Token | : |
Token ID | 25 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
CRIP | +1.730 |
HS | +1.701 |
Sen | +1.630 |
Secretary | +1.609 |
IER | +1.600 |
Neg logit contributions | |
!-- | -1.980 |
isphere | -1.825 |
consolidated | -1.767 |
cient | -1.716 |
colle | -1.700 |
Token | David |
Token ID | 3271 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
CRIP | +1.143 |
HS | +1.126 |
Sen | +1.079 |
Secretary | +1.064 |
IER | +1.057 |
Neg logit contributions | |
!-- | -1.374 |
isphere | -1.271 |
consolidated | -1.233 |
cient | -1.194 |
colle | -1.179 |
Token | A |
Token ID | 317 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
!-- | +0.512 |
isphere | +0.460 |
consolidated | +0.449 |
cient | +0.433 |
colle | +0.430 |
Neg logit contributions | |
CRIP | -0.577 |
HS | -0.560 |
Sen | -0.540 |
Secretary | -0.534 |
IER | -0.533 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
!-- | +0.711 |
isphere | +0.630 |
consolidated | +0.614 |
cient | +0.591 |
colle | +0.583 |
Neg logit contributions | |
CRIP | -0.973 |
HS | -0.929 |
Sen | -0.904 |
Secretary | -0.901 |
IER | -0.898 |
Token | Sle |
Token ID | 19498 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
CRIP | +1.046 |
HS | +1.019 |
Sen | +0.970 |
Secretary | +0.954 |
IER | +0.950 |
Neg logit contributions | |
!-- | -1.516 |
isphere | -1.405 |
consolidated | -1.371 |
cient | -1.332 |
colle | -1.324 |
Token | et |
Token ID | 316 |
Feature activation | +7.90e+00 |
Pos logit contributions | |
CRIP | +0.813 |
HS | +0.796 |
Sen | +0.751 |
serial | +0.729 |
ipal | +0.727 |
Neg logit contributions | |
!-- | -1.762 |
isphere | -1.658 |
consolidated | -1.637 |
colle | -1.617 |
cient | -1.568 |
Token | , |
Token ID | 11 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
HS | +5.261 |
CRIP | +5.128 |
Sen | +4.974 |
Secretary | +4.932 |
ipal | +4.903 |
Neg logit contributions | |
!-- | -5.524 |
isphere | -5.237 |
consolidated | -4.965 |
cient | -4.783 |
colle | -4.685 |
Token | d |
Token ID | 288 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
CRIP | +1.971 |
HS | +1.967 |
Sen | +1.868 |
Secretary | +1.850 |
ipal | +1.823 |
Neg logit contributions | |
!-- | -2.892 |
isphere | -2.721 |
consolidated | -2.602 |
cient | -2.537 |
colle | -2.480 |
Token | sle |
Token ID | 26738 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
!-- | +0.190 |
isphere | +0.174 |
consolidated | +0.169 |
cient | +0.166 |
colle | +0.164 |
Neg logit contributions | |
CRIP | -0.156 |
HS | -0.150 |
Sen | -0.144 |
IER | -0.143 |
Roose | -0.142 |
Token | et |
Token ID | 316 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
CRIP | +0.119 |
HS | +0.115 |
Sen | +0.109 |
Secretary | +0.106 |
IER | +0.106 |
Neg logit contributions | |
!-- | -0.221 |
isphere | -0.206 |
consolidated | -0.202 |
cient | -0.196 |
colle | -0.195 |
Token | @ |
Token ID | 31 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
CRIP | +1.540 |
HS | +1.534 |
Sen | +1.420 |
Secretary | +1.399 |
ipal | +1.384 |
Neg logit contributions | |
!-- | -3.420 |
isphere | -3.192 |
consolidated | -3.138 |
cient | -3.032 |
colle | -3.026 |
Token | - |
Token ID | 12 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
CRIP | +2.379 |
HS | +2.327 |
Sen | +2.241 |
Secretary | +2.214 |
IER | +2.204 |
Neg logit contributions | |
!-- | -2.227 |
isphere | -2.028 |
consolidated | -1.974 |
cient | -1.894 |
colle | -1.890 |
Token | impact |
Token ID | 48240 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
CRIP | +0.902 |
HS | +0.873 |
Sen | +0.830 |
Secretary | +0.816 |
IER | +0.814 |
Neg logit contributions | |
!-- | -1.408 |
isphere | -1.304 |
consolidated | -1.277 |
cient | -1.240 |
colle | -1.235 |
Token | , |
Token ID | 11 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
CRIP | +3.325 |
HS | +3.296 |
Sen | +3.161 |
Secretary | +3.125 |
IER | +3.094 |
Neg logit contributions | |
!-- | -3.235 |
isphere | -3.013 |
consolidated | -2.897 |
colle | -2.856 |
cient | -2.798 |
Token | environmental |
Token ID | 6142 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
CRIP | +2.820 |
HS | +2.793 |
Sen | +2.673 |
Roose | +2.632 |
Secretary | +2.629 |
Neg logit contributions | |
!-- | -3.118 |
isphere | -2.850 |
consolidated | -2.729 |
cient | -2.654 |
colle | -2.605 |
Token | - |
Token ID | 12 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
CRIP | +2.511 |
HS | +2.468 |
Sen | +2.373 |
Secretary | +2.350 |
IER | +2.324 |
Neg logit contributions | |
!-- | -2.438 |
isphere | -2.234 |
consolidated | -2.181 |
colle | -2.087 |
cient | -2.078 |
Token | management |
Token ID | 27604 |
Feature activation | +7.84e+00 |
Pos logit contributions | |
HS | +2.235 |
CRIP | +2.234 |
Sen | +2.137 |
Secretary | +2.106 |
serial | +2.083 |
Neg logit contributions | |
!-- | -3.157 |
isphere | -2.917 |
consolidated | -2.871 |
colle | -2.780 |
cient | -2.758 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
HS | +4.658 |
CRIP | +4.505 |
Sen | +4.407 |
Secretary | +4.349 |
Roose | +4.346 |
Neg logit contributions | |
colle | -5.657 |
isphere | -5.611 |
!-- | -5.562 |
consolidated | -5.376 |
�� | -5.156 |
Token | environmental |
Token ID | 6142 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
CRIP | +2.676 |
HS | +2.647 |
Sen | +2.537 |
Roose | +2.493 |
Secretary | +2.492 |
Neg logit contributions | |
!-- | -2.930 |
isphere | -2.677 |
consolidated | -2.569 |
cient | -2.496 |
colle | -2.453 |
Token | - |
Token ID | 12 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
CRIP | +2.306 |
HS | +2.255 |
Sen | +2.171 |
Secretary | +2.146 |
IER | +2.136 |
Neg logit contributions | |
!-- | -2.152 |
isphere | -1.956 |
consolidated | -1.906 |
cient | -1.828 |
colle | -1.822 |
Token | technology |
Token ID | 45503 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
CRIP | +2.281 |
HS | +2.273 |
Sen | +2.169 |
Secretary | +2.140 |
serial | +2.111 |
Neg logit contributions | |
!-- | -3.240 |
isphere | -2.992 |
consolidated | -2.947 |
colle | -2.848 |
cient | -2.833 |
Token | , |
Token ID | 11 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
HS | +4.103 |
CRIP | +4.095 |
Sen | +3.942 |
Secretary | +3.883 |
Roose | +3.837 |
Neg logit contributions | |
!-- | -4.474 |
isphere | -4.386 |
colle | -4.221 |
consolidated | -4.174 |
cient | -4.066 |
Token | ulse |
Token ID | 9615 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
!-- | +0.029 |
isphere | +0.026 |
consolidated | +0.026 |
colle | +0.025 |
cient | +0.025 |
Neg logit contributions | |
CRIP | -0.023 |
HS | -0.023 |
Sen | -0.022 |
Secretary | -0.021 |
IER | -0.021 |
Token | Amount |
Token ID | 31264 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
!-- | +2.602 |
isphere | +2.334 |
consolidated | +2.248 |
cient | +2.225 |
~~ | +2.165 |
Neg logit contributions | |
CRIP | -2.132 |
HS | -2.065 |
Roose | -1.984 |
ipal | -1.962 |
Sen | -1.953 |
Token | ; |
Token ID | 26 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
!-- | +0.270 |
isphere | +0.242 |
consolidated | +0.237 |
cient | +0.227 |
colle | +0.225 |
Neg logit contributions | |
CRIP | -0.309 |
HS | -0.302 |
Sen | -0.291 |
Secretary | -0.289 |
Roose | -0.287 |
Token | } |
Token ID | 1782 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
!-- | +2.124 |
isphere | +1.886 |
consolidated | +1.873 |
colle | +1.774 |
cient | +1.771 |
Neg logit contributions | |
CRIP | -2.427 |
HS | -2.365 |
Sen | -2.281 |
Secretary | -2.279 |
IER | -2.256 |
Token | 1 |
Token ID | 352 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
CRIP | +0.828 |
HS | +0.801 |
Sen | +0.762 |
Secretary | +0.749 |
IER | +0.747 |
Neg logit contributions | |
!-- | -1.273 |
isphere | -1.178 |
consolidated | -1.153 |
cient | -1.120 |
colle | -1.115 |
Token | 2 |
Token ID | 362 |
Feature activation | +7.81e+00 |
Pos logit contributions | |
CRIP | +1.929 |
HS | +1.854 |
Sen | +1.745 |
IER | +1.662 |
1280 | +1.655 |
Neg logit contributions | |
!-- | -4.536 |
isphere | -4.339 |
colle | -4.165 |
consolidated | -4.156 |
cient | -4.146 |
Token | 3 |
Token ID | 513 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
CRIP | +4.167 |
HS | +4.059 |
Sutherland | +3.803 |
Sen | +3.789 |
serial | +3.715 |
Neg logit contributions | |
!-- | -6.314 |
isphere | -6.129 |
colle | -5.953 |
cient | -5.727 |
consolidated | -5.689 |
Token | 4 |
Token ID | 604 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
CRIP | +3.608 |
HS | +3.469 |
Sen | +3.250 |
serial | +3.234 |
Secretary | +3.176 |
Neg logit contributions | |
!-- | -5.967 |
isphere | -5.673 |
cient | -5.430 |
consolidated | -5.418 |
colle | -5.381 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
CRIP | +2.425 |
HS | +2.324 |
Sen | +2.168 |
IER | +2.120 |
serial | +2.113 |
Neg logit contributions | |
!-- | -5.207 |
isphere | -4.907 |
consolidated | -4.763 |
cient | -4.691 |
colle | -4.672 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
CRIP | +1.986 |
HS | +1.918 |
Sen | +1.778 |
IER | +1.737 |
Secretary | +1.734 |
Neg logit contributions | |
!-- | -4.056 |
isphere | -3.776 |
consolidated | -3.685 |
cient | -3.621 |
colle | -3.588 |
Token | 7 |
Token ID | 767 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
CRIP | +1.727 |
HS | +1.679 |
Sen | +1.573 |
IER | +1.530 |
Secretary | +1.521 |
Neg logit contributions | |
!-- | -3.313 |
isphere | -3.077 |
consolidated | -3.015 |
cient | -2.955 |
colle | -2.936 |
Token | been |
Token ID | 587 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
CRIP | +0.753 |
HS | +0.736 |
Sen | +0.709 |
Secretary | +0.700 |
IER | +0.697 |
Neg logit contributions | |
!-- | -0.767 |
isphere | -0.699 |
consolidated | -0.676 |
cient | -0.656 |
colle | -0.652 |
Token | more |
Token ID | 517 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
!-- | +0.016 |
isphere | +0.015 |
consolidated | +0.015 |
cient | +0.014 |
colle | +0.014 |
Neg logit contributions | |
CRIP | -0.016 |
HS | -0.016 |
Sen | -0.015 |
Secretary | -0.015 |
IER | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
CRIP | +0.781 |
HS | +0.765 |
Sen | +0.739 |
Secretary | +0.728 |
IER | +0.725 |
Neg logit contributions | |
!-- | -0.789 |
isphere | -0.719 |
consolidated | -0.690 |
cient | -0.670 |
colle | -0.666 |
Token | a |
Token ID | 257 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
!-- | +0.039 |
isphere | +0.036 |
consolidated | +0.035 |
cient | +0.034 |
colle | +0.033 |
Neg logit contributions | |
CRIP | -0.040 |
HS | -0.039 |
Sen | -0.037 |
Secretary | -0.037 |
IER | -0.037 |
Token | liability |
Token ID | 12247 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
CRIP | +0.263 |
HS | +0.257 |
Sen | +0.247 |
Secretary | +0.243 |
IER | +0.243 |
Neg logit contributions | |
!-- | -0.273 |
isphere | -0.250 |
consolidated | -0.242 |
cient | -0.235 |
colle | -0.233 |
Token | than |
Token ID | 621 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
!-- | +0.374 |
isphere | +0.334 |
consolidated | +0.327 |
cient | +0.312 |
colle | +0.310 |
Neg logit contributions | |
CRIP | -0.454 |
HS | -0.443 |
Sen | -0.426 |
Secretary | -0.422 |
IER | -0.421 |
Token | an |
Token ID | 281 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
HS | +4.374 |
CRIP | +4.345 |
Sen | +4.275 |
Roose | +4.221 |
IER | +4.183 |
Neg logit contributions | |
!-- | -5.553 |
isphere | -5.394 |
cient | -4.994 |
consolidated | -4.926 |
cius | -4.791 |
Token | asset |
Token ID | 11171 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
CRIP | +2.000 |
HS | +1.951 |
Sen | +1.884 |
IER | +1.879 |
ipal | +1.852 |
Neg logit contributions | |
!-- | -2.262 |
isphere | -2.106 |
consolidated | -2.018 |
cient | -1.947 |
colle | -1.943 |
Token | , |
Token ID | 11 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
CRIP | +0.604 |
HS | +0.590 |
Sen | +0.570 |
Secretary | +0.563 |
IER | +0.562 |
Neg logit contributions | |
!-- | -0.522 |
isphere | -0.472 |
consolidated | -0.458 |
cient | -0.441 |
colle | -0.438 |
Token | connecting |
Token ID | 14320 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
!-- | +0.270 |
isphere | +0.246 |
consolidated | +0.242 |
cient | +0.231 |
colle | +0.231 |
Neg logit contributions | |
CRIP | -0.257 |
HS | -0.250 |
Sen | -0.239 |
IER | -0.237 |
Secretary | -0.236 |
Token | Land |
Token ID | 6379 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
CRIP | +1.362 |
HS | +1.339 |
Sen | +1.300 |
Secretary | +1.273 |
IER | +1.267 |
Neg logit contributions | |
!-- | -1.405 |
isphere | -1.284 |
consolidated | -1.240 |
cient | -1.206 |
colle | -1.192 |
Token | prohibited |
Token ID | 12244 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
!-- | +1.601 |
isphere | +1.437 |
consolidated | +1.435 |
colle | +1.375 |
cient | +1.360 |
Neg logit contributions | |
CRIP | -1.504 |
HS | -1.469 |
Sen | -1.399 |
Secretary | -1.390 |
IER | -1.385 |
Token | without |
Token ID | 1231 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
!-- | +0.551 |
isphere | +0.499 |
consolidated | +0.488 |
cient | +0.470 |
colle | +0.467 |
Neg logit contributions | |
CRIP | -0.558 |
HS | -0.544 |
Sen | -0.523 |
Secretary | -0.517 |
IER | -0.516 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
CRIP | +0.245 |
HS | +0.239 |
Sen | +0.230 |
Secretary | +0.227 |
IER | +0.226 |
Neg logit contributions | |
!-- | -0.237 |
isphere | -0.215 |
consolidated | -0.208 |
cient | -0.202 |
colle | -0.200 |
Token | express |
Token ID | 4911 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
!-- | +0.113 |
isphere | +0.103 |
consolidated | +0.101 |
cient | +0.097 |
colle | +0.097 |
Neg logit contributions | |
CRIP | -0.106 |
HS | -0.103 |
Sen | -0.099 |
Secretary | -0.098 |
IER | -0.098 |
Token | written |
Token ID | 3194 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
CRIP | +1.370 |
HS | +1.339 |
Sen | +1.298 |
Secretary | +1.282 |
IER | +1.279 |
Neg logit contributions | |
!-- | -1.066 |
isphere | -0.957 |
consolidated | -0.922 |
cient | -0.888 |
colle | -0.882 |
Token | permission |
Token ID | 7170 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
CRIP | +1.601 |
HS | +1.561 |
Sen | +1.497 |
Secretary | +1.475 |
IER | +1.467 |
Neg logit contributions | |
!-- | -2.147 |
isphere | -1.978 |
consolidated | -1.914 |
cient | -1.877 |
colle | -1.871 |
Token | of |
Token ID | 286 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
CRIP | +4.728 |
HS | +4.647 |
Secretary | +4.434 |
Sen | +4.430 |
IER | +4.315 |
Neg logit contributions | |
!-- | -5.432 |
isphere | -4.939 |
consolidated | -4.786 |
colle | -4.691 |
cient | -4.647 |
Token | Money |
Token ID | 12911 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
CRIP | +2.927 |
HS | +2.892 |
Roose | +2.748 |
Sen | +2.747 |
Secretary | +2.710 |
Neg logit contributions | |
!-- | -3.216 |
isphere | -3.042 |
consolidated | -2.880 |
cient | -2.836 |
colle | -2.788 |
Token | Morning |
Token ID | 14410 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
CRIP | +2.485 |
HS | +2.479 |
Sen | +2.378 |
Secretary | +2.368 |
IER | +2.353 |
Neg logit contributions | |
!-- | -1.967 |
isphere | -1.784 |
consolidated | -1.745 |
colle | -1.719 |
cient | -1.651 |
Token | . |
Token ID | 13 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
!-- | +0.687 |
isphere | +0.614 |
consolidated | +0.604 |
cient | +0.574 |
colle | +0.571 |
Neg logit contributions | |
CRIP | -0.795 |
HS | -0.776 |
Sen | -0.748 |
IER | -0.740 |
Secretary | -0.739 |
Token | 16 |
Token ID | 1467 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
CRIP | +0.470 |
HS | +0.458 |
Sen | +0.440 |
Secretary | +0.434 |
IER | +0.432 |
Neg logit contributions | |
!-- | -0.532 |
isphere | -0.487 |
consolidated | -0.474 |
cient | -0.459 |
colle | -0.457 |
Token | bourne |
Token ID | 12544 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
HS | +0.601 |
CRIP | +0.601 |
Sen | +0.574 |
ipal | +0.574 |
serial | +0.567 |
Neg logit contributions | |
!-- | -0.486 |
isphere | -0.437 |
consolidated | -0.431 |
colle | -0.418 |
cient | -0.404 |
Token | - |
Token ID | 12 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
CRIP | +1.121 |
HS | +1.101 |
Sen | +1.059 |
Secretary | +1.039 |
ipal | +1.035 |
Neg logit contributions | |
!-- | -1.165 |
isphere | -1.090 |
consolidated | -1.046 |
colle | -1.029 |
cient | -1.009 |
Token | 3000 |
Token ID | 23924 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
CRIP | +1.375 |
HS | +1.356 |
Sen | +1.304 |
serial | +1.280 |
Secretary | +1.279 |
Neg logit contributions | |
!-- | -1.307 |
isphere | -1.190 |
consolidated | -1.146 |
colle | -1.109 |
cient | -1.100 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
CRIP | +2.759 |
HS | +2.713 |
Sen | +2.582 |
Secretary | +2.539 |
IER | +2.528 |
Neg logit contributions | |
!-- | -3.112 |
isphere | -2.901 |
consolidated | -2.801 |
colle | -2.739 |
cient | -2.719 |
Token | vic |
Token ID | 20429 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
CRIP | +1.595 |
HS | +1.564 |
Sen | +1.504 |
Secretary | +1.483 |
Roose | +1.475 |
Neg logit contributions | |
!-- | -1.422 |
isphere | -1.294 |
consolidated | -1.245 |
cient | -1.199 |
colle | -1.185 |
Token |
|
Token ID | 198 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
CRIP | +0.486 |
HS | +0.476 |
Sen | +0.457 |
Secretary | +0.450 |
IER | +0.449 |
Neg logit contributions | |
!-- | -0.535 |
isphere | -0.489 |
consolidated | -0.478 |
colle | -0.464 |
cient | -0.462 |
Token |
|
Token ID | 198 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
HS | +3.704 |
CRIP | +3.516 |
Sen | +3.515 |
Secretary | +3.406 |
Quotes | +3.376 |
Neg logit contributions | |
isphere | -6.278 |
colle | -6.198 |
!-- | -6.146 |
exha | -5.961 |
consolidated | -5.943 |
Token | First |
Token ID | 5962 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
HS | +1.968 |
CRIP | +1.859 |
Sen | +1.783 |
Secretary | +1.771 |
ipal | +1.735 |
Neg logit contributions | |
!-- | -5.824 |
consolidated | -5.485 |
colle | -5.474 |
isphere | -5.472 |
cient | -5.187 |
Token | posted |
Token ID | 4481 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
!-- | +0.237 |
isphere | +0.205 |
consolidated | +0.192 |
colle | +0.186 |
cient | +0.183 |
Neg logit contributions | |
CRIP | -0.515 |
HS | -0.510 |
Sen | -0.493 |
Secretary | -0.490 |
ipal | -0.488 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
!-- | +0.045 |
isphere | +0.042 |
consolidated | +0.041 |
cient | +0.039 |
colle | +0.039 |
Neg logit contributions | |
CRIP | -0.033 |
HS | -0.032 |
Sen | -0.031 |
Secretary | -0.030 |
IER | -0.030 |
Token | R |
Token ID | 49 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
CRIP | +0.876 |
HS | +0.855 |
Sen | +0.821 |
Secretary | +0.807 |
IER | +0.800 |
Neg logit contributions | |
!-- | -1.109 |
isphere | -1.024 |
consolidated | -1.004 |
colle | -0.968 |
cient | -0.966 |
Token | MB |
Token ID | 10771 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
CRIP | +2.757 |
HS | +2.749 |
Sen | +2.558 |
1280 | +2.537 |
IER | +2.527 |
Neg logit contributions | |
!-- | -4.020 |
isphere | -3.840 |
colle | -3.697 |
consolidated | -3.665 |
cient | -3.598 |
Token | Texture |
Token ID | 44409 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
CRIP | +2.962 |
HS | +2.887 |
1280 | +2.701 |
Sen | +2.696 |
IER | +2.665 |
Neg logit contributions | |
!-- | -4.917 |
isphere | -4.653 |
consolidated | -4.436 |
cient | -4.385 |
colle | -4.365 |
Token | Units |
Token ID | 27719 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
HS | +3.303 |
CRIP | +3.283 |
Sen | +3.099 |
1280 | +3.095 |
serial | +3.057 |
Neg logit contributions | |
!-- | -3.814 |
isphere | -3.483 |
cient | -3.348 |
consolidated | -3.332 |
colle | -3.229 |
Token | 144 |
Token ID | 20224 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
CRIP | +1.327 |
HS | +1.296 |
Sen | +1.235 |
IER | +1.210 |
Secretary | +1.205 |
Neg logit contributions | |
!-- | -1.854 |
isphere | -1.724 |
consolidated | -1.668 |
cient | -1.631 |
colle | -1.619 |
Token | 64 |
Token ID | 5598 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
CRIP | +0.644 |
HS | +0.619 |
Sen | +0.586 |
Secretary | +0.577 |
IER | +0.573 |
Neg logit contributions | |
!-- | -1.224 |
isphere | -1.135 |
consolidated | -1.118 |
cient | -1.087 |
colle | -1.083 |
Token | 104 |
Token ID | 14436 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
CRIP | +1.298 |
HS | +1.253 |
Sen | +1.164 |
IER | +1.134 |
Secretary | +1.120 |
Neg logit contributions | |
!-- | -3.146 |
isphere | -2.971 |
consolidated | -2.889 |
cient | -2.831 |
colle | -2.825 |
Token | 80 |
Token ID | 4019 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
CRIP | +2.969 |
HS | +2.943 |
1280 | +2.738 |
Sen | +2.678 |
Sutherland | +2.613 |
Neg logit contributions | |
!-- | -7.016 |
isphere | -6.796 |
colle | -6.407 |
consolidated | -6.407 |
cient | -6.369 |
Token | 120 |
Token ID | 7982 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
CRIP | +1.604 |
HS | +1.566 |
Sen | +1.446 |
IER | +1.416 |
1280 | +1.405 |
Neg logit contributions | |
!-- | -3.584 |
isphere | -3.406 |
consolidated | -3.278 |
colle | -3.233 |
cient | -3.231 |
Token | 160 |
Token ID | 13454 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
CRIP | +2.205 |
HS | +2.163 |
Sen | +1.981 |
1280 | +1.980 |
IER | +1.949 |
Neg logit contributions | |
!-- | -5.086 |
isphere | -4.859 |
consolidated | -4.634 |
cient | -4.624 |
colle | -4.604 |
Token | Texture |
Token ID | 44409 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
CRIP | +1.684 |
HS | +1.638 |
Sen | +1.515 |
IER | +1.492 |
Secretary | +1.469 |
Neg logit contributions | |
!-- | -3.677 |
isphere | -3.495 |
consolidated | -3.361 |
cient | -3.324 |
colle | -3.306 |
Token | fill |
Token ID | 6070 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
HS | +3.372 |
CRIP | +3.274 |
1280 | +3.089 |
Sutherland | +3.082 |
Sen | +3.077 |
Neg logit contributions | |
!-- | -4.101 |
isphere | -3.814 |
cient | -3.584 |
omore | -3.562 |
consolidated | -3.510 |
Token | 's |
Token ID | 338 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
!-- | +0.359 |
isphere | +0.320 |
consolidated | +0.312 |
cient | +0.298 |
colle | +0.295 |
Neg logit contributions | |
CRIP | -0.479 |
HS | -0.467 |
Sen | -0.451 |
Secretary | -0.447 |
IER | -0.447 |
Token | The |
Token ID | 383 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
!-- | +0.971 |
isphere | +0.883 |
consolidated | +0.873 |
cient | +0.843 |
colle | +0.836 |
Neg logit contributions | |
CRIP | -0.847 |
HS | -0.824 |
Sen | -0.786 |
IER | -0.784 |
Secretary | -0.779 |
Token | Hobbit |
Token ID | 43877 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
CRIP | +0.306 |
HS | +0.292 |
Sen | +0.271 |
IER | +0.265 |
Secretary | +0.265 |
Neg logit contributions | |
!-- | -0.760 |
isphere | -0.711 |
consolidated | -0.699 |
cient | -0.683 |
colle | -0.679 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
CRIP | +1.578 |
HS | +1.540 |
Sen | +1.480 |
Secretary | +1.454 |
IER | +1.453 |
Neg logit contributions | |
!-- | -1.541 |
isphere | -1.401 |
consolidated | -1.354 |
cient | -1.315 |
colle | -1.312 |
Token | introducing |
Token ID | 16118 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
CRIP | +1.181 |
HS | +1.151 |
Sen | +1.108 |
Secretary | +1.092 |
IER | +1.087 |
Neg logit contributions | |
!-- | -1.177 |
isphere | -1.076 |
consolidated | -1.040 |
cient | -1.007 |
colle | -1.001 |
Token | Gand |
Token ID | 17727 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
!-- | +0.760 |
