Token | broccoli |
Token ID | 44653 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
arre | +2.601 |
rule | +2.572 |
crab | +2.060 |
hig | +1.915 |
Kerr | +1.849 |
Neg logit contributions | |
Roose | -6.581 |
Cumm | -6.372 |
STD | -6.169 |
Garrison | -6.044 |
onom | -6.007 |
Token | for |
Token ID | 329 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
arre | +2.483 |
rule | +2.473 |
crab | +2.076 |
hig | +2.047 |
Kerr | +2.023 |
Neg logit contributions | |
Roose | -2.946 |
Cumm | -2.853 |
STD | -2.689 |
| -2.616 |
Garrison | -2.610 |
Token | a |
Token ID | 257 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
arre | +1.326 |
rule | +1.309 |
crab | +1.130 |
hig | +1.117 |
Kerr | +1.098 |
Neg logit contributions | |
Roose | -1.263 |
Cumm | -1.211 |
STD | -1.142 |
kson | -1.116 |
| -1.112 |
Token | few |
Token ID | 1178 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
arre | +1.082 |
rule | +1.070 |
crab | +0.900 |
hig | +0.895 |
Kerr | +0.876 |
Neg logit contributions | |
Roose | -1.272 |
Cumm | -1.228 |
STD | -1.164 |
| -1.140 |
kson | -1.135 |
Token | minutes |
Token ID | 2431 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Roose | +1.915 |
Cumm | +1.813 |
STD | +1.691 |
| +1.674 |
kson | +1.645 |
Neg logit contributions | |
arre | -3.108 |
rule | -3.054 |
hig | -2.684 |
crab | -2.660 |
モ | -2.617 |
Token | until |
Token ID | 1566 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
Roose | +0.287 |
Cumm | +0.275 |
STD | +0.260 |
| +0.257 |
Garrison | +0.254 |
Neg logit contributions | |
arre | -0.294 |
rule | -0.291 |
hig | -0.248 |
crab | -0.247 |
Kerr | -0.241 |
Token | fork |
Token ID | 15563 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
rule | +5.375 |
arre | +4.992 |
crab | +4.988 |
Smash | +4.257 |
hig | +4.155 |
Neg logit contributions | |
Cumm | -14.373 |
Roose | -14.348 |
Garrison | -13.516 |
STD | -13.381 |
ratulations | -13.321 |
Token | - |
Token ID | 12 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
rule | +3.857 |
arre | +3.840 |
crab | +3.283 |
hig | +3.174 |
Smash | +3.142 |
Neg logit contributions | |
Roose | -5.066 |
Cumm | -4.940 |
STD | -4.591 |
kson | -4.583 |
Garrison | -4.520 |
Token | t |
Token ID | 83 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
rule | +5.644 |
arre | +5.566 |
crab | +4.569 |
hig | +4.422 |
Smash | +4.416 |
Neg logit contributions | |
Roose | -5.212 |
Cumm | -5.050 |
STD | -4.596 |
Garrison | -4.543 |
kson | -4.408 |
Token | ender |
Token ID | 2194 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
arre | +3.483 |
rule | +3.425 |
crab | +2.703 |
Kerr | +2.636 |
Smash | +2.605 |
Neg logit contributions | |
Roose | -4.637 |
Cumm | -4.478 |
STD | -4.245 |
Garrison | -4.158 |
| -4.089 |
Token | . |
Token ID | 13 |
Feature activation | +9.58e+00 |
Pos logit contributions | |
arre | +2.288 |
rule | +2.271 |
crab | +1.906 |
hig | +1.856 |
Kerr | +1.849 |
Neg logit contributions | |
Roose | -2.812 |
Cumm | -2.699 |
STD | -2.567 |
kson | -2.505 |
Garrison | -2.500 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Roose | +1.171 |
Cumm | +1.134 |
STD | +1.086 |
| +1.054 |
Garrison | +1.044 |
Neg logit contributions | |
arre | -1.188 |
rule | -1.164 |
crab | -0.985 |
hig | -0.972 |
Kerr | -0.967 |
Token | full |
Token ID | 1336 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
arre | +1.040 |
rule | +1.023 |
crab | +0.861 |
hig | +0.858 |
Kerr | +0.840 |
Neg logit contributions | |
Roose | -1.199 |
Cumm | -1.156 |
STD | -1.098 |
| -1.078 |
kson | -1.070 |
Token | sensor |
Token ID | 12694 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
arre | +0.175 |
rule | +0.171 |
crab | +0.143 |
hig | +0.143 |
Kerr | +0.140 |
Neg logit contributions | |
Roose | -0.202 |
Cumm | -0.195 |
STD | -0.186 |
| -0.182 |
Garrison | -0.181 |
Token | area |
Token ID | 1989 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
Roose | +2.675 |
Cumm | +2.592 |
STD | +2.515 |
| +2.463 |
onom | +2.445 |
Neg logit contributions | |
arre | -2.694 |
rule | -2.643 |
crab | -2.216 |
Kerr | -2.206 |
hig | -2.196 |
Token | with |
Token ID | 351 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
Roose | +0.397 |
Cumm | +0.381 |
STD | +0.363 |
| +0.356 |
kson | +0.352 |
Neg logit contributions | |
arre | -0.389 |
rule | -0.382 |
crab | -0.323 |
hig | -0.320 |
Kerr | -0.316 |
Token | v |
Token ID | 410 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
arre | +0.646 |
rule | +0.637 |
crab | +0.543 |
hig | +0.541 |
Kerr | +0.531 |
Neg logit contributions | |
Roose | -0.645 |
Cumm | -0.620 |
STD | -0.586 |
| -0.575 |
kson | -0.570 |
Token | ign |
Token ID | 570 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
arre | +9.904 |
rule | +9.647 |
hig | +8.256 |
crab | +8.162 |
Smash | +8.133 |
Neg logit contributions | |
Roose | -9.465 |
Cumm | -9.085 |
Garrison | -8.511 |
kson | -8.481 |
STD | -8.431 |
Token | etting |
Token ID | 35463 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
arre | +1.918 |
rule | +1.889 |
crab | +1.417 |
hig | +1.414 |
Kerr | +1.396 |
Neg logit contributions | |
Roose | -4.115 |
Cumm | -3.979 |
STD | -3.805 |
| -3.800 |
Garrison | -3.793 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
arre | +2.290 |
rule | +2.264 |
crab | +1.914 |
hig | +1.909 |
Kerr | +1.862 |
Neg logit contributions | |
Roose | -2.604 |
Cumm | -2.512 |
STD | -2.371 |
kson | -2.328 |
| -2.325 |
Token | So |
Token ID | 1406 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
arre | +0.116 |
rule | +0.114 |
crab | +0.097 |
hig | +0.096 |
Kerr | +0.094 |
Neg logit contributions | |
Roose | -0.122 |
Cumm | -0.117 |
STD | -0.111 |
| -0.110 |
Garrison | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
Roose | +0.693 |
Cumm | +0.668 |
STD | +0.635 |
| +0.623 |
Garrison | +0.613 |
Neg logit contributions | |
arre | -0.718 |
rule | -0.705 |
crab | -0.598 |
hig | -0.593 |
Kerr | -0.586 |
Token | focus |
Token ID | 2962 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
arre | +0.503 |
rule | +0.494 |
crab | +0.420 |
hig | +0.419 |
Kerr | +0.413 |
Neg logit contributions | |
Roose | -0.495 |
Cumm | -0.477 |
STD | -0.451 |
| -0.441 |
Garrison | -0.437 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
arre | +1.565 |
rule | +1.546 |
crab | +1.318 |
hig | +1.315 |
Kerr | +1.287 |
Neg logit contributions | |
Roose | -1.609 |
Cumm | -1.546 |
STD | -1.461 |
| -1.431 |
kson | -1.424 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
arre | +0.749 |
rule | +0.737 |
crab | +0.631 |
hig | +0.628 |
Kerr | +0.618 |
Neg logit contributions | |
Roose | -0.712 |
Cumm | -0.685 |
STD | -0.647 |
| -0.633 |
Garrison | -0.627 |
Token | stealth |
Token ID | 19159 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
arre | +0.910 |
rule | +0.896 |
crab | +0.758 |
hig | +0.755 |
Kerr | +0.740 |
Neg logit contributions | |
Roose | -0.987 |
Cumm | -0.951 |
STD | -0.901 |
| -0.885 |
kson | -0.877 |
Token | - |
Token ID | 12 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
arre | +2.189 |
rule | +2.157 |
crab | +1.815 |
hig | +1.800 |
Kerr | +1.756 |
Neg logit contributions | |
Roose | -2.679 |
Cumm | -2.582 |
STD | -2.450 |
| -2.405 |
kson | -2.404 |
Token | lite |
Token ID | 36890 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
arre | +0.999 |
rule | +0.985 |
crab | +0.853 |
hig | +0.850 |
Kerr | +0.836 |
Neg logit contributions | |
Roose | -0.830 |
Cumm | -0.795 |
STD | -0.747 |
| -0.731 |
kson | -0.724 |
Token | shenanigans |
Token ID | 48949 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
rule | +8.899 |
arre | +8.742 |
rog | +7.758 |
crab | +7.666 |
Smash | +7.559 |
Neg logit contributions | |
Roose | -10.257 |
Cumm | -9.653 |
govtrack | -9.282 |
kson | -9.266 |
STD | -9.071 |
Token | and |
Token ID | 290 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
arre | +3.238 |
rule | +3.208 |
hig | +2.728 |
crab | +2.726 |
Kerr | +2.663 |
Neg logit contributions | |
Roose | -3.534 |
Cumm | -3.411 |
STD | -3.229 |
| -3.187 |
kson | -3.186 |
Token | precision |
Token ID | 15440 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
arre | +1.927 |
rule | +1.899 |
crab | +1.623 |
hig | +1.614 |
Kerr | +1.575 |
Neg logit contributions | |
Roose | -2.042 |
Cumm | -1.963 |
STD | -1.854 |
| -1.824 |
kson | -1.819 |
Token | platform |
Token ID | 3859 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
arre | +1.192 |
rule | +1.173 |
crab | +0.990 |
hig | +0.986 |
Kerr | +0.966 |
Neg logit contributions | |
Roose | -1.333 |
Cumm | -1.285 |
STD | -1.219 |
| -1.196 |
kson | -1.187 |
Token | ing |
Token ID | 278 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
arre | +5.066 |
rule | +5.024 |
crab | +4.334 |
hig | +4.236 |
Smash | +4.192 |
Neg logit contributions | |
Roose | -5.238 |
Cumm | -5.019 |
STD | -4.718 |
kson | -4.663 |
| -4.658 |
Token | states |
Token ID | 2585 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
arre | +4.380 |
rule | +4.231 |
crab | +3.684 |
hig | +3.609 |
Kerr | +3.591 |
Neg logit contributions | |
Roose | -5.353 |
Cumm | -5.161 |
STD | -4.850 |
| -4.763 |
kson | -4.727 |
Token | , |
Token ID | 11 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
arre | +2.078 |
rule | +2.039 |
crab | +1.718 |
hig | +1.705 |
Kerr | +1.671 |
Neg logit contributions | |
Roose | -2.665 |
Cumm | -2.572 |
STD | -2.452 |
| -2.401 |
kson | -2.395 |
Token | � |
Token ID | 447 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
arre | +0.228 |
rule | +0.225 |
crab | +0.192 |
hig | +0.191 |
Kerr | +0.187 |
Neg logit contributions | |
Roose | -0.220 |
Cumm | -0.212 |
STD | -0.200 |
| -0.196 |
kson | -0.194 |
Token | � |
Token ID | 251 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
Roose | +0.434 |
Cumm | +0.416 |
STD | +0.390 |
| +0.384 |
kson | +0.378 |
Neg logit contributions | |
arre | -0.534 |
rule | -0.527 |
crab | -0.458 |
hig | -0.454 |
Kerr | -0.445 |
Token | Ms |
Token ID | 6997 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
arre | +3.665 |
rule | +3.652 |
crab | +3.121 |
hig | +3.104 |
Kerr | +3.080 |
Neg logit contributions | |
Roose | -4.090 |
Cumm | -3.896 |
STD | -3.739 |
| -3.694 |
Garrison | -3.638 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
arre | +1.803 |
rule | +1.783 |
crab | +1.484 |
hig | +1.461 |
Kerr | +1.461 |
Neg logit contributions | |
Roose | -2.150 |
Cumm | -2.067 |
STD | -1.963 |
| -1.923 |
kson | -1.909 |
Token | Set |
Token ID | 5345 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
rule | +6.127 |
arre | +6.105 |
Kerr | +5.579 |
Smash | +5.059 |
hig | +4.838 |
Neg logit contributions | |
Roose | -11.422 |
Cumm | -10.942 |
| -10.820 |
STD | -10.558 |
ratulations | -10.542 |
Token | zer |
Token ID | 9107 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
arre | +1.678 |
rule | +1.661 |
crab | +1.339 |
hig | +1.308 |
Kerr | +1.283 |
Neg logit contributions | |
Roose | -2.417 |
Cumm | -2.348 |
STD | -2.222 |
Garrison | -2.181 |
| -2.174 |
Token | said |
Token ID | 531 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Roose | +0.255 |
Cumm | +0.243 |
STD | +0.227 |
| +0.222 |
kson | +0.220 |
Neg logit contributions | |
arre | -0.354 |
rule | -0.350 |
crab | -0.305 |
hig | -0.305 |
Kerr | -0.300 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
arre | +0.507 |
rule | +0.499 |
crab | +0.421 |
hig | +0.419 |
Kerr | +0.411 |
Neg logit contributions | |
Roose | -0.574 |
Cumm | -0.552 |
STD | -0.525 |
| -0.514 |
kson | -0.510 |
Token | � |
Token ID | 564 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Roose | +0.806 |
Cumm | +0.777 |
STD | +0.735 |
| +0.724 |
Garrison | +0.715 |
Neg logit contributions | |
arre | -0.777 |
rule | -0.764 |
crab | -0.649 |
hig | -0.647 |
Kerr | -0.629 |
Token | plummeted |
Token ID | 44282 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Roose | +2.404 |
Cumm | +2.335 |
STD | +2.188 |
| +2.139 |
Garrison | +2.114 |
Neg logit contributions | |
arre | -2.969 |
rule | -2.922 |
hig | -2.463 |
crab | -2.461 |
Kerr | -2.445 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
arre | +1.246 |
rule | +1.228 |
crab | +1.051 |
hig | +1.048 |
Kerr | +1.026 |
Neg logit contributions | |
Roose | -1.274 |
Cumm | -1.225 |
STD | -1.157 |
| -1.136 |
kson | -1.131 |
Token | his |
Token ID | 465 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
arre | +0.951 |
rule | +0.937 |
crab | +0.803 |
hig | +0.800 |
Kerr | +0.785 |
Neg logit contributions | |
Roose | -0.899 |
Cumm | -0.863 |
STD | -0.815 |
| -0.798 |
Garrison | -0.791 |
Token | commander |
Token ID | 11561 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Roose | +1.951 |
Cumm | +1.852 |
STD | +1.783 |
Garrison | +1.728 |
| +1.719 |
Neg logit contributions | |
arre | -1.831 |
rule | -1.771 |
hig | -1.499 |
crab | -1.481 |
Kerr | -1.471 |
Token | , |
Token ID | 11 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Roose | +0.202 |
Cumm | +0.194 |
STD | +0.183 |
| +0.180 |
Garrison | +0.178 |
Neg logit contributions | |
arre | -0.201 |
rule | -0.198 |
crab | -0.168 |
hig | -0.168 |
Kerr | -0.164 |
Token | Gen |
Token ID | 5215 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
arre | +2.152 |
rule | +2.118 |
crab | +1.822 |
hig | +1.809 |
Kerr | +1.787 |
Neg logit contributions | |
Roose | -2.139 |
Cumm | -2.071 |
STD | -1.960 |
| -1.918 |
kson | -1.900 |
Token | . |
Token ID | 13 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
arre | +6.286 |
rule | +6.269 |
Kerr | +5.440 |
crab | +5.086 |
Smash | +5.008 |
Neg logit contributions | |
Roose | -11.691 |
Cumm | -11.239 |
MpServer | -11.160 |
STD | -11.131 |
kson | -10.632 |
Token | Douglas |
Token ID | 15796 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
arre | +4.970 |
rule | +4.878 |
Kerr | +4.535 |
crab | +4.316 |
Smash | +4.315 |
Neg logit contributions | |
Roose | -5.457 |
Cumm | -5.327 |
MpServer | -5.140 |
STD | -5.131 |
kson | -5.063 |
Token | MacArthur |
Token ID | 46626 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Roose | +2.738 |
Cumm | +2.650 |
STD | +2.517 |
Garrison | +2.509 |
| +2.485 |
Neg logit contributions | |
arre | -1.972 |
rule | -1.946 |
hig | -1.575 |
crab | -1.566 |
モ | -1.504 |
Token | , |
Token ID | 11 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
Roose | +3.083 |
Cumm | +2.961 |
STD | +2.780 |
Garrison | +2.751 |
| +2.729 |
Neg logit contributions | |
arre | -3.440 |
rule | -3.391 |
hig | -2.864 |
crab | -2.860 |
Kerr | -2.735 |
Token | defied |
Token ID | 47437 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Roose | +2.058 |
Cumm | +1.961 |
STD | +1.850 |
| +1.825 |
Garrison | +1.824 |
Neg logit contributions | |
arre | -2.230 |
rule | -2.208 |
crab | -1.854 |
hig | -1.852 |
Kerr | -1.812 |
Token | an |
Token ID | 281 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
arre | +0.117 |
rule | +0.116 |
crab | +0.099 |
hig | +0.098 |
Kerr | +0.097 |
Neg logit contributions | |
Roose | -0.110 |
Cumm | -0.106 |
STD | -0.100 |
| -0.098 |
Garrison | -0.097 |
Token | ambitious |
Token ID | 14742 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
arre | +0.728 |
rule | +0.717 |
crab | +0.617 |
hig | +0.615 |
Kerr | +0.604 |
Neg logit contributions | |
Roose | -0.659 |
Cumm | -0.632 |
STD | -0.596 |
| -0.583 |
kson | -0.579 |
Token | project |
Token ID | 1628 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
arre | +2.029 |
rule | +2.007 |
crab | +1.733 |
hig | +1.723 |
Kerr | +1.690 |
Neg logit contributions | |
Roose | -1.988 |
Cumm | -1.904 |
STD | -1.788 |
kson | -1.761 |
| -1.759 |
Token | has |
Token ID | 468 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Roose | +0.983 |
Cumm | +0.943 |
STD | +0.895 |
| +0.874 |
kson | +0.865 |
Neg logit contributions | |
arre | -1.065 |
rule | -1.053 |
crab | -0.894 |
hig | -0.888 |
Kerr | -0.879 |
Token | something |
Token ID | 1223 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
arre | +2.461 |
rule | +2.424 |
crab | +2.091 |
hig | +2.078 |
Kerr | +2.039 |
Neg logit contributions | |
Roose | -2.396 |
Cumm | -2.308 |
STD | -2.168 |
| -2.126 |
Garrison | -2.119 |
Token | to |
Token ID | 284 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
arre | +3.011 |
rule | +2.986 |
crab | +2.556 |
hig | +2.535 |
Kerr | +2.489 |
Neg logit contributions | |
Roose | -3.592 |
Cumm | -3.492 |
STD | -3.319 |
kson | -3.260 |
| -3.227 |
Token | do |
Token ID | 466 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
arre | +7.511 |
rule | +7.317 |
crab | +6.280 |
hig | +6.068 |
Kerr | +5.755 |
Neg logit contributions | |
Roose | -11.130 |
Cumm | -11.008 |
| -10.093 |
Garrison | -10.061 |
STD | -10.056 |
Token | with |
Token ID | 351 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
arre | +3.766 |
rule | +3.700 |
hig | +3.060 |
crab | +3.054 |
Kerr | +2.985 |
Neg logit contributions | |
Roose | -5.434 |
Cumm | -5.227 |
STD | -4.924 |
| -4.820 |
Garrison | -4.800 |
Token | having |
Token ID | 1719 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Roose | +1.740 |
Cumm | +1.680 |
STD | +1.581 |
| +1.541 |
Garrison | +1.530 |
Neg logit contributions | |
arre | -2.104 |
rule | -2.059 |
crab | -1.759 |
hig | -1.750 |
Kerr | -1.722 |
Token | M |
Token ID | 337 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
arre | +0.088 |
rule | +0.086 |
crab | +0.074 |
hig | +0.073 |
Kerr | +0.072 |
Neg logit contributions | |
Roose | -0.084 |
Cumm | -0.080 |
STD | -0.076 |
| -0.074 |
Garrison | -0.074 |
Token | imi |
Token ID | 25236 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
Roose | +0.182 |
Cumm | +0.175 |
STD | +0.165 |
| +0.162 |
kson | +0.161 |
Neg logit contributions | |
arre | -0.194 |
rule | -0.192 |
crab | -0.165 |
hig | -0.164 |
Kerr | -0.161 |
Token | problem |
Token ID | 1917 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
Roose | +0.544 |
Cumm | +0.523 |
STD | +0.496 |
| +0.487 |
Garrison | +0.481 |
Neg logit contributions | |
arre | -0.538 |
rule | -0.528 |
hig | -0.446 |
crab | -0.446 |
Kerr | -0.438 |
Token | . |
Token ID | 13 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Roose | +2.325 |
Cumm | +2.239 |
STD | +2.111 |
| +2.094 |
Garrison | +2.064 |
Neg logit contributions | |
arre | -2.344 |
rule | -2.321 |
crab | -1.959 |
hig | -1.941 |
Kerr | -1.904 |
Token | � |
Token ID | 447 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
arre | +2.831 |
rule | +2.789 |
crab | +2.382 |
Kerr | +2.377 |
hig | +2.345 |
Neg logit contributions | |
Roose | -2.988 |
Cumm | -2.865 |
STD | -2.730 |
kson | -2.652 |
| -2.648 |
Token | � |
Token ID | 251 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
arre | +0.462 |
rule | +0.455 |
crab | +0.382 |
hig | +0.381 |
Kerr | +0.373 |
Neg logit contributions | |
Roose | -0.536 |
Cumm | -0.517 |
STD | -0.491 |
| -0.481 |
kson | -0.478 |
Token | Expl |
Token ID | 5905 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
arre | +1.111 |
rule | +1.094 |
crab | +0.929 |
hig | +0.925 |
Kerr | +0.908 |
Neg logit contributions | |
Roose | -1.161 |
Cumm | -1.118 |
STD | -1.059 |
| -1.038 |
kson | -1.030 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Roose | +2.188 |
Cumm | +2.110 |
STD | +1.998 |
| +1.976 |
onom | +1.970 |
Neg logit contributions | |
arre | -1.754 |
rule | -1.738 |
hig | -1.466 |
crab | -1.457 |
Kerr | -1.429 |
Token | Marin |
Token ID | 36384 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
rule | +7.132 |
arre | +7.114 |
Kerr | +6.419 |
crab | +6.235 |
hig | +5.926 |
Neg logit contributions | |
Roose | -10.674 |
Cumm | -9.973 |
STD | -9.836 |
kson | -9.482 |
onom | -9.474 |
Token | , |
Token ID | 11 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
arre | +2.006 |
rule | +1.966 |
hig | +1.675 |
crab | +1.675 |
Kerr | +1.645 |
Neg logit contributions | |
Roose | -2.135 |
Cumm | -2.049 |
STD | -1.950 |
| -1.909 |
Garrison | -1.890 |
Token | � |
Token ID | 564 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
arre | +0.685 |
rule | +0.675 |
crab | +0.576 |
hig | +0.574 |
Kerr | +0.563 |
Neg logit contributions | |
Roose | -0.653 |
Cumm | -0.628 |
STD | -0.592 |
| -0.582 |
kson | -0.576 |
Token | � |
Token ID | 250 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
arre | +0.518 |
rule | +0.511 |
crab | +0.446 |
hig | +0.445 |
Kerr | +0.438 |
Neg logit contributions | |
Roose | -0.378 |
Cumm | -0.360 |
STD | -0.337 |
| -0.328 |
Garrison | -0.326 |
Token | When |
Token ID | 2215 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
Roose | +0.783 |
Cumm | +0.758 |
STD | +0.711 |
| +0.707 |
kson | +0.695 |
Neg logit contributions | |
arre | -0.855 |
rule | -0.833 |
hig | -0.725 |
crab | -0.725 |
Kerr | -0.711 |
Token | " |
Token ID | 1 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
arre | +0.638 |
rule | +0.627 |
crab | +0.519 |
hig | +0.515 |
Kerr | +0.504 |
Neg logit contributions | |
Roose | -0.873 |
Cumm | -0.843 |
STD | -0.803 |
| -0.790 |
kson | -0.785 |
Token | hypothesis |
Token ID | 14078 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
arre | +2.774 |
rule | +2.753 |
crab | +2.245 |
hig | +2.206 |
Kerr | +2.181 |
Neg logit contributions | |
Roose | -4.868 |
Cumm | -4.712 |
| -4.493 |
STD | -4.491 |
kson | -4.448 |
Token | , |
Token ID | 11 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
arre | +3.530 |
rule | +3.467 |
crab | +2.989 |
hig | +2.968 |
Kerr | +2.937 |
Neg logit contributions | |
Roose | -4.102 |
Cumm | -3.946 |
STD | -3.775 |
| -3.732 |
kson | -3.687 |
Token | which |
Token ID | 543 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
arre | +4.354 |
rule | +4.327 |
Kerr | +3.734 |
hig | +3.720 |
crab | +3.720 |
Neg logit contributions | |
Roose | -5.076 |
Cumm | -4.891 |
STD | -4.699 |
| -4.617 |
kson | -4.587 |
Token | attributes |
Token ID | 12608 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
arre | +2.322 |
rule | +2.288 |
hig | +1.991 |
crab | +1.983 |
Kerr | +1.970 |
Neg logit contributions | |
Roose | -2.295 |
Cumm | -2.201 |
STD | -2.103 |
| -2.080 |
onom | -2.034 |
Token | im |
