Token | Atomic |
Token ID | 28976 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
acs | +0.298 |
olla | +0.297 |
ktop | +0.297 |
rog | +0.292 |
impaired | +0.285 |
Neg logit contributions | |
Yao | -0.247 |
Debor | -0.219 |
intern | -0.214 |
JC | -0.213 |
Spencer | -0.213 |
Token | < |
Token ID | 1279 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
acs | +0.276 |
olla | +0.276 |
ktop | +0.276 |
rog | +0.271 |
impaired | +0.265 |
Neg logit contributions | |
Yao | -0.224 |
Debor | -0.198 |
intern | -0.193 |
JC | -0.193 |
Spencer | -0.193 |
Token | T |
Token ID | 309 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Yao | +0.707 |
Debor | +0.626 |
intern | +0.620 |
JC | +0.617 |
Spencer | +0.617 |
Neg logit contributions | |
acs | -0.761 |
ktop | -0.760 |
olla | -0.758 |
rog | -0.748 |
impaired | -0.725 |
Token | > |
Token ID | 1875 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Yao | +1.133 |
Debor | +0.962 |
JC | +0.950 |
intern | +0.948 |
Spencer | +0.946 |
Neg logit contributions | |
acs | -1.974 |
ktop | -1.973 |
olla | -1.960 |
rog | -1.940 |
impaired | -1.900 |
Token | { |
Token ID | 1391 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
acs | +0.357 |
olla | +0.356 |
ktop | +0.356 |
rog | +0.348 |
impaired | +0.337 |
Neg logit contributions | |
Yao | -0.509 |
Debor | -0.464 |
intern | -0.456 |
JC | -0.456 |
Spencer | -0.455 |
Token | /// |
Token ID | 34013 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
Yao | +1.946 |
intern | +1.735 |
Debor | +1.727 |
Spencer | +1.718 |
JC | +1.692 |
Neg logit contributions | |
acs | -1.992 |
ktop | -1.978 |
olla | -1.975 |
rog | -1.949 |
impaired | -1.878 |
Token | Create |
Token ID | 13610 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Yao | +4.173 |
intern | +3.768 |
Debor | +3.731 |
Spencer | +3.647 |
JC | +3.638 |
Neg logit contributions | |
acs | -4.309 |
ktop | -4.300 |
olla | -4.285 |
rog | -4.179 |
lime | -4.086 |
Token | a |
Token ID | 257 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Yao | +2.188 |
intern | +1.984 |
Debor | +1.974 |
JC | +1.944 |
Spencer | +1.932 |
Neg logit contributions | |
acs | -1.772 |
olla | -1.769 |
ktop | -1.768 |
rog | -1.729 |
impaired | -1.655 |
Token | new |
Token ID | 649 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Yao | +1.235 |
Debor | +1.112 |
intern | +1.103 |
JC | +1.094 |
Spencer | +1.090 |
Neg logit contributions | |
acs | -1.039 |
ktop | -1.037 |
olla | -1.033 |
rog | -1.013 |
impaired | -0.977 |
Token | , |
Token ID | 11 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Yao | +0.725 |
Debor | +0.646 |
intern | +0.639 |
JC | +0.631 |
Spencer | +0.629 |
Neg logit contributions | |
acs | -0.777 |
olla | -0.775 |
ktop | -0.774 |
rog | -0.760 |
impaired | -0.738 |
Token | null |
Token ID | 9242 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
Yao | +0.741 |
intern | +0.664 |
Debor | +0.664 |
JC | +0.655 |
unden | +0.654 |
Neg logit contributions | |
acs | -0.660 |
ktop | -0.659 |
olla | -0.658 |
rog | -0.645 |
lime | -0.618 |
Token | our |
Token ID | 674 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Yao | +0.283 |
Debor | +0.256 |
intern | +0.251 |
JC | +0.251 |
Spencer | +0.251 |
Neg logit contributions | |
ktop | -0.237 |
olla | -0.237 |
acs | -0.236 |
rog | -0.231 |
impaired | -0.224 |
Token | work |
Token ID | 670 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Yao | +0.372 |
Debor | +0.336 |
intern | +0.329 |
JC | +0.329 |
Spencer | +0.328 |
Neg logit contributions | |
olla | -0.343 |
acs | -0.342 |
ktop | -0.342 |
rog | -0.334 |
impaired | -0.326 |
Token | is |
Token ID | 318 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
olla | +0.635 |
ktop | +0.633 |
acs | +0.630 |
rog | +0.614 |
impaired | +0.594 |
Neg logit contributions | |
Yao | -0.890 |
Debor | -0.810 |
intern | -0.801 |
JC | -0.801 |
Spencer | -0.797 |
Token | appreciated |
Token ID | 16373 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Yao | +0.610 |
Debor | +0.566 |
unden | +0.551 |
•• | +0.549 |
Spencer | +0.546 |
Neg logit contributions | |
acs | -0.434 |
olla | -0.425 |
rog | -0.421 |
impaired | -0.416 |
ktop | -0.413 |
Token | . |
Token ID | 13 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
Yao | +0.855 |
JC | +0.764 |
Debor | +0.762 |
intern | +0.756 |
Spencer | +0.748 |
Neg logit contributions | |
olla | -0.950 |
ktop | -0.944 |
acs | -0.933 |
rog | -0.921 |
neur | -0.896 |
Token | Please |
Token ID | 4222 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
Yao | +0.709 |
Debor | +0.634 |
Spencer | +0.622 |
JC | +0.619 |
intern | +0.614 |
Neg logit contributions | |
ktop | -0.755 |
olla | -0.749 |
acs | -0.744 |
rog | -0.731 |
impaired | -0.713 |
Token | click |
Token ID | 3904 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
Yao | +3.420 |
intern | +3.121 |
JC | +3.078 |
Spencer | +3.044 |
EB | +3.010 |
Neg logit contributions | |
ktop | -4.662 |
olla | -4.599 |
acs | -4.403 |
\/\/ | -4.285 |
rog | -4.254 |
Token | below |
Token ID | 2174 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Yao | +2.487 |
JC | +2.145 |
EB | +2.139 |
intern | +2.135 |
Spencer | +2.132 |
Neg logit contributions | |
olla | -2.819 |
ktop | -2.800 |
acs | -2.735 |
lime | -2.631 |
phthal | -2.602 |
Token | to |
Token ID | 284 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
ktop | +0.225 |
olla | +0.224 |
acs | +0.224 |
rog | +0.219 |
impaired | +0.213 |
Neg logit contributions | |
Yao | -0.244 |
Debor | -0.219 |
JC | -0.216 |
intern | -0.215 |
Spencer | -0.214 |
Token | become |
Token ID | 1716 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Yao | +0.790 |
Spencer | +0.727 |
Debor | +0.726 |
intern | +0.724 |
JC | +0.724 |
Neg logit contributions | |
ktop | -0.509 |
olla | -0.505 |
acs | -0.489 |
rog | -0.477 |
impaired | -0.464 |
Token | an |
Token ID | 281 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Yao | +0.536 |
Debor | +0.489 |
intern | +0.480 |
Spencer | +0.479 |
JC | +0.477 |
Neg logit contributions | |
ktop | -0.457 |
olla | -0.456 |
acs | -0.447 |
rog | -0.437 |
\/\/ | -0.430 |
Token | me |
Token ID | 502 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
olla | +0.434 |
acs | +0.434 |
ktop | +0.433 |
rog | +0.427 |
impaired | +0.419 |
Neg logit contributions | |
Yao | -0.261 |
Debor | -0.226 |
intern | -0.218 |
JC | -0.218 |
Spencer | -0.217 |
Token | feel |
Token ID | 1254 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Yao | +1.129 |
intern | +1.003 |
Spencer | +1.001 |
JC | +1.000 |
Debor | +1.000 |
Neg logit contributions | |
ktop | -0.967 |
olla | -0.955 |
acs | -0.942 |
rog | -0.928 |
impaired | -0.891 |
Token | all |
Token ID | 477 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
acs | +1.034 |
olla | +1.034 |
ktop | +1.029 |
rog | +1.011 |
impaired | +0.986 |
Neg logit contributions | |
Yao | -1.265 |
Debor | -1.152 |
intern | -1.123 |
JC | -1.123 |
Spencer | -1.121 |
Token | sort |
Token ID | 3297 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Yao | +0.235 |
Debor | +0.211 |
Spencer | +0.209 |
intern | +0.209 |
JC | +0.208 |
Neg logit contributions | |
olla | -0.187 |
ktop | -0.187 |
acs | -0.186 |
rog | -0.182 |
impaired | -0.174 |
Token | of |
Token ID | 286 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
Yao | +2.084 |
JC | +1.856 |
Spencer | +1.854 |
intern | +1.852 |
Debor | +1.842 |
Neg logit contributions | |
ktop | -1.900 |
acs | -1.891 |
olla | -1.879 |
rog | -1.845 |
impaired | -1.791 |
Token | -" |
Token ID | 21215 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Yao | +0.074 |
Debor | +0.067 |
intern | +0.066 |
JC | +0.065 |
Spencer | +0.065 |
Neg logit contributions | |
olla | -0.061 |
ktop | -0.061 |
acs | -0.061 |
rog | -0.059 |
impaired | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Yao | +4.139 |
Spencer | +3.714 |
Debor | +3.672 |
JC | +3.650 |
intern | +3.581 |
Neg logit contributions | |
ktop | -3.840 |
acs | -3.761 |
olla | -3.750 |
rog | -3.660 |
impaired | -3.556 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Yao | +1.973 |
Spencer | +1.768 |
Debor | +1.747 |
JC | +1.744 |
•• | +1.738 |
Neg logit contributions | |
ktop | -1.610 |
acs | -1.578 |
olla | -1.571 |
impaired | -1.533 |
neur | -1.528 |
Token | She |
Token ID | 3347 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Yao | +1.631 |
•• | +1.439 |
Spencer | +1.432 |
Debor | +1.432 |
JC | +1.419 |
Neg logit contributions | |
ktop | -1.669 |
olla | -1.644 |
acs | -1.642 |
impaired | -1.605 |
rog | -1.592 |
Token | cuts |
Token ID | 6630 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Yao | +1.697 |
intern | +1.534 |
Debor | +1.515 |
Spencer | +1.514 |
JC | +1.501 |
Neg logit contributions | |
ktop | -1.462 |
olla | -1.435 |
acs | -1.423 |
rog | -1.405 |
impaired | -1.347 |
Token | me |
Token ID | 502 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
Yao | +0.730 |
Debor | +0.638 |
Spencer | +0.626 |
JC | +0.625 |
intern | +0.622 |
Neg logit contributions | |
acs | -0.997 |
ktop | -0.995 |
olla | -0.993 |
rog | -0.974 |
impaired | -0.951 |
Token |
|
Token ID | 198 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ktop | +0.598 |
acs | +0.593 |
olla | +0.592 |
rog | +0.576 |
impaired | +0.563 |
Neg logit contributions | |
Yao | -0.840 |
Debor | -0.760 |
JC | -0.752 |
intern | -0.750 |
Spencer | -0.749 |
Token | impl |
Token ID | 23928 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ktop | +0.570 |
acs | +0.569 |
olla | +0.569 |
rog | +0.555 |
impaired | +0.542 |
Neg logit contributions | |
Yao | -0.703 |
Debor | -0.636 |
intern | -0.623 |
JC | -0.623 |
Spencer | -0.622 |
Token | Board |
Token ID | 5926 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Yao | +1.733 |
Debor | +1.515 |
JC | +1.505 |
intern | +1.500 |
EB | +1.490 |
Neg logit contributions | |
ktop | -2.204 |
olla | -2.176 |
acs | -2.167 |
rog | -2.153 |
impaired | -2.081 |
Token | { |
Token ID | 1391 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
acs | +0.950 |
olla | +0.950 |
ktop | +0.948 |
rog | +0.927 |
impaired | +0.901 |
Neg logit contributions | |
Yao | -1.230 |
Debor | -1.119 |
intern | -1.096 |
JC | -1.095 |
Spencer | -1.093 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Yao | +1.870 |
intern | +1.696 |
Debor | +1.678 |
Spencer | +1.673 |
JC | +1.666 |
Neg logit contributions | |
acs | -1.590 |
ktop | -1.590 |
olla | -1.587 |
rog | -1.545 |
lime | -1.487 |
Token | fn |
Token ID | 24714 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
Yao | +1.836 |
intern | +1.625 |
Debor | +1.598 |
JC | +1.597 |
EB | +1.594 |
Neg logit contributions | |
olla | -2.069 |
ktop | -2.066 |
acs | -2.042 |
rog | -1.997 |
lime | -1.959 |
Token | copy |
Token ID | 4866 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
Yao | +3.741 |
intern | +3.378 |
JC | +3.340 |
EB | +3.273 |
Debor | +3.271 |
Neg logit contributions | |
ktop | -4.146 |
olla | -4.046 |
acs | -4.005 |
rog | -3.932 |
lime | -3.824 |
Token | _ |
Token ID | 62 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Yao | +0.693 |
Debor | +0.621 |
intern | +0.611 |
JC | +0.608 |
Spencer | +0.607 |
Neg logit contributions | |
ktop | -0.681 |
acs | -0.679 |
olla | -0.679 |
rog | -0.664 |
impaired | -0.649 |
Token | board |
Token ID | 3526 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
Yao | +0.904 |
Debor | +0.812 |
intern | +0.801 |
JC | +0.800 |
Spencer | +0.794 |
Neg logit contributions | |
ktop | -0.793 |
olla | -0.786 |
acs | -0.784 |
rog | -0.762 |
impaired | -0.752 |
Token | ( |
Token ID | 357 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Yao | +0.592 |
Debor | +0.530 |
intern | +0.524 |
JC | +0.522 |
Spencer | +0.519 |
Neg logit contributions | |
ktop | -0.583 |
acs | -0.578 |
olla | -0.577 |
rog | -0.567 |
impaired | -0.553 |
Token | & |
Token ID | 1222 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Yao | +0.697 |
intern | +0.604 |
Debor | +0.596 |
JC | +0.587 |
Spencer | +0.586 |
Neg logit contributions | |
ktop | -1.024 |
acs | -1.009 |
olla | -1.005 |
rog | -0.988 |
impaired | -0.976 |
Token | $ |
Token ID | 720 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Yao | +0.514 |
Debor | +0.465 |
intern | +0.456 |
Spencer | +0.455 |
JC | +0.455 |
Neg logit contributions | |
acs | -0.452 |
ktop | -0.452 |
olla | -0.452 |
rog | -0.441 |
impaired | -0.429 |
Token | 11 |
Token ID | 1157 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Yao | +1.074 |
Debor | +0.934 |
Spencer | +0.922 |
JC | +0.921 |
•• | +0.918 |
Neg logit contributions | |
ktop | -1.428 |
acs | -1.406 |
olla | -1.403 |
rog | -1.373 |
impaired | -1.371 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Yao | +0.389 |
Debor | +0.352 |
intern | +0.343 |
JC | +0.343 |
Spencer | +0.343 |
Neg logit contributions | |
olla | -0.364 |
acs | -0.364 |
ktop | -0.363 |
rog | -0.356 |
impaired | -0.347 |
Token | 25 |
Token ID | 1495 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
Yao | +0.722 |
Debor | +0.643 |
JC | +0.630 |
Spencer | +0.627 |
intern | +0.623 |
Neg logit contributions | |
ktop | -0.781 |
acs | -0.776 |
olla | -0.772 |
rog | -0.760 |
impaired | -0.750 |
Token | million |
Token ID | 1510 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Yao | +0.674 |
Debor | +0.606 |
intern | +0.592 |
JC | +0.591 |
Spencer | +0.591 |
Neg logit contributions | |
acs | -0.659 |
olla | -0.659 |
ktop | -0.658 |
rog | -0.645 |
impaired | -0.629 |
Token | contract |
Token ID | 2775 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
Yao | +1.688 |
Debor | +1.539 |
intern | +1.528 |
Spencer | +1.527 |
JC | +1.523 |
Neg logit contributions | |
ktop | -1.038 |
acs | -1.026 |
olla | -1.025 |
rog | -0.995 |
impaired | -0.962 |
Token | signed |
Token ID | 4488 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Yao | +3.304 |
intern | +2.870 |
Spencer | +2.852 |
JC | +2.829 |
Debor | +2.829 |
Neg logit contributions | |
ktop | -4.543 |
acs | -4.473 |
olla | -4.472 |
rog | -4.351 |
lime | -4.306 |
Token | in |
Token ID | 287 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
Yao | +1.599 |
Debor | +1.429 |
intern | +1.403 |
Spencer | +1.394 |
JC | +1.391 |
Neg logit contributions | |
olla | -1.784 |
ktop | -1.782 |
acs | -1.772 |
rog | -1.737 |
impaired | -1.689 |
Token | March |
Token ID | 2805 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ktop | +0.067 |
acs | +0.067 |
olla | +0.067 |
rog | +0.066 |
impaired | +0.064 |
Neg logit contributions | |
Yao | -0.060 |
Debor | -0.054 |
intern | -0.053 |
Spencer | -0.052 |
JC | -0.052 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
ktop | +0.262 |
olla | +0.261 |
acs | +0.261 |
rog | +0.255 |
impaired | +0.249 |
Neg logit contributions | |
Yao | -0.268 |
Debor | -0.241 |
intern | -0.236 |
JC | -0.235 |
Spencer | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
acs | +0.398 |
olla | +0.396 |
ktop | +0.394 |
rog | +0.387 |
impaired | +0.375 |
Neg logit contributions | |
Yao | -0.621 |
Debor | -0.571 |
JC | -0.558 |
intern | -0.557 |
Spencer | -0.556 |
Token | sudo |
Token ID | 24032 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Yao | +0.091 |
Debor | +0.081 |
intern | +0.079 |
JC | +0.079 |
Spencer | +0.079 |
Neg logit contributions | |
ktop | -0.091 |
olla | -0.091 |
acs | -0.091 |
rog | -0.089 |
impaired | -0.087 |
Token | l |
Token ID | 300 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Yao | +1.073 |
Debor | +0.968 |
intern | +0.961 |
JC | +0.950 |
Spencer | +0.947 |
Neg logit contributions | |
olla | -0.892 |
ktop | -0.889 |
acs | -0.887 |
rog | -0.874 |
impaired | -0.844 |
Token | sh |
Token ID | 1477 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
ktop | +0.115 |
olla | +0.114 |
acs | +0.114 |
rog | +0.111 |
impaired | +0.108 |
Neg logit contributions | |
Yao | -0.207 |
Debor | -0.191 |
intern | -0.187 |
JC | -0.187 |
Spencer | -0.187 |
Token | w |
Token ID | 86 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
Yao | +0.384 |
Debor | +0.346 |
intern | +0.339 |
JC | +0.338 |
Spencer | +0.337 |
Neg logit contributions | |
ktop | -0.346 |
olla | -0.346 |
acs | -0.345 |
rog | -0.339 |
impaired | -0.330 |
Token | - |
Token ID | 532 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
acs | +0.662 |
olla | +0.661 |
ktop | +0.660 |
rog | +0.646 |
impaired | +0.628 |
Neg logit contributions | |
Yao | -0.820 |
Debor | -0.745 |
intern | -0.729 |
JC | -0.728 |
Spencer | -0.727 |
Token | C |
Token ID | 34 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
Yao | +1.280 |
Debor | +1.165 |
intern | +1.142 |
Spencer | +1.139 |
JC | +1.138 |
Neg logit contributions | |
ktop | -0.944 |
acs | -0.939 |
olla | -0.938 |
rog | -0.915 |
impaired | -0.902 |
Token | network |
Token ID | 3127 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Yao | +3.939 |
Debor | +3.522 |
intern | +3.506 |
Spencer | +3.495 |
EB | +3.469 |
Neg logit contributions | |
ktop | -3.781 |
olla | -3.764 |
acs | -3.731 |
rog | -3.675 |
impaired | -3.615 |
Token |
|
Token ID | 198 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
acs | +1.754 |
olla | +1.742 |
ktop | +1.741 |
rog | +1.714 |
impaired | +1.658 |
Neg logit contributions | |
Yao | -1.897 |
Debor | -1.718 |
JC | -1.679 |
Spencer | -1.675 |
unden | -1.668 |
Token |
|
Token ID | 198 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
Yao | +0.564 |
JC | +0.503 |
Debor | +0.503 |
Spencer | +0.501 |
intern | +0.500 |
Neg logit contributions | |
ktop | -0.435 |
acs | -0.427 |
olla | -0.426 |
rog | -0.413 |
neur | -0.409 |
Token | This |
Token ID | 1212 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Yao | +0.704 |
Debor | +0.632 |
•• | +0.617 |
intern | +0.617 |
JC | +0.616 |
Neg logit contributions | |
ktop | -0.706 |
olla | -0.703 |
acs | -0.703 |
rog | -0.686 |
impaired | -0.682 |
Token | will |
Token ID | 481 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Yao | +0.567 |
Debor | +0.519 |
intern | +0.511 |
JC | +0.508 |
Spencer | +0.506 |
Neg logit contributions | |
olla | -0.396 |
ktop | -0.394 |
acs | -0.393 |
rog | -0.384 |
impaired | -0.374 |
Token | � |
Token ID | 247 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Yao | +0.108 |
Debor | +0.098 |
intern | +0.096 |
Spencer | +0.096 |
JC | +0.096 |
Neg logit contributions | |
ktop | -0.074 |
acs | -0.073 |
olla | -0.073 |
rog | -0.071 |
impaired | -0.070 |
Token | t |
Token ID | 83 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
Yao | +0.272 |
Debor | +0.245 |
intern | +0.240 |
JC | +0.240 |
Spencer | +0.240 |
Neg logit contributions | |
ktop | -0.252 |
acs | -0.252 |
olla | -0.252 |
rog | -0.247 |
impaired | -0.241 |
Token | top |
Token ID | 1353 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Yao | +0.490 |
Debor | +0.440 |
intern | +0.437 |
JC | +0.436 |
Spencer | +0.435 |
Neg logit contributions | |
olla | -0.404 |
ktop | -0.404 |
acs | -0.402 |
rog | -0.395 |
impaired | -0.382 |
Token | Curtis |
Token ID | 25157 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Yao | +1.928 |
Debor | +1.728 |
Spencer | +1.723 |
JC | +1.710 |
intern | +1.700 |
Neg logit contributions | |
ktop | -1.658 |
acs | -1.653 |
olla | -1.652 |
rog | -1.611 |
impaired | -1.561 |
Token | K |
Token ID | 509 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
Yao | +0.940 |
Debor | +0.841 |
Spencer | +0.823 |
intern | +0.822 |
JC | +0.821 |
Neg logit contributions | |
olla | -0.967 |
acs | -0.967 |
ktop | -0.966 |
rog | -0.950 |
impaired | -0.924 |
Token | uy |
Token ID | 4669 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Yao | +0.404 |
Debor | +0.364 |
Spencer | +0.357 |
intern | +0.356 |
JC | +0.355 |
Neg logit contributions | |
ktop | -0.374 |
olla | -0.369 |
acs | -0.368 |
rog | -0.362 |
impaired | -0.357 |
Token | k |
Token ID | 74 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Yao | +4.176 |
Spencer | +3.722 |
Debor | +3.720 |
intern | +3.714 |
JC | +3.713 |
Neg logit contributions | |
olla | -3.387 |
acs | -3.375 |
ktop | -3.373 |
impaired | -3.336 |
rog | -3.334 |
Token | end |
Token ID | 437 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
Yao | +0.389 |
Debor | +0.362 |
intern | +0.356 |
JC | +0.356 |
Spencer | +0.355 |
Neg logit contributions | |
acs | -0.153 |
olla | -0.153 |
ktop | -0.152 |
rog | -0.147 |
impaired | -0.141 |
Token | all |
Token ID | 439 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ktop | +0.455 |
acs | +0.452 |
olla | +0.450 |
rog | +0.442 |
impaired | +0.433 |
Neg logit contributions | |
Yao | -0.603 |
Debor | -0.543 |
intern | -0.538 |
JC | -0.535 |
Spencer | -0.535 |
Token | � |
Token ID | 447 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
olla | +0.166 |
acs | +0.166 |
ktop | +0.166 |
rog | +0.163 |
impaired | +0.159 |
Neg logit contributions | |
Yao | -0.157 |
Debor | -0.140 |
intern | -0.137 |
Spencer | -0.137 |
JC | -0.137 |
Token | � |
Token ID | 247 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Yao | +0.998 |
Debor | +0.903 |
intern | +0.898 |
JC | +0.889 |
Spencer | +0.888 |
Neg logit contributions | |
ktop | -0.725 |
acs | -0.715 |
olla | -0.713 |
rog | -0.688 |
impaired | -0.680 |
Token | things |
Token ID | 1243 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
acs | +0.610 |
ktop | +0.609 |
olla | +0.607 |
rog | +0.596 |
impaired | +0.582 |
Neg logit contributions | |
Yao | -0.669 |
Debor | -0.605 |
Spencer | -0.588 |
JC | -0.588 |
unden | -0.587 |
Token | . |
Token ID | 13 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
Yao | +0.215 |
Debor | +0.194 |
JC | +0.190 |
intern | +0.190 |
Spencer | +0.189 |
Neg logit contributions | |
acs | -0.199 |
olla | -0.199 |
ktop | -0.199 |
rog | -0.195 |
impaired | -0.190 |
Token | See |
Token ID | 4091 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
olla | +0.074 |
ktop | +0.074 |
acs | +0.074 |
rog | +0.073 |
impaired | +0.071 |
Neg logit contributions | |
Yao | -0.067 |
Debor | -0.060 |
intern | -0.059 |
JC | -0.059 |
Spencer | -0.058 |
Token | | |
Token ID | 930 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Yao | +1.350 |
Debor | +1.217 |
intern | +1.199 |
JC | +1.190 |
Spencer | +1.186 |
Neg logit contributions | |
olla | -1.410 |
ktop | -1.399 |
acs | -1.398 |
rog | -1.373 |
impaired | -1.338 |
Token | aut |
Token ID | 2306 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Yao | +0.218 |
Debor | +0.194 |
intern | +0.189 |
JC | +0.189 |
Spencer | +0.189 |
Neg logit contributions | |
