Token | the |
Token ID | 262 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
profit | +0.290 |
ailability | +0.287 |
arcity | +0.284 |
secure | +0.267 |
peril | +0.266 |
Neg logit contributions | |
Ba | -0.377 |
Probe | -0.377 |
Instrument | -0.374 |
Asuka | -0.372 |
coord | -0.372 |
Token | world |
Token ID | 995 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Probe | +0.308 |
Ba | +0.308 |
Instrument | +0.308 |
coord | +0.305 |
Asuka | +0.304 |
Neg logit contributions | |
ailability | -0.266 |
profit | -0.265 |
arcity | -0.261 |
paren | -0.244 |
secure | -0.244 |
Token | is |
Token ID | 318 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Ba | +0.286 |
Probe | +0.286 |
Instrument | +0.285 |
coord | +0.283 |
Asuka | +0.282 |
Neg logit contributions | |
ailability | -0.303 |
profit | -0.303 |
arcity | -0.298 |
secure | -0.281 |
paren | -0.281 |
Token | being |
Token ID | 852 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
profit | +0.033 |
ailability | +0.033 |
arcity | +0.033 |
secure | +0.031 |
paren | +0.031 |
Neg logit contributions | |
Probe | -0.036 |
Ba | -0.036 |
Instrument | -0.036 |
coord | -0.035 |
Asuka | -0.035 |
Token | held |
Token ID | 2714 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
profit | +0.603 |
ailability | +0.593 |
arcity | +0.593 |
secure | +0.567 |
peril | +0.566 |
Neg logit contributions | |
Ba | -0.733 |
Probe | -0.729 |
Instrument | -0.727 |
Asuka | -0.720 |
coord | -0.716 |
Token | hostage |
Token ID | 23229 |
Feature activation | +7.67e+00 |
Pos logit contributions | |
profit | +1.511 |
ailability | +1.500 |
arcity | +1.494 |
peril | +1.442 |
secure | +1.430 |
Neg logit contributions | |
Probe | -1.756 |
Ba | -1.754 |
Instrument | -1.733 |
coord | -1.723 |
Asuka | -1.706 |
Token | by |
Token ID | 416 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
profit | +4.270 |
arcity | +4.138 |
ides | +4.126 |
peril | +4.094 |
secure | +4.062 |
Neg logit contributions | |
Probe | -5.804 |
Ba | -5.714 |
coord | -5.683 |
Instrument | -5.668 |
Asuka | -5.619 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
profit | +0.391 |
ailability | +0.388 |
arcity | +0.384 |
secure | +0.363 |
peril | +0.362 |
Neg logit contributions | |
Probe | -0.424 |
Ba | -0.424 |
Instrument | -0.422 |
Asuka | -0.418 |
coord | -0.417 |
Token | DES |
Token ID | 30910 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
profit | +0.959 |
ailability | +0.951 |
arcity | +0.942 |
secure | +0.896 |
ides | +0.891 |
Neg logit contributions | |
Probe | -0.925 |
Ba | -0.918 |
Instrument | -0.917 |
Asuka | -0.914 |
coord | -0.906 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Probe | +0.320 |
Ba | +0.320 |
Instrument | +0.318 |
coord | +0.316 |
Asuka | +0.315 |
Neg logit contributions | |
profit | -0.268 |
ailability | -0.268 |
arcity | -0.264 |
secure | -0.247 |
paren | -0.247 |
Token |
|
Token ID | 198 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
profit | +0.120 |
arcity | +0.117 |
ailability | +0.117 |
secure | +0.112 |
ides | +0.111 |
Neg logit contributions | |
Probe | -0.109 |
coord | -0.109 |
Ba | -0.108 |
Instrument | -0.108 |
Asuka | -0.108 |
Token | I |
Token ID | 314 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
Probe | +1.189 |
Ba | +1.187 |
Instrument | +1.182 |
Asuka | +1.173 |
coord | +1.172 |
Neg logit contributions | |
ailability | -1.087 |
profit | -1.084 |
arcity | -1.068 |
secure | -1.005 |
paren | -1.001 |
Token | 've |
Token ID | 1053 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
profit | +0.417 |
ailability | +0.409 |
arcity | +0.406 |
secure | +0.380 |
ides | +0.379 |
Neg logit contributions | |
Ba | -0.600 |
Probe | -0.600 |
Instrument | -0.598 |
Asuka | -0.595 |
coord | -0.593 |
Token | been |
Token ID | 587 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
profit | +0.488 |
arcity | +0.475 |
ailability | +0.474 |
ides | +0.449 |
secure | +0.448 |
Neg logit contributions | |
Ba | -0.594 |
Probe | -0.591 |
Instrument | -0.588 |
Asuka | -0.581 |
coord | -0.581 |
Token | heavily |
Token ID | 7272 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
profit | +0.877 |
arcity | +0.856 |
ailability | +0.854 |
peril | +0.829 |
ides | +0.818 |
Neg logit contributions | |
Ba | -0.921 |
Probe | -0.909 |
Instrument | -0.904 |
coord | -0.893 |
Asuka | -0.890 |
Token | using |
Token ID | 1262 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
profit | +0.434 |
ailability | +0.427 |
arcity | +0.420 |
peril | +0.404 |
secure | +0.404 |
Neg logit contributions | |
Ba | -0.430 |
Probe | -0.426 |
Instrument | -0.424 |
Asuka | -0.421 |
coord | -0.420 |
Token | Angular |
Token ID | 28147 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
profit | +0.833 |
ailability | +0.815 |
arcity | +0.813 |
ides | +0.773 |
secure | +0.772 |
Neg logit contributions | |
Ba | -0.878 |
Probe | -0.866 |
coord | -0.858 |
Instrument | -0.858 |
Asuka | -0.856 |
Token | JS |
Token ID | 20120 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
profit | +3.735 |
ailability | +3.525 |
arcity | +3.503 |
secure | +3.472 |
paren | +3.384 |
Neg logit contributions | |
Asuka | -5.624 |
Ba | -5.557 |
coord | -5.508 |
bats | -5.484 |
Probe | -5.455 |
Token | . |
Token ID | 13 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
profit | +1.653 |
ailability | +1.609 |
arcity | +1.603 |
ides | +1.541 |
secure | +1.534 |
Neg logit contributions | |
Ba | -1.922 |
Asuka | -1.907 |
Probe | -1.895 |
coord | -1.886 |
Instrument | -1.877 |
Token | It |
Token ID | 632 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Ba | +0.228 |
Probe | +0.228 |
coord | +0.227 |
Instrument | +0.225 |
Asuka | +0.224 |
Neg logit contributions | |
profit | -0.234 |
ailability | -0.229 |
arcity | -0.227 |
secure | -0.216 |
ides | -0.216 |
Token | 's |
Token ID | 338 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
profit | +0.183 |
arcity | +0.180 |
ailability | +0.179 |
ides | +0.170 |
secure | +0.170 |
Neg logit contributions | |
Probe | -0.185 |
Ba | -0.185 |
Instrument | -0.184 |
coord | -0.183 |
Asuka | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Probe | +0.634 |
Ba | +0.634 |
Instrument | +0.631 |
coord | +0.626 |
Asuka | +0.626 |
Neg logit contributions | |
profit | -0.551 |
ailability | -0.550 |
arcity | -0.542 |
secure | -0.508 |
paren | -0.507 |
Token | let |
Token ID | 1309 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Probe | +0.083 |
Ba | +0.083 |
Instrument | +0.082 |
coord | +0.081 |
Asuka | +0.081 |
Neg logit contributions | |
profit | -0.069 |
ailability | -0.068 |
arcity | -0.068 |
secure | -0.064 |
peril | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
profit | +0.337 |
ailability | +0.331 |
arcity | +0.331 |
peril | +0.314 |
ides | +0.312 |
Neg logit contributions | |
Probe | -0.360 |
Ba | -0.360 |
Instrument | -0.356 |
coord | -0.354 |
Asuka | -0.352 |
Token | future |
Token ID | 2003 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Probe | +0.002 |
Ba | +0.002 |
Instrument | +0.002 |
coord | +0.002 |
Asuka | +0.002 |
Neg logit contributions | |
profit | -0.002 |
ailability | -0.002 |
arcity | -0.002 |
peril | -0.002 |
ides | -0.002 |
Token | be |
Token ID | 307 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Ba | +0.974 |
Probe | +0.974 |
Instrument | +0.969 |
coord | +0.963 |
Asuka | +0.962 |
Neg logit contributions | |
profit | -0.797 |
ailability | -0.796 |
arcity | -0.783 |
secure | -0.733 |
paren | -0.731 |
Token | held |
Token ID | 2714 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
profit | +1.217 |
arcity | +1.186 |
ailability | +1.184 |
peril | +1.137 |
ides | +1.134 |
Neg logit contributions | |
Ba | -1.354 |
Probe | -1.351 |
Instrument | -1.336 |
coord | -1.326 |
Asuka | -1.310 |
Token | hostage |
Token ID | 23229 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
profit | +1.465 |
arcity | +1.445 |
ailability | +1.445 |
peril | +1.400 |
secure | +1.374 |
Neg logit contributions | |
Probe | -1.707 |
Ba | -1.701 |
Instrument | -1.678 |
coord | -1.669 |
bats | -1.651 |
Token | by |
Token ID | 416 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
profit | +3.912 |
arcity | +3.808 |
ides | +3.730 |
peril | +3.704 |
ailability | +3.687 |
Neg logit contributions | |
Probe | -5.294 |
Ba | -5.198 |
coord | -5.168 |
Instrument | -5.116 |
Amp | -5.115 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
profit | +0.239 |
ailability | +0.235 |
arcity | +0.234 |
peril | +0.223 |
ides | +0.223 |
Neg logit contributions | |
Probe | -0.241 |
Ba | -0.239 |
Instrument | -0.237 |
coord | -0.235 |
Asuka | -0.235 |
Token | failures |
Token ID | 15536 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Probe | +0.242 |
Ba | +0.241 |
Instrument | +0.238 |
coord | +0.237 |
Asuka | +0.236 |
Neg logit contributions | |
profit | -0.245 |
ailability | -0.242 |
arcity | -0.241 |
peril | -0.229 |
ides | -0.228 |
Token | of |
Token ID | 286 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
profit | +0.314 |
ailability | +0.313 |
arcity | +0.307 |
secure | +0.283 |
ides | +0.283 |
Neg logit contributions | |
Probe | -0.526 |
Ba | -0.525 |
Instrument | -0.523 |
coord | -0.519 |
Asuka | -0.519 |
Token | the |
Token ID | 262 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
profit | +0.376 |
arcity | +0.372 |
ailability | +0.371 |
ides | +0.353 |
peril | +0.351 |
Neg logit contributions | |
Probe | -0.380 |
Ba | -0.378 |
Instrument | -0.373 |
coord | -0.370 |
Asuka | -0.369 |
Token | turn |
Token ID | 1210 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
profit | +0.731 |
ailability | +0.715 |
arcity | +0.709 |
paren | +0.680 |
peril | +0.678 |
Neg logit contributions | |
Ba | -0.780 |
Instrument | -0.774 |
Asuka | -0.774 |
Probe | -0.773 |
coord | -0.765 |
Token | : |
Token ID | 1058 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
profit | +2.155 |
arcity | +2.084 |
ailability | +2.083 |
paren | +2.000 |
secure | +1.994 |
Neg logit contributions | |
Instrument | -2.637 |
Probe | -2.636 |
Asuka | -2.616 |
Ba | -2.613 |
coord | -2.595 |
Token | self |
Token ID | 2116 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
profit | +1.532 |
arcity | +1.496 |
ailability | +1.495 |
peril | +1.437 |
secure | +1.431 |
Neg logit contributions | |
Ba | -1.470 |
Instrument | -1.442 |
Probe | -1.436 |
bats | -1.432 |
Asuka | -1.431 |
Token | . |
Token ID | 764 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
profit | +0.828 |
ailability | +0.811 |
arcity | +0.800 |
paren | +0.742 |
secure | +0.741 |
Neg logit contributions | |
Probe | -1.669 |
Ba | -1.666 |
Instrument | -1.661 |
Asuka | -1.654 |
coord | -1.647 |
Token | clone |
Token ID | 21018 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
profit | +1.807 |
arcity | +1.739 |
ailability | +1.734 |
secure | +1.663 |
paren | +1.655 |
Neg logit contributions | |
Instrument | -2.308 |
Ba | -2.294 |
Probe | -2.291 |
Asuka | -2.281 |
coord | -2.260 |
Token | (), |
Token ID | 29994 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
profit | +0.625 |
ailability | +0.617 |
arcity | +0.610 |
secure | +0.578 |
paren | +0.578 |
Neg logit contributions | |
Probe | -0.686 |
Instrument | -0.685 |
Ba | -0.683 |
Asuka | -0.678 |
coord | -0.677 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
profit | +3.839 |
peril | +3.672 |
ailability | +3.624 |
paren | +3.601 |
arcity | +3.595 |
Neg logit contributions | |
Ba | -4.708 |
Asuka | -4.602 |
Instrument | -4.562 |
bats | -4.553 |
Probe | -4.516 |
Token | : |
Token ID | 1058 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
profit | +0.892 |
ailability | +0.890 |
arcity | +0.876 |
secure | +0.820 |
paren | +0.817 |
Neg logit contributions | |
Ba | -1.115 |
Probe | -1.115 |
Instrument | -1.110 |
Asuka | -1.101 |
coord | -1.101 |
Token | self |
Token ID | 2116 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
profit | +1.265 |
arcity | +1.237 |
ailability | +1.234 |
peril | +1.191 |
ides | +1.181 |
Neg logit contributions | |
Ba | -1.219 |
Probe | -1.198 |
Asuka | -1.192 |
Instrument | -1.191 |
coord | -1.183 |
Token | . |
Token ID | 764 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
profit | +0.538 |
ailability | +0.535 |
arcity | +0.525 |
secure | +0.481 |
paren | +0.479 |
Neg logit contributions | |
Probe | -1.044 |
Ba | -1.043 |
Instrument | -1.038 |
coord | -1.032 |
Asuka | -1.032 |
Token | pieces |
Token ID | 34154 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
profit | +1.623 |
arcity | +1.551 |
ailability | +1.534 |
paren | +1.491 |
secure | +1.487 |
Neg logit contributions | |
Instrument | -1.924 |
Probe | -1.921 |
Ba | -1.915 |
Asuka | -1.909 |
coord | -1.896 |
Token |
|
Token ID | 198 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
profit | +0.112 |
ailability | +0.111 |
arcity | +0.110 |
secure | +0.104 |
peril | +0.103 |
Neg logit contributions | |
Ba | -0.123 |
Probe | -0.122 |
coord | -0.121 |
Instrument | -0.121 |
Asuka | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
profit | +0.500 |
arcity | +0.481 |
secure | +0.463 |
ides | +0.463 |
ailability | +0.463 |
Neg logit contributions | |
coord | -0.479 |
Probe | -0.477 |
Instrument | -0.472 |
Ba | -0.471 |
Asuka | -0.470 |
Token | Like |
Token ID | 7594 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
profit | +0.542 |
arcity | +0.520 |
ailability | +0.517 |
secure | +0.497 |
paren | +0.493 |
Neg logit contributions | |
Probe | -0.640 |
coord | -0.634 |
Instrument | -0.634 |
Asuka | -0.633 |
Ba | -0.624 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Ba | +0.245 |
Probe | +0.244 |
Instrument | +0.243 |
coord | +0.242 |
Asuka | +0.241 |
Neg logit contributions | |
profit | -0.229 |
ailability | -0.226 |
arcity | -0.224 |
secure | -0.212 |
peril | -0.211 |
Token | great |
Token ID | 1049 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
profit | +0.964 |
ailability | +0.947 |
arcity | +0.939 |
peril | +0.900 |
ides | +0.895 |
Neg logit contributions | |
Ba | -0.970 |
Instrument | -0.965 |
Probe | -0.965 |
Asuka | -0.954 |
coord | -0.952 |
Token | editorial |
Token ID | 13684 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
profit | +0.826 |
ailability | +0.812 |
arcity | +0.808 |
peril | +0.772 |
ides | +0.768 |
Neg logit contributions | |
Probe | -0.838 |
Ba | -0.832 |
Instrument | -0.828 |
coord | -0.824 |
Asuka | -0.821 |
Token | cartoon |
Token ID | 16251 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
profit | +3.951 |
peril | +3.848 |
ailability | +3.818 |
arcity | +3.799 |
ides | +3.793 |
Neg logit contributions | |
Ba | -4.435 |
bats | -4.389 |
Probe | -4.350 |
Asuka | -4.327 |
Instrument | -4.311 |
Token | , |
Token ID | 11 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
profit | +0.470 |
ailability | +0.465 |
arcity | +0.460 |
peril | +0.437 |
ides | +0.435 |
Neg logit contributions | |
Probe | -0.512 |
Ba | -0.511 |
Instrument | -0.509 |
coord | -0.504 |
Asuka | -0.503 |
Token | this |
Token ID | 428 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
profit | +0.633 |
ailability | +0.622 |
arcity | +0.619 |
peril | +0.586 |
secure | +0.584 |
Neg logit contributions | |
Ba | -0.691 |
Probe | -0.688 |
Instrument | -0.685 |
coord | -0.684 |
Asuka | -0.681 |
Token | public |
Token ID | 1171 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
profit | +0.353 |
ailability | +0.347 |
arcity | +0.346 |
peril | +0.328 |
ides | +0.326 |
Neg logit contributions | |
Ba | -0.395 |
Probe | -0.394 |
Instrument | -0.392 |
coord | -0.390 |
Asuka | -0.389 |
Token | sculpture |
Token ID | 26924 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Probe | +0.919 |
Ba | +0.919 |
Instrument | +0.913 |
coord | +0.907 |
Asuka | +0.907 |
Neg logit contributions | |
profit | -0.901 |
ailability | -0.896 |
arcity | -0.885 |
secure | -0.834 |
peril | -0.833 |
Token | and |
Token ID | 290 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Probe | +0.957 |
Ba | +0.956 |
Instrument | +0.951 |
coord | +0.945 |
Asuka | +0.944 |
Neg logit contributions | |
ailability | -0.812 |
profit | -0.811 |
arcity | -0.798 |
secure | -0.747 |
paren | -0.746 |
Token | the |
Token ID | 262 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
profit | +0.282 |
ailability | +0.279 |
arcity | +0.277 |
ides | +0.263 |
peril | +0.262 |
Neg logit contributions | |
Ba | -0.301 |
Probe | -0.300 |
Instrument | -0.298 |
coord | -0.296 |
Asuka | -0.295 |
Token | 260 |
Token ID | 21148 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Ba | +0.067 |
Probe | +0.067 |
Instrument | +0.066 |
Asuka | +0.066 |
coord | +0.066 |
Neg logit contributions | |
profit | -0.065 |
ailability | -0.065 |
arcity | -0.064 |
secure | -0.061 |
peril | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
Ba | +0.611 |
Probe | +0.611 |
Instrument | +0.607 |
coord | +0.602 |
Asuka | +0.601 |
Neg logit contributions | |
profit | -0.786 |
ailability | -0.785 |
arcity | -0.775 |
secure | -0.735 |
paren | -0.734 |
Token | pound |
Token ID | 19568 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
profit | +0.361 |
ailability | +0.357 |
arcity | +0.351 |
secure | +0.333 |
paren | +0.330 |
Neg logit contributions | |
Probe | -0.450 |
Instrument | -0.448 |
Ba | -0.446 |
Asuka | -0.445 |
coord | -0.444 |
Token | Rip |
Token ID | 29496 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
Probe | +1.895 |
Ba | +1.893 |
Instrument | +1.887 |
Asuka | +1.875 |
coord | +1.873 |
Neg logit contributions | |
ailability | -1.701 |
profit | -1.693 |
arcity | -1.669 |
paren | -1.567 |
secure | -1.560 |
Token | kowski |
Token ID | 26216 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
profit | +2.918 |
arcity | +2.710 |
ides | +2.639 |
ð | +2.613 |
secure | +2.579 |
Neg logit contributions | |
coord | -5.671 |
Probe | -5.653 |
Instrument | -5.636 |
Asuka | -5.598 |
Ba | -5.525 |
Token | and |
Token ID | 290 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
profit | +1.293 |
arcity | +1.267 |
ailability | +1.263 |
ides | +1.230 |
peril | +1.205 |
Neg logit contributions | |
Ba | -1.795 |
Probe | -1.795 |
Instrument | -1.791 |
Asuka | -1.771 |
coord | -1.768 |
Token | Bell |
Token ID | 7459 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
profit | +0.362 |
ailability | +0.358 |
arcity | +0.357 |
ides | +0.338 |
peril | +0.338 |
Neg logit contributions | |
Ba | -0.389 |
Probe | -0.389 |
Instrument | -0.385 |
coord | -0.381 |
Asuka | -0.381 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
profit | +0.693 |
ailability | +0.686 |
arcity | +0.684 |
ides | +0.645 |
peril | +0.640 |
Neg logit contributions | |
Probe | -0.901 |
Instrument | -0.899 |
Ba | -0.897 |
Asuka | -0.891 |
coord | -0.887 |
Token |
|
Token ID | 198 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
coord | +0.070 |
Ba | +0.070 |
Probe | +0.070 |
Instrument | +0.069 |
Asuka | +0.069 |
Neg logit contributions | |
profit | -0.073 |
arcity | -0.071 |
ailability | -0.071 |
secure | -0.068 |
ides | -0.068 |
Token | insurers |
Token ID | 24668 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
profit | +1.723 |
ailability | +1.633 |
arcity | +1.592 |
peril | +1.552 |
ides | +1.548 |
Neg logit contributions | |
Probe | -2.173 |
Ba | -2.163 |
Asuka | -2.139 |
coord | -2.132 |
Instrument | -2.130 |
Token | United |
Token ID | 1578 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
profit | +1.295 |
ailability | +1.274 |
arcity | +1.240 |
ides | +1.195 |
peril | +1.172 |
Neg logit contributions | |
Ba | -1.636 |
Probe | -1.631 |
coord | -1.627 |
Instrument | -1.618 |
Asuka | -1.613 |
Token | Health |
Token ID | 18081 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Probe | +0.269 |
Ba | +0.269 |
Instrument | +0.267 |
coord | +0.266 |
Asuka | +0.266 |
Neg logit contributions | |
profit | -0.182 |
ailability | -0.181 |
arcity | -0.177 |
secure | -0.165 |
paren | -0.165 |
Token | Group |
Token ID | 4912 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
profit | +0.981 |
ailability | +0.950 |
arcity | +0.920 |
ides | +0.900 |
paren | +0.890 |
Neg logit contributions | |
Ba | -1.462 |
Asuka | -1.455 |
Probe | -1.452 |
coord | -1.445 |
Instrument | -1.443 |
Token | , |
Token ID | 11 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
profit | +0.373 |
ailability | +0.371 |
arcity | +0.365 |
secure | +0.343 |
paren | +0.342 |
Neg logit contributions | |
Ba | -0.440 |
Probe | -0.440 |
Instrument | -0.437 |
Asuka | -0.435 |
coord | -0.434 |
Token | Hum |
Token ID | 11054 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
Probe | +0.335 |
Ba | +0.334 |
Instrument | +0.333 |
coord | +0.330 |
Asuka | +0.330 |
Neg logit contributions | |
profit | -0.301 |
ailability | -0.301 |
arcity | -0.296 |
secure | -0.278 |
paren | -0.277 |
Token | ana |
Token ID | 2271 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
profit | +3.436 |
arcity | +3.128 |
ides | +3.095 |
ailability | +3.023 |
orem | +2.972 |
Neg logit contributions | |
bats | -5.168 |
coord | -5.138 |
Asuka | -5.129 |
Probe | -5.124 |
Instrument | -5.077 |
Token | and |
Token ID | 290 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
profit | +1.682 |
ailability | +1.650 |
arcity | +1.623 |
ides | +1.558 |
secure | +1.540 |
Neg logit contributions | |
Ba | -2.088 |
coord | -2.070 |
Probe | -2.065 |
Instrument | -2.062 |
Asuka | -2.060 |
Token | A |
Token ID | 317 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
profit | +0.383 |
ailability | +0.378 |
arcity | +0.374 |
ides | +0.353 |
secure | +0.353 |
Neg logit contributions | |
Ba | -0.401 |
Probe | -0.400 |
Instrument | -0.398 |
coord | -0.397 |
Asuka | -0.395 |
Token | et |
Token ID | 316 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
profit | +1.068 |
ailability | +1.045 |
arcity | +1.039 |
ides | +0.978 |
secure | +0.969 |
Neg logit contributions | |
Probe | -1.489 |
Instrument | -1.483 |
Ba | -1.483 |
coord | -1.477 |
Asuka | -1.475 |
Token | na |
Token ID | 2616 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
profit | +1.044 |
ailability | +1.031 |
arcity | +1.031 |
secure | +0.986 |
ides | +0.983 |
Neg logit contributions | |
Probe | -0.525 |
Ba | -0.522 |
Instrument | -0.519 |
coord | -0.517 |
Asuka | -0.514 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Ba | +0.698 |
Probe | +0.698 |
Instrument | +0.695 |
coord | +0.687 |
Asuka | +0.687 |
Neg logit contributions | |
profit | -0.645 |
ailability | -0.640 |
arcity | -0.632 |
ides | -0.603 |
peril | -0.602 |
Token | edge |
Token ID | 5743 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
profit | +0.195 |
ailability | +0.192 |
arcity | +0.190 |
peril | +0.183 |
ides | +0.182 |
Neg logit contributions | |
Ba | -0.195 |
Instrument | -0.194 |
Probe | -0.193 |
Asuka | -0.191 |
coord | -0.191 |
Token | while |
Token ID | 981 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Ba | +0.453 |
Probe | +0.452 |
Instrument | +0.450 |
coord | +0.446 |
Asuka | +0.446 |
Neg logit contributions | |
profit | -0.417 |
ailability | -0.414 |
arcity | -0.409 |
ides | -0.388 |
peril | -0.387 |
Token | fullback |
Token ID | 49570 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
profit | +1.891 |
ailability | +1.868 |
arcity | +1.843 |
peril | +1.812 |
ides | +1.798 |
Neg logit contributions | |
Probe | -2.002 |
Ba | -1.996 |
Instrument | -1.983 |
bats | -1.950 |
coord | -1.947 |
Token | Aaron |
Token ID | 12139 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
Probe | +0.669 |
Ba | +0.668 |
Instrument | +0.664 |
coord | +0.660 |
Asuka | +0.659 |
Neg logit contributions | |
profit | -0.637 |
ailability | -0.634 |
arcity | -0.626 |
secure | -0.591 |
ides | -0.588 |
Token | Rip |
Token ID | 29496 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
Ba | +0.488 |
Probe | +0.485 |