isphere | +0.686 |
consolidated | +0.673 |
cient | +0.648 |
colle | +0.643 |
Neg logit contributions | |
CRIP | -0.763 |
HS | -0.745 |
Sen | -0.715 |
IER | -0.708 |
Secretary | -0.707 |
Token | alf |
Token ID | 1604 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
HS | +3.016 |
CRIP | +2.817 |
Sen | +2.771 |
wy | +2.749 |
Sutherland | +2.733 |
Neg logit contributions | |
!-- | -6.759 |
consolidated | -6.235 |
colle | -6.221 |
isphere | -6.209 |
cient | -5.990 |
Token | . |
Token ID | 13 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
CRIP | +2.867 |
HS | +2.799 |
Sen | +2.685 |
Roose | +2.644 |
Secretary | +2.632 |
Neg logit contributions | |
!-- | -3.130 |
isphere | -2.883 |
consolidated | -2.804 |
colle | -2.719 |
cient | -2.717 |
Token |
|
Token ID | 198 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
CRIP | +0.469 |
HS | +0.456 |
Sen | +0.438 |
IER | +0.434 |
Secretary | +0.433 |
Neg logit contributions | |
!-- | -0.504 |
isphere | -0.457 |
consolidated | -0.447 |
cient | -0.434 |
colle | -0.429 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
CRIP | +0.420 |
HS | +0.412 |
Sen | +0.395 |
Secretary | +0.388 |
IER | +0.386 |
Neg logit contributions | |
!-- | -0.501 |
isphere | -0.465 |
consolidated | -0.452 |
colle | -0.440 |
cient | -0.435 |
Token | AL |
Token ID | 1847 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
!-- | +0.900 |
isphere | +0.820 |
consolidated | +0.796 |
cient | +0.782 |
colle | +0.766 |
Neg logit contributions | |
CRIP | -0.695 |
HS | -0.673 |
Sen | -0.645 |
Roose | -0.641 |
ipal | -0.639 |
Token | to |
Token ID | 284 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
CRIP | +2.497 |
HS | +2.443 |
Sen | +2.364 |
IER | +2.325 |
Secretary | +2.322 |
Neg logit contributions | |
!-- | -2.461 |
isphere | -2.239 |
consolidated | -2.157 |
cient | -2.103 |
colle | -2.092 |
Token | do |
Token ID | 466 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
CRIP | +1.980 |
HS | +1.955 |
Sen | +1.897 |
Secretary | +1.855 |
ipal | +1.845 |
Neg logit contributions | |
!-- | -2.401 |
isphere | -2.243 |
consolidated | -2.152 |
cient | -2.101 |
colle | -2.072 |
Token | with |
Token ID | 351 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
CRIP | +1.760 |
HS | +1.734 |
Sen | +1.702 |
Secretary | +1.669 |
IER | +1.643 |
Neg logit contributions | |
!-- | -2.408 |
isphere | -2.294 |
colle | -2.208 |
consolidated | -2.202 |
cient | -2.112 |
Token | electoral |
Token ID | 13901 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
CRIP | +0.548 |
HS | +0.535 |
Sen | +0.514 |
Secretary | +0.507 |
IER | +0.505 |
Neg logit contributions | |
!-- | -0.584 |
isphere | -0.533 |
consolidated | -0.518 |
cient | -0.502 |
colle | -0.498 |
Token | politics |
Token ID | 4819 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
!-- | +0.871 |
isphere | +0.807 |
consolidated | +0.789 |
cient | +0.767 |
colle | +0.763 |
Neg logit contributions | |
CRIP | -0.556 |
HS | -0.538 |
Sen | -0.512 |
Secretary | -0.503 |
IER | -0.501 |
Token | than |
Token ID | 621 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
CRIP | +0.867 |
HS | +0.847 |
Sen | +0.820 |
Secretary | +0.809 |
IER | +0.804 |
Neg logit contributions | |
!-- | -0.755 |
isphere | -0.687 |
consolidated | -0.664 |
cient | -0.639 |
colle | -0.636 |
Token | it |
Token ID | 340 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
HS | +4.258 |
CRIP | +4.204 |
Secretary | +4.049 |
Sen | +4.040 |
Roose | +3.983 |
Neg logit contributions | |
!-- | -5.423 |
isphere | -5.019 |
consolidated | -4.715 |
cient | -4.689 |
colle | -4.590 |
Token | had |
Token ID | 550 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
CRIP | +3.165 |
HS | +3.163 |
Sen | +3.008 |
Secretary | +2.972 |
ipal | +2.947 |
Neg logit contributions | |
!-- | -4.472 |
isphere | -4.195 |
consolidated | -3.982 |
cient | -3.922 |
colle | -3.910 |
Token | to |
Token ID | 284 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
CRIP | +2.692 |
HS | +2.657 |
Sen | +2.538 |
Secretary | +2.512 |
ipal | +2.482 |
Neg logit contributions | |
!-- | -3.556 |
isphere | -3.293 |
consolidated | -3.181 |
cient | -3.091 |
colle | -3.072 |
Token | do |
Token ID | 466 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
HS | +3.761 |
CRIP | +3.708 |
Sen | +3.591 |
Secretary | +3.530 |
ipal | +3.528 |
Neg logit contributions | |
!-- | -5.377 |
isphere | -5.179 |
consolidated | -4.797 |
colle | -4.758 |
cient | -4.683 |
Token | with |
Token ID | 351 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
HS | +3.737 |
CRIP | +3.731 |
Sen | +3.608 |
Secretary | +3.573 |
IER | +3.493 |
Neg logit contributions | |
!-- | -5.289 |
isphere | -5.020 |
consolidated | -4.746 |
colle | -4.699 |
cient | -4.598 |
Token | Amount |
Token ID | 31264 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
!-- | +2.602 |
isphere | +2.334 |
consolidated | +2.248 |
cient | +2.225 |
~~ | +2.165 |
Neg logit contributions | |
CRIP | -2.132 |
HS | -2.065 |
Roose | -1.984 |
ipal | -1.962 |
Sen | -1.953 |
Token | ; |
Token ID | 26 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
!-- | +0.270 |
isphere | +0.242 |
consolidated | +0.237 |
cient | +0.227 |
colle | +0.225 |
Neg logit contributions | |
CRIP | -0.309 |
HS | -0.302 |
Sen | -0.291 |
Secretary | -0.289 |
Roose | -0.287 |
Token | } |
Token ID | 1782 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
!-- | +2.124 |
isphere | +1.886 |
consolidated | +1.873 |
colle | +1.774 |
cient | +1.771 |
Neg logit contributions | |
CRIP | -2.427 |
HS | -2.365 |
Sen | -2.281 |
Secretary | -2.279 |
IER | -2.256 |
Token | 1 |
Token ID | 352 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
CRIP | +0.828 |
HS | +0.801 |
Sen | +0.762 |
Secretary | +0.749 |
IER | +0.747 |
Neg logit contributions | |
!-- | -1.273 |
isphere | -1.178 |
consolidated | -1.153 |
cient | -1.120 |
colle | -1.115 |
Token | 2 |
Token ID | 362 |
Feature activation | +7.81e+00 |
Pos logit contributions | |
CRIP | +1.929 |
HS | +1.854 |
Sen | +1.745 |
IER | +1.662 |
1280 | +1.655 |
Neg logit contributions | |
!-- | -4.536 |
isphere | -4.339 |
colle | -4.165 |
consolidated | -4.156 |
cient | -4.146 |
Token | 3 |
Token ID | 513 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
CRIP | +4.167 |
HS | +4.059 |
Sutherland | +3.803 |
Sen | +3.789 |
serial | +3.715 |
Neg logit contributions | |
!-- | -6.314 |
isphere | -6.129 |
colle | -5.953 |
cient | -5.727 |
consolidated | -5.689 |
Token | 4 |
Token ID | 604 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
CRIP | +3.608 |
HS | +3.469 |
Sen | +3.250 |
serial | +3.234 |
Secretary | +3.176 |
Neg logit contributions | |
!-- | -5.967 |
isphere | -5.673 |
cient | -5.430 |
consolidated | -5.418 |
colle | -5.381 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
CRIP | +2.425 |
HS | +2.324 |
Sen | +2.168 |
IER | +2.120 |
serial | +2.113 |
Neg logit contributions | |
!-- | -5.207 |
isphere | -4.907 |
consolidated | -4.763 |
cient | -4.691 |
colle | -4.672 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
CRIP | +1.986 |
HS | +1.918 |
Sen | +1.778 |
IER | +1.737 |
Secretary | +1.734 |
Neg logit contributions | |
!-- | -4.056 |
isphere | -3.776 |
consolidated | -3.685 |
cient | -3.621 |
colle | -3.588 |
Token | 7 |
Token ID | 767 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
CRIP | +1.727 |
HS | +1.679 |
Sen | +1.573 |
IER | +1.530 |
Secretary | +1.521 |
Neg logit contributions | |
!-- | -3.313 |
isphere | -3.077 |
consolidated | -3.015 |
cient | -2.955 |
colle | -2.936 |
Token | 8 |
Token ID | 807 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
CRIP | +1.651 |
HS | +1.588 |
Sen | +1.488 |
Secretary | +1.455 |
IER | +1.454 |
Neg logit contributions | |
!-- | -3.365 |
isphere | -3.146 |
consolidated | -3.082 |
cient | -3.019 |
colle | -2.997 |
Token | Then |
Token ID | 3244 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
CRIP | +0.263 |
HS | +0.255 |
Sen | +0.245 |
Secretary | +0.241 |
IER | +0.241 |
Neg logit contributions | |
!-- | -0.302 |
isphere | -0.276 |
consolidated | -0.270 |
cient | -0.261 |
colle | -0.259 |
Token | , |
Token ID | 11 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
CRIP | +0.466 |
HS | +0.455 |
Sen | +0.438 |
Secretary | +0.432 |
IER | +0.431 |
Neg logit contributions | |
!-- | -0.445 |
isphere | -0.404 |
consolidated | -0.393 |
cient | -0.379 |
colle | -0.376 |
Token | as |
Token ID | 355 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
CRIP | +0.234 |
HS | +0.227 |
Sen | +0.218 |
Secretary | +0.215 |
IER | +0.215 |
Neg logit contributions | |
!-- | -0.251 |
isphere | -0.229 |
consolidated | -0.224 |
cient | -0.216 |
colle | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
!-- | +0.274 |
isphere | +0.249 |
consolidated | +0.243 |
cient | +0.234 |
colle | +0.233 |
Neg logit contributions | |
CRIP | -0.266 |
HS | -0.258 |
Sen | -0.248 |
Secretary | -0.245 |
IER | -0.244 |
Token | Guardian |
Token ID | 8283 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
!-- | +0.571 |
isphere | +0.525 |
consolidated | +0.513 |
cient | +0.498 |
colle | +0.495 |
Neg logit contributions | |
CRIP | -0.426 |
HS | -0.414 |
Sen | -0.395 |
Secretary | -0.389 |
IER | -0.388 |
Token | piece |
Token ID | 3704 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
CRIP | +1.620 |
HS | +1.592 |
Sen | +1.513 |
Secretary | +1.492 |
IER | +1.482 |
Neg logit contributions | |
!-- | -1.988 |
isphere | -1.834 |
consolidated | -1.765 |
cient | -1.727 |
colle | -1.705 |
Token | outlines |
Token ID | 27430 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
CRIP | +4.084 |
HS | +4.040 |
Sen | +3.850 |
Roose | +3.798 |
Secretary | +3.788 |
Neg logit contributions | |
!-- | -5.340 |
isphere | -4.897 |
consolidated | -4.635 |
colle | -4.609 |
cient | -4.586 |
Token | , |
Token ID | 11 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
CRIP | +3.676 |
HS | +3.618 |
Sen | +3.489 |
Secretary | +3.440 |
IER | +3.423 |
Neg logit contributions | |
!-- | -3.620 |
isphere | -3.318 |
consolidated | -3.203 |
cient | -3.104 |
colle | -3.101 |
Token | � |
Token ID | 564 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
!-- | +0.065 |
isphere | +0.059 |
consolidated | +0.058 |
cient | +0.056 |
colle | +0.055 |
Neg logit contributions | |
CRIP | -0.063 |
HS | -0.061 |
Sen | -0.059 |
Secretary | -0.058 |
IER | -0.058 |
Token | � |
Token ID | 250 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
!-- | +0.394 |
isphere | +0.359 |
consolidated | +0.351 |
cient | +0.340 |
colle | +0.337 |
Neg logit contributions | |
CRIP | -0.359 |
HS | -0.348 |
Sen | -0.333 |
IER | -0.330 |
Secretary | -0.329 |
Token | Over |
Token ID | 5886 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
CRIP | +0.424 |
HS | +0.412 |
Sen | +0.394 |
Secretary | +0.388 |
IER | +0.388 |
Neg logit contributions | |
!-- | -0.538 |
isphere | -0.495 |
consolidated | -0.483 |
cient | -0.468 |
colle | -0.466 |
Token | understand |
Token ID | 1833 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
CRIP | +0.453 |
HS | +0.442 |
Sen | +0.426 |
Secretary | +0.420 |
IER | +0.417 |
Neg logit contributions | |
!-- | -0.505 |
isphere | -0.462 |
consolidated | -0.448 |
cient | -0.435 |
colle | -0.431 |
Token | what |
Token ID | 644 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
CRIP | +0.196 |
HS | +0.190 |
Sen | +0.182 |
IER | +0.180 |
Secretary | +0.180 |
Neg logit contributions | |
!-- | -0.218 |
isphere | -0.199 |
consolidated | -0.195 |
cient | -0.188 |
colle | -0.187 |
Token | their |
Token ID | 511 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
CRIP | +0.551 |
HS | +0.535 |
Sen | +0.512 |
Secretary | +0.504 |
IER | +0.504 |
Neg logit contributions | |
!-- | -0.680 |
isphere | -0.623 |
consolidated | -0.610 |
cient | -0.590 |
colle | -0.587 |
Token | respective |
Token ID | 11756 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
CRIP | +1.474 |
HS | +1.435 |
Sen | +1.390 |
Secretary | +1.373 |
IER | +1.363 |
Neg logit contributions | |
!-- | -1.490 |
isphere | -1.366 |
consolidated | -1.308 |
cient | -1.280 |
colle | -1.266 |
Token | pres |
Token ID | 906 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
CRIP | +1.695 |
HS | +1.652 |
Sen | +1.598 |
Secretary | +1.576 |
Roose | +1.569 |
Neg logit contributions | |
!-- | -1.609 |
isphere | -1.464 |
consolidated | -1.410 |
cient | -1.370 |
colle | -1.356 |
Token | id |
Token ID | 312 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
CRIP | +0.041 |
HS | +0.039 |
Sen | +0.037 |
Secretary | +0.036 |
IER | +0.036 |
Neg logit contributions | |
!-- | -0.089 |
isphere | -0.083 |
consolidated | -0.081 |
cient | -0.080 |
colle | -0.079 |
Token | encies |
Token ID | 3976 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
HS | +2.858 |
CRIP | +2.852 |
Sen | +2.612 |
ipal | +2.544 |
Secretary | +2.536 |
Neg logit contributions | |
!-- | -6.569 |
isphere | -6.196 |
consolidated | -6.144 |
colle | -6.021 |
cient | -5.826 |
Token | might |
Token ID | 1244 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
CRIP | +1.424 |
HS | +1.393 |
Sen | +1.335 |
Secretary | +1.320 |
IER | +1.315 |
Neg logit contributions | |
!-- | -1.463 |
isphere | -1.337 |
consolidated | -1.294 |
cient | -1.253 |
colle | -1.248 |
Token | look |
Token ID | 804 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
CRIP | +0.483 |
HS | +0.470 |
Sen | +0.450 |
Secretary | +0.443 |
IER | +0.443 |
Neg logit contributions | |
!-- | -0.572 |
isphere | -0.526 |
consolidated | -0.512 |
cient | -0.497 |
colle | -0.494 |
Token | like |
Token ID | 588 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
CRIP | +2.053 |
HS | +2.031 |
Sen | +1.967 |
Secretary | +1.943 |
Roose | +1.933 |
Neg logit contributions | |
!-- | -1.724 |
isphere | -1.586 |
consolidated | -1.494 |
cient | -1.454 |
colle | -1.453 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
!-- | +0.548 |
isphere | +0.487 |
consolidated | +0.480 |
cient | +0.456 |
colle | +0.453 |
Neg logit contributions | |
CRIP | -0.640 |
HS | -0.626 |
Sen | -0.600 |
Secretary | -0.593 |
IER | -0.593 |
Token | * |
Token ID | 1635 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
!-- | +0.404 |
isphere | +0.372 |
consolidated | +0.363 |
cient | +0.352 |
colle | +0.350 |
Neg logit contributions | |
CRIP | -0.317 |
HS | -0.308 |
Sen | -0.295 |
Secretary | -0.290 |
IER | -0.290 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
CRIP | +1.811 |
HS | +1.765 |
Sen | +1.670 |
IER | +1.670 |
Secretary | +1.634 |
Neg logit contributions | |
!-- | -2.128 |
isphere | -1.989 |
consolidated | -1.909 |
cient | -1.868 |
colle | -1.846 |
Token | ; |
Token ID | 26 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
CRIP | +1.363 |
HS | +1.335 |
Sen | +1.277 |
IER | +1.268 |
Secretary | +1.253 |
Neg logit contributions | |
!-- | -1.146 |
isphere | -1.043 |
consolidated | -1.003 |
cient | -0.966 |
colle | -0.959 |
Token | } |
Token ID | 1782 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
!-- | +1.198 |
isphere | +1.093 |
consolidated | +1.072 |
cient | +1.034 |
colle | +1.030 |
Neg logit contributions | |
CRIP | -1.005 |
HS | -0.977 |
Sen | -0.938 |
Secretary | -0.926 |
IER | -0.922 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
CRIP | +0.896 |
HS | +0.874 |
Sen | +0.838 |
IER | +0.825 |
Secretary | +0.823 |
Neg logit contributions | |
!-- | -0.951 |
isphere | -0.871 |
consolidated | -0.844 |
cient | -0.819 |
colle | -0.812 |
Token | 2 |
Token ID | 362 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
CRIP | +1.663 |
HS | +1.612 |
Sen | +1.533 |
IER | +1.495 |
Secretary | +1.490 |
Neg logit contributions | |
!-- | -2.499 |
isphere | -2.323 |
consolidated | -2.254 |
cient | -2.200 |
colle | -2.192 |
Token | 3 |
Token ID | 513 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
CRIP | +3.831 |
HS | +3.721 |
Sen | +3.497 |
Sutherland | +3.438 |
IER | +3.425 |
Neg logit contributions | |
!-- | -5.494 |
isphere | -5.179 |
consolidated | -4.949 |
colle | -4.878 |
cient | -4.834 |
Token | void |
Token ID | 7951 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
CRIP | +2.960 |
HS | +2.859 |
Sen | +2.679 |
Secretary | +2.627 |
serial | +2.626 |
Neg logit contributions | |
!-- | -5.147 |
isphere | -4.850 |
consolidated | -4.688 |
cient | -4.636 |
colle | -4.592 |
Token | vert |
Token ID | 9421 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
!-- | +1.998 |
isphere | +1.851 |
consolidated | +1.809 |
cient | +1.758 |
colle | +1.749 |
Neg logit contributions | |
CRIP | -1.311 |
HS | -1.270 |
Sen | -1.209 |
Secretary | -1.187 |
IER | -1.184 |
Token | ( |
Token ID | 357 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
!-- | +1.433 |
isphere | +1.283 |
consolidated | +1.249 |
cient | +1.196 |
colle | +1.181 |
Neg logit contributions | |
CRIP | -1.814 |
HS | -1.770 |
Sen | -1.710 |
Secretary | -1.693 |
IER | -1.688 |
Token | in |
Token ID | 287 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
!-- | +4.060 |
isphere | +3.620 |
consolidated | +3.561 |
cient | +3.354 |
bench | +3.259 |
Neg logit contributions | |
CRIP | -5.681 |
HS | -5.573 |
Sen | -5.382 |
Secretary | -5.376 |
IER | -5.367 |
Token | less |
Token ID | 1342 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
!-- | +1.093 |
isphere | +0.988 |
consolidated | +0.974 |
cient | +0.933 |
colle | +0.927 |
Neg logit contributions | |
CRIP | -1.097 |
HS | -1.060 |
Sen | -1.020 |
Secretary | -1.007 |
IER | -1.007 |
Token | than |
Token ID | 621 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
CRIP | +1.029 |
HS | +1.013 |
Sen | +0.975 |
Secretary | +0.961 |
IER | +0.960 |
Neg logit contributions | |
!-- | -0.900 |
isphere | -0.811 |
consolidated | -0.783 |
cient | -0.755 |
colle | -0.754 |
Token | two |
Token ID | 734 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
CRIP | +0.764 |
HS | +0.750 |
Sen | +0.718 |
Roose | +0.710 |
Secretary | +0.710 |
Neg logit contributions | |
!-- | -0.863 |
isphere | -0.796 |
consolidated | -0.766 |
cient | -0.748 |
colle | -0.744 |
Token | hours |
Token ID | 2250 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
!-- | +0.837 |
isphere | +0.763 |
consolidated | +0.748 |
cient | +0.717 |
colle | +0.713 |
Neg logit contributions | |
CRIP | -0.813 |
HS | -0.792 |
Sen | -0.759 |
IER | -0.751 |
Secretary | -0.750 |
Token | before |
Token ID | 878 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
!-- | +0.722 |
isphere | +0.662 |
consolidated | +0.651 |
cient | +0.626 |
colle | +0.623 |
Neg logit contributions | |
CRIP | -0.572 |
HS | -0.552 |
Sen | -0.528 |
Secretary | -0.521 |
IER | -0.521 |
Token | boarding |
Token ID | 25523 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
!-- | +1.291 |
isphere | +1.170 |
consolidated | +1.152 |
cient | +1.101 |
colle | +1.098 |
Neg logit contributions | |
CRIP | -1.274 |
HS | -1.230 |
Sen | -1.185 |
Secretary | -1.168 |
IER | -1.167 |
Token | time |
Token ID | 640 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
HS | +4.268 |
CRIP | +4.122 |
Sen | +4.098 |
IER | +3.943 |
Sutherland | +3.930 |
Neg logit contributions | |
!-- | -4.952 |
isphere | -4.575 |
cient | -4.368 |
consolidated | -4.350 |
colle | -4.334 |
Token | but |
Token ID | 475 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
CRIP | +1.331 |
HS | +1.312 |
Sen | +1.261 |
IER | +1.239 |
Secretary | +1.237 |
Neg logit contributions | |
!-- | -1.428 |
isphere | -1.312 |
consolidated | -1.268 |
cient | -1.240 |
colle | -1.239 |
Token | most |
Token ID | 749 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
!-- | +1.241 |
isphere | +1.125 |
consolidated | +1.108 |
colle | +1.055 |
cient | +1.055 |
Neg logit contributions | |
CRIP | -1.237 |
HS | -1.192 |
Sen | -1.149 |
IER | -1.137 |
Secretary | -1.135 |
Token | of |
Token ID | 286 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
!-- | +0.114 |
isphere | +0.104 |
consolidated | +0.102 |
cient | +0.098 |
colle | +0.098 |
Neg logit contributions | |
CRIP | -0.098 |
HS | -0.095 |
Sen | -0.091 |
Secretary | -0.090 |
IER | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
!-- | +0.332 |
isphere | +0.299 |
consolidated | +0.292 |
cient | +0.280 |
colle | +0.278 |
Neg logit contributions | |
CRIP | -0.386 |
HS | -0.377 |
Sen | -0.364 |
Secretary | -0.359 |
IER | -0.359 |
Token | electoral |
Token ID | 13901 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
CRIP | +0.548 |
HS | +0.535 |
Sen | +0.514 |
Secretary | +0.507 |
IER | +0.505 |
Neg logit contributions | |
!-- | -0.584 |
isphere | -0.533 |
consolidated | -0.518 |
cient | -0.502 |
colle | -0.498 |
Token | politics |
Token ID | 4819 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
!-- | +0.871 |
isphere | +0.807 |
consolidated | +0.789 |
cient | +0.767 |
colle | +0.763 |
Neg logit contributions | |
CRIP | -0.556 |
HS | -0.538 |
Sen | -0.512 |
Secretary | -0.503 |
IER | -0.501 |
Token | than |
Token ID | 621 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
CRIP | +0.867 |
HS | +0.847 |
Sen | +0.820 |
Secretary | +0.809 |
IER | +0.804 |
Neg logit contributions | |
!-- | -0.755 |
isphere | -0.687 |
consolidated | -0.664 |
cient | -0.639 |
colle | -0.636 |
Token | it |
Token ID | 340 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
HS | +4.258 |
CRIP | +4.204 |
Secretary | +4.049 |
Sen | +4.040 |
Roose | +3.983 |
Neg logit contributions | |
!-- | -5.423 |
isphere | -5.019 |
consolidated | -4.715 |
cient | -4.689 |
colle | -4.590 |
Token | had |
Token ID | 550 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
CRIP | +3.165 |
HS | +3.163 |
Sen | +3.008 |
Secretary | +2.972 |
ipal | +2.947 |
Neg logit contributions | |
!-- | -4.472 |
isphere | -4.195 |
consolidated | -3.982 |
cient | -3.922 |
colle | -3.910 |
Token | to |
Token ID | 284 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
CRIP | +2.692 |
HS | +2.657 |
Sen | +2.538 |
Secretary | +2.512 |
ipal | +2.482 |
Neg logit contributions | |
!-- | -3.556 |
isphere | -3.293 |
consolidated | -3.181 |
cient | -3.091 |
colle | -3.072 |
Token | do |
Token ID | 466 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
HS | +3.761 |
CRIP | +3.708 |
Sen | +3.591 |
Secretary | +3.530 |
ipal | +3.528 |
Neg logit contributions | |
!-- | -5.377 |
isphere | -5.179 |
consolidated | -4.797 |
colle | -4.758 |
cient | -4.683 |
Token | with |
Token ID | 351 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
HS | +3.737 |
CRIP | +3.731 |
Sen | +3.608 |
Secretary | +3.573 |
IER | +3.493 |
Neg logit contributions | |
!-- | -5.289 |
isphere | -5.020 |
consolidated | -4.746 |
colle | -4.699 |
cient | -4.598 |
Token | any |
Token ID | 597 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
CRIP | +3.127 |
HS | +3.096 |
Sen | +2.971 |
Secretary | +2.955 |
Roose | +2.933 |
Neg logit contributions | |
!-- | -3.505 |
isphere | -3.239 |
consolidated | -3.053 |
cient | -3.024 |
colle | -2.963 |
Token | humanitarian |
Token ID | 15706 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
CRIP | +1.669 |
HS | +1.632 |
Sen | +1.570 |
Secretary | +1.555 |
IER | +1.536 |
Neg logit contributions | |
!-- | -1.744 |
isphere | -1.593 |
consolidated | -1.532 |
cient | -1.493 |
colle | -1.479 |
Token | impulses |
Token ID | 37505 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
CRIP | +1.641 |
HS | +1.618 |
Sen | +1.541 |
Secretary | +1.529 |
IER | +1.524 |
Neg logit contributions | |
!-- | -1.826 |