olla | -0.244 |
acs | -0.244 |
ktop | -0.243 |
rog | -0.239 |
impaired | -0.233 |
Token | oc |
Token ID | 420 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
Yao | +1.417 |
Debor | +1.275 |
intern | +1.266 |
JC | +1.262 |
Spencer | +1.253 |
Neg logit contributions | |
olla | -1.158 |
ktop | -1.156 |
acs | -1.144 |
rog | -1.130 |
impaired | -1.117 |
Token | omm |
Token ID | 2002 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Yao | +3.643 |
intern | +3.341 |
Debor | +3.305 |
JC | +3.244 |
Spencer | +3.205 |
Neg logit contributions | |
olla | -3.712 |
ktop | -3.702 |
impaired | -3.648 |
acs | -3.628 |
neur | -3.607 |
Token | and |
Token ID | 392 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
Yao | +1.209 |
Debor | +1.123 |
intern | +1.104 |
Spencer | +1.098 |
JC | +1.095 |
Neg logit contributions | |
ktop | -0.860 |
olla | -0.859 |
acs | -0.841 |
rog | -0.839 |
impaired | -0.827 |
Token | | |
Token ID | 91 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Yao | +0.644 |
Debor | +0.573 |
intern | +0.559 |
JC | +0.557 |
Spencer | +0.555 |
Neg logit contributions | |
olla | -0.794 |
acs | -0.792 |
ktop | -0.792 |
rog | -0.777 |
impaired | -0.762 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Yao | +1.191 |
Debor | +1.080 |
intern | +1.063 |
JC | +1.058 |
Spencer | +1.052 |
Neg logit contributions | |
olla | -1.116 |
ktop | -1.111 |
acs | -1.109 |
rog | -1.088 |
impaired | -1.065 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Yao | +0.270 |
Debor | +0.244 |
JC | +0.239 |
intern | +0.238 |
Spencer | +0.238 |
Neg logit contributions | |
olla | -0.264 |
ktop | -0.264 |
acs | -0.262 |
rog | -0.258 |
impaired | -0.251 |
Token | STR |
Token ID | 19269 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Yao | +0.051 |
Debor | +0.046 |
JC | +0.045 |
intern | +0.045 |
Spencer | +0.045 |
Neg logit contributions | |
acs | -0.049 |
ktop | -0.049 |
olla | -0.049 |
rog | -0.049 |
impaired | -0.047 |
Token | UCT |
Token ID | 18415 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
Yao | +0.244 |
Debor | +0.212 |
JC | +0.208 |
intern | +0.208 |
Spencer | +0.207 |
Neg logit contributions | |
ktop | -0.338 |
olla | -0.337 |
acs | -0.337 |
rog | -0.332 |
impaired | -0.325 |
Token | URE |
Token ID | 11335 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
acs | +0.719 |
ktop | +0.719 |
olla | +0.719 |
rog | +0.705 |
impaired | +0.690 |
Neg logit contributions | |
Yao | -0.623 |
Debor | -0.553 |
intern | -0.539 |
JC | -0.539 |
Spencer | -0.539 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
acs | +0.166 |
olla | +0.165 |
ktop | +0.165 |
rog | +0.162 |
impaired | +0.157 |
Neg logit contributions | |
Yao | -0.187 |
Debor | -0.169 |
JC | -0.165 |
intern | -0.165 |
Spencer | -0.165 |
Token |
|
Token ID | 198 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Yao | +2.134 |
JC | +1.902 |
Spencer | +1.883 |
intern | +1.870 |
Debor | +1.857 |
Neg logit contributions | |
ktop | -1.882 |
acs | -1.835 |
olla | -1.820 |
neur | -1.782 |
impaired | -1.771 |
Token | Please |
Token ID | 5492 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
Yao | +2.214 |
•• | +1.990 |
Spencer | +1.957 |
Debor | +1.940 |
JC | +1.937 |
Neg logit contributions | |
ktop | -2.109 |
acs | -2.090 |
olla | -2.083 |
impaired | -2.051 |
neur | -2.014 |
Token | find |
Token ID | 1064 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Yao | +3.244 |
intern | +2.911 |
JC | +2.872 |
Spencer | +2.842 |
Debor | +2.833 |
Neg logit contributions | |
ktop | -4.267 |
olla | -4.223 |
acs | -4.215 |
rog | -4.073 |
lime | -4.000 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Yao | +2.149 |
Spencer | +1.927 |
Debor | +1.922 |
intern | +1.922 |
JC | +1.922 |
Neg logit contributions | |
acs | -1.866 |
olla | -1.865 |
ktop | -1.853 |
rog | -1.802 |
impaired | -1.751 |
Token | full |
Token ID | 1336 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
Yao | +0.911 |
Debor | +0.807 |
Spencer | +0.805 |
intern | +0.801 |
JC | +0.798 |
Neg logit contributions | |
acs | -0.893 |
ktop | -0.892 |
olla | -0.886 |
rog | -0.868 |
impaired | -0.850 |
Token | list |
Token ID | 1351 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
acs | +0.731 |
ktop | +0.730 |
olla | +0.730 |
rog | +0.714 |
impaired | +0.696 |
Neg logit contributions | |
Yao | -0.689 |
Debor | -0.614 |
intern | -0.604 |
Spencer | -0.602 |
JC | -0.600 |
Token | of |
Token ID | 286 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Yao | +0.653 |
Debor | +0.595 |
intern | +0.583 |
JC | +0.582 |
Spencer | +0.582 |
Neg logit contributions | |
olla | -0.501 |
acs | -0.500 |
ktop | -0.500 |
rog | -0.489 |
impaired | -0.475 |
Token | $ |
Token ID | 720 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Yao | +0.479 |
Debor | +0.433 |
intern | +0.426 |
Spencer | +0.426 |
JC | +0.426 |
Neg logit contributions | |
acs | -0.430 |
ktop | -0.430 |
olla | -0.429 |
rog | -0.419 |
impaired | -0.408 |
Token | 16 |
Token ID | 1433 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Yao | +1.146 |
Debor | +0.999 |
Spencer | +0.986 |
JC | +0.986 |
•• | +0.983 |
Neg logit contributions | |
ktop | -1.477 |
acs | -1.453 |
olla | -1.447 |
rog | -1.420 |
impaired | -1.418 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Yao | +0.626 |
Debor | +0.564 |
intern | +0.551 |
JC | +0.550 |
Spencer | +0.549 |
Neg logit contributions | |
acs | -0.594 |
olla | -0.594 |
ktop | -0.593 |
rog | -0.582 |
impaired | -0.567 |
Token | 25 |
Token ID | 1495 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Yao | +1.422 |
Debor | +1.264 |
JC | +1.240 |
Spencer | +1.234 |
•• | +1.224 |
Neg logit contributions | |
ktop | -1.569 |
acs | -1.556 |
olla | -1.543 |
rog | -1.526 |
neur | -1.515 |
Token | million |
Token ID | 1510 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Yao | +0.785 |
Debor | +0.706 |
intern | +0.690 |
JC | +0.689 |
Spencer | +0.688 |
Neg logit contributions | |
acs | -0.774 |
olla | -0.773 |
ktop | -0.772 |
rog | -0.758 |
impaired | -0.739 |
Token | contract |
Token ID | 2775 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
Yao | +1.611 |
Debor | +1.473 |
intern | +1.459 |
Spencer | +1.458 |
JC | +1.456 |
Neg logit contributions | |
ktop | -1.048 |
acs | -1.036 |
olla | -1.033 |
rog | -1.003 |
lime | -0.972 |
Token | signed |
Token ID | 4488 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Yao | +3.253 |
intern | +2.839 |
Spencer | +2.822 |
Debor | +2.817 |
JC | +2.799 |
Neg logit contributions | |
ktop | -4.293 |
olla | -4.223 |
acs | -4.222 |
rog | -4.111 |
lime | -4.069 |
Token | in |
Token ID | 287 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
Yao | +1.318 |
Debor | +1.178 |
intern | +1.157 |
Spencer | +1.149 |
JC | +1.148 |
Neg logit contributions | |
olla | -1.469 |
ktop | -1.468 |
acs | -1.459 |
rog | -1.431 |
impaired | -1.389 |
Token | February |
Token ID | 3945 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
acs | +0.385 |
olla | +0.384 |
ktop | +0.384 |
rog | +0.377 |
impaired | +0.367 |
Neg logit contributions | |
Yao | -0.352 |
Debor | -0.314 |
intern | -0.307 |
JC | -0.306 |
Spencer | -0.306 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Yao | +0.301 |
Debor | +0.270 |
intern | +0.264 |
JC | +0.263 |
Spencer | +0.263 |
Neg logit contributions | |
ktop | -0.310 |
olla | -0.309 |
acs | -0.309 |
rog | -0.302 |
impaired | -0.295 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Yao | +0.236 |
Debor | +0.216 |
intern | +0.212 |
JC | +0.212 |
Spencer | +0.212 |
Neg logit contributions | |
acs | -0.156 |
olla | -0.156 |
ktop | -0.155 |
rog | -0.152 |
impaired | -0.147 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Yao | +1.933 |
Debor | +1.691 |
JC | +1.671 |
intern | +1.670 |
Spencer | +1.661 |
Neg logit contributions | |
acs | -2.297 |
ktop | -2.288 |
olla | -2.285 |
rog | -2.257 |
lime | -2.186 |
Token | { |
Token ID | 1391 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
olla | +0.908 |
acs | +0.908 |
ktop | +0.908 |
rog | +0.888 |
impaired | +0.865 |
Neg logit contributions | |
Yao | -1.046 |
Debor | -0.946 |
intern | -0.926 |
JC | -0.925 |
Spencer | -0.924 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Yao | +2.287 |
intern | +2.083 |
Debor | +2.043 |
Spencer | +2.035 |
JC | +2.023 |
Neg logit contributions | |
acs | -2.218 |
ktop | -2.214 |
olla | -2.204 |
rog | -2.135 |
lime | -2.087 |
Token | } |
Token ID | 1782 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Yao | +2.099 |
intern | +1.895 |
Debor | +1.846 |
JC | +1.834 |
Spencer | +1.830 |
Neg logit contributions | |
ktop | -2.194 |
acs | -2.193 |
olla | -2.164 |
rog | -2.103 |
lime | -2.056 |
Token | pub |
Token ID | 2240 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
acs | +0.297 |
olla | +0.297 |
ktop | +0.295 |
rog | +0.288 |
impaired | +0.278 |
Neg logit contributions | |
Yao | -0.374 |
Debor | -0.339 |
intern | -0.336 |
Spencer | -0.333 |
JC | -0.332 |
Token | fn |
Token ID | 24714 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Yao | +0.073 |
Debor | +0.066 |
intern | +0.065 |
JC | +0.065 |
Spencer | +0.065 |
Neg logit contributions | |
olla | -0.061 |
acs | -0.061 |
ktop | -0.061 |
rog | -0.060 |
impaired | -0.058 |
Token | pin |
Token ID | 6757 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Yao | +3.821 |
intern | +3.455 |
JC | +3.398 |
Spencer | +3.348 |
Debor | +3.344 |
Neg logit contributions | |
ktop | -3.649 |
acs | -3.636 |
olla | -3.603 |
rog | -3.516 |
lime | -3.443 |
Token | () |
Token ID | 7499 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
ktop | +0.147 |
acs | +0.146 |
olla | +0.146 |
rog | +0.142 |
impaired | +0.139 |
Neg logit contributions | |
Yao | -0.167 |
Debor | -0.150 |
intern | -0.148 |
JC | -0.148 |
Spencer | -0.147 |
Token | -> |
Token ID | 4613 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ktop | +0.013 |
acs | +0.013 |
olla | +0.013 |
rog | +0.013 |
impaired | +0.012 |
Neg logit contributions | |
Yao | -0.020 |
Debor | -0.018 |
intern | -0.018 |
JC | -0.018 |
Spencer | -0.018 |
Token | Guard |
Token ID | 4932 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Yao | +1.941 |
intern | +1.718 |
Debor | +1.690 |
JC | +1.688 |
Spencer | +1.672 |
Neg logit contributions | |
acs | -2.229 |
ktop | -2.209 |
olla | -2.175 |
rog | -2.156 |
lime | -2.096 |
Token | ; |
Token ID | 2162 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Yao | +0.299 |
intern | +0.267 |
Debor | +0.266 |
Spencer | +0.264 |
JC | +0.264 |
Neg logit contributions | |
ktop | -0.273 |
acs | -0.270 |
olla | -0.269 |
rog | -0.265 |
impaired | -0.257 |
Token | surface |
Token ID | 4417 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Yao | +0.483 |
Debor | +0.439 |
intern | +0.434 |
Spencer | +0.433 |
JC | +0.431 |
Neg logit contributions | |
olla | -0.375 |
ktop | -0.373 |
acs | -0.372 |
rog | -0.366 |
impaired | -0.349 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Yao | +0.203 |
Debor | +0.182 |
intern | +0.179 |
Spencer | +0.178 |
JC | +0.178 |
Neg logit contributions | |
olla | -0.209 |
ktop | -0.208 |
acs | -0.207 |
rog | -0.203 |
impaired | -0.196 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ktop | +0.155 |
olla | +0.153 |
acs | +0.152 |
rog | +0.149 |
impaired | +0.146 |
Neg logit contributions | |
Yao | -0.208 |
Debor | -0.189 |
Spencer | -0.186 |
JC | -0.186 |
intern | -0.184 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ktop | +0.111 |
acs | +0.109 |
olla | +0.109 |
rog | +0.106 |
neur | +0.105 |
Neg logit contributions | |
Yao | -0.143 |
JC | -0.128 |
Debor | -0.128 |
Spencer | -0.128 |
intern | -0.127 |
Token | Media |
Token ID | 13152 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ktop | +0.272 |
olla | +0.269 |
acs | +0.267 |
impaired | +0.261 |
rog | +0.260 |
Neg logit contributions | |
Yao | -0.277 |
Debor | -0.247 |
•• | -0.244 |
Spencer | -0.243 |
JC | -0.243 |
Token | playback |
Token ID | 16388 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
Yao | +1.151 |
Debor | +1.001 |
intern | +0.992 |
Spencer | +0.982 |
JC | +0.980 |
Neg logit contributions | |
ktop | -1.793 |
olla | -1.785 |
acs | -1.774 |
rog | -1.742 |
impaired | -1.696 |
Token | is |
Token ID | 318 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
Yao | +3.740 |
Spencer | +3.335 |
intern | +3.328 |
JC | +3.318 |
Debor | +3.220 |
Neg logit contributions | |
olla | -3.548 |
acs | -3.509 |
ktop | -3.509 |
rog | -3.368 |
lime | -3.324 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
olla | +0.031 |
ktop | +0.031 |
acs | +0.031 |
rog | +0.030 |
impaired | +0.029 |
Neg logit contributions | |
Yao | -0.060 |
Debor | -0.056 |
Spencer | -0.055 |
intern | -0.055 |
JC | -0.055 |
Token | on |
Token ID | 319 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
Yao | +0.162 |
Debor | +0.142 |
JC | +0.141 |
intern | +0.140 |
Spencer | +0.140 |
Neg logit contributions | |
acs | -0.203 |
ktop | -0.203 |
olla | -0.202 |
rog | -0.199 |
impaired | -0.193 |
Token | your |
Token ID | 534 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Yao | +0.325 |
Debor | +0.292 |
intern | +0.290 |
JC | +0.290 |
Spencer | +0.288 |
Neg logit contributions | |
acs | -0.271 |
olla | -0.271 |
ktop | -0.269 |
rog | -0.264 |
impaired | -0.255 |
Token | device |
Token ID | 3335 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
acs | +0.137 |
ktop | +0.136 |
olla | +0.135 |
rog | +0.131 |
impaired | +0.123 |
Neg logit contributions | |
Yao | -0.248 |
intern | -0.227 |
Debor | -0.227 |
Spencer | -0.225 |
JC | -0.225 |
Token | f |
Token ID | 277 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
Yao | +1.719 |
intern | +1.546 |
JC | +1.517 |
Spencer | +1.502 |
EB | +1.498 |
Neg logit contributions | |
olla | -1.755 |
ktop | -1.727 |
acs | -1.726 |
rog | -1.694 |
lime | -1.626 |
Token | rit |
Token ID | 799 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Yao | +0.104 |
Spencer | +0.097 |
Debor | +0.096 |
intern | +0.096 |
•• | +0.096 |
Neg logit contributions | |
olla | -0.036 |
ktop | -0.035 |
acs | -0.035 |
impaired | -0.034 |
neur | -0.033 |
Token | ters |
Token ID | 1010 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Yao | +0.805 |
Debor | +0.706 |
intern | +0.694 |
Spencer | +0.692 |
JC | +0.689 |
Neg logit contributions | |
olla | -1.094 |
ktop | -1.093 |
acs | -1.081 |
rog | -1.063 |
impaired | -1.059 |
Token | in |
Token ID | 287 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
Yao | +0.132 |
Debor | +0.116 |
intern | +0.115 |
JC | +0.114 |
Spencer | +0.114 |
Neg logit contributions | |
olla | -0.157 |
ktop | -0.156 |
acs | -0.155 |
rog | -0.152 |
impaired | -0.148 |
Token | the |
Token ID | 262 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
Yao | +0.735 |
intern | +0.655 |
JC | +0.653 |
Debor | +0.650 |
Spencer | +0.649 |
Neg logit contributions | |
acs | -0.622 |
olla | -0.617 |
ktop | -0.617 |
rog | -0.600 |
impaired | -0.579 |
Token | skillet |
Token ID | 41306 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
Yao | +0.746 |
intern | +0.664 |
JC | +0.663 |
Spencer | +0.662 |
Debor | +0.660 |
Neg logit contributions | |
olla | -0.662 |
acs | -0.661 |
ktop | -0.656 |
rog | -0.648 |
impaired | -0.627 |
Token | ( |
Token ID | 357 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Yao | +3.238 |
JC | +2.853 |
intern | +2.849 |
Debor | +2.804 |
Spencer | +2.764 |
Neg logit contributions | |
ktop | -4.011 |
olla | -3.920 |
acs | -3.903 |
rog | -3.819 |
phthal | -3.708 |
Token | don |
Token ID | 9099 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Yao | +1.846 |
Debor | +1.674 |
intern | +1.668 |
•• | +1.661 |
Spencer | +1.637 |
Neg logit contributions | |
olla | -1.624 |
ktop | -1.613 |
acs | -1.608 |
impaired | -1.593 |
neur | -1.553 |
Token | � |
Token ID | 447 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Yao | +1.253 |
intern | +1.103 |
Debor | +1.101 |
Spencer | +1.081 |
JC | +1.081 |
Neg logit contributions | |
ktop | -1.684 |
olla | -1.671 |
acs | -1.664 |
rog | -1.628 |
impaired | -1.626 |
Token | � |
Token ID | 247 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
Yao | +1.834 |
Debor | +1.644 |
intern | +1.634 |
Spencer | +1.632 |
JC | +1.610 |
Neg logit contributions | |
ktop | -1.373 |
acs | -1.356 |
olla | -1.346 |
rog | -1.301 |
impaired | -1.295 |
Token | t |
Token ID | 83 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Yao | +0.677 |
Debor | +0.606 |
intern | +0.600 |
Spencer | +0.597 |
JC | +0.595 |
Neg logit contributions | |
ktop | -0.681 |
olla | -0.679 |
acs | -0.677 |
rog | -0.658 |
impaired | -0.653 |
Token | gh |
Token ID | 456 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Yao | +1.080 |
Debor | +0.982 |
JC | +0.968 |
intern | +0.968 |
Spencer | +0.968 |
Neg logit contributions | |
acs | -0.786 |
ktop | -0.785 |
olla | -0.782 |
rog | -0.761 |
impaired | -0.744 |
Token | sacrificed |
Token ID | 27445 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Yao | +0.233 |
Debor | +0.209 |
intern | +0.206 |
JC | +0.205 |
Spencer | +0.205 |
Neg logit contributions | |
olla | -0.215 |
acs | -0.214 |
ktop | -0.214 |
rog | -0.209 |
impaired | -0.203 |
Token | and |
Token ID | 290 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Yao | +0.320 |
Debor | +0.289 |
JC | +0.284 |
intern | +0.283 |
Spencer | +0.283 |
Neg logit contributions | |
acs | -0.298 |
olla | -0.298 |
ktop | -0.295 |
rog | -0.289 |
impaired | -0.281 |
Token | Dirk |
Token ID | 42761 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
acs | +0.469 |
ktop | +0.467 |
olla | +0.466 |
rog | +0.455 |
impaired | +0.441 |
Neg logit contributions | |
Yao | -0.532 |
Debor | -0.481 |
JC | -0.473 |
Spencer | -0.472 |
intern | -0.471 |
Token | K |
Token ID | 509 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
Yao | +0.714 |
Debor | +0.637 |
Spencer | +0.629 |
JC | +0.627 |
intern | +0.624 |
Neg logit contributions | |
ktop | -0.736 |
acs | -0.734 |
olla | -0.730 |
rog | -0.717 |
impaired | -0.698 |
Token | uy |
Token ID | 4669 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Yao | +0.580 |
Debor | +0.524 |
intern | +0.513 |
JC | +0.512 |
Spencer | +0.512 |
Neg logit contributions | |
acs | -0.520 |
olla | -0.520 |
ktop | -0.519 |
rog | -0.508 |
impaired | -0.496 |
Token | t |
Token ID | 83 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
Yao | +3.484 |
JC | +3.106 |
Spencer | +3.101 |
Debor | +3.083 |
EB | +3.060 |
Neg logit contributions | |
olla | -3.629 |
ktop | -3.607 |
acs | -3.602 |
rog | -3.561 |
impaired | -3.537 |
Token | switching |
Token ID | 15430 |
Feature activation | -9.39e-02 |
Pos logit contributions | |
olla | +0.530 |
acs | +0.529 |
ktop | +0.529 |
rog | +0.516 |
impaired | +0.502 |
Neg logit contributions | |
Yao | -0.661 |
Debor | -0.601 |
intern | -0.590 |
JC | -0.589 |
Spencer | -0.588 |
Token | fl |
Token ID | 781 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
olla | +0.067 |
acs | +0.067 |
ktop | +0.067 |
rog | +0.065 |
impaired | +0.063 |
Neg logit contributions | |
Yao | -0.073 |
Debor | -0.066 |
JC | -0.065 |
intern | -0.065 |
Spencer | -0.065 |
Token | anks |
Token ID | 2283 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
ktop | +0.315 |
olla | +0.314 |
acs | +0.313 |
rog | +0.306 |
impaired | +0.302 |
Neg logit contributions | |
Yao | -0.244 |
Debor | -0.214 |
intern | -0.209 |
JC | -0.209 |
Spencer | -0.209 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
olla | +0.001 |
acs | +0.001 |
ktop | +0.001 |
rog | +0.001 |
impaired | +0.001 |
Neg logit contributions | |
Yao | -0.001 |
Debor | -0.001 |
intern | -0.001 |
JC | -0.001 |
Spencer | -0.001 |
Token | weird |
Token ID | 7650 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
olla | +0.336 |
acs | +0.335 |
ktop | +0.334 |
rog | +0.323 |
impaired | +0.312 |
Neg logit contributions | |
Yao | -0.485 |
Debor | -0.441 |
intern | -0.436 |
JC | -0.435 |
Spencer | -0.435 |
Token | feeling |
Token ID | 4203 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
olla | +0.757 |
acs | +0.757 |
ktop | +0.754 |
rog | +0.732 |
impaired | +0.702 |
Neg logit contributions | |
Yao | -1.680 |
Debor | -1.557 |
intern | -1.530 |
JC | -1.529 |
Spencer | -1.528 |
Token | ." |
Token ID | 526 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
acs | +1.236 |
olla | +1.235 |
ktop | +1.232 |
rog | +1.210 |
impaired | +1.174 |
Neg logit contributions | |
Yao | -1.304 |
Debor | -1.173 |
intern | -1.151 |
Spencer | -1.147 |
JC | -1.147 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Yao | +2.086 |
Spencer | +1.849 |
JC | +1.845 |
Debor | +1.844 |
•• | +1.812 |
Neg logit contributions | |
ktop | -1.819 |
acs | -1.774 |
neur | -1.757 |
olla | -1.748 |
impaired | -1.725 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Yao | +1.114 |
JC | +0.990 |
Spencer | +0.987 |
intern | +0.981 |
Debor | +0.976 |
Neg logit contributions | |
ktop | -0.936 |
olla | -0.913 |
acs | -0.912 |
rog | -0.882 |
neur | -0.881 |
Token | Video |
Token ID | 10798 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Yao | +0.853 |
•• | +0.758 |
Debor | +0.754 |
Spencer | +0.748 |
JC | +0.748 |
Neg logit contributions | |
ktop | -0.804 |
olla | -0.792 |
acs | -0.788 |
impaired | -0.770 |
rog | -0.767 |
Token | : |
Token ID | 25 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Yao | +2.996 |
intern | +2.567 |
Spencer | +2.517 |
JC | +2.512 |
Debor | +2.512 |
Neg logit contributions | |
ktop | -4.366 |
olla | -4.232 |
acs | -4.151 |
rog | -4.042 |
\/\/ | -4.008 |
Token | CH |
Token ID | 5870 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Yao | +1.828 |
JC | +1.611 |
Debor | +1.604 |
Spencer | +1.602 |
EB | +1.573 |
Neg logit contributions | |
ktop | -2.008 |
olla | -1.975 |
acs | -1.959 |
rog | -1.933 |
impaired | -1.887 |
Token | I |
Token ID | 40 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Yao | +0.081 |
Debor | +0.073 |
intern | +0.071 |
JC | +0.071 |
Spencer | +0.071 |
Neg logit contributions | |
acs | -0.079 |
olla | -0.079 |
ktop | -0.079 |
rog | -0.078 |
impaired | -0.075 |
Token | @ |
Token ID | 31 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
acs | +1.184 |
olla | +1.183 |
ktop | +1.179 |
rog | +1.159 |
impaired | +1.129 |
Neg logit contributions | |
Yao | -1.277 |
Debor | -1.155 |
intern | -1.126 |
Spencer | -1.124 |
JC | -1.122 |
Token | ST |
Token ID | 2257 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Yao | +0.416 |