coord | +0.484 |
Instrument | +0.483 |
Asuka | +0.478 |
Neg logit contributions | |
profit | -0.457 |
ailability | -0.451 |
arcity | -0.449 |
ides | -0.426 |
secure | -0.425 |
Token | kowski |
Token ID | 26216 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
profit | +3.376 |
arcity | +3.308 |
ides | +3.215 |
ailability | +3.200 |
paren | +3.120 |
Neg logit contributions | |
Probe | -4.908 |
Asuka | -4.897 |
Instrument | -4.869 |
Ba | -4.835 |
Amp | -4.823 |
Token | and |
Token ID | 290 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
profit | +0.582 |
ailability | +0.573 |
arcity | +0.572 |
ides | +0.550 |
peril | +0.548 |
Neg logit contributions | |
Probe | -0.543 |
Ba | -0.543 |
Instrument | -0.540 |
Asuka | -0.534 |
coord | -0.532 |
Token | running |
Token ID | 2491 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
Probe | +0.278 |
Ba | +0.277 |
Instrument | +0.275 |
coord | +0.272 |
Asuka | +0.272 |
Neg logit contributions | |
profit | -0.255 |
ailability | -0.252 |
arcity | -0.249 |
peril | -0.237 |
ides | -0.237 |
Token | back |
Token ID | 736 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Probe | +1.353 |
Ba | +1.350 |
Instrument | +1.342 |
coord | +1.328 |
Asuka | +1.327 |
Neg logit contributions | |
profit | -1.904 |
ailability | -1.899 |
arcity | -1.877 |
secure | -1.788 |
paren | -1.783 |
Token | Sam |
Token ID | 3409 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
Probe | +1.078 |
Ba | +1.077 |
Instrument | +1.072 |
coord | +1.064 |
Asuka | +1.063 |
Neg logit contributions | |
profit | -1.033 |
ailability | -1.032 |
arcity | -1.017 |
secure | -0.957 |
paren | -0.954 |
Token | ( |
Token ID | 357 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
profit | +1.117 |
ailability | +1.100 |
arcity | +1.093 |
secure | +1.046 |
ides | +1.042 |
Neg logit contributions | |
Ba | -0.878 |
Probe | -0.874 |
Asuka | -0.871 |
coord | -0.869 |
Instrument | -0.862 |
Token | June |
Token ID | 15749 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
Probe | +0.118 |
Instrument | +0.117 |
Ba | +0.117 |
coord | +0.117 |
Asuka | +0.116 |
Neg logit contributions | |
profit | -0.075 |
ailability | -0.074 |
arcity | -0.073 |
secure | -0.069 |
paren | -0.068 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
profit | +0.525 |
ailability | +0.522 |
arcity | +0.516 |
secure | +0.486 |
ides | +0.484 |
Neg logit contributions | |
Ba | -0.526 |
Probe | -0.526 |
Instrument | -0.522 |
Asuka | -0.519 |
coord | -0.518 |
Token | ), |
Token ID | 828 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
Ba | +1.259 |
Probe | +1.253 |
Instrument | +1.252 |
Asuka | +1.239 |
coord | +1.237 |
Neg logit contributions | |
ailability | -1.026 |
profit | -1.025 |
arcity | -1.005 |
secure | -0.944 |
peril | -0.940 |
Token | Innov |
Token ID | 43405 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
profit | +0.021 |
ailability | +0.020 |
arcity | +0.020 |
secure | +0.019 |
paren | +0.019 |
Neg logit contributions | |
Ba | -0.019 |
Probe | -0.019 |
Instrument | -0.019 |
coord | -0.019 |
Asuka | -0.019 |
Token | ative |
Token ID | 876 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
profit | +1.528 |
ailability | +1.495 |
arcity | +1.493 |
secure | +1.401 |
ides | +1.398 |
Neg logit contributions | |
Probe | -2.195 |
Asuka | -2.190 |
coord | -2.185 |
Ba | -2.185 |
Instrument | -2.161 |
Token | ( |
Token ID | 357 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
profit | +4.676 |
arcity | +4.540 |
ailability | +4.475 |
secure | +4.363 |
ides | +4.356 |
Neg logit contributions | |
Asuka | -3.509 |
Ba | -3.489 |
coord | -3.470 |
bats | -3.413 |
Probe | -3.384 |
Token | June |
Token ID | 15749 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Probe | +0.314 |
Instrument | +0.312 |
Ba | +0.312 |
coord | +0.311 |
Asuka | +0.310 |
Neg logit contributions | |
profit | -0.222 |
ailability | -0.218 |
arcity | -0.215 |
secure | -0.202 |
paren | -0.201 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
profit | +0.373 |
ailability | +0.370 |
arcity | +0.366 |
secure | +0.345 |
ides | +0.344 |
Neg logit contributions | |
Ba | -0.404 |
Probe | -0.403 |
Instrument | -0.399 |
coord | -0.399 |
Asuka | -0.399 |
Token | ), |
Token ID | 828 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Ba | +1.487 |
Probe | +1.479 |
Instrument | +1.479 |
Asuka | +1.462 |
coord | +1.461 |
Neg logit contributions | |
profit | -1.233 |
ailability | -1.231 |
arcity | -1.208 |
secure | -1.135 |
peril | -1.131 |
Token | and |
Token ID | 290 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
profit | +0.076 |
ailability | +0.076 |
arcity | +0.075 |
secure | +0.071 |
paren | +0.071 |
Neg logit contributions | |
Ba | -0.071 |
Probe | -0.071 |
Instrument | -0.071 |
coord | -0.071 |
Asuka | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
profit | +0.049 |
arcity | +0.048 |
ailability | +0.046 |
secure | +0.046 |
ides | +0.046 |
Neg logit contributions | |
Probe | -0.046 |
coord | -0.046 |
Instrument | -0.045 |
Ba | -0.045 |
Asuka | -0.045 |
Token | In |
Token ID | 818 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
profit | +0.241 |
ailability | +0.238 |
arcity | +0.236 |
secure | +0.223 |
paren | +0.222 |
Neg logit contributions | |
Probe | -0.259 |
Instrument | -0.257 |
Ba | -0.257 |
coord | -0.256 |
Asuka | -0.255 |
Token | early |
Token ID | 1903 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
profit | +0.454 |
ailability | +0.448 |
arcity | +0.445 |
secure | +0.423 |
paren | +0.418 |
Neg logit contributions | |
Ba | -0.479 |
Probe | -0.476 |
Asuka | -0.473 |
coord | -0.473 |
Instrument | -0.473 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
profit | +1.060 |
arcity | +1.016 |
ailability | +1.004 |
peril | +0.990 |
ides | +0.981 |
Neg logit contributions | |
Ba | -1.275 |
Probe | -1.267 |
Instrument | -1.251 |
coord | -1.250 |
Asuka | -1.243 |
Token | Innov |
Token ID | 43405 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
profit | +0.366 |
ailability | +0.363 |
arcity | +0.358 |
paren | +0.338 |
secure | +0.337 |
Neg logit contributions | |
Ba | -0.389 |
Probe | -0.388 |
Instrument | -0.385 |
coord | -0.385 |
Asuka | -0.384 |
Token | ative |
Token ID | 876 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
profit | +1.313 |
ailability | +1.283 |
arcity | +1.274 |
secure | +1.139 |
ides | +1.134 |
Neg logit contributions | |
Probe | -3.608 |
Ba | -3.598 |
Asuka | -3.592 |
coord | -3.585 |
Instrument | -3.561 |
Token | announced |
Token ID | 3414 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
profit | +3.863 |
ailability | +3.594 |
arcity | +3.594 |
secure | +3.584 |
ides | +3.580 |
Neg logit contributions | |
Asuka | -4.218 |
Ba | -4.207 |
bats | -4.179 |
Probe | -4.122 |
coord | -4.085 |
Token | an |
Token ID | 281 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
profit | +0.795 |
ailability | +0.786 |
arcity | +0.774 |
paren | +0.731 |
secure | +0.730 |
Neg logit contributions | |
Ba | -0.947 |
Probe | -0.943 |
Asuka | -0.937 |
Instrument | -0.935 |
coord | -0.932 |
Token | alliance |
Token ID | 12801 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
profit | +0.064 |
ailability | +0.063 |
arcity | +0.062 |
secure | +0.059 |
ides | +0.059 |
Neg logit contributions | |
Ba | -0.072 |
Probe | -0.072 |
Asuka | -0.071 |
coord | -0.071 |
Instrument | -0.071 |
Token | with |
Token ID | 351 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Probe | +0.127 |
Ba | +0.127 |
Instrument | +0.126 |
coord | +0.125 |
Asuka | +0.125 |
Neg logit contributions | |
profit | -0.122 |
ailability | -0.122 |
arcity | -0.120 |
secure | -0.113 |
paren | -0.113 |
Token | B |
Token ID | 347 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
profit | +0.107 |
ailability | +0.106 |
arcity | +0.105 |
secure | +0.099 |
paren | +0.099 |
Neg logit contributions | |
Ba | -0.100 |
Probe | -0.099 |
Instrument | -0.099 |
coord | -0.098 |
Asuka | -0.098 |
Token | in |
Token ID | 287 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Probe | +0.245 |
Ba | +0.245 |
Instrument | +0.244 |
coord | +0.242 |
Asuka | +0.242 |
Neg logit contributions | |
profit | -0.201 |
ailability | -0.201 |
arcity | -0.198 |
secure | -0.185 |
paren | -0.185 |
Token | a |
Token ID | 257 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Ba | +0.241 |
Probe | +0.241 |
Instrument | +0.240 |
coord | +0.238 |
Asuka | +0.238 |
Neg logit contributions | |
profit | -0.201 |
ailability | -0.200 |
arcity | -0.198 |
secure | -0.186 |
paren | -0.185 |
Token | strongly |
Token ID | 7634 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Probe | +0.396 |
Ba | +0.396 |
Instrument | +0.394 |
coord | +0.391 |
Asuka | +0.391 |
Neg logit contributions | |
profit | -0.333 |
ailability | -0.332 |
arcity | -0.327 |
secure | -0.306 |
paren | -0.306 |
Token | word |
Token ID | 1573 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Probe | +1.510 |
Ba | +1.508 |
Instrument | +1.504 |
coord | +1.497 |
Asuka | +1.489 |
Neg logit contributions | |
ailability | -1.234 |
profit | -1.229 |
arcity | -1.213 |
paren | -1.128 |
secure | -1.127 |
Token | ed |
Token ID | 276 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
profit | +0.984 |
arcity | +0.933 |
ailability | +0.866 |
secure | +0.845 |
paren | +0.836 |
Neg logit contributions | |
Probe | -2.893 |
Ba | -2.882 |
Instrument | -2.873 |
coord | -2.860 |
Asuka | -2.859 |
Token | editorial |
Token ID | 13684 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
profit | +0.509 |
ailability | +0.501 |
arcity | +0.498 |
ides | +0.468 |
peril | +0.467 |
Neg logit contributions | |
Ba | -0.714 |
Probe | -0.711 |
Instrument | -0.708 |
coord | -0.705 |
Asuka | -0.704 |
Token | this |
Token ID | 428 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
profit | +3.276 |
ailability | +3.184 |
arcity | +3.182 |
ides | +3.124 |
peril | +3.048 |
Neg logit contributions | |
Ba | -4.810 |
coord | -4.750 |
Instrument | -4.742 |
Probe | -4.720 |
bats | -4.653 |
Token | week |
Token ID | 1285 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
profit | +0.262 |
ailability | +0.260 |
arcity | +0.258 |
peril | +0.245 |
ides | +0.245 |
Neg logit contributions | |
Ba | -0.239 |
Probe | -0.239 |
Instrument | -0.237 |
coord | -0.236 |
Asuka | -0.235 |
Token | that |
Token ID | 326 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
profit | +0.278 |
ailability | +0.276 |
arcity | +0.272 |
secure | +0.255 |
ides | +0.254 |
Neg logit contributions | |
Ba | -0.353 |
Probe | -0.353 |
Instrument | -0.351 |
coord | -0.349 |
Asuka | -0.348 |
Token | Britain |
Token ID | 5491 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
profit | +0.083 |
ailability | +0.082 |
arcity | +0.081 |
ides | +0.076 |
secure | +0.076 |
Neg logit contributions | |
Ba | -0.114 |
Probe | -0.114 |
Instrument | -0.113 |
coord | -0.112 |
Asuka | -0.112 |
Token | had |
Token ID | 550 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
profit | +0.555 |
ailability | +0.547 |
arcity | +0.544 |
ides | +0.521 |
peril | +0.519 |
Neg logit contributions | |
Ba | -0.542 |
Probe | -0.541 |
Instrument | -0.538 |
coord | -0.534 |
Asuka | -0.534 |
Token | in |
Token ID | 287 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
profit | +2.624 |
arcity | +2.570 |
ailability | +2.538 |
peril | +2.444 |
ides | +2.429 |
Neg logit contributions | |
Ba | -2.881 |
Probe | -2.862 |
coord | -2.860 |
Instrument | -2.860 |
Asuka | -2.853 |
Token | 54 |
Token ID | 7175 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
profit | +0.488 |
arcity | +0.475 |
ailability | +0.470 |
peril | +0.454 |
ides | +0.450 |
Neg logit contributions | |
Ba | -0.547 |
Probe | -0.541 |
coord | -0.540 |
Instrument | -0.538 |
Asuka | -0.537 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
profit | +0.094 |
ailability | +0.093 |
arcity | +0.092 |
secure | +0.087 |
ides | +0.087 |
Neg logit contributions | |
Probe | -0.089 |
Ba | -0.089 |
Instrument | -0.089 |
Asuka | -0.088 |
coord | -0.088 |
Token | / |
Token ID | 14 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
profit | +0.973 |
ailability | +0.960 |
arcity | +0.949 |
ides | +0.915 |
secure | +0.913 |
Neg logit contributions | |
Ba | -0.711 |
Probe | -0.711 |
Instrument | -0.709 |
Asuka | -0.707 |
coord | -0.699 |
Token | 3 |
Token ID | 18 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
profit | +1.091 |
arcity | +1.039 |
ailability | +1.017 |
ides | +1.005 |
secure | +0.999 |
Neg logit contributions | |
Asuka | -1.339 |
Probe | -1.329 |
coord | -1.326 |
Instrument | -1.317 |
Ba | -1.313 |
Token | IP |
Token ID | 6101 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
profit | +0.823 |
ailability | +0.806 |
arcity | +0.804 |
ides | +0.771 |
secure | +0.771 |
Neg logit contributions | |
Probe | -0.536 |
Ba | -0.533 |
Instrument | -0.531 |
Asuka | -0.529 |
coord | -0.520 |
Token | in |
Token ID | 287 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
profit | +3.773 |
arcity | +3.629 |
ailability | +3.586 |
ides | +3.563 |
peril | +3.511 |
Neg logit contributions | |
Instrument | -4.261 |
Probe | -4.240 |
Asuka | -4.207 |
Ba | -4.201 |
coord | -4.194 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
profit | +0.470 |
arcity | +0.458 |
ailability | +0.451 |
peril | +0.437 |
ides | +0.433 |
Neg logit contributions | |
Ba | -0.527 |
Probe | -0.521 |
Instrument | -0.519 |
coord | -0.518 |
Asuka | -0.515 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
profit | +0.523 |
ailability | +0.516 |
arcity | +0.512 |
peril | +0.483 |
ides | +0.483 |
Neg logit contributions | |
Ba | -0.573 |
Probe | -0.572 |
Instrument | -0.570 |
coord | -0.567 |
Asuka | -0.566 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
profit | +0.128 |
arcity | +0.124 |
ailability | +0.122 |
secure | +0.119 |
ides | +0.119 |
Neg logit contributions | |
Probe | -0.118 |
coord | -0.118 |
Instrument | -0.117 |
Ba | -0.117 |
Asuka | -0.116 |
Token | D |
Token ID | 35 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
profit | +0.284 |
ailability | +0.279 |
arcity | +0.277 |
secure | +0.264 |
ides | +0.262 |
Neg logit contributions | |
Probe | -0.285 |
Instrument | -0.282 |
coord | -0.281 |
Asuka | -0.280 |
Ba | -0.280 |
Token | Phone |
Token ID | 6132 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
profit | +1.601 |
arcity | +1.529 |
ailability | +1.528 |
secure | +1.490 |
paren | +1.469 |
Neg logit contributions | |
Probe | -1.654 |
Asuka | -1.649 |
Instrument | -1.648 |
Ba | -1.630 |
coord | -1.628 |
Token | List |
Token ID | 8053 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Ba | +2.372 |
Probe | +2.365 |
Instrument | +2.350 |
coord | +2.331 |
Asuka | +2.317 |
Neg logit contributions | |
ailability | -2.399 |
profit | -2.371 |
arcity | -2.352 |
paren | -2.205 |
secure | -2.200 |
Token | Ctrl |
Token ID | 40069 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Ba | +1.854 |
Probe | +1.853 |
Instrument | +1.842 |
coord | +1.828 |
Asuka | +1.823 |
Neg logit contributions | |
ailability | -2.061 |
profit | -2.059 |
arcity | -2.031 |
secure | -1.918 |
paren | -1.912 |
Token | "> |
Token ID | 5320 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Probe | +1.168 |
Ba | +1.167 |
Instrument | +1.161 |
coord | +1.152 |
Asuka | +1.152 |
Neg logit contributions | |
profit | -1.080 |
ailability | -1.076 |
arcity | -1.061 |
secure | -0.999 |
paren | -0.995 |
Token | < |
Token ID | 1279 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
profit | +0.423 |
ailability | +0.416 |
arcity | +0.412 |
secure | +0.400 |
ides | +0.400 |
Neg logit contributions | |
Ba | -0.238 |
Probe | -0.238 |
Asuka | -0.237 |
Instrument | -0.236 |
coord | -0.234 |
Token | ul |
Token ID | 377 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
profit | +1.887 |
ailability | +1.797 |
arcity | +1.765 |
secure | +1.756 |
paren | +1.748 |
Neg logit contributions | |
Probe | -2.124 |
Asuka | -2.120 |
Ba | -2.105 |
Instrument | -2.091 |
coord | -2.082 |
Token | > |
Token ID | 29 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
profit | +4.400 |
arcity | +4.263 |
ides | +4.203 |
ailability | +4.200 |
paren | +4.167 |
Neg logit contributions | |
Ba | -3.670 |
Asuka | -3.581 |
Probe | -3.546 |
bats | -3.532 |
Instrument | -3.486 |
Token | < |
Token ID | 1279 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
profit | +1.903 |
ailability | +1.863 |
arcity | +1.837 |
secure | +1.817 |
paren | +1.810 |
Neg logit contributions | |
Probe | -1.100 |
Ba | -1.099 |
Asuka | -1.097 |
Instrument | -1.089 |
coord | -1.085 |
Token | li |
Token ID | 4528 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
profit | +2.093 |
ailability | +1.969 |
arcity | +1.936 |
ides | +1.918 |
secure | +1.912 |
Neg logit contributions | |
Probe | -2.537 |
Ba | -2.513 |
Asuka | -2.507 |
coord | -2.490 |
Instrument | -2.486 |
Token | ng |
Token ID | 23370 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
profit | +2.647 |
ailability | +2.618 |
arcity | +2.592 |
paren | +2.553 |
peril | +2.528 |
Neg logit contributions | |
Ba | -1.752 |
Probe | -1.749 |
Asuka | -1.734 |
Instrument | -1.720 |
bats | -1.714 |
Token | - |
Token ID | 12 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
profit | +2.413 |
secure | +2.322 |
arcity | +2.312 |
paren | +2.291 |
ð | +2.252 |
Neg logit contributions | |
Ba | -2.440 |
Asuka | -2.419 |
Probe | -2.407 |
coord | -2.393 |
Instrument | -2.380 |
Token | Airport |
Token ID | 12690 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
Ba | +0.045 |
Probe | +0.045 |
Instrument | +0.045 |
coord | +0.045 |
Asuka | +0.045 |
Neg logit contributions | |
profit | -0.048 |
ailability | -0.048 |
arcity | -0.047 |
secure | -0.045 |
ides | -0.045 |
Token | Authority |
Token ID | 11416 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Probe | +0.477 |
Ba | +0.476 |
Instrument | +0.475 |
coord | +0.470 |
Asuka | +0.469 |
Neg logit contributions | |
profit | -0.440 |
ailability | -0.440 |
arcity | -0.433 |
secure | -0.407 |
paren | -0.406 |
Token | , |
Token ID | 11 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
Instrument | +1.793 |
Probe | +1.791 |
Ba | +1.778 |
coord | +1.767 |
Asuka | +1.748 |
Neg logit contributions | |
ailability | -1.678 |
arcity | -1.662 |
profit | -1.661 |
paren | -1.551 |
secure | -1.549 |
Token | and |
Token ID | 290 |
Feature activation | -5.00e-04 |
Pos logit contributions | |
Probe | +0.638 |
Ba | +0.637 |
Instrument | +0.634 |
coord | +0.629 |
Asuka | +0.629 |
Neg logit contributions | |
profit | -0.552 |
ailability | -0.551 |
arcity | -0.543 |
secure | -0.509 |
paren | -0.508 |
Token | Innov |
Token ID | 43405 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Ba | +0.000 |
Probe | +0.000 |
Instrument | +0.000 |
coord | +0.000 |
Asuka | +0.000 |
Neg logit contributions | |
profit | -0.000 |
ailability | -0.000 |
arcity | -0.000 |
secure | -0.000 |
peril | -0.000 |
Token | ative |
Token ID | 876 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
profit | +1.452 |
ailability | +1.415 |
arcity | +1.410 |
secure | +1.320 |
ides | +1.319 |
Neg logit contributions | |
Probe | -2.410 |
coord | -2.403 |
Ba | -2.401 |
Asuka | -2.396 |
Instrument | -2.372 |
Token | Employee |
Token ID | 36824 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
profit | +4.635 |
arcity | +4.494 |
ailability | +4.447 |
ides | +4.352 |
secure | +4.313 |
Neg logit contributions | |
Ba | -3.410 |
coord | -3.409 |
Asuka | -3.387 |
Probe | -3.320 |
bats | -3.312 |
Token | Solutions |
Token ID | 23555 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
profit | +1.652 |
ailability | +1.627 |
arcity | +1.614 |
secure | +1.535 |
ides | +1.535 |
Neg logit contributions | |
Ba | -1.456 |
Probe | -1.444 |
coord | -1.439 |
Asuka | -1.431 |
Instrument | -1.430 |
Token | . |
Token ID | 13 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
profit | +0.839 |
ailability | +0.832 |
arcity | +0.820 |
secure | +0.771 |
ides | +0.771 |
Neg logit contributions | |
Ba | -1.007 |
Probe | -1.005 |
Instrument | -0.995 |
Asuka | -0.994 |
coord | -0.994 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
profit | +0.377 |
arcity | +0.368 |
ailability | +0.363 |
secure | +0.349 |
ides | +0.349 |
Neg logit contributions | |
coord | -0.350 |
Ba | -0.349 |
Probe | -0.348 |
Instrument | -0.344 |
Asuka | -0.343 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
profit | +0.105 |
arcity | +0.102 |
ailability | +0.100 |
secure | +0.098 |
ides | +0.098 |
Neg logit contributions | |
Probe | -0.098 |
coord | -0.098 |
Instrument | -0.097 |
Ba | -0.097 |
Asuka | -0.096 |
Token | ements |
Token ID | 3196 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
profit | +1.976 |
ailability | +1.951 |
arcity | +1.909 |
ides | +1.848 |
paren | +1.816 |
Neg logit contributions | |
Probe | -2.668 |
Asuka | -2.650 |
Ba | -2.638 |
Instrument | -2.635 |
Amp | -2.594 |
Token | ré |
Token ID | 40560 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Ba | +0.339 |
Probe | +0.339 |
Instrument | +0.337 |
Asuka | +0.334 |
coord | +0.334 |
Neg logit contributions | |
profit | -0.315 |
ailability | -0.314 |
arcity | -0.309 |
secure | -0.292 |
paren | -0.291 |
Token | c |
Token ID | 66 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Probe | +0.143 |
Ba | +0.143 |
Instrument | +0.142 |
Asuka | +0.141 |
coord | +0.141 |
Neg logit contributions | |
profit | -0.114 |
ailability | -0.113 |
arcity | -0.111 |
secure | -0.104 |
paren | -0.104 |
Token | ents |
Token ID | 658 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
profit | +1.173 |
arcity | +1.155 |
ailability | +1.134 |
ides | +1.111 |
paren | +1.089 |
Neg logit contributions | |
Probe | -1.273 |
Instrument | -1.271 |
Ba | -1.260 |
Asuka | -1.259 |
coord | -1.245 |
Token | ind |
Token ID | 773 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Probe | +0.818 |
Ba | +0.818 |
Instrument | +0.814 |
coord | +0.809 |
Asuka | +0.806 |
Neg logit contributions | |
profit | -0.758 |
ailability | -0.757 |
arcity | -0.747 |
secure | -0.701 |
paren | -0.699 |
Token | iqu |
Token ID | 1557 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
profit | +1.083 |
ailability | +1.063 |
arcity | +1.053 |
ides | +1.005 |
secure | +0.988 |
Neg logit contributions | |
Probe | -1.489 |
Ba | -1.483 |
Asuka | -1.476 |
Instrument | -1.472 |
coord | -1.463 |
Token | ent |
Token ID | 298 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
profit | +3.642 |
arcity | +3.496 |
ailability | +3.488 |
ides | +3.487 |
paren | +3.457 |
Neg logit contributions | |
Probe | -4.447 |
Asuka | -4.406 |
Ba | -4.371 |
Instrument | -4.343 |
Amp | -4.289 |
Token | qu |
Token ID | 627 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
profit | +1.158 |
ailability | +1.149 |
arcity | +1.129 |
ides | +1.073 |
paren | +1.071 |
Neg logit contributions | |
Probe | -1.266 |
Ba | -1.264 |
Asuka | -1.255 |
Instrument | -1.254 |
coord | -1.233 |
Token | ' |
Token ID | 6 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
profit | +1.250 |
arcity | +1.226 |
ailability | +1.220 |
ides | +1.172 |
paren | +1.159 |
Neg logit contributions | |
Probe | -1.338 |
Asuka | -1.321 |
Ba | -1.320 |
Instrument | -1.316 |
coord | -1.306 |
Token | ils |
Token ID | 4487 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
profit | +1.020 |
ailability | +1.002 |
arcity | +0.996 |
ides | +0.947 |
secure | +0.945 |
Neg logit contributions | |
Probe | -1.033 |
Instrument | -1.026 |
Asuka | -1.020 |
Ba | -1.019 |
coord | -1.017 |
Token | ont |
Token ID | 39585 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Probe | +0.092 |
Ba | +0.092 |
Instrument | +0.092 |
Asuka | +0.091 |
coord | +0.090 |
Neg logit contributions | |
profit | -0.090 |