isphere | -1.697 |
consolidated | -1.613 |
colle | -1.570 |
cient | -1.564 |
Token | politics |
Token ID | 4819 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
!-- | +0.871 |
isphere | +0.807 |
consolidated | +0.789 |
cient | +0.767 |
colle | +0.763 |
Neg logit contributions | |
CRIP | -0.556 |
HS | -0.538 |
Sen | -0.512 |
Secretary | -0.503 |
IER | -0.501 |
Token | than |
Token ID | 621 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
CRIP | +0.867 |
HS | +0.847 |
Sen | +0.820 |
Secretary | +0.809 |
IER | +0.804 |
Neg logit contributions | |
!-- | -0.755 |
isphere | -0.687 |
consolidated | -0.664 |
cient | -0.639 |
colle | -0.636 |
Token | it |
Token ID | 340 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
HS | +4.258 |
CRIP | +4.204 |
Secretary | +4.049 |
Sen | +4.040 |
Roose | +3.983 |
Neg logit contributions | |
!-- | -5.423 |
isphere | -5.019 |
consolidated | -4.715 |
cient | -4.689 |
colle | -4.590 |
Token | had |
Token ID | 550 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
CRIP | +3.165 |
HS | +3.163 |
Sen | +3.008 |
Secretary | +2.972 |
ipal | +2.947 |
Neg logit contributions | |
!-- | -4.472 |
isphere | -4.195 |
consolidated | -3.982 |
cient | -3.922 |
colle | -3.910 |
Token | to |
Token ID | 284 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
CRIP | +2.692 |
HS | +2.657 |
Sen | +2.538 |
Secretary | +2.512 |
ipal | +2.482 |
Neg logit contributions | |
!-- | -3.556 |
isphere | -3.293 |
consolidated | -3.181 |
cient | -3.091 |
colle | -3.072 |
Token | do |
Token ID | 466 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
HS | +3.761 |
CRIP | +3.708 |
Sen | +3.591 |
Secretary | +3.530 |
ipal | +3.528 |
Neg logit contributions | |
!-- | -5.377 |
isphere | -5.179 |
consolidated | -4.797 |
colle | -4.758 |
cient | -4.683 |
Token | with |
Token ID | 351 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
HS | +3.737 |
CRIP | +3.731 |
Sen | +3.608 |
Secretary | +3.573 |
IER | +3.493 |
Neg logit contributions | |
!-- | -5.289 |
isphere | -5.020 |
consolidated | -4.746 |
colle | -4.699 |
cient | -4.598 |
Token | any |
Token ID | 597 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
CRIP | +3.127 |
HS | +3.096 |
Sen | +2.971 |
Secretary | +2.955 |
Roose | +2.933 |
Neg logit contributions | |
!-- | -3.505 |
isphere | -3.239 |
consolidated | -3.053 |
cient | -3.024 |
colle | -2.963 |
Token | humanitarian |
Token ID | 15706 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
CRIP | +1.669 |
HS | +1.632 |
Sen | +1.570 |
Secretary | +1.555 |
IER | +1.536 |
Neg logit contributions | |
!-- | -1.744 |
isphere | -1.593 |
consolidated | -1.532 |
cient | -1.493 |
colle | -1.479 |
Token | impulses |
Token ID | 37505 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
CRIP | +1.641 |
HS | +1.618 |
Sen | +1.541 |
Secretary | +1.529 |
IER | +1.524 |
Neg logit contributions | |
!-- | -1.826 |
isphere | -1.697 |
consolidated | -1.613 |
colle | -1.570 |
cient | -1.564 |
Token | on |
Token ID | 319 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
CRIP | +1.590 |
HS | +1.562 |
Sen | +1.510 |
Secretary | +1.491 |
ipal | +1.470 |
Neg logit contributions | |
!-- | -1.483 |
isphere | -1.370 |
consolidated | -1.311 |
cient | -1.273 |
colle | -1.266 |
Token |
|
Token ID | 198 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
CRIP | +0.422 |
HS | +0.408 |
Sen | +0.391 |
Secretary | +0.390 |
IER | +0.389 |
Neg logit contributions | |
!-- | -0.450 |
isphere | -0.406 |
consolidated | -0.403 |
cient | -0.387 |
colle | -0.385 |
Token |
|
Token ID | 198 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
!-- | +0.647 |
isphere | +0.584 |
consolidated | +0.572 |
cient | +0.555 |
colle | +0.543 |
Neg logit contributions | |
CRIP | -0.597 |
HS | -0.577 |
Sen | -0.553 |
IER | -0.549 |
Secretary | -0.547 |
Token | 1993 |
Token ID | 24465 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
!-- | +0.430 |
isphere | +0.388 |
consolidated | +0.377 |
cient | +0.369 |
colle | +0.362 |
Neg logit contributions | |
CRIP | -0.409 |
HS | -0.399 |
Roose | -0.384 |
Sen | -0.378 |
IER | -0.378 |
Token | Jerry |
Token ID | 13075 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
CRIP | +1.516 |
HS | +1.481 |
Sen | +1.412 |
Secretary | +1.385 |
Roose | +1.381 |
Neg logit contributions | |
!-- | -2.242 |
isphere | -2.081 |
consolidated | -2.030 |
cient | -1.968 |
colle | -1.959 |
Token | Se |
Token ID | 1001 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
CRIP | +0.933 |
HS | +0.925 |
Sen | +0.875 |
Roose | +0.861 |
Sutherland | +0.853 |
Neg logit contributions | |
!-- | -1.779 |
isphere | -1.679 |
consolidated | -1.638 |
colle | -1.606 |
cient | -1.593 |
Token | infeld |
Token ID | 47187 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
!-- | +1.223 |
isphere | +1.152 |
consolidated | +1.128 |
cient | +1.109 |
colle | +1.097 |
Neg logit contributions | |
CRIP | -0.377 |
HS | -0.353 |
Sen | -0.324 |
IER | -0.316 |
Secretary | -0.315 |
Token |
|
Token ID | 198 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
CRIP | +3.829 |
HS | +3.743 |
Sen | +3.581 |
serial | +3.495 |
Secretary | +3.477 |
Neg logit contributions | |
!-- | -5.340 |
isphere | -5.019 |
consolidated | -4.772 |
cient | -4.668 |
colle | -4.655 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
CRIP | +0.242 |
HS | +0.237 |
Sen | +0.227 |
Secretary | +0.223 |
IER | +0.222 |
Neg logit contributions | |
!-- | -0.282 |
isphere | -0.260 |
consolidated | -0.253 |
colle | -0.245 |
cient | -0.244 |
Token | 1993 |
Token ID | 24465 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
CRIP | +0.083 |
HS | +0.080 |
Roose | +0.077 |
Sen | +0.076 |
IER | +0.076 |
Neg logit contributions | |
!-- | -0.088 |
isphere | -0.080 |
consolidated | -0.078 |
cient | -0.076 |
colle | -0.075 |
Token | Garry |
Token ID | 45354 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
CRIP | +1.585 |
HS | +1.547 |
Sen | +1.480 |
Secretary | +1.452 |
Roose | +1.449 |
Neg logit contributions | |
!-- | -2.192 |
isphere | -2.032 |
consolidated | -1.980 |
cient | -1.920 |
colle | -1.908 |
Token | Sh |
Token ID | 911 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
CRIP | +0.852 |
HS | +0.844 |
Sen | +0.814 |
Roose | +0.806 |
Sutherland | +0.796 |
Neg logit contributions | |
!-- | -1.233 |
isphere | -1.149 |
consolidated | -1.123 |
colle | -1.098 |
cient | -1.084 |
Token | so |
Token ID | 523 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
!-- | +0.232 |
isphere | +0.211 |
consolidated | +0.205 |
cient | +0.197 |
colle | +0.196 |
Neg logit contributions | |
CRIP | -0.253 |
HS | -0.247 |
Sen | -0.238 |
Secretary | -0.235 |
IER | -0.234 |
Token | their |
Token ID | 511 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
CRIP | +1.167 |
HS | +1.139 |
Sen | +1.090 |
Secretary | +1.072 |
IER | +1.064 |
Neg logit contributions | |
!-- | -1.548 |
isphere | -1.433 |
consolidated | -1.388 |
cient | -1.351 |
colle | -1.341 |
Token | teams |
Token ID | 3466 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
CRIP | +1.007 |
HS | +0.983 |
Sen | +0.949 |
Secretary | +0.935 |
Roose | +0.930 |
Neg logit contributions | |
!-- | -1.063 |
isphere | -0.975 |
consolidated | -0.932 |
cient | -0.911 |
colle | -0.903 |
Token | are |
Token ID | 389 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
HS | +1.947 |
CRIP | +1.946 |
Sen | +1.833 |
Secretary | +1.813 |
Roose | +1.805 |
Neg logit contributions | |
!-- | -2.068 |
isphere | -1.908 |
consolidated | -1.798 |
colle | -1.775 |
cient | -1.761 |
Token | manufacturing |
Token ID | 9138 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
CRIP | +1.088 |
HS | +1.074 |
Sen | +1.034 |
Roose | +1.021 |
Secretary | +1.019 |
Neg logit contributions | |
!-- | -1.174 |
isphere | -1.072 |
consolidated | -1.017 |
colle | -1.001 |
cient | -1.000 |
Token | all |
Token ID | 477 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
CRIP | +2.070 |
HS | +2.036 |
Sen | +1.946 |
Secretary | +1.921 |
Roose | +1.918 |
Neg logit contributions | |
!-- | -2.079 |
isphere | -1.909 |
consolidated | -1.819 |
cient | -1.781 |
colle | -1.759 |
Token | kinds |
Token ID | 6982 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
CRIP | +3.746 |
HS | +3.692 |
Sen | +3.567 |
Secretary | +3.480 |
Quotes | +3.465 |
Neg logit contributions | |
!-- | -5.116 |
isphere | -4.845 |
colle | -4.673 |
consolidated | -4.658 |
cient | -4.588 |
Token | of |
Token ID | 286 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
CRIP | +1.385 |
HS | +1.372 |
Sen | +1.317 |
Secretary | +1.296 |
IER | +1.276 |
Neg logit contributions | |
!-- | -1.463 |
isphere | -1.361 |
consolidated | -1.321 |
colle | -1.303 |
cient | -1.264 |
Token | ways |
Token ID | 2842 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
CRIP | +1.985 |
HS | +1.933 |
Sen | +1.847 |
Secretary | +1.813 |
Roose | +1.811 |
Neg logit contributions | |
!-- | -2.921 |
isphere | -2.723 |
consolidated | -2.622 |
cient | -2.572 |
colle | -2.544 |
Token | for |
Token ID | 329 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
CRIP | +2.560 |
HS | +2.517 |
Sen | +2.406 |
Secretary | +2.371 |
IER | +2.364 |
Neg logit contributions | |
!-- | -2.929 |
isphere | -2.701 |
consolidated | -2.619 |
cient | -2.544 |
colle | -2.532 |
Token | them |
Token ID | 606 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
CRIP | +1.179 |
HS | +1.148 |
Sen | +1.100 |
Secretary | +1.085 |
IER | +1.082 |
Neg logit contributions | |
!-- | -1.358 |
isphere | -1.243 |
consolidated | -1.213 |
cient | -1.173 |
colle | -1.167 |
Token | that |
Token ID | 326 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
CRIP | +0.925 |
HS | +0.907 |
Sen | +0.863 |
Secretary | +0.846 |
IER | +0.844 |
Neg logit contributions | |
!-- | -1.134 |
isphere | -1.038 |
consolidated | -1.009 |
cient | -0.985 |
colle | -0.973 |
Token | the |
Token ID | 262 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
!-- | +0.650 |
isphere | +0.589 |
consolidated | +0.576 |
cient | +0.555 |
colle | +0.551 |
Neg logit contributions | |
CRIP | -0.660 |
HS | -0.641 |
Sen | -0.617 |
Secretary | -0.611 |
IER | -0.610 |
Token | health |
Token ID | 1535 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
CRIP | +0.502 |
HS | +0.492 |
Sen | +0.473 |
Secretary | +0.465 |
IER | +0.464 |
Neg logit contributions | |
!-- | -0.510 |
isphere | -0.466 |
consolidated | -0.451 |
cient | -0.435 |
colle | -0.434 |
Token | benefits |
Token ID | 4034 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
!-- | +0.267 |
isphere | +0.243 |
consolidated | +0.236 |
cient | +0.228 |
colle | +0.227 |
Neg logit contributions | |
CRIP | -0.262 |
HS | -0.256 |
Sen | -0.246 |
Secretary | -0.243 |
IER | -0.242 |
Token | outwe |
Token ID | 26644 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
CRIP | +2.505 |
HS | +2.466 |
Sen | +2.366 |
IER | +2.321 |
Secretary | +2.313 |
Neg logit contributions | |
!-- | -2.806 |
isphere | -2.581 |
consolidated | -2.459 |
colle | -2.440 |
cient | -2.407 |
Token | ighed |
Token ID | 12570 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
HS | +1.899 |
CRIP | +1.857 |
Sen | +1.819 |
ipal | +1.805 |
serial | +1.690 |
Neg logit contributions | |
!-- | -6.650 |
isphere | -6.435 |
colle | -6.287 |
consolidated | -6.241 |
rods | -6.126 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
HS | +4.060 |
CRIP | +4.054 |
Sen | +3.805 |
IER | +3.765 |
ipal | +3.734 |
Neg logit contributions | |
!-- | -4.815 |
isphere | -4.580 |
consolidated | -4.253 |
colle | -4.221 |
cius | -4.124 |
Token | risks |
Token ID | 7476 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
CRIP | +1.729 |
HS | +1.697 |
Sen | +1.604 |
IER | +1.571 |
Secretary | +1.564 |
Neg logit contributions | |
!-- | -2.434 |
isphere | -2.276 |
consolidated | -2.191 |
cient | -2.136 |
colle | -2.131 |
Token | connected |
Token ID | 5884 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
CRIP | +0.531 |
HS | +0.519 |
Sen | +0.500 |
Secretary | +0.494 |
IER | +0.493 |
Neg logit contributions | |
!-- | -0.459 |
isphere | -0.415 |
consolidated | -0.403 |
cient | -0.387 |
colle | -0.385 |
Token | to |
Token ID | 284 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
CRIP | +1.464 |
HS | +1.423 |
Sen | +1.366 |
Secretary | +1.348 |
IER | +1.344 |
Neg logit contributions | |
!-- | -1.633 |
isphere | -1.492 |
consolidated | -1.457 |
cient | -1.409 |
colle | -1.400 |
Token | the |
Token ID | 262 |
Feature activation | +5.82e-03 |
Pos logit contributions | |
CRIP | +0.612 |
HS | +0.599 |
Sen | +0.575 |
Secretary | +0.565 |
IER | +0.564 |
Neg logit contributions | |
!-- | -0.628 |
isphere | -0.573 |
consolidated | -0.555 |
cient | -0.536 |
colle | -0.534 |
Token | inance |
Token ID | 14149 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
CRIP | +0.425 |
HS | +0.410 |
Sen | +0.394 |
Secretary | +0.389 |
IER | +0.389 |
Neg logit contributions | |
!-- | -0.506 |
isphere | -0.464 |
consolidated | -0.452 |
cient | -0.440 |
colle | -0.434 |
Token | , |
Token ID | 11 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
HS | +3.324 |
CRIP | +3.278 |
Sen | +3.180 |
Roose | +3.132 |
Secretary | +3.124 |
Neg logit contributions | |
!-- | -3.586 |
isphere | -3.496 |
colle | -3.393 |
consolidated | -3.319 |
cient | -3.219 |
Token | aust |
Token ID | 38132 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
CRIP | +1.601 |
HS | +1.569 |
Sen | +1.508 |
Secretary | +1.482 |
IER | +1.473 |
Neg logit contributions | |
!-- | -1.794 |
isphere | -1.646 |
consolidated | -1.590 |
cient | -1.543 |
colle | -1.529 |
Token | ral |
Token ID | 1373 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
CRIP | +0.095 |
HS | +0.094 |
Sen | +0.091 |
ipal | +0.090 |
Roose | +0.090 |
Neg logit contributions | |
!-- | -0.093 |
isphere | -0.085 |
consolidated | -0.082 |
colle | -0.080 |
cient | -0.079 |
Token | ia |
Token ID | 544 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
CRIP | +1.050 |
HS | +1.031 |
ipal | +0.960 |
Sen | +0.958 |
Secretary | +0.941 |
Neg logit contributions | |
!-- | -2.292 |
isphere | -2.140 |
consolidated | -2.112 |
colle | -2.077 |
cient | -2.035 |
Token |
|
Token ID | 198 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
CRIP | +1.621 |
HS | +1.581 |
Sen | +1.520 |
Secretary | +1.497 |
IER | +1.496 |
Neg logit contributions | |
!-- | -1.756 |
isphere | -1.610 |
consolidated | -1.566 |
cient | -1.513 |
colle | -1.508 |
Token |
|
Token ID | 198 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
HS | +3.410 |
CRIP | +3.255 |
Sen | +3.242 |
Secretary | +3.148 |
Quotes | +3.100 |
Neg logit contributions | |
isphere | -5.521 |
!-- | -5.454 |
colle | -5.449 |
consolidated | -5.248 |
exha | -5.182 |
Token | First |
Token ID | 5962 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
HS | +1.818 |
CRIP | +1.780 |
Sen | +1.674 |
Secretary | +1.654 |
serial | +1.608 |
Neg logit contributions | |
!-- | -5.431 |
consolidated | -5.115 |
colle | -5.059 |
isphere | -5.045 |
cient | -4.829 |
Token | posted |
Token ID | 4481 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
!-- | +0.308 |
isphere | +0.267 |
consolidated | +0.249 |
colle | +0.242 |
cient | +0.238 |
Neg logit contributions | |
CRIP | -0.652 |
HS | -0.648 |
Sen | -0.629 |
Secretary | -0.624 |
ipal | -0.621 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
!-- | +0.148 |
isphere | +0.137 |
consolidated | +0.134 |
cient | +0.130 |
colle | +0.129 |
Neg logit contributions | |
CRIP | -0.107 |
HS | -0.104 |
Sen | -0.099 |
Secretary | -0.097 |
IER | -0.097 |
Token | Screen |
Token ID | 23901 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
CRIP | +0.884 |
HS | +0.863 |
Sen | +0.829 |
Secretary | +0.815 |
IER | +0.808 |
Neg logit contributions | |
!-- | -1.122 |
isphere | -1.036 |
consolidated | -1.015 |
colle | -0.979 |
cient | -0.977 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
!-- | +0.626 |
isphere | +0.567 |
consolidated | +0.553 |
cient | +0.538 |
colle | +0.526 |
Neg logit contributions | |
CRIP | -0.573 |
HS | -0.555 |
Sen | -0.531 |
IER | -0.526 |
Roose | -0.526 |
Token | pur |
Token ID | 14225 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
!-- | +1.159 |
isphere | +1.064 |
consolidated | +1.033 |
cient | +1.008 |
colle | +0.994 |
Neg logit contributions | |
CRIP | -0.915 |
HS | -0.883 |
Sen | -0.843 |
IER | -0.836 |
Roose | -0.835 |
Token | ak |
Token ID | 461 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
!-- | +0.219 |
isphere | +0.197 |
consolidated | +0.191 |
cient | +0.183 |
colle | +0.182 |
Neg logit contributions | |
CRIP | -0.269 |
HS | -0.262 |
Sen | -0.253 |
Secretary | -0.251 |
IER | -0.250 |
Token | ushi |
Token ID | 17731 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
!-- | +2.492 |
isphere | +2.279 |
consolidated | +2.224 |
cient | +2.168 |
colle | +2.141 |
Neg logit contributions | |
CRIP | -2.048 |
HS | -1.973 |
Sen | -1.886 |
Secretary | -1.876 |
IER | -1.876 |
Token | Profile |
Token ID | 13118 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
!-- | +1.871 |
isphere | +1.703 |
consolidated | +1.665 |
cient | +1.610 |
colle | +1.599 |
Neg logit contributions | |
CRIP | -1.710 |
HS | -1.659 |
Sen | -1.592 |
IER | -1.575 |
Secretary | -1.574 |
Token | Joined |
Token ID | 16709 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
!-- | +3.902 |
consolidated | +3.242 |
isphere | +3.206 |
colle | +3.011 |
cient | +3.007 |
Neg logit contributions | |
CRIP | -7.070 |
HS | -6.732 |
IER | -6.618 |
ipal | -6.568 |
serial | -6.563 |
Token | August |
Token ID | 2932 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
!-- | +6.057 |
consolidated | +4.915 |
-- | +4.888 |
cient | +4.739 |
isphere | +4.730 |
Neg logit contributions | |
CRIP | -9.352 |
ipal | -8.616 |
HS | -8.606 |
IER | -8.567 |
tailed | -8.403 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
!-- | +1.513 |
isphere | +1.348 |
consolidated | +1.314 |
cient | +1.260 |
colle | +1.242 |
Neg logit contributions | |
CRIP | -1.953 |
HS | -1.903 |
Sen | -1.838 |
Secretary | -1.821 |
IER | -1.819 |
Token | United |
Token ID | 1578 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
!-- | +2.432 |
isphere | +2.158 |
consolidated | +2.142 |
cient | +2.069 |
colle | +2.020 |
Neg logit contributions | |
CRIP | -2.589 |
HS | -2.481 |
IER | -2.393 |
Sen | -2.384 |
ipal | -2.381 |
Token | States |
Token ID | 1829 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
!-- | +2.316 |
isphere | +2.086 |
consolidated | +2.016 |
cient | +1.942 |
colle | +1.931 |
Neg logit contributions | |
CRIP | -2.757 |
HS | -2.653 |
IER | -2.574 |
Secretary | -2.547 |
Sen | -2.533 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
!-- | +1.508 |
isphere | +1.385 |
consolidated | +1.370 |
cient | +1.339 |
colle | +1.321 |
Neg logit contributions | |
CRIP | -0.838 |
HS | -0.797 |
Sen | -0.753 |
IER | -0.747 |
Secretary | -0.744 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
CRIP | +1.099 |
HS | +1.079 |
Sen | +1.034 |
IER | +1.016 |
Secretary | +1.012 |
Neg logit contributions | |
!-- | -1.286 |
isphere | -1.208 |
consolidated | -1.169 |
colle | -1.142 |
cient | -1.133 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
!-- | +1.238 |
isphere | +1.102 |
consolidated | +1.083 |
cient | +1.054 |
colle | +1.014 |
Neg logit contributions | |
CRIP | -1.196 |
HS | -1.147 |
Sen | -1.100 |
IER | -1.098 |
Roose | -1.092 |
Token | Ko |
Token ID | 48735 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
!-- | +1.853 |
isphere | +1.704 |
consolidated | +1.641 |
cient | +1.622 |
colle | +1.585 |
Neg logit contributions | |
CRIP | -1.409 |
HS | -1.337 |
Roose | -1.282 |
IER | -1.276 |
Sen | -1.275 |
Token | Do |
Token ID | 5211 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
!-- | +2.838 |
isphere | +2.596 |
consolidated | +2.509 |
cient | +2.467 |
colle | +2.427 |
Neg logit contributions | |
CRIP | -2.302 |
HS | -2.191 |
Sen | -2.105 |
Secretary | -2.103 |
IER | -2.095 |
Token | Profile |
Token ID | 13118 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
!-- | +2.093 |
isphere | +1.914 |
consolidated | +1.861 |
cient | +1.822 |
colle | +1.795 |
Neg logit contributions | |
CRIP | -1.738 |
HS | -1.664 |
Sen | -1.589 |
Secretary | -1.584 |
IER | -1.578 |
Token | Joined |
Token ID | 16709 |
Feature activation | -9.44e+00 |
Pos logit contributions | |
!-- | +4.262 |
consolidated | +3.586 |
isphere | +3.520 |
cient | +3.397 |
~~ | +3.333 |
Neg logit contributions | |
CRIP | -6.904 |
HS | -6.524 |
IER | -6.406 |
Sen | -6.328 |
serial | -6.326 |
Token | December |
Token ID | 3426 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
!-- | +5.251 |
consolidated | +4.359 |
-- | +4.233 |
isphere | +4.195 |
cient | +4.175 |
Neg logit contributions | |
CRIP | -7.923 |
HS | -7.403 |
IER | -7.342 |
ipal | -7.324 |
Sen | -7.187 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
CRIP | +0.680 |
HS | +0.671 |
Sen | +0.650 |
Roose | +0.644 |
Secretary | +0.640 |
Neg logit contributions | |
!-- | -0.599 |
isphere | -0.555 |
consolidated | -0.529 |
colle | -0.514 |
cient | -0.507 |
Token | United |
Token ID | 1578 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
!-- | +2.182 |
isphere | +1.943 |
consolidated | +1.925 |
cient | +1.849 |
colle | +1.813 |
Neg logit contributions | |
CRIP | -2.366 |
HS | -2.275 |
Sen | -2.190 |
IER | -2.189 |
Secretary | -2.184 |
Token | States |
Token ID | 1829 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
!-- | +1.573 |
isphere | +1.416 |
consolidated | +1.383 |
cient | +1.333 |
colle | +1.310 |
Neg logit contributions | |
CRIP | -1.645 |
HS | -1.592 |
Sen | -1.526 |
Secretary | -1.519 |
IER | -1.518 |
Token | 6 |
Token ID | 718 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
CRIP | +0.106 |
HS | +0.102 |
Sen | +0.096 |
Secretary | +0.095 |
IER | +0.094 |
Neg logit contributions | |
!-- | -0.201 |
isphere | -0.187 |
consolidated | -0.184 |
cient | -0.179 |
colle | -0.178 |
Token | data |
Token ID | 7890 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
!-- | +4.322 |
isphere | +3.998 |
consolidated | +3.862 |
cient | +3.815 |
colle | +3.628 |
Neg logit contributions | |
CRIP | -3.087 |
HS | -2.927 |
Roose | -2.831 |
Sen | -2.811 |
IER | -2.800 |
Token | _ |
Token ID | 4808 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
!-- | +2.743 |
isphere | +2.377 |
consolidated | +2.373 |
cient | +2.236 |
colle | +2.184 |
Neg logit contributions | |
CRIP | -4.042 |
HS | -3.945 |
Secretary | -3.826 |
Sen | -3.823 |
IER | -3.781 |
Token | full |
Token ID | 1336 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
!-- | +2.907 |
consolidated | +2.592 |
isphere | +2.557 |
cient | +2.398 |
colle | +2.340 |
Neg logit contributions | |
CRIP | -4.675 |
HS | -4.577 |
Sen | -4.426 |
Secretary | -4.413 |
Roose | -4.394 |
Token | v |
Token ID | 410 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
!-- | +4.323 |
consolidated | +3.909 |
isphere | +3.877 |
cient | +3.720 |
colle | +3.679 |
Neg logit contributions | |
CRIP | -3.546 |
HS | -3.465 |
Secretary | -3.316 |
Sen | -3.304 |
IER | -3.286 |
Token | ) |
Token ID | 1267 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
!-- | +2.830 |
isphere | +2.445 |
consolidated | +2.419 |
cient | +2.292 |
colle | +2.153 |
Neg logit contributions | |
CRIP | -5.331 |
HS | -5.182 |
Sen | -5.030 |
IER | -5.028 |
Secretary | -4.995 |
Token | { |