Debor | +0.357 |
JC | +0.355 |
Spencer | +0.355 |
intern | +0.350 |
Neg logit contributions | |
ktop | -0.564 |
olla | -0.558 |
acs | -0.557 |
rog | -0.548 |
impaired | -0.540 |
Token | free |
Token ID | 1479 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Yao | +0.826 |
intern | +0.702 |
Debor | +0.701 |
Spencer | +0.701 |
JC | +0.696 |
Neg logit contributions | |
olla | -1.007 |
acs | -1.006 |
ktop | -0.997 |
rog | -0.985 |
neur | -0.953 |
Token | newsletters |
Token ID | 16983 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ktop | +1.468 |
acs | +1.462 |
olla | +1.454 |
rog | +1.436 |
impaired | +1.397 |
Neg logit contributions | |
Yao | -1.193 |
Debor | -1.072 |
unden | -1.059 |
Spencer | -1.034 |
intern | -1.031 |
Token | . |
Token ID | 13 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
olla | +1.547 |
acs | +1.545 |
ktop | +1.542 |
rog | +1.512 |
impaired | +1.474 |
Neg logit contributions | |
Yao | -1.682 |
Debor | -1.520 |
unden | -1.482 |
intern | -1.481 |
JC | -1.480 |
Token |
|
Token ID | 198 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
Yao | +0.064 |
Debor | +0.057 |
JC | +0.056 |
Spencer | +0.055 |
EB | +0.055 |
Neg logit contributions | |
ktop | -0.081 |
acs | -0.081 |
olla | -0.080 |
rog | -0.080 |
impaired | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ktop | +0.574 |
acs | +0.572 |
olla | +0.570 |
rog | +0.556 |
impaired | +0.542 |
Neg logit contributions | |
Yao | -0.838 |
Debor | -0.763 |
JC | -0.751 |
Spencer | -0.750 |
intern | -0.749 |
Token | Update |
Token ID | 10260 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
olla | +0.790 |
acs | +0.790 |
ktop | +0.787 |
rog | +0.774 |
impaired | +0.753 |
Neg logit contributions | |
Yao | -0.799 |
Debor | -0.720 |
intern | -0.703 |
JC | -0.701 |
Spencer | -0.700 |
Token | , |
Token ID | 11 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Yao | +3.214 |
Debor | +2.869 |
intern | +2.833 |
Spencer | +2.825 |
JC | +2.806 |
Neg logit contributions | |
ktop | -3.930 |
acs | -3.879 |
olla | -3.875 |
rog | -3.775 |
impaired | -3.684 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Yao | +1.277 |
Debor | +1.144 |
Spencer | +1.127 |
intern | +1.123 |
JC | +1.122 |
Neg logit contributions | |
ktop | -1.317 |
olla | -1.311 |
acs | -1.310 |
rog | -1.279 |
impaired | -1.237 |
Token | : |
Token ID | 25 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Yao | +0.218 |
Debor | +0.194 |
intern | +0.189 |
JC | +0.189 |
Spencer | +0.189 |
Neg logit contributions | |
ktop | -0.256 |
acs | -0.256 |
olla | -0.256 |
rog | -0.250 |
impaired | -0.245 |
Token | 01 |
Token ID | 486 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Yao | +0.746 |
Debor | +0.656 |
JC | +0.644 |
Spencer | +0.642 |
intern | +0.636 |
Neg logit contributions | |
ktop | -0.954 |
acs | -0.950 |
olla | -0.948 |
rog | -0.931 |
impaired | -0.914 |
Token | p |
Token ID | 279 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Yao | +1.920 |
Debor | +1.731 |
JC | +1.726 |
Spencer | +1.707 |
intern | +1.706 |
Neg logit contributions | |
ktop | -1.916 |
olla | -1.900 |
acs | -1.898 |
rog | -1.837 |
impaired | -1.806 |
Token | ta |
Token ID | 8326 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Yao | +0.319 |
Debor | +0.284 |
JC | +0.277 |
Spencer | +0.277 |
intern | +0.276 |
Neg logit contributions | |
ktop | -0.382 |
olla | -0.381 |
acs | -0.380 |
rog | -0.374 |
impaired | -0.367 |
Token | Pi |
Token ID | 13993 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
olla | +0.365 |
ktop | +0.365 |
acs | +0.365 |
rog | +0.359 |
impaired | +0.351 |
Neg logit contributions | |
Yao | -0.253 |
Debor | -0.221 |
JC | -0.215 |
intern | -0.215 |
Spencer | -0.215 |
Token | ($ |
Token ID | 7198 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Yao | +0.073 |
Debor | +0.066 |
intern | +0.064 |
JC | +0.064 |
Spencer | +0.064 |
Neg logit contributions | |
ktop | -0.072 |
olla | -0.072 |
acs | -0.072 |
rog | -0.071 |
impaired | -0.069 |
Token | 400 |
Token ID | 7029 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
olla | +1.112 |
acs | +1.112 |
ktop | +1.108 |
rog | +1.087 |
impaired | +1.055 |
Neg logit contributions | |
Yao | -1.320 |
Debor | -1.198 |
intern | -1.173 |
JC | -1.170 |
Spencer | -1.168 |
Token | per |
Token ID | 583 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Yao | +1.183 |
Debor | +1.063 |
intern | +1.048 |
Spencer | +1.045 |
JC | +1.044 |
Neg logit contributions | |
ktop | -1.112 |
olla | -1.111 |
acs | -1.108 |
rog | -1.091 |
impaired | -1.059 |
Token | semester |
Token ID | 24878 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
Yao | +1.823 |
intern | +1.601 |
Debor | +1.591 |
Spencer | +1.583 |
JC | +1.574 |
Neg logit contributions | |
olla | -2.524 |
ktop | -2.522 |
acs | -2.498 |
rog | -2.473 |
impaired | -2.404 |
Token | ), |
Token ID | 828 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
Yao | +3.832 |
intern | +3.475 |
Debor | +3.461 |
JC | +3.440 |
Spencer | +3.427 |
Neg logit contributions | |
ktop | -3.163 |
acs | -3.129 |
olla | -3.119 |
rog | -3.088 |
neur | -2.960 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
acs | +0.728 |
olla | +0.727 |
ktop | +0.726 |
rog | +0.713 |
impaired | +0.697 |
Neg logit contributions | |
Yao | -0.638 |
Debor | -0.569 |
intern | -0.554 |
JC | -0.553 |
Spencer | -0.552 |
Token | Delta |
Token ID | 16978 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
ktop | +0.115 |
olla | +0.115 |
acs | +0.115 |
rog | +0.113 |
impaired | +0.110 |
Neg logit contributions | |
Yao | -0.106 |
Debor | -0.095 |
JC | -0.093 |
Spencer | -0.093 |
intern | -0.093 |
Token | Tau |
Token ID | 36849 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Yao | +0.650 |
Debor | +0.576 |
JC | +0.566 |
Spencer | +0.564 |
intern | +0.562 |
Neg logit contributions | |
ktop | -0.805 |
olla | -0.803 |
acs | -0.801 |
rog | -0.787 |
impaired | -0.773 |
Token | Delta |
Token ID | 16978 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Yao | +0.821 |
Debor | +0.730 |
JC | +0.718 |
Spencer | +0.714 |
intern | +0.713 |
Neg logit contributions | |
ktop | -0.930 |
acs | -0.924 |
olla | -0.921 |
rog | -0.904 |
impaired | -0.891 |
Token | ay |
Token ID | 323 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Yao | +0.442 |
Debor | +0.352 |
Spencer | +0.342 |
intern | +0.342 |
JC | +0.340 |
Neg logit contributions | |
ktop | -1.156 |
acs | -1.152 |
olla | -1.144 |
rog | -1.131 |
impaired | -1.122 |
Token | ko |
Token ID | 7204 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ktop | +0.369 |
olla | +0.365 |
acs | +0.364 |
rog | +0.360 |
impaired | +0.353 |
Neg logit contributions | |
Yao | -0.257 |
Debor | -0.225 |
JC | -0.221 |
intern | -0.220 |
Spencer | -0.219 |
Token | ( |
Token ID | 357 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
Yao | +0.216 |
Debor | +0.195 |
intern | +0.191 |
JC | +0.191 |
Spencer | +0.191 |
Neg logit contributions | |
ktop | -0.198 |
olla | -0.198 |
acs | -0.198 |
rog | -0.194 |
impaired | -0.189 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Yao | +0.399 |
Debor | +0.355 |
Spencer | +0.349 |
JC | +0.348 |
intern | +0.346 |
Neg logit contributions | |
ktop | -0.463 |
olla | -0.460 |
acs | -0.459 |
rog | -0.448 |
impaired | -0.444 |
Token | : |
Token ID | 25 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
olla | +0.134 |
acs | +0.133 |
ktop | +0.133 |
rog | +0.131 |
impaired | +0.128 |
Neg logit contributions | |
Yao | -0.120 |
Debor | -0.108 |
intern | -0.104 |
JC | -0.104 |
Spencer | -0.104 |
Token | 05 |
Token ID | 2713 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
Yao | +1.080 |
Debor | +0.935 |
JC | +0.926 |
Spencer | +0.922 |
intern | +0.911 |
Neg logit contributions | |
ktop | -1.476 |
acs | -1.456 |
olla | -1.454 |
rog | -1.428 |
impaired | -1.414 |
Token | ) |
Token ID | 8 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Yao | +3.878 |
JC | +3.482 |
Spencer | +3.467 |
Debor | +3.460 |
intern | +3.450 |
Neg logit contributions | |
ktop | -3.111 |
acs | -3.093 |
olla | -3.060 |
rog | -3.014 |
impaired | -2.915 |
Token | and |
Token ID | 290 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Yao | +1.523 |
Debor | +1.352 |
Spencer | +1.329 |
JC | +1.328 |
intern | +1.326 |
Neg logit contributions | |
ktop | -1.843 |
acs | -1.837 |
olla | -1.835 |
rog | -1.802 |
impaired | -1.758 |
Token | Vladimir |
Token ID | 14840 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Yao | +0.211 |
Debor | +0.188 |
Spencer | +0.185 |
JC | +0.184 |
intern | +0.183 |
Neg logit contributions | |
ktop | -0.239 |
olla | -0.239 |
acs | -0.238 |
rog | -0.234 |
impaired | -0.227 |
Token | Tar |
Token ID | 14110 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
Yao | +0.492 |
Debor | +0.409 |
intern | +0.390 |
JC | +0.388 |
Spencer | +0.387 |
Neg logit contributions | |
acs | -1.187 |
olla | -1.185 |
ktop | -1.184 |
rog | -1.169 |
impaired | -1.149 |
Token | as |
Token ID | 292 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
ktop | +0.082 |
olla | +0.082 |
acs | +0.082 |
rog | +0.080 |
impaired | +0.079 |
Neg logit contributions | |
Yao | -0.063 |
Debor | -0.056 |
intern | -0.054 |
JC | -0.054 |
Spencer | -0.054 |
Token | ushes |
Token ID | 17237 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Yao | +1.367 |
Spencer | +1.248 |
intern | +1.244 |
Debor | +1.231 |
JC | +1.228 |
Neg logit contributions | |
ktop | -0.828 |
olla | -0.806 |
rog | -0.788 |
acs | -0.783 |
impaired | -0.777 |
Token | : |
Token ID | 25 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Yao | +2.200 |
JC | +1.886 |
Spencer | +1.883 |
intern | +1.856 |
Debor | +1.844 |
Neg logit contributions | |
ktop | -3.214 |
acs | -3.157 |
olla | -3.140 |
neur | -3.100 |
rog | -3.085 |
Token | 33 |
Token ID | 4747 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Yao | +0.960 |
Debor | +0.844 |
Spencer | +0.825 |
JC | +0.823 |
intern | +0.815 |
Neg logit contributions | |
ktop | -1.292 |
acs | -1.286 |
olla | -1.284 |
rog | -1.259 |
impaired | -1.229 |
Token |
|
Token ID | 198 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Yao | +1.488 |
Debor | +1.347 |
JC | +1.336 |
intern | +1.331 |
Spencer | +1.330 |
Neg logit contributions | |
ktop | -1.110 |
acs | -1.098 |
olla | -1.089 |
rog | -1.068 |
neur | -1.043 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
Yao | +2.501 |
JC | +2.224 |
Spencer | +2.216 |
Debor | +2.213 |
intern | +2.195 |
Neg logit contributions | |
ktop | -2.187 |
acs | -2.145 |
olla | -2.114 |
neur | -2.074 |
impaired | -2.053 |
Token | Opp |
Token ID | 27524 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
Yao | +2.557 |
•• | +2.342 |
Debor | +2.239 |
Spencer | +2.226 |
JC | +2.194 |
Neg logit contributions | |
ktop | -2.573 |
acs | -2.554 |
olla | -2.521 |
impaired | -2.487 |
neur | -2.469 |
Token | onent |
Token ID | 3471 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Yao | +3.852 |
Debor | +3.485 |
Spencer | +3.442 |
JC | +3.439 |
intern | +3.436 |
Neg logit contributions | |
ktop | -3.022 |
acs | -3.000 |
olla | -2.950 |
impaired | -2.862 |
rog | -2.840 |
Token | : |
Token ID | 25 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
Yao | +2.426 |
JC | +2.084 |
Spencer | +2.075 |
Debor | +2.052 |
intern | +2.037 |
Neg logit contributions | |
ktop | -3.591 |
acs | -3.532 |
olla | -3.500 |
neur | -3.443 |
rog | -3.428 |
Token | Miami |
Token ID | 8437 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ktop | +0.051 |
acs | +0.051 |
olla | +0.051 |
rog | +0.049 |
impaired | +0.048 |
Neg logit contributions | |
Yao | -0.045 |
Debor | -0.040 |
JC | -0.039 |
Spencer | -0.039 |
intern | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Yao | +3.142 |
JC | +2.843 |
Debor | +2.841 |
intern | +2.816 |
Spencer | +2.798 |
Neg logit contributions | |
ktop | -2.534 |
acs | -2.494 |
olla | -2.494 |
rog | -2.441 |
lime | -2.370 |
Token |
|
Token ID | 198 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Yao | +1.969 |
JC | +1.757 |
Spencer | +1.747 |
intern | +1.736 |
Debor | +1.732 |
Neg logit contributions | |
ktop | -1.690 |
acs | -1.652 |
olla | -1.634 |
neur | -1.604 |
rog | -1.598 |
Token | he |
Token ID | 339 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Yao | +0.353 |
Debor | +0.320 |
Spencer | +0.315 |
JC | +0.313 |
intern | +0.312 |
Neg logit contributions | |
ktop | -0.293 |
acs | -0.292 |
olla | -0.292 |
rog | -0.285 |
impaired | -0.276 |
Token | says |
Token ID | 1139 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Yao | +0.319 |
Debor | +0.292 |
intern | +0.288 |
Spencer | +0.286 |
JC | +0.286 |
Neg logit contributions | |
ktop | -0.230 |
acs | -0.227 |
olla | -0.226 |
rog | -0.223 |
impaired | -0.214 |
Token | , |
Token ID | 11 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
acs | +1.080 |
olla | +1.079 |
ktop | +1.076 |
rog | +1.056 |
impaired | +1.030 |
Neg logit contributions | |
Yao | -1.154 |
Debor | -1.041 |
intern | -1.017 |
JC | -1.016 |
Spencer | -1.014 |
Token | sounding |
Token ID | 22655 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Yao | +0.353 |
Debor | +0.316 |
intern | +0.310 |
Spencer | +0.309 |
JC | +0.308 |
Neg logit contributions | |
olla | -0.357 |
ktop | -0.356 |
acs | -0.355 |
rog | -0.348 |
impaired | -0.337 |
Token | p |
Token ID | 279 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Yao | +1.422 |
intern | +1.274 |
Debor | +1.272 |
Spencer | +1.266 |
JC | +1.257 |
Neg logit contributions | |
olla | -1.104 |
ktop | -1.097 |
acs | -1.089 |
rog | -1.055 |
lime | -1.022 |
Token | ained |
Token ID | 1328 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
Yao | +0.707 |
Debor | +0.649 |
intern | +0.643 |
Spencer | +0.642 |
JC | +0.641 |
Neg logit contributions | |
ktop | -0.300 |
acs | -0.297 |
olla | -0.295 |
rog | -0.281 |
impaired | -0.278 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Yao | +3.190 |
intern | +2.793 |
Debor | +2.773 |
Spencer | +2.760 |
JC | +2.723 |
Neg logit contributions | |
acs | -3.823 |
ktop | -3.784 |
olla | -3.737 |
rog | -3.713 |
\/\/ | -3.551 |
Token |
|
Token ID | 198 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
Yao | +0.889 |
Debor | +0.801 |
Spencer | +0.789 |
JC | +0.784 |
intern | +0.769 |
Neg logit contributions | |
ktop | -0.813 |
acs | -0.806 |
olla | -0.803 |
rog | -0.788 |
impaired | -0.774 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Yao | +0.732 |
Spencer | +0.652 |
JC | +0.651 |
Debor | +0.651 |
•• | +0.645 |
Neg logit contributions | |
ktop | -0.575 |
acs | -0.564 |
olla | -0.562 |
rog | -0.545 |
neur | -0.544 |
Token | So |
Token ID | 2396 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
Yao | +0.199 |
Debor | +0.178 |
•• | +0.175 |
Spencer | +0.175 |
JC | +0.174 |
Neg logit contributions | |
ktop | -0.195 |
olla | -0.194 |
acs | -0.194 |
rog | -0.189 |
impaired | -0.187 |
Token | you |
Token ID | 345 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Yao | +0.808 |
Debor | +0.727 |
Spencer | +0.721 |
intern | +0.715 |
JC | +0.715 |
Neg logit contributions | |
olla | -0.646 |
acs | -0.643 |
ktop | -0.642 |
rog | -0.626 |
impaired | -0.607 |
Token | comment |
Token ID | 2912 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
acs | +2.387 |
olla | +2.386 |
ktop | +2.380 |
rog | +2.346 |
impaired | +2.293 |
Neg logit contributions | |
Yao | -2.257 |
Debor | -2.049 |
unden | -1.999 |
intern | -1.956 |
Spencer | -1.955 |
Token | on |
Token ID | 319 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
olla | +3.824 |
impaired | +3.772 |
rog | +3.763 |
ktop | +3.718 |
acs | +3.704 |
Neg logit contributions | |
Yao | -4.931 |
unden | -4.679 |
Debor | -4.609 |
confir | -4.421 |
•• | -4.344 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
olla | +2.197 |
acs | +2.176 |
ktop | +2.162 |
rog | +2.156 |
impaired | +2.109 |
Neg logit contributions | |
Yao | -3.268 |
Debor | -3.041 |
unden | -2.970 |
intern | -2.878 |
JC | -2.869 |
Token | Share |
Token ID | 8734 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
acs | +3.128 |
olla | +3.120 |
impaired | +3.089 |
rog | +3.068 |
lime | +3.031 |
Neg logit contributions | |
Yao | -3.269 |
Debor | -3.066 |
unden | -2.915 |
•• | -2.874 |
Palest | -2.842 |
Token | this |
Token ID | 428 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
olla | +0.492 |
ktop | +0.491 |
acs | +0.490 |
rog | +0.478 |
impaired | +0.466 |
Neg logit contributions | |
Yao | -0.456 |
Debor | -0.406 |
intern | -0.399 |
JC | -0.398 |
Spencer | -0.397 |
Token | comment |
Token ID | 2912 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
acs | +1.169 |
olla | +1.169 |
ktop | +1.164 |
rog | +1.151 |
impaired | +1.123 |
Neg logit contributions | |
Yao | -1.080 |
Debor | -0.974 |
unden | -0.951 |
Spencer | -0.937 |
JC | -0.937 |
Token | on |
Token ID | 319 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
olla | +4.205 |
acs | +4.154 |
ktop | +4.126 |
rog | +4.109 |
impaired | +4.023 |
Neg logit contributions | |
Yao | -4.709 |
unden | -4.698 |
Debor | -4.400 |
confir | -4.308 |
Palest | -4.261 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
olla | +2.657 |
rog | +2.632 |
acs | +2.617 |
ktop | +2.598 |
impaired | +2.559 |
Neg logit contributions | |
Yao | -2.879 |
unden | -2.580 |
Debor | -2.570 |
Palest | -2.470 |
•• | -2.443 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
acs | +2.600 |
olla | +2.594 |
ktop | +2.557 |
rog | +2.531 |
impaired | +2.494 |
Neg logit contributions | |
Yao | -3.556 |
Debor | -3.262 |
intern | -3.190 |
unden | -3.185 |
•• | -3.169 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ktop | +1.456 |
acs | +1.456 |
olla | +1.454 |
rog | +1.417 |
impaired | +1.375 |
Neg logit contributions | |
Yao | -2.174 |
Debor | -1.985 |
JC | -1.951 |
intern | -1.950 |
Spencer | -1.948 |
Token | NY |
Token ID | 12805 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
ktop | +1.100 |
acs | +1.098 |
olla | +1.097 |
rog | +1.070 |
impaired | +1.047 |
Neg logit contributions | |
Yao | -1.322 |
Debor | -1.198 |
JC | -1.174 |
intern | -1.174 |
Spencer | -1.173 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ktop | +0.204 |
acs | +0.201 |
olla | +0.200 |
rog | +0.194 |
impaired | +0.189 |
Neg logit contributions | |
Yao | -0.268 |
Debor | -0.242 |
JC | -0.241 |
Spencer | -0.239 |
intern | -0.239 |
Token |
|
Token ID | 198 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
ktop | +1.342 |
acs | +1.333 |
olla | +1.331 |
rog | +1.295 |
impaired | +1.262 |
Neg logit contributions | |
Yao | -1.931 |
Debor | -1.752 |
JC | -1.731 |
intern | -1.727 |
Spencer | -1.727 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ktop | +0.674 |
acs | +0.673 |
olla | +0.671 |
rog | +0.657 |
impaired | +0.640 |
Neg logit contributions | |
Yao | -0.789 |
Debor | -0.714 |
JC | -0.700 |
intern | -0.699 |
Spencer | -0.698 |
Token | Share |
Token ID | 8734 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Yao | +0.763 |
Debor | +0.660 |
JC | +0.651 |
Spencer | +0.651 |
intern | +0.650 |
Neg logit contributions | |
ktop | -1.169 |
olla | -1.169 |
acs | -1.168 |
rog | -1.142 |
impaired | -1.119 |
Token | this |
Token ID | 428 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Yao | +0.145 |
Debor | +0.128 |
Spencer | +0.127 |
intern | +0.127 |
JC | +0.126 |
Neg logit contributions | |
ktop | -0.169 |
olla | -0.168 |
acs | -0.167 |
rog | -0.162 |
\/\/ | -0.158 |
Token | comment |
Token ID | 2912 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
acs | +2.387 |
olla | +2.386 |
ktop | +2.380 |
rog | +2.346 |
impaired | +2.293 |
Neg logit contributions | |
Yao | -2.257 |
Debor | -2.049 |
unden | -1.999 |
intern | -1.956 |
Spencer | -1.955 |
Token | on |
Token ID | 319 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
olla | +3.824 |
impaired | +3.772 |
rog | +3.763 |
ktop | +3.718 |
acs | +3.704 |
Neg logit contributions | |
Yao | -4.931 |
unden | -4.679 |
Debor | -4.609 |
confir | -4.421 |
•• | -4.344 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
olla | +2.197 |
acs | +2.176 |
ktop | +2.162 |
rog | +2.156 |
impaired | +2.109 |
Neg logit contributions | |
Yao | -3.268 |
Debor | -3.041 |
unden | -2.970 |
intern | -2.878 |
JC | -2.869 |
Token | Share |
Token ID | 8734 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
acs | +3.128 |
olla | +3.120 |
impaired | +3.089 |
rog | +3.068 |
lime | +3.031 |
Neg logit contributions | |
Yao | -3.269 |
Debor | -3.066 |
unden | -2.915 |
•• | -2.874 |
Palest | -2.842 |
Token | this |
Token ID | 428 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
olla | +0.492 |
ktop | +0.491 |
acs | +0.490 |
rog | +0.478 |
impaired | +0.466 |
Neg logit contributions | |
Yao | -0.456 |
Debor | -0.406 |
intern | -0.399 |
JC | -0.398 |
Spencer | -0.397 |
Token | comment |
Token ID | 2912 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
acs | +1.169 |
olla | +1.169 |
ktop | +1.164 |
rog | +1.151 |
impaired | +1.123 |
Neg logit contributions | |
Yao | -1.080 |
Debor | -0.974 |
unden | -0.951 |
Spencer | -0.937 |
JC | -0.937 |
Token | type |
Token ID | 2099 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
olla | +1.600 |
acs | +1.596 |
ktop | +1.582 |
rog | +1.559 |
impaired | +1.521 |
Neg logit contributions | |
Yao | -1.788 |
Debor | -1.626 |
intern | -1.580 |
unden | -1.578 |
JC | -1.576 |
Token | - |
Token ID | 12 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
acs | +1.497 |
olla | +1.496 |
ktop | +1.472 |
rog | +1.461 |
impaired | +1.422 |
Neg logit contributions | |
Yao | -2.026 |
Debor | -1.854 |
unden | -1.805 |
Spencer | -1.798 |
intern | -1.796 |
Token | 94 |
Token ID | 5824 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ktop | +0.142 |
acs | +0.141 |
olla | +0.141 |
rog | +0.138 |
impaired | +0.135 |
Neg logit contributions | |
Yao | -0.138 |
Debor | -0.124 |
JC | -0.122 |
Spencer | -0.121 |
intern | -0.121 |
Token | Jin |
Token ID | 17297 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
olla | +1.510 |
acs | +1.507 |
ktop | +1.501 |
rog | +1.482 |
impaired | +1.450 |
Neg logit contributions | |
Yao | -1.204 |
Debor | -1.074 |
intern | -1.045 |
unden | -1.043 |
JC | -1.040 |
Token | - |
Token ID | 12 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
olla | +1.121 |
acs | +1.120 |
ktop | +1.111 |
rog | +1.096 |
impaired | +1.063 |
Neg logit contributions | |
Yao | -1.310 |
Debor | -1.197 |
intern | -1.165 |
Spencer | -1.164 |
JC | -1.163 |
