Token |
|
Token ID | 198 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
antha | +0.523 |
arov | +0.452 |
unction | +0.447 |
iversal | +0.446 |
66666666 | +0.435 |
Neg logit contributions | |
disproportion | -0.606 |
disadvant | -0.454 |
Penet | -0.451 |
Valkyrie | -0.439 |
scapego | -0.416 |
Token | " |
Token ID | 1 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
antha | +0.488 |
iversal | +0.411 |
arov | +0.409 |
unction | +0.406 |
66666666 | +0.389 |
Neg logit contributions | |
disproportion | -0.675 |
Penet | -0.523 |
disadvant | -0.510 |
Valkyrie | -0.510 |
Carmen | -0.485 |
Token | For |
Token ID | 1890 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
antha | +1.143 |
arov | +0.953 |
iversal | +0.951 |
unction | +0.941 |
66666666 | +0.907 |
Neg logit contributions | |
disproportion | -1.715 |
Penet | -1.330 |
disadvant | -1.313 |
Valkyrie | -1.304 |
scapego | -1.238 |
Token | all |
Token ID | 477 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
disproportion | +1.550 |
Penet | +1.139 |
Valkyrie | +1.103 |
disadvant | +1.097 |
Carmen | +1.034 |
Neg logit contributions | |
antha | -1.647 |
iversal | -1.435 |
arov | -1.424 |
unction | -1.419 |
66666666 | -1.367 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
antha | +0.321 |
iversal | +0.280 |
arov | +0.278 |
unction | +0.277 |
66666666 | +0.267 |
Neg logit contributions | |
disproportion | -0.300 |
Penet | -0.220 |
Valkyrie | -0.214 |
disadvant | -0.213 |
Carmen | -0.198 |
Token | pomp |
Token ID | 49435 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
antha | +1.315 |
arov | +1.144 |
iversal | +1.140 |
unction | +1.136 |
66666666 | +1.095 |
Neg logit contributions | |
disproportion | -1.210 |
Penet | -0.890 |
Valkyrie | -0.864 |
disadvant | -0.858 |
Carmen | -0.805 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
antha | +6.798 |
unction | +5.888 |
iversal | +5.868 |
arov | +5.839 |
atomic | +5.500 |
Neg logit contributions | |
disproportion | -8.038 |
Penet | -6.162 |
Valkyrie | -5.957 |
disadvant | -5.954 |
Carmen | -5.537 |
Token | ceremony |
Token ID | 10542 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
antha | +1.223 |
iversal | +1.066 |
arov | +1.053 |
unction | +1.050 |
66666666 | +1.015 |
Neg logit contributions | |
disproportion | -1.171 |
Penet | -0.857 |
Valkyrie | -0.834 |
disadvant | -0.829 |
scapego | -0.781 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
antha | +2.602 |
arov | +2.265 |
iversal | +2.263 |
unction | +2.248 |
66666666 | +2.162 |
Neg logit contributions | |
disproportion | -2.492 |
Penet | -1.837 |
Valkyrie | -1.775 |
disadvant | -1.763 |
Carmen | -1.659 |
Token | nothing |
Token ID | 2147 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
antha | +0.188 |
iversal | +0.164 |
arov | +0.163 |
unction | +0.162 |
66666666 | +0.157 |
Neg logit contributions | |
disproportion | -0.170 |
Penet | -0.124 |
Valkyrie | -0.120 |
disadvant | -0.119 |
Carmen | -0.112 |
Token | in |
Token ID | 287 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
disproportion | +1.500 |
Penet | +1.112 |
Valkyrie | +1.078 |
disadvant | +1.072 |
Carmen | +1.012 |
Neg logit contributions | |
antha | -1.517 |
iversal | -1.316 |
arov | -1.307 |
unction | -1.302 |
66666666 | -1.254 |
Token | of |
Token ID | 286 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
antha | +2.708 |
arov | +2.343 |
iversal | +2.315 |
unction | +2.310 |
66666666 | +2.231 |
Neg logit contributions | |
disproportion | -2.558 |
Penet | -1.901 |
Valkyrie | -1.858 |
disadvant | -1.814 |
Carmen | -1.719 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
antha | +0.086 |
iversal | +0.075 |
arov | +0.075 |
unction | +0.074 |
66666666 | +0.072 |
Neg logit contributions | |
disproportion | -0.077 |
Penet | -0.056 |
Valkyrie | -0.054 |
disadvant | -0.054 |
Carmen | -0.051 |
Token | ACA |
Token ID | 27628 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
disproportion | +1.431 |
