Token | the |
Token ID | 262 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Defender | +0.564 |
ilan | +0.546 |
shade | +0.541 |
Interstitial | +0.539 |
tein | +0.535 |
Neg logit contributions | |
resa | -0.625 |
Scotland | -0.534 |
Ireland | -0.474 |
Mitt | -0.473 |
Vice | -0.458 |
Token | Laser |
Token ID | 23222 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Defender | +0.201 |
ilan | +0.195 |
shade | +0.192 |
Interstitial | +0.192 |
tein | +0.190 |
Neg logit contributions | |
resa | -0.241 |
Scotland | -0.206 |
Mitt | -0.184 |
Ireland | -0.184 |
Vice | -0.178 |
Token | Inter |
Token ID | 4225 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Defender | +0.487 |
ilan | +0.465 |
shade | +0.464 |
Interstitial | +0.457 |
tein | +0.456 |
Neg logit contributions | |
resa | -0.725 |
Scotland | -0.630 |
Ireland | -0.571 |
Mitt | -0.567 |
Vice | -0.554 |
Token | fer |
Token ID | 2232 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
resa | +2.581 |
Scotland | +2.276 |
Mitt | +2.075 |
Ireland | +2.073 |
Vice | +2.033 |
Neg logit contributions | |
Defender | -1.335 |
shade | -1.267 |
ilan | -1.257 |
Interstitial | -1.245 |
tein | -1.240 |
Token | ometer |
Token ID | 15635 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
resa | +2.481 |
Scotland | +1.990 |
Mitt | +1.746 |
Ireland | +1.696 |
Hub | +1.638 |
Neg logit contributions | |
Defender | -3.348 |
shade | -3.267 |
Interstitial | -3.244 |
ilan | -3.225 |
tein | -3.200 |
Token | Grav |
Token ID | 32599 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
resa | +1.622 |
Scotland | +1.362 |
Mitt | +1.227 |
Ireland | +1.180 |
Vice | +1.148 |
Neg logit contributions | |
Defender | -1.674 |
ilan | -1.651 |
tein | -1.634 |
shade | -1.617 |
lycer | -1.617 |
Token | itational |
Token ID | 22181 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
resa | +3.764 |
Scotland | +3.193 |
Ireland | +2.780 |
Mitt | +2.778 |
ersive | +2.662 |
Neg logit contributions | |
Defender | -4.266 |
shade | -4.139 |
Interstitial | -4.090 |
ilan | -3.999 |
inventoryQuantity | -3.970 |
Token | - |
Token ID | 12 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
resa | +1.657 |
Scotland | +1.406 |
Mitt | +1.304 |
Ireland | +1.235 |
Hub | +1.197 |
Neg logit contributions | |
ilan | -1.475 |
Defender | -1.474 |
Interstitial | -1.464 |
shade | -1.458 |
inventoryQuantity | -1.421 |
Token | wave |
Token ID | 19204 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
resa | +0.206 |
Scotland | +0.179 |
Ireland | +0.162 |
Mitt | +0.161 |
Vice | +0.157 |
Neg logit contributions | |
Defender | -0.143 |
ilan | -0.137 |
shade | -0.137 |
Interstitial | -0.135 |
tein | -0.135 |
Token | Observatory |
Token ID | 25758 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Defender | +0.775 |
ilan | +0.740 |
shade | +0.739 |
Interstitial | +0.727 |
tein | +0.725 |
Neg logit contributions | |
resa | -1.184 |
Scotland | -1.029 |
Ireland | -0.934 |
Mitt | -0.928 |
Vice | -0.908 |
Token | ( |
Token ID | 357 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
resa | +0.559 |
Scotland | +0.471 |
Mitt | +0.419 |
Ireland | +0.414 |
Task | +0.400 |
Neg logit contributions | |
Defender | -0.557 |
ilan | -0.541 |
Interstitial | -0.538 |
shade | -0.534 |
tein | -0.532 |
Token | "> |
Token ID | 5320 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
resa | +1.117 |
Scotland | +0.949 |
Ireland | +0.853 |
Mitt | +0.847 |
Task | +0.842 |
Neg logit contributions | |
Defender | -1.002 |
ilan | -0.971 |
tein | -0.967 |
shade | -0.959 |
Interstitial | -0.944 |
Token | < |
Token ID | 1279 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
resa | +0.195 |
Scotland | +0.167 |
Ireland | +0.150 |
Mitt | +0.148 |
Task | +0.146 |
Neg logit contributions | |
Defender | -0.168 |
ilan | -0.163 |
tein | -0.162 |
shade | -0.162 |
Interstitial | -0.159 |
Token | ul |
Token ID | 377 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
resa | +1.360 |
Scotland | +1.140 |
Ireland | +1.024 |
Task | +1.000 |
Mitt | +0.993 |
Neg logit contributions | |
Defender | -1.316 |
shade | -1.258 |
ilan | -1.255 |
tein | -1.254 |
Interstitial | -1.232 |
Token | > |
Token ID | 29 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
resa | +1.020 |
Scotland | +0.874 |
Mitt | +0.794 |
Ireland | +0.791 |
Task | +0.775 |
Neg logit contributions | |
Defender | -0.815 |
ilan | -0.786 |
Interstitial | -0.782 |
tein | -0.775 |
shade | -0.773 |
Token | < |
Token ID | 1279 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Defender | +0.819 |
ilan | +0.788 |
shade | +0.786 |
tein | +0.776 |
Interstitial | +0.776 |
Neg logit contributions | |
resa | -1.004 |
Scotland | -0.858 |
Ireland | -0.772 |
Mitt | -0.766 |
Vice | -0.748 |
Token | li |
Token ID | 4528 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
resa | +1.215 |
Scotland | +1.063 |
Ireland | +0.974 |
Mitt | +0.963 |
Task | +0.955 |
Neg logit contributions | |
Defender | -0.665 |
shade | -0.628 |
ilan | -0.622 |
tein | -0.617 |
Interstitial | -0.615 |
Token | ng |
Token ID | 23370 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
resa | +4.287 |
Scotland | +3.689 |
Mitt | +3.381 |
Ireland | +3.341 |
Task | +3.301 |
Neg logit contributions | |
Defender | -3.343 |
ilan | -3.196 |
Interstitial | -3.193 |
tein | -3.162 |
inventoryQuantity | -3.132 |
Token | - |
Token ID | 12 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
Defender | +1.076 |
ilan | +1.032 |
shade | +1.031 |
Interstitial | +1.017 |
tein | +1.013 |
Neg logit contributions | |
resa | -1.413 |
Scotland | -1.216 |
Ireland | -1.094 |
Mitt | -1.088 |
Vice | -1.061 |
Token | repeat |
Token ID | 44754 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
resa | +0.811 |
Scotland | +0.705 |
Ireland | +0.643 |
Mitt | +0.633 |
Task | +0.627 |
Neg logit contributions | |
Defender | -0.496 |
shade | -0.476 |
Interstitial | -0.472 |
ilan | -0.465 |
tein | -0.463 |
Token | =" |
Token ID | 2625 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
resa | +0.802 |
Scotland | +0.649 |
Mitt | +0.567 |
Task | +0.556 |
Ireland | +0.555 |
Neg logit contributions | |
Defender | -1.171 |
ilan | -1.148 |
shade | -1.144 |
Interstitial | -1.136 |
tein | -1.135 |
Token | phone |
Token ID | 4862 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Defender | +0.912 |
shade | +0.878 |
ilan | +0.877 |
tein | +0.865 |
Interstitial | +0.862 |
Neg logit contributions | |
resa | -0.991 |
Scotland | -0.842 |
Ireland | -0.751 |
Mitt | -0.742 |
Vice | -0.725 |
Token | "> |
Token ID | 5320 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
resa | +0.731 |
Scotland | +0.619 |
Ireland | +0.558 |
Mitt | +0.556 |
Task | +0.549 |
Neg logit contributions | |
Defender | -0.635 |
ilan | -0.613 |
tein | -0.610 |
shade | -0.605 |
Interstitial | -0.603 |
Token | < |
Token ID | 1279 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Defender | +0.077 |
ilan | +0.074 |
shade | +0.073 |
tein | +0.073 |
Interstitial | +0.073 |
Neg logit contributions | |
resa | -0.088 |
Scotland | -0.075 |
Ireland | -0.068 |
Mitt | -0.067 |
Vice | -0.066 |
Token | ul |
Token ID | 377 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
resa | +1.061 |
Scotland | +0.865 |
Ireland | +0.759 |
Mitt | +0.744 |
Task | +0.733 |
Neg logit contributions | |
Defender | -1.296 |
shade | -1.247 |
ilan | -1.239 |
tein | -1.235 |
Interstitial | -1.223 |
Token | > |
Token ID | 29 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
resa | +1.653 |
Scotland | +1.414 |
Mitt | +1.292 |
Ireland | +1.280 |
Vice | +1.257 |
Neg logit contributions | |
Defender | -1.288 |
ilan | -1.237 |
Interstitial | -1.235 |
tein | -1.214 |
shade | -1.209 |
Token | < |
Token ID | 1279 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Defender | +0.854 |
ilan | +0.823 |
shade | +0.818 |
Interstitial | +0.809 |
tein | +0.808 |
Neg logit contributions | |
resa | -1.031 |
Scotland | -0.880 |
Ireland | -0.793 |
Mitt | -0.788 |
Vice | -0.768 |
Token | li |
Token ID | 4528 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
resa | +0.918 |
Scotland | +0.799 |
Ireland | +0.734 |
Mitt | +0.723 |
Task | +0.716 |
Neg logit contributions | |
Defender | -0.519 |
shade | -0.493 |
ilan | -0.484 |
tein | -0.482 |
Interstitial | -0.479 |
Token | ng |
Token ID | 23370 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
resa | +4.295 |
Scotland | +3.652 |
Mitt | +3.391 |
Ireland | +3.340 |
Vice | +3.305 |
Neg logit contributions | |
Defender | -3.210 |
ilan | -3.064 |
Interstitial | -3.028 |
tein | -2.941 |
shade | -2.906 |
Token | - |
Token ID | 12 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Defender | +1.175 |
shade | +1.127 |
ilan | +1.126 |
Interstitial | +1.110 |
tein | +1.109 |
Neg logit contributions | |
resa | -1.613 |
Scotland | -1.391 |
Ireland | -1.253 |
Mitt | -1.247 |
Vice | -1.214 |
Token | repeat |
Token ID | 44754 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
resa | +0.221 |
Scotland | +0.191 |
Ireland | +0.173 |
Mitt | +0.171 |
Vice | +0.169 |
Neg logit contributions | |
Defender | -0.150 |
shade | -0.143 |
ilan | -0.143 |
Interstitial | -0.142 |
tein | -0.140 |
Token | =" |
Token ID | 2625 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
resa | +0.901 |
Scotland | +0.738 |
Ireland | +0.637 |
Mitt | +0.634 |
Vice | +0.612 |
Neg logit contributions | |
Defender | -1.176 |
ilan | -1.139 |
shade | -1.138 |
Interstitial | -1.125 |
tein | -1.123 |
Token | phone |
Token ID | 4862 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
Defender | +1.432 |
shade | +1.382 |
ilan | +1.381 |
Interstitial | +1.363 |
tein | +1.362 |
Neg logit contributions | |
resa | -1.342 |
Scotland | -1.122 |
Ireland | -0.988 |
Mitt | -0.978 |
Vice | -0.950 |
Token | }} |
Token ID | 34949 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Defender | +0.116 |
ilan | +0.112 |
shade | +0.111 |
Interstitial | +0.110 |
tein | +0.110 |
Neg logit contributions | |
resa | -0.124 |
Scotland | -0.105 |
Ireland | -0.093 |
Mitt | -0.092 |
Vice | -0.090 |
Token |
|
Token ID | 3556 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Defender | +0.330 |
ilan | +0.321 |
shade | +0.319 |
Interstitial | +0.316 |
tein | +0.316 |
Neg logit contributions | |
resa | -0.271 |
Scotland | -0.223 |
Ireland | -0.194 |
Mitt | -0.193 |
Task | -0.187 |
Token | p |
Token ID | 79 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
resa | +1.904 |
Scotland | +1.651 |
Ireland | +1.510 |
Mitt | +1.507 |
Vice | +1.478 |
Neg logit contributions | |
Defender | -1.070 |
shade | -1.003 |
ilan | -0.987 |
Interstitial | -0.979 |
tein | -0.974 |
Token | > |
Token ID | 29 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
resa | +2.824 |
Scotland | +2.413 |
Mitt | +2.152 |
Ireland | +2.132 |
Vice | +2.107 |
Neg logit contributions | |
Defender | -2.429 |
ilan | -2.340 |
Interstitial | -2.328 |
tein | -2.302 |
shade | -2.292 |
Token | |
Token ID | 7359 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Defender | +1.374 |
ilan | +1.329 |
shade | +1.327 |
Interstitial | +1.312 |
tein | +1.309 |
Neg logit contributions | |
resa | -1.254 |
Scotland | -1.047 |
Ireland | -0.919 |
Mitt | -0.912 |
Vice | -0.884 |
Token | li |
Token ID | 4528 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
resa | +2.617 |
Scotland | +2.242 |
Ireland | +2.059 |
Mitt | +2.042 |
Vice | +2.010 |
Neg logit contributions | |
Defender | -1.589 |
shade | -1.505 |
ilan | -1.449 |
Interstitial | -1.445 |
tein | -1.445 |
Token | > |
Token ID | 29 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
resa | +3.918 |
Scotland | +3.338 |
Ireland | +2.975 |
Mitt | +2.969 |
Vice | +2.920 |
Neg logit contributions | |
Defender | -3.331 |
ilan | -3.198 |
Interstitial | -3.166 |
shade | -3.151 |
tein | -3.122 |
Token | |
Token ID | 7359 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Defender | +1.181 |
ilan | +1.144 |
shade | +1.142 |
Interstitial | +1.129 |
tein | +1.128 |
Neg logit contributions | |
resa | -1.082 |
Scotland | -0.903 |
Ireland | -0.794 |
Mitt | -0.789 |
Vice | -0.765 |
Token | ul |
Token ID | 377 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
resa | +1.336 |
Scotland | +1.068 |
Ireland | +0.927 |
Mitt | +0.913 |
Vice | +0.889 |
Neg logit contributions | |
Defender | -1.799 |
shade | -1.740 |
ilan | -1.720 |
Interstitial | -1.713 |
tein | -1.707 |
Token | > |
Token ID | 29 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
resa | +0.820 |
Scotland | +0.704 |
Ireland | +0.634 |
Mitt | +0.632 |
Vice | +0.617 |
Neg logit contributions | |
Defender | -0.613 |
ilan | -0.587 |
shade | -0.580 |
Interstitial | -0.580 |
tein | -0.574 |
Token | |
Token ID | 7359 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Defender | +0.770 |
ilan | +0.747 |
shade | +0.744 |
tein | +0.737 |
Interstitial | +0.736 |
Neg logit contributions | |
resa | -0.733 |
Scotland | -0.614 |
Ireland | -0.543 |
Mitt | -0.540 |
Vice | -0.525 |
Token | group |
Token ID | 1448 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
resa | +0.099 |
Scotland | +0.083 |
Mitt | +0.072 |
Ireland | +0.072 |
Vice | +0.070 |
Neg logit contributions | |
Defender | -0.109 |
ilan | -0.106 |
Interstitial | -0.106 |
shade | -0.106 |
tein | -0.105 |
Token | Raqqa |
Token ID | 30391 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
resa | +1.238 |
Scotland | +1.055 |
Mitt | +0.948 |
Ireland | +0.931 |
Vice | +0.906 |
Neg logit contributions | |
Defender | -1.106 |
Interstitial | -1.083 |
ilan | -1.077 |
shade | -1.075 |
tein | -1.069 |
Token | is |
Token ID | 318 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Defender | +0.381 |
ilan | +0.368 |
shade | +0.368 |
Interstitial | +0.365 |
tein | +0.363 |
Neg logit contributions | |
resa | -0.442 |
Scotland | -0.377 |
Ireland | -0.337 |
Mitt | -0.335 |
Vice | -0.326 |
Token | Being |
Token ID | 11204 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Defender | +0.346 |
ilan | +0.333 |
shade | +0.333 |
Interstitial | +0.328 |
tein | +0.327 |
Neg logit contributions | |
resa | -0.298 |
Scotland | -0.247 |
Ireland | -0.217 |
Mitt | -0.214 |
Vice | -0.208 |
Token | Sl |
Token ID | 3454 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Defender | +0.312 |
ilan | +0.299 |
shade | +0.298 |
tein | +0.293 |
Interstitial | +0.290 |
Neg logit contributions | |
resa | -0.238 |
Scotland | -0.195 |
Ireland | -0.171 |
Mitt | -0.165 |
Vice | -0.163 |
Token | aughtered |
Token ID | 32734 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
resa | +0.635 |
Scotland | +0.550 |
Ireland | +0.496 |
Mitt | +0.492 |
Vice | +0.481 |
Neg logit contributions | |
Defender | -0.480 |
ilan | -0.463 |
shade | -0.460 |
tein | -0.453 |
Interstitial | -0.451 |
Token | Sil |
Token ID | 4243 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
resa | +3.224 |
Scotland | +2.722 |
Mitt | +2.465 |
Ireland | +2.383 |
Vice | +2.317 |
Neg logit contributions | |
Defender | -3.747 |
shade | -3.702 |
Interstitial | -3.698 |
ilan | -3.681 |
tein | -3.647 |
Token | ently |
Token ID | 1473 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Defender | +0.169 |
Interstitial | +0.166 |
shade | +0.162 |
ilan | +0.162 |
tein | +0.162 |
Neg logit contributions | |
resa | -0.179 |
Scotland | -0.152 |
Ireland | -0.135 |
Mitt | -0.134 |
Vice | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
resa | +0.470 |
Scotland | +0.394 |
Ireland | +0.346 |
Mitt | +0.345 |
Vice | +0.333 |
Neg logit contributions | |
Defender | -0.493 |
ilan | -0.479 |
shade | -0.478 |
Interstitial | -0.476 |
tein | -0.474 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
resa | +0.803 |
Scotland | +0.692 |
Ireland | +0.620 |
Mitt | +0.619 |
Vice | +0.602 |
Neg logit contributions | |
Defender | -0.650 |
shade | -0.629 |
ilan | -0.629 |
tein | -0.624 |
Interstitial | -0.622 |
Token |
|
Token ID | 198 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
resa | +0.889 |
Scotland | +0.768 |
Ireland | +0.693 |
Mitt | +0.689 |
Vice | +0.672 |
Neg logit contributions | |
Defender | -0.658 |
ilan | -0.632 |
shade | -0.631 |
Interstitial | -0.622 |
tein | -0.620 |
Token | , |
Token ID | 11 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
resa | +1.577 |
Scotland | +1.338 |
Mitt | +1.190 |
Ireland | +1.187 |
Vice | +1.149 |
Neg logit contributions | |
Defender | -1.477 |
ilan | -1.426 |
shade | -1.418 |
Interstitial | -1.413 |
tein | -1.403 |
Token | but |
Token ID | 475 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
resa | +0.337 |
Scotland | +0.286 |
Ireland | +0.255 |
Mitt | +0.252 |
Vice | +0.246 |
Neg logit contributions | |
Defender | -0.303 |
shade | -0.291 |
ilan | -0.291 |
Interstitial | -0.287 |
tein | -0.286 |
Token | will |
Token ID | 481 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
resa | +0.449 |
Scotland | +0.375 |
Ireland | +0.329 |
Mitt | +0.322 |
Vice | +0.314 |
Neg logit contributions | |
Defender | -0.497 |
shade | -0.480 |
ilan | -0.477 |
Interstitial | -0.470 |
tein | -0.470 |
Token | need |
Token ID | 761 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
resa | +1.143 |
Scotland | +0.967 |
Ireland | +0.857 |
Mitt | +0.854 |
Vice | +0.827 |
Neg logit contributions | |
Defender | -1.093 |
ilan | -1.057 |
shade | -1.050 |
Interstitial | -1.044 |
tein | -1.038 |
Token | 60 |
Token ID | 3126 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
resa | +1.169 |
Scotland | +0.976 |
Mitt | +0.858 |
Ireland | +0.851 |
Vice | +0.825 |
Neg logit contributions | |
Defender | -1.318 |
ilan | -1.277 |
Interstitial | -1.271 |
shade | -1.270 |
tein | -1.262 |
Token | votes |
Token ID | 5690 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
resa | +1.652 |
Scotland | +1.409 |
Mitt | +1.267 |
Ireland | +1.259 |
Vice | +1.229 |
Neg logit contributions | |
Defender | -1.404 |
ilan | -1.350 |
shade | -1.346 |
Interstitial | -1.345 |
tein | -1.322 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
resa | +3.483 |
Scotland | +2.944 |
Mitt | +2.663 |
Ireland | +2.587 |
Vice | +2.526 |
Neg logit contributions | |
Defender | -3.487 |
Interstitial | -3.385 |
ilan | -3.384 |
shade | -3.351 |
tein | -3.309 |
Token | pass |
Token ID | 1208 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
resa | +1.221 |
Scotland | +1.041 |
Mitt | +0.935 |
Ireland | +0.926 |
Vice | +0.902 |
Neg logit contributions | |
Defender | -1.035 |
ilan | -1.006 |
Interstitial | -0.995 |
shade | -0.987 |
tein | -0.984 |
Token | the |
Token ID | 262 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
resa | +0.858 |
Scotland | +0.726 |
Ireland | +0.644 |
Mitt | +0.643 |
Vice | +0.623 |
Neg logit contributions | |
Defender | -0.822 |
ilan | -0.794 |
shade | -0.790 |
Interstitial | -0.783 |
tein | -0.781 |
Token | Senate |
Token ID | 3845 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
resa | +0.351 |
Scotland | +0.275 |
Ireland | +0.227 |
Mitt | +0.221 |
Vice | +0.212 |
Neg logit contributions | |
Defender | -0.635 |
shade | -0.616 |
ilan | -0.615 |
Interstitial | -0.609 |
tein | -0.607 |
Token | , |
Token ID | 11 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
resa | +0.373 |
Scotland | +0.314 |
Ireland | +0.278 |
Mitt | +0.278 |
Vice | +0.269 |
Neg logit contributions | |
Defender | -0.363 |
ilan | -0.351 |
shade | -0.350 |
Interstitial | -0.346 |
tein | -0.345 |
Token | ) |
Token ID | 8 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
resa | +2.185 |
Scotland | +1.801 |
Mitt | +1.583 |
Ireland | +1.551 |
Task | +1.494 |
Neg logit contributions | |
Defender | -2.577 |
Interstitial | -2.506 |
ilan | -2.496 |
shade | -2.463 |
tein | -2.459 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
resa | +0.150 |
Scotland | +0.126 |
Ireland | +0.111 |
Mitt | +0.110 |
Vice | +0.107 |
Neg logit contributions | |
Defender | -0.156 |
ilan | -0.151 |
shade | -0.151 |
Interstitial | -0.149 |
tein | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
resa | +0.173 |
Scotland | +0.147 |
Mitt | +0.131 |
Ireland | +0.131 |
Vice | +0.126 |
Neg logit contributions | |
Defender | -0.154 |
ilan | -0.150 |
shade | -0.148 |
Interstitial | -0.148 |
tein | -0.147 |
Token | University |
Token ID | 2059 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
Defender | +0.021 |
ilan | +0.021 |
shade | +0.020 |
Interstitial | +0.020 |
tein | +0.020 |
Neg logit contributions | |
resa | -0.020 |
Scotland | -0.017 |
Ireland | -0.015 |
Mitt | -0.015 |
Vice | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Defender | +0.049 |
ilan | +0.047 |
shade | +0.047 |
Interstitial | +0.046 |
tein | +0.046 |
Neg logit contributions | |
resa | -0.058 |
Scotland | -0.049 |
Ireland | -0.044 |
Mitt | -0.044 |
Vice | -0.043 |
Token | Calgary |
Token ID | 17842 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
Defender | +0.141 |
ilan | +0.137 |
shade | +0.137 |
Interstitial | +0.136 |
tein | +0.135 |
Neg logit contributions | |
resa | -0.127 |
Scotland | -0.106 |
Ireland | -0.093 |
Mitt | -0.093 |
Vice | -0.089 |
Token | ( |
Token ID | 357 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
resa | +3.433 |
Scotland | +2.882 |
Mitt | +2.579 |
Ireland | +2.508 |
Task | +2.411 |
Neg logit contributions | |
Defender | -3.519 |
ilan | -3.458 |
Interstitial | -3.427 |
inventoryQuantity | -3.395 |
shade | -3.392 |
Token | which |
Token ID | 4758 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
resa | +0.157 |
Scotland | +0.137 |
Ireland | +0.125 |
Mitt | +0.123 |
Vice | +0.121 |
Neg logit contributions | |
Defender | -0.099 |
shade | -0.095 |
ilan | -0.095 |
tein | -0.093 |
Interstitial | -0.093 |
Token | has |
Token ID | 468 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
resa | +0.196 |
Scotland | +0.165 |
Mitt | +0.147 |
Ireland | +0.146 |
Vice | +0.140 |
Neg logit contributions | |
Defender | -0.193 |
ilan | -0.188 |
Interstitial | -0.186 |
shade | -0.185 |
tein | -0.185 |
Token | the |
Token ID | 262 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
resa | +0.065 |
Scotland | +0.055 |
Ireland | +0.049 |
Mitt | +0.049 |
Vice | +0.048 |
Neg logit contributions | |
Defender | -0.060 |
ilan | -0.058 |
shade | -0.058 |
Interstitial | -0.057 |
tein | -0.057 |
Token | Hyp |
Token ID | 21209 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
resa | +0.060 |
Scotland | +0.051 |
Mitt | +0.046 |
Ireland | +0.046 |
Vice | +0.044 |
Neg logit contributions | |
Defender | -0.048 |
ilan | -0.047 |
Interstitial | -0.046 |
shade | -0.046 |
tein | -0.046 |
Token | Radio |
Token ID | 8829 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Defender | +0.361 |
ilan | +0.348 |
shade | +0.345 |
Interstitial | +0.342 |
tein | +0.340 |
Neg logit contributions | |
resa | -0.609 |
Scotland | -0.530 |
Ireland | -0.483 |
Mitt | -0.482 |
Vice | -0.470 |
Token | website |
Token ID | 3052 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
resa | +0.111 |
Scotland | +0.095 |
Ireland | +0.085 |
Mitt | +0.084 |
Vice | +0.082 |
Neg logit contributions | |
Defender | -0.094 |
ilan | -0.091 |
shade | -0.091 |
Interstitial | -0.090 |
tein | -0.089 |
Token | will |
Token ID | 481 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
resa | +0.483 |
Scotland | +0.405 |
Ireland | +0.358 |
Mitt | +0.357 |
Vice | +0.345 |
Neg logit contributions | |
Defender | -0.495 |
ilan | -0.481 |
shade | -0.476 |
Interstitial | -0.474 |
tein | -0.473 |
Token | look |
Token ID | 804 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Defender | +0.634 |
shade | +0.614 |
ilan | +0.608 |
Interstitial | +0.601 |
tein | +0.601 |
Neg logit contributions | |
resa | -0.631 |
Scotland | -0.532 |
Ireland | -0.471 |
Mitt | -0.466 |
Vice | -0.455 |
Token | a |
Token ID | 257 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
resa | +0.439 |
Scotland | +0.371 |
Ireland | +0.328 |
Mitt | +0.327 |
Vice | +0.316 |
Neg logit contributions | |
Defender | -0.425 |
ilan | -0.410 |
shade | -0.409 |
Interstitial | -0.405 |