Token ID | 545 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
arre | +5.651 |
rule | +5.499 |
hig | +4.819 |
crab | +4.786 |
Kerr | +4.684 |
Neg logit contributions | |
Roose | -6.255 |
Cumm | -6.126 |
| -5.703 |
STD | -5.690 |
govtrack | -5.661 |
Token | bal |
Token ID | 6893 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
arre | +6.939 |
rule | +6.845 |
crab | +5.260 |
Smash | +5.091 |
hig | +5.070 |
Neg logit contributions | |
Roose | -11.615 |
Cumm | -11.049 |
STD | -10.691 |
MpServer | -10.284 |
Garrison | -10.261 |
Token | ances |
Token ID | 1817 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
arre | +0.400 |
rule | +0.396 |
crab | +0.357 |
hig | +0.356 |
Kerr | +0.352 |
Neg logit contributions | |
Roose | -0.139 |
Cumm | -0.129 |
STD | -0.114 |
| -0.109 |
kson | -0.107 |
Token | in |
Token ID | 287 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
arre | +1.095 |
rule | +1.077 |
crab | +0.917 |
hig | +0.914 |
Kerr | +0.896 |
Neg logit contributions | |
Roose | -1.155 |
Cumm | -1.113 |
STD | -1.052 |
| -1.032 |
kson | -1.025 |
Token | dopamine |
Token ID | 26252 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
arre | +1.244 |
rule | +1.226 |
crab | +1.048 |
hig | +1.044 |
Kerr | +1.024 |
Neg logit contributions | |
Roose | -1.225 |
Cumm | -1.178 |
STD | -1.112 |
| -1.091 |
kson | -1.081 |
Token | levels |
Token ID | 2974 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
arre | +0.548 |
rule | +0.539 |
crab | +0.458 |
hig | +0.456 |
Kerr | +0.448 |
Neg logit contributions | |
Roose | -0.568 |
Cumm | -0.547 |
STD | -0.518 |
| -0.507 |
kson | -0.503 |
Token | Current |
Token ID | 11297 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
arre | +0.397 |
rule | +0.392 |
crab | +0.330 |
hig | +0.330 |
Kerr | +0.323 |
Neg logit contributions | |
Roose | -0.422 |
Cumm | -0.405 |
STD | -0.383 |
| -0.375 |
kson | -0.375 |
Token | version |
Token ID | 2196 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Roose | +1.030 |
Cumm | +0.990 |
STD | +0.943 |
| +0.919 |
Garrison | +0.908 |
Neg logit contributions | |
arre | -1.047 |
rule | -1.038 |
crab | -0.882 |
hig | -0.872 |
Kerr | -0.863 |
Token | : |
Token ID | 25 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
arre | +0.087 |
rule | +0.086 |
crab | +0.074 |
hig | +0.073 |
Kerr | +0.072 |
Neg logit contributions | |
Roose | -0.083 |
Cumm | -0.079 |
STD | -0.075 |
| -0.074 |
Garrison | -0.073 |
Token | Mix |
Token ID | 15561 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
arre | +0.830 |
rule | +0.818 |
crab | +0.696 |
hig | +0.691 |
Kerr | +0.680 |
Neg logit contributions | |
Roose | -0.836 |
Cumm | -0.805 |
STD | -0.763 |
| -0.747 |
Garrison | -0.739 |
Token | bus |
Token ID | 10885 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
arre | +1.721 |
rule | +1.698 |
crab | +1.488 |
hig | +1.482 |
Kerr | +1.453 |
Neg logit contributions | |
Roose | -1.108 |
Cumm | -1.053 |
STD | -0.985 |
| -0.958 |
kson | -0.957 |
Token | v |
Token ID | 410 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Roose | +2.272 |
Cumm | +2.189 |
STD | +2.089 |
| +2.035 |
Garrison | +2.020 |
Neg logit contributions | |
arre | -2.314 |
rule | -2.289 |
crab | -1.947 |
hig | -1.907 |
Kerr | -1.904 |
Token | 3 |
Token ID | 18 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
arre | +7.246 |
rule | +7.104 |
Smash | +5.766 |
Kerr | +5.760 |
hig | +5.694 |
Neg logit contributions | |
Roose | -10.492 |
Cumm | -10.124 |
kson | -9.566 |
Garrison | -9.551 |
STD | -9.498 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
arre | +0.046 |
rule | +0.046 |
crab | +0.039 |
hig | +0.038 |
Kerr | +0.038 |
Neg logit contributions | |
Roose | -0.049 |
Cumm | -0.048 |
STD | -0.045 |
| -0.044 |
Garrison | -0.044 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
arre | +1.416 |
rule | +1.395 |
crab | +1.176 |
hig | +1.171 |
Kerr | +1.151 |
Neg logit contributions | |
Roose | -1.569 |
Cumm | -1.511 |
STD | -1.433 |
| -1.405 |
kson | -1.396 |
Token | ( |
Token ID | 357 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Roose | +1.843 |
Cumm | +1.787 |
STD | +1.705 |
| +1.670 |
Garrison | +1.646 |
Neg logit contributions | |
arre | -1.829 |
rule | -1.798 |
crab | -1.530 |
hig | -1.506 |
Kerr | -1.494 |
Token | Product |
Token ID | 15667 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
arre | +0.809 |
rule | +0.797 |
crab | +0.673 |
hig | +0.671 |
Kerr | +0.657 |
Neg logit contributions | |
Roose | -0.874 |
Cumm | -0.841 |
STD | -0.797 |
| -0.781 |
kson | -0.777 |
Token | towel |
Token ID | 24808 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
Roose | +0.553 |
Cumm | +0.486 |
STD | +0.431 |
| +0.408 |
Garrison | +0.389 |
Neg logit contributions | |
arre | -2.146 |
rule | -2.115 |
hig | -1.924 |
crab | -1.909 |
Kerr | -1.892 |
Token | - |
Token ID | 12 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
Roose | +3.676 |
Cumm | +3.468 |
STD | +3.382 |
| +3.300 |
Garrison | +3.216 |
Neg logit contributions | |
arre | -4.943 |
rule | -4.807 |
hig | -4.168 |
モ | -4.145 |
Kerr | -4.142 |
Token | lined |
Token ID | 10837 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
Roose | +0.414 |
Cumm | +0.262 |
STD | +0.178 |
| +0.160 |
onom | +0.109 |
Neg logit contributions | |
arre | -7.058 |
rule | -6.861 |
Kerr | -6.559 |
hig | -6.548 |
crab | -6.528 |
Token | plate |
Token ID | 7480 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
rule | +2.336 |
arre | +2.299 |
crab | +1.936 |
hig | +1.839 |
Kerr | +1.799 |
Neg logit contributions | |
Roose | -4.025 |
Cumm | -3.916 |
kson | -3.662 |
Garrison | -3.654 |
STD | -3.642 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
arre | +0.241 |
rule | +0.236 |
hig | +0.201 |
crab | +0.200 |
Kerr | +0.196 |
Neg logit contributions | |
Roose | -0.254 |
Cumm | -0.244 |
STD | -0.232 |
| -0.228 |
Garrison | -0.226 |
Token | Serve |
Token ID | 35557 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
arre | +0.098 |
rule | +0.095 |
hig | +0.077 |
crab | +0.076 |
Kerr | +0.073 |
Neg logit contributions | |
Roose | -0.166 |
Cumm | -0.161 |
STD | -0.154 |
| -0.153 |
Garrison | -0.151 |
Token | hot |
Token ID | 3024 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
arre | +4.549 |
rule | +4.027 |
crab | +3.924 |
Smash | +3.484 |
hig | +3.434 |
Neg logit contributions | |
Roose | -13.151 |
Cumm | -13.134 |
STD | -12.307 |
kson | -12.235 |
govtrack | -12.183 |
Token | ! |
Token ID | 0 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
arre | +0.811 |
rule | +0.796 |
crab | +0.673 |
hig | +0.671 |
Kerr | +0.656 |
Neg logit contributions | |
Roose | -0.911 |
Cumm | -0.877 |
STD | -0.834 |
| -0.818 |
kson | -0.812 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Roose | +3.184 |
Cumm | +3.140 |
| +2.931 |
STD | +2.885 |
Garrison | +2.835 |
Neg logit contributions | |
arre | -3.732 |
rule | -3.698 |
hig | -3.167 |
crab | -3.092 |
Kerr | -3.038 |
Token | Image |
Token ID | 5159 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Roose | +1.745 |
Cumm | +1.678 |
| +1.596 |
STD | +1.593 |
onom | +1.550 |
Neg logit contributions | |
arre | -1.891 |
rule | -1.838 |
hig | -1.622 |
crab | -1.615 |
Kerr | -1.586 |
Token | copyright |
Token ID | 6634 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
arre | +1.755 |
rule | +1.732 |
crab | +1.463 |
hig | +1.456 |
Kerr | +1.431 |
Neg logit contributions | |
Roose | -2.025 |
Cumm | -1.946 |
STD | -1.843 |
kson | -1.817 |
| -1.800 |
Token | fail |
Token ID | 2038 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
arre | +2.795 |
rule | +2.775 |
crab | +2.409 |
hig | +2.386 |
Kerr | +2.325 |
Neg logit contributions | |
Roose | -2.590 |
Cumm | -2.480 |
STD | -2.322 |
kson | -2.284 |
| -2.275 |
Token | to |
Token ID | 284 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
arre | +1.213 |
rule | +1.198 |
crab | +1.021 |
hig | +1.016 |
Kerr | +0.996 |
Neg logit contributions | |
Roose | -1.250 |
Cumm | -1.202 |
STD | -1.137 |
| -1.114 |
kson | -1.108 |
Token | reward |
Token ID | 6721 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
arre | +1.344 |
rule | +1.326 |
crab | +1.136 |
hig | +1.131 |
Kerr | +1.109 |
Neg logit contributions | |
Roose | -1.296 |
Cumm | -1.245 |
STD | -1.176 |
| -1.151 |
kson | -1.143 |
Token | with |
Token ID | 351 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Roose | +0.010 |
Cumm | +0.010 |
STD | +0.009 |
| +0.009 |
Garrison | +0.009 |
Neg logit contributions | |
arre | -0.011 |
rule | -0.010 |
crab | -0.009 |
hig | -0.009 |
Kerr | -0.009 |
Token | great |
Token ID | 1049 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
arre | +0.452 |
rule | +0.445 |
crab | +0.379 |
hig | +0.378 |
Kerr | +0.372 |
Neg logit contributions | |
Roose | -0.426 |
Cumm | -0.410 |
STD | -0.387 |
| -0.380 |
kson | -0.376 |
Token | v |
Token ID | 410 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
arre | +0.391 |
rule | +0.384 |
crab | +0.321 |
hig | +0.320 |
Kerr | +0.314 |
Neg logit contributions | |
Roose | -0.443 |
Cumm | -0.428 |
STD | -0.406 |
| -0.399 |
kson | -0.396 |
Token | istas |
Token ID | 37503 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
arre | +6.576 |
rule | +6.128 |
crab | +4.818 |
Smash | +4.707 |
hig | +4.697 |
Neg logit contributions | |
Roose | -11.373 |
Cumm | -11.063 |
STD | -10.680 |
Garrison | -10.624 |
| -10.384 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
arre | +0.892 |
rule | +0.879 |
crab | +0.746 |
hig | +0.743 |
Kerr | +0.729 |
Neg logit contributions | |
Roose | -0.943 |
Cumm | -0.907 |
STD | -0.859 |
| -0.841 |
kson | -0.836 |
Token | You |
Token ID | 921 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Roose | +1.451 |
Cumm | +1.394 |
STD | +1.314 |
| +1.312 |
Garrison | +1.280 |
Neg logit contributions | |
arre | -1.494 |
rule | -1.462 |
hig | -1.244 |
crab | -1.242 |
Kerr | -1.206 |
Token | need |
Token ID | 761 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
Roose | +1.691 |
Cumm | +1.643 |
STD | +1.542 |
| +1.525 |
kson | +1.491 |
Neg logit contributions | |
arre | -2.113 |
rule | -2.064 |
Kerr | -1.764 |
crab | -1.761 |
hig | -1.760 |
Token | to |
Token ID | 284 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Roose | +4.354 |
Cumm | +4.272 |
STD | +4.030 |
| +3.995 |
Garrison | +3.859 |
Neg logit contributions | |
arre | -5.278 |
rule | -5.154 |
hig | -4.364 |
モ | -4.339 |
Kerr | -4.329 |
Token | at |
Token ID | 379 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
arre | +3.836 |
rule | +3.812 |
crab | +3.324 |
hig | +3.273 |
Kerr | +3.206 |
Neg logit contributions | |
Roose | -4.226 |
Cumm | -4.076 |
STD | -3.834 |
| -3.774 |
kson | -3.754 |
Token | 56 |
Token ID | 7265 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
Roose | +2.100 |
Cumm | +2.033 |
STD | +1.919 |
| +1.864 |
Garrison | +1.863 |
Neg logit contributions | |
arre | -2.301 |
rule | -2.269 |
crab | -1.893 |
hig | -1.879 |
モ | -1.845 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
arre | +0.537 |
rule | +0.529 |
crab | +0.450 |
hig | +0.449 |
Kerr | +0.439 |
Neg logit contributions | |
Roose | -0.536 |
Cumm | -0.516 |
STD | -0.488 |
| -0.479 |
Garrison | -0.473 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Roose | +1.487 |
Cumm | +1.438 |
STD | +1.356 |
| +1.331 |
kson | +1.324 |
Neg logit contributions | |
arre | -1.653 |
rule | -1.633 |
crab | -1.394 |
hig | -1.389 |
Kerr | -1.355 |
Token | km |
Token ID | 10571 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
arre | +1.387 |
rule | +1.367 |
crab | +1.173 |
hig | +1.169 |
Kerr | +1.149 |
Neg logit contributions | |
Roose | -1.294 |
Cumm | -1.242 |
STD | -1.171 |
| -1.147 |
kson | -1.138 |
Token | / |
Token ID | 14 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
arre | +4.544 |
rule | +4.487 |
crab | +3.869 |
hig | +3.846 |
Kerr | +3.766 |
Neg logit contributions | |
Roose | -4.878 |
Cumm | -4.655 |
kson | -4.370 |
STD | -4.363 |
Garrison | -4.273 |
Token | h |
Token ID | 71 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
rule | +7.271 |
arre | +7.064 |
crab | +5.923 |
hig | +5.667 |
Kerr | +5.562 |
Neg logit contributions | |
Roose | -11.137 |
Cumm | -10.744 |
kson | -9.992 |
STD | -9.869 |
Garrison | -9.827 |
Token | ( |
Token ID | 357 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
arre | +0.551 |
rule | +0.542 |
crab | +0.459 |
hig | +0.457 |
Kerr | +0.448 |
Neg logit contributions | |
Roose | -0.571 |
Cumm | -0.552 |
STD | -0.523 |
| -0.513 |
Garrison | -0.508 |
Token | 35 |
Token ID | 2327 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
Roose | +0.285 |
Cumm | +0.275 |
STD | +0.260 |
| +0.256 |
kson | +0.253 |
Neg logit contributions | |
arre | -0.277 |
rule | -0.271 |
crab | -0.233 |
hig | -0.232 |
Kerr | -0.227 |
Token | , |
Token ID | 11 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
arre | +2.845 |
rule | +2.793 |
crab | +2.394 |
hig | +2.374 |
Kerr | +2.344 |
Neg logit contributions | |
Roose | -3.292 |
Cumm | -3.146 |
STD | -2.958 |
kson | -2.925 |
Garrison | -2.923 |
Token | 000 |
Token ID | 830 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
arre | +0.005 |
rule | +0.005 |
crab | +0.004 |
hig | +0.004 |
Kerr | +0.004 |
Neg logit contributions | |
Roose | -0.004 |
Cumm | -0.004 |
STD | -0.004 |
| -0.004 |
kson | -0.004 |
Token | tactical |
Token ID | 16106 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
Roose | +2.700 |
Cumm | +2.592 |
STD | +2.444 |
| +2.427 |
onom | +2.408 |
Neg logit contributions | |
arre | -2.757 |
rule | -2.693 |
crab | -2.329 |
hig | -2.301 |
Kerr | -2.267 |
Token | v |
Token ID | 410 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
Roose | +3.420 |
Cumm | +3.305 |
STD | +3.128 |
| +3.115 |
onom | +3.098 |
Neg logit contributions | |
arre | -3.114 |
rule | -3.029 |
crab | -2.566 |
hig | -2.561 |
Kerr | -2.509 |
Token | anguard |
Token ID | 23521 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
arre | +5.840 |
rule | +5.720 |
Kerr | +4.671 |
crab | +4.625 |
hig | +4.604 |
Neg logit contributions | |
Roose | -7.862 |
Cumm | -7.519 |
STD | -7.253 |
Garrison | -6.991 |
kson | -6.968 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
arre | +0.851 |
rule | +0.838 |
crab | +0.712 |
hig | +0.710 |
Kerr | +0.697 |
Neg logit contributions | |
Roose | -0.878 |
Cumm | -0.845 |
STD | -0.800 |
| -0.784 |
kson | -0.778 |
Token | The |
Token ID | 383 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
Roose | +1.810 |
Cumm | +1.744 |
| +1.639 |
STD | +1.628 |
Garrison | +1.613 |
Neg logit contributions | |
arre | -1.869 |
rule | -1.839 |
crab | -1.592 |
hig | -1.571 |
Kerr | -1.525 |
Token | im |
Token ID | 545 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
Roose | +2.133 |
Cumm | +2.046 |
STD | +1.931 |
| +1.916 |
Garrison | +1.903 |
Neg logit contributions | |
arre | -1.948 |
rule | -1.914 |
crab | -1.613 |
hig | -1.607 |
Kerr | -1.579 |
Token | me |
Token ID | 1326 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
arre | +8.518 |
rule | +8.431 |
crab | +7.073 |
hig | +7.071 |
Kerr | +6.936 |
Neg logit contributions | |
Roose | -9.300 |
Cumm | -8.851 |
STD | -8.629 |
kson | -8.282 |
Garrison | -8.146 |
Token | di |
Token ID | 2566 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
arre | +2.911 |
rule | +2.867 |
crab | +2.382 |
hig | +2.327 |
Kerr | +2.261 |
Neg logit contributions | |
Roose | -4.166 |
Cumm | -4.037 |
STD | -3.823 |
kson | -3.761 |
| -3.749 |
Token | ate |
Token ID | 378 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
arre | +6.348 |
rule | +6.242 |
crab | +5.321 |
hig | +5.215 |
Kerr | +5.189 |
Neg logit contributions | |
Roose | -6.008 |
Cumm | -5.843 |
STD | -5.483 |
kson | -5.368 |
Garrison | -5.295 |
Token | att |
Token ID | 708 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
arre | +1.881 |
rule | +1.855 |
crab | +1.580 |
hig | +1.576 |
Kerr | +1.546 |
Neg logit contributions | |
Roose | -1.969 |
Cumm | -1.893 |
STD | -1.798 |
| -1.751 |
kson | -1.749 |
Token | a |
Token ID | 257 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
arre | +5.223 |
rule | +5.095 |
hig | +4.305 |
crab | +4.291 |
Smash | +4.181 |
Neg logit contributions | |
Roose | -5.282 |
Cumm | -4.963 |
STD | -4.825 |
kson | -4.646 |
Garrison | -4.640 |
Token | reached |
Token ID | 4251 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
arre | +3.733 |
rule | +3.593 |
hig | +3.155 |
crab | +3.153 |
Kerr | +3.051 |
Neg logit contributions | |
Roose | -3.522 |
Cumm | -3.383 |
STD | -3.188 |
kson | -3.145 |
Garrison | -3.111 |
Token | a |
Token ID | 257 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
arre | +0.076 |
rule | +0.075 |
crab | +0.064 |
hig | +0.063 |
Kerr | +0.062 |
Neg logit contributions | |
Roose | -0.072 |
Cumm | -0.070 |
STD | -0.066 |
| -0.065 |
Garrison | -0.064 |
Token | place |
Token ID | 1295 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Roose | +0.044 |
Cumm | +0.043 |
STD | +0.040 |
| +0.039 |
Garrison | +0.039 |
Neg logit contributions | |
arre | -0.051 |
rule | -0.050 |
crab | -0.043 |
hig | -0.043 |
Kerr | -0.043 |
Token | in |
Token ID | 287 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
arre | +0.318 |
rule | +0.313 |
crab | +0.263 |
hig | +0.262 |
Kerr | +0.257 |
Neg logit contributions | |
Roose | -0.355 |
Cumm | -0.342 |
STD | -0.324 |
| -0.319 |
kson | -0.316 |
Token | our |
Token ID | 674 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
arre | +2.171 |
rule | +2.139 |
hig | +1.836 |
crab | +1.834 |
Kerr | +1.802 |
Neg logit contributions | |
Roose | -2.189 |
Cumm | -2.097 |
STD | -1.981 |
kson | -1.952 |
| -1.934 |
Token | lives |
Token ID | 3160 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
arre | +0.661 |
rule | +0.650 |
crab | +0.552 |
hig | +0.551 |
Kerr | +0.537 |
Neg logit contributions | |
Roose | -0.721 |
Cumm | -0.694 |
STD | -0.657 |
| -0.644 |
kson | -0.643 |
Token | that |
Token ID | 326 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
arre | +6.480 |
rule | +6.190 |
hig | +5.505 |
crab | +5.287 |
Kerr | +5.209 |
Neg logit contributions | |
Roose | -10.915 |
Cumm | -10.502 |
STD | -10.121 |
kson | -9.868 |
govtrack | -9.776 |
Token | we |
Token ID | 356 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Roose | +0.151 |
Cumm | +0.144 |
STD | +0.136 |
| +0.134 |
Garrison | +0.132 |
Neg logit contributions | |
arre | -0.167 |
rule | -0.166 |
crab | -0.142 |
hig | -0.141 |
Kerr | -0.138 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
arre | +2.624 |
rule | +2.572 |
hig | +2.232 |
crab | +2.228 |
Kerr | +2.178 |
Neg logit contributions | |
Roose | -2.328 |
Cumm | -2.229 |
STD | -2.100 |
kson | -2.053 |
Garrison | -2.031 |
Token | we |
Token ID | 356 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
Roose | +1.009 |
Cumm | +0.968 |
STD | +0.922 |
| +0.910 |
Garrison | +0.892 |
Neg logit contributions | |
arre | -1.114 |
rule | -1.104 |
crab | -0.939 |
hig | -0.933 |
Kerr | -0.916 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
arre | +3.277 |
rule | +3.202 |
hig | +2.747 |
crab | +2.731 |
Kerr | +2.676 |
Neg logit contributions | |
Roose | -3.290 |
Cumm | -3.157 |
STD | -2.982 |
kson | -2.916 |
Garrison | -2.899 |
Token | discern |
Token ID | 22024 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Roose | +2.121 |
Cumm | +2.113 |
STD | +1.978 |
| +1.976 |
Garrison | +1.925 |
Neg logit contributions | |
arre | -2.551 |
rule | -2.493 |
Kerr | -2.097 |
ミ | -2.094 |
crab | -2.084 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
arre | +1.700 |
rule | +1.683 |
crab | +1.442 |
hig | +1.434 |
Kerr | +1.401 |
Neg logit contributions | |
Roose | -1.880 |
Cumm | -1.789 |
STD | -1.679 |
kson | -1.663 |
Garrison | -1.647 |
Token | size |
Token ID | 2546 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
arre | +2.113 |
rule | +2.106 |
crab | +1.835 |
hig | +1.829 |
Kerr | +1.793 |
Neg logit contributions | |
Roose | -1.751 |
Cumm | -1.672 |
STD | -1.549 |
kson | -1.523 |
| -1.512 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
arre | +1.997 |
rule | +1.986 |
crab | +1.676 |
hig | +1.652 |
Kerr | +1.625 |
Neg logit contributions | |
Roose | -2.446 |
Cumm | -2.345 |
STD | -2.212 |
kson | -2.182 |
Garrison | -2.163 |
Token | individual |
Token ID | 1981 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
arre | +0.903 |
rule | +0.892 |
crab | +0.784 |
hig | +0.782 |
Kerr | +0.770 |
Neg logit contributions | |
Roose | -0.587 |
Cumm | -0.558 |
STD | -0.519 |
| -0.506 |
kson | -0.500 |
Token | pixels |
Token ID | 17848 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
arre | +1.507 |
rule | +1.462 |
crab | +1.199 |
hig | +1.196 |
Kerr | +1.166 |
Neg logit contributions | |
Roose | -2.453 |
Cumm | -2.371 |
STD | -2.256 |
| -2.214 |
kson | -2.208 |
Token | due |
Token ID | 2233 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
arre | +8.157 |
rule | +7.978 |
hig | +7.358 |
crab | +7.257 |
Kerr | +6.875 |
Neg logit contributions | |
Roose | -9.648 |
Cumm | -8.776 |
kson | -8.380 |
Garrison | -8.333 |
onom | -8.267 |
Token | to |
Token ID | 284 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
arre | +0.909 |
rule | +0.902 |
crab | +0.763 |
hig | +0.756 |
Kerr | +0.743 |
Neg logit contributions | |
Roose | -1.011 |
Cumm | -0.971 |
STD | -0.917 |
kson | -0.899 |
| -0.897 |
Token | the |
Token ID | 262 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
arre | +0.033 |
rule | +0.032 |
crab | +0.027 |
hig | +0.027 |
Kerr | +0.027 |
Neg logit contributions | |
Roose | -0.031 |
Cumm | -0.030 |
STD | -0.029 |
| -0.028 |
Garrison | -0.028 |
Token | amount |
Token ID | 2033 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
arre | +3.327 |
rule | +3.253 |
crab | +2.764 |
hig | +2.737 |
Kerr | +2.674 |
Neg logit contributions | |
Roose | -4.725 |
Cumm | -4.444 |
STD | -4.225 |
kson | -4.180 |
Garrison | -4.139 |
Token | they |
Token ID | 484 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Roose | +3.000 |
Cumm | +2.924 |