Penet | +1.060 |
Valkyrie | +1.027 |
disadvant | +1.023 |
Carmen | +0.968 |
Neg logit contributions | |
antha | -1.441 |
iversal | -1.253 |
arov | -1.240 |
unction | -1.238 |
66666666 | -1.190 |
Token | was |
Token ID | 373 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
disproportion | +1.493 |
Penet | +1.095 |
Valkyrie | +1.059 |
disadvant | +1.054 |
Carmen | +0.993 |
Neg logit contributions | |
antha | -1.602 |
iversal | -1.397 |
arov | -1.386 |
unction | -1.382 |
66666666 | -1.331 |
Token | good |
Token ID | 922 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
antha | +0.557 |
arov | +0.487 |
iversal | +0.484 |
unction | +0.481 |
66666666 | +0.464 |
Neg logit contributions | |
disproportion | -0.508 |
Penet | -0.374 |
Valkyrie | -0.364 |
disadvant | -0.357 |
Carmen | -0.340 |
Token | enough |
Token ID | 1576 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
antha | +3.626 |
iversal | +3.168 |
arov | +3.117 |
unction | +3.116 |
66666666 | +3.011 |
Neg logit contributions | |
disproportion | -3.556 |
Penet | -2.650 |
Valkyrie | -2.579 |
disadvant | -2.533 |
Carmen | -2.386 |
Token | for |
Token ID | 329 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
antha | +6.491 |
iversal | +5.601 |
arov | +5.558 |
unction | +5.503 |
66666666 | +5.331 |
Neg logit contributions | |
disproportion | -7.168 |
Penet | -5.433 |
Valkyrie | -5.366 |
disadvant | -5.198 |
Carmen | -4.899 |
Token | those |
Token ID | 883 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
antha | +2.175 |
iversal | +1.875 |
arov | +1.872 |
unction | +1.867 |
66666666 | +1.806 |
Neg logit contributions | |
disproportion | -1.990 |
Penet | -1.466 |
Valkyrie | -1.428 |
disadvant | -1.402 |
Carmen | -1.312 |
Token | who |
Token ID | 508 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
antha | +2.508 |
arov | +2.149 |
iversal | +2.132 |
unction | +2.105 |
66666666 | +2.038 |
Neg logit contributions | |
disproportion | -2.761 |
Penet | -2.109 |
Valkyrie | -2.068 |
disadvant | -2.005 |
Carmen | -1.916 |
Token | couldn |
Token ID | 3521 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
disproportion | +0.694 |
Penet | +0.507 |
Valkyrie | +0.492 |
disadvant | +0.489 |
Carmen | +0.457 |
Neg logit contributions | |
antha | -0.781 |
iversal | -0.682 |
arov | -0.679 |
unction | -0.674 |
66666666 | -0.651 |
Token | 't |
Token ID | 470 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
disproportion | +0.708 |
Penet | +0.540 |
disadvant | +0.526 |
Valkyrie | +0.526 |
Carmen | +0.498 |
Neg logit contributions | |
antha | -0.591 |
iversal | -0.504 |
arov | -0.501 |
unction | -0.499 |
66666666 | -0.479 |
Token | as |
Token ID | 355 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
disproportion | +1.159 |
Penet | +0.845 |
Valkyrie | +0.817 |
disadvant | +0.814 |
Carmen | +0.768 |
Neg logit contributions | |
antha | -1.272 |
iversal | -1.113 |
arov | -1.103 |
unction | -1.097 |
66666666 | -1.059 |
Token | long |
Token ID | 890 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
disproportion | +1.066 |
Penet | +0.775 |
Valkyrie | +0.750 |
disadvant | +0.743 |
Carmen | +0.702 |
Neg logit contributions | |
antha | -1.201 |
iversal | -1.054 |
arov | -1.046 |
unction | -1.041 |
66666666 | -1.005 |
Token | as |
Token ID | 355 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
disproportion | +0.268 |
Penet | +0.197 |
Valkyrie | +0.191 |
disadvant | +0.189 |
Carmen | +0.179 |
Neg logit contributions | |
antha | -0.283 |
iversal | -0.246 |
arov | -0.245 |
unction | -0.243 |
66666666 | -0.235 |
Token | there |
Token ID | 612 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
disproportion | +0.660 |
Penet | +0.487 |
Valkyrie | +0.472 |
disadvant | +0.467 |
Carmen | +0.445 |
Neg logit contributions | |
antha | -0.680 |
iversal | -0.593 |
arov | -0.590 |
unction | -0.586 |
66666666 | -0.566 |
Token | is |
Token ID | 318 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
antha | +1.126 |
