Token | necessary |
Token ID | 3306 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Kubrick | +0.164 |
tires | +0.145 |
chess | +0.144 |
Redd | +0.141 |
� | +0.135 |
Neg logit contributions | |
Appearance | -0.231 |
��極 | -0.218 |
heit | -0.197 |
aneers | -0.194 |
adan | -0.190 |
Token | packages |
Token ID | 10392 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Appearance | +1.746 |
��極 | +1.631 |
heit | +1.525 |
aneers | +1.506 |
adan | +1.476 |
Neg logit contributions | |
Kubrick | -0.758 |
tires | -0.632 |
chess | -0.631 |
Redd | -0.626 |
� | -0.590 |
Token | from |
Token ID | 422 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Appearance | +1.462 |
��極 | +1.335 |
heit | +1.258 |
aneers | +1.223 |
adan | +1.212 |
Neg logit contributions | |
Kubrick | -0.880 |
tires | -0.761 |
Redd | -0.760 |
chess | -0.758 |
� | -0.725 |
Token | im |
Token ID | 545 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Appearance | +0.458 |
��極 | +0.429 |
heit | +0.388 |
aneers | +0.380 |
adan | +0.373 |
Neg logit contributions | |
Kubrick | -0.351 |
tires | -0.313 |
chess | -0.311 |
Redd | -0.307 |
� | -0.294 |
Token | utils |
Token ID | 26791 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Appearance | +0.587 |
��極 | +0.546 |
heit | +0.499 |
aneers | +0.488 |
adan | +0.482 |
Neg logit contributions | |
Kubrick | -0.456 |
tires | -0.406 |
chess | -0.404 |
Redd | -0.397 |
� | -0.382 |
Token | import |
Token ID | 1330 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
Kubrick | +0.699 |
chess | +0.614 |
tires | +0.613 |
Redd | +0.586 |
Pens | +0.565 |
Neg logit contributions | |
Appearance | -1.168 |
��極 | -1.122 |
heit | -1.012 |
aneers | -0.999 |
adan | -0.981 |
Token | paths |
Token ID | 13532 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Appearance | +3.349 |
��極 | +2.921 |
heit | +2.540 |
aneers | +2.415 |
ighthouse | +2.297 |
Neg logit contributions | |
Kubrick | -5.738 |
Redd | -5.304 |
tires | -5.268 |
chess | -5.204 |
� | -5.144 |
Token | import |
Token ID | 1330 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
Kubrick | +0.610 |
chess | +0.536 |
tires | +0.535 |
Redd | +0.510 |
Pens | +0.493 |
Neg logit contributions | |
Appearance | -1.023 |
��極 | -0.989 |
heit | -0.889 |
aneers | -0.880 |
adan | -0.864 |
Token | n |
Token ID | 299 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Appearance | +4.291 |
��極 | +3.832 |
heit | +3.523 |
aneers | +3.408 |
adan | +3.367 |
Neg logit contributions | |
Kubrick | -3.710 |
Redd | -3.403 |
tires | -3.297 |
� | -3.244 |
chess | -3.236 |
Token | umpy |
Token ID | 32152 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Appearance | +0.709 |
��極 | +0.664 |
heit | +0.623 |
aneers | +0.611 |
adan | +0.604 |
Neg logit contributions | |
Kubrick | -0.352 |
tires | -0.302 |
chess | -0.299 |
Redd | -0.293 |
� | -0.278 |
Token | as |
Token ID | 355 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
Appearance | +1.304 |
��極 | +1.226 |
heit | +1.117 |
aneers | +1.097 |
adan | +1.080 |
Neg logit contributions | |
Kubrick | -0.859 |
tires | -0.756 |
chess | -0.753 |
Redd | -0.739 |
� | -0.706 |
Token | necessary |
Token ID | 3306 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Kubrick | +0.175 |
tires | +0.155 |
chess | +0.154 |
Redd | +0.150 |
Pens | +0.144 |
Neg logit contributions | |
Appearance | -0.258 |
��極 | -0.244 |
heit | -0.221 |
aneers | -0.218 |
adan | -0.214 |
Token | packages |
Token ID | 10392 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Appearance | +1.868 |
��極 | +1.741 |
heit | +1.607 |
aneers | +1.570 |
adan | +1.552 |
Neg logit contributions | |
Kubrick | -1.033 |
tires | -0.893 |
chess | -0.884 |
Redd | -0.883 |
� | -0.846 |
Token | from |
Token ID | 422 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Appearance | +1.474 |
��極 | +1.375 |
heit | +1.255 |
aneers | +1.231 |
adan | +1.212 |
Neg logit contributions | |
Kubrick | -0.980 |
tires | -0.863 |
chess | -0.858 |
Redd | -0.854 |
� | -0.814 |
Token | im |
Token ID | 545 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Appearance | +0.452 |
��極 | +0.426 |
heit | +0.386 |
aneers | +0.379 |
adan | +0.373 |
Neg logit contributions | |
Kubrick | -0.316 |
tires | -0.280 |
chess | -0.279 |
Redd | -0.273 |
� | -0.261 |
Token | utils |
Token ID | 26791 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Appearance | +1.030 |
��極 | +0.967 |
heit | +0.869 |
aneers | +0.854 |
adan | +0.836 |
Neg logit contributions | |
Kubrick | -0.828 |
tires | -0.740 |
chess | -0.739 |
Redd | -0.723 |
� | -0.696 |
Token | import |
Token ID | 1330 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
Kubrick | +0.399 |
chess | +0.352 |
tires | +0.351 |
Redd | +0.338 |
Pens | +0.326 |
Neg logit contributions | |
Appearance | -0.628 |
��極 | -0.597 |
heit | -0.542 |
aneers | -0.533 |
adan | -0.524 |
Token | paths |
Token ID | 13532 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Appearance | +5.011 |
��極 | +4.559 |
heit | +4.187 |
aneers | +4.061 |
adan | +4.003 |
Neg logit contributions | |
Kubrick | -3.493 |
Redd | -3.179 |
tires | -3.097 |
chess | -3.040 |
� | -3.027 |
Token | import |
Token ID | 1330 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Kubrick | +0.485 |
tires | +0.429 |
chess | +0.428 |
Redd | +0.414 |
Pens | +0.399 |
Neg logit contributions | |
Appearance | -0.735 |
��極 | -0.699 |
heit | -0.632 |
aneers | -0.622 |
adan | -0.611 |
Token | n |
Token ID | 299 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
Appearance | +4.273 |
��極 | +3.901 |
heit | +3.577 |
aneers | +3.479 |
adan | +3.422 |
Neg logit contributions | |
Kubrick | -3.018 |
Redd | -2.733 |
tires | -2.674 |
chess | -2.626 |
� | -2.603 |
Token | umpy |
Token ID | 32152 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Appearance | +0.716 |
��極 | +0.676 |
heit | +0.620 |
aneers | +0.610 |
adan | +0.601 |
Neg logit contributions | |
Kubrick | -0.389 |
tires | -0.337 |
chess | -0.335 |
Redd | -0.327 |
� | -0.311 |
Token | as |
Token ID | 355 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Appearance | +1.531 |
��極 | +1.434 |
heit | +1.310 |
aneers | +1.284 |
adan | +1.265 |
Neg logit contributions | |
Kubrick | -1.022 |
tires | -0.895 |
chess | -0.891 |
Redd | -0.884 |
� | -0.841 |
Token | fat |
Token ID | 3735 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Appearance | +0.777 |
��極 | +0.735 |
heit | +0.666 |
aneers | +0.655 |
adan | +0.643 |
Neg logit contributions | |
Kubrick | -0.516 |
tires | -0.456 |
chess | -0.455 |
Redd | -0.443 |
� | -0.424 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Appearance | +2.063 |
��極 | +1.940 |
heit | +1.774 |
aneers | +1.742 |
adan | +1.718 |
Neg logit contributions | |
Kubrick | -1.302 |
tires | -1.134 |
chess | -1.134 |
Redd | -1.115 |
Pens | -1.058 |
Token | not |
Token ID | 407 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
Appearance | +0.236 |
��極 | +0.222 |
heit | +0.201 |
aneers | +0.197 |
adan | +0.193 |
Neg logit contributions | |
Kubrick | -0.176 |
tires | -0.156 |
chess | -0.156 |
Redd | -0.153 |
� | -0.146 |
Token | all |
Token ID | 477 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Appearance | +0.896 |
��極 | +0.837 |
heit | +0.759 |
aneers | +0.746 |
adan | +0.733 |
Neg logit contributions | |
Kubrick | -0.649 |
tires | -0.574 |
chess | -0.573 |
Redd | -0.564 |
� | -0.541 |
Token | 53 |
Token ID | 7192 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Appearance | +1.211 |
��極 | +1.137 |
heit | +1.032 |
aneers | +1.014 |
adan | +0.996 |
Neg logit contributions | |
Kubrick | -0.853 |
tires | -0.755 |
chess | -0.752 |
Redd | -0.738 |
� | -0.706 |
Token | Euro |
Token ID | 1898 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
Appearance | +0.977 |
��極 | +0.919 |
heit | +0.831 |
aneers | +0.816 |
adan | +0.801 |
Neg logit contributions | |
Kubrick | -0.714 |
tires | -0.635 |
chess | -0.633 |
Redd | -0.620 |
� | -0.594 |
Token | - |
Token ID | 12 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Appearance | +5.118 |
��極 | +4.809 |
heit | +4.433 |
aneers | +4.354 |
adan | +4.289 |
Neg logit contributions | |
Kubrick | -3.256 |
chess | -2.806 |
tires | -2.798 |
Redd | -2.734 |
� | -2.625 |
Token | region |
Token ID | 36996 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Kubrick | +0.832 |
tires | +0.757 |
Redd | +0.752 |
chess | +0.750 |
� | +0.712 |
Neg logit contributions | |
Appearance | -0.954 |
��極 | -0.898 |
heit | -0.798 |
aneers | -0.771 |
�� | -0.764 |
Token | countries |
Token ID | 2678 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Appearance | +0.472 |
��極 | +0.447 |
heit | +0.404 |
aneers | +0.395 |
adan | +0.388 |
Neg logit contributions | |
Kubrick | -0.334 |
chess | -0.298 |
tires | -0.297 |
Redd | -0.289 |
Pens | -0.277 |
Token | are |
Token ID | 389 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
Appearance | +1.841 |
��極 | +1.719 |
heit | +1.568 |
aneers | +1.537 |
adan | +1.514 |
Neg logit contributions | |
Kubrick | -1.322 |
tires | -1.166 |
chess | -1.165 |
Redd | -1.152 |
� | -1.101 |
Token | equal |
Token ID | 4961 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Appearance | +0.893 |
��極 | +0.838 |
heit | +0.758 |
aneers | +0.744 |
adan | +0.731 |
Neg logit contributions | |
Kubrick | -0.663 |
tires | -0.589 |
chess | -0.587 |
Redd | -0.576 |
� | -0.552 |
Token | 283 |
Token ID | 30290 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Kubrick | +0.056 |
tires | +0.051 |
chess | +0.051 |
Redd | +0.050 |
� | +0.048 |
Neg logit contributions | |
Appearance | -0.053 |
��極 | -0.050 |
heit | -0.044 |
aneers | -0.043 |
adan | -0.042 |
Token | 185 |
Token ID | 21652 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Appearance | +0.335 |
��極 | +0.318 |
heit | +0.290 |
aneers | +0.286 |
adan | +0.280 |
Neg logit contributions | |
Kubrick | -0.198 |
tires | -0.175 |
chess | -0.173 |
Redd | -0.168 |
� | -0.161 |
Token | 307 |
Token ID | 22996 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Appearance | +0.589 |
��極 | +0.557 |
heit | +0.500 |
aneers | +0.494 |
adan | +0.484 |
Neg logit contributions | |
Kubrick | -0.441 |
tires | -0.396 |
chess | -0.394 |
Redd | -0.384 |
� | -0.371 |
Token | 18 |
Token ID | 1507 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Appearance | +0.736 |
��極 | +0.693 |
heit | +0.613 |
aneers | +0.605 |
adan | +0.590 |
Neg logit contributions | |
Kubrick | -0.698 |
tires | -0.636 |
chess | -0.633 |
Redd | -0.617 |
� | -0.600 |
Token | ; |
Token ID | 26 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Appearance | +0.088 |
��極 | +0.083 |
heit | +0.073 |
aneers | +0.072 |
adan | +0.071 |
Neg logit contributions | |
Kubrick | -0.083 |
tires | -0.076 |
chess | -0.075 |
Redd | -0.074 |
� | -0.071 |
Token | float |
Token ID | 12178 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Appearance | +1.160 |
��極 | +1.094 |
heit | +0.993 |
aneers | +0.975 |
adan | +0.958 |
Neg logit contributions | |
Kubrick | -0.795 |
tires | -0.704 |
chess | -0.701 |
Redd | -0.685 |
� | -0.656 |
Token | time |
Token ID | 640 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
Appearance | +4.638 |
��極 | +4.285 |
heit | +3.903 |
aneers | +3.806 |
adan | +3.734 |
Neg logit contributions | |
Kubrick | -3.460 |
Redd | -3.073 |
chess | -3.052 |
tires | -3.018 |
� | -2.916 |
Token | = |
Token ID | 796 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Kubrick | +0.041 |
tires | +0.036 |
chess | +0.036 |
Redd | +0.036 |
� | +0.034 |
Neg logit contributions | |
Appearance | -0.060 |
��極 | -0.057 |
heit | -0.051 |
aneers | -0.051 |
adan | -0.050 |
Token | ( |
Token ID | 357 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Appearance | +1.123 |
��極 | +1.058 |
heit | +0.957 |
aneers | +0.941 |
adan | +0.924 |
Neg logit contributions | |
Kubrick | -0.808 |
tires | -0.717 |
chess | -0.715 |
Redd | -0.699 |
� | -0.670 |
Token | sin |
Token ID | 31369 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
Kubrick | +0.123 |
tires | +0.111 |
chess | +0.110 |
Redd | +0.108 |
� | +0.105 |
Neg logit contributions | |
Appearance | -0.142 |
��極 | -0.133 |
heit | -0.119 |
aneers | -0.117 |
adan | -0.114 |
Token | (_ |
Token ID | 44104 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Appearance | +3.500 |
��極 | +3.282 |
heit | +2.988 |
aneers | +2.906 |
adan | +2.878 |
Neg logit contributions | |
Kubrick | -2.544 |
chess | -2.248 |
tires | -2.238 |
Redd | -2.201 |
� | -2.123 |
Token | from |
Token ID | 422 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Appearance | +1.462 |
��極 | +1.335 |
heit | +1.258 |
aneers | +1.223 |
adan | +1.212 |
Neg logit contributions | |
Kubrick | -0.880 |
tires | -0.761 |
Redd | -0.760 |
chess | -0.758 |
� | -0.725 |
Token | im |
Token ID | 545 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Appearance | +0.458 |
��極 | +0.429 |
heit | +0.388 |
aneers | +0.380 |
adan | +0.373 |
Neg logit contributions | |
Kubrick | -0.351 |
tires | -0.313 |
chess | -0.311 |
Redd | -0.307 |
� | -0.294 |
Token | utils |
Token ID | 26791 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Appearance | +0.587 |
��極 | +0.546 |
heit | +0.499 |
aneers | +0.488 |
adan | +0.482 |
Neg logit contributions | |
Kubrick | -0.456 |
tires | -0.406 |
chess | -0.404 |
Redd | -0.397 |
� | -0.382 |
Token | import |
Token ID | 1330 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
Kubrick | +0.699 |
chess | +0.614 |
tires | +0.613 |
Redd | +0.586 |
Pens | +0.565 |
Neg logit contributions | |
Appearance | -1.168 |
��極 | -1.122 |
heit | -1.012 |
aneers | -0.999 |
adan | -0.981 |
Token | paths |
Token ID | 13532 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Appearance | +3.349 |
��極 | +2.921 |
heit | +2.540 |
aneers | +2.415 |
ighthouse | +2.297 |
Neg logit contributions | |
Kubrick | -5.738 |
Redd | -5.304 |
tires | -5.268 |
chess | -5.204 |
� | -5.144 |
Token | import |
Token ID | 1330 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
Kubrick | +0.610 |
chess | +0.536 |
tires | +0.535 |
Redd | +0.510 |
Pens | +0.493 |
Neg logit contributions | |
Appearance | -1.023 |
��極 | -0.989 |
heit | -0.889 |
aneers | -0.880 |
adan | -0.864 |
Token | n |
Token ID | 299 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Appearance | +4.291 |
��極 | +3.832 |
heit | +3.523 |
aneers | +3.408 |
adan | +3.367 |
Neg logit contributions | |
Kubrick | -3.710 |
Redd | -3.403 |
tires | -3.297 |
� | -3.244 |
chess | -3.236 |
Token | umpy |
Token ID | 32152 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Appearance | +0.709 |
��極 | +0.664 |
heit | +0.623 |
aneers | +0.611 |
adan | +0.604 |
Neg logit contributions | |
Kubrick | -0.352 |
tires | -0.302 |
chess | -0.299 |
Redd | -0.293 |
� | -0.278 |
Token | as |
Token ID | 355 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
Appearance | +1.304 |
��極 | +1.226 |
heit | +1.117 |
aneers | +1.097 |
adan | +1.080 |
Neg logit contributions | |
Kubrick | -0.859 |
tires | -0.756 |
chess | -0.753 |
Redd | -0.739 |
� | -0.706 |
Token | np |
Token ID | 45941 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Appearance | +0.887 |
��極 | +0.801 |
heit | +0.748 |
aneers | +0.717 |
adan | +0.715 |
Neg logit contributions | |
Kubrick | -0.718 |
Redd | -0.648 |
tires | -0.640 |
chess | -0.628 |
� | -0.621 |
Token | import |
Token ID | 1330 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
Appearance | +0.438 |
��極 | +0.416 |
heit | +0.378 |
aneers | +0.372 |
adan | +0.366 |
Neg logit contributions | |
Kubrick | -0.271 |
tires | -0.239 |
chess | -0.239 |
Redd | -0.230 |
Pens | -0.220 |
Token | Go |
Token ID | 1514 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Kubrick | +0.323 |
chess | +0.294 |
tires | +0.294 |
Redd | +0.285 |
Pens | +0.278 |
Neg logit contributions | |
Appearance | -0.322 |
��極 | -0.305 |
heit | -0.271 |
aneers | -0.264 |
adan | -0.257 |
Token | players |
Token ID | 1938 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Appearance | +1.345 |
��極 | +1.262 |
heit | +1.150 |
aneers | +1.130 |
adan | +1.112 |
Neg logit contributions | |
Kubrick | -0.882 |
tires | -0.774 |
chess | -0.772 |
Redd | -0.758 |
� | -0.723 |
Token | make |
Token ID | 787 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Appearance | +0.459 |
��極 | +0.430 |
heit | +0.389 |
aneers | +0.382 |
adan | +0.375 |
Neg logit contributions | |
Kubrick | -0.345 |
tires | -0.307 |
chess | -0.306 |
Redd | -0.301 |
� | -0.289 |
Token | their |
Token ID | 511 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Kubrick | +0.388 |
tires | +0.349 |
chess | +0.348 |
Redd | +0.341 |
� | +0.329 |
Neg logit contributions | |
Appearance | -0.434 |
��極 | -0.406 |
heit | -0.363 |
aneers | -0.356 |
adan | -0.349 |
Token | way |
Token ID | 835 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
Appearance | +0.403 |
��極 | +0.379 |
heit | +0.339 |
aneers | +0.332 |
adan | +0.324 |
Neg logit contributions | |
Kubrick | -0.366 |
tires | -0.331 |
chess | -0.330 |
Redd | -0.323 |
Pens | -0.311 |
Token | through |
Token ID | 832 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
Appearance | +0.739 |
��極 | +0.690 |
heit | +0.632 |
aneers | +0.620 |
adan | +0.610 |
Neg logit contributions | |
Kubrick | -0.506 |
tires | -0.446 |
chess | -0.443 |
Redd | -0.438 |
� | -0.420 |
Token | Battery |
Token ID | 23490 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Appearance | +4.522 |
��極 | +4.170 |
heit | +3.793 |
aneers | +3.714 |
adan | +3.678 |
Neg logit contributions | |
Kubrick | -3.292 |
tires | -2.888 |
chess | -2.879 |
Redd | -2.872 |
� | -2.790 |
Token | Park |
Token ID | 3250 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
Appearance | +0.408 |
��極 | +0.385 |
heit | +0.349 |
aneers | +0.343 |
adan | +0.335 |
Neg logit contributions | |
Kubrick | -0.294 |
tires | -0.262 |
chess | -0.261 |
Redd | -0.254 |
Pens | -0.246 |
Token | as |
Token ID | 355 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Kubrick | +0.057 |
tires | +0.050 |
chess | +0.050 |
Redd | +0.048 |
Pens | +0.046 |
Neg logit contributions | |
Appearance | -0.090 |
��極 | -0.086 |
heit | -0.078 |
aneers | -0.077 |
adan | -0.075 |
Token | they |
Token ID | 484 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
Appearance | +1.017 |
��極 | +0.946 |
heit | +0.850 |
aneers | +0.833 |
adan | +0.817 |
Neg logit contributions | |
Kubrick | -0.911 |
tires | -0.818 |
chess | -0.816 |
Redd | -0.804 |
� | -0.776 |
Token | look |
Token ID | 804 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
Kubrick | +0.013 |
tires | +0.012 |
chess | +0.012 |
Redd | +0.011 |
� | +0.011 |
Neg logit contributions | |
Appearance | -0.016 |
��極 | -0.015 |
heit | -0.013 |
aneers | -0.013 |
adan | -0.013 |
Token | na |
Token ID | 12385 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Appearance | +2.813 |
��極 | +2.628 |
heit | +2.414 |
aneers | +2.360 |
adan | +2.344 |
Neg logit contributions | |
Kubrick | -1.867 |
Redd | -1.627 |
chess | -1.625 |
tires | -1.621 |
� | -1.536 |
Token | ring |
Token ID | 5858 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Appearance | +3.081 |
��極 | +2.877 |
heit | +2.620 |
aneers | +2.558 |
adan | +2.535 |
Neg logit contributions | |
Kubrick | -2.217 |
tires | -1.951 |
chess | -1.948 |
Redd | -1.945 |
� | -1.848 |
Token | mag |
Token ID | 2153 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Appearance | +0.279 |
��極 | +0.261 |
heit | +0.232 |
aneers | +0.227 |
adan | +0.221 |
Neg logit contributions | |
Kubrick | -0.256 |
tires | -0.232 |
chess | -0.231 |
Redd | -0.226 |
Pens | -0.218 |
Token | ul |
Token ID | 377 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Appearance | +1.529 |
��極 | +1.426 |
heit | +1.277 |
aneers | +1.250 |
adan | +1.227 |
Neg logit contributions | |
Kubrick | -1.395 |
tires | -1.256 |
chess | -1.253 |
Redd | -1.231 |
� | -1.186 |
Token | ang |
Token ID | 648 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Appearance | +0.460 |
��極 | +0.428 |
heit | +0.380 |
aneers | +0.372 |
adan | +0.364 |
Neg logit contributions | |
Kubrick | -0.465 |
tires | -0.421 |
chess | -0.420 |
Redd | -0.413 |
� | -0.399 |
Token | ang |
Token ID | 3550 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
Appearance | +1.958 |
��極 | +1.843 |
heit | +1.685 |
aneers | +1.654 |
adan | +1.632 |
Neg logit contributions | |
Kubrick | -1.234 |
tires | -1.076 |
chess | -1.076 |
Redd | -1.059 |
� | -1.008 |
Token | nat |
Token ID | 34664 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Appearance | +4.537 |
��極 | +4.221 |
heit | +3.840 |
aneers | +3.736 |
adan | +3.717 |
Neg logit contributions | |
Kubrick | -3.263 |
Redd | -2.886 |
chess | -2.859 |
tires | -2.840 |
� | -2.750 |
Token | ut |
Token ID | 315 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Appearance | +1.533 |
��極 | +1.423 |
heit | +1.280 |
aneers | +1.254 |
adan | +1.237 |
Neg logit contributions | |
Kubrick | -1.477 |
chess | -1.332 |
tires | -1.331 |
Redd | -1.312 |
� | -1.264 |
Token | u |
Token ID | 84 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Appearance | +0.500 |
��極 | +0.467 |
heit | +0.416 |
aneers | +0.407 |
adan | +0.398 |
Neg logit contributions | |
Kubrick | -0.481 |
tires | -0.434 |
chess | -0.433 |
Redd | -0.426 |
� | -0.410 |
Token | wa |
Token ID | 10247 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Appearance | +1.411 |
��極 | +1.326 |
heit | +1.207 |
aneers | +1.184 |
adan | +1.167 |
Neg logit contributions | |
Kubrick | -0.987 |
tires | -0.870 |
chess | -0.869 |
Redd | -0.854 |
� | -0.817 |
Token | na |
Token ID | 12385 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
Appearance | +1.838 |
��極 | +1.729 |
heit | +1.583 |
aneers | +1.553 |
adan | +1.533 |
Neg logit contributions | |
Kubrick | -1.152 |
tires | -1.005 |
chess | -1.002 |
Redd | -0.989 |
� | -0.939 |
Token | 's |
Token ID | 338 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
Kubrick | +0.164 |
tires | +0.146 |
chess | +0.145 |
Redd | +0.140 |
Pens | +0.134 |
Neg logit contributions | |
Appearance | -0.268 |
��極 | -0.256 |
heit | -0.231 |
aneers | -0.228 |
adan | -0.224 |
Token | sunk |
Token ID | 24790 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
Appearance | +0.938 |
��極 | +0.876 |
heit | +0.796 |
aneers | +0.778 |
adan | +0.767 |
Neg logit contributions | |
Kubrick | -0.683 |
chess | -0.601 |
tires | -0.600 |
Redd | -0.594 |
� | -0.568 |
Token | en |
Token ID | 268 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
Appearance | +0.079 |
��極 | +0.074 |
heit | +0.068 |
aneers | +0.067 |
adan | +0.065 |
Neg logit contributions | |
Kubrick | -0.049 |
tires | -0.043 |
chess | -0.043 |
Redd | -0.042 |
Pens | -0.040 |
Token | fireplace |
Token ID | 44250 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Appearance | +0.774 |
��極 | +0.723 |
heit | +0.660 |
aneers | +0.645 |
adan | +0.635 |
Neg logit contributions | |
Kubrick | -0.538 |
tires | -0.472 |
chess | -0.472 |
Redd | -0.467 |
� | -0.447 |
Token | in |
Token ID | 287 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Appearance | +2.952 |
��極 | +2.729 |
heit | +2.513 |
aneers | +2.440 |