Token ID | 1391 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
!-- | +4.351 |
isphere | +3.720 |
consolidated | +3.705 |
cient | +3.517 |
-- | +3.408 |
Neg logit contributions | |
CRIP | -6.600 |
HS | -6.436 |
Secretary | -6.227 |
IER | -6.218 |
Roose | -6.196 |
Token | // |
Token ID | 3373 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
!-- | +3.670 |
consolidated | +3.096 |
isphere | +2.746 |
bench | +2.591 |
-- | +2.568 |
Neg logit contributions | |
CRIP | -9.225 |
Secretary | -8.883 |
HS | -8.839 |
Roose | -8.720 |
Sen | -8.659 |
Token | Time |
Token ID | 3862 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
!-- | +3.070 |
isphere | +2.712 |
consolidated | +2.705 |
cient | +2.600 |
colle | +2.581 |
Neg logit contributions | |
CRIP | -2.742 |
HS | -2.609 |
Secretary | -2.477 |
Sen | -2.470 |
ipal | -2.458 |
Token | component |
Token ID | 7515 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
!-- | +0.621 |
isphere | +0.572 |
consolidated | +0.554 |
cient | +0.538 |
colle | +0.538 |
Neg logit contributions | |
CRIP | -0.512 |
HS | -0.499 |
Sen | -0.478 |
Secretary | -0.472 |
IER | -0.471 |
Token | const |
Token ID | 1500 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
!-- | +0.458 |
isphere | +0.421 |
consolidated | +0.405 |
cient | +0.394 |
colle | +0.392 |
Neg logit contributions | |
CRIP | -0.458 |
HS | -0.447 |
Sen | -0.431 |
Secretary | -0.423 |
IER | -0.422 |
Token | float |
Token ID | 12178 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
!-- | +1.432 |
isphere | +1.308 |
consolidated | +1.281 |
cient | +1.235 |
colle | +1.227 |
Neg logit contributions | |
CRIP | -1.243 |
HS | -1.207 |
Sen | -1.159 |
Secretary | -1.145 |
IER | -1.140 |
Token | Starcraft |
Token ID | 44197 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
!-- | +1.438 |
isphere | +1.310 |
consolidated | +1.279 |
cient | +1.233 |
colle | +1.227 |
Neg logit contributions | |
CRIP | -1.374 |
HS | -1.335 |
Sen | -1.283 |
Secretary | -1.268 |
IER | -1.266 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
!-- | +1.812 |
isphere | +1.668 |
consolidated | +1.634 |
cient | +1.582 |
colle | +1.573 |
Neg logit contributions | |
CRIP | -1.313 |
HS | -1.268 |
Sen | -1.211 |
IER | -1.194 |
Secretary | -1.194 |
Token |
|
Token ID | 198 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
!-- | +0.976 |
isphere | +0.873 |
consolidated | +0.857 |
cient | +0.833 |
colle | +0.807 |
Neg logit contributions | |
CRIP | -0.928 |
HS | -0.891 |
Sen | -0.855 |
IER | -0.851 |
Secretary | -0.847 |
Token | re |
Token ID | 260 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
!-- | +3.775 |
isphere | +3.486 |
cient | +3.324 |
consolidated | +3.302 |
colle | +3.203 |
Neg logit contributions | |
CRIP | -2.828 |
HS | -2.633 |
Roose | -2.604 |
Sutherland | -2.577 |
IER | -2.538 |
Token | i |
Token ID | 72 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
!-- | +1.610 |
isphere | +1.486 |
consolidated | +1.437 |
cient | +1.410 |
colle | +1.388 |
Neg logit contributions | |
CRIP | -1.298 |
HS | -1.245 |
Sen | -1.193 |
Secretary | -1.183 |
IER | -1.180 |
Token | Profile |
Token ID | 13118 |
Feature activation | -9.05e+00 |
Pos logit contributions | |
!-- | +3.197 |
isphere | +2.943 |
consolidated | +2.832 |
cient | +2.824 |
colle | +2.737 |
Neg logit contributions | |
CRIP | -2.580 |
HS | -2.423 |
Secretary | -2.334 |
IER | -2.327 |
Roose | -2.321 |
Token | Blog |
Token ID | 14001 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
!-- | +4.558 |
consolidated | +3.771 |
isphere | +3.682 |
cient | +3.508 |
colle | +3.462 |
Neg logit contributions | |
CRIP | -8.115 |
HS | -7.634 |
IER | -7.578 |
serial | -7.474 |
Secretary | -7.458 |
Token | Joined |
Token ID | 16709 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
!-- | +3.374 |
consolidated | +2.762 |
isphere | +2.669 |
cient | +2.465 |
~~ | +2.431 |
Neg logit contributions | |
CRIP | -7.238 |
HS | -6.811 |
IER | -6.776 |
Sen | -6.626 |
Secretary | -6.622 |
Token | October |
Token ID | 3267 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
!-- | +5.231 |
consolidated | +4.371 |
isphere | +4.274 |
cient | +4.191 |
-- | +4.168 |
Neg logit contributions | |
CRIP | -7.481 |
HS | -6.940 |
IER | -6.913 |
ipal | -6.880 |
Sen | -6.795 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
CRIP | +0.428 |
HS | +0.426 |
Sen | +0.412 |
Roose | +0.407 |
Secretary | +0.406 |
Neg logit contributions | |
!-- | -0.410 |
isphere | -0.381 |
consolidated | -0.363 |
colle | -0.357 |
cient | -0.350 |
Token | United |
Token ID | 1578 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
!-- | +1.805 |
isphere | +1.608 |
consolidated | +1.591 |
cient | +1.532 |
colle | +1.506 |
Neg logit contributions | |
CRIP | -1.925 |
HS | -1.850 |
IER | -1.785 |
Sen | -1.777 |
ipal | -1.775 |
Token |
|
Token ID | 198 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
!-- | +0.976 |
isphere | +0.873 |
consolidated | +0.857 |
cient | +0.833 |
colle | +0.807 |
Neg logit contributions | |
CRIP | -0.928 |
HS | -0.891 |
Sen | -0.855 |
IER | -0.851 |
Secretary | -0.847 |
Token | re |
Token ID | 260 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
!-- | +3.775 |
isphere | +3.486 |
cient | +3.324 |
consolidated | +3.302 |
colle | +3.203 |
Neg logit contributions | |
CRIP | -2.828 |
HS | -2.633 |
Roose | -2.604 |
Sutherland | -2.577 |
IER | -2.538 |
Token | i |
Token ID | 72 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
!-- | +1.610 |
isphere | +1.486 |
consolidated | +1.437 |
cient | +1.410 |
colle | +1.388 |
Neg logit contributions | |
CRIP | -1.298 |
HS | -1.245 |
Sen | -1.193 |
Secretary | -1.183 |
IER | -1.180 |
Token | Profile |
Token ID | 13118 |
Feature activation | -9.05e+00 |
Pos logit contributions | |
!-- | +3.197 |
isphere | +2.943 |
consolidated | +2.832 |
cient | +2.824 |
colle | +2.737 |
Neg logit contributions | |
CRIP | -2.580 |
HS | -2.423 |
Secretary | -2.334 |
IER | -2.327 |
Roose | -2.321 |
Token | Blog |
Token ID | 14001 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
!-- | +4.558 |
consolidated | +3.771 |
isphere | +3.682 |
cient | +3.508 |
colle | +3.462 |
Neg logit contributions | |
CRIP | -8.115 |
HS | -7.634 |
IER | -7.578 |
serial | -7.474 |
Secretary | -7.458 |
Token | Joined |
Token ID | 16709 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
!-- | +3.374 |
consolidated | +2.762 |
isphere | +2.669 |
cient | +2.465 |
~~ | +2.431 |
Neg logit contributions | |
CRIP | -7.238 |
HS | -6.811 |
IER | -6.776 |
Sen | -6.626 |
Secretary | -6.622 |
Token | October |
Token ID | 3267 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
!-- | +5.231 |
consolidated | +4.371 |
isphere | +4.274 |
cient | +4.191 |
-- | +4.168 |
Neg logit contributions | |
CRIP | -7.481 |
HS | -6.940 |
IER | -6.913 |
ipal | -6.880 |
Sen | -6.795 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
CRIP | +0.428 |
HS | +0.426 |
Sen | +0.412 |
Roose | +0.407 |
Secretary | +0.406 |
Neg logit contributions | |
!-- | -0.410 |
isphere | -0.381 |
consolidated | -0.363 |
colle | -0.357 |
cient | -0.350 |
Token | United |
Token ID | 1578 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
!-- | +1.805 |
isphere | +1.608 |
consolidated | +1.591 |
cient | +1.532 |
colle | +1.506 |
Neg logit contributions | |
CRIP | -1.925 |
HS | -1.850 |
IER | -1.785 |
Sen | -1.777 |
ipal | -1.775 |
Token | States |
Token ID | 1829 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
!-- | +2.135 |
isphere | +1.917 |
consolidated | +1.855 |
cient | +1.793 |
colle | +1.766 |
Neg logit contributions | |
CRIP | -2.641 |
HS | -2.530 |
IER | -2.458 |
Secretary | -2.435 |
Sen | -2.412 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
!-- | +0.999 |
isphere | +0.921 |
consolidated | +0.909 |
cient | +0.888 |
colle | +0.878 |
Neg logit contributions | |
CRIP | -0.547 |
HS | -0.522 |
Sen | -0.493 |
IER | -0.488 |
Secretary | -0.487 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
!-- | +2.477 |
isphere | +2.134 |
consolidated | +2.113 |
cient | +2.076 |
-- | +2.029 |
Neg logit contributions | |
CRIP | -2.624 |
HS | -2.482 |
IER | -2.403 |
Roose | -2.401 |
ipal | -2.396 |
Token | heart |
Token ID | 11499 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
!-- | +3.398 |
isphere | +3.125 |
cient | +2.987 |
consolidated | +2.979 |
colle | +2.883 |
Neg logit contributions | |
CRIP | -2.539 |
HS | -2.375 |
Roose | -2.323 |
Sutherland | -2.301 |
IER | -2.292 |
Token | l |
Token ID | 75 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
!-- | +2.593 |
isphere | +2.396 |
consolidated | +2.318 |
cient | +2.280 |
colle | +2.236 |
Neg logit contributions | |
CRIP | -2.080 |
HS | -1.989 |
Sen | -1.906 |
Secretary | -1.887 |
IER | -1.885 |
Token | xp |
Token ID | 42372 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
!-- | +1.720 |
isphere | +1.581 |
consolidated | +1.535 |
cient | +1.501 |
colle | +1.476 |
Neg logit contributions | |
CRIP | -1.508 |
HS | -1.445 |
Sen | -1.387 |
IER | -1.375 |
Secretary | -1.371 |
Token | Profile |
Token ID | 13118 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
!-- | +0.332 |
isphere | +0.303 |
consolidated | +0.295 |
cient | +0.285 |
colle | +0.283 |
Neg logit contributions | |
CRIP | -0.322 |
HS | -0.313 |
Sen | -0.301 |
Secretary | -0.297 |
IER | -0.297 |
Token | Joined |
Token ID | 16709 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
!-- | +3.742 |
consolidated | +3.117 |
isphere | +3.101 |
cient | +2.961 |
colle | +2.887 |
Neg logit contributions | |
CRIP | -6.438 |
HS | -6.111 |
IER | -5.974 |
Sen | -5.922 |
serial | -5.914 |
Token | September |
Token ID | 2693 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
!-- | +5.020 |
consolidated | +4.180 |
isphere | +4.079 |
-- | +4.053 |
cient | +4.027 |
Neg logit contributions | |
CRIP | -7.364 |
HS | -6.867 |
ipal | -6.778 |
IER | -6.769 |
Sen | -6.688 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
!-- | +0.548 |
isphere | +0.498 |
consolidated | +0.480 |
colle | +0.462 |
cient | +0.461 |
Neg logit contributions | |
CRIP | -0.655 |
HS | -0.643 |
Sen | -0.622 |
Secretary | -0.614 |
Roose | -0.611 |
Token | United |
Token ID | 1578 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
!-- | +2.224 |
isphere | +1.979 |
consolidated | +1.963 |
cient | +1.886 |
colle | +1.851 |
Neg logit contributions | |
CRIP | -2.417 |
HS | -2.320 |
IER | -2.231 |
Sen | -2.230 |
Secretary | -2.223 |
Token | States |
Token ID | 1829 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
!-- | +2.394 |
isphere | +2.166 |
consolidated | +2.083 |
cient | +2.026 |
colle | +1.988 |
Neg logit contributions | |
CRIP | -2.920 |
HS | -2.786 |
IER | -2.704 |
Secretary | -2.684 |
Sen | -2.659 |
Token | 10 |
Token ID | 838 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
!-- | +0.203 |
isphere | +0.188 |
consolidated | +0.185 |
cient | +0.180 |
colle | +0.179 |
Neg logit contributions | |
CRIP | -0.108 |
HS | -0.104 |
Sen | -0.098 |
Secretary | -0.096 |
IER | -0.096 |
Token | app |
Token ID | 598 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
!-- | +1.608 |
isphere | +1.428 |
consolidated | +1.384 |
cient | +1.320 |
colle | +1.310 |
Neg logit contributions | |
CRIP | -2.336 |
HS | -2.287 |
Sen | -2.213 |
Secretary | -2.190 |
IER | -2.186 |
Token | data |
Token ID | 7890 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
!-- | +3.898 |
isphere | +3.603 |
consolidated | +3.477 |
cient | +3.444 |
colle | +3.267 |
Neg logit contributions | |
CRIP | -2.780 |
HS | -2.629 |
Roose | -2.545 |
Sen | -2.528 |
IER | -2.521 |
Token | _ |
Token ID | 4808 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
!-- | +3.100 |
isphere | +2.509 |
consolidated | +2.498 |
cient | +2.439 |
-- | +2.372 |
Neg logit contributions | |
CRIP | -5.531 |
HS | -5.352 |
Secretary | -5.225 |
Roose | -5.196 |
Sen | -5.193 |
Token | full |
Token ID | 1336 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
!-- | +3.441 |
consolidated | +3.050 |
isphere | +3.040 |
cient | +2.839 |
colle | +2.768 |
Neg logit contributions | |
CRIP | -5.315 |
HS | -5.231 |
Secretary | -5.117 |
Sen | -5.105 |
Roose | -5.088 |
Token | v |
Token ID | 410 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
!-- | +4.705 |
isphere | +4.240 |
consolidated | +4.193 |
cient | +4.009 |
colle | +3.911 |
Neg logit contributions | |
CRIP | -5.259 |
HS | -5.179 |
Secretary | -5.052 |
IER | -4.980 |
Roose | -4.959 |
Token | ) |
Token ID | 1267 |
Feature activation | -8.68e+00 |
Pos logit contributions | |
!-- | +3.131 |
isphere | +2.729 |
consolidated | +2.712 |
cient | +2.539 |
colle | +2.413 |
Neg logit contributions | |
CRIP | -6.330 |
HS | -6.197 |
IER | -6.045 |
Sen | -5.996 |
Secretary | -5.989 |
Token | { |
Token ID | 1391 |
Feature activation | -8.49e+00 |
Pos logit contributions | |
!-- | +4.602 |
isphere | +4.101 |
consolidated | +4.051 |
cient | +3.769 |
rods | +3.710 |
Neg logit contributions | |
CRIP | -7.211 |
HS | -7.187 |
Secretary | -6.911 |
IER | -6.901 |
Roose | -6.834 |
Token | v |
Token ID | 410 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
!-- | +5.892 |
consolidated | +5.267 |
isphere | +5.074 |
colle | +4.948 |
cient | +4.909 |
Neg logit contributions | |
CRIP | -5.806 |
HS | -5.765 |
Secretary | -5.702 |
Sen | -5.553 |
IER | -5.544 |
Token | . |
Token ID | 764 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
!-- | +4.427 |
consolidated | +3.896 |
isphere | +3.826 |
cient | +3.741 |
-- | +3.612 |
Neg logit contributions | |
CRIP | -4.920 |
HS | -4.712 |
IER | -4.620 |
Sen | -4.565 |
Secretary | -4.539 |
Token | vertex |
Token ID | 37423 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
!-- | +4.003 |
isphere | +3.606 |
consolidated | +3.594 |
cient | +3.420 |
colle | +3.385 |
Neg logit contributions | |
CRIP | -4.069 |
HS | -3.946 |
IER | -3.818 |
Secretary | -3.809 |
Sen | -3.801 |
Token | . |
Token ID | 764 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
!-- | +2.629 |
isphere | +2.362 |
consolidated | +2.332 |
cient | +2.262 |
colle | +2.190 |
Neg logit contributions | |
CRIP | -2.517 |
HS | -2.436 |
Sen | -2.349 |
IER | -2.329 |
Secretary | -2.325 |
Token | J |
Token ID | 41 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
!-- | +3.796 |
isphere | +3.494 |
cient | +3.339 |
consolidated | +3.319 |
colle | +3.218 |
Neg logit contributions | |
CRIP | -2.830 |
HS | -2.645 |
Roose | -2.596 |
Sutherland | -2.569 |
IER | -2.555 |
Token | aaaa |
Token ID | 24794 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
!-- | +2.766 |
isphere | +2.559 |
consolidated | +2.463 |
cient | +2.435 |
colle | +2.385 |
Neg logit contributions | |
CRIP | -2.146 |
HS | -2.017 |
Sen | -1.950 |
Roose | -1.946 |
Secretary | -1.943 |
Token | asper |
Token ID | 32981 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
!-- | +2.779 |
isphere | +2.557 |
consolidated | +2.460 |
cient | +2.426 |
colle | +2.384 |
Neg logit contributions | |
CRIP | -2.068 |
HS | -1.962 |
Sen | -1.876 |
Secretary | -1.864 |
Roose | -1.864 |
Token | Profile |
Token ID | 13118 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
!-- | +0.288 |
isphere | +0.261 |
consolidated | +0.253 |
cient | +0.244 |
colle | +0.242 |
Neg logit contributions | |
CRIP | -0.321 |
HS | -0.313 |
Sen | -0.302 |
Secretary | -0.298 |
IER | -0.298 |
Token | Blog |
Token ID | 14001 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
!-- | +4.234 |
consolidated | +3.485 |
isphere | +3.458 |
cient | +3.296 |
colle | +3.241 |
Neg logit contributions | |
CRIP | -7.052 |
HS | -6.706 |
IER | -6.554 |
serial | -6.516 |
ipal | -6.506 |
Token | Joined |
Token ID | 16709 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
!-- | +3.179 |
consolidated | +2.596 |
isphere | +2.551 |
cient | +2.373 |
~~ | +2.308 |
Neg logit contributions | |
CRIP | -6.562 |
HS | -6.209 |
IER | -6.113 |
Sen | -6.022 |
Secretary | -6.019 |
Token | April |
Token ID | 3035 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
!-- | +4.985 |
consolidated | +4.180 |
isphere | +4.086 |
cient | +4.026 |
-- | +3.992 |
Neg logit contributions | |
CRIP | -7.106 |
HS | -6.623 |
IER | -6.547 |
ipal | -6.537 |
Sen | -6.456 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
CRIP | +0.005 |
HS | +0.005 |
Sen | +0.005 |
Roose | +0.004 |
Secretary | +0.004 |
Neg logit contributions | |
!-- | -0.004 |
isphere | -0.004 |
consolidated | -0.004 |
colle | -0.004 |
cient | -0.003 |
Token | United |
Token ID | 1578 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
!-- | +2.434 |
isphere | +2.148 |
consolidated | +2.137 |
cient | +2.062 |
colle | +2.008 |
Neg logit contributions | |
CRIP | -2.657 |
HS | -2.554 |
IER | -2.468 |
ipal | -2.457 |
Sen | -2.451 |
Token | States |
Token ID | 1829 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
!-- | +2.241 |
isphere | +2.024 |
consolidated | +1.945 |
cient | +1.880 |
colle | +1.851 |
Neg logit contributions | |
CRIP | -2.814 |
HS | -2.690 |
IER | -2.618 |
Secretary | -2.594 |
ipal | -2.570 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
!-- | +0.635 |
isphere | +0.586 |
consolidated | +0.578 |
cient | +0.564 |
colle | +0.558 |
Neg logit contributions | |
CRIP | -0.346 |
HS | -0.331 |
Sen | -0.312 |
IER | -0.308 |
Secretary | -0.308 |
Token | of |
Token ID | 286 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
!-- | +1.343 |
isphere | +1.237 |
consolidated | +1.205 |
cient | +1.174 |
colle | +1.160 |
Neg logit contributions | |
CRIP | -1.060 |
HS | -1.015 |
Sen | -0.970 |
Secretary | -0.961 |
IER | -0.960 |
Token | Dal |
Token ID | 12348 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
CRIP | +0.308 |
HS | +0.301 |
Sen | +0.290 |
Roose | +0.284 |
Secretary | +0.284 |
Neg logit contributions | |
!-- | -0.337 |
isphere | -0.310 |
consolidated | -0.300 |
cient | -0.290 |
colle | -0.289 |
Token | K |
Token ID | 42 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
CRIP | +0.729 |
HS | +0.725 |
Sen | +0.689 |
Roose | +0.664 |
IER | +0.663 |
Neg logit contributions | |
!-- | -1.451 |
isphere | -1.349 |
consolidated | -1.326 |
colle | -1.294 |
cient | -1.279 |
Token | Profile |
Token ID | 13118 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
!-- | +2.246 |
isphere | +2.049 |
consolidated | +2.007 |
cient | +1.944 |
colle | +1.922 |
Neg logit contributions | |
CRIP | -1.859 |
HS | -1.781 |
Sen | -1.710 |
Secretary | -1.700 |
IER | -1.693 |
Token | Blog |
Token ID | 14001 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
!-- | +4.462 |
consolidated | +3.795 |
isphere | +3.689 |
cient | +3.555 |
colle | +3.501 |
Neg logit contributions | |
CRIP | -6.965 |
HS | -6.600 |
IER | -6.478 |
serial | -6.438 |
ipal | -6.396 |
Token | Joined |
Token ID | 16709 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
!-- | +3.342 |
consolidated | +2.729 |
isphere | +2.653 |
cient | +2.458 |
~~ | +2.424 |
Neg logit contributions | |
CRIP | -6.951 |
HS | -6.558 |
IER | -6.475 |
Secretary | -6.385 |
Sen | -6.368 |
Token | June |
Token ID | 2795 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
!-- | +4.906 |
consolidated | +4.155 |
isphere | +4.042 |
cient | +3.960 |
-- | +3.932 |
Neg logit contributions | |
CRIP | -7.077 |
HS | -6.599 |
IER | -6.533 |
ipal | -6.525 |
Sen | -6.444 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
!-- | +1.248 |
isphere | +1.114 |
consolidated | +1.087 |
cient | +1.043 |
colle | +1.029 |
Neg logit contributions | |
CRIP | -1.565 |
HS | -1.526 |
Sen | -1.474 |
IER | -1.458 |
Secretary | -1.458 |
Token | Canada |
Token ID | 3340 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
!-- | +2.123 |
isphere | +1.878 |
consolidated | +1.871 |
cient | +1.798 |
colle | +1.756 |
Neg logit contributions | |
CRIP | -2.414 |
HS | -2.326 |
IER | -2.244 |
Sen | -2.237 |
Secretary | -2.234 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
!-- | +0.487 |
isphere | +0.450 |
consolidated | +0.443 |
cient | +0.433 |
colle | +0.427 |
Neg logit contributions | |
CRIP | -0.268 |
HS | -0.257 |
Sen | -0.242 |
IER | -0.239 |
Secretary | -0.239 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
!-- | +1.940 |
isphere | +1.753 |
consolidated | +1.741 |
cient | +1.700 |
colle | +1.663 |
Neg logit contributions | |
CRIP | -1.380 |
HS | -1.319 |
IER | -1.265 |
Sen | -1.264 |
ipal | -1.255 |
Token | data |
Token ID | 7890 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
!-- | +3.898 |
isphere | +3.603 |
consolidated | +3.477 |
cient | +3.444 |
colle | +3.267 |
Neg logit contributions | |
CRIP | -2.780 |
HS | -2.629 |
Roose | -2.545 |
Sen | -2.528 |
IER | -2.521 |
Token | _ |
Token ID | 4808 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
!-- | +3.100 |
isphere | +2.509 |
consolidated | +2.498 |
cient | +2.439 |
-- | +2.372 |
Neg logit contributions | |
CRIP | -5.531 |
HS | -5.352 |
Secretary | -5.225 |
Roose | -5.196 |
Sen | -5.193 |
Token | full |
Token ID | 1336 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
!-- | +3.441 |
consolidated | +3.050 |
isphere | +3.040 |
cient | +2.839 |
colle | +2.768 |
Neg logit contributions | |
CRIP | -5.315 |
HS | -5.231 |
Secretary | -5.117 |
Sen | -5.105 |
Roose | -5.088 |
Token | v |
Token ID | 410 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
!-- | +4.705 |
isphere | +4.240 |
consolidated | +4.193 |
cient | +4.009 |
colle | +3.911 |
Neg logit contributions | |
CRIP | -5.259 |
HS | -5.179 |
Secretary | -5.052 |
IER | -4.980 |
Roose | -4.959 |
Token | ) |
Token ID | 1267 |
Feature activation | -8.68e+00 |
Pos logit contributions | |
!-- | +3.131 |
isphere | +2.729 |
consolidated | +2.712 |
cient | +2.539 |
colle | +2.413 |
Neg logit contributions | |
CRIP | -6.330 |
HS | -6.197 |
IER | -6.045 |
Sen | -5.996 |
Secretary | -5.989 |
Token | { |
Token ID | 1391 |
Feature activation | -8.49e+00 |
Pos logit contributions | |
!-- | +4.602 |
isphere | +4.101 |
consolidated | +4.051 |
cient | +3.769 |
rods | +3.710 |
Neg logit contributions | |
CRIP | -7.211 |
HS | -7.187 |
Secretary | -6.911 |
IER | -6.901 |
Roose | -6.834 |
Token | v |
Token ID | 410 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
!-- | +5.892 |
consolidated | +5.267 |
isphere | +5.074 |
colle | +4.948 |
cient | +4.909 |
Neg logit contributions | |
CRIP | -5.806 |
HS | -5.765 |
Secretary | -5.702 |
Sen | -5.553 |
IER | -5.544 |
Token | . |
Token ID | 764 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
!-- | +4.427 |
consolidated | +3.896 |
isphere | +3.826 |
cient | +3.741 |
-- | +3.612 |
Neg logit contributions | |
CRIP | -4.920 |
HS | -4.712 |
IER | -4.620 |
Sen | -4.565 |
Secretary | -4.539 |
Token | vertex |
Token ID | 37423 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
!-- | +4.003 |
isphere | +3.606 |
consolidated | +3.594 |
cient | +3.420 |
colle | +3.385 |
Neg logit contributions | |
CRIP | -4.069 |
HS | -3.946 |
IER | -3.818 |
Secretary | -3.809 |
Sen | -3.801 |
Token | . |
Token ID | 764 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
!-- | +2.629 |
isphere | +2.362 |
consolidated | +2.332 |
cient | +2.262 |
colle | +2.190 |
Neg logit contributions | |
CRIP | -2.517 |
HS | -2.436 |
Sen | -2.349 |
IER | -2.329 |
Secretary | -2.325 |
Token | x |
Token ID | 2124 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
!-- | +4.367 |
isphere | +3.871 |
consolidated | +3.837 |
cient | +3.676 |
colle | +3.599 |
Neg logit contributions | |
