891 |
foreskin | +5.654 |
Neg logit contributions | |
Seym | -17.362 |
Pru | -16.466 |
Corm | -15.798 |
Ham | -15.455 |
encers | -14.853 |
Token | 11 |
Token ID | 1367 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
CARD | +3.720 |
infect | +3.180 |
foreskin | +3.086 |
helic | +3.048 |
beard | +2.997 |
Neg logit contributions | |
Ham | -2.347 |
Seym | -2.214 |
Pru | -2.076 |
slam | -2.039 |
ouver | -1.991 |
Token | 66 |
Token ID | 2791 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
CARD | +2.389 |
infect | +2.040 |
foreskin | +1.942 |
helic | +1.914 |
beard | +1.894 |
Neg logit contributions | |
Ham | -1.702 |
Seym | -1.637 |
Pru | -1.572 |
slam | -1.516 |
Corm | -1.479 |
Token | 589 |
Token ID | 44169 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
CARD | +0.137 |
infect | +0.119 |
foreskin | +0.114 |
helic | +0.113 |
beard | +0.111 |
Neg logit contributions | |
Ham | -0.086 |
Seym | -0.078 |
Pru | -0.077 |
slam | -0.074 |
Corm | -0.073 |
Token | x |
Token ID | 2124 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
CARD | +0.331 |
infect | +0.280 |
foreskin | +0.268 |
helic | +0.264 |
beard | +0.259 |
Neg logit contributions | |
Ham | -0.302 |
Seym | -0.282 |
Pru | -0.277 |
slam | -0.268 |
Corm | -0.264 |
Token | with |
Token ID | 351 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
CARD | +3.449 |
infect | +2.942 |
beard | +2.822 |
foreskin | +2.818 |
helic | +2.791 |
Neg logit contributions | |
Ham | -2.902 |
Seym | -2.758 |
Pru | -2.638 |
Corm | -2.486 |
encers | -2.484 |
Token | the |
Token ID | 262 |
Feature activation | -7.82e+00 |
Pos logit contributions | |
CARD | +5.601 |
infect | +4.708 |
beard | +4.651 |
foreskin | +4.627 |
helic | +4.578 |
Neg logit contributions | |
Ham | -4.725 |
Seym | -4.497 |
Pru | -4.278 |
encers | -4.146 |
Ryan | -4.117 |
Token | hood |
Token ID | 14263 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
CARD | +6.692 |
beard | +5.652 |
infect | +5.618 |
foreskin | +5.576 |
helic | +5.506 |
Neg logit contributions | |
Ham | -5.185 |
Seym | -4.976 |
Pru | -4.737 |
encers | -4.610 |
Ryan | -4.579 |
Token | pulled |
Token ID | 5954 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
CARD | +9.435 |
infect | +8.241 |
beard | +8.035 |
helic | +7.851 |
foreskin | +7.802 |
Neg logit contributions | |
Seym | -8.911 |
Ham | -8.698 |
Pru | -8.419 |
Corm | -7.768 |
encers | -7.711 |
Token | over |
Token ID | 625 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
CARD | +7.412 |
infect | +6.382 |
beard | +6.321 |
foreskin | +6.226 |
helic | +6.146 |
Neg logit contributions | |
Ham | -7.348 |
Seym | -7.328 |
Pru | -6.818 |
encers | -6.432 |
Corm | -6.340 |
Token | his |
Token ID | 465 |
Feature activation | -1.78e+01 |
Pos logit contributions | |
CARD | +6.838 |
infect | +5.595 |
beard | +5.507 |
foreskin | +5.363 |
helic | +5.148 |
Neg logit contributions | |
Ham | -9.323 |
Seym | -9.275 |
Pru | -8.868 |
encers | -8.550 |
Corm | -8.388 |
Token | face |
Token ID | 1986 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
CARD | +9.799 |
beard | +9.551 |
foreskin | +8.762 |
infect | +8.027 |
helic | +7.785 |
Neg logit contributions | |
Seym | -14.105 |
Ham | -13.913 |
Pru | -13.052 |
encers | -12.855 |
ouver | -12.730 |
Token | walked |
Token ID | 6807 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
CARD | +8.302 |
infect | +7.060 |
beard | +7.048 |
foreskin | +6.774 |
helic | +6.668 |
Neg logit contributions | |
Seym | -6.939 |
Ham | -6.937 |
Pru | -6.394 |
encers | -6.049 |
ouver | -5.953 |
Token | up |
Token ID | 510 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
CARD | +2.235 |
infect | +1.905 |
foreskin | +1.825 |
beard | +1.811 |
helic | +1.806 |
Neg logit contributions | |
Ham | -1.918 |
Seym | -1.793 |
Pru | -1.740 |
encers | -1.647 |
slam | -1.643 |
Token | to |
Token ID | 284 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
CARD | +1.423 |
infect | +1.200 |
foreskin | +1.145 |
helic | +1.135 |
beard | +1.117 |
Neg logit contributions | |
Ham | -1.283 |
Seym | -1.194 |
Pru | -1.177 |
slam | -1.135 |
Corm | -1.121 |
Token | the |
Token ID | 262 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
CARD | +2.409 |
infect | +2.074 |
foreskin | +1.985 |
helic | +1.979 |
beard | +1.954 |
Neg logit contributions | |
Ham | -1.677 |
Seym | -1.549 |
Pru | -1.506 |
slam | -1.442 |
Corm | -1.426 |
Token | both |
Token ID | 1111 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
CARD | +3.334 |
infect | +2.802 |
foreskin | +2.685 |
helic | +2.656 |
beard | +2.613 |
Neg logit contributions | |
Ham | -2.701 |
Seym | -2.523 |
Pru | -2.461 |
slam | -2.355 |
encers | -2.336 |
Token | ends |
Token ID | 5645 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
Ham | +1.000 |
Seym | +0.913 |
Pru | +0.909 |
slam | +0.883 |
Corm | +0.869 |
Neg logit contributions | |
CARD | -1.249 |
infect | -1.075 |
foreskin | -1.027 |
helic | -1.016 |
beard | -0.995 |
Token | of |
Token ID | 286 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
CARD | +5.882 |
infect | +4.956 |
foreskin | +4.739 |
helic | +4.730 |
beard | +4.649 |
Neg logit contributions | |
Ham | -5.039 |
Seym | -4.757 |
Pru | -4.563 |
encers | -4.339 |
Corm | -4.308 |
Token | the |
Token ID | 262 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
CARD | +2.836 |
infect | +2.401 |
foreskin | +2.307 |
helic | +2.287 |
beard | +2.243 |
Neg logit contributions | |
Ham | -2.223 |
Seym | -2.061 |
Pru | -2.016 |
slam | -1.946 |
Corm | -1.908 |
Token | clue |
Token ID | 18437 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
CARD | +4.362 |
infect | +3.679 |
foreskin | +3.565 |
helic | +3.521 |
beard | +3.455 |
Neg logit contributions | |
Ham | -3.472 |
Seym | -3.243 |
Pru | -3.154 |
slam | -3.014 |
encers | -2.990 |
Token | look |
Token ID | 804 |
Feature activation | -1.72e+01 |
Pos logit contributions | |
CARD | +1.848 |
infect | +1.573 |
foreskin | +1.505 |
helic | +1.489 |
beard | +1.465 |
Neg logit contributions | |
Ham | -1.536 |
Seym | -1.430 |
Pru | -1.398 |
slam | -1.337 |
Corm | -1.328 |
Token | like |
Token ID | 588 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
CARD | +13.263 |
infect | +11.000 |
foreskin | +10.522 |
helic | +10.503 |
beard | +10.254 |
Neg logit contributions | |
Ham | -10.595 |
Seym | -10.311 |
encers | -9.555 |
ownt | -9.334 |
Pru | -9.259 |
Token | a |
Token ID | 257 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
CARD | +6.867 |
infect | +5.662 |
foreskin | +5.567 |
helic | +5.526 |
beard | +5.381 |
Neg logit contributions | |
Ham | -5.179 |
Seym | -4.816 |
Pru | -4.562 |
encers | -4.485 |
ownt | -4.437 |
Token | definition |
Token ID | 6770 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
CARD | +4.097 |
infect | +3.442 |
foreskin | +3.353 |
helic | +3.326 |
beard | +3.264 |
Neg logit contributions | |
Ham | -3.111 |
Seym | -2.902 |
Pru | -2.821 |
encers | -2.708 |
slam | -2.668 |
Token | – |
Token ID | 784 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Ham | +0.404 |
Seym | +0.371 |
Pru | +0.366 |
slam | +0.354 |
Corm | +0.349 |
Neg logit contributions | |
CARD | -0.511 |
infect | -0.438 |
foreskin | -0.419 |
helic | -0.415 |
beard | -0.406 |
Token | move |
Token ID | 1445 |
Feature activation | +7.83e+00 |
Pos logit contributions | |
Ham | +0.157 |
Seym | +0.145 |
Pru | +0.143 |
slam | +0.138 |
Corm | +0.136 |
Neg logit contributions | |
CARD | -0.199 |
infect | -0.170 |
foreskin | -0.163 |
helic | -0.161 |
beard | -0.158 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Ham | +2.453 |
Pru | +2.226 |
Seym | +2.216 |
slam | +2.165 |
Corm | +2.122 |
Neg logit contributions | |
CARD | -3.173 |
infect | -2.723 |
foreskin | -2.605 |
helic | -2.591 |
beard | -2.526 |
Token | it |
Token ID | 340 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Ham | +0.320 |
Seym | +0.292 |
Pru | +0.290 |
slam | +0.280 |
Corm | +0.276 |
Neg logit contributions | |
CARD | -0.421 |
infect | -0.363 |
foreskin | -0.347 |
helic | -0.344 |
beard | -0.336 |
Token | for |
Token ID | 329 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
CARD | +1.247 |
infect | +1.071 |
foreskin | +1.024 |
helic | +1.008 |
beard | +0.991 |
Neg logit contributions | |
Ham | -1.055 |
Seym | -0.975 |
Pru | -0.962 |
slam | -0.923 |
Corm | -0.912 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
CARD | +1.857 |
infect | +1.583 |
foreskin | +1.525 |
helic | +1.506 |
beard | +1.482 |
Neg logit contributions | |
Ham | -1.498 |
Seym | -1.385 |
Pru | -1.353 |
slam | -1.295 |
encers | -1.283 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
CARD | +2.018 |
infect | +1.694 |
foreskin | +1.605 |
helic | +1.585 |
beard | +1.553 |
Neg logit contributions | |
Ham | -2.151 |
Seym | -2.033 |
Pru | -1.996 |
slam | -1.923 |
Corm | -1.911 |
Token | ."[ |
Token ID | 18161 |
Feature activation | -1.71e+01 |
Pos logit contributions | |
Ham | +1.968 |
Seym | +1.789 |
Pru | +1.784 |
slam | +1.745 |
Corm | +1.712 |
Neg logit contributions | |
CARD | -2.498 |
infect | -2.141 |
foreskin | -2.045 |
helic | -2.024 |
beard | -1.976 |
Token | 154 |
Token ID | 21526 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
CARD | +10.411 |
infect | +9.351 |
giving | +8.612 |
helic | +8.018 |
beard | +7.917 |
Neg logit contributions | |
Ham | -12.500 |
Pru | -12.358 |
Seym | -11.961 |
ouver | -11.896 |
slam | -11.833 |
Token | ] |
Token ID | 60 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
CARD | +1.855 |
infect | +1.565 |
foreskin | +1.490 |
helic | +1.473 |
beard | +1.437 |
Neg logit contributions | |
Ham | -1.818 |
Seym | -1.678 |
Pru | -1.671 |
slam | -1.619 |
Corm | -1.596 |
Token | The |
Token ID | 383 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
CARD | +1.034 |
infect | +0.875 |
foreskin | +0.839 |
helic | +0.826 |
beard | +0.811 |
Neg logit contributions | |
Ham | -0.821 |
Seym | -0.767 |
Pru | -0.739 |
slam | -0.727 |
ouver | -0.707 |
Token | game |
Token ID | 983 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
CARD | +0.026 |
infect | +0.022 |
foreskin | +0.021 |
helic | +0.021 |
beard | +0.020 |
Neg logit contributions | |
Ham | -0.021 |
Seym | -0.020 |
Pru | -0.019 |
slam | -0.019 |
Corm | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Ham | +1.104 |
Seym | +1.012 |
Pru | +1.006 |
slam | +0.977 |
Corm | +0.962 |
Neg logit contributions | |
CARD | -1.299 |
infect | -1.111 |
foreskin | -1.060 |
helic | -1.049 |
beard | -1.026 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Ham | +1.335 |
Pru | +1.175 |
slam | +1.144 |
Seym | +1.129 |
Corm | +1.127 |
Neg logit contributions | |
CARD | -1.982 |
infect | -1.724 |
helic | -1.665 |
foreskin | -1.662 |
beard | -1.609 |
Token | But |
Token ID | 1537 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Ham | +1.514 |
Pru | +1.248 |
Seym | +1.240 |
slam | +1.215 |
Ryan | +1.214 |
Neg logit contributions | |
CARD | -3.256 |
infect | -2.870 |
foreskin | -2.807 |
helic | -2.794 |
beard | -2.734 |
Token | DON |
Token ID | 23917 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
CARD | +0.994 |
infect | +0.842 |
foreskin | +0.811 |
helic | +0.801 |
beard | +0.788 |
Neg logit contributions | |