ailability | -0.089 |
arcity | -0.088 |
secure | -0.083 |
peril | -0.083 |
Token | � |
Token ID | 123 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
profit | +0.752 |
ailability | +0.743 |
arcity | +0.732 |
ides | +0.706 |
ð | +0.706 |
Neg logit contributions | |
Probe | -0.640 |
Ba | -0.633 |
Instrument | -0.633 |
Asuka | -0.627 |
coord | -0.623 |
Token | � |
Token ID | 228 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
Ba | +0.575 |
Probe | +0.575 |
Instrument | +0.572 |
coord | +0.568 |
Asuka | +0.568 |
Neg logit contributions | |
ailability | -0.466 |
profit | -0.466 |
arcity | -0.459 |
secure | -0.429 |
paren | -0.427 |
Token | ς |
Token ID | 35558 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Probe | +0.254 |
Ba | +0.254 |
Instrument | +0.253 |
coord | +0.251 |
Asuka | +0.251 |
Neg logit contributions | |
profit | -0.197 |
ailability | -0.197 |
arcity | -0.193 |
secure | -0.181 |
paren | -0.181 |
Token | ( |
Token ID | 357 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Probe | +0.308 |
Ba | +0.307 |
Instrument | +0.306 |
coord | +0.304 |
Asuka | +0.303 |
Neg logit contributions | |
profit | -0.293 |
ailability | -0.291 |
arcity | -0.287 |
secure | -0.271 |
ides | -0.270 |
Token | Ant |
Token ID | 13217 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Probe | +0.385 |
Ba | +0.385 |
Instrument | +0.383 |
coord | +0.380 |
Asuka | +0.380 |
Neg logit contributions | |
profit | -0.357 |
ailability | -0.356 |
arcity | -0.351 |
secure | -0.330 |
paren | -0.329 |
Token | iqu |
Token ID | 1557 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
profit | +0.232 |
ailability | +0.229 |
arcity | +0.228 |
ides | +0.214 |
secure | +0.213 |
Neg logit contributions | |
Probe | -0.266 |
Ba | -0.265 |
Instrument | -0.264 |
coord | -0.263 |
Asuka | -0.262 |
Token | ities |
Token ID | 871 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
profit | +3.989 |
arcity | +3.912 |
ailability | +3.903 |
ides | +3.877 |
ð | +3.717 |
Neg logit contributions | |
coord | -4.075 |
Probe | -4.051 |
Instrument | -3.997 |
Asuka | -3.971 |
Ba | -3.967 |
Token | of |
Token ID | 286 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
profit | +0.949 |
ailability | +0.943 |
arcity | +0.933 |
ides | +0.881 |
peril | +0.877 |
Neg logit contributions | |
Ba | -1.093 |
Probe | -1.093 |
coord | -1.084 |
Instrument | -1.083 |
Asuka | -1.078 |
Token | the |
Token ID | 262 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
profit | +0.350 |
ailability | +0.348 |
arcity | +0.344 |
ides | +0.326 |
secure | +0.325 |
Neg logit contributions | |
Ba | -0.350 |
Probe | -0.350 |
Instrument | -0.347 |
coord | -0.347 |
Asuka | -0.345 |
Token | Jews |
Token ID | 6771 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Ba | +0.285 |
Probe | +0.285 |
Instrument | +0.283 |
coord | +0.283 |
Asuka | +0.281 |
Neg logit contributions | |
profit | -0.330 |
ailability | -0.328 |
arcity | -0.325 |
secure | -0.308 |
ides | -0.307 |
Token | I |
Token ID | 314 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Probe | +1.416 |
Instrument | +1.412 |
Ba | +1.412 |
Asuka | +1.398 |
coord | +1.392 |
Neg logit contributions | |
ailability | -1.225 |
profit | -1.218 |
arcity | -1.201 |
secure | -1.125 |
paren | -1.121 |
Token | multiple |
Token ID | 3294 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
profit | +0.287 |
ailability | +0.285 |
arcity | +0.283 |
peril | +0.268 |
ides | +0.267 |
Neg logit contributions | |
Probe | -0.309 |
Ba | -0.308 |
Instrument | -0.307 |
coord | -0.304 |
Asuka | -0.302 |
Token | different |
Token ID | 1180 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
profit | +0.872 |
ailability | +0.859 |
arcity | +0.853 |
ides | +0.825 |
peril | +0.823 |
Neg logit contributions | |
Ba | -0.926 |
Probe | -0.926 |
Instrument | -0.922 |
Asuka | -0.908 |
coord | -0.907 |
Token | perspectives |
Token ID | 22582 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
profit | +0.840 |
ailability | +0.827 |
arcity | +0.818 |
peril | +0.795 |
ides | +0.790 |
Neg logit contributions | |
Probe | -0.895 |
Ba | -0.894 |
Instrument | -0.889 |
Asuka | -0.876 |
coord | -0.876 |
Token | of |
Token ID | 286 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
profit | +0.054 |
ailability | +0.054 |
arcity | +0.053 |
secure | +0.050 |
ides | +0.050 |
Neg logit contributions | |
Probe | -0.071 |
Ba | -0.071 |
Instrument | -0.070 |
coord | -0.070 |
Asuka | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
profit | +0.055 |
ailability | +0.055 |
arcity | +0.054 |
peril | +0.051 |
secure | +0.051 |
Neg logit contributions | |
Ba | -0.056 |
Probe | -0.056 |
Instrument | -0.055 |
coord | -0.055 |
Asuka | -0.055 |
Token | Halo |
Token ID | 18597 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
Ba | +0.252 |
Probe | +0.252 |
Instrument | +0.250 |
coord | +0.249 |
Asuka | +0.247 |
Neg logit contributions | |
profit | -0.242 |
ailability | -0.240 |
arcity | -0.238 |
peril | -0.225 |
ides | -0.224 |
Token | universe |
Token ID | 6881 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
profit | +3.784 |
arcity | +3.630 |
ailability | +3.612 |
peril | +3.538 |
ides | +3.502 |
Neg logit contributions | |
Ba | -4.199 |
Asuka | -4.161 |
bats | -4.078 |
Probe | -4.072 |
coord | -4.071 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
profit | +0.160 |
ailability | +0.158 |
arcity | +0.157 |
ides | +0.147 |
peril | +0.146 |
Neg logit contributions | |
Ba | -0.221 |
Probe | -0.221 |
Instrument | -0.220 |
coord | -0.219 |
Asuka | -0.218 |
Token |
|
Token ID | 198 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
Ba | +0.025 |
coord | +0.025 |
Probe | +0.025 |
Instrument | +0.025 |
Asuka | +0.025 |
Neg logit contributions | |
profit | -0.027 |
arcity | -0.027 |
ailability | -0.027 |
ides | -0.025 |
secure | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Probe | +0.040 |
Ba | +0.040 |
Instrument | +0.040 |
coord | +0.040 |
Asuka | +0.040 |
Neg logit contributions | |
profit | -0.045 |
ailability | -0.045 |
arcity | -0.044 |
secure | -0.042 |
paren | -0.042 |
Token | These |
Token ID | 4711 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
profit | +0.173 |
ailability | +0.171 |
arcity | +0.169 |
secure | +0.160 |
paren | +0.159 |
Neg logit contributions | |
Probe | -0.187 |
Instrument | -0.186 |
Ba | -0.186 |
coord | -0.185 |
Asuka | -0.185 |
Token | and |
Token ID | 290 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
profit | +0.202 |
ailability | +0.200 |
arcity | +0.197 |
peril | +0.189 |
secure | +0.188 |
Neg logit contributions | |
Ba | -0.218 |
Probe | -0.218 |
Instrument | -0.216 |
coord | -0.216 |
Asuka | -0.213 |
Token | set |
Token ID | 900 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
profit | +0.047 |
ailability | +0.046 |
arcity | +0.046 |
peril | +0.044 |
secure | +0.044 |
Neg logit contributions | |
Probe | -0.050 |
Ba | -0.050 |
coord | -0.050 |
Instrument | -0.050 |
Asuka | -0.049 |
Token | his |
Token ID | 465 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
profit | +0.837 |
ailability | +0.829 |
arcity | +0.819 |
peril | +0.781 |
secure | +0.775 |
Neg logit contributions | |
Probe | -0.907 |
Ba | -0.904 |
Instrument | -0.899 |
coord | -0.899 |
Asuka | -0.887 |
Token | vengeance |
Token ID | 30657 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
profit | +0.510 |
ailability | +0.499 |
arcity | +0.494 |
peril | +0.478 |
ides | +0.472 |
Neg logit contributions | |
Ba | -0.478 |
Probe | -0.476 |
coord | -0.471 |
Instrument | -0.471 |
Asuka | -0.469 |
Token | into |
Token ID | 656 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ailability | +0.070 |
profit | +0.070 |
arcity | +0.069 |
secure | +0.064 |
paren | +0.064 |
Neg logit contributions | |
Ba | -0.094 |
Probe | -0.094 |
Instrument | -0.093 |
Asuka | -0.093 |
coord | -0.092 |
Token | motion |
Token ID | 6268 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
profit | +1.327 |
ailability | +1.280 |
arcity | +1.261 |
peril | +1.216 |
ides | +1.178 |
Neg logit contributions | |
Probe | -2.554 |
Ba | -2.551 |
coord | -2.532 |
Instrument | -2.526 |
Asuka | -2.503 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
profit | +2.980 |
arcity | +2.814 |
peril | +2.811 |
ides | +2.792 |
ailability | +2.788 |
Neg logit contributions | |
coord | -4.942 |
Probe | -4.931 |
Ba | -4.882 |
Instrument | -4.839 |
Asuka | -4.799 |
Token | While |
Token ID | 2893 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
profit | +0.250 |
arcity | +0.243 |
ailability | +0.240 |
secure | +0.233 |
ides | +0.233 |
Neg logit contributions | |
coord | -0.243 |
Ba | -0.238 |
Probe | -0.238 |
Instrument | -0.235 |
elim | -0.233 |
Token | Yoshi |
Token ID | 38936 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
profit | +2.390 |
peril | +2.312 |
ailability | +2.302 |
arcity | +2.301 |
secure | +2.266 |
Neg logit contributions | |
Ba | -2.661 |
Probe | -2.661 |
coord | -2.657 |
Instrument | -2.619 |
bats | -2.575 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Probe | +0.262 |
Ba | +0.262 |
Instrument | +0.260 |
coord | +0.258 |
Asuka | +0.258 |
Neg logit contributions | |
profit | -0.258 |
ailability | -0.258 |
arcity | -0.254 |
secure | -0.239 |
paren | -0.239 |
Token | away |
Token ID | 1497 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
profit | +0.676 |
ailability | +0.666 |
arcity | +0.662 |
peril | +0.633 |
secure | +0.628 |
Neg logit contributions | |
Ba | -0.739 |
Probe | -0.739 |
Instrument | -0.734 |
coord | -0.730 |
Asuka | -0.725 |
Token | Phone |
Token ID | 6132 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
profit | +2.040 |
arcity | +1.961 |
ailability | +1.958 |
secure | +1.915 |
paren | +1.914 |
Neg logit contributions | |
Asuka | -1.764 |
Probe | -1.751 |
Instrument | -1.742 |
coord | -1.720 |
Ba | -1.708 |
Token | List |
Token ID | 8053 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Ba | +2.126 |
Probe | +2.124 |
Instrument | +2.108 |
coord | +2.090 |
Asuka | +2.076 |
Neg logit contributions | |
ailability | -1.698 |
profit | -1.686 |
arcity | -1.666 |
secure | -1.553 |
peril | -1.547 |
Token | Ctrl |
Token ID | 40069 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Probe | +0.743 |
Ba | +0.740 |
Instrument | +0.737 |
Asuka | +0.730 |
coord | +0.729 |
Neg logit contributions | |
profit | -1.368 |
ailability | -1.364 |
arcity | -1.351 |
secure | -1.293 |
paren | -1.291 |
Token | "> |
Token ID | 5320 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Probe | +0.416 |
Ba | +0.416 |
Instrument | +0.414 |
coord | +0.410 |
Asuka | +0.410 |
Neg logit contributions | |
profit | -0.459 |
ailability | -0.458 |
arcity | -0.452 |
secure | -0.427 |
paren | -0.426 |
Token | < |
Token ID | 1279 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
profit | +0.987 |
ailability | +0.985 |
arcity | +0.970 |
paren | +0.940 |
ides | +0.939 |
Neg logit contributions | |
Ba | -0.528 |
Probe | -0.528 |
Asuka | -0.519 |
Instrument | -0.518 |
coord | -0.515 |
Token | ul |
Token ID | 377 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
profit | +1.470 |
ailability | +1.423 |
arcity | +1.392 |
paren | +1.347 |
ides | +1.336 |
Neg logit contributions | |
Probe | -2.531 |
Ba | -2.514 |
Asuka | -2.507 |
Instrument | -2.499 |
coord | -2.493 |
Token | > |
Token ID | 29 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
profit | +4.232 |
ailability | +4.157 |
arcity | +4.131 |
paren | +4.085 |
ides | +4.069 |
Neg logit contributions | |
Ba | -3.670 |
Probe | -3.588 |
Asuka | -3.556 |
bats | -3.518 |
Instrument | -3.511 |
Token | < |
Token ID | 1279 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
profit | +2.418 |
ailability | +2.411 |
arcity | +2.364 |
paren | +2.309 |
ides | +2.307 |
Neg logit contributions | |
Probe | -1.384 |
Ba | -1.383 |
Asuka | -1.364 |
Instrument | -1.350 |
coord | -1.349 |
Token | li |
Token ID | 4528 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
profit | +2.281 |
ailability | +2.192 |
arcity | +2.154 |
paren | +2.129 |
ides | +2.109 |
Neg logit contributions | |
Probe | -2.750 |
Asuka | -2.716 |
Ba | -2.714 |
coord | -2.706 |
Instrument | -2.696 |
Token | ng |
Token ID | 23370 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ailability | +2.886 |
profit | +2.882 |
arcity | +2.846 |
paren | +2.782 |
ides | +2.762 |
Neg logit contributions | |
Probe | -1.658 |
Ba | -1.654 |
Asuka | -1.624 |
Instrument | -1.622 |
bats | -1.592 |
Token | - |
Token ID | 12 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
profit | +2.180 |
arcity | +2.076 |
paren | +2.063 |
secure | +2.052 |
ides | +2.023 |
Neg logit contributions | |
coord | -2.155 |
Asuka | -2.144 |
Probe | -2.127 |
Instrument | -2.122 |
Ba | -2.106 |
Token | While |
Token ID | 2893 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Ba | +0.531 |
Probe | +0.530 |
Instrument | +0.526 |
coord | +0.526 |
Asuka | +0.522 |
Neg logit contributions | |
profit | -0.535 |
ailability | -0.531 |
arcity | -0.526 |
secure | -0.497 |
paren | -0.495 |
Token | all |
Token ID | 477 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
profit | +1.816 |
ailability | +1.780 |
arcity | +1.768 |
peril | +1.703 |
secure | +1.696 |
Neg logit contributions | |
Ba | -1.996 |
Probe | -1.980 |
coord | -1.975 |
Instrument | -1.954 |
Asuka | -1.943 |
Token | three |
Token ID | 1115 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
Probe | +0.762 |
Instrument | +0.761 |
Ba | +0.760 |
Asuka | +0.754 |
coord | +0.753 |
Neg logit contributions | |
ailability | -0.609 |
profit | -0.605 |
arcity | -0.598 |
secure | -0.557 |
paren | -0.556 |
Token | titles |
Token ID | 8714 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
profit | +0.359 |
ailability | +0.359 |
arcity | +0.354 |
secure | +0.331 |
paren | +0.331 |
Neg logit contributions | |
Probe | -0.420 |
Ba | -0.420 |
Instrument | -0.418 |
coord | -0.415 |
Asuka | -0.415 |
Token | t |
Token ID | 256 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
profit | +0.270 |
ailability | +0.268 |
arcity | +0.265 |
secure | +0.249 |
peril | +0.248 |
Neg logit contributions | |
Probe | -0.312 |
Ba | -0.312 |
Instrument | -0.310 |
coord | -0.308 |
Asuka | -0.307 |
Token | ipt |
Token ID | 10257 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
Ba | +1.172 |
Probe | +1.171 |
Instrument | +1.164 |
coord | +1.158 |
Asuka | +1.156 |
Neg logit contributions | |
ailability | -0.558 |
profit | -0.556 |
arcity | -0.542 |
paren | -0.496 |
secure | -0.493 |
Token | oe |
Token ID | 2577 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
profit | +2.584 |
arcity | +2.488 |
ides | +2.405 |
secure | +2.367 |
ailability | +2.333 |
Neg logit contributions | |
Ba | -5.294 |
Probe | -5.246 |
coord | -5.211 |
Instrument | -5.210 |
Asuka | -5.198 |
Token | into |
Token ID | 656 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
profit | +1.249 |
arcity | +1.224 |
ailability | +1.217 |
peril | +1.190 |
ides | +1.168 |
Neg logit contributions | |
Probe | -1.274 |
Ba | -1.269 |
Instrument | -1.261 |
coord | -1.257 |
Asuka | -1.241 |
Token | min |
Token ID | 949 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
profit | +0.763 |
ailability | +0.761 |
arcity | +0.749 |
peril | +0.717 |
ides | +0.710 |
Neg logit contributions | |
Ba | -0.825 |
Probe | -0.825 |
Instrument | -0.818 |
coord | -0.815 |
Asuka | -0.809 |
Token | ig |
Token ID | 328 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Probe | +1.158 |
Ba | +1.155 |
Instrument | +1.149 |
coord | +1.139 |
Asuka | +1.137 |
Neg logit contributions | |
profit | -1.751 |
ailability | -1.743 |
arcity | -1.727 |
secure | -1.646 |
paren | -1.642 |
Token | ame |
Token ID | 480 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Ba | +0.791 |
Probe | +0.789 |
Instrument | +0.785 |
Asuka | +0.780 |
coord | +0.780 |
Neg logit contributions | |
profit | -0.813 |
ailability | -0.813 |
arcity | -0.798 |
secure | -0.756 |
paren | -0.752 |
Token | reason |
Token ID | 1738 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
profit | +0.083 |
ailability | +0.082 |
arcity | +0.081 |
ides | +0.077 |
secure | +0.077 |
Neg logit contributions | |
Probe | -0.080 |
Ba | -0.080 |
Instrument | -0.080 |
coord | -0.079 |
Asuka | -0.079 |
Token | why |
Token ID | 1521 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
profit | +0.107 |
arcity | +0.105 |
ailability | +0.105 |
ides | +0.099 |
secure | +0.099 |
Neg logit contributions | |
Ba | -0.121 |
Probe | -0.121 |
Instrument | -0.119 |
coord | -0.119 |
Asuka | -0.119 |
Token | they |
Token ID | 484 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
Ba | +0.176 |
Probe | +0.176 |
Instrument | +0.174 |
coord | +0.174 |
Asuka | +0.172 |
Neg logit contributions | |
profit | -0.159 |
ailability | -0.156 |
arcity | -0.156 |
secure | -0.148 |
ides | -0.148 |
Token | aired |
Token ID | 18530 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Probe | +0.552 |
Ba | +0.552 |
Instrument | +0.549 |
coord | +0.545 |
Asuka | +0.544 |
Neg logit contributions | |
profit | -0.521 |
ailability | -0.519 |
arcity | -0.512 |
secure | -0.482 |
paren | -0.480 |
Token | FINAL |
Token ID | 25261 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
Probe | +1.224 |
Ba | +1.224 |
Instrument | +1.215 |
coord | +1.206 |
Asuka | +1.203 |
Neg logit contributions | |
profit | -1.095 |
ailability | -1.086 |
arcity | -1.076 |
secure | -1.016 |
peril | -1.010 |
Token | EX |
Token ID | 7788 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
Probe | +2.278 |
Ba | +2.276 |
Instrument | +2.262 |
coord | +2.242 |
Asuka | +2.240 |
Neg logit contributions | |
profit | -2.990 |
ailability | -2.986 |
arcity | -2.950 |
secure | -2.801 |
paren | -2.794 |
Token | AM |
Token ID | 2390 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Ba | +4.328 |
Probe | +4.290 |
Instrument | +4.271 |
Asuka | +4.258 |
coord | +4.204 |
Neg logit contributions | |
ailability | -4.409 |
arcity | -4.298 |
profit | -4.295 |
secure | -3.989 |
paren | -3.980 |
Token | as |
Token ID | 355 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
profit | +0.636 |
ailability | +0.625 |
arcity | +0.619 |
peril | +0.591 |
ides | +0.588 |
Neg logit contributions | |
Probe | -0.757 |
Instrument | -0.755 |
Ba | -0.754 |
Asuka | -0.749 |
coord | -0.746 |
Token | the |
Token ID | 262 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Probe | +0.709 |
Ba | +0.708 |
Instrument | +0.704 |
coord | +0.698 |
Asuka | +0.696 |
Neg logit contributions | |
profit | -0.682 |
ailability | -0.678 |
arcity | -0.670 |
secure | -0.634 |
ides | -0.632 |
Token | premiere |
Token ID | 19245 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Ba | +0.404 |
Probe | +0.403 |
Instrument | +0.399 |
coord | +0.397 |
Asuka | +0.395 |
Neg logit contributions | |
profit | -0.379 |
ailability | -0.376 |
arcity | -0.371 |
peril | -0.352 |
secure | -0.352 |
Token | rather |
Token ID | 2138 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
profit | +0.366 |
ailability | +0.360 |
arcity | +0.359 |
peril | +0.347 |
ides | +0.344 |
Neg logit contributions | |
Probe | -0.307 |
Ba | -0.307 |
Instrument | -0.303 |
coord | -0.299 |
Asuka | -0.298 |
Token | d |
Token ID | 67 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
Probe | +0.249 |
Ba | +0.249 |
Instrument | +0.248 |
coord | +0.246 |
Asuka | +0.246 |
Neg logit contributions | |
profit | -0.228 |
ailability | -0.227 |
arcity | -0.224 |
secure | -0.211 |
paren | -0.210 |
Token | viewed |
Token ID | 9569 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
Instrument | +0.320 |
Ba | +0.320 |
Probe | +0.320 |
Asuka | +0.318 |
coord | +0.317 |
Neg logit contributions | |
profit | -0.285 |
ailability | -0.281 |
arcity | -0.279 |
ides | -0.264 |
secure | -0.261 |
Token | a |
Token ID | 257 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Ba | +0.033 |
Probe | +0.033 |
Instrument | +0.033 |
coord | +0.033 |
Asuka | +0.033 |
Neg logit contributions | |
profit | -0.032 |
ailability | -0.032 |
arcity | -0.031 |
secure | -0.030 |
ides | -0.030 |
Token | cell |
Token ID | 2685 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
profit | +0.189 |
ailability | +0.188 |
arcity | +0.185 |
secure | +0.175 |
ides | +0.175 |
Neg logit contributions | |
Ba | -0.203 |
Probe | -0.203 |
Instrument | -0.202 |
coord | -0.201 |
Asuka | -0.201 |
Token | - |
Token ID | 12 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Probe | +0.737 |
Ba | +0.736 |
Instrument | +0.732 |
coord | +0.727 |
Asuka | +0.726 |
Neg logit contributions | |
profit | -0.664 |
ailability | -0.663 |
arcity | -0.654 |
secure | -0.614 |
paren | -0.612 |
Token | phone |
Token ID | 4862 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
Ba | +1.267 |
Probe | +1.260 |
Instrument | +1.249 |
coord | +1.239 |
Asuka | +1.230 |
Neg logit contributions | |
ailability | -2.207 |
profit | -2.189 |
arcity | -2.180 |
peril | -2.069 |
paren | -2.068 |
Token | video |
Token ID | 2008 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Probe | +4.145 |
Ba | +4.099 |
Instrument | +4.080 |
coord | +4.050 |
Asuka | +4.031 |
Neg logit contributions | |
ailability | -4.342 |
arcity | -4.259 |
profit | -4.209 |
paren | -4.010 |
profits | -3.930 |
Token | of |
Token ID | 286 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Probe | +0.197 |
Ba | +0.197 |
Instrument | +0.196 |
coord | +0.195 |
Asuka | +0.194 |
Neg logit contributions | |
profit | -0.148 |
ailability | -0.148 |
arcity | -0.145 |
secure | -0.136 |
paren | -0.135 |
Token | Ford |
Token ID | 8092 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Ba | +0.261 |
Probe | +0.261 |
coord | +0.260 |
Instrument | +0.260 |
Asuka | +0.258 |
Neg logit contributions | |
profit | -0.273 |
ailability | -0.271 |
arcity | -0.268 |
secure | -0.254 |
peril | -0.254 |
Token | inh |
Token ID | 25783 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Probe | +1.313 |
Ba | +1.312 |
Instrument | +1.305 |
coord | +1.295 |
Asuka | +1.293 |
Neg logit contributions | |
profit | -1.289 |
ailability | -1.287 |
arcity | -1.271 |
secure | -1.194 |
paren | -1.191 |
Token | aling |
Token ID | 4272 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Probe | +1.314 |
Ba | +1.306 |
Instrument | +1.304 |
coord | +1.304 |
Asuka | +1.299 |
Neg logit contributions | |
profit | -0.904 |
ailability | -0.892 |
arcity | -0.887 |
secure | -0.827 |
ides | -0.826 |
Token | but |
Token ID | 475 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Probe | +0.101 |
Ba | +0.101 |
Instrument | +0.100 |
coord | +0.100 |
Asuka | +0.099 |
Neg logit contributions | |
profit | -0.092 |
ailability | -0.091 |
arcity | -0.090 |
secure | -0.085 |
ides | -0.085 |
Token | decided |
Token ID | 3066 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
Ba | +0.492 |
Probe | +0.491 |
Instrument | +0.488 |
coord | +0.485 |
Asuka | +0.482 |
Neg logit contributions | |
profit | -0.487 |
ailability | -0.481 |
arcity | -0.477 |
secure | -0.452 |
peril | -0.451 |
Token | that |
Token ID | 326 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
profit | +0.030 |
ailability | +0.029 |
arcity | +0.029 |
secure | +0.027 |
ides | +0.027 |
Neg logit contributions | |
Probe | -0.028 |
Ba | -0.028 |
Instrument | -0.028 |
coord | -0.028 |
Asuka | -0.028 |
Token | what |
Token ID | 644 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
Ba | +0.732 |
Probe | +0.730 |
Instrument | +0.726 |
coord | +0.719 |
Asuka | +0.716 |
Neg logit contributions | |
profit | -0.705 |
ailability | -0.693 |
arcity | -0.688 |
secure | -0.652 |
ides | -0.651 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Probe | +1.868 |
Ba | +1.862 |
Instrument | +1.857 |
Asuka | +1.847 |
coord | +1.842 |
Neg logit contributions | |