tein | -0.404 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
resa | +0.375 |
Scotland | +0.315 |
Ireland | +0.278 |
Mitt | +0.277 |
Task | +0.267 |
Neg logit contributions | |
Defender | -0.380 |
ilan | -0.367 |
Interstitial | -0.364 |
tein | -0.363 |
shade | -0.361 |
Token | different |
Token ID | 1180 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
resa | +3.301 |
Scotland | +2.776 |
Mitt | +2.483 |
Ireland | +2.423 |
Task | +2.307 |
Neg logit contributions | |
Defender | -3.624 |
ilan | -3.557 |
tein | -3.546 |
Interstitial | -3.526 |
lycer | -3.472 |
Token | . |
Token ID | 13 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
resa | +0.486 |
Scotland | +0.413 |
Mitt | +0.368 |
Ireland | +0.367 |
Vice | +0.355 |
Neg logit contributions | |
Defender | -0.443 |
ilan | -0.430 |
tein | -0.424 |
Interstitial | -0.424 |
shade | -0.423 |
Token | The |
Token ID | 383 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Defender | +0.051 |
ilan | +0.049 |
shade | +0.049 |
Interstitial | +0.048 |
tein | +0.048 |
Neg logit contributions | |
resa | -0.069 |
Scotland | -0.059 |
Ireland | -0.054 |
Mitt | -0.053 |
Vice | -0.052 |
Token | player |
Token ID | 2137 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
resa | +0.203 |
Scotland | +0.173 |
Ireland | +0.154 |
Mitt | +0.154 |
Vice | +0.149 |
Neg logit contributions | |
Defender | -0.172 |
ilan | -0.167 |
shade | -0.165 |
Interstitial | -0.164 |
tein | -0.164 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Defender | +0.215 |
ilan | +0.207 |
shade | +0.206 |
Interstitial | +0.204 |
tein | +0.204 |
Neg logit contributions | |
resa | -0.239 |
Scotland | -0.203 |
Ireland | -0.181 |
Mitt | -0.180 |
Vice | -0.175 |
Token | Smith |
Token ID | 17919 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
resa | +0.299 |
Scotland | +0.240 |
Mitt | +0.205 |
Ireland | +0.205 |
Vice | +0.196 |
Neg logit contributions | |
Defender | -0.417 |
ilan | -0.405 |
shade | -0.405 |
Interstitial | -0.400 |
tein | -0.397 |
Token | sonian |
Token ID | 35202 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
resa | +0.781 |
Scotland | +0.680 |
Ireland | +0.616 |
Mitt | +0.608 |
Vice | +0.598 |
Neg logit contributions | |
Defender | -0.500 |
shade | -0.479 |
ilan | -0.477 |
Interstitial | -0.468 |
tein | -0.465 |
Token | Center |
Token ID | 3337 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
resa | +0.699 |
Scotland | +0.580 |
Mitt | +0.504 |
Ireland | +0.501 |
Vice | +0.484 |
Neg logit contributions | |
Defender | -0.860 |
ilan | -0.841 |
shade | -0.837 |
tein | -0.835 |
Interstitial | -0.834 |
Token | for |
Token ID | 329 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
Defender | +0.347 |
ilan | +0.341 |
shade | +0.337 |
tein | +0.335 |
Interstitial | +0.333 |
Neg logit contributions | |
resa | -0.440 |
Scotland | -0.377 |
Mitt | -0.341 |
Ireland | -0.338 |
Vice | -0.330 |
Token | Ast |
Token ID | 8304 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
Defender | +0.040 |
ilan | +0.039 |
tein | +0.038 |
shade | +0.038 |
Interstitial | +0.038 |
Neg logit contributions | |
resa | -0.065 |
Scotland | -0.057 |
Mitt | -0.052 |
Ireland | -0.052 |
Vice | -0.050 |
Token | roph |
Token ID | 10051 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
Defender | +0.039 |
ilan | +0.038 |
shade | +0.037 |
Interstitial | +0.037 |
tein | +0.037 |
Neg logit contributions | |
resa | -0.038 |
Scotland | -0.032 |
Ireland | -0.029 |
Mitt | -0.029 |
Vice | -0.028 |
Token | ysics |
Token ID | 23154 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
resa | +2.874 |
Scotland | +2.330 |
Ireland | +1.959 |
Mitt | +1.951 |
oya | +1.917 |
Neg logit contributions | |
Defender | -4.049 |
Interstitial | -4.030 |
shade | -3.930 |
tein | -3.914 |
inventoryQuantity | -3.870 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
resa | +1.317 |
Scotland | +1.118 |
Mitt | +1.009 |
Ireland | +0.996 |
Task | +0.965 |
Neg logit contributions | |
Defender | -1.165 |
ilan | -1.138 |
Interstitial | -1.135 |
shade | -1.109 |
tein | -1.106 |
Token | his |
Token ID | 465 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
resa | +0.804 |
Scotland | +0.680 |
Mitt | +0.608 |
Ireland | +0.603 |
Vice | +0.583 |
Neg logit contributions | |
Defender | -0.791 |
ilan | -0.773 |
Interstitial | -0.763 |
tein | -0.762 |
shade | -0.761 |
Token | coll |
Token ID | 2927 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
resa | +0.625 |
Scotland | +0.514 |
Mitt | +0.447 |
Ireland | +0.446 |
Vice | +0.429 |
Neg logit contributions | |
Defender | -0.747 |
ilan | -0.726 |
shade | -0.720 |
Interstitial | -0.719 |
tein | -0.716 |
Token | agues |
Token ID | 6120 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
resa | +0.504 |
Scotland | +0.419 |
Ireland | +0.366 |
Mitt | +0.366 |
Vice | +0.354 |
Neg logit contributions | |
Defender | -0.544 |
shade | -0.526 |
ilan | -0.525 |
Interstitial | -0.521 |
tein | -0.519 |
Token | euph |
Token ID | 40381 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
resa | +0.594 |
Scotland | +0.500 |
Mitt | +0.448 |
Ireland | +0.442 |
Vice | +0.428 |
Neg logit contributions | |
Defender | -0.570 |
ilan | -0.556 |
Interstitial | -0.552 |
tein | -0.548 |
shade | -0.546 |
Token | oria |
Token ID | 7661 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
resa | +0.297 |
Scotland | +0.250 |
Ireland | +0.223 |
Mitt | +0.222 |
Vice | +0.216 |
Neg logit contributions | |
Defender | -0.273 |
ilan | -0.262 |
Interstitial | -0.262 |
shade | -0.261 |
tein | -0.260 |
Token | wears |
Token ID | 17326 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
resa | +1.103 |
Scotland | +0.928 |
Mitt | +0.849 |
Ireland | +0.827 |
Vice | +0.800 |
Neg logit contributions | |
Defender | -1.020 |
ilan | -1.011 |
tein | -1.001 |
Interstitial | -0.997 |
shade | -0.974 |
Token | off |
Token ID | 572 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
resa | +0.479 |
Scotland | +0.416 |
Mitt | +0.383 |
Ireland | +0.379 |
Vice | +0.372 |
Neg logit contributions | |
Defender | -0.283 |
tein | -0.282 |
ilan | -0.280 |
Interstitial | -0.279 |
lycer | -0.273 |
Token | a |
Token ID | 257 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
resa | +1.077 |
Scotland | +0.913 |
Mitt | +0.841 |
Ireland | +0.822 |
Vice | +0.795 |
Neg logit contributions | |
Defender | -0.930 |
ilan | -0.909 |
tein | -0.902 |
Interstitial | -0.900 |
shade | -0.884 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
resa | +0.713 |
Scotland | +0.605 |
Mitt | +0.538 |
Ireland | +0.536 |
Vice | +0.516 |
Neg logit contributions | |
Defender | -0.673 |
ilan | -0.653 |
Interstitial | -0.651 |
tein | -0.644 |
shade | -0.643 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
resa | +3.485 |
Scotland | +2.935 |
Mitt | +2.763 |
Ireland | +2.641 |
Vice | +2.554 |
Neg logit contributions | |
Defender | -3.227 |
Interstitial | -3.188 |
ilan | -3.183 |
tein | -3.130 |
shade | -3.028 |
Token | though |
Token ID | 996 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
resa | +0.918 |
Scotland | +0.776 |
Ireland | +0.689 |
Mitt | +0.688 |
Vice | +0.666 |
Neg logit contributions | |
Defender | -0.872 |
ilan | -0.843 |
shade | -0.838 |
Interstitial | -0.833 |
tein | -0.830 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Defender | +0.125 |
ilan | +0.120 |
shade | +0.118 |
Interstitial | +0.118 |
tein | +0.117 |
Neg logit contributions | |
resa | -0.160 |
Scotland | -0.138 |
Mitt | -0.125 |
Ireland | -0.124 |
Vice | -0.121 |
Token | the |
Token ID | 262 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
resa | +0.217 |
Scotland | +0.184 |
Ireland | +0.163 |
Mitt | +0.161 |
Vice | +0.157 |
Neg logit contributions | |
Defender | -0.211 |
shade | -0.204 |
ilan | -0.204 |
Interstitial | -0.201 |
tein | -0.200 |
Token | question |
Token ID | 1808 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
resa | +0.615 |
Scotland | +0.515 |
Mitt | +0.458 |
Ireland | +0.456 |
Vice | +0.441 |
Neg logit contributions | |
Defender | -0.598 |
ilan | -0.581 |
Interstitial | -0.576 |
shade | -0.574 |
tein | -0.571 |
Token | It |
Token ID | 1026 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
resa | +0.327 |
Scotland | +0.278 |
Ireland | +0.246 |
Mitt | +0.244 |
Vice | +0.238 |
Neg logit contributions | |
Defender | -0.310 |
shade | -0.300 |
ilan | -0.300 |
tein | -0.296 |
Interstitial | -0.295 |
Token | � |
Token ID | 447 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
resa | +0.062 |
Scotland | +0.052 |
Ireland | +0.046 |
Mitt | +0.046 |
Vice | +0.045 |
Neg logit contributions | |
Defender | -0.057 |
ilan | -0.055 |
shade | -0.055 |
Interstitial | -0.054 |
tein | -0.054 |
Token | � |
Token ID | 247 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
resa | +0.006 |
Scotland | +0.005 |
Ireland | +0.004 |
Mitt | +0.004 |
Vice | +0.004 |
Neg logit contributions | |
Defender | -0.011 |
ilan | -0.010 |
shade | -0.010 |
Interstitial | -0.010 |
tein | -0.010 |
Token | s |
Token ID | 82 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
resa | +0.279 |
Scotland | +0.237 |
Ireland | +0.210 |
Mitt | +0.210 |
Vice | +0.203 |
Neg logit contributions | |
Defender | -0.257 |
ilan | -0.247 |
shade | -0.246 |
Interstitial | -0.244 |
tein | -0.243 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
resa | +0.052 |
Scotland | +0.044 |
Ireland | +0.039 |
Mitt | +0.039 |
Vice | +0.038 |
Neg logit contributions | |
Defender | -0.051 |
ilan | -0.049 |
shade | -0.049 |
Interstitial | -0.049 |
tein | -0.048 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
resa | +0.780 |
Scotland | +0.658 |
Ireland | +0.582 |
Mitt | +0.582 |
Vice | +0.561 |
Neg logit contributions | |
Defender | -0.752 |
ilan | -0.728 |
shade | -0.721 |
Interstitial | -0.721 |
tein | -0.718 |
Token | early |
Token ID | 1903 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
resa | +3.416 |
Scotland | +2.907 |
Mitt | +2.597 |
Ireland | +2.578 |
Task | +2.450 |
Neg logit contributions | |
Defender | -3.318 |
Interstitial | -3.212 |
ilan | -3.193 |
tein | -3.192 |
shade | -3.125 |
Token | at |
Token ID | 379 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Defender | +0.111 |
ilan | +0.107 |
shade | +0.107 |
Interstitial | +0.106 |
tein | +0.105 |
Neg logit contributions | |
resa | -0.113 |
Scotland | -0.095 |
Ireland | -0.084 |
Mitt | -0.084 |
Vice | -0.081 |
Token | this |
Token ID | 428 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
resa | +0.317 |
Scotland | +0.272 |
Ireland | +0.244 |
Mitt | +0.243 |
Vice | +0.236 |
Neg logit contributions | |
Defender | -0.255 |
ilan | -0.245 |
shade | -0.245 |
Interstitial | -0.242 |
tein | -0.241 |
Token | stage |
Token ID | 3800 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
resa | +1.298 |
Scotland | +1.136 |
Ireland | +1.027 |
Mitt | +1.025 |
Task | +0.994 |
Neg logit contributions | |
Defender | -0.902 |
ilan | -0.871 |
Interstitial | -0.851 |
shade | -0.848 |
tein | -0.844 |
Token | , |
Token ID | 11 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
resa | +0.616 |
Scotland | +0.525 |
Mitt | +0.468 |
Ireland | +0.468 |
Vice | +0.451 |
Neg logit contributions | |
Defender | -0.553 |
ilan | -0.532 |
shade | -0.530 |
Interstitial | -0.526 |
tein | -0.523 |
Token | � |
Token ID | 447 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
resa | +0.156 |
Scotland | +0.132 |
Ireland | +0.117 |
Mitt | +0.116 |
Vice | +0.113 |
Neg logit contributions | |
Defender | -0.147 |
ilan | -0.142 |
shade | -0.141 |
Interstitial | -0.140 |
tein | -0.139 |
Token | � |
Token ID | 251 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
resa | +0.445 |
Scotland | +0.357 |
Ireland | +0.303 |
Mitt | +0.299 |
Vice | +0.287 |
Neg logit contributions | |
Defender | -0.673 |
ilan | -0.655 |
shade | -0.653 |
Interstitial | -0.647 |
tein | -0.646 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
resa | +0.193 |
Scotland | +0.164 |
Ireland | +0.146 |
Mitt | +0.146 |
Vice | +0.141 |
Neg logit contributions | |
Defender | -0.175 |
ilan | -0.169 |
shade | -0.169 |
Interstitial | -0.167 |
tein | -0.166 |
Token | this |
Token ID | 428 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
resa | +0.130 |
Scotland | +0.107 |
Ireland | +0.094 |
Mitt | +0.093 |
Vice | +0.090 |
Neg logit contributions | |
Defender | -0.151 |
ilan | -0.146 |
shade | -0.145 |
Interstitial | -0.145 |
tein | -0.144 |
Token | a |
Token ID | 257 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
resa | +1.127 |
Scotland | +0.941 |
Ireland | +0.830 |
Mitt | +0.829 |
Vice | +0.798 |
Neg logit contributions | |
Defender | -1.187 |
ilan | -1.150 |
shade | -1.141 |
Interstitial | -1.139 |
tein | -1.132 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
resa | +0.490 |
Scotland | +0.410 |
Mitt | +0.364 |
Ireland | +0.363 |
Task | +0.351 |
Neg logit contributions | |
Defender | -0.487 |
ilan | -0.471 |
Interstitial | -0.467 |
shade | -0.465 |
tein | -0.464 |
Token | more |
Token ID | 517 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
resa | +3.266 |
Scotland | +2.727 |
Mitt | +2.457 |
Ireland | +2.421 |
Task | +2.320 |
Neg logit contributions | |
Defender | -3.366 |
Interstitial | -3.254 |
ilan | -3.245 |
tein | -3.210 |
shade | -3.183 |
Token | complicated |
Token ID | 8253 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
resa | +0.219 |
Scotland | +0.184 |
Ireland | +0.163 |
Mitt | +0.162 |
Vice | +0.157 |
Neg logit contributions | |
Defender | -0.216 |
ilan | -0.209 |
shade | -0.209 |
Interstitial | -0.206 |
tein | -0.205 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
resa | +1.375 |
Scotland | +1.145 |
Mitt | +1.017 |
Ireland | +1.002 |
Task | +0.978 |
Neg logit contributions | |
Defender | -1.524 |
ilan | -1.477 |
Interstitial | -1.463 |
tein | -1.463 |
shade | -1.455 |
Token | Perhaps |
Token ID | 8673 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
resa | +0.291 |
Scotland | +0.250 |
Ireland | +0.225 |
Mitt | +0.224 |
Vice | +0.218 |
Neg logit contributions | |
Defender | -0.226 |
ilan | -0.218 |
shade | -0.217 |
Interstitial | -0.215 |
tein | -0.214 |
Token | the |
Token ID | 262 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
resa | +0.945 |
Scotland | +0.798 |
Mitt | +0.710 |
Ireland | +0.705 |
Vice | +0.681 |
Neg logit contributions | |
Defender | -0.914 |
ilan | -0.889 |
Interstitial | -0.878 |
shade | -0.877 |
tein | -0.876 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
resa | +0.494 |
Scotland | +0.426 |
Ireland | +0.385 |
Mitt | +0.383 |
Vice | +0.374 |
Neg logit contributions | |
Defender | -0.354 |
ilan | -0.339 |
shade | -0.339 |
Interstitial | -0.334 |
tein | -0.333 |
Token | The |
Token ID | 464 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
resa | +0.365 |
Scotland | +0.308 |
Mitt | +0.274 |
Ireland | +0.274 |
Vice | +0.264 |
Neg logit contributions | |
Defender | -0.329 |
ilan | -0.318 |
shade | -0.316 |
Interstitial | -0.314 |
tein | -0.310 |
Token | Orbital |
Token ID | 45453 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
resa | +0.667 |
Scotland | +0.557 |
Ireland | +0.491 |
Mitt | +0.489 |
Vice | +0.474 |
Neg logit contributions | |
Defender | -0.695 |
ilan | -0.673 |
shade | -0.671 |
Interstitial | -0.665 |
tein | -0.663 |
Token | ATK |
Token ID | 24526 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
resa | +0.374 |
Scotland | +0.319 |
Mitt | +0.287 |
Ireland | +0.286 |
Vice | +0.277 |
Neg logit contributions | |
Defender | -0.311 |
ilan | -0.305 |
shade | -0.301 |
Interstitial | -0.301 |
tein | -0.299 |
Token | Cy |
Token ID | 5934 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
resa | +1.781 |
Scotland | +1.518 |
Mitt | +1.386 |
Ireland | +1.367 |
Vice | +1.339 |
Neg logit contributions | |
Defender | -1.335 |
ilan | -1.313 |
Interstitial | -1.299 |
shade | -1.289 |
tein | -1.288 |
Token | gn |
Token ID | 4593 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
resa | +0.733 |
Scotland | +0.596 |
Ireland | +0.514 |
Mitt | +0.510 |
Vice | +0.494 |
Neg logit contributions | |
Defender | -0.970 |
ilan | -0.942 |
shade | -0.942 |
Interstitial | -0.935 |
tein | -0.930 |
Token | us |
Token ID | 385 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
resa | +1.848 |
Scotland | +1.292 |
Ireland | +0.989 |
Mitt | +0.965 |
Task | +0.912 |
Neg logit contributions | |
Defender | -4.774 |
Interstitial | -4.671 |
shade | -4.661 |
tein | -4.637 |
ilan | -4.619 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
resa | +1.064 |
Scotland | +0.901 |
Mitt | +0.812 |
Ireland | +0.802 |
Vice | +0.785 |
Neg logit contributions | |
Defender | -0.927 |
ilan | -0.909 |
Interstitial | -0.898 |
shade | -0.897 |
tein | -0.893 |
Token | on |
Token ID | 319 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
resa | +0.841 |
Scotland | +0.709 |
Ireland | +0.627 |
Mitt | +0.625 |
Vice | +0.606 |
Neg logit contributions | |
Defender | -0.828 |
ilan | -0.801 |
shade | -0.798 |
Interstitial | -0.791 |
tein | -0.788 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
resa | +1.172 |
Scotland | +0.984 |
Mitt | +0.885 |
Ireland | +0.874 |
Vice | +0.853 |
Neg logit contributions | |
Defender | -1.103 |
ilan | -1.074 |
Interstitial | -1.068 |
shade | -1.059 |
tein | -1.055 |
Token | mission |
Token ID | 4365 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
resa | +0.113 |
Scotland | +0.093 |
Ireland | +0.080 |
Mitt | +0.078 |
Vice | +0.076 |
Neg logit contributions | |
Defender | -0.153 |
shade | -0.149 |
ilan | -0.148 |
tein | -0.146 |
Interstitial | -0.146 |
Token | placeholder |
Token ID | 46076 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
resa | +0.625 |
Scotland | +0.526 |
Ireland | +0.472 |
Mitt | +0.470 |
Task | +0.459 |
Neg logit contributions | |
Defender | -0.555 |
ilan | -0.538 |
tein | -0.528 |
shade | -0.525 |
Interstitial | -0.524 |
Token |
|
Token ID | 3556 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Defender | +1.105 |
ilan | +1.065 |
shade | +1.060 |
Interstitial | +1.049 |
tein | +1.046 |
Neg logit contributions | |
resa | -1.247 |
Scotland | -1.061 |
Ireland | -0.947 |
Mitt | -0.941 |
Vice | -0.915 |
Token | p |
Token ID | 79 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
resa | +1.249 |
Scotland | +1.091 |
Ireland | +0.998 |
Mitt | +0.991 |
Vice | +0.975 |
Neg logit contributions | |
Defender | -0.692 |
shade | -0.648 |
ilan | -0.643 |
Interstitial | -0.636 |
tein | -0.632 |
Token | > |
Token ID | 29 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
resa | +2.203 |
Scotland | +1.889 |
Mitt | +1.686 |
Ireland | +1.670 |
Task | +1.641 |
Neg logit contributions | |
Defender | -1.811 |
ilan | -1.749 |
Interstitial | -1.723 |
shade | -1.712 |
tein | -1.706 |
Token | |
Token ID | 7359 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Defender | +1.216 |
ilan | +1.179 |
shade | +1.175 |
Interstitial | +1.162 |
tein | +1.161 |
Neg logit contributions | |
resa | -1.051 |
Scotland | -0.872 |
Ireland | -0.762 |
Mitt | -0.757 |
Vice | -0.732 |
Token | li |
Token ID | 4528 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
resa | +2.420 |
Scotland | +2.080 |
Ireland | +1.915 |
Mitt | +1.888 |
Vice | +1.870 |
Neg logit contributions | |
Defender | -1.432 |
shade | -1.356 |
Interstitial | -1.304 |
ilan | -1.300 |
tein | -1.293 |
Token | > |
Token ID | 29 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
resa | +3.589 |
Scotland | +3.068 |
Mitt | +2.756 |
Ireland | +2.736 |
Task | +2.680 |
Neg logit contributions | |
Defender | -2.995 |
ilan | -2.886 |
Interstitial | -2.850 |
shade | -2.844 |
tein | -2.800 |
Token | |
Token ID | 7359 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Defender | +1.216 |
ilan | +1.177 |
shade | +1.175 |
Interstitial | +1.162 |
tein | +1.159 |
Neg logit contributions | |
resa | -1.054 |
Scotland | -0.874 |
Ireland | -0.764 |
Mitt | -0.758 |
Vice | -0.734 |
Token | ul |
Token ID | 377 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
resa | +1.091 |
Scotland | +0.896 |
Ireland | +0.778 |
Mitt | +0.771 |
Vice | +0.745 |
Neg logit contributions | |
Defender | -1.356 |
ilan | -1.312 |
shade | -1.312 |
Interstitial | -1.297 |
tein | -1.294 |
Token | > |
Token ID | 29 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
resa | +0.769 |
Scotland | +0.666 |
Ireland | +0.601 |
Mitt | +0.599 |
Vice | +0.584 |
Neg logit contributions | |
Defender | -0.540 |
ilan | -0.518 |
shade | -0.516 |
Interstitial | -0.510 |
tein | -0.506 |
Token | |
Token ID | 7359 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Defender | +0.935 |
ilan | +0.907 |
shade | +0.905 |
Interstitial | +0.894 |
tein | +0.894 |
Neg logit contributions | |
resa | -0.817 |
Scotland | -0.679 |
Ireland | -0.594 |
Mitt | -0.591 |
Vice | -0.572 |
Token | … |
Token ID | 1399 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
resa | +0.461 |
Scotland | +0.387 |
Mitt | +0.343 |
Ireland | +0.342 |
Vice | +0.330 |
Neg logit contributions | |
Defender | -0.464 |
ilan | -0.449 |
shade | -0.446 |
tein | -0.444 |
Interstitial | -0.443 |
Token | Qu |
Token ID | 2264 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
resa | +0.889 |
Scotland | +0.758 |
Ireland | +0.676 |
Mitt | +0.675 |
Vice | +0.654 |
Neg logit contributions | |
Defender | -0.787 |
ilan | -0.760 |
shade | -0.756 |
Interstitial | -0.751 |
tein | -0.749 |
Token | antic |
Token ID | 5109 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
resa | +0.458 |
Scotland | +0.390 |
Ireland | +0.347 |
Mitt | +0.343 |
Vice | +0.335 |
Neg logit contributions | |
Defender | -0.404 |
shade | -0.386 |
ilan | -0.385 |
Interstitial | -0.385 |
tein | -0.381 |
Token | looked |
Token ID | 3114 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
resa | +1.170 |
Scotland | +1.005 |
Mitt | +0.902 |
Ireland | +0.899 |
Vice | +0.873 |
Neg logit contributions | |
Defender | -0.955 |
ilan | -0.922 |
shade | -0.916 |
Interstitial | -0.912 |
tein | -0.908 |
Token | a |
Token ID | 257 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
resa | +0.670 |
Scotland | +0.569 |
Ireland | +0.507 |
Mitt | +0.504 |
Vice | +0.490 |
Neg logit contributions | |
Defender | -0.603 |
ilan | -0.581 |
shade | -0.580 |
Interstitial | -0.573 |
tein | -0.571 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
resa | +0.649 |
Scotland | +0.548 |
Ireland | +0.484 |
Mitt | +0.483 |
Task | +0.467 |
Neg logit contributions | |
Defender | -0.640 |
ilan | -0.620 |
Interstitial | -0.613 |
tein | -0.613 |
shade | -0.609 |
Token | low |
Token ID | 1877 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
resa | +3.281 |
Scotland | +2.779 |
Mitt | +2.487 |
Ireland | +2.441 |
Vice | +2.348 |
Neg logit contributions | |
Defender | -3.316 |
ilan | -3.197 |
Interstitial | -3.196 |
tein | -3.187 |
shade | -3.129 |
Token | energy |
Token ID | 2568 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
Defender | +0.067 |
ilan | +0.065 |
shade | +0.065 |
Interstitial | +0.065 |
tein | +0.064 |
Neg logit contributions | |
resa | -0.073 |
Scotland | -0.062 |
Mitt | -0.055 |
Ireland | -0.055 |
Vice | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Defender | +0.432 |
ilan | +0.416 |
shade | +0.415 |
Interstitial | +0.410 |
tein | +0.409 |
Neg logit contributions | |
resa | -0.506 |
Scotland | -0.432 |
Ireland | -0.386 |
Mitt | -0.384 |
Vice | -0.373 |
Token | hardly |
Token ID | 8941 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Defender | +0.100 |
shade | +0.096 |
ilan | +0.096 |
Interstitial | +0.095 |
tein | +0.094 |
Neg logit contributions | |
resa | -0.110 |
Scotland | -0.093 |
Ireland | -0.083 |
Mitt | -0.082 |
Vice | -0.080 |
Token | ever |
Token ID | 1683 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Defender | +0.225 |
shade | +0.216 |
ilan | +0.216 |
Interstitial | +0.212 |
tein | +0.211 |
Neg logit contributions | |
resa | -0.285 |
Scotland | -0.245 |
Ireland | -0.220 |
Mitt | -0.218 |
Vice | -0.213 |
Token | and |