Ham | -0.841 |
Seym | -0.784 |
Pru | -0.767 |
slam | -0.731 |
Corm | -0.727 |
Token | � |
Token ID | 447 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
CARD | +3.780 |
infect | +3.099 |
foreskin | +2.930 |
helic | +2.922 |
beard | +2.898 |
Neg logit contributions | |
Ham | -3.282 |
Seym | -3.226 |
Pru | -3.045 |
slam | -2.984 |
ouver | -2.953 |
Token | � |
Token ID | 247 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
Ham | +1.412 |
Pru | +1.258 |
Seym | +1.251 |
slam | +1.221 |
Ryan | +1.192 |
Neg logit contributions | |
CARD | -2.073 |
infect | -1.801 |
foreskin | -1.731 |
helic | -1.722 |
beard | -1.678 |
Token | T |
Token ID | 51 |
Feature activation | -1.70e+01 |
Pos logit contributions | |
CARD | +0.567 |
infect | +0.484 |
foreskin | +0.459 |
helic | +0.455 |
beard | +0.446 |
Neg logit contributions | |
Ham | -0.494 |
Seym | -0.459 |
Pru | -0.454 |
slam | -0.439 |
Corm | -0.432 |
Token | DO |
Token ID | 8410 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
CARD | +13.036 |
infect | +9.644 |
helic | +9.595 |
beard | +9.495 |
foreskin | +9.410 |
Neg logit contributions | |
Seym | -11.619 |
Ham | -11.402 |
Pru | -10.648 |
encers | -10.387 |
ouver | -10.168 |
Token | IT |
Token ID | 7283 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
CARD | +4.583 |
infect | +3.503 |
foreskin | +3.330 |
helic | +3.261 |
beard | +3.210 |
Neg logit contributions | |
Ham | -5.034 |
Seym | -5.000 |
Pru | -4.744 |
slam | -4.598 |
encers | -4.534 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Ham | +0.342 |
Seym | +0.316 |
Pru | +0.313 |
slam | +0.304 |
Corm | +0.300 |
Neg logit contributions | |
CARD | -0.362 |
infect | -0.306 |
foreskin | -0.291 |
helic | -0.288 |
beard | -0.281 |
Token |
|
Token ID | 198 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
Ham | +1.347 |
Seym | +1.227 |
Pru | +1.223 |
slam | +1.186 |
Corm | +1.170 |
Neg logit contributions | |
CARD | -1.683 |
infect | -1.453 |
foreskin | -1.388 |
helic | -1.377 |
beard | -1.344 |
Token |
|
Token ID | 198 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Ham | +2.733 |
Pru | +2.301 |
Ryan | +2.281 |
slam | +2.266 |
Corm | +2.242 |
Neg logit contributions | |
CARD | -4.563 |
infect | -4.018 |
helic | -3.963 |
foreskin | -3.898 |
beard | -3.768 |
Token | E |
Token ID | 36 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Ham | +1.557 |
Pru | +1.409 |
Seym | +1.398 |
slam | +1.367 |
Corm | +1.367 |
Neg logit contributions | |
CARD | -1.488 |
infect | -1.262 |
foreskin | -1.201 |
helic | -1.193 |
beard | -1.157 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Ham | +2.297 |
Seym | +2.102 |
Pru | +2.089 |
slam | +2.015 |
Corm | +2.001 |
Neg logit contributions | |
CARD | -3.114 |
infect | -2.731 |
foreskin | -2.603 |
helic | -2.581 |
beard | -2.514 |
Token | DP |
Token ID | 6322 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
CARD | +2.182 |
infect | +1.894 |
foreskin | +1.803 |
helic | +1.792 |
beard | +1.761 |
Neg logit contributions | |
Ham | -1.468 |
Seym | -1.343 |
Pru | -1.335 |
slam | -1.290 |
Corm | -1.260 |
Token | 02 |
Token ID | 2999 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Ham | +0.046 |
Seym | +0.040 |
Pru | +0.039 |
slam | +0.037 |
Corm | +0.036 |
Neg logit contributions | |
CARD | -0.116 |
infect | -0.104 |
foreskin | -0.100 |
helic | -0.100 |
beard | -0.098 |
Token | _ |
Token ID | 62 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Ham | +0.549 |
Pru | +0.489 |
Seym | +0.487 |
slam | +0.473 |
Corm | +0.465 |
Neg logit contributions | |
CARD | -0.823 |
infect | -0.716 |
foreskin | -0.689 |
helic | -0.684 |
beard | -0.669 |
Token | 00 |
Token ID | 405 |
Feature activation | -1.69e+01 |
Pos logit contributions | |
CARD | +2.282 |
infect | +1.994 |
foreskin | +1.908 |
helic | +1.890 |
beard | +1.862 |
Neg logit contributions | |
Ham | -1.375 |
Seym | -1.262 |
Pru | -1.241 |
slam | -1.194 |
Corm | -1.176 |
Token | 65 |
Token ID | 2996 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
CARD | +8.408 |
infect | +6.285 |
giving | +5.214 |
foreskin | +5.191 |
helic | +5.061 |
Neg logit contributions | |
Seym | -15.912 |
Pru | -14.945 |
slam | -14.433 |
Corm | -14.245 |
Ham | -14.221 |
Token | E |
Token ID | 36 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Ham | +1.741 |
Pru | +1.575 |
Seym | +1.560 |
slam | +1.529 |
Corm | +1.527 |
Neg logit contributions | |
CARD | -1.676 |
infect | -1.420 |
foreskin | -1.354 |
helic | -1.344 |
beard | -1.303 |
Token | & |
Token ID | 5 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
Ham | +2.105 |
Seym | +1.927 |
Pru | +1.916 |
slam | +1.846 |
Corm | +1.833 |
Neg logit contributions | |
CARD | -2.855 |
infect | -2.497 |
foreskin | -2.384 |
helic | -2.361 |
beard | -2.303 |
Token | for |
Token ID | 1640 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
CARD | +0.689 |
infect | +0.593 |
foreskin | +0.561 |
helic | +0.555 |
beard | +0.545 |
Neg logit contributions | |
Ham | -0.572 |
Seym | -0.530 |
Pru | -0.526 |
slam | -0.508 |
Corm | -0.501 |
Token | = |
Token ID | 28 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
CARD | +1.257 |
infect | +1.089 |
foreskin | +1.025 |
helic | +1.017 |
beard | +0.994 |
Neg logit contributions | |
Ham | -1.036 |
Seym | -0.974 |
Pru | -0.957 |
slam | -0.925 |
Corm | -0.915 |
Token | 38 |
Token ID | 2548 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
Ham | +3.742 |
Ryan | +3.123 |
Pru | +3.080 |
Corm | +3.077 |
7601 | +3.039 |
Neg logit contributions | |
CARD | -6.522 |
infect | -5.872 |
helic | -5.762 |
foreskin | -5.727 |
beard | -5.552 |
Token | x |
Token ID | 2124 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
CARD | +3.795 |
infect | +3.046 |
foreskin | +2.964 |
beard | +2.898 |
helic | +2.879 |
Neg logit contributions | |
Ham | -4.199 |
Seym | -4.171 |
Pru | -3.907 |
ouver | -3.779 |
encers | -3.752 |
Token | . |
Token ID | 13 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
Ham | +0.365 |
Seym | +0.329 |
Pru | +0.329 |
slam | +0.319 |
Corm | +0.314 |
Neg logit contributions | |
CARD | -0.477 |
infect | -0.411 |
foreskin | -0.393 |
helic | -0.390 |
beard | -0.381 |
Token | x |
Token ID | 87 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
CARD | +4.377 |
infect | +3.735 |
giving | +3.473 |
foreskin | +3.285 |
beard | +3.214 |
Neg logit contributions | |
Seym | -6.253 |
Ham | -5.827 |
Pru | -5.807 |
slam | -5.507 |
Corm | -5.460 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
CARD | +4.958 |
infect | +4.145 |
giving | +3.959 |
foreskin | +3.828 |
beard | +3.772 |
Neg logit contributions | |
Seym | -5.737 |
Ham | -5.253 |
Pru | -5.110 |
slam | -4.875 |
Corm | -4.781 |
Token | x |
Token ID | 87 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
CARD | +6.839 |
infect | +6.514 |
giving | +5.992 |
sters | +5.235 |
iov | +5.133 |
Neg logit contributions | |
Seym | -13.748 |
Pru | -12.913 |
oun | -12.711 |
Ham | -12.257 |
Corm | -12.138 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
CARD | +8.586 |
infect | +8.310 |
giving | +7.382 |
foreskin | +6.835 |
beard | +6.795 |
Neg logit contributions | |
Seym | -15.122 |
oun | -14.579 |
Pru | -14.038 |
Corm | -13.402 |
Ham | -13.375 |
Token | 156 |
Token ID | 21599 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
infect | +8.442 |
CARD | +7.467 |
helic | +6.634 |
giving | +6.628 |
foreskin | +6.249 |
Neg logit contributions | |
Pru | -17.008 |
Seym | -16.656 |
oun | -16.564 |
Corm | -16.383 |
Ham | -16.190 |
Token | 10 |
Token ID | 838 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
CARD | +3.786 |
infect | +3.238 |
foreskin | +3.158 |
helic | +3.114 |
beard | +3.062 |
Neg logit contributions | |
Ham | -2.397 |
Seym | -2.258 |
Pru | -2.121 |
slam | -2.071 |
ouver | -2.030 |
Token | 23 |
Token ID | 1954 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
CARD | +4.432 |
infect | +3.734 |
giving | +3.543 |
foreskin | +3.521 |
beard | +3.459 |
Neg logit contributions | |
Seym | -3.453 |
Ham | -3.379 |
Pru | -3.208 |
slam | -3.084 |
Corm | -3.004 |
Token | 688 |
Token ID | 34427 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
CARD | +2.359 |
infect | +2.044 |
foreskin | +1.946 |
helic | +1.939 |
beard | +1.905 |
Neg logit contributions | |
Ham | -1.556 |
Seym | -1.455 |
Pru | -1.422 |
slam | -1.366 |
Corm | -1.337 |
Token | x |
Token ID | 2124 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Ham | +2.550 |
Pru | +2.313 |
slam | +2.260 |
Seym | +2.252 |
Corm | +2.224 |
Neg logit contributions | |
CARD | -3.216 |
infect | -2.795 |
foreskin | -2.653 |
helic | -2.637 |
beard | -2.558 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
Ham | +1.133 |
Pru | +1.007 |
Seym | +0.986 |
slam | +0.979 |
Corm | +0.967 |
Neg logit contributions | |
CARD | -1.550 |
infect | -1.343 |
foreskin | -1.290 |
helic | -1.285 |
beard | -1.248 |
Token | x |
Token ID | 87 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
CARD | +3.581 |
infect | +3.048 |
giving | +2.794 |
foreskin | +2.743 |
beard | +2.665 |
Neg logit contributions | |
Seym | -4.590 |
Ham | -4.415 |
Pru | -4.322 |
slam | -4.119 |
Corm | -4.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
CARD | +3.669 |
infect | +3.085 |
foreskin | +2.892 |
giving | +2.891 |
beard | +2.827 |
Neg logit contributions | |
Seym | -3.713 |
Ham | -3.545 |
Pru | -3.382 |
slam | -3.244 |
Corm | -3.175 |
Token | x |
Token ID | 87 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
CARD | +6.007 |
infect | +5.287 |
giving | +4.953 |
sters | +4.426 |
foreskin | +4.406 |
Neg logit contributions | |
Seym | -10.288 |
Pru | -9.482 |
Ham | -9.277 |
oun | -9.038 |
Corm | -8.949 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e+01 |
Pos logit contributions | |
CARD | +7.966 |
infect | +6.677 |
giving | +6.429 |
foreskin | +5.824 |
sters | +5.638 |
Neg logit contributions | |
Seym | -12.450 |
oun | -11.022 |
Pru | -10.790 |
Ham | -10.633 |
Corm | -10.270 |
Token | 164 |
Token ID | 23237 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
CARD | +7.594 |
infect | +7.148 |
giving | +6.111 |
foreskin | +5.460 |
iov | +5.409 |
Neg logit contributions | |
Seym | -15.655 |
Pru | -14.965 |
Ham | -14.665 |
Corm | -14.641 |
slam | -14.094 |
Token | 103 |
Token ID | 15349 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
CARD | +4.509 |
infect | +3.850 |
foreskin | +3.741 |
helic | +3.696 |
beard | +3.615 |
Neg logit contributions | |
Ham | -2.860 |
Seym | -2.726 |
Pru | -2.540 |
slam | -2.476 |
ouver | -2.442 |
Token | 15 |
Token ID | 1314 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
CARD | +0.729 |
infect | +0.628 |
foreskin | +0.603 |
helic | +0.596 |
beard | +0.586 |
Neg logit contributions | |
Ham | -0.457 |
Seym | -0.429 |
Pru | -0.414 |
slam | -0.401 |
Corm | -0.388 |
Token | 24 |
Token ID | 1731 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Ham | +0.826 |
Seym | +0.739 |
Pru | +0.736 |
slam | +0.711 |
Corm | +0.700 |
Neg logit contributions | |
CARD | -1.271 |
infect | -1.109 |
foreskin | -1.065 |
helic | -1.057 |
beard | -1.035 |
Token | x |
Token ID | 2124 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
CARD | +1.866 |
infect | +1.546 |