STD | +2.800 |
| +2.744 |
Garrison | +2.677 |
Neg logit contributions | |
arre | -4.210 |
rule | -4.163 |
モ | -3.522 |
ミ | -3.499 |
crab | -3.490 |
Token | [ |
Token ID | 685 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
arre | +3.543 |
rule | +3.495 |
crab | +3.037 |
hig | +2.996 |
Kerr | +2.956 |
Neg logit contributions | |
Roose | -3.672 |
Cumm | -3.550 |
STD | -3.301 |
| -3.225 |
govtrack | -3.215 |
Token | edit |
Token ID | 4370 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Roose | +1.820 |
Cumm | +1.758 |
STD | +1.677 |
| +1.640 |
kson | +1.623 |
Neg logit contributions | |
arre | -1.981 |
rule | -1.924 |
hig | -1.691 |
crab | -1.672 |
Kerr | -1.635 |
Token | ] |
Token ID | 2361 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
Roose | +1.519 |
Cumm | +1.434 |
STD | +1.373 |
| +1.361 |
Garrison | +1.325 |
Neg logit contributions | |
arre | -2.269 |
rule | -2.234 |
hig | -1.977 |
crab | -1.957 |
Kerr | -1.916 |
Token |
|
Token ID | 198 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
Roose | +4.031 |
Cumm | +3.895 |
| +3.815 |
STD | +3.769 |
Garrison | +3.640 |
Neg logit contributions | |
arre | -4.772 |
rule | -4.604 |
hig | -4.139 |
crab | -4.011 |
Kerr | -3.885 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Roose | +0.628 |
Cumm | +0.607 |
STD | +0.579 |
| +0.574 |
Garrison | +0.563 |
Neg logit contributions | |
arre | -0.585 |
rule | -0.570 |
hig | -0.489 |
crab | -0.485 |
Kerr | -0.473 |
Token | Gen |
Token ID | 13746 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
Roose | +0.745 |
Cumm | +0.713 |
STD | +0.677 |
| +0.669 |
kson | +0.658 |
Neg logit contributions | |
arre | -0.799 |
rule | -0.785 |
hig | -0.681 |
crab | -0.679 |
Kerr | -0.667 |
Token | etics |
Token ID | 14596 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
arre | +9.538 |
rule | +9.199 |
crab | +7.818 |
Smash | +7.716 |
hig | +7.633 |
Neg logit contributions | |
Roose | -8.506 |
Cumm | -8.013 |
STD | -7.529 |
kson | -7.348 |
| -7.168 |
Token | [ |
Token ID | 685 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
arre | +2.099 |
rule | +2.073 |
crab | +1.747 |
hig | +1.729 |
Kerr | +1.691 |
Neg logit contributions | |
Roose | -2.562 |
Cumm | -2.470 |
STD | -2.339 |
| -2.307 |
kson | -2.294 |
Token | edit |
Token ID | 4370 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
Roose | +2.663 |
Cumm | +2.572 |
STD | +2.474 |
| +2.453 |
onom | +2.397 |
Neg logit contributions | |
arre | -3.173 |
rule | -3.031 |
hig | -2.744 |
crab | -2.678 |
Kerr | -2.643 |
Token | ] |
Token ID | 2361 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
Roose | +2.780 |
Cumm | +2.619 |
| +2.572 |
STD | +2.538 |
Garrison | +2.440 |
Neg logit contributions | |
arre | -4.803 |
rule | -4.685 |
hig | -4.287 |
crab | -4.173 |
Kerr | -4.080 |
Token |
|
Token ID | 198 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
Roose | +3.710 |
Cumm | +3.594 |
| +3.489 |
STD | +3.468 |
Garrison | +3.343 |
Neg logit contributions | |
arre | -4.315 |
rule | -4.175 |
hig | -3.721 |
crab | -3.611 |
Kerr | -3.509 |
Token | file |
Token ID | 2393 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
arre | +1.046 |
rule | +1.024 |
crab | +0.810 |
hig | +0.807 |
Kerr | +0.782 |
Neg logit contributions | |
Roose | -1.919 |
Cumm | -1.863 |
STD | -1.782 |
| -1.757 |
kson | -1.750 |
Token | you |
Token ID | 345 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
arre | +2.888 |
rule | +2.841 |
hig | +2.450 |
crab | +2.416 |
Kerr | +2.369 |
Neg logit contributions | |
Roose | -3.117 |
Cumm | -3.006 |
STD | -2.821 |
kson | -2.785 |
| -2.770 |
Token | had |
Token ID | 550 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
arre | +4.318 |
rule | +4.220 |
hig | +3.617 |
crab | +3.552 |
Smash | +3.412 |
Neg logit contributions | |
Roose | -5.614 |
Cumm | -5.460 |
STD | -5.108 |
kson | -5.038 |
Garrison | -5.014 |
Token | downloaded |
Token ID | 15680 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
arre | +2.708 |
rule | +2.641 |
hig | +2.270 |
crab | +2.254 |
Kerr | +2.196 |
Neg logit contributions | |
Roose | -3.077 |
Cumm | -2.969 |
STD | -2.785 |
| -2.749 |
kson | -2.737 |
Token | earlier |
Token ID | 2961 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
arre | +5.175 |
rule | +5.078 |
hig | +4.416 |
crab | +4.356 |
Smash | +4.279 |
Neg logit contributions | |
Roose | -6.179 |
Cumm | -5.913 |
STD | -5.537 |
kson | -5.530 |
| -5.449 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
arre | +3.268 |
rule | +3.208 |
hig | +2.744 |
crab | +2.720 |
Kerr | +2.666 |
Neg logit contributions | |
Roose | -3.785 |
Cumm | -3.632 |
STD | -3.432 |
| -3.367 |
kson | -3.359 |
Token | It |
Token ID | 632 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
arre | +7.236 |
rule | +7.235 |
Smash | +6.506 |
Kerr | +6.323 |
hig | +6.241 |
Neg logit contributions | |
Roose | -9.656 |
Cumm | -9.172 |
kson | -8.779 |
govtrack | -8.722 |
STD | -8.687 |
Token | should |
Token ID | 815 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
arre | +5.034 |
rule | +4.974 |
hig | +4.357 |
crab | +4.190 |
Smash | +4.112 |
Neg logit contributions | |
Roose | -6.394 |
Cumm | -6.198 |
STD | -5.780 |
Garrison | -5.718 |
kson | -5.641 |
Token | be |
Token ID | 307 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
arre | +2.628 |
rule | +2.605 |
hig | +2.262 |
crab | +2.238 |
Kerr | +2.193 |
Neg logit contributions | |
Roose | -2.498 |
Cumm | -2.403 |
STD | -2.241 |
kson | -2.202 |
Garrison | -2.193 |
Token | called |
Token ID | 1444 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
arre | +3.699 |
rule | +3.616 |
hig | +3.176 |
crab | +3.111 |
Kerr | +3.080 |
Neg logit contributions | |
Roose | -4.108 |
Cumm | -3.936 |
STD | -3.720 |
kson | -3.699 |
Garrison | -3.654 |
Token | plugin |
Token ID | 13877 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Roose | +0.084 |
Cumm | +0.081 |
STD | +0.077 |
| +0.076 |
Garrison | +0.075 |
Neg logit contributions | |
arre | -0.074 |
rule | -0.073 |
crab | -0.061 |
hig | -0.060 |
Kerr | -0.059 |
Token | 41 |
Token ID | 6073 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
arre | +2.614 |
rule | +2.587 |
crab | +2.221 |
hig | +2.209 |
Kerr | +2.165 |
Neg logit contributions | |
Roose | -2.865 |
Cumm | -2.753 |
STD | -2.596 |
| -2.562 |
Garrison | -2.537 |
Token | . |
Token ID | 13 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Roose | +2.201 |
Cumm | +2.137 |
STD | +2.021 |
| +1.980 |
kson | +1.936 |
Neg logit contributions | |
arre | -2.432 |
rule | -2.382 |
hig | -2.048 |
crab | -2.046 |
Kerr | -1.991 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
arre | +2.617 |
rule | +2.588 |
crab | +2.153 |
hig | +2.136 |
Kerr | +2.135 |
Neg logit contributions | |
Roose | -3.054 |
Cumm | -2.928 |
STD | -2.782 |
Garrison | -2.718 |
| -2.716 |
Token | - |
Token ID | 12 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
Roose | +1.337 |
Cumm | +1.297 |
STD | +1.224 |
| +1.199 |
kson | +1.184 |
Neg logit contributions | |
arre | -1.460 |
rule | -1.426 |
crab | -1.222 |
hig | -1.217 |
Kerr | -1.184 |
Token | meter |
Token ID | 27231 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
Roose | +1.669 |
Cumm | +1.621 |
STD | +1.505 |
| +1.486 |
kson | +1.465 |
Neg logit contributions | |
arre | -2.108 |
rule | -2.038 |
crab | -1.811 |
hig | -1.808 |
Smash | -1.749 |
Token | per |
Token ID | 583 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
arre | +4.057 |
rule | +4.010 |
crab | +3.492 |
hig | +3.470 |
Kerr | +3.376 |
Neg logit contributions | |
Roose | -4.688 |
Cumm | -4.482 |
STD | -4.216 |
| -4.215 |
kson | -4.165 |
Token | second |
Token ID | 1218 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
rule | +7.551 |
arre | +7.500 |
crab | +6.598 |
hig | +6.524 |
Kerr | +6.329 |
Neg logit contributions | |
Roose | -9.698 |
Cumm | -9.244 |
Garrison | -8.663 |
govtrack | -8.605 |
STD | -8.582 |
Token | ( |
Token ID | 357 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
arre | +1.240 |
rule | +1.221 |
crab | +1.026 |
hig | +1.022 |
Kerr | +1.000 |
Neg logit contributions | |
Roose | -1.477 |
Cumm | -1.424 |
STD | -1.350 |
| -1.328 |
kson | -1.319 |
Token | 92 |
Token ID | 5892 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
arre | +0.883 |
rule | +0.868 |
crab | +0.738 |
hig | +0.734 |
Kerr | +0.720 |
Neg logit contributions | |
Roose | -0.933 |
Cumm | -0.900 |
STD | -0.853 |
| -0.837 |
kson | -0.829 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
arre | +0.872 |
rule | +0.858 |
crab | +0.729 |
hig | +0.727 |
Kerr | +0.713 |
Neg logit contributions | |
Roose | -0.895 |
Cumm | -0.862 |
STD | -0.816 |
| -0.800 |
kson | -0.792 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
arre | +1.643 |
rule | +1.619 |
crab | +1.360 |
hig | +1.351 |
Kerr | +1.333 |
Neg logit contributions | |
Roose | -1.858 |
Cumm | -1.787 |
STD | -1.697 |
| -1.662 |
Garrison | -1.654 |
Token | : |
Token ID | 25 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
arre | +0.914 |
rule | +0.895 |
crab | +0.772 |
hig | +0.768 |
Kerr | +0.757 |
Neg logit contributions | |
Roose | -0.843 |
Cumm | -0.806 |
STD | -0.759 |
kson | -0.744 |
| -0.743 |
Token | Relic |
Token ID | 43437 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Roose | +0.154 |
Cumm | +0.149 |
STD | +0.140 |
| +0.137 |
Garrison | +0.136 |
Neg logit contributions | |
arre | -0.168 |
rule | -0.166 |
crab | -0.141 |
hig | -0.141 |
Kerr | -0.137 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
arre | +1.876 |
rule | +1.827 |
crab | +1.508 |
hig | +1.490 |
Kerr | +1.474 |
Neg logit contributions | |
Roose | -2.741 |
Cumm | -2.631 |
STD | -2.514 |
| -2.473 |
kson | -2.467 |
Token |
|
Token ID | 198 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
arre | +0.418 |
rule | +0.410 |
crab | +0.346 |
hig | +0.344 |
Kerr | +0.338 |
Neg logit contributions | |
Roose | -0.481 |
Cumm | -0.463 |
STD | -0.439 |
| -0.431 |
kson | -0.428 |
Token |
|
Token ID | 198 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
arre | +0.038 |
rule | +0.037 |
hig | +0.031 |
crab | +0.031 |
Kerr | +0.030 |
Neg logit contributions | |
Roose | -0.042 |
Cumm | -0.041 |
STD | -0.039 |
| -0.038 |
Garrison | -0.038 |
Token | Gen |
Token ID | 13746 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
arre | +0.356 |
rule | +0.351 |
crab | +0.303 |
hig | +0.302 |
Kerr | +0.296 |
Neg logit contributions | |
Roose | -0.330 |
Cumm | -0.317 |
STD | -0.300 |
| -0.295 |
kson | -0.290 |
Token | re |
Token ID | 260 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
arre | +6.655 |
rule | +6.642 |
Smash | +5.035 |
crab | +4.960 |
ミ | +4.935 |
Neg logit contributions | |
Roose | -11.118 |
Cumm | -10.442 |
STD | -10.105 |
kson | -9.928 |
govtrack | -9.907 |
Token | : |
Token ID | 25 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
arre | +1.540 |
rule | +1.522 |
crab | +1.305 |
hig | +1.293 |
Kerr | +1.278 |
Neg logit contributions | |
Roose | -1.466 |
Cumm | -1.396 |
STD | -1.314 |
kson | -1.291 |
| -1.286 |
Token | Strategy |
Token ID | 20561 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
arre | +3.043 |
rule | +3.004 |
crab | +2.556 |
hig | +2.546 |
Smash | +2.512 |
Neg logit contributions | |
Roose | -3.422 |
Cumm | -3.248 |
STD | -3.065 |
kson | -3.049 |
| -3.020 |
Token |
|
Token ID | 198 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
arre | +5.252 |
rule | +5.184 |
crab | +4.376 |
hig | +4.344 |
Smash | +4.333 |
Neg logit contributions | |
Roose | -6.512 |
Cumm | -6.088 |
kson | -5.795 |
STD | -5.778 |
govtrack | -5.647 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
arre | +0.354 |
rule | +0.347 |
crab | +0.292 |
hig | +0.292 |
Kerr | +0.285 |
Neg logit contributions | |
Roose | -0.408 |
Cumm | -0.394 |
STD | -0.375 |
| -0.369 |
Garrison | -0.365 |
Token | James |
Token ID | 3700 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Roose | +0.533 |
Cumm | +0.513 |
STD | +0.485 |
| +0.475 |
Garrison | +0.473 |
Neg logit contributions | |
arre | -0.533 |
rule | -0.525 |
crab | -0.445 |
hig | -0.444 |
Kerr | -0.435 |
Token | Gunn |
Token ID | 40837 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Roose | +2.331 |
Cumm | +2.254 |
STD | +2.101 |
Garrison | +2.092 |
| +2.054 |
Neg logit contributions | |
arre | -2.320 |
rule | -2.284 |
hig | -1.960 |
crab | -1.944 |
モ | -1.869 |
Token | 's |
Token ID | 338 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
Roose | +0.324 |
Cumm | +0.310 |
STD | +0.292 |
| +0.286 |
Garrison | +0.283 |
Neg logit contributions | |
arre | -0.390 |
rule | -0.385 |
crab | -0.333 |
hig | -0.332 |
Kerr | -0.326 |
Token | GU |
Token ID | 19348 |
Feature activation | +7.63e+00 |
Pos logit contributions | |
arre | +0.025 |
rule | +0.024 |
crab | +0.020 |
hig | +0.020 |
Kerr | +0.020 |
Neg logit contributions | |
Roose | -0.028 |
Cumm | -0.027 |
STD | -0.026 |
| -0.025 |
Garrison | -0.025 |
Token | ARD |
Token ID | 9795 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
arre | +5.077 |
rule | +5.064 |
crab | +4.346 |
hig | +4.298 |
Kerr | +4.243 |
Neg logit contributions | |
Roose | -5.633 |
Cumm | -5.362 |
kson | -5.029 |
STD | -5.018 |
| -5.017 |
Token | I |
Token ID | 40 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
arre | +1.797 |
rule | +1.777 |
crab | +1.501 |
hig | +1.484 |
Kerr | +1.477 |
Neg logit contributions | |
Roose | -2.049 |
Cumm | -1.972 |
STD | -1.864 |
| -1.835 |
kson | -1.832 |
Token | ANS |
Token ID | 15037 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
arre | +6.614 |
rule | +6.142 |
crab | +5.420 |
Kerr | +5.126 |
hig | +5.062 |
Neg logit contributions | |
Roose | -10.630 |
Cumm | -10.375 |
govtrack | -9.823 |
kson | -9.573 |
onom | -9.535 |
Token | OF |
Token ID | 3963 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
arre | +1.793 |
rule | +1.778 |
crab | +1.411 |
hig | +1.390 |
Kerr | +1.354 |
Neg logit contributions | |
Roose | -3.417 |
Cumm | -3.305 |
STD | -3.159 |
kson | -3.119 |
onom | -3.083 |
Token | THE |
Token ID | 3336 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
arre | +3.050 |
rule | +2.994 |
crab | +2.516 |
Kerr | +2.514 |
hig | +2.487 |
Neg logit contributions | |
Roose | -5.663 |
Cumm | -5.375 |
govtrack | -5.125 |
kson | -5.102 |
horse | -5.037 |
Token | G |
Token ID | 402 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
rule | +3.062 |
arre | +3.004 |
crab | +2.620 |
hig | +2.585 |
Kerr | +2.582 |
Neg logit contributions | |
Roose | -2.779 |
Cumm | -2.721 |
kson | -2.498 |
STD | -2.471 |
onom | -2.425 |
Token | AL |
Token ID | 1847 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Roose | +0.924 |
Cumm | +0.882 |
STD | +0.865 |
| +0.855 |
kson | +0.842 |
Neg logit contributions | |
arre | -0.923 |
rule | -0.884 |
hig | -0.762 |
crab | -0.758 |
モ | -0.755 |
Token | Offensive |
Token ID | 26855 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
arre | +2.078 |
rule | +2.061 |
crab | +1.744 |
hig | +1.723 |
Kerr | +1.709 |
Neg logit contributions | |
Roose | -2.163 |
Cumm | -2.095 |
STD | -1.976 |
| -1.937 |
kson | -1.923 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
arre | +0.528 |
rule | +0.521 |
crab | +0.443 |
hig | +0.440 |
Kerr | +0.432 |
Neg logit contributions | |
Roose | -0.560 |
Cumm | -0.540 |
STD | -0.511 |
| -0.500 |
kson | -0.498 |
Token |
|
Token ID | 198 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
arre | +1.078 |
rule | +1.063 |
crab | +0.901 |
hig | +0.896 |
Kerr | +0.886 |
Neg logit contributions | |
Roose | -1.154 |
Cumm | -1.115 |
STD | -1.058 |
| -1.034 |
kson | -1.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Roose | +0.349 |
Cumm | +0.338 |
STD | +0.321 |
| +0.319 |
Garrison | +0.312 |
Neg logit contributions | |
arre | -0.322 |
rule | -0.314 |
hig | -0.269 |
crab | -0.267 |
Kerr | -0.260 |
Token | On |
Token ID | 2202 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
arre | +1.117 |
rule | +1.106 |
crab | +0.939 |
hig | +0.934 |
Kerr | +0.918 |
Neg logit contributions | |
Roose | -1.067 |
Cumm | -1.028 |
STD | -0.970 |
| -0.943 |
kson | -0.943 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.88e+01 |
Pos logit contributions | |
Roose | +5.318 |
Cumm | +5.196 |
| +4.867 |
STD | +4.762 |
Garrison | +4.720 |
Neg logit contributions | |
arre | -7.518 |
rule | -7.198 |
crab | -6.224 |
モ | -6.157 |
hig | -6.069 |
Token | September |
Token ID | 2693 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Cumm | +7.972 |
| +7.961 |
Roose | +7.879 |
Garrison | +7.391 |
STD | +7.124 |
Neg logit contributions | |
rule | -15.115 |
arre | -14.745 |
hig | -12.713 |
antry | -12.704 |
crab | -12.631 |
Token | 1941 |
Token ID | 23234 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Roose | +1.488 |
Cumm | +1.431 |
STD | +1.357 |
| +1.335 |
Garrison | +1.330 |
Neg logit contributions | |
arre | -1.241 |
rule | -1.214 |
hig | -1.010 |
crab | -1.010 |
Kerr | -0.987 |
Token | Zh |
Token ID | 10511 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
arre | +2.161 |
rule | +2.132 |
crab | +1.839 |
hig | +1.830 |
Kerr | +1.813 |
Neg logit contributions | |
Roose | -2.050 |
Cumm | -1.980 |
STD | -1.884 |
| -1.839 |
kson | -1.836 |
Token | uk |
Token ID | 2724 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
arre | +0.348 |
rule | +0.340 |
crab | +0.265 |
hig | +0.263 |
Kerr | +0.253 |
Neg logit contributions | |
Roose | -0.731 |
Cumm | -0.709 |
STD | -0.681 |
| -0.674 |
kson | -0.671 |
Token | ov |
Token ID | 709 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
arre | +0.431 |
rule | +0.422 |
crab | +0.336 |
hig | +0.334 |
Kerr | +0.325 |
Neg logit contributions | |
Roose | -0.761 |
Cumm | -0.738 |
STD | -0.707 |
| -0.696 |
kson | -0.692 |
Token | The |
Token ID | 464 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
Roose | +1.690 |
Cumm | +1.617 |
| +1.544 |
STD | +1.533 |
onom | +1.513 |
Neg logit contributions | |
arre | -1.898 |
rule | -1.851 |
crab | -1.630 |
hig | -1.621 |
Kerr | -1.588 |
Token | Nov |
Token ID | 5267 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
Roose | +4.892 |
Cumm | +4.659 |
STD | +4.493 |
| +4.319 |
Garrison | +4.309 |
Neg logit contributions | |
arre | -5.288 |
rule | -5.165 |
crab | -4.353 |
Kerr | -4.346 |
hig | -4.318 |
Token | ice |
Token ID | 501 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Roose | +2.249 |
Cumm | +2.153 |
STD | +2.052 |
| +2.015 |
onom | +1.985 |
Neg logit contributions | |
arre | -3.015 |
rule | -2.963 |
hig | -2.629 |
crab | -2.611 |
Kerr | -2.597 |
Token | No |
Token ID | 1400 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
arre | +0.191 |
rule | +0.189 |
crab | +0.161 |
hig | +0.160 |
Kerr | +0.157 |
Neg logit contributions | |
Roose | -0.213 |
Cumm | -0.205 |
STD | -0.194 |
| -0.191 |
kson | -0.190 |
Token | Long |
Token ID | 5882 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
arre | +0.680 |
rule | +0.672 |
crab | +0.589 |
hig | +0.586 |
Kerr | +0.581 |
Neg logit contributions | |
Roose | -0.481 |
Cumm | -0.457 |
STD | -0.426 |
| -0.416 |
kson | -0.414 |
Token | er |
Token ID | 263 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
Roose | +1.437 |
Cumm | +1.375 |
STD | +1.301 |
| +1.275 |
kson | +1.262 |
Neg logit contributions | |
arre | -2.141 |
rule | -2.113 |
hig | -1.869 |
crab | -1.859 |
Kerr | -1.811 |
Token | Podcast |
Token ID | 16036 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
Roose | +7.415 |
Cumm | +7.004 |
STD | +6.916 |
Garrison | +6.833 |
onom | +6.629 |
Neg logit contributions | |
rule | -12.693 |
arre | -12.657 |
crab | -10.645 |
モ | -10.642 |
ミ | -10.591 |
Token | intro |
Token ID | 18951 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Roose | +4.453 |
Cumm | +4.245 |
STD | +4.010 |
Garrison | +3.983 |
| +3.964 |
Neg logit contributions | |
arre | -5.135 |
rule | -5.127 |
crab | -4.296 |
Kerr | -4.231 |
モ | -4.214 |
Token | music |
Token ID | 2647 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Roose | +1.342 |
Cumm | +1.297 |
STD | +1.227 |
| +1.210 |
Garrison | +1.195 |
Neg logit contributions | |
arre | -1.370 |
rule | -1.351 |
crab | -1.149 |
hig | -1.141 |
Kerr | -1.124 |
Token | was |
Token ID | 373 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
Roose | +2.110 |
Cumm | +2.046 |
STD | +1.918 |
| +1.912 |
Garrison | +1.879 |
Neg logit contributions | |
arre | -2.305 |
rule | -2.269 |
crab | -1.950 |
hig | -1.926 |
Kerr | -1.893 |
Token | composed |
Token ID | 13160 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Roose | +3.755 |
Cumm | +3.594 |
| +3.414 |
Garrison | +3.396 |
STD | +3.350 |
Neg logit contributions | |
arre | -4.134 |
rule | -4.133 |
crab | -3.506 |
hig | -3.430 |
Kerr | -3.376 |
Token | cl |
Token ID | 537 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
arre | +3.147 |
rule | +3.097 |
hig | +2.651 |
crab | +2.646 |
Kerr | +2.557 |
Neg logit contributions | |
Roose | -3.932 |
Cumm | -3.730 |
kson | -3.512 |
STD | -3.496 |
Garrison | -3.471 |
Token | ojure |
Token ID | 32511 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Roose | +0.361 |
Cumm | +0.344 |
STD | +0.321 |
| +0.316 |
kson | +0.314 |
Neg logit contributions | |
arre | -0.549 |
rule | -0.541 |
crab | -0.480 |
hig | -0.479 |
Kerr | -0.471 |
Token | | |
Token ID | 930 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
Roose | +1.595 |
Cumm | +1.550 |
STD | +1.483 |
| +1.457 |
Garrison | +1.442 |
Neg logit contributions | |
arre | -1.024 |
rule | -1.006 |
crab | -0.816 |
hig | -0.810 |
Kerr | -0.792 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
arre | +0.061 |
rule | +0.060 |
crab | +0.051 |
hig | +0.051 |
Kerr | +0.050 |
Neg logit contributions | |
Roose | -0.063 |
Cumm | -0.061 |
STD | -0.058 |
| -0.057 |
kson | -0.056 |
Token | . |
Token ID | 764 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Roose | +2.994 |
Cumm | +2.741 |
| +2.700 |
STD | +2.568 |
Garrison | +2.340 |
Neg logit contributions | |
arre | -11.379 |
rule | -11.081 |
��� | -10.427 |