adan | +2.419 |
Neg logit contributions | |
Kubrick | -2.075 |
Redd | -1.813 |
chess | -1.813 |
tires | -1.807 |
� | -1.729 |
Token | order |
Token ID | 1502 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
Appearance | +1.911 |
��極 | +1.767 |
heit | +1.619 |
aneers | +1.574 |
adan | +1.559 |
Neg logit contributions | |
Kubrick | -1.337 |
tires | -1.175 |
chess | -1.172 |
Redd | -1.167 |
� | -1.120 |
Token | to |
Token ID | 284 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Appearance | +4.394 |
��極 | +4.139 |
heit | +3.772 |
aneers | +3.682 |
adan | +3.640 |
Neg logit contributions | |
Kubrick | -3.248 |
Redd | -2.865 |
chess | -2.825 |
tires | -2.816 |
Pens | -2.669 |
Token | dry |
Token ID | 5894 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Appearance | +1.302 |
��極 | +1.214 |
heit | +1.098 |
aneers | +1.075 |
adan | +1.058 |
Neg logit contributions | |
Kubrick | -1.060 |
tires | -0.944 |
chess | -0.944 |
Redd | -0.930 |
� | -0.894 |
Token | their |
Token ID | 511 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
Appearance | +2.079 |
��極 | +1.953 |
heit | +1.775 |
aneers | +1.738 |
adan | +1.712 |
Neg logit contributions | |
Kubrick | -1.461 |
tires | -1.288 |
chess | -1.287 |
Redd | -1.263 |
� | -1.208 |
Token | clothes |
Token ID | 8242 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Appearance | +0.788 |
��極 | +0.744 |
heit | +0.677 |
aneers | +0.666 |
adan | +0.654 |
Neg logit contributions | |
Kubrick | -0.506 |
tires | -0.445 |
chess | -0.444 |
Redd | -0.434 |
� | -0.414 |
Token | . |
Token ID | 13 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Appearance | +0.872 |
��極 | +0.822 |
heit | +0.746 |
aneers | +0.733 |
adan | +0.721 |
Neg logit contributions | |
Kubrick | -0.578 |
tires | -0.511 |
chess | -0.509 |
Redd | -0.497 |
� | -0.475 |
Token | the |
Token ID | 262 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Kubrick | +0.265 |
tires | +0.235 |
chess | +0.235 |
Redd | +0.231 |
� | +0.222 |
Neg logit contributions | |
Appearance | -0.351 |
��極 | -0.329 |
heit | -0.298 |
aneers | -0.292 |
adan | -0.287 |
Token | Incredible |
Token ID | 33832 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Appearance | +0.532 |
��極 | +0.497 |
heit | +0.451 |
aneers | +0.442 |
adan | +0.435 |
Neg logit contributions | |
Kubrick | -0.388 |
chess | -0.343 |
tires | -0.342 |
Redd | -0.340 |
� | -0.327 |
Token | Hulk |
Token ID | 22860 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Appearance | +0.109 |
��極 | +0.100 |
heit | +0.088 |
aneers | +0.086 |
adan | +0.084 |
Neg logit contributions | |
Kubrick | -0.122 |
tires | -0.111 |
chess | -0.111 |
Redd | -0.110 |
� | -0.106 |
Token | had |
Token ID | 550 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Appearance | +1.129 |
��極 | +1.063 |
heit | +0.980 |
aneers | +0.961 |
adan | +0.948 |
Neg logit contributions | |
Kubrick | -0.616 |
tires | -0.530 |
chess | -0.530 |
Redd | -0.525 |
� | -0.497 |
Token | gone |
Token ID | 3750 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Appearance | +0.621 |
��極 | +0.580 |
heit | +0.527 |
aneers | +0.517 |
adan | +0.508 |
Neg logit contributions | |
Kubrick | -0.455 |
chess | -0.403 |
tires | -0.402 |
Redd | -0.399 |
� | -0.382 |
Token | through |
Token ID | 832 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
Appearance | +0.279 |
��極 | +0.262 |
heit | +0.239 |
aneers | +0.235 |
adan | +0.232 |
Neg logit contributions | |
Kubrick | -0.176 |
tires | -0.154 |
chess | -0.154 |
Redd | -0.152 |
� | -0.145 |
Token | there |
Token ID | 612 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Appearance | +4.308 |
��極 | +4.000 |
heit | +3.631 |
aneers | +3.547 |
adan | +3.515 |
Neg logit contributions | |
Kubrick | -3.237 |
Redd | -2.938 |
chess | -2.866 |
tires | -2.847 |
� | -2.826 |
Token | in |
Token ID | 287 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Appearance | +0.372 |
��極 | +0.353 |
heit | +0.328 |
aneers | +0.322 |
adan | +0.318 |
Neg logit contributions | |
Kubrick | -0.150 |
tires | -0.124 |
chess | -0.124 |
Redd | -0.122 |
� | -0.114 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Appearance | +0.214 |
��極 | +0.200 |
heit | +0.181 |
aneers | +0.178 |
adan | +0.175 |
Neg logit contributions | |
Kubrick | -0.157 |
tires | -0.139 |
chess | -0.139 |
Redd | -0.136 |
� | -0.131 |
Token | rage |
Token ID | 14404 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Kubrick | +0.076 |
tires | +0.067 |
chess | +0.067 |
Redd | +0.066 |
� | +0.064 |
Neg logit contributions | |
Appearance | -0.104 |
��極 | -0.097 |
heit | -0.088 |
aneers | -0.086 |
adan | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Appearance | +1.525 |
��極 | +1.447 |
heit | +1.347 |
aneers | +1.326 |
adan | +1.313 |
Neg logit contributions | |
Kubrick | -0.551 |
tires | -0.448 |
chess | -0.447 |
Redd | -0.440 |
� | -0.406 |
Token | its |
Token ID | 663 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Kubrick | +0.349 |
tires | +0.308 |
chess | +0.307 |
Redd | +0.301 |
� | +0.287 |
Neg logit contributions | |
Appearance | -0.523 |
��極 | -0.492 |
heit | -0.447 |
aneers | -0.439 |
adan | -0.432 |
Token | intentions |
Token ID | 14953 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Kubrick | +0.110 |
tires | +0.097 |
chess | +0.097 |
Redd | +0.096 |
� | +0.092 |
Neg logit contributions | |
Appearance | -0.146 |
��極 | -0.136 |
heit | -0.123 |
aneers | -0.120 |
adan | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
Appearance | +0.164 |
��極 | +0.155 |
heit | +0.140 |
aneers | +0.138 |
adan | +0.136 |
Neg logit contributions | |
Kubrick | -0.105 |
tires | -0.092 |
chess | -0.092 |
Redd | -0.090 |
� | -0.086 |
Token | He |
Token ID | 679 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Appearance | +0.491 |
��極 | +0.462 |
heit | +0.418 |
aneers | +0.411 |
adan | +0.403 |
Neg logit contributions | |
Kubrick | -0.358 |
tires | -0.317 |
chess | -0.316 |
Redd | -0.310 |
� | -0.297 |
Token | went |
Token ID | 1816 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
Appearance | +0.160 |
��極 | +0.151 |
heit | +0.136 |
aneers | +0.134 |
adan | +0.131 |
Neg logit contributions | |
Kubrick | -0.112 |
tires | -0.099 |
chess | -0.099 |
Redd | -0.096 |
� | -0.092 |
Token | through |
Token ID | 832 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
Appearance | +0.028 |
��極 | +0.027 |
heit | +0.024 |
aneers | +0.024 |
adan | +0.024 |
Neg logit contributions | |
Kubrick | -0.018 |
tires | -0.016 |
chess | -0.016 |
Redd | -0.015 |
� | -0.014 |
Token | something |
Token ID | 1223 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Appearance | +4.283 |
��極 | +3.961 |
heit | +3.573 |
aneers | +3.507 |
adan | +3.483 |
Neg logit contributions | |
Kubrick | -3.206 |
Redd | -2.828 |
tires | -2.818 |
chess | -2.806 |
� | -2.717 |
Token | similar |
Token ID | 2092 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Kubrick | +0.127 |
tires | +0.113 |
chess | +0.113 |
Redd | +0.110 |
Pens | +0.106 |
Neg logit contributions | |
Appearance | -0.167 |
��極 | -0.157 |
heit | -0.142 |
aneers | -0.139 |
adan | -0.136 |
Token | the |
Token ID | 262 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
Kubrick | +0.640 |
chess | +0.558 |
tires | +0.558 |
Redd | +0.536 |
Pens | +0.514 |
Neg logit contributions | |
Appearance | -1.087 |
��極 | -1.040 |
heit | -0.945 |
aneers | -0.935 |
adan | -0.909 |
Token | year |
Token ID | 614 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Kubrick | +0.626 |
tires | +0.558 |
chess | +0.558 |
Redd | +0.541 |
Pens | +0.523 |
Neg logit contributions | |
Appearance | -0.819 |
��極 | -0.774 |
heit | -0.701 |
aneers | -0.687 |
adan | -0.671 |
Token | before |
Token ID | 878 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Kubrick | +0.569 |
chess | +0.480 |
tires | +0.479 |
Redd | +0.459 |
Pens | +0.439 |
Neg logit contributions | |
Appearance | -1.259 |
��極 | -1.207 |
heit | -1.108 |
aneers | -1.093 |
adan | -1.071 |
Token | your |
Token ID | 534 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Appearance | +0.905 |
��極 | +0.850 |
heit | +0.769 |
aneers | +0.755 |
adan | +0.742 |
Neg logit contributions | |
Kubrick | -0.660 |
tires | -0.586 |
chess | -0.584 |
Redd | -0.573 |
� | -0.549 |
Token | starting |
Token ID | 3599 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
Appearance | +0.425 |
��極 | +0.399 |
heit | +0.363 |
aneers | +0.356 |
adan | +0.350 |
Neg logit contributions | |
Kubrick | -0.289 |
tires | -0.254 |
chess | -0.253 |
Redd | -0.249 |
� | -0.239 |
Token | distance |
Token ID | 5253 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
Appearance | +0.720 |
��極 | +0.678 |
heit | +0.615 |
aneers | +0.603 |
adan | +0.593 |
Neg logit contributions | |
Kubrick | -0.503 |
tires | -0.444 |
chess | -0.443 |
Redd | -0.434 |
� | -0.416 |
Token | , |
Token ID | 11 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Appearance | +0.718 |
��極 | +0.674 |
heit | +0.615 |
aneers | +0.604 |
adan | +0.595 |
Neg logit contributions | |
Kubrick | -0.448 |
tires | -0.391 |
chess | -0.390 |
Redd | -0.384 |
� | -0.366 |
Token | go |
Token ID | 467 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
Appearance | +0.857 |
��極 | +0.803 |
heit | +0.728 |
aneers | +0.714 |
adan | +0.702 |
Neg logit contributions | |
Kubrick | -0.627 |
tires | -0.556 |
chess | -0.554 |
Redd | -0.546 |
� | -0.523 |
Token | through |
Token ID | 832 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
Appearance | +0.914 |
��極 | +0.864 |
heit | +0.783 |
aneers | +0.770 |
adan | +0.756 |
Neg logit contributions | |
Kubrick | -0.607 |
tires | -0.535 |
chess | -0.535 |
Redd | -0.520 |
Pens | -0.498 |
Token | your |
Token ID | 534 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Appearance | +4.296 |
��極 | +3.970 |
heit | +3.640 |
aneers | +3.553 |
adan | +3.505 |
Neg logit contributions | |
Kubrick | -3.110 |
chess | -2.731 |
Redd | -2.729 |
tires | -2.722 |
� | -2.628 |
Token | routine |
Token ID | 8027 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Kubrick | +0.137 |
tires | +0.122 |
chess | +0.122 |
Redd | +0.118 |
Pens | +0.114 |
Neg logit contributions | |
Appearance | -0.201 |
��極 | -0.191 |
heit | -0.173 |
aneers | -0.171 |
adan | -0.167 |
Token | , |
Token ID | 11 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Appearance | +0.559 |
��極 | +0.527 |
heit | +0.479 |
aneers | +0.471 |
adan | +0.463 |
Neg logit contributions | |
Kubrick | -0.366 |
tires | -0.323 |
chess | -0.322 |
Redd | -0.314 |
� | -0.300 |
Token | and |
Token ID | 290 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Appearance | +0.495 |
��極 | +0.464 |
heit | +0.420 |
aneers | +0.412 |
adan | +0.405 |
Neg logit contributions | |
Kubrick | -0.372 |
tires | -0.331 |
chess | -0.330 |
Redd | -0.324 |
� | -0.311 |
Token | make |
Token ID | 787 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Appearance | +0.158 |
��極 | +0.148 |
heit | +0.133 |
aneers | +0.130 |
adan | +0.128 |
Neg logit contributions | |
Kubrick | -0.130 |
tires | -0.116 |
chess | -0.116 |
Redd | -0.113 |
� | -0.109 |
Token | from |
Token ID | 422 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Appearance | +1.474 |
��極 | +1.375 |
heit | +1.255 |
aneers | +1.231 |
adan | +1.212 |
Neg logit contributions | |
Kubrick | -0.980 |
tires | -0.863 |
chess | -0.858 |
Redd | -0.854 |
� | -0.814 |
Token | im |
Token ID | 545 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Appearance | +0.452 |
��極 | +0.426 |
heit | +0.386 |
aneers | +0.379 |
adan | +0.373 |
Neg logit contributions | |
Kubrick | -0.316 |
tires | -0.280 |
chess | -0.279 |
Redd | -0.273 |
� | -0.261 |
Token | utils |
Token ID | 26791 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Appearance | +1.030 |
��極 | +0.967 |
heit | +0.869 |
aneers | +0.854 |
adan | +0.836 |
Neg logit contributions | |
Kubrick | -0.828 |
tires | -0.740 |
chess | -0.739 |
Redd | -0.723 |
� | -0.696 |
Token | import |
Token ID | 1330 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
Kubrick | +0.399 |
chess | +0.352 |
tires | +0.351 |
Redd | +0.338 |
Pens | +0.326 |
Neg logit contributions | |
Appearance | -0.628 |
��極 | -0.597 |
heit | -0.542 |
aneers | -0.533 |
adan | -0.524 |
Token | paths |
Token ID | 13532 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Appearance | +5.011 |
��極 | +4.559 |
heit | +4.187 |
aneers | +4.061 |
adan | +4.003 |
Neg logit contributions | |
Kubrick | -3.493 |
Redd | -3.179 |
tires | -3.097 |
chess | -3.040 |
� | -3.027 |
Token | import |
Token ID | 1330 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Kubrick | +0.485 |
tires | +0.429 |
chess | +0.428 |
Redd | +0.414 |
Pens | +0.399 |
Neg logit contributions | |
Appearance | -0.735 |
��極 | -0.699 |
heit | -0.632 |
aneers | -0.622 |
adan | -0.611 |
Token | n |
Token ID | 299 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
Appearance | +4.273 |
��極 | +3.901 |
heit | +3.577 |
aneers | +3.479 |
adan | +3.422 |
Neg logit contributions | |
Kubrick | -3.018 |
Redd | -2.733 |
tires | -2.674 |
chess | -2.626 |
� | -2.603 |
Token | umpy |
Token ID | 32152 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Appearance | +0.716 |
��極 | +0.676 |
heit | +0.620 |
aneers | +0.610 |
adan | +0.601 |
Neg logit contributions | |
Kubrick | -0.389 |
tires | -0.337 |
chess | -0.335 |
Redd | -0.327 |
� | -0.311 |
Token | as |
Token ID | 355 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Appearance | +1.531 |
��極 | +1.434 |
heit | +1.310 |
aneers | +1.284 |
adan | +1.265 |
Neg logit contributions | |
Kubrick | -1.022 |
tires | -0.895 |
chess | -0.891 |
Redd | -0.884 |
� | -0.841 |
Token | np |
Token ID | 45941 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
Appearance | +0.552 |
��極 | +0.518 |
heit | +0.469 |
aneers | +0.460 |
adan | +0.453 |
Neg logit contributions | |
Kubrick | -0.405 |
tires | -0.358 |
chess | -0.357 |
Redd | -0.352 |
� | -0.337 |
Token | import |
Token ID | 1330 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Appearance | +0.908 |
��極 | +0.859 |
heit | +0.779 |
aneers | +0.766 |
adan | +0.753 |
Neg logit contributions | |
Kubrick | -0.602 |
tires | -0.531 |
chess | -0.530 |
Redd | -0.515 |
Pens | -0.494 |
Token | )." |
Token ID | 21387 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Kubrick | +0.970 |
tires | +0.860 |
chess | +0.856 |
Redd | +0.814 |
Pens | +0.801 |
Neg logit contributions | |
Appearance | -1.687 |
��極 | -1.627 |
heit | -1.482 |
aneers | -1.441 |
adan | -1.421 |
Token | We |
Token ID | 1135 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Kubrick | +0.292 |
tires | +0.264 |
chess | +0.263 |
Redd | +0.263 |
� | +0.251 |
Neg logit contributions | |
Appearance | -0.309 |
��極 | -0.292 |
heit | -0.258 |
aneers | -0.252 |
adan | -0.247 |
Token | have |
Token ID | 423 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
Appearance | +0.418 |
��極 | +0.392 |
heit | +0.354 |
aneers | +0.348 |
adan | +0.342 |
Neg logit contributions | |
Kubrick | -0.324 |
tires | -0.288 |
chess | -0.288 |
Redd | -0.283 |
� | -0.272 |
Token | all |
Token ID | 477 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Kubrick | +0.582 |
chess | +0.516 |
tires | +0.516 |
Redd | +0.497 |
Pens | +0.479 |
Neg logit contributions | |
Appearance | -0.849 |
��極 | -0.803 |
heit | -0.725 |
aneers | -0.713 |
adan | -0.700 |
Token | gone |
Token ID | 3750 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Kubrick | +0.725 |
tires | +0.646 |
chess | +0.645 |
Redd | +0.622 |
Pens | +0.597 |
Neg logit contributions | |
Appearance | -1.064 |
��極 | -1.007 |
heit | -0.909 |
aneers | -0.892 |
adan | -0.876 |
Token | through |
Token ID | 832 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
Appearance | +1.295 |
��極 | +1.211 |
heit | +1.096 |
aneers | +1.073 |
adan | +1.063 |
Neg logit contributions | |
Kubrick | -1.009 |
tires | -0.895 |
Redd | -0.889 |
chess | -0.888 |
� | -0.852 |
Token | some |
Token ID | 617 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Appearance | +3.796 |
��極 | +3.494 |
heit | +3.155 |
aneers | +3.101 |
adan | +3.047 |
Neg logit contributions | |
Kubrick | -3.266 |
Redd | -2.971 |
tires | -2.897 |
� | -2.881 |
chess | -2.857 |
Token | situations |
Token ID | 7445 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Appearance | +0.383 |
��極 | +0.355 |
heit | +0.321 |
aneers | +0.313 |
adan | +0.309 |
Neg logit contributions | |
Kubrick | -0.316 |
tires | -0.280 |
Redd | -0.280 |
chess | -0.279 |
� | -0.270 |
Token | here |
Token ID | 994 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Kubrick | +0.169 |
tires | +0.148 |
chess | +0.148 |
Redd | +0.144 |
� | +0.138 |
Neg logit contributions | |
Appearance | -0.269 |
��極 | -0.254 |
heit | -0.231 |
aneers | -0.227 |
adan | -0.224 |
Token | that |
Token ID | 326 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
Appearance | +0.137 |
��極 | +0.129 |
heit | +0.118 |
aneers | +0.116 |
adan | +0.114 |
Neg logit contributions | |
Kubrick | -0.083 |
tires | -0.073 |
chess | -0.073 |
Redd | -0.071 |
� | -0.068 |
Token | none |
Token ID | 4844 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
Appearance | +0.666 |
��極 | +0.621 |
heit | +0.562 |
aneers | +0.550 |
adan | +0.541 |
Neg logit contributions | |
Kubrick | -0.535 |
tires | -0.478 |
chess | -0.476 |
Redd | -0.473 |
� | -0.453 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Kubrick | +0.021 |
chess | +0.018 |
tires | +0.018 |
Redd | +0.018 |
� | +0.017 |
Neg logit contributions | |
Appearance | -0.030 |
��極 | -0.028 |
heit | -0.025 |
aneers | -0.025 |
adan | -0.024 |
Token | " |
Token ID | 1 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Kubrick | +0.115 |
tires | +0.102 |
chess | +0.102 |
Redd | +0.101 |
� | +0.096 |
Neg logit contributions | |
Appearance | -0.145 |
��極 | -0.136 |
heit | -0.122 |
aneers | -0.120 |
adan | -0.117 |
Token | I |
Token ID | 40 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Kubrick | +0.320 |
tires | +0.287 |
chess | +0.286 |
Redd | +0.285 |
� | +0.273 |
Neg logit contributions | |
Appearance | -0.342 |
��極 | -0.324 |
heit | -0.285 |
aneers | -0.280 |
adan | -0.273 |
Token | just |
Token ID | 655 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Kubrick | +0.242 |
tires | +0.216 |
chess | +0.214 |
Redd | +0.209 |
Pens | +0.201 |
Neg logit contributions | |
Appearance | -0.316 |
��極 | -0.298 |
heit | -0.268 |
aneers | -0.264 |
adan | -0.258 |
Token | went |
Token ID | 1816 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Appearance | +0.132 |
��極 | +0.124 |
heit | +0.111 |
aneers | +0.109 |
adan | +0.107 |
Neg logit contributions | |
Kubrick | -0.113 |
tires | -0.102 |
chess | -0.102 |
Redd | -0.099 |
� | -0.096 |
Token | through |
Token ID | 832 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
Kubrick | +0.102 |
tires | +0.090 |
chess | +0.090 |
Redd | +0.087 |
Pens | +0.084 |
Neg logit contributions | |
Appearance | -0.157 |
��極 | -0.149 |
heit | -0.134 |
aneers | -0.133 |
adan | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
Appearance | +4.095 |
��極 | +3.758 |
heit | +3.479 |
aneers | +3.380 |
adan | +3.357 |
Neg logit contributions | |
Kubrick | -3.057 |
chess | -2.728 |
tires | -2.724 |
Redd | -2.722 |
� | -2.614 |
Token | LA |
Token ID | 9131 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
Appearance | +0.677 |
��極 | +0.638 |
heit | +0.578 |
aneers | +0.568 |
adan | +0.558 |
Neg logit contributions | |
Kubrick | -0.465 |
tires | -0.411 |
chess | -0.410 |
Redd | -0.401 |
� | -0.384 |
Token | X |
Token ID | 55 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Appearance | +0.073 |
��極 | +0.069 |
heit | +0.062 |
aneers | +0.061 |
adan | +0.060 |
Neg logit contributions | |
Kubrick | -0.053 |
tires | -0.047 |
chess | -0.047 |
Redd | -0.045 |
Pens | -0.044 |
Token | security |
Token ID | 2324 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Kubrick | +0.318 |
tires | +0.281 |
chess | +0.280 |
Redd | +0.272 |
Pens | +0.261 |
Neg logit contributions | |
Appearance | -0.465 |
��極 | -0.440 |
heit | -0.397 |
aneers | -0.391 |
adan | -0.383 |
Token | line |
Token ID | 1627 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Kubrick | +0.729 |
tires | +0.643 |
chess | +0.642 |
Redd | +0.617 |
Pens | +0.595 |
Neg logit contributions | |
Appearance | -1.136 |
��極 | -1.082 |
heit | -0.978 |
aneers | -0.961 |
adan | -0.939 |
Token | as |
Token ID | 355 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
Appearance | +1.304 |
��極 | +1.226 |
heit | +1.117 |
aneers | +1.097 |
adan | +1.080 |
Neg logit contributions | |
Kubrick | -0.859 |
tires | -0.756 |
chess | -0.753 |
Redd | -0.739 |
� | -0.706 |
Token | np |
Token ID | 45941 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Appearance | +0.887 |
��極 | +0.801 |
heit | +0.748 |
aneers | +0.717 |
adan | +0.715 |
Neg logit contributions | |
Kubrick | -0.718 |
Redd | -0.648 |
tires | -0.640 |
chess | -0.628 |
� | -0.621 |
Token | import |
Token ID | 1330 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
Appearance | +0.438 |
��極 | +0.416 |
heit | +0.378 |
aneers | +0.372 |
adan | +0.366 |
Neg logit contributions | |
Kubrick | -0.271 |
tires | -0.239 |
chess | -0.239 |
Redd | -0.230 |
Pens | -0.220 |
Token | arg |
Token ID | 1822 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Appearance | +3.333 |
��極 | +3.028 |
heit | +2.721 |
aneers | +2.658 |
adan | +2.610 |
Neg logit contributions | |
Kubrick | -3.353 |
Redd | -3.055 |
tires | -2.997 |
chess | -2.971 |
� | -2.920 |
Token | parse |
Token ID | 29572 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
Kubrick | +1.397 |
tires | +1.267 |
chess | +1.259 |
Redd | +1.237 |
Pens | +1.191 |
Neg logit contributions | |
Appearance | -1.417 |
��極 | -1.346 |
heit | -1.164 |
aneers | -1.138 |
adan | -1.111 |
Token | import |
Token ID | 1330 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Kubrick | +0.019 |
tires | +0.017 |
chess | +0.017 |
Redd | +0.017 |
Pens | +0.016 |
Neg logit contributions | |
Appearance | -0.031 |
��極 | -0.029 |
heit | -0.027 |
aneers | -0.026 |
adan | -0.026 |
Token | im |
Token ID | 545 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Appearance | +3.752 |
��極 | +3.288 |
heit | +3.073 |
adan | +2.931 |
aneers | +2.924 |
Neg logit contributions | |
Kubrick | -3.369 |
Redd | -3.139 |
tires | -3.007 |
� | -2.980 |
chess | -2.962 |
Token | utils |
Token ID | 26791 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Appearance | +0.297 |
��極 | +0.279 |
heit | +0.253 |
aneers | +0.248 |
adan | +0.244 |
Neg logit contributions | |
Kubrick | -0.222 |
tires | -0.197 |
chess | -0.197 |
Redd | -0.193 |
� | -0.185 |
Token | import |
Token ID | 1330 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Kubrick | +0.783 |
chess | +0.691 |
tires | +0.687 |
Redd | +0.650 |
Pens | +0.634 |
Neg logit contributions | |
Appearance | -1.329 |
��極 | -1.286 |
heit | -1.160 |
aneers | -1.147 |
adan | -1.122 |
Token | c |
Token ID | 269 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
Appearance | +3.973 |
��極 | +3.652 |
heit | +3.345 |
aneers | +3.286 |