iversal | +0.969 |
arov | +0.961 |
unction | +0.960 |
66666666 | +0.919 |
Neg logit contributions | |
disproportion | -1.214 |
Penet | -0.914 |
Valkyrie | -0.888 |
disadvant | -0.886 |
Carmen | -0.837 |
Token | sufficient |
Token ID | 6751 |
Feature activation | +7.63e+00 |
Pos logit contributions | |
antha | +2.036 |
iversal | +1.760 |
unction | +1.757 |
arov | +1.755 |
66666666 | +1.677 |
Neg logit contributions | |
disproportion | -1.940 |
Penet | -1.435 |
Valkyrie | -1.391 |
disadvant | -1.390 |
Carmen | -1.300 |
Token | calcium |
Token ID | 19700 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
antha | +6.355 |
unction | +5.369 |
arov | +5.369 |
iversal | +5.267 |
66666666 | +5.069 |
Neg logit contributions | |
disproportion | -7.121 |
Penet | -5.467 |
disadvant | -5.415 |
Valkyrie | -5.279 |
Carmen | -5.040 |
Token | chloride |
Token ID | 44921 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
antha | +4.570 |
arov | +3.887 |
unction | +3.871 |
iversal | +3.835 |
66666666 | +3.699 |
Neg logit contributions | |
disproportion | -4.769 |
Penet | -3.600 |
Valkyrie | -3.535 |
disadvant | -3.520 |
Carmen | -3.320 |
Token | in |
Token ID | 287 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
antha | +2.846 |
arov | +2.441 |
unction | +2.428 |
iversal | +2.424 |
66666666 | +2.322 |
Neg logit contributions | |
disproportion | -2.959 |
Penet | -2.226 |
disadvant | -2.173 |
Valkyrie | -2.170 |
Carmen | -2.041 |
Token | it |
Token ID | 340 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
antha | +1.531 |
iversal | +1.333 |
arov | +1.322 |
unction | +1.319 |
66666666 | +1.270 |
Neg logit contributions | |
disproportion | -1.441 |
Penet | -1.059 |
Valkyrie | -1.025 |
disadvant | -1.021 |
Carmen | -0.962 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
disproportion | +0.945 |
Penet | +0.684 |
Valkyrie | +0.655 |
disadvant | +0.649 |
Carmen | +0.614 |
Neg logit contributions | |
antha | -1.082 |
iversal | -0.951 |
arov | -0.943 |
unction | -0.932 |
66666666 | -0.906 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
disproportion | +0.141 |
Penet | +0.104 |
Valkyrie | +0.101 |
disadvant | +0.101 |
Carmen | +0.095 |
Neg logit contributions | |
antha | -0.144 |
iversal | -0.125 |
arov | -0.124 |
unction | -0.124 |
66666666 | -0.119 |
Token | which |
Token ID | 543 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
antha | +1.480 |
iversal | +1.284 |
arov | +1.280 |
unction | +1.276 |
66666666 | +1.229 |
Neg logit contributions | |
disproportion | -1.346 |
Penet | -0.981 |
Valkyrie | -0.948 |
disadvant | -0.946 |
Carmen | -0.883 |
Token | was |
Token ID | 373 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
antha | +0.433 |
iversal | +0.375 |
arov | +0.375 |
unction | +0.372 |
66666666 | +0.360 |
Neg logit contributions | |
disproportion | -0.397 |
Penet | -0.291 |
Valkyrie | -0.281 |
disadvant | -0.280 |
Carmen | -0.262 |
Token | built |
Token ID | 3170 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
antha | +1.452 |
arov | +1.260 |
unction | +1.249 |
iversal | +1.246 |
66666666 | +1.202 |
Neg logit contributions | |
disproportion | -1.311 |
Penet | -0.967 |
Valkyrie | -0.929 |
disadvant | -0.921 |
Carmen | -0.861 |
Token | on |
Token ID | 319 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
antha | +0.437 |
iversal | +0.377 |
arov | +0.374 |
unction | +0.373 |
66666666 | +0.358 |
Neg logit contributions | |
disproportion | -0.463 |
Penet | -0.348 |
Valkyrie | -0.337 |
disadvant | -0.336 |
Carmen | -0.318 |
Token | farmland |
Token ID | 45723 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
antha | +0.764 |
iversal | +0.666 |
arov | +0.662 |
unction | +0.661 |
66666666 | +0.637 |
Neg logit contributions | |
disproportion | -0.689 |
Penet | -0.502 |
Valkyrie | -0.484 |
disadvant | -0.484 |
Carmen | -0.453 |
Token | owned |
Token ID | 6898 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
antha | +6.535 |
arov | +5.626 |