CRIP | -4.941 |
HS | -4.805 |
Sen | -4.661 |
Secretary | -4.647 |
IER | -4.620 |
Token |
|
Token ID | 198 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
!-- | +1.788 |
isphere | +1.573 |
consolidated | +1.549 |
cient | +1.514 |
~~ | +1.460 |
Neg logit contributions | |
CRIP | -1.798 |
HS | -1.714 |
IER | -1.647 |
Sen | -1.641 |
Roose | -1.641 |
Token | Master |
Token ID | 18254 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
!-- | +2.548 |
isphere | +2.347 |
consolidated | +2.251 |
cient | +2.237 |
colle | +2.176 |
Neg logit contributions | |
CRIP | -1.915 |
HS | -1.812 |
Roose | -1.750 |
IER | -1.730 |
Sutherland | -1.728 |
Token | of |
Token ID | 286 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
!-- | +1.343 |
isphere | +1.237 |
consolidated | +1.205 |
cient | +1.174 |
colle | +1.160 |
Neg logit contributions | |
CRIP | -1.060 |
HS | -1.015 |
Sen | -0.970 |
Secretary | -0.961 |
IER | -0.960 |
Token | Dal |
Token ID | 12348 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
CRIP | +0.308 |
HS | +0.301 |
Sen | +0.290 |
Roose | +0.284 |
Secretary | +0.284 |
Neg logit contributions | |
!-- | -0.337 |
isphere | -0.310 |
consolidated | -0.300 |
cient | -0.290 |
colle | -0.289 |
Token | K |
Token ID | 42 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
CRIP | +0.729 |
HS | +0.725 |
Sen | +0.689 |
Roose | +0.664 |
IER | +0.663 |
Neg logit contributions | |
!-- | -1.451 |
isphere | -1.349 |
consolidated | -1.326 |
colle | -1.294 |
cient | -1.279 |
Token | Profile |
Token ID | 13118 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
!-- | +2.246 |
isphere | +2.049 |
consolidated | +2.007 |
cient | +1.944 |
colle | +1.922 |
Neg logit contributions | |
CRIP | -1.859 |
HS | -1.781 |
Sen | -1.710 |
Secretary | -1.700 |
IER | -1.693 |
Token | Blog |
Token ID | 14001 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
!-- | +4.462 |
consolidated | +3.795 |
isphere | +3.689 |
cient | +3.555 |
colle | +3.501 |
Neg logit contributions | |
CRIP | -6.965 |
HS | -6.600 |
IER | -6.478 |
serial | -6.438 |
ipal | -6.396 |
Token | Joined |
Token ID | 16709 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
!-- | +3.342 |
consolidated | +2.729 |
isphere | +2.653 |
cient | +2.458 |
~~ | +2.424 |
Neg logit contributions | |
CRIP | -6.951 |
HS | -6.558 |
IER | -6.475 |
Secretary | -6.385 |
Sen | -6.368 |
Token | June |
Token ID | 2795 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
!-- | +4.906 |
consolidated | +4.155 |
isphere | +4.042 |
cient | +3.960 |
-- | +3.932 |
Neg logit contributions | |
CRIP | -7.077 |
HS | -6.599 |
IER | -6.533 |
ipal | -6.525 |
Sen | -6.444 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
!-- | +1.248 |
isphere | +1.114 |
consolidated | +1.087 |
cient | +1.043 |
colle | +1.029 |
Neg logit contributions | |
CRIP | -1.565 |
HS | -1.526 |
Sen | -1.474 |
IER | -1.458 |
Secretary | -1.458 |
Token | Canada |
Token ID | 3340 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
!-- | +2.123 |
isphere | +1.878 |
consolidated | +1.871 |
cient | +1.798 |
colle | +1.756 |
Neg logit contributions | |
CRIP | -2.414 |
HS | -2.326 |
IER | -2.244 |
Sen | -2.237 |
Secretary | -2.234 |
Token |
|
Token ID | 198 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
!-- | +3.757 |
isphere | +3.381 |
consolidated | +3.308 |
cient | +3.240 |
colle | +3.188 |
Neg logit contributions | |
CRIP | -2.521 |
HS | -2.374 |
ipal | -2.302 |
Sen | -2.292 |
serial | -2.291 |
Token |
|
Token ID | 198 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
!-- | +2.643 |
isphere | +2.272 |
consolidated | +2.249 |
cient | +2.213 |
-- | +2.169 |
Neg logit contributions | |
CRIP | -2.835 |
HS | -2.677 |
IER | -2.594 |
Roose | -2.592 |
ipal | -2.591 |
Token | J |
Token ID | 41 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
!-- | +3.796 |
isphere | +3.494 |
cient | +3.339 |
consolidated | +3.319 |
colle | +3.218 |
Neg logit contributions | |
CRIP | -2.830 |
HS | -2.645 |
Roose | -2.596 |
Sutherland | -2.569 |
IER | -2.555 |
Token | aaaa |
Token ID | 24794 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
!-- | +2.766 |
isphere | +2.559 |
consolidated | +2.463 |
cient | +2.435 |
colle | +2.385 |
Neg logit contributions | |
CRIP | -2.146 |
HS | -2.017 |
Sen | -1.950 |
Roose | -1.946 |
Secretary | -1.943 |
Token | asper |
Token ID | 32981 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
!-- | +2.779 |
isphere | +2.557 |
consolidated | +2.460 |
cient | +2.426 |
colle | +2.384 |
Neg logit contributions | |
CRIP | -2.068 |
HS | -1.962 |
Sen | -1.876 |
Secretary | -1.864 |
Roose | -1.864 |
Token | Profile |
Token ID | 13118 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
!-- | +0.288 |
isphere | +0.261 |
consolidated | +0.253 |
cient | +0.244 |
colle | +0.242 |
Neg logit contributions | |
CRIP | -0.321 |
HS | -0.313 |
Sen | -0.302 |
Secretary | -0.298 |
IER | -0.298 |
Token | Blog |
Token ID | 14001 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
!-- | +4.234 |
consolidated | +3.485 |
isphere | +3.458 |
cient | +3.296 |
colle | +3.241 |
Neg logit contributions | |
CRIP | -7.052 |
HS | -6.706 |
IER | -6.554 |
serial | -6.516 |
ipal | -6.506 |
Token | Joined |
Token ID | 16709 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
!-- | +3.179 |
consolidated | +2.596 |
isphere | +2.551 |
cient | +2.373 |
~~ | +2.308 |
Neg logit contributions | |
CRIP | -6.562 |
HS | -6.209 |
IER | -6.113 |
Sen | -6.022 |
Secretary | -6.019 |
Token | April |
Token ID | 3035 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
!-- | +4.985 |
consolidated | +4.180 |
isphere | +4.086 |
cient | +4.026 |
-- | +3.992 |
Neg logit contributions | |
CRIP | -7.106 |
HS | -6.623 |
IER | -6.547 |
ipal | -6.537 |
Sen | -6.456 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
CRIP | +0.005 |
HS | +0.005 |
Sen | +0.005 |
Roose | +0.004 |
Secretary | +0.004 |
Neg logit contributions | |
!-- | -0.004 |
isphere | -0.004 |
consolidated | -0.004 |
colle | -0.004 |
cient | -0.003 |
Token | United |
Token ID | 1578 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
!-- | +2.434 |
isphere | +2.148 |
consolidated | +2.137 |
cient | +2.062 |
colle | +2.008 |
Neg logit contributions | |
CRIP | -2.657 |
HS | -2.554 |
IER | -2.468 |
ipal | -2.457 |
Sen | -2.451 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
CRIP | +1.264 |
HS | +1.247 |
Sen | +1.201 |
Secretary | +1.171 |
Roose | +1.163 |
Neg logit contributions | |
!-- | -1.247 |
isphere | -1.166 |
consolidated | -1.101 |
colle | -1.075 |
cient | -1.074 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
CRIP | +1.099 |
HS | +1.079 |
Sen | +1.034 |
IER | +1.016 |
Secretary | +1.012 |
Neg logit contributions | |
!-- | -1.286 |
isphere | -1.208 |
consolidated | -1.169 |
colle | -1.142 |
cient | -1.133 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
!-- | +1.238 |
isphere | +1.102 |
consolidated | +1.083 |
cient | +1.054 |
colle | +1.014 |
Neg logit contributions | |
CRIP | -1.196 |
HS | -1.147 |
Sen | -1.100 |
IER | -1.098 |
Roose | -1.092 |
Token | Ko |
Token ID | 48735 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
!-- | +1.853 |
isphere | +1.704 |
consolidated | +1.641 |
cient | +1.622 |
colle | +1.585 |
Neg logit contributions | |
CRIP | -1.409 |
HS | -1.337 |
Roose | -1.282 |
IER | -1.276 |
Sen | -1.275 |
Token | Do |
Token ID | 5211 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
!-- | +2.838 |
isphere | +2.596 |
consolidated | +2.509 |
cient | +2.467 |
colle | +2.427 |
Neg logit contributions | |
CRIP | -2.302 |
HS | -2.191 |
Sen | -2.105 |
Secretary | -2.103 |
IER | -2.095 |
Token | Profile |
Token ID | 13118 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
!-- | +2.093 |
isphere | +1.914 |
consolidated | +1.861 |
cient | +1.822 |
colle | +1.795 |
Neg logit contributions | |
CRIP | -1.738 |
HS | -1.664 |
Sen | -1.589 |
Secretary | -1.584 |
IER | -1.578 |
Token | Joined |
Token ID | 16709 |
Feature activation | -9.44e+00 |
Pos logit contributions | |
!-- | +4.262 |
consolidated | +3.586 |
isphere | +3.520 |
cient | +3.397 |
~~ | +3.333 |
Neg logit contributions | |
CRIP | -6.904 |
HS | -6.524 |
IER | -6.406 |
Sen | -6.328 |
serial | -6.326 |
Token | December |
Token ID | 3426 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
!-- | +5.251 |
consolidated | +4.359 |
-- | +4.233 |
isphere | +4.195 |
cient | +4.175 |
Neg logit contributions | |
CRIP | -7.923 |
HS | -7.403 |
IER | -7.342 |
ipal | -7.324 |
Sen | -7.187 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
CRIP | +0.680 |
HS | +0.671 |
Sen | +0.650 |
Roose | +0.644 |
Secretary | +0.640 |
Neg logit contributions | |
!-- | -0.599 |
isphere | -0.555 |
consolidated | -0.529 |
colle | -0.514 |
cient | -0.507 |
Token | United |
Token ID | 1578 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
!-- | +2.182 |
isphere | +1.943 |
consolidated | +1.925 |
cient | +1.849 |
colle | +1.813 |
Neg logit contributions | |
CRIP | -2.366 |
HS | -2.275 |
Sen | -2.190 |
IER | -2.189 |
Secretary | -2.184 |
Token | States |
Token ID | 1829 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
!-- | +1.573 |
isphere | +1.416 |
consolidated | +1.383 |
cient | +1.333 |
colle | +1.310 |
Neg logit contributions | |
CRIP | -1.645 |
HS | -1.592 |
Sen | -1.526 |
Secretary | -1.519 |
IER | -1.518 |
Token | app |
Token ID | 598 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
!-- | +1.897 |
isphere | +1.682 |
consolidated | +1.634 |
cient | +1.555 |
colle | +1.543 |
Neg logit contributions | |
CRIP | -2.776 |
HS | -2.718 |
Sen | -2.629 |
Secretary | -2.603 |
IER | -2.598 |
Token | data |
Token ID | 7890 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
!-- | +4.322 |
isphere | +3.998 |
consolidated | +3.862 |
cient | +3.815 |
colle | +3.628 |
Neg logit contributions | |
CRIP | -3.087 |
HS | -2.927 |
Roose | -2.831 |
Sen | -2.811 |
IER | -2.800 |
Token | _ |
Token ID | 4808 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
!-- | +2.743 |
isphere | +2.377 |
consolidated | +2.373 |
cient | +2.236 |
colle | +2.184 |
Neg logit contributions | |
CRIP | -4.042 |
HS | -3.945 |
Secretary | -3.826 |
Sen | -3.823 |
IER | -3.781 |
Token | full |
Token ID | 1336 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
!-- | +2.907 |
consolidated | +2.592 |
isphere | +2.557 |
cient | +2.398 |
colle | +2.340 |
Neg logit contributions | |
CRIP | -4.675 |
HS | -4.577 |
Sen | -4.426 |
Secretary | -4.413 |
Roose | -4.394 |
Token | v |
Token ID | 410 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
!-- | +4.323 |
consolidated | +3.909 |
isphere | +3.877 |
cient | +3.720 |
colle | +3.679 |
Neg logit contributions | |
CRIP | -3.546 |
HS | -3.465 |
Secretary | -3.316 |
Sen | -3.304 |
IER | -3.286 |
Token | ) |
Token ID | 1267 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
!-- | +2.830 |
isphere | +2.445 |
consolidated | +2.419 |
cient | +2.292 |
colle | +2.153 |
Neg logit contributions | |
CRIP | -5.331 |
HS | -5.182 |
Sen | -5.030 |
IER | -5.028 |
Secretary | -4.995 |
Token | { |
Token ID | 1391 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
!-- | +4.351 |
isphere | +3.720 |
consolidated | +3.705 |
cient | +3.517 |
-- | +3.408 |
Neg logit contributions | |
CRIP | -6.600 |
HS | -6.436 |
Secretary | -6.227 |
IER | -6.218 |
Roose | -6.196 |
Token | // |
Token ID | 3373 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
!-- | +3.670 |
consolidated | +3.096 |
isphere | +2.746 |
bench | +2.591 |
-- | +2.568 |
Neg logit contributions | |
CRIP | -9.225 |
Secretary | -8.883 |
HS | -8.839 |
Roose | -8.720 |
Sen | -8.659 |
Token | Time |
Token ID | 3862 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
!-- | +3.070 |
isphere | +2.712 |
consolidated | +2.705 |
cient | +2.600 |
colle | +2.581 |
Neg logit contributions | |
CRIP | -2.742 |
HS | -2.609 |
Secretary | -2.477 |
Sen | -2.470 |
ipal | -2.458 |
Token | component |
Token ID | 7515 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
!-- | +0.621 |
isphere | +0.572 |
consolidated | +0.554 |
cient | +0.538 |
colle | +0.538 |
Neg logit contributions | |
CRIP | -0.512 |
HS | -0.499 |
Sen | -0.478 |
Secretary | -0.472 |
IER | -0.471 |
Token | const |
Token ID | 1500 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
!-- | +0.458 |
isphere | +0.421 |
consolidated | +0.405 |
cient | +0.394 |
colle | +0.392 |
Neg logit contributions | |
CRIP | -0.458 |
HS | -0.447 |
Sen | -0.431 |
Secretary | -0.423 |
IER | -0.422 |
Token |
|
Token ID | 198 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
!-- | +0.820 |
isphere | +0.739 |
consolidated | +0.728 |
cient | +0.702 |
colle | +0.699 |
Neg logit contributions | |
CRIP | -0.789 |
HS | -0.766 |
Sen | -0.735 |
Secretary | -0.732 |
IER | -0.728 |
Token |
|
Token ID | 198 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
CRIP | +0.552 |
HS | +0.542 |
Sen | +0.521 |
Secretary | +0.512 |
IER | +0.507 |
Neg logit contributions | |
!-- | -0.668 |
isphere | -0.622 |
consolidated | -0.604 |
colle | -0.590 |
cient | -0.581 |
Token | � |
Token ID | 447 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
CRIP | +0.331 |
HS | +0.320 |
Sen | +0.304 |
IER | +0.301 |
Secretary | +0.300 |
Neg logit contributions | |
!-- | -0.460 |
isphere | -0.423 |
consolidated | -0.413 |
cient | -0.403 |
colle | -0.399 |
Token | � |
Token ID | 250 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
!-- | +0.525 |
isphere | +0.487 |
consolidated | +0.477 |
colle | +0.464 |
cient | +0.459 |
Neg logit contributions | |
CRIP | -0.390 |
HS | -0.380 |
Sen | -0.365 |
Secretary | -0.359 |
IER | -0.356 |
Token | Just |
Token ID | 5703 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
CRIP | +0.207 |
HS | +0.201 |
Sen | +0.192 |
Secretary | +0.190 |
IER | +0.189 |
Neg logit contributions | |
!-- | -0.265 |
isphere | -0.243 |
consolidated | -0.238 |
cient | -0.231 |
colle | -0.229 |
Token | Like |
Token ID | 4525 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
!-- | +0.567 |
isphere | +0.518 |
consolidated | +0.505 |
cient | +0.488 |
colle | +0.485 |
Neg logit contributions | |
CRIP | -0.530 |
HS | -0.517 |
Sen | -0.496 |
Secretary | -0.489 |
IER | -0.488 |
Token | Heaven |
Token ID | 11225 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
!-- | +5.765 |
isphere | +5.025 |
-- | +4.861 |
consolidated | +4.848 |
cient | +4.780 |
Neg logit contributions | |
CRIP | -5.229 |
HS | -4.990 |
IER | -4.824 |
Secretary | -4.756 |
Sen | -4.723 |
Token | � |
Token ID | 447 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
!-- | +0.472 |
isphere | +0.428 |
consolidated | +0.421 |
cient | +0.408 |
colle | +0.404 |
Neg logit contributions | |
CRIP | -0.365 |
HS | -0.353 |
Sen | -0.338 |
Secretary | -0.334 |
IER | -0.334 |
Token | � |
Token ID | 251 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
!-- | +0.316 |
isphere | +0.293 |
consolidated | +0.286 |
colle | +0.279 |
cient | +0.276 |
Neg logit contributions | |
CRIP | -0.239 |
HS | -0.234 |
Sen | -0.224 |
Secretary | -0.220 |
Roose | -0.218 |
Token | b |
Token ID | 275 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
!-- | +0.739 |
isphere | +0.668 |
consolidated | +0.660 |
cient | +0.634 |
colle | +0.633 |
Neg logit contributions | |
CRIP | -0.672 |
HS | -0.651 |
Sen | -0.625 |
Secretary | -0.620 |
IER | -0.617 |
Token | / |
Token ID | 14 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
!-- | +2.199 |
isphere | +1.832 |
consolidated | +1.769 |
cient | +1.727 |
~~ | +1.639 |
Neg logit contributions | |
CRIP | -4.118 |
HS | -3.959 |
IER | -3.859 |
Sen | -3.855 |
Secretary | -3.844 |
Token |
|
Token ID | 198 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
!-- | +1.547 |
isphere | +1.407 |
consolidated | +1.371 |
cient | +1.323 |
colle | +1.315 |
Neg logit contributions | |
CRIP | -1.502 |
HS | -1.460 |
Sen | -1.403 |
IER | -1.387 |
Secretary | -1.387 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
!-- | +0.626 |
isphere | +0.567 |
consolidated | +0.553 |
cient | +0.538 |
colle | +0.526 |
Neg logit contributions | |
CRIP | -0.573 |
HS | -0.555 |
Sen | -0.531 |
IER | -0.526 |
Roose | -0.526 |
Token | pur |
Token ID | 14225 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
!-- | +1.159 |
isphere | +1.064 |
consolidated | +1.033 |
cient | +1.008 |
colle | +0.994 |
Neg logit contributions | |
CRIP | -0.915 |
HS | -0.883 |
Sen | -0.843 |
IER | -0.836 |
Roose | -0.835 |
Token | ak |
Token ID | 461 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
!-- | +0.219 |
isphere | +0.197 |
consolidated | +0.191 |
cient | +0.183 |
colle | +0.182 |
Neg logit contributions | |
CRIP | -0.269 |
HS | -0.262 |
Sen | -0.253 |
Secretary | -0.251 |
IER | -0.250 |
Token | ushi |
Token ID | 17731 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
!-- | +2.492 |
isphere | +2.279 |
consolidated | +2.224 |
cient | +2.168 |
colle | +2.141 |
Neg logit contributions | |
CRIP | -2.048 |
HS | -1.973 |
Sen | -1.886 |
Secretary | -1.876 |
IER | -1.876 |
Token | Profile |
Token ID | 13118 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
!-- | +1.871 |
isphere | +1.703 |
consolidated | +1.665 |
cient | +1.610 |
colle | +1.599 |
Neg logit contributions | |
CRIP | -1.710 |
HS | -1.659 |
Sen | -1.592 |
IER | -1.575 |
Secretary | -1.574 |
Token | Joined |
Token ID | 16709 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
!-- | +3.902 |
consolidated | +3.242 |
isphere | +3.206 |
colle | +3.011 |
cient | +3.007 |
Neg logit contributions | |
CRIP | -7.070 |
HS | -6.732 |
IER | -6.618 |
ipal | -6.568 |
serial | -6.563 |
Token | August |
Token ID | 2932 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
!-- | +6.057 |
consolidated | +4.915 |
-- | +4.888 |
cient | +4.739 |
isphere | +4.730 |
Neg logit contributions | |
CRIP | -9.352 |
ipal | -8.616 |
HS | -8.606 |
IER | -8.567 |
tailed | -8.403 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
!-- | +1.513 |
isphere | +1.348 |
consolidated | +1.314 |
cient | +1.260 |
colle | +1.242 |
Neg logit contributions | |
CRIP | -1.953 |
HS | -1.903 |
Sen | -1.838 |
Secretary | -1.821 |
IER | -1.819 |
Token | United |
Token ID | 1578 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
!-- | +2.432 |
isphere | +2.158 |
consolidated | +2.142 |
cient | +2.069 |
colle | +2.020 |
Neg logit contributions | |
CRIP | -2.589 |
HS | -2.481 |
IER | -2.393 |
Sen | -2.384 |
ipal | -2.381 |
Token | States |
Token ID | 1829 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
!-- | +2.316 |
isphere | +2.086 |
consolidated | +2.016 |
cient | +1.942 |
colle | +1.931 |
Neg logit contributions | |
CRIP | -2.757 |
HS | -2.653 |
IER | -2.574 |
Secretary | -2.547 |
Sen | -2.533 |
Token |
|
Token ID | 198 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
!-- | +3.151 |
isphere | +2.671 |
consolidated | +2.651 |
cient | +2.621 |
-- | +2.598 |
Neg logit contributions | |
CRIP | -3.528 |
HS | -3.309 |
IER | -3.228 |
Roose | -3.226 |
ipal | -3.222 |
Token | Dark |
Token ID | 17367 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
!-- | +4.284 |
isphere | +3.942 |
cient | +3.774 |
consolidated | +3.740 |
colle | +3.626 |
Neg logit contributions | |
CRIP | -3.164 |
HS | -2.950 |
Roose | -2.908 |
Sutherland | -2.884 |
IER | -2.854 |
Token | horse |
Token ID | 30527 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
!-- | +1.663 |
isphere | +1.532 |
consolidated | +1.490 |
cient | +1.460 |
colle | +1.432 |
Neg logit contributions | |
CRIP | -1.273 |
HS | -1.218 |
Sen | -1.161 |
IER | -1.150 |
Secretary | -1.147 |
Token | Profile |
Token ID | 13118 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
!-- | +2.067 |
isphere | +1.879 |
consolidated | +1.830 |
cient | +1.788 |
colle | +1.756 |
Neg logit contributions | |
CRIP | -1.881 |
HS | -1.810 |
Sen | -1.730 |
IER | -1.720 |
Secretary | -1.719 |
Token | Blog |
Token ID | 14001 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
!-- | +3.667 |
consolidated | +3.073 |
isphere | +3.032 |
cient | +2.931 |
colle | +2.884 |
Neg logit contributions | |
CRIP | -5.801 |
HS | -5.527 |
IER | -5.378 |
serial | -5.347 |
ipal | -5.345 |
Token | Joined |
Token ID | 16709 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
!-- | +2.987 |
consolidated | +2.446 |
isphere | +2.423 |
cient | +2.254 |
~~ | +2.175 |
Neg logit contributions | |
CRIP | -5.909 |
HS | -5.605 |
IER | -5.501 |
Sen | -5.443 |
Secretary | -5.438 |
Token | December |
Token ID | 3426 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
!-- | +4.552 |
consolidated | +3.868 |
isphere | +3.799 |
cient | +3.698 |
-- | +3.632 |
Neg logit contributions | |
CRIP | -6.386 |
HS | -5.980 |
IER | -5.894 |
ipal | -5.879 |
Sen | -5.829 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
CRIP | +0.658 |
HS | +0.648 |
Sen | +0.626 |
Roose | +0.620 |
Secretary | +0.617 |
Neg logit contributions | |
!-- | -0.582 |
isphere | -0.536 |
consolidated | -0.514 |
colle | -0.498 |
cient | -0.492 |
Token | United |
Token ID | 1578 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
!-- | +1.758 |
isphere | +1.564 |
consolidated | +1.546 |
cient | +1.488 |
colle | +1.458 |
Neg logit contributions | |
CRIP | -1.997 |
HS | -1.927 |
Sen | -1.854 |
IER | -1.852 |
Secretary | -1.846 |
Token | States |
Token ID | 1829 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
!-- | +1.804 |
isphere | +1.635 |
consolidated | +1.581 |
cient | +1.531 |
colle | +1.508 |
Neg logit contributions | |
CRIP | -2.100 |
HS | -2.012 |
IER | -1.948 |
Secretary | -1.933 |
Sen | -1.921 |
Token | 228 |
Token ID | 29041 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
!-- | +0.157 |
isphere | +0.146 |
consolidated | +0.143 |
cient | +0.140 |
colle | +0.139 |
Neg logit contributions | |
CRIP | -0.085 |
HS | -0.081 |
Sen | -0.077 |
Secretary | -0.076 |
IER | -0.076 |
Token | TB |
Token ID | 22737 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
!-- | +4.367 |
isphere | +4.031 |
cient | +3.856 |
consolidated | +3.798 |
~~ | +3.709 |
Neg logit contributions | |
CRIP | -3.257 |
HS | -3.013 |
Roose | -2.985 |
Sutherland | -2.959 |
IER | -2.922 |
Token | one |
Token ID | 505 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
!-- | +1.462 |
isphere | +1.346 |
consolidated | +1.311 |
cient | +1.274 |
colle | +1.262 |
Neg logit contributions | |
CRIP | -1.178 |
HS | -1.131 |
Sen | -1.087 |
Secretary | -1.076 |
IER | -1.072 |
Token | - |
Token ID | 12 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
!-- | +2.024 |
isphere | +1.852 |
consolidated | +1.802 |
cient | +1.756 |
colle | +1.727 |
Neg logit contributions | |
CRIP | -1.806 |
HS | -1.738 |
Sen | -1.662 |
Secretary | -1.652 |
IER | -1.642 |
Token | Profile |
Token ID | 13118 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
!-- | +2.241 |
isphere | +2.064 |
consolidated | +1.995 |
cient | +1.958 |
colle | +1.918 |
Neg logit contributions | |
CRIP | -1.840 |
HS | -1.749 |
Roose | -1.667 |
Sen | -1.661 |
Secretary | -1.658 |
Token | Blog |
Token ID | 14001 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
!-- | +3.543 |
consolidated | +2.988 |
isphere | +2.972 |
cient | +2.860 |
colle | +2.769 |
Neg logit contributions | |
CRIP | -5.655 |
HS | -5.370 |
IER | -5.231 |
ipal | -5.227 |
Sen | -5.211 |
Token | Joined |
Token ID | 16709 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
!-- | +2.865 |