adan | +3.219 |
Neg logit contributions | |
Kubrick | -2.888 |
Redd | -2.613 |
tires | -2.589 |
chess | -2.506 |
� | -2.441 |
Token | v |
Token ID | 85 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
Kubrick | +0.005 |
tires | +0.005 |
chess | +0.005 |
Redd | +0.004 |
� | +0.004 |
Neg logit contributions | |
Appearance | -0.008 |
��極 | -0.007 |
heit | -0.006 |
aneers | -0.006 |
adan | -0.006 |
Token | 27 |
Token ID | 2681 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Appearance | +0.221 |
��極 | +0.208 |
heit | +0.187 |
aneers | +0.183 |
adan | +0.180 |
Neg logit contributions | |
Kubrick | -0.182 |
tires | -0.163 |
chess | -0.162 |
Redd | -0.159 |
� | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
Appearance | +1.172 |
��極 | +1.099 |
heit | +1.007 |
aneers | +0.988 |
adan | +0.971 |
Neg logit contributions | |
Kubrick | -0.725 |
chess | -0.633 |
tires | -0.633 |
Redd | -0.620 |
� | -0.589 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Kubrick | +0.505 |
tires | +0.443 |
chess | +0.439 |
Redd | +0.427 |
Pens | +0.410 |
Neg logit contributions | |
Appearance | -0.854 |
��極 | -0.817 |
heit | -0.738 |
aneers | -0.725 |
adan | -0.717 |
Token | . |
Token ID | 13 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
Kubrick | +0.361 |
tires | +0.317 |
chess | +0.313 |
Redd | +0.305 |
Pens | +0.293 |
Neg logit contributions | |
Appearance | -0.567 |
��極 | -0.546 |
heit | -0.491 |
aneers | -0.482 |
adan | -0.477 |
Token | ( |
Token ID | 357 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
Kubrick | +0.338 |
tires | +0.279 |
chess | +0.278 |
Redd | +0.266 |
Pens | +0.253 |
Neg logit contributions | |
Appearance | -0.854 |
��極 | -0.823 |
heit | -0.755 |
aneers | -0.743 |
adan | -0.738 |
Token | Published |
Token ID | 24492 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Appearance | +0.225 |
��極 | +0.197 |
heit | +0.147 |
aneers | +0.139 |
adan | +0.130 |
Neg logit contributions | |
Kubrick | -0.688 |
tires | -0.645 |
chess | -0.643 |
Redd | -0.637 |
� | -0.624 |
Token | Thursday |
Token ID | 3635 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Appearance | +3.890 |
��極 | +3.475 |
heit | +3.231 |
aneers | +3.185 |
adan | +3.105 |
Neg logit contributions | |
Kubrick | -3.273 |
tires | -2.931 |
Redd | -2.915 |
chess | -2.882 |
� | -2.777 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Kubrick | +0.630 |
tires | +0.548 |
chess | +0.546 |
Redd | +0.532 |
Pens | +0.507 |
Neg logit contributions | |
Appearance | -1.097 |
��極 | -1.043 |
heit | -0.949 |
aneers | -0.937 |
adan | -0.921 |
Token | Dec |
Token ID | 4280 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Kubrick | +0.365 |
tires | +0.329 |
chess | +0.328 |
Redd | +0.321 |
Pens | +0.311 |
Neg logit contributions | |
Appearance | -0.398 |
��極 | -0.375 |
heit | -0.333 |
aneers | -0.326 |
adan | -0.320 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Kubrick | +0.330 |
tires | +0.292 |
chess | +0.291 |
Redd | +0.286 |
� | +0.274 |
Neg logit contributions | |
Appearance | -0.473 |
��極 | -0.444 |
heit | -0.403 |
aneers | -0.396 |
adan | -0.389 |
Token | 27 |
Token ID | 2681 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Kubrick | +0.152 |
tires | +0.132 |
chess | +0.132 |
Redd | +0.129 |
Pens | +0.123 |
Neg logit contributions | |
Appearance | -0.251 |
��極 | -0.239 |
heit | -0.217 |
aneers | -0.214 |
adan | -0.211 |
Token | of |
Token ID | 286 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Appearance | +0.087 |
��極 | +0.082 |
heit | +0.076 |
aneers | +0.074 |
adan | +0.073 |
Neg logit contributions | |
Kubrick | -0.047 |
tires | -0.041 |
chess | -0.041 |
Redd | -0.040 |
� | -0.038 |
Token | fact |
Token ID | 1109 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
Kubrick | +0.345 |
tires | +0.303 |
chess | +0.302 |
Redd | +0.296 |
� | +0.282 |
Neg logit contributions | |
Appearance | -0.547 |
��極 | -0.516 |
heit | -0.470 |
aneers | -0.462 |
adan | -0.455 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Kubrick | +0.364 |
tires | +0.318 |
chess | +0.317 |
Redd | +0.308 |
� | +0.294 |
Neg logit contributions | |
Appearance | -0.612 |
��極 | -0.579 |
heit | -0.528 |
aneers | -0.520 |
adan | -0.511 |
Token | we |
Token ID | 356 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
Appearance | +0.280 |
��極 | +0.264 |
heit | +0.239 |
aneers | +0.235 |
adan | +0.231 |
Neg logit contributions | |
Kubrick | -0.200 |
tires | -0.177 |
chess | -0.177 |
Redd | -0.173 |
� | -0.166 |
Token | went |
Token ID | 1816 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Appearance | +0.044 |
��極 | +0.041 |
heit | +0.037 |
aneers | +0.037 |
adan | +0.036 |
Neg logit contributions | |
Kubrick | -0.032 |
tires | -0.028 |
chess | -0.028 |
Redd | -0.027 |
� | -0.027 |
Token | through |
Token ID | 832 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
Appearance | +0.535 |
��極 | +0.504 |
heit | +0.459 |
aneers | +0.451 |
adan | +0.443 |
Neg logit contributions | |
Kubrick | -0.347 |
tires | -0.305 |
chess | -0.304 |
Redd | -0.298 |
� | -0.284 |
Token | 251 |
Token ID | 34489 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Appearance | +4.069 |
��極 | +3.767 |
heit | +3.409 |
aneers | +3.351 |
adan | +3.346 |
Neg logit contributions | |
Kubrick | -2.999 |
Redd | -2.672 |
tires | -2.647 |
chess | -2.640 |
� | -2.560 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Appearance | +0.428 |
��極 | +0.403 |
heit | +0.366 |
aneers | +0.360 |
adan | +0.354 |
Neg logit contributions | |
Kubrick | -0.287 |
tires | -0.253 |
chess | -0.253 |
Redd | -0.247 |
� | -0.236 |
Token | 000 |
Token ID | 830 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Appearance | +1.419 |
��極 | +1.313 |
heit | +1.172 |
aneers | +1.143 |
adan | +1.121 |
Neg logit contributions | |
Kubrick | -1.441 |
tires | -1.306 |
chess | -1.304 |
Redd | -1.289 |
� | -1.240 |
Token | [ |
Token ID | 685 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Kubrick | +0.420 |
tires | +0.379 |
chess | +0.378 |
Redd | +0.370 |
Pens | +0.357 |
Neg logit contributions | |
Appearance | -0.455 |
��極 | -0.425 |
heit | -0.380 |
aneers | -0.372 |
adan | -0.364 |
Token | le |
Token ID | 293 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
Appearance | +0.485 |
��極 | +0.453 |
heit | +0.407 |
aneers | +0.399 |
adan | +0.392 |
Neg logit contributions | |
Kubrick | -0.418 |
tires | -0.375 |
chess | -0.375 |
Redd | -0.367 |
� | -0.354 |
Token | were |
Token ID | 547 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Appearance | +0.729 |
��極 | +0.686 |
heit | +0.617 |
aneers | +0.607 |
adan | +0.595 |
Neg logit contributions | |
Kubrick | -0.565 |
tires | -0.504 |
chess | -0.503 |
Redd | -0.490 |
Pens | -0.472 |
Token | last |
Token ID | 938 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
Appearance | +0.451 |
��極 | +0.426 |
heit | +0.388 |
aneers | +0.381 |
adan | +0.375 |
Neg logit contributions | |
Kubrick | -0.285 |
tires | -0.250 |
chess | -0.249 |
Redd | -0.243 |
� | -0.232 |
Token | year |
Token ID | 614 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
Appearance | +0.699 |
��極 | +0.658 |
heit | +0.593 |
aneers | +0.583 |
adan | +0.570 |
Neg logit contributions | |
Kubrick | -0.543 |
tires | -0.485 |
chess | -0.484 |
Redd | -0.473 |
Pens | -0.454 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Kubrick | +0.402 |
tires | +0.344 |
chess | +0.343 |
Redd | +0.330 |
Pens | +0.314 |
Neg logit contributions | |
Appearance | -0.837 |
��極 | -0.797 |
heit | -0.730 |
aneers | -0.720 |
adan | -0.706 |
Token | or |
Token ID | 393 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
Appearance | +1.412 |
��極 | +1.323 |
heit | +1.209 |
aneers | +1.185 |
adan | +1.170 |
Neg logit contributions | |
Kubrick | -0.892 |
tires | -0.784 |
chess | -0.778 |
Redd | -0.772 |
� | -0.739 |
Token | is |
Token ID | 318 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Appearance | +0.557 |
��極 | +0.520 |
heit | +0.475 |
aneers | +0.463 |
adan | +0.459 |
Neg logit contributions | |
Kubrick | -0.406 |
tires | -0.360 |
chess | -0.357 |
Redd | -0.356 |
� | -0.341 |
Token | this |
Token ID | 428 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
Appearance | +4.009 |
��極 | +3.710 |
heit | +3.406 |
aneers | +3.269 |
adan | +3.250 |
Neg logit contributions | |
Kubrick | -2.959 |
tires | -2.641 |
Redd | -2.616 |
chess | -2.571 |
� | -2.530 |
Token | more |
Token ID | 517 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Appearance | +0.812 |
��極 | +0.755 |
heit | +0.689 |
aneers | +0.669 |
adan | +0.664 |
Neg logit contributions | |
Kubrick | -0.612 |
tires | -0.541 |
chess | -0.539 |
Redd | -0.537 |
� | -0.516 |
Token | about |
Token ID | 546 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Kubrick | +0.171 |
tires | +0.150 |
chess | +0.150 |
Redd | +0.147 |
� | +0.141 |
Neg logit contributions | |
Appearance | -0.267 |
��極 | -0.251 |
heit | -0.229 |
aneers | -0.225 |
adan | -0.221 |
Token | having |
Token ID | 1719 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Appearance | +0.152 |
��極 | +0.142 |
heit | +0.130 |
aneers | +0.127 |
adan | +0.125 |
Neg logit contributions | |
Kubrick | -0.108 |
tires | -0.095 |
chess | -0.095 |
Redd | -0.094 |
� | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
Appearance | +1.962 |
��極 | +1.820 |
heit | +1.664 |
aneers | +1.622 |
adan | +1.604 |
Neg logit contributions | |
Kubrick | -1.409 |
Redd | -1.239 |
tires | -1.238 |
chess | -1.233 |
� | -1.194 |
Token | b |
Token ID | 65 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
Appearance | +0.459 |
��極 | +0.433 |
heit | +0.394 |
aneers | +0.388 |
adan | +0.381 |
Neg logit contributions | |
Kubrick | -0.294 |
tires | -0.258 |
chess | -0.257 |
Redd | -0.252 |
� | -0.240 |
Token | ] |
Token ID | 60 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Appearance | +0.072 |
��極 | +0.068 |
heit | +0.061 |
aneers | +0.060 |
adan | +0.059 |
Neg logit contributions | |
Kubrick | -0.051 |
tires | -0.045 |
chess | -0.045 |
Redd | -0.044 |
� | -0.042 |
Token | Personal |
Token ID | 30228 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Appearance | +2.199 |
��極 | +2.049 |
heit | +1.873 |
aneers | +1.831 |
adan | +1.811 |
Neg logit contributions | |
Kubrick | -1.429 |
tires | -1.258 |
chess | -1.250 |
Redd | -1.215 |
� | -1.167 |
Token | best |
Token ID | 1266 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Appearance | +0.594 |
��極 | +0.553 |
heit | +0.502 |
aneers | +0.491 |
adan | +0.483 |
Neg logit contributions | |
Kubrick | -0.450 |
tires | -0.399 |
chess | -0.397 |
Redd | -0.392 |
� | -0.376 |
Token | : |
Token ID | 25 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Appearance | +0.023 |
��極 | +0.022 |
heit | +0.020 |
aneers | +0.020 |
adan | +0.019 |
Neg logit contributions | |
Kubrick | -0.016 |
tires | -0.014 |
chess | -0.014 |
Redd | -0.014 |
� | -0.013 |
Token | [/ |
Token ID | 13412 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Appearance | +0.331 |
��極 | +0.308 |
heit | +0.269 |
aneers | +0.263 |
adan | +0.257 |
Neg logit contributions | |
Kubrick | -0.391 |
tires | -0.356 |
chess | -0.356 |
Redd | -0.351 |
Pens | -0.339 |
Token | b |
Token ID | 65 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Appearance | +3.834 |
��極 | +3.377 |
heit | +3.299 |
adan | +3.166 |
aneers | +3.147 |
Neg logit contributions | |
Kubrick | -3.098 |
chess | -2.776 |
tires | -2.748 |
Redd | -2.680 |
� | -2.646 |
Token | ] |
Token ID | 60 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Appearance | +0.619 |
��極 | +0.580 |
heit | +0.526 |
aneers | +0.516 |
adan | +0.508 |
Neg logit contributions | |
Kubrick | -0.450 |
tires | -0.399 |
chess | -0.398 |
Redd | -0.390 |
� | -0.374 |
Token | 00 |
Token ID | 3571 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Appearance | +1.362 |
��極 | +1.278 |
heit | +1.161 |
aneers | +1.139 |
adan | +1.122 |
Neg logit contributions | |
Kubrick | -0.934 |
tires | -0.826 |
chess | -0.823 |
Redd | -0.807 |
� | -0.774 |
Token | : |
Token ID | 25 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Kubrick | +0.443 |
tires | +0.392 |
chess | +0.390 |
Redd | +0.382 |
� | +0.365 |
Neg logit contributions | |
Appearance | -0.642 |
��極 | -0.608 |
heit | -0.548 |
aneers | -0.539 |
adan | -0.530 |
Token | 47 |
Token ID | 2857 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Appearance | +1.506 |
��極 | +1.348 |
heit | +1.226 |
aneers | +1.196 |
adan | +1.182 |
Neg logit contributions | |
Kubrick | -1.587 |
chess | -1.446 |
tires | -1.438 |
Redd | -1.413 |
� | -1.374 |
Token | conditions |
Token ID | 3403 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Appearance | +0.206 |
��極 | +0.194 |
heit | +0.176 |
aneers | +0.173 |
adan | +0.170 |
Neg logit contributions | |
Kubrick | -0.136 |
tires | -0.120 |
chess | -0.120 |
Redd | -0.117 |
� | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Kubrick | +1.389 |
tires | +1.227 |
chess | +1.224 |
Redd | +1.175 |
Pens | +1.127 |
Neg logit contributions | |
Appearance | -2.128 |
��極 | -2.031 |
heit | -1.827 |
aneers | -1.809 |
adan | -1.765 |
Token | such |
Token ID | 884 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Appearance | +0.030 |
��極 | +0.028 |
heit | +0.026 |
aneers | +0.025 |
adan | +0.025 |
Neg logit contributions | |
Kubrick | -0.022 |
tires | -0.020 |
chess | -0.020 |
Redd | -0.019 |
� | -0.019 |
Token | as |
Token ID | 355 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Kubrick | +0.168 |
tires | +0.148 |
chess | +0.148 |
Redd | +0.144 |
� | +0.138 |
Neg logit contributions | |
Appearance | -0.259 |
��極 | -0.244 |
heit | -0.222 |
aneers | -0.218 |
adan | -0.214 |
Token | going |
Token ID | 1016 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
Appearance | +1.073 |
��極 | +1.001 |
heit | +0.914 |
aneers | +0.891 |
adan | +0.883 |
Neg logit contributions | |
Kubrick | -0.739 |
tires | -0.648 |
chess | -0.647 |
Redd | -0.642 |
� | -0.614 |
Token | through |
Token ID | 832 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Appearance | +0.929 |
��極 | +0.869 |
heit | +0.799 |
aneers | +0.778 |
adan | +0.775 |
Neg logit contributions | |
Kubrick | -0.601 |
tires | -0.524 |
chess | -0.521 |
Redd | -0.520 |
� | -0.494 |
Token | worker |
Token ID | 8383 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Appearance | +4.034 |
��極 | +3.755 |
heit | +3.430 |
aneers | +3.332 |
adan | +3.327 |
Neg logit contributions | |
Kubrick | -2.911 |
Redd | -2.564 |
tires | -2.544 |
chess | -2.532 |
� | -2.448 |
Token | - |
Token ID | 12 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Kubrick | +0.908 |
tires | +0.798 |
chess | +0.787 |
Redd | +0.752 |
� | +0.719 |
Neg logit contributions | |
Appearance | -1.667 |
��極 | -1.596 |
heit | -1.448 |
aneers | -1.436 |
adan | -1.399 |
Token | ret |
Token ID | 1186 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Appearance | +0.511 |
��極 | +0.481 |
heit | +0.432 |
aneers | +0.425 |
adan | +0.414 |
Neg logit contributions | |
Kubrick | -0.410 |
tires | -0.367 |
chess | -0.365 |
Redd | -0.359 |
� | -0.344 |
Token | raining |
Token ID | 24674 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Kubrick | +0.992 |
tires | +0.889 |
chess | +0.869 |
Redd | +0.854 |
� | +0.816 |
Neg logit contributions | |
Appearance | -1.462 |
��極 | -1.393 |
heit | -1.254 |
aneers | -1.236 |
adan | -1.208 |
Token | programs |
Token ID | 4056 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Kubrick | +0.587 |
tires | +0.508 |
chess | +0.506 |
Redd | +0.494 |
� | +0.469 |
Neg logit contributions | |
Appearance | -1.071 |
��極 | -1.013 |
heit | -0.927 |
aneers | -0.913 |
adan | -0.899 |
Token | part |
Token ID | 636 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Kubrick | +1.319 |
tires | +1.183 |
chess | +1.176 |
Redd | +1.119 |
Pens | +1.093 |
Neg logit contributions | |
Appearance | -1.705 |
��極 | -1.608 |
heit | -1.450 |
aneers | -1.434 |
adan | -1.387 |
Token | of |
Token ID | 286 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Kubrick | +0.933 |
tires | +0.802 |
chess | +0.799 |
Redd | +0.776 |
� | +0.737 |
Neg logit contributions | |
Appearance | -1.789 |
��極 | -1.697 |
heit | -1.557 |
aneers | -1.530 |
adan | -1.504 |
Token | HH |
Token ID | 47138 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Kubrick | +0.374 |
tires | +0.330 |
chess | +0.328 |
Redd | +0.317 |
Pens | +0.309 |
Neg logit contributions | |
Appearance | -0.511 |
��極 | -0.487 |
heit | -0.439 |
aneers | -0.431 |
adan | -0.422 |
Token | N |
Token ID | 45 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Kubrick | +0.189 |
tires | +0.167 |
chess | +0.166 |
Redd | +0.162 |
Pens | +0.156 |
Neg logit contributions | |
Appearance | -0.269 |
��極 | -0.255 |
heit | -0.230 |
aneers | -0.226 |
adan | -0.221 |
Token | three |
Token ID | 1115 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
Appearance | +0.424 |
��極 | +0.401 |
heit | +0.365 |
aneers | +0.359 |
adan | +0.353 |
Neg logit contributions | |
Kubrick | -0.260 |
tires | -0.228 |
chess | -0.227 |
Redd | -0.222 |
� | -0.211 |
Token | times |
Token ID | 1661 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
Kubrick | +0.377 |
tires | +0.331 |
chess | +0.330 |
Redd | +0.317 |
Pens | +0.306 |
Neg logit contributions | |
Appearance | -0.608 |
��極 | -0.575 |
heit | -0.525 |
aneers | -0.517 |
adan | -0.506 |
Token | each |
Token ID | 1123 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Kubrick | +3.459 |
chess | +3.019 |
tires | +3.005 |
Pens | +2.749 |
Redd | +2.707 |
Neg logit contributions | |
Appearance | -5.584 |
��極 | -5.368 |
heit | -4.858 |
aneers | -4.826 |
ighthouse | -4.648 |
Token | , |
Token ID | 11 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Kubrick | +0.361 |
tires | +0.318 |
chess | +0.318 |
Redd | +0.306 |
Pens | +0.296 |
Neg logit contributions | |
Appearance | -0.527 |
��極 | -0.502 |
heit | -0.455 |
aneers | -0.448 |
adan | -0.436 |
Token | but |
Token ID | 475 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Kubrick | +1.872 |
tires | +1.632 |
chess | +1.622 |
Redd | +1.550 |
Pens | +1.528 |
Neg logit contributions | |
Appearance | -2.813 |
��極 | -2.710 |
heit | -2.455 |
aneers | -2.415 |
adan | -2.349 |
Token | not |
Token ID | 407 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Kubrick | +1.132 |
tires | +1.000 |
chess | +0.993 |
Redd | +0.958 |
Pens | +0.943 |
Neg logit contributions | |
Appearance | -1.476 |
��極 | -1.410 |
heit | -1.266 |
aneers | -1.245 |
adan | -1.216 |
Token | in |
Token ID | 287 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Kubrick | +1.394 |
tires | +1.229 |
chess | +1.216 |
Redd | +1.173 |
Pens | +1.138 |
Neg logit contributions | |
Appearance | -2.054 |
��極 | -1.951 |
heit | -1.771 |
aneers | -1.736 |
adan | -1.699 |
Token | removed |
Token ID | 4615 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
Kubrick | +0.296 |
tires | +0.261 |
chess | +0.260 |
Redd | +0.253 |
� | +0.242 |
Neg logit contributions | |
Appearance | -0.457 |
��極 | -0.433 |
heit | -0.392 |
aneers | -0.386 |
adan | -0.379 |
Token | . |
Token ID | 13 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Kubrick | +0.625 |
tires | +0.550 |
chess | +0.549 |
Redd | +0.534 |
Pens | +0.511 |
Neg logit contributions | |
Appearance | -0.964 |
��極 | -0.912 |
heit | -0.828 |
aneers | -0.814 |
adan | -0.800 |
Token | Thus |
Token ID | 6660 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Kubrick | +0.292 |
tires | +0.259 |
chess | +0.259 |
Redd | +0.255 |
� | +0.245 |
Neg logit contributions | |
Appearance | -0.388 |
��極 | -0.362 |
heit | -0.327 |
aneers | -0.321 |
adan | -0.316 |
Token | to |
Token ID | 284 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Appearance | +1.461 |
��極 | +1.342 |
heit | +1.238 |
aneers | +1.211 |
adan | +1.205 |
Neg logit contributions | |
Kubrick | -0.960 |
tires | -0.835 |
Redd | -0.835 |
chess | -0.828 |
� | -0.797 |
Token | include |
Token ID | 2291 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Kubrick | +0.487 |
tires | +0.438 |
chess | +0.437 |
Redd | +0.424 |
Pens | +0.411 |
Neg logit contributions | |
Appearance | -0.589 |
��極 | -0.560 |
heit | -0.499 |
aneers | -0.491 |
adan | -0.479 |
Token | "\ |
Token ID | 37082 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
Appearance | +1.216 |
��極 | +1.127 |
heit | +1.032 |
aneers | +1.010 |
adan | +0.999 |
Neg logit contributions | |
Kubrick | -0.847 |
tires | -0.745 |
chess | -0.740 |
Redd | -0.740 |
� | -0.705 |
Token | :" |
Token ID | 11097 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Kubrick | +3.866 |
tires | +3.506 |
chess | +3.488 |
Redd | +3.357 |
� | +3.261 |
Neg logit contributions | |
Appearance | -4.749 |
��極 | -4.502 |
heit | -4.029 |
aneers | -3.981 |
adan | -3.824 |
Token | you |
Token ID | 345 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Kubrick | +1.651 |
chess | +1.453 |
tires | +1.451 |
Redd | +1.382 |
Pens | +1.333 |
Neg logit contributions | |
Appearance | -2.836 |
��極 | -2.750 |
heit | -2.461 |
aneers | -2.419 |
adan | -2.379 |
Token | have |
Token ID | 423 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Appearance | +0.427 |
��極 | +0.402 |
heit | +0.366 |
aneers | +0.360 |
adan | +0.354 |
Neg logit contributions | |
Kubrick | -0.275 |
tires | -0.241 |
chess | -0.241 |
Redd | -0.236 |
� | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Appearance | +0.509 |
��極 | +0.479 |
heit | +0.437 |
aneers | +0.429 |
adan | +0.422 |
Neg logit contributions | |
Kubrick | -0.325 |
tires | -0.285 |
chess | -0.284 |
Redd | -0.279 |
� | -0.265 |
Token | specify |
Token ID | 11986 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Appearance | +0.115 |
��極 | +0.108 |
heit | +0.097 |
aneers | +0.095 |
adan | +0.093 |
Neg logit contributions | |
Kubrick | -0.093 |
tires | -0.084 |
chess | -0.084 |
Redd | -0.081 |
Pens | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Appearance | +0.010 |
��極 | +0.009 |
heit | +0.008 |
aneers | +0.008 |
adan | +0.008 |
Neg logit contributions | |
Kubrick | -0.007 |
tires | -0.006 |
chess | -0.006 |
Redd | -0.006 |
� | -0.006 |
Token | It |
Token ID | 1026 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
Appearance | +0.203 |
��極 | +0.190 |
heit | +0.170 |
aneers | +0.166 |
adan | +0.163 |
Neg logit contributions | |
Kubrick | -0.186 |
tires | -0.168 |
chess | -0.167 |
Redd | -0.165 |
� | -0.159 |
Token | would |
Token ID | 561 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Appearance | +0.907 |
��極 | +0.858 |
heit | +0.786 |
aneers | +0.773 |
adan | +0.761 |
Neg logit contributions | |
Kubrick | -0.500 |
tires | -0.433 |
chess | -0.431 |
Redd | -0.421 |
� | -0.399 |
Token | be |
Token ID | 307 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Kubrick | +0.243 |
tires | +0.215 |
chess | +0.214 |
Redd | +0.207 |
� | +0.200 |
Neg logit contributions | |
Appearance | -0.370 |
��極 | -0.351 |
heit | -0.317 |
aneers | -0.313 |
adan | -0.306 |
Token | dis |
Token ID | 595 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Appearance | +0.456 |
��極 | +0.427 |
heit | +0.387 |
aneers | +0.380 |