ailability | -2.094 |
profit | -2.081 |
arcity | -2.058 |
paren | -1.943 |
secure | -1.939 |
Token | hell |
Token ID | 5968 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
Probe | +1.171 |
Ba | +1.170 |
Instrument | +1.164 |
coord | +1.154 |
Asuka | +1.153 |
Neg logit contributions | |
profit | -1.351 |
ailability | -1.350 |
arcity | -1.332 |
secure | -1.261 |
paren | -1.258 |
Token | I |
Token ID | 314 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
Asuka | +4.018 |
Ba | +4.007 |
Instrument | +3.999 |
Probe | +3.972 |
coord | +3.962 |
Neg logit contributions | |
ailability | -4.227 |
arcity | -4.189 |
profit | -4.112 |
paren | -3.883 |
secure | -3.840 |
Token | 'll |
Token ID | 1183 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Ba | +0.538 |
Probe | +0.538 |
Instrument | +0.536 |
coord | +0.530 |
Asuka | +0.530 |
Neg logit contributions | |
profit | -0.517 |
ailability | -0.509 |
arcity | -0.507 |
secure | -0.479 |
peril | -0.478 |
Token | just |
Token ID | 655 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
profit | +0.269 |
arcity | +0.262 |
ailability | +0.259 |
peril | +0.249 |
secure | +0.248 |
Neg logit contributions | |
Probe | -0.293 |
Ba | -0.292 |
Instrument | -0.291 |
Asuka | -0.288 |
coord | -0.287 |
Token | put |
Token ID | 1234 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Probe | +1.438 |
Ba | +1.436 |
Instrument | +1.429 |
coord | +1.419 |
Asuka | +1.417 |
Neg logit contributions | |
profit | -1.298 |
ailability | -1.292 |
arcity | -1.275 |
secure | -1.200 |
paren | -1.196 |
Token | it |
Token ID | 340 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Ba | +0.100 |
Probe | +0.100 |
Instrument | +0.099 |
coord | +0.099 |
Asuka | +0.098 |
Neg logit contributions | |
profit | -0.087 |
ailability | -0.085 |
arcity | -0.085 |
secure | -0.080 |
peril | -0.080 |
Token | by |
Token ID | 416 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
profit | +0.251 |
ailability | +0.247 |
arcity | +0.247 |
peril | +0.236 |
ides | +0.235 |
Neg logit contributions | |
Ba | -0.259 |
Probe | -0.259 |
Instrument | -0.256 |
coord | -0.255 |
Asuka | -0.253 |
Token | Campbell |
Token ID | 14327 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
profit | +0.372 |
arcity | +0.367 |
ailability | +0.366 |
peril | +0.348 |
ides | +0.347 |
Neg logit contributions | |
Probe | -0.403 |
Ba | -0.403 |
Instrument | -0.398 |
coord | -0.397 |
Asuka | -0.393 |
Token | himself |
Token ID | 2241 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
profit | +0.253 |
ailability | +0.252 |
arcity | +0.249 |
ides | +0.235 |
secure | +0.234 |
Neg logit contributions | |
Probe | -0.295 |
Ba | -0.295 |
Instrument | -0.294 |
coord | -0.292 |
Asuka | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
profit | +0.497 |
ailability | +0.490 |
arcity | +0.486 |
ides | +0.459 |
peril | +0.457 |
Neg logit contributions | |
Ba | -0.647 |
Probe | -0.647 |
Instrument | -0.642 |
coord | -0.640 |
Asuka | -0.635 |
Token | His |
Token ID | 2399 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
profit | +0.162 |
arcity | +0.158 |
ailability | +0.156 |
ides | +0.150 |
secure | +0.150 |
Neg logit contributions | |
coord | -0.159 |
Probe | -0.158 |
Ba | -0.157 |
Instrument | -0.156 |
Asuka | -0.154 |
Token | ex |
Token ID | 409 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
profit | +0.752 |
ailability | +0.744 |
arcity | +0.737 |
peril | +0.703 |
ides | +0.702 |
Neg logit contributions | |
Ba | -0.802 |
Probe | -0.801 |
Instrument | -0.792 |
coord | -0.789 |
Asuka | -0.784 |
Token | uber |
Token ID | 18478 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Ba | +3.768 |
Instrument | +3.740 |
Asuka | +3.727 |
Probe | +3.719 |
coord | +3.662 |
Neg logit contributions | |
ailability | -4.353 |
profit | -4.321 |
arcity | -4.243 |
secure | -4.002 |
paren | -3.972 |
Token | ant |
Token ID | 415 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
profit | +0.905 |
ailability | +0.896 |
arcity | +0.887 |
secure | +0.818 |
paren | +0.815 |
Neg logit contributions | |
Probe | -1.509 |
Ba | -1.506 |
Instrument | -1.500 |
coord | -1.493 |
Asuka | -1.490 |
Token | praise |
Token ID | 13463 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
profit | +0.420 |
ailability | +0.415 |
arcity | +0.411 |
ides | +0.395 |
peril | +0.393 |
Neg logit contributions | |
Ba | -0.432 |
Probe | -0.432 |
Instrument | -0.426 |
coord | -0.425 |
Asuka | -0.421 |
Token | of |
Token ID | 286 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
Probe | +0.515 |
Ba | +0.515 |
Instrument | +0.513 |
coord | +0.509 |
Asuka | +0.509 |
Neg logit contributions | |
profit | -0.444 |
ailability | -0.443 |
arcity | -0.436 |
secure | -0.409 |
paren | -0.408 |
Token | myth |
Token ID | 7918 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
profit | +0.377 |
ailability | +0.373 |
arcity | +0.371 |
peril | +0.352 |
ides | +0.351 |
Neg logit contributions | |
Probe | -0.383 |
Ba | -0.382 |
coord | -0.378 |
Instrument | -0.378 |
Asuka | -0.371 |
Token | � |
Token ID | 250 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
Probe | +0.422 |
Ba | +0.422 |
Instrument | +0.420 |
Asuka | +0.417 |
coord | +0.417 |
Neg logit contributions | |
profit | -0.364 |
ailability | -0.361 |
arcity | -0.356 |
secure | -0.335 |
paren | -0.334 |
Token | che |
Token ID | 2395 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
profit | +0.538 |
ailability | +0.524 |
arcity | +0.521 |
secure | +0.500 |
paren | +0.495 |
Neg logit contributions | |
Probe | -0.549 |
Instrument | -0.544 |
Ba | -0.542 |
coord | -0.540 |
Asuka | -0.540 |
Token | er |
Token ID | 263 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
profit | +1.186 |
arcity | +1.164 |
ailability | +1.150 |
ides | +1.104 |
secure | +1.103 |
Neg logit contributions | |
Ba | -1.022 |
Probe | -1.021 |
Instrument | -1.021 |
coord | -1.005 |
Asuka | -1.001 |
Token | on |
Token ID | 319 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
profit | +1.619 |
ailability | +1.606 |
arcity | +1.578 |
ides | +1.521 |
ð | +1.517 |
Neg logit contributions | |
Probe | -1.821 |
Ba | -1.807 |
Instrument | -1.803 |
coord | -1.801 |
Asuka | -1.788 |
Token | his |
Token ID | 465 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Probe | +0.242 |
Ba | +0.241 |
Instrument | +0.240 |
coord | +0.238 |
Asuka | +0.238 |
Neg logit contributions | |
profit | -0.230 |
ailability | -0.229 |
arcity | -0.226 |
secure | -0.213 |
paren | -0.212 |
Token | ex |
Token ID | 409 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
Probe | +0.108 |
Ba | +0.108 |
Instrument | +0.107 |
coord | +0.106 |
Asuka | +0.106 |
Neg logit contributions | |
profit | -0.105 |
ailability | -0.104 |
arcity | -0.103 |
peril | -0.097 |
ides | -0.097 |
Token | - |
Token ID | 12 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Ba | +3.845 |
Probe | +3.816 |
Asuka | +3.797 |
Instrument | +3.782 |
coord | +3.739 |
Neg logit contributions | |
ailability | -4.256 |
profit | -4.190 |
arcity | -4.180 |
paren | -3.897 |
secure | -3.889 |
Token | f |
Token ID | 69 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
profit | +0.536 |
ailability | +0.517 |
arcity | +0.514 |
secure | +0.502 |
paren | +0.498 |
Neg logit contributions | |
Probe | -0.404 |
Instrument | -0.400 |
coord | -0.394 |
Asuka | -0.391 |
Ba | -0.390 |
Token | ellow |
Token ID | 5037 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
profit | +0.056 |
ailability | +0.055 |
arcity | +0.055 |
secure | +0.052 |
ides | +0.052 |
Neg logit contributions | |
Probe | -0.052 |
Ba | -0.052 |
Instrument | -0.052 |
coord | -0.051 |
Asuka | -0.051 |
Token | eat |
Token ID | 4483 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
Probe | +2.820 |
Ba | +2.819 |
Instrument | +2.799 |
Asuka | +2.795 |
coord | +2.795 |
Neg logit contributions | |
ailability | -2.663 |
profit | -2.647 |
arcity | -2.619 |
secure | -2.464 |
paren | -2.455 |
Token | ers |
Token ID | 364 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
profit | +0.037 |
ailability | +0.036 |
arcity | +0.036 |
secure | +0.034 |
ides | +0.034 |
Neg logit contributions | |
Probe | -0.033 |
Ba | -0.032 |
Instrument | -0.032 |
Asuka | -0.032 |
coord | -0.032 |
Token | Skip |
Token ID | 32214 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Probe | +0.626 |
Ba | +0.624 |
Instrument | +0.622 |
coord | +0.618 |
Asuka | +0.618 |
Neg logit contributions | |
profit | -0.600 |
ailability | -0.598 |
arcity | -0.591 |
secure | -0.557 |
paren | -0.554 |
Token | Bay |
Token ID | 4696 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
Ba | +2.116 |
Probe | +2.083 |
Instrument | +2.063 |
Asuka | +2.058 |
coord | +2.030 |
Neg logit contributions | |
ailability | -2.414 |
profit | -2.394 |
arcity | -2.372 |
paren | -2.244 |
secure | -2.224 |
Token | less |
Token ID | 1203 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
profit | +0.491 |
arcity | +0.485 |
ailability | +0.479 |
secure | +0.465 |
ides | +0.462 |
Neg logit contributions | |
Probe | -0.426 |
Ba | -0.422 |
Asuka | -0.421 |
coord | -0.418 |
Instrument | -0.415 |
Token | (@ |
Token ID | 4275 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Ba | +2.221 |
Probe | +2.219 |
Instrument | +2.209 |
coord | +2.184 |
Asuka | +2.181 |
Neg logit contributions | |
ailability | -2.632 |
profit | -2.614 |
arcity | -2.584 |
paren | -2.447 |
secure | -2.434 |
Token | Real |
Token ID | 15633 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Ba | +1.619 |
Probe | +1.606 |
Instrument | +1.595 |
coord | +1.583 |
Asuka | +1.578 |
Neg logit contributions | |
ailability | -1.895 |
profit | -1.883 |
arcity | -1.861 |
peril | -1.756 |
secure | -1.756 |
Token | Skip |
Token ID | 50232 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
Ba | +1.078 |
Probe | +1.075 |
Instrument | +1.065 |
coord | +1.053 |
Asuka | +1.051 |
Neg logit contributions | |
ailability | -2.213 |
profit | -2.213 |
arcity | -2.188 |
secure | -2.095 |
paren | -2.091 |
Token | Bay |
Token ID | 15262 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Ba | +2.762 |
Probe | +2.585 |
Instrument | +2.545 |
bats | +2.524 |
coord | +2.508 |
Neg logit contributions | |
ailability | -5.473 |
profit | -5.348 |
arcity | -5.277 |
paren | -5.130 |
peril | -5.120 |
Token | less |
Token ID | 1203 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Ba | +0.988 |
Probe | +0.970 |
Instrument | +0.970 |
coord | +0.951 |
Asuka | +0.948 |
Neg logit contributions | |
ailability | -1.404 |
profit | -1.373 |
arcity | -1.356 |
peril | -1.300 |
paren | -1.297 |
Token | ) |
Token ID | 8 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Ba | +2.536 |
Probe | +2.499 |
Instrument | +2.476 |
coord | +2.445 |
Asuka | +2.434 |
Neg logit contributions | |
ailability | -3.263 |
profit | -3.244 |
arcity | -3.190 |
peril | -3.059 |
paren | -3.042 |
Token | January |
Token ID | 3269 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
Probe | +1.627 |
Ba | +1.625 |
Instrument | +1.621 |
coord | +1.608 |
Asuka | +1.608 |
Neg logit contributions | |
ailability | -1.152 |
profit | -1.149 |
arcity | -1.129 |
secure | -1.048 |
paren | -1.047 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
profit | +0.410 |
arcity | +0.399 |
ailability | +0.386 |
ides | +0.382 |
peril | +0.379 |
Neg logit contributions | |
coord | -0.498 |
Ba | -0.496 |
Probe | -0.495 |
Instrument | -0.492 |
Asuka | -0.489 |
Token | a |
Token ID | 64 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Probe | +1.629 |
Ba | +1.629 |
Instrument | +1.619 |
coord | +1.605 |
Asuka | +1.605 |
Neg logit contributions | |
ailability | -1.654 |
profit | -1.653 |
arcity | -1.629 |
secure | -1.536 |
paren | -1.531 |
Token | shot |
Token ID | 2823 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Probe | +0.106 |
Ba | +0.106 |
Instrument | +0.106 |
coord | +0.106 |
Asuka | +0.105 |
Neg logit contributions | |
profit | -0.105 |
ailability | -0.104 |
arcity | -0.103 |
ides | -0.098 |
secure | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Ba | +0.394 |
coord | +0.392 |
Probe | +0.391 |
Instrument | +0.391 |
Asuka | +0.387 |
Neg logit contributions | |
profit | -0.350 |
arcity | -0.344 |
ailability | -0.344 |
ides | -0.325 |
peril | -0.323 |
Token | killed |
Token ID | 2923 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
profit | +0.244 |
ailability | +0.241 |
arcity | +0.237 |
peril | +0.229 |
secure | +0.228 |
Neg logit contributions | |
Ba | -0.268 |
Probe | -0.268 |
coord | -0.267 |
Instrument | -0.265 |
Asuka | -0.261 |
Token | his |
Token ID | 465 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Ba | +0.253 |
Probe | +0.253 |
Instrument | +0.251 |
coord | +0.251 |
Asuka | +0.248 |
Neg logit contributions | |
profit | -0.276 |
ailability | -0.273 |
arcity | -0.271 |
ides | -0.256 |
secure | -0.256 |
Token | ex |
Token ID | 409 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
profit | +0.180 |
ailability | +0.175 |
arcity | +0.174 |
peril | +0.168 |
ides | +0.167 |
Neg logit contributions | |
Ba | -0.183 |
Probe | -0.181 |
coord | -0.180 |
Instrument | -0.180 |
Asuka | -0.178 |
Token | - |
Token ID | 12 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
Ba | +3.139 |
Probe | +3.113 |
Instrument | +3.097 |
Asuka | +3.064 |
Amp | +2.984 |
Neg logit contributions | |
ailability | -4.985 |
arcity | -4.910 |
profit | -4.875 |
ð | -4.570 |
peril | -4.559 |
Token | wife |
Token ID | 22095 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
profit | +0.647 |
ailability | +0.617 |
arcity | +0.614 |
secure | +0.606 |
paren | +0.602 |
Neg logit contributions | |
Probe | -0.497 |
Instrument | -0.490 |
coord | -0.490 |
Asuka | -0.485 |
Ba | -0.478 |
Token | , |
Token ID | 11 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
profit | +0.851 |
arcity | +0.829 |
ailability | +0.826 |
ides | +0.792 |
peril | +0.787 |
Neg logit contributions | |
Ba | -0.948 |
coord | -0.947 |
Probe | -0.947 |
Instrument | -0.942 |
Asuka | -0.929 |
Token | 33 |
Token ID | 4747 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Ba | +0.426 |
Probe | +0.426 |
Instrument | +0.424 |
coord | +0.422 |
Asuka | +0.418 |
Neg logit contributions | |
profit | -0.415 |
ailability | -0.410 |
arcity | -0.406 |
secure | -0.384 |
ides | -0.384 |
Token | - |
Token ID | 12 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
Ba | +0.419 |
Probe | +0.419 |
Instrument | +0.418 |
coord | +0.418 |
Asuka | +0.413 |
Neg logit contributions | |
profit | -0.504 |
ailability | -0.498 |
arcity | -0.494 |
secure | -0.471 |
ides | -0.468 |
Token | More |
Token ID | 3125 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
profit | +0.601 |
ailability | +0.592 |
arcity | +0.591 |
ides | +0.558 |
secure | +0.557 |
Neg logit contributions | |
Ba | -0.611 |
Probe | -0.607 |
Instrument | -0.607 |
coord | -0.605 |
Asuka | -0.600 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
profit | +1.208 |
arcity | +1.167 |
ailability | +1.159 |
ides | +1.119 |
secure | +1.114 |
Neg logit contributions | |
coord | -1.466 |
Probe | -1.445 |
Instrument | -1.444 |
Ba | -1.443 |
Asuka | -1.438 |
Token | H |
Token ID | 39 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Probe | +0.373 |
Ba | +0.371 |
Instrument | +0.371 |
coord | +0.368 |
Asuka | +0.368 |
Neg logit contributions | |
profit | -0.333 |
ailability | -0.330 |
arcity | -0.327 |
secure | -0.308 |
paren | -0.307 |
Token | ats |
Token ID | 1381 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
profit | +0.294 |
ailability | +0.293 |
arcity | +0.291 |
ides | +0.275 |
secure | +0.272 |
Neg logit contributions | |
Probe | -0.297 |
Ba | -0.295 |
Instrument | -0.295 |
coord | -0.294 |
Asuka | -0.293 |
Token | une |
Token ID | 1726 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Probe | +1.193 |
Ba | +1.190 |
Instrument | +1.184 |
coord | +1.177 |
Asuka | +1.176 |
Neg logit contributions | |
profit | -1.249 |
ailability | -1.245 |
arcity | -1.228 |
secure | -1.160 |
ides | -1.159 |
Token | Mik |
Token ID | 17722 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
Ba | +0.827 |
Probe | +0.825 |
Instrument | +0.819 |
coord | +0.813 |
Asuka | +0.810 |
Neg logit contributions | |
profit | -1.345 |
ailability | -1.339 |
arcity | -1.326 |
secure | -1.266 |
ides | -1.264 |
Token | u |
Token ID | 84 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Ba | +3.247 |
Instrument | +3.173 |
Probe | +3.158 |
Asuka | +3.126 |
ibe | +3.095 |
Neg logit contributions | |
ailability | -4.879 |
profit | -4.767 |
arcity | -4.755 |
peril | -4.494 |
secure | -4.459 |
Token | : |
Token ID | 25 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Probe | +1.662 |
Ba | +1.661 |
Instrument | +1.652 |
coord | +1.639 |
Asuka | +1.637 |
Neg logit contributions | |
profit | -1.755 |
ailability | -1.752 |
arcity | -1.729 |
secure | -1.633 |
paren | -1.628 |
Token | Project |
Token ID | 4935 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
Probe | +1.507 |
Ba | +1.506 |
Instrument | +1.495 |
coord | +1.487 |
Asuka | +1.481 |
Neg logit contributions | |
profit | -1.828 |
ailability | -1.821 |
arcity | -1.800 |
secure | -1.708 |
paren | -1.702 |
Token | Div |
Token ID | 4777 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Ba | +0.020 |
Probe | +0.020 |
Instrument | +0.020 |
coord | +0.019 |
Asuka | +0.019 |
Neg logit contributions | |
profit | -0.024 |
ailability | -0.024 |
arcity | -0.023 |
secure | -0.022 |
paren | -0.022 |
Token | a |
Token ID | 64 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Ba | +1.207 |
Probe | +1.206 |
Instrument | +1.201 |
Asuka | +1.193 |
coord | +1.191 |
Neg logit contributions | |
ailability | -0.893 |
profit | -0.892 |
arcity | -0.876 |
secure | -0.817 |
paren | -0.814 |
Token | prison |
Token ID | 3770 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Probe | +0.455 |
Ba | +0.455 |
Instrument | +0.452 |
coord | +0.449 |
Asuka | +0.449 |
Neg logit contributions | |
profit | -0.431 |
ailability | -0.430 |
arcity | -0.424 |
secure | -0.399 |
paren | -0.397 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
profit | +0.064 |
ailability | +0.063 |
arcity | +0.062 |
secure | +0.058 |
ides | +0.058 |
Neg logit contributions | |
Ba | -0.084 |
Probe | -0.084 |
Instrument | -0.084 |
coord | -0.083 |
Asuka | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
coord | +0.172 |
Ba | +0.171 |
Probe | +0.170 |
Instrument | +0.169 |
Asuka | +0.169 |
Neg logit contributions | |
profit | -0.178 |
arcity | -0.174 |
ailability | -0.174 |
secure | -0.166 |
ides | -0.165 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Probe | +0.043 |
coord | +0.042 |
Instrument | +0.042 |
Ba | +0.042 |
Asuka | +0.042 |
Neg logit contributions | |
profit | -0.046 |
arcity | -0.045 |
ailability | -0.045 |
secure | -0.043 |
ides | -0.043 |
Token | K |
Token ID | 42 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
profit | +0.152 |
ailability | +0.149 |
arcity | +0.148 |
secure | +0.141 |
paren | +0.140 |
Neg logit contributions | |
Probe | -0.157 |
Instrument | -0.156 |
coord | -0.155 |
Ba | -0.155 |
Asuka | -0.155 |
Token | lass |
Token ID | 31172 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
Ba | +1.544 |
Instrument | +1.527 |
Probe | +1.525 |
coord | +1.520 |
Asuka | +1.513 |
Neg logit contributions | |
ailability | -0.972 |
profit | -0.966 |
arcity | -0.939 |
secure | -0.882 |
paren | -0.878 |
Token | was |
Token ID | 373 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
Ba | +3.734 |
Probe | +3.716 |
Instrument | +3.687 |
coord | +3.656 |
Asuka | +3.625 |
Neg logit contributions | |
ailability | -4.217 |
profit | -4.119 |
arcity | -4.109 |
paren | -3.888 |
secure | -3.840 |
Token | found |
Token ID | 1043 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Probe | +0.433 |
Ba | +0.432 |
Instrument | +0.430 |
coord | +0.427 |
Asuka | +0.426 |
Neg logit contributions | |
profit | -0.449 |
ailability | -0.449 |
arcity | -0.443 |
secure | -0.418 |
paren | -0.416 |
Token | in |
Token ID | 287 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
profit | +0.570 |
ailability | +0.566 |
arcity | +0.561 |
peril | +0.536 |
secure | +0.534 |
Neg logit contributions | |
Probe | -0.520 |
Ba | -0.517 |
Instrument | -0.515 |
coord | -0.513 |
Asuka | -0.508 |
Token | her |
Token ID | 607 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
profit | +0.281 |
ailability | +0.279 |
arcity | +0.276 |
secure | +0.263 |
peril | +0.263 |
Neg logit contributions | |
Ba | -0.299 |
Probe | -0.299 |
coord | -0.297 |
Instrument | -0.296 |
Asuka | -0.292 |
Token | North |
Token ID | 2258 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
profit | +0.266 |
ailability | +0.261 |
arcity | +0.258 |
peril | +0.248 |
secure | +0.247 |
Neg logit contributions | |
Probe | -0.289 |
Ba | -0.288 |
Instrument | -0.286 |
coord | -0.285 |
Asuka | -0.281 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
profit | +0.971 |
arcity | +0.940 |
ailability | +0.939 |
peril | +0.893 |
ides | +0.887 |
Neg logit contributions | |
Probe | -1.289 |
Ba | -1.285 |
Instrument | -1.284 |
coord | -1.278 |
Asuka | -1.265 |
Token | This |
Token ID | 770 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
coord | +0.125 |
Ba | +0.124 |
Probe | +0.123 |
Instrument | +0.123 |
Asuka | +0.122 |
Neg logit contributions | |
profit | -0.127 |
arcity | -0.124 |
ailability | -0.122 |
ides | -0.118 |
secure | -0.117 |
Token | shows |
Token ID | 2523 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
profit | +0.287 |
arcity | +0.281 |
ailability | +0.280 |
peril | +0.271 |
ides | +0.268 |
Neg logit contributions | |
Ba | -0.272 |
Probe | -0.270 |
Instrument | -0.269 |
Asuka | -0.266 |
coord | -0.266 |
Token | that |
Token ID | 326 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
Ba | +0.061 |
Probe | +0.061 |
Instrument | +0.060 |
coord | +0.060 |
Asuka | +0.060 |
Neg logit contributions | |
profit | -0.050 |
ailability | -0.049 |
arcity | -0.049 |
peril | -0.046 |
ides | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
profit | +0.407 |
arcity | +0.399 |
ailability | +0.395 |
peril | +0.382 |
ides | +0.380 |
Neg logit contributions | |
Ba | -0.455 |
Probe | -0.451 |
Instrument | -0.451 |
coord | -0.445 |
Asuka | -0.445 |
Token | ex |
Token ID | 409 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
Ba | +0.558 |
Probe | +0.555 |
Instrument | +0.553 |
coord | +0.549 |
Asuka | +0.548 |
Neg logit contributions | |
profit | -0.528 |
ailability | -0.522 |
arcity | -0.517 |
peril | -0.488 |
ides | -0.487 |
Token | oplan |
Token ID | 46853 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Ba | +5.706 |
Probe | +5.693 |
Asuka | +5.625 |
coord | +5.618 |
Instrument | +5.605 |
Neg logit contributions | |
ailability | -2.260 |
arcity | -2.111 |
profit | -2.085 |
secure | -1.896 |
ð | -1.825 |
Token | et |
Token ID | 316 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
profit | +1.265 |
arcity | +1.226 |
ailability | +1.210 |
ides | +1.176 |
secure | +1.134 |
Neg logit contributions | |
Instrument | -1.852 |
Ba | -1.846 |
Probe | -1.844 |
Asuka | -1.830 |
coord | -1.826 |
Token | must |
Token ID | 1276 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Ba | +1.028 |
Probe | +1.026 |
Instrument | +1.022 |
coord | +1.013 |
Asuka | +1.011 |
Neg logit contributions | |
profit | -1.080 |
ailability | -1.074 |
arcity | -1.062 |
secure | -1.003 |
peril | -1.000 |
Token | have |
Token ID | 423 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
profit | +0.211 |
ailability | +0.209 |
arcity | +0.207 |
secure | +0.194 |
ides | +0.194 |
Neg logit contributions | |
Probe | -0.244 |
Ba | -0.244 |
Instrument | -0.243 |
coord | -0.240 |
Asuka | -0.240 |
Token | a |