Token | class |
Token ID | 4871 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
acs | +1.319 |
olla | +1.319 |
ktop | +1.311 |
rog | +1.292 |
impaired | +1.252 |
Neg logit contributions | |
Yao | -1.444 |
Debor | -1.310 |
intern | -1.279 |
Spencer | -1.275 |
JC | -1.273 |
Token | and |
Token ID | 290 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
olla | +4.195 |
acs | +4.189 |
rog | +4.117 |
ktop | +4.046 |
impaired | +4.022 |
Neg logit contributions | |
Yao | -4.506 |
Debor | -4.127 |
unden | -4.033 |
Spencer | -3.960 |
JC | -3.939 |
Token | type |
Token ID | 2099 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
olla | +1.477 |
acs | +1.475 |
ktop | +1.468 |
rog | +1.445 |
impaired | +1.411 |
Neg logit contributions | |
Yao | -1.646 |
Debor | -1.494 |
intern | -1.454 |
Spencer | -1.452 |
JC | -1.450 |
Token | - |
Token ID | 12 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
olla | +1.750 |
acs | +1.749 |
ktop | +1.742 |
rog | +1.711 |
impaired | +1.661 |
Neg logit contributions | |
Yao | -2.250 |
Debor | -2.054 |
unden | -2.010 |
intern | -2.005 |
Spencer | -2.000 |
Token | 96 |
Token ID | 4846 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ktop | +0.228 |
olla | +0.226 |
acs | +0.226 |
rog | +0.221 |
impaired | +0.217 |
Neg logit contributions | |
Yao | -0.250 |
Debor | -0.225 |
JC | -0.222 |
Spencer | -0.221 |
intern | -0.221 |
Token | ), |
Token ID | 828 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
olla | +0.385 |
acs | +0.385 |
ktop | +0.384 |
rog | +0.378 |
impaired | +0.369 |
Neg logit contributions | |
Yao | -0.344 |
Debor | -0.308 |
intern | -0.300 |
JC | -0.299 |
Spencer | -0.299 |
Token | : |
Token ID | 25 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Yao | +1.201 |
Debor | +1.052 |
JC | +1.040 |
Spencer | +1.033 |
intern | +1.028 |
Neg logit contributions | |
ktop | -1.564 |
acs | -1.551 |
olla | -1.544 |
rog | -1.520 |
impaired | -1.488 |
Token | 05 |
Token ID | 8870 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
acs | +0.289 |
ktop | +0.288 |
olla | +0.288 |
rog | +0.284 |
impaired | +0.277 |
Neg logit contributions | |
Yao | -0.245 |
Debor | -0.218 |
JC | -0.213 |
intern | -0.213 |
Spencer | -0.212 |
Token | 43 |
Token ID | 3559 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Yao | +0.536 |
Debor | +0.470 |
JC | +0.458 |
Spencer | +0.455 |
intern | +0.454 |
Neg logit contributions | |
ktop | -0.719 |
acs | -0.714 |
olla | -0.711 |
rog | -0.699 |
impaired | -0.689 |
Token | z |
Token ID | 89 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ktop | +0.732 |
acs | +0.727 |
olla | +0.726 |
rog | +0.706 |
impaired | +0.690 |
Neg logit contributions | |
Yao | -1.168 |
Debor | -1.069 |
intern | -1.055 |
JC | -1.054 |
Spencer | -1.052 |
Token | ST |
Token ID | 3563 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Yao | +0.019 |
Debor | +0.017 |
JC | +0.017 |
intern | +0.017 |
Spencer | +0.017 |
Neg logit contributions | |
ktop | -0.020 |
acs | -0.020 |
olla | -0.020 |
rog | -0.020 |
impaired | -0.019 |
Token | OW |
Token ID | 3913 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
olla | +1.151 |
acs | +1.147 |
ktop | +1.140 |
rog | +1.124 |
impaired | +1.089 |
Neg logit contributions | |
Yao | -1.378 |
Debor | -1.259 |
JC | -1.224 |
intern | -1.224 |
Spencer | -1.220 |
Token | MA |
Token ID | 8779 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
olla | +4.503 |
acs | +4.484 |
ktop | +4.403 |
rog | +4.358 |
impaired | +4.305 |
Neg logit contributions | |
Yao | -4.113 |
Debor | -3.683 |
unden | -3.647 |
intern | -3.549 |
Spencer | -3.543 |
Token | IN |
Token ID | 1268 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
acs | +0.648 |
ktop | +0.648 |
olla | +0.647 |
rog | +0.636 |
impaired | +0.624 |
Neg logit contributions | |
Yao | -0.488 |
Debor | -0.427 |
JC | -0.420 |
intern | -0.418 |
Spencer | -0.418 |
Token | RE |
Token ID | 4526 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
olla | +0.439 |
acs | +0.439 |
ktop | +0.439 |
rog | +0.430 |
impaired | +0.419 |
Neg logit contributions | |
Yao | -0.420 |
Debor | -0.377 |
JC | -0.368 |
intern | -0.368 |
Spencer | -0.367 |
Token | P |
Token ID | 47 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Yao | +0.206 |
Debor | +0.185 |
intern | +0.180 |
JC | +0.180 |
Spencer | +0.180 |
Neg logit contributions | |
olla | -0.206 |
acs | -0.206 |
ktop | -0.206 |
rog | -0.202 |
impaired | -0.197 |
Token | ORTS |
Token ID | 33002 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
acs | +0.149 |
olla | +0.149 |
ktop | +0.148 |
rog | +0.146 |
impaired | +0.142 |
Neg logit contributions | |
Yao | -0.126 |
Debor | -0.112 |
intern | -0.109 |
JC | -0.109 |
Spencer | -0.109 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
olla | +2.033 |
acs | +2.032 |
ktop | +2.023 |
rog | +1.997 |
impaired | +1.952 |
Neg logit contributions | |
Yao | -1.848 |
Debor | -1.661 |
unden | -1.614 |
JC | -1.603 |
Spencer | -1.603 |
Token | on |
Token ID | 319 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
olla | +4.064 |
acs | +4.014 |
ktop | +3.982 |
rog | +3.977 |
impaired | +3.876 |
Neg logit contributions | |
Yao | -4.420 |
unden | -4.356 |
Debor | -4.108 |
confir | -4.069 |
Palest | -3.948 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
olla | +2.690 |
acs | +2.667 |
ktop | +2.646 |
rog | +2.625 |
impaired | +2.510 |
Neg logit contributions | |
Yao | -3.632 |
unden | -3.473 |
Debor | -3.405 |
confir | -3.315 |
intern | -3.273 |
Token | Share |
Token ID | 8734 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
acs | +3.938 |
olla | +3.935 |
rog | +3.858 |
ktop | +3.856 |
impaired | +3.774 |
Neg logit contributions | |
Yao | -3.580 |
unden | -3.483 |
Debor | -3.342 |
confir | -3.254 |
intern | -3.160 |
Token | this |
Token ID | 428 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ktop | +0.625 |
acs | +0.624 |
olla | +0.622 |
rog | +0.608 |
impaired | +0.593 |
Neg logit contributions | |
Yao | -0.570 |
Debor | -0.506 |
intern | -0.499 |
JC | -0.498 |
Spencer | -0.498 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
olla | +1.305 |
acs | +1.305 |
ktop | +1.303 |
rog | +1.280 |
impaired | +1.250 |
Neg logit contributions | |
Yao | -1.151 |
Debor | -1.027 |
intern | -1.000 |
JC | -0.999 |
Spencer | -0.998 |
Token | on |
Token ID | 319 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
olla | +4.156 |
acs | +4.110 |
ktop | +4.085 |
rog | +4.063 |
impaired | +3.966 |
Neg logit contributions | |
Yao | -4.384 |
unden | -4.268 |
Debor | -4.064 |
confir | -3.998 |
Palest | -3.899 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
olla | +2.885 |
acs | +2.846 |
rog | +2.838 |
ktop | +2.820 |
impaired | +2.748 |
Neg logit contributions | |
Yao | -2.730 |
unden | -2.570 |
Debor | -2.472 |
confir | -2.460 |
intern | -2.399 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
olla | +2.955 |
acs | +2.951 |
ktop | +2.895 |
rog | +2.884 |
impaired | +2.798 |
Neg logit contributions | |
Yao | -4.707 |
Debor | -4.340 |
unden | -4.245 |
intern | -4.237 |
•• | -4.226 |
Token |
|
Token ID | 198 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
olla | +2.146 |
acs | +2.140 |
ktop | +2.119 |
rog | +2.089 |
impaired | +2.012 |
Neg logit contributions | |
Yao | -3.453 |
Debor | -3.191 |
unden | -3.176 |
intern | -3.116 |
JC | -3.104 |
Token | NY |
Token ID | 12805 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
olla | +1.847 |
acs | +1.846 |
ktop | +1.832 |
rog | +1.804 |
impaired | +1.734 |
Neg logit contributions | |
Yao | -2.787 |
Debor | -2.557 |
intern | -2.502 |
JC | -2.497 |
Spencer | -2.495 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ktop | +1.073 |
acs | +1.068 |
olla | +1.066 |
rog | +1.035 |
impaired | +1.007 |
Neg logit contributions | |
Yao | -1.535 |
Debor | -1.395 |
JC | -1.375 |
Spencer | -1.373 |
intern | -1.373 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ktop | +1.461 |
acs | +1.459 |
olla | +1.458 |
rog | +1.419 |
impaired | +1.378 |
Neg logit contributions | |
Yao | -2.172 |
Debor | -1.982 |
JC | -1.948 |
intern | -1.948 |
Spencer | -1.946 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ktop | +0.933 |
acs | +0.925 |
olla | +0.917 |
rog | +0.895 |
impaired | +0.885 |
Neg logit contributions | |
Yao | -1.004 |
Debor | -0.898 |
JC | -0.889 |
Spencer | -0.887 |
•• | -0.886 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Yao | +0.505 |
Debor | +0.435 |
Spencer | +0.431 |
JC | +0.431 |
intern | +0.427 |
Neg logit contributions | |
ktop | -0.793 |
acs | -0.791 |
olla | -0.790 |
rog | -0.772 |
impaired | -0.756 |
Token | this |
Token ID | 428 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ktop | +0.131 |
olla | +0.130 |
acs | +0.130 |
rog | +0.126 |
lime | +0.122 |
Neg logit contributions | |
Yao | -0.110 |
intern | -0.097 |
Debor | -0.097 |
JC | -0.096 |
Spencer | -0.096 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
olla | +2.033 |
acs | +2.032 |
ktop | +2.023 |
rog | +1.997 |
impaired | +1.952 |
Neg logit contributions | |
Yao | -1.848 |
Debor | -1.661 |
unden | -1.614 |
JC | -1.603 |
Spencer | -1.603 |
Token | on |
Token ID | 319 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
olla | +4.064 |
acs | +4.014 |
ktop | +3.982 |
rog | +3.977 |
impaired | +3.876 |
Neg logit contributions | |
Yao | -4.420 |
unden | -4.356 |
Debor | -4.108 |
confir | -4.069 |
Palest | -3.948 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
olla | +2.690 |
acs | +2.667 |
ktop | +2.646 |
rog | +2.625 |
impaired | +2.510 |
Neg logit contributions | |
Yao | -3.632 |
unden | -3.473 |
Debor | -3.405 |
confir | -3.315 |
intern | -3.273 |
Token | Share |
Token ID | 8734 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
acs | +3.938 |
olla | +3.935 |
rog | +3.858 |
ktop | +3.856 |
impaired | +3.774 |
Neg logit contributions | |
Yao | -3.580 |
unden | -3.483 |
Debor | -3.342 |
confir | -3.254 |
intern | -3.160 |
Token | this |
Token ID | 428 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ktop | +0.625 |
acs | +0.624 |
olla | +0.622 |
rog | +0.608 |
impaired | +0.593 |
Neg logit contributions | |
Yao | -0.570 |
Debor | -0.506 |
intern | -0.499 |
JC | -0.498 |
Spencer | -0.498 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
olla | +1.305 |
acs | +1.305 |
ktop | +1.303 |
rog | +1.280 |
impaired | +1.250 |
Neg logit contributions | |
Yao | -1.151 |
Debor | -1.027 |
intern | -1.000 |
JC | -0.999 |
Spencer | -0.998 |
Token | Middle |
Token ID | 6046 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
olla | +0.881 |
ktop | +0.881 |
acs | +0.880 |
rog | +0.863 |
impaired | +0.842 |
Neg logit contributions | |
Yao | -0.779 |
Debor | -0.697 |
intern | -0.679 |
JC | -0.678 |
Spencer | -0.677 |
Token | Level |
Token ID | 5684 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
olla | +0.138 |
ktop | +0.138 |
acs | +0.137 |
rog | +0.134 |
impaired | +0.131 |
Neg logit contributions | |
Yao | -0.135 |
Debor | -0.121 |
JC | -0.119 |
intern | -0.118 |
Spencer | -0.118 |
Token | Education |
Token ID | 7868 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Yao | +0.735 |
Debor | +0.656 |
intern | +0.641 |
JC | +0.641 |
Spencer | +0.639 |
Neg logit contributions | |
ktop | -0.859 |
olla | -0.857 |
acs | -0.853 |
rog | -0.835 |
impaired | -0.816 |
Token | , |
Token ID | 11 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
acs | +0.801 |
olla | +0.800 |
ktop | +0.798 |
rog | +0.784 |
impaired | +0.766 |
Neg logit contributions | |
Yao | -0.772 |
Debor | -0.692 |
intern | -0.674 |
JC | -0.674 |
Spencer | -0.673 |
Token | 33 |
Token ID | 4747 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
olla | +0.395 |
acs | +0.395 |
ktop | +0.394 |
rog | +0.387 |
impaired | +0.377 |
Neg logit contributions | |
Yao | -0.363 |
Debor | -0.324 |
intern | -0.317 |
JC | -0.316 |
Spencer | -0.316 |
Token | ( |
Token ID | 7 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
olla | +0.952 |
acs | +0.951 |
ktop | +0.938 |
rog | +0.928 |
impaired | +0.901 |
Neg logit contributions | |
Yao | -1.143 |
Debor | -1.036 |
Spencer | -1.008 |
unden | -1.005 |
JC | -1.004 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
olla | +4.049 |
acs | +4.045 |
rog | +3.963 |
ktop | +3.952 |
impaired | +3.825 |
Neg logit contributions | |
Yao | -4.256 |
Debor | -3.848 |
unden | -3.799 |
intern | -3.740 |
JC | -3.685 |
Token | ), |
Token ID | 828 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
olla | +0.739 |
acs | +0.739 |
ktop | +0.736 |
rog | +0.720 |
impaired | +0.697 |
Neg logit contributions | |
Yao | -1.118 |
Debor | -1.024 |
intern | -1.003 |
JC | -1.002 |
Spencer | -1.001 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
olla | +0.494 |
acs | +0.494 |
ktop | +0.494 |
rog | +0.484 |
impaired | +0.473 |
Neg logit contributions | |
Yao | -0.441 |
Debor | -0.393 |
JC | -0.383 |
intern | -0.383 |
Spencer | -0.382 |
Token | - |
Token ID | 532 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
ktop | +0.118 |
olla | +0.118 |
acs | +0.117 |
rog | +0.115 |
impaired | +0.111 |
Neg logit contributions | |
Yao | -0.184 |
Debor | -0.169 |
JC | -0.166 |
Spencer | -0.166 |
intern | -0.166 |
Token | 13 |
Token ID | 1511 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
ktop | +0.022 |
acs | +0.022 |
olla | +0.022 |
rog | +0.022 |
impaired | +0.021 |
Neg logit contributions | |
Yao | -0.018 |
Debor | -0.016 |
JC | -0.016 |
intern | -0.016 |
Spencer | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ktop | +1.291 |
acs | +1.288 |
olla | +1.287 |
rog | +1.251 |
impaired | +1.215 |
Neg logit contributions | |
Yao | -1.901 |
Debor | -1.734 |
JC | -1.704 |
intern | -1.703 |
Spencer | -1.701 |
Token |
|
Token ID | 198 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
ktop | +1.183 |
acs | +1.177 |
olla | +1.175 |
rog | +1.143 |
impaired | +1.113 |
Neg logit contributions | |
Yao | -1.708 |
Debor | -1.552 |
JC | -1.531 |
intern | -1.529 |
Spencer | -1.528 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ktop | +0.572 |
acs | +0.564 |
olla | +0.558 |
rog | +0.544 |
impaired | +0.543 |
Neg logit contributions | |
Yao | -0.589 |
Debor | -0.522 |
JC | -0.521 |
•• | -0.520 |
Spencer | -0.519 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Yao | +0.277 |
Debor | +0.240 |
JC | +0.236 |
Spencer | +0.236 |
intern | +0.235 |
Neg logit contributions | |
ktop | -0.423 |
acs | -0.422 |
olla | -0.421 |
rog | -0.412 |
impaired | -0.404 |
Token | this |
Token ID | 428 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ktop | +0.116 |
acs | +0.116 |
olla | +0.115 |
rog | +0.112 |
impaired | +0.109 |
Neg logit contributions | |
Yao | -0.098 |
Debor | -0.086 |
intern | -0.086 |
JC | -0.086 |
Spencer | -0.086 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
olla | +1.932 |
acs | +1.932 |
ktop | +1.927 |
rog | +1.896 |
impaired | +1.853 |
Neg logit contributions | |
Yao | -1.722 |
Debor | -1.540 |
JC | -1.494 |
intern | -1.494 |
Spencer | -1.493 |
Token | on |
Token ID | 319 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
olla | +4.007 |
acs | +3.961 |
ktop | +3.929 |
rog | +3.912 |
impaired | +3.818 |
Neg logit contributions | |
Yao | -4.236 |
unden | -4.109 |
Debor | -3.915 |
confir | -3.851 |
Palest | -3.743 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
olla | +2.641 |
acs | +2.624 |
ktop | +2.609 |
rog | +2.571 |
impaired | +2.473 |
Neg logit contributions | |
Yao | -3.383 |
unden | -3.175 |
Debor | -3.150 |
intern | -3.046 |
confir | -3.040 |
Token | Share |
Token ID | 8734 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
olla | +3.893 |
acs | +3.883 |
ktop | +3.832 |
rog | +3.805 |
impaired | +3.715 |
Neg logit contributions | |
Yao | -3.384 |
unden | -3.283 |
Debor | -3.139 |
confir | -3.083 |
intern | -2.991 |
Token | this |
Token ID | 428 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ktop | +0.644 |
acs | +0.644 |
olla | +0.642 |
rog | +0.627 |
impaired | +0.611 |
Neg logit contributions | |
Yao | -0.585 |
Debor | -0.519 |
intern | -0.512 |
JC | -0.511 |
Spencer | -0.511 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
acs | +1.150 |
olla | +1.149 |
ktop | +1.149 |
rog | +1.125 |
impaired | +1.099 |
Neg logit contributions | |
Yao | -0.995 |
Debor | -0.884 |
intern | -0.866 |
JC | -0.864 |
Spencer | -0.862 |
Token | 10 |
Token ID | 940 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
ktop | +0.378 |
olla | +0.377 |
acs | +0.375 |
rog | +0.368 |
impaired | +0.361 |
Neg logit contributions | |
Yao | -0.411 |
Debor | -0.370 |
Spencer | -0.362 |
intern | -0.362 |
JC | -0.361 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Yao | +0.055 |
Debor | +0.049 |
JC | +0.048 |
intern | +0.048 |
Spencer | +0.048 |
Neg logit contributions | |
ktop | -0.055 |
acs | -0.055 |
olla | -0.055 |
rog | -0.054 |
impaired | -0.053 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ktop | +1.660 |
olla | +1.654 |
acs | +1.644 |
rog | +1.610 |
impaired | +1.592 |
Neg logit contributions | |
Yao | -1.336 |
Debor | -1.177 |
•• | -1.160 |
Spencer | -1.157 |
JC | -1.157 |
Token | 71 |
Token ID | 4869 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
olla | +1.252 |
ktop | +1.251 |
acs | +1.249 |
rog | +1.226 |
impaired | +1.199 |
Neg logit contributions | |
Yao | -1.323 |
Debor | -1.189 |
intern | -1.173 |
unden | -1.171 |
Spencer | -1.157 |
Token | / |
Token ID | 14 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ktop | +1.780 |
acs | +1.775 |
olla | +1.775 |
rog | +1.738 |
impaired | +1.700 |
Neg logit contributions | |
Yao | -1.932 |
Debor | -1.736 |
JC | -1.705 |
Spencer | -1.703 |
intern | -1.699 |
Token | journal |
Token ID | 24891 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
ktop | +1.366 |
olla | +1.365 |
acs | +1.359 |
rog | +1.329 |
impaired | +1.291 |
Neg logit contributions | |
Yao | -1.984 |
Debor | -1.812 |
JC | -1.781 |
intern | -1.781 |
Spencer | -1.777 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
olla | +3.741 |
acs | +3.722 |
rog | +3.668 |
ktop | +3.652 |
impaired | +3.439 |
Neg logit contributions | |
Yao | -4.586 |
unden | -4.457 |
Debor | -4.265 |
confir | -4.199 |
Spencer | -4.101 |
Token | p |
Token ID | 79 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
acs | +1.956 |
olla | +1.939 |
ktop | +1.914 |
rog | +1.909 |
impaired | +1.831 |
Neg logit contributions | |
Yao | -1.751 |
Debor | -1.577 |
unden | -1.537 |
JC | -1.521 |
Spencer | -1.516 |
Token | one |
Token ID | 505 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
olla | +2.722 |
acs | +2.718 |
ktop | +2.677 |
rog | +2.671 |
impaired | +2.588 |
Neg logit contributions | |
Yao | -1.457 |
Debor | -1.288 |
unden | -1.212 |
JC | -1.203 |
Spencer | -1.188 |
Token | . |
Token ID | 13 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
ktop | +0.190 |
acs | +0.189 |
olla | +0.188 |
rog | +0.184 |
impaired | +0.182 |
Neg logit contributions | |
Yao | -0.180 |
JC | -0.157 |
Debor | -0.157 |
intern | -0.156 |
Spencer | -0.155 |
Token | 00 |
Token ID | 405 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
ktop | +0.673 |
olla | +0.672 |
acs | +0.671 |
rog | +0.658 |
impaired | +0.644 |
Neg logit contributions | |
Yao | -0.704 |
Debor | -0.632 |
intern | -0.620 |
JC | -0.619 |
Spencer | -0.618 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
olla | +1.928 |
acs | +1.927 |
ktop | +1.922 |
rog | +1.892 |
impaired | +1.849 |
Neg logit contributions | |
Yao | -1.721 |
Debor | -1.541 |
JC | -1.494 |
intern | -1.494 |
Spencer | -1.493 |
Token | on |
Token ID | 319 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
olla | +3.873 |
acs | +3.830 |
ktop | +3.801 |
rog | +3.786 |
impaired | +3.692 |
Neg logit contributions | |
Yao | -4.089 |
unden | -3.966 |
Debor | -3.781 |
confir | -3.714 |
Palest | -3.612 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
olla | +2.585 |
acs | +2.567 |
ktop | +2.551 |
rog | +2.519 |
impaired | +2.418 |
Neg logit contributions | |
Yao | -3.334 |
unden | -3.144 |
Debor | -3.110 |
confir | -3.009 |
intern | -3.005 |
Token | Share |
Token ID | 8734 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
olla | +3.867 |
acs | +3.861 |
ktop | +3.799 |
rog | +3.784 |
impaired | +3.694 |
Neg logit contributions | |
Yao | -3.374 |
unden | -3.274 |
Debor | -3.134 |
confir | -3.078 |
intern | -2.981 |
Token | this |
Token ID | 428 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ktop | +0.449 |
acs | +0.448 |
olla | +0.447 |
rog | +0.437 |
impaired | +0.425 |
Neg logit contributions | |
Yao | -0.404 |
Debor | -0.358 |
intern | -0.353 |
JC | -0.353 |
Spencer | -0.353 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
acs | +1.286 |
olla | +1.286 |
ktop | +1.284 |
rog | +1.261 |
impaired | +1.231 |
Neg logit contributions | |
Yao | -1.128 |
Debor | -1.005 |
intern | -0.980 |
JC | -0.979 |
Spencer | -0.977 |
Token | on |
Token ID | 319 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
olla | +4.014 |
acs | +3.970 |
ktop | +3.948 |
rog | +3.921 |
impaired | +3.832 |
Neg logit contributions | |
Yao | -4.189 |
unden | -4.041 |
Debor | -3.870 |
confir | -3.786 |
Palest | -3.699 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
olla | +2.653 |
acs | +2.624 |
rog | +2.613 |
ktop | +2.601 |
impaired | +2.535 |
Neg logit contributions | |
Yao | -2.460 |
unden | -2.294 |
Debor | -2.220 |
confir | -2.193 |
intern | -2.155 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
acs | +2.706 |
olla | +2.700 |
ktop | +2.649 |
rog | +2.639 |
impaired | +2.553 |
Neg logit contributions | |
Yao | -4.502 |
Debor | -4.157 |
unden | -4.060 |
intern | -4.058 |
•• | -4.044 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
olla | +2.296 |
acs | +2.289 |
ktop | +2.259 |
rog | +2.235 |
impaired | +2.148 |
Neg logit contributions | |
Yao | -3.764 |
unden | -3.497 |
Debor | -3.488 |
intern | -3.401 |
JC | -3.385 |
Token | NY |
Token ID | 12805 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
acs | +2.064 |
olla | +2.063 |
ktop | +2.040 |
rog | +2.020 |
impaired | +1.928 |
Neg logit contributions | |
Yao | -3.219 |
Debor | -2.962 |
intern | -2.894 |
JC | -2.886 |
Spencer | -2.885 |
Token | type |
Token ID | 2099 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
acs | +0.604 |
olla | +0.604 |
ktop | +0.601 |
rog | +0.590 |
impaired | +0.575 |
Neg logit contributions | |
Yao | -0.702 |
Debor | -0.636 |
intern | -0.621 |
JC | -0.621 |