iversal | +5.586 |
unction | +5.501 |
66666666 | +5.396 |
Neg logit contributions | |
disproportion | -6.857 |
Penet | -5.215 |
Valkyrie | -5.028 |
disadvant | -4.962 |
Carmen | -4.619 |
Token | by |
Token ID | 416 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
antha | +2.886 |
iversal | +2.441 |
arov | +2.420 |
unction | +2.410 |
66666666 | +2.297 |
Neg logit contributions | |
disproportion | -3.865 |
Penet | -2.992 |
Valkyrie | -2.917 |
disadvant | -2.903 |
Carmen | -2.777 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
antha | +0.994 |
iversal | +0.860 |
arov | +0.856 |
unction | +0.853 |
66666666 | +0.824 |
Neg logit contributions | |
disproportion | -0.943 |
Penet | -0.691 |
disadvant | -0.670 |
Valkyrie | -0.668 |
Carmen | -0.624 |
Token | Sherman |
Token ID | 23198 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
antha | +0.153 |
iversal | +0.132 |
arov | +0.132 |
unction | +0.131 |
66666666 | +0.127 |
Neg logit contributions | |
disproportion | -0.150 |
Penet | -0.111 |
disadvant | -0.107 |
Valkyrie | -0.107 |
Carmen | -0.101 |
Token | family |
Token ID | 1641 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
antha | +1.736 |
iversal | +1.504 |
arov | +1.504 |
unction | +1.492 |
66666666 | +1.449 |
Neg logit contributions | |
disproportion | -1.541 |
Penet | -1.114 |
disadvant | -1.075 |
Valkyrie | -1.074 |
scapego | -1.002 |
Token | dwellings |
Token ID | 50078 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
disproportion | +2.137 |
Penet | +1.569 |
Valkyrie | +1.528 |
disadvant | +1.518 |
Carmen | +1.435 |
Neg logit contributions | |
antha | -2.212 |
iversal | -1.931 |
unction | -1.908 |
arov | -1.902 |
atomic | -1.814 |
Token | . |
Token ID | 13 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
antha | +0.623 |
iversal | +0.541 |
arov | +0.539 |
unction | +0.537 |
66666666 | +0.517 |
Neg logit contributions | |
disproportion | -0.592 |
Penet | -0.438 |
Valkyrie | -0.424 |
disadvant | -0.421 |
Carmen | -0.397 |
Token | If |
Token ID | 1002 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
disproportion | +0.696 |
Penet | +0.517 |
disadvant | +0.503 |
Valkyrie | +0.502 |
Carmen | +0.472 |
Neg logit contributions | |
antha | -0.673 |
iversal | -0.581 |
arov | -0.577 |
unction | -0.575 |
66666666 | -0.555 |
Token | there |
Token ID | 612 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
antha | +0.741 |
iversal | +0.644 |
arov | +0.641 |
unction | +0.638 |
66666666 | +0.617 |
Neg logit contributions | |
disproportion | -0.676 |
Penet | -0.495 |
Valkyrie | -0.478 |
disadvant | -0.476 |
Carmen | -0.445 |
Token | is |
Token ID | 318 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
antha | +0.680 |
iversal | +0.587 |
arov | +0.583 |
unction | +0.581 |
66666666 | +0.558 |
Neg logit contributions | |
disproportion | -0.691 |
Penet | -0.517 |
Valkyrie | -0.503 |
disadvant | -0.500 |
Carmen | -0.473 |
Token | enough |
Token ID | 1576 |
Feature activation | +7.48e+00 |
Pos logit contributions | |
antha | +1.805 |
arov | +1.578 |
iversal | +1.567 |
unction | +1.563 |
66666666 | +1.502 |
Neg logit contributions | |
disproportion | -1.582 |
Penet | -1.175 |
Valkyrie | -1.137 |
disadvant | -1.111 |
Carmen | -1.050 |
Token | of |
Token ID | 286 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
antha | +6.528 |
arov | +5.785 |
unction | +5.539 |
iversal | +5.475 |
66666666 | +5.426 |
Neg logit contributions | |
disproportion | -6.403 |
Penet | -4.968 |
Valkyrie | -4.688 |
disadvant | -4.672 |
Recomm | -4.398 |
Token | a |
Token ID | 257 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
antha | +0.782 |
iversal | +0.685 |
arov | +0.681 |
unction | +0.680 |
66666666 | +0.654 |
Neg logit contributions | |
disproportion | -0.687 |
Penet | -0.499 |
Valkyrie | -0.482 |
disadvant | -0.479 |
Carmen | -0.448 |
Token | herd |
Token ID | 27638 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
disproportion | +0.529 |