Token ID | 257 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Probe | +0.724 |
Ba | +0.724 |
Instrument | +0.720 |
coord | +0.716 |
Asuka | +0.715 |
Neg logit contributions | |
profit | -0.662 |
ailability | -0.662 |
arcity | -0.652 |
secure | -0.612 |
paren | -0.611 |
Token | Photos |
Token ID | 21197 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Probe | +0.159 |
Instrument | +0.157 |
coord | +0.157 |
Ba | +0.156 |
Asuka | +0.156 |
Neg logit contributions | |
profit | -0.141 |
ailability | -0.138 |
arcity | -0.137 |
secure | -0.131 |
paren | -0.130 |
Token | courtesy |
Token ID | 12537 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
Probe | +0.124 |
Ba | +0.123 |
Instrument | +0.123 |
coord | +0.122 |
Asuka | +0.122 |
Neg logit contributions | |
profit | -0.110 |
ailability | -0.108 |
arcity | -0.108 |
ides | -0.102 |
secure | -0.101 |
Token | of |
Token ID | 286 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
profit | +0.211 |
ailability | +0.210 |
arcity | +0.206 |
secure | +0.191 |
paren | +0.191 |
Neg logit contributions | |
Probe | -0.323 |
Ba | -0.322 |
Instrument | -0.321 |
coord | -0.319 |
Asuka | -0.318 |
Token | © |
Token ID | 10673 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Ba | +0.046 |
Probe | +0.046 |
Instrument | +0.045 |
coord | +0.045 |
Asuka | +0.045 |
Neg logit contributions | |
profit | -0.049 |
ailability | -0.048 |
arcity | -0.048 |
secure | -0.045 |
ides | -0.045 |
Token | K |
Token ID | 42 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
profit | +0.628 |
ailability | +0.620 |
arcity | +0.617 |
secure | +0.585 |
ides | +0.582 |
Neg logit contributions | |
Probe | -0.602 |
Ba | -0.598 |
Instrument | -0.598 |
coord | -0.596 |
Asuka | -0.592 |
Token | elli |
Token ID | 23225 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
Ba | +2.313 |
Probe | +2.282 |
Instrument | +2.272 |
Asuka | +2.253 |
coord | +2.249 |
Neg logit contributions | |
ailability | -2.671 |
profit | -2.652 |
arcity | -2.609 |
peril | -2.484 |
secure | -2.484 |
Token | ( |
Token ID | 357 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Ba | +4.023 |
Probe | +3.951 |
Asuka | +3.912 |
Instrument | +3.906 |
Amp | +3.835 |
Neg logit contributions | |
ailability | -3.922 |
profit | -3.833 |
arcity | -3.797 |
paren | -3.575 |
peril | -3.554 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Ba | +1.214 |
Probe | +1.214 |
Instrument | +1.207 |
coord | +1.198 |
Asuka | +1.197 |
Neg logit contributions | |
profit | -1.189 |
ailability | -1.187 |
arcity | -1.171 |
secure | -1.102 |
paren | -1.099 |
Token | ickr |
Token ID | 18994 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Probe | +0.832 |
Ba | +0.829 |
Instrument | +0.827 |
Asuka | +0.819 |
coord | +0.819 |
Neg logit contributions | |
profit | -0.745 |
ailability | -0.738 |
arcity | -0.737 |
secure | -0.690 |
ides | -0.690 |
Token | : |
Token ID | 25 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Ba | +0.809 |
Probe | +0.808 |
Instrument | +0.807 |
Asuka | +0.803 |
coord | +0.800 |
Neg logit contributions | |
ailability | -0.801 |
profit | -0.798 |
arcity | -0.786 |
secure | -0.739 |
paren | -0.739 |
Token | brow |
Token ID | 4772 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Probe | +1.044 |
Ba | +1.043 |
Instrument | +1.037 |
coord | +1.029 |
Asuka | +1.028 |
Neg logit contributions | |
profit | -1.117 |
ailability | -1.115 |
arcity | -1.100 |
secure | -1.040 |
paren | -1.037 |
Token | O |
Token ID | 440 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
profit | +0.015 |
arcity | +0.015 |
ailability | +0.014 |
ides | +0.014 |
secure | +0.014 |
Neg logit contributions | |
coord | -0.010 |
Ba | -0.010 |
Probe | -0.010 |
Instrument | -0.010 |
Asuka | -0.010 |
Token | & |
Token ID | 5 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Probe | +0.808 |
Ba | +0.804 |
Instrument | +0.803 |
coord | +0.801 |
Asuka | +0.799 |
Neg logit contributions | |
profit | -0.404 |
ailability | -0.394 |
arcity | -0.392 |
secure | -0.360 |
ides | -0.358 |
Token | A |
Token ID | 32 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
coord | +0.035 |
Probe | +0.035 |
Instrument | +0.034 |
Asuka | +0.034 |
Ba | +0.033 |
Neg logit contributions | |
profit | -0.037 |
arcity | -0.035 |
ailability | -0.034 |
secure | -0.034 |
ides | -0.034 |
Token | - |
Token ID | 12 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
coord | +0.059 |
Probe | +0.058 |
Ba | +0.058 |
Asuka | +0.057 |
Instrument | +0.057 |
Neg logit contributions | |
profit | -0.066 |
arcity | -0.064 |
ides | -0.062 |
secure | -0.062 |
ð | -0.062 |
Token | C |
Token ID | 34 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
Probe | +0.559 |
coord | +0.555 |
Instrument | +0.555 |
Ba | +0.553 |
Asuka | +0.552 |
Neg logit contributions | |
profit | -0.608 |
ailability | -0.596 |
arcity | -0.593 |
secure | -0.566 |
ides | -0.564 |
Token | left |
Token ID | 9464 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
Probe | +0.035 |
Instrument | +0.035 |
Ba | +0.035 |
coord | +0.035 |
Asuka | +0.035 |
Neg logit contributions | |
profit | -0.034 |
ailability | -0.034 |
arcity | -0.034 |
ides | -0.032 |
secure | -0.032 |
Token | Pal |
Token ID | 3175 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Probe | +3.842 |
Ba | +3.821 |
Instrument | +3.800 |
Asuka | +3.765 |
coord | +3.719 |
Neg logit contributions | |
ailability | -4.052 |
profit | -3.932 |
arcity | -3.891 |
secure | -3.674 |
peril | -3.670 |
Token | let |
Token ID | 1616 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
profit | +0.262 |
arcity | +0.258 |
ailability | +0.256 |
secure | +0.245 |
ides | +0.244 |
Neg logit contributions | |
Ba | -0.230 |
Probe | -0.229 |
coord | -0.229 |
Instrument | -0.228 |
Asuka | -0.227 |
Token | Ads |
Token ID | 47442 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Probe | +2.499 |
Ba | +2.482 |
Instrument | +2.481 |
Asuka | +2.447 |
coord | +2.432 |
Neg logit contributions | |
ailability | -3.062 |
profit | -3.028 |
arcity | -2.994 |
paren | -2.838 |
peril | -2.824 |
Token | - |
Token ID | 12 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Probe | +1.881 |
Ba | +1.880 |
Instrument | +1.870 |
Asuka | +1.848 |
coord | +1.839 |
Neg logit contributions | |
ailability | -2.429 |
profit | -2.419 |
arcity | -2.385 |
peril | -2.264 |
secure | -2.264 |
Token | He |
Token ID | 1544 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Probe | +0.724 |
Instrument | +0.719 |
Ba | +0.718 |
coord | +0.717 |
Asuka | +0.714 |
Neg logit contributions | |
profit | -0.722 |
ailability | -0.712 |
arcity | -0.706 |
secure | -0.670 |
ides | -0.667 |
Token | details |
Token ID | 3307 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Ba | +0.913 |
Probe | +0.909 |
Instrument | +0.903 |
coord | +0.897 |
Asuka | +0.894 |
Neg logit contributions | |
profit | -0.730 |
ailability | -0.720 |
arcity | -0.711 |
ides | -0.675 |
secure | -0.673 |
Token | below |
Token ID | 2174 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Probe | +2.273 |
Instrument | +2.264 |
Ba | +2.263 |
Asuka | +2.253 |
coord | +2.229 |
Neg logit contributions | |
ailability | -2.141 |
profit | -2.110 |
arcity | -2.102 |
paren | -1.957 |
secure | -1.940 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
profit | +1.014 |
ailability | +0.996 |
arcity | +0.985 |
ides | +0.936 |
secure | +0.926 |
Neg logit contributions | |
Probe | -1.402 |
Ba | -1.402 |
Instrument | -1.389 |
coord | -1.388 |
Asuka | -1.378 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Ba | +0.156 |
coord | +0.156 |
Probe | +0.156 |
Instrument | +0.153 |
Asuka | +0.152 |
Neg logit contributions | |
profit | -0.164 |
ailability | -0.160 |
arcity | -0.160 |
secure | -0.153 |
ides | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
Probe | +0.879 |
Ba | +0.879 |
Instrument | +0.874 |
coord | +0.866 |
Asuka | +0.865 |
Neg logit contributions | |
profit | -1.027 |
ailability | -1.026 |
arcity | -1.012 |
secure | -0.958 |
paren | -0.956 |
Token | ■ |
Token ID | 29316 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
Probe | +0.645 |
Ba | +0.643 |
Instrument | +0.641 |
coord | +0.637 |
Asuka | +0.636 |
Neg logit contributions | |
profit | -0.639 |
ailability | -0.634 |
arcity | -0.626 |
secure | -0.593 |
paren | -0.590 |
Token | Opening |
Token ID | 25522 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
Instrument | +3.619 |
Probe | +3.596 |
Ba | +3.592 |
Asuka | +3.570 |
Amp | +3.478 |
Neg logit contributions | |
ailability | -4.323 |
arcity | -4.250 |
profit | -4.233 |
paren | -3.982 |
peril | -3.959 |
Token | Theme |
Token ID | 26729 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Probe | +2.473 |
Ba | +2.466 |
Instrument | +2.464 |
Asuka | +2.438 |
coord | +2.437 |
Neg logit contributions | |
ailability | -2.905 |
profit | -2.898 |
arcity | -2.864 |
secure | -2.705 |
paren | -2.701 |
Token | Movie |
Token ID | 15875 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Probe | +1.679 |
Ba | +1.678 |
Instrument | +1.670 |
coord | +1.657 |
Asuka | +1.655 |
Neg logit contributions | |
profit | -1.685 |
ailability | -1.682 |
arcity | -1.659 |
secure | -1.564 |
paren | -1.559 |
Token | The |
Token ID | 383 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Probe | +1.551 |
Ba | +1.550 |
Instrument | +1.543 |
coord | +1.529 |
Asuka | +1.528 |
Neg logit contributions | |
profit | -1.809 |
ailability | -1.808 |
arcity | -1.784 |
secure | -1.688 |
paren | -1.684 |
Token | opening |
Token ID | 4756 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
Ba | +0.066 |
Probe | +0.066 |
coord | +0.065 |
Instrument | +0.065 |
Asuka | +0.065 |
Neg logit contributions | |
profit | -0.077 |
ailability | -0.076 |
arcity | -0.075 |
secure | -0.071 |
ides | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
profit | +0.433 |
ailability | +0.431 |
arcity | +0.425 |
secure | +0.398 |
paren | +0.397 |
Neg logit contributions | |
Probe | -0.554 |
Ba | -0.554 |
Instrument | -0.551 |
coord | -0.548 |
Asuka | -0.547 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
profit | +0.403 |
ailability | +0.393 |
arcity | +0.392 |
secure | +0.373 |
paren | +0.371 |
Neg logit contributions | |
coord | -0.401 |
Probe | -0.401 |
Ba | -0.400 |
Instrument | -0.395 |
Asuka | -0.395 |
Token | S |
Token ID | 50 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Probe | +0.513 |
Ba | +0.511 |
Instrument | +0.510 |
coord | +0.506 |
Asuka | +0.506 |
Neg logit contributions | |
profit | -0.458 |
ailability | -0.456 |
arcity | -0.450 |
secure | -0.423 |
paren | -0.422 |
Token | AC |
Token ID | 2246 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Probe | +0.374 |
Ba | +0.373 |
Instrument | +0.372 |
coord | +0.369 |
Asuka | +0.368 |
Neg logit contributions | |
profit | -0.355 |
ailability | -0.354 |
arcity | -0.349 |
secure | -0.329 |
ides | -0.328 |
Token | RAM |
Token ID | 24115 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Ba | +0.723 |
Probe | +0.723 |
Instrument | +0.720 |
Asuka | +0.714 |
coord | +0.713 |
Neg logit contributions | |
profit | -0.724 |
ailability | -0.721 |
arcity | -0.713 |
secure | -0.672 |
paren | -0.670 |
Token | ENT |
Token ID | 3525 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
Ba | +1.550 |
Probe | +1.545 |
Instrument | +1.543 |
coord | +1.532 |
Asuka | +1.529 |
Neg logit contributions | |
ailability | -1.249 |
profit | -1.246 |
arcity | -1.223 |
secure | -1.142 |
paren | -1.138 |
Token | O |
Token ID | 46 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Ba | +2.428 |
Asuka | +2.394 |
Instrument | +2.360 |
coord | +2.335 |
Amp | +2.290 |
Neg logit contributions | |
ailability | -5.458 |
arcity | -5.342 |
profit | -5.222 |
paren | -5.208 |
ð | -5.040 |
Token | — |
Token ID | 851 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Ba | +0.945 |
Probe | +0.943 |
Instrument | +0.937 |
coord | +0.935 |
Asuka | +0.931 |
Neg logit contributions | |
profit | -0.847 |
ailability | -0.839 |
arcity | -0.833 |
ides | -0.784 |
secure | -0.783 |
Token | Thousands |
Token ID | 30405 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Ba | +1.109 |
Probe | +1.108 |
Instrument | +1.102 |
coord | +1.097 |
Asuka | +1.092 |
Neg logit contributions | |
profit | -1.097 |
ailability | -1.090 |
arcity | -1.079 |
secure | -1.017 |
paren | -1.014 |
Token | of |
Token ID | 286 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Ba | +1.940 |
Probe | +1.935 |
Instrument | +1.931 |
coord | +1.915 |
Asuka | +1.913 |
Neg logit contributions | |
ailability | -1.319 |
profit | -1.300 |
arcity | -1.287 |
paren | -1.212 |
secure | -1.188 |
Token | students |
Token ID | 2444 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
Ba | +0.407 |
Probe | +0.405 |
Instrument | +0.403 |
coord | +0.401 |
Asuka | +0.399 |
Neg logit contributions | |
profit | -0.364 |
ailability | -0.358 |
arcity | -0.356 |
peril | -0.337 |
secure | -0.336 |
Token | ," |
Token ID | 553 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Probe | +1.604 |
Instrument | +1.601 |
Ba | +1.601 |
coord | +1.592 |
Asuka | +1.591 |
Neg logit contributions | |
ailability | -1.251 |
profit | -1.243 |
arcity | -1.224 |
paren | -1.140 |
secure | -1.134 |
Token | he |
Token ID | 339 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Probe | +0.214 |
Ba | +0.214 |
Instrument | +0.213 |
coord | +0.212 |
Asuka | +0.211 |
Neg logit contributions | |
profit | -0.177 |
ailability | -0.177 |
arcity | -0.174 |
secure | -0.163 |
paren | -0.163 |
Token | said |
Token ID | 531 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
Probe | +0.212 |
Ba | +0.212 |
Instrument | +0.211 |
coord | +0.209 |
Asuka | +0.209 |
Neg logit contributions | |
profit | -0.262 |
ailability | -0.262 |
arcity | -0.258 |
secure | -0.245 |
paren | -0.244 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Ba | +0.714 |
Probe | +0.713 |
Instrument | +0.710 |
coord | +0.704 |
Asuka | +0.704 |
Neg logit contributions | |
ailability | -0.529 |
profit | -0.528 |
arcity | -0.516 |
secure | -0.483 |
paren | -0.482 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
Ba | +0.096 |
Probe | +0.096 |
Instrument | +0.096 |
coord | +0.096 |
Asuka | +0.095 |
Neg logit contributions | |
profit | -0.103 |
ailability | -0.102 |
arcity | -0.101 |
secure | -0.096 |
ides | -0.095 |
Token | Meg |
Token ID | 42672 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
Probe | +0.641 |
Ba | +0.641 |
Instrument | +0.638 |
coord | +0.633 |
Asuka | +0.633 |
Neg logit contributions | |
profit | -0.572 |
ailability | -0.571 |
arcity | -0.562 |
secure | -0.529 |
paren | -0.527 |
Token | ach |
Token ID | 620 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Probe | +3.696 |
Ba | +3.683 |
Instrument | +3.637 |
Asuka | +3.632 |
Amp | +3.568 |
Neg logit contributions | |
ailability | -3.955 |
profit | -3.921 |
arcity | -3.869 |
paren | -3.680 |
secure | -3.655 |
Token | urch |
Token ID | 2575 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Probe | +1.237 |
Ba | +1.233 |
Instrument | +1.226 |
Asuka | +1.216 |
coord | +1.209 |
Neg logit contributions | |
ailability | -1.574 |
profit | -1.566 |
arcity | -1.546 |
secure | -1.472 |
paren | -1.472 |
Token | founder |
Token ID | 9119 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Probe | +1.247 |
Ba | +1.246 |
Instrument | +1.240 |
coord | +1.230 |
Asuka | +1.229 |
Neg logit contributions | |
profit | -1.322 |
ailability | -1.319 |
arcity | -1.302 |
secure | -1.229 |
paren | -1.226 |
Token | Rev |
Token ID | 5416 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
profit | +0.401 |
ailability | +0.394 |
arcity | +0.392 |
ides | +0.372 |
peril | +0.371 |
Neg logit contributions | |
Ba | -0.441 |
Probe | -0.437 |
Instrument | -0.436 |
coord | -0.435 |
Asuka | -0.430 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
profit | +1.386 |
ailability | +1.363 |
arcity | +1.363 |
ides | +1.289 |
secure | +1.277 |
Neg logit contributions | |
Probe | -1.471 |
coord | -1.467 |
Instrument | -1.457 |
Ba | -1.455 |
Asuka | -1.446 |
Token | of |
Token ID | 286 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Instrument | +1.064 |
Ba | +1.063 |
Probe | +1.063 |
Asuka | +1.059 |
coord | +1.053 |
Neg logit contributions | |
ailability | -0.849 |
profit | -0.838 |
arcity | -0.830 |
secure | -0.770 |
paren | -0.768 |
Token | meat |
Token ID | 6174 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
Ba | +0.218 |
Probe | +0.217 |
Instrument | +0.215 |
coord | +0.214 |
Asuka | +0.212 |
Neg logit contributions | |
profit | -0.225 |
ailability | -0.222 |
arcity | -0.220 |
peril | -0.211 |
ides | -0.209 |
Token | from |
Token ID | 422 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
profit | +0.343 |
ailability | +0.340 |
arcity | +0.336 |
ides | +0.317 |
secure | +0.317 |
Neg logit contributions | |
Probe | -0.401 |
Ba | -0.401 |
Instrument | -0.399 |
coord | -0.397 |
Asuka | -0.395 |
Token | grocery |
Token ID | 16918 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
profit | +0.302 |
ailability | +0.299 |
arcity | +0.297 |
peril | +0.283 |
ides | +0.283 |
Neg logit contributions | |
Ba | -0.310 |
Probe | -0.310 |
Instrument | -0.308 |
coord | -0.307 |
Asuka | -0.304 |
Token | - |
Token ID | 12 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Probe | +1.456 |
Ba | +1.455 |
Instrument | +1.445 |
coord | +1.443 |
Asuka | +1.435 |
Neg logit contributions | |
ailability | -1.602 |
profit | -1.588 |
arcity | -1.573 |
secure | -1.479 |
paren | -1.477 |
Token | store |
Token ID | 8095 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
Ba | +1.032 |
Probe | +1.028 |
Instrument | +1.021 |
coord | +1.013 |
Asuka | +1.010 |
Neg logit contributions | |
ailability | -1.395 |
profit | -1.389 |
arcity | -1.377 |
paren | -1.302 |
secure | -1.302 |
Token | fl |
Token ID | 781 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
Probe | +3.138 |
Instrument | +3.127 |
coord | +3.110 |
Ba | +3.106 |
Asuka | +3.101 |
Neg logit contributions | |
ailability | -4.529 |
profit | -4.441 |
arcity | -4.420 |
secure | -4.165 |
vernment | -4.150 |
Token | iers |
Token ID | 3183 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
Probe | +0.050 |
Ba | +0.050 |
Instrument | +0.050 |
Asuka | +0.050 |
coord | +0.050 |
Neg logit contributions | |
profit | -0.037 |
arcity | -0.037 |
ailability | -0.037 |
ides | -0.035 |
secure | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
profit | +0.571 |
ailability | +0.565 |
arcity | +0.558 |
ides | +0.525 |
secure | +0.524 |
Neg logit contributions | |
Ba | -0.750 |
Probe | -0.750 |
Instrument | -0.745 |
coord | -0.741 |
Asuka | -0.738 |
Token | then |
Token ID | 788 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Ba | +0.020 |
Probe | +0.020 |
Instrument | +0.020 |
coord | +0.019 |
Asuka | +0.019 |
Neg logit contributions | |
profit | -0.018 |
ailability | -0.018 |
arcity | -0.018 |
peril | -0.017 |
ides | -0.017 |
Token | paste |
Token ID | 17008 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
profit | +0.134 |
ailability | +0.132 |
arcity | +0.131 |
peril | +0.125 |
ides | +0.124 |
Neg logit contributions | |
Ba | -0.148 |
Probe | -0.147 |
Instrument | -0.146 |
coord | -0.145 |
Asuka | -0.145 |
Token | appearing |
Token ID | 12655 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Probe | +2.527 |
Ba | +2.525 |
Instrument | +2.513 |
Asuka | +2.483 |
coord | +2.477 |
Neg logit contributions | |
ailability | -2.528 |
profit | -2.499 |
arcity | -2.464 |
paren | -2.323 |
secure | -2.311 |
Token | for |
Token ID | 329 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Ba | +1.334 |
Probe | +1.332 |
Instrument | +1.326 |
Asuka | +1.315 |
coord | +1.314 |
Neg logit contributions | |
ailability | -1.579 |
profit | -1.576 |
arcity | -1.554 |
paren | -1.468 |
secure | -1.467 |
Token | Gh |
Token ID | 11972 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
Probe | +1.091 |
Ba | +1.091 |
Instrument | +1.084 |
coord | +1.076 |
Asuka | +1.075 |
Neg logit contributions | |
profit | -1.245 |
ailability | -1.242 |
arcity | -1.227 |
secure | -1.161 |
paren | -1.157 |
Token | ai |
Token ID | 1872 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Ba | +2.523 |
Probe | +2.462 |
Instrument | +2.450 |
Asuka | +2.413 |
coord | +2.410 |
Neg logit contributions | |
ailability | -2.361 |
profit | -2.225 |
arcity | -2.180 |
peril | -2.073 |
paren | -2.073 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Probe | +1.666 |
Ba | +1.660 |
Instrument | +1.654 |
coord | +1.638 |
Asuka | +1.636 |
Neg logit contributions | |
ailability | -1.701 |
profit | -1.691 |
arcity | -1.669 |
paren | -1.572 |
secure | -1.570 |
Token | pleaded |
Token ID | 16407 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
Ba | +0.911 |
Probe | +0.911 |
Instrument | +0.906 |
coord | +0.899 |
Asuka | +0.897 |
Neg logit contributions | |
profit | -0.888 |
ailability | -0.884 |
arcity | -0.873 |
secure | -0.823 |
ides | -0.820 |
Token | that |
Token ID | 326 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Ba | +3.627 |
Probe | +3.625 |
Instrument | +3.622 |
coord | +3.602 |
Asuka | +3.577 |
Neg logit contributions | |
ailability | -4.050 |
profit | -4.024 |
arcity | -3.920 |
paren | -3.721 |
secure | -3.686 |
Token | more |
Token ID | 517 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Ba | +0.945 |
Probe | +0.944 |
Instrument | +0.939 |
Asuka | +0.932 |
coord | +0.932 |
Neg logit contributions | |
profit | -0.921 |
ailability | -0.915 |
arcity | -0.907 |
secure | -0.855 |
ides | -0.851 |
Token | than |
Token ID | 621 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Probe | +1.476 |
Ba | +1.474 |
Instrument | +1.466 |
coord | +1.458 |
Asuka | +1.452 |
Neg logit contributions | |
ailability | -1.430 |
profit | -1.426 |
arcity | -1.407 |
secure | -1.320 |
paren | -1.317 |
Token | Rs |
Token ID | 12820 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Ba | +0.086 |
Probe | +0.085 |
Instrument | +0.085 |
coord | +0.084 |
Asuka | +0.084 |
Neg logit contributions | |
profit | -0.079 |
ailability | -0.077 |
arcity | -0.077 |
peril | -0.073 |
ides | -0.073 |
Token | 50 |
Token ID | 2026 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
Probe | +1.080 |
Ba | +1.080 |
Instrument | +1.074 |
coord | +1.068 |
Asuka | +1.066 |
Neg logit contributions | |
profit | -1.049 |
ailability | -1.043 |
arcity | -1.031 |
secure | -0.971 |
paren | -0.968 |
Token | Japan |
Token ID | 2869 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
profit | +0.958 |
arcity | +0.927 |
ailability | +0.918 |
peril | +0.881 |
ides | +0.877 |
Neg logit contributions | |
Ba | -1.004 |
Probe | -0.992 |
Instrument | -0.981 |
bats | -0.972 |
coord | -0.971 |
Token | steering |
Token ID | 19702 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Ba | +0.464 |
Probe | +0.462 |
Instrument | +0.459 |
Asuka | +0.455 |
coord | +0.454 |
Neg logit contributions | |
profit | -0.455 |
ailability | -0.447 |
arcity | -0.444 |
ides | -0.420 |
secure | -0.420 |
Token | committee |
Token ID | 5583 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
profit | +0.788 |
arcity | +0.767 |
ailability | +0.765 |
peril | +0.725 |
ides | +0.725 |
Neg logit contributions | |
Probe | -0.887 |
Ba | -0.885 |
Instrument | -0.877 |
Asuka | -0.872 |
coord | -0.867 |
Token | chairman |
Token ID | 8900 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Ba | +0.046 |
Probe | +0.046 |
Instrument | +0.046 |
coord | +0.045 |
Asuka | +0.045 |
Neg logit contributions | |
profit | -0.039 |
ailability | -0.038 |
arcity | -0.038 |
ides | -0.036 |
peril | -0.036 |
Token | Kan |
Token ID | 14248 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Probe | +1.549 |
Ba | +1.545 |
Instrument | +1.541 |
Asuka | +1.530 |
coord | +1.524 |