hig | -10.258 |
crab | -10.097 |
Token | 7 |
Token ID | 767 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
arre | +1.135 |
rule | +1.118 |
crab | +0.951 |
hig | +0.947 |
Kerr | +0.930 |
Neg logit contributions | |
Roose | -1.160 |
Cumm | -1.117 |
STD | -1.057 |
| -1.037 |
Garrison | -1.027 |
Token | . |
Token ID | 764 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Roose | +4.064 |
Cumm | +3.787 |
| +3.770 |
STD | +3.441 |
Garrison | +3.129 |
Neg logit contributions | |
arre | -15.429 |
rule | -14.982 |
��� | -14.779 |
hig | -14.194 |
undai | -14.189 |
Token | 0 |
Token ID | 657 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
arre | +0.999 |
rule | +0.985 |
crab | +0.839 |
hig | +0.837 |
Kerr | +0.822 |
Neg logit contributions | |
Roose | -1.016 |
Cumm | -0.976 |
STD | -0.923 |
| -0.904 |
kson | -0.900 |
Token | | |
Token ID | 930 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Roose | +1.793 |
Cumm | +1.748 |
STD | +1.679 |
| +1.658 |
Garrison | +1.624 |
Neg logit contributions | |
arre | -1.236 |
rule | -1.206 |
crab | -0.994 |
hig | -0.987 |
Kerr | -0.956 |
Token | 40 |
Token ID | 2319 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Roose | +1.153 |
Cumm | +1.111 |
STD | +1.046 |
| +1.029 |
Garrison | +1.008 |
Neg logit contributions | |
arre | -1.373 |
rule | -1.359 |
crab | -1.162 |
hig | -1.158 |
Kerr | -1.133 |
Token | 93 |
Token ID | 6052 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Roose | +3.126 |
Cumm | +3.018 |
STD | +2.867 |
| +2.847 |
kson | +2.780 |
Neg logit contributions | |
arre | -3.069 |
rule | -2.998 |
hig | -2.562 |
crab | -2.553 |
Kerr | -2.483 |
Token | inct |
Token ID | 4612 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
arre | +0.192 |
rule | +0.190 |
hig | +0.167 |
crab | +0.166 |
Kerr | +0.163 |
Neg logit contributions | |
Roose | -0.131 |
Cumm | -0.125 |
STD | -0.115 |
| -0.113 |
kson | -0.112 |
Token | ure |
Token ID | 495 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
arre | +1.563 |
rule | +1.544 |
crab | +1.352 |
hig | +1.346 |
Kerr | +1.328 |
Neg logit contributions | |
Roose | -1.042 |
Cumm | -0.994 |
STD | -0.923 |
| -0.899 |
Garrison | -0.893 |
Token | or |
Token ID | 393 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
Roose | +3.280 |
Cumm | +3.200 |
STD | +3.052 |
| +2.981 |
Garrison | +2.926 |
Neg logit contributions | |
arre | -3.675 |
rule | -3.528 |
モ | -2.988 |
crab | -2.975 |
hig | -2.953 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Roose | +0.511 |
Cumm | +0.495 |
STD | +0.469 |
| +0.461 |
Garrison | +0.455 |
Neg logit contributions | |
arre | -0.507 |
rule | -0.498 |
crab | -0.420 |
hig | -0.419 |
Kerr | -0.410 |
Token | few |
Token ID | 1178 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Roose | +1.344 |
Cumm | +1.305 |
STD | +1.234 |
| +1.210 |
Garrison | +1.201 |
Neg logit contributions | |
arre | -1.263 |
rule | -1.238 |
crab | -1.034 |
hig | -1.031 |
Kerr | -1.012 |
Token | dro |
Token ID | 3102 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Roose | +1.186 |
Cumm | +1.144 |
STD | +1.083 |
| +1.059 |
Garrison | +1.052 |
Neg logit contributions | |
arre | -1.317 |
rule | -1.295 |
hig | -1.095 |
crab | -1.093 |
Kerr | -1.077 |
Token | pper |
Token ID | 2848 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Roose | +8.454 |
Cumm | +8.107 |
onom | +7.754 |
kson | +7.645 |
STD | +7.398 |
Neg logit contributions | |
arre | -11.332 |
rule | -10.893 |
crab | -9.903 |
ミ | -9.827 |
Kerr | -9.738 |
Token | ful |
Token ID | 913 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Roose | +1.640 |
Cumm | +1.585 |
STD | +1.506 |
| +1.478 |
onom | +1.459 |
Neg logit contributions | |
arre | -1.698 |
rule | -1.663 |
crab | -1.408 |
hig | -1.398 |
Kerr | -1.386 |
Token | s |
Token ID | 82 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
Roose | +1.284 |
Cumm | +1.243 |
STD | +1.186 |
| +1.169 |
kson | +1.156 |
Neg logit contributions | |
arre | -1.123 |
rule | -1.105 |
crab | -0.919 |
hig | -0.912 |
Kerr | -0.903 |
Token | of |
Token ID | 286 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
Roose | +2.264 |
Cumm | +2.213 |
STD | +2.093 |
| +2.059 |
onom | +2.029 |
Neg logit contributions | |
arre | -2.538 |
rule | -2.484 |
crab | -2.095 |
hig | -2.081 |
Kerr | -2.080 |
Token | t |
Token ID | 256 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Roose | +0.709 |
Cumm | +0.688 |
STD | +0.653 |
| +0.641 |
Garrison | +0.634 |
Neg logit contributions | |
arre | -0.674 |
rule | -0.658 |
crab | -0.550 |
hig | -0.549 |
Kerr | -0.540 |
Token | s |
Token ID | 82 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
Roose | +5.713 |
Cumm | +5.353 |
| +5.331 |
STD | +5.274 |
kson | +5.133 |
Neg logit contributions | |
arre | -6.106 |
rule | -5.982 |
Kerr | -5.358 |
モ | -5.276 |
hig | -5.265 |
Token | invoke |
Token ID | 26342 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
Roose | +4.357 |
Cumm | +4.221 |
STD | +4.036 |
| +3.969 |
onom | +3.845 |
Neg logit contributions | |
arre | -4.606 |
rule | -4.468 |
crab | -3.890 |
hig | -3.866 |
Kerr | -3.801 |
Token | local |
Token ID | 1957 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
Roose | +3.444 |
Cumm | +3.261 |
STD | +3.230 |
| +3.102 |
Garrison | +2.992 |
Neg logit contributions | |
arre | -4.127 |
rule | -4.009 |
crab | -3.466 |
hig | -3.454 |
Kerr | -3.421 |
Token | - |
Token ID | 532 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
Roose | +6.745 |
STD | +6.566 |
Cumm | +6.263 |
| +6.261 |
Garrison | +5.851 |
Neg logit contributions | |
arre | -9.610 |
rule | -9.263 |
hig | -8.148 |
Kerr | -8.121 |
crab | -8.119 |
Token | f |
Token ID | 69 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
Roose | +3.642 |
Cumm | +3.465 |
STD | +3.367 |
| +3.222 |
Garrison | +3.219 |
Neg logit contributions | |
arre | -4.803 |
rule | -4.610 |
crab | -4.150 |
hig | -4.138 |
Kerr | -4.050 |
Token | test |
Token ID | 1332 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
Roose | +4.844 |
STD | +4.673 |
Cumm | +4.639 |
| +4.436 |
Garrison | +4.284 |
Neg logit contributions | |
arre | -5.650 |
rule | -5.458 |
Kerr | -4.717 |
crab | -4.716 |
hig | -4.694 |
Token | - |
Token ID | 532 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
Roose | +6.724 |
STD | +6.566 |
| +6.350 |
Cumm | +6.319 |
Garrison | +5.861 |
Neg logit contributions | |
arre | -11.827 |
rule | -11.431 |
モ | -10.370 |
hig | -10.309 |
ミ | -10.221 |
Token | p |
Token ID | 79 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
Roose | +1.928 |
Cumm | +1.848 |
STD | +1.780 |
| +1.730 |
Garrison | +1.713 |
Neg logit contributions | |
arre | -1.920 |
rule | -1.867 |
crab | -1.617 |
hig | -1.614 |
Kerr | -1.568 |
Token | data |
Token ID | 1366 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
Roose | +4.196 |
Cumm | +4.020 |
STD | +4.009 |
| +3.822 |
Garrison | +3.689 |
Neg logit contributions | |
arre | -4.744 |
rule | -4.594 |
crab | -3.985 |
hig | -3.979 |
モ | -3.943 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
Roose | +3.475 |
Cumm | +3.320 |
STD | +3.218 |
| +3.141 |
onom | +3.054 |
Neg logit contributions | |
arre | -4.167 |
rule | -4.073 |
crab | -3.549 |
hig | -3.535 |
Kerr | -3.461 |
Token | json |
Token ID | 17752 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
arre | +0.008 |
rule | +0.008 |
crab | +0.006 |
hig | +0.006 |
Kerr | +0.006 |
Neg logit contributions | |
Roose | -0.012 |
Cumm | -0.012 |
STD | -0.011 |
| -0.011 |
kson | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
Roose | +2.124 |
Cumm | +2.029 |
STD | +1.925 |
| +1.896 |
onom | +1.889 |
Neg logit contributions | |
arre | -2.091 |
rule | -2.040 |
crab | -1.729 |
hig | -1.699 |
Kerr | -1.669 |
Token | Nov |
Token ID | 5267 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Roose | +3.338 |
Cumm | +3.091 |
STD | +2.942 |
Garrison | +2.838 |
onom | +2.831 |
Neg logit contributions | |
arre | -5.520 |
rule | -5.400 |
crab | -4.692 |
モ | -4.650 |
Kerr | -4.625 |
Token | ice |
Token ID | 501 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
Roose | +2.243 |
Cumm | +2.137 |
STD | +2.032 |
| +1.989 |
onom | +1.973 |
Neg logit contributions | |
arre | -3.055 |
rule | -3.008 |
crab | -2.656 |
hig | -2.645 |
Kerr | -2.624 |
Token | No |
Token ID | 1400 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Roose | +0.026 |
Cumm | +0.025 |
STD | +0.024 |
| +0.024 |
kson | +0.023 |
Neg logit contributions | |
arre | -0.027 |
rule | -0.026 |
crab | -0.022 |
hig | -0.022 |
Kerr | -0.022 |
Token | Long |
Token ID | 5882 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Roose | +0.160 |
Cumm | +0.153 |
STD | +0.142 |
| +0.139 |
Garrison | +0.137 |
Neg logit contributions | |
arre | -0.239 |
rule | -0.236 |
crab | -0.207 |
hig | -0.206 |
Kerr | -0.203 |
Token | er |
Token ID | 263 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
Roose | +1.034 |
Cumm | +0.993 |
STD | +0.936 |
| +0.916 |
kson | +0.905 |
Neg logit contributions | |
arre | -1.517 |
rule | -1.498 |
crab | -1.316 |
hig | -1.314 |
Kerr | -1.278 |
Token | podcast |
Token ID | 9905 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
Roose | +5.708 |
STD | +5.141 |
Cumm | +5.073 |
onom | +5.038 |
Garrison | +4.980 |
Neg logit contributions | |
rule | -12.963 |
arre | -12.839 |
ミ | -11.255 |
crab | -11.116 |
モ | -11.060 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Roose | +4.003 |
Cumm | +3.760 |
onom | +3.636 |
STD | +3.613 |
| +3.593 |
Neg logit contributions | |
arre | -4.724 |
rule | -4.691 |
crab | -3.991 |
hig | -3.920 |
Kerr | -3.908 |
Token | It |
Token ID | 632 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Roose | +0.907 |
Cumm | +0.870 |
STD | +0.824 |
| +0.816 |
Garrison | +0.805 |
Neg logit contributions | |
arre | -0.946 |
rule | -0.929 |
crab | -0.795 |
hig | -0.788 |
Kerr | -0.767 |
Token | helps |
Token ID | 5419 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Roose | +1.190 |
Cumm | +1.143 |
STD | +1.088 |
| +1.077 |
onom | +1.066 |
Neg logit contributions | |
arre | -1.120 |
rule | -1.100 |
crab | -0.932 |
hig | -0.916 |
Kerr | -0.913 |
Token | immensely |
Token ID | 29731 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
arre | +1.190 |
rule | +1.175 |
crab | +1.016 |
hig | +1.012 |
Kerr | +0.994 |
Neg logit contributions | |
Roose | -1.056 |
Cumm | -1.015 |
STD | -0.954 |
| -0.934 |
kson | -0.929 |
Token | 7 |
Token ID | 767 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
arre | +2.367 |
rule | +2.344 |
crab | +2.015 |
hig | +2.009 |
Kerr | +1.970 |
Neg logit contributions | |
Roose | -2.291 |
Cumm | -2.194 |
STD | -2.065 |
kson | -2.027 |
| -2.021 |
Token | sweet |
Token ID | 6029 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
arre | +1.545 |
rule | +1.521 |
crab | +1.296 |
hig | +1.292 |
Kerr | +1.268 |
Neg logit contributions | |
Roose | -1.565 |
Cumm | -1.500 |
STD | -1.417 |
| -1.387 |
kson | -1.384 |
Token | put |
Token ID | 1234 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
arre | +1.143 |
rule | +1.126 |
crab | +0.953 |
hig | +0.949 |
Kerr | +0.930 |
Neg logit contributions | |
Roose | -1.249 |
Cumm | -1.202 |
STD | -1.139 |
| -1.117 |
kson | -1.111 |
Token | ts |
Token ID | 912 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
arre | +3.268 |
rule | +3.244 |
crab | +2.709 |
hig | +2.676 |
Smash | +2.593 |
Neg logit contributions | |
Roose | -4.430 |
Cumm | -4.291 |
Garrison | -4.034 |
STD | -4.034 |
| -3.982 |
Token | . |
Token ID | 13 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
arre | +0.436 |
rule | +0.429 |
crab | +0.365 |
hig | +0.363 |
Kerr | +0.358 |
Neg logit contributions | |
Roose | -0.432 |
Cumm | -0.416 |
STD | -0.393 |
| -0.387 |
Garrison | -0.383 |
Token | Wo |
Token ID | 22173 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
arre | +2.572 |
rule | +2.557 |
crab | +2.146 |
hig | +2.134 |
Kerr | +2.129 |
Neg logit contributions | |
Roose | -2.999 |
Cumm | -2.880 |
STD | -2.732 |
kson | -2.685 |
Garrison | -2.662 |
Token | oh |
Token ID | 1219 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
Roose | +8.184 |
Cumm | +7.503 |
STD | +7.135 |
| +6.900 |
onom | +6.872 |
Neg logit contributions | |
arre | -10.576 |
rule | -10.227 |
ドラゴン | -9.063 |
hig | -8.776 |
crab | -8.774 |
Token | oo |
Token ID | 2238 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
Roose | +3.061 |
Cumm | +2.908 |
STD | +2.693 |
| +2.691 |
kson | +2.662 |
Neg logit contributions | |
arre | -3.554 |
rule | -3.466 |
hig | -2.980 |
crab | -2.966 |
Kerr | -2.912 |
Token | ! |
Token ID | 0 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Roose | +2.985 |
Cumm | +2.877 |
STD | +2.696 |
| +2.687 |
Garrison | +2.654 |
Neg logit contributions | |
arre | -3.092 |
rule | -2.987 |
hig | -2.546 |
crab | -2.527 |
Kerr | -2.491 |
Token |
|
Token ID | 198 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Roose | +1.302 |
Cumm | +1.260 |
STD | +1.190 |
| +1.179 |
Garrison | +1.159 |
Neg logit contributions | |
arre | -1.264 |
rule | -1.229 |
crab | -1.043 |
hig | -1.039 |
Kerr | -1.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
arre | +0.456 |
rule | +0.449 |
crab | +0.377 |
hig | +0.375 |
Kerr | +0.367 |
Neg logit contributions | |
Roose | -0.538 |
Cumm | -0.519 |
STD | -0.493 |
| -0.485 |
kson | -0.481 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
Roose | +3.412 |
Cumm | +3.330 |
| +3.121 |
STD | +3.117 |
onom | +3.061 |
Neg logit contributions | |
arre | -3.450 |
rule | -3.382 |
hig | -2.869 |
crab | -2.856 |
ミ | -2.770 |
Token | The |
Token ID | 383 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
arre | +0.421 |
rule | +0.414 |
crab | +0.356 |
hig | +0.354 |
Kerr | +0.348 |
Neg logit contributions | |
Roose | -0.381 |
Cumm | -0.366 |
STD | -0.344 |
| -0.337 |
Garrison | -0.335 |
Token | Economist |
Token ID | 36619 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
Roose | +1.739 |
Cumm | +1.667 |
STD | +1.579 |
| +1.551 |
Garrison | +1.534 |
Neg logit contributions | |
arre | -1.724 |
rule | -1.709 |
hig | -1.445 |
crab | -1.438 |
Kerr | -1.401 |
Token | Newspaper |
Token ID | 49598 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
Cumm | +3.771 |
Roose | +3.762 |
STD | +3.585 |
onom | +3.490 |
| +3.445 |
Neg logit contributions | |
rule | -5.301 |
arre | -5.293 |
crab | -4.619 |
hig | -4.615 |
Kerr | -4.563 |
Token | Limited |
Token ID | 15302 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
Roose | +3.842 |
Cumm | +3.628 |
| +3.481 |
STD | +3.468 |
Garrison | +3.398 |
Neg logit contributions | |
rule | -4.612 |
arre | -4.592 |
hig | -3.844 |
crab | -3.830 |
Kerr | -3.737 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
Roose | +6.626 |
| +6.578 |
Cumm | +6.566 |
STD | +6.255 |
Garrison | +6.007 |
Neg logit contributions | |
rule | -9.329 |
arre | -9.248 |
hig | -7.984 |
crab | -7.963 |
Kerr | -7.791 |
Token | London |
Token ID | 3576 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Roose | +7.637 |
Cumm | +7.357 |
STD | +7.284 |
| +7.143 |
Garrison | +6.891 |
Neg logit contributions | |
arre | -10.727 |
rule | -10.305 |
crab | -9.478 |
hig | -9.116 |
antry | -8.921 |
Token | . |
Token ID | 13 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
Cumm | +5.516 |
Roose | +5.493 |
| +5.341 |
STD | +5.324 |
onom | +5.045 |
Neg logit contributions | |
rule | -8.227 |
arre | -8.078 |
hig | -7.206 |
crab | -7.054 |
ミ | -7.043 |
Token | All |
Token ID | 1439 |
Feature activation | -8.38e+00 |
Pos logit contributions | |
Roose | +5.864 |
Cumm | +5.542 |
| +5.435 |
STD | +5.375 |
Garrison | +5.319 |
Neg logit contributions | |
arre | -7.377 |
rule | -7.165 |
crab | -6.246 |
rog | -6.082 |
hig | -6.078 |
Token | Rights |
Token ID | 6923 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
Roose | +4.241 |
Cumm | +4.024 |
| +3.790 |
STD | +3.771 |
onom | +3.670 |
Neg logit contributions | |
rule | -7.424 |
arre | -7.243 |
hig | -6.422 |
Kerr | -6.401 |
モ | -6.380 |
Token | Reserved |
Token ID | 33876 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
Roose | +2.404 |
Cumm | +2.307 |
STD | +2.173 |
| +2.159 |
Garrison | +2.104 |
Neg logit contributions | |
arre | -2.852 |
rule | -2.795 |
crab | -2.412 |
hig | -2.380 |
モ | -2.289 |
Token | a |
Token ID | 257 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Roose | +1.246 |
Cumm | +1.203 |
STD | +1.146 |
| +1.112 |
Garrison | +1.109 |
Neg logit contributions | |
arre | -1.374 |
rule | -1.351 |
hig | -1.151 |
crab | -1.147 |
Kerr | -1.123 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
Roose | +1.290 |
Cumm | +1.251 |
STD | +1.190 |
| +1.158 |
Garrison | +1.156 |
Neg logit contributions | |
arre | -1.267 |
rule | -1.246 |
hig | -1.042 |
crab | -1.042 |
Kerr | -1.020 |
Token | stream |
Token ID | 4269 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
Roose | +0.598 |
Cumm | +0.575 |
STD | +0.539 |
| +0.525 |
Garrison | +0.523 |
Neg logit contributions | |
arre | -0.772 |
rule | -0.762 |
hig | -0.659 |
crab | -0.659 |
Kerr | -0.647 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
arre | +0.051 |
rule | +0.050 |
crab | +0.043 |
hig | +0.043 |
Kerr | +0.042 |
Neg logit contributions | |
Roose | -0.050 |
Cumm | -0.048 |
STD | -0.045 |
| -0.044 |
kson | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Roose | +1.457 |
Cumm | +1.407 |
STD | +1.342 |
| +1.304 |
Garrison | +1.299 |
Neg logit contributions | |
arre | -1.589 |
rule | -1.561 |
hig | -1.327 |
crab | -1.321 |
Kerr | -1.296 |
Token | so |
Token ID | 523 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
arre | +0.997 |
rule | +0.982 |
crab | +0.838 |
hig | +0.833 |
Kerr | +0.818 |
Neg logit contributions | |
Roose | -1.022 |
Cumm | -0.982 |
STD | -0.929 |
| -0.911 |
kson | -0.905 |
Token | on |
Token ID | 319 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Roose | +6.261 |
Cumm | +5.969 |
onom | +5.703 |
| +5.636 |
Garrison | +5.537 |
Neg logit contributions | |
arre | -11.786 |
rule | -11.757 |
hig | -10.167 |
crab | -10.028 |
Kerr | -10.027 |
Token | — |
Token ID | 960 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
Roose | +0.921 |
Cumm | +0.885 |
STD | +0.834 |
| +0.816 |
Garrison | +0.808 |
Neg logit contributions | |
arre | -1.058 |
rule | -1.043 |
crab | -0.897 |
hig | -0.895 |
Kerr | -0.880 |
Token | you |
Token ID | 5832 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
rule | +3.523 |
arre | +3.480 |
crab | +2.873 |
hig | +2.852 |
Kerr | +2.819 |
Neg logit contributions | |
Roose | -4.051 |
Cumm | -3.869 |
STD | -3.666 |
kson | -3.585 |
Garrison | -3.565 |
Token | need |
Token ID | 761 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
arre | +0.133 |
rule | +0.131 |
crab | +0.113 |
hig | +0.113 |
Kerr | +0.111 |
Neg logit contributions | |
Roose | -0.109 |
Cumm | -0.105 |
STD | -0.099 |
| -0.097 |
Garrison | -0.096 |
Token | Pixel |
Token ID | 11349 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Roose | +3.195 |
Cumm | +3.111 |
STD | +2.955 |
| +2.892 |
Garrison | +2.871 |
Neg logit contributions | |
arre | -3.459 |
rule | -3.360 |
hig | -2.869 |
crab | -2.867 |
Kerr | -2.784 |
Token | , |
Token ID | 11 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
Roose | +2.455 |
Cumm | +2.364 |
STD | +2.265 |
| +2.174 |
Garrison | +2.160 |
Neg logit contributions | |
arre | -2.649 |
rule | -2.617 |
crab | -2.249 |
hig | -2.240 |
Kerr | -2.175 |
Token | 54 |
Token ID | 7175 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
Roose | +4.017 |
Cumm | +3.806 |
STD | +3.740 |
| +3.531 |
Garrison | +3.492 |
Neg logit contributions | |
arre | -5.552 |
rule | -5.429 |
crab | -4.698 |
hig | -4.671 |
モ | -4.531 |
Token | , |
Token ID | 11 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
Roose | +3.945 |
Cumm | +3.841 |
STD | +3.644 |
Garrison | +3.536 |
| +3.536 |
Neg logit contributions | |
arre | -4.398 |
rule | -4.324 |
hig | -3.736 |
crab | -3.722 |
Kerr | -3.626 |
Token | 225 |
Token ID | 18500 |
Feature activation | -8.84e+00 |
Pos logit contributions | |
Roose | +4.309 |
Cumm | +4.153 |
STD | +3.958 |
Garrison | +3.823 |
| +3.822 |
Neg logit contributions | |
arre | -5.561 |
rule | -5.473 |
crab | -4.672 |
hig | -4.639 |
モ | -4.539 |
Token | - |
Token ID | 532 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Roose | +4.737 |
Cumm | +4.600 |
STD | +4.238 |
| +4.125 |
Garrison | +4.051 |
Neg logit contributions | |
arre | -7.667 |
rule | -7.512 |
crab | -6.654 |
hig | -6.640 |
モ | -6.459 |
Token | 234 |
Token ID | 34323 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
Roose | +1.871 |
Cumm | +1.812 |
STD | +1.694 |
| +1.657 |
Garrison | +1.647 |
Neg logit contributions | |
arre | -2.174 |
rule | -2.146 |
hig | -1.847 |
crab | -1.821 |
モ | -1.754 |
Token | . |
Token ID | 764 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Cumm | +2.239 |
Roose | +2.221 |
| +2.088 |
STD | +1.896 |
Garrison | +1.703 |
Neg logit contributions | |
��� | -15.870 |
arre | -15.855 |
rule | -15.409 |
undai | -14.905 |
hig | -14.782 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
arre | +1.906 |
rule | +1.881 |
crab | +1.562 |
hig | +1.547 |
Kerr | +1.534 |
Neg logit contributions | |
Roose | -2.475 |
Cumm | -2.372 |
STD | -2.263 |
kson | -2.211 |
| -2.205 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Roose | +1.374 |
Cumm | +1.335 |
| +1.274 |
STD | +1.273 |
Garrison | +1.234 |
Neg logit contributions | |
arre | -1.391 |
rule | -1.347 |
hig | -1.179 |
crab | -1.158 |
Kerr | -1.125 |
Token | Google |
Token ID | 11708 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
arre | +1.254 |
rule | +1.236 |
crab | +0.995 |
hig | +0.987 |
Kerr | +0.972 |
Neg logit contributions | |
Roose | -1.915 |
Cumm | -1.852 |
STD | -1.768 |
| -1.733 |
Garrison | -1.728 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Roose | +4.369 |
Cumm | +4.365 |
STD | +4.193 |
| +4.113 |
Garrison | +4.066 |
Neg logit contributions | |
arre | -3.802 |
rule | -3.774 |
hig | -3.081 |