Penet | +0.395 |
Valkyrie | +0.380 |
disadvant | +0.378 |
Carmen | +0.356 |
Neg logit contributions | |
antha | -0.566 |
arov | -0.493 |
iversal | -0.492 |
unction | -0.488 |
66666666 | -0.470 |
Token | approach |
Token ID | 3164 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
antha | +1.722 |
arov | +1.532 |
unction | +1.520 |
iversal | +1.513 |
66666666 | +1.454 |
Neg logit contributions | |
disproportion | -1.442 |
Penet | -1.050 |
Valkyrie | -1.015 |
disadvant | -1.002 |
Carmen | -0.932 |
Token | to |
Token ID | 284 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
antha | +0.559 |
iversal | +0.484 |
arov | +0.482 |
unction | +0.481 |
66666666 | +0.462 |
Neg logit contributions | |
disproportion | -0.545 |
Penet | -0.404 |
Valkyrie | -0.392 |
disadvant | -0.388 |
Carmen | -0.366 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
antha | +0.617 |
iversal | +0.537 |
arov | +0.532 |
unction | +0.531 |
66666666 | +0.512 |
Neg logit contributions | |
disproportion | -0.583 |
Penet | -0.429 |
Valkyrie | -0.417 |
disadvant | -0.414 |
Carmen | -0.391 |
Token | Still |
Token ID | 7831 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
antha | +1.107 |
arov | +0.953 |
iversal | +0.946 |
unction | +0.942 |
66666666 | +0.921 |
Neg logit contributions | |
disproportion | -1.151 |
Penet | -0.836 |
disadvant | -0.834 |
Valkyrie | -0.816 |
scapego | -0.776 |
Token | though |
Token ID | 996 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
antha | +1.890 |
iversal | +1.655 |
arov | +1.643 |
unction | +1.639 |
66666666 | +1.581 |
Neg logit contributions | |
disproportion | -1.642 |
Penet | -1.188 |
Valkyrie | -1.148 |
disadvant | -1.141 |
Carmen | -1.072 |
Token | , |
Token ID | 11 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
disproportion | +1.120 |
Penet | +0.800 |
disadvant | +0.770 |
Valkyrie | +0.769 |
Carmen | +0.717 |
Neg logit contributions | |
antha | -1.405 |
iversal | -1.236 |
arov | -1.224 |
unction | -1.220 |
66666666 | -1.178 |
Token | with |
Token ID | 351 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
disproportion | +0.183 |
Penet | +0.134 |
Valkyrie | +0.130 |
disadvant | +0.129 |
Carmen | +0.122 |
Neg logit contributions | |
antha | -0.198 |
iversal | -0.173 |
arov | -0.172 |
unction | -0.171 |
66666666 | -0.165 |
Token | enough |
Token ID | 1576 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
antha | +0.076 |
iversal | +0.067 |
arov | +0.066 |
unction | +0.066 |
66666666 | +0.064 |
Neg logit contributions | |
disproportion | -0.068 |
Penet | -0.049 |
Valkyrie | -0.048 |
disadvant | -0.047 |
Carmen | -0.045 |
Token | property |
Token ID | 3119 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
antha | +6.673 |
arov | +5.853 |
unction | +5.742 |
iversal | +5.683 |
66666666 | +5.645 |
Neg logit contributions | |
disproportion | -6.511 |
Penet | -4.826 |
disadvant | -4.701 |
Valkyrie | -4.653 |
Carmen | -4.455 |
Token | , |
Token ID | 11 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
antha | +4.302 |
arov | +3.714 |
iversal | +3.685 |
unction | +3.659 |
66666666 | +3.533 |
Neg logit contributions | |
disproportion | -4.545 |
Penet | -3.388 |
Valkyrie | -3.337 |
disadvant | -3.309 |
Carmen | -3.146 |
Token | one |
Token ID | 530 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
antha | +0.948 |
iversal | +0.825 |
arov | +0.820 |
unction | +0.817 |
66666666 | +0.788 |
Neg logit contributions | |
disproportion | -0.885 |
Penet | -0.649 |
Valkyrie | -0.629 |
disadvant | -0.626 |
Carmen | -0.590 |
Token | can |
Token ID | 460 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
antha | +2.322 |
iversal | +1.967 |
arov | +1.966 |
unction | +1.949 |
66666666 | +1.882 |
Neg logit contributions | |
disproportion | -2.793 |
Penet | -2.146 |
Valkyrie | -2.084 |
disadvant | -2.070 |
Carmen | -1.976 |
Token | let |
Token ID | 1309 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
antha | +0.164 |
iversal | +0.142 |