Neg logit contributions | |
ailability | -1.782 |
profit | -1.775 |
arcity | -1.753 |
secure | -1.657 |
paren | -1.655 |
Token | ek |
Token ID | 988 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
Ba | +1.837 |
Probe | +1.830 |
Instrument | +1.819 |
Asuka | +1.813 |
coord | +1.796 |
Neg logit contributions | |
ailability | -1.831 |
profit | -1.819 |
arcity | -1.794 |
secure | -1.687 |
paren | -1.684 |
Token | o |
Token ID | 78 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Asuka | +4.026 |
Ba | +3.996 |
Probe | +3.991 |
Instrument | +3.983 |
coord | +3.892 |
Neg logit contributions | |
ailability | -3.670 |
profit | -3.558 |
arcity | -3.544 |
paren | -3.311 |
secure | -3.290 |
Token | " |
Token ID | 366 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
Ba | +2.017 |
Probe | +2.013 |
Instrument | +2.002 |
Asuka | +2.001 |
coord | +1.971 |
Neg logit contributions | |
ailability | -2.359 |
profit | -2.335 |
arcity | -2.316 |
paren | -2.192 |
secure | -2.181 |
Token | H |
Token ID | 39 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Ba | +0.602 |
Probe | +0.602 |
Instrument | +0.598 |
coord | +0.594 |
Asuka | +0.593 |
Neg logit contributions | |
profit | -0.662 |
ailability | -0.662 |
arcity | -0.653 |
secure | -0.617 |
paren | -0.615 |
Token | ame |
Token ID | 480 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
profit | +0.173 |
arcity | +0.171 |
ailability | +0.171 |
ides | +0.162 |
secure | +0.161 |
Neg logit contributions | |
Probe | -0.167 |
Instrument | -0.165 |
Ba | -0.164 |
coord | -0.164 |
Asuka | -0.164 |
Token | ko |
Token ID | 7204 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Probe | +0.235 |
Instrument | +0.234 |
Ba | +0.233 |
coord | +0.233 |
Asuka | +0.232 |
Neg logit contributions | |
profit | -0.235 |
ailability | -0.232 |
arcity | -0.230 |
secure | -0.218 |
ides | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Probe | +0.127 |
Ba | +0.127 |
Instrument | +0.127 |
coord | +0.126 |
Asuka | +0.126 |
Neg logit contributions | |
profit | -0.090 |
ailability | -0.090 |
arcity | -0.089 |
secure | -0.083 |
ides | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Ba | +0.213 |
coord | +0.213 |
Probe | +0.213 |
Instrument | +0.211 |
Asuka | +0.210 |
Neg logit contributions | |
profit | -0.228 |
arcity | -0.224 |
ailability | -0.222 |
secure | -0.212 |
ides | -0.211 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Probe | +0.470 |
Ba | +0.467 |
Instrument | +0.466 |
coord | +0.466 |
Asuka | +0.462 |
Neg logit contributions | |
profit | -0.529 |
arcity | -0.518 |
ailability | -0.516 |
secure | -0.493 |
ides | -0.491 |
Token | R |
Token ID | 49 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
Probe | +0.139 |
Instrument | +0.137 |
coord | +0.137 |
Asuka | +0.137 |
Ba | +0.137 |
Neg logit contributions | |
profit | -0.124 |
ailability | -0.121 |
arcity | -0.120 |
secure | -0.114 |
paren | -0.114 |
Token | S |
Token ID | 311 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Probe | +0.638 |
Instrument | +0.633 |
Ba | +0.632 |
coord | +0.626 |
Asuka | +0.625 |
Neg logit contributions | |
profit | -0.643 |
ailability | -0.640 |
arcity | -0.634 |
ides | -0.602 |
secure | -0.596 |
Token | enth |
Token ID | 7944 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Probe | +0.883 |
Ba | +0.882 |
Instrument | +0.878 |
Asuka | +0.871 |
coord | +0.869 |
Neg logit contributions | |
profit | -0.967 |
ailability | -0.967 |
arcity | -0.952 |
secure | -0.900 |
paren | -0.900 |
Token | il |
Token ID | 346 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Instrument | +3.831 |
Ba | +3.827 |
Probe | +3.825 |
Asuka | +3.773 |
coord | +3.739 |
Neg logit contributions | |
ailability | -3.798 |
profit | -3.677 |
arcity | -3.615 |
paren | -3.436 |
secure | -3.396 |
Token | Kumar |
Token ID | 26105 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Probe | +1.467 |
Ba | +1.467 |
Instrument | +1.458 |
coord | +1.449 |
Asuka | +1.444 |
Neg logit contributions | |
profit | -1.508 |
ailability | -1.498 |
arcity | -1.485 |
ides | -1.404 |
secure | -1.402 |
Token | / |
Token ID | 14 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Probe | +1.213 |
Ba | +1.213 |
Instrument | +1.206 |
coord | +1.198 |
Asuka | +1.196 |
Neg logit contributions | |
profit | -1.189 |
ailability | -1.185 |
arcity | -1.170 |
secure | -1.103 |
paren | -1.099 |
Token | Press |
Token ID | 13800 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Probe | +0.804 |
Ba | +0.803 |
Instrument | +0.800 |
coord | +0.794 |
Asuka | +0.793 |
Neg logit contributions | |
profit | -0.728 |
ailability | -0.725 |
arcity | -0.716 |
secure | -0.674 |
paren | -0.671 |
Token | Trust |
Token ID | 9870 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Ba | +0.376 |
Probe | +0.375 |
Instrument | +0.373 |
coord | +0.372 |
Asuka | +0.371 |
Neg logit contributions | |
profit | -0.257 |
ailability | -0.256 |
arcity | -0.253 |
secure | -0.235 |
paren | -0.234 |
Token | action |
Token ID | 2223 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Ba | +0.523 |
Probe | +0.522 |
Instrument | +0.519 |
Asuka | +0.517 |
coord | +0.515 |
Neg logit contributions | |
profit | -0.386 |
ailability | -0.382 |
arcity | -0.376 |
secure | -0.352 |
ides | -0.352 |
Token | was |
Token ID | 373 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Probe | +0.633 |
Ba | +0.632 |
Instrument | +0.628 |
coord | +0.623 |
Asuka | +0.622 |
Neg logit contributions | |
profit | -0.812 |
ailability | -0.809 |
arcity | -0.800 |
secure | -0.760 |
paren | -0.758 |
Token | taken |
Token ID | 2077 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Probe | +1.083 |
Ba | +1.079 |
Instrument | +1.074 |
coord | +1.067 |
Asuka | +1.063 |
Neg logit contributions | |
ailability | -1.391 |
profit | -1.386 |
arcity | -1.371 |
paren | -1.297 |
secure | -1.296 |
Token | against |
Token ID | 1028 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Ba | +0.122 |
Probe | +0.121 |
Instrument | +0.121 |
coord | +0.120 |
Asuka | +0.120 |
Neg logit contributions | |
profit | -0.124 |
ailability | -0.123 |
arcity | -0.122 |
secure | -0.115 |
ides | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Ba | +0.853 |
Probe | +0.847 |
Instrument | +0.843 |
coord | +0.841 |
Asuka | +0.839 |
Neg logit contributions | |
profit | -0.880 |
ailability | -0.864 |
arcity | -0.860 |
peril | -0.819 |
ides | -0.818 |
Token | accused |
Token ID | 5371 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Ba | +0.763 |
Probe | +0.759 |
Instrument | +0.757 |
coord | +0.752 |
Asuka | +0.751 |
Neg logit contributions | |
profit | -0.692 |
ailability | -0.679 |
arcity | -0.674 |
ides | -0.640 |
peril | -0.637 |
Token | for |
Token ID | 329 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Probe | +4.057 |
Ba | +4.038 |
Instrument | +4.029 |
Asuka | +3.989 |
coord | +3.974 |
Neg logit contributions | |
ailability | -3.593 |
arcity | -3.488 |
profit | -3.485 |
paren | -3.267 |
secure | -3.240 |
Token | causing |
Token ID | 6666 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Ba | +0.666 |
Probe | +0.664 |
Instrument | +0.659 |
Asuka | +0.654 |
coord | +0.653 |
Neg logit contributions | |
profit | -0.705 |
ailability | -0.697 |
arcity | -0.692 |
peril | -0.657 |
ides | -0.656 |
Token | destruction |
Token ID | 8166 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Probe | +0.238 |
Ba | +0.237 |
Instrument | +0.236 |
coord | +0.234 |
Asuka | +0.234 |
Neg logit contributions | |
profit | -0.233 |
ailability | -0.232 |
arcity | -0.230 |
peril | -0.217 |
ides | -0.216 |
Token | to |
Token ID | 284 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Ba | +0.209 |
Probe | +0.209 |
Instrument | +0.208 |
Asuka | +0.207 |
coord | +0.206 |
Neg logit contributions | |
profit | -0.136 |
ailability | -0.136 |
arcity | -0.133 |
secure | -0.124 |
paren | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
profit | +0.246 |
ailability | +0.245 |
arcity | +0.242 |
peril | +0.231 |
ides | +0.230 |
Neg logit contributions | |
Probe | -0.246 |
Ba | -0.246 |
Instrument | -0.244 |
coord | -0.244 |
Asuka | -0.241 |
Token | 10 |
Token ID | 838 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
profit | +1.022 |
arcity | +0.997 |
ailability | +0.984 |
peril | +0.958 |
ides | +0.948 |
Neg logit contributions | |
Ba | -0.996 |
Instrument | -0.976 |
coord | -0.973 |
Probe | -0.972 |
Asuka | -0.967 |
Token | , |
Token ID | 11 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Ba | +0.474 |
Probe | +0.472 |
Instrument | +0.470 |
coord | +0.468 |
Asuka | +0.466 |
Neg logit contributions | |
profit | -0.476 |
ailability | -0.472 |
arcity | -0.469 |
secure | -0.441 |
ides | -0.440 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
profit | +0.643 |
arcity | +0.635 |
ailability | +0.632 |
ides | +0.599 |
secure | +0.598 |
Neg logit contributions | |
Ba | -0.558 |
Probe | -0.555 |
coord | -0.555 |
Instrument | -0.553 |
Asuka | -0.548 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
profit | +0.941 |
arcity | +0.923 |
ailability | +0.907 |
peril | +0.866 |
ides | +0.864 |
Neg logit contributions | |
Ba | -1.019 |
coord | -1.011 |
Instrument | -1.000 |
Probe | -1.000 |
Asuka | -0.995 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
profit | +1.072 |
arcity | +1.022 |
ides | +0.997 |
secure | +0.992 |
ð | +0.989 |
Neg logit contributions | |
coord | -1.096 |
Probe | -1.082 |
Instrument | -1.070 |
Asuka | -1.070 |
Ba | -1.063 |
Token | Pe |
Token ID | 6435 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
profit | +1.031 |
arcity | +0.986 |
ailability | +0.975 |
secure | +0.942 |
ides | +0.936 |
Neg logit contributions | |
Probe | -1.283 |
coord | -1.273 |
Instrument | -1.270 |
Asuka | -1.267 |
Ba | -1.248 |
Token | ak |
Token ID | 461 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
profit | +2.926 |
arcity | +2.920 |
ides | +2.760 |
ailability | +2.753 |
ð | +2.712 |
Neg logit contributions | |
Instrument | -2.946 |
Probe | -2.926 |
Asuka | -2.917 |
coord | -2.903 |
Ba | -2.847 |
Token | price |
Token ID | 2756 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Probe | +0.335 |
Ba | +0.333 |
Instrument | +0.332 |
coord | +0.329 |
Asuka | +0.329 |
Neg logit contributions | |
ailability | -0.302 |
profit | -0.300 |
arcity | -0.297 |
secure | -0.279 |
paren | -0.278 |
Token | : |
Token ID | 25 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
profit | +0.682 |
arcity | +0.665 |
ailability | +0.662 |
peril | +0.632 |
ides | +0.627 |
Neg logit contributions | |
Ba | -0.815 |
Probe | -0.810 |
Instrument | -0.808 |
Asuka | -0.800 |
coord | -0.800 |
Token | $ |
Token ID | 720 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Ba | +0.112 |
Probe | +0.111 |
Instrument | +0.111 |
coord | +0.110 |
Asuka | +0.110 |
Neg logit contributions | |
profit | -0.123 |
ailability | -0.122 |
arcity | -0.121 |
secure | -0.114 |
ides | -0.114 |
Token | 266 |
Token ID | 25540 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Probe | +0.693 |
Ba | +0.692 |
Instrument | +0.689 |
coord | +0.685 |
Asuka | +0.683 |
Neg logit contributions | |
profit | -0.801 |
ailability | -0.796 |
arcity | -0.788 |
secure | -0.747 |
paren | -0.745 |
Token | 155 |
Token ID | 18742 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
profit | +0.617 |
ailability | +0.614 |
arcity | +0.606 |
secure | +0.574 |
paren | +0.572 |
Neg logit contributions | |
Probe | -0.563 |
Ba | -0.562 |
Instrument | -0.559 |
coord | -0.555 |
Asuka | -0.554 |
Token | ] |
Token ID | 60 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Ba | +0.621 |
Probe | +0.619 |
Instrument | +0.618 |
Asuka | +0.613 |
coord | +0.609 |
Neg logit contributions | |
profit | -0.591 |
ailability | -0.591 |
arcity | -0.579 |
secure | -0.545 |
peril | -0.544 |
Token | An |
Token ID | 1052 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
profit | +0.184 |
arcity | +0.181 |
ailability | +0.181 |
secure | +0.171 |
ides | +0.171 |
Neg logit contributions | |
Ba | -0.172 |
Probe | -0.171 |
coord | -0.171 |
Instrument | -0.170 |
Asuka | -0.168 |
Token | ' |
Token ID | 705 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
profit | +0.227 |
ailability | +0.224 |
arcity | +0.223 |
secure | +0.209 |
ides | +0.209 |
Neg logit contributions | |
Ba | -0.229 |
Probe | -0.228 |
coord | -0.227 |
Instrument | -0.225 |
Asuka | -0.223 |
Token | inter |
Token ID | 3849 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
profit | +0.263 |
ailability | +0.259 |
arcity | +0.257 |
secure | +0.244 |
ides | +0.242 |
Neg logit contributions | |
Probe | -0.276 |
Instrument | -0.274 |
coord | -0.273 |
Ba | -0.273 |
Asuka | -0.272 |
Token | active |
Token ID | 5275 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
profit | +0.496 |
ailability | +0.486 |
arcity | +0.483 |
secure | +0.460 |
ides | +0.457 |
Neg logit contributions | |
Ba | -0.480 |
Probe | -0.478 |
Instrument | -0.476 |
Asuka | -0.475 |
coord | -0.474 |
Token | review |
Token ID | 2423 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
profit | +3.348 |
arcity | +3.216 |
ailability | +3.207 |
peril | +3.157 |
ides | +3.118 |
Neg logit contributions | |
Ba | -3.344 |
bats | -3.304 |
Probe | -3.273 |
coord | -3.262 |
Instrument | -3.261 |
Token | ' |
Token ID | 6 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
profit | +0.216 |
ailability | +0.214 |
arcity | +0.212 |
secure | +0.200 |
ides | +0.199 |
Neg logit contributions | |
Ba | -0.225 |
Probe | -0.224 |
Instrument | -0.223 |
coord | -0.222 |
Asuka | -0.221 |
Token | was |
Token ID | 373 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
profit | +0.632 |
ailability | +0.623 |
arcity | +0.616 |
secure | +0.581 |
ides | +0.579 |
Neg logit contributions | |
Ba | -0.690 |
Probe | -0.689 |
Instrument | -0.684 |
coord | -0.683 |
Asuka | -0.680 |
Token | created |
Token ID | 2727 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Probe | +0.327 |
Ba | +0.327 |
Instrument | +0.325 |
coord | +0.324 |
Asuka | +0.322 |
Neg logit contributions | |
profit | -0.297 |
ailability | -0.294 |
arcity | -0.291 |
secure | -0.274 |
ides | -0.273 |
Token | specially |
Token ID | 20905 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Probe | +0.109 |
Ba | +0.109 |
Instrument | +0.109 |
coord | +0.108 |
Asuka | +0.108 |
Neg logit contributions | |
ailability | -0.109 |
profit | -0.109 |
arcity | -0.107 |
secure | -0.101 |
paren | -0.101 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Probe | +0.969 |
Ba | +0.968 |
Instrument | +0.964 |
Asuka | +0.957 |
coord | +0.956 |
Neg logit contributions | |
ailability | -0.806 |
profit | -0.804 |
arcity | -0.791 |
secure | -0.740 |
paren | -0.739 |
Token | [ |
Token ID | 685 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
profit | +0.052 |
ailability | +0.051 |
arcity | +0.051 |
secure | +0.046 |
ides | +0.046 |
Neg logit contributions | |
Ba | -0.099 |
Probe | -0.099 |
Instrument | -0.098 |
coord | -0.098 |
Asuka | -0.098 |
Token | 13 |
Token ID | 1485 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
Probe | +0.234 |
Ba | +0.233 |
Instrument | +0.232 |
coord | +0.230 |
Asuka | +0.230 |
Neg logit contributions | |
profit | -0.284 |
ailability | -0.282 |
arcity | -0.279 |
secure | -0.265 |
paren | -0.264 |
Token | ]: |
Token ID | 5974 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Probe | +0.559 |
Ba | +0.559 |
Instrument | +0.557 |
Asuka | +0.552 |
coord | +0.551 |
Neg logit contributions | |
ailability | -0.508 |
profit | -0.508 |
arcity | -0.498 |
secure | -0.468 |
paren | -0.467 |
Token | 182 |
Token ID | 24294 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Probe | +0.331 |
Ba | +0.331 |
Instrument | +0.328 |
coord | +0.327 |
Asuka | +0.326 |
Neg logit contributions | |
profit | -0.368 |
ailability | -0.366 |
arcity | -0.362 |
secure | -0.343 |
ides | -0.341 |
Token | While |
Token ID | 2893 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Probe | +0.170 |
Ba | +0.170 |
Instrument | +0.169 |
coord | +0.168 |
Asuka | +0.168 |
Neg logit contributions | |
profit | -0.155 |
ailability | -0.155 |
arcity | -0.153 |
secure | -0.144 |
paren | -0.143 |
Token | Cob |
Token ID | 14828 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
profit | +2.712 |
arcity | +2.622 |
ailability | +2.605 |
ides | +2.561 |
peril | +2.547 |
Neg logit contributions | |
Ba | -3.192 |
Probe | -3.161 |
coord | -3.150 |
Asuka | -3.126 |
Instrument | -3.114 |
Token | ain |
Token ID | 391 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
Ba | +1.008 |
Probe | +1.008 |
Instrument | +0.999 |
coord | +0.987 |
Asuka | +0.985 |
Neg logit contributions | |
profit | -2.173 |
ailability | -2.172 |
arcity | -2.148 |
secure | -2.059 |
paren | -2.054 |
Token | insisted |
Token ID | 11189 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Probe | +0.422 |
Ba | +0.421 |
Instrument | +0.419 |
coord | +0.416 |
Asuka | +0.416 |
Neg logit contributions | |
ailability | -0.422 |
profit | -0.422 |
arcity | -0.415 |
secure | -0.391 |
paren | -0.391 |
Token | on |
Token ID | 319 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
profit | +0.797 |
ailability | +0.790 |
arcity | +0.782 |
ides | +0.734 |
secure | +0.732 |
Neg logit contributions | |
Probe | -1.035 |
Ba | -1.034 |
coord | -1.024 |
Instrument | -1.022 |
Asuka | -1.018 |
Token | the |
Token ID | 262 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
profit | +0.986 |
ailability | +0.968 |
arcity | +0.962 |
ides | +0.920 |
peril | +0.919 |
Neg logit contributions | |
Ba | -1.030 |
Probe | -1.028 |
Instrument | -1.013 |
coord | -1.010 |
Asuka | -1.004 |
Token | ale |
Token ID | 1000 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
profit | +1.134 |
arcity | +1.121 |
ailability | +1.120 |
ides | +1.061 |
paren | +1.046 |
Neg logit contributions | |
Probe | -1.297 |
Instrument | -1.280 |
Ba | -1.279 |
Asuka | -1.278 |
coord | -1.270 |
Token | urs |
Token ID | 1834 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
profit | +0.393 |
ailability | +0.391 |
arcity | +0.384 |
secure | +0.352 |
ides | +0.352 |
Neg logit contributions | |
Probe | -0.739 |
Ba | -0.738 |
Instrument | -0.735 |
Asuka | -0.732 |
coord | -0.730 |
Token | les |
Token ID | 10287 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
profit | +0.637 |
ailability | +0.631 |
arcity | +0.621 |
peril | +0.589 |
paren | +0.589 |
Neg logit contributions | |
Ba | -0.702 |
Probe | -0.701 |
Asuka | -0.695 |
Instrument | -0.694 |
coord | -0.684 |
Token | plus |
Token ID | 5556 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Ba | +0.436 |
Probe | +0.435 |
Instrument | +0.433 |
Asuka | +0.430 |
coord | +0.428 |
Neg logit contributions | |
profit | -0.438 |
ailability | -0.436 |
arcity | -0.430 |
secure | -0.407 |
peril | -0.405 |
Token | bas |
Token ID | 1615 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
profit | +1.085 |
ailability | +1.073 |
arcity | +1.052 |
ides | +1.006 |
paren | +1.004 |
Neg logit contributions | |
Ba | -1.132 |
Probe | -1.131 |
Asuka | -1.123 |
Instrument | -1.119 |
coord | -1.105 |
Token | iques |
Token ID | 6368 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
profit | +2.018 |
ailability | +1.998 |
arcity | +1.977 |
ides | +1.916 |
peril | +1.878 |
Neg logit contributions | |
Probe | -2.162 |
Asuka | -2.153 |
Ba | -2.145 |
Instrument | -2.114 |
coord | -2.084 |
Token | . |
Token ID | 13 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
profit | +2.954 |
ailability | +2.893 |
arcity | +2.844 |
peril | +2.778 |
ides | +2.763 |
Neg logit contributions | |
Ba | -3.293 |
Asuka | -3.272 |
Probe | -3.257 |
Instrument | -3.200 |
bats | -3.187 |
Token | Il |
Token ID | 13778 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
profit | +0.636 |
ailability | +0.623 |
arcity | +0.619 |
secure | +0.592 |
paren | +0.589 |
Neg logit contributions | |
Probe | -0.665 |
coord | -0.663 |
Asuka | -0.663 |
Ba | -0.660 |
Instrument | -0.660 |
Token | app |
Token ID | 598 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Probe | +0.258 |
Ba | +0.258 |
Instrument | +0.257 |
Asuka | +0.256 |
coord | +0.253 |
Neg logit contributions | |
profit | -0.258 |
ailability | -0.255 |
arcity | -0.252 |
peril | -0.239 |
secure | -0.238 |
Token | ara |
Token ID | 3301 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
profit | +0.315 |
ailability | +0.312 |
arcity | +0.309 |
secure | +0.290 |
ides | +0.290 |
Neg logit contributions | |
Probe | -0.347 |
Ba | -0.346 |
Instrument | -0.344 |
Asuka | -0.342 |
coord | -0.341 |
Token | î |
Token ID | 34803 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
profit | +0.258 |
ailability | +0.256 |
arcity | +0.251 |
ides | +0.239 |
peril | +0.237 |
Neg logit contributions | |
Probe | -0.336 |
Asuka | -0.334 |
Instrument | -0.333 |
Ba | -0.333 |
coord | -0.330 |
Token | know |
Token ID | 760 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Probe | +0.812 |
Ba | +0.811 |
Instrument | +0.807 |
coord | +0.802 |
Asuka | +0.801 |
Neg logit contributions | |
ailability | -0.795 |
profit | -0.785 |
arcity | -0.779 |
secure | -0.730 |
paren | -0.729 |
Token | more |
Token ID | 517 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Probe | +1.080 |
Ba | +1.078 |
Instrument | +1.077 |
coord | +1.069 |
Asuka | +1.068 |
Neg logit contributions | |
ailability | -1.065 |
profit | -1.057 |
arcity | -1.047 |
secure | -0.980 |
paren | -0.973 |
Token | about |
Token ID | 546 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
profit | +1.064 |
ailability | +1.050 |
arcity | +1.038 |
paren | +0.994 |
peril | +0.988 |
Neg logit contributions | |
Probe | -1.122 |
Ba | -1.120 |
Instrument | -1.110 |
coord | -1.101 |
Asuka | -1.101 |
Token | the |
Token ID | 262 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
profit | +0.254 |
ailability | +0.252 |
arcity | +0.249 |
peril | +0.235 |
secure | +0.235 |
Neg logit contributions | |
Ba | -0.267 |
Probe | -0.267 |
Instrument | -0.265 |
coord | -0.263 |
Asuka | -0.263 |
Token | trans |
Token ID | 1007 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
Probe | +0.236 |
Ba | +0.236 |
Instrument | +0.234 |
coord | +0.232 |
Asuka | +0.232 |
Neg logit contributions | |
profit | -0.228 |
ailability | -0.227 |
arcity | -0.224 |
paren | -0.211 |
peril | -0.211 |
Token | itive |
Token ID | 1800 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
ailability | +0.040 |
profit | +0.040 |
arcity | +0.039 |
secure | +0.037 |
peril | +0.037 |
Neg logit contributions | |
Ba | -0.043 |
Probe | -0.043 |
Instrument | -0.043 |
coord | -0.043 |
Asuka | -0.043 |
Token | inference |
Token ID | 32278 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
profit | +3.468 |
ailability | +3.343 |
arcity | +3.313 |
paren | +3.276 |
peril | +3.260 |
Neg logit contributions | |
Probe | -3.843 |
Ba | -3.783 |
bats | -3.739 |
Asuka | -3.731 |
coord | -3.716 |
Token | ( |
Token ID | 357 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Ba | +1.307 |
Probe | +1.307 |
Instrument | +1.306 |
coord | +1.289 |
Asuka | +1.288 |
Neg logit contributions | |
ailability | -1.450 |
profit | -1.440 |
arcity | -1.432 |
secure | -1.344 |
ides | -1.330 |
Token | if |
Token ID | 361 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
profit | +0.200 |
ailability | +0.196 |
arcity | +0.194 |
paren | +0.184 |
secure | +0.184 |
Neg logit contributions | |
Probe | -0.220 |
Instrument | -0.219 |
Ba | -0.219 |
coord | -0.217 |
Asuka | -0.217 |
Token | A |
Token ID | 317 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Probe | +1.890 |
Ba | +1.889 |
Instrument | +1.887 |
Asuka | +1.875 |
coord | +1.861 |
Neg logit contributions | |
ailability | -1.874 |
profit | -1.863 |
arcity | -1.843 |
secure | -1.728 |
paren | -1.721 |