crab | -3.039 |
モ | -2.938 |
Token | THE |
Token ID | 3336 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
arre | +0.354 |
rule | +0.348 |
crab | +0.291 |
hig | +0.289 |
Kerr | +0.283 |
Neg logit contributions | |
Roose | -0.432 |
Cumm | -0.417 |
STD | -0.397 |
| -0.390 |
Garrison | -0.387 |
Token | V |
Token ID | 569 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
Roose | +1.759 |
Cumm | +1.647 |
STD | +1.595 |
| +1.519 |
Garrison | +1.497 |
Neg logit contributions | |
arre | -2.845 |
rule | -2.816 |
hig | -2.463 |
crab | -2.445 |
Kerr | -2.413 |
Token | AM |
Token ID | 2390 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
arre | +2.392 |
rule | +2.325 |
crab | +1.926 |
Kerr | +1.882 |
hig | +1.873 |
Neg logit contributions | |
Roose | -3.183 |
Cumm | -3.074 |
STD | -2.900 |
kson | -2.874 |
Garrison | -2.845 |
Token | PI |
Token ID | 11901 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
arre | +1.464 |
rule | +1.440 |
crab | +1.200 |
hig | +1.194 |
Kerr | +1.174 |
Neg logit contributions | |
Roose | -1.805 |
Cumm | -1.744 |
STD | -1.650 |
| -1.619 |
kson | -1.617 |
Token | RE |
Token ID | 2200 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
arre | +4.314 |
rule | +4.205 |
crab | +3.627 |
Kerr | +3.613 |
Smash | +3.549 |
Neg logit contributions | |
Roose | -2.998 |
Cumm | -2.913 |
STD | -2.626 |
onom | -2.592 |
kson | -2.566 |
Token | SL |
Token ID | 12419 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
Roose | +0.795 |
Cumm | +0.767 |
STD | +0.737 |
| +0.718 |
Garrison | +0.712 |
Neg logit contributions | |
arre | -0.677 |
rule | -0.665 |
crab | -0.557 |
hig | -0.555 |
Kerr | -0.543 |
Token | AY |
Token ID | 4792 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Roose | +3.618 |
STD | +3.265 |
Cumm | +3.257 |
| +3.094 |
Garrison | +2.901 |
Neg logit contributions | |
rule | -14.382 |
arre | -14.142 |
hig | -13.668 |
��� | -13.337 |
paran | -13.142 |
Token | ER |
Token ID | 1137 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Roose | +2.183 |
Cumm | +2.060 |
STD | +2.000 |
| +1.935 |
Garrison | +1.870 |
Neg logit contributions | |
arre | -3.996 |
rule | -3.926 |
hig | -3.596 |
crab | -3.496 |
foss | -3.381 |
Token | ( |
Token ID | 357 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Roose | +0.889 |
Cumm | +0.858 |
STD | +0.821 |
| +0.803 |
Garrison | +0.795 |
Neg logit contributions | |
arre | -0.784 |
rule | -0.771 |
crab | -0.649 |
hig | -0.642 |
Kerr | -0.630 |
Token | Dark |
Token ID | 17367 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
arre | +1.204 |
rule | +1.187 |
crab | +1.010 |
hig | +1.006 |
Kerr | +0.988 |
Neg logit contributions | |
Roose | -1.206 |
Cumm | -1.160 |
STD | -1.097 |
| -1.073 |
kson | -1.067 |
Token | Horse |
Token ID | 18455 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
Roose | +1.275 |
Cumm | +1.192 |
STD | +1.107 |
| +1.069 |
Garrison | +1.067 |
Neg logit contributions | |
arre | -2.522 |
rule | -2.492 |
hig | -2.233 |
crab | -2.224 |
Kerr | -2.173 |
Token | . |
Token ID | 13 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
Roose | +4.028 |
Cumm | +3.920 |
| +3.831 |
STD | +3.734 |
Garrison | +3.663 |
Neg logit contributions | |
arre | -5.010 |
rule | -4.980 |
hig | -4.467 |
crab | -4.293 |
Kerr | -4.172 |
Token | A |
Token ID | 32 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
Roose | +2.136 |
Cumm | +2.029 |
| +1.939 |
STD | +1.906 |
Garrison | +1.854 |
Neg logit contributions | |
arre | -3.124 |
rule | -3.078 |
hig | -2.756 |
crab | -2.701 |
Kerr | -2.616 |
Token | . |
Token ID | 13 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
Roose | +4.743 |
Cumm | +4.630 |
STD | +4.399 |
| +4.382 |
onom | +4.253 |
Neg logit contributions | |
arre | -5.237 |
rule | -5.197 |
crab | -4.373 |
hig | -4.369 |
Kerr | -4.300 |
Token | I |
Token ID | 40 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
Roose | +4.220 |
Cumm | +4.061 |
| +3.954 |
STD | +3.853 |
Garrison | +3.713 |
Neg logit contributions | |
arre | -6.034 |
rule | -5.835 |
crab | -5.080 |
hig | -5.030 |
Kerr | -4.887 |
Token | . |
Token ID | 13 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
Roose | +2.295 |
Cumm | +2.196 |
STD | +2.112 |
| +2.105 |
Garrison | +2.048 |
Neg logit contributions | |
arre | -2.486 |
rule | -2.439 |
hig | -2.144 |
crab | -2.097 |
Kerr | -2.050 |
Token | R |
Token ID | 49 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
Roose | +2.765 |
Cumm | +2.484 |
STD | +2.384 |
| +2.351 |
Garrison | +2.296 |
Neg logit contributions | |
arre | -6.083 |
rule | -5.908 |
hig | -5.504 |
crab | -5.388 |
Kerr | -5.217 |
Token | . |
Token ID | 764 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
Roose | +9.047 |
Cumm | +8.985 |
| +8.837 |
STD | +8.559 |
Garrison | +8.321 |
Neg logit contributions | |
rule | -8.481 |
arre | -8.455 |
Kerr | -6.930 |
ドラゴン | -6.898 |
crab | -6.890 |
Token | Des |
Token ID | 5960 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
Roose | +3.083 |
Cumm | +2.965 |
| +2.841 |
STD | +2.762 |
Garrison | +2.713 |
Neg logit contributions | |
arre | -3.633 |
rule | -3.607 |
crab | -3.152 |
hig | -3.145 |
Kerr | -3.043 |
Token | ren |
Token ID | 8851 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
Roose | +2.891 |
Cumm | +2.798 |
STD | +2.653 |
| +2.620 |
Garrison | +2.609 |
Neg logit contributions | |
arre | -2.539 |
rule | -2.521 |
crab | -2.096 |
hig | -2.088 |
Kerr | -2.074 |
Token | se |
Token ID | 325 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
arre | +7.040 |
rule | +6.686 |
crab | +5.837 |
hig | +5.742 |
Smash | +5.618 |
Neg logit contributions | |
Roose | -6.294 |
Cumm | -5.932 |
STD | -5.674 |
| -5.434 |
Garrison | -5.423 |
Token | ign |
Token ID | 570 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
arre | +1.442 |
rule | +1.418 |
crab | +1.231 |
hig | +1.223 |
Kerr | +1.204 |
Neg logit contributions | |
Roose | -1.184 |
Cumm | -1.132 |
STD | -1.065 |
| -1.039 |
Garrison | -1.029 |
Token | rights |
Token ID | 2489 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
arre | +1.110 |
rule | +1.094 |
crab | +0.936 |
hig | +0.932 |
Kerr | +0.915 |
Neg logit contributions | |
Roose | -1.072 |
Cumm | -1.030 |
STD | -0.974 |
| -0.953 |
kson | -0.946 |
Token | advocates |
Token ID | 11009 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
Roose | +0.439 |
Cumm | +0.422 |
STD | +0.394 |
| +0.384 |
Garrison | +0.382 |
Neg logit contributions | |
arre | -0.600 |
rule | -0.591 |
crab | -0.515 |
hig | -0.514 |
Kerr | -0.506 |
Token | showed |
Token ID | 3751 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
arre | +0.676 |
rule | +0.666 |
crab | +0.570 |
hig | +0.568 |
Kerr | +0.558 |
Neg logit contributions | |
Roose | -0.641 |
Cumm | -0.616 |
STD | -0.582 |
| -0.570 |
kson | -0.565 |
Token | up |
Token ID | 510 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
arre | +0.313 |
rule | +0.308 |
crab | +0.263 |
hig | +0.262 |
Kerr | +0.257 |
Neg logit contributions | |
Roose | -0.310 |
Cumm | -0.298 |
STD | -0.282 |
| -0.276 |
Garrison | -0.274 |
Token | in |
Token ID | 287 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
arre | +0.812 |
rule | +0.800 |
crab | +0.682 |
hig | +0.680 |
Kerr | +0.667 |
Neg logit contributions | |
Roose | -0.820 |
Cumm | -0.789 |
STD | -0.747 |
| -0.732 |
kson | -0.726 |
Token | dro |
Token ID | 3102 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
arre | +1.563 |
rule | +1.541 |
crab | +1.319 |
hig | +1.313 |
Kerr | +1.294 |
Neg logit contributions | |
Roose | -1.593 |
Cumm | -1.529 |
STD | -1.447 |
| -1.423 |
kson | -1.413 |
Token | ves |
Token ID | 1158 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
Roose | +2.455 |
kson | +1.798 |
Cumm | +1.723 |
onom | +1.717 |
horse | +1.313 |
Neg logit contributions | |
arre | -15.494 |
rule | -15.415 |
ミ | -14.708 |
crab | -14.598 |
Kerr | -14.578 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Roose | +2.402 |
Cumm | +2.277 |
STD | +2.161 |
Garrison | +2.122 |
| +2.105 |
Neg logit contributions | |
arre | -2.688 |
rule | -2.647 |
hig | -2.224 |
crab | -2.218 |
モ | -2.193 |
Token | some |
Token ID | 617 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Roose | +1.213 |
Cumm | +1.163 |
STD | +1.095 |
Garrison | +1.074 |
| +1.069 |
Neg logit contributions | |
arre | -1.269 |
rule | -1.254 |
hig | -1.055 |
crab | -1.050 |
Kerr | -1.032 |
Token | driving |
Token ID | 5059 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Roose | +1.380 |
Cumm | +1.323 |
STD | +1.252 |
Garrison | +1.222 |
| +1.220 |
Neg logit contributions | |
arre | -1.358 |
rule | -1.332 |
hig | -1.116 |
crab | -1.111 |
Kerr | -1.095 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
arre | +1.923 |
rule | +1.905 |
crab | +1.637 |
hig | +1.618 |
Kerr | +1.590 |
Neg logit contributions | |
Roose | -2.077 |
Cumm | -2.001 |
STD | -1.891 |
| -1.869 |
kson | -1.855 |
Token | ER |
Token ID | 13793 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Roose | +3.263 |
Cumm | +3.171 |
STD | +2.998 |
| +2.975 |
Garrison | +2.871 |
Neg logit contributions | |
arre | -3.684 |
rule | -3.667 |
crab | -3.148 |
hig | -3.128 |
Kerr | -3.073 |
Token | T |
Token ID | 51 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
Roose | +1.676 |
Cumm | +1.619 |
STD | +1.545 |
| +1.517 |
kson | +1.498 |
Neg logit contributions | |
arre | -1.652 |
rule | -1.631 |
crab | -1.385 |
hig | -1.375 |
Kerr | -1.346 |
Token | IA |
Token ID | 3539 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Roose | +3.516 |
Cumm | +3.420 |
STD | +3.262 |
| +3.201 |
kson | +3.107 |
Neg logit contributions | |
arre | -3.647 |
rule | -3.638 |
crab | -3.107 |
hig | -3.086 |
Kerr | -3.008 |
Token | P |
Token ID | 350 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Roose | +2.177 |
Cumm | +2.105 |
STD | +2.008 |
| +1.964 |
Garrison | +1.911 |
Neg logit contributions | |
arre | -2.685 |
rule | -2.652 |
crab | -2.291 |
hig | -2.266 |
Kerr | -2.226 |
Token | AR |
Token ID | 5923 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
Roose | +0.341 |
Cumm | +0.327 |
STD | +0.310 |
| +0.303 |
Garrison | +0.300 |
Neg logit contributions | |
arre | -0.359 |
rule | -0.354 |
crab | -0.303 |
hig | -0.302 |
Kerr | -0.296 |
Token | S |
Token ID | 50 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
Roose | +3.354 |
Cumm | +3.236 |
STD | +3.151 |
| +3.042 |
kson | +2.953 |
Neg logit contributions | |
arre | -4.678 |
rule | -4.635 |
crab | -4.060 |
hig | -4.038 |
Kerr | -3.941 |
Token | . |
Token ID | 764 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Roose | +7.444 |
Cumm | +7.402 |
STD | +7.255 |
| +7.232 |
Garrison | +6.589 |
Neg logit contributions | |
rule | -10.111 |
arre | -9.986 |
crab | -8.640 |
hig | -8.484 |
モ | -8.437 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
arre | +0.997 |
rule | +0.977 |
crab | +0.814 |
hig | +0.813 |
Kerr | +0.793 |
Neg logit contributions | |
Roose | -1.262 |
Cumm | -1.211 |
STD | -1.148 |
kson | -1.138 |
Garrison | -1.125 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Roose | +0.309 |
Cumm | +0.299 |
STD | +0.285 |
| +0.282 |
Garrison | +0.277 |
Neg logit contributions | |
arre | -0.282 |
rule | -0.275 |
hig | -0.235 |
crab | -0.233 |
Kerr | -0.228 |
Token | The |
Token ID | 464 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Roose | +1.260 |
Cumm | +1.208 |
STD | +1.146 |
| +1.141 |
onom | +1.111 |
Neg logit contributions | |
arre | -1.427 |
rule | -1.391 |
crab | -1.227 |
hig | -1.223 |
Kerr | -1.204 |
Token | Incarnation |
Token ID | 47881 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Roose | +0.724 |
Cumm | +0.696 |
STD | +0.658 |
| +0.647 |
Garrison | +0.641 |
Neg logit contributions | |
arre | -0.747 |
rule | -0.734 |
crab | -0.628 |
hig | -0.625 |
Kerr | -0.616 |
Token | _ |
Token ID | 62 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Roose | +4.302 |
Cumm | +4.270 |
STD | +4.233 |
| +3.965 |
Garrison | +3.677 |
Neg logit contributions | |
arre | -7.783 |
rule | -7.520 |
crab | -6.754 |
hig | -6.746 |
ミ | -6.619 |
Token | EX |
Token ID | 6369 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
arre | +1.096 |
rule | +1.084 |
crab | +0.925 |
hig | +0.921 |
Kerr | +0.906 |
Neg logit contributions | |
Roose | -1.039 |
Cumm | -0.998 |
STD | -0.938 |
| -0.920 |
kson | -0.916 |
Token | TR |
Token ID | 5446 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
arre | +1.903 |
rule | +1.881 |
crab | +1.619 |
hig | +1.601 |
Kerr | +1.589 |
Neg logit contributions | |
Roose | -1.699 |
Cumm | -1.629 |
STD | -1.519 |
kson | -1.496 |
| -1.489 |
Token | ACT |
Token ID | 10659 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
Roose | +3.562 |
Cumm | +3.514 |
STD | +3.390 |
| +3.334 |
Garrison | +3.200 |
Neg logit contributions | |
arre | -3.469 |
rule | -3.441 |
hig | -3.034 |
crab | -2.947 |
Kerr | -2.859 |
Token | ( |
Token ID | 357 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
Roose | +5.228 |
Cumm | +5.128 |
STD | +5.123 |
| +4.910 |
kson | +4.655 |
Neg logit contributions | |
arre | -5.816 |
rule | -5.660 |
crab | -5.041 |
hig | -4.954 |
ミ | -4.876 |
Token | line |
Token ID | 1627 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
Roose | +2.667 |
Cumm | +2.562 |
STD | +2.496 |
| +2.408 |
Garrison | +2.356 |
Neg logit contributions | |
arre | -3.067 |
rule | -2.989 |
crab | -2.588 |
hig | -2.553 |
Kerr | -2.539 |
Token | , |
Token ID | 837 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Roose | +5.410 |
Cumm | +5.061 |
STD | +4.902 |
| +4.570 |
onom | +4.516 |
Neg logit contributions | |
arre | -12.147 |
rule | -12.110 |
crab | -11.215 |
hig | -11.031 |
ミ | -11.022 |
Token | r |
Token ID | 374 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
Roose | +2.265 |
Cumm | +2.177 |
STD | +2.112 |
| +2.040 |
Garrison | +1.992 |
Neg logit contributions | |
arre | -2.500 |
rule | -2.447 |
crab | -2.089 |
hig | -2.068 |
Kerr | -2.055 |
Token | ' |
Token ID | 705 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
Roose | +3.795 |
Cumm | +3.702 |
STD | +3.545 |
| +3.443 |
onom | +3.392 |
Neg logit contributions | |
arre | -5.517 |
rule | -5.460 |
crab | -4.855 |
hig | -4.774 |
Kerr | -4.729 |
Token | \ |
Token ID | 59 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Roose | +3.470 |
Cumm | +3.379 |
| +3.234 |
STD | +3.232 |
kson | +3.126 |
Neg logit contributions | |
arre | -3.483 |
rule | -3.414 |
crab | -2.961 |
hig | -2.935 |
Kerr | -2.857 |
Token | [ |
Token ID | 58 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
arre | +0.351 |
rule | +0.346 |
crab | +0.292 |
hig | +0.290 |
Kerr | +0.285 |
Neg logit contributions | |
Roose | -0.391 |
Cumm | -0.377 |
STD | -0.357 |
| -0.351 |
kson | -0.348 |
Token | and |
Token ID | 290 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
arre | +0.262 |
rule | +0.258 |
crab | +0.220 |
hig | +0.219 |
Kerr | +0.215 |
Neg logit contributions | |
Roose | -0.265 |
Cumm | -0.255 |
STD | -0.241 |
| -0.237 |
kson | -0.235 |
Token | V |
Token ID | 569 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Roose | +1.515 |
Cumm | +1.448 |
STD | +1.364 |
| +1.335 |
Garrison | +1.326 |
Neg logit contributions | |
arre | -1.949 |
rule | -1.925 |
crab | -1.664 |
hig | -1.659 |
Kerr | -1.618 |
Token | odka |
Token ID | 28601 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
Roose | +0.961 |
Cumm | +0.907 |
STD | +0.839 |
| +0.829 |
kson | +0.809 |
Neg logit contributions | |
arre | -1.824 |
rule | -1.803 |
crab | -1.616 |
hig | -1.615 |
Kerr | -1.580 |
Token | O |
Token ID | 440 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
Roose | +1.895 |
Cumm | +1.784 |
STD | +1.687 |
| +1.632 |
onom | +1.628 |
Neg logit contributions | |
arre | -2.702 |
rule | -2.666 |
crab | -2.332 |
hig | -2.324 |
Kerr | -2.270 |
Token | ' |
Token ID | 6 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
Roose | +3.893 |
Cumm | +3.701 |
| +3.649 |
STD | +3.620 |
onom | +3.544 |
Neg logit contributions | |
arre | -3.981 |
rule | -3.914 |
hig | -3.395 |
crab | -3.382 |
Kerr | -3.299 |
Token | Clock |
Token ID | 44758 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
Roose | +4.003 |
Cumm | +3.915 |
STD | +3.677 |
| +3.656 |
kson | +3.496 |
Neg logit contributions | |
arre | -6.054 |
rule | -5.898 |
hig | -5.428 |
crab | -5.307 |
Kerr | -5.129 |
Token | Podcast |
Token ID | 16036 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Roose | +4.839 |
Cumm | +4.504 |
STD | +4.485 |
Garrison | +4.244 |
onom | +4.237 |
Neg logit contributions | |
rule | -13.130 |
arre | -12.986 |
crab | -11.486 |
Kerr | -11.325 |
hig | -11.294 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Roose | +2.670 |
Cumm | +2.584 |
STD | +2.443 |
| +2.400 |
Garrison | +2.384 |
Neg logit contributions | |
arre | -2.654 |
rule | -2.641 |
crab | -2.227 |
hig | -2.217 |
Kerr | -2.173 |
Token | Author |
Token ID | 6434 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
arre | +0.140 |
rule | +0.138 |
crab | +0.120 |
hig | +0.119 |
Kerr | +0.117 |
Neg logit contributions | |
Roose | -0.116 |
Cumm | -0.111 |
STD | -0.104 |
| -0.102 |
kson | -0.101 |
Token | of |
Token ID | 286 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Roose | +0.699 |
Cumm | +0.674 |
STD | +0.639 |
| +0.631 |
Garrison | +0.621 |
Neg logit contributions | |
arre | -0.697 |
rule | -0.689 |
hig | -0.584 |
crab | -0.584 |
Kerr | -0.569 |
Token | The |
Token ID | 383 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
Roose | +0.138 |
Cumm | +0.133 |
STD | +0.125 |
| +0.123 |
kson | +0.122 |
Neg logit contributions | |
arre | -0.148 |
rule | -0.146 |
crab | -0.125 |
hig | -0.125 |
Kerr | -0.123 |
Token | P |
Token ID | 47 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Roose | +0.266 |
Cumm | +0.257 |
STD | +0.243 |
| +0.241 |
kson | +0.236 |
Neg logit contributions | |
arre | -0.278 |
rule | -0.273 |
crab | -0.236 |
hig | -0.235 |
Kerr | -0.232 |
Token | R |
Token ID | 371 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
arre | +1.946 |
rule | +1.907 |
hig | +1.648 |
crab | +1.647 |
Kerr | +1.618 |
Neg logit contributions | |
Roose | -1.619 |
Cumm | -1.544 |
STD | -1.450 |
kson | -1.415 |
| -1.412 |
Token | IM |
Token ID | 3955 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Roose | +2.838 |
Cumm | +2.767 |
STD | +2.600 |
| +2.520 |
onom | +2.487 |
Neg logit contributions | |
rule | -4.235 |
arre | -4.225 |
crab | -3.702 |
hig | -3.671 |
Kerr | -3.645 |
Token | A |
Token ID | 32 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
arre | +1.582 |
rule | +1.541 |
crab | +1.334 |
hig | +1.321 |
Kerr | +1.306 |
Neg logit contributions | |
Roose | -1.479 |
Cumm | -1.407 |
STD | -1.316 |
kson | -1.306 |
Garrison | -1.301 |
Token | S |
Token ID | 311 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
Roose | +1.052 |
Cumm | +1.008 |
STD | +0.952 |
| +0.935 |
Garrison | +0.914 |
Neg logit contributions | |
arre | -1.457 |
rule | -1.446 |
crab | -1.258 |
hig | -1.250 |
Kerr | -1.233 |
Token | EC |
Token ID | 13182 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
Roose | +4.747 |
Cumm | +4.683 |
STD | +4.502 |
| +4.481 |
Garrison | +4.322 |
Neg logit contributions | |
arre | -4.304 |
rule | -4.255 |
crab | -3.592 |
hig | -3.528 |
Kerr | -3.459 |
Token | UN |
Token ID | 4944 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Roose | +8.538 |
Cumm | +8.378 |
STD | +8.282 |
| +8.240 |
kson | +7.759 |
Neg logit contributions | |
rule | -9.031 |
arre | -8.715 |
crab | -7.553 |
hig | -7.401 |
ミ | -7.349 |
Token | D |
Token ID | 35 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
Roose | +3.150 |
Cumm | +3.081 |
STD | +2.938 |
| +2.889 |
Garrison | +2.811 |
Neg logit contributions | |
arre | -3.048 |
rule | -3.009 |
hig | -2.526 |
crab | -2.523 |
Kerr | -2.443 |
Token | � |
Token ID | 127 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
Roose | +1.906 |
Cumm | +1.844 |
STD | +1.756 |
| +1.721 |
Garrison | +1.677 |
Neg logit contributions | |
arre | -2.094 |
rule | -2.074 |
crab | -1.786 |
hig | -1.775 |
Kerr | -1.733 |
Token | � |
Token ID | 228 |
Feature activation | -9.14e+00 |
Pos logit contributions | |
Roose | +2.698 |
Cumm | +2.606 |
STD | +2.484 |
| +2.449 |
Garrison | +2.414 |
Neg logit contributions | |
arre | -2.822 |
rule | -2.790 |
crab | -2.392 |
hig | -2.369 |
Kerr | -2.321 |
Token | P |
Token ID | 350 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Roose | +6.034 |
Cumm | +5.992 |
STD | +5.793 |
| +5.722 |
Garrison | +5.396 |
Neg logit contributions | |
arre | -6.566 |
rule | -6.505 |
crab | -5.532 |
hig | -5.482 |
Kerr | -5.347 |
Token | cl |
Token ID | 537 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
arre | +3.342 |
rule | +3.289 |
crab | +2.814 |
hig | +2.810 |
Kerr | +2.716 |
Neg logit contributions | |
Roose | -4.403 |
Cumm | -4.171 |
kson | -3.937 |
STD | -3.899 |
onom | -3.885 |
Token | ojure |
Token ID | 32511 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
arre | +0.375 |
rule | +0.370 |
crab | +0.325 |
hig | +0.324 |
Kerr | +0.319 |
Neg logit contributions | |
Roose | -0.259 |
Cumm | -0.247 |
STD | -0.231 |
| -0.226 |
kson | -0.224 |
Token | | |
Token ID | 930 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
Roose | +1.098 |
Cumm | +1.066 |
STD | +1.020 |
| +1.003 |
Garrison | +0.994 |
Neg logit contributions | |
arre | -0.688 |
rule | -0.675 |
crab | -0.546 |
hig | -0.542 |
Kerr | -0.529 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
arre | +0.498 |
rule | +0.491 |
hig | +0.416 |
crab | +0.416 |
Kerr | +0.407 |
Neg logit contributions | |
Roose | -0.535 |
Cumm | -0.513 |
STD | -0.486 |
kson | -0.476 |
| -0.476 |
Token | . |
Token ID | 764 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Roose | +2.538 |
Cumm | +2.315 |
| +2.242 |
STD | +2.137 |
Garrison | +1.935 |
Neg logit contributions | |
arre | -10.606 |
rule | -10.347 |
��� | -9.641 |
hig | -9.570 |
crab | -9.444 |
Token | 8 |
Token ID | 807 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