adan | +0.374 |
Neg logit contributions | |
Kubrick | -0.329 |
tires | -0.291 |
chess | -0.291 |
Redd | -0.286 |
� | -0.274 |
Token | pir |
Token ID | 4063 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
Appearance | +0.016 |
��極 | +0.014 |
heit | +0.013 |
aneers | +0.013 |
adan | +0.012 |
Neg logit contributions | |
Kubrick | -0.016 |
tires | -0.014 |
chess | -0.014 |
Redd | -0.014 |
� | -0.013 |
Token | iting |
Token ID | 1780 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Kubrick | +2.806 |
tires | +2.490 |
chess | +2.446 |
Redd | +2.299 |
Pens | +2.260 |
Neg logit contributions | |
Appearance | -5.504 |
��極 | -5.320 |
aneers | -4.756 |
heit | -4.733 |
�� | -4.573 |
Token | if |
Token ID | 611 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
Kubrick | +0.567 |
tires | +0.487 |
chess | +0.486 |
Redd | +0.465 |
� | +0.443 |
Neg logit contributions | |
Appearance | -1.133 |
��極 | -1.081 |
heit | -0.987 |
aneers | -0.977 |
adan | -0.957 |
Token | the |
Token ID | 262 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Appearance | +0.516 |
��極 | +0.484 |
heit | +0.437 |
aneers | +0.429 |
adan | +0.421 |
Neg logit contributions | |
Kubrick | -0.399 |
tires | -0.356 |
chess | -0.355 |
Redd | -0.348 |
� | -0.334 |
Token | book |
Token ID | 1492 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
Kubrick | +0.191 |
tires | +0.168 |
chess | +0.167 |
Redd | +0.162 |
Pens | +0.155 |
Neg logit contributions | |
Appearance | -0.309 |
��極 | -0.294 |
heit | -0.267 |
aneers | -0.263 |
adan | -0.258 |
Token | came |
Token ID | 1625 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
Kubrick | +0.478 |
tires | +0.425 |
chess | +0.419 |
Redd | +0.403 |
Pens | +0.391 |
Neg logit contributions | |
Appearance | -0.724 |
��極 | -0.693 |
heit | -0.624 |
aneers | -0.614 |
adan | -0.602 |
Token | oub |
Token ID | 12944 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Kubrick | +0.070 |
tires | +0.062 |
chess | +0.062 |
Redd | +0.061 |
Pens | +0.058 |
Neg logit contributions | |
Appearance | -0.088 |
��極 | -0.083 |
heit | -0.074 |
aneers | -0.073 |
adan | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Kubrick | +1.003 |
tires | +0.872 |
chess | +0.869 |
Redd | +0.833 |
Pens | +0.801 |
Neg logit contributions | |
Appearance | -1.763 |
��極 | -1.680 |
heit | -1.525 |
aneers | -1.510 |
adan | -1.482 |
Token | who |
Token ID | 508 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Kubrick | +0.258 |
tires | +0.226 |
chess | +0.225 |
Redd | +0.220 |
Pens | +0.210 |
Neg logit contributions | |
Appearance | -0.404 |
��極 | -0.382 |
heit | -0.348 |
aneers | -0.342 |
adan | -0.336 |
Token | won |
Token ID | 1839 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
Appearance | +0.615 |
��極 | +0.578 |
heit | +0.529 |
aneers | +0.520 |
adan | +0.513 |
Neg logit contributions | |
Kubrick | -0.364 |
tires | -0.318 |
chess | -0.317 |
Redd | -0.312 |
� | -0.297 |
Token | three |
Token ID | 1115 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
Appearance | +0.730 |
��極 | +0.689 |
heit | +0.626 |
aneers | +0.615 |
adan | +0.605 |
Neg logit contributions | |
Kubrick | -0.484 |
tires | -0.426 |
chess | -0.425 |
Redd | -0.416 |
Pens | -0.397 |
Token | times |
Token ID | 1661 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
Kubrick | +0.367 |
tires | +0.324 |
chess | +0.324 |
Redd | +0.313 |
Pens | +0.303 |
Neg logit contributions | |
Appearance | -0.525 |
��極 | -0.497 |
heit | -0.451 |
aneers | -0.443 |
adan | -0.435 |
Token | for |
Token ID | 329 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Kubrick | +2.884 |
chess | +2.477 |
tires | +2.476 |
Pens | +2.276 |
Redd | +2.263 |
Neg logit contributions | |
Appearance | -5.321 |
��極 | -5.132 |
heit | -4.666 |
aneers | -4.621 |
adan | -4.498 |
Token | Monk |
Token ID | 28854 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Kubrick | +0.830 |
chess | +0.736 |
tires | +0.735 |
Redd | +0.714 |
Pens | +0.694 |
Neg logit contributions | |
Appearance | -1.038 |
��極 | -0.988 |
heit | -0.886 |
aneers | -0.872 |
adan | -0.855 |
Token | . |
Token ID | 13 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
Kubrick | +1.412 |
tires | +1.239 |
chess | +1.231 |
Redd | +1.173 |
Pens | +1.139 |
Neg logit contributions | |
Appearance | -2.224 |
��極 | -2.139 |
heit | -1.913 |
aneers | -1.906 |
adan | -1.857 |
Token | ( |
Token ID | 357 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Kubrick | +0.332 |
tires | +0.293 |
chess | +0.292 |
Redd | +0.287 |
Pens | +0.276 |
Neg logit contributions | |
Appearance | -0.420 |
��極 | -0.399 |
heit | -0.358 |
aneers | -0.352 |
adan | -0.346 |
Token | Fun |
Token ID | 24629 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Kubrick | +0.146 |
tires | +0.131 |
chess | +0.130 |
Redd | +0.129 |
� | +0.123 |
Neg logit contributions | |
Appearance | -0.168 |
��極 | -0.158 |
heit | -0.141 |
aneers | -0.139 |
adan | -0.135 |
Token | Reuters |
Token ID | 8428 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Appearance | +1.627 |
��極 | +1.519 |
heit | +1.378 |
aneers | +1.348 |
adan | +1.332 |
Neg logit contributions | |
Kubrick | -1.237 |
tires | -1.099 |
chess | -1.097 |
Redd | -1.080 |
� | -1.034 |
Token | in |
Token ID | 287 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Appearance | +0.144 |
��極 | +0.134 |
heit | +0.121 |
aneers | +0.119 |
adan | +0.117 |
Neg logit contributions | |
Kubrick | -0.115 |
tires | -0.103 |
chess | -0.103 |
Redd | -0.101 |
� | -0.097 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Appearance | +0.816 |
��極 | +0.764 |
heit | +0.696 |
aneers | +0.681 |
adan | +0.673 |
Neg logit contributions | |
Kubrick | -0.559 |
tires | -0.493 |
chess | -0.492 |
Redd | -0.484 |
� | -0.462 |
Token | during |
Token ID | 1141 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Appearance | +0.267 |
��極 | +0.252 |
heit | +0.229 |
aneers | +0.225 |
adan | +0.221 |
Neg logit contributions | |
Kubrick | -0.172 |
tires | -0.151 |
chess | -0.150 |
Redd | -0.147 |
� | -0.140 |
Token | Operation |
Token ID | 14680 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Kubrick | +0.300 |
tires | +0.267 |
chess | +0.266 |
Redd | +0.256 |
Pens | +0.248 |
Neg logit contributions | |
Appearance | -0.433 |
��極 | -0.412 |
heit | -0.370 |
aneers | -0.366 |
adan | -0.356 |
Token | Cast |
Token ID | 5833 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
Appearance | +0.980 |
��極 | +0.914 |
heit | +0.816 |
aneers | +0.798 |
adan | +0.783 |
Neg logit contributions | |
Kubrick | -0.925 |
tires | -0.834 |
chess | -0.832 |
Redd | -0.818 |
� | -0.789 |
Token | Lead |
Token ID | 20116 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Kubrick | +3.316 |
chess | +2.989 |
tires | +2.951 |
Redd | +2.856 |
Pens | +2.816 |
Neg logit contributions | |
Appearance | -4.168 |
��極 | -4.008 |
heit | -3.608 |
aneers | -3.548 |
�� | -3.390 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Kubrick | +0.092 |
tires | +0.081 |
chess | +0.081 |
Redd | +0.078 |
� | +0.075 |
Neg logit contributions | |
Appearance | -0.148 |
��極 | -0.141 |
heit | -0.128 |
aneers | -0.126 |
adan | -0.123 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Kubrick | +0.128 |
tires | +0.113 |
chess | +0.113 |
Redd | +0.110 |
� | +0.105 |
Neg logit contributions | |
Appearance | -0.184 |
��極 | -0.173 |
heit | -0.157 |
aneers | -0.154 |
adan | -0.152 |
Token | Winter |
Token ID | 35376 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Appearance | +0.197 |
��極 | +0.184 |
heit | +0.165 |
aneers | +0.162 |
adan | +0.158 |
Neg logit contributions | |
Kubrick | -0.168 |
tires | -0.151 |
chess | -0.151 |
Redd | -0.149 |
� | -0.143 |
Token | in |
Token ID | 287 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Appearance | +1.121 |
��極 | +1.053 |
heit | +0.956 |
aneers | +0.938 |
adan | +0.923 |
Neg logit contributions | |
Kubrick | -0.778 |
tires | -0.687 |
chess | -0.685 |
Redd | -0.672 |
� | -0.643 |
Token | went |
Token ID | 1816 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
Kubrick | +0.620 |
tires | +0.552 |
chess | +0.549 |
Redd | +0.532 |
� | +0.513 |
Neg logit contributions | |
Appearance | -0.857 |
��極 | -0.808 |
heit | -0.727 |
aneers | -0.717 |
adan | -0.700 |
Token | through |
Token ID | 832 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
Kubrick | +0.629 |
chess | +0.555 |
tires | +0.555 |
Redd | +0.536 |
� | +0.516 |
Neg logit contributions | |
Appearance | -0.958 |
��極 | -0.909 |
heit | -0.821 |
aneers | -0.810 |
adan | -0.791 |
Token | weekly |
Token ID | 10273 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Appearance | +3.805 |
��極 | +3.507 |
heit | +3.217 |
aneers | +3.116 |
adan | +3.108 |
Neg logit contributions | |
Kubrick | -2.921 |
Redd | -2.603 |
chess | -2.584 |
tires | -2.583 |
� | -2.485 |
Token | " |
Token ID | 366 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Kubrick | +0.199 |
tires | +0.176 |
chess | +0.176 |
Redd | +0.172 |
� | +0.164 |
Neg logit contributions | |
Appearance | -0.293 |
��極 | -0.276 |
heit | -0.250 |
aneers | -0.246 |
adan | -0.242 |
Token | re |
Token ID | 260 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Kubrick | +1.071 |
tires | +0.968 |
chess | +0.965 |
Redd | +0.959 |
� | +0.919 |
Neg logit contributions | |
Appearance | -1.198 |
��極 | -1.132 |
heit | -0.996 |
aneers | -0.979 |
adan | -0.954 |
Token | par |
Token ID | 1845 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
Kubrick | +0.925 |
tires | +0.841 |
chess | +0.837 |
Redd | +0.826 |
Pens | +0.796 |
Neg logit contributions | |
Appearance | -0.889 |
��極 | -0.835 |
heit | -0.734 |
aneers | -0.718 |
adan | -0.699 |
Token | ative |
Token ID | 876 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Kubrick | +3.378 |
tires | +3.102 |
chess | +3.073 |
Redd | +2.919 |
Pens | +2.891 |
Neg logit contributions | |
Appearance | -4.018 |
��極 | -3.868 |
heit | -3.396 |
aneers | -3.310 |
�� | -3.253 |
Token | therapy |
Token ID | 9102 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Kubrick | +1.374 |
chess | +1.206 |
tires | +1.196 |
Redd | +1.143 |
� | +1.096 |
Neg logit contributions | |
Appearance | -2.444 |
��極 | -2.329 |
heit | -2.128 |
aneers | -2.092 |
adan | -2.046 |
Token | " |
Token ID | 1 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Kubrick | +1.327 |
tires | +1.149 |
chess | +1.144 |
Redd | +1.095 |
Pens | +1.041 |
Neg logit contributions | |
Appearance | -2.705 |
��極 | -2.579 |
heit | -2.360 |
aneers | -2.321 |
adan | -2.289 |
Token | sessions |
Token ID | 10991 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Kubrick | +0.236 |
tires | +0.205 |
chess | +0.205 |
Redd | +0.200 |
� | +0.191 |
Neg logit contributions | |
Appearance | -0.411 |
��極 | -0.388 |
heit | -0.355 |
aneers | -0.349 |
adan | -0.344 |
Token | through |
Token ID | 832 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Kubrick | +0.478 |
tires | +0.420 |
chess | +0.417 |
Redd | +0.400 |
Pens | +0.385 |
Neg logit contributions | |
Appearance | -0.809 |
��極 | -0.771 |
heit | -0.698 |
aneers | -0.688 |
adan | -0.675 |
Token | = |
Token ID | 796 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
Kubrick | +0.168 |
tires | +0.149 |
chess | +0.148 |
Redd | +0.145 |
� | +0.139 |
Neg logit contributions | |
Appearance | -0.250 |
��極 | -0.236 |
heit | -0.214 |
aneers | -0.210 |
adan | -0.207 |
Token | ($ |
Token ID | 7198 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Appearance | +0.777 |
��極 | +0.728 |
heit | +0.657 |
aneers | +0.644 |
adan | +0.632 |
Neg logit contributions | |
Kubrick | -0.616 |
tires | -0.550 |
chess | -0.548 |
Redd | -0.538 |
� | -0.516 |
Token | text |
Token ID | 5239 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Kubrick | +0.091 |
tires | +0.082 |
chess | +0.081 |
Redd | +0.080 |
� | +0.076 |
Neg logit contributions | |
Appearance | -0.117 |
��極 | -0.110 |
heit | -0.099 |
aneers | -0.098 |
adan | -0.095 |
Token | - |
Token ID | 532 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Kubrick | +0.240 |
chess | +0.214 |
tires | +0.213 |
Redd | +0.208 |
Pens | +0.200 |
Neg logit contributions | |
Appearance | -0.339 |
��極 | -0.322 |
heit | -0.290 |
aneers | -0.285 |
adan | -0.280 |
Token | split |
Token ID | 35312 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
Kubrick | +0.820 |
chess | +0.743 |
tires | +0.737 |
Redd | +0.723 |
Pens | +0.695 |
Neg logit contributions | |
Appearance | -0.968 |
��極 | -0.923 |
heit | -0.823 |
aneers | -0.809 |
adan | -0.786 |
Token | "\ |
Token ID | 37082 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
Appearance | +0.715 |
��極 | +0.673 |
heit | +0.612 |
aneers | +0.601 |
adan | +0.593 |
Neg logit contributions | |
Kubrick | -0.449 |
tires | -0.393 |
chess | -0.391 |
Redd | -0.383 |
� | -0.368 |
Token | r |
Token ID | 81 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Kubrick | +3.055 |
tires | +2.754 |
chess | +2.748 |
Redd | +2.701 |
� | +2.559 |
Neg logit contributions | |
Appearance | -4.313 |
��極 | -4.134 |
heit | -3.723 |
aneers | -3.681 |
adan | -3.558 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Appearance | +0.336 |
��極 | +0.318 |
heit | +0.288 |
aneers | +0.283 |
adan | +0.278 |
Neg logit contributions | |
Kubrick | -0.223 |
tires | -0.197 |
chess | -0.196 |
Redd | -0.192 |
� | -0.183 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Kubrick | +1.000 |
tires | +0.883 |
chess | +0.876 |
Redd | +0.860 |
� | +0.818 |
Neg logit contributions | |
Appearance | -1.543 |
��極 | -1.476 |
heit | -1.323 |
aneers | -1.303 |
adan | -1.279 |
Token | ") |
Token ID | 4943 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Kubrick | +0.822 |
tires | +0.723 |
chess | +0.722 |
Redd | +0.709 |
� | +0.675 |
Neg logit contributions | |
Appearance | -1.332 |
��極 | -1.266 |
heit | -1.144 |
aneers | -1.128 |
adan | -1.108 |
Token | $ |
Token ID | 720 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Kubrick | +0.156 |
chess | +0.138 |
tires | +0.138 |
Redd | +0.133 |
Pens | +0.129 |
Neg logit contributions | |
Appearance | -0.225 |
��極 | -0.213 |
heit | -0.193 |
aneers | -0.190 |
adan | -0.186 |
Token | _ |
Token ID | 62 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
Kubrick | +0.103 |
tires | +0.089 |
chess | +0.089 |
Redd | +0.087 |
� | +0.083 |
Neg logit contributions | |
Appearance | -0.176 |
��極 | -0.164 |
heit | -0.152 |
aneers | -0.149 |
adan | -0.147 |
Token | images |
Token ID | 17566 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Kubrick | +0.553 |
tires | +0.501 |
chess | +0.497 |
Redd | +0.490 |
� | +0.471 |
Neg logit contributions | |
Appearance | -0.586 |
��極 | -0.552 |
heit | -0.487 |
aneers | -0.476 |
adan | -0.465 |
Token | ( |
Token ID | 357 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Kubrick | +1.044 |
tires | +0.865 |
chess | +0.861 |
Redd | +0.831 |
� | +0.774 |
Neg logit contributions | |
Appearance | -2.711 |
��極 | -2.587 |
heit | -2.388 |
aneers | -2.354 |
adan | -2.323 |
Token | args |
Token ID | 26498 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
Kubrick | +0.860 |
tires | +0.766 |
chess | +0.765 |
Redd | +0.759 |
� | +0.731 |
Neg logit contributions | |
Appearance | -1.050 |
��極 | -0.977 |
heit | -0.882 |
aneers | -0.866 |
adan | -0.850 |
Token | [ |
Token ID | 685 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Appearance | +0.719 |
��極 | +0.673 |
heit | +0.626 |
aneers | +0.619 |
ighthouse | +0.609 |
Neg logit contributions | |
Kubrick | -0.287 |
tires | -0.238 |
chess | -0.236 |
Redd | -0.234 |
� | -0.220 |
Token | " |
Token ID | 366 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
Kubrick | +0.894 |
tires | +0.779 |
chess | +0.778 |
Redd | +0.753 |
Pens | +0.718 |
Neg logit contributions | |
Appearance | -1.570 |
��極 | -1.487 |
heit | -1.361 |
aneers | -1.344 |
adan | -1.317 |
Token | images |
Token ID | 17566 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Kubrick | +3.237 |
tires | +2.968 |
chess | +2.894 |
Redd | +2.850 |
nails | +2.682 |
Neg logit contributions | |
Appearance | -4.076 |
��極 | -4.025 |
heit | -3.431 |
aneers | -3.336 |
�� | -3.287 |
Token | " |
Token ID | 1 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Kubrick | +1.077 |
tires | +0.939 |
chess | +0.930 |
Redd | +0.903 |
Pens | +0.855 |
Neg logit contributions | |
Appearance | -1.984 |
��極 | -1.929 |
heit | -1.721 |
aneers | -1.699 |
�� | -1.666 |
Token | ] |
Token ID | 2361 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Kubrick | +1.292 |
tires | +1.132 |
chess | +1.126 |
Redd | +1.077 |
Pens | +1.035 |
Neg logit contributions | |
Appearance | -2.268 |
��極 | -2.189 |
heit | -1.974 |
aneers | -1.934 |
adan | -1.897 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Appearance | +1.828 |
��極 | +1.696 |
heit | +1.567 |
aneers | +1.544 |
adan | +1.516 |
Neg logit contributions | |
Kubrick | -1.095 |
tires | -0.947 |
chess | -0.939 |
Redd | -0.932 |
Pens | -0.885 |
Token | : |
Token ID | 1058 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
Kubrick | +0.090 |
tires | +0.080 |
chess | +0.080 |
Redd | +0.078 |
Pens | +0.075 |
Neg logit contributions | |
Appearance | -0.121 |
��極 | -0.114 |
heit | -0.103 |
aneers | -0.101 |
adan | -0.099 |
Token | ling |
Token ID | 1359 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
Kubrick | +1.003 |
tires | +0.895 |
chess | +0.893 |
Redd | +0.876 |
� | +0.841 |
Neg logit contributions | |
Appearance | -1.268 |
��極 | -1.190 |
heit | -1.072 |
aneers | -1.051 |
adan | -1.033 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Appearance | +0.945 |
��極 | +0.881 |
heit | +0.806 |
aneers | +0.789 |
adan | +0.783 |
Neg logit contributions | |
Kubrick | -0.594 |
tires | -0.516 |
chess | -0.515 |
Redd | -0.509 |
� | -0.485 |
Token | � |
Token ID | 564 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Kubrick | +0.282 |
tires | +0.254 |
chess | +0.253 |
Redd | +0.249 |
Pens | +0.241 |
Neg logit contributions | |
Appearance | -0.277 |
��極 | -0.260 |
heit | -0.230 |
aneers | -0.225 |
adan | -0.220 |
Token | � |
Token ID | 250 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Appearance | +0.122 |
��極 | +0.113 |
heit | +0.101 |
aneers | +0.099 |
adan | +0.097 |
Neg logit contributions | |
Kubrick | -0.120 |
tires | -0.108 |
chess | -0.108 |
Redd | -0.106 |
� | -0.102 |
Token | Six |
Token ID | 21447 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
Kubrick | +0.158 |
tires | +0.143 |
chess | +0.142 |
Redd | +0.140 |
� | +0.135 |
Neg logit contributions | |
Appearance | -0.154 |
��極 | -0.143 |
heit | -0.127 |
aneers | -0.124 |
adan | -0.121 |
Token | times |
Token ID | 1661 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
Appearance | +0.996 |
��極 | +0.937 |
heit | +0.856 |
aneers | +0.841 |
adan | +0.830 |
Neg logit contributions | |
Kubrick | -0.604 |
tires | -0.524 |
chess | -0.524 |
Redd | -0.516 |
� | -0.490 |
Token | tonight |
Token ID | 9975 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Kubrick | +2.830 |
tires | +2.453 |
chess | +2.450 |
Redd | +2.328 |
Pens | +2.295 |
Neg logit contributions | |
Appearance | -4.537 |
��極 | -4.343 |
heit | -3.910 |
aneers | -3.877 |
adan | -3.770 |
Token | I |
Token ID | 314 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Kubrick | +1.120 |
chess | +0.977 |
tires | +0.976 |
Redd | +0.947 |
Pens | +0.910 |
Neg logit contributions | |
Appearance | -1.815 |
��極 | -1.723 |
heit | -1.565 |
aneers | -1.542 |
adan | -1.507 |
Token | have |
Token ID | 423 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
Kubrick | +0.020 |
tires | +0.018 |
chess | +0.017 |
Redd | +0.017 |
� | +0.016 |
Neg logit contributions | |
Appearance | -0.028 |
��極 | -0.026 |
heit | -0.023 |
aneers | -0.023 |
adan | -0.023 |
Token | said |
Token ID | 531 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Kubrick | +0.402 |
tires | +0.356 |
chess | +0.354 |
Redd | +0.347 |
� | +0.332 |
Neg logit contributions | |
Appearance | -0.574 |
��極 | -0.540 |
heit | -0.490 |
aneers | -0.481 |
adan | -0.473 |
Token | to |
Token ID | 284 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
Appearance | +0.331 |
��極 | +0.311 |
heit | +0.283 |
aneers | +0.278 |
adan | +0.273 |
Neg logit contributions | |
Kubrick | -0.224 |
tires | -0.198 |
chess | -0.197 |
Redd | -0.194 |
� | -0.185 |
Token | � |
Token ID | 122 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Kubrick | +1.313 |
tires | +1.199 |
chess | +1.193 |
Redd | +1.177 |
� | +1.138 |
Neg logit contributions | |
Appearance | -1.163 |
��極 | -1.071 |
heit | -0.953 |
aneers | -0.927 |
adan | -0.907 |
Token | ek |
Token ID | 988 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Kubrick | +0.178 |
tires | +0.166 |
chess | +0.165 |
Redd | +0.163 |
� | +0.159 |
Neg logit contributions | |
Appearance | -0.090 |
��極 | -0.080 |
heit | -0.066 |
aneers | -0.063 |
adan | -0.062 |
Token | has |
Token ID | 468 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Appearance | +0.262 |
��極 | +0.246 |
heit | +0.223 |
aneers | +0.220 |
adan | +0.216 |
Neg logit contributions | |
Kubrick | -0.175 |
tires | -0.155 |
chess | -0.154 |
Redd | -0.151 |
� | -0.144 |
Token | said |
Token ID | 531 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Kubrick | +0.080 |
tires | +0.071 |
chess | +0.071 |
Redd | +0.070 |
� | +0.067 |
Neg logit contributions | |
Appearance | -0.105 |
��極 | -0.098 |
heit | -0.089 |
aneers | -0.087 |
adan | -0.086 |
Token | numerous |
Token ID | 6409 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
Kubrick | +0.270 |
tires | +0.236 |
chess | +0.235 |
Redd | +0.229 |
� | +0.218 |
Neg logit contributions | |
Appearance | -0.460 |
��極 | -0.435 |
heit | -0.397 |
aneers | -0.391 |
adan | -0.384 |
Token | times |
Token ID | 1661 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
Kubrick | +0.391 |
tires | +0.333 |
chess | +0.331 |
Redd | +0.319 |
� | +0.302 |
Neg logit contributions | |
Appearance | -0.867 |
��極 | -0.825 |
heit | -0.759 |
aneers | -0.748 |
adan | -0.736 |
Token | , |
Token ID | 11 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
Kubrick | +2.445 |
tires | +2.127 |
chess | +2.111 |
Redd | +1.988 |
� | +1.941 |
Neg logit contributions | |
Appearance | -4.604 |
��極 | -4.401 |
heit | -3.954 |
aneers | -3.948 |
adan | -3.852 |
Token | it |
Token ID | 340 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
Kubrick | +0.620 |
tires | +0.545 |
chess | +0.544 |
Redd | +0.530 |
� | +0.507 |
Neg logit contributions | |
Appearance | -0.959 |
��極 | -0.907 |
heit | -0.824 |
aneers | -0.811 |
adan | -0.796 |
Token | � |
Token ID | 447 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
Kubrick | +0.525 |
tires | +0.455 |
chess | +0.449 |
Redd | +0.435 |
� | +0.419 |
Neg logit contributions | |
Appearance | -1.015 |
��極 | -0.965 |
heit | -0.883 |
aneers | -0.870 |
adan | -0.855 |
Token | � |
Token ID | 247 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Kubrick | +0.745 |
tires | +0.679 |
chess | +0.676 |
Redd | +0.668 |
� | +0.647 |
Neg logit contributions | |
Appearance | -0.642 |
��極 | -0.589 |
heit | -0.519 |
aneers | -0.512 |
adan | -0.497 |
Token | s |