Token ID | 290 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
resa | +2.165 |
Scotland | +1.788 |
Mitt | +1.597 |
Ireland | +1.570 |
Vice | +1.546 |
Neg logit contributions | |
Defender | -2.281 |
Interstitial | -2.200 |
ilan | -2.194 |
shade | -2.175 |
tein | -2.169 |
Token | two |
Token ID | 734 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
resa | +0.542 |
Scotland | +0.458 |
Ireland | +0.406 |
Mitt | +0.405 |
Vice | +0.393 |
Neg logit contributions | |
Defender | -0.515 |
ilan | -0.497 |
shade | -0.495 |
Interstitial | -0.491 |
tein | -0.489 |
Token | more |
Token ID | 517 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Defender | +0.779 |
shade | +0.750 |
ilan | +0.742 |
tein | +0.728 |
Interstitial | +0.727 |
Neg logit contributions | |
resa | -0.829 |
Scotland | -0.706 |
Ireland | -0.631 |
Mitt | -0.617 |
Task | -0.602 |
Token | powerful |
Token ID | 3665 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Defender | +0.210 |
ilan | +0.202 |
shade | +0.202 |
Interstitial | +0.199 |
tein | +0.198 |
Neg logit contributions | |
resa | -0.234 |
Scotland | -0.199 |
Ireland | -0.177 |
Mitt | -0.176 |
Vice | -0.171 |
Token | Be |
Token ID | 1355 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
resa | +1.270 |
Scotland | +1.081 |
Mitt | +0.964 |
Ireland | +0.961 |
Vice | +0.934 |
Neg logit contributions | |
Defender | -1.110 |
ilan | -1.079 |
shade | -1.067 |
Interstitial | -1.064 |
tein | -1.060 |
Token | cht |
Token ID | 21474 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
resa | +1.920 |
Scotland | +1.667 |
Ireland | +1.510 |
Mitt | +1.502 |
Vice | +1.467 |
Neg logit contributions | |
Defender | -1.285 |
ilan | -1.229 |
shade | -1.228 |
Interstitial | -1.211 |
tein | -1.205 |
Token | el |
Token ID | 417 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
resa | +2.758 |
Scotland | +2.163 |
Mitt | +1.902 |
Ireland | +1.857 |
Vice | +1.819 |
Neg logit contributions | |
Defender | -3.830 |
Interstitial | -3.770 |
shade | -3.755 |
ilan | -3.703 |
tein | -3.682 |
Token | A |
Token ID | 317 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Defender | +0.376 |
ilan | +0.363 |
shade | +0.361 |
Interstitial | +0.358 |
tein | +0.356 |
Neg logit contributions | |
resa | -0.447 |
Scotland | -0.382 |
Ireland | -0.341 |
Mitt | -0.340 |
Vice | -0.331 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
resa | +1.906 |
Scotland | +1.621 |
Ireland | +1.452 |
Mitt | +1.444 |
Vice | +1.408 |
Neg logit contributions | |
Defender | -1.582 |
ilan | -1.531 |
shade | -1.526 |
Interstitial | -1.521 |
tein | -1.507 |
Token | B |
Token ID | 33 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
resa | +1.879 |
Scotland | +1.597 |
Ireland | +1.416 |
Mitt | +1.416 |
Vice | +1.373 |
Neg logit contributions | |
Defender | -1.737 |
ilan | -1.700 |
shade | -1.683 |
Interstitial | -1.676 |
tein | -1.667 |
Token | reactors |
Token ID | 28502 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
resa | +1.043 |
Scotland | +0.886 |
Mitt | +0.789 |
Ireland | +0.788 |
Vice | +0.765 |
Neg logit contributions | |
Defender | -0.931 |
ilan | -0.908 |
shade | -0.901 |
Interstitial | -0.895 |
tein | -0.889 |
Token | � |
Token ID | 251 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
resa | +0.163 |
Scotland | +0.139 |
Ireland | +0.123 |
Mitt | +0.122 |
Vice | +0.119 |
Neg logit contributions | |
Defender | -0.150 |
ilan | -0.145 |
shade | -0.145 |
Interstitial | -0.143 |
tein | -0.142 |
Token |
|
Token ID | 198 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
resa | +0.451 |
Scotland | +0.388 |
Ireland | +0.350 |
Mitt | +0.349 |
Vice | +0.340 |
Neg logit contributions | |
Defender | -0.343 |
ilan | -0.330 |
shade | -0.329 |
tein | -0.324 |
Interstitial | -0.324 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
resa | +0.391 |
Scotland | +0.337 |
Ireland | +0.305 |
Mitt | +0.303 |
Vice | +0.295 |
Neg logit contributions | |
Defender | -0.277 |
ilan | -0.265 |
shade | -0.265 |
Interstitial | -0.261 |
tein | -0.260 |
Token | Watch |
Token ID | 10723 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
resa | +0.109 |
Scotland | +0.092 |
Ireland | +0.081 |
Mitt | +0.080 |
Vice | +0.078 |
Neg logit contributions | |
Defender | -0.113 |
ilan | -0.110 |
shade | -0.109 |
Interstitial | -0.108 |
tein | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Defender | +0.178 |
ilan | +0.172 |
shade | +0.172 |
Interstitial | +0.169 |
tein | +0.169 |
Neg logit contributions | |
resa | -0.179 |
Scotland | -0.151 |
Ireland | -0.134 |
Mitt | -0.132 |
Vice | -0.129 |
Token | moment |
Token ID | 2589 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
resa | +0.955 |
Scotland | +0.805 |
Mitt | +0.727 |
Ireland | +0.721 |
Vice | +0.702 |
Neg logit contributions | |
Defender | -0.805 |
ilan | -0.783 |
shade | -0.775 |
tein | -0.770 |
Interstitial | -0.768 |
Token | unfold |
Token ID | 16631 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
resa | +3.479 |
Scotland | +2.973 |
Mitt | +2.720 |
Ireland | +2.681 |
Vice | +2.590 |
Neg logit contributions | |
Defender | -3.038 |
ilan | -2.955 |
tein | -2.934 |
Interstitial | -2.931 |
shade | -2.926 |
Token | below |
Token ID | 2174 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
resa | +0.605 |
Scotland | +0.520 |
Mitt | +0.471 |
Ireland | +0.470 |
Vice | +0.458 |
Neg logit contributions | |
Defender | -0.441 |
ilan | -0.424 |
tein | -0.420 |
shade | -0.420 |
Interstitial | -0.417 |
Token | : |
Token ID | 25 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
resa | +0.967 |
Scotland | +0.813 |
Mitt | +0.722 |
Ireland | +0.720 |
Vice | +0.698 |
Neg logit contributions | |
Defender | -0.973 |
ilan | -0.937 |
shade | -0.935 |
tein | -0.934 |
Interstitial | -0.926 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
resa | +0.547 |
Scotland | +0.471 |
Mitt | +0.425 |
Ireland | +0.425 |
Vice | +0.414 |
Neg logit contributions | |
Defender | -0.413 |
ilan | -0.399 |
shade | -0.397 |
tein | -0.394 |
Interstitial | -0.391 |
Token | Mar |
Token ID | 7676 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
resa | +0.370 |
Scotland | +0.315 |
Ireland | +0.279 |
Mitt | +0.273 |
Vice | +0.270 |
Neg logit contributions | |
Defender | -0.362 |
shade | -0.349 |
ilan | -0.348 |
tein | -0.344 |
Interstitial | -0.342 |
Token | deprecated |
Token ID | 39224 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Defender | +0.209 |
ilan | +0.201 |
shade | +0.201 |
Interstitial | +0.198 |
tein | +0.198 |
Neg logit contributions | |
resa | -0.216 |
Scotland | -0.182 |
Ireland | -0.161 |
Mitt | -0.160 |
Vice | -0.156 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
resa | +0.291 |
Scotland | +0.244 |
Ireland | +0.215 |
Mitt | +0.215 |
Task | +0.208 |
Neg logit contributions | |
Defender | -0.291 |
ilan | -0.282 |
tein | -0.280 |
shade | -0.279 |
Interstitial | -0.279 |
Token | you |
Token ID | 345 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Defender | +0.082 |
ilan | +0.079 |
shade | +0.079 |
Interstitial | +0.078 |
tein | +0.078 |
Neg logit contributions | |
resa | -0.085 |
Scotland | -0.072 |
Ireland | -0.063 |
Mitt | -0.063 |
Vice | -0.061 |
Token | should |
Token ID | 815 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Defender | +0.207 |
ilan | +0.200 |
shade | +0.199 |
Interstitial | +0.197 |
tein | +0.196 |
Neg logit contributions | |
resa | -0.222 |
Scotland | -0.188 |
Ireland | -0.167 |
Mitt | -0.166 |
Vice | -0.161 |
Token | use |
Token ID | 779 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Defender | +0.918 |
ilan | +0.885 |
shade | +0.884 |
Interstitial | +0.872 |
tein | +0.870 |
Neg logit contributions | |
resa | -1.006 |
Scotland | -0.855 |
Ireland | -0.761 |
Mitt | -0.756 |
Vice | -0.735 |
Token | https |
Token ID | 3740 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
Defender | +0.380 |
ilan | +0.369 |
shade | +0.367 |
Interstitial | +0.365 |
tein | +0.364 |
Neg logit contributions | |
resa | -0.345 |
Scotland | -0.287 |
Ireland | -0.251 |
Mitt | -0.250 |
Vice | -0.242 |
Token | :// |
Token ID | 1378 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
resa | +2.163 |
Scotland | +1.676 |
Mitt | +1.332 |
Ireland | +1.323 |
Task | +1.260 |
Neg logit contributions | |
Defender | -4.313 |
ilan | -4.270 |
Interstitial | -4.232 |
tein | -4.224 |
shade | -4.197 |
Token | api |
Token ID | 40391 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
resa | +0.742 |
Scotland | +0.626 |
Ireland | +0.557 |
Mitt | +0.552 |
Vice | +0.538 |
Neg logit contributions | |
Defender | -0.701 |
ilan | -0.675 |
shade | -0.674 |
Interstitial | -0.669 |
tein | -0.666 |
Token | . |
Token ID | 764 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Defender | +0.300 |
ilan | +0.290 |
shade | +0.290 |
Interstitial | +0.286 |
tein | +0.286 |
Neg logit contributions | |
resa | -0.262 |
Scotland | -0.218 |
Ireland | -0.191 |
Mitt | -0.189 |
Vice | -0.183 |
Token | nice |
Token ID | 44460 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
resa | +0.334 |
Scotland | +0.287 |
Ireland | +0.258 |
Mitt | +0.257 |
Vice | +0.250 |
Neg logit contributions | |
Defender | -0.260 |
ilan | -0.250 |
shade | -0.249 |
Interstitial | -0.247 |
tein | -0.246 |
Token | hash |
Token ID | 17831 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
resa | +0.755 |
Scotland | +0.669 |
Ireland | +0.615 |
Mitt | +0.611 |
Vice | +0.601 |
Neg logit contributions | |
Defender | -0.326 |
ilan | -0.303 |
shade | -0.302 |
Interstitial | -0.299 |
tein | -0.296 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
resa | +0.149 |
Scotland | +0.129 |
Ireland | +0.116 |
Mitt | +0.116 |
Vice | +0.113 |
Neg logit contributions | |
Defender | -0.109 |
ilan | -0.105 |
shade | -0.104 |
Interstitial | -0.103 |
tein | -0.103 |
Token | The |
Token ID | 464 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
Defender | +0.090 |
ilan | +0.087 |
shade | +0.087 |
Interstitial | +0.086 |
tein | +0.085 |
Neg logit contributions | |
resa | -0.100 |
Scotland | -0.085 |
Ireland | -0.075 |
Mitt | -0.075 |
Vice | -0.073 |
Token | film |
Token ID | 2646 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
resa | +0.684 |
Scotland | +0.572 |
Mitt | +0.509 |
Ireland | +0.509 |
Vice | +0.492 |
Neg logit contributions | |
Defender | -0.635 |
ilan | -0.618 |
shade | -0.611 |
Interstitial | -0.611 |
tein | -0.607 |
Token | seemed |
Token ID | 3947 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
resa | +0.779 |
Scotland | +0.667 |
Mitt | +0.600 |
Ireland | +0.600 |
Vice | +0.580 |
Neg logit contributions | |
Defender | -0.631 |
ilan | -0.614 |
Interstitial | -0.607 |
shade | -0.604 |
tein | -0.601 |
Token | every |
Token ID | 790 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
resa | +0.557 |
Scotland | +0.470 |
Ireland | +0.415 |
Mitt | +0.413 |
Vice | +0.399 |
Neg logit contributions | |
Defender | -0.559 |
ilan | -0.541 |
shade | -0.538 |
Interstitial | -0.533 |
tein | -0.533 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
Defender | +0.757 |
shade | +0.732 |
ilan | +0.728 |
Interstitial | +0.716 |
tein | +0.716 |
Neg logit contributions | |
resa | -0.837 |
Scotland | -0.711 |
Ireland | -0.634 |
Mitt | -0.629 |
Vice | -0.613 |
Token | as |
Token ID | 355 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
resa | +3.366 |
Scotland | +2.875 |
Mitt | +2.546 |
Ireland | +2.542 |
Task | +2.453 |
Neg logit contributions | |
Defender | -3.109 |
Interstitial | -3.051 |
ilan | -3.048 |
shade | -3.028 |
tein | -3.019 |
Token | sensational |
Token ID | 31826 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
resa | +0.907 |
Scotland | +0.764 |
Mitt | +0.674 |
Ireland | +0.673 |
Vice | +0.648 |
Neg logit contributions | |
Defender | -0.931 |
ilan | -0.900 |
shade | -0.894 |
Interstitial | -0.891 |
tein | -0.888 |
Token | istic |
Token ID | 2569 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
resa | +0.917 |
Scotland | +0.780 |
Mitt | +0.697 |
Ireland | +0.694 |
Vice | +0.676 |
Neg logit contributions | |
Defender | -0.816 |
ilan | -0.788 |
shade | -0.785 |
Interstitial | -0.784 |
tein | -0.779 |
Token | as |
Token ID | 355 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
resa | +0.447 |
Scotland | +0.381 |
Mitt | +0.340 |
Ireland | +0.339 |
Vice | +0.330 |
Neg logit contributions | |
Defender | -0.393 |
ilan | -0.380 |
shade | -0.378 |
Interstitial | -0.377 |
tein | -0.375 |
Token | its |
Token ID | 663 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
resa | +0.317 |
Scotland | +0.267 |
Ireland | +0.235 |
Mitt | +0.234 |
Vice | +0.226 |
Neg logit contributions | |
Defender | -0.330 |
ilan | -0.321 |
shade | -0.319 |
Interstitial | -0.317 |
tein | -0.316 |
Token | G |
Token ID | 38 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
resa | +0.839 |
Scotland | +0.717 |
Ireland | +0.646 |
Mitt | +0.645 |
Vice | +0.630 |
Neg logit contributions | |
Defender | -0.663 |
ilan | -0.639 |
Interstitial | -0.639 |
shade | -0.638 |
tein | -0.633 |
Token | - |
Token ID | 12 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
resa | +0.981 |
Scotland | +0.834 |
Mitt | +0.753 |
Ireland | +0.747 |
Vice | +0.727 |
Neg logit contributions | |
Defender | -0.816 |
ilan | -0.802 |
Interstitial | -0.798 |
shade | -0.795 |
tein | -0.793 |
Token | 83 |
Token ID | 5999 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
resa | +1.207 |
Scotland | +1.025 |
Ireland | +0.913 |
Mitt | +0.900 |
Task | +0.882 |
Neg logit contributions | |
Defender | -1.162 |
ilan | -1.126 |
shade | -1.126 |
tein | -1.111 |
Interstitial | -1.107 |
Token | Active |
Token ID | 14199 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
resa | +0.906 |
Scotland | +0.772 |
Mitt | +0.694 |
Ireland | +0.689 |
Vice | +0.671 |
Neg logit contributions | |
Defender | -0.757 |
ilan | -0.743 |
shade | -0.739 |
Interstitial | -0.735 |
tein | -0.731 |
Token | Elect |
Token ID | 5903 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Defender | +0.547 |
ilan | +0.527 |
shade | +0.526 |
Interstitial | +0.519 |
tein | +0.518 |
Neg logit contributions | |
resa | -0.689 |
Scotland | -0.591 |
Ireland | -0.530 |
Mitt | -0.528 |
Vice | -0.514 |
Token | ron |
Token ID | 1313 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
resa | +1.548 |
Scotland | +1.285 |
Mitt | +1.155 |
Ireland | +1.128 |
Vice | +1.095 |
Neg logit contributions | |
Defender | -1.525 |
Interstitial | -1.488 |
shade | -1.486 |
tein | -1.464 |
ilan | -1.452 |
Token | ically |
Token ID | 1146 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
resa | +3.584 |
Scotland | +3.061 |
Mitt | +2.866 |
Ireland | +2.725 |
Task | +2.669 |
Neg logit contributions | |
Defender | -2.765 |
ilan | -2.751 |
Interstitial | -2.750 |
tein | -2.694 |
inventoryQuantity | -2.693 |
Token | Sc |
Token ID | 1446 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
resa | +2.010 |
Scotland | +1.724 |
Mitt | +1.553 |
Ireland | +1.530 |
Task | +1.486 |
Neg logit contributions | |
Defender | -1.657 |
ilan | -1.633 |
shade | -1.621 |
Interstitial | -1.621 |
tein | -1.599 |
Token | anned |
Token ID | 3577 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
resa | +0.724 |
Scotland | +0.615 |
Mitt | +0.553 |
Ireland | +0.550 |
Vice | +0.539 |
Neg logit contributions | |
Defender | -0.558 |
shade | -0.536 |
Interstitial | -0.535 |
ilan | -0.532 |
tein | -0.524 |
Token | Array |
Token ID | 15690 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
resa | +0.824 |
Scotland | +0.703 |
Mitt | +0.640 |
Ireland | +0.628 |
Vice | +0.614 |
Neg logit contributions | |
Defender | -0.657 |
ilan | -0.650 |
shade | -0.646 |
Interstitial | -0.642 |
tein | -0.638 |
Token | Rad |
Token ID | 5325 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Defender | +0.003 |
ilan | +0.003 |
shade | +0.003 |
Interstitial | +0.003 |
tein | +0.003 |
Neg logit contributions | |
resa | -0.004 |
Scotland | -0.003 |
Mitt | -0.003 |
Ireland | -0.003 |
Vice | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
resa | +0.037 |
Scotland | +0.032 |
Ireland | +0.029 |
Mitt | +0.029 |
Vice | +0.028 |
Neg logit contributions | |
Defender | -0.026 |
ilan | -0.024 |
shade | -0.024 |
Interstitial | -0.024 |
tein | -0.024 |
Token | Subscribe |
Token ID | 27125 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Defender | +0.040 |
ilan | +0.038 |
shade | +0.038 |
Interstitial | +0.038 |
tein | +0.037 |
Neg logit contributions | |
resa | -0.054 |
Scotland | -0.045 |
Mitt | -0.041 |
Ireland | -0.041 |
geist | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Defender | +0.156 |
shade | +0.150 |
ilan | +0.148 |
tein | +0.144 |
Interstitial | +0.144 |
Neg logit contributions | |
resa | -0.170 |
Scotland | -0.145 |
Ireland | -0.129 |
Mitt | -0.126 |
Vice | -0.125 |
Token | our |
Token ID | 674 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Defender | +0.256 |
shade | +0.245 |
ilan | +0.244 |
Interstitial | +0.241 |
tein | +0.239 |
Neg logit contributions | |
resa | -0.295 |
Scotland | -0.251 |
Ireland | -0.225 |
Mitt | -0.222 |
Vice | -0.217 |
Token | free |
Token ID | 1479 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Defender | +0.183 |
shade | +0.175 |
ilan | +0.171 |
tein | +0.168 |
Interstitial | +0.167 |
Neg logit contributions | |
resa | -0.250 |
Scotland | -0.215 |
Ireland | -0.195 |
Mitt | -0.192 |
Vice | -0.190 |
Token | newsletters |
Token ID | 16983 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
resa | +1.836 |
Scotland | +1.627 |
Ireland | +1.499 |
Mitt | +1.493 |
Vice | +1.461 |
Neg logit contributions | |
Defender | -0.808 |
ilan | -0.767 |
shade | -0.763 |
Interstitial | -0.751 |
tein | -0.747 |
Token | . |
Token ID | 13 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Defender | +3.336 |
shade | +3.277 |
ilan | +3.237 |
plagiar | +3.019 |
tein | +3.014 |
Neg logit contributions | |
resa | -3.995 |
Scotland | -3.467 |
Ireland | -3.122 |
geist | -3.046 |
Vice | -3.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Defender | +0.451 |
ilan | +0.435 |
shade | +0.430 |
Interstitial | +0.429 |
tein | +0.421 |
Neg logit contributions | |
resa | -0.815 |
Scotland | -0.718 |
Ireland | -0.657 |
Mitt | -0.657 |
Vice | -0.640 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Defender | +0.730 |
shade | +0.692 |
ilan | +0.690 |
Interstitial | +0.675 |
tein | +0.672 |
Neg logit contributions | |
resa | -1.124 |
Scotland | -0.965 |
Ireland | -0.877 |
Mitt | -0.867 |
Vice | -0.847 |
Token | Update |
Token ID | 10260 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
Defender | +0.745 |
ilan | +0.720 |
shade | +0.716 |
Interstitial | +0.713 |
tein | +0.703 |
Neg logit contributions | |
resa | -0.782 |
Scotland | -0.654 |
Mitt | -0.580 |
Ireland | -0.579 |
Task | -0.558 |
Token | , |
Token ID | 11 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
Defender | +1.869 |
shade | +1.795 |
ilan | +1.790 |
Interstitial | +1.753 |
tein | +1.748 |
Neg logit contributions | |
resa | -2.273 |
Scotland | -1.954 |
Ireland | -1.749 |
Mitt | -1.720 |
Vice | -1.690 |
Token | dain |
Token ID | 27162 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
resa | +0.327 |
Scotland | +0.256 |
Mitt | +0.213 |
Ireland | +0.213 |
Vice | +0.203 |
Neg logit contributions | |
Defender | -0.554 |
shade | -0.539 |
ilan | -0.537 |
Interstitial | -0.534 |
tein | -0.529 |
Token | in |
Token ID | 287 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
resa | +0.362 |
Scotland | +0.303 |
Ireland | +0.267 |
Mitt | +0.267 |
Vice | +0.257 |
Neg logit contributions | |
Defender | -0.378 |
ilan | -0.365 |
shade | -0.364 |
Interstitial | -0.361 |
tein | -0.360 |
Token | public |
Token ID | 1171 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
resa | +0.350 |
Scotland | +0.295 |
Ireland | +0.261 |
Mitt | +0.259 |
Vice | +0.252 |
Neg logit contributions | |
Defender | -0.349 |
ilan | -0.337 |
shade | -0.336 |
Interstitial | -0.332 |
tein | -0.331 |
Token | — |
Token ID | 960 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
resa | +0.627 |
Scotland | +0.527 |
Mitt | +0.470 |
Ireland | +0.465 |
Vice | +0.450 |
Neg logit contributions | |
Defender | -0.615 |
ilan | -0.600 |
Interstitial | -0.593 |
tein | -0.589 |
shade | -0.586 |
Token | p |
Token ID | 79 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Defender | +0.273 |
ilan | +0.262 |
shade | +0.262 |
Interstitial | +0.258 |
tein | +0.257 |
Neg logit contributions | |
resa | -0.342 |
Scotland | -0.293 |
Ireland | -0.263 |
Mitt | -0.261 |
Vice | -0.254 |
Token | iss |
Token ID | 747 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Defender | +0.682 |
ilan | +0.663 |
shade | +0.661 |
tein | +0.649 |
Interstitial | +0.648 |
Neg logit contributions | |
resa | -0.685 |
Scotland | -0.580 |
Ireland | -0.514 |
Mitt | -0.511 |
Vice | -0.494 |
Token | ing |
Token ID | 278 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Defender | +3.568 |
shade | +3.495 |
ilan | +3.459 |
tein | +3.379 |
Interstitial | +3.347 |
Neg logit contributions | |
resa | -3.796 |
Scotland | -3.235 |
Ireland | -2.891 |
Mitt | -2.770 |
Vice | -2.763 |
Token | off |
Token ID | 572 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Defender | +1.671 |
shade | +1.624 |
ilan | +1.598 |
tein | +1.555 |
Interstitial | +1.551 |
Neg logit contributions | |
resa | -2.032 |
Scotland | -1.755 |
Ireland | -1.580 |
Mitt | -1.526 |
Task | -1.513 |
Token | one |
Token ID | 530 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Defender | +0.976 |
shade | +0.946 |
ilan | +0.939 |
Interstitial | +0.923 |
tein | +0.919 |
Neg logit contributions | |
resa | -1.033 |
Scotland | -0.880 |
Ireland | -0.782 |
Mitt | -0.766 |
Vice | -0.751 |
Token | of |
Token ID | 286 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
resa | +0.251 |
Scotland | +0.213 |
Ireland | +0.190 |
Mitt | +0.189 |
Vice | +0.184 |
Neg logit contributions | |
Defender | -0.229 |
ilan | -0.220 |
shade | -0.220 |
Interstitial | -0.217 |
tein | -0.217 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
resa | +0.422 |
Scotland | +0.356 |
Ireland | +0.314 |
Mitt | +0.313 |
Vice | +0.303 |
Neg logit contributions | |
Defender | -0.421 |
ilan | -0.407 |
shade | -0.406 |
Interstitial | -0.403 |
tein | -0.401 |
Token | to |
Token ID | 284 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Defender | +0.621 |
shade | +0.597 |
ilan | +0.597 |
Interstitial | +0.587 |
tein | +0.586 |
Neg logit contributions | |
resa | -0.703 |
Scotland | -0.598 |
Ireland | -0.534 |
Mitt | -0.528 |
Vice | -0.516 |
Token | the |
Token ID | 262 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Defender | +0.241 |
ilan | +0.233 |
shade | +0.233 |
Interstitial | +0.229 |
tein | +0.229 |
Neg logit contributions | |
resa | -0.232 |
Scotland | -0.194 |
Ireland | -0.171 |
Mitt | -0.170 |
Vice | -0.165 |
Token | prisoners |
Token ID | 10577 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Defender | +0.275 |
ilan | +0.265 |
shade | +0.265 |
Interstitial | +0.262 |
tein | +0.261 |
Neg logit contributions | |
resa | -0.291 |
Scotland | -0.247 |
Ireland | -0.219 |
Mitt | -0.218 |
Vice | -0.211 |
Token | in |
Token ID | 287 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
Defender | +1.112 |
shade | +1.071 |
ilan | +1.068 |
Interstitial | +1.047 |
tein | +1.045 |
Neg logit contributions | |
resa | -1.248 |
Scotland | -1.062 |
Ireland | -0.949 |
Mitt | -0.933 |
Vice | -0.914 |
Token | the |
Token ID | 262 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Defender | +0.671 |
shade | +0.647 |
ilan | +0.645 |
tein | +0.636 |
Interstitial | +0.635 |
Neg logit contributions | |
resa | -0.690 |
Scotland | -0.582 |
Ireland | -0.516 |
Mitt | -0.511 |
Vice | -0.498 |
Token | yard |
Token ID | 12699 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
Defender | +0.377 |
ilan | +0.365 |
shade | +0.361 |
Interstitial | +0.360 |
tein | +0.358 |
Neg logit contributions | |