consolidated | +2.354 |
isphere | +2.351 |
cient | +2.166 |
~~ | +2.067 |
Neg logit contributions | |
CRIP | -5.710 |
HS | -5.419 |
IER | -5.308 |
Sen | -5.269 |
Secretary | -5.242 |
Token | November |
Token ID | 3389 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
!-- | +4.545 |
consolidated | +3.873 |
isphere | +3.793 |
cient | +3.686 |
-- | +3.631 |
Neg logit contributions | |
CRIP | -6.354 |
HS | -5.963 |
IER | -5.873 |
ipal | -5.869 |
Sen | -5.815 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
CRIP | +0.844 |
HS | +0.836 |
Sen | +0.808 |
Roose | +0.802 |
Secretary | +0.798 |
Neg logit contributions | |
!-- | -0.766 |
isphere | -0.709 |
consolidated | -0.677 |
colle | -0.660 |
cient | -0.648 |
Token | United |
Token ID | 1578 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
!-- | +2.365 |
isphere | +2.096 |
consolidated | +2.078 |
cient | +1.998 |
colle | +1.947 |
Neg logit contributions | |
CRIP | -2.741 |
HS | -2.628 |
IER | -2.541 |
Sen | -2.529 |
ipal | -2.527 |
Token | States |
Token ID | 1829 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
!-- | +1.368 |
isphere | +1.240 |
consolidated | +1.199 |
cient | +1.162 |
colle | +1.141 |
Neg logit contributions | |
CRIP | -1.594 |
HS | -1.530 |
IER | -1.477 |
Secretary | -1.467 |
Sen | -1.463 |
Token | 21 |
Token ID | 2310 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
CRIP | +0.170 |
HS | +0.164 |
Sen | +0.155 |
Secretary | +0.152 |
IER | +0.152 |
Neg logit contributions | |
!-- | -0.322 |
isphere | -0.299 |
consolidated | -0.294 |
cient | -0.286 |
colle | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
CRIP | +0.902 |
HS | +0.882 |
Sen | +0.846 |
Secretary | +0.834 |
IER | +0.830 |
Neg logit contributions | |
!-- | -1.012 |
isphere | -0.929 |
consolidated | -0.901 |
cient | -0.872 |
colle | -0.864 |
Token | same |
Token ID | 976 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
CRIP | +1.349 |
HS | +1.327 |
Sen | +1.281 |
Secretary | +1.263 |
Roose | +1.263 |
Neg logit contributions | |
!-- | -1.179 |
isphere | -1.075 |
consolidated | -1.026 |
cient | -0.994 |
colle | -0.979 |
Token | person |
Token ID | 1048 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
CRIP | +0.851 |
HS | +0.830 |
Sen | +0.799 |
Secretary | +0.788 |
IER | +0.787 |
Neg logit contributions | |
!-- | -0.834 |
isphere | -0.759 |
consolidated | -0.738 |
cient | -0.712 |
colle | -0.707 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
CRIP | +1.701 |
HS | +1.664 |
Sen | +1.606 |
Secretary | +1.587 |
IER | +1.581 |
Neg logit contributions | |
!-- | -1.488 |
isphere | -1.352 |
consolidated | -1.308 |
cient | -1.258 |
colle | -1.253 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
CRIP | +1.090 |
HS | +1.065 |
Sen | +1.023 |
Secretary | +1.005 |
IER | +0.999 |
Neg logit contributions | |
!-- | -1.307 |
isphere | -1.208 |
consolidated | -1.174 |
cient | -1.133 |
colle | -1.130 |
Token | Published |
Token ID | 24492 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
CRIP | +0.711 |
HS | +0.693 |
Sen | +0.665 |
Secretary | +0.654 |
IER | +0.649 |
Neg logit contributions | |
!-- | -0.901 |
isphere | -0.831 |
consolidated | -0.814 |
cient | -0.785 |
colle | -0.785 |
Token | on |
Token ID | 319 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
!-- | +5.075 |
consolidated | +4.550 |
isphere | +4.422 |
cient | +4.331 |
colle | +4.252 |
Neg logit contributions | |
CRIP | -5.415 |
HS | -5.239 |
Secretary | -4.984 |
ipal | -4.980 |
IER | -4.934 |
Token | 28 |
Token ID | 2579 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
!-- | +2.325 |
isphere | +2.085 |
consolidated | +2.071 |
cient | +1.989 |
colle | +1.975 |
Neg logit contributions | |
CRIP | -2.241 |
HS | -2.146 |
Sen | -2.061 |
IER | -2.060 |
Secretary | -2.046 |
Token | December |
Token ID | 3426 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
!-- | +0.800 |
isphere | +0.725 |
consolidated | +0.707 |
cient | +0.681 |
colle | +0.676 |
Neg logit contributions | |
CRIP | -0.845 |
HS | -0.823 |
Sen | -0.793 |
Secretary | -0.783 |
IER | -0.782 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
CRIP | +0.908 |
HS | +0.887 |
Sen | +0.853 |
Secretary | +0.839 |
IER | +0.837 |
Neg logit contributions | |
!-- | -0.973 |
isphere | -0.902 |
consolidated | -0.870 |
colle | -0.841 |
cient | -0.840 |
Token | 10 |
Token ID | 838 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
!-- | +1.142 |
isphere | +1.033 |
consolidated | +1.014 |
cient | +0.977 |
colle | +0.968 |
Neg logit contributions | |
CRIP | -1.100 |
HS | -1.069 |
Sen | -1.026 |
Secretary | -1.015 |
IER | -1.012 |
Token | : |
Token ID | 25 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
!-- | +1.630 |
isphere | +1.443 |
consolidated | +1.414 |
cient | +1.377 |
-- | +1.321 |
Neg logit contributions | |
CRIP | -1.654 |
HS | -1.582 |
IER | -1.521 |
Sen | -1.521 |
Secretary | -1.515 |
Token | 47 |
Token ID | 2857 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
!-- | +2.185 |
isphere | +1.981 |
consolidated | +1.956 |
cient | +1.887 |
colle | +1.865 |
Neg logit contributions | |
CRIP | -1.424 |
HS | -1.404 |
Roose | -1.342 |
IER | -1.336 |
Secretary | -1.332 |
Token | ] |
Token ID | 60 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
!-- | +1.622 |
isphere | +1.499 |
consolidated | +1.474 |
cient | +1.444 |
colle | +1.415 |
Neg logit contributions | |
CRIP | -0.781 |
HS | -0.738 |
Sen | -0.694 |
IER | -0.685 |
Secretary | -0.683 |
Token | < |
Token ID | 1279 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
!-- | +2.774 |
isphere | +2.427 |
consolidated | +2.410 |
colle | +2.322 |
cient | +2.296 |
Neg logit contributions | |
CRIP | -3.217 |
HS | -3.138 |
Sen | -3.019 |
Secretary | -3.018 |
ipal | -2.985 |
Token | literally |
Token ID | 43819 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
!-- | +2.592 |
isphere | +2.365 |
consolidated | +2.273 |
cient | +2.258 |
colle | +2.210 |
Neg logit contributions | |
CRIP | -2.031 |
HS | -1.935 |
IER | -1.849 |
Roose | -1.849 |
Sen | -1.847 |
Token | _ |
Token ID | 62 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
!-- | +2.328 |
isphere | +2.143 |
consolidated | +2.052 |
cient | +2.046 |
colle | +1.995 |
Neg logit contributions | |
CRIP | -1.920 |
HS | -1.840 |
IER | -1.761 |
Sen | -1.753 |
Roose | -1.749 |
Token | worst |
Token ID | 41430 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
!-- | +5.921 |
isphere | +5.469 |
cient | +5.241 |
consolidated | +5.121 |
colle | +4.967 |
Neg logit contributions | |
CRIP | -4.595 |
HS | -4.246 |
Roose | -4.142 |
IER | -4.125 |
Sutherland | -4.101 |
Token | _ |
Token ID | 62 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
CRIP | +0.126 |
HS | +0.123 |
Sen | +0.118 |
Secretary | +0.117 |
IER | +0.117 |
Neg logit contributions | |
!-- | -0.113 |
isphere | -0.102 |
consolidated | -0.100 |
cient | -0.096 |
colle | -0.095 |
Token | user |
Token ID | 7220 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
!-- | +2.722 |
isphere | +2.494 |
consolidated | +2.375 |
cient | +2.372 |
colle | +2.288 |
Neg logit contributions | |
CRIP | -2.286 |
HS | -2.156 |
Roose | -2.106 |
IER | -2.074 |
Sen | -2.073 |
Token | > |
Token ID | 29 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
!-- | +1.368 |
isphere | +1.235 |
consolidated | +1.191 |
cient | +1.163 |
colle | +1.134 |
Neg logit contributions | |
CRIP | -1.564 |
HS | -1.510 |
Sen | -1.457 |
IER | -1.445 |
Secretary | -1.444 |
Token | lol |
Token ID | 19462 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
!-- | +3.629 |
isphere | +3.248 |
consolidated | +3.183 |
colle | +3.088 |
cient | +3.023 |
Neg logit contributions | |
CRIP | -3.977 |
HS | -3.848 |
Sen | -3.717 |
Secretary | -3.708 |
IER | -3.690 |
Token | 12 |
Token ID | 1105 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
!-- | +1.356 |
isphere | +1.231 |
consolidated | +1.204 |
cient | +1.177 |
colle | +1.146 |
Neg logit contributions | |
CRIP | -1.034 |
HS | -0.993 |
Sen | -0.951 |
IER | -0.946 |
ipal | -0.943 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
CRIP | +1.979 |
HS | +1.936 |
Sen | +1.865 |
Secretary | +1.827 |
IER | +1.822 |
Neg logit contributions | |
!-- | -2.044 |
isphere | -1.891 |
consolidated | -1.828 |
colle | -1.766 |
cient | -1.766 |
Token |
|
Token ID | 198 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
CRIP | +1.308 |
HS | +1.276 |
Sen | +1.225 |
Secretary | +1.202 |
Roose | +1.194 |
Neg logit contributions | |
!-- | -1.504 |
isphere | -1.388 |
consolidated | -1.348 |
cient | -1.301 |
colle | -1.297 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
HS | +1.845 |
CRIP | +1.840 |
Sen | +1.772 |
Secretary | +1.725 |
Quotes | +1.689 |
Neg logit contributions | |
!-- | -2.506 |
isphere | -2.399 |
colle | -2.325 |
consolidated | -2.313 |
cient | -2.210 |
Token | - |
Token ID | 12 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
CRIP | +0.741 |
HS | +0.723 |
Sen | +0.695 |
Secretary | +0.683 |
IER | +0.677 |
Neg logit contributions | |
!-- | -0.926 |
isphere | -0.852 |
consolidated | -0.838 |
colle | -0.806 |
cient | -0.804 |
Token | Daniel |
Token ID | 7806 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
!-- | +0.253 |
isphere | +0.232 |
consolidated | +0.227 |
cient | +0.219 |
colle | +0.218 |
Neg logit contributions | |
CRIP | -0.216 |
HS | -0.210 |
Sen | -0.202 |
Secretary | -0.199 |
IER | -0.198 |
Token | C |
Token ID | 327 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
CRIP | +1.764 |
HS | +1.704 |
Sen | +1.625 |
Roose | +1.596 |
Secretary | +1.584 |
Neg logit contributions | |
!-- | -2.894 |
isphere | -2.706 |
consolidated | -2.629 |
cient | -2.588 |
colle | -2.564 |
Token | . |
Token ID | 13 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
!-- | +0.530 |
isphere | +0.479 |
consolidated | +0.467 |
cient | +0.449 |
colle | +0.447 |
Neg logit contributions | |
CRIP | -0.585 |
HS | -0.569 |
Sen | -0.549 |
Secretary | -0.542 |
IER | -0.542 |
Token | Peterson |
Token ID | 18914 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
CRIP | +0.454 |
HS | +0.441 |
Sen | +0.423 |
Secretary | +0.416 |
IER | +0.415 |
Neg logit contributions | |
!-- | -0.551 |
isphere | -0.505 |
consolidated | -0.493 |
cient | -0.478 |
colle | -0.475 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
CRIP | +2.777 |
HS | +2.726 |
Sen | +2.624 |
Secretary | +2.577 |
Roose | +2.560 |
Neg logit contributions | |
!-- | -2.812 |
isphere | -2.598 |
consolidated | -2.484 |
cient | -2.416 |
colle | -2.386 |
Token | in |
Token ID | 287 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
CRIP | +1.474 |
HS | +1.440 |
Sen | +1.389 |
Secretary | +1.368 |
Roose | +1.359 |
Neg logit contributions | |
!-- | -1.569 |
isphere | -1.440 |
consolidated | -1.388 |
cient | -1.344 |
colle | -1.327 |
Token | : |
Token ID | 25 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
!-- | +0.977 |
isphere | +0.889 |
consolidated | +0.868 |
cient | +0.839 |
colle | +0.831 |
Neg logit contributions | |
CRIP | -0.904 |
HS | -0.877 |
Sen | -0.843 |
Secretary | -0.832 |
IER | -0.831 |
Token | Lic |
Token ID | 26656 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
CRIP | +0.935 |
HS | +0.920 |
Sen | +0.880 |
Secretary | +0.865 |
IER | +0.860 |
Neg logit contributions | |
!-- | -1.200 |
isphere | -1.111 |
consolidated | -1.083 |
colle | -1.046 |
cient | -1.045 |
Token | enses |
Token ID | 4541 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
CRIP | +2.978 |
HS | +2.941 |
Sen | +2.837 |
Secretary | +2.789 |
ipal | +2.765 |
Neg logit contributions | |
!-- | -2.754 |
isphere | -2.513 |
consolidated | -2.444 |
colle | -2.362 |
cient | -2.314 |
Token | and |
Token ID | 290 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
CRIP | +2.576 |
HS | +2.527 |
Sen | +2.429 |
Secretary | +2.397 |
IER | +2.389 |
Neg logit contributions | |
!-- | -2.620 |
isphere | -2.419 |
consolidated | -2.294 |
colle | -2.252 |
cient | -2.247 |
Token | acc |
Token ID | 697 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
!-- | +0.064 |
isphere | +0.059 |
consolidated | +0.057 |
cient | +0.055 |
colle | +0.055 |
Neg logit contributions | |
CRIP | -0.058 |
HS | -0.056 |
Sen | -0.054 |
Secretary | -0.053 |
IER | -0.053 |
Token | reditation |
Token ID | 42845 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
CRIP | +1.324 |
HS | +1.311 |
Sen | +1.251 |
Secretary | +1.233 |
ipal | +1.223 |
Neg logit contributions | |
!-- | -1.697 |
isphere | -1.568 |
consolidated | -1.524 |
colle | -1.478 |
cient | -1.466 |
Token | aren |
Token ID | 3588 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
CRIP | +3.183 |
HS | +3.130 |
Sen | +3.030 |
Secretary | +2.989 |
IER | +2.967 |
Neg logit contributions | |
!-- | -3.282 |
isphere | -3.059 |
consolidated | -2.868 |
cient | -2.857 |
colle | -2.828 |
Token | � |
Token ID | 447 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
HS | +1.178 |
CRIP | +1.169 |
Sen | +1.094 |
Secretary | +1.071 |
IER | +1.060 |
Neg logit contributions | |
!-- | -2.390 |
isphere | -2.290 |
colle | -2.250 |
consolidated | -2.242 |
cient | -2.147 |
Token | � |
Token ID | 247 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
CRIP | +0.271 |
HS | +0.265 |
Sen | +0.252 |
Secretary | +0.249 |
IER | +0.248 |
Neg logit contributions | |
!-- | -0.364 |
isphere | -0.335 |
consolidated | -0.328 |
colle | -0.317 |
cient | -0.317 |
Token | t |
Token ID | 83 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
CRIP | +0.208 |
HS | +0.203 |
Sen | +0.194 |
Secretary | +0.192 |
IER | +0.191 |
Neg logit contributions | |
!-- | -0.239 |
isphere | -0.219 |
consolidated | -0.214 |
cient | -0.207 |
colle | -0.206 |
Token | required |
Token ID | 2672 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
CRIP | +0.412 |
HS | +0.403 |
Sen | +0.387 |
Secretary | +0.382 |
IER | +0.380 |
Neg logit contributions | |
!-- | -0.449 |
isphere | -0.412 |
consolidated | -0.399 |
cient | -0.386 |
colle | -0.386 |
Token | the |
Token ID | 262 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
CRIP | +0.334 |
HS | +0.324 |
Sen | +0.311 |
Secretary | +0.307 |
IER | +0.306 |
Neg logit contributions | |
!-- | -0.390 |
isphere | -0.357 |
consolidated | -0.349 |
cient | -0.337 |
colle | -0.335 |
Token | proposed |
Token ID | 5150 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
!-- | +0.564 |
isphere | +0.514 |
consolidated | +0.506 |
cient | +0.486 |
colle | +0.483 |
Neg logit contributions | |
CRIP | -0.545 |
HS | -0.528 |
Sen | -0.509 |
Secretary | -0.502 |
IER | -0.502 |
Token | museum |
Token ID | 13257 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
!-- | +0.047 |
isphere | +0.043 |
consolidated | +0.042 |
cient | +0.041 |
colle | +0.040 |
Neg logit contributions | |
CRIP | -0.041 |
HS | -0.040 |
Sen | -0.038 |
Secretary | -0.038 |
IER | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
CRIP | +1.220 |
HS | +1.191 |
Sen | +1.146 |
Secretary | +1.131 |
IER | +1.127 |
Neg logit contributions | |
!-- | -1.251 |
isphere | -1.136 |
consolidated | -1.102 |
cient | -1.069 |
colle | -1.061 |
Token | location |
Token ID | 4067 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
!-- | +0.988 |
isphere | +0.902 |
consolidated | +0.894 |
colle | +0.850 |
cient | +0.850 |
Neg logit contributions | |
CRIP | -0.923 |
HS | -0.894 |
Sen | -0.859 |
Secretary | -0.850 |
IER | -0.846 |
Token | with |
Token ID | 351 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
CRIP | +1.019 |
HS | +0.994 |
Sen | +0.958 |
Secretary | +0.944 |
IER | +0.943 |
Neg logit contributions | |
!-- | -1.028 |
isphere | -0.935 |
consolidated | -0.908 |
cient | -0.878 |
colle | -0.874 |
Token | much |
Token ID | 881 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
CRIP | +2.230 |
HS | +2.190 |
Sen | +2.100 |
Roose | +2.070 |
IER | +2.062 |
Neg logit contributions | |
!-- | -2.342 |
isphere | -2.139 |
consolidated | -2.031 |
cient | -2.004 |
colle | -1.985 |
Token | higher |
Token ID | 2440 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
CRIP | +0.209 |
HS | +0.204 |
Sen | +0.197 |
Secretary | +0.194 |
IER | +0.194 |
Neg logit contributions | |
!-- | -0.207 |
isphere | -0.188 |
consolidated | -0.183 |
cient | -0.177 |
colle | -0.176 |
Token | visibility |
Token ID | 20742 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
CRIP | +0.226 |
HS | +0.219 |
Sen | +0.210 |
IER | +0.206 |
Secretary | +0.206 |
Neg logit contributions | |
!-- | -0.290 |
isphere | -0.268 |
consolidated | -0.259 |
cient | -0.254 |
colle | -0.251 |
Token | than |
Token ID | 621 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
CRIP | +0.169 |
HS | +0.165 |
Sen | +0.159 |
Secretary | +0.157 |
IER | +0.157 |
Neg logit contributions | |
!-- | -0.153 |
isphere | -0.138 |
consolidated | -0.134 |
cient | -0.129 |
colle | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
CRIP | +0.604 |
HS | +0.594 |
Sen | +0.568 |
Secretary | +0.559 |
IER | +0.557 |
Neg logit contributions | |
!-- | -0.625 |
isphere | -0.572 |
consolidated | -0.551 |
cient | -0.537 |
colle | -0.534 |
Token | р |
Token ID | 21169 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
CRIP | +0.310 |
HS | +0.302 |
Sen | +0.289 |
Secretary | +0.285 |
IER | +0.284 |
Neg logit contributions | |
!-- | -0.376 |
isphere | -0.345 |
consolidated | -0.338 |
cient | -0.326 |
colle | -0.325 |
Token | а |
Token ID | 16142 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
CRIP | +1.561 |
HS | +1.521 |
Sen | +1.451 |
Secretary | +1.427 |
IER | +1.424 |
Neg logit contributions | |
!-- | -1.970 |
isphere | -1.819 |
consolidated | -1.778 |
colle | -1.716 |
cient | -1.700 |
Token | н |
Token ID | 22177 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
CRIP | +3.476 |
HS | +3.427 |
Sen | +3.230 |
IER | +3.169 |
Secretary | +3.160 |
Neg logit contributions | |
!-- | -4.428 |
isphere | -4.177 |
consolidated | -4.006 |
colle | -3.868 |
cient | -3.818 |
Token | е |
Token ID | 16843 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
CRIP | +1.979 |
HS | +1.933 |
Sen | +1.833 |
IER | +1.814 |
Secretary | +1.804 |
Neg logit contributions | |
!-- | -2.682 |
isphere | -2.501 |
consolidated | -2.425 |
cient | -2.344 |
colle | -2.341 |
Token | н |
Token ID | 22177 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
CRIP | +0.838 |
HS | +0.818 |
Sen | +0.785 |
IER | +0.772 |
Secretary | +0.772 |
Neg logit contributions | |
!-- | -0.882 |
isphere | -0.811 |
consolidated | -0.785 |
cient | -0.758 |
colle | -0.753 |
Token | и |
Token ID | 18849 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
CRIP | +2.358 |
HS | +2.328 |
Sen | +2.226 |
IER | +2.188 |
Secretary | +2.183 |
Neg logit contributions | |
!-- | -2.716 |
isphere | -2.520 |
consolidated | -2.432 |
cient | -2.339 |
colle | -2.338 |
Token | я |
Token ID | 40623 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
CRIP | +1.959 |
HS | +1.917 |
Sen | +1.824 |
IER | +1.790 |
Secretary | +1.788 |
Neg logit contributions | |
!-- | -2.666 |
isphere | -2.474 |
consolidated | -2.410 |
cient | -2.339 |
colle | -2.321 |
Token | . |
Token ID | 13 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
CRIP | +1.017 |
HS | +0.993 |
Sen | +0.957 |
Secretary | +0.943 |
IER | +0.943 |
Neg logit contributions | |
!-- | -0.881 |
isphere | -0.804 |
consolidated | -0.775 |
cient | -0.745 |
colle | -0.740 |
Token | � |
Token ID | 12466 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
!-- | +0.564 |
isphere | +0.508 |
consolidated | +0.498 |
cient | +0.480 |
colle | +0.476 |
Neg logit contributions | |
CRIP | -0.601 |
HS | -0.586 |
Sen | -0.564 |
Secretary | -0.558 |
IER | -0.557 |
Token | � |
Token ID | 250 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
CRIP | +0.642 |
HS | +0.625 |
Sen | +0.599 |
Secretary | +0.592 |
IER | +0.588 |
Neg logit contributions | |
!-- | -0.693 |
isphere | -0.635 |
consolidated | -0.618 |
cient | -0.595 |
colle | -0.594 |
Token | н |
Token ID | 22177 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
CRIP | +1.362 |
HS | +1.336 |
Sen | +1.282 |
IER | +1.261 |
Secretary | +1.256 |
Neg logit contributions | |
!-- | -1.568 |
isphere | -1.442 |
consolidated | -1.414 |
colle | -1.360 |
cient | -1.348 |
Token | decades |
Token ID | 4647 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
!-- | +0.637 |
isphere | +0.582 |
consolidated | +0.572 |
colle | +0.549 |
cient | +0.549 |
Neg logit contributions | |
CRIP | -0.567 |
HS | -0.550 |
Sen | -0.526 |
IER | -0.520 |
Secretary | -0.520 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
CRIP | +0.406 |
HS | +0.397 |
Sen | +0.383 |
Secretary | +0.378 |
IER | +0.377 |
Neg logit contributions | |
!-- | -0.357 |
isphere | -0.323 |
consolidated | -0.313 |
cient | -0.302 |
colle | -0.300 |
Token | it |
Token ID | 340 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
CRIP | +0.886 |
HS | +0.870 |
Sen | +0.835 |
Secretary | +0.824 |
Roose | +0.821 |
Neg logit contributions | |
!-- | -0.914 |
isphere | -0.835 |
consolidated | -0.804 |
cient | -0.784 |
colle | -0.777 |
Token | is |
Token ID | 318 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
CRIP | +0.527 |
HS | +0.518 |
Sen | +0.498 |
Secretary | +0.491 |
IER | +0.488 |
Neg logit contributions | |
!-- | -0.535 |
isphere | -0.489 |
consolidated | -0.472 |
cient | -0.458 |
colle | -0.456 |
Token | worth |
Token ID | 2861 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
CRIP | +0.388 |
HS | +0.379 |
Sen | +0.363 |
Secretary | +0.358 |
IER | +0.357 |
Neg logit contributions | |
!-- | -0.424 |
isphere | -0.388 |
consolidated | -0.377 |
cient | -0.365 |
colle | -0.363 |
Token | putting |
Token ID | 5137 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
CRIP | +1.284 |
HS | +1.259 |
Sen | +1.219 |
Secretary | +1.197 |
Roose | +1.192 |
Neg logit contributions | |
!-- | -1.382 |
isphere | -1.259 |
consolidated | -1.218 |
cient | -1.187 |
colle | -1.178 |
Token | such |
Token ID | 884 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
CRIP | +2.778 |
HS | +2.751 |
Sen | +2.650 |
Roose | +2.614 |
Secretary | +2.607 |
Neg logit contributions | |
!-- | -2.973 |
isphere | -2.723 |
consolidated | -2.586 |
cient | -2.555 |
colle | -2.521 |
Token | a |
Token ID | 257 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
CRIP | +1.247 |
HS | +1.219 |
Sen | +1.174 |
Secretary | +1.155 |
Roose | +1.151 |
Neg logit contributions | |
!-- | -1.327 |
isphere | -1.213 |
consolidated | -1.166 |
cient | -1.136 |
colle | -1.128 |
Token | claim |
Token ID | 1624 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
!-- | +0.239 |
isphere | +0.217 |
consolidated | +0.211 |
cient | +0.204 |
colle | +0.203 |
Neg logit contributions | |
CRIP | -0.240 |
HS | -0.234 |
Sen | -0.226 |
Secretary | -0.223 |
IER | -0.222 |
Token | in |
Token ID | 287 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
CRIP | +0.697 |
HS | +0.679 |
Sen | +0.651 |
Secretary | +0.641 |
IER | +0.640 |
Neg logit contributions | |
!-- | -0.827 |
isphere | -0.761 |
consolidated | -0.740 |
cient | -0.718 |
colle | -0.716 |
Token | perspective |
Token ID | 6650 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
CRIP | +1.260 |
HS | +1.233 |
Sen | +1.189 |
Secretary | +1.172 |
IER | +1.165 |
Neg logit contributions | |
!-- | -1.215 |
isphere | -1.104 |
consolidated | -1.066 |
cient | -1.035 |
colle | -1.027 |
Token | didnt |