foreskin | +1.487 |
helic | +1.460 |
beard | +1.445 |
Neg logit contributions | |
Ham | -1.835 |
Seym | -1.759 |
Pru | -1.692 |
slam | -1.632 |
Corm | -1.607 |
Token | planet |
Token ID | 5440 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
CARD | +0.374 |
infect | +0.315 |
foreskin | +0.302 |
helic | +0.298 |
beard | +0.291 |
Neg logit contributions | |
Ham | -0.352 |
Seym | -0.323 |
Pru | -0.321 |
slam | -0.312 |
Ryan | -0.307 |
Token | Venus |
Token ID | 21094 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Ham | +1.162 |
Seym | +1.068 |
Pru | +1.060 |
slam | +1.029 |
Corm | +1.014 |
Neg logit contributions | |
CARD | -1.324 |
infect | -1.129 |
foreskin | -1.076 |
helic | -1.065 |
beard | -1.041 |
Token | in |
Token ID | 287 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Ham | +0.938 |
Seym | +0.855 |
Pru | +0.849 |
slam | +0.823 |
Corm | +0.810 |
Neg logit contributions | |
CARD | -1.238 |
infect | -1.068 |
foreskin | -1.021 |
helic | -1.012 |
beard | -0.990 |
Token | her |
Token ID | 607 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
CARD | +1.560 |
infect | +1.323 |
foreskin | +1.285 |
helic | +1.267 |
beard | +1.249 |
Neg logit contributions | |
Ham | -1.224 |
Seym | -1.106 |
Pru | -1.085 |
encers | -1.053 |
Ryan | -1.046 |
Token | honor |
Token ID | 7522 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Ham | +0.214 |
Seym | +0.195 |
Pru | +0.192 |
slam | +0.185 |
Corm | +0.183 |
Neg logit contributions | |
CARD | -0.299 |
infect | -0.258 |
foreskin | -0.249 |
helic | -0.246 |
beard | -0.242 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.66e+01 |
Pos logit contributions | |
CARD | +0.953 |
infect | +0.815 |
foreskin | +0.780 |
helic | +0.770 |
beard | +0.755 |
Neg logit contributions | |
Ham | -0.783 |
Seym | -0.720 |
Pru | -0.713 |
slam | -0.689 |
Corm | -0.679 |
Token | 55 |
Token ID | 2816 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
CARD | +9.566 |
infect | +7.895 |
giving | +7.157 |
beard | +7.092 |
foreskin | +6.983 |
Neg logit contributions | |
Ham | -13.078 |
Seym | -13.035 |
Pru | -12.999 |
slam | -12.458 |
ouver | -12.381 |
Token | ] |
Token ID | 60 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
CARD | +2.419 |
infect | +2.029 |
foreskin | +1.937 |
helic | +1.906 |
beard | +1.861 |
Neg logit contributions | |
Ham | -2.416 |
Seym | -2.232 |
Pru | -2.227 |
slam | -2.154 |
Corm | -2.128 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
CARD | +1.556 |
infect | +1.319 |
foreskin | +1.270 |
helic | +1.240 |
beard | +1.222 |
Neg logit contributions | |
Ham | -1.239 |
Seym | -1.139 |
Pru | -1.118 |
slam | -1.102 |
encers | -1.065 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
CARD | +1.572 |
infect | +1.347 |
foreskin | +1.278 |
helic | +1.247 |
beard | +1.242 |
Neg logit contributions | |
Ham | -1.277 |
Seym | -1.251 |
Pru | -1.188 |
slam | -1.143 |
Corm | -1.121 |
Token | In |
Token ID | 818 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Ham | +0.084 |
Seym | +0.078 |
Pru | +0.077 |
slam | +0.074 |
Corm | +0.073 |
Neg logit contributions | |
CARD | -0.124 |
infect | -0.108 |
foreskin | -0.103 |
helic | -0.102 |
beard | -0.100 |
Token | VPN |
Token ID | 21669 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Ham | +3.245 |
Pru | +3.003 |
Seym | +2.961 |
slam | +2.906 |
Corm | +2.887 |
Neg logit contributions | |
CARD | -2.724 |
infect | -2.260 |
foreskin | -2.166 |
helic | -2.108 |
beard | -2.072 |
Token | s |
Token ID | 82 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Ham | +2.715 |
Pru | +2.450 |
Seym | +2.431 |
slam | +2.371 |
Corm | +2.343 |
Neg logit contributions | |
CARD | -3.565 |
infect | -3.094 |
foreskin | -2.976 |
helic | -2.923 |
beard | -2.877 |
Token | ! |
Token ID | 0 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
Ham | +1.693 |
Seym | +1.540 |
Pru | +1.538 |
slam | +1.488 |
Corm | +1.470 |
Neg logit contributions | |
CARD | -2.162 |
infect | -1.866 |
foreskin | -1.788 |
helic | -1.768 |
beard | -1.732 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
CARD | +2.108 |
infect | +1.803 |
foreskin | +1.712 |
helic | +1.702 |
beard | +1.665 |
Neg logit contributions | |
Ham | -1.667 |
Seym | -1.538 |
Pru | -1.509 |
slam | -1.474 |
Corm | -1.439 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
CARD | +0.013 |
infect | +0.011 |
foreskin | +0.011 |
helic | +0.010 |
beard | +0.010 |
Neg logit contributions | |
Ham | -0.010 |
Seym | -0.009 |
Pru | -0.009 |
slam | -0.008 |
Corm | -0.008 |
Token | HOW |
Token ID | 37181 |
Feature activation | -1.66e+01 |
Pos logit contributions | |
CARD | +1.340 |
infect | +1.178 |
foreskin | +1.099 |
helic | +1.088 |
beard | +1.068 |
Neg logit contributions | |
Ham | -0.984 |
Seym | -0.941 |
Pru | -0.919 |
slam | -0.892 |
Corm | -0.871 |
Token | TO |
Token ID | 5390 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
CARD | +9.583 |
DATA | +6.296 |
infect | +6.283 |
foreskin | +6.180 |
beard | +5.966 |
Neg logit contributions | |
Seym | -14.947 |
Ham | -14.100 |
Pru | -13.868 |
ouver | -13.462 |
slam | -13.333 |
Token | INST |
Token ID | 40589 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
CARD | +5.931 |
infect | +4.494 |
foreskin | +4.216 |
helic | +4.129 |
DATA | +4.124 |
Neg logit contributions | |
Ham | -6.545 |
Seym | -6.535 |
Pru | -6.076 |
ouver | -6.011 |
encers | -5.945 |
Token | ALL |
Token ID | 7036 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
CARD | +1.767 |
infect | +1.417 |
foreskin | +1.331 |
helic | +1.321 |
beard | +1.276 |
Neg logit contributions | |
Ham | -1.999 |
Seym | -1.931 |
Pru | -1.859 |
slam | -1.805 |
Corm | -1.776 |
Token | NET |
Token ID | 30502 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
CARD | +4.633 |
infect | +3.751 |
foreskin | +3.591 |
helic | +3.507 |
beard | +3.445 |
Neg logit contributions | |
Ham | -4.221 |
Seym | -4.054 |
slam | -3.775 |
Pru | -3.755 |
ouver | -3.697 |
Token | FL |
Token ID | 3697 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
CARD | +4.868 |
infect | +3.941 |
helic | +3.637 |
foreskin | +3.592 |
giving | +3.519 |
Neg logit contributions | |
Seym | -5.179 |
Ham | -4.924 |
Pru | -4.924 |
Corm | -4.685 |
slam | -4.670 |
Token | has |
Token ID | 468 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
Ham | +1.375 |
Seym | +1.253 |
Pru | +1.245 |
slam | +1.206 |
Corm | +1.187 |
Neg logit contributions | |
CARD | -1.802 |
infect | -1.552 |
foreskin | -1.485 |
helic | -1.471 |
beard | -1.440 |
Token | one |
Token ID | 530 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
Ham | +3.621 |
Pru | +3.315 |
Seym | +3.273 |
slam | +3.207 |
Corm | +3.139 |
Neg logit contributions | |
CARD | -5.169 |
infect | -4.497 |
foreskin | -4.250 |
helic | -4.197 |
beard | -4.133 |
Token | nuclear |
Token ID | 4523 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
Ham | +4.479 |
Pru | +4.128 |
Seym | +4.062 |
slam | +4.023 |
Corm | +3.953 |
Neg logit contributions | |
CARD | -6.207 |
infect | -5.431 |
foreskin | -5.101 |
helic | -5.026 |
beard | -4.931 |
Token | - |
Token ID | 12 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Ham | +3.622 |
Pru | +3.293 |
Seym | +3.267 |
slam | +3.240 |
Corm | +3.170 |
Neg logit contributions | |
CARD | -4.743 |
infect | -4.098 |
foreskin | -3.896 |
helic | -3.843 |
beard | -3.784 |
Token | powered |
Token ID | 12293 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
Ham | +1.954 |
Seym | +1.788 |
Pru | +1.786 |
slam | +1.744 |
Corm | +1.716 |
Neg logit contributions | |
CARD | -1.855 |
infect | -1.533 |
foreskin | -1.478 |
helic | -1.457 |
beard | -1.429 |
Token | cruiser |
Token ID | 35239 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
Ham | +4.316 |
Pru | +3.936 |
Seym | +3.917 |
slam | +3.866 |
Corm | +3.853 |
Neg logit contributions | |
CARD | -5.900 |
infect | -5.151 |
foreskin | -4.859 |
helic | -4.747 |
beard | -4.682 |
Token | in |
Token ID | 287 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Ham | +7.152 |
Pru | +6.628 |
slam | +6.613 |
Corm | +6.386 |
compliment | +6.252 |
Neg logit contributions | |
CARD | -10.610 |
infect | -9.467 |
foreskin | -8.794 |
helic | -8.709 |
beard | -8.552 |
Token | operation |
Token ID | 4905 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Ham | +1.692 |
Seym | +1.539 |
Pru | +1.529 |
slam | +1.479 |
Corm | +1.456 |
Neg logit contributions | |
CARD | -2.349 |
infect | -2.034 |
foreskin | -1.945 |
helic | -1.927 |
beard | -1.888 |
Token | and |
Token ID | 290 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
Ham | +1.532 |
Seym | +1.401 |
Pru | +1.392 |
slam | +1.351 |
Corm | +1.332 |
Neg logit contributions | |
CARD | -1.906 |
infect | -1.640 |
foreskin | -1.563 |
helic | -1.549 |
beard | -1.515 |
Token | three |
Token ID | 1115 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
Ham | +2.279 |
Seym | +2.072 |
Pru | +2.072 |
slam | +2.009 |
Corm | +1.973 |
Neg logit contributions | |
CARD | -3.028 |
infect | -2.618 |
foreskin | -2.492 |
helic | -2.469 |
beard | -2.420 |
Token | others |
Token ID | 1854 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Ham | +3.919 |
Pru | +3.572 |
Seym | +3.548 |
slam | +3.501 |
Corm | +3.440 |
Neg logit contributions | |
CARD | -5.660 |
infect | -4.944 |
foreskin | -4.707 |
helic | -4.598 |
beard | -4.556 |
Token | hours |
Token ID | 2250 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
Ham | +0.808 |
Seym | +0.740 |
Pru | +0.734 |
slam | +0.711 |
Corm | +0.700 |
Neg logit contributions | |
CARD | -1.004 |
infect | -0.862 |
foreskin | -0.823 |
helic | -0.815 |
beard | -0.798 |
Token | . |
Token ID | 13 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
Ham | +2.774 |
Pru | +2.463 |
Seym | +2.459 |
slam | +2.415 |
Ryan | +2.357 |
Neg logit contributions | |
CARD | -3.574 |
infect | -3.091 |
foreskin | -2.945 |
helic | -2.916 |
beard | -2.844 |
Token | Now |
Token ID | 3844 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Ham | +3.904 |
Pru | +3.453 |
Seym | +3.398 |
slam | +3.318 |
Corm | +3.299 |
Neg logit contributions | |
CARD | -5.373 |
infect | -4.670 |
foreskin | -4.503 |
helic | -4.442 |
beard | -4.345 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Ham | +0.436 |
Seym | +0.401 |
Pru | +0.396 |
slam | +0.383 |
Corm | +0.378 |
Neg logit contributions | |
CARD | -0.543 |
infect | -0.466 |
foreskin | -0.445 |
helic | -0.441 |
beard | -0.432 |
Token | to |
Token ID | 284 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
CARD | +1.000 |
infect | +0.854 |
foreskin | +0.820 |
helic | +0.814 |
beard | +0.795 |
Neg logit contributions | |
Ham | -0.812 |
Seym | -0.752 |
Pru | -0.739 |
slam | -0.708 |
Corm | -0.705 |
Token | be |
Token ID | 307 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
Ham | +2.585 |
Pru | +2.341 |
Seym | +2.326 |
slam | +2.300 |
Corm | +2.228 |
Neg logit contributions | |
CARD | -3.324 |
infect | -2.863 |
foreskin | -2.731 |
helic | -2.701 |
beard | -2.646 |
Token | clear |
Token ID | 1598 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Ham | +7.210 |
Pru | +6.707 |
slam | +6.559 |
compliment | +6.234 |
Corm | +6.144 |
Neg logit contributions | |
CARD | -12.173 |
infect | -10.390 |