resa | -0.454 |
Scotland | -0.388 |
Ireland | -0.347 |
Mitt | -0.346 |
Vice | -0.336 |
Token | , |
Token ID | 11 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
Defender | +3.386 |
shade | +3.289 |
ilan | +3.233 |
tein | +3.160 |
Interstitial | +3.127 |
Neg logit contributions | |
resa | -3.931 |
Scotland | -3.351 |
Ireland | -3.021 |
Mitt | -2.907 |
Vice | -2.897 |
Token | though |
Token ID | 996 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
Defender | +0.442 |
ilan | +0.425 |
shade | +0.425 |
Interstitial | +0.417 |
tein | +0.417 |
Neg logit contributions | |
resa | -0.491 |
Scotland | -0.416 |
Ireland | -0.372 |
Mitt | -0.367 |
Vice | -0.359 |
Token | he |
Token ID | 339 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
Defender | +0.688 |
shade | +0.663 |
ilan | +0.660 |
tein | +0.650 |
Interstitial | +0.650 |
Neg logit contributions | |
resa | -0.669 |
Scotland | -0.561 |
Ireland | -0.496 |
Mitt | -0.488 |
Vice | -0.478 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
Defender | +0.500 |
shade | +0.480 |
ilan | +0.477 |
tein | +0.470 |
Interstitial | +0.466 |
Neg logit contributions | |
resa | -0.675 |
Scotland | -0.584 |
Ireland | -0.527 |
Mitt | -0.520 |
Vice | -0.511 |
Token | � |
Token ID | 447 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Defender | +0.009 |
ilan | +0.008 |
shade | +0.008 |
Interstitial | +0.008 |
tein | +0.008 |
Neg logit contributions | |
resa | -0.018 |
Scotland | -0.016 |
Ireland | -0.015 |
Mitt | -0.015 |
Vice | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Defender | +0.107 |
ilan | +0.103 |
shade | +0.102 |
Interstitial | +0.101 |
tein | +0.101 |
Neg logit contributions | |
resa | -0.138 |
Scotland | -0.119 |
Ireland | -0.107 |
Mitt | -0.106 |
Vice | -0.103 |
Token | governor |
Token ID | 8153 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
resa | +0.147 |
Scotland | +0.118 |
Ireland | +0.100 |
Mitt | +0.098 |
Task | +0.095 |
Neg logit contributions | |
Defender | -0.214 |
shade | -0.207 |
ilan | -0.206 |
Interstitial | -0.204 |
tein | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | -6.31e-03 |
Pos logit contributions | |
resa | +0.386 |
Scotland | +0.324 |
Mitt | +0.288 |
Ireland | +0.285 |
Vice | +0.277 |
Neg logit contributions | |
Defender | -0.396 |
ilan | -0.384 |
shade | -0.382 |
Interstitial | -0.380 |
tein | -0.378 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Defender | +0.004 |
ilan | +0.004 |
shade | +0.004 |
Interstitial | +0.004 |
tein | +0.004 |
Neg logit contributions | |
resa | -0.005 |
Scotland | -0.005 |
Ireland | -0.004 |
Mitt | -0.004 |
Vice | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Defender | +0.135 |
ilan | +0.129 |
shade | +0.129 |
Interstitial | +0.126 |
tein | +0.126 |
Neg logit contributions | |
resa | -0.194 |
Scotland | -0.167 |
Ireland | -0.151 |
Mitt | -0.150 |
Vice | -0.147 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
Defender | +0.215 |
ilan | +0.205 |
shade | +0.205 |
Interstitial | +0.202 |
tein | +0.201 |
Neg logit contributions | |
resa | -0.337 |
Scotland | -0.293 |
Ireland | -0.267 |
Mitt | -0.265 |
Vice | -0.259 |
Token | Continue |
Token ID | 10054 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Defender | +3.065 |
ilan | +2.933 |
shade | +2.914 |
Interstitial | +2.904 |
tein | +2.805 |
Neg logit contributions | |
resa | -4.243 |
Scotland | -3.695 |
Ireland | -3.308 |
Mitt | -3.273 |
Vice | -3.203 |
Token | reading |
Token ID | 3555 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
resa | +1.403 |
Scotland | +1.232 |
Ireland | +1.123 |
Mitt | +1.120 |
Vice | +1.096 |
Neg logit contributions | |
Defender | -0.791 |
ilan | -0.758 |
shade | -0.752 |
tein | -0.748 |
Interstitial | -0.746 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Defender | +0.144 |
shade | +0.140 |
ilan | +0.138 |
Interstitial | +0.136 |
tein | +0.135 |
Neg logit contributions | |
resa | -0.159 |
Scotland | -0.134 |
Ireland | -0.119 |
Mitt | -0.117 |
Vice | -0.115 |
Token | main |
Token ID | 1388 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
resa | +0.119 |
Scotland | +0.106 |
Ireland | +0.096 |
Mitt | +0.094 |
Vice | +0.093 |
Neg logit contributions | |
Defender | -0.070 |
shade | -0.067 |
ilan | -0.067 |
Interstitial | -0.066 |
tein | -0.065 |
Token | story |
Token ID | 1621 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
resa | +0.728 |
Scotland | +0.629 |
Ireland | +0.565 |
Mitt | +0.558 |
Vice | +0.546 |
Neg logit contributions | |
Defender | -0.564 |
shade | -0.544 |
ilan | -0.540 |
Interstitial | -0.532 |
tein | -0.530 |
Token |
|
Token ID | 198 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Defender | +0.125 |
ilan | +0.119 |
shade | +0.119 |
Interstitial | +0.116 |
tein | +0.116 |
Neg logit contributions | |
resa | -0.181 |
Scotland | -0.155 |
Ireland | -0.141 |
Mitt | -0.140 |
Vice | -0.136 |
Token | Subscribe |
Token ID | 27125 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Defender | +0.176 |
ilan | +0.168 |
shade | +0.166 |
Interstitial | +0.165 |
tein | +0.161 |
Neg logit contributions | |
resa | -0.239 |
Scotland | -0.201 |
Mitt | -0.183 |
Ireland | -0.182 |
geist | -0.178 |
Token | to |
Token ID | 284 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Defender | +0.123 |
shade | +0.118 |
ilan | +0.117 |
tein | +0.114 |
Interstitial | +0.114 |
Neg logit contributions | |
resa | -0.134 |
Scotland | -0.114 |
Ireland | -0.102 |
Mitt | -0.099 |
Vice | -0.098 |
Token | our |
Token ID | 674 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Defender | +0.319 |
shade | +0.306 |
ilan | +0.303 |
Interstitial | +0.300 |
tein | +0.298 |
Neg logit contributions | |
resa | -0.374 |
Scotland | -0.318 |
Ireland | -0.284 |
Mitt | -0.280 |
Vice | -0.275 |
Token | free |
Token ID | 1479 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Defender | +0.152 |
shade | +0.146 |
ilan | +0.143 |
tein | +0.140 |
Interstitial | +0.139 |
Neg logit contributions | |
resa | -0.207 |
Scotland | -0.179 |
Ireland | -0.162 |
Mitt | -0.159 |
Vice | -0.158 |
Token | newsletters |
Token ID | 16983 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
resa | +1.908 |
Scotland | +1.691 |
Ireland | +1.558 |
Mitt | +1.551 |
Vice | +1.519 |
Neg logit contributions | |
Defender | -0.840 |
ilan | -0.797 |
shade | -0.792 |
Interstitial | -0.780 |
tein | -0.776 |
Token | . |
Token ID | 13 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Defender | +3.263 |
shade | +3.196 |
ilan | +3.167 |
plagiar | +2.954 |
tein | +2.947 |
Neg logit contributions | |
resa | -3.896 |
Scotland | -3.379 |
Ireland | -3.044 |
geist | -2.965 |
Mitt | -2.939 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Defender | +0.428 |
ilan | +0.412 |
shade | +0.408 |
Interstitial | +0.407 |
tein | +0.400 |
Neg logit contributions | |
resa | -0.770 |
Scotland | -0.679 |
Ireland | -0.621 |
Mitt | -0.621 |
Vice | -0.604 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Defender | +0.763 |
shade | +0.723 |
ilan | +0.722 |
Interstitial | +0.705 |
tein | +0.703 |
Neg logit contributions | |
resa | -1.165 |
Scotland | -1.001 |
Ireland | -0.910 |
Mitt | -0.900 |
Vice | -0.879 |
Token | If |
Token ID | 1532 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Defender | +0.782 |
ilan | +0.756 |
shade | +0.751 |
Interstitial | +0.749 |
tein | +0.737 |
Neg logit contributions | |
resa | -0.815 |
Scotland | -0.681 |
Mitt | -0.604 |
Ireland | -0.603 |
Task | -0.580 |
Token | you |
Token ID | 345 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
resa | +1.097 |
Scotland | +0.914 |
Mitt | +0.816 |
Ireland | +0.803 |
Vice | +0.775 |
Neg logit contributions | |
Defender | -1.164 |
ilan | -1.134 |
Interstitial | -1.122 |
shade | -1.119 |
tein | -1.115 |
Token | public |
Token ID | 1171 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Defender | +0.309 |
ilan | +0.298 |
shade | +0.297 |
Interstitial | +0.295 |
tein | +0.293 |
Neg logit contributions | |
resa | -0.327 |
Scotland | -0.277 |
Ireland | -0.246 |
Mitt | -0.245 |
Vice | -0.237 |
Token | speeches |
Token ID | 18138 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
resa | +0.880 |
Scotland | +0.737 |
Mitt | +0.650 |
Ireland | +0.645 |
Vice | +0.624 |
Neg logit contributions | |
Defender | -0.972 |
ilan | -0.949 |
Interstitial | -0.937 |
tein | -0.936 |
shade | -0.932 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Defender | +0.609 |
ilan | +0.588 |
shade | +0.588 |
Interstitial | +0.579 |
tein | +0.578 |
Neg logit contributions | |
resa | -0.591 |
Scotland | -0.496 |
Ireland | -0.439 |
Mitt | -0.433 |
Vice | -0.421 |
Token |
|
Token ID | 198 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
Defender | +0.324 |
ilan | +0.313 |
shade | +0.313 |
Interstitial | +0.308 |
tein | +0.308 |
Neg logit contributions | |
resa | -0.423 |
Scotland | -0.366 |
Mitt | -0.329 |
Ireland | -0.329 |
Vice | -0.320 |
Token |
|
Token ID | 198 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
Defender | +0.434 |
shade | +0.412 |
ilan | +0.412 |
Interstitial | +0.404 |
tein | +0.403 |
Neg logit contributions | |
resa | -0.646 |
Scotland | -0.555 |
Ireland | -0.503 |
Mitt | -0.499 |
Vice | -0.487 |
Token | Newsletter |
Token ID | 33031 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Defender | +0.559 |
ilan | +0.536 |
shade | +0.534 |
Interstitial | +0.529 |
tein | +0.525 |
Neg logit contributions | |
resa | -0.754 |
Scotland | -0.648 |
Ireland | -0.584 |
Mitt | -0.582 |
Vice | -0.566 |
Token | Sign |
Token ID | 5865 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Defender | +2.839 |
shade | +2.654 |
ilan | +2.636 |
Interstitial | +2.574 |
tein | +2.549 |
Neg logit contributions | |
resa | -4.245 |
Scotland | -3.784 |
Ireland | -3.420 |
Vice | -3.341 |
Mitt | -3.332 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Defender | +0.357 |
ilan | +0.336 |
Interstitial | +0.333 |
shade | +0.333 |
tein | +0.328 |
Neg logit contributions | |
resa | -0.556 |
Scotland | -0.484 |
Ireland | -0.441 |
Mitt | -0.432 |
Vice | -0.428 |
Token | Continue |
Token ID | 10054 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
resa | +1.062 |
Scotland | +0.909 |
Ireland | +0.816 |
Mitt | +0.810 |
Vice | +0.789 |
Neg logit contributions | |
Defender | -0.862 |
ilan | -0.827 |
shade | -0.826 |
Interstitial | -0.816 |
tein | -0.812 |
Token | reading |
Token ID | 3555 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
resa | +2.293 |
Scotland | +2.013 |
Ireland | +1.832 |
Mitt | +1.832 |
Vice | +1.792 |
Neg logit contributions | |
Defender | -1.317 |
ilan | -1.272 |
tein | -1.252 |
shade | -1.246 |
Interstitial | -1.239 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
resa | +0.608 |
Scotland | +0.508 |
Ireland | +0.452 |
Mitt | +0.445 |
Vice | +0.436 |
Neg logit contributions | |
Defender | -0.574 |
shade | -0.556 |
ilan | -0.550 |
Interstitial | -0.545 |
tein | -0.541 |
Token | ong |
Token ID | 506 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
resa | +0.057 |
Scotland | +0.049 |
Ireland | +0.044 |
Mitt | +0.044 |
Vice | +0.043 |
Neg logit contributions | |
Defender | -0.040 |
shade | -0.038 |
ilan | -0.038 |
Interstitial | -0.038 |
tein | -0.037 |
Token | had |
Token ID | 550 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Defender | +0.656 |
ilan | +0.630 |
shade | +0.629 |
Interstitial | +0.619 |
tein | +0.618 |
Neg logit contributions | |
resa | -0.805 |
Scotland | -0.689 |
Ireland | -0.619 |
Mitt | -0.613 |
Vice | -0.600 |
Token | just |
Token ID | 655 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
Defender | +0.196 |
shade | +0.189 |
ilan | +0.189 |
Interstitial | +0.186 |
tein | +0.185 |
Neg logit contributions | |
resa | -0.216 |
Scotland | -0.183 |
Ireland | -0.164 |
Mitt | -0.162 |
Vice | -0.158 |
Token | blown |
Token ID | 16318 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Defender | +0.385 |
ilan | +0.372 |
shade | +0.372 |
Interstitial | +0.365 |
tein | +0.365 |
Neg logit contributions | |
resa | -0.411 |
Scotland | -0.347 |
Ireland | -0.310 |
Mitt | -0.306 |
Vice | -0.299 |
Token | me |
Token ID | 502 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Defender | +1.253 |
shade | +1.211 |
ilan | +1.206 |
Interstitial | +1.186 |
tein | +1.183 |
Neg logit contributions | |
resa | -1.462 |
Scotland | -1.246 |
Ireland | -1.114 |
Mitt | -1.102 |
Vice | -1.080 |
Token | away |
Token ID | 1497 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
Defender | +1.147 |
shade | +1.102 |
ilan | +1.097 |
Interstitial | +1.080 |
tein | +1.074 |
Neg logit contributions | |
resa | -1.514 |
Scotland | -1.302 |
Ireland | -1.175 |
Mitt | -1.164 |
Vice | -1.139 |
Token | when |
Token ID | 618 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
Defender | +3.093 |
shade | +2.971 |
ilan | +2.967 |
Interstitial | +2.882 |
tein | +2.856 |
Neg logit contributions | |
resa | -3.890 |
Scotland | -3.296 |
Ireland | -2.997 |
Mitt | -2.908 |
Vice | -2.897 |
Token | Dead |
Token ID | 5542 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Defender | +0.432 |
ilan | +0.416 |
shade | +0.416 |
Interstitial | +0.410 |
tein | +0.409 |
Neg logit contributions | |
resa | -0.474 |
Scotland | -0.402 |
Ireland | -0.358 |
Mitt | -0.355 |
Vice | -0.346 |
Token | Kenn |
Token ID | 7158 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Defender | +0.767 |
ilan | +0.739 |
shade | +0.738 |
Interstitial | +0.729 |
tein | +0.727 |
Neg logit contributions | |
resa | -0.836 |
Scotland | -0.710 |
Ireland | -0.631 |
Mitt | -0.628 |
Vice | -0.610 |
Token | ed |
Token ID | 276 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
resa | +0.267 |
Scotland | +0.217 |
Mitt | +0.189 |
Ireland | +0.188 |
Vice | +0.179 |
Neg logit contributions | |
Defender | -0.345 |
Interstitial | -0.335 |
ilan | -0.334 |
tein | -0.333 |
shade | -0.333 |
Token | ys |
Token ID | 893 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
resa | +0.330 |
Scotland | +0.256 |
Ireland | +0.209 |
Mitt | +0.206 |
Vice | +0.198 |
Neg logit contributions | |
Defender | -0.621 |
shade | -0.605 |
ilan | -0.604 |
Interstitial | -0.595 |
tein | -0.594 |
Token | sites |
Token ID | 5043 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Defender | +1.137 |
ilan | +1.092 |
shade | +1.089 |
Interstitial | +1.081 |
tein | +1.072 |
Neg logit contributions | |
resa | -1.510 |
Scotland | -1.301 |
Ireland | -1.173 |
Mitt | -1.167 |
Vice | -1.138 |
Token | reported |
Token ID | 2098 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Defender | +0.932 |
shade | +0.894 |
ilan | +0.894 |
tein | +0.876 |
Interstitial | +0.873 |
Neg logit contributions | |
resa | -1.100 |
Scotland | -0.937 |
Ireland | -0.840 |
Mitt | -0.829 |
Vice | -0.811 |
Token | . |
Token ID | 13 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
resa | +0.217 |
Scotland | +0.180 |
Ireland | +0.157 |
Mitt | +0.157 |
Vice | +0.151 |
Neg logit contributions | |
Defender | -0.254 |
ilan | -0.246 |
shade | -0.245 |
Interstitial | -0.244 |
tein | -0.243 |
Token |
|
Token ID | 198 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Defender | +0.427 |
ilan | +0.411 |
shade | +0.411 |
Interstitial | +0.405 |
tein | +0.404 |
Neg logit contributions | |
resa | -0.567 |
Scotland | -0.490 |
Ireland | -0.441 |
Mitt | -0.440 |
Vice | -0.429 |
Token |
|
Token ID | 198 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
Defender | +0.309 |
shade | +0.294 |
ilan | +0.294 |
Interstitial | +0.288 |
tein | +0.288 |
Neg logit contributions | |
resa | -0.452 |
Scotland | -0.388 |
Ireland | -0.352 |
Mitt | -0.349 |
Vice | -0.341 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
Defender | +0.454 |
ilan | +0.436 |
shade | +0.435 |
Interstitial | +0.430 |
tein | +0.428 |
Neg logit contributions | |
resa | -0.581 |
Scotland | -0.498 |
Ireland | -0.448 |
Mitt | -0.446 |
Vice | -0.433 |
Token | Continue |
Token ID | 10054 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Defender | +2.963 |
ilan | +2.838 |
shade | +2.827 |
Interstitial | +2.807 |
tein | +2.740 |
Neg logit contributions | |
resa | -3.991 |
Scotland | -3.469 |
Ireland | -3.104 |
Mitt | -3.081 |
Vice | -3.010 |
Token | reading |
Token ID | 3555 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
resa | +1.407 |
Scotland | +1.234 |
Ireland | +1.125 |
Mitt | +1.122 |
Vice | +1.097 |
Neg logit contributions | |
Defender | -0.793 |
ilan | -0.760 |
shade | -0.751 |
tein | -0.749 |
Interstitial | -0.749 |
Token | the |
Token ID | 262 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
Defender | +0.283 |
shade | +0.276 |
ilan | +0.271 |
Interstitial | +0.268 |
tein | +0.266 |
Neg logit contributions | |
resa | -0.318 |
Scotland | -0.267 |
Ireland | -0.238 |
Mitt | -0.234 |
Vice | -0.229 |
Token | main |
Token ID | 1388 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Defender | +0.054 |
shade | +0.052 |
ilan | +0.052 |
Interstitial | +0.051 |
tein | +0.050 |
Neg logit contributions | |
resa | -0.091 |
Scotland | -0.080 |
Ireland | -0.073 |
Mitt | -0.072 |
Vice | -0.071 |
Token | story |
Token ID | 1621 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
resa | +0.486 |
Scotland | +0.420 |
Ireland | +0.377 |
Mitt | +0.373 |
Vice | +0.365 |
Neg logit contributions | |
Defender | -0.373 |
shade | -0.360 |
ilan | -0.357 |
Interstitial | -0.352 |
tein | -0.350 |
Token | Robert |
Token ID | 5199 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Defender | +0.072 |
shade | +0.069 |
ilan | +0.069 |
Interstitial | +0.068 |
tein | +0.068 |
Neg logit contributions | |
resa | -0.082 |
Scotland | -0.070 |
Ireland | -0.062 |
Mitt | -0.062 |
Vice | -0.060 |
Token | Pic |
Token ID | 15085 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
resa | +1.247 |
Scotland | +1.072 |
Mitt | +0.971 |
Ireland | +0.961 |
Vice | +0.932 |
Neg logit contributions | |
Defender | -0.960 |
Interstitial | -0.925 |
shade | -0.923 |
ilan | -0.922 |
tein | -0.911 |
Token | ardo |
Token ID | 13109 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
resa | +0.533 |
Scotland | +0.445 |
Ireland | +0.390 |
Mitt | +0.388 |
Vice | +0.375 |
Neg logit contributions | |
Defender | -0.584 |
ilan | -0.565 |
shade | -0.564 |
Interstitial | -0.558 |
tein | -0.556 |
Token | took |
Token ID | 1718 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
Defender | +0.338 |
ilan | +0.324 |
shade | +0.324 |
Interstitial | +0.319 |
tein | +0.318 |
Neg logit contributions | |
resa | -0.427 |
Scotland | -0.366 |
Ireland | -0.329 |
Mitt | -0.326 |
Vice | -0.319 |
Token | me |
Token ID | 502 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Defender | +0.459 |
shade | +0.445 |
ilan | +0.442 |
tein | +0.436 |
Interstitial | +0.435 |
Neg logit contributions | |
resa | -0.444 |
Scotland | -0.372 |
Ireland | -0.329 |
Mitt | -0.324 |
Vice | -0.317 |
Token | aside |
Token ID | 7263 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
resa | +0.017 |
Scotland | +0.014 |
Ireland | +0.013 |
Mitt | +0.013 |
Vice | +0.012 |
Neg logit contributions | |
Defender | -0.014 |
ilan | -0.013 |
shade | -0.013 |
Interstitial | -0.013 |
tein | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
Defender | +3.188 |
shade | +3.095 |
ilan | +3.074 |
tein | +2.964 |
Interstitial | +2.944 |
Neg logit contributions | |
resa | -3.646 |
Scotland | -3.095 |
Ireland | -2.815 |
Vice | -2.707 |
Mitt | -2.699 |
Token | he |
Token ID | 339 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
Defender | +0.481 |
shade | +0.462 |
ilan | +0.460 |
tein | +0.450 |
Interstitial | +0.449 |
Neg logit contributions | |
resa | -0.633 |
Scotland | -0.543 |
Ireland | -0.492 |
Mitt | -0.483 |
Vice | -0.477 |
Token | said |
Token ID | 531 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Defender | +0.325 |
ilan | +0.312 |
shade | +0.311 |
tein | +0.305 |
Interstitial | +0.305 |
Neg logit contributions | |
resa | -0.455 |
Scotland | -0.394 |
Ireland | -0.356 |
Mitt | -0.353 |
Vice | -0.346 |
Token | � |
Token ID | 564 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Defender | +0.459 |
shade | +0.441 |
ilan | +0.440 |
Interstitial | +0.433 |
tein | +0.431 |
Neg logit contributions | |
resa | -0.579 |
Scotland | -0.497 |
Ireland | -0.447 |
Mitt | -0.442 |
Vice | -0.433 |
Token | � |
Token ID | 250 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
resa | +0.390 |
Scotland | +0.333 |
Ireland | +0.297 |
Mitt | +0.295 |
Vice | +0.288 |
Neg logit contributions | |
Defender | -0.338 |
ilan | -0.325 |
shade | -0.324 |
Interstitial | -0.320 |
tein | -0.319 |
Token | le |
Token ID | 293 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
resa | +0.274 |
Scotland | +0.237 |
Ireland | +0.215 |
Mitt | +0.213 |
Vice | +0.208 |
Neg logit contributions | |
Defender | -0.190 |
shade | -0.181 |
ilan | -0.181 |
Interstitial | -0.180 |
tein | -0.178 |
Token | noted |
Token ID | 4367 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
resa | +1.035 |
Scotland | +0.884 |
Mitt | +0.802 |
Ireland | +0.796 |
Vice | +0.778 |
Neg logit contributions | |
Defender | -0.842 |
shade | -0.809 |
Interstitial | -0.809 |
ilan | -0.805 |
tein | -0.798 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
resa | +0.623 |
Scotland | +0.515 |
Mitt | +0.449 |
Ireland | +0.448 |
Vice | +0.435 |
Neg logit contributions | |
Defender | -0.766 |
ilan | -0.741 |
shade | -0.740 |
Interstitial | -0.738 |
tein | -0.737 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
Defender | +0.094 |
ilan | +0.090 |
shade | +0.090 |
Interstitial | +0.089 |
tein | +0.089 |
Neg logit contributions | |
resa | -0.122 |
Scotland | -0.105 |
Ireland | -0.095 |
Mitt | -0.094 |
Vice | -0.092 |
Token | T |
Token ID | 51 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
resa | +0.689 |
Scotland | +0.589 |
Ireland | +0.523 |
Mitt | +0.509 |
Vice | +0.505 |
Neg logit contributions | |
Defender | -0.672 |
shade | -0.649 |
ilan | -0.645 |
tein | -0.641 |
Interstitial | -0.633 |
Token | EL |
Token ID | 3698 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
Defender | +0.733 |
ilan | +0.708 |
shade | +0.706 |
Interstitial | +0.697 |
tein | +0.696 |
Neg logit contributions | |
resa | -0.745 |
Scotland | -0.629 |
Ireland | -0.556 |
Mitt | -0.553 |
Vice | -0.537 |
Token | AV |
Token ID | 14661 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Defender | +0.660 |
shade | +0.528 |
ilan | +0.512 |
tein | +0.476 |
Interstitial | +0.425 |
Neg logit contributions | |
resa | -6.166 |
Scotland | -5.599 |
Ireland | -5.266 |
Mitt | -5.197 |
Vice | -5.166 |
Token | IV |
Token ID | 3824 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Defender | +0.469 |
ilan | +0.448 |
shade | +0.410 |
tein | +0.405 |
Interstitial | +0.397 |
Neg logit contributions | |
resa | -1.573 |
Scotland | -1.426 |
Ireland | -1.311 |
Mitt | -1.308 |
geist | -1.303 |
Token | – |
Token ID | 784 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
Defender | +0.584 |
ilan | +0.565 |
shade | +0.564 |
Interstitial | +0.557 |
tein | +0.556 |
Neg logit contributions | |
resa | -0.697 |
Scotland | -0.597 |
Ireland | -0.536 |
Mitt | -0.534 |
Vice | -0.518 |
Token | A |
Token ID | 317 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
resa | +0.731 |
Scotland | +0.623 |
Mitt | +0.554 |
Ireland | +0.553 |
Vice | +0.535 |
Neg logit contributions | |
Defender | -0.672 |
ilan | -0.657 |
shade | -0.655 |
Interstitial | -0.647 |
tein | -0.646 |
Token | clandestine |
Token ID | 39903 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
resa | +0.239 |
Scotland | +0.201 |
Ireland | +0.177 |
Mitt | +0.177 |
Vice | +0.171 |
Neg logit contributions | |
Defender | -0.236 |
ilan | -0.229 |
shade | -0.227 |
Interstitial | -0.227 |
tein | -0.225 |
Token | " |
Token ID | 366 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
resa | +0.141 |
Scotland | +0.120 |
Ireland | +0.107 |
Mitt | +0.107 |
Vice | +0.104 |
Neg logit contributions | |
Defender | -0.124 |