Token ID | 82 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Kubrick | +0.367 |
tires | +0.326 |
chess | +0.322 |
Redd | +0.315 |
Pens | +0.303 |
Neg logit contributions | |
Appearance | -0.544 |
��極 | -0.513 |
heit | -0.464 |
aneers | -0.457 |
adan | -0.448 |
Token | � |
Token ID | 447 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
Kubrick | +0.100 |
tires | +0.088 |
chess | +0.088 |
Redd | +0.086 |
� | +0.082 |
Neg logit contributions | |
Appearance | -0.154 |
��極 | -0.145 |
heit | -0.132 |
aneers | -0.130 |
adan | -0.128 |
Token | � |
Token ID | 251 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Appearance | +0.404 |
��極 | +0.372 |
heit | +0.327 |
aneers | +0.321 |
adan | +0.313 |
Neg logit contributions | |
Kubrick | -0.469 |
tires | -0.427 |
chess | -0.426 |
Redd | -0.420 |
� | -0.407 |
Token | even |
Token ID | 772 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Kubrick | +0.323 |
tires | +0.286 |
chess | +0.285 |
Redd | +0.278 |
� | +0.266 |
Neg logit contributions | |
Appearance | -0.463 |
��極 | -0.437 |
heit | -0.395 |
aneers | -0.389 |
adan | -0.382 |
Token | when |
Token ID | 618 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Kubrick | +0.142 |
tires | +0.125 |
chess | +0.124 |
Redd | +0.121 |
� | +0.116 |
Neg logit contributions | |
Appearance | -0.222 |
��極 | -0.209 |
heit | -0.190 |
aneers | -0.187 |
adan | -0.184 |
Token | the |
Token ID | 262 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Kubrick | +0.142 |
tires | +0.127 |
chess | +0.126 |
Redd | +0.123 |
Pens | +0.118 |
Neg logit contributions | |
Appearance | -0.192 |
��極 | -0.181 |
heit | -0.163 |
aneers | -0.160 |
adan | -0.157 |
Token | content |
Token ID | 2695 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
Kubrick | +0.329 |
tires | +0.292 |
chess | +0.291 |
Redd | +0.284 |
Pens | +0.272 |
Neg logit contributions | |
Appearance | -0.467 |
��極 | -0.441 |
heit | -0.399 |
aneers | -0.392 |
adan | -0.385 |
Token | remains |
Token ID | 3793 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
Kubrick | +2.455 |
tires | +2.179 |
chess | +2.131 |
Redd | +2.013 |
� | +1.965 |
Neg logit contributions | |
Appearance | -4.558 |
��極 | -4.366 |
heit | -3.938 |
aneers | -3.907 |
adan | -3.819 |
Token | slightly |
Token ID | 4622 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
Kubrick | +1.789 |
tires | +1.593 |
chess | +1.575 |
Redd | +1.530 |
Pens | +1.467 |
Neg logit contributions | |
Appearance | -2.508 |
��極 | -2.377 |
heit | -2.137 |
aneers | -2.115 |
adan | -2.071 |
Token | vacant |
Token ID | 23957 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Appearance | +0.662 |
��極 | +0.619 |
heit | +0.563 |
aneers | +0.550 |
adan | +0.542 |
Neg logit contributions | |
Kubrick | -0.477 |
chess | -0.423 |
tires | -0.421 |
Redd | -0.418 |
� | -0.400 |
Token | . |
Token ID | 13 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Kubrick | +1.141 |
tires | +0.998 |
chess | +0.990 |
Redd | +0.943 |
Pens | +0.912 |
Neg logit contributions | |
Appearance | -1.899 |
��極 | -1.818 |
heit | -1.641 |
aneers | -1.634 |
adan | -1.591 |
Token | � |
Token ID | 564 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Kubrick | +0.507 |
tires | +0.451 |
chess | +0.450 |
Redd | +0.442 |
Pens | +0.430 |
Neg logit contributions | |
Appearance | -0.567 |
��極 | -0.541 |
heit | -0.481 |
aneers | -0.472 |
adan | -0.463 |
Token | gender |
Token ID | 5279 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Kubrick | +0.186 |
tires | +0.168 |
chess | +0.168 |
Redd | +0.164 |
Pens | +0.159 |
Neg logit contributions | |
Appearance | -0.198 |
��極 | -0.187 |
heit | -0.165 |
aneers | -0.163 |
adan | -0.159 |
Token | to |
Token ID | 284 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
Kubrick | +0.115 |
chess | +0.101 |
tires | +0.101 |
Redd | +0.098 |
� | +0.094 |
Neg logit contributions | |
Appearance | -0.188 |
��極 | -0.180 |
heit | -0.163 |
aneers | -0.161 |
adan | -0.157 |
Token | score |
Token ID | 4776 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Kubrick | +0.685 |
tires | +0.610 |
chess | +0.608 |
Redd | +0.594 |
Pens | +0.569 |
Neg logit contributions | |
Appearance | -0.916 |
��極 | -0.864 |
heit | -0.780 |
aneers | -0.765 |
adan | -0.749 |
Token | a |
Token ID | 257 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Appearance | +0.934 |
��極 | +0.874 |
heit | +0.791 |
aneers | +0.775 |
adan | +0.762 |
Neg logit contributions | |
Kubrick | -0.718 |
tires | -0.638 |
chess | -0.636 |
Redd | -0.625 |
� | -0.601 |
Token | de |
Token ID | 390 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Kubrick | +0.358 |
tires | +0.321 |
chess | +0.321 |
Redd | +0.311 |
Pens | +0.300 |
Neg logit contributions | |
Appearance | -0.475 |
��極 | -0.449 |
heit | -0.404 |
aneers | -0.398 |
adan | -0.390 |
Token | cept |
Token ID | 984 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
Kubrick | +0.835 |
chess | +0.763 |
tires | +0.763 |
Redd | +0.747 |
Pens | +0.725 |
Neg logit contributions | |
Appearance | -0.786 |
��極 | -0.729 |
heit | -0.645 |
aneers | -0.631 |
adan | -0.622 |
Token | ively |
Token ID | 2280 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Kubrick | +3.255 |
chess | +2.970 |
tires | +2.966 |
Redd | +2.842 |
� | +2.798 |
Neg logit contributions | |
Appearance | -3.675 |
��極 | -3.508 |
heit | -3.141 |
aneers | -3.034 |
�� | -2.919 |
Token | easy |
Token ID | 2562 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Kubrick | +0.476 |
tires | +0.422 |
chess | +0.420 |
Redd | +0.410 |
Pens | +0.392 |
Neg logit contributions | |
Appearance | -0.688 |
��極 | -0.648 |
heit | -0.588 |
aneers | -0.578 |
adan | -0.568 |
Token | point |
Token ID | 966 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Appearance | +1.232 |
��極 | +1.152 |
heit | +1.036 |
aneers | +1.015 |
adan | +0.997 |
Neg logit contributions | |
Kubrick | -1.027 |
tires | -0.918 |
chess | -0.915 |
Redd | -0.900 |
� | -0.866 |
Token | . |
Token ID | 13 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Appearance | +0.152 |
��極 | +0.144 |
heit | +0.131 |
aneers | +0.129 |
adan | +0.126 |
Neg logit contributions | |
Kubrick | -0.096 |
tires | -0.084 |
chess | -0.084 |
Redd | -0.081 |
Pens | -0.078 |
Token | Worse |
Token ID | 36855 |
Feature activation | -2.74e-03 |
Pos logit contributions | |
Kubrick | +0.063 |
tires | +0.056 |
chess | +0.056 |
Redd | +0.055 |
Pens | +0.053 |
Neg logit contributions | |
Appearance | -0.070 |
��極 | -0.067 |
heit | -0.060 |
aneers | -0.059 |
adan | -0.057 |
Token | Getty |
Token ID | 6633 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Appearance | +1.300 |
��極 | +1.210 |
heit | +1.077 |
aneers | +1.054 |
adan | +1.031 |
Neg logit contributions | |
Kubrick | -1.285 |
tires | -1.162 |
chess | -1.159 |
Redd | -1.141 |
� | -1.101 |
Token | Images |
Token ID | 5382 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Kubrick | +1.398 |
chess | +1.259 |
tires | +1.258 |
Redd | +1.220 |
Pens | +1.195 |
Neg logit contributions | |
Appearance | -1.503 |
��極 | -1.417 |
heit | -1.256 |
aneers | -1.230 |
adan | -1.207 |
Token | ) |
Token ID | 8 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Kubrick | +1.209 |
chess | +1.068 |
tires | +1.068 |
Redd | +1.042 |
Pens | +0.999 |
Neg logit contributions | |
Appearance | -1.749 |
��極 | -1.649 |
heit | -1.492 |
aneers | -1.469 |
adan | -1.443 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Kubrick | +0.778 |
tires | +0.695 |
chess | +0.692 |
Redd | +0.673 |
Pens | +0.662 |
Neg logit contributions | |
Appearance | -0.968 |
��極 | -0.929 |
heit | -0.831 |
aneers | -0.815 |
adan | -0.799 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Kubrick | +0.716 |
tires | +0.618 |
chess | +0.614 |
Redd | +0.593 |
Pens | +0.575 |
Neg logit contributions | |
Appearance | -1.444 |
��極 | -1.391 |
heit | -1.263 |
aneers | -1.239 |
adan | -1.223 |
Token | Sen |
Token ID | 2311 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
Kubrick | +1.129 |
tires | +1.028 |
chess | +1.022 |
Redd | +0.990 |
Pens | +0.975 |
Neg logit contributions | |
Appearance | -1.150 |
��極 | -1.097 |
heit | -0.969 |
aneers | -0.949 |
adan | -0.933 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Kubrick | +2.583 |
tires | +2.275 |
chess | +2.213 |
Redd | +2.137 |
Pens | +2.071 |
Neg logit contributions | |
Appearance | -4.405 |
��極 | -4.307 |
heit | -3.820 |
aneers | -3.772 |
�� | -3.693 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Kubrick | +1.113 |
tires | +0.995 |
chess | +0.987 |
Redd | +0.953 |
Pens | +0.929 |
Neg logit contributions | |
Appearance | -1.513 |
��極 | -1.441 |
heit | -1.302 |
aneers | -1.275 |
adan | -1.246 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Kubrick | +0.830 |
tires | +0.740 |
chess | +0.731 |
Redd | +0.707 |
Pens | +0.689 |
Neg logit contributions | |
Appearance | -1.234 |
��極 | -1.183 |
heit | -1.060 |
aneers | -1.041 |
adan | -1.016 |
Token | of |
Token ID | 286 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
Kubrick | +0.752 |
tires | +0.656 |
chess | +0.650 |
Redd | +0.629 |
Pens | +0.603 |
Neg logit contributions | |
Appearance | -1.380 |
��極 | -1.314 |
heit | -1.200 |
aneers | -1.180 |
adan | -1.165 |
Token | Alabama |
Token ID | 9266 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
Kubrick | +0.390 |
tires | +0.348 |
chess | +0.347 |
Redd | +0.335 |
Pens | +0.324 |
Neg logit contributions | |
Appearance | -0.625 |
��極 | -0.598 |
heit | -0.541 |
aneers | -0.535 |
adan | -0.523 |
Token | the |
Token ID | 262 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
Kubrick | +1.188 |
tires | +1.048 |
chess | +1.044 |
Redd | +0.998 |
Pens | +0.972 |
Neg logit contributions | |
Appearance | -1.858 |
��極 | -1.777 |
heit | -1.595 |
aneers | -1.562 |
adan | -1.541 |
Token | House |
Token ID | 2097 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Kubrick | +0.539 |
tires | +0.474 |
chess | +0.473 |
Redd | +0.463 |
� | +0.442 |
Neg logit contributions | |
Appearance | -0.836 |
��極 | -0.788 |
heit | -0.717 |
aneers | -0.705 |
adan | -0.694 |
Token | by |
Token ID | 416 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Kubrick | +1.681 |
tires | +1.488 |
chess | +1.484 |
Redd | +1.413 |
Pens | +1.377 |
Neg logit contributions | |
Appearance | -2.658 |
��極 | -2.546 |
heit | -2.289 |
aneers | -2.255 |
adan | -2.212 |
Token | just |
Token ID | 655 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
Kubrick | +0.109 |
tires | +0.096 |
chess | +0.096 |
Redd | +0.094 |
� | +0.090 |
Neg logit contributions | |
Appearance | -0.153 |
��極 | -0.144 |
heit | -0.131 |
aneers | -0.128 |
adan | -0.126 |
Token | one |
Token ID | 530 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
Kubrick | +0.651 |
tires | +0.580 |
chess | +0.577 |
Redd | +0.561 |
Pens | +0.538 |
Neg logit contributions | |
Appearance | -0.931 |
��極 | -0.880 |
heit | -0.796 |
aneers | -0.782 |
adan | -0.767 |
Token | vote |
Token ID | 3015 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
Kubrick | +0.053 |
tires | +0.047 |
chess | +0.047 |
Redd | +0.047 |
� | +0.045 |
Neg logit contributions | |
Appearance | -0.059 |
��極 | -0.054 |
heit | -0.049 |
aneers | -0.048 |
adan | -0.047 |
Token | .) |
Token ID | 2014 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Kubrick | +2.610 |
tires | +2.306 |
chess | +2.296 |
Redd | +2.128 |
� | +2.099 |
Neg logit contributions | |
Appearance | -4.395 |
��極 | -4.240 |
heit | -3.781 |
aneers | -3.686 |
ighthouse | -3.648 |
Token | It |
Token ID | 632 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
Appearance | +0.244 |
��極 | +0.228 |
heit | +0.206 |
aneers | +0.202 |
adan | +0.199 |
Neg logit contributions | |
Kubrick | -0.190 |
tires | -0.170 |
chess | -0.169 |
Redd | -0.166 |
� | -0.160 |
Token | will |
Token ID | 481 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Kubrick | +0.021 |
tires | +0.018 |
chess | +0.018 |
Redd | +0.018 |
� | +0.017 |
Neg logit contributions | |
Appearance | -0.035 |
��極 | -0.033 |
heit | -0.030 |
aneers | -0.030 |
adan | -0.029 |
Token | also |
Token ID | 635 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Kubrick | +0.008 |
tires | +0.007 |
chess | +0.007 |
Redd | +0.007 |
� | +0.007 |
Neg logit contributions | |
Appearance | -0.010 |
��極 | -0.010 |
heit | -0.009 |
aneers | -0.009 |
adan | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
Appearance | +0.626 |
��極 | +0.580 |
heit | +0.529 |
aneers | +0.517 |
adan | +0.512 |
Neg logit contributions | |
Kubrick | -0.497 |
chess | -0.439 |
tires | -0.438 |
Redd | -0.437 |
� | -0.419 |
Token | pun |
Token ID | 4000 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Appearance | +0.143 |
��極 | +0.135 |
heit | +0.123 |
aneers | +0.121 |
adan | +0.119 |
Neg logit contributions | |
Kubrick | -0.089 |
tires | -0.078 |
chess | -0.077 |
Redd | -0.075 |
� | -0.072 |
Token | ks |
Token ID | 591 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
Kubrick | +0.177 |
tires | +0.159 |
chess | +0.158 |
Redd | +0.154 |
Pens | +0.149 |
Neg logit contributions | |
Appearance | -0.214 |
��極 | -0.201 |
heit | -0.179 |
aneers | -0.176 |
adan | -0.172 |
Token | and |
Token ID | 290 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Kubrick | +0.341 |
tires | +0.301 |
chess | +0.299 |
Redd | +0.286 |
Pens | +0.276 |
Neg logit contributions | |
Appearance | -0.540 |
��極 | -0.517 |
heit | -0.465 |
aneers | -0.457 |
adan | -0.449 |
Token | the |
Token ID | 262 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Kubrick | +0.168 |
tires | +0.150 |
chess | +0.149 |
Redd | +0.146 |
� | +0.140 |
Neg logit contributions | |
Appearance | -0.221 |
��極 | -0.209 |
heit | -0.188 |
aneers | -0.185 |
adan | -0.181 |
Token | cycle |
Token ID | 6772 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Appearance | +0.323 |
��極 | +0.305 |
heit | +0.276 |
aneers | +0.271 |
adan | +0.266 |
Neg logit contributions | |
Kubrick | -0.222 |
tires | -0.196 |
chess | -0.196 |
Redd | -0.191 |
� | -0.183 |
Token | continued |
Token ID | 3767 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Kubrick | +0.352 |
tires | +0.305 |
chess | +0.304 |
Redd | +0.294 |
� | +0.280 |
Neg logit contributions | |
Appearance | -0.654 |
��極 | -0.621 |
heit | -0.568 |
aneers | -0.559 |
adan | -0.550 |
Token | . |
Token ID | 13 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
Kubrick | +2.593 |
tires | +2.277 |
chess | +2.261 |
Redd | +2.102 |
Pens | +2.043 |
Neg logit contributions | |
Appearance | -4.419 |
��極 | -4.340 |
heit | -3.817 |
aneers | -3.816 |
�� | -3.727 |
Token | No |
Token ID | 1400 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
Kubrick | +0.715 |
tires | +0.636 |
chess | +0.633 |
Redd | +0.621 |
Pens | +0.604 |
Neg logit contributions | |
Appearance | -0.836 |
��極 | -0.801 |
heit | -0.711 |
aneers | -0.698 |
adan | -0.682 |
Token | one |
Token ID | 530 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Kubrick | +0.623 |
tires | +0.553 |
chess | +0.552 |
Redd | +0.536 |
Pens | +0.516 |
Neg logit contributions | |
Appearance | -0.850 |
��極 | -0.806 |
heit | -0.724 |
aneers | -0.714 |
adan | -0.698 |
Token | was |
Token ID | 373 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
Appearance | +0.109 |
��極 | +0.101 |
heit | +0.093 |
aneers | +0.091 |
adan | +0.090 |
Neg logit contributions | |
Kubrick | -0.075 |
chess | -0.066 |
tires | -0.066 |
Redd | -0.065 |
� | -0.062 |
Token | interested |
Token ID | 4609 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Kubrick | +0.580 |
tires | +0.516 |
chess | +0.513 |
Redd | +0.499 |
� | +0.479 |
Neg logit contributions | |
Appearance | -0.809 |
��極 | -0.763 |
heit | -0.688 |
aneers | -0.680 |
adan | -0.665 |
Token | customers |
Token ID | 4297 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Appearance | +0.655 |
��極 | +0.613 |
heit | +0.553 |
aneers | +0.542 |
adan | +0.532 |
Neg logit contributions | |
Kubrick | -0.526 |
tires | -0.469 |
chess | -0.468 |
Redd | -0.462 |
� | -0.444 |
Token | might |
Token ID | 1244 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Kubrick | +0.629 |
tires | +0.560 |
chess | +0.552 |
Redd | +0.530 |
Pens | +0.512 |
Neg logit contributions | |
Appearance | -1.005 |
��極 | -0.956 |
heit | -0.864 |
aneers | -0.848 |
adan | -0.830 |
Token | need |
Token ID | 761 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Kubrick | +0.579 |
tires | +0.519 |
chess | +0.514 |
Redd | +0.496 |
Pens | +0.479 |
Neg logit contributions | |
Appearance | -0.790 |
��極 | -0.753 |
heit | -0.672 |
aneers | -0.662 |
adan | -0.648 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Kubrick | +0.704 |
tires | +0.623 |
chess | +0.620 |
Redd | +0.603 |
Pens | +0.578 |
Neg logit contributions | |
Appearance | -1.055 |
��極 | -0.996 |
heit | -0.905 |
aneers | -0.889 |
adan | -0.869 |
Token | be |
Token ID | 307 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Kubrick | +0.780 |
tires | +0.707 |
chess | +0.700 |
Redd | +0.675 |
Pens | +0.656 |
Neg logit contributions | |
Appearance | -0.911 |
��極 | -0.865 |
heit | -0.768 |
aneers | -0.753 |
adan | -0.733 |
Token | dial |
Token ID | 5980 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
Kubrick | +1.087 |
tires | +0.976 |
chess | +0.970 |
Redd | +0.948 |
� | +0.911 |
Neg logit contributions | |
Appearance | -1.352 |
��極 | -1.265 |
heit | -1.139 |
aneers | -1.120 |
adan | -1.096 |
Token | ed |
Token ID | 276 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Kubrick | +2.464 |
tires | +2.147 |
chess | +2.127 |
Redd | +2.034 |
Pens | +1.970 |
Neg logit contributions | |
Appearance | -4.515 |
��極 | -4.300 |
aneers | -3.884 |
heit | -3.851 |
ighthouse | -3.755 |
Token | back |
Token ID | 736 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Appearance | +0.275 |
��極 | +0.259 |
heit | +0.237 |
aneers | +0.232 |
adan | +0.229 |
Neg logit contributions | |
Kubrick | -0.169 |
tires | -0.148 |
chess | -0.148 |
Redd | -0.144 |
� | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Appearance | +0.353 |
��極 | +0.333 |
heit | +0.302 |
aneers | +0.297 |
adan | +0.292 |
Neg logit contributions | |
Kubrick | -0.232 |
tires | -0.204 |
chess | -0.204 |
Redd | -0.199 |
� | -0.191 |
Token | In |
Token ID | 554 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
Appearance | +0.269 |
��極 | +0.255 |
heit | +0.230 |
aneers | +0.226 |
adan | +0.222 |
Neg logit contributions | |
Kubrick | -0.192 |
tires | -0.170 |
chess | -0.169 |
Redd | -0.166 |
Pens | -0.159 |
Token | a |
Token ID | 257 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Kubrick | +0.581 |
tires | +0.514 |
chess | +0.514 |
Redd | +0.500 |
Pens | +0.482 |
Neg logit contributions | |
Appearance | -0.829 |
��極 | -0.787 |
heit | -0.709 |
aneers | -0.696 |
adan | -0.683 |
Token | - |
Token ID | 12 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Kubrick | +0.017 |
tires | +0.015 |
chess | +0.015 |
Redd | +0.014 |
Pens | +0.014 |
Neg logit contributions | |
Appearance | -0.025 |
��極 | -0.024 |
heit | -0.022 |
aneers | -0.021 |
adan | -0.021 |
Token | We |
Token ID | 1135 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Appearance | +1.325 |
��極 | +1.238 |
heit | +1.123 |
aneers | +1.097 |
adan | +1.083 |
Neg logit contributions | |
Kubrick | -1.039 |
tires | -0.927 |
chess | -0.927 |
Redd | -0.896 |
� | -0.869 |
Token | ber |
Token ID | 527 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Kubrick | +0.157 |
tires | +0.142 |
chess | +0.140 |
Redd | +0.137 |
Pens | +0.133 |
Neg logit contributions | |
Appearance | -0.175 |
��極 | -0.165 |
heit | -0.145 |
aneers | -0.143 |
�� | -0.139 |
Token | ( |
Token ID | 357 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Kubrick | +0.791 |
tires | +0.695 |
chess | +0.693 |
Redd | +0.663 |
Pens | +0.648 |
Neg logit contributions | |
Appearance | -1.237 |
��極 | -1.169 |
aneers | -1.046 |
heit | -1.044 |
adan | -1.022 |
Token | Un |
Token ID | 3118 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Appearance | +0.161 |
��極 | +0.151 |
heit | +0.136 |
aneers | +0.133 |
adan | +0.131 |
Neg logit contributions | |
Kubrick | -0.129 |
tires | -0.115 |
chess | -0.115 |
Redd | -0.113 |
� | -0.109 |
Token | ivers |
Token ID | 1191 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
Appearance | +1.233 |
��極 | +1.142 |
heit | +1.007 |
aneers | +0.985 |
adan | +0.961 |
Neg logit contributions | |
Kubrick | -1.357 |
tires | -1.235 |
chess | -1.232 |
Redd | -1.212 |
� | -1.173 |
Token | ité |
Token ID | 43816 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Kubrick | +3.173 |
chess | +2.792 |
tires | +2.768 |
Redd | +2.743 |
Pens | +2.734 |
Neg logit contributions | |
Appearance | -3.771 |
��極 | -3.546 |
aneers | -3.052 |
heit | -3.040 |
�� | -3.018 |
Token | de |
Token ID | 390 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Kubrick | +0.962 |
tires | +0.848 |
chess | +0.846 |
Redd | +0.822 |
Pens | +0.796 |
Neg logit contributions | |
Appearance | -1.370 |
��極 | -1.290 |
heit | -1.174 |
aneers | -1.156 |
adan | -1.127 |
Token | T |
Token ID | 309 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Appearance | +1.315 |
��極 | +1.240 |
heit | +1.130 |
aneers | +1.109 |
adan | +1.093 |
Neg logit contributions | |
Kubrick | -0.796 |
tires | -0.696 |
chess | -0.693 |
Redd | -0.682 |
� | -0.649 |
Token | oul |
Token ID | 2852 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Appearance | +0.360 |
��極 | +0.338 |
heit | +0.305 |
aneers | +0.299 |
adan | +0.293 |
Neg logit contributions | |
Kubrick | -0.281 |
tires | -0.251 |
chess | -0.250 |
Redd | -0.245 |
� | -0.236 |
Token | ouse |
Token ID | 1076 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Appearance | +0.364 |
��極 | +0.338 |
heit | +0.297 |
aneers | +0.290 |
adan | +0.284 |
Neg logit contributions | |
Kubrick | -0.393 |
tires | -0.359 |
chess | -0.357 |
Redd | -0.351 |
Pens | -0.341 |
Token | great |
Token ID | 1049 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
Kubrick | +1.832 |
tires | +1.636 |
chess | +1.621 |
Redd | +1.554 |
Pens | +1.495 |
Neg logit contributions | |
Appearance | -2.623 |
��極 | -2.540 |
heit | -2.235 |
aneers | -2.224 |
adan | -2.167 |
Token | abuse |
Token ID | 5076 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Appearance | +0.008 |
��極 | +0.007 |
heit | +0.006 |
aneers | +0.006 |
adan | +0.006 |
Neg logit contributions | |
Kubrick | -0.006 |
tires | -0.005 |
chess | -0.005 |
Redd | -0.005 |
� | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Kubrick | +0.258 |
tires | +0.226 |
chess | +0.224 |
Redd | +0.217 |
� | +0.207 |
Neg logit contributions | |
Appearance | -0.446 |
��極 | -0.424 |
heit | -0.385 |
aneers | -0.379 |
adan | -0.373 |
Token | it |
Token ID | 340 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Appearance | +0.203 |
��極 | +0.191 |
heit | +0.171 |
aneers | +0.168 |
adan | +0.165 |
Neg logit contributions | |
Kubrick | -0.169 |
tires | -0.152 |
chess | -0.151 |
Redd | -0.147 |
Pens | -0.142 |
Token | either |
Token ID | 2035 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Kubrick | +0.388 |
tires | +0.336 |
chess | +0.335 |