Spencer | -0.620 |
Token | - |
Token ID | 12 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
acs | +0.785 |
olla | +0.785 |
ktop | +0.784 |
rog | +0.767 |
impaired | +0.746 |
Neg logit contributions | |
Yao | -0.947 |
Debor | -0.860 |
intern | -0.841 |
JC | -0.840 |
Spencer | -0.839 |
Token | 93 |
Token ID | 6052 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ktop | +0.358 |
olla | +0.356 |
acs | +0.355 |
rog | +0.347 |
impaired | +0.339 |
Neg logit contributions | |
Yao | -0.382 |
Debor | -0.344 |
intern | -0.337 |
JC | -0.336 |
Spencer | -0.336 |
Token | Shang |
Token ID | 45797 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ktop | +0.133 |
acs | +0.133 |
olla | +0.133 |
rog | +0.130 |
impaired | +0.127 |
Neg logit contributions | |
Yao | -0.144 |
Debor | -0.130 |
intern | -0.127 |
JC | -0.127 |
Spencer | -0.127 |
Token | - |
Token ID | 12 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Yao | +0.292 |
Debor | +0.262 |
JC | +0.258 |
Spencer | +0.258 |
intern | +0.257 |
Neg logit contributions | |
ktop | -0.239 |
acs | -0.238 |
olla | -0.235 |
rog | -0.229 |
impaired | -0.225 |
Token | class |
Token ID | 4871 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
ktop | +0.864 |
acs | +0.863 |
olla | +0.863 |
rog | +0.844 |
impaired | +0.825 |
Neg logit contributions | |
Yao | -0.899 |
Debor | -0.808 |
intern | -0.789 |
JC | -0.789 |
Spencer | -0.788 |
Token | and |
Token ID | 290 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
acs | +3.776 |
olla | +3.767 |
rog | +3.682 |
ktop | +3.654 |
impaired | +3.609 |
Neg logit contributions | |
Yao | -4.367 |
Debor | -3.994 |
unden | -3.891 |
Spencer | -3.836 |
JC | -3.825 |
Token | type |
Token ID | 2099 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
olla | +1.758 |
acs | +1.754 |
ktop | +1.739 |
rog | +1.723 |
impaired | +1.687 |
Neg logit contributions | |
Yao | -1.850 |
Debor | -1.685 |
unden | -1.641 |
intern | -1.629 |
Spencer | -1.626 |
Token | - |
Token ID | 12 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
olla | +1.615 |
acs | +1.611 |
ktop | +1.589 |
rog | +1.580 |
impaired | +1.533 |
Neg logit contributions | |
Yao | -2.132 |
Debor | -1.956 |
unden | -1.903 |
intern | -1.896 |
Spencer | -1.891 |
Token | 95 |
Token ID | 3865 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ktop | +0.272 |
acs | +0.270 |
olla | +0.270 |
rog | +0.264 |
impaired | +0.259 |
Neg logit contributions | |
Yao | -0.268 |
Debor | -0.240 |
JC | -0.235 |
Spencer | -0.235 |
intern | -0.234 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
olla | +0.485 |
acs | +0.485 |
ktop | +0.484 |
rog | +0.477 |
impaired | +0.466 |
Neg logit contributions | |
Yao | -0.363 |
Debor | -0.321 |
intern | -0.312 |
JC | -0.311 |
Spencer | -0.311 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
olla | +1.932 |
acs | +1.932 |
ktop | +1.927 |
rog | +1.896 |
impaired | +1.853 |
Neg logit contributions | |
Yao | -1.722 |
Debor | -1.540 |
JC | -1.494 |
intern | -1.494 |
Spencer | -1.493 |
Token | on |
Token ID | 319 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
olla | +4.007 |
acs | +3.961 |
ktop | +3.929 |
rog | +3.912 |
impaired | +3.818 |
Neg logit contributions | |
Yao | -4.236 |
unden | -4.109 |
Debor | -3.915 |
confir | -3.851 |
Palest | -3.743 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
olla | +2.641 |
acs | +2.624 |
ktop | +2.609 |
rog | +2.571 |
impaired | +2.473 |
Neg logit contributions | |
Yao | -3.383 |
unden | -3.175 |
Debor | -3.150 |
intern | -3.046 |
confir | -3.040 |
Token | Share |
Token ID | 8734 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
olla | +3.893 |
acs | +3.883 |
ktop | +3.832 |
rog | +3.805 |
impaired | +3.715 |
Neg logit contributions | |
Yao | -3.384 |
unden | -3.283 |
Debor | -3.139 |
confir | -3.083 |
intern | -2.991 |
Token | this |
Token ID | 428 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ktop | +0.644 |
acs | +0.644 |
olla | +0.642 |
rog | +0.627 |
impaired | +0.611 |
Neg logit contributions | |
Yao | -0.585 |
Debor | -0.519 |
intern | -0.512 |
JC | -0.511 |
Spencer | -0.511 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
acs | +1.150 |
olla | +1.149 |
ktop | +1.149 |
rog | +1.125 |
impaired | +1.099 |
Neg logit contributions | |
Yao | -0.995 |
Debor | -0.884 |
intern | -0.866 |
JC | -0.864 |
Spencer | -0.862 |
Token | on |
Token ID | 319 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
olla | +4.009 |
acs | +3.970 |
ktop | +3.949 |
rog | +3.918 |
impaired | +3.830 |
Neg logit contributions | |
Yao | -4.160 |
unden | -3.991 |
Debor | -3.832 |
confir | -3.741 |
Palest | -3.660 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
olla | +2.626 |
acs | +2.599 |
rog | +2.585 |
ktop | +2.575 |
impaired | +2.509 |
Neg logit contributions | |
Yao | -2.423 |
unden | -2.252 |
Debor | -2.187 |
confir | -2.149 |
intern | -2.121 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
acs | +2.698 |
olla | +2.690 |
ktop | +2.639 |
rog | +2.632 |
impaired | +2.541 |
Neg logit contributions | |
Yao | -4.512 |
Debor | -4.165 |
unden | -4.072 |
intern | -4.069 |
•• | -4.050 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
olla | +2.443 |
acs | +2.434 |
ktop | +2.395 |
rog | +2.378 |
impaired | +2.281 |
Neg logit contributions | |
Yao | -4.079 |
unden | -3.823 |
Debor | -3.788 |
intern | -3.690 |
confir | -3.679 |
Token | NY |
Token ID | 12805 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
acs | +2.286 |
olla | +2.283 |
ktop | +2.248 |
rog | +2.239 |
impaired | +2.126 |
Neg logit contributions | |
Yao | -3.636 |
Debor | -3.352 |
intern | -3.270 |
JC | -3.260 |
Spencer | -3.260 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ktop | +1.004 |
acs | +0.998 |
olla | +0.997 |
rog | +0.969 |
impaired | +0.942 |
Neg logit contributions | |
Yao | -1.438 |
Debor | -1.308 |
JC | -1.288 |
intern | -1.287 |
Spencer | -1.286 |
Token |
|
Token ID | 198 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ktop | +1.052 |
acs | +1.044 |
olla | +1.041 |
rog | +1.013 |
impaired | +0.989 |
Neg logit contributions | |
Yao | -1.490 |
Debor | -1.350 |
JC | -1.336 |
intern | -1.333 |
Spencer | -1.333 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ktop | +0.401 |
acs | +0.395 |
olla | +0.390 |
rog | +0.381 |
impaired | +0.380 |
Neg logit contributions | |
Yao | -0.406 |
•• | -0.359 |
Debor | -0.359 |
JC | -0.358 |
Spencer | -0.357 |
Token | Share |
Token ID | 8734 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
Yao | +0.328 |
Debor | +0.283 |
Spencer | +0.280 |
JC | +0.280 |
intern | +0.278 |
Neg logit contributions | |
ktop | -0.510 |
acs | -0.508 |
olla | -0.508 |
rog | -0.497 |
impaired | -0.486 |
Token | this |
Token ID | 428 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ktop | +0.077 |
acs | +0.077 |
olla | +0.077 |
rog | +0.075 |
impaired | +0.072 |
Neg logit contributions | |
Yao | -0.065 |
Debor | -0.057 |
intern | -0.057 |
JC | -0.057 |
Spencer | -0.057 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
olla | +1.928 |
acs | +1.927 |
ktop | +1.922 |
rog | +1.892 |
impaired | +1.849 |
Neg logit contributions | |
Yao | -1.721 |
Debor | -1.541 |
JC | -1.494 |
intern | -1.494 |
Spencer | -1.493 |
Token | on |
Token ID | 319 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
olla | +3.873 |
acs | +3.830 |
ktop | +3.801 |
rog | +3.786 |
impaired | +3.692 |
Neg logit contributions | |
Yao | -4.089 |
unden | -3.966 |
Debor | -3.781 |
confir | -3.714 |
Palest | -3.612 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
olla | +2.585 |
acs | +2.567 |
ktop | +2.551 |
rog | +2.519 |
impaired | +2.418 |
Neg logit contributions | |
Yao | -3.334 |
unden | -3.144 |
Debor | -3.110 |
confir | -3.009 |
intern | -3.005 |
Token | Share |
Token ID | 8734 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
olla | +3.867 |
acs | +3.861 |
ktop | +3.799 |
rog | +3.784 |
impaired | +3.694 |
Neg logit contributions | |
Yao | -3.374 |
unden | -3.274 |
Debor | -3.134 |
confir | -3.078 |
intern | -2.981 |
Token | this |
Token ID | 428 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ktop | +0.449 |
acs | +0.448 |
olla | +0.447 |
rog | +0.437 |
impaired | +0.425 |
Neg logit contributions | |
Yao | -0.404 |
Debor | -0.358 |
intern | -0.353 |
JC | -0.353 |
Spencer | -0.353 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
acs | +1.286 |
olla | +1.286 |
ktop | +1.284 |
rog | +1.261 |
impaired | +1.231 |
Neg logit contributions | |
Yao | -1.128 |
Debor | -1.005 |
intern | -0.980 |
JC | -0.979 |
Spencer | -0.977 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
olla | +2.690 |
acs | +2.667 |
ktop | +2.646 |
rog | +2.625 |
impaired | +2.510 |
Neg logit contributions | |
Yao | -3.632 |
unden | -3.473 |
Debor | -3.405 |
confir | -3.315 |
intern | -3.273 |
Token | Share |
Token ID | 8734 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
acs | +3.938 |
olla | +3.935 |
rog | +3.858 |
ktop | +3.856 |
impaired | +3.774 |
Neg logit contributions | |
Yao | -3.580 |
unden | -3.483 |
Debor | -3.342 |
confir | -3.254 |
intern | -3.160 |
Token | this |
Token ID | 428 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ktop | +0.625 |
acs | +0.624 |
olla | +0.622 |
rog | +0.608 |
impaired | +0.593 |
Neg logit contributions | |
Yao | -0.570 |
Debor | -0.506 |
intern | -0.499 |
JC | -0.498 |
Spencer | -0.498 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
olla | +1.305 |
acs | +1.305 |
ktop | +1.303 |
rog | +1.280 |
impaired | +1.250 |
Neg logit contributions | |
Yao | -1.151 |
Debor | -1.027 |
intern | -1.000 |
JC | -0.999 |
Spencer | -0.998 |
Token | on |
Token ID | 319 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
olla | +4.156 |
acs | +4.110 |
ktop | +4.085 |
rog | +4.063 |
impaired | +3.966 |
Neg logit contributions | |
Yao | -4.384 |
unden | -4.268 |
Debor | -4.064 |
confir | -3.998 |
Palest | -3.899 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
olla | +2.885 |
acs | +2.846 |
rog | +2.838 |
ktop | +2.820 |
impaired | +2.748 |
Neg logit contributions | |
Yao | -2.730 |
unden | -2.570 |
Debor | -2.472 |
confir | -2.460 |
intern | -2.399 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
olla | +2.955 |
acs | +2.951 |
ktop | +2.895 |
rog | +2.884 |
impaired | +2.798 |
Neg logit contributions | |
Yao | -4.707 |
Debor | -4.340 |
unden | -4.245 |
intern | -4.237 |
•• | -4.226 |
Token |
|
Token ID | 198 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
olla | +2.146 |
acs | +2.140 |
ktop | +2.119 |
rog | +2.089 |
impaired | +2.012 |
Neg logit contributions | |
Yao | -3.453 |
Debor | -3.191 |
unden | -3.176 |
intern | -3.116 |
JC | -3.104 |
Token | NY |
Token ID | 12805 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
olla | +1.847 |
acs | +1.846 |
ktop | +1.832 |
rog | +1.804 |
impaired | +1.734 |
Neg logit contributions | |
Yao | -2.787 |
Debor | -2.557 |
intern | -2.502 |
JC | -2.497 |
Spencer | -2.495 |
Token | T |
Token ID | 51 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ktop | +0.554 |
acs | +0.549 |
olla | +0.545 |
rog | +0.536 |
impaired | +0.527 |
Neg logit contributions | |
Yao | -0.440 |
JC | -0.381 |
Debor | -0.380 |
Spencer | -0.379 |
intern | -0.377 |
Token | Pick |
Token ID | 12346 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
acs | +1.555 |
ktop | +1.554 |
olla | +1.549 |
rog | +1.503 |
impaired | +1.442 |
Neg logit contributions | |
Yao | -2.880 |
Debor | -2.645 |
JC | -2.614 |
Spencer | -2.612 |
intern | -2.610 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ktop | +0.933 |
acs | +0.925 |
olla | +0.917 |
rog | +0.895 |
impaired | +0.885 |
Neg logit contributions | |
Yao | -1.004 |
Debor | -0.898 |
JC | -0.889 |
Spencer | -0.887 |
•• | -0.886 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Yao | +0.505 |
Debor | +0.435 |
Spencer | +0.431 |
JC | +0.431 |
intern | +0.427 |
Neg logit contributions | |
ktop | -0.793 |
acs | -0.791 |
olla | -0.790 |
rog | -0.772 |
impaired | -0.756 |
Token | this |
Token ID | 428 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ktop | +0.131 |
olla | +0.130 |
acs | +0.130 |
rog | +0.126 |
lime | +0.122 |
Neg logit contributions | |
Yao | -0.110 |
intern | -0.097 |
Debor | -0.097 |
JC | -0.096 |
Spencer | -0.096 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
olla | +2.033 |
acs | +2.032 |
ktop | +2.023 |
rog | +1.997 |
impaired | +1.952 |
Neg logit contributions | |
Yao | -1.848 |
Debor | -1.661 |
unden | -1.614 |
JC | -1.603 |
Spencer | -1.603 |
Token | on |
Token ID | 319 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
olla | +4.064 |
acs | +4.014 |
ktop | +3.982 |
rog | +3.977 |
impaired | +3.876 |
Neg logit contributions | |
Yao | -4.420 |
unden | -4.356 |
Debor | -4.108 |
confir | -4.069 |
Palest | -3.948 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
olla | +2.690 |
acs | +2.667 |
ktop | +2.646 |
rog | +2.625 |
impaired | +2.510 |
Neg logit contributions | |
Yao | -3.632 |
unden | -3.473 |
Debor | -3.405 |
confir | -3.315 |
intern | -3.273 |
Token | Share |
Token ID | 8734 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
acs | +3.938 |
olla | +3.935 |
rog | +3.858 |
ktop | +3.856 |
impaired | +3.774 |
Neg logit contributions | |
Yao | -3.580 |
unden | -3.483 |
Debor | -3.342 |
confir | -3.254 |
intern | -3.160 |
Token | this |
Token ID | 428 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ktop | +0.625 |
acs | +0.624 |
olla | +0.622 |
rog | +0.608 |
impaired | +0.593 |
Neg logit contributions | |
Yao | -0.570 |
Debor | -0.506 |
intern | -0.499 |
JC | -0.498 |
Spencer | -0.498 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
olla | +1.305 |
acs | +1.305 |
ktop | +1.303 |
rog | +1.280 |
impaired | +1.250 |
Neg logit contributions | |
Yao | -1.151 |
Debor | -1.027 |
intern | -1.000 |
JC | -0.999 |
Spencer | -0.998 |
Token | on |
Token ID | 319 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
olla | +4.156 |
acs | +4.110 |
ktop | +4.085 |
rog | +4.063 |
impaired | +3.966 |
Neg logit contributions | |
Yao | -4.384 |
unden | -4.268 |
Debor | -4.064 |
confir | -3.998 |
Palest | -3.899 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
olla | +2.885 |
acs | +2.846 |
rog | +2.838 |
ktop | +2.820 |
impaired | +2.748 |
Neg logit contributions | |
Yao | -2.730 |
unden | -2.570 |
Debor | -2.472 |
confir | -2.460 |
intern | -2.399 |
Token | in |
Token ID | 287 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
olla | +0.441 |
ktop | +0.439 |
acs | +0.439 |
rog | +0.430 |
impaired | +0.418 |
Neg logit contributions | |
Yao | -0.436 |
Debor | -0.392 |
intern | -0.383 |
JC | -0.383 |
Spencer | -0.382 |
Token | your |
Token ID | 534 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Yao | +0.360 |
Debor | +0.324 |
intern | +0.320 |
JC | +0.320 |
Spencer | +0.319 |
Neg logit contributions | |
olla | -0.330 |
ktop | -0.329 |
acs | -0.329 |
rog | -0.322 |
impaired | -0.310 |
Token | performance |
Token ID | 2854 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
acs | +0.776 |
olla | +0.776 |
ktop | +0.774 |
rog | +0.759 |
impaired | +0.741 |
Neg logit contributions | |
Yao | -0.869 |
Debor | -0.787 |
intern | -0.767 |
JC | -0.767 |
Spencer | -0.766 |
Token | as |
Token ID | 355 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
acs | +1.059 |
olla | +1.058 |
ktop | +1.056 |
rog | +1.035 |
impaired | +1.010 |
Neg logit contributions | |
Yao | -1.254 |
Debor | -1.138 |
intern | -1.111 |
JC | -1.110 |
Spencer | -1.110 |
Token | a |
Token ID | 257 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
olla | +0.412 |
ktop | +0.410 |
acs | +0.409 |
rog | +0.399 |
impaired | +0.385 |
Neg logit contributions | |
Yao | -0.541 |
Debor | -0.492 |
JC | -0.484 |
intern | -0.484 |
Spencer | -0.483 |
Token | result |
Token ID | 1255 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
acs | +0.870 |
olla | +0.869 |
ktop | +0.868 |
rog | +0.853 |
impaired | +0.831 |
Neg logit contributions | |
Yao | -1.030 |
Debor | -0.937 |
intern | -0.913 |
JC | -0.912 |
Spencer | -0.911 |
Token | of |
Token ID | 286 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
acs | +3.101 |
olla | +3.073 |
ktop | +3.058 |
rog | +3.019 |
impaired | +2.997 |
Neg logit contributions | |
Yao | -4.569 |
Debor | -4.209 |
unden | -4.128 |
JC | -4.086 |
Spencer | -4.085 |
Token | truly |
Token ID | 4988 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
olla | +0.499 |
acs | +0.498 |
ktop | +0.498 |
rog | +0.486 |
impaired | +0.470 |
Neg logit contributions | |
Yao | -0.577 |
Debor | -0.522 |
intern | -0.512 |
JC | -0.511 |
Spencer | -0.510 |
Token | believing |
Token ID | 14773 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Yao | +0.424 |
Debor | +0.381 |
intern | +0.380 |
JC | +0.378 |
Spencer | +0.375 |
Neg logit contributions | |
olla | -0.377 |
ktop | -0.373 |
acs | -0.372 |
rog | -0.363 |
\/\/ | -0.347 |
Token | in |
Token ID | 287 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
Yao | +0.329 |
Debor | +0.295 |
JC | +0.290 |
intern | +0.289 |
Spencer | +0.289 |
Neg logit contributions | |
olla | -0.321 |
ktop | -0.321 |
acs | -0.319 |
rog | -0.312 |
impaired | -0.302 |
Token | your |
Token ID | 534 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
olla | +0.432 |
acs | +0.432 |
ktop | +0.431 |
rog | +0.422 |
impaired | +0.411 |
Neg logit contributions | |
Yao | -0.501 |
Debor | -0.454 |
intern | -0.444 |
JC | -0.444 |
Spencer | -0.443 |
Token | atives |
Token ID | 2929 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Yao | +0.770 |
Debor | +0.681 |
intern | +0.672 |
Spencer | +0.669 |
JC | +0.667 |
Neg logit contributions | |
ktop | -0.882 |
olla | -0.873 |
acs | -0.861 |
rog | -0.846 |
impaired | -0.841 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
acs | +0.427 |
olla | +0.427 |
ktop | +0.426 |
rog | +0.419 |
impaired | +0.408 |
Neg logit contributions | |
Yao | -0.398 |
Debor | -0.357 |
intern | -0.348 |
JC | -0.347 |
Spencer | -0.346 |
Token | � |
Token ID | 447 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Yao | +0.195 |
Debor | +0.174 |
JC | +0.170 |
Spencer | +0.170 |
intern | +0.169 |
Neg logit contributions | |
ktop | -0.222 |
olla | -0.222 |
acs | -0.222 |
rog | -0.218 |
impaired | -0.213 |
Token | � |
Token ID | 251 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
acs | +0.266 |
olla | +0.265 |
ktop | +0.264 |
rog | +0.260 |
impaired | +0.253 |
Neg logit contributions | |
Yao | -0.300 |
Debor | -0.272 |
intern | -0.266 |
JC | -0.265 |
Spencer | -0.265 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
acs | +0.168 |
olla | +0.168 |
ktop | +0.167 |
rog | +0.165 |
impaired | +0.161 |
Neg logit contributions | |
Yao | -0.142 |
Debor | -0.126 |
intern | -0.123 |
JC | -0.123 |
Spencer | -0.122 |
Token | FILE |
Token ID | 25664 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
ktop | +0.307 |
olla | +0.307 |
acs | +0.307 |
rog | +0.300 |
impaired | +0.294 |
Neg logit contributions | |
Yao | -0.318 |
Debor | -0.285 |
JC | -0.279 |
Spencer | -0.279 |
intern | -0.278 |
Token | : |
Token ID | 25 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
olla | +2.750 |
rog | +2.696 |
acs | +2.676 |
ktop | +2.673 |
impaired | +2.638 |
Neg logit contributions | |
Yao | -4.719 |
Debor | -4.378 |
unden | -4.293 |
JC | -4.241 |
intern | -4.230 |
Token | Delhi |
Token ID | 12517 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Yao | +0.628 |
Debor | +0.560 |
Spencer | +0.548 |
JC | +0.547 |
intern | +0.542 |
Neg logit contributions | |
ktop | -0.706 |
olla | -0.703 |
acs | -0.703 |
rog | -0.688 |
impaired | -0.673 |
Token | Law |
Token ID | 3854 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
acs | +0.889 |
olla | +0.889 |
ktop | +0.887 |
rog | +0.866 |
impaired | +0.840 |
Neg logit contributions | |
Yao | -1.294 |
Debor | -1.184 |
intern | -1.160 |
JC | -1.159 |
Spencer | -1.158 |
Token | Minister |
Token ID | 4139 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Yao | +0.009 |
Debor | +0.008 |
JC | +0.008 |
intern | +0.008 |
Spencer | +0.008 |
Neg logit contributions | |
ktop | -0.007 |
acs | -0.007 |
olla | -0.007 |
rog | -0.007 |
impaired | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Yao | +0.159 |
Debor | +0.143 |
JC | +0.139 |
Spencer | +0.139 |
intern | +0.139 |
Neg logit contributions | |
ktop | -0.159 |
olla | -0.159 |
acs | -0.159 |
rog | -0.155 |
impaired | -0.152 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ktop | +0.572 |
acs | +0.564 |
olla | +0.558 |
rog | +0.544 |
impaired | +0.543 |
Neg logit contributions | |
Yao | -0.589 |
Debor | -0.522 |
JC | -0.521 |
•• | -0.520 |
Spencer | -0.519 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Yao | +0.277 |
Debor | +0.240 |
JC | +0.236 |
Spencer | +0.236 |
intern | +0.235 |
Neg logit contributions | |
ktop | -0.423 |
acs | -0.422 |
olla | -0.421 |
rog | -0.412 |
impaired | -0.404 |
Token | this |
Token ID | 428 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ktop | +0.116 |
acs | +0.116 |
olla | +0.115 |
rog | +0.112 |
impaired | +0.109 |
Neg logit contributions | |
Yao | -0.098 |
Debor | -0.086 |
intern | -0.086 |
JC | -0.086 |
Spencer | -0.086 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
olla | +1.932 |
acs | +1.932 |
ktop | +1.927 |
rog | +1.896 |
impaired | +1.853 |
Neg logit contributions | |
Yao | -1.722 |
Debor | -1.540 |
JC | -1.494 |
intern | -1.494 |
Spencer | -1.493 |
Token | on |
Token ID | 319 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
olla | +4.007 |
acs | +3.961 |
ktop | +3.929 |
rog | +3.912 |
impaired | +3.818 |
Neg logit contributions | |
Yao | -4.236 |
unden | -4.109 |
Debor | -3.915 |
confir | -3.851 |
Palest | -3.743 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
olla | +2.641 |
acs | +2.624 |
ktop | +2.609 |
rog | +2.571 |
impaired | +2.473 |
Neg logit contributions | |
Yao | -3.383 |
unden | -3.175 |
Debor | -3.150 |
intern | -3.046 |
confir | -3.040 |
Token | Share |
Token ID | 8734 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
olla | +3.893 |
acs | +3.883 |
ktop | +3.832 |
rog | +3.805 |
impaired | +3.715 |
Neg logit contributions | |
Yao | -3.384 |
unden | -3.283 |
Debor | -3.139 |
confir | -3.083 |
intern | -2.991 |
Token | this |
Token ID | 428 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ktop | +0.644 |
acs | +0.644 |
olla | +0.642 |
rog | +0.627 |
impaired | +0.611 |
Neg logit contributions | |