ilan | -0.120 |
shade | -0.119 |
Interstitial | -0.118 |
tein | -0.118 |
Token | watching |
Token ID | 50042 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Defender | +0.531 |
ilan | +0.512 |
shade | +0.512 |
Interstitial | +0.505 |
tein | +0.504 |
Neg logit contributions | |
resa | -0.563 |
Scotland | -0.477 |
Ireland | -0.424 |
Mitt | -0.421 |
Vice | -0.409 |
Token | paint |
Token ID | 7521 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
resa | +0.025 |
Scotland | +0.021 |
Mitt | +0.019 |
Ireland | +0.019 |
Vice | +0.018 |
Neg logit contributions | |
Defender | -0.024 |
ilan | -0.023 |
shade | -0.023 |
Interstitial | -0.023 |
tein | -0.022 |
Token | dry |
Token ID | 5894 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
resa | +1.156 |
Scotland | +0.968 |
Mitt | +0.865 |
Ireland | +0.856 |
Vice | +0.830 |
Neg logit contributions | |
Defender | -1.178 |
ilan | -1.149 |
Interstitial | -1.139 |
tein | -1.132 |
shade | -1.115 |
Token | / |
Token ID | 14 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Defender | +0.128 |
ilan | +0.123 |
shade | +0.122 |
Interstitial | +0.122 |
tein | +0.122 |
Neg logit contributions | |
resa | -0.140 |
Scotland | -0.119 |
Mitt | -0.106 |
Ireland | -0.106 |
Task | -0.102 |
Token | th |
Token ID | 400 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
resa | +0.258 |
Scotland | +0.221 |
Ireland | +0.198 |
Mitt | +0.196 |
Vice | +0.191 |
Neg logit contributions | |
Defender | -0.219 |
ilan | -0.211 |
shade | -0.209 |
tein | -0.207 |
Interstitial | -0.207 |
Token | rob |
Token ID | 22609 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Defender | +3.106 |
ilan | +3.021 |
shade | +2.994 |
tein | +2.964 |
Interstitial | +2.946 |
Neg logit contributions | |
resa | -3.597 |
Scotland | -3.098 |
Ireland | -2.774 |
Mitt | -2.739 |
Vice | -2.661 |
Token | bing |
Token ID | 4623 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Defender | +0.703 |
ilan | +0.673 |
shade | +0.672 |
Interstitial | +0.663 |
tein | +0.659 |
Neg logit contributions | |
resa | -1.031 |
Scotland | -0.893 |
Ireland | -0.808 |
Mitt | -0.805 |
Vice | -0.785 |
Token | hemorrh |
Token ID | 42203 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Defender | +0.542 |
shade | +0.522 |
ilan | +0.522 |
Interstitial | +0.514 |
tein | +0.512 |
Neg logit contributions | |
resa | -0.612 |
Scotland | -0.521 |
Ireland | -0.465 |
Mitt | -0.460 |
Vice | -0.449 |
Token | oids |
Token ID | 10994 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
resa | +0.382 |
Scotland | +0.324 |
Ireland | +0.288 |
Mitt | +0.288 |
Vice | +0.278 |
Neg logit contributions | |
Defender | -0.342 |
ilan | -0.327 |
shade | -0.326 |
Interstitial | -0.324 |
tein | -0.323 |
Token | / |
Token ID | 14 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Defender | +0.429 |
ilan | +0.414 |
shade | +0.412 |
Interstitial | +0.408 |
tein | +0.407 |
Neg logit contributions | |
resa | -0.463 |
Scotland | -0.392 |
Ireland | -0.349 |
Mitt | -0.347 |
Vice | -0.337 |
Token | for |
Token ID | 329 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
resa | +0.596 |
Scotland | +0.508 |
Mitt | +0.459 |
Ireland | +0.452 |
Vice | +0.439 |
Neg logit contributions | |
Defender | -0.505 |
ilan | -0.490 |
Interstitial | -0.489 |
shade | -0.488 |
tein | -0.486 |
Token | watching |
Token ID | 4964 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
resa | +0.485 |
Scotland | +0.412 |
Mitt | +0.368 |
Ireland | +0.367 |
Vice | +0.355 |
Neg logit contributions | |
Defender | -0.434 |
ilan | -0.423 |
shade | -0.418 |
Interstitial | -0.417 |
tein | -0.414 |
Token | TV |
Token ID | 3195 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Defender | +0.836 |
ilan | +0.806 |
shade | +0.806 |
Interstitial | +0.794 |
tein | +0.793 |
Neg logit contributions | |
resa | -0.873 |
Scotland | -0.738 |
Ireland | -0.655 |
Mitt | -0.648 |
Vice | -0.632 |
Token | : |
Token ID | 25 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Defender | +0.609 |
ilan | +0.586 |
shade | +0.585 |
Interstitial | +0.578 |
tein | +0.576 |
Neg logit contributions | |
resa | -0.722 |
Scotland | -0.617 |
Ireland | -0.552 |
Mitt | -0.549 |
Vice | -0.535 |
Token | North |
Token ID | 2258 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
resa | +1.115 |
Scotland | +0.945 |
Mitt | +0.851 |
Ireland | +0.840 |
Vice | +0.816 |
Neg logit contributions | |
Defender | -0.995 |
ilan | -0.974 |
shade | -0.963 |
tein | -0.961 |
Interstitial | -0.961 |
Token | Korea |
Token ID | 4969 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
Defender | +0.992 |
ilan | +0.961 |
shade | +0.960 |
Interstitial | +0.950 |
tein | +0.947 |
Neg logit contributions | |
resa | -0.901 |
Scotland | -0.752 |
Ireland | -0.661 |
Mitt | -0.657 |
Vice | -0.635 |
Token | executes |
Token ID | 42985 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
Defender | +3.187 |
shade | +3.045 |
ilan | +2.985 |
tein | +2.953 |
Interstitial | +2.942 |
Neg logit contributions | |
resa | -3.487 |
Scotland | -2.981 |
Ireland | -2.671 |
Mitt | -2.583 |
Vice | -2.539 |
Token | 80 |
Token ID | 4019 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Defender | +0.072 |
shade | +0.069 |
ilan | +0.069 |
Interstitial | +0.068 |
tein | +0.068 |
Neg logit contributions | |
resa | -0.075 |
Scotland | -0.064 |
Ireland | -0.057 |
Mitt | -0.056 |
Vice | -0.054 |
Token | people |
Token ID | 661 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
resa | +0.554 |
Scotland | +0.469 |
Mitt | +0.419 |
Ireland | +0.417 |
Vice | +0.407 |
Neg logit contributions | |
Defender | -0.497 |
ilan | -0.482 |
shade | -0.478 |
Interstitial | -0.477 |
tein | -0.472 |
Token | in |
Token ID | 287 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
resa | +1.124 |
Scotland | +0.959 |
Mitt | +0.861 |
Ireland | +0.856 |
Vice | +0.835 |
Neg logit contributions | |
Defender | -0.926 |
ilan | -0.896 |
shade | -0.890 |
Interstitial | -0.887 |
tein | -0.879 |
Token | public |
Token ID | 1171 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
resa | +0.188 |
Scotland | +0.158 |
Ireland | +0.140 |
Mitt | +0.140 |
Vice | +0.135 |
Neg logit contributions | |
Defender | -0.183 |
ilan | -0.177 |
shade | -0.176 |
Interstitial | -0.175 |
tein | -0.174 |
Token | of |
Token ID | 286 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
resa | +0.092 |
Scotland | +0.078 |
Ireland | +0.070 |
Mitt | +0.069 |
Vice | +0.068 |
Neg logit contributions | |
Defender | -0.077 |
shade | -0.074 |
ilan | -0.074 |
tein | -0.073 |
Interstitial | -0.073 |
Token | job |
Token ID | 1693 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
resa | +0.396 |
Scotland | +0.326 |
Ireland | +0.283 |
Mitt | +0.282 |
Vice | +0.271 |
Neg logit contributions | |
Defender | -0.485 |
ilan | -0.468 |
shade | -0.467 |
Interstitial | -0.465 |
tein | -0.463 |
Token | losses |
Token ID | 9089 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
resa | +0.215 |
Scotland | +0.177 |
Ireland | +0.154 |
Mitt | +0.152 |
Vice | +0.147 |
Neg logit contributions | |
Defender | -0.264 |
ilan | -0.255 |
shade | -0.255 |
Interstitial | -0.252 |
tein | -0.252 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
resa | +1.710 |
Scotland | +1.461 |
Mitt | +1.309 |
Ireland | +1.305 |
Task | +1.252 |
Neg logit contributions | |
Defender | -1.515 |
ilan | -1.458 |
Interstitial | -1.457 |
shade | -1.452 |
tein | -1.444 |
Token | further |
Token ID | 2252 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
resa | +0.012 |
Scotland | +0.010 |
Ireland | +0.009 |
Mitt | +0.009 |
Vice | +0.008 |
Neg logit contributions | |
Defender | -0.011 |
ilan | -0.011 |
shade | -0.011 |
Interstitial | -0.011 |
tein | -0.011 |
Token | dent |
Token ID | 18794 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
Defender | +0.151 |
ilan | +0.146 |
shade | +0.145 |
Interstitial | +0.145 |
tein | +0.144 |
Neg logit contributions | |
resa | -0.137 |
Scotland | -0.114 |
Ireland | -0.100 |
Mitt | -0.100 |
Vice | -0.096 |
Token | McDonald |
Token ID | 14115 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Defender | +2.916 |
ilan | +2.830 |
shade | +2.816 |
Interstitial | +2.764 |
tein | +2.719 |
Neg logit contributions | |
resa | -3.644 |
Scotland | -3.147 |
Ireland | -2.814 |
Mitt | -2.782 |
Vice | -2.770 |
Token | 's |
Token ID | 338 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
resa | +0.873 |
Scotland | +0.754 |
Ireland | +0.680 |
Mitt | +0.676 |
Vice | +0.657 |
Neg logit contributions | |
Defender | -0.675 |
ilan | -0.658 |
Interstitial | -0.649 |
shade | -0.648 |
tein | -0.646 |
Token | share |
Token ID | 2648 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Defender | +1.115 |
ilan | +1.076 |
shade | +1.075 |
Interstitial | +1.062 |
tein | +1.058 |
Neg logit contributions | |
resa | -1.153 |
Scotland | -0.974 |
Ireland | -0.863 |
Mitt | -0.856 |
Vice | -0.833 |
Token | of |
Token ID | 286 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
resa | +0.311 |
Scotland | +0.268 |
Ireland | +0.244 |
Mitt | +0.242 |
Task | +0.234 |
Neg logit contributions | |
Defender | -0.203 |
ilan | -0.196 |
tein | -0.194 |
Interstitial | -0.192 |
shade | -0.190 |
Token | India |
Token ID | 3794 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Defender | +0.217 |
ilan | +0.210 |
shade | +0.210 |
Interstitial | +0.208 |
tein | +0.207 |
Neg logit contributions | |
resa | -0.159 |
Scotland | -0.129 |
Ireland | -0.111 |
Mitt | -0.110 |
Vice | -0.106 |
Token | line |
Token ID | 1627 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
Defender | +0.306 |
shade | +0.295 |
ilan | +0.295 |
tein | +0.290 |
Interstitial | +0.290 |
Neg logit contributions | |
resa | -0.303 |
Scotland | -0.255 |
Ireland | -0.225 |
Mitt | -0.223 |
Vice | -0.217 |
Token | with |
Token ID | 351 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
Defender | +0.498 |
ilan | +0.478 |
shade | +0.478 |
Interstitial | +0.470 |
tein | +0.470 |
Neg logit contributions | |
resa | -0.582 |
Scotland | -0.497 |
Ireland | -0.444 |
Mitt | -0.440 |
Vice | -0.430 |
Token | Crosby |
Token ID | 33098 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
resa | +0.004 |
Scotland | +0.003 |
Ireland | +0.003 |
Mitt | +0.003 |
Vice | +0.003 |
Neg logit contributions | |
Defender | -0.004 |
ilan | -0.004 |
shade | -0.004 |
Interstitial | -0.004 |
tein | -0.004 |
Token | or |
Token ID | 393 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Defender | +1.006 |
ilan | +0.968 |
shade | +0.966 |
Interstitial | +0.951 |
tein | +0.950 |
Neg logit contributions | |
resa | -1.092 |
Scotland | -0.930 |
Ireland | -0.830 |
Mitt | -0.815 |
Vice | -0.799 |
Token | Malk |
Token ID | 41980 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Defender | +0.305 |
shade | +0.294 |
ilan | +0.294 |
Interstitial | +0.290 |
tein | +0.289 |
Neg logit contributions | |
resa | -0.306 |
Scotland | -0.258 |
Ireland | -0.229 |
Mitt | -0.226 |
Vice | -0.220 |
Token | in |
Token ID | 259 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
Defender | +0.722 |
ilan | +0.687 |
shade | +0.678 |
tein | +0.663 |
lycer | +0.656 |
Neg logit contributions | |
resa | -1.089 |
Scotland | -0.952 |
Ireland | -0.882 |
Mitt | -0.845 |
Vice | -0.836 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Defender | +3.065 |
shade | +2.924 |
ilan | +2.916 |
tein | +2.866 |
Interstitial | +2.851 |
Neg logit contributions | |
resa | -3.546 |
Scotland | -3.045 |
Ireland | -2.749 |
Mitt | -2.632 |
Vice | -2.623 |
Token | instead |
Token ID | 2427 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Defender | +0.267 |
shade | +0.257 |
ilan | +0.257 |
Interstitial | +0.253 |
tein | +0.252 |
Neg logit contributions | |
resa | -0.293 |
Scotland | -0.249 |
Ireland | -0.222 |
Mitt | -0.219 |
Vice | -0.214 |
Token | being |
Token ID | 852 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
resa | +0.928 |
Scotland | +0.790 |
Mitt | +0.706 |
Ireland | +0.703 |
Task | +0.680 |
Neg logit contributions | |
Defender | -0.832 |
ilan | -0.806 |
shade | -0.798 |
Interstitial | -0.797 |
tein | -0.791 |
Token | stuck |
Token ID | 7819 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
resa | +0.053 |
Scotland | +0.045 |
Ireland | +0.040 |
Mitt | +0.039 |
Vice | +0.039 |
Neg logit contributions | |
Defender | -0.051 |
shade | -0.049 |
ilan | -0.049 |
Interstitial | -0.048 |
tein | -0.048 |
Token | on |
Token ID | 319 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
resa | +0.677 |
Scotland | +0.579 |
Mitt | +0.519 |
Ireland | +0.515 |
Vice | +0.500 |
Neg logit contributions | |
Defender | -0.592 |
ilan | -0.573 |
shade | -0.570 |
Interstitial | -0.568 |
tein | -0.567 |
Token | At |
Token ID | 2953 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
Defender | +0.419 |
ilan | +0.404 |
shade | +0.402 |
Interstitial | +0.402 |
tein | +0.397 |
Neg logit contributions | |
resa | -0.433 |
Scotland | -0.361 |
Mitt | -0.320 |
Ireland | -0.319 |
Vice | -0.307 |
Token | first |
Token ID | 717 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
resa | +0.747 |
Scotland | +0.635 |
Mitt | +0.572 |
Ireland | +0.570 |
Vice | +0.553 |
Neg logit contributions | |
Defender | -0.608 |
ilan | -0.590 |
shade | -0.582 |
Interstitial | -0.582 |
tein | -0.574 |
Token | it |
Token ID | 340 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
resa | +0.354 |
Scotland | +0.300 |
Ireland | +0.268 |
Mitt | +0.267 |
Vice | +0.259 |
Neg logit contributions | |
Defender | -0.319 |
ilan | -0.308 |
shade | -0.306 |
Interstitial | -0.303 |
tein | -0.302 |
Token | blew |
Token ID | 17948 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
resa | +0.202 |
Scotland | +0.175 |
Mitt | +0.159 |
Ireland | +0.158 |
Vice | +0.153 |
Neg logit contributions | |
Defender | -0.137 |
ilan | -0.132 |
Interstitial | -0.132 |
shade | -0.130 |
tein | -0.129 |
Token | me |
Token ID | 502 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
Defender | +0.959 |
shade | +0.933 |
ilan | +0.916 |
tein | +0.907 |
Interstitial | +0.903 |
Neg logit contributions | |
resa | -0.964 |
Scotland | -0.813 |
Ireland | -0.720 |
Mitt | -0.704 |
Vice | -0.698 |
Token | away |
Token ID | 1497 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
Defender | +0.585 |
shade | +0.564 |
ilan | +0.563 |
Interstitial | +0.554 |
tein | +0.553 |
Neg logit contributions | |
resa | -0.630 |
Scotland | -0.534 |
Ireland | -0.475 |
Mitt | -0.471 |
Vice | -0.459 |
Token | ", |
Token ID | 1600 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Defender | +3.089 |
shade | +2.965 |
ilan | +2.917 |
tein | +2.875 |
Interstitial | +2.824 |
Neg logit contributions | |
resa | -3.509 |
Scotland | -2.968 |
Ireland | -2.665 |
Vice | -2.609 |
Mitt | -2.566 |
Token | Ms |
Token ID | 6997 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
resa | +0.692 |
Scotland | +0.590 |
Mitt | +0.528 |
Ireland | +0.524 |
Vice | +0.507 |
Neg logit contributions | |
Defender | -0.624 |
ilan | -0.605 |
shade | -0.601 |
Interstitial | -0.600 |
tein | -0.594 |
Token | Al |
Token ID | 978 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
Defender | +1.280 |
shade | +1.216 |
ilan | +1.216 |
tein | +1.189 |
Interstitial | +1.182 |
Neg logit contributions | |
resa | -2.237 |
Scotland | -1.962 |
Ireland | -1.794 |
Mitt | -1.769 |
Vice | -1.748 |
Token | br |
Token ID | 1671 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
Defender | +0.616 |
ilan | +0.595 |
shade | +0.592 |
tein | +0.585 |
Interstitial | +0.585 |
Neg logit contributions | |
resa | -0.705 |
Scotland | -0.603 |
Ireland | -0.539 |
Mitt | -0.535 |
Vice | -0.520 |
Token | itton |
Token ID | 47304 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Defender | +0.245 |
ilan | +0.239 |
shade | +0.237 |
tein | +0.236 |
Interstitial | +0.231 |
Neg logit contributions | |
resa | -0.329 |
Scotland | -0.287 |
Mitt | -0.257 |
Ireland | -0.256 |
Vice | -0.250 |
Token | explains |
Token ID | 6688 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
resa | +0.795 |
Scotland | +0.682 |
Mitt | +0.614 |
Ireland | +0.613 |
Vice | +0.596 |
Neg logit contributions | |
Defender | -0.632 |
ilan | -0.606 |
shade | -0.606 |
Interstitial | -0.603 |
tein | -0.596 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
resa | +0.443 |
Scotland | +0.369 |
Ireland | +0.322 |
Mitt | +0.322 |
Vice | +0.312 |
Neg logit contributions | |
Defender | -0.507 |
ilan | -0.489 |
shade | -0.487 |
tein | -0.485 |
Interstitial | -0.484 |
Token |
|
Token ID | 198 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Defender | +0.070 |
ilan | +0.067 |
shade | +0.067 |
Interstitial | +0.066 |
tein | +0.066 |
Neg logit contributions | |
resa | -0.090 |
Scotland | -0.078 |
Ireland | -0.070 |
Mitt | -0.069 |
Vice | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Defender | +0.111 |
shade | +0.106 |
ilan | +0.106 |
Interstitial | +0.104 |
tein | +0.104 |
Neg logit contributions | |
resa | -0.159 |
Scotland | -0.137 |
Ireland | -0.124 |
Mitt | -0.123 |
Vice | -0.120 |
Token | Setting |
Token ID | 34149 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Defender | +0.364 |
ilan | +0.352 |
shade | +0.351 |
Interstitial | +0.349 |
tein | +0.345 |
Neg logit contributions | |
resa | -0.386 |
Scotland | -0.324 |
Mitt | -0.288 |
Ireland | -0.288 |
Vice | -0.277 |
Token | aside |
Token ID | 7263 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
resa | +0.415 |
Scotland | +0.352 |
Ireland | +0.312 |
Mitt | +0.312 |
Task | +0.300 |
Neg logit contributions | |
Defender | -0.395 |
ilan | -0.382 |
shade | -0.378 |
Interstitial | -0.377 |
tein | -0.376 |
Token | the |
Token ID | 262 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
Defender | +3.120 |
shade | +3.051 |
ilan | +2.978 |
tein | +2.947 |
Interstitial | +2.944 |
Neg logit contributions | |
resa | -3.449 |
Scotland | -2.907 |
Ireland | -2.631 |
Vice | -2.535 |
Mitt | -2.533 |
Token | drama |
Token ID | 10512 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Defender | +0.631 |
shade | +0.610 |
ilan | +0.608 |
Interstitial | +0.600 |
tein | +0.600 |
Neg logit contributions | |
resa | -0.610 |
Scotland | -0.513 |
Ireland | -0.454 |
Mitt | -0.448 |
Vice | -0.436 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Defender | +1.279 |
shade | +1.230 |
ilan | +1.226 |
Interstitial | +1.209 |
tein | +1.204 |
Neg logit contributions | |
resa | -1.560 |
Scotland | -1.337 |
Ireland | -1.199 |
Mitt | -1.185 |
Vice | -1.160 |
Token | tsun |
Token ID | 28798 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Defender | +0.094 |
ilan | +0.091 |
shade | +0.090 |
Interstitial | +0.089 |
tein | +0.089 |
Neg logit contributions | |
resa | -0.095 |
Scotland | -0.080 |
Ireland | -0.071 |
Mitt | -0.070 |
Vice | -0.068 |
Token | am |
Token ID | 321 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Defender | +0.314 |
ilan | +0.306 |
shade | +0.304 |
Interstitial | +0.301 |
tein | +0.297 |
Neg logit contributions | |
resa | -0.226 |
Scotland | -0.184 |
Ireland | -0.159 |
Mitt | -0.155 |
Task | -0.150 |
Token | � |
Token ID | 247 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
Defender | +0.769 |
shade | +0.746 |
ilan | +0.745 |
Interstitial | +0.741 |
tein | +0.735 |
Neg logit contributions | |
resa | -0.467 |
Scotland | -0.373 |
Ireland | -0.311 |
Mitt | -0.305 |
Vice | -0.291 |
Token | s |
Token ID | 82 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
Defender | +0.578 |
ilan | +0.557 |
shade | +0.556 |
Interstitial | +0.550 |
tein | +0.548 |
Neg logit contributions | |
resa | -0.647 |
Scotland | -0.550 |
Ireland | -0.490 |
Mitt | -0.488 |
Vice | -0.474 |
Token | � |
Token ID | 564 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Defender | +0.495 |
ilan | +0.477 |
shade | +0.476 |
Interstitial | +0.470 |
tein | +0.469 |
Neg logit contributions | |
resa | -0.529 |
Scotland | -0.448 |
Ireland | -0.398 |
Mitt | -0.396 |
Vice | -0.385 |
Token | � |
Token ID | 246 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Defender | +0.265 |
ilan | +0.255 |
shade | +0.255 |
Interstitial | +0.251 |
tein | +0.250 |
Neg logit contributions | |
resa | -0.336 |
Scotland | -0.289 |
Ireland | -0.259 |
Mitt | -0.258 |
Vice | -0.252 |
Token | Far |
Token ID | 21428 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
resa | +0.195 |
Scotland | +0.165 |
Ireland | +0.146 |
Mitt | +0.143 |
Vice | +0.141 |
Neg logit contributions | |
Defender | -0.197 |
shade | -0.191 |
ilan | -0.190 |
tein | -0.188 |
Interstitial | -0.187 |
Token | Away |
Token ID | 21986 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
Defender | +0.494 |
ilan | +0.476 |
shade | +0.475 |
Interstitial | +0.468 |
tein | +0.467 |
Neg logit contributions | |
resa | -0.741 |
Scotland | -0.641 |
Ireland | -0.582 |
Mitt | -0.579 |
Vice | -0.565 |
Token | � |
Token ID | 447 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
Defender | +3.275 |
shade | +3.137 |
ilan | +3.131 |
Interstitial | +3.081 |
tein | +3.069 |
Neg logit contributions | |
resa | -3.323 |
Scotland | -2.801 |
Ireland | -2.503 |
Mitt | -2.439 |
Vice | -2.402 |
Token | � |
Token ID | 247 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Defender | +0.571 |
ilan | +0.554 |
shade | +0.554 |
Interstitial | +0.550 |
tein | +0.547 |
Neg logit contributions | |
resa | -0.328 |
Scotland | -0.258 |
Ireland | -0.213 |
Mitt | -0.209 |
Vice | -0.201 |
Token | that |
Token ID | 326 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
Defender | +0.367 |
ilan | +0.355 |
shade | +0.353 |
Interstitial | +0.350 |
tein | +0.349 |
Neg logit contributions | |
resa | -0.383 |
Scotland | -0.324 |
Ireland | -0.287 |
Mitt | -0.286 |
Vice | -0.277 |
Token | stuck |
Token ID | 7819 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Defender | +0.438 |
ilan | +0.421 |
shade | +0.419 |
Interstitial | +0.414 |
tein | +0.413 |
Neg logit contributions | |
resa | -0.572 |
Scotland | -0.492 |
Ireland | -0.443 |
Mitt | -0.441 |
Vice | -0.429 |
Token | in |
Token ID | 287 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Defender | +0.802 |
shade | +0.770 |
ilan | +0.769 |
Interstitial | +0.759 |
tein | +0.756 |
Neg logit contributions | |
resa | -0.958 |
Scotland | -0.819 |
Ireland | -0.733 |
Mitt | -0.727 |
Vice | -0.710 |
Token | AL |
Token ID | 1847 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
resa | +0.131 |
Scotland | +0.113 |
Ireland | +0.103 |
Mitt | +0.102 |
Vice | +0.099 |
Neg logit contributions | |
Defender | -0.095 |
ilan | -0.092 |
shade | -0.091 |
Interstitial | -0.090 |
tein | -0.090 |
Token | YS |
Token ID | 16309 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Defender | +2.067 |
shade | +2.001 |
ilan | +2.001 |
tein | +1.973 |
Interstitial | +1.970 |
Neg logit contributions | |
resa | -1.791 |
Scotland | -1.484 |
Ireland | -1.294 |
Mitt | -1.282 |
Task | -1.242 |
Token | IS |
Token ID | 1797 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Defender | +0.895 |
shade | +0.854 |
ilan | +0.851 |
Interstitial | +0.835 |
tein | +0.834 |
Neg logit contributions | |
resa | -1.376 |
Scotland | -1.190 |
Ireland | -1.078 |
Mitt | -1.074 |
Vice | -1.050 |
Token | / |
Token ID | 14 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
resa | +0.408 |
Scotland | +0.334 |
Mitt | +0.290 |
Ireland | +0.286 |
Vice | +0.275 |
Neg logit contributions | |
Defender | -0.563 |
ilan | -0.550 |
tein | -0.547 |
shade | -0.546 |
Interstitial | -0.544 |
Token | OP |
Token ID | 3185 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
resa | +0.573 |
Scotland | +0.493 |
Ireland | +0.441 |
Mitt | +0.438 |
Vice | +0.430 |
Neg logit contributions | |
Defender | -0.491 |
ilan | -0.476 |
shade | -0.472 |
tein | -0.468 |
Interstitial | -0.468 |
Token | IN |
Token ID | 1268 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
Defender | +0.568 |
ilan | +0.539 |
shade | +0.536 |
Interstitial | +0.528 |
tein | +0.527 |