Token ID | 42547 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
!-- | +0.247 |
isphere | +0.226 |
consolidated | +0.220 |
cient | +0.213 |
colle | +0.212 |
Neg logit contributions | |
CRIP | -0.226 |
HS | -0.220 |
Sen | -0.211 |
Secretary | -0.208 |
IER | -0.208 |
Token | get |
Token ID | 651 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
CRIP | +0.370 |
HS | +0.366 |
Sen | +0.347 |
Secretary | +0.342 |
IER | +0.340 |
Neg logit contributions | |
!-- | -0.443 |
isphere | -0.412 |
consolidated | -0.396 |
cient | -0.386 |
colle | -0.385 |
Token | a |
Token ID | 257 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
!-- | +0.161 |
isphere | +0.147 |
consolidated | +0.143 |
cient | +0.139 |
colle | +0.138 |
Neg logit contributions | |
CRIP | -0.150 |
HS | -0.146 |
Sen | -0.140 |
Secretary | -0.138 |
IER | -0.138 |
Token | next |
Token ID | 1306 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
!-- | +0.886 |
isphere | +0.801 |
consolidated | +0.785 |
cient | +0.751 |
colle | +0.750 |
Neg logit contributions | |
CRIP | -0.947 |
HS | -0.922 |
Sen | -0.890 |
Secretary | -0.878 |
IER | -0.877 |
Token | round |
Token ID | 2835 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
!-- | +0.807 |
isphere | +0.732 |
consolidated | +0.713 |
cient | +0.687 |
colle | +0.683 |
Neg logit contributions | |
CRIP | -0.857 |
HS | -0.835 |
Sen | -0.805 |
Secretary | -0.795 |
IER | -0.793 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
CRIP | +0.552 |
HS | +0.540 |
Sen | +0.517 |
Secretary | +0.512 |
IER | +0.511 |
Neg logit contributions | |
!-- | -0.545 |
isphere | -0.496 |
consolidated | -0.483 |
cient | -0.466 |
colle | -0.465 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
!-- | +0.140 |
isphere | +0.128 |
consolidated | +0.125 |
cient | +0.120 |
colle | +0.120 |
Neg logit contributions | |
CRIP | -0.130 |
HS | -0.127 |
Sen | -0.122 |
Secretary | -0.120 |
IER | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
CRIP | +0.196 |
HS | +0.192 |
Sen | +0.184 |
Secretary | +0.181 |
IER | +0.180 |
Neg logit contributions | |
!-- | -0.232 |
isphere | -0.215 |
consolidated | -0.209 |
colle | -0.204 |
cient | -0.202 |
Token | Off |
Token ID | 9362 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
CRIP | +0.119 |
HS | +0.115 |
Sen | +0.110 |
Secretary | +0.108 |
IER | +0.108 |
Neg logit contributions | |
!-- | -0.162 |
isphere | -0.150 |
consolidated | -0.147 |
cient | -0.142 |
colle | -0.142 |
Token | er |
Token ID | 263 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
CRIP | +0.360 |
HS | +0.354 |
Sen | +0.342 |
Secretary | +0.335 |
ipal | +0.334 |
Neg logit contributions | |
!-- | -0.395 |
isphere | -0.363 |
consolidated | -0.355 |
colle | -0.346 |
cient | -0.340 |
Token | : |
Token ID | 25 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
!-- | +0.305 |
isphere | +0.276 |
consolidated | +0.270 |
cient | +0.259 |
colle | +0.258 |
Neg logit contributions | |
CRIP | -0.306 |
HS | -0.296 |
Sen | -0.286 |
Secretary | -0.284 |
Roose | -0.282 |
Token | prescribed |
Token ID | 14798 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
CRIP | +1.263 |
HS | +1.251 |
Sen | +1.188 |
Secretary | +1.165 |
IER | +1.152 |
Neg logit contributions | |
!-- | -1.567 |
isphere | -1.456 |
consolidated | -1.401 |
colle | -1.366 |
cient | -1.353 |
Token | , |
Token ID | 11 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
CRIP | +0.518 |
HS | +0.505 |
Sen | +0.485 |
Secretary | +0.478 |
IER | +0.477 |
Neg logit contributions | |
!-- | -0.553 |
isphere | -0.506 |
consolidated | -0.492 |
cient | -0.476 |
colle | -0.473 |
Token | and |
Token ID | 290 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
!-- | +0.577 |
isphere | +0.512 |
consolidated | +0.500 |
cient | +0.476 |
colle | +0.473 |
Neg logit contributions | |
CRIP | -0.813 |
HS | -0.793 |
Sen | -0.767 |
Secretary | -0.760 |
IER | -0.760 |
Token | often |
Token ID | 1690 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
!-- | +0.532 |
isphere | +0.478 |
consolidated | +0.469 |
cient | +0.448 |
colle | +0.446 |
Neg logit contributions | |
CRIP | -0.615 |
HS | -0.597 |
Sen | -0.576 |
Secretary | -0.570 |
IER | -0.570 |
Token | to |
Token ID | 284 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
!-- | +0.111 |
isphere | +0.101 |
consolidated | +0.099 |
cient | +0.095 |
colle | +0.095 |
Neg logit contributions | |
CRIP | -0.104 |
HS | -0.101 |
Sen | -0.097 |
Secretary | -0.096 |
IER | -0.095 |
Token | opioids |
Token ID | 39032 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
CRIP | +0.893 |
HS | +0.874 |
Sen | +0.836 |
Secretary | +0.821 |
IER | +0.818 |
Neg logit contributions | |
!-- | -0.975 |
isphere | -0.894 |
consolidated | -0.861 |
cient | -0.838 |
colle | -0.832 |
Token | illicit |
Token ID | 24271 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
CRIP | +0.311 |
HS | +0.304 |
Sen | +0.292 |
Secretary | +0.288 |
IER | +0.287 |
Neg logit contributions | |
!-- | -0.306 |
isphere | -0.279 |
consolidated | -0.270 |
cient | -0.261 |
colle | -0.260 |
Token | ly |
Token ID | 306 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
!-- | +0.027 |
isphere | +0.025 |
consolidated | +0.024 |
cient | +0.023 |
colle | +0.023 |
Neg logit contributions | |
CRIP | -0.029 |
HS | -0.028 |
Sen | -0.027 |
Secretary | -0.027 |
IER | -0.026 |
Token | distributed |
Token ID | 9387 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
!-- | +0.538 |
isphere | +0.487 |
consolidated | +0.470 |
cient | +0.453 |
colle | +0.451 |
Neg logit contributions | |
CRIP | -0.630 |
HS | -0.616 |
Sen | -0.594 |
Secretary | -0.586 |
IER | -0.584 |
Token | . |
Token ID | 13 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
!-- | +1.508 |
isphere | +1.350 |
consolidated | +1.331 |
cient | +1.273 |
colle | +1.259 |
Neg logit contributions | |
CRIP | -1.682 |
HS | -1.633 |
Sen | -1.578 |
Secretary | -1.564 |
IER | -1.558 |
Token | In |
Token ID | 554 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
!-- | +0.683 |
isphere | +0.620 |
consolidated | +0.606 |
cient | +0.586 |
colle | +0.581 |
Neg logit contributions | |
CRIP | -0.650 |
HS | -0.631 |
Sen | -0.606 |
Secretary | -0.599 |
IER | -0.599 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
!-- | +0.446 |
isphere | +0.405 |
consolidated | +0.395 |
cient | +0.381 |
colle | +0.379 |
Neg logit contributions | |
CRIP | -0.418 |
HS | -0.408 |
Sen | -0.391 |
Secretary | -0.387 |
IER | -0.385 |
Token | � |
Token ID | 447 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
!-- | +1.374 |
isphere | +1.247 |
consolidated | +1.221 |
cient | +1.183 |
colle | +1.172 |
Neg logit contributions | |
CRIP | -1.222 |
HS | -1.187 |
Sen | -1.136 |
Secretary | -1.123 |
IER | -1.121 |
Token | � |
Token ID | 251 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
!-- | +1.892 |
isphere | +1.712 |
consolidated | +1.675 |
cient | +1.629 |
colle | +1.621 |
Neg logit contributions | |
CRIP | -1.727 |
HS | -1.661 |
Sen | -1.593 |
IER | -1.580 |
ipal | -1.577 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
!-- | +1.134 |
isphere | +1.026 |
consolidated | +1.005 |
cient | +0.972 |
colle | +0.963 |
Neg logit contributions | |
CRIP | -1.060 |
HS | -1.030 |
Sen | -0.987 |
Secretary | -0.978 |
IER | -0.973 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
!-- | +0.866 |
isphere | +0.781 |
consolidated | +0.765 |
cient | +0.742 |
colle | +0.725 |
Neg logit contributions | |
CRIP | -0.801 |
HS | -0.774 |
Sen | -0.743 |
IER | -0.736 |
Secretary | -0.735 |
Token | A |
Token ID | 32 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
!-- | +0.918 |
isphere | +0.832 |
consolidated | +0.812 |
cient | +0.796 |
colle | +0.780 |
Neg logit contributions | |
CRIP | -0.708 |
HS | -0.681 |
Roose | -0.647 |
Sen | -0.647 |
ipal | -0.647 |
Token | high |
Token ID | 1029 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
!-- | +0.233 |
isphere | +0.213 |
consolidated | +0.207 |
cient | +0.200 |
colle | +0.198 |
Neg logit contributions | |
CRIP | -0.226 |
HS | -0.221 |
Sen | -0.212 |
Secretary | -0.209 |
IER | -0.209 |
Token | school |
Token ID | 1524 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
!-- | +0.087 |
isphere | +0.079 |
consolidated | +0.077 |
cient | +0.074 |
colle | +0.074 |
Neg logit contributions | |
CRIP | -0.081 |
HS | -0.078 |
Sen | -0.075 |
Secretary | -0.074 |
IER | -0.074 |
Token | wide |
Token ID | 3094 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
!-- | +0.314 |
isphere | +0.288 |
consolidated | +0.281 |
cient | +0.271 |
colle | +0.270 |
Neg logit contributions | |
CRIP | -0.278 |
HS | -0.271 |
Sen | -0.260 |
Secretary | -0.256 |
IER | -0.256 |
Token | receiver |
Token ID | 9733 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
CRIP | +0.737 |
HS | +0.723 |
Sen | +0.689 |
IER | +0.674 |
Secretary | +0.674 |
Neg logit contributions | |
!-- | -1.143 |
isphere | -1.070 |
consolidated | -1.039 |
cient | -1.011 |
colle | -1.005 |
Token | in |
Token ID | 287 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
CRIP | +0.015 |
HS | +0.015 |
Sen | +0.014 |
Secretary | +0.014 |
IER | +0.014 |
Neg logit contributions | |
!-- | -0.016 |
isphere | -0.015 |
consolidated | -0.015 |
cient | -0.014 |
colle | -0.014 |
Token | satisfied |
Token ID | 11378 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
!-- | +2.045 |
isphere | +1.882 |
consolidated | +1.859 |
cient | +1.799 |
colle | +1.787 |
Neg logit contributions | |
CRIP | -1.393 |
HS | -1.341 |
Sen | -1.280 |
Secretary | -1.258 |
IER | -1.255 |
Token | . |
Token ID | 13 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
!-- | +1.344 |
isphere | +1.209 |
consolidated | +1.197 |
cient | +1.146 |
colle | +1.136 |
Neg logit contributions | |
CRIP | -1.283 |
HS | -1.241 |
Sen | -1.191 |
Roose | -1.175 |
Secretary | -1.174 |
Token | � |
Token ID | 447 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
CRIP | +0.611 |
HS | +0.597 |
Sen | +0.572 |
Secretary | +0.563 |
IER | +0.561 |
Neg logit contributions | |
!-- | -0.731 |
isphere | -0.672 |
consolidated | -0.654 |
cient | -0.633 |
colle | -0.631 |
Token | � |
Token ID | 251 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
!-- | +0.410 |
isphere | +0.374 |
consolidated | +0.365 |
cient | +0.353 |
colle | +0.351 |
Neg logit contributions | |
CRIP | -0.376 |
HS | -0.364 |
Sen | -0.350 |
Secretary | -0.345 |
IER | -0.344 |
Token |
|
Token ID | 198 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
!-- | +0.269 |
isphere | +0.245 |
consolidated | +0.240 |
cient | +0.232 |
colle | +0.230 |
Neg logit contributions | |
CRIP | -0.239 |
HS | -0.231 |
Sen | -0.222 |
Secretary | -0.219 |
IER | -0.219 |
Token |
|
Token ID | 198 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
CRIP | +0.473 |
HS | +0.464 |
Sen | +0.445 |
Secretary | +0.438 |
IER | +0.435 |
Neg logit contributions | |
!-- | -0.565 |
isphere | -0.524 |
consolidated | -0.509 |
colle | -0.496 |
cient | -0.490 |
Token | The |
Token ID | 464 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
CRIP | +0.403 |
HS | +0.392 |
Sen | +0.376 |
Secretary | +0.370 |
IER | +0.369 |
Neg logit contributions | |
!-- | -0.507 |
isphere | -0.466 |
consolidated | -0.456 |
cient | -0.441 |
colle | -0.439 |
Token | rest |
Token ID | 1334 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
CRIP | +0.187 |
HS | +0.184 |
Sen | +0.177 |
Secretary | +0.175 |
IER | +0.175 |
Neg logit contributions | |
!-- | -0.150 |
isphere | -0.135 |
consolidated | -0.130 |
cient | -0.125 |
colle | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
!-- | +1.120 |
isphere | +1.021 |
consolidated | +1.006 |
cient | +0.962 |
colle | +0.955 |
Neg logit contributions | |
CRIP | -1.005 |
HS | -0.970 |
Sen | -0.932 |
IER | -0.920 |
Secretary | -0.920 |
Token | nearly |
Token ID | 3016 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
CRIP | +0.103 |
HS | +0.100 |
Sen | +0.096 |
Secretary | +0.094 |
IER | +0.094 |
Neg logit contributions | |
!-- | -0.137 |
isphere | -0.126 |
consolidated | -0.123 |
cient | -0.120 |
colle | -0.119 |
Token | two |
Token ID | 734 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
CRIP | +0.946 |
HS | +0.936 |
Sen | +0.894 |
Secretary | +0.879 |
Roose | +0.872 |
Neg logit contributions | |
!-- | -1.224 |
isphere | -1.139 |
consolidated | -1.091 |
cient | -1.070 |
colle | -1.061 |
Token | . |
Token ID | 13 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
!-- | +0.548 |
isphere | +0.496 |
consolidated | +0.483 |
cient | +0.464 |
colle | +0.463 |
Neg logit contributions | |
CRIP | -0.591 |
HS | -0.576 |
Sen | -0.555 |
Secretary | -0.548 |
IER | -0.547 |
Token | We |
Token ID | 775 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
CRIP | +0.719 |
HS | +0.706 |
Sen | +0.681 |
Secretary | +0.672 |
Roose | +0.670 |
Neg logit contributions | |
!-- | -0.655 |
isphere | -0.603 |
consolidated | -0.583 |
colle | -0.561 |
cient | -0.557 |
Token | went |
Token ID | 1816 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
!-- | +1.026 |
isphere | +0.940 |
consolidated | +0.924 |
cient | +0.891 |
colle | +0.887 |
Neg logit contributions | |
CRIP | -0.794 |
HS | -0.768 |
Sen | -0.736 |
Secretary | -0.726 |
IER | -0.725 |
Token | to |
Token ID | 284 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
!-- | +0.194 |
isphere | +0.177 |
consolidated | +0.173 |
cient | +0.167 |
colle | +0.166 |
Neg logit contributions | |
CRIP | -0.180 |
HS | -0.175 |
Sen | -0.168 |
Secretary | -0.166 |
IER | -0.166 |
Token | a |
Token ID | 257 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
!-- | +0.630 |
isphere | +0.571 |
consolidated | +0.555 |
cient | +0.535 |
colle | +0.531 |
Neg logit contributions | |
CRIP | -0.681 |
HS | -0.665 |
Sen | -0.640 |
Secretary | -0.632 |
IER | -0.631 |
Token | room |
Token ID | 2119 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
!-- | +0.113 |
isphere | +0.102 |
consolidated | +0.100 |
cient | +0.096 |
colle | +0.096 |
Neg logit contributions | |
CRIP | -0.115 |
HS | -0.112 |
Sen | -0.108 |
Secretary | -0.106 |
IER | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
!-- | +0.177 |
isphere | +0.161 |
consolidated | +0.157 |
cient | +0.151 |
colle | +0.150 |
Neg logit contributions | |
CRIP | -0.181 |
HS | -0.176 |
Sen | -0.169 |
Secretary | -0.167 |
IER | -0.167 |
Token | and |
Token ID | 290 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
!-- | +0.077 |
isphere | +0.070 |
consolidated | +0.067 |
cient | +0.065 |
colle | +0.065 |
Neg logit contributions | |
CRIP | -0.081 |
HS | -0.079 |
Sen | -0.076 |
Secretary | -0.076 |
IER | -0.075 |
Token | began |
Token ID | 2540 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
!-- | +0.478 |
isphere | +0.432 |
consolidated | +0.420 |
cient | +0.404 |
colle | +0.401 |
Neg logit contributions | |
CRIP | -0.546 |
HS | -0.534 |
Sen | -0.515 |
Secretary | -0.508 |
IER | -0.507 |
Token | with |
Token ID | 351 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
!-- | +1.415 |
isphere | +1.282 |
consolidated | +1.259 |
cient | +1.210 |
colle | +1.207 |
Neg logit contributions | |
CRIP | -1.329 |
HS | -1.295 |
Sen | -1.246 |
IER | -1.233 |
Secretary | -1.232 |
Token | a |
Token ID | 257 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
!-- | +0.338 |
isphere | +0.307 |
consolidated | +0.298 |
cient | +0.288 |
colle | +0.286 |
Neg logit contributions | |
CRIP | -0.360 |
HS | -0.351 |
Sen | -0.338 |
Secretary | -0.334 |
IER | -0.333 |
Token | called |
Token ID | 7174 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
!-- | +1.484 |
isphere | +1.378 |
consolidated | +1.348 |
cient | +1.317 |
colle | +1.298 |
Neg logit contributions | |
CRIP | -0.828 |
HS | -0.794 |
Sen | -0.748 |
IER | -0.741 |
Roose | -0.736 |
Token | ' |
Token ID | 705 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
!-- | +0.282 |
isphere | +0.256 |
consolidated | +0.247 |
cient | +0.238 |
colle | +0.236 |
Neg logit contributions | |
CRIP | -0.309 |
HS | -0.301 |
Sen | -0.291 |
Secretary | -0.287 |
IER | -0.286 |
Token | New |
Token ID | 3791 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
!-- | +0.574 |
isphere | +0.517 |
consolidated | +0.502 |
cient | +0.483 |
colle | +0.479 |
Neg logit contributions | |
CRIP | -0.679 |
HS | -0.663 |
Sen | -0.640 |
Secretary | -0.632 |
IER | -0.631 |
Token | Blood |
Token ID | 7235 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
!-- | +0.657 |
isphere | +0.598 |
consolidated | +0.583 |
cient | +0.562 |
colle | +0.559 |
Neg logit contributions | |
CRIP | -0.646 |
HS | -0.630 |
Sen | -0.605 |
Secretary | -0.597 |
IER | -0.596 |
Token | ' |
Token ID | 6 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
!-- | +1.922 |
isphere | +1.720 |
consolidated | +1.709 |
cient | +1.629 |
colle | +1.620 |
Neg logit contributions | |
CRIP | -2.296 |
HS | -2.197 |
Sen | -2.135 |
Secretary | -2.104 |
IER | -2.100 |
Token | at |
Token ID | 379 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
CRIP | +0.350 |
HS | +0.342 |
Sen | +0.329 |
Secretary | +0.324 |
IER | +0.323 |
Neg logit contributions | |
!-- | -0.358 |
isphere | -0.326 |
consolidated | -0.315 |
cient | -0.307 |
colle | -0.304 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
!-- | +1.614 |
isphere | +1.461 |
consolidated | +1.448 |
colle | +1.376 |
cient | +1.375 |
Neg logit contributions | |
CRIP | -1.827 |
HS | -1.779 |
Sen | -1.708 |
Secretary | -1.690 |
IER | -1.690 |
Token | convention |
Token ID | 9831 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
!-- | +0.860 |
isphere | +0.787 |
consolidated | +0.773 |
cient | +0.741 |
colle | +0.740 |
Neg logit contributions | |
CRIP | -0.805 |
HS | -0.782 |
Sen | -0.751 |
Secretary | -0.741 |
IER | -0.740 |
Token | , |
Token ID | 11 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
!-- | +1.583 |
isphere | +1.450 |
consolidated | +1.437 |
colle | +1.364 |
cient | +1.363 |
Neg logit contributions | |
CRIP | -1.366 |
HS | -1.321 |
Sen | -1.263 |
IER | -1.256 |
Secretary | -1.245 |
Token | the |
Token ID | 262 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
CRIP | +0.029 |
HS | +0.028 |
Sen | +0.027 |
Secretary | +0.027 |
IER | +0.027 |
Neg logit contributions | |
!-- | -0.027 |
isphere | -0.025 |
consolidated | -0.024 |
cient | -0.023 |
colle | -0.023 |
Token | Mil |
Token ID | 4460 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
!-- | +0.529 |
isphere | +0.484 |
consolidated | +0.470 |
cient | +0.455 |
colle | +0.452 |
Neg logit contributions | |
CRIP | -0.486 |
HS | -0.473 |
Sen | -0.454 |
Secretary | -0.448 |
IER | -0.447 |
Token | and |
Token ID | 290 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
!-- | +0.561 |
isphere | +0.507 |
consolidated | +0.494 |
cient | +0.474 |
colle | +0.470 |
Neg logit contributions | |
CRIP | -0.640 |
HS | -0.625 |
Sen | -0.602 |
Secretary | -0.595 |
IER | -0.594 |
Token | its |
Token ID | 663 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
!-- | +1.173 |
isphere | +1.057 |
consolidated | +1.035 |
cient | +0.989 |
colle | +0.986 |
Neg logit contributions | |
CRIP | -1.315 |
HS | -1.283 |
Sen | -1.236 |
Secretary | -1.224 |
IER | -1.221 |
Token | decision |
Token ID | 2551 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
!-- | +1.873 |
isphere | +1.691 |
consolidated | +1.674 |
cient | +1.595 |
colle | +1.593 |
Neg logit contributions | |
CRIP | -1.869 |
HS | -1.820 |
Sen | -1.748 |
Secretary | -1.733 |
IER | -1.729 |
Token | to |
Token ID | 284 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
!-- | +1.203 |
isphere | +1.093 |
consolidated | +1.080 |
cient | +1.032 |
colle | +1.025 |
Neg logit contributions | |
CRIP | -1.204 |
HS | -1.169 |
Sen | -1.121 |
Roose | -1.116 |
IER | -1.113 |
Token | give |
Token ID | 1577 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
!-- | +1.640 |
isphere | +1.485 |
consolidated | +1.469 |
cient | +1.405 |
colle | +1.402 |
Neg logit contributions | |
CRIP | -1.515 |
HS | -1.471 |
Sen | -1.415 |
Secretary | -1.402 |
IER | -1.400 |
Token | a |
Token ID | 257 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
!-- | +1.277 |
isphere | +1.151 |
consolidated | +1.135 |
cient | +1.085 |
colle | +1.077 |
Neg logit contributions | |
CRIP | -1.352 |
HS | -1.318 |
Sen | -1.270 |
Secretary | -1.257 |
IER | -1.255 |
Token | higher |
Token ID | 2440 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
!-- | +2.432 |
isphere | +2.205 |
consolidated | +2.199 |
colle | +2.085 |
cient | +2.083 |
Neg logit contributions | |
CRIP | -2.365 |
HS | -2.297 |
Sen | -2.212 |
IER | -2.186 |
Secretary | -2.185 |
Token | search |
Token ID | 2989 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
!-- | +1.992 |
isphere | +1.803 |
consolidated | +1.788 |
cient | +1.703 |
colle | +1.699 |
Neg logit contributions | |
CRIP | -1.875 |
HS | -1.824 |
Sen | -1.756 |
Secretary | -1.728 |
IER | -1.725 |
Token | engine |
Token ID | 3113 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
!-- | +2.554 |
isphere | +2.291 |
consolidated | +2.287 |
cient | +2.175 |
colle | +2.160 |
Neg logit contributions | |
CRIP | -2.508 |
HS | -2.438 |
Sen | -2.352 |
IER | -2.314 |
Secretary | -2.309 |
Token | ranking |
Token ID | 12759 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
!-- | +1.961 |
isphere | +1.768 |
consolidated | +1.756 |
colle | +1.671 |
cient | +1.665 |
Neg logit contributions | |
CRIP | -1.976 |
HS | -1.926 |
Sen | -1.853 |
Secretary | -1.827 |
IER | -1.827 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
!-- | +0.968 |
isphere | +0.878 |
consolidated | +0.861 |
cient | +0.825 |
colle | +0.821 |
Neg logit contributions | |
CRIP | -0.941 |
HS | -0.915 |
Sen | -0.880 |
Secretary | -0.867 |
IER | -0.866 |
Token | any |
Token ID | 597 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
CRIP | +0.391 |
HS | +0.380 |
Sen | +0.363 |
Secretary | +0.357 |
IER | +0.357 |
Neg logit contributions | |
!-- | -0.519 |
isphere | -0.478 |
consolidated | -0.466 |
cient | -0.453 |
colle | -0.450 |
Token | refund |
Token ID | 12929 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
!-- | +0.239 |
isphere | +0.216 |
consolidated | +0.210 |
cient | +0.203 |
colle | +0.201 |
Neg logit contributions | |
CRIP | -0.261 |
HS | -0.255 |
Sen | -0.245 |
Secretary | -0.242 |
IER | -0.242 |
Token | from |
Token ID | 422 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
CRIP | +0.910 |
HS | +0.894 |
Sen | +0.855 |
Secretary | +0.848 |
IER | +0.845 |
Neg logit contributions | |
!-- | -0.970 |
isphere | -0.886 |
consolidated | -0.855 |
cient | -0.834 |
colle | -0.831 |
Token | developer |
Token ID | 8517 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
CRIP | +0.743 |
HS | +0.717 |
Sen | +0.669 |
Secretary | +0.654 |
Roose | +0.653 |
Neg logit contributions | |
!-- | -1.754 |
isphere | -1.652 |
consolidated | -1.607 |
cient | -1.574 |
colle | -1.569 |
Token | Winter |
Token ID | 10633 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
CRIP | +0.087 |
HS | +0.085 |
Sen | +0.081 |
Secretary | +0.080 |
IER | +0.080 |
Neg logit contributions | |
!-- | -0.108 |
isphere | -0.099 |
consolidated | -0.097 |
cient | -0.093 |
colle | -0.093 |
Token | ke |
Token ID | 365 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
!-- | +0.464 |
isphere | +0.409 |
consolidated | +0.399 |
colle | +0.382 |
cient | +0.378 |
Neg logit contributions | |
CRIP | -0.706 |
HS | -0.695 |
Sen | -0.672 |