arre | +1.863 |
rule | +1.839 |
crab | +1.583 |
hig | +1.578 |
Kerr | +1.556 |
Neg logit contributions | |
Roose | -1.707 |
Cumm | -1.635 |
STD | -1.540 |
| -1.505 |
kson | -1.503 |
Token | . |
Token ID | 764 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
Roose | +2.758 |
| +2.567 |
Cumm | +2.458 |
STD | +2.230 |
Garrison | +1.902 |
Neg logit contributions | |
arre | -15.110 |
rule | -14.552 |
��� | -14.491 |
undai | -13.866 |
hig | -13.805 |
Token | 0 |
Token ID | 657 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
arre | +0.545 |
rule | +0.538 |
crab | +0.460 |
hig | +0.459 |
Kerr | +0.451 |
Neg logit contributions | |
Roose | -0.523 |
Cumm | -0.501 |
STD | -0.473 |
| -0.463 |
kson | -0.461 |
Token | | |
Token ID | 930 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Roose | +0.779 |
Cumm | +0.758 |
STD | +0.727 |
| +0.720 |
Garrison | +0.707 |
Neg logit contributions | |
arre | -0.525 |
rule | -0.512 |
hig | -0.419 |
crab | -0.419 |
Kerr | -0.403 |
Token | 301 |
Token ID | 25643 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
Roose | +0.121 |
Cumm | +0.116 |
STD | +0.109 |
| +0.107 |
Garrison | +0.105 |
Neg logit contributions | |
arre | -0.143 |
rule | -0.141 |
crab | -0.121 |
hig | -0.121 |
Kerr | -0.118 |
Token | 6 |
Token ID | 21 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Roose | +0.064 |
Cumm | +0.061 |
STD | +0.058 |
| +0.057 |
kson | +0.057 |
Neg logit contributions | |
arre | -0.059 |
rule | -0.058 |
crab | -0.049 |
hig | -0.049 |
Kerr | -0.048 |
Token | podcast |
Token ID | 9905 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Roose | +1.509 |
Cumm | +1.447 |
STD | +1.374 |
| +1.335 |
Garrison | +1.320 |
Neg logit contributions | |
arre | -1.697 |
rule | -1.664 |
crab | -1.429 |
hig | -1.417 |
Kerr | -1.406 |
Token | was |
Token ID | 373 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Roose | +0.429 |
Cumm | +0.410 |
STD | +0.387 |
| +0.380 |
Garrison | +0.377 |
Neg logit contributions | |
arre | -0.490 |
rule | -0.486 |
crab | -0.415 |
hig | -0.412 |
Kerr | -0.407 |
Token | interesting |
Token ID | 3499 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Roose | +0.982 |
Cumm | +0.943 |
STD | +0.885 |
| +0.871 |
Garrison | +0.863 |
Neg logit contributions | |
arre | -1.179 |
rule | -1.168 |
crab | -0.993 |
hig | -0.989 |
Kerr | -0.973 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Roose | +0.402 |
Cumm | +0.387 |
STD | +0.366 |
| +0.359 |
Garrison | +0.356 |
Neg logit contributions | |
arre | -0.397 |
rule | -0.391 |
crab | -0.333 |
hig | -0.331 |
Kerr | -0.325 |
Token | take |
Token ID | 1011 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
Roose | +0.174 |
Cumm | +0.167 |
STD | +0.158 |
| +0.155 |
Garrison | +0.154 |
Neg logit contributions | |
arre | -0.182 |
rule | -0.179 |
crab | -0.152 |
hig | -0.151 |
Kerr | -0.149 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Roose | +2.559 |
Cumm | +2.442 |
STD | +2.265 |
Garrison | +2.256 |
| +2.209 |
Neg logit contributions | |
arre | -3.365 |
rule | -3.279 |
hig | -2.843 |
crab | -2.799 |
モ | -2.767 |
Token | few |
Token ID | 1178 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
Roose | +7.795 |
Cumm | +7.341 |
STD | +6.975 |
Garrison | +6.958 |
| +6.849 |
Neg logit contributions | |
arre | -10.799 |
rule | -10.014 |
モ | -8.470 |
antry | -8.229 |
hig | -8.029 |
Token | seconds |
Token ID | 4201 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
Roose | +4.773 |
Cumm | +4.578 |
Garrison | +4.316 |
STD | +4.300 |
| +4.225 |
Neg logit contributions | |
arre | -5.862 |
rule | -5.777 |
hig | -4.842 |
Kerr | -4.770 |
モ | -4.755 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Roose | +2.710 |
Cumm | +2.588 |
STD | +2.440 |
| +2.432 |
Garrison | +2.429 |
Neg logit contributions | |
arre | -3.071 |
rule | -2.995 |
crab | -2.571 |
hig | -2.569 |
Kerr | -2.517 |
Token | let |
Token ID | 1309 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Roose | +1.341 |
Cumm | +1.294 |
STD | +1.234 |
| +1.223 |
Garrison | +1.205 |
Neg logit contributions | |
arre | -1.262 |
rule | -1.225 |
crab | -1.022 |
hig | -1.014 |
Kerr | -1.010 |
Token | Will |
Token ID | 2561 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
Roose | +2.029 |
Cumm | +1.922 |
STD | +1.782 |
onom | +1.762 |
| +1.757 |
Neg logit contributions | |
arre | -2.646 |
rule | -2.600 |
hig | -2.242 |
crab | -2.239 |
Kerr | -2.182 |
Token | s |
Token ID | 264 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Roose | +2.905 |
Cumm | +2.826 |
STD | +2.662 |
| +2.625 |
Garrison | +2.533 |
Neg logit contributions | |
arre | -3.189 |
rule | -3.181 |
crab | -2.666 |
hig | -2.637 |
Kerr | -2.584 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
arre | +1.579 |
rule | +1.564 |
crab | +1.306 |
hig | +1.289 |
Kerr | +1.277 |
Neg logit contributions | |
Roose | -1.915 |
Cumm | -1.840 |
STD | -1.742 |
kson | -1.703 |
Garrison | -1.703 |
Token | t |
Token ID | 83 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
arre | +1.870 |
rule | +1.858 |
crab | +1.603 |
hig | +1.591 |
Kerr | +1.577 |
Neg logit contributions | |
Roose | -1.384 |
Cumm | -1.314 |
STD | -1.221 |
Garrison | -1.187 |
kson | -1.184 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
arre | +0.178 |
rule | +0.175 |
crab | +0.148 |
hig | +0.148 |
Kerr | +0.144 |
Neg logit contributions | |
Roose | -0.191 |
Cumm | -0.184 |
STD | -0.174 |
| -0.171 |
Garrison | -0.170 |
Token | F |
Token ID | 376 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
arre | +3.807 |
rule | +3.762 |
crab | +3.279 |
Kerr | +3.277 |
hig | +3.254 |
Neg logit contributions | |
Roose | -3.779 |
Cumm | -3.594 |
kson | -3.388 |
govtrack | -3.350 |
Garrison | -3.345 |
Token | RA |
Token ID | 3861 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Roose | +0.415 |
Cumm | +0.405 |
STD | +0.384 |
| +0.378 |
kson | +0.374 |
Neg logit contributions | |
arre | -0.338 |
rule | -0.334 |
hig | -0.280 |
crab | -0.280 |
Kerr | -0.273 |
Token | 13 |
Token ID | 1511 |
Feature activation | -8.36e+00 |
Pos logit contributions | |
Cumm | +6.227 |
Roose | +6.002 |
STD | +5.986 |
| +5.671 |
Garrison | +5.528 |
Neg logit contributions | |
arre | -11.581 |
rule | -11.378 |
crab | -9.949 |
モ | -9.891 |
ドラゴン | -9.849 |
Token | Rom |
Token ID | 3570 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Roose | +5.480 |
Cumm | +5.364 |
Garrison | +4.913 |
STD | +4.907 |
| +4.902 |
Neg logit contributions | |
arre | -6.445 |
rule | -6.311 |
hig | -5.385 |
crab | -5.291 |
モ | -5.291 |
Token | ain |
Token ID | 391 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Roose | +0.315 |
Cumm | +0.305 |
STD | +0.285 |
| +0.278 |
Garrison | +0.276 |
Neg logit contributions | |
rule | -0.368 |
arre | -0.367 |
crab | -0.317 |
hig | -0.315 |
モ | -0.308 |
Token | Fe |
Token ID | 5452 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
Roose | +0.230 |
Cumm | +0.226 |
STD | +0.210 |
| +0.203 |
Garrison | +0.201 |
Neg logit contributions | |
arre | -0.274 |
rule | -0.271 |
crab | -0.232 |
hig | -0.231 |
モ | -0.226 |
Token | ill |
Token ID | 359 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Roose | +0.303 |
Cumm | +0.286 |
STD | +0.256 |
onom | +0.249 |
Garrison | +0.248 |
Neg logit contributions | |
arre | -0.702 |
rule | -0.696 |
hig | -0.627 |
crab | -0.625 |
Kerr | -0.616 |
Token | mag |
Token ID | 2153 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
arre | +1.641 |
rule | +1.617 |
crab | +1.368 |
hig | +1.367 |
Kerr | +1.333 |
Neg logit contributions | |
Roose | -1.749 |
Cumm | -1.688 |
STD | -1.597 |
| -1.568 |
kson | -1.555 |
Token | ul |
Token ID | 377 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
arre | +0.729 |
rule | +0.718 |
crab | +0.611 |
hig | +0.608 |
Kerr | +0.597 |
Neg logit contributions | |
Roose | -0.753 |
Cumm | -0.724 |
STD | -0.685 |
| -0.671 |
Garrison | -0.666 |
Token | ang |
Token ID | 648 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
Roose | +0.592 |
Cumm | +0.569 |
STD | +0.537 |
| +0.526 |
onom | +0.526 |
Neg logit contributions | |
arre | -0.615 |
rule | -0.606 |
crab | -0.521 |
hig | -0.516 |
Kerr | -0.514 |
Token | ang |
Token ID | 3550 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
arre | +2.799 |
rule | +2.760 |
hig | +2.359 |
crab | +2.346 |
Kerr | +2.257 |
Neg logit contributions | |
Roose | -3.165 |
Cumm | -3.040 |
STD | -2.866 |
| -2.825 |
Garrison | -2.810 |
Token | nat |
Token ID | 34664 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
arre | +0.337 |
rule | +0.331 |
crab | +0.278 |
hig | +0.277 |
Kerr | +0.272 |
Neg logit contributions | |
Roose | -0.378 |
Cumm | -0.365 |
STD | -0.347 |
| -0.340 |
kson | -0.337 |
Token | ut |
Token ID | 315 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
arre | +2.631 |
rule | +2.586 |
crab | +2.190 |
hig | +2.183 |
Kerr | +2.124 |
Neg logit contributions | |
Roose | -2.579 |
Cumm | -2.484 |
STD | -2.357 |
| -2.297 |
Garrison | -2.291 |
Token | u |
Token ID | 84 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
arre | +4.938 |
rule | +4.826 |
crab | +4.137 |
hig | +4.083 |
Kerr | +3.917 |
Neg logit contributions | |
Roose | -4.819 |
Cumm | -4.688 |
STD | -4.432 |
| -4.340 |
Garrison | -4.291 |
Token | wa |
Token ID | 10247 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
arre | +4.152 |
rule | +4.064 |
crab | +3.475 |
hig | +3.472 |
Kerr | +3.309 |
Neg logit contributions | |
Roose | -4.540 |
Cumm | -4.393 |
STD | -4.115 |
| -4.067 |
Garrison | -4.037 |
Token | na |
Token ID | 12385 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
arre | +2.746 |
rule | +2.694 |
hig | +2.296 |
crab | +2.289 |
Kerr | +2.196 |
Neg logit contributions | |
Roose | -3.247 |
Cumm | -3.134 |
STD | -2.946 |
| -2.920 |
Garrison | -2.895 |
Token | ang |
Token ID | 3550 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
arre | +1.757 |
rule | +1.731 |
crab | +1.469 |
hig | +1.468 |
Kerr | +1.423 |
Neg logit contributions | |
Roose | -1.993 |
Cumm | -1.919 |
STD | -1.813 |
| -1.787 |
kson | -1.772 |
Token | kan |
Token ID | 43998 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Roose | +0.299 |
Cumm | +0.288 |
STD | +0.275 |
| +0.269 |
kson | +0.267 |
Neg logit contributions | |
arre | -0.265 |
rule | -0.260 |
crab | -0.218 |
hig | -0.216 |
Kerr | -0.215 |
Token | eyes |
Token ID | 2951 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
arre | +1.905 |
rule | +1.880 |
crab | +1.604 |
hig | +1.594 |
Kerr | +1.561 |
Neg logit contributions | |
Roose | -2.071 |
Cumm | -1.986 |
STD | -1.874 |
| -1.844 |
kson | -1.838 |
Token | are |
Token ID | 389 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
arre | +1.932 |
rule | +1.911 |
crab | +1.641 |
hig | +1.633 |
Kerr | +1.601 |
Neg logit contributions | |
Roose | -1.748 |
Cumm | -1.671 |
STD | -1.567 |
| -1.534 |
kson | -1.526 |
Token | huge |
Token ID | 3236 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Roose | +0.124 |
Cumm | +0.119 |
STD | +0.113 |
| +0.111 |
Garrison | +0.110 |
Neg logit contributions | |
arre | -0.130 |
rule | -0.128 |
hig | -0.108 |
crab | -0.108 |
Kerr | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
arre | +1.771 |
rule | +1.741 |
crab | +1.502 |
hig | +1.485 |
Kerr | +1.454 |
Neg logit contributions | |
Roose | -1.841 |
Cumm | -1.771 |
STD | -1.669 |
| -1.639 |
kson | -1.631 |
Token | her |
Token ID | 607 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
arre | +1.650 |
rule | +1.628 |
crab | +1.410 |
hig | +1.394 |
Kerr | +1.373 |
Neg logit contributions | |
Roose | -1.577 |
Cumm | -1.514 |
STD | -1.422 |
| -1.396 |
kson | -1.392 |
Token | p |
Token ID | 279 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
Roose | +2.600 |
Cumm | +2.511 |
STD | +2.422 |
| +2.368 |
Garrison | +2.355 |
Neg logit contributions | |
arre | -1.917 |
rule | -1.881 |
hig | -1.512 |
crab | -1.501 |
Kerr | -1.493 |
Token | inks |
Token ID | 2973 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
arre | +5.706 |
rule | +5.524 |
crab | +4.574 |
Smash | +4.447 |
hig | +4.446 |
Neg logit contributions | |
Roose | -5.964 |
Cumm | -5.651 |
STD | -5.270 |
| -5.163 |
kson | -5.146 |
Token | ro |
Token ID | 686 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
arre | +2.822 |
rule | +2.809 |
crab | +2.416 |
hig | +2.369 |
Kerr | +2.328 |
Neg logit contributions | |
Roose | -2.685 |
Cumm | -2.573 |
STD | -2.390 |
| -2.371 |
kson | -2.360 |
Token | sy |
Token ID | 1837 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Roose | +1.152 |
Cumm | +1.100 |
STD | +1.069 |
| +1.029 |
kson | +1.018 |
Neg logit contributions | |
arre | -1.293 |
rule | -1.263 |
hig | -1.107 |
crab | -1.107 |
Kerr | -1.098 |
Token | and |
Token ID | 290 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Roose | +0.160 |
Cumm | +0.154 |
STD | +0.146 |
| +0.143 |
Garrison | +0.142 |
Neg logit contributions | |
arre | -0.159 |
rule | -0.157 |
crab | -0.133 |
hig | -0.133 |
Kerr | -0.130 |
Token | her |
Token ID | 607 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Roose | +0.086 |
Cumm | +0.083 |
STD | +0.078 |
| +0.076 |
Garrison | +0.076 |
Neg logit contributions | |
arre | -0.100 |
rule | -0.098 |
crab | -0.084 |
hig | -0.084 |
Kerr | -0.083 |
Token | faded |
Token ID | 24887 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
arre | +1.962 |
rule | +1.927 |
crab | +1.668 |
hig | +1.655 |
Kerr | +1.629 |
Neg logit contributions | |
Roose | -1.888 |
Cumm | -1.814 |
STD | -1.719 |
| -1.682 |
kson | -1.673 |
Token | badly |
Token ID | 11234 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Roose | +1.464 |
Cumm | +1.398 |
STD | +1.321 |
| +1.295 |
Garrison | +1.290 |
Neg logit contributions | |
arre | -1.605 |
rule | -1.589 |
crab | -1.328 |
hig | -1.326 |
モ | -1.314 |
Token | , |
Token ID | 11 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
arre | +0.085 |
rule | +0.084 |
crab | +0.072 |
hig | +0.071 |
Kerr | +0.070 |
Neg logit contributions | |
Roose | -0.083 |
Cumm | -0.080 |
STD | -0.076 |
| -0.074 |
Garrison | -0.074 |
Token | Sunderland |
Token ID | 35706 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
arre | +2.300 |
rule | +2.268 |
crab | +1.968 |
hig | +1.954 |
Kerr | +1.952 |
Neg logit contributions | |
Roose | -2.117 |
Cumm | -2.035 |
STD | -1.931 |
| -1.888 |
kson | -1.872 |
Token | have |
Token ID | 423 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
arre | +0.062 |
rule | +0.061 |
crab | +0.052 |
hig | +0.052 |
Kerr | +0.051 |
Neg logit contributions | |
Roose | -0.055 |
Cumm | -0.053 |
STD | -0.050 |
| -0.049 |
Garrison | -0.049 |
Token | not |
Token ID | 407 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
arre | +0.801 |
rule | +0.789 |
crab | +0.678 |
hig | +0.675 |
Kerr | +0.664 |
Neg logit contributions | |
Roose | -0.740 |
Cumm | -0.711 |
STD | -0.670 |
| -0.656 |
kson | -0.651 |
Token | yet |
Token ID | 1865 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
arre | +4.999 |
rule | +4.869 |
crab | +4.332 |
hig | +4.292 |
Kerr | +4.235 |
Neg logit contributions | |
Roose | -5.146 |
Cumm | -4.968 |
STD | -4.693 |
kson | -4.626 |
onom | -4.613 |
Token | banished |
Token ID | 43926 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
arre | +2.848 |
rule | +2.790 |
crab | +2.439 |
hig | +2.416 |
Kerr | +2.380 |
Neg logit contributions | |
Roose | -2.743 |
Cumm | -2.650 |
STD | -2.506 |
kson | -2.453 |
| -2.449 |
Token | relegation |
Token ID | 47652 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
arre | +1.561 |
rule | +1.540 |
crab | +1.320 |
hig | +1.311 |
Kerr | +1.298 |
Neg logit contributions | |
Roose | -1.557 |
Cumm | -1.501 |
STD | -1.422 |
| -1.396 |
kson | -1.386 |
Token | fears |
Token ID | 10251 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
arre | +2.945 |
rule | +2.920 |
crab | +2.513 |
hig | +2.486 |
Kerr | +2.423 |
Neg logit contributions | |
Roose | -3.209 |
Cumm | -3.103 |
STD | -2.957 |
kson | -2.913 |
| -2.884 |
Token | but |
Token ID | 475 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
arre | +0.236 |
rule | +0.232 |
crab | +0.197 |
hig | +0.197 |
Kerr | +0.193 |
Neg logit contributions | |
Roose | -0.236 |
Cumm | -0.227 |
STD | -0.214 |
| -0.211 |
Garrison | -0.209 |
Token | he |
Token ID | 339 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Roose | +0.836 |
Cumm | +0.803 |
STD | +0.753 |
| +0.741 |
Garrison | +0.738 |
Neg logit contributions | |
arre | -0.921 |
rule | -0.904 |
crab | -0.772 |
hig | -0.770 |
Kerr | -0.753 |
Token | grinned |
Token ID | 36268 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
Roose | +0.410 |
Cumm | +0.392 |
STD | +0.372 |
| +0.366 |
kson | +0.363 |
Neg logit contributions | |
arre | -0.401 |
rule | -0.396 |
crab | -0.335 |
hig | -0.333 |
Kerr | -0.328 |
Token | . |
Token ID | 13 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
Roose | +2.888 |
Cumm | +2.743 |
STD | +2.567 |
| +2.564 |
onom | +2.530 |
Neg logit contributions | |
arre | -3.225 |
rule | -3.190 |
crab | -2.630 |
Kerr | -2.619 |
hig | -2.618 |
Token |
|
Token ID | 198 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Roose | +0.630 |
Cumm | +0.605 |
STD | +0.572 |
| +0.566 |
Garrison | +0.558 |
Neg logit contributions | |
arre | -0.622 |
rule | -0.609 |
crab | -0.519 |
hig | -0.517 |
Kerr | -0.501 |
Token |
|
Token ID | 198 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
arre | +0.293 |
rule | +0.287 |
hig | +0.242 |
crab | +0.242 |
Kerr | +0.236 |
Neg logit contributions | |
Roose | -0.332 |
Cumm | -0.321 |
STD | -0.305 |
| -0.301 |
Garrison | -0.297 |
Token | i |
Token ID | 72 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Roose | +0.469 |
Cumm | +0.449 |
STD | +0.424 |
| +0.420 |
kson | +0.413 |
Neg logit contributions | |
arre | -0.510 |
rule | -0.501 |
crab | -0.433 |
hig | -0.433 |
Kerr | -0.424 |
Token | G |
Token ID | 38 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
arre | +7.512 |
rule | +7.379 |
hig | +6.489 |
crab | +6.442 |
Smash | +6.295 |
Neg logit contributions | |
Roose | -6.589 |
Cumm | -6.398 |
STD | -6.055 |
Garrison | -5.787 |
| -5.759 |
Token | : |
Token ID | 25 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
arre | +2.048 |
rule | +2.016 |
crab | +1.717 |
hig | +1.715 |
Kerr | +1.685 |
Neg logit contributions | |
Roose | -1.969 |
Cumm | -1.893 |
STD | -1.779 |
| -1.749 |
kson | -1.742 |
Token | Ferrari |
Token ID | 23502 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
arre | +1.209 |
rule | +1.192 |
crab | +1.021 |
hig | +1.018 |
Kerr | +1.000 |
Neg logit contributions | |
Roose | -1.170 |
Cumm | -1.125 |
STD | -1.063 |
| -1.040 |
kson | -1.033 |
Token | _ |
Token ID | 62 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
arre | +0.507 |
rule | +0.500 |
crab | +0.427 |
hig | +0.425 |
Kerr | +0.417 |
Neg logit contributions | |
Roose | -0.492 |
Cumm | -0.473 |
STD | -0.447 |
| -0.437 |
Garrison | -0.434 |
Token | 430 |
Token ID | 31794 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
arre | +2.272 |
rule | +2.244 |
crab | +1.914 |
hig | +1.905 |
Kerr | +1.872 |
Neg logit contributions | |
Roose | -2.114 |
Cumm | -2.036 |
STD | -1.921 |
| -1.878 |
kson | -1.863 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Roose | +1.184 |
Cumm | +1.145 |
STD | +1.070 |
| +1.049 |
Garrison | +1.046 |
Neg logit contributions | |
arre | -1.298 |
rule | -1.291 |
crab | -1.101 |
hig | -1.100 |
Kerr | -1.061 |
Token | Paul |
Token ID | 3362 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
Roose | +0.084 |
Cumm | +0.081 |
STD | +0.076 |
| +0.074 |
Garrison | +0.074 |
Neg logit contributions | |
arre | -0.089 |
rule | -0.087 |
crab | -0.075 |
hig | -0.074 |
Kerr | -0.073 |
Token | Me |
Token ID | 2185 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
Roose | +0.605 |
Cumm | +0.586 |
STD | +0.547 |
Garrison | +0.535 |
| +0.533 |
Neg logit contributions | |
arre | -0.629 |
rule | -0.623 |
crab | -0.529 |
hig | -0.528 |
Kerr | -0.508 |
Token | le |
Token ID | 293 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
arre | +0.618 |
rule | +0.609 |
crab | +0.519 |
hig | +0.517 |
Kerr | +0.508 |
Neg logit contributions | |
Roose | -0.617 |
Cumm | -0.594 |
STD | -0.562 |
| -0.550 |
Garrison | -0.545 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
arre | +2.383 |
rule | +2.336 |
crab | +1.976 |
hig | +1.951 |
Kerr | +1.948 |
Neg logit contributions | |
Roose | -2.735 |
Cumm | -2.612 |
STD | -2.499 |
| -2.447 |
Garrison | -2.406 |
Token | testify |
Token ID | 19671 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
Roose | +1.831 |
Cumm | +1.777 |
STD | +1.676 |
| +1.640 |
Garrison | +1.631 |
Neg logit contributions | |
arre | -2.077 |
rule | -2.058 |
hig | -1.752 |
crab | -1.743 |
Kerr | -1.708 |
Token | before |
Token ID | 878 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
arre | +4.066 |
rule | +3.962 |
hig | +3.421 |
crab | +3.399 |
Kerr | +3.362 |
Neg logit contributions | |
Roose | -5.164 |
Cumm | -4.919 |
kson | -4.758 |
STD | -4.747 |
| -4.665 |
Token | Congress |
Token ID | 3162 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
rule | +2.457 |
arre | +2.454 |
crab | +2.110 |
hig | +2.105 |
Kerr | +2.095 |
Neg logit contributions | |
Roose | -2.585 |
Cumm | -2.466 |
kson | -2.340 |
STD | -2.335 |
| -2.313 |
Token | about |
Token ID | 546 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
arre | +1.371 |
rule | +1.346 |
crab | +1.145 |
hig | +1.141 |
Kerr | +1.119 |
Neg logit contributions | |
Roose | -1.477 |
Cumm | -1.422 |
STD | -1.348 |
| -1.321 |
kson | -1.316 |
Token | secret |
Token ID | 3200 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Roose | +2.170 |
Cumm | +2.094 |
STD | +1.986 |
Garrison | +1.937 |
| +1.914 |
Neg logit contributions | |
arre | -2.315 |
rule | -2.280 |
hig | -1.914 |
crab | -1.898 |
モ | -1.864 |
Token | research |
Token ID | 2267 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
Roose | +1.355 |
Cumm | +1.314 |
STD | +1.256 |
Garrison | +1.219 |