Neg logit contributions | |
resa | -1.106 |
Scotland | -0.975 |
Ireland | -0.894 |
Mitt | -0.891 |
Vice | -0.871 |
Token | ION |
Token ID | 2849 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Defender | +3.472 |
shade | +3.400 |
ilan | +3.350 |
Interstitial | +3.311 |
tein | +3.256 |
Neg logit contributions | |
resa | -3.106 |
Scotland | -2.536 |
Mitt | -2.189 |
Ireland | -2.161 |
Vice | -2.100 |
Token | : |
Token ID | 25 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
Defender | +0.810 |
ilan | +0.794 |
shade | +0.789 |
Interstitial | +0.786 |
tein | +0.785 |
Neg logit contributions | |
resa | -0.842 |
Scotland | -0.719 |
Mitt | -0.643 |
Ireland | -0.638 |
Vice | -0.623 |
Token |
|
Token ID | 198 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
resa | +0.579 |
Scotland | +0.500 |
Ireland | +0.451 |
Mitt | +0.450 |
Vice | +0.438 |
Neg logit contributions | |
Defender | -0.431 |
ilan | -0.415 |
shade | -0.414 |
Interstitial | -0.408 |
tein | -0.408 |
Token |
|
Token ID | 198 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Defender | +0.360 |
shade | +0.343 |
ilan | +0.343 |
Interstitial | +0.337 |
tein | +0.336 |
Neg logit contributions | |
resa | -0.523 |
Scotland | -0.450 |
Ireland | -0.408 |
Mitt | -0.405 |
Vice | -0.395 |
Token | If |
Token ID | 1532 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Defender | +0.401 |
ilan | +0.389 |
shade | +0.387 |
Interstitial | +0.384 |
tein | +0.381 |
Neg logit contributions | |
resa | -0.365 |
Scotland | -0.303 |
Ireland | -0.266 |
Mitt | -0.265 |
Vice | -0.255 |
Token | el |
Token ID | 1288 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Defender | +0.124 |
ilan | +0.120 |
shade | +0.119 |
Interstitial | +0.119 |
tein | +0.118 |
Neg logit contributions | |
resa | -0.122 |
Scotland | -0.102 |
Mitt | -0.091 |
Ireland | -0.090 |
Vice | -0.087 |
Token | it |
Token ID | 270 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
Defender | +2.040 |
ilan | +1.973 |
shade | +1.970 |
Interstitial | +1.947 |
tein | +1.943 |
Neg logit contributions | |
resa | -1.886 |
Scotland | -1.579 |
Ireland | -1.386 |
Mitt | -1.374 |
Vice | -1.333 |
Token | ist |
Token ID | 396 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
resa | +0.674 |
Scotland | +0.572 |
Ireland | +0.508 |
Mitt | +0.504 |
Vice | +0.490 |
Neg logit contributions | |
Defender | -0.625 |
ilan | -0.603 |
shade | -0.602 |
Interstitial | -0.594 |
tein | -0.593 |
Token | liberal |
Token ID | 7270 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
resa | +0.229 |
Scotland | +0.193 |
Mitt | +0.171 |
Ireland | +0.171 |
Vice | +0.165 |
Neg logit contributions | |
Defender | -0.221 |
ilan | -0.213 |
shade | -0.211 |
Interstitial | -0.211 |
tein | -0.210 |
Token | sn |
Token ID | 3013 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
resa | +0.726 |
Scotland | +0.605 |
Mitt | +0.539 |
Ireland | +0.535 |
Vice | +0.516 |
Neg logit contributions | |
Defender | -0.749 |
ilan | -0.721 |
Interstitial | -0.719 |
shade | -0.718 |
tein | -0.714 |
Token | ob |
Token ID | 672 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
Defender | +0.370 |
shade | +0.357 |
ilan | +0.356 |
Interstitial | +0.354 |
tein | +0.351 |
Neg logit contributions | |
resa | -0.372 |
Scotland | -0.313 |
Ireland | -0.276 |
Mitt | -0.275 |
Vice | -0.266 |
Token | bery |
Token ID | 13001 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Defender | +2.134 |
shade | +2.064 |
ilan | +2.019 |
tein | +1.935 |
Interstitial | +1.904 |
Neg logit contributions | |
resa | -4.361 |
Scotland | -3.888 |
Ireland | -3.580 |
Task | -3.476 |
Vice | -3.472 |
Token | , |
Token ID | 11 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
Defender | +0.239 |
shade | +0.231 |
ilan | +0.230 |
Interstitial | +0.226 |
tein | +0.226 |
Neg logit contributions | |
resa | -0.265 |
Scotland | -0.225 |
Ireland | -0.201 |
Mitt | -0.198 |
Vice | -0.194 |
Token | and |
Token ID | 290 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Defender | +0.032 |
ilan | +0.031 |
shade | +0.030 |
Interstitial | +0.030 |
tein | +0.030 |
Neg logit contributions | |
resa | -0.034 |
Scotland | -0.029 |
Ireland | -0.026 |
Mitt | -0.026 |
Vice | -0.025 |
Token | have |
Token ID | 423 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
resa | +0.312 |
Scotland | +0.263 |
Mitt | +0.234 |
Ireland | +0.233 |
Vice | +0.225 |
Neg logit contributions | |
Defender | -0.306 |
ilan | -0.297 |
shade | -0.294 |
Interstitial | -0.293 |
tein | -0.292 |
Token | doubled |
Token ID | 15229 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
resa | +0.382 |
Scotland | +0.326 |
Mitt | +0.293 |
Ireland | +0.292 |
Vice | +0.283 |
Neg logit contributions | |
Defender | -0.318 |
ilan | -0.307 |
shade | -0.304 |
Interstitial | -0.303 |
tein | -0.302 |
Token | As |
Token ID | 1722 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
Defender | +1.122 |
ilan | +1.083 |
shade | +1.079 |
Interstitial | +1.066 |
tein | +1.064 |
Neg logit contributions | |
resa | -1.212 |
Scotland | -1.027 |
Ireland | -0.913 |
Mitt | -0.908 |
Vice | -0.882 |
Token | yu |
Token ID | 24767 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Defender | +0.641 |
shade | +0.617 |
ilan | +0.616 |
Interstitial | +0.611 |
tein | +0.609 |
Neg logit contributions | |
resa | -0.681 |
Scotland | -0.577 |
Ireland | -0.513 |
Mitt | -0.509 |
Vice | -0.496 |
Token |
|
Token ID | 198 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
resa | +0.408 |
Scotland | +0.351 |
Ireland | +0.316 |
Mitt | +0.314 |
Vice | +0.308 |
Neg logit contributions | |
Defender | -0.336 |
shade | -0.323 |
ilan | -0.323 |
Interstitial | -0.320 |
tein | -0.319 |
Token |
|
Token ID | 198 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Defender | +0.003 |
ilan | +0.003 |
shade | +0.003 |
Interstitial | +0.003 |
tein | +0.003 |
Neg logit contributions | |
resa | -0.004 |
Scotland | -0.004 |
Ireland | -0.003 |
Mitt | -0.003 |
Vice | -0.003 |
Token | K |
Token ID | 42 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Defender | +0.273 |
shade | +0.263 |
ilan | +0.263 |
Interstitial | +0.260 |
tein | +0.259 |
Neg logit contributions | |
resa | -0.277 |
Scotland | -0.234 |
Ireland | -0.207 |
Mitt | -0.205 |
Vice | -0.200 |
Token | ong |
Token ID | 506 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
Defender | +1.210 |
ilan | +1.167 |
shade | +1.164 |
Interstitial | +1.150 |
tein | +1.147 |
Neg logit contributions | |
resa | -1.310 |
Scotland | -1.111 |
Ireland | -0.988 |
Mitt | -0.982 |
Vice | -0.954 |
Token |
|
Token ID | 198 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
Defender | +3.251 |
ilan | +3.118 |
shade | +3.118 |
tein | +3.055 |
Interstitial | +3.046 |
Neg logit contributions | |
resa | -3.299 |
Scotland | -2.775 |
Ireland | -2.466 |
Mitt | -2.440 |
Vice | -2.359 |
Token |
|
Token ID | 198 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Defender | +0.486 |
shade | +0.463 |
ilan | +0.463 |
tein | +0.452 |
Interstitial | +0.452 |
Neg logit contributions | |
resa | -0.717 |
Scotland | -0.618 |
Ireland | -0.560 |
Mitt | -0.556 |
Vice | -0.543 |
Token | Ch |
Token ID | 1925 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Defender | +0.648 |
shade | +0.625 |
ilan | +0.625 |
Interstitial | +0.617 |
tein | +0.616 |
Neg logit contributions | |
resa | -0.652 |
Scotland | -0.550 |
Ireland | -0.486 |
Mitt | -0.482 |
Vice | -0.469 |
Token | oya |
Token ID | 23790 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
Defender | +0.758 |
ilan | +0.730 |
shade | +0.730 |
Interstitial | +0.721 |
tein | +0.718 |
Neg logit contributions | |
resa | -0.829 |
Scotland | -0.703 |
Ireland | -0.626 |
Mitt | -0.622 |
Vice | -0.605 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Defender | +0.353 |
shade | +0.340 |
ilan | +0.340 |
Interstitial | +0.336 |
tein | +0.335 |
Neg logit contributions | |
resa | -0.440 |
Scotland | -0.380 |
Ireland | -0.342 |
Mitt | -0.340 |
Vice | -0.332 |
Token | - |
Token ID | 532 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
resa | +0.005 |
Scotland | +0.004 |
Ireland | +0.004 |
Mitt | +0.004 |
Vice | +0.004 |
Neg logit contributions | |
Defender | -0.003 |
ilan | -0.002 |
shade | -0.002 |
Interstitial | -0.002 |
tein | -0.002 |
Token | 202 |
Token ID | 22131 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
resa | +1.669 |
Scotland | +1.401 |
Mitt | +1.234 |
Ireland | +1.223 |
Vice | +1.191 |
Neg logit contributions | |
Defender | -1.855 |
ilan | -1.808 |
Interstitial | -1.806 |
shade | -1.803 |
tein | -1.795 |
Token | . |
Token ID | 764 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Defender | +0.059 |
shade | +0.057 |
ilan | +0.057 |
Interstitial | +0.056 |
tein | +0.056 |
Neg logit contributions | |
resa | -0.058 |
Scotland | -0.049 |
Ireland | -0.043 |
Mitt | -0.043 |
Vice | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
resa | +1.791 |
Scotland | +1.549 |
Ireland | +1.393 |
Mitt | +1.391 |
Vice | +1.352 |
Neg logit contributions | |
Defender | -1.422 |
ilan | -1.373 |
shade | -1.368 |
Interstitial | -1.359 |
tein | -1.351 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
resa | +1.688 |
Scotland | +1.461 |
Ireland | +1.312 |
Mitt | +1.308 |
Vice | +1.273 |
Neg logit contributions | |
Defender | -1.321 |
ilan | -1.274 |
shade | -1.269 |
Interstitial | -1.261 |
tein | -1.253 |
Token | Google |
Token ID | 11708 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
resa | +1.042 |
Scotland | +0.878 |
Ireland | +0.771 |
Mitt | +0.751 |
Vice | +0.742 |
Neg logit contributions | |
Defender | -1.222 |
shade | -1.181 |
ilan | -1.175 |
tein | -1.160 |
Interstitial | -1.156 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
resa | +2.757 |
Scotland | +2.390 |
Mitt | +2.178 |
Ireland | +2.145 |
Task | +2.099 |
Neg logit contributions | |
Defender | -2.027 |
ilan | -2.001 |
Interstitial | -1.967 |
shade | -1.957 |
tein | -1.943 |
Token | Crossref |
Token ID | 23613 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
resa | +1.283 |
Scotland | +1.125 |
Mitt | +1.024 |
Ireland | +1.024 |
Vice | +0.995 |
Neg logit contributions | |
Defender | -0.802 |
ilan | -0.773 |
Interstitial | -0.771 |
tein | -0.767 |
shade | -0.765 |
Token | | |
Token ID | 930 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
resa | +1.351 |
Scotland | +1.164 |
Ireland | +1.049 |
Mitt | +1.049 |
Vice | +1.016 |
Neg logit contributions | |
Defender | -1.047 |
ilan | -1.009 |
shade | -1.006 |
tein | -0.995 |
Interstitial | -0.994 |
Token | ISI |
Token ID | 22048 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
resa | +0.454 |
Scotland | +0.380 |
Ireland | +0.333 |
Mitt | +0.332 |
Vice | +0.320 |
Neg logit contributions | |
Defender | -0.505 |
ilan | -0.491 |
shade | -0.489 |
Interstitial | -0.484 |
tein | -0.483 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
resa | +2.380 |
Scotland | +2.055 |
Mitt | +1.843 |
Ireland | +1.837 |
Vice | +1.792 |
Neg logit contributions | |
Defender | -1.933 |
ilan | -1.874 |
shade | -1.873 |
Interstitial | -1.854 |
tein | -1.846 |
Token | of |
Token ID | 286 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
resa | +0.098 |
Scotland | +0.083 |
Ireland | +0.075 |
Mitt | +0.075 |
Vice | +0.072 |
Neg logit contributions | |
Defender | -0.088 |
ilan | -0.085 |
shade | -0.085 |
Interstitial | -0.084 |
tein | -0.084 |
Token | Pre |
Token ID | 3771 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Defender | +0.109 |
shade | +0.103 |
ilan | +0.103 |
Interstitial | +0.101 |
tein | +0.101 |
Neg logit contributions | |
resa | -0.198 |
Scotland | -0.174 |
Ireland | -0.159 |
Mitt | -0.157 |
Vice | -0.155 |
Token | y |
Token ID | 88 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
resa | +0.681 |
Scotland | +0.554 |
Ireland | +0.475 |
Mitt | +0.470 |
Vice | +0.453 |
Neg logit contributions | |
Defender | -0.933 |
ilan | -0.904 |
shade | -0.904 |
Interstitial | -0.893 |
tein | -0.892 |
Token |
|
Token ID | 198 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
resa | +0.747 |
Scotland | +0.640 |
Mitt | +0.574 |
Ireland | +0.572 |
Vice | +0.554 |
Neg logit contributions | |
Defender | -0.627 |
ilan | -0.605 |
shade | -0.603 |
tein | -0.599 |
Interstitial | -0.598 |
Token |
|
Token ID | 198 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
Defender | +0.199 |
shade | +0.190 |
ilan | +0.189 |
Interstitial | +0.185 |
tein | +0.185 |
Neg logit contributions | |
resa | -0.296 |
Scotland | -0.254 |
Ireland | -0.231 |
Mitt | -0.230 |
Vice | -0.224 |
Token | https |
Token ID | 5450 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Defender | +0.379 |
ilan | +0.365 |
shade | +0.365 |
Interstitial | +0.360 |
tein | +0.360 |
Neg logit contributions | |
resa | -0.397 |
Scotland | -0.336 |
Ireland | -0.298 |
Mitt | -0.296 |
Vice | -0.288 |
Token | :// |
Token ID | 1378 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
resa | +1.408 |
Scotland | +1.078 |
Ireland | +0.869 |
Mitt | +0.854 |
Vice | +0.818 |
Neg logit contributions | |
Defender | -2.854 |
ilan | -2.778 |
shade | -2.778 |
Interstitial | -2.758 |
tein | -2.752 |
Token | kill |
Token ID | 12728 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
resa | +0.064 |
Scotland | +0.055 |
Ireland | +0.049 |
Mitt | +0.048 |
Vice | +0.048 |
Neg logit contributions | |
Defender | -0.051 |
shade | -0.049 |
ilan | -0.048 |
Interstitial | -0.048 |
tein | -0.047 |
Token | ert |
Token ID | 861 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
Defender | +0.521 |
ilan | +0.501 |
shade | +0.501 |
Interstitial | +0.496 |
tein | +0.493 |
Neg logit contributions | |
resa | -0.556 |
Scotland | -0.470 |
Ireland | -0.418 |
Mitt | -0.415 |
Vice | -0.403 |
Token | of |
Token ID | 1659 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
resa | +0.084 |
Scotland | +0.072 |
Ireland | +0.065 |
Mitt | +0.064 |
Vice | +0.063 |
Neg logit contributions | |
Defender | -0.067 |
shade | -0.063 |
Interstitial | -0.063 |
ilan | -0.063 |
tein | -0.062 |
Token | ure |
Token ID | 495 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Defender | +0.819 |
ilan | +0.789 |
shade | +0.786 |
Interstitial | +0.775 |
tein | +0.775 |
Neg logit contributions | |
resa | -1.052 |
Scotland | -0.906 |
Ireland | -0.814 |
Mitt | -0.810 |
Vice | -0.789 |
Token | mail |
Token ID | 4529 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
resa | +1.494 |
Scotland | +1.256 |
Ireland | +1.102 |
Mitt | +1.088 |
Vice | +1.061 |
Neg logit contributions | |
Defender | -1.644 |
ilan | -1.591 |
shade | -1.590 |
Interstitial | -1.567 |
tein | -1.566 |
Token | this |
Token ID | 428 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
resa | +1.781 |
Scotland | +1.500 |
Mitt | +1.388 |
Ireland | +1.334 |
Task | +1.310 |
Neg logit contributions | |
Defender | -1.595 |
ilan | -1.564 |
Interstitial | -1.563 |
shade | -1.537 |
tein | -1.514 |
Token | to |
Token ID | 284 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Defender | +0.020 |
shade | +0.020 |
ilan | +0.019 |
tein | +0.019 |
Interstitial | +0.018 |
Neg logit contributions | |
resa | -0.024 |
Scotland | -0.021 |
Ireland | -0.019 |
Mitt | -0.019 |
Vice | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Defender | +0.014 |
shade | +0.013 |
tein | +0.013 |
ilan | +0.013 |
plagiar | +0.013 |
Neg logit contributions | |
resa | -0.015 |
Scotland | -0.013 |
Ireland | -0.012 |
Vice | -0.011 |
Mitt | -0.011 |
Token | friend |
Token ID | 1545 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Defender | +0.167 |
shade | +0.164 |
ilan | +0.159 |
tein | +0.159 |
plagiar | +0.155 |
Neg logit contributions | |
resa | -0.251 |
Scotland | -0.216 |
Ireland | -0.198 |
Vice | -0.188 |
Task | -0.188 |
Token | Print |
Token ID | 12578 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
Defender | +0.335 |
ilan | +0.312 |
shade | +0.309 |
tein | +0.305 |
lycer | +0.303 |
Neg logit contributions | |
resa | -0.479 |
Scotland | -0.417 |
Ireland | -0.376 |
Mitt | -0.369 |
Vice | -0.368 |
Token | able |
Token ID | 540 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
resa | +2.450 |
Scotland | +2.098 |
Mitt | +1.942 |
Ireland | +1.923 |
Task | +1.912 |
Neg logit contributions | |
Defender | -2.447 |
Interstitial | -2.391 |
shade | -2.347 |
ilan | -2.347 |
tein | -2.341 |
Token | version |
Token ID | 2196 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Defender | +2.130 |
ilan | +2.064 |
shade | +2.060 |
Interstitial | +2.036 |
tein | +2.033 |
Neg logit contributions | |
resa | -1.506 |
Scotland | -1.221 |
Ireland | -1.043 |
Mitt | -1.023 |
Vice | -0.989 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
Defender | +0.080 |
ilan | +0.077 |
shade | +0.077 |
Interstitial | +0.076 |
tein | +0.075 |
Neg logit contributions | |
resa | -0.110 |
Scotland | -0.095 |
Ireland | -0.086 |
Mitt | -0.085 |
Vice | -0.083 |
Token | Rob |
Token ID | 14350 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
resa | +0.304 |
Scotland | +0.259 |
Ireland | +0.230 |
Mitt | +0.225 |
Vice | +0.222 |
Neg logit contributions | |
Defender | -0.297 |
shade | -0.287 |
ilan | -0.286 |
tein | -0.283 |
Interstitial | -0.281 |
Token | C |
Token ID | 327 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Defender | +0.533 |
shade | +0.514 |
ilan | +0.514 |
Interstitial | +0.510 |
tein | +0.506 |
Neg logit contributions | |
resa | -0.609 |
Scotland | -0.518 |
Ireland | -0.462 |
Mitt | -0.461 |
Vice | -0.447 |
Token | seconds |
Token ID | 4201 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
resa | +0.975 |
Scotland | +0.815 |
Mitt | +0.719 |
Ireland | +0.712 |
Task | +0.687 |
Neg logit contributions | |
Defender | -1.082 |
ilan | -1.050 |
Interstitial | -1.045 |
shade | -1.040 |
tein | -1.036 |
Token | with |
Token ID | 351 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
resa | +1.846 |
Scotland | +1.583 |
Mitt | +1.439 |
Ireland | +1.416 |
Task | +1.394 |
Neg logit contributions | |
Defender | -1.622 |
ilan | -1.568 |
Interstitial | -1.567 |
shade | -1.538 |
tein | -1.536 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
resa | +0.903 |
Scotland | +0.753 |
Mitt | +0.672 |
Ireland | +0.663 |
Task | +0.645 |
Neg logit contributions | |
Defender | -0.928 |
ilan | -0.899 |
Interstitial | -0.896 |
shade | -0.888 |
tein | -0.886 |
Token | couple |
Token ID | 3155 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
resa | +0.988 |
Scotland | +0.835 |
Mitt | +0.751 |
Ireland | +0.741 |
Task | +0.725 |
Neg logit contributions | |
Defender | -0.895 |
Interstitial | -0.868 |
ilan | -0.867 |
shade | -0.857 |
tein | -0.856 |
Token | of |
Token ID | 286 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
resa | +0.721 |
Scotland | +0.612 |
Mitt | +0.548 |
Ireland | +0.545 |
Task | +0.529 |
Neg logit contributions | |
Defender | -0.639 |
ilan | -0.617 |
shade | -0.613 |
Interstitial | -0.612 |
tein | -0.608 |
Token | clicks |
Token ID | 25785 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
resa | +1.300 |
Scotland | +1.091 |
Mitt | +0.984 |
Ireland | +0.960 |
Task | +0.946 |
Neg logit contributions | |
Defender | -1.242 |
Interstitial | -1.206 |
ilan | -1.206 |
tein | -1.192 |
shade | -1.191 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
resa | +2.599 |
Scotland | +2.219 |
Mitt | +2.020 |
Ireland | +1.972 |
Task | +1.956 |
Neg logit contributions | |
Defender | -2.431 |
ilan | -2.351 |
Interstitial | -2.346 |
tein | -2.329 |
shade | -2.313 |
Token | then |
Token ID | 788 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
resa | +0.745 |
Scotland | +0.615 |
Ireland | +0.534 |
Mitt | +0.533 |
Vice | +0.513 |
Neg logit contributions | |
Defender | -0.895 |
ilan | -0.868 |
shade | -0.865 |
Interstitial | -0.859 |
tein | -0.856 |
Token | you |
Token ID | 345 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
resa | +1.597 |
Scotland | +1.313 |
Mitt | +1.172 |
Ireland | +1.146 |
Vice | +1.108 |
Neg logit contributions | |
Defender | -1.793 |
ilan | -1.751 |
Interstitial | -1.751 |
tein | -1.734 |
shade | -1.730 |
Token | might |
Token ID | 1244 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
resa | +1.113 |
Scotland | +0.950 |
Mitt | +0.851 |
Ireland | +0.850 |
Vice | +0.824 |
Neg logit contributions | |
Defender | -0.901 |
ilan | -0.866 |
Interstitial | -0.861 |
shade | -0.858 |
tein | -0.856 |
Token | want |
Token ID | 765 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
resa | +1.279 |
Scotland | +1.064 |
Mitt | +0.946 |
Ireland | +0.931 |
Task | +0.903 |
Neg logit contributions | |
Defender | -1.316 |
ilan | -1.281 |
Interstitial | -1.278 |
tein | -1.262 |
shade | -1.250 |
Token | prepare |
Token ID | 8335 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Defender | +0.030 |
ilan | +0.029 |
Interstitial | +0.029 |
shade | +0.029 |
tein | +0.029 |
Neg logit contributions | |
resa | -0.033 |
Scotland | -0.028 |
Mitt | -0.025 |
Ireland | -0.025 |
Vice | -0.024 |
Token | you |
Token ID | 345 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
resa | +0.368 |
Scotland | +0.309 |
Mitt | +0.274 |
Ireland | +0.274 |
Vice | +0.264 |
Neg logit contributions | |
Defender | -0.364 |
ilan | -0.353 |
shade | -0.350 |
Interstitial | -0.348 |
tein | -0.347 |
Token | for |
Token ID | 329 |
Feature activation | -9.44e-04 |
Pos logit contributions | |
resa | +0.692 |
Scotland | +0.593 |
Mitt | +0.537 |
Ireland | +0.529 |
Task | +0.516 |
Neg logit contributions | |
Defender | -0.564 |
ilan | -0.548 |
tein | -0.544 |
shade | -0.543 |
Interstitial | -0.542 |
Token | the |
Token ID | 262 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Defender | +0.001 |
shade | +0.001 |
ilan | +0.001 |
Interstitial | +0.001 |
tein | +0.001 |
Neg logit contributions | |
resa | -0.001 |
Scotland | -0.001 |
Ireland | -0.001 |
Mitt | -0.001 |
Vice | -0.001 |
Token | awful |
Token ID | 12659 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
Defender | +0.245 |
shade | +0.236 |
ilan | +0.233 |
Interstitial | +0.230 |
tein | +0.230 |
Neg logit contributions | |
resa | -0.232 |
Scotland | -0.197 |
Ireland | -0.175 |
Mitt | -0.170 |
Vice | -0.167 |
Token | moment |
Token ID | 2589 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
resa | +0.527 |
Scotland | +0.445 |
Ireland | +0.395 |
Mitt | +0.393 |
Vice | +0.381 |
Neg logit contributions | |
Defender | -0.507 |
ilan | -0.489 |
shade | -0.488 |
Interstitial | -0.483 |
tein | -0.481 |
Token | when |
Token ID | 618 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
resa | +2.548 |
Scotland | +2.132 |
Mitt | +1.945 |
Ireland | +1.887 |
Vice | +1.831 |
Neg logit contributions | |
Defender | -2.521 |
ilan | -2.462 |
Interstitial | -2.444 |
shade | -2.427 |
tein | -2.420 |
Token | you |
Token ID | 345 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
resa | +0.884 |
Scotland | +0.745 |
Mitt | +0.664 |
Ireland | +0.660 |
Vice | +0.638 |
Neg logit contributions | |
Defender | -0.853 |
ilan | -0.829 |
shade | -0.820 |
Interstitial | -0.817 |
tein | -0.813 |
Token | administer |
Token ID | 21766 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
resa | +0.995 |
Scotland | +0.841 |
Mitt | +0.746 |
Ireland | +0.746 |
Vice | +0.722 |
Neg logit contributions | |
Defender | -0.917 |
ilan | -0.889 |
shade | -0.880 |
Interstitial | -0.878 |
tein | -0.873 |
Token | CPR |
Token ID | 42920 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
resa | +0.052 |
Scotland | +0.044 |
Ireland | +0.039 |
Mitt | +0.039 |
Vice | +0.038 |
Neg logit contributions | |
Defender | -0.046 |
ilan | -0.045 |
shade | -0.044 |
Interstitial | -0.044 |
tein | -0.044 |
Token | for |
Token ID | 329 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
resa | +0.069 |
Scotland | +0.058 |
Mitt | +0.052 |
Ireland | +0.052 |
Task | +0.050 |
Neg logit contributions | |
Defender | -0.060 |
ilan | -0.058 |
shade | -0.058 |
Interstitial | -0.058 |
tein | -0.057 |
Token | macro |