helic | -10.259 |
foreskin | -10.102 |
beard | -9.790 |
Token | , |
Token ID | 11 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
CARD | +1.034 |
infect | +0.882 |
foreskin | +0.843 |
helic | +0.835 |
beard | +0.818 |
Neg logit contributions | |
Ham | -0.871 |
Seym | -0.806 |
Pru | -0.794 |
slam | -0.770 |
Corm | -0.758 |
Token | we |
Token ID | 356 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
Ham | +0.006 |
Seym | +0.005 |
Pru | +0.005 |
slam | +0.005 |
Corm | +0.005 |
Neg logit contributions | |
CARD | -0.008 |
infect | -0.007 |
foreskin | -0.007 |
helic | -0.007 |
beard | -0.006 |
Token | are |
Token ID | 389 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
CARD | +0.837 |
infect | +0.717 |
foreskin | +0.687 |
helic | +0.679 |
beard | +0.664 |
Neg logit contributions | |
Ham | -0.718 |
Seym | -0.670 |
Pru | -0.653 |
Corm | -0.627 |
slam | -0.627 |
Token | not |
Token ID | 407 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
Ham | +0.859 |
Seym | +0.781 |
Pru | +0.777 |
slam | +0.753 |
Corm | +0.739 |
Neg logit contributions | |
CARD | -1.152 |
infect | -0.994 |
foreskin | -0.950 |
helic | -0.942 |
beard | -0.922 |
Token | AC |
Token ID | 2246 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
CARD | +3.692 |
infect | +3.269 |
foreskin | +3.002 |
helic | +2.954 |
giving | +2.951 |
Neg logit contributions | |
Seym | -2.581 |
Ham | -2.564 |
Pru | -2.486 |
slam | -2.347 |
Corm | -2.335 |
Token | LU |
Token ID | 41596 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
CARD | +2.205 |
infect | +1.815 |
foreskin | +1.672 |
helic | +1.648 |
beard | +1.612 |
Neg logit contributions | |
Ham | -2.868 |
Seym | -2.791 |
Pru | -2.707 |
slam | -2.618 |
Corm | -2.602 |
Token | _ |
Token ID | 62 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
CARD | +0.124 |
infect | +0.108 |
foreskin | +0.103 |
helic | +0.102 |
beard | +0.100 |
Neg logit contributions | |
Ham | -0.086 |
Seym | -0.079 |
Pru | -0.078 |
slam | -0.075 |
Corm | -0.074 |
Token | OR |
Token ID | 1581 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
CARD | +1.515 |
infect | +1.310 |
foreskin | +1.241 |
helic | +1.215 |
beard | +1.204 |
Neg logit contributions | |
Ham | -1.126 |
Seym | -1.080 |
Pru | -1.039 |
slam | -1.006 |
Corm | -0.986 |
Token | ) |
Token ID | 8 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
CARD | +4.635 |
infect | +3.801 |
giving | +3.566 |
foreskin | +3.532 |
beard | +3.447 |
Neg logit contributions | |
Seym | -5.616 |
Ham | -5.286 |
Pru | -5.134 |
slam | -4.965 |
ouver | -4.868 |
Token | May |
Token ID | 1737 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
CARD | +0.413 |
infect | +0.356 |
foreskin | +0.341 |
helic | +0.338 |
beard | +0.331 |
Neg logit contributions | |
Ham | -0.311 |
Seym | -0.284 |
Pru | -0.282 |
slam | -0.272 |
Corm | -0.268 |
Token | 29 |
Token ID | 2808 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
Ham | +4.176 |
Pru | +3.566 |
Corm | +3.303 |
Ryan | +3.195 |
Seym | +3.173 |
Neg logit contributions | |
CARD | -16.038 |
infect | -14.697 |
helic | -13.927 |
beard | -13.859 |
foreskin | -13.848 |
Token | , |
Token ID | 11 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
Ham | +3.275 |
Pru | +2.827 |
slam | +2.747 |
Ryan | +2.747 |
Corm | +2.745 |
Neg logit contributions | |
CARD | -5.137 |
infect | -4.528 |
helic | -4.440 |
foreskin | -4.366 |
beard | -4.204 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
Ham | +1.915 |
Pru | +1.686 |
Corm | +1.620 |
slam | +1.604 |
Ryan | +1.583 |
Neg logit contributions | |
CARD | -3.552 |
infect | -3.176 |
helic | -3.083 |
foreskin | -3.041 |
beard | -2.943 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
CARD | +2.754 |
infect | +2.353 |
foreskin | +2.243 |
helic | +2.218 |
beard | +2.182 |
Neg logit contributions | |
Ham | -2.189 |
Seym | -2.026 |
Pru | -1.990 |
slam | -1.915 |
Corm | -1.897 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Ham | +1.335 |
Pru | +1.175 |
slam | +1.144 |
Seym | +1.129 |
Corm | +1.127 |
Neg logit contributions | |
CARD | -1.982 |
infect | -1.724 |
helic | -1.665 |
foreskin | -1.662 |
beard | -1.609 |
Token | 's |
Token ID | 338 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
Ham | +2.405 |
Pru | +2.174 |
Seym | +2.162 |
slam | +2.123 |
Corm | +2.070 |
Neg logit contributions | |
CARD | -3.415 |
infect | -2.957 |
foreskin | -2.825 |
helic | -2.803 |
beard | -2.726 |
Token | reference |
Token ID | 4941 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
Ham | +3.773 |
Pru | +3.480 |
slam | +3.451 |
Seym | +3.428 |
Corm | +3.318 |
Neg logit contributions | |
CARD | -4.919 |
infect | -4.317 |
foreskin | -4.030 |
helic | -4.016 |
beard | -3.858 |
Token | to |
Token ID | 284 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
CARD | +3.041 |
infect | +2.557 |
foreskin | +2.448 |
helic | +2.414 |
beard | +2.371 |
Neg logit contributions | |
Ham | -2.829 |
Seym | -2.640 |
Pru | -2.595 |
slam | -2.500 |
Corm | -2.480 |
Token | the |
Token ID | 262 |
Feature activation | +6.23e+00 |
Pos logit contributions | |
Ham | +4.598 |
Pru | +4.192 |
slam | +4.121 |
Seym | +4.119 |
Corm | +4.016 |
Neg logit contributions | |
CARD | -6.438 |
infect | -5.645 |
foreskin | -5.297 |
helic | -5.251 |
beard | -5.115 |
Token | US |
Token ID | 1294 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Ham | +4.260 |
Pru | +3.948 |
Seym | +3.890 |
slam | +3.856 |
Corm | +3.766 |
Neg logit contributions | |
CARD | -5.311 |
infect | -4.623 |
foreskin | -4.311 |
helic | -4.296 |
beard | -4.180 |
Token | - |
Token ID | 12 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
Ham | +1.475 |
Seym | +1.346 |
Pru | +1.339 |
slam | +1.301 |
Corm | +1.279 |
Neg logit contributions | |
CARD | -1.823 |
infect | -1.567 |
foreskin | -1.495 |
helic | -1.479 |
beard | -1.446 |
Token | led |
Token ID | 992 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Ham | +6.745 |
Ryan | +5.671 |
Pru | +5.370 |
slam | +5.341 |
Sham | +5.321 |
Neg logit contributions | |
CARD | -11.310 |
foreskin | -9.801 |
helic | -9.605 |
infect | -9.485 |
beard | -9.469 |
Token | NATO |
Token ID | 11332 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
Ham | +4.001 |
Pru | +3.696 |
Seym | +3.646 |
slam | +3.637 |
Corm | +3.551 |
Neg logit contributions | |
CARD | -4.254 |
infect | -3.669 |
foreskin | -3.431 |
helic | -3.327 |
beard | -3.299 |
Token | military |
Token ID | 2422 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Ham | +0.763 |
Seym | +0.710 |
Pru | +0.704 |
slam | +0.684 |
Corm | +0.677 |
Neg logit contributions | |
CARD | -0.679 |
infect | -0.564 |
foreskin | -0.535 |
helic | -0.531 |
beard | -0.515 |
Token | alliance |
Token ID | 12801 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Ham | +2.142 |
Pru | +1.980 |
Seym | +1.980 |
slam | +1.937 |
Corm | +1.902 |
Neg logit contributions | |
CARD | -1.856 |
infect | -1.544 |
foreskin | -1.451 |
helic | -1.426 |
beard | -1.391 |
Token | as |
Token ID | 355 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
CARD | +2.367 |
infect | +2.008 |
foreskin | +1.935 |
helic | +1.908 |
beard | +1.883 |
Neg logit contributions | |
Ham | -2.008 |
Seym | -1.868 |
Pru | -1.818 |
slam | -1.729 |
Corm | -1.723 |
Token | Skyrim |
Token ID | 21789 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
Ham | +2.726 |
Seym | +2.519 |
Pru | +2.515 |
slam | +2.469 |
Corm | +2.450 |
Neg logit contributions | |
CARD | -2.201 |
infect | -1.821 |
foreskin | -1.734 |
helic | -1.714 |
beard | -1.639 |
Token | folder |
Token ID | 9483 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Ham | +0.641 |
Seym | +0.595 |
Pru | +0.593 |
slam | +0.579 |
Corm | +0.573 |
Neg logit contributions | |
CARD | -0.508 |
infect | -0.417 |
foreskin | -0.395 |
helic | -0.389 |
beard | -0.377 |
Token | or |
Token ID | 393 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Ham | +3.969 |
Pru | +3.519 |
slam | +3.448 |
Seym | +3.445 |
Ryan | +3.402 |
Neg logit contributions | |
CARD | -5.561 |
infect | -4.866 |
foreskin | -4.763 |
helic | -4.684 |
beard | -4.543 |
Token | install |
Token ID | 2721 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Ham | +0.376 |
Seym | +0.344 |
Pru | +0.343 |
slam | +0.333 |
Corm | +0.328 |
Neg logit contributions | |
CARD | -0.450 |
infect | -0.386 |
foreskin | -0.368 |
helic | -0.365 |
beard | -0.356 |
Token | with |
Token ID | 351 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
Ham | +0.561 |
Seym | +0.511 |
Pru | +0.509 |
slam | +0.494 |
Corm | +0.487 |
Neg logit contributions | |
CARD | -0.696 |
infect | -0.597 |
foreskin | -0.571 |
helic | -0.565 |
beard | -0.553 |
Token | N |
Token ID | 399 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
Ham | +4.095 |
slam | +3.699 |
Pru | +3.667 |
Seym | +3.570 |
Corm | +3.519 |
Neg logit contributions | |
CARD | -5.670 |
infect | -4.928 |
foreskin | -4.823 |
helic | -4.740 |
beard | -4.546 |
Token | MM |
Token ID | 12038 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
Ham | +6.570 |
slam | +5.176 |
ouver | +5.091 |
ault | +4.983 |
Ryan | +4.971 |
Neg logit contributions | |
CARD | -11.877 |
helic | -10.747 |
foreskin | -10.315 |
infect | -9.912 |
Dise | -9.895 |
Token | then |
Token ID | 788 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
Ham | +4.379 |
slam | +3.837 |
Pru | +3.831 |
Seym | +3.810 |
Corm | +3.727 |
Neg logit contributions | |
CARD | -6.129 |
infect | -5.314 |
foreskin | -5.215 |
helic | -5.142 |
beard | -4.983 |
Token | -- |
Token ID | 1377 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
Ham | +4.719 |
slam | +4.383 |
Pru | +4.234 |
Corm | +4.137 |
Seym | +4.100 |
Neg logit contributions | |
CARD | -6.227 |
infect | -5.371 |
foreskin | -5.208 |
helic | -5.108 |
beard | -4.940 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
Ham | +2.904 |
Pru | +2.591 |
slam | +2.568 |
Seym | +2.564 |
Corm | +2.484 |
Neg logit contributions | |
CARD | -3.650 |
infect | -3.119 |
foreskin | -3.025 |
helic | -3.001 |
beard | -2.896 |
Token | The |
Token ID | 464 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
CARD | +4.979 |
infect | +4.434 |
giving | +4.040 |
foreskin | +4.033 |
helic | +3.952 |
Neg logit contributions | |
Seym | -3.446 |
Ham | -3.331 |
Pru | -3.317 |
slam | -3.144 |
Corm | -3.081 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Ham | +2.401 |
Seym | +2.182 |
Pru | +2.158 |
slam | +2.110 |
Corm | +2.083 |
Neg logit contributions | |
CARD | -3.160 |
infect | -2.737 |
foreskin | -2.626 |
helic | -2.596 |
beard | -2.529 |
Token | something |
Token ID | 1223 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Ham | +1.070 |
Seym | +0.976 |
Pru | +0.969 |
slam | +0.938 |
Corm | +0.923 |
Neg logit contributions | |
CARD | -1.409 |
infect | -1.215 |
foreskin | -1.163 |
helic | -1.152 |
beard | -1.127 |
Token | good |
Token ID | 922 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Ham | +2.143 |
Seym | +1.958 |
Pru | +1.948 |
slam | +1.895 |
Corm | +1.867 |
Neg logit contributions | |
CARD | -2.597 |
infect | -2.224 |
foreskin | -2.122 |
helic | -2.102 |
beard | -2.053 |
Token | comes |
Token ID | 2058 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