Token | > |
Token ID | 29 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
profit | +0.433 |
ailability | +0.426 |
arcity | +0.422 |
paren | +0.402 |
ides | +0.402 |
Neg logit contributions | |
Probe | -0.421 |
Ba | -0.421 |
Instrument | -0.417 |
Asuka | -0.416 |
coord | -0.414 |
Token | , |
Token ID | 11 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
Ba | +0.545 |
Probe | +0.544 |
Instrument | +0.542 |
Asuka | +0.539 |
coord | +0.538 |
Neg logit contributions | |
profit | -0.468 |
ailability | -0.467 |
arcity | -0.461 |
secure | -0.432 |
paren | -0.429 |
Token | eff |
Token ID | 914 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
profit | +0.046 |
ailability | +0.045 |
arcity | +0.044 |
peril | +0.042 |
paren | +0.042 |
Neg logit contributions | |
Probe | -0.064 |
Ba | -0.064 |
Instrument | -0.064 |
coord | -0.063 |
Asuka | -0.063 |
Token | em |
Token ID | 368 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Probe | +0.747 |
Ba | +0.747 |
Instrument | +0.744 |
coord | +0.739 |
Asuka | +0.738 |
Neg logit contributions | |
profit | -0.501 |
ailability | -0.498 |
arcity | -0.491 |
secure | -0.456 |
paren | -0.454 |
Token | inate |
Token ID | 4559 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
profit | +1.105 |
arcity | +1.085 |
ailability | +1.050 |
paren | +1.041 |
secure | +1.038 |
Neg logit contributions | |
Probe | -1.168 |
coord | -1.156 |
Instrument | -1.154 |
Asuka | -1.137 |
Ba | -1.123 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
profit | +1.197 |
arcity | +1.147 |
ailability | +1.130 |
peril | +1.114 |
ð | +1.110 |
Neg logit contributions | |
Probe | -1.664 |
Ba | -1.649 |
Instrument | -1.648 |
coord | -1.643 |
Asuka | -1.618 |
Token | decad |
Token ID | 46734 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
profit | +0.959 |
ailability | +0.945 |
arcity | +0.929 |
peril | +0.894 |
secure | +0.883 |
Neg logit contributions | |
Probe | -1.225 |
Instrument | -1.216 |
Ba | -1.211 |
coord | -1.200 |
Asuka | -1.193 |
Token | ent |
Token ID | 298 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
profit | +1.092 |
arcity | +1.065 |
ailability | +1.040 |
ides | +0.980 |
secure | +0.980 |
Neg logit contributions | |
Probe | -1.873 |
Ba | -1.863 |
coord | -1.860 |
Instrument | -1.856 |
Asuka | -1.845 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
profit | +1.410 |
ailability | +1.410 |
arcity | +1.379 |
ides | +1.303 |
peril | +1.301 |
Neg logit contributions | |
Probe | -1.825 |
Ba | -1.804 |
Instrument | -1.801 |
coord | -1.792 |
Asuka | -1.777 |
Token | eastern |
Token ID | 10183 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
profit | +1.141 |
ailability | +1.139 |
arcity | +1.109 |
peril | +1.063 |
secure | +1.056 |
Neg logit contributions | |
Probe | -1.463 |
Ba | -1.452 |
Instrument | -1.450 |
coord | -1.433 |
Asuka | -1.427 |
Token | � |
Token ID | 564 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
profit | +0.628 |
ailability | +0.628 |
arcity | +0.617 |
peril | +0.579 |
paren | +0.578 |
Neg logit contributions | |
Probe | -0.715 |
Ba | -0.714 |
Instrument | -0.709 |
coord | -0.704 |
Asuka | -0.704 |
Token | � |
Token ID | 246 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
profit | +0.759 |
arcity | +0.730 |
ailability | +0.727 |
ides | +0.682 |
paren | +0.680 |
Neg logit contributions | |
Probe | -1.245 |
Ba | -1.244 |
Instrument | -1.242 |
Asuka | -1.236 |
coord | -1.231 |
Token | � |
Token ID | 447 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Probe | +0.427 |
Ba | +0.427 |
Instrument | +0.425 |
coord | +0.421 |
Asuka | +0.421 |
Neg logit contributions | |
profit | -0.415 |
ailability | -0.414 |
arcity | -0.408 |
secure | -0.385 |
paren | -0.383 |
Token | � |
Token ID | 247 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
profit | +0.190 |
ailability | +0.188 |
arcity | +0.187 |
secure | +0.176 |
ides | +0.175 |
Neg logit contributions | |
Probe | -0.206 |
Ba | -0.205 |
Instrument | -0.204 |
coord | -0.203 |
Asuka | -0.203 |
Token | re |
Token ID | 260 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
profit | +0.103 |
ailability | +0.103 |
arcity | +0.101 |
secure | +0.096 |
ides | +0.095 |
Neg logit contributions | |
Probe | -0.118 |
Ba | -0.118 |
Instrument | -0.117 |
coord | -0.117 |
Asuka | -0.117 |
Token | like |
Token ID | 588 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Probe | +0.813 |
Ba | +0.812 |
Instrument | +0.808 |
Asuka | +0.802 |
coord | +0.801 |
Neg logit contributions | |
profit | -0.812 |
ailability | -0.809 |
arcity | -0.798 |
secure | -0.754 |
paren | -0.752 |
Token | the |
Token ID | 262 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Probe | +0.971 |
Ba | +0.971 |
Instrument | +0.965 |
coord | +0.957 |
Asuka | +0.956 |
Neg logit contributions | |
profit | -1.028 |
ailability | -1.024 |
arcity | -1.011 |
secure | -0.955 |
paren | -0.953 |
Token | pulse |
Token ID | 19445 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
profit | +0.300 |
ailability | +0.297 |
arcity | +0.294 |
peril | +0.281 |
ides | +0.279 |
Neg logit contributions | |
Ba | -0.304 |
Probe | -0.302 |
Instrument | -0.301 |
Asuka | -0.298 |
coord | -0.298 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
profit | +1.104 |
ailability | +1.088 |
arcity | +1.072 |
ides | +1.036 |
ð | +1.033 |
Neg logit contributions | |
Ba | -1.571 |
Probe | -1.556 |
Instrument | -1.545 |
Asuka | -1.543 |
coord | -1.535 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
profit | +0.763 |
ailability | +0.756 |
arcity | +0.749 |
peril | +0.713 |
ides | +0.707 |
Neg logit contributions | |
Ba | -0.847 |
Probe | -0.844 |
Instrument | -0.835 |
coord | -0.829 |
Asuka | -0.827 |
Token | loss |
Token ID | 2994 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
Probe | +1.283 |
Ba | +1.280 |
Instrument | +1.274 |
coord | +1.267 |
Asuka | +1.266 |
Neg logit contributions | |
ailability | -1.215 |
profit | -1.214 |
arcity | -1.195 |
secure | -1.124 |
paren | -1.122 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
Ba | +0.027 |
Probe | +0.027 |
Instrument | +0.027 |
coord | +0.027 |
Asuka | +0.027 |
Neg logit contributions | |
profit | -0.025 |
ailability | -0.024 |
arcity | -0.024 |
ides | -0.023 |
peril | -0.023 |
Token | So |
Token ID | 1406 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
profit | +0.378 |
arcity | +0.370 |
ailability | +0.369 |
ð | +0.352 |
ides | +0.352 |
Neg logit contributions | |
coord | -0.370 |
Ba | -0.370 |
Probe | -0.369 |
Instrument | -0.364 |
Asuka | -0.364 |
Token | optimistic |
Token ID | 16915 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
profit | +0.571 |
ailability | +0.561 |
arcity | +0.560 |
ides | +0.531 |
peril | +0.530 |
Neg logit contributions | |
Probe | -0.599 |
Ba | -0.597 |
Instrument | -0.595 |
Asuka | -0.588 |
coord | -0.588 |
Token | for |
Token ID | 329 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Ba | +0.699 |
Probe | +0.699 |
Instrument | +0.697 |
Asuka | +0.691 |
coord | +0.691 |
Neg logit contributions | |
ailability | -0.580 |
profit | -0.579 |
arcity | -0.570 |
secure | -0.533 |
paren | -0.531 |
Token | the |
Token ID | 262 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
profit | +0.763 |
arcity | +0.747 |
ailability | +0.743 |
peril | +0.711 |
ides | +0.711 |
Neg logit contributions | |
Ba | -0.749 |
Probe | -0.744 |
coord | -0.739 |
Instrument | -0.734 |
Asuka | -0.726 |
Token | season |
Token ID | 1622 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
profit | +0.596 |
arcity | +0.582 |
ailability | +0.576 |
peril | +0.557 |
ides | +0.554 |
Neg logit contributions | |
Ba | -0.623 |
Probe | -0.618 |
coord | -0.614 |
Instrument | -0.612 |
Asuka | -0.606 |
Token | and |
Token ID | 290 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
profit | +0.836 |
ailability | +0.819 |
arcity | +0.812 |
ides | +0.773 |
secure | +0.769 |
Neg logit contributions | |
Probe | -1.093 |
Ba | -1.089 |
Instrument | -1.081 |
coord | -1.079 |
Asuka | -1.071 |
Token | still |
Token ID | 991 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
profit | +0.130 |
ailability | +0.128 |
arcity | +0.127 |
peril | +0.120 |
ides | +0.120 |
Neg logit contributions | |
Ba | -0.136 |
Probe | -0.136 |
Instrument | -0.135 |
coord | -0.134 |
Asuka | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
profit | +1.327 |
ailability | +1.302 |
arcity | +1.292 |
peril | +1.246 |
ides | +1.243 |
Neg logit contributions | |
Probe | -1.289 |
Ba | -1.284 |
Instrument | -1.271 |
coord | -1.261 |
Asuka | -1.260 |
Token | long |
Token ID | 890 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
profit | +0.546 |
ailability | +0.538 |
arcity | +0.534 |
ides | +0.507 |
peril | +0.506 |
Neg logit contributions | |
Ba | -0.575 |
Probe | -0.575 |
Instrument | -0.572 |
Asuka | -0.568 |
coord | -0.567 |
Token | way |
Token ID | 835 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
profit | +0.712 |
ailability | +0.706 |
arcity | +0.697 |
peril | +0.668 |
ides | +0.663 |
Neg logit contributions | |
Probe | -0.771 |
Instrument | -0.766 |
Ba | -0.765 |
coord | -0.765 |
Asuka | -0.759 |
Token | to |
Token ID | 284 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Probe | +0.110 |
Ba | +0.109 |
Instrument | +0.109 |
coord | +0.108 |
Asuka | +0.108 |
Neg logit contributions | |
profit | -0.114 |
ailability | -0.113 |
arcity | -0.112 |
secure | -0.106 |
peril | -0.106 |
Token | go |
Token ID | 467 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
profit | +0.030 |
ailability | +0.030 |
arcity | +0.029 |
secure | +0.028 |
peril | +0.028 |
Neg logit contributions | |
Probe | -0.033 |
Ba | -0.032 |
Instrument | -0.032 |
coord | -0.032 |
Asuka | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
profit | +0.429 |
ailability | +0.425 |
arcity | +0.420 |
secure | +0.398 |
peril | +0.397 |
Neg logit contributions | |
Probe | -0.501 |
Ba | -0.499 |
Instrument | -0.495 |
coord | -0.493 |
Asuka | -0.493 |
Token | be |
Token ID | 307 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
Probe | +0.184 |
Ba | +0.184 |
Instrument | +0.183 |
coord | +0.182 |
Asuka | +0.182 |
Neg logit contributions | |
profit | -0.146 |
ailability | -0.145 |
arcity | -0.143 |
secure | -0.134 |
peril | -0.133 |
Token | peaceful |
Token ID | 12309 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Probe | +0.033 |
Ba | +0.033 |
Instrument | +0.033 |
coord | +0.032 |
Asuka | +0.032 |
Neg logit contributions | |
profit | -0.029 |
ailability | -0.029 |
arcity | -0.028 |
secure | -0.027 |
paren | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
profit | +0.076 |
ailability | +0.075 |
arcity | +0.075 |
secure | +0.070 |
peril | +0.070 |
Neg logit contributions | |
Probe | -0.085 |
Ba | -0.085 |
Instrument | -0.084 |
Asuka | -0.084 |
coord | -0.084 |
Token | acknowledging |
Token ID | 25937 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
profit | +0.175 |
ailability | +0.173 |
arcity | +0.171 |
secure | +0.162 |
peril | +0.162 |
Neg logit contributions | |
Probe | -0.191 |
Ba | -0.190 |
Instrument | -0.189 |
Asuka | -0.188 |
coord | -0.188 |
Token | the |
Token ID | 262 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
Probe | +0.130 |
Ba | +0.129 |
Instrument | +0.129 |
coord | +0.128 |
Asuka | +0.128 |
Neg logit contributions | |
profit | -0.120 |
ailability | -0.119 |
arcity | -0.118 |
peril | -0.111 |
secure | -0.111 |
Token | sovereignty |
Token ID | 18582 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
profit | +0.636 |
ailability | +0.623 |
arcity | +0.622 |
peril | +0.603 |
ides | +0.588 |
Neg logit contributions | |
Probe | -0.692 |
Ba | -0.686 |
Instrument | -0.677 |
Asuka | -0.676 |
coord | -0.674 |
Token | of |
Token ID | 286 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
profit | +0.639 |
ailability | +0.634 |
arcity | +0.624 |
peril | +0.580 |
secure | +0.578 |
Neg logit contributions | |
Probe | -1.058 |
Ba | -1.054 |
Instrument | -1.049 |
coord | -1.043 |
Asuka | -1.042 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
profit | +0.332 |
ailability | +0.327 |
arcity | +0.325 |
peril | +0.308 |
ides | +0.308 |
Neg logit contributions | |
Probe | -0.343 |
Ba | -0.341 |
Instrument | -0.338 |
coord | -0.337 |
Asuka | -0.336 |
Token | Jewish |
Token ID | 5582 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Probe | +0.258 |
Ba | +0.257 |
Instrument | +0.254 |
coord | +0.254 |
Asuka | +0.254 |
Neg logit contributions | |
profit | -0.240 |
ailability | -0.238 |
arcity | -0.235 |
peril | -0.223 |
secure | -0.223 |
Token | people |
Token ID | 661 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
Probe | +0.474 |
Ba | +0.474 |
Instrument | +0.471 |
coord | +0.468 |
Asuka | +0.468 |
Neg logit contributions | |
profit | -0.459 |
ailability | -0.458 |
arcity | -0.452 |
secure | -0.426 |
paren | -0.425 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
profit | +0.139 |
ailability | +0.139 |
arcity | +0.137 |
secure | +0.127 |
peril | +0.127 |
Neg logit contributions | |
Probe | -0.201 |
Ba | -0.200 |
Instrument | -0.199 |
coord | -0.198 |
Asuka | -0.198 |
Token | Each |
Token ID | 5501 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Probe | +0.137 |
coord | +0.136 |
Ba | +0.136 |
Instrument | +0.135 |
Asuka | +0.134 |
Neg logit contributions | |
profit | -0.143 |
ailability | -0.141 |
arcity | -0.141 |
secure | -0.134 |
ides | -0.134 |
Token | had |
Token ID | 550 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
profit | +0.334 |
ailability | +0.331 |
arcity | +0.326 |
ides | +0.311 |
peril | +0.310 |
Neg logit contributions | |
Ba | -0.366 |
Probe | -0.365 |
Instrument | -0.362 |
coord | -0.360 |
Asuka | -0.360 |
Token | a |
Token ID | 257 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
Probe | +0.873 |
Ba | +0.873 |
Instrument | +0.868 |
coord | +0.862 |
Asuka | +0.861 |
Neg logit contributions | |
profit | -0.820 |
ailability | -0.818 |
arcity | -0.807 |
secure | -0.760 |
paren | -0.757 |
Token | pile |
Token ID | 14540 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Ba | +0.454 |
Probe | +0.453 |
Instrument | +0.451 |
coord | +0.448 |
Asuka | +0.447 |
Neg logit contributions | |
profit | -0.436 |
ailability | -0.433 |
arcity | -0.428 |
secure | -0.405 |
ides | -0.404 |
Token | of |
Token ID | 286 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
Ba | +0.249 |
Probe | +0.249 |
Instrument | +0.248 |
coord | +0.246 |
Asuka | +0.246 |
Neg logit contributions | |
profit | -0.151 |
ailability | -0.151 |
arcity | -0.148 |
secure | -0.137 |
paren | -0.136 |
Token | envelop |
Token ID | 16441 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
profit | +0.652 |
ailability | +0.644 |
arcity | +0.637 |
peril | +0.611 |
ides | +0.610 |
Neg logit contributions | |
Probe | -0.676 |
Ba | -0.676 |
coord | -0.669 |
Instrument | -0.667 |
Asuka | -0.661 |
Token | es |
Token ID | 274 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
profit | +0.303 |
ailability | +0.301 |
arcity | +0.296 |
secure | +0.281 |
ides | +0.280 |
Neg logit contributions | |
Ba | -0.343 |
Probe | -0.343 |
Instrument | -0.341 |
coord | -0.339 |
Asuka | -0.339 |
Token | for |
Token ID | 329 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
profit | +1.383 |
ailability | +1.371 |
arcity | +1.354 |
ides | +1.298 |
peril | +1.296 |
Neg logit contributions | |
Probe | -1.713 |
Ba | -1.710 |
Instrument | -1.696 |
coord | -1.688 |
Asuka | -1.678 |
Token | present |
Token ID | 1944 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Probe | +0.048 |
Ba | +0.048 |
Instrument | +0.048 |
coord | +0.048 |
Asuka | +0.047 |
Neg logit contributions | |
profit | -0.048 |
ailability | -0.048 |
arcity | -0.047 |
secure | -0.045 |
ides | -0.045 |
Token | ers |
Token ID | 364 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
profit | +0.279 |
ailability | +0.278 |
arcity | +0.275 |
secure | +0.258 |
paren | +0.257 |
Neg logit contributions | |
Probe | -0.278 |
Ba | -0.278 |
Instrument | -0.276 |
Asuka | -0.274 |
coord | -0.274 |
Token | - |
Token ID | 12 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
profit | +0.184 |
ailability | +0.181 |
arcity | +0.180 |
ides | +0.172 |
peril | +0.172 |
Neg logit contributions | |
Ba | -0.160 |
Probe | -0.159 |
Asuka | -0.158 |
Instrument | -0.157 |
coord | -0.155 |
Token | based |
Token ID | 3106 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Probe | +0.496 |
Ba | +0.493 |
Instrument | +0.492 |
Asuka | +0.492 |
coord | +0.489 |
Neg logit contributions | |
profit | -0.403 |
ailability | -0.393 |
arcity | -0.389 |
secure | -0.370 |
ides | -0.367 |
Token | temperature |
Token ID | 5951 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Ba | +0.201 |
Probe | +0.200 |
Asuka | +0.198 |
Instrument | +0.197 |
coord | +0.196 |
Neg logit contributions | |
profit | -0.209 |
ailability | -0.204 |
arcity | -0.203 |
peril | -0.194 |
ides | -0.193 |
Token | estimates |
Token ID | 7746 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
profit | +1.000 |
arcity | +0.970 |
ailability | +0.965 |
peril | +0.948 |
ides | +0.944 |
Neg logit contributions | |
Ba | -0.911 |
Asuka | -0.910 |
Probe | -0.904 |
Instrument | -0.898 |
Amp | -0.887 |
Token | to |
Token ID | 284 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
profit | +0.387 |
ailability | +0.380 |
arcity | +0.378 |
ides | +0.357 |
peril | +0.355 |
Neg logit contributions | |
Ba | -0.465 |
Probe | -0.465 |
Asuka | -0.460 |
Instrument | -0.460 |
coord | -0.459 |
Token | reach |
Token ID | 3151 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
profit | +0.010 |
ailability | +0.010 |
arcity | +0.010 |
secure | +0.009 |
peril | +0.009 |
Neg logit contributions | |
Ba | -0.011 |
Probe | -0.011 |
Instrument | -0.011 |
Asuka | -0.011 |
coord | -0.011 |
Token | their |
Token ID | 511 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Probe | +1.428 |
Ba | +1.427 |
Instrument | +1.425 |
coord | +1.416 |
Asuka | +1.405 |
Neg logit contributions | |
ailability | -1.450 |
profit | -1.447 |
arcity | -1.429 |
secure | -1.346 |
paren | -1.338 |
Token | conclusion |
Token ID | 7664 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
profit | +0.242 |
ailability | +0.239 |
arcity | +0.237 |
peril | +0.227 |
secure | +0.226 |
Neg logit contributions | |
Ba | -0.186 |
Probe | -0.186 |
Instrument | -0.184 |
Asuka | -0.183 |
coord | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Probe | +1.270 |
Ba | +1.270 |
Instrument | +1.269 |
coord | +1.255 |
Asuka | +1.255 |
Neg logit contributions | |
ailability | -1.040 |
profit | -1.037 |
arcity | -1.021 |
secure | -0.953 |
paren | -0.950 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Probe | +0.106 |
Ba | +0.106 |
Instrument | +0.105 |
coord | +0.105 |
Asuka | +0.105 |
Neg logit contributions | |
profit | -0.113 |
ailability | -0.112 |
arcity | -0.111 |
secure | -0.105 |
paren | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
Probe | +0.244 |
Ba | +0.242 |
coord | +0.242 |
Instrument | +0.242 |
Asuka | +0.240 |
Neg logit contributions | |
profit | -0.273 |
arcity | -0.267 |
ailability | -0.266 |
secure | -0.254 |
ides | -0.254 |
Token | read |
Token ID | 1100 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Ba | +0.224 |
Probe | +0.223 |
Instrument | +0.222 |
Asuka | +0.220 |
coord | +0.220 |
Neg logit contributions | |
profit | -0.193 |
ailability | -0.190 |
arcity | -0.187 |
ides | -0.178 |
peril | -0.178 |
Token | () |
Token ID | 3419 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
profit | +0.330 |
ailability | +0.326 |
arcity | +0.321 |
paren | +0.306 |
secure | +0.306 |
Neg logit contributions | |
Probe | -0.356 |
Ba | -0.355 |
Instrument | -0.355 |
Asuka | -0.352 |
coord | -0.352 |
Token | returns |
Token ID | 5860 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
profit | +2.046 |
arcity | +1.956 |
ailability | +1.942 |
peril | +1.933 |
ides | +1.924 |
Neg logit contributions | |
Instrument | -2.467 |
Ba | -2.462 |
bats | -2.440 |
Probe | -2.433 |
Asuka | -2.425 |
Token | : |
Token ID | 25 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
profit | +0.604 |
ailability | +0.591 |
arcity | +0.584 |
peril | +0.565 |
ides | +0.562 |
Neg logit contributions | |
Ba | -0.805 |
Probe | -0.800 |
Instrument | -0.799 |
Asuka | -0.794 |
coord | -0.791 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Ba | +0.051 |
Probe | +0.051 |
Instrument | +0.050 |
Asuka | +0.050 |
coord | +0.050 |
Neg logit contributions | |
profit | -0.056 |
ailability | -0.056 |
arcity | -0.055 |
secure | -0.052 |
paren | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Probe | +0.740 |
Ba | +0.738 |
Instrument | +0.735 |
coord | +0.731 |
Asuka | +0.728 |
Neg logit contributions | |
profit | -0.849 |
ailability | -0.840 |
arcity | -0.835 |
secure | -0.792 |
paren | -0.790 |
Token | + |
Token ID | 10 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Probe | +0.520 |
Instrument | +0.516 |
Ba | +0.516 |
Asuka | +0.514 |
coord | +0.514 |
Neg logit contributions | |
profit | -0.449 |
ailability | -0.442 |
arcity | -0.437 |
secure | -0.414 |
paren | -0.412 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
profit | +1.067 |
arcity | +1.006 |
ailability | +1.004 |
ides | +0.958 |
secure | +0.955 |
Neg logit contributions | |
Probe | -1.809 |
coord | -1.804 |
Ba | -1.800 |
Instrument | -1.796 |
Asuka | -1.795 |
Token | --+ |
Token ID | 44785 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Probe | +0.017 |
Ba | +0.017 |
Instrument | +0.017 |
coord | +0.016 |
Asuka | +0.016 |
Neg logit contributions | |
profit | -0.008 |
ailability | -0.008 |
arcity | -0.007 |
secure | -0.007 |
paren | -0.007 |
Token | | |
Token ID | 930 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
profit | +1.765 |
ailability | +1.751 |
arcity | +1.688 |
ides | +1.630 |
peril | +1.612 |
Neg logit contributions | |
Ba | -2.566 |
Probe | -2.533 |
Asuka | -2.520 |
Instrument | -2.519 |
coord | -2.514 |
Token | ... |
Token ID | 2644 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
profit | +0.610 |
ailability | +0.606 |
arcity | +0.590 |
peril | +0.555 |
ides | +0.555 |
Neg logit contributions | |
Ba | -0.947 |
Probe | -0.933 |
Asuka | -0.931 |
Instrument | -0.927 |
coord | -0.924 |
Token | your |
Token ID | 534 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Ba | +0.639 |
Probe | +0.638 |
Instrument | +0.635 |
coord | +0.631 |
Asuka | +0.629 |
Neg logit contributions | |
profit | -0.619 |
ailability | -0.614 |
arcity | -0.607 |
secure | -0.574 |
peril | -0.573 |
Token | PC |
Token ID | 4217 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
Ba | +0.186 |
Probe | +0.185 |
Instrument | +0.184 |
coord | +0.183 |
Asuka | +0.182 |
Neg logit contributions | |
profit | -0.221 |
ailability | -0.219 |
arcity | -0.217 |
peril | -0.207 |
secure | -0.206 |
Token | hal |
Token ID | 10284 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
Ba | +0.438 |
Probe | +0.436 |
Instrument | +0.434 |
coord | +0.432 |
Asuka | +0.431 |
Neg logit contributions | |
profit | -0.467 |
ailability | -0.463 |
arcity | -0.459 |
secure | -0.434 |
peril | -0.434 |
Token | ts |
Token ID | 912 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
profit | +0.470 |
ailability | +0.463 |
arcity | +0.462 |
ides | +0.437 |
paren | +0.434 |
Neg logit contributions | |
Probe | -0.565 |
Ba | -0.565 |
Instrument | -0.564 |
coord | -0.561 |
Asuka | -0.558 |
Token | , |
Token ID | 11 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Ba | +0.187 |
Probe | +0.187 |
Instrument | +0.186 |
coord | +0.185 |
Asuka | +0.185 |
Neg logit contributions | |
profit | -0.170 |
ailability | -0.170 |
arcity | -0.167 |
secure | -0.158 |
peril | -0.157 |
Token | or |