Redd | +0.327 |
� | +0.311 |
Neg logit contributions | |
Appearance | -0.699 |
��極 | -0.661 |
heit | -0.605 |
aneers | -0.595 |
adan | -0.586 |
Token | spells |
Token ID | 10377 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
Kubrick | +1.043 |
tires | +0.906 |
chess | +0.894 |
Redd | +0.856 |
Pens | +0.816 |
Neg logit contributions | |
Appearance | -2.097 |
��極 | -2.013 |
heit | -1.834 |
aneers | -1.807 |
adan | -1.775 |
Token | short |
Token ID | 1790 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Kubrick | +3.145 |
tires | +2.868 |
chess | +2.842 |
Redd | +2.682 |
Pens | +2.618 |
Neg logit contributions | |
Appearance | -3.744 |
��極 | -3.638 |
heit | -3.177 |
aneers | -3.172 |
ighthouse | -3.048 |
Token | life |
Token ID | 1204 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
Appearance | +0.140 |
��極 | +0.131 |
heit | +0.119 |
aneers | +0.117 |
adan | +0.115 |
Neg logit contributions | |
Kubrick | -0.100 |
chess | -0.088 |
tires | -0.087 |
Redd | -0.086 |
� | -0.082 |
Token | or |
Token ID | 393 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Kubrick | +0.450 |
tires | +0.387 |
chess | +0.386 |
Redd | +0.375 |
� | +0.356 |
Neg logit contributions | |
Appearance | -0.870 |
��極 | -0.824 |
heit | -0.756 |
aneers | -0.744 |
adan | -0.733 |
Token | exotic |
Token ID | 21036 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Appearance | +0.303 |
��極 | +0.284 |
heit | +0.259 |
aneers | +0.254 |
adan | +0.250 |
Neg logit contributions | |
Kubrick | -0.199 |
tires | -0.174 |
chess | -0.174 |
Redd | -0.172 |
� | -0.164 |
Token | technology |
Token ID | 3037 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
Appearance | +0.548 |
��極 | +0.516 |
heit | +0.467 |
aneers | +0.459 |
adan | +0.451 |
Neg logit contributions | |
Kubrick | -0.385 |
tires | -0.341 |
chess | -0.340 |
Redd | -0.333 |
� | -0.319 |
Token | ( |
Token ID | 357 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Kubrick | +1.264 |
tires | +1.108 |
chess | +1.096 |
Redd | +1.041 |
Pens | +1.014 |
Neg logit contributions | |
Appearance | -2.149 |
��極 | -2.058 |
heit | -1.868 |
aneers | -1.840 |
adan | -1.804 |
Token | who |
Token ID | 8727 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Kubrick | +0.089 |
tires | +0.081 |
chess | +0.081 |
Redd | +0.080 |
� | +0.077 |
Neg logit contributions | |
Appearance | -0.083 |
��極 | -0.077 |
heit | -0.068 |
aneers | -0.067 |
adan | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
Appearance | +1.600 |
��極 | +1.487 |
heit | +1.365 |
aneers | +1.345 |
adan | +1.325 |
Neg logit contributions | |
Kubrick | -1.005 |
chess | -0.882 |
tires | -0.880 |
Redd | -0.879 |
� | -0.833 |
Token | nominated |
Token ID | 19332 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
Appearance | +0.047 |
��極 | +0.044 |
heit | +0.039 |
aneers | +0.039 |
adan | +0.038 |
Neg logit contributions | |
Kubrick | -0.042 |
tires | -0.037 |
chess | -0.037 |
Redd | -0.037 |
� | -0.035 |
Token | eight |
Token ID | 3624 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Appearance | +0.966 |
��極 | +0.911 |
heit | +0.827 |
aneers | +0.813 |
adan | +0.799 |
Neg logit contributions | |
Kubrick | -0.645 |
tires | -0.569 |
chess | -0.567 |
Redd | -0.554 |
� | -0.530 |
Token | times |
Token ID | 1661 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
Kubrick | +0.106 |
tires | +0.090 |
chess | +0.090 |
Redd | +0.086 |
Pens | +0.081 |
Neg logit contributions | |
Appearance | -0.235 |
��極 | -0.224 |
heit | -0.206 |
aneers | -0.203 |
adan | -0.200 |
Token | for |
Token ID | 329 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Kubrick | +2.434 |
chess | +2.126 |
tires | +2.119 |
Pens | +1.938 |
Redd | +1.936 |
Neg logit contributions | |
Appearance | -4.414 |
��極 | -4.269 |
heit | -3.850 |
aneers | -3.787 |
adan | -3.698 |
Token | Monk |
Token ID | 28854 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Kubrick | +0.806 |
chess | +0.723 |
tires | +0.721 |
Redd | +0.700 |
Pens | +0.682 |
Neg logit contributions | |
Appearance | -0.897 |
��極 | -0.851 |
heit | -0.759 |
aneers | -0.745 |
adan | -0.728 |
Token | ), |
Token ID | 828 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Kubrick | +1.325 |
chess | +1.164 |
tires | +1.163 |
Redd | +1.101 |
Pens | +1.066 |
Neg logit contributions | |
Appearance | -2.226 |
��極 | -2.148 |
heit | -1.934 |
aneers | -1.907 |
adan | -1.868 |
Token | Gu |
Token ID | 1962 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Appearance | +0.324 |
��極 | +0.303 |
heit | +0.275 |
aneers | +0.268 |
adan | +0.265 |
Neg logit contributions | |
Kubrick | -0.230 |
tires | -0.204 |
chess | -0.204 |
Redd | -0.201 |
� | -0.193 |
Token | illa |
Token ID | 5049 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Kubrick | +0.887 |
tires | +0.788 |
chess | +0.787 |
Redd | +0.774 |
Pens | +0.743 |
Neg logit contributions | |
Appearance | -0.992 |
��極 | -0.962 |
heit | -0.814 |
aneers | -0.809 |
�� | -0.799 |
Token | career |
Token ID | 3451 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Appearance | +0.752 |
��極 | +0.699 |
heit | +0.624 |
aneers | +0.612 |
adan | +0.601 |
Neg logit contributions | |
Kubrick | -0.693 |
tires | -0.623 |
chess | -0.622 |
Redd | -0.614 |
� | -0.591 |
Token | out |
Token ID | 503 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
Appearance | +0.150 |
��極 | +0.142 |
heit | +0.129 |
aneers | +0.127 |
adan | +0.124 |
Neg logit contributions | |
Kubrick | -0.097 |
tires | -0.085 |
chess | -0.085 |
Redd | -0.082 |
Pens | -0.079 |
Token | of |
Token ID | 286 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Kubrick | +0.496 |
tires | +0.428 |
chess | +0.427 |
Redd | +0.415 |
� | +0.392 |
Neg logit contributions | |
Appearance | -0.951 |
��極 | -0.905 |
heit | -0.826 |
aneers | -0.815 |
adan | -0.801 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Kubrick | +1.256 |
tires | +1.112 |
chess | +1.110 |
Redd | +1.079 |
Pens | +1.036 |
Neg logit contributions | |
Appearance | -1.807 |
��極 | -1.720 |
heit | -1.552 |
aneers | -1.527 |
adan | -1.495 |
Token | un |
Token ID | 555 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
Appearance | +0.223 |
��極 | +0.209 |
heit | +0.190 |
aneers | +0.187 |
adan | +0.184 |
Neg logit contributions | |
Kubrick | -0.153 |
tires | -0.135 |
chess | -0.135 |
Redd | -0.132 |
� | -0.127 |
Token | hing |
Token ID | 722 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
Kubrick | +0.619 |
tires | +0.560 |
chess | +0.557 |
Redd | +0.545 |
Pens | +0.526 |
Neg logit contributions | |
Appearance | -0.687 |
��極 | -0.649 |
heit | -0.572 |
aneers | -0.563 |
adan | -0.549 |
Token | ed |
Token ID | 276 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Kubrick | +2.446 |
tires | +2.149 |
chess | +2.099 |
Redd | +2.079 |
Pens | +1.944 |
Neg logit contributions | |
Appearance | -4.417 |
��極 | -4.236 |
heit | -3.812 |
aneers | -3.727 |
�� | -3.671 |
Token | lun |
Token ID | 14678 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Kubrick | +0.291 |
tires | +0.257 |
chess | +0.256 |
Redd | +0.250 |
Pens | +0.239 |
Neg logit contributions | |
Appearance | -0.435 |
��極 | -0.411 |
heit | -0.373 |
aneers | -0.367 |
adan | -0.360 |
Token | atics |
Token ID | 23372 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Kubrick | +0.537 |
tires | +0.498 |
chess | +0.495 |
Redd | +0.484 |
Pens | +0.472 |
Neg logit contributions | |
Appearance | -0.382 |
��極 | -0.356 |
heit | -0.297 |
aneers | -0.288 |
�� | -0.282 |
Token | . |
Token ID | 13 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
Kubrick | +0.258 |
tires | +0.226 |
chess | +0.225 |
Redd | +0.218 |
� | +0.209 |
Neg logit contributions | |
Appearance | -0.425 |
��極 | -0.403 |
heit | -0.366 |
aneers | -0.360 |
adan | -0.354 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Kubrick | +0.466 |
tires | +0.415 |
chess | +0.414 |
Redd | +0.406 |
Pens | +0.392 |
Neg logit contributions | |
Appearance | -0.554 |
��極 | -0.526 |
heit | -0.470 |
aneers | -0.461 |
adan | -0.452 |
Token | 28 |
Token ID | 2579 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Appearance | +0.175 |
��極 | +0.165 |
heit | +0.148 |
aneers | +0.145 |
adan | +0.142 |
Neg logit contributions | |
Kubrick | -0.142 |
tires | -0.127 |
chess | -0.127 |
Redd | -0.124 |
Pens | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Kubrick | +0.368 |
tires | +0.321 |
chess | +0.320 |
Redd | +0.312 |
� | +0.297 |
Neg logit contributions | |
Appearance | -0.622 |
��極 | -0.588 |
heit | -0.537 |
aneers | -0.528 |
adan | -0.520 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Kubrick | +0.740 |
tires | +0.653 |
chess | +0.651 |
Redd | +0.633 |
Pens | +0.607 |
Neg logit contributions | |
Appearance | -1.141 |
��極 | -1.082 |
heit | -0.981 |
aneers | -0.964 |
adan | -0.947 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Kubrick | +1.253 |
tires | +1.106 |
chess | +1.098 |
Redd | +1.061 |
Pens | +1.018 |
Neg logit contributions | |
Appearance | -1.947 |
��極 | -1.876 |
heit | -1.675 |
aneers | -1.661 |
adan | -1.618 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
Kubrick | +0.890 |
tires | +0.806 |
chess | +0.805 |
Redd | +0.788 |
Pens | +0.769 |
Neg logit contributions | |
Appearance | -0.865 |
��極 | -0.819 |
heit | -0.721 |
aneers | -0.703 |
adan | -0.687 |
Token | / |
Token ID | 14 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Appearance | +0.548 |
��極 | +0.514 |
heit | +0.466 |
aneers | +0.457 |
adan | +0.449 |
Neg logit contributions | |
Kubrick | -0.401 |
tires | -0.357 |
chess | -0.355 |
Redd | -0.349 |
� | -0.334 |
Token | Michael |
Token ID | 13256 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
Appearance | +2.557 |
��極 | +2.385 |
heit | +2.141 |
aneers | +2.097 |
adan | +2.065 |
Neg logit contributions | |
Kubrick | -2.220 |
tires | -1.991 |
chess | -1.987 |
Redd | -1.944 |
� | -1.875 |
Token | K |
Token ID | 509 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
Appearance | +0.792 |
��極 | +0.747 |
heit | +0.671 |
aneers | +0.657 |
adan | +0.643 |
Neg logit contributions | |
Kubrick | -0.645 |
tires | -0.573 |
chess | -0.573 |
Redd | -0.561 |
Pens | -0.542 |
Token | lim |
Token ID | 2475 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Appearance | +0.946 |
��極 | +0.887 |
heit | +0.806 |
aneers | +0.792 |
adan | +0.783 |
Neg logit contributions | |
Kubrick | -0.648 |
tires | -0.573 |
chess | -0.572 |
Redd | -0.558 |
� | -0.536 |
Token | enty |
Token ID | 3787 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Appearance | +1.008 |
��極 | +0.942 |
heit | +0.809 |
aneers | +0.780 |
ighthouse | +0.764 |
Neg logit contributions | |
Kubrick | -1.341 |
tires | -1.229 |
chess | -1.216 |
Redd | -1.195 |
Pens | -1.163 |
Token | ev |
Token ID | 1990 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Kubrick | +0.073 |
tires | +0.065 |
chess | +0.064 |
Redd | +0.063 |
� | +0.061 |
Neg logit contributions | |
Appearance | -0.098 |
��極 | -0.092 |
heit | -0.083 |
aneers | -0.082 |
adan | -0.080 |
Token | grid |
Token ID | 10706 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Appearance | +0.363 |
��極 | +0.344 |
heit | +0.311 |
aneers | +0.306 |
adan | +0.301 |
Neg logit contributions | |
Kubrick | -0.250 |
tires | -0.221 |
chess | -0.220 |
Redd | -0.215 |
Pens | -0.205 |
Token | cell |
Token ID | 3846 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Kubrick | +0.953 |
tires | +0.864 |
chess | +0.860 |
Redd | +0.839 |
Pens | +0.814 |
Neg logit contributions | |
Appearance | -1.088 |
��極 | -1.029 |
heit | -0.916 |
aneers | -0.901 |
adan | -0.887 |
Token | volume |
Token ID | 6115 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Appearance | +0.379 |
��極 | +0.357 |
heit | +0.323 |
aneers | +0.317 |
adan | +0.311 |
Neg logit contributions | |
Kubrick | -0.275 |
tires | -0.244 |
chess | -0.244 |
Redd | -0.239 |
� | -0.228 |
Token | . |
Token ID | 13 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
Appearance | +1.788 |
��極 | +1.676 |
heit | +1.527 |
aneers | +1.498 |
adan | +1.471 |
Neg logit contributions | |
Kubrick | -1.208 |
tires | -1.058 |
chess | -1.057 |
Redd | -1.036 |
� | -0.992 |
Token | const |
Token ID | 1500 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Kubrick | +0.395 |
tires | +0.361 |
chess | +0.357 |
Redd | +0.352 |
Pens | +0.341 |
Neg logit contributions | |
Appearance | -0.432 |
��極 | -0.410 |
heit | -0.364 |
aneers | -0.357 |
adan | -0.351 |
Token | float |
Token ID | 12178 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Appearance | +2.540 |
��極 | +2.370 |
heit | +2.146 |
aneers | +2.104 |
adan | +2.063 |
Neg logit contributions | |
Kubrick | -1.950 |
tires | -1.729 |
chess | -1.728 |
Redd | -1.700 |
� | -1.632 |
Token | one |
Token ID | 530 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Appearance | +3.756 |
��極 | +3.505 |
heit | +3.185 |
aneers | +3.121 |
adan | +3.058 |
Neg logit contributions | |
Kubrick | -2.691 |
chess | -2.370 |
tires | -2.362 |
Redd | -2.323 |
� | -2.236 |
Token | Over |
Token ID | 5886 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Kubrick | +0.016 |
tires | +0.014 |
chess | +0.014 |
Redd | +0.014 |
� | +0.013 |
Neg logit contributions | |
Appearance | -0.020 |
��極 | -0.019 |
heit | -0.017 |
aneers | -0.016 |
adan | -0.016 |
Token | Cell |
Token ID | 28780 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Kubrick | +0.318 |
tires | +0.282 |
chess | +0.280 |
Redd | +0.276 |
� | +0.261 |
Neg logit contributions | |
Appearance | -0.494 |
��極 | -0.469 |
heit | -0.422 |
aneers | -0.419 |
adan | -0.411 |
Token | Volume |
Token ID | 31715 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Kubrick | +0.835 |
tires | +0.749 |
chess | +0.741 |
Redd | +0.740 |
Pens | +0.700 |
Neg logit contributions | |
Appearance | -1.205 |
��極 | -1.152 |
heit | -1.029 |
aneers | -1.017 |
adan | -1.001 |
Token | = |
Token ID | 796 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Appearance | +0.123 |
��極 | +0.117 |
heit | +0.105 |
aneers | +0.104 |
adan | +0.102 |
Neg logit contributions | |
Kubrick | -0.081 |
tires | -0.072 |
chess | -0.071 |
Redd | -0.071 |
� | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Kubrick | +0.064 |
tires | +0.058 |
chess | +0.057 |
Redd | +0.056 |
Pens | +0.053 |
Neg logit contributions | |
Appearance | -0.095 |
��極 | -0.091 |
heit | -0.081 |
aneers | -0.079 |
adan | -0.078 |
Token | we |
Token ID | 356 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Appearance | +1.432 |
��極 | +1.330 |
heit | +1.201 |
aneers | +1.174 |
adan | +1.152 |
Neg logit contributions | |
Kubrick | -1.209 |
tires | -1.079 |
chess | -1.079 |
Redd | -1.066 |
� | -1.024 |
Token | � |
Token ID | 447 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Appearance | +1.494 |
��極 | +1.367 |
heit | +1.270 |
aneers | +1.244 |
ighthouse | +1.225 |
Neg logit contributions | |
Kubrick | -0.998 |
Redd | -0.876 |
tires | -0.873 |
chess | -0.865 |
� | -0.823 |
Token | � |
Token ID | 247 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Appearance | +0.216 |
��極 | +0.199 |
heit | +0.175 |
aneers | +0.173 |
adan | +0.168 |
Neg logit contributions | |
Kubrick | -0.249 |
tires | -0.228 |
chess | -0.227 |
Redd | -0.224 |
� | -0.217 |
Token | ll |
Token ID | 297 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Appearance | +0.386 |
��極 | +0.365 |
heit | +0.334 |
aneers | +0.328 |
adan | +0.323 |
Neg logit contributions | |
Kubrick | -0.226 |
tires | -0.197 |
chess | -0.196 |
Redd | -0.192 |
� | -0.182 |
Token | send |
Token ID | 3758 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
Appearance | +1.331 |
��極 | +1.215 |
heit | +1.101 |
aneers | +1.063 |
adan | +1.050 |
Neg logit contributions | |
Kubrick | -1.266 |
tires | -1.138 |
chess | -1.136 |
Redd | -1.122 |
Pens | -1.075 |
Token | you |
Token ID | 345 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
Appearance | +3.036 |
��極 | +2.812 |
heit | +2.574 |
�� | +2.544 |
aneers | +2.537 |
Neg logit contributions | |
Kubrick | -2.328 |
Redd | -2.086 |
tires | -2.060 |
chess | -2.058 |
� | -2.000 |
Token | three |
Token ID | 1115 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
Kubrick | +1.904 |
tires | +1.710 |
chess | +1.699 |
Redd | +1.656 |
Pens | +1.600 |
Neg logit contributions | |
Appearance | -2.600 |
��極 | -2.485 |
heit | -2.227 |
aneers | -2.191 |
adan | -2.155 |
Token | meaningful |
Token ID | 11570 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Kubrick | +0.510 |
chess | +0.460 |
tires | +0.460 |
Redd | +0.457 |
� | +0.443 |
Neg logit contributions | |
Appearance | -0.451 |
��極 | -0.410 |
heit | -0.366 |
aneers | -0.357 |
adan | -0.351 |
Token | actions |
Token ID | 4028 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Appearance | +1.102 |
��極 | +0.974 |
heit | +0.870 |
aneers | +0.861 |
adan | +0.851 |
Neg logit contributions | |
Kubrick | -1.438 |
Redd | -1.297 |
tires | -1.296 |
chess | -1.281 |
� | -1.260 |
Token | you |
Token ID | 345 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Kubrick | +0.235 |
chess | +0.207 |
tires | +0.206 |
Redd | +0.204 |
� | +0.195 |
Neg logit contributions | |
Appearance | -0.346 |
��極 | -0.320 |
heit | -0.296 |
aneers | -0.291 |
adan | -0.286 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Kubrick | +0.021 |
chess | +0.018 |
tires | +0.018 |
Redd | +0.018 |
� | +0.017 |
Neg logit contributions | |
Appearance | -0.030 |
��極 | -0.028 |
heit | -0.025 |
aneers | -0.025 |
adan | -0.024 |
Token | " |
Token ID | 1 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Kubrick | +0.115 |
tires | +0.102 |
chess | +0.102 |
Redd | +0.101 |
� | +0.096 |
Neg logit contributions | |
Appearance | -0.145 |
��極 | -0.136 |
heit | -0.122 |
aneers | -0.120 |
adan | -0.117 |
Token | I |
Token ID | 40 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Kubrick | +0.320 |
tires | +0.287 |
chess | +0.286 |
Redd | +0.285 |
� | +0.273 |
Neg logit contributions | |
Appearance | -0.342 |
��極 | -0.324 |
heit | -0.285 |
aneers | -0.280 |
adan | -0.273 |
Token | just |
Token ID | 655 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Kubrick | +0.242 |
tires | +0.216 |
chess | +0.214 |
Redd | +0.209 |
Pens | +0.201 |
Neg logit contributions | |
Appearance | -0.316 |
��極 | -0.298 |
heit | -0.268 |
aneers | -0.264 |
adan | -0.258 |
Token | went |
Token ID | 1816 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Appearance | +0.132 |
��極 | +0.124 |
heit | +0.111 |
aneers | +0.109 |
adan | +0.107 |
Neg logit contributions | |
Kubrick | -0.113 |
tires | -0.102 |
chess | -0.102 |
Redd | -0.099 |
� | -0.096 |
Token | through |
Token ID | 832 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
Kubrick | +0.102 |
tires | +0.090 |
chess | +0.090 |
Redd | +0.087 |
Pens | +0.084 |
Neg logit contributions | |
Appearance | -0.157 |
��極 | -0.149 |
heit | -0.134 |
aneers | -0.133 |
adan | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
Appearance | +4.095 |
��極 | +3.758 |
heit | +3.479 |
aneers | +3.380 |
adan | +3.357 |
Neg logit contributions | |
Kubrick | -3.057 |
chess | -2.728 |
tires | -2.724 |
Redd | -2.722 |
� | -2.614 |
Token | LA |
Token ID | 9131 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
Appearance | +0.677 |
��極 | +0.638 |
heit | +0.578 |
aneers | +0.568 |
adan | +0.558 |
Neg logit contributions | |
Kubrick | -0.465 |
tires | -0.411 |
chess | -0.410 |
Redd | -0.401 |
� | -0.384 |
Token | X |
Token ID | 55 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Appearance | +0.073 |
��極 | +0.069 |
heit | +0.062 |
aneers | +0.061 |
adan | +0.060 |
Neg logit contributions | |
Kubrick | -0.053 |
tires | -0.047 |
chess | -0.047 |
Redd | -0.045 |
Pens | -0.044 |
Token | security |
Token ID | 2324 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Kubrick | +0.318 |
tires | +0.281 |
chess | +0.280 |
Redd | +0.272 |
Pens | +0.261 |
Neg logit contributions | |
Appearance | -0.465 |
��極 | -0.440 |
heit | -0.397 |
aneers | -0.391 |
adan | -0.383 |
Token | line |
Token ID | 1627 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Kubrick | +0.729 |
tires | +0.643 |
chess | +0.642 |
Redd | +0.617 |
Pens | +0.595 |
Neg logit contributions | |
Appearance | -1.136 |
��極 | -1.082 |
heit | -0.978 |
aneers | -0.961 |
adan | -0.939 |
Token | , |
Token ID | 11 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Kubrick | +0.406 |
tires | +0.359 |
chess | +0.358 |
Redd | +0.345 |
Pens | +0.332 |
Neg logit contributions | |
Appearance | -0.647 |
��極 | -0.614 |
heit | -0.556 |
aneers | -0.547 |
adan | -0.536 |
Token | drilling |
Token ID | 19747 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Kubrick | +0.228 |
tires | +0.203 |
chess | +0.203 |
Redd | +0.197 |
Pens | +0.190 |
Neg logit contributions | |
Appearance | -0.309 |
��極 | -0.291 |
heit | -0.262 |
aneers | -0.258 |
adan | -0.252 |
Token | hundreds |
Token ID | 5179 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Appearance | +0.995 |
��極 | +0.937 |
heit | +0.850 |
aneers | +0.834 |
adan | +0.819 |
Neg logit contributions | |
Kubrick | -0.690 |
tires | -0.612 |
chess | -0.609 |
Redd | -0.596 |
Pens | -0.570 |
Token | of |
Token ID | 286 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Appearance | +0.802 |
��極 | +0.761 |
heit | +0.694 |
aneers | +0.686 |
adan | +0.674 |
Neg logit contributions | |
Kubrick | -0.463 |
chess | -0.400 |
tires | -0.399 |
Redd | -0.395 |
� | -0.373 |
Token | wells |
Token ID | 22571 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
Kubrick | +0.182 |
tires | +0.165 |
chess | +0.164 |
Redd | +0.160 |
Pens | +0.155 |
Neg logit contributions | |
Appearance | -0.212 |
��極 | -0.199 |
heit | -0.178 |
aneers | -0.174 |
adan | -0.171 |
Token | across |
Token ID | 1973 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Appearance | +0.960 |
��極 | +0.907 |
heit | +0.824 |
aneers | +0.809 |
adan | +0.796 |
Neg logit contributions | |
Kubrick | -0.617 |
tires | -0.544 |
chess | -0.541 |
Redd | -0.527 |
Pens | -0.504 |
Token | Texas |
Token ID | 3936 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Appearance | +2.755 |
��極 | +2.576 |
heit | +2.344 |
aneers | +2.298 |
adan | +2.266 |
Neg logit contributions | |
Kubrick | -1.997 |
tires | -1.756 |
chess | -1.749 |
Redd | -1.722 |
� | -1.665 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Appearance | +1.276 |
��極 | +1.202 |
heit | +1.093 |
aneers | +1.074 |
adan | +1.057 |
Neg logit contributions | |
Kubrick | -0.845 |
tires | -0.743 |
chess | -0.741 |
Redd | -0.726 |
� | -0.694 |
Token | At |
Token ID | 1629 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Appearance | +0.099 |
��極 | +0.094 |
heit | +0.083 |
aneers | +0.081 |
adan | +0.080 |
Neg logit contributions | |
Kubrick | -0.094 |
tires | -0.084 |
chess | -0.084 |
Redd | -0.082 |
Pens | -0.080 |
Token | his |
Token ID | 465 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
Kubrick | +0.261 |
chess | +0.232 |
tires | +0.231 |
Redd | +0.225 |
Pens | +0.219 |
Neg logit contributions | |
Appearance | -0.371 |
��極 | -0.353 |
heit | -0.317 |
aneers | -0.312 |
adan | -0.306 |
Token | low |