CARD | +0.969 |
infect | +0.837 |
foreskin | +0.801 |
helic | +0.789 |
beard | +0.778 |
Neg logit contributions | |
Ham | -0.730 |
Seym | -0.674 |
Pru | -0.662 |
slam | -0.635 |
Corm | -0.627 |
Token | from |
Token ID | 422 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Ham | +2.416 |
Pru | +2.136 |
Seym | +2.124 |
slam | +2.092 |
Corm | +2.047 |
Neg logit contributions | |
CARD | -4.158 |
infect | -3.635 |
foreskin | -3.518 |
helic | -3.493 |
beard | -3.396 |
Token | it |
Token ID | 340 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
CARD | +0.673 |
infect | +0.566 |
foreskin | +0.541 |
helic | +0.533 |
beard | +0.526 |
Neg logit contributions | |
Ham | -0.614 |
Seym | -0.573 |
Pru | -0.564 |
slam | -0.545 |
Corm | -0.538 |
Token | . |
Token ID | 13 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
Ham | +2.359 |
Seym | +2.129 |
Pru | +2.115 |
slam | +2.066 |
Corm | +2.036 |
Neg logit contributions | |
CARD | -3.219 |
infect | -2.789 |
foreskin | -2.678 |
helic | -2.654 |
beard | -2.584 |
Token | � |
Token ID | 447 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Ham | +3.497 |
Pru | +3.046 |
Seym | +3.019 |
Ryan | +2.968 |
Corm | +2.946 |
Neg logit contributions | |
CARD | -5.354 |
infect | -4.744 |
foreskin | -4.619 |
helic | -4.591 |
beard | -4.445 |
Token | � |
Token ID | 251 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
Ham | +1.956 |
Pru | +1.726 |
Seym | +1.724 |
slam | +1.674 |
Corm | +1.628 |
Neg logit contributions | |
CARD | -3.073 |
infect | -2.674 |
foreskin | -2.575 |
helic | -2.563 |
beard | -2.489 |
Token | Organ |
Token ID | 26121 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Ham | +5.346 |
Pru | +4.618 |
Ryan | +4.578 |
Seym | +4.533 |
Corm | +4.519 |
Neg logit contributions | |
CARD | -7.195 |
infect | -6.386 |
foreskin | -6.233 |
helic | -6.166 |
beard | -5.964 |
Token | izer |
Token ID | 7509 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
Ham | +1.697 |
Seym | +1.532 |
Pru | +1.524 |
slam | +1.485 |
Corm | +1.461 |
Neg logit contributions | |
CARD | -2.357 |
infect | -2.030 |
foreskin | -1.956 |
helic | -1.934 |
beard | -1.894 |
Token | earthquakes |
Token ID | 29781 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Ham | +1.587 |
Seym | +1.444 |
Pru | +1.436 |
slam | +1.403 |
Corm | +1.375 |
Neg logit contributions | |
CARD | -2.103 |
infect | -1.825 |
foreskin | -1.741 |
helic | -1.718 |
beard | -1.684 |
Token | � |
Token ID | 447 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
Ham | +0.752 |
Seym | +0.689 |
Pru | +0.683 |
slam | +0.661 |
Corm | +0.651 |
Neg logit contributions | |
CARD | -0.952 |
infect | -0.818 |
foreskin | -0.782 |
helic | -0.774 |
beard | -0.758 |
Token | � |
Token ID | 251 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
CARD | +3.379 |
infect | +2.907 |
foreskin | +2.762 |
helic | +2.730 |
beard | +2.687 |
Neg logit contributions | |
Ham | -2.850 |
Seym | -2.685 |
Pru | -2.626 |
Corm | -2.518 |
slam | -2.504 |
Token | — |
Token ID | 851 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Ham | +0.603 |
Seym | +0.555 |
Pru | +0.550 |
slam | +0.530 |
Corm | +0.522 |
Neg logit contributions | |
CARD | -0.743 |
infect | -0.637 |
foreskin | -0.607 |
helic | -0.603 |
beard | -0.589 |
Token | and |
Token ID | 290 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
Ham | +0.424 |
Seym | +0.390 |
Pru | +0.386 |
slam | +0.372 |
Corm | +0.368 |
Neg logit contributions | |
CARD | -0.531 |
infect | -0.456 |
foreskin | -0.435 |
helic | -0.432 |
beard | -0.422 |
Token | a |
Token ID | 257 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
Ham | +2.028 |
Seym | +1.843 |
Pru | +1.838 |
slam | +1.785 |
Corm | +1.758 |
Neg logit contributions | |
CARD | -2.737 |
infect | -2.376 |
foreskin | -2.275 |
helic | -2.248 |
beard | -2.197 |
Token | total |
Token ID | 2472 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Ham | +1.909 |
Seym | +1.738 |
Pru | +1.731 |
slam | +1.699 |
Corm | +1.661 |
Neg logit contributions | |
CARD | -2.527 |
infect | -2.202 |
foreskin | -2.091 |
helic | -2.070 |
beard | -2.016 |
Token | retreat |
Token ID | 13703 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Ham | +1.386 |
Seym | +1.257 |
Pru | +1.244 |
slam | +1.221 |
Corm | +1.196 |
Neg logit contributions | |
CARD | -1.908 |
infect | -1.658 |
foreskin | -1.584 |
helic | -1.569 |
beard | -1.532 |
Token | of |
Token ID | 286 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Ham | +1.514 |
Seym | +1.375 |
Pru | +1.366 |
slam | +1.334 |
Corm | +1.309 |
Neg logit contributions | |
CARD | -2.001 |
infect | -1.730 |
foreskin | -1.655 |
helic | -1.639 |
beard | -1.602 |
Token | Hel |
Token ID | 5053 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Ham | +1.018 |
Seym | +0.928 |
Pru | +0.922 |
slam | +0.894 |
Corm | +0.880 |
Neg logit contributions | |
CARD | -1.354 |
infect | -1.171 |
foreskin | -1.119 |
helic | -1.108 |
beard | -1.085 |
Token | heim |
Token ID | 9096 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
Ham | +2.037 |
Pru | +1.831 |
Seym | +1.828 |
slam | +1.782 |
Corm | +1.759 |
Neg logit contributions | |
CARD | -2.601 |
infect | -2.220 |
foreskin | -2.145 |
helic | -2.124 |
beard | -2.078 |
Token | no |
Token ID | 645 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Ham | +2.024 |
Pru | +1.839 |
Seym | +1.835 |
slam | +1.783 |
Corm | +1.752 |
Neg logit contributions | |
CARD | -2.691 |
infect | -2.321 |
foreskin | -2.209 |
helic | -2.189 |
beard | -2.147 |
Token | such |
Token ID | 884 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
CARD | +1.787 |
infect | +1.524 |
foreskin | +1.481 |
helic | +1.454 |
beard | +1.438 |
Neg logit contributions | |
Ham | -1.582 |
Seym | -1.470 |
Pru | -1.430 |
slam | -1.371 |
Ryan | -1.368 |
Token | boundaries |
Token ID | 13215 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
CARD | +0.932 |
infect | +0.792 |
foreskin | +0.766 |
helic | +0.756 |
beard | +0.742 |
Neg logit contributions | |
Ham | -0.830 |
Seym | -0.770 |
Pru | -0.755 |
slam | -0.724 |
Corm | -0.719 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
CARD | +0.012 |
infect | +0.010 |
foreskin | +0.010 |
helic | +0.010 |
beard | +0.010 |
Neg logit contributions | |
Ham | -0.010 |
Seym | -0.009 |
Pru | -0.009 |
slam | -0.009 |
Corm | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
CARD | +2.319 |
infect | +1.915 |
foreskin | +1.834 |
helic | +1.785 |
giving | +1.777 |
Neg logit contributions | |
Ham | -1.903 |
Seym | -1.810 |
slam | -1.708 |
Pru | -1.691 |
ouver | -1.674 |
Token | Lac |
Token ID | 23115 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
CARD | +4.204 |
infect | +3.558 |
foreskin | +3.486 |
helic | +3.399 |
beard | +3.346 |
Neg logit contributions | |
Ham | -3.779 |
Seym | -3.512 |
Pru | -3.373 |
encers | -3.271 |
slam | -3.255 |
Token | anian |
Token ID | 38336 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
Ham | +4.761 |
Seym | +4.268 |
Pru | +4.207 |
slam | +4.101 |
Ryan | +4.099 |
Neg logit contributions | |
CARD | -6.990 |
infect | -5.937 |
foreskin | -5.874 |
helic | -5.809 |
beard | -5.617 |
Token | do |
Token ID | 466 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
Ham | +4.931 |
Pru | +4.579 |
slam | +4.496 |
Seym | +4.439 |
Corm | +4.374 |
Neg logit contributions | |
CARD | -6.008 |
infect | -5.159 |
foreskin | -4.840 |
helic | -4.812 |
beard | -4.641 |
Token | jo |
Token ID | 7639 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
Ham | +0.024 |
Seym | +0.021 |
Pru | +0.021 |
slam | +0.020 |
Corm | +0.019 |
Neg logit contributions | |
CARD | -0.060 |
infect | -0.053 |
foreskin | -0.051 |
helic | -0.051 |
beard | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
CARD | +3.600 |
infect | +3.064 |
foreskin | +2.967 |
helic | +2.902 |
beard | +2.891 |
Neg logit contributions | |
Ham | -3.043 |
Seym | -2.849 |
Pru | -2.725 |
slam | -2.623 |
Corm | -2.596 |
Token |
|
Token ID | 198 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
CARD | +0.312 |
infect | +0.268 |
foreskin | +0.256 |
helic | +0.253 |
beard | +0.248 |
Neg logit contributions | |
Ham | -0.237 |
Seym | -0.218 |
Pru | -0.213 |
slam | -0.208 |
Corm | -0.202 |
Token | Photo |
Token ID | 5555 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
Ham | +2.336 |
Pru | +2.034 |
Corm | +1.880 |
slam | +1.850 |
Ryan | +1.795 |
Neg logit contributions | |
CARD | -6.225 |
infect | -5.747 |
helic | -5.606 |
foreskin | -5.493 |
beard | -5.344 |
Token | : |
Token ID | 25 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
CARD | +4.814 |
infect | +3.690 |
giving | +3.536 |
foreskin | +3.383 |
beard | +3.350 |
Neg logit contributions | |
Seym | -8.125 |
Ham | -7.561 |
Pru | -7.289 |
slam | -7.056 |
ouver | -7.051 |
Token | Le |
Token ID | 1004 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Ham | +1.403 |
Pru | +1.291 |
Seym | +1.289 |
slam | +1.245 |
Corm | +1.240 |
Neg logit contributions | |
CARD | -1.604 |
infect | -1.384 |
foreskin | -1.308 |
helic | -1.299 |
beard | -1.262 |
Token | a |
Token ID | 64 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
CARD | +1.221 |
infect | +1.045 |
foreskin | +0.981 |
helic | +0.958 |
beard | +0.955 |
Neg logit contributions | |
Ham | -1.184 |
Seym | -1.145 |
Pru | -1.102 |
slam | -1.068 |
Corm | -1.056 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | +8.75e+00 |
Pos logit contributions | |
Ham | +3.877 |
Pru | +3.552 |
slam | +3.374 |
Ryan | +3.357 |
Seym | +3.328 |
Neg logit contributions | |
CARD | -4.713 |
infect | -4.172 |
helic | -3.927 |
foreskin | -3.893 |
beard | -3.787 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
Ham | +4.834 |
Pru | +4.106 |
Corm | +4.003 |
Ryan | +4.001 |
slam | +3.922 |
Neg logit contributions | |
CARD | -8.534 |
infect | -7.771 |
helic | -7.647 |
foreskin | -7.410 |
beard | -7.116 |
Token | The |
Token ID | 383 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
Ham | +3.070 |
Pru | +2.759 |
Corm | +2.656 |
slam | +2.583 |
Ryan | +2.563 |
Neg logit contributions | |
CARD | -4.702 |
infect | -4.256 |
helic | -4.083 |
foreskin | -4.038 |
beard | -3.893 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
Ham | +3.854 |
Pru | +3.457 |
Corm | +3.344 |
slam | +3.299 |
Ryan | +3.271 |
Neg logit contributions | |
CARD | -5.434 |
infect | -4.935 |
helic | -4.635 |
foreskin | -4.564 |
beard | -4.425 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Ham | +2.273 |
Pru | +2.020 |
slam | +1.882 |
Corm | +1.869 |
Seym | +1.841 |
Neg logit contributions | |
CARD | -5.219 |
infect | -4.731 |
helic | -4.561 |
foreskin | -4.513 |
beard | -4.371 |
Token | of |
Token ID | 286 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
Ham | +1.724 |
Pru | +1.520 |
slam | +1.493 |
Corm | +1.458 |
Ryan | +1.455 |
Neg logit contributions | |
CARD | -2.509 |
infect | -2.188 |
helic | -2.099 |
foreskin | -2.094 |
beard | -2.020 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
Ham | +2.042 |
Pru | +1.821 |
Seym | +1.707 |
slam | +1.703 |
Corm | +1.694 |
Neg logit contributions | |
CARD | -3.784 |
infect | -3.371 |
foreskin | -3.229 |
helic | -3.225 |
beard | -3.111 |
Token | a |