Yao | -0.585 |
Debor | -0.519 |
intern | -0.512 |
JC | -0.511 |
Spencer | -0.511 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
acs | +1.150 |
olla | +1.149 |
ktop | +1.149 |
rog | +1.125 |
impaired | +1.099 |
Neg logit contributions | |
Yao | -0.995 |
Debor | -0.884 |
intern | -0.866 |
JC | -0.864 |
Spencer | -0.862 |
Token | on |
Token ID | 319 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
olla | +4.009 |
acs | +3.970 |
ktop | +3.949 |
rog | +3.918 |
impaired | +3.830 |
Neg logit contributions | |
Yao | -4.160 |
unden | -3.991 |
Debor | -3.832 |
confir | -3.741 |
Palest | -3.660 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
olla | +2.626 |
acs | +2.599 |
rog | +2.585 |
ktop | +2.575 |
impaired | +2.509 |
Neg logit contributions | |
Yao | -2.423 |
unden | -2.252 |
Debor | -2.187 |
confir | -2.149 |
intern | -2.121 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ktop | +0.401 |
acs | +0.395 |
olla | +0.390 |
rog | +0.381 |
impaired | +0.380 |
Neg logit contributions | |
Yao | -0.406 |
•• | -0.359 |
Debor | -0.359 |
JC | -0.358 |
Spencer | -0.357 |
Token | Share |
Token ID | 8734 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
Yao | +0.328 |
Debor | +0.283 |
Spencer | +0.280 |
JC | +0.280 |
intern | +0.278 |
Neg logit contributions | |
ktop | -0.510 |
acs | -0.508 |
olla | -0.508 |
rog | -0.497 |
impaired | -0.486 |
Token | this |
Token ID | 428 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ktop | +0.077 |
acs | +0.077 |
olla | +0.077 |
rog | +0.075 |
impaired | +0.072 |
Neg logit contributions | |
Yao | -0.065 |
Debor | -0.057 |
intern | -0.057 |
JC | -0.057 |
Spencer | -0.057 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
olla | +1.928 |
acs | +1.927 |
ktop | +1.922 |
rog | +1.892 |
impaired | +1.849 |
Neg logit contributions | |
Yao | -1.721 |
Debor | -1.541 |
JC | -1.494 |
intern | -1.494 |
Spencer | -1.493 |
Token | on |
Token ID | 319 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
olla | +3.873 |
acs | +3.830 |
ktop | +3.801 |
rog | +3.786 |
impaired | +3.692 |
Neg logit contributions | |
Yao | -4.089 |
unden | -3.966 |
Debor | -3.781 |
confir | -3.714 |
Palest | -3.612 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
olla | +2.585 |
acs | +2.567 |
ktop | +2.551 |
rog | +2.519 |
impaired | +2.418 |
Neg logit contributions | |
Yao | -3.334 |
unden | -3.144 |
Debor | -3.110 |
confir | -3.009 |
intern | -3.005 |
Token | Share |
Token ID | 8734 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
olla | +3.867 |
acs | +3.861 |
ktop | +3.799 |
rog | +3.784 |
impaired | +3.694 |
Neg logit contributions | |
Yao | -3.374 |
unden | -3.274 |
Debor | -3.134 |
confir | -3.078 |
intern | -2.981 |
Token | this |
Token ID | 428 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ktop | +0.449 |
acs | +0.448 |
olla | +0.447 |
rog | +0.437 |
impaired | +0.425 |
Neg logit contributions | |
Yao | -0.404 |
Debor | -0.358 |
intern | -0.353 |
JC | -0.353 |
Spencer | -0.353 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
acs | +1.286 |
olla | +1.286 |
ktop | +1.284 |
rog | +1.261 |
impaired | +1.231 |
Neg logit contributions | |
Yao | -1.128 |
Debor | -1.005 |
intern | -0.980 |
JC | -0.979 |
Spencer | -0.977 |
Token | on |
Token ID | 319 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
olla | +4.014 |
acs | +3.970 |
ktop | +3.948 |
rog | +3.921 |
impaired | +3.832 |
Neg logit contributions | |
Yao | -4.189 |
unden | -4.041 |
Debor | -3.870 |
confir | -3.786 |
Palest | -3.699 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
olla | +2.653 |
acs | +2.624 |
rog | +2.613 |
ktop | +2.601 |
impaired | +2.535 |
Neg logit contributions | |
Yao | -2.460 |
unden | -2.294 |
Debor | -2.220 |
confir | -2.193 |
intern | -2.155 |
Token | Enter |
Token ID | 6062 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
ktop | +2.039 |
acs | +2.003 |
olla | +1.973 |
rog | +1.934 |
neur | +1.879 |
Neg logit contributions | |
Yao | -3.307 |
unden | -3.233 |
Debor | -3.149 |
intern | -3.072 |
•• | -3.047 |
Token | Your |
Token ID | 3406 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Yao | +3.252 |
Spencer | +2.953 |
JC | +2.932 |
Debor | +2.907 |
intern | +2.881 |
Neg logit contributions | |
ktop | -2.933 |
olla | -2.844 |
acs | -2.819 |
rog | -2.726 |
impaired | -2.646 |
Token | Name |
Token ID | 6530 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Yao | +0.321 |
Debor | +0.298 |
intern | +0.293 |
unden | +0.291 |
JC | +0.291 |
Neg logit contributions | |
olla | -0.167 |
acs | -0.167 |
ktop | -0.164 |
rog | -0.162 |
impaired | -0.156 |
Token | Add |
Token ID | 3060 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
Yao | +0.755 |
Debor | +0.682 |
unden | +0.670 |
intern | +0.669 |
JC | +0.662 |
Neg logit contributions | |
olla | -0.665 |
acs | -0.665 |
ktop | -0.661 |
rog | -0.651 |
impaired | -0.631 |
Token | a |
Token ID | 257 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
Yao | +0.582 |
JC | +0.527 |
Spencer | +0.526 |
Debor | +0.525 |
intern | +0.523 |
Neg logit contributions | |
acs | -0.429 |
ktop | -0.429 |
olla | -0.418 |
rog | -0.406 |
impaired | -0.392 |
Token | comment |
Token ID | 2912 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
Yao | +0.483 |
Debor | +0.429 |
intern | +0.420 |
JC | +0.419 |
Spencer | +0.419 |
Neg logit contributions | |
ktop | -0.568 |
acs | -0.567 |
olla | -0.564 |
rog | -0.554 |
impaired | -0.541 |
Token | here |
Token ID | 994 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
olla | +3.037 |
ktop | +3.000 |
rog | +2.991 |
acs | +2.934 |
impaired | +2.885 |
Neg logit contributions | |
Yao | -4.281 |
unden | -3.964 |
Debor | -3.903 |
intern | -3.795 |
•• | -3.790 |
Token | Ver |
Token ID | 4643 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
olla | +1.530 |
acs | +1.512 |
ktop | +1.500 |
rog | +1.471 |
impaired | +1.446 |
Neg logit contributions | |
Yao | -1.281 |
Debor | -1.163 |
unden | -1.121 |
intern | -1.115 |
•• | -1.099 |
Token | ification |
Token ID | 2649 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Yao | +0.209 |
Debor | +0.189 |
JC | +0.186 |
intern | +0.186 |
Spencer | +0.185 |
Neg logit contributions | |
ktop | -0.182 |
olla | -0.181 |
acs | -0.181 |
rog | -0.176 |
impaired | -0.173 |
Token | Send |
Token ID | 16290 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
olla | +0.748 |
acs | +0.738 |
rog | +0.735 |
ktop | +0.733 |
impaired | +0.719 |
Neg logit contributions | |
Yao | -0.514 |
Debor | -0.457 |
unden | -0.447 |
intern | -0.439 |
•• | -0.432 |
Token | Email |
Token ID | 9570 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
Yao | +0.458 |
Debor | +0.385 |
JC | +0.377 |
Spencer | +0.371 |
intern | +0.369 |
Neg logit contributions | |
ktop | -1.008 |
olla | -1.001 |
acs | -0.997 |
rog | -0.974 |
impaired | -0.958 |
Token | are |
Token ID | 389 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Yao | +1.399 |
Debor | +1.269 |
intern | +1.257 |
Spencer | +1.246 |
JC | +1.239 |
Neg logit contributions | |
olla | -1.168 |
ktop | -1.167 |
acs | -1.161 |
rog | -1.141 |
impaired | -1.085 |
Token | also |
Token ID | 635 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Yao | +1.275 |
Debor | +1.157 |
intern | +1.151 |
Spencer | +1.139 |
JC | +1.134 |
Neg logit contributions | |
ktop | -1.058 |
olla | -1.053 |
acs | -1.042 |
rog | -1.024 |
\/\/ | -0.974 |
Token | alike |
Token ID | 12936 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Yao | +0.615 |
Debor | +0.558 |
intern | +0.551 |
Spencer | +0.548 |
JC | +0.545 |
Neg logit contributions | |
ktop | -0.524 |
olla | -0.521 |
acs | -0.517 |
rog | -0.509 |
impaired | -0.486 |
Token | in |
Token ID | 287 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Yao | +1.843 |
Debor | +1.658 |
intern | +1.626 |
Spencer | +1.618 |
unden | +1.605 |
Neg logit contributions | |
ktop | -2.015 |
olla | -2.012 |
acs | -1.989 |
rog | -1.955 |
\/\/ | -1.883 |
Token | the |
Token ID | 262 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Yao | +2.097 |
Debor | +1.902 |
intern | +1.888 |
Spencer | +1.879 |
JC | +1.855 |
Neg logit contributions | |
acs | -1.640 |
ktop | -1.632 |
olla | -1.632 |
rog | -1.600 |
impaired | -1.521 |
Token | fact |
Token ID | 1109 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
Yao | +1.526 |
Debor | +1.387 |
intern | +1.374 |
Spencer | +1.359 |
unden | +1.354 |
Neg logit contributions | |
acs | -1.309 |
olla | -1.296 |
ktop | -1.293 |
rog | -1.262 |
impaired | -1.201 |
Token | that |
Token ID | 326 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
Yao | +2.409 |
Debor | +2.160 |
intern | +2.134 |
Spencer | +2.132 |
JC | +2.110 |
Neg logit contributions | |
ktop | -2.286 |
acs | -2.277 |
olla | -2.272 |
rog | -2.223 |
impaired | -2.161 |
Token | they |
Token ID | 484 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Yao | +0.460 |
Debor | +0.418 |
intern | +0.412 |
Spencer | +0.410 |
JC | +0.407 |
Neg logit contributions | |
ktop | -0.381 |
acs | -0.379 |
olla | -0.378 |
rog | -0.367 |
impaired | -0.355 |
Token | have |
Token ID | 423 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Yao | +1.058 |
Debor | +0.955 |
intern | +0.946 |
Spencer | +0.934 |
JC | +0.933 |
Neg logit contributions | |
olla | -0.964 |
acs | -0.962 |
ktop | -0.962 |
rog | -0.941 |
impaired | -0.905 |
Token | at |
Token ID | 379 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Yao | +0.586 |
Debor | +0.535 |
intern | +0.529 |
Spencer | +0.523 |
JC | +0.521 |
Neg logit contributions | |
acs | -0.453 |
olla | -0.452 |
ktop | -0.450 |
rog | -0.439 |
impaired | -0.419 |
Token | some |
Token ID | 617 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Yao | +0.636 |
Debor | +0.579 |
intern | +0.573 |
Spencer | +0.570 |
JC | +0.566 |
Neg logit contributions | |
acs | -0.473 |
ktop | -0.469 |
olla | -0.465 |
rog | -0.454 |
impaired | -0.441 |
Token | their |
Token ID | 511 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ktop | +0.127 |
olla | +0.127 |
acs | +0.126 |
rog | +0.123 |
impaired | +0.119 |
Neg logit contributions | |
Yao | -0.172 |
Debor | -0.156 |
intern | -0.154 |
JC | -0.154 |
Spencer | -0.154 |
Token | life |
Token ID | 1204 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Yao | +0.033 |
Debor | +0.030 |
intern | +0.030 |
JC | +0.029 |
Spencer | +0.029 |
Neg logit contributions | |
acs | -0.023 |
ktop | -0.023 |
olla | -0.023 |
rog | -0.023 |
impaired | -0.022 |
Token | from |
Token ID | 422 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
acs | +0.012 |
ktop | +0.012 |
olla | +0.012 |
rog | +0.012 |
impaired | +0.012 |
Neg logit contributions | |
Yao | -0.011 |
Debor | -0.010 |
intern | -0.010 |
JC | -0.010 |
Spencer | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
acs | +0.456 |
olla | +0.456 |
ktop | +0.455 |
rog | +0.444 |
impaired | +0.429 |
Neg logit contributions | |
Yao | -0.597 |
Debor | -0.542 |
intern | -0.534 |
JC | -0.532 |
Spencer | -0.532 |
Token | polar |
Token ID | 13559 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
olla | +0.229 |
acs | +0.229 |
ktop | +0.229 |
rog | +0.224 |
impaired | +0.217 |
Neg logit contributions | |
Yao | -0.274 |
Debor | -0.248 |
intern | -0.244 |
JC | -0.243 |
Spencer | -0.243 |
Token | opposite |
Token ID | 6697 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
acs | +0.757 |
olla | +0.755 |
ktop | +0.753 |
rog | +0.742 |
impaired | +0.723 |
Neg logit contributions | |
Yao | -0.873 |
Debor | -0.792 |
JC | -0.771 |
Spencer | -0.768 |
intern | -0.767 |
Token | vantage |
Token ID | 47929 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
Yao | +2.220 |
intern | +1.990 |
Debor | +1.990 |
Spencer | +1.984 |
JC | +1.972 |
Neg logit contributions | |
ktop | -2.097 |
olla | -2.082 |
acs | -2.074 |
rog | -2.048 |
impaired | -1.941 |
Token | point |
Token ID | 966 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Yao | +0.530 |
Debor | +0.466 |
intern | +0.461 |
Spencer | +0.458 |
JC | +0.457 |
Neg logit contributions | |
acs | -0.653 |
olla | -0.651 |
ktop | -0.651 |
rog | -0.635 |
impaired | -0.618 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
acs | +0.222 |
olla | +0.222 |
ktop | +0.222 |
rog | +0.217 |
impaired | +0.212 |
Neg logit contributions | |
Yao | -0.224 |
Debor | -0.202 |
intern | -0.197 |
JC | -0.197 |
Spencer | -0.197 |
Token | For |
Token ID | 1114 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ktop | +0.394 |
acs | +0.394 |
olla | +0.393 |
rog | +0.385 |
impaired | +0.376 |
Neg logit contributions | |
Yao | -0.393 |
Debor | -0.353 |
Spencer | -0.344 |
JC | -0.344 |
intern | -0.343 |
Token | Bob |
Token ID | 5811 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Yao | +0.182 |
Debor | +0.165 |
Spencer | +0.162 |
intern | +0.162 |
JC | +0.162 |
Neg logit contributions | |
ktop | -0.147 |
acs | -0.147 |
olla | -0.146 |
rog | -0.143 |
impaired | -0.138 |
Token | bit |
Token ID | 1643 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
olla | +0.184 |
ktop | +0.183 |
acs | +0.183 |
rog | +0.177 |
impaired | +0.168 |
Neg logit contributions | |
Yao | -0.309 |
Debor | -0.283 |
intern | -0.281 |
Spencer | -0.279 |
JC | -0.279 |
Token | strange |
Token ID | 6283 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
olla | +0.370 |
ktop | +0.369 |
acs | +0.368 |
rog | +0.357 |
impaired | +0.338 |
Neg logit contributions | |
Yao | -0.688 |
Debor | -0.633 |
intern | -0.627 |
Spencer | -0.624 |
JC | -0.623 |
Token | ." |
Token ID | 526 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
acs | +0.113 |
olla | +0.113 |
ktop | +0.113 |
rog | +0.111 |
impaired | +0.107 |
Neg logit contributions | |
Yao | -0.116 |
Debor | -0.104 |
intern | -0.103 |
Spencer | -0.102 |
JC | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Yao | +1.832 |
Spencer | +1.635 |
Debor | +1.634 |
JC | +1.633 |
intern | +1.601 |
Neg logit contributions | |
ktop | -1.567 |
acs | -1.540 |
olla | -1.520 |
neur | -1.514 |
impaired | -1.494 |
Token |
|
Token ID | 198 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Yao | +0.191 |
JC | +0.171 |
Debor | +0.170 |
Spencer | +0.170 |
intern | +0.169 |
Neg logit contributions | |
ktop | -0.149 |
acs | -0.146 |
olla | -0.146 |
rog | -0.142 |
neur | -0.140 |
Token | Video |
Token ID | 10798 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Yao | +0.254 |
Debor | +0.227 |
JC | +0.224 |
Spencer | +0.223 |
•• | +0.222 |
Neg logit contributions | |
ktop | -0.244 |
olla | -0.243 |
acs | -0.241 |
rog | -0.236 |
impaired | -0.233 |
Token | : |
Token ID | 25 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Yao | +1.956 |
JC | +1.675 |
Spencer | +1.649 |
intern | +1.639 |
Debor | +1.634 |
Neg logit contributions | |
ktop | -2.897 |
acs | -2.822 |
olla | -2.811 |
rog | -2.736 |
neur | -2.699 |
Token | W |
Token ID | 370 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
Yao | +1.139 |
JC | +1.002 |
Debor | +0.997 |
Spencer | +0.987 |
EB | +0.978 |
Neg logit contributions | |
ktop | -1.360 |
olla | -1.341 |
acs | -1.336 |
rog | -1.322 |
impaired | -1.280 |
Token | PG |
Token ID | 6968 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ktop | +0.332 |
olla | +0.329 |
acs | +0.329 |
rog | +0.322 |
impaired | +0.313 |
Neg logit contributions | |
Yao | -0.369 |
Debor | -0.332 |
JC | -0.327 |
intern | -0.326 |
Spencer | -0.325 |
Token | @ |
Token ID | 31 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Yao | +0.083 |
Debor | +0.075 |
intern | +0.073 |
JC | +0.073 |
Spencer | +0.073 |
Neg logit contributions | |
acs | -0.077 |
olla | -0.077 |
ktop | -0.077 |
rog | -0.076 |
impaired | -0.074 |
Token | FL |
Token ID | 3697 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ktop | +0.012 |
olla | +0.012 |
acs | +0.012 |
rog | +0.012 |
impaired | +0.011 |
Neg logit contributions | |
Yao | -0.011 |
Debor | -0.010 |
JC | -0.010 |
Spencer | -0.010 |
intern | -0.010 |
Token | Dear |
Token ID | 20266 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
Yao | +0.387 |
Debor | +0.353 |
Spencer | +0.347 |
JC | +0.346 |
•• | +0.346 |
Neg logit contributions | |
ktop | -0.265 |
olla | -0.263 |
acs | -0.263 |
rog | -0.254 |
impaired | -0.251 |
Token | George |
Token ID | 4502 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Yao | +0.613 |
Debor | +0.556 |
Spencer | +0.544 |
JC | +0.544 |
intern | +0.542 |
Neg logit contributions | |
ktop | -0.547 |
olla | -0.542 |
acs | -0.541 |
rog | -0.528 |
impaired | -0.514 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Yao | +1.270 |
Debor | +1.131 |
Spencer | +1.106 |
intern | +1.103 |
JC | +1.100 |
Neg logit contributions | |
ktop | -1.445 |
acs | -1.439 |
olla | -1.439 |
rog | -1.412 |
impaired | -1.382 |
Token |
|
Token ID | 198 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Yao | +1.161 |
Debor | +1.051 |
JC | +1.036 |
Spencer | +1.035 |
intern | +1.030 |
Neg logit contributions | |
ktop | -0.896 |
acs | -0.885 |
olla | -0.878 |
rog | -0.855 |
impaired | -0.839 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Yao | +0.463 |
Debor | +0.413 |
JC | +0.413 |
Spencer | +0.411 |
intern | +0.409 |
Neg logit contributions | |
ktop | -0.361 |
acs | -0.355 |
olla | -0.352 |
rog | -0.343 |
neur | -0.339 |
Token | I |
Token ID | 40 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Yao | +0.907 |
Debor | +0.810 |
Spencer | +0.794 |
•• | +0.793 |
JC | +0.792 |
Neg logit contributions | |
ktop | -0.930 |
olla | -0.919 |
acs | -0.918 |
rog | -0.894 |
impaired | -0.889 |
Token | had |
Token ID | 550 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Yao | +2.317 |
Debor | +2.099 |
intern | +2.069 |
Spencer | +2.066 |
JC | +2.052 |
Neg logit contributions | |
ktop | -2.116 |
acs | -2.085 |
olla | -2.084 |
rog | -2.045 |
impaired | -1.983 |
Token | a |
Token ID | 257 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
Yao | +2.118 |
Debor | +1.912 |
intern | +1.882 |
Spencer | +1.877 |
JC | +1.873 |
Neg logit contributions | |
ktop | -1.849 |
acs | -1.840 |
olla | -1.832 |
rog | -1.787 |
lime | -1.718 |
Token | dream |
Token ID | 4320 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
Yao | +0.693 |
Debor | +0.627 |
JC | +0.620 |
intern | +0.619 |
Spencer | +0.617 |
Neg logit contributions | |
ktop | -0.552 |
acs | -0.551 |
olla | -0.548 |
rog | -0.533 |
impaired | -0.517 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ktop | +0.687 |
acs | +0.686 |
olla | +0.684 |
rog | +0.671 |
impaired | +0.652 |
Neg logit contributions | |
Yao | -0.752 |
Debor | -0.679 |
intern | -0.666 |
Spencer | -0.664 |
JC | -0.664 |
Token | a |
Token ID | 257 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
acs | +0.852 |
olla | +0.851 |
ktop | +0.849 |
rog | +0.831 |
impaired | +0.810 |
Neg logit contributions | |
Yao | -1.000 |
Debor | -0.906 |
intern | -0.886 |
JC | -0.885 |
Spencer | -0.884 |
Token | ar |
Token ID | 283 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Yao | +1.740 |
Debor | +1.530 |
intern | +1.520 |
JC | +1.519 |
Spencer | +1.507 |
Neg logit contributions | |
ktop | -1.859 |
acs | -1.817 |
olla | -1.804 |
impaired | -1.791 |
neur | -1.787 |
Token | ap |
Token ID | 499 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Yao | +2.032 |
JC | +1.805 |
Debor | +1.803 |
intern | +1.797 |
Spencer | +1.778 |
Neg logit contributions | |
ktop | -1.981 |
acs | -1.917 |
olla | -1.895 |
neur | -1.895 |
impaired | -1.868 |
Token | at |
Token ID | 265 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Yao | +0.888 |
Debor | +0.796 |
intern | +0.787 |
JC | +0.780 |
Spencer | +0.775 |
Neg logit contributions | |
ktop | -0.856 |
acs | -0.845 |
olla | -0.840 |
rog | -0.823 |
impaired | -0.811 |
Token | ang |
Token ID | 648 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ktop | +0.337 |
acs | +0.337 |
olla | +0.336 |
rog | +0.329 |
impaired | +0.321 |
Neg logit contributions | |
Yao | -0.356 |
Debor | -0.321 |
intern | -0.314 |
JC | -0.314 |
Spencer | -0.313 |
Token | p |
Token ID | 279 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Yao | +1.912 |
Debor | +1.723 |
intern | +1.711 |
JC | +1.697 |
Spencer | +1.680 |
Neg logit contributions | |
ktop | -1.703 |
acs | -1.690 |
olla | -1.676 |
rog | -1.635 |
impaired | -1.589 |
Token | anta |
Token ID | 4910 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Yao | +1.214 |
Debor | +1.072 |
intern | +1.055 |
Spencer | +1.050 |
JC | +1.048 |
Neg logit contributions | |
ktop | -1.265 |
olla | -1.246 |
acs | -1.245 |
rog | -1.225 |
impaired | -1.215 |
Token | o |
Token ID | 78 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
Yao | +2.679 |
intern | +2.405 |
JC | +2.385 |
Debor | +2.383 |
Spencer | +2.338 |
Neg logit contributions | |
ktop | -2.358 |
acs | -2.304 |
olla | -2.296 |
rog | -2.244 |
impaired | -2.211 |
Token | ( |
Token ID | 357 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Yao | +0.600 |
Debor | +0.540 |
intern | +0.534 |
JC | +0.533 |
Spencer | +0.529 |
Neg logit contributions | |
ktop | -0.511 |
acs | -0.508 |
olla | -0.506 |
rog | -0.494 |
impaired | -0.482 |
Token | Although |
Token ID | 7003 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
Yao | +0.938 |
Debor | +0.843 |
Spencer | +0.824 |
JC | +0.824 |
intern | +0.823 |
Neg logit contributions | |
ktop | -0.914 |
olla | -0.905 |
acs | -0.903 |
rog | -0.877 |
impaired | -0.869 |
Token | we |
Token ID | 356 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Yao | +0.720 |
Debor | +0.652 |
intern | +0.639 |
JC | +0.638 |
Spencer | +0.638 |
Neg logit contributions | |
ktop | -0.624 |
acs | -0.622 |
olla | -0.621 |
rog | -0.606 |
impaired | -0.588 |
Token | are |
Token ID | 389 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Yao | +0.858 |
Debor | +0.781 |
intern | +0.771 |
JC | +0.766 |
Spencer | +0.764 |
Neg logit contributions | |
ktop | -0.686 |
olla | -0.683 |
acs | -0.680 |
rog | -0.668 |
impaired | -0.644 |
Token | a |
Token ID | 257 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
acs | +0.665 |
olla | +0.664 |
ktop | +0.664 |
rog | +0.646 |
impaired | +0.626 |
Neg logit contributions | |
Yao | -0.896 |
Debor | -0.816 |
intern | -0.802 |
Spencer | -0.799 |
JC | -0.799 |
Token | ur |
Token ID | 2956 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
olla | +1.405 |
acs | +1.403 |
ktop | +1.401 |
rog | +1.379 |
impaired | +1.344 |
Neg logit contributions | |
Yao | -1.571 |
Debor | -1.424 |
JC | -1.388 |
intern | -1.386 |