Token ID | 15021 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Defender | +0.089 |
ilan | +0.086 |
shade | +0.085 |
Interstitial | +0.084 |
tein | +0.084 |
Neg logit contributions | |
resa | -0.110 |
Scotland | -0.094 |
Ireland | -0.085 |
Mitt | -0.084 |
Vice | -0.082 |
Token | sites |
Token ID | 5043 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
resa | +1.669 |
Scotland | +1.406 |
Ireland | +1.265 |
Mitt | +1.263 |
Task | +1.219 |
Neg logit contributions | |
Defender | -1.527 |
ilan | -1.473 |
shade | -1.455 |
tein | -1.443 |
Interstitial | -1.436 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
resa | +0.750 |
Scotland | +0.633 |
Ireland | +0.561 |
Mitt | +0.560 |
Vice | +0.540 |
Neg logit contributions | |
Defender | -0.727 |
ilan | -0.703 |
shade | -0.699 |
Interstitial | -0.693 |
tein | -0.692 |
Token | � |
Token ID | 447 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
resa | +0.263 |
Scotland | +0.223 |
Ireland | +0.199 |
Mitt | +0.197 |
Vice | +0.192 |
Neg logit contributions | |
Defender | -0.243 |
ilan | -0.234 |
shade | -0.234 |
Interstitial | -0.231 |
tein | -0.231 |
Token | � |
Token ID | 251 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
resa | +0.164 |
Scotland | +0.138 |
Ireland | +0.122 |
Mitt | +0.121 |
Vice | +0.118 |
Neg logit contributions | |
Defender | -0.165 |
ilan | -0.159 |
shade | -0.159 |
Interstitial | -0.157 |
tein | -0.156 |
Token | he |
Token ID | 339 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
resa | +0.400 |
Scotland | +0.342 |
Mitt | +0.308 |
Ireland | +0.306 |
Vice | +0.297 |
Neg logit contributions | |
Defender | -0.332 |
ilan | -0.321 |
shade | -0.319 |
tein | -0.317 |
Interstitial | -0.316 |
Token | claimed |
Token ID | 4752 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
resa | +0.364 |
Scotland | +0.310 |
Mitt | +0.281 |
Ireland | +0.278 |
Vice | +0.271 |
Neg logit contributions | |
Defender | -0.296 |
shade | -0.284 |
ilan | -0.282 |
Interstitial | -0.280 |
tein | -0.279 |
Token | , |
Token ID | 11 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
resa | +0.947 |
Scotland | +0.782 |
Mitt | +0.690 |
Ireland | +0.681 |
Vice | +0.658 |
Neg logit contributions | |
Defender | -1.151 |
ilan | -1.118 |
tein | -1.111 |
shade | -1.107 |
Interstitial | -1.101 |
Token | according |
Token ID | 1864 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Defender | +0.390 |
ilan | +0.375 |
shade | +0.374 |
Interstitial | +0.370 |
tein | +0.369 |
Neg logit contributions | |
resa | -0.497 |
Scotland | -0.428 |
Ireland | -0.384 |
Mitt | -0.383 |
Vice | -0.373 |
Token | to |
Token ID | 284 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
resa | +0.601 |
Scotland | +0.505 |
Ireland | +0.446 |
Mitt | +0.443 |
Vice | +0.430 |
Neg logit contributions | |
Defender | -0.619 |
ilan | -0.598 |
shade | -0.597 |
Interstitial | -0.590 |
tein | -0.589 |
Token | a |
Token ID | 257 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
Defender | +0.168 |
ilan | +0.163 |
Interstitial | +0.162 |
shade | +0.162 |
tein | +0.162 |
Neg logit contributions | |
resa | -0.177 |
Scotland | -0.149 |
Mitt | -0.134 |
Ireland | -0.132 |
Vice | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
resa | +0.632 |
Scotland | +0.538 |
Mitt | +0.483 |
Ireland | +0.481 |
Vice | +0.467 |
Neg logit contributions | |
Defender | -0.542 |
ilan | -0.526 |
shade | -0.522 |
Interstitial | -0.519 |
tein | -0.518 |
Token | Mary |
Token ID | 5335 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
resa | +0.246 |
Scotland | +0.205 |
Mitt | +0.181 |
Ireland | +0.181 |
Vice | +0.175 |
Neg logit contributions | |
Defender | -0.257 |
ilan | -0.249 |
shade | -0.248 |
Interstitial | -0.247 |
tein | -0.246 |
Token | Mc |
Token ID | 1982 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Defender | +0.315 |
ilan | +0.305 |
shade | +0.304 |
Interstitial | +0.302 |
tein | +0.302 |
Neg logit contributions | |
resa | -0.328 |
Scotland | -0.278 |
Ireland | -0.247 |
Mitt | -0.246 |
Vice | -0.238 |
Token | Leod |
Token ID | 44559 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
resa | +1.139 |
Scotland | +0.967 |
Ireland | +0.857 |
Mitt | +0.845 |
Vice | +0.828 |
Neg logit contributions | |
Defender | -1.153 |
shade | -1.120 |
ilan | -1.119 |
Interstitial | -1.104 |
tein | -1.104 |
Token | Beth |
Token ID | 19223 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
resa | +0.202 |
Scotland | +0.172 |
Mitt | +0.155 |
Ireland | +0.154 |
Vice | +0.149 |
Neg logit contributions | |
Defender | -0.172 |
ilan | -0.168 |
shade | -0.166 |
tein | -0.165 |
Interstitial | -0.165 |
Token | une |
Token ID | 1726 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
Defender | +0.529 |
ilan | +0.507 |
shade | +0.506 |
Interstitial | +0.497 |
tein | +0.497 |
Neg logit contributions | |
resa | -0.738 |
Scotland | -0.639 |
Ireland | -0.578 |
Mitt | -0.573 |
Vice | -0.560 |
Token | Memorial |
Token ID | 14861 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
resa | +0.486 |
Scotland | +0.414 |
Mitt | +0.374 |
Ireland | +0.370 |
Vice | +0.358 |
Neg logit contributions | |
Defender | -0.409 |
ilan | -0.402 |
tein | -0.396 |
shade | -0.395 |
Interstitial | -0.394 |
Token | , |
Token ID | 11 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Defender | +1.380 |
ilan | +1.331 |
shade | +1.326 |
Interstitial | +1.311 |
tein | +1.308 |
Neg logit contributions | |
resa | -1.615 |
Scotland | -1.378 |
Ireland | -1.232 |
Mitt | -1.227 |
Vice | -1.191 |
Token | by |
Token ID | 416 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
resa | +0.192 |
Scotland | +0.162 |
Ireland | +0.144 |
Mitt | +0.143 |
Vice | +0.139 |
Neg logit contributions | |
Defender | -0.186 |
ilan | -0.180 |
shade | -0.180 |
Interstitial | -0.178 |
tein | -0.177 |
Token | artist |
Token ID | 6802 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Defender | +0.362 |
ilan | +0.349 |
shade | +0.349 |
Interstitial | +0.344 |
tein | +0.344 |
Neg logit contributions | |
resa | -0.356 |
Scotland | -0.300 |
Ireland | -0.265 |
Mitt | -0.262 |
Vice | -0.254 |
Token | Robert |
Token ID | 5199 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
resa | +0.736 |
Scotland | +0.619 |
Mitt | +0.549 |
Ireland | +0.548 |
Vice | +0.528 |
Neg logit contributions | |
Defender | -0.724 |
ilan | -0.699 |
shade | -0.698 |
Interstitial | -0.695 |
tein | -0.693 |
Token | career |
Token ID | 3451 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
resa | +0.751 |
Scotland | +0.625 |
Mitt | +0.551 |
Ireland | +0.549 |
Task | +0.529 |
Neg logit contributions | |
Defender | -0.819 |
ilan | -0.799 |
shade | -0.792 |
Interstitial | -0.788 |
tein | -0.788 |
Token | & |
Token ID | 1222 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
resa | +0.482 |
Scotland | +0.399 |
Ireland | +0.348 |
Mitt | +0.346 |
Task | +0.334 |
Neg logit contributions | |
Defender | -0.565 |
ilan | -0.548 |
shade | -0.547 |
Interstitial | -0.543 |
tein | -0.541 |
Token | organization |
Token ID | 4009 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
resa | +0.055 |
Scotland | +0.046 |
Ireland | +0.040 |
Mitt | +0.040 |
Vice | +0.038 |
Neg logit contributions | |
Defender | -0.061 |
ilan | -0.059 |
shade | -0.059 |
Interstitial | -0.058 |
tein | -0.058 |
Token | ? |
Token ID | 30 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
resa | +0.192 |
Scotland | +0.159 |
Ireland | +0.138 |
Mitt | +0.137 |
Vice | +0.132 |
Neg logit contributions | |
Defender | -0.235 |
ilan | -0.229 |
shade | -0.228 |
tein | -0.226 |
Interstitial | -0.226 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Defender | +0.397 |
shade | +0.383 |
ilan | +0.382 |
Interstitial | +0.377 |
tein | +0.376 |
Neg logit contributions | |
resa | -0.532 |
Scotland | -0.460 |
Ireland | -0.415 |
Mitt | -0.414 |
Vice | -0.403 |
Token |
|
Token ID | 198 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
resa | +0.956 |
Scotland | +0.827 |
Ireland | +0.745 |
Mitt | +0.741 |
Vice | +0.723 |
Neg logit contributions | |
Defender | -0.719 |
ilan | -0.691 |
shade | -0.689 |
Interstitial | -0.681 |
tein | -0.678 |
Token | Section |
Token ID | 16375 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
resa | +0.546 |
Scotland | +0.468 |
Ireland | +0.418 |
Mitt | +0.407 |
Task | +0.404 |
Neg logit contributions | |
Defender | -0.513 |
shade | -0.496 |
ilan | -0.491 |
tein | -0.486 |
Interstitial | -0.483 |
Token | III |
Token ID | 6711 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
resa | +1.221 |
Scotland | +1.044 |
Mitt | +0.951 |
Ireland | +0.944 |
Vice | +0.925 |
Neg logit contributions | |
Defender | -0.889 |
ilan | -0.858 |
shade | -0.857 |
Interstitial | -0.853 |
tein | -0.843 |
Token | : |
Token ID | 25 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
resa | +0.098 |
Scotland | +0.084 |
Ireland | +0.075 |
Mitt | +0.075 |
Task | +0.073 |
Neg logit contributions | |
Defender | -0.082 |
shade | -0.080 |
ilan | -0.079 |
Interstitial | -0.079 |
tein | -0.078 |
Token | Lean |
Token ID | 45661 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
resa | +0.852 |
Scotland | +0.731 |
Mitt | +0.656 |
Ireland | +0.655 |
Task | +0.635 |
Neg logit contributions | |
Defender | -0.716 |
shade | -0.697 |
ilan | -0.696 |
Interstitial | -0.688 |
tein | -0.686 |
Token | Six |
Token ID | 9699 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
resa | +0.536 |
Scotland | +0.455 |
Ireland | +0.408 |
Mitt | +0.406 |
Task | +0.395 |
Neg logit contributions | |
Defender | -0.482 |
shade | -0.468 |
ilan | -0.466 |
Interstitial | -0.461 |
tein | -0.461 |
Token | This |
Token ID | 770 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
Defender | +0.181 |
shade | +0.173 |
ilan | +0.173 |
Interstitial | +0.170 |
tein | +0.169 |
Neg logit contributions | |
resa | -0.221 |
Scotland | -0.190 |
Ireland | -0.170 |
Mitt | -0.168 |
Vice | -0.165 |
Token | is |
Token ID | 318 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Defender | +0.379 |
ilan | +0.365 |
shade | +0.363 |
Interstitial | +0.361 |
tein | +0.360 |
Neg logit contributions | |
resa | -0.412 |
Scotland | -0.349 |
Ireland | -0.311 |
Mitt | -0.310 |
Vice | -0.300 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
resa | +0.015 |
Scotland | +0.012 |
Ireland | +0.011 |
Mitt | +0.011 |
Vice | +0.011 |
Neg logit contributions | |
Defender | -0.014 |
ilan | -0.014 |
shade | -0.014 |
Interstitial | -0.013 |
tein | -0.013 |
Token | best |
Token ID | 1266 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Defender | +0.197 |
ilan | +0.190 |
shade | +0.188 |
Interstitial | +0.187 |
tein | +0.187 |
Neg logit contributions | |
resa | -0.233 |
Scotland | -0.198 |
Ireland | -0.177 |
Mitt | -0.177 |
Vice | -0.172 |
Token | possible |
Token ID | 1744 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Defender | +0.586 |
ilan | +0.564 |
shade | +0.564 |
Interstitial | +0.557 |
tein | +0.555 |
Neg logit contributions | |
resa | -0.648 |
Scotland | -0.551 |
Ireland | -0.490 |
Mitt | -0.487 |
Vice | -0.474 |
Token | image |
Token ID | 2939 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
resa | +0.152 |
Scotland | +0.129 |
Ireland | +0.115 |
Mitt | +0.115 |
Vice | +0.111 |
Neg logit contributions | |
Defender | -0.137 |
ilan | -0.133 |
shade | -0.131 |
Interstitial | -0.131 |
tein | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
resa | +0.386 |
Scotland | +0.328 |
Ireland | +0.292 |
Mitt | +0.292 |
Vice | +0.283 |
Neg logit contributions | |
Defender | -0.342 |
ilan | -0.330 |
shade | -0.328 |
Interstitial | -0.326 |
tein | -0.324 |
Token | lens |
Token ID | 10317 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
resa | +0.129 |
Scotland | +0.109 |
Ireland | +0.097 |
Mitt | +0.097 |
Vice | +0.093 |
Neg logit contributions | |
Defender | -0.118 |
ilan | -0.114 |
shade | -0.113 |
Interstitial | -0.113 |
tein | -0.112 |
Token | can |
Token ID | 460 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Defender | +0.055 |
ilan | +0.053 |
shade | +0.053 |
Interstitial | +0.052 |
tein | +0.052 |
Neg logit contributions | |
resa | -0.060 |
Scotland | -0.051 |
Ireland | -0.045 |
Mitt | -0.045 |
Vice | -0.044 |
Token | make |
Token ID | 787 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Defender | +0.196 |
shade | +0.189 |
ilan | +0.188 |
Interstitial | +0.186 |
tein | +0.185 |
Neg logit contributions | |
resa | -0.223 |
Scotland | -0.190 |
Ireland | -0.170 |
Mitt | -0.168 |
Vice | -0.164 |
Token | in |
Token ID | 287 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Defender | +0.121 |
ilan | +0.117 |
shade | +0.116 |
Interstitial | +0.115 |
tein | +0.115 |
Neg logit contributions | |
resa | -0.133 |
Scotland | -0.113 |
Ireland | -0.100 |
Mitt | -0.100 |
Vice | -0.097 |
Token | So |
Token ID | 1406 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Defender | +0.914 |
ilan | +0.870 |
shade | +0.870 |
Interstitial | +0.855 |
tein | +0.852 |
Neg logit contributions | |
resa | -1.216 |
Scotland | -1.045 |
Ireland | -0.943 |
Mitt | -0.929 |
Vice | -0.914 |
Token | there |
Token ID | 612 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Defender | +0.507 |
ilan | +0.489 |
shade | +0.488 |
Interstitial | +0.482 |
tein | +0.480 |
Neg logit contributions | |
resa | -0.553 |
Scotland | -0.470 |
Ireland | -0.418 |
Mitt | -0.414 |
Vice | -0.404 |
Token | are |
Token ID | 389 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
resa | +0.886 |
Scotland | +0.754 |
Mitt | +0.675 |
Ireland | +0.671 |
Vice | +0.653 |
Neg logit contributions | |
Defender | -0.772 |
ilan | -0.746 |
shade | -0.741 |
Interstitial | -0.738 |
tein | -0.735 |
Token | 100 |
Token ID | 1802 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
Defender | +0.104 |
ilan | +0.100 |
shade | +0.100 |
Interstitial | +0.099 |
tein | +0.099 |
Neg logit contributions | |
resa | -0.111 |
Scotland | -0.094 |
Ireland | -0.084 |
Mitt | -0.083 |
Vice | -0.081 |
Token | lock |
Token ID | 5793 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
resa | +0.763 |
Scotland | +0.641 |
Mitt | +0.574 |
Ireland | +0.571 |
Task | +0.555 |
Neg logit contributions | |
Defender | -0.708 |
ilan | -0.685 |
shade | -0.681 |
Interstitial | -0.675 |
tein | -0.673 |
Token | ers |
Token ID | 364 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
resa | +1.160 |
Scotland | +0.987 |
Mitt | +0.878 |
Ireland | +0.874 |
Task | +0.855 |
Neg logit contributions | |
Defender | -1.099 |
ilan | -1.068 |
Interstitial | -1.055 |
tein | -1.051 |
shade | -1.039 |
Token | in |
Token ID | 287 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
resa | +1.591 |
Scotland | +1.344 |
Mitt | +1.203 |
Ireland | +1.190 |
Task | +1.154 |
Neg logit contributions | |
Defender | -1.524 |
ilan | -1.480 |
Interstitial | -1.466 |
tein | -1.459 |
shade | -1.457 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
resa | +0.847 |
Scotland | +0.718 |
Ireland | +0.637 |
Mitt | +0.635 |
Vice | +0.615 |
Neg logit contributions | |
Defender | -0.803 |
ilan | -0.777 |
shade | -0.773 |
Interstitial | -0.767 |
tein | -0.764 |
Token | row |
Token ID | 5752 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
resa | +0.943 |
Scotland | +0.802 |
Mitt | +0.717 |
Ireland | +0.712 |
Task | +0.693 |
Neg logit contributions | |
Defender | -0.843 |
ilan | -0.824 |
Interstitial | -0.822 |
tein | -0.814 |
shade | -0.805 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
resa | +1.631 |
Scotland | +1.373 |
Mitt | +1.216 |
Ireland | +1.209 |
Task | +1.171 |
Neg logit contributions | |
Defender | -1.659 |
ilan | -1.613 |
Interstitial | -1.599 |
shade | -1.592 |
tein | -1.589 |
Token | They |
Token ID | 1119 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
resa | +0.220 |
Scotland | +0.189 |
Ireland | +0.170 |
Mitt | +0.169 |
Vice | +0.165 |
Neg logit contributions | |
Defender | -0.171 |
ilan | -0.164 |
shade | -0.164 |
Interstitial | -0.162 |
tein | -0.161 |
Token | of |
Token ID | 286 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
Defender | +0.708 |
ilan | +0.681 |
shade | +0.679 |
Interstitial | +0.671 |
tein | +0.669 |
Neg logit contributions | |
resa | -0.846 |
Scotland | -0.723 |
Ireland | -0.648 |
Mitt | -0.644 |
Vice | -0.627 |
Token | glowing |
Token ID | 21377 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Defender | +0.378 |
ilan | +0.365 |
shade | +0.363 |
Interstitial | +0.360 |
tein | +0.359 |
Neg logit contributions | |
resa | -0.405 |
Scotland | -0.342 |
Ireland | -0.304 |
Mitt | -0.303 |
Vice | -0.294 |
Token | praise |
Token ID | 13463 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
Defender | +0.274 |
ilan | +0.263 |
Interstitial | +0.259 |
shade | +0.259 |
tein | +0.258 |
Neg logit contributions | |
resa | -0.401 |
Scotland | -0.347 |
Mitt | -0.315 |
Ireland | -0.314 |
Vice | -0.306 |
Token | for |
Token ID | 329 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
Defender | +0.061 |
ilan | +0.059 |
shade | +0.058 |
tein | +0.058 |
Interstitial | +0.058 |
Neg logit contributions | |
resa | -0.072 |
Scotland | -0.061 |
Mitt | -0.055 |
Ireland | -0.055 |
Vice | -0.053 |
Token | this |
Token ID | 428 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Defender | +0.055 |
ilan | +0.053 |
shade | +0.053 |
Interstitial | +0.053 |
tein | +0.052 |
Neg logit contributions | |
resa | -0.059 |
Scotland | -0.050 |
Ireland | -0.044 |
Mitt | -0.044 |
Vice | -0.043 |
Token | yo |
Token ID | 27406 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Defender | +0.360 |
ilan | +0.347 |
shade | +0.347 |
Interstitial | +0.343 |
tein | +0.342 |
Neg logit contributions | |
resa | -0.370 |
Scotland | -0.312 |
Ireland | -0.276 |
Mitt | -0.275 |
Vice | -0.267 |
Token | - |
Token ID | 12 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
Defender | +0.830 |
ilan | +0.798 |
shade | +0.797 |
Interstitial | +0.785 |
tein | +0.783 |
Neg logit contributions | |
resa | -1.038 |
Scotland | -0.891 |
Ireland | -0.800 |
Mitt | -0.795 |
Vice | -0.775 |
Token | yo |
Token ID | 8226 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
resa | +0.437 |
Scotland | +0.333 |
Ireland | +0.270 |
Mitt | +0.265 |
Vice | +0.254 |
Neg logit contributions | |
Defender | -0.879 |
ilan | -0.854 |
shade | -0.854 |
Interstitial | -0.851 |
tein | -0.844 |
Token | in |
Token ID | 287 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
resa | +0.953 |
Scotland | +0.809 |
Mitt | +0.738 |
Ireland | +0.724 |
Task | +0.707 |
Neg logit contributions | |
Defender | -0.807 |
ilan | -0.794 |
Interstitial | -0.788 |
tein | -0.774 |
shade | -0.767 |
Token | throwing |
Token ID | 9644 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Defender | +0.232 |
ilan | +0.225 |
shade | +0.223 |
Interstitial | +0.221 |
tein | +0.221 |
Neg logit contributions | |
resa | -0.236 |
Scotland | -0.200 |
Ireland | -0.177 |
Mitt | -0.177 |
Vice | -0.170 |
Token | community |
Token ID | 2055 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Defender | +0.226 |
ilan | +0.220 |
Interstitial | +0.217 |
tein | +0.215 |
shade | +0.214 |
Neg logit contributions | |
resa | -0.247 |
Scotland | -0.209 |
Mitt | -0.186 |
Ireland | -0.186 |
Vice | -0.179 |
Token | of |
Token ID | 286 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
Defender | +0.170 |
ilan | +0.163 |
Interstitial | +0.162 |
shade | +0.162 |
tein | +0.162 |
Neg logit contributions | |
resa | -0.187 |
Scotland | -0.158 |
Ireland | -0.142 |
Mitt | -0.141 |
Vice | -0.136 |
Token | a |
Token ID | 257 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
Defender | +0.468 |
ilan | +0.452 |
shade | +0.449 |
Interstitial | +0.445 |
tein | +0.445 |
Neg logit contributions | |
resa | -0.514 |
Scotland | -0.437 |
Ireland | -0.389 |
Mitt | -0.388 |
Vice | -0.376 |
Token | keyword |
Token ID | 21179 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
Defender | +0.620 |
ilan | +0.600 |
shade | +0.596 |
Interstitial | +0.592 |
tein | +0.591 |
Neg logit contributions | |
resa | -0.695 |
Scotland | -0.590 |
Ireland | -0.526 |
Mitt | -0.525 |
Vice | -0.509 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Defender | +0.366 |
shade | +0.353 |
ilan | +0.353 |
Interstitial | +0.348 |
tein | +0.347 |
Neg logit contributions | |
resa | -0.378 |
Scotland | -0.319 |
Ireland | -0.283 |
Mitt | -0.281 |
Vice | -0.273 |
Token | It |
Token ID | 632 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Defender | +1.022 |
shade | +0.975 |
ilan | +0.974 |
Interstitial | +0.961 |
tein | +0.956 |
Neg logit contributions | |
resa | -1.303 |
Scotland | -1.118 |
Ireland | -1.004 |
Mitt | -0.993 |
Vice | -0.974 |
Token | 's |
Token ID | 338 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Defender | +0.855 |
shade | +0.820 |
ilan | +0.820 |
Interstitial | +0.805 |
tein | +0.803 |
Neg logit contributions | |
resa | -1.177 |
Scotland | -1.016 |
Ireland | -0.918 |
Mitt | -0.910 |
Vice | -0.890 |
Token | good |
Token ID | 922 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
Defender | +0.775 |
shade | +0.747 |
ilan | +0.746 |
Interstitial | +0.735 |
tein | +0.732 |
Neg logit contributions | |
resa | -0.807 |
Scotland | -0.682 |
Ireland | -0.605 |
Mitt | -0.599 |
Vice | -0.585 |
Token | to |
Token ID | 284 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
resa | +0.055 |
Scotland | +0.047 |
Mitt | +0.042 |
Ireland | +0.042 |
Task | +0.040 |
Neg logit contributions | |
Defender | -0.052 |
ilan | -0.051 |
shade | -0.050 |
Interstitial | -0.050 |
tein | -0.050 |
Token | think |
Token ID | 892 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Defender | +0.285 |
shade | +0.275 |
ilan | +0.274 |
Interstitial | +0.270 |
tein | +0.269 |
Neg logit contributions | |
resa | -0.318 |
Scotland | -0.271 |
Ireland | -0.241 |
Mitt | -0.239 |
Vice | -0.234 |
Token | about |
Token ID | 546 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Defender | +0.314 |
ilan | +0.304 |
shade | +0.302 |
Interstitial | +0.301 |
tein | +0.299 |
Neg logit contributions | |
resa | -0.315 |
Scotland | -0.266 |
Ireland | -0.236 |
Mitt | -0.235 |
Vice | -0.226 |
Token | all |
Token ID | 477 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
Defender | +0.121 |
ilan | +0.117 |
shade | +0.116 |
Interstitial | +0.116 |
tein | +0.115 |
Neg logit contributions | |
resa | -0.121 |
Scotland | -0.102 |
Ireland | -0.090 |
Mitt | -0.090 |
Task | -0.087 |
Token | � |
Token ID | 250 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
Defender | +1.919 |
shade | +1.845 |
ilan | +1.845 |
Interstitial | +1.824 |
tein | +1.812 |
Neg logit contributions | |
resa | -2.137 |
Scotland | -1.815 |
Ireland | -1.616 |
Mitt | -1.605 |
Vice | -1.565 |
Token | The |
Token ID | 464 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Defender | +0.641 |
ilan | +0.619 |
shade | +0.618 |
Interstitial | +0.613 |
tein | +0.609 |
Neg logit contributions | |
resa | -0.624 |
Scotland | -0.522 |
Ireland | -0.460 |
Mitt | -0.459 |
Vice | -0.443 |
Token | attempt |
Token ID | 2230 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
Defender | +0.347 |
shade | +0.336 |
ilan | +0.335 |
Interstitial | +0.330 |
tein | +0.330 |
Neg logit contributions | |
resa | -0.322 |
Scotland | -0.272 |
Ireland | -0.239 |
Mitt | -0.236 |
Vice | -0.230 |
Token | to |
Token ID | 284 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Defender | +0.590 |
ilan | +0.569 |
shade | +0.568 |
Interstitial | +0.561 |
tein | +0.559 |
Neg logit contributions | |
resa | -0.617 |
Scotland | -0.522 |
Ireland | -0.463 |
Mitt | -0.459 |
Vice | -0.447 |
Token | blur |
Token ID | 23671 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Defender | +0.728 |
shade | +0.705 |
ilan | +0.701 |
tein | +0.691 |
Interstitial | +0.690 |
Neg logit contributions | |
resa | -0.775 |
Scotland | -0.657 |
Ireland | -0.584 |
Mitt | -0.577 |
Vice | -0.565 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
resa | +0.187 |
Scotland | +0.157 |
Ireland | +0.139 |