| +1.212 |
Neg logit contributions | |
arre | -1.285 |
rule | -1.254 |
hig | -1.044 |
crab | -1.034 |
Kerr | -1.014 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Roose | +2.629 |
Cumm | +2.557 |
STD | +2.404 |
| +2.343 |
Garrison | +2.318 |
Neg logit contributions | |
arre | -3.097 |
rule | -3.055 |
crab | -2.593 |
hig | -2.591 |
モ | -2.548 |
Token | across |
Token ID | 1973 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
Roose | +1.992 |
Cumm | +1.931 |
STD | +1.805 |
| +1.787 |
Garrison | +1.779 |
Neg logit contributions | |
arre | -2.144 |
rule | -2.118 |
crab | -1.777 |
hig | -1.774 |
モ | -1.739 |
Token | the |
Token ID | 262 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
Roose | +4.133 |
Cumm | +4.033 |
| +3.741 |
STD | +3.720 |
Garrison | +3.667 |
Neg logit contributions | |
arre | -5.017 |
rule | -4.945 |
hig | -4.245 |
ミ | -4.223 |
モ | -4.190 |
Token | south |
Token ID | 5366 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
Roose | +3.112 |
Cumm | +2.956 |
STD | +2.760 |
| +2.742 |
Garrison | +2.714 |
Neg logit contributions | |
arre | -3.853 |
rule | -3.811 |
hig | -3.222 |
crab | -3.205 |
モ | -3.200 |
Token | - |
Token ID | 12 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
Roose | +3.453 |
Cumm | +3.298 |
STD | +3.081 |
| +3.079 |
Garrison | +3.056 |
Neg logit contributions | |
arre | -3.850 |
rule | -3.803 |
hig | -3.217 |
crab | -3.183 |
モ | -3.146 |
Token | e |
Token ID | 68 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
Roose | +2.539 |
Cumm | +2.387 |
| +2.218 |
STD | +2.195 |
Garrison | +2.152 |
Neg logit contributions | |
arre | -4.368 |
rule | -4.297 |
hig | -3.854 |
crab | -3.843 |
Kerr | -3.790 |
Token | astern |
Token ID | 6470 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
arre | +0.972 |
rule | +0.964 |
crab | +0.861 |
hig | +0.859 |
Kerr | +0.850 |
Neg logit contributions | |
Roose | -0.430 |
Cumm | -0.400 |
STD | -0.366 |
| -0.353 |
Garrison | -0.348 |
Token | Bahamas |
Token ID | 45726 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
arre | +0.559 |
rule | +0.551 |
crab | +0.473 |
hig | +0.471 |
Kerr | +0.463 |
Neg logit contributions | |
Roose | -0.517 |
Cumm | -0.497 |
STD | -0.469 |
| -0.459 |
kson | -0.455 |
Token | late |
Token ID | 2739 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Roose | +0.944 |
Cumm | +0.907 |
STD | +0.854 |
| +0.841 |
Garrison | +0.834 |
Neg logit contributions | |
arre | -1.078 |
rule | -1.064 |
crab | -0.906 |
hig | -0.904 |
Kerr | -0.891 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
Roose | +3.016 |
Cumm | +2.977 |
STD | +2.805 |
| +2.787 |
Garrison | +2.769 |
Neg logit contributions | |
arre | -2.270 |
rule | -2.232 |
hig | -1.770 |
crab | -1.751 |
Kerr | -1.738 |
Token | and |
Token ID | 290 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Roose | +3.286 |
Cumm | +3.206 |
STD | +3.014 |
| +2.946 |
Garrison | +2.923 |
Neg logit contributions | |
arre | -3.769 |
rule | -3.735 |
crab | -3.142 |
hig | -3.132 |
モ | -3.113 |
Token | induced |
Token ID | 17223 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Roose | +4.042 |
Cumm | +3.833 |
STD | +3.772 |
| +3.626 |
onom | +3.606 |
Neg logit contributions | |
arre | -4.842 |
rule | -4.780 |
hig | -4.294 |
crab | -4.252 |
Kerr | -4.220 |
Token | nerve |
Token ID | 16384 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Roose | +0.750 |
Cumm | +0.719 |
STD | +0.690 |
| +0.668 |
Garrison | +0.663 |
Neg logit contributions | |
arre | -0.799 |
rule | -0.788 |
crab | -0.668 |
hig | -0.667 |
Kerr | -0.657 |
Token | damage |
Token ID | 2465 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
Roose | +1.903 |
Cumm | +1.839 |
STD | +1.765 |
| +1.707 |
Garrison | +1.699 |
Neg logit contributions | |
arre | -1.978 |
rule | -1.953 |
hig | -1.672 |
crab | -1.649 |
Kerr | -1.626 |
Token | .[ |
Token ID | 3693 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
arre | +0.615 |
rule | +0.606 |
crab | +0.513 |
hig | +0.511 |
Kerr | +0.501 |
Neg logit contributions | |
Roose | -0.660 |
Cumm | -0.635 |
STD | -0.602 |
| -0.590 |
kson | -0.586 |
Token | 25 |
Token ID | 1495 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Roose | +2.742 |
Cumm | +2.637 |
STD | +2.455 |
| +2.409 |
kson | +2.389 |
Neg logit contributions | |
arre | -3.947 |
rule | -3.807 |
hig | -3.427 |
crab | -3.377 |
Kerr | -3.338 |
Token | ] |
Token ID | 60 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
arre | +1.321 |
rule | +1.307 |
crab | +1.066 |
hig | +1.044 |
Kerr | +1.040 |
Neg logit contributions | |
Roose | -2.038 |
Cumm | -1.959 |
STD | -1.868 |
| -1.843 |
kson | -1.834 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
arre | +0.428 |
rule | +0.421 |
crab | +0.357 |
hig | +0.355 |
Kerr | +0.350 |
Neg logit contributions | |
Roose | -0.457 |
Cumm | -0.440 |
STD | -0.416 |
| -0.409 |
kson | -0.406 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Roose | +0.908 |
Cumm | +0.880 |
STD | +0.839 |
| +0.835 |
Garrison | +0.815 |
Neg logit contributions | |
arre | -0.877 |
rule | -0.855 |
hig | -0.739 |
crab | -0.729 |
Kerr | -0.710 |
Token | Other |
Token ID | 6395 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Roose | +0.943 |
Cumm | +0.903 |
STD | +0.861 |
| +0.846 |
kson | +0.831 |
Neg logit contributions | |
arre | -0.987 |
rule | -0.970 |
crab | -0.841 |
hig | -0.841 |
Kerr | -0.822 |
Token | animals |
Token ID | 4695 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Roose | +2.888 |
Cumm | +2.765 |
STD | +2.706 |
Garrison | +2.562 |
| +2.556 |
Neg logit contributions | |
arre | -2.872 |
rule | -2.842 |
crab | -2.371 |
hig | -2.366 |
Kerr | -2.322 |
Token | [ |
Token ID | 685 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
Roose | +3.229 |
Cumm | +3.100 |
STD | +2.994 |
| +2.875 |
Garrison | +2.846 |
Neg logit contributions | |
arre | -3.562 |
rule | -3.540 |
crab | -2.990 |
hig | -2.989 |
モ | -2.963 |
Token | to |
Token ID | 284 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Roose | +1.374 |
Cumm | +1.335 |
STD | +1.250 |
| +1.234 |
Garrison | +1.222 |
Neg logit contributions | |
arre | -1.474 |
rule | -1.448 |
crab | -1.245 |
hig | -1.237 |
Kerr | -1.214 |
Token | identity |
Token ID | 5369 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Roose | +0.604 |
Cumm | +0.582 |
STD | +0.550 |
| +0.541 |
Garrison | +0.536 |
Neg logit contributions | |
arre | -0.588 |
rule | -0.575 |
crab | -0.490 |
hig | -0.487 |
Kerr | -0.475 |
Token | are |
Token ID | 389 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
arre | +0.077 |
rule | +0.075 |
crab | +0.065 |
hig | +0.065 |
Kerr | +0.063 |
Neg logit contributions | |
Roose | -0.071 |
Cumm | -0.068 |
STD | -0.064 |
| -0.063 |
kson | -0.063 |
Token | now |
Token ID | 783 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
arre | +0.859 |
rule | +0.846 |
crab | +0.724 |
hig | +0.721 |
Kerr | +0.708 |
Neg logit contributions | |
Roose | -0.834 |
Cumm | -0.801 |
STD | -0.757 |
| -0.742 |
kson | -0.736 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
arre | +0.688 |
rule | +0.677 |
crab | +0.579 |
hig | +0.576 |
Kerr | +0.566 |
Neg logit contributions | |
Roose | -0.665 |
Cumm | -0.640 |
STD | -0.604 |
| -0.592 |
kson | -0.587 |
Token | exclusively |
Token ID | 11541 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
arre | +0.098 |
rule | +0.097 |
crab | +0.083 |
hig | +0.082 |
Kerr | +0.081 |
Neg logit contributions | |
Roose | -0.095 |
Cumm | -0.092 |
STD | -0.087 |
| -0.085 |
Garrison | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
arre | +2.829 |
rule | +2.812 |
crab | +2.413 |
hig | +2.399 |
Kerr | +2.362 |
Neg logit contributions | |
Roose | -3.017 |
Cumm | -2.901 |
STD | -2.732 |
| -2.679 |
kson | -2.671 |
Token | preserve |
Token ID | 12201 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
arre | +3.582 |
rule | +3.555 |
crab | +2.991 |
hig | +2.970 |
Kerr | +2.922 |
Neg logit contributions | |
Roose | -4.000 |
Cumm | -3.899 |
STD | -3.649 |
Garrison | -3.583 |
kson | -3.582 |
Token | of |
Token ID | 286 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
rule | +2.358 |
arre | +2.352 |
crab | +1.954 |
hig | +1.938 |
Kerr | +1.910 |
Neg logit contributions | |
Roose | -2.941 |
Cumm | -2.842 |
STD | -2.704 |
kson | -2.634 |
Garrison | -2.633 |
Token | the |
Token ID | 262 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Roose | +0.019 |
Cumm | +0.019 |
STD | +0.018 |
| +0.017 |
Garrison | +0.017 |
Neg logit contributions | |
arre | -0.020 |
rule | -0.019 |
crab | -0.017 |
hig | -0.016 |
Kerr | -0.016 |
Token | no |
Token ID | 645 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Roose | +0.290 |
Cumm | +0.278 |
STD | +0.263 |
| +0.259 |
Garrison | +0.258 |
Neg logit contributions | |
arre | -0.274 |
rule | -0.268 |
crab | -0.226 |
hig | -0.225 |
Kerr | -0.220 |
Token | This |
Token ID | 1212 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
arre | +1.590 |
rule | +1.573 |
crab | +1.337 |
hig | +1.334 |
Kerr | +1.311 |
Neg logit contributions | |
Roose | -1.484 |
Cumm | -1.421 |
STD | -1.342 |
kson | -1.302 |
| -1.302 |
Token | week |
Token ID | 1285 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
arre | +2.106 |
rule | +2.080 |
crab | +1.778 |
hig | +1.768 |
Kerr | +1.726 |
Neg logit contributions | |
Roose | -2.246 |
Cumm | -2.147 |
STD | -2.033 |
kson | -1.996 |
| -1.995 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
arre | +0.344 |
rule | +0.339 |
crab | +0.290 |
hig | +0.289 |
Kerr | +0.283 |
Neg logit contributions | |
Roose | -0.334 |
Cumm | -0.321 |
STD | -0.304 |
| -0.298 |
kson | -0.295 |
Token | the |
Token ID | 262 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
arre | +1.440 |
rule | +1.417 |
crab | +1.207 |
hig | +1.205 |
Kerr | +1.183 |
Neg logit contributions | |
Roose | -1.491 |
Cumm | -1.432 |
STD | -1.360 |
| -1.332 |
kson | -1.324 |
Token | giant |
Token ID | 6175 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
Roose | +0.756 |
Cumm | +0.732 |
STD | +0.691 |
| +0.677 |
Garrison | +0.676 |
Neg logit contributions | |
arre | -0.687 |
rule | -0.675 |
crab | -0.567 |
hig | -0.564 |
Kerr | -0.552 |
Token | PS |
Token ID | 6599 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Roose | +0.374 |
Cumm | +0.361 |
STD | +0.341 |
| +0.333 |
Garrison | +0.333 |
Neg logit contributions | |
arre | -0.350 |
rule | -0.343 |
hig | -0.288 |
crab | -0.288 |
Kerr | -0.282 |
Token | AC |
Token ID | 2246 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
arre | +0.808 |
rule | +0.791 |
crab | +0.665 |
hig | +0.660 |
Kerr | +0.647 |
Neg logit contributions | |
Roose | -0.987 |
Cumm | -0.948 |
STD | -0.903 |
| -0.891 |
kson | -0.886 |
Token | is |
Token ID | 318 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
arre | +0.066 |
rule | +0.065 |
crab | +0.055 |
hig | +0.055 |
Kerr | +0.054 |
Neg logit contributions | |
Roose | -0.069 |
Cumm | -0.066 |
STD | -0.063 |
| -0.061 |
Garrison | -0.061 |
Token | launching |
Token ID | 13925 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Roose | +1.795 |
Cumm | +1.737 |
STD | +1.629 |
| +1.590 |
Garrison | +1.590 |
Neg logit contributions | |
arre | -2.028 |
rule | -2.001 |
crab | -1.687 |
hig | -1.677 |
Kerr | -1.660 |
Token | a |
Token ID | 257 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Roose | +0.096 |
Cumm | +0.093 |
STD | +0.088 |
| +0.086 |
Garrison | +0.085 |
Neg logit contributions | |
arre | -0.104 |
rule | -0.102 |
crab | -0.087 |
hig | -0.087 |
Kerr | -0.086 |
Token | series |
Token ID | 2168 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Roose | +0.851 |
Cumm | +0.823 |
STD | +0.778 |
| +0.761 |
Garrison | +0.759 |
Neg logit contributions | |
arre | -0.830 |
rule | -0.814 |
crab | -0.682 |
hig | -0.681 |
Kerr | -0.669 |
Token | � |
Token ID | 447 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
arre | +0.742 |
rule | +0.731 |
crab | +0.622 |
hig | +0.619 |
Kerr | +0.607 |
Neg logit contributions | |
Roose | -0.760 |
Cumm | -0.732 |
STD | -0.692 |
| -0.679 |
kson | -0.673 |
Token | � |
Token ID | 251 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
arre | +1.219 |
rule | +1.199 |
crab | +1.035 |
hig | +1.035 |
Kerr | +1.020 |
Neg logit contributions | |
Roose | -1.024 |
Cumm | -0.977 |
STD | -0.923 |
| -0.895 |
kson | -0.895 |
Token | � |
Token ID | 564 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
arre | +2.251 |
rule | +2.218 |
Kerr | +1.874 |
crab | +1.874 |
hig | +1.862 |
Neg logit contributions | |
Roose | -2.460 |
Cumm | -2.359 |
STD | -2.254 |
kson | -2.192 |
| -2.188 |
Token | � |
Token ID | 250 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
arre | +1.398 |
rule | +1.378 |
hig | +1.196 |
crab | +1.196 |
Kerr | +1.180 |
Neg logit contributions | |
Roose | -1.032 |
Cumm | -0.990 |
STD | -0.926 |
kson | -0.897 |
Garrison | -0.896 |
Token | They |
Token ID | 2990 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
arre | +0.150 |
rule | +0.147 |
crab | +0.127 |
hig | +0.127 |
Kerr | +0.124 |
Neg logit contributions | |
Roose | -0.136 |
Cumm | -0.130 |
STD | -0.123 |
| -0.121 |
Garrison | -0.119 |
Token | don |
Token ID | 836 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
arre | +1.992 |
rule | +1.947 |
hig | +1.697 |
crab | +1.694 |
Kerr | +1.655 |
Neg logit contributions | |
Roose | -1.734 |
Cumm | -1.672 |
STD | -1.568 |
| -1.528 |
Garrison | -1.523 |
Token | � |
Token ID | 447 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
arre | +2.549 |
rule | +2.506 |
crab | +2.131 |
hig | +2.117 |
Kerr | +2.094 |
Neg logit contributions | |
Roose | -2.547 |
Cumm | -2.440 |
STD | -2.300 |
Garrison | -2.238 |
| -2.226 |
Token | � |
Token ID | 247 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
arre | +0.620 |
rule | +0.611 |
crab | +0.522 |
hig | +0.521 |
Kerr | +0.510 |
Neg logit contributions | |
Roose | -0.602 |
Cumm | -0.579 |
STD | -0.546 |
| -0.537 |
kson | -0.533 |
Token | t |
Token ID | 83 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
Roose | +0.416 |
Cumm | +0.397 |
STD | +0.372 |
| +0.363 |
kson | +0.359 |
Neg logit contributions | |
arre | -0.624 |
rule | -0.617 |
crab | -0.542 |
hig | -0.539 |
Kerr | -0.532 |
Token | like |
Token ID | 588 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
arre | +0.719 |
rule | +0.708 |
crab | +0.612 |
hig | +0.610 |
Kerr | +0.601 |
Neg logit contributions | |
Roose | -0.596 |
Cumm | -0.571 |
STD | -0.538 |
| -0.526 |
Garrison | -0.520 |
Token | surprises |
Token ID | 24072 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
arre | +0.950 |
rule | +0.936 |
crab | +0.801 |
hig | +0.798 |
Kerr | +0.785 |
Neg logit contributions | |
Roose | -0.929 |
Cumm | -0.893 |
STD | -0.844 |
| -0.828 |
kson | -0.822 |
Token | I |
Token ID | 314 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Roose | +2.043 |
Cumm | +1.972 |
STD | +1.848 |
| +1.824 |
kson | +1.792 |
Neg logit contributions | |
arre | -2.404 |
rule | -2.372 |
crab | -2.011 |
hig | -1.993 |
モ | -1.972 |
Token | only |
Token ID | 691 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Roose | +1.182 |
Cumm | +1.135 |
STD | +1.073 |
| +1.067 |
Garrison | +1.039 |
Neg logit contributions | |
arre | -1.257 |
rule | -1.228 |
crab | -1.039 |
Kerr | -1.032 |
hig | -1.026 |
Token | want |
Token ID | 765 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Roose | +0.332 |
Cumm | +0.319 |
STD | +0.302 |
| +0.298 |
Garrison | +0.293 |
Neg logit contributions | |
arre | -0.333 |
rule | -0.327 |
crab | -0.277 |
hig | -0.276 |
Kerr | -0.273 |
Token | those |
Token ID | 883 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Roose | +2.187 |
Cumm | +2.114 |
STD | +1.997 |
| +1.958 |
Garrison | +1.934 |
Neg logit contributions | |
arre | -2.387 |
rule | -2.346 |
crab | -1.987 |
hig | -1.978 |
Kerr | -1.937 |
Token | that |
Token ID | 326 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
arre | +0.237 |
rule | +0.234 |
crab | +0.203 |
hig | +0.202 |
Kerr | +0.199 |
Neg logit contributions | |
Roose | -0.183 |
Cumm | -0.175 |
STD | -0.164 |
| -0.160 |
Garrison | -0.158 |
Token | attempted |
Token ID | 7482 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Roose | +1.370 |
Cumm | +1.316 |
STD | +1.242 |
| +1.220 |
Garrison | +1.197 |
Neg logit contributions | |
arre | -1.594 |
rule | -1.563 |
crab | -1.344 |
hig | -1.328 |
Kerr | -1.317 |
Token | to |
Token ID | 284 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Roose | +1.428 |
Cumm | +1.381 |
STD | +1.311 |
| +1.279 |
Garrison | +1.265 |
Neg logit contributions | |
arre | -1.492 |
rule | -1.465 |
crab | -1.246 |
hig | -1.234 |
Kerr | -1.214 |
Token | reach |
Token ID | 3151 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
Roose | +0.733 |
Cumm | +0.706 |
STD | +0.669 |
| +0.656 |
Garrison | +0.645 |
Neg logit contributions | |
arre | -0.824 |
rule | -0.808 |
crab | -0.691 |
hig | -0.687 |
Kerr | -0.682 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
arre | +0.603 |
rule | +0.593 |
crab | +0.508 |
hig | +0.505 |
Kerr | +0.496 |
Neg logit contributions | |
Roose | -0.573 |
Cumm | -0.550 |
STD | -0.520 |
| -0.509 |
kson | -0.504 |
Token | answer |
Token ID | 3280 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
Roose | +0.811 |
Cumm | +0.780 |
STD | +0.739 |
| +0.722 |
Garrison | +0.716 |
Neg logit contributions | |
arre | -0.853 |
rule | -0.837 |
crab | -0.713 |
hig | -0.702 |
Kerr | -0.695 |
Token | by |
Token ID | 416 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
arre | +0.003 |
rule | +0.003 |
crab | +0.002 |
hig | +0.002 |
Kerr | +0.002 |
Neg logit contributions | |
Roose | -0.003 |
Cumm | -0.002 |
STD | -0.002 |
| -0.002 |
Garrison | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
Roose | +2.401 |
Cumm | +2.334 |
STD | +2.188 |
Garrison | +2.154 |
| +2.094 |
Neg logit contributions | |
arre | -2.774 |
rule | -2.709 |
hig | -2.319 |
crab | -2.307 |
モ | -2.261 |
Token | rink |
Token ID | 47925 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
Roose | +4.255 |
Cumm | +4.186 |
STD | +4.018 |
Garrison | +3.938 |
| +3.919 |
Neg logit contributions | |
arre | -2.809 |
rule | -2.719 |
hig | -2.180 |
crab | -2.143 |
モ | -2.098 |
Token | in |
Token ID | 287 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
Roose | +2.181 |
Cumm | +2.118 |
STD | +1.994 |
Garrison | +1.947 |
kson | +1.943 |
Neg logit contributions | |
arre | -2.509 |
rule | -2.478 |
hig | -2.096 |
crab | -2.079 |
モ | -2.066 |
Token | a |
Token ID | 257 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
arre | +2.859 |
rule | +2.815 |
crab | +2.416 |
hig | +2.394 |
Kerr | +2.378 |
Neg logit contributions | |
Roose | -3.103 |
Cumm | -2.976 |
STD | -2.838 |
| -2.790 |
kson | -2.776 |
Token | different |
Token ID | 1180 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
arre | +0.705 |
rule | +0.695 |
crab | +0.591 |
hig | +0.589 |
Kerr | +0.577 |
Neg logit contributions | |
Roose | -0.718 |
Cumm | -0.691 |
STD | -0.653 |
| -0.640 |
Garrison | -0.635 |
Token | dressing |
Token ID | 18544 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
Roose | +0.211 |
Cumm | +0.204 |
STD | +0.195 |
| +0.190 |
kson | +0.190 |
Neg logit contributions | |
arre | -0.180 |
rule | -0.177 |
hig | -0.147 |
crab | -0.146 |
Kerr | -0.142 |
Token | room |
Token ID | 2119 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Roose | +2.388 |
Cumm | +2.326 |
STD | +2.153 |
Garrison | +2.134 |
| +2.116 |
Neg logit contributions | |
arre | -3.513 |
rule | -3.501 |
hig | -3.034 |
crab | -2.998 |
モ | -2.933 |
Token | ? |
Token ID | 30 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
Roose | +1.043 |
Cumm | +1.009 |
STD | +0.953 |
| +0.926 |
kson | +0.926 |
Neg logit contributions | |
arre | -1.141 |
rule | -1.125 |
hig | -0.955 |
crab | -0.951 |
Kerr | -0.935 |
Token | It |
Token ID | 632 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
arre | +0.569 |
rule | +0.560 |
crab | +0.478 |
hig | +0.476 |
Kerr | +0.467 |
Neg logit contributions | |
Roose | -0.567 |
Cumm | -0.545 |
STD | -0.515 |
| -0.505 |
Garrison | -0.501 |
Token | 's |
Token ID | 338 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
arre | +0.147 |
rule | +0.145 |
crab | +0.126 |
hig | +0.125 |
Kerr | +0.123 |
Neg logit contributions | |
Roose | -0.121 |
Cumm | -0.116 |
STD | -0.109 |
| -0.106 |
kson | -0.105 |
Token | going |
Token ID | 1016 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
arre | +3.046 |
rule | +2.991 |
crab | +2.641 |
hig | +2.606 |
Kerr | +2.563 |
Neg logit contributions | |
Roose | -3.263 |
Cumm | -3.128 |
STD | -2.955 |
kson | -2.910 |
| -2.909 |
Token | visitors |
Token ID | 9692 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
arre | +0.939 |
rule | +0.922 |
crab | +0.762 |
hig | +0.757 |
Kerr | +0.742 |
Neg logit contributions | |
Roose | -1.289 |
Cumm | -1.248 |
STD | -1.189 |
| -1.170 |
kson | -1.161 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
arre | +0.719 |
rule | +0.709 |
crab | +0.600 |
hig | +0.598 |
Kerr | +0.586 |
Neg logit contributions | |
Roose | -0.762 |
Cumm | -0.733 |
STD | -0.694 |
| -0.682 |
Garrison | -0.675 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Roose | +2.143 |
Cumm | +2.046 |
| +1.912 |
STD | +1.910 |
Garrison | +1.882 |
Neg logit contributions | |
arre | -2.420 |
rule | -2.386 |
hig | -2.064 |
crab | -2.056 |
モ | -1.972 |
Token | Christian |
Token ID | 20298 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Roose | +1.996 |
Cumm | +1.920 |
| +1.825 |
STD | +1.822 |
onom | +1.774 |
Neg logit contributions | |
arre | -2.152 |
rule | -2.092 |
hig | -1.845 |
crab | -1.839 |
Kerr | -1.805 |
Token | philosopher |
Token ID | 23723 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
arre | +0.774 |
rule | +0.762 |
crab | +0.652 |
hig | +0.649 |
Kerr | +0.638 |
Neg logit contributions | |
Roose | -0.753 |
Cumm | -0.724 |
STD | -0.684 |
| -0.670 |
kson | -0.665 |
Token | and |
Token ID | 290 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