Token ID | 1877 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Appearance | +0.026 |
��極 | +0.024 |
heit | +0.022 |
aneers | +0.021 |
adan | +0.021 |
Neg logit contributions | |
Kubrick | -0.020 |
tires | -0.018 |
chess | -0.018 |
Redd | -0.018 |
Pens | -0.017 |
Token | tension |
Token ID | 12097 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Kubrick | +0.040 |
tires | +0.036 |
chess | +0.036 |
Redd | +0.035 |
Pens | +0.034 |
Neg logit contributions | |
Appearance | -0.046 |
��極 | -0.044 |
heit | -0.039 |
aneers | -0.038 |
adan | -0.037 |
Token | between |
Token ID | 1022 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Appearance | +0.360 |
��極 | +0.343 |
heit | +0.310 |
aneers | +0.305 |
adan | +0.299 |
Neg logit contributions | |
Kubrick | -0.221 |
tires | -0.195 |
chess | -0.194 |
Redd | -0.188 |
Pens | -0.179 |
Token | communities |
Token ID | 5348 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
Appearance | +0.136 |
��極 | +0.128 |
heit | +0.115 |
aneers | +0.113 |
adan | +0.111 |
Neg logit contributions | |
Kubrick | -0.108 |
tires | -0.097 |
chess | -0.097 |
Redd | -0.095 |
Pens | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
Kubrick | +0.602 |
chess | +0.534 |
tires | +0.530 |
Redd | +0.507 |
Pens | +0.491 |
Neg logit contributions | |
Appearance | -0.986 |
��極 | -0.940 |
heit | -0.849 |
aneers | -0.837 |
adan | -0.817 |
Token |
|
Token ID | 198 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Kubrick | +0.038 |
tires | +0.033 |
chess | +0.033 |
Redd | +0.032 |
Pens | +0.031 |
Neg logit contributions | |
Appearance | -0.057 |
��極 | -0.054 |
heit | -0.049 |
aneers | -0.048 |
adan | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Appearance | +0.390 |
��極 | +0.364 |
heit | +0.333 |
aneers | +0.327 |
adan | +0.321 |
Neg logit contributions | |
Kubrick | -0.272 |
tires | -0.240 |
chess | -0.240 |
Redd | -0.234 |
� | -0.225 |
Token | The |
Token ID | 464 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Appearance | +0.194 |
��極 | +0.183 |
heit | +0.162 |
aneers | +0.159 |
adan | +0.155 |
Neg logit contributions | |
Kubrick | -0.176 |
tires | -0.158 |
Redd | -0.158 |
chess | -0.157 |
� | -0.151 |
Token | Bomber |
Token ID | 38474 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Kubrick | +0.094 |
tires | +0.084 |
chess | +0.084 |
Redd | +0.081 |
Pens | +0.079 |
Neg logit contributions | |
Appearance | -0.126 |
��極 | -0.120 |
heit | -0.109 |
aneers | -0.107 |
adan | -0.104 |
Token | Command |
Token ID | 9455 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Kubrick | +0.262 |
tires | +0.232 |
chess | +0.232 |
Redd | +0.226 |
Pens | +0.218 |
Neg logit contributions | |
Appearance | -0.360 |
��極 | -0.340 |
heit | -0.308 |
aneers | -0.301 |
adan | -0.296 |
Token | Memorial |
Token ID | 14861 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Appearance | +0.791 |
��極 | +0.745 |
heit | +0.674 |
aneers | +0.662 |
adan | +0.650 |
Neg logit contributions | |
Kubrick | -0.572 |
tires | -0.507 |
chess | -0.506 |
Redd | -0.495 |
Pens | -0.474 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Appearance | +1.721 |
��極 | +1.615 |
heit | +1.471 |
aneers | +1.443 |
adan | +1.420 |
Neg logit contributions | |
Kubrick | -1.143 |
tires | -1.008 |
chess | -1.003 |
Redd | -0.987 |
� | -0.942 |
Token | pretty |
Token ID | 2495 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
Kubrick | +0.099 |
tires | +0.088 |
chess | +0.088 |
Redd | +0.086 |
� | +0.082 |
Neg logit contributions | |
Appearance | -0.146 |
��極 | -0.137 |
heit | -0.125 |
aneers | -0.122 |
adan | -0.120 |
Token | cool |
Token ID | 3608 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
Kubrick | +0.553 |
tires | +0.493 |
chess | +0.489 |
Redd | +0.478 |
� | +0.457 |
Neg logit contributions | |
Appearance | -0.742 |
��極 | -0.700 |
heit | -0.629 |
aneers | -0.621 |
adan | -0.610 |
Token | . |
Token ID | 13 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Kubrick | +1.321 |
tires | +1.144 |
chess | +1.141 |
Redd | +1.090 |
Pens | +1.043 |
Neg logit contributions | |
Appearance | -2.278 |
��極 | -2.177 |
heit | -1.975 |
aneers | -1.959 |
adan | -1.905 |
Token | With |
Token ID | 2080 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
Appearance | +0.393 |
��極 | +0.365 |
heit | +0.326 |
aneers | +0.319 |
adan | +0.313 |
Neg logit contributions | |
Kubrick | -0.371 |
tires | -0.336 |
chess | -0.335 |
Redd | -0.329 |
� | -0.318 |
Token | that |
Token ID | 326 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Kubrick | +0.441 |
tires | +0.391 |
chess | +0.389 |
Redd | +0.381 |
Pens | +0.366 |
Neg logit contributions | |
Appearance | -0.588 |
��極 | -0.554 |
heit | -0.501 |
aneers | -0.492 |
adan | -0.482 |
Token | said |
Token ID | 531 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Kubrick | +0.432 |
tires | +0.379 |
chess | +0.377 |
Redd | +0.366 |
Pens | +0.350 |
Neg logit contributions | |
Appearance | -0.693 |
��極 | -0.656 |
heit | -0.597 |
aneers | -0.589 |
adan | -0.578 |
Token | , |
Token ID | 11 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
Appearance | +0.296 |
��極 | +0.279 |
heit | +0.255 |
aneers | +0.250 |
adan | +0.247 |
Neg logit contributions | |
Kubrick | -0.173 |
tires | -0.151 |
chess | -0.151 |
Redd | -0.148 |
� | -0.140 |
Token | I |
Token ID | 314 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Appearance | +0.766 |
��極 | +0.716 |
heit | +0.647 |
aneers | +0.633 |
adan | +0.624 |
Neg logit contributions | |
Kubrick | -0.592 |
tires | -0.530 |
chess | -0.529 |
Redd | -0.521 |
� | -0.501 |
Token | guess |
Token ID | 4724 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Appearance | +0.176 |
��極 | +0.165 |
heit | +0.149 |
aneers | +0.147 |
adan | +0.144 |
Neg logit contributions | |
Kubrick | -0.128 |
tires | -0.114 |
chess | -0.113 |
Redd | -0.111 |
� | -0.106 |
Token | there |
Token ID | 612 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
Kubrick | +0.983 |
tires | +0.874 |
chess | +0.871 |
Redd | +0.848 |
Pens | +0.820 |
Neg logit contributions | |
Appearance | -1.243 |
��極 | -1.175 |
heit | -1.056 |
aneers | -1.042 |
adan | -1.016 |
Token | � |
Token ID | 447 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Kubrick | +0.028 |
tires | +0.024 |
chess | +0.024 |
Redd | +0.024 |
� | +0.023 |
Neg logit contributions | |
Appearance | -0.048 |
��極 | -0.045 |
heit | -0.041 |
aneers | -0.041 |
adan | -0.040 |
Token | but |
Token ID | 4360 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Kubrick | +0.415 |
tires | +0.377 |
chess | +0.376 |
Redd | +0.373 |
Pens | +0.358 |
Neg logit contributions | |
Appearance | -0.400 |
��極 | -0.374 |
heit | -0.329 |
aneers | -0.322 |
adan | -0.313 |
Token | I |
Token ID | 314 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Appearance | +0.369 |
��極 | +0.347 |
heit | +0.313 |
aneers | +0.308 |
adan | +0.302 |
Neg logit contributions | |
Kubrick | -0.276 |
tires | -0.246 |
chess | -0.245 |
Redd | -0.239 |
Pens | -0.230 |
Token | don |
Token ID | 836 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Appearance | +0.227 |
��極 | +0.213 |
heit | +0.190 |
aneers | +0.188 |
adan | +0.183 |
Neg logit contributions | |
Kubrick | -0.194 |
tires | -0.174 |
chess | -0.173 |
Redd | -0.169 |
� | -0.163 |
Token | � |
Token ID | 447 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Kubrick | +0.447 |
tires | +0.392 |
chess | +0.388 |
Redd | +0.383 |
� | +0.365 |
Neg logit contributions | |
Appearance | -0.735 |
��極 | -0.702 |
heit | -0.632 |
aneers | -0.624 |
adan | -0.612 |
Token | � |
Token ID | 247 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Appearance | +0.343 |
��極 | +0.317 |
heit | +0.278 |
aneers | +0.271 |
adan | +0.265 |
Neg logit contributions | |
Kubrick | -0.410 |
tires | -0.374 |
chess | -0.373 |
Redd | -0.367 |
� | -0.356 |
Token | t |
Token ID | 83 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
Appearance | +0.478 |
��極 | +0.453 |
heit | +0.411 |
aneers | +0.406 |
adan | +0.396 |
Neg logit contributions | |
Kubrick | -0.290 |
tires | -0.256 |
chess | -0.253 |
Redd | -0.247 |
� | -0.236 |
Token | think |
Token ID | 892 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Appearance | +0.054 |
��極 | +0.051 |
heit | +0.045 |
aneers | +0.045 |
adan | +0.043 |
Neg logit contributions | |
Kubrick | -0.051 |
tires | -0.046 |
chess | -0.046 |
Redd | -0.045 |
� | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
Appearance | +1.452 |
��極 | +1.359 |
heit | +1.233 |
aneers | +1.209 |
adan | +1.190 |
Neg logit contributions | |
Kubrick | -1.064 |
tires | -0.943 |
chess | -0.941 |
Redd | -0.925 |
� | -0.888 |
Token | governor |
Token ID | 8153 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
Appearance | +0.803 |
��極 | +0.753 |
heit | +0.678 |
aneers | +0.665 |
adan | +0.653 |
Neg logit contributions | |
Kubrick | -0.645 |
tires | -0.577 |
chess | -0.575 |
Redd | -0.563 |
� | -0.541 |
Token | would |
Token ID | 561 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
Kubrick | +0.463 |
tires | +0.411 |
chess | +0.405 |
Redd | +0.391 |
� | +0.379 |
Neg logit contributions | |
Appearance | -0.754 |
��極 | -0.717 |
heit | -0.648 |
aneers | -0.638 |
adan | -0.625 |
Token | disagree |
Token ID | 12546 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Appearance | +0.542 |
��極 | +0.510 |
heit | +0.458 |
aneers | +0.450 |
adan | +0.441 |
Neg logit contributions | |
Kubrick | -0.428 |
tires | -0.383 |
chess | -0.381 |
Redd | -0.373 |
� | -0.359 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
Kubrick | +0.376 |
tires | +0.333 |
chess | +0.331 |
Redd | +0.322 |
Pens | +0.308 |
Neg logit contributions | |
Appearance | -0.561 |
��極 | -0.530 |
heit | -0.482 |
aneers | -0.472 |
adan | -0.464 |
Token | officers |
Token ID | 3790 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Kubrick | +0.018 |
tires | +0.017 |
chess | +0.017 |
Redd | +0.016 |
Pens | +0.016 |
Neg logit contributions | |
Appearance | -0.015 |
��極 | -0.014 |
heit | -0.013 |
aneers | -0.012 |
adan | -0.012 |
Token | told |
Token ID | 1297 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
Appearance | +1.223 |
��極 | +1.141 |
heit | +1.039 |
aneers | +1.016 |
adan | +1.008 |
Neg logit contributions | |
Kubrick | -0.898 |
chess | -0.795 |
Redd | -0.793 |
tires | -0.790 |
� | -0.755 |
Token | Di |
Token ID | 6031 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
Appearance | +0.923 |
��極 | +0.866 |
heit | +0.784 |
aneers | +0.769 |
adan | +0.756 |
Neg logit contributions | |
Kubrick | -0.683 |
tires | -0.607 |
chess | -0.605 |
Redd | -0.593 |
� | -0.569 |
Token | allo |
Token ID | 49457 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Kubrick | +0.029 |
tires | +0.026 |
chess | +0.026 |
Redd | +0.025 |
� | +0.024 |
Neg logit contributions | |
Appearance | -0.037 |
��極 | -0.035 |
heit | -0.031 |
aneers | -0.030 |
adan | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Appearance | +0.302 |
��極 | +0.285 |
heit | +0.259 |
aneers | +0.255 |
adan | +0.251 |
Neg logit contributions | |
Kubrick | -0.189 |
tires | -0.166 |
chess | -0.165 |
Redd | -0.161 |
� | -0.154 |
Token | the |
Token ID | 262 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Appearance | +0.181 |
��極 | +0.171 |
heit | +0.157 |
aneers | +0.154 |
adan | +0.152 |
Neg logit contributions | |
Kubrick | -0.095 |
tires | -0.082 |
chess | -0.082 |
Redd | -0.080 |
� | -0.076 |
Token | suit |
Token ID | 6050 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
Appearance | +0.332 |
��極 | +0.313 |
heit | +0.284 |
aneers | +0.278 |
adan | +0.273 |
Neg logit contributions | |
Kubrick | -0.243 |
tires | -0.216 |
chess | -0.215 |
Redd | -0.210 |
Pens | -0.202 |
Token | claimed |
Token ID | 4752 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Appearance | +0.954 |
��極 | +0.898 |
heit | +0.816 |
aneers | +0.802 |
adan | +0.788 |
Neg logit contributions | |
Kubrick | -0.644 |
tires | -0.567 |
chess | -0.566 |
Redd | -0.556 |
� | -0.531 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Kubrick | +0.878 |
tires | +0.775 |
chess | +0.768 |
Redd | +0.744 |
� | +0.713 |
Neg logit contributions | |
Appearance | -1.393 |
��極 | -1.311 |
heit | -1.188 |
aneers | -1.174 |
adan | -1.155 |
Token | Am |
Token ID | 1703 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Appearance | +0.193 |
��極 | +0.182 |
heit | +0.165 |
aneers | +0.162 |
adan | +0.159 |
Neg logit contributions | |
Kubrick | -0.135 |
tires | -0.119 |
chess | -0.119 |
Redd | -0.117 |
� | -0.111 |
Token | parties |
Token ID | 4671 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Appearance | +1.452 |
��極 | +1.352 |
heit | +1.212 |
aneers | +1.187 |
adan | +1.165 |
Neg logit contributions | |
Kubrick | -1.324 |
tires | -1.189 |
chess | -1.186 |
Redd | -1.169 |
� | -1.125 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Appearance | +2.320 |
��極 | +2.179 |
heit | +1.989 |
aneers | +1.955 |
adan | +1.928 |
Neg logit contributions | |
Kubrick | -1.489 |
tires | -1.307 |
chess | -1.300 |
Redd | -1.280 |
� | -1.221 |
Token | But |
Token ID | 887 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
Kubrick | +0.126 |
tires | +0.111 |
chess | +0.111 |
Redd | +0.109 |
Pens | +0.106 |
Neg logit contributions | |
Appearance | -0.159 |
��極 | -0.153 |
heit | -0.137 |
aneers | -0.134 |
adan | -0.131 |
Token | above |
Token ID | 2029 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Kubrick | +0.434 |
tires | +0.383 |
chess | +0.383 |
Redd | +0.369 |
Pens | +0.357 |
Neg logit contributions | |
Appearance | -0.637 |
��極 | -0.606 |
heit | -0.545 |
aneers | -0.538 |
adan | -0.525 |
Token | all |
Token ID | 477 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
Kubrick | +0.335 |
tires | +0.295 |
chess | +0.294 |
Redd | +0.287 |
� | +0.274 |
Neg logit contributions | |
Appearance | -0.517 |
��極 | -0.488 |
heit | -0.444 |
aneers | -0.436 |
adan | -0.429 |
Token | , |
Token ID | 11 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Kubrick | +0.571 |
tires | +0.498 |
chess | +0.498 |
Redd | +0.480 |
Pens | +0.460 |
Neg logit contributions | |
Appearance | -0.980 |
��極 | -0.932 |
heit | -0.845 |
aneers | -0.834 |
adan | -0.816 |
Token | the |
Token ID | 262 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Appearance | +0.482 |
��極 | +0.454 |
heit | +0.411 |
aneers | +0.404 |
adan | +0.396 |
Neg logit contributions | |
Kubrick | -0.339 |
tires | -0.300 |
chess | -0.299 |
Redd | -0.292 |
� | -0.280 |
Token | electoral |
Token ID | 13901 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Appearance | +0.617 |
��極 | +0.581 |
heit | +0.521 |
aneers | +0.510 |
adan | +0.500 |
Neg logit contributions | |
Kubrick | -0.523 |
tires | -0.470 |
chess | -0.469 |
Redd | -0.457 |
� | -0.441 |
Token | outcome |
Token ID | 8055 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Kubrick | +0.208 |
chess | +0.189 |
tires | +0.188 |
Redd | +0.181 |
Pens | +0.177 |
Neg logit contributions | |
Appearance | -0.243 |
��極 | -0.231 |
heit | -0.206 |
aneers | -0.202 |
adan | -0.197 |
Token | would |
Token ID | 561 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Kubrick | +0.184 |
tires | +0.162 |
chess | +0.161 |
Redd | +0.157 |
� | +0.150 |
Neg logit contributions | |
Appearance | -0.294 |
��極 | -0.278 |
heit | -0.253 |
aneers | -0.249 |
adan | -0.244 |
Token | probably |
Token ID | 2192 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
Kubrick | +0.233 |
tires | +0.209 |
chess | +0.208 |
Redd | +0.204 |
� | +0.196 |
Neg logit contributions | |
Appearance | -0.285 |
��極 | -0.267 |
heit | -0.240 |
aneers | -0.236 |
adan | -0.231 |
Token | to |
Token ID | 284 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Appearance | +1.886 |
��極 | +1.774 |
heit | +1.617 |
aneers | +1.584 |
adan | +1.561 |
Neg logit contributions | |
Kubrick | -1.244 |
tires | -1.096 |
chess | -1.091 |
Redd | -1.073 |
� | -1.023 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
Kubrick | +0.202 |
chess | +0.177 |
tires | +0.177 |
Redd | +0.173 |
Pens | +0.167 |
Neg logit contributions | |
Appearance | -0.280 |
��極 | -0.266 |
heit | -0.240 |
aneers | -0.236 |
adan | -0.231 |
Token | main |
Token ID | 1388 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Kubrick | +0.366 |
chess | +0.326 |
tires | +0.325 |
Redd | +0.314 |
Pens | +0.306 |
Neg logit contributions | |
Appearance | -0.491 |
��極 | -0.464 |
heit | -0.420 |
aneers | -0.414 |
adan | -0.405 |
Token | gate |
Token ID | 8946 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Appearance | +1.062 |
��極 | +0.998 |
heit | +0.902 |
aneers | +0.886 |
adan | +0.870 |
Neg logit contributions | |
Kubrick | -0.783 |
tires | -0.696 |
chess | -0.694 |
Redd | -0.680 |
� | -0.651 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Appearance | +0.205 |
��極 | +0.194 |
heit | +0.176 |
aneers | +0.174 |
adan | +0.171 |
Neg logit contributions | |
Kubrick | -0.130 |
tires | -0.114 |
chess | -0.114 |
Redd | -0.111 |
� | -0.106 |
Token | where |
Token ID | 810 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
Kubrick | +0.104 |
tires | +0.092 |
chess | +0.092 |
Redd | +0.089 |
Pens | +0.085 |
Neg logit contributions | |
Appearance | -0.155 |
��極 | -0.147 |
heit | -0.133 |
aneers | -0.131 |
adan | -0.129 |
Token | that |
Token ID | 326 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
Kubrick | +0.708 |
tires | +0.632 |
chess | +0.629 |
Redd | +0.614 |
Pens | +0.597 |
Neg logit contributions | |
Appearance | -0.806 |
��極 | -0.765 |
heit | -0.679 |
aneers | -0.669 |
adan | -0.654 |
Token | photo |
Token ID | 4590 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Kubrick | +0.510 |
tires | +0.452 |
chess | +0.452 |
Redd | +0.440 |
Pens | +0.421 |
Neg logit contributions | |
Appearance | -0.704 |
��極 | -0.663 |
heit | -0.600 |
aneers | -0.593 |
adan | -0.578 |
Token | he |
Token ID | 339 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
Appearance | +0.543 |
��極 | +0.513 |
heit | +0.467 |
aneers | +0.459 |
adan | +0.451 |
Neg logit contributions | |
Kubrick | -0.352 |
tires | -0.309 |
chess | -0.308 |
Redd | -0.299 |
� | -0.287 |
Token | instantly |
Token ID | 11101 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Kubrick | +0.005 |
tires | +0.005 |
chess | +0.005 |
Redd | +0.005 |
Pens | +0.004 |
Neg logit contributions | |
Appearance | -0.008 |
��極 | -0.008 |
heit | -0.007 |
aneers | -0.007 |
adan | -0.007 |
Token | recognized |
Token ID | 8018 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Appearance | +0.225 |
��極 | +0.211 |
heit | +0.191 |
aneers | +0.187 |
adan | +0.184 |
Neg logit contributions | |
Kubrick | -0.167 |
tires | -0.149 |
chess | -0.148 |
Redd | -0.145 |
� | -0.139 |
Token | ( |
Token ID | 7 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
Kubrick | +0.587 |
tires | +0.517 |
chess | +0.517 |
Redd | +0.502 |
Pens | +0.480 |
Neg logit contributions | |
Appearance | -0.932 |
��極 | -0.884 |
heit | -0.809 |
aneers | -0.795 |
adan | -0.779 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Kubrick | +0.596 |
tires | +0.535 |
chess | +0.533 |
Redd | +0.525 |
� | +0.505 |
Neg logit contributions | |
Appearance | -0.731 |
��極 | -0.688 |
heit | -0.616 |
aneers | -0.606 |
adan | -0.588 |
Token | ) |
Token ID | 8 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Kubrick | +0.914 |
tires | +0.810 |
chess | +0.809 |
Redd | +0.790 |
� | +0.756 |
Neg logit contributions | |
Appearance | -1.365 |
��極 | -1.286 |
heit | -1.170 |
aneers | -1.151 |
adan | -1.124 |
Token | of |
Token ID | 286 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Kubrick | +0.595 |
tires | +0.514 |
chess | +0.513 |
Redd | +0.496 |
� | +0.472 |
Neg logit contributions | |
Appearance | -1.134 |
��極 | -1.075 |
heit | -0.989 |
aneers | -0.973 |
adan | -0.957 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Kubrick | +0.817 |
chess | +0.720 |
tires | +0.712 |
Redd | +0.685 |
Pens | +0.669 |
Neg logit contributions | |
Appearance | -1.277 |
��極 | -1.208 |
heit | -1.103 |
aneers | -1.087 |
adan | -1.066 |
Token | Crimes |
Token ID | 32655 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Kubrick | +1.127 |
chess | +1.012 |
tires | +1.011 |
Redd | +0.974 |
Pens | +0.960 |
Neg logit contributions | |
Appearance | -1.320 |
��極 | -1.245 |
heit | -1.130 |
aneers | -1.116 |
adan | -1.086 |
Token | Act |
Token ID | 2191 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
Kubrick | +0.184 |
chess | +0.159 |
tires | +0.159 |
Redd | +0.153 |
Pens | +0.149 |
Neg logit contributions | |
Appearance | -0.319 |
��極 | -0.304 |
heit | -0.278 |
aneers | -0.274 |
adan | -0.270 |
Token | 1958 |
Token ID | 24648 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Kubrick | +0.058 |
tires | +0.051 |
chess | +0.051 |
Redd | +0.050 |
Pens | +0.048 |
Neg logit contributions | |
Appearance | -0.086 |
��極 | -0.081 |
heit | -0.074 |
aneers | -0.073 |
adan | -0.071 |
Token | ( |
Token ID | 357 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Kubrick | +0.896 |
tires | +0.788 |
chess | +0.786 |
Redd | +0.757 |
Pens | +0.729 |
Neg logit contributions | |
Appearance | -1.426 |
��極 | -1.351 |
heit | -1.233 |
aneers | -1.212 |
adan | -1.192 |
Token | V |
Token ID | 53 |
Feature activation | -3.23e-04 |
Pos logit contributions | |
Kubrick | +0.432 |
tires | +0.389 |
chess | +0.388 |
Redd | +0.384 |
� | +0.368 |
Neg logit contributions | |
Appearance | -0.510 |
��極 | -0.476 |
heit | -0.429 |
aneers | -0.420 |
adan | -0.409 |
Token | ic |
Token ID | 291 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
Kubrick | +0.000 |
tires | +0.000 |
chess | +0.000 |
Redd | +0.000 |
� | +0.000 |
Neg logit contributions | |
Appearance | -0.000 |
��極 | -0.000 |
heit | -0.000 |
aneers | -0.000 |
adan | -0.000 |
Token | core |
Token ID | 4755 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Kubrick | +0.185 |
tires | +0.153 |
chess | +0.152 |
Redd | +0.149 |
� | +0.139 |
Neg logit contributions | |
Appearance | -0.471 |
��極 | -0.446 |
heit | -0.414 |
aneers | -0.408 |
adan | -0.403 |
Token | right |
Token ID | 826 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Appearance | +0.469 |
��極 | +0.440 |
heit | +0.399 |
aneers | +0.392 |
adan | +0.386 |
Neg logit contributions | |
Kubrick | -0.333 |
tires | -0.295 |
chess | -0.294 |
Redd | -0.288 |
� | -0.277 |
Token | now |
Token ID | 783 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Kubrick | +0.194 |
tires | +0.177 |
chess | +0.177 |
Redd | +0.173 |
Pens | +0.168 |
Neg logit contributions | |
Appearance | -0.168 |
��極 | -0.158 |
heit | -0.137 |
aneers | -0.134 |
adan | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Kubrick | +0.444 |
tires | +0.393 |
chess | +0.391 |
Redd | +0.383 |
� | +0.366 |
Neg logit contributions | |
Appearance | -0.651 |
��極 | -0.616 |
heit | -0.556 |
aneers | -0.547 |
adan | -0.538 |
Token | I |
Token ID | 314 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Kubrick | +0.423 |
tires | +0.384 |
chess | +0.383 |
Redd | +0.378 |
� | +0.365 |
Neg logit contributions | |
Appearance | -0.391 |
��極 | -0.362 |
heit | -0.320 |
aneers | -0.313 |
adan | -0.306 |