arov | +0.142 |
unction | +0.140 |
66666666 | +0.136 |
Neg logit contributions | |
disproportion | -0.165 |
Penet | -0.123 |
Valkyrie | -0.119 |
disadvant | -0.119 |
Carmen | -0.112 |
Token | urally |
Token ID | 20221 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
antha | +3.056 |
iversal | +2.686 |
arov | +2.681 |
unction | +2.677 |
66666666 | +2.569 |
Neg logit contributions | |
disproportion | -2.872 |
Penet | -2.094 |
disadvant | -2.071 |
Valkyrie | -2.018 |
scapego | -1.900 |
Token | generated |
Token ID | 7560 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
antha | +0.421 |
iversal | +0.367 |
arov | +0.364 |
unction | +0.363 |
66666666 | +0.350 |
Neg logit contributions | |
disproportion | -0.396 |
Penet | -0.290 |
Valkyrie | -0.281 |
disadvant | -0.280 |
Carmen | -0.264 |
Token | universe |
Token ID | 6881 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
antha | +0.814 |
iversal | +0.701 |
arov | +0.696 |
unction | +0.692 |
66666666 | +0.667 |
Neg logit contributions | |
disproportion | -0.857 |
Penet | -0.642 |
disadvant | -0.622 |
Valkyrie | -0.622 |
Carmen | -0.585 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
antha | +1.121 |
iversal | +0.973 |
arov | +0.963 |
unction | +0.961 |
66666666 | +0.925 |
Neg logit contributions | |
disproportion | -1.115 |
Penet | -0.828 |
Valkyrie | -0.800 |
disadvant | -0.799 |
Carmen | -0.753 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
antha | +1.316 |
arov | +1.140 |
unction | +1.121 |
iversal | +1.112 |
66666666 | +1.099 |
Neg logit contributions | |
disproportion | -1.607 |
disadvant | -1.225 |
Penet | -1.192 |
Valkyrie | -1.162 |
scapego | -1.110 |
Token | Col |
Token ID | 5216 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
antha | +1.065 |
iversal | +0.895 |
arov | +0.891 |
unction | +0.886 |
66666666 | +0.847 |
Neg logit contributions | |
disproportion | -1.505 |
Penet | -1.164 |
disadvant | -1.141 |
Valkyrie | -1.132 |
Carmen | -1.082 |
Token | on |
Token ID | 261 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
antha | +5.480 |
iversal | +4.713 |
unction | +4.630 |
arov | +4.546 |
atomic | +4.315 |
Neg logit contributions | |
disproportion | -8.014 |
Penet | -6.325 |
disadvant | -6.219 |
Valkyrie | -6.153 |
scapego | -5.906 |
Token | ize |
Token ID | 1096 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
disproportion | +0.301 |
Penet | +0.190 |
Valkyrie | +0.180 |
disadvant | +0.179 |
Carmen | +0.162 |
Neg logit contributions | |
antha | -0.561 |
iversal | -0.504 |
arov | -0.501 |
unction | -0.500 |
66666666 | -0.486 |
Token | unch |
Token ID | 16258 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
disproportion | +0.427 |
Penet | +0.314 |
Valkyrie | +0.305 |
disadvant | +0.302 |
Carmen | +0.286 |
Neg logit contributions | |
antha | -0.454 |
iversal | -0.395 |
arov | -0.393 |
unction | -0.392 |
66666666 | -0.377 |
Token | arted |
Token ID | 19112 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
disproportion | +0.242 |
Penet | +0.158 |
Valkyrie | +0.151 |
disadvant | +0.148 |
Carmen | +0.138 |
Neg logit contributions | |
antha | -0.406 |
iversal | -0.362 |
arov | -0.361 |
unction | -0.360 |
66666666 | -0.351 |
Token | planets |
Token ID | 14705 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
antha | +0.194 |
iversal | +0.165 |
arov | +0.164 |
unction | +0.163 |
66666666 | +0.156 |
Neg logit contributions | |
disproportion | -0.236 |
Penet | -0.180 |
Valkyrie | -0.175 |
disadvant | -0.175 |
Carmen | -0.166 |
Token | neuro |
Token ID | 7669 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
disproportion | +0.300 |
Penet | +0.218 |
Valkyrie | +0.210 |
disadvant | +0.210 |
Carmen | +0.196 |
Neg logit contributions | |
antha | -0.340 |
iversal | -0.296 |
arov | -0.295 |
unction | -0.295 |
66666666 | -0.284 |
Token | sur |
Token ID | 11793 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
antha | +1.277 |
iversal | +1.012 |
arov | +0.997 |