Token ID | 257 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
CARD | +1.730 |
infect | +1.470 |
helic | +1.404 |
foreskin | +1.403 |
beard | +1.372 |
Neg logit contributions | |
Ham | -1.454 |
Seym | -1.353 |
Pru | -1.313 |
slam | -1.269 |
ouver | -1.254 |
Token | great |
Token ID | 1049 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
CARD | +0.453 |
infect | +0.388 |
foreskin | +0.371 |
helic | +0.369 |
beard | +0.361 |
Neg logit contributions | |
Ham | -0.360 |
Seym | -0.330 |
Pru | -0.326 |
slam | -0.313 |
Corm | -0.310 |
Token | development |
Token ID | 2478 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
CARD | +1.427 |
infect | +1.218 |
foreskin | +1.163 |
helic | +1.161 |
beard | +1.140 |
Neg logit contributions | |
Ham | -1.122 |
Seym | -1.046 |
Pru | -1.017 |
slam | -0.972 |
Corm | -0.968 |
Token | , |
Token ID | 11 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
Ham | +2.103 |
Pru | +1.905 |
Seym | +1.882 |
slam | +1.877 |
Corm | +1.807 |
Neg logit contributions | |
CARD | -2.824 |
infect | -2.470 |
foreskin | -2.347 |
helic | -2.315 |
beard | -2.260 |
Token | and |
Token ID | 290 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
Ham | +0.525 |
Seym | +0.482 |
Pru | +0.477 |
slam | +0.462 |
Corm | +0.455 |
Neg logit contributions | |
CARD | -0.647 |
infect | -0.555 |
foreskin | -0.530 |
helic | -0.526 |
beard | -0.514 |
Token | I |
Token ID | 314 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
CARD | +4.228 |
infect | +3.513 |
helic | +3.434 |
foreskin | +3.353 |
beard | +3.335 |
Neg logit contributions | |
Ham | -3.559 |
Seym | -3.346 |
Pru | -3.134 |
ouver | -3.092 |
encers | -3.087 |
Token | 've |
Token ID | 1053 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Ham | +1.852 |
Pru | +1.690 |
Seym | +1.677 |
slam | +1.663 |
Corm | +1.612 |
Neg logit contributions | |
CARD | -2.312 |
infect | -1.989 |
foreskin | -1.892 |
helic | -1.869 |
beard | -1.827 |
Token | been |
Token ID | 587 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Ham | +2.060 |
Pru | +1.878 |
Seym | +1.864 |
slam | +1.838 |
Corm | +1.785 |
Neg logit contributions | |
CARD | -2.694 |
infect | -2.319 |
foreskin | -2.203 |
helic | -2.184 |
beard | -2.132 |
Token | working |
Token ID | 1762 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
Ham | +0.470 |
Seym | +0.433 |
Pru | +0.428 |
slam | +0.414 |
Corm | +0.409 |
Neg logit contributions | |
CARD | -0.547 |
infect | -0.468 |
foreskin | -0.446 |
helic | -0.442 |
beard | -0.433 |
Token | on |
Token ID | 319 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
CARD | +3.132 |
infect | +2.704 |
foreskin | +2.617 |
helic | +2.580 |
beard | +2.561 |
Neg logit contributions | |
Ham | -2.354 |
Seym | -2.210 |
Pru | -2.136 |
slam | -2.047 |
encers | -2.008 |
Token | a |
Token ID | 257 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
CARD | +7.348 |
infect | +5.993 |
helic | +5.924 |
foreskin | +5.767 |
beard | +5.676 |
Neg logit contributions | |
Ham | -6.766 |
Seym | -6.537 |
encers | -6.025 |
ouver | -6.016 |
Ryan | -6.011 |
Token | Sy |
Token ID | 13940 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
Ham | +1.127 |
Seym | +1.023 |
Pru | +1.016 |
slam | +0.983 |
Corm | +0.967 |
Neg logit contributions | |
CARD | -1.535 |
infect | -1.326 |
foreskin | -1.272 |
helic | -1.260 |
beard | -1.234 |
Token | fy |
Token ID | 24928 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
CARD | +5.755 |
infect | +4.964 |
foreskin | +4.628 |
giving | +4.422 |
beard | +4.407 |
Neg logit contributions | |
Seym | -8.044 |
Ham | -7.951 |
Pru | -7.903 |
Corm | -7.475 |
slam | -7.393 |
Token | � |
Token ID | 447 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
CARD | +3.041 |
infect | +2.613 |
foreskin | +2.484 |
helic | +2.482 |
beard | +2.426 |
Neg logit contributions | |
Ham | -2.387 |
Seym | -2.222 |
Pru | -2.180 |
slam | -2.105 |
Corm | -2.072 |
Token | � |
Token ID | 247 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Ham | +1.787 |
Pru | +1.606 |
Seym | +1.593 |
slam | +1.571 |
Corm | +1.529 |
Neg logit contributions | |
CARD | -2.264 |
infect | -1.953 |
foreskin | -1.863 |
helic | -1.848 |
beard | -1.798 |
Token | s |
Token ID | 82 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
CARD | +0.955 |
infect | +0.823 |
foreskin | +0.780 |
helic | +0.776 |
beard | +0.757 |
Neg logit contributions | |
Ham | -0.786 |
Seym | -0.728 |
Pru | -0.718 |
slam | -0.695 |
Corm | -0.685 |
Token | return |
Token ID | 1441 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
CARD | +0.565 |
infect | +0.482 |
foreskin | +0.461 |
helic | +0.460 |
beard | +0.451 |
Neg logit contributions | |
Ham | -0.462 |
Seym | -0.424 |
Pru | -0.419 |
slam | -0.403 |
Corm | -0.399 |
Token | to |
Token ID | 284 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
CARD | +1.218 |
infect | +1.030 |
foreskin | +0.981 |
helic | +0.978 |
beard | +0.960 |
Neg logit contributions | |
Ham | -1.079 |
Seym | -0.998 |
Pru | -0.986 |
Corm | -0.943 |
slam | -0.939 |
Token | speculative |
Token ID | 28991 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
CARD | +0.224 |
infect | +0.192 |
foreskin | +0.183 |
helic | +0.182 |
beard | +0.178 |
Neg logit contributions | |
Ham | -0.179 |
Seym | -0.164 |
Pru | -0.162 |
slam | -0.156 |
Corm | -0.154 |
Token | fiction |
Token ID | 10165 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
CARD | +2.802 |
infect | +2.386 |
foreskin | +2.305 |
helic | +2.298 |
beard | +2.249 |
Neg logit contributions | |
Ham | -2.396 |
Seym | -2.237 |
Pru | -2.186 |
encers | -2.083 |
ouver | -2.069 |
Token | form |
Token ID | 1296 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
CARD | +3.110 |
infect | +2.640 |
helic | +2.521 |
foreskin | +2.510 |
beard | +2.467 |
Neg logit contributions | |
Ham | -2.751 |
Seym | -2.574 |
Pru | -2.503 |
encers | -2.371 |
ouver | -2.369 |
Token | isn |
Token ID | 2125 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Ham | +2.427 |
Seym | +2.204 |
Pru | +2.195 |
slam | +2.133 |
Corm | +2.104 |
Neg logit contributions | |
CARD | -3.255 |
infect | -2.814 |
foreskin | -2.704 |
helic | -2.669 |
beard | -2.607 |
Token | learn |
Token ID | 2193 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
CARD | +1.448 |
infect | +1.239 |
foreskin | +1.189 |
helic | +1.166 |
beard | +1.157 |
Neg logit contributions | |
Ham | -1.236 |
Seym | -1.160 |
Pru | -1.123 |
Corm | -1.069 |
Ryan | -1.067 |
Token | more |
Token ID | 517 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Ham | +0.664 |
Seym | +0.605 |
Pru | +0.603 |
slam | +0.586 |
Corm | +0.576 |
Neg logit contributions | |
CARD | -0.836 |
infect | -0.720 |
foreskin | -0.685 |
helic | -0.680 |
beard | -0.665 |
Token | about |
Token ID | 546 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Ham | +2.200 |
Seym | +2.014 |
Pru | +2.012 |
slam | +1.971 |
Corm | +1.943 |
Neg logit contributions | |
CARD | -2.367 |
infect | -2.008 |
foreskin | -1.905 |
helic | -1.892 |
beard | -1.837 |
Token | social |
Token ID | 1919 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Ham | +0.425 |
Seym | +0.388 |
Pru | +0.385 |
slam | +0.373 |
Corm | +0.367 |
Neg logit contributions | |
CARD | -0.563 |
infect | -0.485 |
foreskin | -0.464 |
helic | -0.460 |
beard | -0.450 |
Token | justice |
Token ID | 5316 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
CARD | +0.737 |
infect | +0.637 |
foreskin | +0.613 |
helic | +0.603 |
beard | +0.591 |
Neg logit contributions | |
Ham | -0.567 |
Seym | -0.520 |
Pru | -0.512 |
slam | -0.493 |
Corm | -0.487 |
Token | from |
Token ID | 422 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
CARD | +0.763 |
infect | +0.656 |
foreskin | +0.629 |
helic | +0.621 |
beard | +0.610 |
Neg logit contributions | |
Ham | -0.624 |
Seym | -0.576 |
Pru | -0.566 |
slam | -0.546 |
Corm | -0.539 |
Token | atheists |
Token ID | 28473 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Ham | +0.091 |
Seym | +0.083 |
Pru | +0.082 |
slam | +0.080 |
Corm | +0.078 |
Neg logit contributions | |
CARD | -0.115 |
infect | -0.099 |
foreskin | -0.095 |
helic | -0.093 |
beard | -0.092 |
Token | who |
Token ID | 508 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
CARD | +0.198 |
infect | +0.170 |
foreskin | +0.162 |
helic | +0.160 |
beard | +0.157 |
Neg logit contributions | |
Ham | -0.167 |
Seym | -0.154 |
Pru | -0.152 |
slam | -0.148 |
Corm | -0.145 |
Token | shared |
Token ID | 4888 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
CARD | +0.950 |
infect | +0.815 |
foreskin | +0.779 |
helic | +0.769 |
beard | +0.758 |
Neg logit contributions | |
Ham | -0.818 |
Seym | -0.762 |
Pru | -0.743 |
slam | -0.709 |
Corm | -0.708 |
Token | their |
Token ID | 511 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
CARD | +4.202 |
infect | +3.636 |
foreskin | +3.526 |
helic | +3.465 |
beard | +3.459 |
Neg logit contributions | |
Ham | -3.144 |
Seym | -2.927 |
Pru | -2.769 |
encers | -2.692 |
slam | -2.685 |
Token | concerns |
Token ID | 4786 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
CARD | +2.319 |
infect | +1.980 |
foreskin | +1.920 |
helic | +1.873 |
beard | +1.864 |
Neg logit contributions | |
Ham | -2.107 |
Seym | -1.971 |
Pru | -1.891 |
slam | -1.820 |
encers | -1.816 |
Token | as |
Token ID | 355 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
CARD | +0.931 |
infect | +0.793 |
foreskin | +0.751 |
helic | +0.748 |
beard | +0.729 |
Neg logit contributions | |
Ham | -0.837 |
Seym | -0.778 |
Pru | -0.772 |
slam | -0.748 |
Corm | -0.732 |
Token | Goldman |
Token ID | 18740 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
Ham | +1.135 |
Seym | +1.034 |
Pru | +1.026 |
slam | +0.993 |
Corm | +0.977 |
Neg logit contributions | |
CARD | -1.539 |
infect | -1.332 |
foreskin | -1.274 |
helic | -1.262 |
beard | -1.236 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
CARD | +0.834 |
infect | +0.720 |
foreskin | +0.689 |
helic | +0.685 |
beard | +0.671 |
Neg logit contributions | |
Ham | -0.592 |
Seym | -0.541 |
Pru | -0.536 |
slam | -0.516 |
Corm | -0.508 |
Token | to |
Token ID | 284 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
CARD | +0.917 |
infect | +0.779 |
foreskin | +0.746 |
helic | +0.740 |
beard | +0.726 |
Neg logit contributions | |
Ham | -0.790 |
Seym | -0.733 |
Pru | -0.722 |
slam | -0.695 |
Corm | -0.686 |
Token | j |
Token ID | 474 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
Ham | +2.702 |
Pru | +2.440 |
slam | +2.429 |
Seym | +2.409 |
Corm | +2.327 |
Neg logit contributions | |
CARD | -3.454 |
infect | -2.971 |
foreskin | -2.848 |
helic | -2.821 |
beard | -2.752 |
Token | ett |
Token ID | 3087 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
CARD | +4.739 |
infect | +4.103 |
foreskin | +3.649 |
helic | +3.597 |
beard | +3.560 |
Neg logit contributions | |
Seym | -5.035 |
Ham | -4.977 |
Pru | -4.797 |
slam | -4.524 |
Corm | -4.511 |
Token | ison |
Token ID | 1653 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
CARD | +5.727 |
infect | +5.146 |
foreskin | +4.830 |
beard | +4.731 |
helic | +4.634 |
Neg logit contributions | |
Seym | -4.328 |
Ham | -4.327 |
Pru | -3.982 |
Corm | -3.565 |
Ryan | -3.558 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