Token | 'm |
Token ID | 1101 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
Kubrick | +1.288 |
tires | +1.162 |
chess | +1.154 |
Redd | +1.117 |
Pens | +1.081 |
Neg logit contributions | |
Appearance | -1.545 |
��極 | -1.475 |
heit | -1.294 |
aneers | -1.274 |
�� | -1.238 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Kubrick | +0.504 |
tires | +0.440 |
chess | +0.439 |
Redd | +0.423 |
Pens | +0.402 |
Neg logit contributions | |
Appearance | -0.878 |
��極 | -0.837 |
heit | -0.750 |
aneers | -0.749 |
adan | -0.731 |
Token | nan |
Token ID | 15709 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Kubrick | +0.716 |
chess | +0.618 |
tires | +0.617 |
Redd | +0.595 |
Pens | +0.566 |
Neg logit contributions | |
Appearance | -1.319 |
��極 | -1.254 |
heit | -1.142 |
aneers | -1.127 |
adan | -1.105 |
Token | ocl |
Token ID | 38679 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Kubrick | +0.347 |
tires | +0.310 |
chess | +0.309 |
Redd | +0.303 |
� | +0.291 |
Neg logit contributions | |
Appearance | -0.430 |
��極 | -0.402 |
heit | -0.363 |
aneers | -0.356 |
adan | -0.349 |
Token | oud |
Token ID | 2778 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Kubrick | +0.204 |
tires | +0.181 |
chess | +0.180 |
Redd | +0.177 |
� | +0.170 |
Neg logit contributions | |
Appearance | -0.265 |
��極 | -0.252 |
heit | -0.220 |
aneers | -0.217 |
�� | -0.214 |
Token | wasn |
Token ID | 2492 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Appearance | +0.112 |
��極 | +0.104 |
heit | +0.098 |
adan | +0.096 |
aneers | +0.096 |
Neg logit contributions | |
Kubrick | -0.055 |
chess | -0.047 |
Redd | -0.046 |
tires | -0.046 |
� | -0.043 |
Token | � |
Token ID | 564 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
Appearance | +0.196 |
��極 | +0.185 |
heit | +0.168 |
aneers | +0.164 |
adan | +0.162 |
Neg logit contributions | |
Kubrick | -0.144 |
tires | -0.128 |
chess | -0.127 |
Redd | -0.124 |
Pens | -0.119 |
Token | � |
Token ID | 250 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
Appearance | +0.032 |
��極 | +0.030 |
heit | +0.027 |
aneers | +0.026 |
adan | +0.026 |
Neg logit contributions | |
Kubrick | -0.031 |
tires | -0.028 |
chess | -0.028 |
Redd | -0.027 |
� | -0.026 |
Token | in |
Token ID | 259 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Appearance | +0.074 |
��極 | +0.070 |
heit | +0.062 |
aneers | +0.061 |
adan | +0.059 |
Neg logit contributions | |
Kubrick | -0.064 |
tires | -0.057 |
chess | -0.057 |
Redd | -0.056 |
� | -0.054 |
Token | fer |
Token ID | 2232 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
Appearance | +1.030 |
��極 | +0.952 |
heit | +0.827 |
aneers | +0.805 |
adan | +0.785 |
Neg logit contributions | |
Kubrick | -1.318 |
tires | -1.206 |
chess | -1.205 |
Redd | -1.186 |
� | -1.151 |
Token | ior |
Token ID | 1504 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Appearance | +0.669 |
��極 | +0.622 |
heit | +0.547 |
aneers | +0.534 |
adan | +0.522 |
Neg logit contributions | |
Kubrick | -0.734 |
tires | -0.669 |
chess | -0.666 |
Redd | -0.656 |
Pens | -0.634 |
Token | � |
Token ID | 447 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Kubrick | +0.755 |
chess | +0.652 |
tires | +0.649 |
Redd | +0.621 |
Pens | +0.595 |
Neg logit contributions | |
Appearance | -1.476 |
��極 | -1.418 |
heit | -1.292 |
aneers | -1.274 |
adan | -1.250 |
Token | � |
Token ID | 251 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Kubrick | +0.475 |
tires | +0.431 |
chess | +0.431 |
Redd | +0.423 |
� | +0.411 |
Neg logit contributions | |
Appearance | -0.422 |
��極 | -0.390 |
heit | -0.342 |
aneers | -0.338 |
adan | -0.329 |
Token | races |
Token ID | 9558 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
Kubrick | +0.715 |
tires | +0.632 |
chess | +0.632 |
Redd | +0.614 |
Pens | +0.589 |
Neg logit contributions | |
Appearance | -1.020 |
��極 | -0.968 |
heit | -0.870 |
aneers | -0.856 |
adan | -0.842 |
Token | . |
Token ID | 13 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Appearance | +0.068 |
��極 | +0.064 |
heit | +0.058 |
aneers | +0.057 |
adan | +0.056 |
Neg logit contributions | |
Kubrick | -0.043 |
tires | -0.038 |
chess | -0.038 |
Redd | -0.037 |
� | -0.035 |
Token | With |
Token ID | 2080 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
Kubrick | +0.387 |
tires | +0.343 |
chess | +0.342 |
Redd | +0.336 |
Pens | +0.326 |
Neg logit contributions | |
Appearance | -0.443 |
��極 | -0.422 |
heit | -0.378 |
aneers | -0.370 |
adan | -0.363 |
Token | the |
Token ID | 262 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Appearance | +0.027 |
��極 | +0.026 |
heit | +0.023 |
aneers | +0.023 |
adan | +0.022 |
Neg logit contributions | |
Kubrick | -0.020 |
tires | -0.018 |
chess | -0.018 |
Redd | -0.017 |
Pens | -0.017 |
Token | as |
Token ID | 355 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Kubrick | +0.173 |
tires | +0.152 |
chess | +0.152 |
Redd | +0.146 |
Pens | +0.140 |
Neg logit contributions | |
Appearance | -0.284 |
��極 | -0.270 |
heit | -0.244 |
aneers | -0.241 |
adan | -0.236 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Appearance | +0.536 |
��極 | +0.501 |
heit | +0.456 |
aneers | +0.446 |
adan | +0.442 |
Neg logit contributions | |
Kubrick | -0.383 |
tires | -0.337 |
chess | -0.336 |
Redd | -0.334 |
� | -0.319 |
Token | clock |
Token ID | 8801 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Appearance | +0.136 |
��極 | +0.128 |
heit | +0.116 |
aneers | +0.114 |
adan | +0.112 |
Neg logit contributions | |
Kubrick | -0.094 |
tires | -0.083 |
chess | -0.082 |
Redd | -0.081 |
� | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
Appearance | +0.137 |
��極 | +0.129 |
heit | +0.118 |
aneers | +0.116 |
adan | +0.114 |
Neg logit contributions | |
Kubrick | -0.086 |
tires | -0.076 |
chess | -0.076 |
Redd | -0.074 |
� | -0.071 |
Token | Y |
Token ID | 575 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
Kubrick | +0.034 |
tires | +0.031 |
chess | +0.031 |
Redd | +0.030 |
� | +0.029 |
Neg logit contributions | |
Appearance | -0.041 |
��極 | -0.038 |
heit | -0.035 |
aneers | -0.034 |
adan | -0.033 |
Token | up |
Token ID | 929 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
Kubrick | +0.774 |
tires | +0.703 |
chess | +0.700 |
Redd | +0.687 |
� | +0.669 |
Neg logit contributions | |
Appearance | -0.787 |
��極 | -0.738 |
heit | -0.654 |
aneers | -0.639 |
adan | -0.620 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Kubrick | +0.513 |
tires | +0.452 |
chess | +0.449 |
Redd | +0.436 |
� | +0.417 |
Neg logit contributions | |
Appearance | -0.818 |
��極 | -0.776 |
heit | -0.705 |
aneers | -0.694 |
adan | -0.681 |
Token | the |
Token ID | 262 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Kubrick | +0.776 |
tires | +0.689 |
chess | +0.687 |
Redd | +0.665 |
Pens | +0.639 |
Neg logit contributions | |
Appearance | -1.115 |
��極 | -1.056 |
heit | -0.954 |
aneers | -0.939 |
adan | -0.920 |
Token | Rebel |
Token ID | 24551 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Kubrick | +0.126 |
tires | +0.112 |
chess | +0.112 |
Redd | +0.109 |
Pens | +0.105 |
Neg logit contributions | |
Appearance | -0.168 |
��極 | -0.158 |
heit | -0.143 |
aneers | -0.140 |
adan | -0.138 |
Token | Alliance |
Token ID | 10302 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Appearance | +0.490 |
��極 | +0.457 |
heit | +0.406 |
aneers | +0.397 |
adan | +0.388 |
Neg logit contributions | |
Kubrick | -0.500 |
tires | -0.454 |
chess | -0.453 |
Redd | -0.444 |
Pens | -0.430 |
Token | thought |
Token ID | 1807 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Appearance | +1.477 |
��極 | +1.394 |
heit | +1.271 |
aneers | +1.249 |
adan | +1.229 |
Neg logit contributions | |
Kubrick | -0.911 |
tires | -0.798 |
chess | -0.795 |
Redd | -0.778 |
� | -0.741 |
Token | Trump |
Token ID | 1301 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Kubrick | +0.383 |
tires | +0.332 |
chess | +0.331 |
Redd | +0.321 |
Pens | +0.308 |
Neg logit contributions | |
Appearance | -0.671 |
��極 | -0.635 |
heit | -0.581 |
aneers | -0.573 |
adan | -0.563 |
Token | profess |
Token ID | 2992 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Kubrick | +0.212 |
tires | +0.187 |
chess | +0.185 |
Redd | +0.178 |
Pens | +0.173 |
Neg logit contributions | |
Appearance | -0.339 |
��極 | -0.323 |
heit | -0.293 |
aneers | -0.290 |
adan | -0.283 |
Token | es |
Token ID | 274 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Kubrick | +0.769 |
tires | +0.688 |
chess | +0.685 |
Redd | +0.670 |
� | +0.644 |
Neg logit contributions | |
Appearance | -0.999 |
��極 | -0.940 |
heit | -0.845 |
aneers | -0.830 |
adan | -0.816 |
Token | not |
Token ID | 407 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Kubrick | +0.083 |
tires | +0.074 |
chess | +0.073 |
Redd | +0.072 |
� | +0.069 |
Neg logit contributions | |
Appearance | -0.122 |
��極 | -0.115 |
heit | -0.105 |
aneers | -0.103 |
adan | -0.101 |
Token | to |
Token ID | 284 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
Appearance | +0.431 |
��極 | +0.406 |
heit | +0.370 |
aneers | +0.363 |
adan | +0.358 |
Neg logit contributions | |
Kubrick | -0.277 |
tires | -0.243 |
chess | -0.243 |
Redd | -0.239 |
� | -0.227 |
Token | understand |
Token ID | 1833 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Kubrick | +0.655 |
tires | +0.585 |
chess | +0.582 |
Redd | +0.561 |
Pens | +0.543 |
Neg logit contributions | |
Appearance | -0.900 |
��極 | -0.856 |
heit | -0.768 |
aneers | -0.758 |
adan | -0.739 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Kubrick | +1.971 |
chess | +1.762 |
tires | +1.750 |
Redd | +1.661 |
Pens | +1.638 |
Neg logit contributions | |
Appearance | -2.862 |
��極 | -2.764 |
heit | -2.476 |
aneers | -2.465 |
adan | -2.380 |
Token | phenomenon |
Token ID | 10733 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Kubrick | +0.104 |
tires | +0.092 |
chess | +0.091 |
Redd | +0.090 |
� | +0.086 |
Neg logit contributions | |
Appearance | -0.139 |
��極 | -0.130 |
heit | -0.118 |
aneers | -0.115 |
adan | -0.114 |
Token | of |
Token ID | 286 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
Kubrick | +0.099 |
tires | +0.086 |
chess | +0.086 |
Redd | +0.083 |
Pens | +0.080 |
Neg logit contributions | |
Appearance | -0.173 |
��極 | -0.164 |
heit | -0.150 |
aneers | -0.148 |
adan | -0.145 |
Token | the |
Token ID | 262 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
Kubrick | +0.002 |
tires | +0.001 |
chess | +0.001 |
Redd | +0.001 |
� | +0.001 |
Neg logit contributions | |
Appearance | -0.002 |
��極 | -0.002 |
heit | -0.002 |
aneers | -0.002 |
adan | -0.002 |
Token | expectations |
Token ID | 9027 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Kubrick | +0.610 |
tires | +0.543 |
chess | +0.542 |
Redd | +0.527 |
Pens | +0.507 |
Neg logit contributions | |
Appearance | -0.828 |
��極 | -0.780 |
heit | -0.707 |
aneers | -0.694 |
adan | -0.681 |
Token | text |
Token ID | 2420 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
Kubrick | +0.300 |
tires | +0.262 |
chess | +0.261 |
Redd | +0.253 |
Pens | +0.241 |
Neg logit contributions | |
Appearance | -0.537 |
��極 | -0.511 |
heit | -0.465 |
aneers | -0.459 |
adan | -0.451 |
Token | can |
Token ID | 460 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Kubrick | +0.496 |
tires | +0.436 |
chess | +0.435 |
Redd | +0.419 |
Pens | +0.403 |
Neg logit contributions | |
Appearance | -0.816 |
��極 | -0.779 |
heit | -0.704 |
aneers | -0.694 |
adan | -0.684 |
Token | go |
Token ID | 467 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Kubrick | +0.133 |
tires | +0.118 |
chess | +0.118 |
Redd | +0.114 |
Pens | +0.110 |
Neg logit contributions | |
Appearance | -0.186 |
��極 | -0.177 |
heit | -0.158 |
aneers | -0.156 |
adan | -0.153 |
Token | in |
Token ID | 287 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Kubrick | +0.266 |
tires | +0.234 |
chess | +0.233 |
Redd | +0.227 |
� | +0.216 |
Neg logit contributions | |
Appearance | -0.433 |
��極 | -0.410 |
heit | -0.373 |
aneers | -0.367 |
adan | -0.361 |
Token | each |
Token ID | 1123 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Appearance | +0.464 |
��極 | +0.436 |
heit | +0.396 |
aneers | +0.388 |
adan | +0.382 |
Neg logit contributions | |
Kubrick | -0.330 |
tires | -0.292 |
chess | -0.291 |
Redd | -0.285 |
� | -0.273 |
Token | text |
Token ID | 2420 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
Appearance | +1.102 |
��極 | +1.028 |
heit | +0.939 |
aneers | +0.919 |
adan | +0.905 |
Neg logit contributions | |
Kubrick | -0.744 |
tires | -0.655 |
chess | -0.650 |
Redd | -0.643 |
� | -0.617 |
Token | box |
Token ID | 3091 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Kubrick | +1.981 |
chess | +1.804 |
tires | +1.778 |
Redd | +1.696 |
Pens | +1.671 |
Neg logit contributions | |
Appearance | -2.718 |
��極 | -2.632 |
heit | -2.336 |
aneers | -2.325 |
adan | -2.260 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Kubrick | +1.133 |
chess | +0.998 |
tires | +0.998 |
Redd | +0.956 |
Pens | +0.923 |
Neg logit contributions | |
Appearance | -1.806 |
��極 | -1.731 |
heit | -1.559 |
aneers | -1.540 |
adan | -1.508 |
Token |
|
Token ID | 198 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Kubrick | +0.086 |
tires | +0.076 |
chess | +0.076 |
Redd | +0.074 |
Pens | +0.072 |
Neg logit contributions | |
Appearance | -0.110 |
��極 | -0.104 |
heit | -0.094 |
aneers | -0.092 |
adan | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
Appearance | +0.491 |
��極 | +0.453 |
heit | +0.417 |
aneers | +0.409 |
adan | +0.403 |
Neg logit contributions | |
Kubrick | -0.353 |
chess | -0.313 |
tires | -0.312 |
Redd | -0.306 |
� | -0.295 |
Token | The |
Token ID | 464 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
Appearance | +0.588 |
��極 | +0.548 |
heit | +0.492 |
aneers | +0.482 |
adan | +0.473 |
Neg logit contributions | |
Kubrick | -0.521 |
tires | -0.468 |
chess | -0.467 |
Redd | -0.458 |
� | -0.442 |
Token | be |
Token ID | 307 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Kubrick | +0.281 |
tires | +0.252 |
chess | +0.251 |
Redd | +0.242 |
Pens | +0.234 |
Neg logit contributions | |
Appearance | -0.377 |
��極 | -0.359 |
heit | -0.320 |
aneers | -0.315 |
adan | -0.309 |
Token | very |
Token ID | 845 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Kubrick | +0.769 |
tires | +0.684 |
chess | +0.677 |
Redd | +0.659 |
Pens | +0.629 |
Neg logit contributions | |
Appearance | -1.148 |
��極 | -1.089 |
heit | -0.983 |
aneers | -0.968 |
adan | -0.949 |
Token | tough |
Token ID | 5802 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Appearance | +0.324 |
��極 | +0.306 |
heit | +0.276 |
aneers | +0.272 |
adan | +0.267 |
Neg logit contributions | |
Kubrick | -0.229 |
tires | -0.204 |
chess | -0.203 |
Redd | -0.198 |
Pens | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Appearance | +0.290 |
��極 | +0.273 |
heit | +0.249 |
aneers | +0.244 |
adan | +0.240 |
Neg logit contributions | |
Kubrick | -0.188 |
tires | -0.165 |
chess | -0.164 |
Redd | -0.161 |
� | -0.154 |
Token | If |
Token ID | 1002 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
Kubrick | +0.435 |
tires | +0.388 |
chess | +0.386 |
Redd | +0.379 |
Pens | +0.366 |
Neg logit contributions | |
Appearance | -0.520 |
��極 | -0.494 |
heit | -0.442 |
aneers | -0.433 |
adan | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
Kubrick | +0.634 |
tires | +0.573 |
chess | +0.569 |
Redd | +0.554 |
Pens | +0.534 |
Neg logit contributions | |
Appearance | -0.739 |
��極 | -0.699 |
heit | -0.621 |
aneers | -0.611 |
adan | -0.597 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Kubrick | +1.884 |
tires | +1.656 |
chess | +1.624 |
Redd | +1.597 |
Pens | +1.524 |
Neg logit contributions | |
Appearance | -3.151 |
��極 | -3.101 |
heit | -2.723 |
aneers | -2.694 |
�� | -2.660 |
Token | something |
Token ID | 18927 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Kubrick | +2.154 |
tires | +1.989 |
Redd | +1.968 |
chess | +1.960 |
� | +1.877 |
Neg logit contributions | |
Appearance | -1.714 |
��極 | -1.615 |
heit | -1.348 |
aneers | -1.335 |
�� | -1.287 |
Token | has |
Token ID | 468 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Appearance | +0.371 |
��極 | +0.347 |
heit | +0.317 |
aneers | +0.311 |
adan | +0.306 |
Neg logit contributions | |
Kubrick | -0.250 |
tires | -0.220 |
chess | -0.220 |
Redd | -0.217 |
� | -0.207 |
Token | to |
Token ID | 284 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Kubrick | +1.048 |
tires | +0.922 |
chess | +0.912 |
Redd | +0.877 |
� | +0.839 |
Neg logit contributions | |
Appearance | -1.678 |
��極 | -1.608 |
heit | -1.442 |
aneers | -1.427 |
adan | -1.403 |
Token | be |
Token ID | 307 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Kubrick | +1.197 |
tires | +1.084 |
chess | +1.068 |
Redd | +1.012 |
Pens | +0.981 |
Neg logit contributions | |
Appearance | -1.562 |
��極 | -1.511 |
heit | -1.310 |
aneers | -1.305 |
adan | -1.271 |
Token | news |
Token ID | 1705 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Appearance | +1.274 |
��極 | +1.192 |
heit | +1.105 |
aneers | +1.086 |
adan | +1.069 |
Neg logit contributions | |
Kubrick | -0.712 |
tires | -0.614 |
chess | -0.612 |
Redd | -0.602 |
� | -0.573 |
Token | pl |
Token ID | 458 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Kubrick | +0.599 |
tires | +0.500 |
chess | +0.499 |
Redd | +0.481 |
� | +0.448 |
Neg logit contributions | |
Appearance | -1.480 |
��極 | -1.413 |
heit | -1.301 |
aneers | -1.284 |
adan | -1.265 |
Token | s |
Token ID | 82 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Kubrick | +0.712 |
tires | +0.629 |
chess | +0.623 |
Redd | +0.610 |
Pens | +0.584 |
Neg logit contributions | |
Appearance | -1.072 |
��極 | -1.023 |
heit | -0.916 |
aneers | -0.901 |
adan | -0.883 |
Token | . |
Token ID | 13 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Kubrick | +0.793 |
tires | +0.697 |
chess | +0.693 |
Redd | +0.678 |
Pens | +0.645 |
Neg logit contributions | |
Appearance | -1.214 |
��極 | -1.167 |
heit | -1.041 |
aneers | -1.027 |
adan | -1.009 |
Token | Writer |
Token ID | 26606 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Kubrick | +0.357 |
chess | +0.319 |
tires | +0.318 |
Redd | +0.310 |
Pens | +0.299 |
Neg logit contributions | |
Appearance | -0.454 |
��極 | -0.432 |
heit | -0.388 |
aneers | -0.382 |
adan | -0.372 |
Token | " |
Token ID | 366 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
Kubrick | +1.837 |
chess | +1.652 |
tires | +1.629 |
Redd | +1.559 |
Pens | +1.528 |
Neg logit contributions | |
Appearance | -2.428 |
��極 | -2.340 |
heit | -2.097 |
aneers | -2.092 |
adan | -2.006 |
Token | I |
Token ID | 40 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Kubrick | +2.862 |
chess | +2.599 |
tires | +2.589 |
Redd | +2.563 |
� | +2.455 |
Neg logit contributions | |
Appearance | -3.263 |
��極 | -3.108 |
heit | -2.741 |
aneers | -2.715 |
adan | -2.622 |
Token | was |
Token ID | 373 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
Kubrick | +0.717 |
tires | +0.640 |
chess | +0.639 |
Redd | +0.615 |
Pens | +0.596 |
Neg logit contributions | |
Appearance | -0.922 |
��極 | -0.869 |
heit | -0.778 |
aneers | -0.770 |
adan | -0.750 |
Token | born |
Token ID | 4642 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Appearance | +0.029 |
��極 | +0.027 |
heit | +0.024 |
aneers | +0.024 |
adan | +0.023 |
Neg logit contributions | |
Kubrick | -0.021 |
tires | -0.019 |
chess | -0.019 |
Redd | -0.018 |
� | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
Appearance | +1.300 |
��極 | +1.221 |
heit | +1.117 |
aneers | +1.094 |
adan | +1.081 |
Neg logit contributions | |
Kubrick | -0.820 |
tires | -0.719 |
chess | -0.711 |
Redd | -0.705 |
� | -0.671 |
Token | the |
Token ID | 262 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
Appearance | +0.889 |
��極 | +0.830 |
heit | +0.754 |
aneers | +0.736 |
adan | +0.726 |
Neg logit contributions | |
Kubrick | -0.653 |
tires | -0.579 |
chess | -0.574 |
Redd | -0.571 |
� | -0.548 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Kubrick | +0.173 |
tires | +0.153 |
chess | +0.152 |
Redd | +0.149 |
� | +0.143 |
Neg logit contributions | |
Appearance | -0.251 |
��極 | -0.235 |
heit | -0.214 |
aneers | -0.210 |
adan | -0.207 |
Token | H |
Token ID | 39 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
Appearance | +0.021 |
��極 | +0.020 |
heit | +0.018 |
aneers | +0.018 |
adan | +0.017 |
Neg logit contributions | |
Kubrick | -0.017 |
tires | -0.015 |
chess | -0.015 |
Redd | -0.015 |
� | -0.014 |
Token | att |
Token ID | 1078 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Appearance | +0.061 |
��極 | +0.057 |
heit | +0.050 |
aneers | +0.049 |
adan | +0.048 |
Neg logit contributions | |
Kubrick | -0.059 |
tires | -0.053 |
chess | -0.053 |
Redd | -0.052 |
� | -0.050 |
Token | if |
Token ID | 361 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Appearance | +1.392 |
��極 | +1.301 |
heit | +1.165 |
aneers | +1.142 |
adan | +1.120 |
Neg logit contributions | |
Kubrick | -1.228 |
tires | -1.104 |
chess | -1.101 |
Redd | -1.081 |
� | -1.041 |
Token | att |
Token ID | 1078 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Kubrick | +0.900 |
chess | +0.801 |
tires | +0.801 |
Redd | +0.779 |
Pens | +0.760 |
Neg logit contributions | |
Appearance | -1.022 |
��極 | -0.971 |
heit | -0.852 |
aneers | -0.843 |
�� | -0.823 |
Token | eners |
Token ID | 36014 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Kubrick | +0.886 |
chess | +0.793 |
tires | +0.793 |
Redd | +0.764 |
Pens | +0.756 |
Neg logit contributions | |
Appearance | -1.024 |
��極 | -0.967 |
heit | -0.851 |
aneers | -0.844 |
�� | -0.823 |
Token | [ |
Token ID | 58 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Kubrick | +2.671 |
chess | +2.371 |
tires | +2.359 |
Redd | +2.249 |
Pens | +2.211 |
Neg logit contributions | |
Appearance | -3.659 |
��極 | -3.502 |
heit | -3.109 |
aneers | -3.093 |
�� | -3.000 |
Token | 28 |
Token ID | 2078 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Kubrick | +0.859 |
tires | +0.772 |
chess | +0.770 |
Redd | +0.761 |
� | +0.729 |
Neg logit contributions | |
Appearance | -0.888 |
��極 | -0.842 |
heit | -0.742 |
aneers | -0.728 |
adan | -0.711 |
Token | ] |
Token ID | 60 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Kubrick | +0.884 |
tires | +0.780 |
chess | +0.780 |
Redd | +0.760 |
� | +0.730 |
Neg logit contributions | |
Appearance | -1.307 |
��極 | -1.231 |
heit | -1.116 |
aneers | -1.100 |
adan | -1.077 |
Token | is |
Token ID | 318 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
Kubrick | +0.206 |
tires | +0.182 |
chess | +0.181 |
Redd | +0.176 |
Pens | +0.169 |
Neg logit contributions | |
Appearance | -0.300 |
��極 | -0.284 |
heit | -0.257 |
aneers | -0.253 |
adan | -0.248 |
Token | an |
Token ID | 281 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Kubrick | +0.504 |
tires | +0.444 |
chess | +0.443 |
Redd | +0.431 |
Pens | +0.414 |
Neg logit contributions | |
Appearance | -0.720 |
��極 | -0.679 |
heit | -0.613 |
aneers | -0.605 |
adan | -0.593 |