unction | +0.995 |
atomic | +0.925 |
Neg logit contributions | |
disproportion | -2.699 |
Penet | -2.190 |
Valkyrie | -2.150 |
disadvant | -2.146 |
Carmen | -2.051 |
Token | geon |
Token ID | 6281 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
disproportion | +0.305 |
Penet | +0.239 |
Valkyrie | +0.233 |
disadvant | +0.231 |
Carmen | +0.223 |
Neg logit contributions | |
antha | -0.209 |
iversal | -0.174 |
arov | -0.173 |
unction | -0.172 |
66666666 | -0.166 |
Token | specializing |
Token ID | 40847 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
disproportion | +0.005 |
Penet | +0.003 |
Valkyrie | +0.003 |
disadvant | +0.003 |
Carmen | +0.003 |
Neg logit contributions | |
antha | -0.005 |
iversal | -0.004 |
arov | -0.004 |
unction | -0.004 |
66666666 | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
antha | +0.073 |
iversal | +0.062 |
arov | +0.062 |
unction | +0.061 |
66666666 | +0.059 |
Neg logit contributions | |
disproportion | -0.076 |
Penet | -0.057 |
Valkyrie | -0.055 |
disadvant | -0.054 |
Carmen | -0.052 |
Token | epilepsy |
Token ID | 35325 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
antha | +2.687 |
unction | +2.341 |
iversal | +2.337 |
arov | +2.317 |
66666666 | +2.227 |
Neg logit contributions | |
disproportion | -2.408 |
Penet | -1.753 |
disadvant | -1.716 |
Valkyrie | -1.702 |
Carmen | -1.584 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
antha | +6.513 |
iversal | +5.707 |
arov | +5.672 |
unction | +5.592 |
atomic | +5.385 |
Neg logit contributions | |
disproportion | -6.680 |
Penet | -4.923 |
Valkyrie | -4.841 |
disadvant | -4.818 |
Carmen | -4.474 |
Token | Chang |
Token ID | 22597 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
antha | +1.794 |
iversal | +1.575 |
arov | +1.564 |
unction | +1.560 |
66666666 | +1.509 |
Neg logit contributions | |
disproportion | -1.460 |
Penet | -1.036 |
Valkyrie | -1.001 |
disadvant | -0.998 |
Carmen | -0.925 |
Token | already |
Token ID | 1541 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
disproportion | +1.053 |
Penet | +0.776 |
Valkyrie | +0.751 |
disadvant | +0.746 |
Carmen | +0.707 |
Neg logit contributions | |
antha | -1.105 |
iversal | -0.962 |
arov | -0.952 |
unction | -0.951 |
66666666 | -0.915 |
Token | has |
Token ID | 468 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
disproportion | +0.506 |
Penet | +0.363 |
Valkyrie | +0.350 |
disadvant | +0.349 |
Carmen | +0.326 |
Neg logit contributions | |
antha | -0.616 |
iversal | -0.540 |
arov | -0.538 |
unction | -0.535 |
66666666 | -0.518 |
Token | access |
Token ID | 1895 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
disproportion | +1.092 |
Penet | +0.797 |
Valkyrie | +0.771 |
disadvant | +0.767 |
Carmen | +0.722 |
Neg logit contributions | |
antha | -1.200 |
iversal | -1.047 |
arov | -1.040 |
unction | -1.037 |
66666666 | -0.999 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
antha | +3.506 |
iversal | +3.045 |
unction | +3.005 |
arov | +2.979 |
66666666 | +2.918 |
Neg logit contributions | |
disproportion | -3.489 |
Penet | -2.570 |
disadvant | -2.510 |
Valkyrie | -2.477 |
scapego | -2.356 |
Token | giving |
Token ID | 3501 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
antha | +1.205 |
iversal | +1.048 |
arov | +1.041 |
unction | +1.037 |
66666666 | +1.000 |
Neg logit contributions | |
disproportion | -1.135 |
Penet | -0.834 |
Valkyrie | -0.806 |
disadvant | -0.804 |
Carmen | -0.758 |
Token | 43 |
Token ID | 5946 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
antha | +0.090 |
iversal | +0.079 |
arov | +0.078 |
unction | +0.078 |
66666666 | +0.075 |
Neg logit contributions | |
disproportion | -0.083 |
Penet | -0.061 |
Valkyrie | -0.059 |
disadvant | -0.058 |
Carmen | -0.055 |
Token | % |
Token ID | 4 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
antha | +1.512 |
iversal | +1.292 |
unction | +1.283 |
arov | +1.283 |
66666666 | +1.231 |
Neg logit contributions | |