Roose | +4.094 |
Cumm | +3.939 |
STD | +3.631 |
Garrison | +3.621 |
| +3.583 |
Neg logit contributions | |
arre | -4.706 |
rule | -4.675 |
hig | -3.917 |
crab | -3.906 |
ミ | -3.850 |
Token | blogger |
Token ID | 23530 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
Roose | +2.658 |
Cumm | +2.564 |
STD | +2.426 |
Garrison | +2.372 |
| +2.346 |
Neg logit contributions | |
arre | -2.846 |
rule | -2.801 |
hig | -2.341 |
crab | -2.332 |
モ | -2.302 |
Token | Dr |
Token ID | 1583 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Roose | +2.496 |
Cumm | +2.407 |
STD | +2.227 |
Garrison | +2.220 |
| +2.189 |
Neg logit contributions | |
arre | -2.796 |
rule | -2.773 |
crab | -2.341 |
hig | -2.338 |
モ | -2.278 |
Token | Glenn |
Token ID | 17551 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Roose | +0.795 |
Cumm | +0.769 |
STD | +0.721 |
| +0.710 |
Garrison | +0.707 |
Neg logit contributions | |
arre | -0.776 |
rule | -0.767 |
crab | -0.654 |
hig | -0.651 |
Kerr | -0.632 |
Token | Peoples |
Token ID | 41770 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Roose | +0.886 |
Cumm | +0.856 |
STD | +0.806 |
Garrison | +0.795 |
| +0.792 |
Neg logit contributions | |
arre | -0.786 |
rule | -0.776 |
crab | -0.653 |
hig | -0.651 |
Kerr | -0.627 |
Token | is |
Token ID | 318 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
arre | +0.104 |
rule | +0.102 |
crab | +0.087 |
hig | +0.087 |
Kerr | +0.086 |
Neg logit contributions | |
Roose | -0.100 |
Cumm | -0.096 |
STD | -0.091 |
| -0.089 |
kson | -0.088 |
Token | stop |
Token ID | 2245 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
Roose | +0.277 |
Cumm | +0.267 |
STD | +0.253 |
| +0.251 |
Garrison | +0.245 |
Neg logit contributions | |
arre | -0.277 |
rule | -0.273 |
crab | -0.233 |
hig | -0.229 |
Kerr | -0.228 |
Token | using |
Token ID | 1262 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
Roose | +1.289 |
Cumm | +1.240 |
STD | +1.159 |
| +1.137 |
Garrison | +1.121 |
Neg logit contributions | |
arre | -1.889 |
rule | -1.881 |
crab | -1.632 |
hig | -1.607 |
Kerr | -1.591 |
Token | that |
Token ID | 326 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
Roose | +0.458 |
Cumm | +0.440 |
STD | +0.416 |
| +0.407 |
Garrison | +0.401 |
Neg logit contributions | |
arre | -0.547 |
rule | -0.542 |
crab | -0.467 |
hig | -0.462 |
Kerr | -0.455 |
Token | particular |
Token ID | 1948 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
Roose | +5.308 |
Cumm | +5.201 |
STD | +5.086 |
| +4.943 |
Garrison | +4.794 |
Neg logit contributions | |
arre | -5.707 |
rule | -5.612 |
crab | -4.774 |
モ | -4.626 |
Kerr | -4.584 |
Token | device |
Token ID | 3335 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Roose | +4.075 |
Cumm | +3.975 |
STD | +3.841 |
| +3.720 |
Garrison | +3.666 |
Neg logit contributions | |
arre | -4.209 |
rule | -4.130 |
crab | -3.473 |
hig | -3.383 |
モ | -3.358 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Roose | +1.212 |
Cumm | +1.169 |
STD | +1.110 |
| +1.086 |
kson | +1.073 |
Neg logit contributions | |
arre | -1.291 |
rule | -1.273 |
crab | -1.091 |
hig | -1.074 |
Kerr | -1.065 |
Token | you |
Token ID | 345 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Roose | +1.588 |
Cumm | +1.534 |
STD | +1.458 |
| +1.436 |
Garrison | +1.401 |
Neg logit contributions | |
arre | -1.773 |
rule | -1.745 |
crab | -1.499 |
hig | -1.478 |
Kerr | -1.454 |
Token | lose |
Token ID | 4425 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Roose | +1.948 |
Cumm | +1.886 |
STD | +1.804 |
| +1.785 |
onom | +1.748 |
Neg logit contributions | |
arre | -1.816 |
rule | -1.785 |
crab | -1.527 |
Kerr | -1.504 |
hig | -1.498 |
Token | access |
Token ID | 1895 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Roose | +0.735 |
Cumm | +0.710 |
STD | +0.676 |
| +0.663 |
Garrison | +0.652 |
Neg logit contributions | |
arre | -0.779 |
rule | -0.766 |
crab | -0.653 |
hig | -0.647 |
Kerr | -0.640 |
Token | to |
Token ID | 284 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
Roose | +1.115 |
Cumm | +1.075 |
STD | +1.021 |
| +1.002 |
Garrison | +0.989 |
Neg logit contributions | |
arre | -1.122 |
rule | -1.105 |
crab | -0.943 |
hig | -0.936 |
Kerr | -0.923 |
Token | that |
Token ID | 326 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
Roose | +3.176 |
Cumm | +3.072 |
STD | +2.955 |
| +2.886 |
Garrison | +2.831 |
Neg logit contributions | |
arre | -3.727 |
rule | -3.696 |
crab | -3.168 |
hig | -3.085 |
Kerr | -3.073 |
Token | main |
Token ID | 1388 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
arre | +0.489 |
rule | +0.482 |
crab | +0.410 |
hig | +0.409 |
Kerr | +0.401 |
Neg logit contributions | |
Roose | -0.493 |
Cumm | -0.474 |
STD | -0.449 |
| -0.440 |
Garrison | -0.436 |
Token | platform |
Token ID | 3859 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Roose | +0.100 |
Cumm | +0.096 |
STD | +0.091 |
| +0.089 |
Garrison | +0.089 |
Neg logit contributions | |
arre | -0.096 |
rule | -0.095 |
crab | -0.080 |
hig | -0.080 |
Kerr | -0.078 |
Token | were |
Token ID | 547 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
arre | +1.314 |
rule | +1.294 |
crab | +1.104 |
hig | +1.100 |
Kerr | +1.081 |
Neg logit contributions | |
Roose | -1.355 |
Cumm | -1.303 |
STD | -1.233 |
| -1.208 |
kson | -1.201 |
Token | buying |
Token ID | 7067 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
arre | +0.317 |
rule | +0.313 |
crab | +0.267 |
hig | +0.266 |
Kerr | +0.262 |
Neg logit contributions | |
Roose | -0.304 |
Cumm | -0.292 |
STD | -0.276 |
| -0.271 |
kson | -0.268 |
Token | a |
Token ID | 257 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
arre | +1.298 |
rule | +1.279 |
crab | +1.091 |
hig | +1.089 |
Kerr | +1.071 |
Neg logit contributions | |
Roose | -1.311 |
Cumm | -1.258 |
STD | -1.191 |
| -1.165 |
kson | -1.158 |
Token | piece |
Token ID | 3704 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
arre | +0.493 |
rule | +0.485 |
crab | +0.412 |
hig | +0.411 |
Kerr | +0.403 |
Neg logit contributions | |
Roose | -0.506 |
Cumm | -0.487 |
STD | -0.461 |
| -0.452 |
Garrison | -0.448 |
Token | of |
Token ID | 286 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Roose | +1.491 |
Cumm | +1.437 |
STD | +1.363 |
| +1.338 |
Garrison | +1.324 |
Neg logit contributions | |
arre | -1.420 |
rule | -1.398 |
crab | -1.184 |
hig | -1.180 |
Kerr | -1.158 |
Token | hardware |
Token ID | 6890 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
arre | +0.358 |
rule | +0.353 |
crab | +0.299 |
hig | +0.298 |
Kerr | +0.292 |
Neg logit contributions | |
Roose | -0.384 |
Cumm | -0.370 |
STD | -0.350 |
| -0.344 |
Garrison | -0.341 |
Token | based |
Token ID | 1912 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Roose | +3.333 |
Cumm | +3.250 |
STD | +3.057 |
| +2.995 |
Garrison | +2.992 |
Neg logit contributions | |
arre | -3.795 |
rule | -3.736 |
crab | -3.153 |
hig | -3.125 |
モ | -3.110 |
Token | on |
Token ID | 319 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
arre | +1.106 |
rule | +1.090 |
crab | +0.943 |
hig | +0.941 |
Kerr | +0.926 |
Neg logit contributions | |
Roose | -0.957 |
Cumm | -0.915 |
STD | -0.860 |
| -0.840 |
kson | -0.834 |
Token | putting |
Token ID | 5137 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
arre | +2.452 |
rule | +2.407 |
hig | +2.080 |
crab | +2.070 |
Kerr | +2.038 |
Neg logit contributions | |
Roose | -2.604 |
Cumm | -2.484 |
STD | -2.364 |
| -2.312 |
kson | -2.311 |
Token | image |
Token ID | 2939 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Roose | +3.923 |
STD | +3.889 |
Cumm | +3.837 |
| +3.813 |
Garrison | +3.652 |
Neg logit contributions | |
arre | -3.475 |
rule | -3.215 |
モ | -2.689 |
hig | -2.636 |
ミ | -2.618 |
Token | Path |
Token ID | 15235 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
Roose | +0.357 |
Cumm | +0.345 |
STD | +0.332 |
| +0.328 |
Garrison | +0.322 |
Neg logit contributions | |
arre | -0.285 |
rule | -0.277 |
crab | -0.232 |
hig | -0.232 |
Kerr | -0.220 |
Token | in |
Token ID | 287 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Roose | +0.584 |
Cumm | +0.563 |
STD | +0.537 |
| +0.529 |
Garrison | +0.517 |
Neg logit contributions | |
arre | -0.642 |
rule | -0.630 |
hig | -0.541 |
crab | -0.540 |
Kerr | -0.529 |
Token | paths |
Token ID | 13532 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
Roose | +0.386 |
Cumm | +0.375 |
STD | +0.362 |
| +0.357 |
kson | +0.353 |
Neg logit contributions | |
arre | -0.230 |
rule | -0.225 |
crab | -0.178 |
hig | -0.176 |
Kerr | -0.172 |
Token | . |
Token ID | 764 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
Roose | +0.240 |
Cumm | +0.222 |
STD | +0.200 |
| +0.192 |
Garrison | +0.184 |
Neg logit contributions | |
arre | -0.728 |
rule | -0.718 |
hig | -0.648 |
crab | -0.647 |
Kerr | -0.642 |
Token | list |
Token ID | 1351 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
arre | +0.554 |
rule | +0.544 |
crab | +0.444 |
hig | +0.443 |
Kerr | +0.430 |
Neg logit contributions | |
Roose | -0.843 |
Cumm | -0.816 |
STD | -0.777 |
| -0.766 |
kson | -0.762 |
Token | _ |
Token ID | 62 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
Roose | +4.985 |
| +4.766 |
STD | +4.573 |
Cumm | +4.521 |
kson | +4.260 |
Neg logit contributions | |
arre | -10.729 |
��� | -10.405 |
rule | -10.297 |
hig | -9.720 |
crab | -9.525 |
Token | images |
Token ID | 17566 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
Roose | +2.661 |
Cumm | +2.511 |
| +2.485 |
onom | +2.424 |
STD | +2.414 |
Neg logit contributions | |
arre | -4.210 |
rule | -4.055 |
hig | -3.723 |
crab | -3.696 |
Kerr | -3.674 |
Token | ( |
Token ID | 357 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Roose | +3.843 |
Cumm | +3.712 |
STD | +3.672 |
| +3.612 |
kson | +3.427 |
Neg logit contributions | |
arre | -4.181 |
rule | -4.009 |
hig | -3.572 |
crab | -3.493 |
Kerr | -3.437 |
Token | args |
Token ID | 26498 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
Roose | +1.184 |
Cumm | +1.122 |
STD | +1.105 |
Garrison | +1.066 |
| +1.058 |
Neg logit contributions | |
arre | -1.089 |
rule | -1.060 |
crab | -0.890 |
hig | -0.887 |
モ | -0.878 |
Token | [ |
Token ID | 685 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
Roose | +5.034 |
Cumm | +5.022 |
STD | +4.927 |
| +4.825 |
onom | +4.661 |
Neg logit contributions | |
rule | -7.591 |
arre | -7.434 |
��� | -6.508 |
hig | -6.505 |
crab | -6.379 |
Token | 05 |
Token ID | 2713 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
arre | +1.660 |
rule | +1.636 |
crab | +1.370 |
hig | +1.362 |
Kerr | +1.343 |
Neg logit contributions | |
Roose | -1.933 |
Cumm | -1.861 |
STD | -1.768 |
| -1.727 |
kson | -1.724 |
Token | goals |
Token ID | 4661 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Roose | +3.130 |
Cumm | +3.018 |
STD | +2.898 |
| +2.828 |
Garrison | +2.802 |
Neg logit contributions | |
arre | -4.193 |
rule | -4.074 |
crab | -3.583 |
hig | -3.503 |
Kerr | -3.467 |
Token | - |
Token ID | 12 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
arre | +0.891 |
rule | +0.880 |
hig | +0.743 |
crab | +0.742 |
Kerr | +0.722 |
Neg logit contributions | |
Roose | -0.989 |
Cumm | -0.947 |
STD | -0.896 |
kson | -0.879 |
| -0.878 |
Token | against |
Token ID | 32826 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Roose | +2.770 |
Cumm | +2.683 |
| +2.579 |
STD | +2.578 |
onom | +2.522 |
Neg logit contributions | |
arre | -2.526 |
rule | -2.423 |
crab | -2.157 |
hig | -2.103 |
Kerr | -2.094 |
Token | average |
Token ID | 2811 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
arre | +1.758 |
rule | +1.740 |
hig | +1.524 |
crab | +1.522 |
Kerr | +1.491 |
Neg logit contributions | |
Roose | -1.269 |
Cumm | -1.206 |
STD | -1.116 |
kson | -1.096 |
| -1.092 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
Roose | +1.594 |
Cumm | +1.549 |
STD | +1.482 |
| +1.453 |
Garrison | +1.428 |
Neg logit contributions | |
arre | -1.718 |
rule | -1.697 |
crab | -1.450 |
hig | -1.422 |
Kerr | -1.420 |
Token | . |
Token ID | 764 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
Roose | +4.991 |
Cumm | +4.783 |
| +4.726 |
STD | +4.624 |
Garrison | +4.385 |
Neg logit contributions | |
arre | -9.932 |
rule | -9.733 |
crab | -8.542 |
モ | -8.532 |
ミ | -8.412 |
Token | 9 |
Token ID | 24 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Roose | +2.377 |
Cumm | +2.274 |
| +2.158 |
STD | +2.142 |
kson | +2.090 |
Neg logit contributions | |
arre | -2.828 |
rule | -2.799 |
hig | -2.448 |
crab | -2.445 |
Kerr | -2.378 |
Token | 37 |
Token ID | 2718 |
Feature activation | -9.05e+00 |
Pos logit contributions | |
arre | +0.172 |
rule | +0.169 |
crab | +0.144 |
hig | +0.143 |
Kerr | +0.140 |
Neg logit contributions | |
Roose | -0.176 |
Cumm | -0.170 |
STD | -0.161 |
| -0.158 |
Garrison | -0.156 |
Token | save |
Token ID | 3613 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Roose | +4.933 |
STD | +4.810 |
Cumm | +4.793 |
| +4.783 |
Garrison | +4.634 |
Neg logit contributions | |
arre | -7.550 |
rule | -7.403 |
crab | -6.439 |
モ | -6.395 |
Kerr | -6.333 |
Token | percentage |
Token ID | 5873 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
arre | +0.103 |
rule | +0.101 |
crab | +0.086 |
hig | +0.085 |
Kerr | +0.084 |
Neg logit contributions | |
Roose | -0.114 |
Cumm | -0.110 |
STD | -0.105 |
| -0.103 |
Garrison | -0.102 |
Token | monthly |
Token ID | 9651 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Roose | +1.086 |
Cumm | +1.047 |
STD | +0.990 |
| +0.972 |
Garrison | +0.965 |
Neg logit contributions | |
arre | -1.031 |
rule | -1.013 |
crab | -0.855 |
hig | -0.849 |
Kerr | -0.832 |
Token | increments |
Token ID | 41867 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Roose | +0.192 |
Cumm | +0.186 |
STD | +0.176 |
| +0.172 |
Garrison | +0.171 |
Neg logit contributions | |
arre | -0.185 |
rule | -0.182 |
crab | -0.154 |
hig | -0.153 |
Kerr | -0.150 |
Token | d |
Token ID | 288 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Roose | +1.023 |
Cumm | +0.986 |
STD | +0.934 |
| +0.916 |
Garrison | +0.904 |
Neg logit contributions | |
arre | -1.056 |
rule | -1.037 |
crab | -0.882 |
hig | -0.871 |
Kerr | -0.862 |
Token | [ |
Token ID | 58 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
arre | +1.898 |
rule | +1.871 |
hig | +1.582 |
crab | +1.569 |
Kerr | +1.543 |
Neg logit contributions | |
Roose | -2.120 |
Cumm | -2.030 |
STD | -1.916 |
| -1.884 |
Garrison | -1.883 |
Token | CO |
Token ID | 8220 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Roose | +1.523 |
Cumm | +1.486 |
STD | +1.424 |
| +1.406 |
kson | +1.388 |
Neg logit contributions | |
arre | -0.879 |
rule | -0.855 |
crab | -0.687 |
hig | -0.682 |
Kerr | -0.662 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
arre | +0.740 |
rule | +0.725 |
crab | +0.593 |
hig | +0.592 |
Kerr | +0.576 |
Neg logit contributions | |
Roose | -1.063 |
Cumm | -1.029 |
STD | -0.985 |
| -0.972 |
Garrison | -0.958 |
Token | ] |
Token ID | 2361 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Cumm | +5.651 |
Roose | +5.513 |
| +5.296 |
STD | +5.243 |
Garrison | +4.868 |
Neg logit contributions | |
arre | -9.843 |
rule | -9.736 |
crab | -8.554 |
モ | -8.467 |
hig | -8.462 |
Token | / |
Token ID | 14 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Roose | +1.754 |
Cumm | +1.700 |
STD | +1.611 |
| +1.592 |
kson | +1.550 |
Neg logit contributions | |
arre | -1.951 |
rule | -1.925 |
crab | -1.663 |
hig | -1.639 |
Kerr | -1.621 |
Token | dt |
Token ID | 28664 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
arre | +1.875 |
rule | +1.853 |
hig | +1.418 |
crab | +1.413 |
Kerr | +1.376 |
Neg logit contributions | |
Roose | -3.704 |
Cumm | -3.577 |
STD | -3.414 |
Garrison | -3.370 |
kson | -3.365 |
Token | computed |
Token ID | 29231 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Roose | +1.596 |
Cumm | +1.550 |
STD | +1.469 |
| +1.448 |
kson | +1.411 |
Neg logit contributions | |
arre | -1.651 |
rule | -1.631 |
crab | -1.400 |
hig | -1.376 |
Kerr | -1.360 |
Token | for |
Token ID | 329 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
arre | +1.145 |
rule | +1.127 |
hig | +0.961 |
crab | +0.958 |
Kerr | +0.938 |
Neg logit contributions | |
Roose | -1.220 |
Cumm | -1.171 |
STD | -1.107 |
| -1.087 |
kson | -1.081 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Roose | +1.544 |
Cumm | +1.496 |
STD | +1.416 |
| +1.398 |
onom | +1.381 |
Neg logit contributions | |
arre | -1.692 |
rule | -1.674 |
crab | -1.428 |
hig | -1.425 |
Kerr | -1.409 |
Token | health |
Token ID | 1535 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Roose | +0.939 |
Cumm | +0.901 |
STD | +0.864 |
| +0.832 |
Garrison | +0.829 |
Neg logit contributions | |
arre | -0.998 |
rule | -0.977 |
crab | -0.830 |
hig | -0.826 |
Kerr | -0.811 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Roose | +1.554 |
Cumm | +1.498 |
STD | +1.425 |
| +1.381 |
onom | +1.379 |
Neg logit contributions | |
arre | -1.754 |
rule | -1.720 |
hig | -1.480 |
crab | -1.476 |
Kerr | -1.448 |
Token | religion |
Token ID | 5737 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
Roose | +0.269 |
Cumm | +0.259 |
STD | +0.247 |
| +0.240 |
Garrison | +0.238 |
Neg logit contributions | |
arre | -0.272 |
rule | -0.267 |
crab | -0.227 |
hig | -0.226 |
Kerr | -0.222 |
Token | and |
Token ID | 290 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
arre | +3.622 |
rule | +3.581 |
crab | +3.009 |
hig | +2.989 |
Kerr | +2.912 |
Neg logit contributions | |
Roose | -4.354 |
Cumm | -4.154 |
STD | -3.907 |
Garrison | -3.848 |
kson | -3.833 |
Token | so |
Token ID | 523 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
arre | +0.129 |
rule | +0.127 |
crab | +0.108 |
hig | +0.108 |
Kerr | +0.106 |
Neg logit contributions | |
Roose | -0.130 |
Cumm | -0.125 |
STD | -0.119 |
| -0.116 |
Garrison | -0.115 |
Token | on |
Token ID | 319 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Roose | +5.553 |
Cumm | +5.208 |
onom | +5.179 |
| +5.153 |
Garrison | +4.902 |
Neg logit contributions | |
rule | -10.734 |
arre | -10.732 |
hig | -9.378 |
crab | -9.306 |
Kerr | -9.269 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
Roose | +1.901 |
Cumm | +1.833 |
STD | +1.747 |
| +1.723 |
Garrison | +1.694 |
Neg logit contributions | |
arre | -2.003 |
rule | -1.974 |
crab | -1.681 |
hig | -1.677 |
Kerr | -1.649 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Roose | +2.859 |
Cumm | +2.755 |
STD | +2.617 |
| +2.587 |
Garrison | +2.544 |
Neg logit contributions | |
arre | -3.026 |
rule | -2.936 |
hig | -2.530 |
crab | -2.522 |
モ | -2.405 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Roose | +1.016 |
Cumm | +0.986 |
STD | +0.938 |
| +0.938 |
Garrison | +0.912 |
Neg logit contributions | |
arre | -0.973 |
rule | -0.945 |
hig | -0.818 |
crab | -0.808 |
Kerr | -0.784 |
Token | Source |
Token ID | 7416 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
Roose | +0.939 |
Cumm | +0.903 |
STD | +0.855 |
| +0.853 |
onom | +0.831 |
Neg logit contributions | |
arre | -1.064 |
rule | -1.035 |
hig | -0.909 |
crab | -0.908 |
Kerr | -0.884 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
arre | +2.486 |
rule | +2.449 |
Kerr | +2.078 |
crab | +2.060 |
hig | +2.048 |
Neg logit contributions | |
Roose | -2.980 |
Cumm | -2.828 |
STD | -2.709 |
kson | -2.691 |
onom | -2.643 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
Roose | +1.274 |
Cumm | +1.236 |
| +1.178 |
STD | +1.176 |
Garrison | +1.142 |
Neg logit contributions | |
arre | -1.255 |
rule | -1.216 |
hig | -1.058 |
crab | -1.043 |
Kerr | -1.014 |
Token | 4 |
Token ID | 19 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
arre | +2.259 |
rule | +2.252 |
crab | +1.840 |
hig | +1.826 |
Kerr | +1.807 |
Neg logit contributions | |
Roose | -2.787 |
Cumm | -2.693 |
STD | -2.550 |
kson | -2.512 |
Garrison | -2.489 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
arre | +0.222 |
rule | +0.218 |
hig | +0.186 |
crab | +0.185 |
Kerr | +0.180 |
Neg logit contributions | |
Roose | -0.233 |
Cumm | -0.225 |
STD | -0.213 |
| -0.210 |
Garrison | -0.208 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Roose | +1.223 |
Cumm | +1.177 |
STD | +1.105 |
Garrison | +1.087 |
| +1.086 |
Neg logit contributions | |
arre | -1.331 |
rule | -1.302 |
hig | -1.122 |
crab | -1.119 |
Kerr | -1.074 |
Token | Sw |
Token ID | 2451 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
arre | +2.949 |
rule | +2.907 |
crab | +2.558 |
Kerr | +2.554 |
hig | +2.544 |
Neg logit contributions | |
Roose | -1.829 |
Cumm | -1.731 |
STD | -1.616 |
| -1.561 |
kson | -1.555 |
Token | inson |
Token ID | 7899 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
Roose | +6.656 |
Cumm | +6.651 |
kson | +6.494 |
| +6.285 |
STD | +6.232 |
Neg logit contributions | |
arre | -9.289 |
rule | -8.735 |
��� | -8.724 |
hig | -8.533 |
ドラゴン | -8.521 |
Token | ( |
Token ID | 357 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
arre | +0.057 |
rule | +0.056 |
hig | +0.047 |
crab | +0.046 |
Kerr | +0.045 |
Neg logit contributions | |
Roose | -0.071 |
Cumm | -0.069 |
STD | -0.065 |
| -0.064 |
Garrison | -0.064 |
Token | 91 |
Token ID | 6420 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Roose | +1.962 |
Cumm | +1.893 |
STD | +1.790 |
| +1.783 |
kson | +1.754 |
Neg logit contributions | |
arre | -1.954 |
rule | -1.888 |
hig | -1.671 |
crab | -1.659 |
Kerr | -1.599 |
Token | ) |
Token ID | 8 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
arre | +1.258 |
rule | +1.238 |
crab | +1.026 |
hig | +1.018 |
Kerr | +1.000 |
Neg logit contributions | |
Roose | -1.658 |
Cumm | -1.599 |
STD | -1.523 |
| -1.494 |
kson | -1.487 |
Token | ( |
Token ID | 357 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
arre | +0.754 |
rule | +0.740 |
crab | +0.616 |
hig | +0.614 |
Kerr | +0.598 |
Neg logit contributions | |
Roose | -0.972 |
Cumm | -0.940 |
STD | -0.895 |
| -0.881 |
kson | -0.873 |