Mitt | +0.138 |
Vice | +0.133 |
Neg logit contributions | |
Defender | -0.197 |
ilan | -0.190 |
shade | -0.190 |
Interstitial | -0.188 |
tein | -0.187 |
Token | boundary |
Token ID | 18645 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Defender | +0.091 |
shade | +0.088 |
ilan | +0.088 |
Interstitial | +0.087 |
tein | +0.086 |
Neg logit contributions | |
resa | -0.090 |
Scotland | -0.076 |
Ireland | -0.067 |
Mitt | -0.067 |
Vice | -0.065 |
Token | lines |
Token ID | 3951 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Defender | +0.370 |
ilan | +0.358 |
shade | +0.358 |
Interstitial | +0.354 |
tein | +0.353 |
Neg logit contributions | |
resa | -0.294 |
Scotland | -0.242 |
Ireland | -0.209 |
Mitt | -0.208 |
Vice | -0.200 |
Token | between |
Token ID | 1022 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Defender | +0.413 |
ilan | +0.399 |
shade | +0.399 |
Interstitial | +0.394 |
tein | +0.393 |
Neg logit contributions | |
resa | -0.349 |
Scotland | -0.289 |
Ireland | -0.252 |
Mitt | -0.249 |
Vice | -0.242 |
Token | sovereign |
Token ID | 18901 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
resa | +0.098 |
Scotland | +0.082 |
Ireland | +0.073 |
Mitt | +0.072 |
Vice | +0.070 |
Neg logit contributions | |
Defender | -0.101 |
ilan | -0.097 |
shade | -0.097 |
Interstitial | -0.096 |
tein | -0.096 |
Token | Israel |
Token ID | 2692 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
Defender | +0.181 |
ilan | +0.175 |
shade | +0.175 |
Interstitial | +0.172 |
tein | +0.172 |
Neg logit contributions | |
resa | -0.167 |
Scotland | -0.139 |
Ireland | -0.122 |
Mitt | -0.121 |
Vice | -0.118 |
Token | of |
Token ID | 286 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Defender | +0.414 |
shade | +0.397 |
ilan | +0.396 |
Interstitial | +0.391 |
tein | +0.389 |
Neg logit contributions | |
resa | -0.503 |
Scotland | -0.430 |
Ireland | -0.386 |
Mitt | -0.382 |
Vice | -0.373 |
Token | American |
Token ID | 1605 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Defender | +0.399 |
shade | +0.387 |
ilan | +0.384 |
Interstitial | +0.377 |
tein | +0.377 |
Neg logit contributions | |
resa | -0.358 |
Scotland | -0.302 |
Ireland | -0.264 |
Mitt | -0.256 |
Vice | -0.252 |
Token | leadership |
Token ID | 5531 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
resa | +0.097 |
Scotland | +0.077 |
Ireland | +0.065 |
Mitt | +0.065 |
Vice | +0.062 |
Neg logit contributions | |
Defender | -0.148 |
ilan | -0.144 |
shade | -0.144 |
Interstitial | -0.143 |
tein | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
resa | +0.523 |
Scotland | +0.439 |
Mitt | +0.387 |
Ireland | +0.387 |
Vice | +0.373 |
Neg logit contributions | |
Defender | -0.535 |
ilan | -0.519 |
shade | -0.515 |
tein | -0.514 |
Interstitial | -0.514 |
Token | That |
Token ID | 1320 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Defender | +0.212 |
ilan | +0.203 |
shade | +0.203 |
Interstitial | +0.201 |
tein | +0.200 |
Neg logit contributions | |
resa | -0.223 |
Scotland | -0.188 |
Ireland | -0.167 |
Mitt | -0.165 |
Vice | -0.161 |
Token | 's |
Token ID | 338 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Defender | +0.309 |
shade | +0.297 |
ilan | +0.296 |
Interstitial | +0.291 |
tein | +0.290 |
Neg logit contributions | |
resa | -0.395 |
Scotland | -0.340 |
Ireland | -0.306 |
Mitt | -0.301 |
Vice | -0.295 |
Token | who |
Token ID | 508 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
Defender | +0.744 |
shade | +0.718 |
ilan | +0.713 |
Interstitial | +0.703 |
tein | +0.694 |
Neg logit contributions | |
resa | -0.764 |
Scotland | -0.644 |
Ireland | -0.571 |
Mitt | -0.556 |
Vice | -0.549 |
Token | we |
Token ID | 356 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
Defender | +0.003 |
ilan | +0.003 |
shade | +0.003 |
Interstitial | +0.003 |
tein | +0.003 |
Neg logit contributions | |
resa | -0.003 |
Scotland | -0.002 |
Ireland | -0.002 |
Mitt | -0.002 |
Vice | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
resa | +0.063 |
Scotland | +0.052 |
Mitt | +0.045 |
Ireland | +0.045 |
Vice | +0.043 |
Neg logit contributions | |
Defender | -0.073 |
ilan | -0.070 |
Interstitial | -0.070 |
shade | -0.070 |
tein | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Defender | +0.076 |
ilan | +0.073 |
shade | +0.073 |
Interstitial | +0.072 |
tein | +0.072 |
Neg logit contributions | |
resa | -0.078 |
Scotland | -0.066 |
Ireland | -0.058 |
Mitt | -0.058 |
Vice | -0.056 |
Token | � |
Token ID | 447 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Defender | +0.186 |
ilan | +0.178 |
shade | +0.178 |
Interstitial | +0.176 |
tein | +0.175 |
Neg logit contributions | |
resa | -0.207 |
Scotland | -0.176 |
Ireland | -0.157 |
Mitt | -0.155 |
Vice | -0.151 |
Token | – |
Token ID | 1906 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Defender | +0.324 |
ilan | +0.313 |
shade | +0.312 |
Interstitial | +0.309 |
tein | +0.308 |
Neg logit contributions | |
resa | -0.327 |
Scotland | -0.276 |
Ireland | -0.244 |
Mitt | -0.243 |
Vice | -0.236 |
Token | Aff |
Token ID | 35191 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
resa | +1.251 |
Scotland | +1.074 |
Ireland | +0.960 |
Mitt | +0.959 |
Vice | +0.931 |
Neg logit contributions | |
Defender | -1.056 |
ilan | -1.016 |
shade | -1.014 |
Interstitial | -1.009 |
tein | -1.009 |
Token | leck |
Token ID | 40667 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
resa | +0.529 |
Scotland | +0.426 |
Ireland | +0.362 |
Mitt | +0.361 |
Vice | +0.345 |
Neg logit contributions | |
Defender | -0.774 |
shade | -0.752 |
ilan | -0.750 |
Interstitial | -0.747 |
tein | -0.742 |
Token | . |
Token ID | 13 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
resa | +0.968 |
Scotland | +0.816 |
Mitt | +0.728 |
Ireland | +0.718 |
Vice | +0.698 |
Neg logit contributions | |
Defender | -0.953 |
ilan | -0.923 |
shade | -0.920 |
tein | -0.915 |
Interstitial | -0.914 |
Token | Damon |
Token ID | 33572 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
resa | +0.544 |
Scotland | +0.468 |
Ireland | +0.419 |
Mitt | +0.419 |
Vice | +0.407 |
Neg logit contributions | |
Defender | -0.440 |
ilan | -0.426 |
shade | -0.424 |
Interstitial | -0.419 |
tein | -0.418 |
Token | said |
Token ID | 531 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Defender | +0.318 |
ilan | +0.306 |
shade | +0.305 |
Interstitial | +0.302 |
tein | +0.301 |
Neg logit contributions | |
resa | -0.384 |
Scotland | -0.329 |
Ireland | -0.294 |
Mitt | -0.293 |
Vice | -0.285 |
Token | he |
Token ID | 339 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
resa | +0.109 |
Scotland | +0.092 |
Mitt | +0.081 |
Ireland | +0.081 |
Vice | +0.078 |
Neg logit contributions | |
Defender | -0.112 |
ilan | -0.108 |
shade | -0.108 |
Interstitial | -0.107 |
tein | -0.107 |
Token | cried |
Token ID | 16896 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
resa | +0.387 |
Scotland | +0.332 |
Ireland | +0.298 |
Mitt | +0.297 |
Vice | +0.289 |
Neg logit contributions | |
Defender | -0.303 |
ilan | -0.291 |
shade | -0.290 |
Interstitial | -0.288 |
tein | -0.286 |
Token | every |
Token ID | 790 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Defender | +0.342 |
shade | +0.329 |
ilan | +0.329 |
Interstitial | +0.324 |
tein | +0.322 |
Neg logit contributions | |
resa | -0.404 |
Scotland | -0.345 |
Ireland | -0.309 |
Mitt | -0.305 |
Vice | -0.298 |
Token | time |
Token ID | 640 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Defender | +1.010 |
shade | +0.976 |
ilan | +0.962 |
Interstitial | +0.952 |
tein | +0.947 |
Neg logit contributions | |
resa | -1.042 |
Scotland | -0.880 |
Ireland | -0.783 |
Mitt | -0.771 |
Vice | -0.755 |
Token | he |
Token ID | 339 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
resa | +1.114 |
Scotland | +0.930 |
Mitt | +0.820 |
Ireland | +0.811 |
Vice | +0.782 |
Neg logit contributions | |
Defender | -1.212 |
ilan | -1.187 |
shade | -1.174 |
tein | -1.170 |
Interstitial | -1.168 |
Token | thunder |
Token ID | 18355 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Defender | +0.584 |
shade | +0.565 |
ilan | +0.557 |
Interstitial | +0.553 |
tein | +0.549 |
Neg logit contributions | |
resa | -0.592 |
Scotland | -0.499 |
Ireland | -0.443 |
Mitt | -0.433 |
Vice | -0.427 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Defender | +0.799 |
ilan | +0.770 |
shade | +0.770 |
Interstitial | +0.760 |
tein | +0.756 |
Neg logit contributions | |
resa | -0.865 |
Scotland | -0.735 |
Ireland | -0.653 |
Mitt | -0.648 |
Vice | -0.631 |
Token | Yet |
Token ID | 6430 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
resa | +0.239 |
Scotland | +0.206 |
Mitt | +0.186 |
Ireland | +0.185 |
Vice | +0.179 |
Neg logit contributions | |
Defender | -0.192 |
ilan | -0.187 |
shade | -0.186 |
tein | -0.183 |
Interstitial | -0.183 |
Token | barely |
Token ID | 8523 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
resa | +1.178 |
Scotland | +1.004 |
Mitt | +0.908 |
Ireland | +0.898 |
Task | +0.866 |
Neg logit contributions | |
Defender | -1.026 |
ilan | -1.000 |
tein | -0.983 |
Interstitial | -0.981 |
shade | -0.979 |
Token | had |
Token ID | 550 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
resa | +0.555 |
Scotland | +0.466 |
Ireland | +0.411 |
Mitt | +0.409 |
Vice | +0.396 |
Neg logit contributions | |
Defender | -0.568 |
ilan | -0.550 |
shade | -0.548 |
Interstitial | -0.543 |
tein | -0.541 |
Token | Brook |
Token ID | 7590 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Defender | +0.064 |
ilan | +0.062 |
shade | +0.062 |
Interstitial | +0.061 |
tein | +0.061 |
Neg logit contributions | |
resa | -0.073 |
Scotland | -0.062 |
Ireland | -0.055 |
Mitt | -0.055 |
Vice | -0.053 |
Token | left |
Token ID | 1364 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
Defender | +1.959 |
shade | +1.894 |
ilan | +1.870 |
Interstitial | +1.852 |
tein | +1.846 |
Neg logit contributions | |
resa | -1.770 |
Scotland | -1.479 |
Ireland | -1.295 |
Mitt | -1.270 |
Vice | -1.255 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Defender | +0.022 |
ilan | +0.021 |
shade | +0.021 |
Interstitial | +0.021 |
tein | +0.021 |
Neg logit contributions | |
resa | -0.022 |
Scotland | -0.018 |
Ireland | -0.016 |
Mitt | -0.016 |
Vice | -0.015 |
Token | ring |
Token ID | 5858 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
resa | +0.089 |
Scotland | +0.076 |
Ireland | +0.068 |
Mitt | +0.068 |
Vice | +0.066 |
Neg logit contributions | |
Defender | -0.076 |
ilan | -0.073 |
Interstitial | -0.072 |
shade | -0.072 |
tein | -0.072 |
Token | having |
Token ID | 1719 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
resa | +1.654 |
Scotland | +1.411 |
Mitt | +1.264 |
Ireland | +1.259 |
Vice | +1.219 |
Neg logit contributions | |
Defender | -1.417 |
ilan | -1.370 |
Interstitial | -1.357 |
tein | -1.354 |
shade | -1.354 |
Token | relinqu |
Token ID | 36610 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
Defender | +0.947 |
shade | +0.911 |
ilan | +0.901 |
Interstitial | +0.891 |
tein | +0.889 |
Neg logit contributions | |
resa | -1.130 |
Scotland | -0.969 |
Ireland | -0.870 |
Mitt | -0.853 |
Vice | -0.841 |
Token | p |
Token ID | 279 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
resa | +0.007 |
Scotland | +0.006 |
Mitt | +0.005 |
Ireland | +0.005 |
Vice | +0.005 |
Neg logit contributions | |
Defender | -0.006 |
shade | -0.006 |
ilan | -0.006 |
Interstitial | -0.006 |
tein | -0.006 |
Token | ē |
Token ID | 27092 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Defender | +0.122 |
shade | +0.117 |
ilan | +0.117 |
Interstitial | +0.116 |
tein | +0.115 |
Neg logit contributions | |
resa | -0.120 |
Scotland | -0.100 |
Ireland | -0.089 |
Mitt | -0.088 |
Vice | -0.085 |
Token | l |
Token ID | 75 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Defender | +1.466 |
ilan | +1.418 |
shade | +1.414 |
tein | +1.398 |
Interstitial | +1.391 |
Neg logit contributions | |
resa | -1.617 |
Scotland | -1.385 |
Ireland | -1.231 |
Mitt | -1.216 |
Vice | -1.187 |
Token | ā |
Token ID | 10235 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
resa | +0.856 |
Scotland | +0.720 |
Mitt | +0.650 |
Ireland | +0.644 |
Vice | +0.627 |
Neg logit contributions | |
Defender | -0.742 |
Interstitial | -0.709 |
ilan | -0.709 |
shade | -0.708 |
tein | -0.695 |
Token | p |
Token ID | 279 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
Defender | +0.948 |
ilan | +0.914 |
shade | +0.912 |
tein | +0.899 |
Interstitial | +0.898 |
Neg logit contributions | |
resa | -1.105 |
Scotland | -0.947 |
Ireland | -0.845 |
Mitt | -0.837 |
Vice | -0.817 |
Token | ū |
Token ID | 20317 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
resa | +0.054 |
Scotland | +0.046 |
Ireland | +0.041 |
Mitt | +0.041 |
Vice | +0.040 |
Neg logit contributions | |
Defender | -0.047 |
shade | -0.045 |
ilan | -0.045 |
Interstitial | -0.045 |
tein | -0.044 |
Token | ke |
Token ID | 885 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
Defender | +1.912 |
ilan | +1.860 |
shade | +1.856 |
tein | +1.838 |
Interstitial | +1.816 |
Neg logit contributions | |
resa | -1.976 |
Scotland | -1.692 |
Ireland | -1.493 |
Mitt | -1.459 |
Vice | -1.438 |
Token | ko |
Token ID | 41727 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
resa | +0.035 |
Scotland | +0.029 |
Ireland | +0.026 |
Mitt | +0.026 |
Vice | +0.025 |
Neg logit contributions | |
Defender | -0.039 |
shade | -0.037 |
ilan | -0.037 |
Interstitial | -0.037 |
tein | -0.037 |
Token | � |
Token ID | 134 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
resa | +1.285 |
Scotland | +1.065 |
Mitt | +0.953 |
Ireland | +0.947 |
Vice | +0.914 |
Neg logit contributions | |
Defender | -1.280 |
Interstitial | -1.230 |
shade | -1.223 |
ilan | -1.221 |
tein | -1.209 |
Token | � |
Token ID | 119 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Defender | +0.684 |
shade | +0.653 |
ilan | +0.653 |
Interstitial | +0.642 |
tein | +0.641 |
Neg logit contributions | |
resa | -1.012 |
Scotland | -0.877 |
Ireland | -0.795 |
Mitt | -0.792 |
Vice | -0.772 |
Token | iko |
Token ID | 12125 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Defender | +0.758 |
ilan | +0.731 |
shade | +0.729 |
Interstitial | +0.719 |
tein | +0.718 |
Neg logit contributions | |
resa | -0.874 |
Scotland | -0.746 |
Ireland | -0.666 |
Mitt | -0.662 |
Vice | -0.644 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Defender | +0.519 |
ilan | +0.500 |
shade | +0.499 |
Interstitial | +0.493 |
tein | +0.492 |
Neg logit contributions | |
resa | -0.566 |
Scotland | -0.480 |
Ireland | -0.427 |
Mitt | -0.425 |
Vice | -0.413 |
Token | If |
Token ID | 1002 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Defender | +0.092 |
ilan | +0.089 |
shade | +0.088 |
Interstitial | +0.087 |
tein | +0.087 |
Neg logit contributions | |
resa | -0.112 |
Scotland | -0.097 |
Ireland | -0.087 |
Mitt | -0.086 |
Vice | -0.084 |
Token | she |
Token ID | 673 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
resa | +0.366 |
Scotland | +0.310 |
Ireland | +0.275 |
Mitt | +0.274 |
Vice | +0.266 |
Neg logit contributions | |
Defender | -0.343 |
ilan | -0.331 |
shade | -0.330 |
Interstitial | -0.327 |
tein | -0.326 |
Token | recovers |
Token ID | 46773 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Defender | +0.014 |
ilan | +0.013 |
shade | +0.013 |
Interstitial | +0.013 |
tein | +0.013 |
Neg logit contributions | |
resa | -0.017 |
Scotland | -0.015 |
Ireland | -0.013 |
Mitt | -0.013 |
Vice | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
resa | +0.530 |
Scotland | +0.458 |
Ireland | +0.409 |
Mitt | +0.408 |
Task | +0.394 |
Neg logit contributions | |
Defender | -0.440 |
ilan | -0.428 |
tein | -0.424 |
Interstitial | -0.423 |
shade | -0.418 |
Token | homeless |
Token ID | 10463 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
resa | +0.389 |
Scotland | +0.330 |
Ireland | +0.294 |
Mitt | +0.292 |
Vice | +0.284 |
Neg logit contributions | |
Defender | -0.356 |
ilan | -0.344 |
shade | -0.343 |
Interstitial | -0.339 |
tein | -0.338 |
Token | advocates |
Token ID | 11009 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Defender | +1.772 |
shade | +1.700 |
ilan | +1.695 |
Interstitial | +1.642 |
tein | +1.640 |
Neg logit contributions | |
resa | -1.997 |
Scotland | -1.704 |
Ireland | -1.519 |
Mitt | -1.501 |
Vice | -1.476 |
Token | say |
Token ID | 910 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Defender | +0.074 |
ilan | +0.071 |
shade | +0.071 |
Interstitial | +0.070 |
tein | +0.070 |
Neg logit contributions | |
resa | -0.080 |
Scotland | -0.068 |
Ireland | -0.060 |
Mitt | -0.060 |
Vice | -0.058 |
Token | they |
Token ID | 484 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
Defender | +0.273 |
ilan | +0.263 |
shade | +0.262 |
Interstitial | +0.260 |
tein | +0.259 |
Neg logit contributions | |
resa | -0.313 |
Scotland | -0.267 |
Ireland | -0.238 |
Mitt | -0.237 |
Vice | -0.230 |
Token | will |
Token ID | 481 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
resa | +0.017 |
Scotland | +0.015 |
Ireland | +0.013 |
Mitt | +0.013 |
Vice | +0.013 |
Neg logit contributions | |
Defender | -0.016 |
ilan | -0.015 |
shade | -0.015 |
Interstitial | -0.015 |
tein | -0.015 |
Token | take |
Token ID | 1011 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
resa | +0.393 |
Scotland | +0.332 |
Mitt | +0.293 |
Ireland | +0.293 |
Task | +0.283 |
Neg logit contributions | |
Defender | -0.372 |
ilan | -0.362 |
Interstitial | -0.360 |
shade | -0.356 |
tein | -0.354 |
Token |
|
Token ID | 198 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Defender | +0.249 |
shade | +0.238 |
ilan | +0.238 |
Interstitial | +0.233 |
tein | +0.233 |
Neg logit contributions | |
resa | -0.363 |
Scotland | -0.313 |
Ireland | -0.284 |
Mitt | -0.282 |
Vice | -0.275 |
Token | � |
Token ID | 447 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
Defender | +0.456 |
shade | +0.439 |
ilan | +0.439 |
tein | +0.433 |
Interstitial | +0.432 |
Neg logit contributions | |
resa | -0.507 |
Scotland | -0.433 |
Ireland | -0.386 |
Mitt | -0.382 |
Vice | -0.373 |
Token | � |
Token ID | 250 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Defender | +0.494 |
ilan | +0.478 |
shade | +0.475 |
tein | +0.471 |
Interstitial | +0.469 |
Neg logit contributions | |
resa | -0.491 |
Scotland | -0.414 |
Ireland | -0.366 |
Mitt | -0.364 |
Vice | -0.353 |
Token | Both |
Token ID | 10265 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
resa | +0.294 |
Scotland | +0.251 |
Ireland | +0.222 |
Mitt | +0.221 |
Vice | +0.215 |
Neg logit contributions | |
Defender | -0.281 |
shade | -0.273 |
ilan | -0.272 |
tein | -0.270 |
Interstitial | -0.268 |
Token | the |
Token ID | 262 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Defender | +1.214 |
ilan | +1.168 |
shade | +1.167 |
Interstitial | +1.150 |
tein | +1.147 |
Neg logit contributions | |
resa | -1.358 |
Scotland | -1.156 |
Ireland | -1.030 |
Mitt | -1.021 |
Vice | -0.996 |
Token | ACLU |
Token ID | 24381 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Defender | +0.194 |
ilan | +0.188 |
shade | +0.187 |
Interstitial | +0.185 |
tein | +0.185 |
Neg logit contributions | |
resa | -0.238 |
Scotland | -0.203 |
Ireland | -0.182 |
Mitt | -0.182 |
Vice | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Defender | +2.220 |
shade | +2.129 |
ilan | +2.128 |
Interstitial | +2.092 |
tein | +2.091 |
Neg logit contributions | |
resa | -2.350 |
Scotland | -1.988 |
Ireland | -1.767 |
Mitt | -1.754 |
Vice | -1.703 |
Token | I |
Token ID | 314 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Defender | +0.147 |
ilan | +0.144 |
shade | +0.143 |
Interstitial | +0.142 |
tein | +0.142 |
Neg logit contributions | |
resa | -0.137 |
Scotland | -0.115 |
Mitt | -0.102 |
Ireland | -0.100 |
Vice | -0.097 |
Token | believe |
Token ID | 1975 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
Defender | +0.340 |
ilan | +0.327 |
shade | +0.326 |
Interstitial | +0.325 |
tein | +0.322 |
Neg logit contributions | |
resa | -0.406 |
Scotland | -0.348 |
Ireland | -0.310 |
Mitt | -0.309 |
Vice | -0.300 |
Token | , |
Token ID | 11 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
resa | +0.017 |
Scotland | +0.015 |
Mitt | +0.013 |
Ireland | +0.013 |
Vice | +0.012 |
Neg logit contributions | |
Defender | -0.017 |
ilan | -0.017 |
Interstitial | -0.017 |
shade | -0.017 |
tein | -0.017 |
Token | as |
Token ID | 355 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
resa | +0.257 |
Scotland | +0.219 |
Mitt | +0.195 |
Ireland | +0.194 |
Vice | +0.188 |
Neg logit contributions | |
Defender | -0.233 |
ilan | -0.225 |
shade | -0.224 |
Interstitial | -0.223 |
tein | -0.223 |
Token | � |
Token ID | 447 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
Defender | +0.185 |
ilan | +0.176 |
shade | +0.175 |
Interstitial | +0.173 |
tein | +0.172 |
Neg logit contributions | |
resa | -0.334 |
Scotland | -0.292 |
Ireland | -0.267 |
Mitt | -0.266 |
Vice | -0.260 |
Token | � |
Token ID | 247 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
resa | +0.056 |
Scotland | +0.045 |
Ireland | +0.039 |
Mitt | +0.039 |
Vice | +0.037 |
Neg logit contributions | |
Defender | -0.073 |
ilan | -0.071 |
shade | -0.071 |
Interstitial | -0.070 |
tein | -0.070 |
Token | t |
Token ID | 83 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Defender | +0.063 |
ilan | +0.060 |
shade | +0.060 |
Interstitial | +0.059 |
tein | +0.059 |
Neg logit contributions | |
resa | -0.107 |
Scotland | -0.093 |
Ireland | -0.085 |
Mitt | -0.084 |
Vice | -0.083 |
Token | as |
Token ID | 355 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
resa | +0.207 |
Scotland | +0.176 |
Ireland | +0.156 |
Mitt | +0.155 |
Vice | +0.151 |
Neg logit contributions | |
Defender | -0.193 |
ilan | -0.186 |
shade | -0.186 |
Interstitial | -0.184 |
tein | -0.183 |
Token | market |
Token ID | 1910 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
resa | +0.522 |
Scotland | +0.441 |
Ireland | +0.391 |
Mitt | +0.390 |
Vice | +0.377 |
Neg logit contributions | |
Defender | -0.503 |
ilan | -0.485 |
shade | -0.483 |
Interstitial | -0.479 |
tein | -0.477 |
Token | able |
Token ID | 540 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Defender | +0.209 |
shade | +0.200 |
ilan | +0.199 |
Interstitial | +0.197 |
tein | +0.195 |
Neg logit contributions | |
resa | -0.276 |
Scotland | -0.238 |
Ireland | -0.215 |
Mitt | -0.212 |
Vice | -0.208 |
Token | as |
Token ID | 355 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Defender | +2.106 |
shade | +2.034 |
ilan | +2.006 |
Interstitial | +1.971 |
tein | +1.969 |
Neg logit contributions | |
resa | -2.597 |
Scotland | -2.226 |
Ireland | -2.002 |
Mitt | -1.951 |
Vice | -1.941 |
Token | TJ |
Token ID | 41852 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Defender | +0.165 |
shade | +0.159 |
ilan | +0.158 |
Interstitial | +0.156 |
tein | +0.156 |
Neg logit contributions | |
resa | -0.172 |
Scotland | -0.146 |
Ireland | -0.129 |
Mitt | -0.127 |
Vice | -0.125 |
Token | Osh |
Token ID | 46614 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Defender | +1.752 |
ilan | +1.699 |
shade | +1.688 |
tein | +1.671 |
Interstitial | +1.652 |
Neg logit contributions | |
resa | -1.209 |
Scotland | -0.992 |
Ireland | -0.851 |
Mitt | -0.813 |
Vice | -0.804 |
Token | ie |
Token ID | 494 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Defender | +0.183 |
shade | +0.181 |
ilan | +0.181 |
tein | +0.177 |
Interstitial | +0.174 |
Neg logit contributions | |
resa | -0.179 |
Scotland | -0.155 |
Ireland | -0.135 |
Vice | -0.132 |
Mitt | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Defender | +1.501 |
ilan | +1.442 |
shade | +1.441 |
Interstitial | +1.422 |
tein | +1.416 |
Neg logit contributions | |
resa | -1.642 |
Scotland | -1.396 |
Ireland | -1.244 |
Mitt | -1.225 |
Vice | -1.200 |