Spencer | -1.384 |
Token | inal |
Token ID | 1292 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
acs | +0.165 |
olla | +0.164 |
ktop | +0.164 |
rog | +0.157 |
impaired | +0.154 |
Neg logit contributions | |
Yao | -0.340 |
Debor | -0.314 |
intern | -0.310 |
JC | -0.309 |
Spencer | -0.308 |
Token | . |
Token ID | 13 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
acs | +0.337 |
olla | +0.335 |
ktop | +0.333 |
rog | +0.326 |
impaired | +0.318 |
Neg logit contributions | |
Yao | -0.361 |
Debor | -0.325 |
intern | -0.321 |
JC | -0.319 |
Spencer | -0.318 |
Token | Pretty |
Token ID | 20090 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ktop | +0.170 |
acs | +0.169 |
olla | +0.169 |
rog | +0.165 |
impaired | +0.162 |
Neg logit contributions | |
Yao | -0.169 |
Debor | -0.151 |
Spencer | -0.148 |
JC | -0.148 |
intern | -0.146 |
Token | much |
Token ID | 881 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
Yao | +0.155 |
Debor | +0.140 |
intern | +0.139 |
Spencer | +0.138 |
JC | +0.138 |
Neg logit contributions | |
ktop | -0.116 |
olla | -0.115 |
acs | -0.115 |
rog | -0.112 |
impaired | -0.107 |
Token | every |
Token ID | 790 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Yao | +0.275 |
Debor | +0.247 |
intern | +0.243 |
Spencer | +0.243 |
JC | +0.242 |
Neg logit contributions | |
ktop | -0.247 |
acs | -0.247 |
olla | -0.246 |
rog | -0.241 |
impaired | -0.231 |
Token | other |
Token ID | 584 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
acs | +0.280 |
ktop | +0.280 |
olla | +0.280 |
rog | +0.273 |
impaired | +0.264 |
Neg logit contributions | |
Yao | -0.369 |
Debor | -0.336 |
intern | -0.330 |
Spencer | -0.329 |
JC | -0.329 |
Token | day |
Token ID | 1110 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Yao | +0.781 |
Debor | +0.709 |
intern | +0.699 |
Spencer | +0.697 |
JC | +0.696 |
Neg logit contributions | |
ktop | -0.607 |
acs | -0.607 |
olla | -0.606 |
rog | -0.590 |
impaired | -0.570 |
Token | I |
Token ID | 314 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Yao | +0.490 |
Debor | +0.441 |
intern | +0.434 |
Spencer | +0.434 |
JC | +0.431 |
Neg logit contributions | |
ktop | -0.458 |
acs | -0.456 |
olla | -0.456 |
rog | -0.446 |
impaired | -0.428 |
Token | can |
Token ID | 460 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
Yao | +0.627 |
Debor | +0.566 |
intern | +0.565 |
Spencer | +0.559 |
JC | +0.558 |
Neg logit contributions | |
ktop | -0.529 |
acs | -0.522 |
olla | -0.521 |
rog | -0.513 |
impaired | -0.493 |
Token | businesses |
Token ID | 5692 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Yao | +0.420 |
Debor | +0.382 |
intern | +0.379 |
JC | +0.375 |
Spencer | +0.375 |
Neg logit contributions | |
ktop | -0.331 |
olla | -0.330 |
acs | -0.330 |
rog | -0.322 |
impaired | -0.311 |
Token | , |
Token ID | 11 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
Yao | +0.074 |
Debor | +0.066 |
intern | +0.065 |
JC | +0.065 |
Spencer | +0.065 |
Neg logit contributions | |
olla | -0.081 |
ktop | -0.081 |
acs | -0.081 |
rog | -0.079 |
impaired | -0.077 |
Token | be |
Token ID | 307 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Yao | +0.443 |
Debor | +0.399 |
intern | +0.395 |
Spencer | +0.391 |
JC | +0.390 |
Neg logit contributions | |
olla | -0.424 |
ktop | -0.423 |
acs | -0.422 |
rog | -0.413 |
impaired | -0.401 |
Token | in |
Token ID | 287 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Yao | +0.373 |
Debor | +0.338 |
intern | +0.334 |
Spencer | +0.330 |
JC | +0.330 |
Neg logit contributions | |
ktop | -0.342 |
olla | -0.341 |
acs | -0.341 |
rog | -0.333 |
impaired | -0.323 |
Token | employment |
Token ID | 7184 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
olla | +0.078 |
acs | +0.078 |
ktop | +0.078 |
rog | +0.076 |
impaired | +0.074 |
Neg logit contributions | |
Yao | -0.096 |
Debor | -0.088 |
intern | -0.086 |
JC | -0.086 |
Spencer | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
olla | +0.538 |
acs | +0.538 |
ktop | +0.538 |
rog | +0.527 |
impaired | +0.514 |
Neg logit contributions | |
Yao | -0.517 |
Debor | -0.464 |
intern | -0.453 |
JC | -0.452 |
Spencer | -0.451 |
Token | qualify |
Token ID | 12780 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Yao | +0.077 |
Debor | +0.069 |
intern | +0.068 |
Spencer | +0.067 |
JC | +0.067 |
Neg logit contributions | |
olla | -0.074 |
acs | -0.074 |
ktop | -0.074 |
rog | -0.072 |
impaired | -0.070 |
Token | for |
Token ID | 329 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Yao | +0.108 |
Debor | +0.098 |
intern | +0.096 |
JC | +0.096 |
Spencer | +0.096 |
Neg logit contributions | |
olla | -0.094 |
acs | -0.094 |
ktop | -0.094 |
rog | -0.092 |
impaired | -0.090 |
Token | benefits |
Token ID | 4034 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
olla | +0.119 |
acs | +0.119 |
ktop | +0.119 |
rog | +0.116 |
impaired | +0.113 |
Neg logit contributions | |
Yao | -0.121 |
Debor | -0.109 |
intern | -0.107 |
JC | -0.107 |
Spencer | -0.107 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Yao | +0.564 |
Debor | +0.504 |
intern | +0.498 |
JC | +0.491 |
Spencer | +0.490 |
Neg logit contributions | |
olla | -0.643 |
ktop | -0.642 |
acs | -0.641 |
rog | -0.631 |
impaired | -0.611 |
Token | access |
Token ID | 1895 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
olla | +0.091 |
acs | +0.091 |
ktop | +0.091 |
rog | +0.089 |
impaired | +0.087 |
Neg logit contributions | |
Yao | -0.097 |
Debor | -0.087 |
intern | -0.086 |
JC | -0.085 |
Spencer | -0.085 |
Token | 's |
Token ID | 338 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Yao | +0.110 |
Debor | +0.099 |
intern | +0.096 |
JC | +0.096 |
Spencer | +0.096 |
Neg logit contributions | |
acs | -0.112 |
olla | -0.112 |
ktop | -0.111 |
rog | -0.109 |
impaired | -0.107 |
Token | offices |
Token ID | 9730 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
acs | +0.153 |
olla | +0.153 |
ktop | +0.153 |
rog | +0.150 |
impaired | +0.146 |
Neg logit contributions | |
Yao | -0.143 |
Debor | -0.128 |
intern | -0.125 |
JC | -0.125 |
Spencer | -0.125 |
Token | in |
Token ID | 287 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
olla | +0.101 |
acs | +0.101 |
ktop | +0.101 |
rog | +0.099 |
impaired | +0.097 |
Neg logit contributions | |
Yao | -0.098 |
Debor | -0.088 |
intern | -0.086 |
JC | -0.086 |
Spencer | -0.085 |
Token | Seoul |
Token ID | 22372 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Yao | +0.337 |
Debor | +0.301 |
Spencer | +0.297 |
JC | +0.297 |
intern | +0.296 |
Neg logit contributions | |
acs | -0.329 |
ktop | -0.328 |
olla | -0.328 |
rog | -0.321 |
impaired | -0.311 |
Token | today |
Token ID | 1909 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Yao | +0.207 |
Debor | +0.186 |
intern | +0.181 |
JC | +0.181 |
Spencer | +0.181 |
Neg logit contributions | |
olla | -0.219 |
acs | -0.219 |
ktop | -0.219 |
rog | -0.215 |
impaired | -0.209 |
Token | , |
Token ID | 11 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
Yao | +0.883 |
Debor | +0.790 |
intern | +0.776 |
JC | +0.773 |
Spencer | +0.767 |
Neg logit contributions | |
olla | -0.981 |
ktop | -0.978 |
acs | -0.975 |
rog | -0.955 |
impaired | -0.927 |
Token | C |
Token ID | 327 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Yao | +0.605 |
Debor | +0.546 |
intern | +0.538 |
JC | +0.535 |
Spencer | +0.533 |
Neg logit contributions | |
olla | -0.567 |
ktop | -0.566 |
acs | -0.565 |
rog | -0.553 |
impaired | -0.535 |
Token | NET |
Token ID | 12884 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
Yao | +0.947 |
Debor | +0.832 |
JC | +0.819 |
Spencer | +0.815 |
intern | +0.813 |
Neg logit contributions | |
olla | -1.214 |
ktop | -1.212 |
acs | -1.209 |
rog | -1.184 |
impaired | -1.167 |
Token | has |
Token ID | 468 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Yao | +0.296 |
Debor | +0.264 |
intern | +0.258 |
JC | +0.257 |
Spencer | +0.256 |
Neg logit contributions | |
ktop | -0.337 |
acs | -0.337 |
olla | -0.337 |
rog | -0.331 |
impaired | -0.323 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Yao | +0.880 |
Debor | +0.803 |
intern | +0.789 |
Spencer | +0.786 |
JC | +0.786 |
Neg logit contributions | |
acs | -0.659 |
olla | -0.657 |
ktop | -0.656 |
rog | -0.641 |
impaired | -0.620 |
Token | . |
Token ID | 13 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Yao | +1.081 |
Debor | +0.975 |
intern | +0.954 |
Spencer | +0.951 |
JC | +0.950 |
Neg logit contributions | |
ktop | -1.081 |
acs | -1.079 |
olla | -1.074 |
rog | -1.053 |
impaired | -1.026 |
Token | for |
Token ID | 329 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Yao | +0.177 |
Debor | +0.160 |
intern | +0.157 |
JC | +0.157 |
Spencer | +0.156 |
Neg logit contributions | |
acs | -0.152 |
olla | -0.152 |
ktop | -0.152 |
rog | -0.149 |
impaired | -0.145 |
Token | the |
Token ID | 262 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
olla | +0.150 |
acs | +0.150 |
ktop | +0.150 |
rog | +0.147 |
impaired | +0.142 |
Neg logit contributions | |
Yao | -0.209 |
Debor | -0.191 |
intern | -0.187 |
JC | -0.186 |
Spencer | -0.186 |
Token | Sh |
Token ID | 911 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
olla | +0.585 |
acs | +0.585 |
ktop | +0.584 |
rog | +0.573 |
impaired | +0.557 |
Neg logit contributions | |
Yao | -0.640 |
Debor | -0.578 |
Spencer | -0.566 |
JC | -0.565 |
intern | -0.565 |
Token | river |
Token ID | 38291 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ktop | +0.113 |
acs | +0.111 |
olla | +0.108 |
impaired | +0.106 |
neur | +0.106 |
Neg logit contributions | |
Yao | -0.154 |
Debor | -0.140 |
intern | -0.138 |
Spencer | -0.138 |
JC | -0.138 |
Token | Award |
Token ID | 11289 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
Yao | +0.193 |
Debor | +0.178 |
Spencer | +0.175 |
JC | +0.175 |
intern | +0.174 |
Neg logit contributions | |
ktop | -0.107 |
olla | -0.106 |
acs | -0.106 |
rog | -0.104 |
impaired | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
olla | +0.654 |
acs | +0.653 |
ktop | +0.650 |
rog | +0.639 |
impaired | +0.625 |
Neg logit contributions | |
Yao | -0.626 |
Debor | -0.562 |
intern | -0.547 |
JC | -0.547 |
Spencer | -0.545 |
Token | please |
Token ID | 3387 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Yao | +1.017 |
Debor | +0.933 |
Spencer | +0.919 |
intern | +0.919 |
JC | +0.919 |
Neg logit contributions | |
ktop | -0.625 |
olla | -0.624 |
acs | -0.624 |
rog | -0.608 |
impaired | -0.585 |
Token | download |
Token ID | 4321 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Yao | +1.168 |
Debor | +1.061 |
intern | +1.049 |
JC | +1.045 |
Spencer | +1.043 |
Neg logit contributions | |
ktop | -0.890 |
olla | -0.890 |
acs | -0.888 |
rog | -0.866 |
impaired | -0.838 |
Token | the |
Token ID | 262 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
Yao | +1.055 |
Debor | +0.963 |
Spencer | +0.945 |
JC | +0.943 |
intern | +0.943 |
Neg logit contributions | |
acs | -0.777 |
ktop | -0.776 |
olla | -0.773 |
rog | -0.756 |
impaired | -0.732 |
Token | Sh |
Token ID | 911 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
Yao | +0.565 |
Debor | +0.497 |
Spencer | +0.488 |
JC | +0.486 |
intern | +0.484 |
Neg logit contributions | |
olla | -0.764 |
ktop | -0.762 |
acs | -0.762 |
rog | -0.751 |
impaired | -0.730 |
Token | river |
Token ID | 38291 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ktop | +0.545 |
acs | +0.541 |
olla | +0.527 |
impaired | +0.514 |
neur | +0.511 |
Neg logit contributions | |
Yao | -0.754 |
Debor | -0.689 |
intern | -0.677 |
Spencer | -0.676 |
JC | -0.676 |
Token | says |
Token ID | 1139 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
olla | +0.541 |
acs | +0.541 |
ktop | +0.540 |
rog | +0.528 |
impaired | +0.513 |
Neg logit contributions | |
Yao | -0.681 |
Debor | -0.619 |
intern | -0.606 |
JC | -0.606 |
Spencer | -0.605 |
Token | have |
Token ID | 423 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
acs | +0.250 |
olla | +0.250 |
ktop | +0.249 |
rog | +0.244 |
impaired | +0.238 |
Neg logit contributions | |
Yao | -0.309 |
Debor | -0.281 |
intern | -0.275 |
JC | -0.275 |
Spencer | -0.274 |
Token | contributed |
Token ID | 8639 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
acs | +0.434 |
olla | +0.434 |
ktop | +0.433 |
rog | +0.424 |
impaired | +0.412 |
Neg logit contributions | |
Yao | -0.513 |
Debor | -0.465 |
intern | -0.455 |
JC | -0.454 |
Spencer | -0.454 |
Token | to |
Token ID | 284 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
olla | +0.046 |
ktop | +0.046 |
acs | +0.046 |
rog | +0.045 |
impaired | +0.043 |
Neg logit contributions | |
Yao | -0.061 |
Debor | -0.055 |
intern | -0.054 |
JC | -0.054 |
Spencer | -0.054 |
Token | Pruitt |
Token ID | 39637 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
olla | +0.283 |
acs | +0.282 |
ktop | +0.282 |
rog | +0.276 |
impaired | +0.269 |
Neg logit contributions | |
Yao | -0.282 |
Debor | -0.253 |
intern | -0.248 |
JC | -0.247 |
Spencer | -0.247 |
Token | � |
Token ID | 447 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Yao | +0.566 |
Debor | +0.508 |
intern | +0.496 |
JC | +0.496 |
Spencer | +0.495 |
Neg logit contributions | |
acs | -0.566 |
olla | -0.566 |
ktop | -0.565 |
rog | -0.554 |
impaired | -0.541 |
Token | � |
Token ID | 247 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Yao | +1.537 |
Debor | +1.388 |
intern | +1.385 |
Spencer | +1.372 |
JC | +1.369 |
Neg logit contributions | |
ktop | -1.154 |
acs | -1.139 |
olla | -1.131 |
rog | -1.091 |
impaired | -1.081 |
Token | s |
Token ID | 82 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Yao | +0.717 |
Debor | +0.650 |
JC | +0.635 |
intern | +0.634 |
Spencer | +0.633 |
Neg logit contributions | |
acs | -0.597 |
olla | -0.596 |
ktop | -0.594 |
rog | -0.584 |
impaired | -0.567 |
Token | campaigns |
Token ID | 9964 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ktop | +0.092 |
olla | +0.092 |
acs | +0.092 |
rog | +0.090 |
impaired | +0.087 |
Neg logit contributions | |
Yao | -0.090 |
Debor | -0.081 |
intern | -0.079 |
JC | -0.079 |
Spencer | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
acs | +0.819 |
olla | +0.817 |
ktop | +0.814 |
rog | +0.803 |
impaired | +0.783 |
Neg logit contributions | |
Yao | -0.859 |
Debor | -0.774 |
unden | -0.754 |
JC | -0.752 |
Spencer | -0.751 |
Token | organizations |
Token ID | 5745 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
olla | +0.244 |
acs | +0.244 |
ktop | +0.244 |
rog | +0.238 |
impaired | +0.232 |
Neg logit contributions | |
Yao | -0.263 |
Debor | -0.238 |
intern | -0.233 |
JC | -0.232 |
Spencer | -0.232 |
Token |
|
Token ID | 198 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
olla | +0.103 |
acs | +0.103 |
ktop | +0.102 |
rog | +0.100 |
impaired | +0.097 |
Neg logit contributions | |
Yao | -0.152 |
Debor | -0.139 |
intern | -0.136 |
JC | -0.136 |
Spencer | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
ktop | +0.405 |
acs | +0.402 |
olla | +0.401 |
rog | +0.391 |
impaired | +0.382 |
Neg logit contributions | |
Yao | -0.573 |
Debor | -0.519 |
JC | -0.513 |
Spencer | -0.512 |
intern | -0.511 |
Token | Do |
Token ID | 5211 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
acs | +0.370 |
ktop | +0.370 |
olla | +0.370 |
rog | +0.362 |
impaired | +0.354 |
Neg logit contributions | |
Yao | -0.396 |
Debor | -0.356 |
JC | -0.348 |
intern | -0.348 |
Spencer | -0.348 |
Token | not |
Token ID | 407 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
olla | +1.062 |
acs | +1.058 |
ktop | +1.055 |
rog | +1.042 |
impaired | +1.019 |
Neg logit contributions | |
Yao | -1.032 |
Debor | -0.938 |
JC | -0.905 |
unden | -0.902 |
Spencer | -0.898 |
Token | use |
Token ID | 779 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Yao | +0.749 |
Debor | +0.668 |
intern | +0.658 |
JC | +0.654 |
Spencer | +0.653 |
Neg logit contributions | |
ktop | -0.782 |
acs | -0.781 |
olla | -0.780 |
rog | -0.765 |
impaired | -0.744 |
Token | social |
Token ID | 1919 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
Yao | +0.998 |
Debor | +0.880 |
intern | +0.874 |
Spencer | +0.871 |
JC | +0.870 |
Neg logit contributions | |
ktop | -1.119 |
acs | -1.119 |
olla | -1.116 |
rog | -1.094 |
impaired | -1.065 |
Token | media |
Token ID | 2056 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
acs | +0.548 |
olla | +0.547 |
ktop | +0.546 |
rog | +0.535 |
impaired | +0.522 |
Neg logit contributions | |
Yao | -0.537 |
Debor | -0.481 |
intern | -0.472 |
JC | -0.470 |
Spencer | -0.470 |
Token | to |
Token ID | 284 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
Yao | +0.362 |
Debor | +0.327 |
intern | +0.320 |
JC | +0.320 |
Spencer | +0.319 |
Neg logit contributions | |
acs | -0.321 |
olla | -0.321 |
ktop | -0.320 |
rog | -0.313 |
impaired | -0.305 |
Token | let |
Token ID | 1309 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
acs | +0.464 |
olla | +0.464 |
ktop | +0.463 |
rog | +0.454 |
impaired | +0.443 |
Neg logit contributions | |
Yao | -0.506 |
Debor | -0.458 |
JC | -0.446 |
intern | -0.445 |
Spencer | -0.445 |
Token | people |
Token ID | 661 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
Yao | +1.765 |
Debor | +1.580 |
Spencer | +1.575 |
intern | +1.573 |
JC | +1.563 |
Neg logit contributions | |
ktop | -1.519 |
olla | -1.506 |
acs | -1.485 |
rog | -1.446 |
impaired | -1.396 |
Token | know |
Token ID | 760 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
ktop | +0.443 |
olla | +0.443 |
acs | +0.442 |
rog | +0.432 |
impaired | +0.420 |
Neg logit contributions | |
Yao | -0.513 |
Debor | -0.464 |
intern | -0.457 |
JC | -0.455 |
Spencer | -0.454 |
Token | she |
Token ID | 673 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Yao | +0.364 |
Debor | +0.331 |
intern | +0.326 |
Spencer | +0.325 |
JC | +0.324 |
Neg logit contributions | |
ktop | -0.283 |
olla | -0.281 |
acs | -0.280 |
rog | -0.274 |
impaired | -0.264 |
Token | would |
Token ID | 561 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ktop | +0.376 |
olla | +0.373 |
acs | +0.373 |
rog | +0.364 |
impaired | +0.347 |
Neg logit contributions | |
Yao | -0.562 |
Debor | -0.515 |
intern | -0.510 |
JC | -0.505 |
Spencer | -0.504 |
Token | put |
Token ID | 1234 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Yao | +0.231 |
Debor | +0.208 |
intern | +0.205 |
JC | +0.204 |
Spencer | +0.203 |
Neg logit contributions | |
ktop | -0.219 |
acs | -0.219 |
olla | -0.218 |
rog | -0.214 |
impaired | -0.208 |
Token | them |
Token ID | 606 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
Yao | +0.422 |
Debor | +0.383 |
Spencer | +0.376 |
intern | +0.375 |
JC | +0.375 |
Neg logit contributions | |
ktop | -0.351 |
olla | -0.350 |
acs | -0.350 |
rog | -0.341 |
impaired | -0.330 |
Token | to |
Token ID | 284 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
Yao | +0.042 |
Debor | +0.038 |
intern | +0.037 |
Spencer | +0.037 |
JC | +0.037 |
Neg logit contributions | |
ktop | -0.045 |
olla | -0.045 |
acs | -0.045 |
rog | -0.044 |
impaired | -0.043 |
Token | sleep |
Token ID | 3993 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
olla | +0.707 |
acs | +0.702 |
ktop | +0.700 |
rog | +0.689 |
impaired | +0.675 |
Neg logit contributions | |
Yao | -0.772 |
Debor | -0.700 |
JC | -0.683 |
unden | -0.682 |
intern | -0.680 |
Token | each |
Token ID | 1123 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
olla | +1.160 |
acs | +1.159 |
ktop | +1.158 |
rog | +1.136 |
impaired | +1.107 |
Neg logit contributions | |
Yao | -1.112 |
Debor | -0.997 |
intern | -0.973 |
JC | -0.971 |
Spencer | -0.971 |
Token | night |
Token ID | 1755 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Yao | +0.842 |
Debor | +0.772 |
intern | +0.765 |
Spencer | +0.761 |
JC | +0.760 |
Neg logit contributions | |
ktop | -0.478 |
acs | -0.476 |
olla | -0.476 |
rog | -0.461 |
impaired | -0.439 |
Token | as |
Token ID | 355 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Yao | +0.405 |
Debor | +0.361 |
intern | +0.356 |
Spencer | +0.354 |
JC | +0.351 |
Neg logit contributions | |
ktop | -0.451 |
acs | -0.448 |
olla | -0.448 |
rog | -0.439 |
impaired | -0.426 |
Token | children |
Token ID | 1751 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Yao | +0.932 |
Debor | +0.849 |
intern | +0.835 |
Spencer | +0.834 |
JC | +0.828 |
Neg logit contributions | |
ktop | -0.742 |
olla | -0.733 |
acs | -0.730 |
rog | -0.713 |
impaired | -0.685 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
acs | +1.489 |
olla | +1.487 |
ktop | +1.483 |
rog | +1.458 |
impaired | +1.424 |
Neg logit contributions | |
Yao | -1.447 |
Debor | -1.299 |
JC | -1.266 |
intern | -1.265 |
Spencer | -1.262 |
Token | action |
Token ID | 2223 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Yao | +0.707 |
Debor | +0.631 |
intern | +0.618 |
JC | +0.615 |
Spencer | +0.615 |
Neg logit contributions | |
ktop | -0.773 |
olla | -0.773 |
acs | -0.773 |
rog | -0.757 |
impaired | -0.737 |
Token | to |
Token ID | 284 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
Yao | +0.308 |
Debor | +0.277 |
intern | +0.271 |
JC | +0.270 |
Spencer | +0.270 |
Neg logit contributions | |
olla | -0.303 |
acs | -0.303 |
ktop | -0.303 |
rog | -0.297 |
impaired | -0.289 |
Token | protect |
Token ID | 1805 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
Yao | +0.045 |
Debor | +0.041 |
intern | +0.040 |
JC | +0.040 |
Spencer | +0.040 |
Neg logit contributions | |
olla | -0.035 |
ktop | -0.035 |
acs | -0.035 |
rog | -0.034 |
impaired | -0.033 |
Token | Oklahoma |
Token ID | 10433 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Yao | +0.002 |
Debor | +0.002 |
intern | +0.002 |
JC | +0.002 |
Spencer | +0.002 |
Neg logit contributions | |
acs | -0.001 |
ktop | -0.001 |
olla | -0.001 |
rog | -0.001 |
impaired | -0.001 |
Token | residents |
Token ID | 5085 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Yao | +0.484 |
Debor | +0.436 |
intern | +0.426 |
JC | +0.426 |
Spencer | +0.425 |
Neg logit contributions | |
olla | -0.457 |
acs | -0.457 |
ktop | -0.457 |
rog | -0.447 |
impaired | -0.436 |
Token | impacted |
Token ID | 20755 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Yao | +0.233 |
Debor | +0.211 |
intern | +0.206 |
JC | +0.206 |
Spencer | +0.206 |
Neg logit contributions | |
acs | -0.200 |
olla | -0.200 |
ktop | -0.200 |
rog | -0.196 |
impaired | -0.191 |
Token | by |