Secretary | -0.664 |
IER | -0.661 |
Token | wl |
Token ID | 40989 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
!-- | +1.932 |
isphere | +1.761 |
consolidated | +1.720 |
cient | +1.658 |
colle | +1.655 |
Neg logit contributions | |
CRIP | -1.841 |
HS | -1.796 |
Sen | -1.724 |
Secretary | -1.704 |
IER | -1.697 |
Token | Games |
Token ID | 5776 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
!-- | +1.351 |
isphere | +1.222 |
consolidated | +1.201 |
cient | +1.138 |
colle | +1.137 |
Neg logit contributions | |
CRIP | -1.410 |
HS | -1.360 |
Sen | -1.314 |
IER | -1.298 |
Secretary | -1.295 |
Token | looks |
Token ID | 3073 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
!-- | +0.291 |
isphere | +0.264 |
consolidated | +0.258 |
cient | +0.248 |
colle | +0.246 |
Neg logit contributions | |
CRIP | -0.299 |
HS | -0.291 |
Sen | -0.280 |
Secretary | -0.277 |
IER | -0.277 |
Token | remote |
Token ID | 6569 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
HS | +2.221 |
CRIP | +2.201 |
Sen | +2.106 |
IER | +2.076 |
Roose | +2.069 |
Neg logit contributions | |
!-- | -2.788 |
isphere | -2.589 |
consolidated | -2.449 |
cient | -2.434 |
colle | -2.421 |
Token | , |
Token ID | 11 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
CRIP | +1.730 |
HS | +1.691 |
Sen | +1.638 |
IER | +1.611 |
Secretary | +1.607 |
Neg logit contributions | |
!-- | -1.596 |
isphere | -1.454 |
consolidated | -1.412 |
colle | -1.363 |
cient | -1.361 |
Token | apparently |
Token ID | 5729 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
CRIP | +0.554 |
HS | +0.543 |
Sen | +0.524 |
Secretary | +0.517 |
IER | +0.516 |
Neg logit contributions | |
!-- | -0.475 |
isphere | -0.430 |
consolidated | -0.414 |
cient | -0.401 |
colle | -0.397 |
Token | mistakenly |
Token ID | 33168 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
CRIP | +1.167 |
HS | +1.149 |
Sen | +1.104 |
Secretary | +1.084 |
Roose | +1.083 |
Neg logit contributions | |
!-- | -1.352 |
isphere | -1.242 |
consolidated | -1.195 |
cient | -1.168 |
colle | -1.155 |
Token | thinking |
Token ID | 3612 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
!-- | +0.750 |
isphere | +0.682 |
consolidated | +0.670 |
cient | +0.644 |
colle | +0.639 |
Neg logit contributions | |
CRIP | -0.687 |
HS | -0.668 |
Sen | -0.640 |
Secretary | -0.632 |
IER | -0.631 |
Token | he |
Token ID | 339 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
CRIP | +1.099 |
HS | +1.086 |
Sen | +1.049 |
Roose | +1.037 |
Secretary | +1.034 |
Neg logit contributions | |
!-- | -0.746 |
isphere | -0.665 |
consolidated | -0.638 |
cient | -0.613 |
colle | -0.607 |
Token | was |
Token ID | 373 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
CRIP | +0.872 |
HS | +0.856 |
Sen | +0.817 |
Secretary | +0.800 |
Roose | +0.798 |
Neg logit contributions | |
!-- | -1.150 |
isphere | -1.064 |
consolidated | -1.029 |
cient | -1.005 |
colle | -1.003 |
Token | reaching |
Token ID | 8978 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
!-- | +0.338 |
isphere | +0.308 |
consolidated | +0.302 |
cient | +0.291 |
colle | +0.289 |
Neg logit contributions | |
CRIP | -0.306 |
HS | -0.297 |
Sen | -0.285 |
Secretary | -0.282 |
IER | -0.281 |
Token | for |
Token ID | 329 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
!-- | +1.975 |
isphere | +1.777 |
consolidated | +1.744 |
cient | +1.663 |
colle | +1.659 |
Neg logit contributions | |
CRIP | -2.041 |
HS | -1.975 |
Sen | -1.902 |
Secretary | -1.884 |
IER | -1.882 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
!-- | +2.346 |
isphere | +2.085 |
consolidated | +2.082 |
colle | +1.994 |
cient | +1.962 |
Neg logit contributions | |
CRIP | -2.845 |
HS | -2.763 |
Sen | -2.664 |
Secretary | -2.644 |
ipal | -2.631 |
Token | gun |
Token ID | 2485 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
!-- | +1.192 |
isphere | +1.096 |
consolidated | +1.078 |
colle | +1.038 |
cient | +1.035 |
Neg logit contributions | |
CRIP | -0.956 |
HS | -0.925 |
Sen | -0.885 |
IER | -0.873 |
Secretary | -0.872 |
Token | , |
Token ID | 11 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
!-- | +1.286 |
isphere | +1.152 |
consolidated | +1.119 |
cient | +1.075 |
colle | +1.064 |
Neg logit contributions | |
CRIP | -1.576 |
HS | -1.534 |
Sen | -1.483 |
Secretary | -1.468 |
Roose | -1.464 |
Token | fired |
Token ID | 6294 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
CRIP | +0.054 |
HS | +0.053 |
Sen | +0.051 |
Secretary | +0.050 |
IER | +0.050 |
Neg logit contributions | |
!-- | -0.065 |
isphere | -0.060 |
consolidated | -0.058 |
cient | -0.056 |
colle | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
CRIP | +1.655 |
HS | +1.620 |
Sen | +1.548 |
IER | +1.528 |
Roose | +1.516 |
Neg logit contributions | |
!-- | -1.856 |
isphere | -1.701 |
consolidated | -1.643 |
cient | -1.610 |
colle | -1.599 |
Token | damage |
Token ID | 2465 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
!-- | +0.450 |
isphere | +0.411 |
consolidated | +0.401 |
cient | +0.387 |
colle | +0.385 |
Neg logit contributions | |
CRIP | -0.408 |
HS | -0.398 |
Sen | -0.381 |
Secretary | -0.376 |
IER | -0.376 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
!-- | +1.229 |
isphere | +1.118 |
consolidated | +1.088 |
cient | +1.051 |
colle | +1.044 |
Neg logit contributions | |
CRIP | -1.220 |
HS | -1.189 |
Sen | -1.143 |
Secretary | -1.129 |
IER | -1.127 |
Token | destruction |
Token ID | 8166 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
CRIP | +1.012 |
HS | +0.992 |
Sen | +0.952 |
IER | +0.935 |
Secretary | +0.930 |
Neg logit contributions | |
!-- | -1.095 |
isphere | -1.001 |
consolidated | -0.962 |
cient | -0.942 |
colle | -0.934 |
Token | of |
Token ID | 286 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
CRIP | +0.488 |
HS | +0.480 |
Sen | +0.457 |
Roose | +0.452 |
IER | +0.450 |
Neg logit contributions | |
!-- | -0.498 |
isphere | -0.457 |
consolidated | -0.439 |
cient | -0.429 |
colle | -0.424 |
Token | twin |
Token ID | 15203 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
CRIP | +0.326 |
HS | +0.320 |
Sen | +0.305 |
Roose | +0.301 |
IER | +0.300 |
Neg logit contributions | |
!-- | -0.367 |
isphere | -0.336 |
consolidated | -0.324 |
cient | -0.316 |
colle | -0.312 |
Token | Gat |
Token ID | 29074 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
!-- | +2.039 |
isphere | +1.856 |
consolidated | +1.821 |
cient | +1.753 |
colle | +1.743 |
Neg logit contributions | |
CRIP | -1.945 |
HS | -1.880 |
Sen | -1.805 |
Secretary | -1.789 |
IER | -1.787 |
Token | ling |
Token ID | 1359 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
HS | +2.015 |
CRIP | +2.012 |
Sen | +1.929 |
IER | +1.897 |
Secretary | +1.891 |
Neg logit contributions | |
!-- | -1.492 |
isphere | -1.342 |
consolidated | -1.300 |
colle | -1.247 |
cient | -1.237 |
Token | guns |
Token ID | 6541 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
CRIP | +0.360 |
HS | +0.353 |
Sen | +0.333 |
IER | +0.326 |
Secretary | +0.325 |
Neg logit contributions | |
!-- | -0.583 |
isphere | -0.544 |
consolidated | -0.529 |
cient | -0.517 |
colle | -0.512 |
Token | and |
Token ID | 290 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
!-- | +0.330 |
isphere | +0.300 |
consolidated | +0.291 |
cient | +0.280 |
colle | +0.280 |
Neg logit contributions | |
CRIP | -0.366 |
HS | -0.358 |
Sen | -0.344 |
IER | -0.340 |
Secretary | -0.339 |
Token | others |
Token ID | 1854 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
CRIP | +0.466 |
HS | +0.457 |
Sen | +0.438 |
Secretary | +0.431 |
IER | +0.430 |
Neg logit contributions | |
!-- | -0.484 |
isphere | -0.440 |
consolidated | -0.427 |
cient | -0.414 |
colle | -0.410 |
Token | ing |
Token ID | 278 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
!-- | +0.277 |
isphere | +0.253 |
consolidated | +0.247 |
cient | +0.239 |
colle | +0.237 |
Neg logit contributions | |
CRIP | -0.248 |
HS | -0.242 |
Sen | -0.232 |
Secretary | -0.229 |
IER | -0.229 |
Token | LD |
Token ID | 27178 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
!-- | +1.056 |
isphere | +0.961 |
consolidated | +0.935 |
cient | +0.903 |
colle | +0.897 |
Neg logit contributions | |
CRIP | -1.045 |
HS | -1.020 |
Sen | -0.980 |
Secretary | -0.966 |
IER | -0.965 |
Token | LC |
Token ID | 5639 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
!-- | +1.409 |
isphere | +1.293 |
consolidated | +1.260 |
cient | +1.226 |
colle | +1.219 |
Neg logit contributions | |
CRIP | -1.052 |
HS | -1.035 |
Sen | -0.990 |
IER | -0.961 |
Secretary | -0.960 |
Token | with |
Token ID | 351 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
!-- | +1.847 |
isphere | +1.682 |
consolidated | +1.653 |
cient | +1.575 |
colle | +1.573 |
Neg logit contributions | |
CRIP | -1.758 |
HS | -1.697 |
Sen | -1.631 |
Secretary | -1.627 |
IER | -1.609 |
Token | Peter |
Token ID | 5613 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
CRIP | +0.342 |
HS | +0.334 |
Sen | +0.321 |
IER | +0.316 |
Secretary | +0.315 |
Neg logit contributions | |
!-- | -0.370 |
isphere | -0.338 |
consolidated | -0.328 |
cient | -0.318 |
colle | -0.316 |
Token | " |
Token ID | 366 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
!-- | +1.632 |
isphere | +1.458 |
consolidated | +1.415 |
cient | +1.362 |
colle | +1.344 |
Neg logit contributions | |
CRIP | -2.179 |
HS | -2.119 |
Sen | -2.047 |
Secretary | -2.029 |
IER | -2.026 |
Token | pt |
Token ID | 457 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
!-- | +5.134 |
isphere | +4.760 |
cient | +4.559 |
consolidated | +4.503 |
~~ | +4.401 |
Neg logit contributions | |
CRIP | -3.723 |
HS | -3.442 |
Roose | -3.416 |
Sutherland | -3.379 |
Secretary | -3.345 |
Token | R |
Token ID | 49 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
!-- | +1.871 |
isphere | +1.716 |
consolidated | +1.675 |
cient | +1.621 |
colle | +1.612 |
Neg logit contributions | |
CRIP | -1.562 |
HS | -1.519 |
Sen | -1.455 |
Secretary | -1.434 |
IER | -1.431 |
Token | " |
Token ID | 1 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
!-- | +2.042 |
isphere | +1.883 |
consolidated | +1.820 |
cient | +1.777 |
colle | +1.746 |
Neg logit contributions | |
CRIP | -1.863 |
HS | -1.792 |
Sen | -1.725 |
Secretary | -1.708 |
Roose | -1.697 |
Token | Prob |
Token ID | 30873 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
!-- | +3.757 |
isphere | +3.432 |
consolidated | +3.384 |
cient | +3.258 |
colle | +3.249 |
Neg logit contributions | |
CRIP | -2.940 |
HS | -2.794 |
Secretary | -2.685 |
Sen | -2.635 |
IER | -2.626 |
Token | st |
Token ID | 301 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
!-- | +2.673 |
isphere | +2.433 |
consolidated | +2.353 |
cient | +2.277 |
colle | +2.224 |
Neg logit contributions | |
CRIP | -2.977 |
HS | -2.845 |
Secretary | -2.740 |
Sen | -2.738 |
IER | -2.728 |
Token | significantly |
Token ID | 5566 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
!-- | +1.207 |
isphere | +1.096 |
consolidated | +1.078 |
cient | +1.028 |
colle | +1.021 |
Neg logit contributions | |
CRIP | -1.234 |
HS | -1.193 |
Sen | -1.151 |
Secretary | -1.138 |
IER | -1.133 |
Token | better |
Token ID | 1365 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
!-- | +0.890 |
isphere | +0.816 |
consolidated | +0.795 |
cient | +0.770 |
colle | +0.766 |
Neg logit contributions | |
CRIP | -0.756 |
HS | -0.735 |
Sen | -0.705 |
Secretary | -0.695 |
IER | -0.693 |
Token | as |
Token ID | 355 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
!-- | +0.077 |
isphere | +0.069 |
consolidated | +0.067 |
cient | +0.065 |
colle | +0.064 |
Neg logit contributions | |
CRIP | -0.089 |
HS | -0.087 |
Sen | -0.084 |
Secretary | -0.083 |
IER | -0.083 |
Token | Domin |
Token ID | 11817 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
!-- | +0.257 |
isphere | +0.233 |
consolidated | +0.228 |
cient | +0.221 |
colle | +0.219 |
Neg logit contributions | |
CRIP | -0.241 |
HS | -0.236 |
Sen | -0.226 |
IER | -0.222 |
Secretary | -0.222 |
Token | ik |
Token ID | 1134 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
!-- | +2.959 |
isphere | +2.747 |
consolidated | +2.671 |
cient | +2.596 |
colle | +2.572 |
Neg logit contributions | |
CRIP | -2.267 |
HS | -2.177 |
Sen | -2.085 |
Secretary | -2.062 |
IER | -2.057 |
Token | " |
Token ID | 366 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
!-- | +2.970 |
isphere | +2.704 |
consolidated | +2.663 |
cient | +2.545 |
colle | +2.523 |
Neg logit contributions | |
CRIP | -2.961 |
HS | -2.859 |
Sen | -2.748 |
Secretary | -2.734 |
IER | -2.720 |
Token | ra |
Token ID | 430 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
!-- | +5.858 |
isphere | +5.414 |
cient | +5.169 |
consolidated | +5.080 |
~~ | +5.029 |
Neg logit contributions | |
CRIP | -4.389 |
Roose | -4.057 |
HS | -4.048 |
Sutherland | -4.007 |
Secretary | -3.908 |
Token | i |
Token ID | 72 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
!-- | +1.314 |
isphere | +1.213 |
consolidated | +1.183 |
cient | +1.150 |
colle | +1.138 |
Neg logit contributions | |
CRIP | -1.021 |
HS | -0.981 |
Sen | -0.939 |
Secretary | -0.930 |
Roose | -0.925 |
Token | N |
Token ID | 45 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
CRIP | +1.360 |
HS | +1.351 |
Sen | +1.296 |
IER | +1.266 |
Secretary | +1.260 |
Neg logit contributions | |
!-- | -1.633 |
isphere | -1.496 |
consolidated | -1.464 |
colle | -1.408 |
cient | -1.401 |
Token | " |
Token ID | 1 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
!-- | +1.396 |
isphere | +1.262 |
consolidated | +1.225 |
cient | +1.181 |
colle | +1.163 |
Neg logit contributions | |
CRIP | -1.656 |
HS | -1.604 |
Sen | -1.548 |
Secretary | -1.537 |
IER | -1.532 |
Token | D |
Token ID | 360 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
!-- | +3.614 |
isphere | +3.292 |
consolidated | +3.254 |
cient | +3.135 |
colle | +3.109 |
Neg logit contributions | |
CRIP | -2.859 |
HS | -2.726 |
Secretary | -2.596 |
Sen | -2.567 |
IER | -2.557 |
Token | Master |
Token ID | 18254 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
!-- | +2.548 |
isphere | +2.347 |
consolidated | +2.251 |
cient | +2.237 |
colle | +2.176 |
Neg logit contributions | |
CRIP | -1.915 |
HS | -1.812 |
Roose | -1.750 |
IER | -1.730 |
Sutherland | -1.728 |
Token | of |
Token ID | 286 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
!-- | +1.343 |
isphere | +1.237 |
consolidated | +1.205 |
cient | +1.174 |
colle | +1.160 |
Neg logit contributions | |
CRIP | -1.060 |
HS | -1.015 |
Sen | -0.970 |
Secretary | -0.961 |
IER | -0.960 |
Token | Dal |
Token ID | 12348 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
CRIP | +0.308 |
HS | +0.301 |
Sen | +0.290 |
Roose | +0.284 |
Secretary | +0.284 |
Neg logit contributions | |
!-- | -0.337 |
isphere | -0.310 |
consolidated | -0.300 |
cient | -0.290 |
colle | -0.289 |
Token | K |
Token ID | 42 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
CRIP | +0.729 |
HS | +0.725 |
Sen | +0.689 |
Roose | +0.664 |
IER | +0.663 |
Neg logit contributions | |
!-- | -1.451 |
isphere | -1.349 |
consolidated | -1.326 |
colle | -1.294 |
cient | -1.279 |
Token | Profile |
Token ID | 13118 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
!-- | +2.246 |
isphere | +2.049 |
consolidated | +2.007 |
cient | +1.944 |
colle | +1.922 |
Neg logit contributions | |
CRIP | -1.859 |
HS | -1.781 |
Sen | -1.710 |
Secretary | -1.700 |
IER | -1.693 |
Token | Blog |
Token ID | 14001 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
!-- | +4.462 |
consolidated | +3.795 |
isphere | +3.689 |
cient | +3.555 |
colle | +3.501 |
Neg logit contributions | |
CRIP | -6.965 |
HS | -6.600 |
IER | -6.478 |
serial | -6.438 |
ipal | -6.396 |
Token | Joined |
Token ID | 16709 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
!-- | +3.342 |
consolidated | +2.729 |
isphere | +2.653 |
cient | +2.458 |
~~ | +2.424 |
Neg logit contributions | |
CRIP | -6.951 |
HS | -6.558 |
IER | -6.475 |
Secretary | -6.385 |
Sen | -6.368 |
Token | June |
Token ID | 2795 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
!-- | +4.906 |
consolidated | +4.155 |
isphere | +4.042 |
cient | +3.960 |
-- | +3.932 |
Neg logit contributions | |
CRIP | -7.077 |
HS | -6.599 |
IER | -6.533 |
ipal | -6.525 |
Sen | -6.444 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
!-- | +1.248 |
isphere | +1.114 |
consolidated | +1.087 |
cient | +1.043 |
colle | +1.029 |
Neg logit contributions | |
CRIP | -1.565 |
HS | -1.526 |
Sen | -1.474 |
IER | -1.458 |
Secretary | -1.458 |
Token | Canada |
Token ID | 3340 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
!-- | +2.123 |
isphere | +1.878 |
consolidated | +1.871 |
cient | +1.798 |
colle | +1.756 |
Neg logit contributions | |
CRIP | -2.414 |
HS | -2.326 |
IER | -2.244 |
Sen | -2.237 |
Secretary | -2.234 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
!-- | +0.487 |
isphere | +0.450 |
consolidated | +0.443 |
cient | +0.433 |
colle | +0.427 |
Neg logit contributions | |
CRIP | -0.268 |
HS | -0.257 |
Sen | -0.242 |
IER | -0.239 |
Secretary | -0.239 |
Token | ground |
Token ID | 2323 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
CRIP | +0.230 |
HS | +0.225 |
Sen | +0.216 |
Secretary | +0.212 |
IER | +0.212 |
Neg logit contributions | |
!-- | -0.232 |
isphere | -0.212 |
consolidated | -0.205 |
cient | -0.198 |
colle | -0.197 |
Token | level |
Token ID | 1241 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
!-- | +0.534 |
isphere | +0.486 |
consolidated | +0.478 |
cient | +0.460 |
colle | +0.457 |
Neg logit contributions | |
CRIP | -0.468 |
HS | -0.455 |
Sen | -0.437 |
Secretary | -0.431 |
IER | -0.428 |
Token | of |
Token ID | 286 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
!-- | +1.110 |
isphere | +1.008 |
consolidated | +0.987 |
colle | +0.945 |
cient | +0.945 |
Neg logit contributions | |
CRIP | -1.137 |
HS | -1.104 |
Sen | -1.065 |
Secretary | -1.054 |
IER | -1.050 |
Token | noise |
Token ID | 7838 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
!-- | +0.340 |
isphere | +0.309 |
consolidated | +0.302 |
cient | +0.291 |
colle | +0.290 |
Neg logit contributions | |
CRIP | -0.328 |
HS | -0.319 |
Sen | -0.307 |
Secretary | -0.303 |
IER | -0.303 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
CRIP | +0.123 |
HS | +0.120 |
Sen | +0.116 |
Secretary | +0.114 |
IER | +0.114 |
Neg logit contributions | |
!-- | -0.118 |
isphere | -0.107 |
consolidated | -0.104 |
cient | -0.100 |
colle | -0.100 |
Token | which |
Token ID | 543 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
CRIP | +1.058 |
HS | +1.031 |
Sen | +0.992 |
Secretary | +0.978 |
IER | +0.977 |
Neg logit contributions | |
!-- | -0.954 |
isphere | -0.862 |
consolidated | -0.834 |
cient | -0.810 |
colle | -0.800 |
Token | my |
Token ID | 616 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
!-- | +4.325 |
consolidated | +3.901 |
isphere | +3.899 |
colle | +3.701 |
cient | +3.653 |
Neg logit contributions | |
CRIP | -4.795 |
HS | -4.647 |
Secretary | -4.508 |
Sen | -4.507 |
IER | -4.431 |
Token | sonic |
Token ID | 36220 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
!-- | +1.820 |
isphere | +1.662 |
consolidated | +1.634 |
cient | +1.567 |
colle | +1.566 |
Neg logit contributions | |
CRIP | -1.763 |
HS | -1.712 |
Sen | -1.647 |
Secretary | -1.633 |
IER | -1.625 |
Token | experiences |
Token ID | 6461 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
!-- | +1.128 |
isphere | +1.032 |
consolidated | +1.008 |
cient | +0.972 |
colle | +0.968 |
Neg logit contributions | |
CRIP | -1.050 |
HS | -1.022 |
Sen | -0.982 |
Secretary | -0.969 |
IER | -0.968 |
Token | were |
Token ID | 547 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
CRIP | +0.175 |
HS | +0.171 |
Sen | +0.164 |
Secretary | +0.162 |
IER | +0.162 |
Neg logit contributions | |
!-- | -0.184 |
isphere | -0.168 |
consolidated | -0.163 |
cient | -0.158 |
colle | -0.157 |
Token | built |
Token ID | 3170 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
!-- | +2.315 |
isphere | +2.107 |
consolidated | +2.094 |
cient | +1.983 |
colle | +1.970 |
Neg logit contributions | |
CRIP | -2.515 |
HS | -2.451 |
Sen | -2.358 |
Secretary | -2.337 |
IER | -2.327 |
Token | on |
Token ID | 319 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
!-- | +1.863 |
isphere | +1.626 |
consolidated | +1.599 |
cient | +1.534 |
colle | +1.484 |
Neg logit contributions | |
CRIP | -2.603 |
HS | -2.527 |
Sen | -2.436 |
IER | -2.427 |
Secretary | -2.426 |
Token | H |
Token ID | 367 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
!-- | +1.511 |
isphere | +1.378 |
consolidated | +1.357 |
cient | +1.311 |
colle | +1.300 |
Neg logit contributions | |
CRIP | -1.157 |
HS | -1.108 |
Sen | -1.069 |
Secretary | -1.055 |
IER | -1.054 |
Token | MD |
Token ID | 12740 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
!-- | +3.463 |
isphere | +3.148 |
consolidated | +3.046 |
cient | +3.009 |
-- | +2.894 |
Neg logit contributions | |
CRIP | -2.471 |
HS | -2.299 |
Roose | -2.280 |
Sen | -2.262 |
Sutherland | -2.251 |
Token | s |
Token ID | 82 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
!-- | +2.036 |
isphere | +1.788 |
consolidated | +1.773 |
cient | +1.683 |
colle | +1.636 |
Neg logit contributions | |
CRIP | -2.557 |
HS | -2.444 |
IER | -2.374 |
Sen | -2.364 |
Secretary | -2.362 |
Token | but |
Token ID | 475 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
!-- | +2.391 |
isphere | +2.045 |
consolidated | +2.031 |
cient | +1.898 |
colle | +1.840 |
Neg logit contributions | |
CRIP | -3.868 |
HS | -3.740 |
Sen | -3.635 |
Secretary | -3.611 |
IER | -3.609 |
Token | it |
Token ID | 340 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
!-- | +4.050 |
isphere | +3.465 |
consolidated | +3.464 |
cient | +3.298 |
-- | +3.236 |
Neg logit contributions | |
CRIP | -5.070 |
HS | -4.794 |
Secretary | -4.705 |
IER | -4.696 |
Roose | -4.691 |
Token | can |
Token ID | 460 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
!-- | +4.241 |
consolidated | +3.725 |
isphere | +3.648 |
cient | +3.582 |
-- | +3.447 |
Neg logit contributions | |
CRIP | -5.474 |
HS | -5.168 |
Roose | -5.136 |
IER | -5.107 |
Secretary | -5.079 |
Token | be |
Token ID | 307 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
!-- | +2.139 |
isphere | +1.930 |
consolidated | +1.914 |
cient | +1.853 |
colle | +1.791 |
Neg logit contributions | |
CRIP | -1.760 |
HS | -1.692 |
Sen | -1.623 |
Secretary | -1.614 |
IER | -1.607 |
Token | eliminated |
Token ID | 15254 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
!-- | +1.381 |
isphere | +1.238 |
consolidated | +1.227 |
cient | +1.176 |
colle | +1.160 |
Neg logit contributions | |
CRIP | -1.384 |
HS | -1.342 |
Sen | -1.291 |
IER | -1.271 |
Secretary | -1.267 |
Token | via |
Token ID | 2884 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
!-- | +1.876 |
isphere | +1.616 |
consolidated | +1.591 |
cient | +1.513 |
-- | +1.467 |
Neg logit contributions | |
CRIP | -2.347 |
HS | -2.298 |
Sen | -2.217 |
IER | -2.205 |
Secretary | -2.199 |
Token | optics |
Token ID | 36237 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
!-- | +2.344 |
isphere | +2.145 |
consolidated | +2.091 |
cient | +2.021 |
colle | +2.015 |
Neg logit contributions | |
CRIP | -2.102 |
HS | -2.049 |
Sen | -1.965 |
Secretary | -1.938 |
IER | -1.934 |