CARD | +2.639 |
infect | +2.235 |
foreskin | +2.142 |
helic | +2.132 |
beard | +2.084 |
Neg logit contributions | |
Ham | -2.156 |
Seym | -1.995 |
Pru | -1.944 |
slam | -1.871 |
Corm | -1.855 |
Token | billions |
Token ID | 13188 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
CARD | +0.234 |
infect | +0.199 |
foreskin | +0.191 |
helic | +0.189 |
beard | +0.185 |
Neg logit contributions | |
Ham | -0.192 |
Seym | -0.177 |
Pru | -0.174 |
slam | -0.167 |
Corm | -0.166 |
Token | in |
Token ID | 287 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Ham | +0.521 |
Seym | +0.476 |
Pru | +0.473 |
slam | +0.458 |
Corm | +0.451 |
Neg logit contributions | |
CARD | -0.658 |
infect | -0.566 |
foreskin | -0.541 |
helic | -0.536 |
beard | -0.524 |
Token | sub |
Token ID | 850 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Ham | +0.678 |
Seym | +0.620 |
Pru | +0.617 |
slam | +0.600 |
Corm | +0.589 |
Neg logit contributions | |
CARD | -0.827 |
infect | -0.710 |
foreskin | -0.677 |
helic | -0.670 |
beard | -0.656 |
Token | these |
Token ID | 777 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
CARD | +2.225 |
infect | +1.888 |
foreskin | +1.846 |
helic | +1.819 |
beard | +1.793 |
Neg logit contributions | |
Ham | -1.925 |
Seym | -1.764 |
Pru | -1.733 |
slam | -1.662 |
Corm | -1.653 |
Token | problems |
Token ID | 2761 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
CARD | +2.022 |
infect | +1.728 |
foreskin | +1.676 |
helic | +1.658 |
beard | +1.636 |
Neg logit contributions | |
Ham | -1.693 |
Seym | -1.559 |
Pru | -1.524 |
slam | -1.461 |
Corm | -1.457 |
Token | that |
Token ID | 326 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Ham | +0.397 |
Seym | +0.363 |
Pru | +0.360 |
slam | +0.348 |
Corm | +0.343 |
Neg logit contributions | |
CARD | -0.500 |
infect | -0.430 |
foreskin | -0.411 |
helic | -0.407 |
beard | -0.399 |
Token | the |
Token ID | 262 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
CARD | +2.437 |
infect | +2.088 |
foreskin | +2.005 |
helic | +1.978 |
beard | +1.951 |
Neg logit contributions | |
Ham | -2.117 |
Seym | -1.953 |
Pru | -1.913 |
slam | -1.855 |
encers | -1.824 |
Token | other |
Token ID | 584 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
CARD | +0.349 |
infect | +0.299 |
foreskin | +0.287 |
helic | +0.283 |
beard | +0.279 |
Neg logit contributions | |
Ham | -0.287 |
Seym | -0.264 |
Pru | -0.261 |
slam | -0.252 |
Corm | -0.248 |
Token | characters |
Token ID | 3435 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Ham | +2.073 |
Seym | +1.895 |
Pru | +1.893 |
slam | +1.840 |
Corm | +1.818 |
Neg logit contributions | |
CARD | -2.494 |
infect | -2.134 |
foreskin | -2.017 |
helic | -2.007 |
beard | -1.949 |
Token | were |
Token ID | 547 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
CARD | +0.105 |
infect | +0.089 |
foreskin | +0.085 |
helic | +0.084 |
beard | +0.082 |
Neg logit contributions | |
Ham | -0.098 |
Seym | -0.090 |
Pru | -0.089 |
slam | -0.087 |
Corm | -0.086 |
Token | having |
Token ID | 1719 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Ham | +1.384 |
Seym | +1.238 |
Pru | +1.235 |
slam | +1.195 |
Corm | +1.166 |
Neg logit contributions | |
CARD | -2.336 |
infect | -2.035 |
foreskin | -1.958 |
helic | -1.944 |
beard | -1.904 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
CARD | +1.264 |
infect | +1.086 |
foreskin | +1.039 |
helic | +1.030 |
beard | +1.010 |
Neg logit contributions | |
Ham | -1.056 |
Seym | -0.970 |
Pru | -0.960 |
slam | -0.926 |
Corm | -0.911 |
Token | My |
Token ID | 2011 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
CARD | +1.543 |
infect | +1.295 |
foreskin | +1.243 |
helic | +1.215 |
beard | +1.204 |
Neg logit contributions | |
Ham | -1.235 |
Seym | -1.162 |
Pru | -1.113 |
slam | -1.110 |
ouver | -1.069 |
Token | guy |
Token ID | 3516 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
CARD | +2.554 |
infect | +2.160 |
foreskin | +2.109 |
helic | +2.055 |
beard | +2.046 |
Neg logit contributions | |
Ham | -2.379 |
Seym | -2.209 |
Pru | -2.167 |
slam | -2.071 |
encers | -2.055 |
Token | high |
Token ID | 8929 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
CARD | +0.993 |
infect | +0.856 |
foreskin | +0.802 |
helic | +0.797 |
beard | +0.777 |
Neg logit contributions | |
Ham | -0.897 |
Seym | -0.842 |
Pru | -0.831 |
slam | -0.804 |
Corm | -0.795 |
Token | voltage |
Token ID | 15004 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
CARD | +1.252 |
infect | +1.076 |
foreskin | +1.029 |
helic | +1.027 |
beard | +1.005 |
Neg logit contributions | |
Ham | -0.919 |
Seym | -0.852 |
Pru | -0.832 |
slam | -0.792 |
Corm | -0.789 |
Token | ) |
Token ID | 8 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
CARD | +0.384 |
infect | +0.328 |
foreskin | +0.314 |
helic | +0.313 |
beard | +0.305 |
Neg logit contributions | |
Ham | -0.308 |
Seym | -0.284 |
Pru | -0.280 |
slam | -0.268 |
Corm | -0.266 |
Token | or |
Token ID | 393 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Ham | +0.139 |
Seym | +0.127 |
Pru | +0.126 |
slam | +0.121 |
Corm | +0.120 |
Neg logit contributions | |
CARD | -0.180 |
infect | -0.155 |
foreskin | -0.148 |
helic | -0.147 |
beard | -0.143 |
Token | overhe |
Token ID | 34789 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
CARD | +1.811 |
infect | +1.554 |
foreskin | +1.484 |
helic | +1.478 |
beard | +1.442 |
Neg logit contributions | |
Ham | -1.470 |
Seym | -1.379 |
Pru | -1.341 |
Corm | -1.282 |
slam | -1.272 |
Token | ating |
Token ID | 803 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
CARD | +2.579 |
infect | +2.325 |
foreskin | +2.172 |
helic | +2.155 |
beard | +2.129 |
Neg logit contributions | |
Ham | -1.453 |
Seym | -1.356 |
Pru | -1.318 |
slam | -1.241 |
Corm | -1.228 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Ham | +0.116 |
Seym | +0.106 |
Pru | +0.105 |
slam | +0.101 |
Corm | +0.100 |
Neg logit contributions | |
CARD | -0.144 |
infect | -0.124 |
foreskin | -0.118 |
helic | -0.117 |
beard | -0.114 |
Token | " |
Token ID | 366 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
CARD | +2.520 |
infect | +2.111 |
foreskin | +2.019 |
helic | +2.009 |
beard | +1.957 |
Neg logit contributions | |
Ham | -2.003 |
Seym | -1.899 |
Pru | -1.819 |
slam | -1.781 |
Ryan | -1.744 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Ham | +1.302 |
Seym | +1.179 |
Pru | +1.172 |
slam | +1.135 |
Corm | +1.117 |
Neg logit contributions | |
CARD | -1.740 |
infect | -1.506 |
foreskin | -1.442 |
helic | -1.425 |
beard | -1.399 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Ham | +1.445 |
Pru | +1.263 |
slam | +1.230 |
Ryan | +1.214 |
Corm | +1.213 |
Neg logit contributions | |
CARD | -2.169 |
infect | -1.888 |
helic | -1.826 |
foreskin | -1.821 |
beard | -1.763 |
Token | If |
Token ID | 1532 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
CARD | +0.093 |
infect | +0.080 |
foreskin | +0.076 |
helic | +0.076 |
beard | +0.074 |
Neg logit contributions | |
Ham | -0.070 |
Seym | -0.065 |
Pru | -0.064 |
slam | -0.062 |
Corm | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
CARD | +3.988 |
beard | +3.372 |
foreskin | +3.367 |
infect | +3.251 |
helic | +3.164 |
Neg logit contributions | |
Ham | -5.907 |
Seym | -5.641 |
Pru | -5.412 |
Ryan | -5.243 |
encers | -5.226 |
Token | rim |
Token ID | 3036 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
Ham | +2.588 |
Pru | +2.366 |
Seym | +2.355 |
slam | +2.301 |
Corm | +2.285 |
Neg logit contributions | |
CARD | -2.377 |
infect | -1.925 |
foreskin | -1.848 |
helic | -1.848 |
beard | -1.752 |
Token | med |
Token ID | 1150 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
CARD | +6.898 |
beard | +6.144 |
foreskin | +5.714 |
infect | +5.574 |
helic | +5.204 |
Neg logit contributions | |
Ham | -11.747 |
Seym | -10.874 |
Pru | -10.590 |
ownt | -10.512 |
ouver | -10.420 |
Token | glasses |
Token ID | 15232 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
CARD | +5.803 |
beard | +5.136 |
foreskin | +4.877 |
helic | +4.536 |
lenses | +4.236 |
Neg logit contributions | |
Ham | -12.101 |
Seym | -11.484 |
Pru | -11.039 |
Ryan | -10.920 |
ownt | -10.909 |
Token | and |
Token ID | 290 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
CARD | +4.745 |
infect | +4.072 |
foreskin | +3.958 |
beard | +3.937 |
helic | +3.913 |
Neg logit contributions | |
Ham | -4.407 |
Seym | -4.143 |
Pru | -3.996 |
encers | -3.834 |
Ryan | -3.789 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
CARD | +7.336 |
beard | +6.473 |
foreskin | +6.343 |
infect | +6.181 |
helic | +6.178 |
Neg logit contributions | |
Ham | -6.645 |
Seym | -6.252 |
Pru | -5.787 |
encers | -5.783 |
ouver | -5.723 |
Token | double |
Token ID | 4274 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
CARD | +8.539 |
beard | +7.651 |
foreskin | +7.437 |
infect | +7.137 |
helic | +7.108 |
Neg logit contributions | |
Ham | -7.307 |
Seym | -6.822 |
encers | -6.564 |
ouver | -6.355 |
Pru | -6.313 |
Token | chin |
Token ID | 22531 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
CARD | +5.268 |
infect | +4.470 |
foreskin | +4.459 |
beard | +4.369 |
helic | +4.347 |
Neg logit contributions | |
Ham | -5.281 |
Seym | -4.999 |
Pru | -4.743 |
encers | -4.694 |
slam | -4.603 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
CARD | +7.694 |
beard | +6.765 |
infect | +6.634 |
foreskin | +6.587 |
helic | +6.398 |
Neg logit contributions | |
Ham | -7.657 |
Seym | -7.366 |
Pru | -7.107 |
encers | -6.844 |
Corm | -6.655 |
Token | He |
Token ID | 679 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
CARD | +1.198 |
infect | +1.006 |
foreskin | +0.968 |
helic | +0.947 |
beard | +0.939 |
Neg logit contributions | |
Ham | -0.973 |
Seym | -0.910 |
Pru | -0.874 |
slam | -0.868 |
ouver | -0.844 |
Token | told |
Token ID | 1297 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
CARD | +2.427 |
infect | +2.082 |
foreskin | +1.987 |
beard | +1.965 |
helic | +1.950 |
Neg logit contributions | |
Ham | -2.425 |
Seym | -2.296 |
Pru | -2.216 |
slam | -2.110 |
Corm | -2.102 |
Token | ann |
Token ID | 1236 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Ham | +2.686 |
Pru | +2.407 |
Seym | +2.397 |
slam | +2.365 |
Corm | +2.300 |
Neg logit contributions | |
CARD | -3.000 |
infect | -2.529 |
foreskin | -2.444 |
helic | -2.422 |
beard | -2.349 |
Token | abe |
Token ID | 11231 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
CARD | +0.433 |
infect | +0.380 |
foreskin | +0.361 |
helic | +0.357 |
beard | +0.353 |
Neg logit contributions | |
Ham | -0.280 |
Seym | -0.259 |
Pru | -0.252 |
slam | -0.243 |
Corm | -0.239 |
Token | hi |
Token ID | 23105 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
CARD | +0.022 |
infect | +0.019 |
foreskin | +0.018 |
helic | +0.018 |
beard | +0.017 |
Neg logit contributions | |
Ham | -0.017 |
Seym | -0.015 |
Pru | -0.015 |
slam | -0.014 |
Corm | -0.014 |
Token | - |
Token ID | 12 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
Ham | +2.631 |
Seym | +2.381 |
Pru | +2.375 |
slam | +2.341 |
Corm | +2.278 |
Neg logit contributions | |
CARD | -3.183 |
infect | -2.719 |