Token ID | 393 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Ba | +0.217 |
Probe | +0.217 |
Instrument | +0.216 |
coord | +0.214 |
Asuka | +0.214 |
Neg logit contributions | |
profit | -0.221 |
ailability | -0.219 |
arcity | -0.217 |
secure | -0.205 |
peril | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
Ba | +0.333 |
Probe | +0.332 |
Instrument | +0.330 |
coord | +0.328 |
Asuka | +0.327 |
Neg logit contributions | |
profit | -0.309 |
ailability | -0.306 |
arcity | -0.303 |
peril | -0.286 |
secure | -0.286 |
Token | watch |
Token ID | 2342 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Ba | +0.451 |
Probe | +0.449 |
Instrument | +0.446 |
coord | +0.443 |
Asuka | +0.443 |
Neg logit contributions | |
profit | -0.580 |
ailability | -0.578 |
arcity | -0.571 |
secure | -0.544 |
peril | -0.542 |
Token | reb |
Token ID | 3405 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
profit | +1.185 |
arcity | +1.156 |
ailability | +1.154 |
peril | +1.110 |
ides | +1.101 |
Neg logit contributions | |
Probe | -1.151 |
Ba | -1.151 |
Instrument | -1.150 |
coord | -1.140 |
Asuka | -1.138 |
Token | oots |
Token ID | 13880 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
profit | +1.126 |
arcity | +1.108 |
ailability | +1.080 |
ides | +1.050 |
secure | +1.035 |
Neg logit contributions | |
Instrument | -1.721 |
Probe | -1.715 |
coord | -1.705 |
Ba | -1.705 |
Asuka | -1.697 |
Token | ( |
Token ID | 357 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
profit | +1.372 |
arcity | +1.337 |
ailability | +1.335 |
peril | +1.288 |
ides | +1.272 |
Neg logit contributions | |
Probe | -1.615 |
Ba | -1.615 |
coord | -1.604 |
Instrument | -1.601 |
Asuka | -1.591 |
Token |
|
Token ID | 198 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
profit | +0.496 |
arcity | +0.481 |
ailability | +0.481 |
ides | +0.463 |
secure | +0.459 |
Neg logit contributions | |
Ba | -0.516 |
Probe | -0.512 |
Asuka | -0.510 |
coord | -0.509 |
Instrument | -0.508 |
Token |
|
Token ID | 198 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
profit | +0.023 |
arcity | +0.022 |
ailability | +0.022 |
secure | +0.021 |
ides | +0.021 |
Neg logit contributions | |
Probe | -0.021 |
coord | -0.021 |
Ba | -0.021 |
Instrument | -0.021 |
Asuka | -0.021 |
Token | UK |
Token ID | 15039 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
profit | +0.335 |
arcity | +0.322 |
ailability | +0.320 |
secure | +0.308 |
paren | +0.306 |
Neg logit contributions | |
Probe | -0.388 |
coord | -0.386 |
Asuka | -0.385 |
Instrument | -0.384 |
Ba | -0.380 |
Token | street |
Token ID | 4675 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Probe | +0.292 |
Ba | +0.292 |
Asuka | +0.290 |
Instrument | +0.290 |
coord | +0.288 |
Neg logit contributions | |
profit | -0.310 |
ailability | -0.308 |
arcity | -0.305 |
paren | -0.288 |
ides | -0.287 |
Token | artist |
Token ID | 6802 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Probe | +0.758 |
Ba | +0.757 |
Instrument | +0.750 |
Asuka | +0.745 |
coord | +0.743 |
Neg logit contributions | |
profit | -0.923 |
ailability | -0.913 |
arcity | -0.908 |
secure | -0.860 |
peril | -0.860 |
Token | Ph |
Token ID | 1380 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Probe | +1.141 |
Instrument | +1.137 |
Ba | +1.136 |
Asuka | +1.124 |
coord | +1.122 |
Neg logit contributions | |
ailability | -1.236 |
profit | -1.228 |
arcity | -1.212 |
secure | -1.145 |
paren | -1.140 |
Token | leg |
Token ID | 1455 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Probe | +0.431 |
Ba | +0.431 |
Instrument | +0.429 |
coord | +0.426 |
Asuka | +0.425 |
Neg logit contributions | |
ailability | -0.355 |
profit | -0.354 |
arcity | -0.348 |
secure | -0.326 |
paren | -0.325 |
Token | m |
Token ID | 76 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
Probe | +0.764 |
Ba | +0.761 |
coord | +0.758 |
Instrument | +0.758 |
Asuka | +0.755 |
Neg logit contributions | |
profit | -0.995 |
arcity | -0.976 |
ailability | -0.966 |
secure | -0.929 |
paren | -0.927 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Probe | +0.547 |
Ba | +0.547 |
Instrument | +0.544 |
coord | +0.540 |
Asuka | +0.540 |
Neg logit contributions | |
profit | -0.540 |
ailability | -0.538 |
arcity | -0.531 |
secure | -0.501 |
paren | -0.499 |
Token | public |
Token ID | 1171 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
profit | +0.956 |
ailability | +0.933 |
arcity | +0.930 |
peril | +0.897 |
ides | +0.886 |
Neg logit contributions | |
Ba | -1.061 |
Probe | -1.057 |
Instrument | -1.054 |
coord | -1.049 |
Asuka | -1.041 |
Token | art |
Token ID | 1242 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Probe | +1.278 |
Ba | +1.276 |
Instrument | +1.270 |
coord | +1.260 |
Asuka | +1.260 |
Neg logit contributions | |
profit | -1.187 |
ailability | -1.182 |
arcity | -1.167 |
secure | -1.098 |
paren | -1.096 |
Token | got |
Token ID | 1392 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Ba | +0.571 |
Probe | +0.569 |
Instrument | +0.568 |
Asuka | +0.562 |
coord | +0.562 |
Neg logit contributions | |
profit | -0.591 |
ailability | -0.583 |
arcity | -0.580 |
secure | -0.551 |
ides | -0.548 |
Token | a |
Token ID | 257 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
Probe | +1.408 |
Ba | +1.405 |
Instrument | +1.398 |
coord | +1.391 |
Asuka | +1.389 |
Neg logit contributions | |
ailability | -1.328 |
profit | -1.325 |
arcity | -1.306 |
secure | -1.225 |
paren | -1.224 |
Token | lot |
Token ID | 1256 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
Ba | +0.003 |
Probe | +0.003 |
Instrument | +0.003 |
coord | +0.003 |
Asuka | +0.003 |
Neg logit contributions | |
profit | -0.003 |
ailability | -0.003 |
arcity | -0.003 |
secure | -0.003 |
ides | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Ba | +0.668 |
Probe | +0.668 |
Instrument | +0.665 |
Asuka | +0.661 |
coord | +0.661 |
Neg logit contributions | |
ailability | -0.417 |
profit | -0.417 |
arcity | -0.410 |
secure | -0.378 |
paren | -0.377 |
Token | feedback |
Token ID | 7538 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
Ba | +0.289 |
Probe | +0.289 |
Instrument | +0.287 |
coord | +0.284 |
Asuka | +0.284 |
Neg logit contributions | |
profit | -0.281 |
ailability | -0.280 |
arcity | -0.276 |
secure | -0.261 |
peril | -0.260 |
Token | from |
Token ID | 422 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Probe | +0.514 |
Ba | +0.513 |
Instrument | +0.511 |
coord | +0.507 |
Asuka | +0.506 |
Neg logit contributions | |
profit | -0.481 |
ailability | -0.479 |
arcity | -0.473 |
secure | -0.445 |
paren | -0.444 |
Token | you |
Token ID | 345 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Ba | +0.298 |
Probe | +0.297 |
Instrument | +0.296 |
coord | +0.292 |
Asuka | +0.291 |
Neg logit contributions | |
profit | -0.295 |
ailability | -0.291 |
arcity | -0.290 |
ides | -0.274 |
secure | -0.274 |
Token | guys |
Token ID | 3730 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
profit | +0.118 |
ailability | +0.117 |
arcity | +0.115 |
secure | +0.109 |
ides | +0.109 |
Neg logit contributions | |
Probe | -0.134 |
Ba | -0.134 |
Instrument | -0.133 |
coord | -0.132 |
Asuka | -0.132 |
Token | ! |
Token ID | 0 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
profit | +0.013 |
ailability | +0.013 |
arcity | +0.013 |
secure | +0.012 |
ides | +0.012 |
Neg logit contributions | |
Ba | -0.016 |
Probe | -0.016 |
Instrument | -0.016 |
coord | -0.016 |
Asuka | -0.015 |
Token | I |
Token ID | 314 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Probe | +0.211 |
Ba | +0.210 |
Instrument | +0.210 |
coord | +0.209 |
Asuka | +0.208 |
Neg logit contributions | |
profit | -0.220 |
ailability | -0.216 |
arcity | -0.215 |
secure | -0.204 |
ides | -0.204 |
Token | was |
Token ID | 373 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Ba | +0.454 |
Probe | +0.453 |
Instrument | +0.452 |
Asuka | +0.448 |
coord | +0.447 |
Neg logit contributions | |
profit | -0.457 |
ailability | -0.450 |
arcity | -0.449 |
secure | -0.426 |
ides | -0.423 |
Token | restaurant |
Token ID | 7072 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
profit | +0.703 |
ailability | +0.690 |
arcity | +0.680 |
ides | +0.653 |
secure | +0.652 |
Neg logit contributions | |
Ba | -0.755 |
Probe | -0.754 |
Instrument | -0.751 |
coord | -0.748 |
Asuka | -0.741 |
Token | in |
Token ID | 287 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
profit | +0.716 |
arcity | +0.698 |
ailability | +0.698 |
secure | +0.667 |
peril | +0.666 |
Neg logit contributions | |
Probe | -0.813 |
Ba | -0.811 |
coord | -0.805 |
Instrument | -0.805 |
Asuka | -0.791 |
Token | LA |
Token ID | 9131 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Ba | +0.150 |
Probe | +0.150 |
Instrument | +0.149 |
coord | +0.148 |
Asuka | +0.147 |
Neg logit contributions | |
profit | -0.102 |
ailability | -0.101 |
arcity | -0.100 |
secure | -0.094 |
peril | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
profit | +0.777 |
ailability | +0.762 |
arcity | +0.758 |
ides | +0.723 |
peril | +0.718 |
Neg logit contributions | |
Ba | -0.895 |
Probe | -0.893 |
Instrument | -0.890 |
coord | -0.888 |
Asuka | -0.879 |
Token | But |
Token ID | 887 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Ba | +0.285 |
coord | +0.285 |
Probe | +0.284 |
Instrument | +0.280 |
Asuka | +0.278 |
Neg logit contributions | |
profit | -0.311 |
arcity | -0.304 |
ailability | -0.302 |
secure | -0.294 |
ides | -0.292 |
Token | once |
Token ID | 1752 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
Probe | +0.355 |
Ba | +0.354 |
Instrument | +0.351 |
coord | +0.348 |
Asuka | +0.346 |
Neg logit contributions | |
profit | -0.356 |
ailability | -0.348 |
arcity | -0.348 |
secure | -0.332 |
peril | -0.332 |
Token | outside |
Token ID | 2354 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
Ba | +2.226 |
Instrument | +2.224 |
Asuka | +2.215 |
Probe | +2.214 |
coord | +2.206 |
Neg logit contributions | |
ailability | -2.595 |
profit | -2.568 |
arcity | -2.551 |
paren | -2.408 |
secure | -2.377 |
Token | she |
Token ID | 673 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
profit | +0.618 |
ailability | +0.605 |
arcity | +0.599 |
peril | +0.573 |
ides | +0.573 |
Neg logit contributions | |
Probe | -0.722 |
Ba | -0.718 |
Instrument | -0.713 |
coord | -0.710 |
Asuka | -0.700 |
Token | was |
Token ID | 373 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
profit | +1.052 |
arcity | +1.024 |
ailability | +1.017 |
peril | +0.993 |
ides | +0.984 |
Neg logit contributions | |
Probe | -1.057 |
Ba | -1.055 |
Instrument | -1.050 |
coord | -1.034 |
Asuka | -1.025 |
Token | seen |
Token ID | 1775 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
profit | +0.882 |
ailability | +0.866 |
arcity | +0.857 |
peril | +0.826 |
secure | +0.820 |
Neg logit contributions | |
Ba | -0.975 |
Probe | -0.975 |
Instrument | -0.964 |
coord | -0.956 |
Asuka | -0.952 |
Token | inspecting |
Token ID | 49889 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
profit | +0.320 |
ailability | +0.315 |
arcity | +0.311 |
peril | +0.300 |
secure | +0.299 |
Neg logit contributions | |
Probe | -0.312 |
Ba | -0.312 |
Instrument | -0.311 |
coord | -0.308 |
Asuka | -0.304 |
Token | views |
Token ID | 5009 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
profit | +0.039 |
ailability | +0.039 |
arcity | +0.038 |
secure | +0.036 |
paren | +0.036 |
Neg logit contributions | |
Probe | -0.035 |
Ba | -0.035 |
Instrument | -0.034 |
coord | -0.034 |
Asuka | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Ba | +0.575 |
Probe | +0.574 |
Instrument | +0.572 |
Asuka | +0.568 |
coord | +0.567 |
Neg logit contributions | |
ailability | -0.354 |
profit | -0.346 |
arcity | -0.342 |
secure | -0.315 |
paren | -0.313 |
Token | Town |
Token ID | 8329 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
profit | +0.961 |
ailability | +0.941 |
arcity | +0.927 |
peril | +0.897 |
ð | +0.895 |
Neg logit contributions | |
Ba | -0.921 |
Asuka | -0.910 |
bats | -0.899 |
coord | -0.899 |
Instrument | -0.895 |
Token | hall |
Token ID | 18323 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
profit | +0.628 |
ailability | +0.619 |
arcity | +0.592 |
ides | +0.529 |
paren | +0.527 |
Neg logit contributions | |
Probe | -2.172 |
Ba | -2.166 |
Instrument | -2.164 |
coord | -2.158 |
Asuka | -2.158 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Probe | +2.128 |
Instrument | +2.119 |
Ba | +2.118 |
coord | +2.080 |
Amp | +2.071 |
Neg logit contributions | |
ailability | -1.920 |
arcity | -1.892 |
profit | -1.876 |
profits | -1.740 |
ginx | -1.712 |
Token | com |
Token ID | 785 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Ba | +0.974 |
Probe | +0.973 |
coord | +0.972 |
Instrument | +0.970 |
Asuka | +0.970 |
Neg logit contributions | |
profit | -0.554 |
ailability | -0.545 |
arcity | -0.541 |
secure | -0.500 |
ides | -0.494 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Probe | +2.216 |
Ba | +2.199 |
Asuka | +2.175 |
Instrument | +2.152 |
Amp | +2.132 |
Neg logit contributions | |
ailability | -2.265 |
profit | -2.178 |
arcity | -2.094 |
profits | -2.039 |
secure | -2.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
coord | +0.105 |
Probe | +0.104 |
Ba | +0.104 |
Instrument | +0.103 |
Asuka | +0.103 |
Neg logit contributions | |
profit | -0.108 |
arcity | -0.106 |
ailability | -0.105 |
ides | -0.100 |
secure | -0.100 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Probe | +0.065 |
coord | +0.065 |
Instrument | +0.064 |
Ba | +0.064 |
Asuka | +0.064 |
Neg logit contributions | |
profit | -0.071 |
arcity | -0.069 |
ailability | -0.068 |
secure | -0.066 |
ides | -0.066 |
Token | Bernie |
Token ID | 33433 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
profit | +0.107 |
arcity | +0.103 |
ailability | +0.102 |
secure | +0.098 |
ides | +0.098 |
Neg logit contributions | |
Probe | -0.131 |
coord | -0.130 |
Instrument | -0.129 |
Asuka | -0.129 |
Ba | -0.128 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Probe | +0.837 |
Ba | +0.835 |
Instrument | +0.833 |
coord | +0.831 |
Asuka | +0.826 |
Neg logit contributions | |
profit | -0.527 |
ailability | -0.523 |
arcity | -0.515 |
ides | -0.481 |
secure | -0.478 |
Token | that |
Token ID | 326 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Ba | +1.313 |
Probe | +1.313 |
Instrument | +1.306 |
Asuka | +1.298 |
coord | +1.296 |
Neg logit contributions | |
ailability | -1.062 |
profit | -1.058 |
arcity | -1.045 |
paren | -0.972 |
secure | -0.970 |
Token | hasn |
Token ID | 5818 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
Probe | +0.133 |
Ba | +0.132 |
Instrument | +0.132 |
coord | +0.131 |
Asuka | +0.131 |
Neg logit contributions | |
profit | -0.130 |
ailability | -0.129 |
arcity | -0.128 |
secure | -0.121 |
ides | -0.120 |
Token | 't |
Token ID | 470 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
profit | +0.568 |
arcity | +0.549 |
ailability | +0.542 |
secure | +0.522 |
ides | +0.520 |
Neg logit contributions | |
Probe | -0.699 |
coord | -0.696 |
Instrument | -0.695 |
Ba | -0.692 |
Asuka | -0.690 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
profit | +0.343 |
ailability | +0.339 |
arcity | +0.336 |
secure | +0.317 |
ides | +0.317 |
Neg logit contributions | |
Probe | -0.366 |
Ba | -0.365 |
Instrument | -0.364 |
coord | -0.361 |
Asuka | -0.358 |
Token | an |
Token ID | 281 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Ba | +1.243 |
Probe | +1.241 |
Instrument | +1.235 |
coord | +1.227 |
Asuka | +1.227 |
Neg logit contributions | |
ailability | -1.054 |
profit | -1.053 |
arcity | -1.040 |
paren | -0.974 |
secure | -0.972 |
Token | ounce |
Token ID | 25799 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
Probe | +0.826 |
Ba | +0.825 |
Instrument | +0.821 |
coord | +0.815 |
Asuka | +0.814 |
Neg logit contributions | |
profit | -0.786 |
ailability | -0.784 |
arcity | -0.773 |
secure | -0.727 |
paren | -0.725 |
Token | of |
Token ID | 286 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Ba | +2.660 |
Instrument | +2.647 |
Probe | +2.633 |
Asuka | +2.629 |
coord | +2.608 |
Neg logit contributions | |
ailability | -1.917 |
arcity | -1.870 |
profit | -1.868 |
paren | -1.745 |
peril | -1.720 |
Token | power |
Token ID | 1176 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
profit | +0.214 |
ailability | +0.213 |
arcity | +0.209 |
secure | +0.197 |
peril | +0.196 |
Neg logit contributions | |
Probe | -0.263 |
Ba | -0.262 |
Instrument | -0.261 |
coord | -0.259 |
Asuka | -0.258 |
Token | over |
Token ID | 625 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
profit | +0.163 |
ailability | +0.161 |
arcity | +0.160 |
secure | +0.150 |
ides | +0.150 |
Neg logit contributions | |
Probe | -0.178 |
Ba | -0.177 |
Instrument | -0.176 |
coord | -0.175 |
Asuka | -0.175 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
profit | +0.337 |
ailability | +0.333 |
arcity | +0.329 |
ides | +0.312 |
secure | +0.311 |
Neg logit contributions | |
Probe | -0.378 |
Ba | -0.376 |
Instrument | -0.376 |
coord | -0.375 |
Asuka | -0.373 |
Token | past |
Token ID | 1613 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
profit | +0.117 |
ailability | +0.116 |
arcity | +0.114 |
secure | +0.107 |
paren | +0.107 |
Neg logit contributions | |
Probe | -0.157 |
Ba | -0.156 |
Instrument | -0.156 |
coord | -0.155 |
Asuka | -0.155 |
Token | exposing |
Token ID | 21294 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Probe | +1.321 |
Ba | +1.319 |
Instrument | +1.312 |
coord | +1.301 |
Asuka | +1.301 |
Neg logit contributions | |
ailability | -1.450 |
profit | -1.448 |
arcity | -1.429 |
secure | -1.347 |
paren | -1.344 |
Token | it |
Token ID | 340 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Probe | +1.699 |
Ba | +1.694 |
Instrument | +1.684 |
Asuka | +1.674 |
coord | +1.671 |
Neg logit contributions | |
ailability | -1.736 |
profit | -1.730 |
arcity | -1.709 |
secure | -1.603 |
paren | -1.596 |
Token | to |
Token ID | 284 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
profit | +0.164 |
ailability | +0.164 |
arcity | +0.162 |
secure | +0.152 |
paren | +0.152 |
Neg logit contributions | |
Probe | -0.180 |
Ba | -0.180 |
Instrument | -0.179 |
coord | -0.178 |
Asuka | -0.178 |
Token | temperatures |
Token ID | 10101 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
profit | +0.276 |
ailability | +0.271 |
arcity | +0.270 |
peril | +0.261 |
ides | +0.259 |
Neg logit contributions | |
Ba | -0.292 |
Probe | -0.291 |
Instrument | -0.291 |
coord | -0.290 |
Asuka | -0.287 |
Token | that |
Token ID | 326 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
profit | +0.897 |
ailability | +0.877 |
arcity | +0.875 |
peril | +0.846 |
ides | +0.841 |
Neg logit contributions | |
Ba | -1.137 |
Probe | -1.130 |
Instrument | -1.125 |
coord | -1.124 |
Asuka | -1.118 |
Token | reached |
Token ID | 4251 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
Ba | +0.033 |
Probe | +0.033 |
Instrument | +0.033 |
coord | +0.032 |
Asuka | +0.032 |
Neg logit contributions | |
profit | -0.030 |
ailability | -0.029 |
arcity | -0.029 |
peril | -0.028 |
secure | -0.028 |
Token | 185 |
Token ID | 22855 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Probe | +2.214 |
Ba | +2.208 |
Instrument | +2.202 |
Asuka | +2.181 |
coord | +2.176 |
Neg logit contributions | |
ailability | -2.284 |
profit | -2.278 |
arcity | -2.250 |
secure | -2.126 |
paren | -2.116 |
Token | degrees |
Token ID | 7370 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Ba | +0.149 |
Probe | +0.149 |
Instrument | +0.148 |
coord | +0.147 |
Asuka | +0.147 |
Neg logit contributions | |
profit | -0.152 |
ailability | -0.152 |
arcity | -0.150 |
secure | -0.141 |
paren | -0.140 |
Token | F |
Token ID | 376 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
profit | +0.856 |
ailability | +0.853 |
arcity | +0.837 |
secure | +0.772 |
paren | +0.771 |
Neg logit contributions | |
Probe | -1.447 |
Ba | -1.445 |
Instrument | -1.438 |
coord | -1.430 |
Asuka | -1.429 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
profit | +0.022 |
ailability | +0.022 |
arcity | +0.021 |
secure | +0.020 |
paren | +0.020 |
Neg logit contributions | |
Probe | -0.022 |
Ba | -0.022 |
Instrument | -0.022 |
coord | -0.022 |
Asuka | -0.022 |
Token | 85 |
Token ID | 7600 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
profit | +0.216 |
ailability | +0.214 |
arcity | +0.211 |
peril | +0.202 |
ides | +0.201 |
Neg logit contributions | |
Probe | -0.217 |
Ba | -0.217 |
Instrument | -0.216 |
coord | -0.215 |
Asuka | -0.214 |
Token | � |
Token ID | 250 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Ba | +1.519 |
Probe | +1.517 |
Instrument | +1.509 |
coord | +1.500 |
Asuka | +1.496 |
Neg logit contributions | |
ailability | -1.101 |
profit | -1.099 |
arcity | -1.086 |
secure | -1.006 |
paren | -1.004 |
Token | S |
Token ID | 50 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
Probe | +0.074 |
Instrument | +0.073 |
Ba | +0.073 |
coord | +0.073 |
Asuka | +0.073 |
Neg logit contributions | |
profit | -0.068 |
ailability | -0.067 |
arcity | -0.066 |
secure | -0.063 |
paren | -0.062 |
Token | egu |
Token ID | 15703 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Probe | +0.046 |
Instrument | +0.046 |
Ba | +0.046 |
Asuka | +0.046 |
coord | +0.046 |
Neg logit contributions | |
profit | -0.046 |
ailability | -0.046 |
arcity | -0.046 |
ides | -0.043 |
secure | -0.043 |
Token | in |
Token ID | 259 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Ba | +0.892 |
Probe | +0.889 |
Instrument | +0.883 |
coord | +0.874 |
Asuka | +0.871 |
Neg logit contributions | |
ailability | -1.492 |
profit | -1.492 |
arcity | -1.473 |
secure | -1.407 |
paren | -1.404 |
Token | City |
Token ID | 2254 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Probe | +0.507 |
Ba | +0.506 |
Instrument | +0.504 |
coord | +0.501 |
Asuka | +0.500 |
Neg logit contributions | |
profit | -0.494 |
ailability | -0.492 |
arcity | -0.485 |
secure | -0.459 |
ides | -0.457 |
Token | Council |
Token ID | 4281 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
Probe | +0.186 |
Ba | +0.186 |
Instrument | +0.185 |
coord | +0.184 |
Asuka | +0.184 |
Neg logit contributions | |
profit | -0.195 |
ailability | -0.193 |
arcity | -0.191 |
secure | -0.181 |
ides | -0.180 |
Token | man |
Token ID | 805 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
Probe | +2.770 |
Instrument | +2.759 |
Ba | +2.758 |
coord | +2.730 |
Asuka | +2.697 |
Neg logit contributions | |
ailability | -2.770 |
profit | -2.727 |
arcity | -2.703 |
secure | -2.533 |
paren | -2.528 |
Token | H |
Token ID | 367 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Ba | +2.178 |
Probe | +2.177 |
Instrument | +2.173 |
Asuka | +2.152 |
coord | +2.130 |
Neg logit contributions | |
ailability | -2.046 |
profit | -2.015 |
arcity | -1.992 |
secure | -1.865 |
paren | -1.853 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Probe | +0.250 |
Ba | +0.249 |
Instrument | +0.248 |
coord | +0.246 |
Asuka | +0.246 |
Neg logit contributions | |
profit | -0.219 |
ailability | -0.218 |
arcity | -0.215 |
secure | -0.202 |
ides | -0.201 |
Token | A |
Token ID | 317 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Probe | +0.795 |
Ba | +0.794 |
Instrument | +0.791 |
coord | +0.786 |
Asuka | +0.784 |
Neg logit contributions | |
profit | -0.768 |
ailability | -0.765 |
arcity | -0.755 |
secure | -0.712 |
paren | -0.709 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Ba | +0.437 |
Probe | +0.437 |
Instrument | +0.434 |
Asuka | +0.431 |
coord | +0.431 |
Neg logit contributions | |
profit | -0.313 |
ailability | -0.313 |
arcity | -0.307 |
secure | -0.286 |
paren | -0.285 |