Token ID | 416 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
acs | +1.715 |
olla | +1.708 |
ktop | +1.692 |
rog | +1.684 |
impaired | +1.670 |
Neg logit contributions | |
Yao | -1.727 |
Debor | -1.555 |
JC | -1.516 |
unden | -1.513 |
Spencer | -1.498 |
Token | sw |
Token ID | 1509 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
acs | +0.876 |
olla | +0.876 |
ktop | +0.875 |
rog | +0.858 |
impaired | +0.836 |
Neg logit contributions | |
Yao | -0.916 |
Debor | -0.825 |
intern | -0.806 |
JC | -0.805 |
Spencer | -0.804 |
Token | arms |
Token ID | 8357 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Yao | +0.536 |
Debor | +0.479 |
JC | +0.464 |
unden | +0.463 |
intern | +0.462 |
Neg logit contributions | |
olla | -0.647 |
acs | -0.646 |
ktop | -0.640 |
rog | -0.634 |
impaired | -0.617 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Yao | +0.902 |
Debor | +0.821 |
intern | +0.805 |
JC | +0.804 |
Spencer | +0.803 |
Neg logit contributions | |
acs | -0.683 |
olla | -0.683 |
ktop | -0.682 |
rog | -0.667 |
impaired | -0.647 |
Token | fracking |
Token ID | 25441 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Yao | +1.137 |
Debor | +1.021 |
intern | +1.015 |
Spencer | +1.012 |
JC | +1.008 |
Neg logit contributions | |
ktop | -1.010 |
olla | -0.996 |
acs | -0.993 |
rog | -0.967 |
lime | -0.926 |
Token | The |
Token ID | 383 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
ktop | +0.072 |
olla | +0.071 |
acs | +0.071 |
rog | +0.070 |
impaired | +0.068 |
Neg logit contributions | |
Yao | -0.077 |
Debor | -0.069 |
Spencer | -0.068 |
JC | -0.067 |
intern | -0.067 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
olla | +0.644 |
ktop | +0.643 |
acs | +0.643 |
rog | +0.626 |
impaired | +0.604 |
Neg logit contributions | |
Yao | -0.830 |
Debor | -0.752 |
intern | -0.741 |
Spencer | -0.739 |
JC | -0.739 |
Token | has |
Token ID | 468 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
olla | +0.691 |
acs | +0.691 |
ktop | +0.690 |
rog | +0.675 |
impaired | +0.656 |
Neg logit contributions | |
Yao | -0.870 |
Debor | -0.791 |
intern | -0.774 |
JC | -0.773 |
Spencer | -0.772 |
Token | been |
Token ID | 587 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
olla | +0.158 |
acs | +0.157 |
ktop | +0.157 |
rog | +0.153 |
impaired | +0.147 |
Neg logit contributions | |
Yao | -0.196 |
Debor | -0.178 |
intern | -0.176 |
Spencer | -0.174 |
JC | -0.174 |
Token | featured |
Token ID | 8096 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
olla | +0.232 |
acs | +0.232 |
ktop | +0.232 |
rog | +0.227 |
impaired | +0.219 |
Neg logit contributions | |
Yao | -0.234 |
Debor | -0.210 |
intern | -0.207 |
Spencer | -0.205 |
JC | -0.205 |
Token | in |
Token ID | 287 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ktop | +1.564 |
olla | +1.563 |
acs | +1.563 |
rog | +1.535 |
impaired | +1.504 |
Neg logit contributions | |
Yao | -1.564 |
Debor | -1.407 |
JC | -1.371 |
intern | -1.368 |
Spencer | -1.367 |
Token | segments |
Token ID | 17894 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
acs | +0.683 |
olla | +0.683 |
ktop | +0.681 |
rog | +0.666 |
impaired | +0.646 |
Neg logit contributions | |
Yao | -0.878 |
Debor | -0.797 |
intern | -0.781 |
JC | -0.781 |
Spencer | -0.780 |
Token | of |
Token ID | 286 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
acs | +1.055 |
olla | +1.055 |
ktop | +1.053 |
rog | +1.033 |
impaired | +1.007 |
Neg logit contributions | |
Yao | -1.117 |
Debor | -1.007 |
intern | -0.983 |
JC | -0.983 |
Spencer | -0.981 |
Token | other |
Token ID | 584 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
acs | +0.441 |
olla | +0.440 |
ktop | +0.440 |
rog | +0.429 |
impaired | +0.416 |
Neg logit contributions | |
Yao | -0.549 |
Debor | -0.498 |
JC | -0.488 |
intern | -0.488 |
Spencer | -0.488 |
Token | episodes |
Token ID | 8640 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
olla | +0.146 |
ktop | +0.146 |
acs | +0.145 |
rog | +0.142 |
impaired | +0.137 |
Neg logit contributions | |
Yao | -0.179 |
Debor | -0.162 |
intern | -0.160 |
JC | -0.159 |
Spencer | -0.159 |
Token | of |
Token ID | 286 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
olla | +0.009 |
acs | +0.009 |
ktop | +0.009 |
rog | +0.009 |
impaired | +0.009 |
Neg logit contributions | |
Yao | -0.010 |
Debor | -0.009 |
intern | -0.009 |
Spencer | -0.009 |
JC | -0.009 |
Token | ] |
Token ID | 60 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
Yao | +1.231 |
Debor | +1.091 |
intern | +1.071 |
JC | +1.064 |
Spencer | +1.061 |
Neg logit contributions | |
olla | -1.480 |
ktop | -1.480 |
acs | -1.480 |
rog | -1.446 |
impaired | -1.406 |
Token | tradition |
Token ID | 6761 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
olla | +0.044 |
acs | +0.044 |
ktop | +0.043 |
rog | +0.043 |
impaired | +0.042 |
Neg logit contributions | |
Yao | -0.040 |
Debor | -0.036 |
intern | -0.035 |
JC | -0.035 |
Spencer | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
acs | +1.474 |
olla | +1.473 |
ktop | +1.471 |
rog | +1.444 |
impaired | +1.409 |
Neg logit contributions | |
Yao | -1.559 |
Debor | -1.408 |
intern | -1.372 |
JC | -1.371 |
Spencer | -1.369 |
Token | where |
Token ID | 810 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
acs | +0.545 |
olla | +0.545 |
ktop | +0.544 |
rog | +0.531 |
impaired | +0.516 |
Neg logit contributions | |
Yao | -0.667 |
Debor | -0.605 |
intern | -0.593 |
JC | -0.593 |
Spencer | -0.592 |
Token | you |
Token ID | 345 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
olla | +0.334 |
acs | +0.334 |
ktop | +0.334 |
rog | +0.325 |
impaired | +0.316 |
Neg logit contributions | |
Yao | -0.400 |
Debor | -0.363 |
Spencer | -0.356 |
intern | -0.356 |
JC | -0.355 |
Token | get |
Token ID | 651 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
olla | +0.674 |
acs | +0.674 |
ktop | +0.673 |
rog | +0.658 |
impaired | +0.639 |
Neg logit contributions | |
Yao | -0.817 |
Debor | -0.742 |
intern | -0.728 |
JC | -0.726 |
Spencer | -0.725 |
Token | the |
Token ID | 262 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
acs | +1.110 |
olla | +1.110 |
ktop | +1.107 |
rog | +1.088 |
impaired | +1.060 |
Neg logit contributions | |
Yao | -1.343 |
Debor | -1.219 |
intern | -1.190 |
JC | -1.190 |
Spencer | -1.187 |
Token | composer |
Token ID | 26777 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Yao | +0.210 |
Debor | +0.190 |
intern | +0.186 |
Spencer | +0.186 |
JC | +0.185 |
Neg logit contributions | |
acs | -0.192 |
olla | -0.192 |
ktop | -0.192 |
rog | -0.187 |
impaired | -0.182 |
Token | -- |
Token ID | 1377 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
acs | +1.104 |
olla | +1.103 |
ktop | +1.102 |
rog | +1.081 |
impaired | +1.057 |
Neg logit contributions | |
Yao | -1.166 |
Debor | -1.051 |
JC | -1.025 |
intern | -1.024 |
Spencer | -1.021 |
Token |
|
Token ID | 198 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
Yao | +0.049 |
Debor | +0.045 |
Spencer | +0.044 |
intern | +0.044 |
JC | +0.044 |
Neg logit contributions | |
acs | -0.042 |
olla | -0.042 |
ktop | -0.041 |
rog | -0.040 |
impaired | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
ktop | +0.387 |
acs | +0.384 |
olla | +0.383 |
rog | +0.373 |
impaired | +0.364 |
Neg logit contributions | |
Yao | -0.537 |
Debor | -0.485 |
JC | -0.481 |
Spencer | -0.480 |
intern | -0.479 |
Token | rop |
Token ID | 1773 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ktop | +0.566 |
olla | +0.565 |
acs | +0.562 |
rog | +0.548 |
impaired | +0.541 |
Neg logit contributions | |
Yao | -0.558 |
Debor | -0.499 |
intern | -0.490 |
Spencer | -0.489 |
JC | -0.488 |
Token | yl |
Token ID | 2645 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Yao | +0.466 |
Debor | +0.427 |
intern | +0.420 |
Spencer | +0.419 |
JC | +0.419 |
Neg logit contributions | |
ktop | -0.330 |
acs | -0.329 |
olla | -0.328 |
rog | -0.319 |
impaired | -0.314 |
Token | methyl |
Token ID | 43654 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Yao | +0.387 |
Debor | +0.350 |
intern | +0.346 |
JC | +0.345 |
Spencer | +0.344 |
Neg logit contributions | |
ktop | -0.323 |
olla | -0.322 |
acs | -0.320 |
rog | -0.311 |
impaired | -0.304 |
Token | - |
Token ID | 12 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
acs | +1.134 |
olla | +1.128 |
ktop | +1.124 |
rog | +1.111 |
impaired | +1.077 |
Neg logit contributions | |
Yao | -1.452 |
Debor | -1.328 |
Spencer | -1.290 |
intern | -1.289 |
JC | -1.287 |
Token | 7 |
Token ID | 22 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Yao | +0.626 |
Debor | +0.560 |
intern | +0.554 |
JC | +0.553 |
Spencer | +0.551 |
Neg logit contributions | |
ktop | -0.578 |
olla | -0.576 |
acs | -0.571 |
rog | -0.557 |
impaired | -0.545 |
Token | -( |
Token ID | 30420 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
Yao | +0.194 |
intern | +0.175 |
Debor | +0.173 |
JC | +0.172 |
Spencer | +0.172 |
Neg logit contributions | |
ktop | -0.165 |
olla | -0.161 |
acs | -0.160 |
rog | -0.155 |
impaired | -0.151 |
Token | 2 |
Token ID | 17 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
acs | +2.837 |
olla | +2.836 |
ktop | +2.806 |
rog | +2.784 |
impaired | +2.709 |
Neg logit contributions | |
Yao | -2.840 |
Debor | -2.570 |
Spencer | -2.495 |
intern | -2.489 |
JC | -2.482 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ktop | +0.662 |
olla | +0.661 |
acs | +0.657 |
rog | +0.644 |
impaired | +0.626 |
Neg logit contributions | |
Yao | -0.747 |
Debor | -0.672 |
intern | -0.663 |
JC | -0.660 |
Spencer | -0.658 |
Token | 6 |
Token ID | 21 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
ktop | +0.215 |
olla | +0.215 |
acs | +0.215 |
rog | +0.209 |
impaired | +0.206 |
Neg logit contributions | |
Yao | -0.191 |
Debor | -0.169 |
intern | -0.166 |
JC | -0.166 |
Spencer | -0.165 |
Token | - |
Token ID | 12 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
Yao | +0.004 |
Debor | +0.003 |
intern | +0.003 |
JC | +0.003 |
Spencer | +0.003 |
Neg logit contributions | |
ktop | -0.003 |
olla | -0.003 |
acs | -0.003 |
rog | -0.003 |
impaired | -0.003 |
Token | dim |
Token ID | 27740 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Yao | +0.079 |
Debor | +0.072 |
intern | +0.071 |
JC | +0.071 |
Spencer | +0.071 |
Neg logit contributions | |
ktop | -0.065 |
olla | -0.065 |
acs | -0.064 |
rog | -0.063 |
impaired | -0.061 |
Token | Alberta |
Token ID | 15555 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Yao | +0.913 |
Debor | +0.819 |
Spencer | +0.810 |
JC | +0.809 |
intern | +0.808 |
Neg logit contributions | |
ktop | -0.896 |
olla | -0.886 |
acs | -0.884 |
rog | -0.862 |
impaired | -0.841 |
Token | is |
Token ID | 318 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
olla | +0.263 |
ktop | +0.263 |
acs | +0.262 |
rog | +0.256 |
impaired | +0.248 |
Neg logit contributions | |
Yao | -0.383 |
Debor | -0.350 |
intern | -0.343 |
JC | -0.343 |
Spencer | -0.342 |
Token | gonna |
Token ID | 8066 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
ktop | +0.306 |
olla | +0.304 |
acs | +0.303 |
rog | +0.296 |
impaired | +0.287 |
Neg logit contributions | |
Yao | -0.370 |
Debor | -0.335 |
intern | -0.329 |
JC | -0.329 |
Spencer | -0.329 |
Token | succeed |
Token ID | 6758 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
olla | +0.416 |
acs | +0.416 |
ktop | +0.416 |
rog | +0.406 |
impaired | +0.395 |
Neg logit contributions | |
Yao | -0.541 |
Debor | -0.492 |
intern | -0.483 |
JC | -0.482 |
Spencer | -0.481 |
Token | by |
Token ID | 416 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Yao | +0.393 |
Debor | +0.353 |
intern | +0.345 |
Spencer | +0.344 |
JC | +0.344 |
Neg logit contributions | |
olla | -0.395 |
ktop | -0.394 |
acs | -0.394 |
rog | -0.385 |
impaired | -0.376 |
Token | pitching |
Token ID | 21088 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Yao | +0.084 |
Debor | +0.076 |
intern | +0.074 |
JC | +0.074 |
Spencer | +0.074 |
Neg logit contributions | |
olla | -0.074 |
acs | -0.074 |
ktop | -0.074 |
rog | -0.072 |
impaired | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
acs | +2.190 |
olla | +2.176 |
rog | +2.162 |
ktop | +2.139 |
impaired | +2.103 |
Neg logit contributions | |
Yao | -2.706 |
Debor | -2.471 |
unden | -2.400 |
intern | -2.396 |
JC | -2.379 |
Token | radical |
Token ID | 7702 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
olla | +0.521 |
acs | +0.521 |
ktop | +0.519 |
rog | +0.510 |
impaired | +0.496 |
Neg logit contributions | |
Yao | -0.619 |
Debor | -0.561 |
intern | -0.549 |
JC | -0.547 |
Spencer | -0.547 |
Token | program |
Token ID | 1430 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
olla | +1.270 |
acs | +1.268 |
ktop | +1.262 |
rog | +1.245 |
impaired | +1.216 |
Neg logit contributions | |
Yao | -1.281 |
Debor | -1.150 |
intern | -1.120 |
JC | -1.118 |
Spencer | -1.116 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
olla | +0.324 |
ktop | +0.323 |
acs | +0.323 |
rog | +0.316 |
impaired | +0.308 |
Neg logit contributions | |
Yao | -0.357 |
Debor | -0.322 |
intern | -0.315 |
Spencer | -0.315 |
JC | -0.315 |
Token | It |
Token ID | 632 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
Yao | +0.365 |
Debor | +0.330 |
JC | +0.323 |
Spencer | +0.323 |
intern | +0.320 |
Neg logit contributions | |
ktop | -0.331 |
acs | -0.327 |
olla | -0.327 |
rog | -0.321 |
impaired | -0.314 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Yao | +1.687 |
intern | +1.528 |
Debor | +1.525 |
Spencer | +1.511 |
JC | +1.506 |
Neg logit contributions | |
ktop | -1.325 |
olla | -1.325 |
acs | -1.305 |
rog | -1.279 |
impaired | -1.229 |
Token | Catholic |
Token ID | 7835 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
Yao | +1.339 |
Spencer | +1.204 |
Debor | +1.198 |
JC | +1.184 |
intern | +1.178 |
Neg logit contributions | |
olla | -1.598 |
ktop | -1.594 |
acs | -1.564 |
rog | -1.539 |
impaired | -1.521 |
Token | Encyclopedia |
Token ID | 36732 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
acs | +0.555 |
ktop | +0.554 |
olla | +0.554 |
rog | +0.543 |
impaired | +0.530 |
Neg logit contributions | |
Yao | -0.618 |
Debor | -0.558 |
JC | -0.545 |
unden | -0.542 |
intern | -0.542 |
Token | , |
Token ID | 11 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
olla | +0.646 |
acs | +0.644 |
ktop | +0.642 |
rog | +0.632 |
impaired | +0.618 |
Neg logit contributions | |
Yao | -0.601 |
Debor | -0.540 |
JC | -0.524 |
unden | -0.523 |
Spencer | -0.523 |
Token | Church |
Token ID | 4564 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
acs | +0.384 |
olla | +0.382 |
ktop | +0.380 |
rog | +0.377 |
impaired | +0.369 |
Neg logit contributions | |
Yao | -0.351 |
Debor | -0.314 |
unden | -0.305 |
JC | -0.304 |
intern | -0.303 |
Token | Fathers |
Token ID | 30969 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
acs | +1.055 |
ktop | +1.049 |
olla | +1.041 |
rog | +1.021 |
impaired | +0.993 |
Neg logit contributions | |
Yao | -1.278 |
Debor | -1.159 |
intern | -1.144 |
Spencer | -1.144 |
JC | -1.135 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
olla | +2.290 |
acs | +2.285 |
rog | +2.280 |
ktop | +2.226 |
lime | +2.195 |
Neg logit contributions | |
Yao | -2.563 |
Debor | -2.391 |
unden | -2.352 |
confir | -2.292 |
JC | -2.258 |
Token | Sum |
Token ID | 5060 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
olla | +0.886 |
ktop | +0.885 |
acs | +0.885 |
rog | +0.867 |
impaired | +0.848 |
Neg logit contributions | |
Yao | -0.748 |
Debor | -0.662 |
intern | -0.650 |
Spencer | -0.648 |
JC | -0.647 |
Token | ma |
Token ID | 2611 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Yao | +0.403 |
Debor | +0.354 |
intern | +0.351 |
JC | +0.347 |
Spencer | +0.343 |
Neg logit contributions | |
ktop | -0.490 |
acs | -0.483 |
olla | -0.482 |
rog | -0.472 |
impaired | -0.468 |
Token | , |
Token ID | 11 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
olla | +1.126 |
acs | +1.111 |
ktop | +1.103 |
rog | +1.094 |
impaired | +1.078 |
Neg logit contributions | |
Yao | -1.171 |
Debor | -1.061 |
unden | -1.048 |
•• | -1.020 |
JC | -1.018 |
Token | Bible |
Token ID | 9111 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
olla | +0.414 |
acs | +0.412 |
ktop | +0.408 |
rog | +0.402 |
impaired | +0.393 |
Neg logit contributions | |
Yao | -0.599 |
Debor | -0.551 |
unden | -0.538 |
JC | -0.534 |
intern | -0.534 |
Token | you |
Token ID | 345 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
olla | +0.199 |
acs | +0.199 |
ktop | +0.199 |
rog | +0.195 |
impaired | +0.190 |
Neg logit contributions | |
Yao | -0.221 |
Debor | -0.200 |
intern | -0.196 |
JC | -0.195 |
Spencer | -0.195 |
Token | this |
Token ID | 428 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Yao | +0.220 |
Debor | +0.198 |
JC | +0.194 |
intern | +0.194 |
Spencer | +0.194 |
Neg logit contributions | |
ktop | -0.197 |
acs | -0.196 |
olla | -0.196 |
rog | -0.191 |
impaired | -0.186 |
Token | post |
Token ID | 1281 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ktop | +0.240 |
acs | +0.240 |
olla | +0.239 |
rog | +0.234 |
impaired | +0.227 |
Neg logit contributions | |
Yao | -0.291 |
Debor | -0.262 |
intern | -0.259 |
JC | -0.258 |
Spencer | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
olla | +1.490 |
acs | +1.485 |
ktop | +1.482 |
rog | +1.457 |
impaired | +1.418 |
Neg logit contributions | |
Yao | -1.512 |
Debor | -1.363 |
JC | -1.328 |
intern | -1.327 |
unden | -1.325 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
acs | +0.571 |
ktop | +0.570 |
olla | +0.570 |
rog | +0.559 |
impaired | +0.546 |
Neg logit contributions | |
Yao | -0.550 |
Debor | -0.493 |
JC | -0.481 |
Spencer | -0.480 |
intern | -0.480 |
Token | THE |
Token ID | 10970 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ktop | +0.395 |
olla | +0.395 |
acs | +0.394 |
rog | +0.385 |
impaired | +0.378 |
Neg logit contributions | |
Yao | -0.408 |
Debor | -0.366 |
JC | -0.358 |
Spencer | -0.358 |
intern | -0.358 |
Token | BALL |
Token ID | 46433 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
acs | +2.788 |
olla | +2.781 |
ktop | +2.767 |
rog | +2.731 |
impaired | +2.672 |
Neg logit contributions | |
Yao | -2.625 |
Debor | -2.369 |
Spencer | -2.287 |
unden | -2.286 |
intern | -2.285 |
Token | OT |
Token ID | 2394 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
ktop | +0.675 |
acs | +0.673 |
olla | +0.673 |
rog | +0.658 |
impaired | +0.643 |
Neg logit contributions | |
Yao | -0.718 |
Debor | -0.645 |
JC | -0.633 |
intern | -0.632 |
Spencer | -0.631 |
Token | FOR |
Token ID | 7473 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Yao | +0.715 |
Debor | +0.640 |
JC | +0.631 |
intern | +0.629 |
EB | +0.627 |
Neg logit contributions | |
ktop | -0.733 |
olla | -0.728 |
acs | -0.728 |
rog | -0.713 |
impaired | -0.690 |
Token | industrial |
Token ID | 7593 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
ktop | +0.120 |
olla | +0.120 |
acs | +0.120 |
rog | +0.117 |
impaired | +0.114 |
Neg logit contributions | |
Yao | -0.123 |
Debor | -0.111 |
JC | -0.108 |
Spencer | -0.108 |
intern | -0.108 |
Token | action |
Token ID | 2223 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Yao | +0.557 |
Debor | +0.500 |
intern | +0.491 |
JC | +0.489 |
Spencer | +0.489 |
Neg logit contributions | |
ktop | -0.544 |
olla | -0.542 |
acs | -0.541 |
rog | -0.528 |
impaired | -0.515 |
Token | pc |
Token ID | 40653 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
olla | +1.559 |
acs | +1.555 |
ktop | +1.552 |
rog | +1.527 |
impaired | +1.493 |
Neg logit contributions | |
Yao | -1.468 |
Debor | -1.312 |
intern | -1.279 |
JC | -1.278 |
Spencer | -1.274 |
Token | Any |
Token ID | 7149 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
acs | +0.691 |
olla | +0.691 |
ktop | +0.687 |
rog | +0.677 |
impaired | +0.657 |
Neg logit contributions | |
Yao | -0.795 |
Debor | -0.720 |
intern | -0.702 |
Spencer | -0.701 |
JC | -0.701 |
Token | where |
Token ID | 3003 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Yao | +0.659 |
Debor | +0.600 |
intern | +0.591 |
JC | +0.591 |
Spencer | +0.588 |
Neg logit contributions | |
ktop | -0.470 |
acs | -0.468 |
olla | -0.468 |
rog | -0.457 |
impaired | -0.444 |
Token | , |
Token ID | 11 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
olla | +0.328 |
acs | +0.328 |
ktop | +0.326 |
rog | +0.321 |
impaired | +0.313 |
Neg logit contributions | |
Yao | -0.315 |
Debor | -0.282 |
intern | -0.275 |
JC | -0.274 |
Spencer | -0.274 |
Token | Splash |
Token ID | 45275 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
acs | +0.700 |
ktop | +0.700 |
olla | +0.699 |
rog | +0.684 |
impaired | +0.667 |
Neg logit contributions | |
Yao | -0.696 |
Debor | -0.627 |
intern | -0.612 |
Spencer | -0.612 |
JC | -0.611 |
Token | Car |
Token ID | 1879 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ktop | +0.311 |
acs | +0.310 |
olla | +0.310 |
rog | +0.304 |
impaired | +0.295 |
Neg logit contributions | |
Yao | -0.318 |
Debor | -0.286 |
JC | -0.280 |
Spencer | -0.280 |
intern | -0.280 |
Token | Wash |
Token ID | 22892 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
olla | +2.017 |
acs | +2.005 |
ktop | +1.977 |
rog | +1.947 |
impaired | +1.884 |
Neg logit contributions | |
Yao | -2.911 |
Debor | -2.671 |
intern | -2.608 |
JC | -2.603 |
unden | -2.603 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
acs | +0.458 |
olla | +0.458 |
ktop | +0.457 |
rog | +0.449 |
impaired | +0.438 |
Neg logit contributions | |
Yao | -0.430 |
Debor | -0.385 |
intern | -0.375 |
JC | -0.375 |
Spencer | -0.374 |
Token | Steven |
Token ID | 8239 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
acs | +1.141 |
olla | +1.139 |
ktop | +1.139 |
rog | +1.117 |
impaired | +1.090 |
Neg logit contributions | |
Yao | -1.059 |
Debor | -0.948 |
intern | -0.924 |
JC | -0.923 |
Spencer | -0.923 |
Token | La |
Token ID | 4689 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ktop | +0.735 |
olla | +0.735 |
acs | +0.735 |
rog | +0.720 |
impaired | +0.703 |
Neg logit contributions | |
Yao | -0.702 |
Debor | -0.629 |
JC | -0.613 |
intern | -0.613 |
Spencer | -0.613 |
Token | M |
Token ID | 44 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
acs | +1.175 |
olla | +1.175 |
ktop | +1.173 |
rog | +1.150 |
impaired | +1.120 |
Neg logit contributions | |
Yao | -1.263 |
Debor | -1.140 |
intern | -1.113 |
JC | -1.112 |
Spencer | -1.111 |