foreskin | -2.610 |
helic | -2.565 |
beard | -2.504 |
Token | fi |
Token ID | 12463 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Ham | +3.379 |
Pru | +2.942 |
slam | +2.930 |
Seym | +2.921 |
Ryan | +2.855 |
Neg logit contributions | |
CARD | -5.053 |
infect | -4.319 |
foreskin | -4.236 |
helic | -4.181 |
beard | -4.070 |
Token | pret |
Token ID | 2181 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
CARD | +0.176 |
infect | +0.151 |
foreskin | +0.144 |
helic | +0.143 |
beard | +0.141 |
Neg logit contributions | |
Ham | -0.140 |
Seym | -0.129 |
Pru | -0.127 |
slam | -0.122 |
Corm | -0.122 |
Token | ender |
Token ID | 2194 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
CARD | +6.733 |
infect | +5.569 |
beard | +5.371 |
foreskin | +5.220 |
helic | +5.094 |
Neg logit contributions | |
Ham | -7.819 |
Seym | -7.625 |
Pru | -7.547 |
Corm | -7.140 |
Ryan | -7.099 |
Token | -- |
Token ID | 1377 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
CARD | +2.448 |
infect | +2.070 |
foreskin | +1.986 |
helic | +1.953 |
beard | +1.940 |
Neg logit contributions | |
Ham | -2.158 |
Seym | -2.029 |
Pru | -1.973 |
Corm | -1.888 |
encers | -1.877 |
Token | an |
Token ID | 281 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
CARD | +2.747 |
infect | +2.327 |
foreskin | +2.227 |
helic | +2.200 |
beard | +2.181 |
Neg logit contributions | |
Ham | -2.354 |
Seym | -2.204 |
Pru | -2.133 |
Corm | -2.049 |
encers | -2.040 |
Token | all |
Token ID | 477 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
CARD | +2.481 |
infect | +2.136 |
foreskin | +2.041 |
helic | +2.018 |
beard | +1.997 |
Neg logit contributions | |
Ham | -1.847 |
Seym | -1.717 |
Pru | -1.678 |
Corm | -1.606 |
slam | -1.603 |
Token | - |
Token ID | 12 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
CARD | +0.876 |
infect | +0.746 |
foreskin | +0.707 |
helic | +0.701 |
beard | +0.691 |
Neg logit contributions | |
Ham | -0.783 |
Seym | -0.728 |
Pru | -0.718 |
slam | -0.692 |
Corm | -0.689 |
Token | Sigma |
Token ID | 31669 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
Ham | +3.388 |
Pru | +3.089 |
Seym | +3.050 |
slam | +2.973 |
Corm | +2.956 |
Neg logit contributions | |
CARD | -4.673 |
infect | -4.122 |
foreskin | -3.862 |
helic | -3.851 |
beard | -3.793 |
Token | The |
Token ID | 383 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Ham | +3.575 |
Pru | +3.246 |
Seym | +3.228 |
slam | +3.166 |
Corm | +3.087 |
Neg logit contributions | |
CARD | -5.716 |
infect | -5.061 |
foreskin | -4.796 |
helic | -4.721 |
beard | -4.718 |
Token | ta |
Token ID | 8326 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Ham | +1.583 |
Seym | +1.450 |
Pru | +1.437 |
slam | +1.387 |
Corm | +1.372 |
Neg logit contributions | |
CARD | -2.003 |
infect | -1.722 |
foreskin | -1.651 |
helic | -1.641 |
beard | -1.597 |
Token | sor |
Token ID | 25655 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
Ham | +0.077 |
Seym | +0.071 |
Pru | +0.070 |
slam | +0.068 |
Corm | +0.067 |
Neg logit contributions | |
CARD | -0.100 |
infect | -0.086 |
foreskin | -0.082 |
helic | -0.082 |
beard | -0.080 |
Token | ority |
Token ID | 29134 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
Ham | +1.980 |
slam | +1.681 |
Seym | +1.680 |
Pru | +1.647 |
Corm | +1.595 |
Neg logit contributions | |
CARD | -4.833 |
infect | -4.285 |
foreskin | -4.166 |
helic | -4.141 |
beard | -4.041 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
Ham | +2.360 |
Seym | +2.147 |
Pru | +2.142 |
slam | +2.089 |
Corm | +2.041 |
Neg logit contributions | |
CARD | -3.101 |
infect | -2.693 |
foreskin | -2.557 |
helic | -2.531 |
beard | -2.490 |
Token | 48 |
Token ID | 2780 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
CARD | +7.276 |
infect | +6.239 |
giving | +5.593 |
foreskin | +5.458 |
helic | +5.428 |
Neg logit contributions | |
Ham | -8.333 |
Pru | -8.092 |
Seym | -7.779 |
ouver | -7.625 |
Corm | -7.547 |
Token | ] |
Token ID | 60 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
CARD | +2.049 |
infect | +1.722 |
foreskin | +1.643 |
helic | +1.617 |
beard | +1.581 |
Neg logit contributions | |
Ham | -2.049 |
Seym | -1.892 |
Pru | -1.885 |
slam | -1.828 |
Corm | -1.796 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
CARD | +0.611 |
infect | +0.524 |
foreskin | +0.502 |
helic | +0.494 |
beard | +0.485 |
Neg logit contributions | |
Ham | -0.459 |
Seym | -0.422 |
Pru | -0.415 |
slam | -0.406 |
Corm | -0.393 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
CARD | +1.370 |
infect | +1.175 |
foreskin | +1.116 |
helic | +1.091 |
beard | +1.085 |
Neg logit contributions | |
Ham | -1.102 |
Seym | -1.072 |
Pru | -1.022 |
slam | -0.984 |
Corm | -0.965 |
Token | In |
Token ID | 818 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
Ham | +1.019 |
Seym | +0.912 |
Pru | +0.907 |
slam | +0.875 |
Corm | +0.861 |
Neg logit contributions | |
CARD | -1.518 |
infect | -1.315 |
foreskin | -1.267 |
helic | -1.258 |
beard | -1.231 |
Token | the |
Token ID | 262 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
CARD | +2.805 |
infect | +2.396 |
foreskin | +2.271 |
helic | +2.262 |
beard | +2.203 |
Neg logit contributions | |
Ham | -2.338 |
Seym | -2.152 |
Pru | -2.096 |
slam | -2.032 |
Corm | -2.012 |
Token | Min |
Token ID | 1855 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
CARD | +1.930 |
infect | +1.648 |
foreskin | +1.576 |
helic | +1.560 |
beard | +1.529 |
Neg logit contributions | |
Ham | -1.586 |
Seym | -1.450 |
Pru | -1.421 |
slam | -1.372 |
encers | -1.362 |
Token | ova |
Token ID | 10071 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
CARD | +4.299 |
infect | +3.764 |
foreskin | +3.357 |
beard | +3.319 |
giving | +3.298 |
Neg logit contributions | |
Ham | -5.196 |
Seym | -5.124 |
Pru | -4.845 |
slam | -4.699 |
Corm | -4.660 |
Token | rapes |
Token ID | 37459 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
CARD | +2.664 |
infect | +2.299 |
foreskin | +2.195 |
helic | +2.187 |
beard | +2.135 |
Neg logit contributions | |
Ham | -2.039 |
Seym | -1.879 |
Pru | -1.832 |
slam | -1.766 |
Corm | -1.758 |
Token | if |
Token ID | 611 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
Ham | +0.682 |
Seym | +0.627 |
Pru | +0.620 |
slam | +0.599 |
Corm | +0.591 |
Neg logit contributions | |
CARD | -0.840 |
infect | -0.720 |
foreskin | -0.687 |
helic | -0.680 |
beard | -0.666 |
Token | it |
Token ID | 340 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
CARD | +5.586 |
infect | +4.729 |
foreskin | +4.522 |
helic | +4.436 |
beard | +4.352 |
Neg logit contributions | |
Ham | -4.614 |
Seym | -4.406 |
Pru | -4.194 |
Corm | -4.012 |
encers | -4.011 |
Token | did |
Token ID | 750 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
CARD | +7.285 |
infect | +6.323 |
foreskin | +6.027 |
beard | +5.968 |
helic | +5.786 |
Neg logit contributions | |
Ham | -7.613 |
Seym | -7.533 |
Pru | -7.129 |
ouver | -6.780 |
Corm | -6.722 |
Token | not |
Token ID | 407 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
CARD | +0.326 |
infect | +0.282 |
foreskin | +0.270 |
helic | +0.267 |
beard | +0.263 |
Neg logit contributions | |
Ham | -0.241 |
Seym | -0.222 |
Pru | -0.219 |
slam | -0.210 |
Corm | -0.208 |
Token | try |
Token ID | 1949 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
CARD | +3.385 |
infect | +2.928 |
foreskin | +2.804 |
helic | +2.744 |
beard | +2.744 |
Neg logit contributions | |
Ham | -2.992 |
Seym | -2.903 |
Pru | -2.793 |
Corm | -2.640 |
Ryan | -2.600 |
Token | the |
Token ID | 262 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
CARD | +1.899 |
infect | +1.605 |
foreskin | +1.527 |
helic | +1.514 |
beard | +1.485 |
Neg logit contributions | |
Ham | -1.752 |
Seym | -1.630 |
Pru | -1.609 |
slam | -1.551 |
Corm | -1.545 |
Token | soldiers |
Token ID | 5795 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
Ham | +1.711 |
Seym | +1.561 |
Pru | +1.552 |
slam | +1.510 |
Corm | +1.481 |
Neg logit contributions | |
CARD | -2.269 |
infect | -1.960 |
foreskin | -1.871 |
helic | -1.856 |
beard | -1.811 |
Token | more |
Token ID | 517 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
CARD | +1.582 |
infect | +1.344 |
foreskin | +1.294 |
helic | +1.277 |
beard | +1.254 |
Neg logit contributions | |
Ham | -1.273 |
Seym | -1.173 |
Pru | -1.153 |
slam | -1.115 |
Corm | -1.093 |
Token | stuff |
Token ID | 3404 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
CARD | +4.134 |
infect | +3.516 |
foreskin | +3.412 |
helic | +3.338 |
beard | +3.288 |
Neg logit contributions | |
Ham | -3.475 |
Seym | -3.238 |
Pru | -3.178 |
slam | -3.019 |
ouver | -3.016 |
Token | like |
Token ID | 588 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
CARD | +5.101 |
infect | +4.158 |
foreskin | +4.011 |
helic | +3.894 |
beard | +3.867 |
Neg logit contributions | |
Ham | -6.351 |
Seym | -6.108 |
Pru | -5.915 |
ouver | -5.667 |
slam | -5.659 |
Token | this |
Token ID | 428 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
CARD | +5.988 |
infect | +4.972 |
foreskin | +4.810 |
helic | +4.735 |
beard | +4.671 |
Neg logit contributions | |
Ham | -5.524 |
Seym | -5.112 |
Pru | -5.024 |
ouver | -4.865 |
slam | -4.854 |
Token | keeps |
Token ID | 7622 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
CARD | +5.211 |
infect | +4.420 |
foreskin | +4.327 |
helic | +4.228 |
beard | +4.203 |
Neg logit contributions | |
Ham | -3.979 |
Seym | -3.772 |
Pru | -3.614 |
ouver | -3.498 |
encers | -3.410 |
Token | getting |
Token ID | 1972 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
CARD | +3.922 |
infect | +3.344 |
foreskin | +3.282 |
helic | +3.197 |
beard | +3.144 |
Neg logit contributions | |
Ham | -3.145 |
Seym | -2.929 |
Pru | -2.831 |
Corm | -2.693 |
slam | -2.689 |
Token | invented |
Token ID | 15646 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
CARD | +8.787 |
foreskin | +7.443 |
infect | +7.319 |
beard | +7.161 |
helic | +7.134 |
Neg logit contributions | |
Ham | -8.302 |
Seym | -8.024 |
Pru | -7.428 |
encers | -7.249 |
ownt | -7.160 |
Token | and |
Token ID | 290 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
CARD | +3.943 |
infect | +3.322 |
foreskin | +3.177 |
helic | +3.153 |
beard | +3.108 |
Neg logit contributions | |
Ham | -3.777 |
Seym | -3.502 |
Pru | -3.470 |
slam | -3.281 |
Corm | -3.256 |
Token | continues |
Token ID | 4477 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
CARD | +5.464 |
infect | +4.644 |
foreskin | +4.543 |
helic | +4.469 |
beard | +4.411 |
Neg logit contributions | |
Ham | -4.764 |
Seym | -4.511 |
Pru | -4.293 |
Corm | -4.112 |
Ryan | -4.090 |
Token | to |
Token ID | 284 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
CARD | +4.957 |
infect | +4.152 |
foreskin | +4.015 |
helic | +3.922 |
beard | +3.873 |
Neg logit contributions | |
Ham | -5.008 |
Seym | -4.695 |
Pru | -4.609 |
slam | -4.416 |
encers | -4.396 |
Token | save |
Token ID | 3613 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
CARD | +5.893 |
infect | +5.051 |
foreskin | +4.888 |
beard | +4.844 |
helic | +4.790 |
Neg logit contributions | |
Ham | -5.414 |
Seym | -5.341 |
Pru | -5.009 |
ouver | -4.743 |
Ryan | -4.710 |