disproportion | -1.733 |
Penet | -1.314 |
disadvant | -1.278 |
Valkyrie | -1.273 |
Carmen | -1.212 |
Token | more |
Token ID | 517 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
antha | +0.283 |
iversal | +0.249 |
arov | +0.247 |
unction | +0.246 |
66666666 | +0.238 |
Neg logit contributions | |
disproportion | -0.232 |
Penet | -0.166 |
Valkyrie | -0.160 |
disadvant | -0.159 |
Carmen | -0.149 |
Token | bandwidth |
Token ID | 19484 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
antha | +3.205 |
iversal | +2.676 |
arov | +2.666 |
unction | +2.651 |
atomic | +2.526 |
Neg logit contributions | |
disproportion | -4.491 |
Penet | -3.493 |
disadvant | -3.465 |
Valkyrie | -3.397 |
Carmen | -3.285 |
Token | than |
Token ID | 621 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
antha | +6.321 |
iversal | +5.433 |
unction | +5.425 |
arov | +5.389 |
66666666 | +5.201 |
Neg logit contributions | |
disproportion | -6.755 |
Penet | -5.046 |
disadvant | -4.988 |
Valkyrie | -4.916 |
Carmen | -4.727 |
Token | the |
Token ID | 262 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
antha | +1.304 |
iversal | +1.128 |
arov | +1.120 |
unction | +1.117 |
66666666 | +1.076 |
Neg logit contributions | |
disproportion | -1.320 |
Penet | -0.981 |
Valkyrie | -0.950 |
disadvant | -0.949 |
Carmen | -0.897 |
Token | GTX |
Token ID | 12646 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
antha | +0.446 |
iversal | +0.387 |
arov | +0.384 |
unction | +0.382 |
66666666 | +0.368 |
Neg logit contributions | |
disproportion | -0.450 |
Penet | -0.334 |
Valkyrie | -0.324 |
disadvant | -0.323 |
Carmen | -0.305 |
Token | 980 |
Token ID | 40022 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
antha | +0.399 |
iversal | +0.333 |
arov | +0.329 |
unction | +0.328 |
66666666 | +0.311 |
Neg logit contributions | |
disproportion | -0.598 |
Penet | -0.470 |
Valkyrie | -0.460 |
disadvant | -0.457 |
Carmen | -0.437 |
Token | GPU |
Token ID | 11362 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
antha | +0.142 |
iversal | +0.124 |
arov | +0.123 |
unction | +0.122 |
66666666 | +0.118 |
Neg logit contributions | |
disproportion | -0.139 |
Penet | -0.103 |
Valkyrie | -0.099 |
disadvant | -0.099 |
Carmen | -0.093 |
Token | usion |
Token ID | 4241 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
disproportion | +1.236 |
Penet | +0.943 |
Valkyrie | +0.918 |
disadvant | +0.908 |
Carmen | +0.868 |
Neg logit contributions | |
antha | -1.062 |
iversal | -0.907 |
arov | -0.899 |
unction | -0.892 |
66666666 | -0.862 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
antha | +1.181 |
iversal | +1.021 |
arov | +1.014 |
unction | +1.012 |
66666666 | +0.972 |
Neg logit contributions | |
disproportion | -1.214 |
Penet | -0.902 |
Valkyrie | -0.877 |
disadvant | -0.875 |
Carmen | -0.827 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
disproportion | +0.393 |
Penet | +0.294 |
disadvant | +0.288 |
Valkyrie | +0.285 |
Carmen | +0.269 |
Neg logit contributions | |
antha | -0.363 |
iversal | -0.312 |
arov | -0.312 |
unction | -0.310 |
66666666 | -0.299 |
Token | With |
Token ID | 3152 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
disproportion | +0.177 |
Penet | +0.138 |
Valkyrie | +0.134 |
disadvant | +0.134 |
Carmen | +0.128 |
Neg logit contributions | |
antha | -0.127 |
iversal | -0.107 |
arov | -0.106 |
unction | -0.105 |
66666666 | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
antha | +0.739 |
iversal | +0.645 |
arov | +0.642 |
unction | +0.640 |
66666666 | +0.616 |
Neg logit contributions | |
disproportion | -0.655 |
Penet | -0.473 |
disadvant | -0.460 |
Valkyrie | -0.458 |
Carmen | -0.429 |
Token | shader |
Token ID | 33030 |
Feature activation | +7.22e+00 |
Pos logit contributions | |
antha | +1.664 |
arov | +1.453 |
iversal | +1.450 |
unction | +1.446 |
66666666 | +1.397 |
Neg logit contributions | |
disproportion | -1.512 |
Penet | -1.093 |
disadvant | -1.064 |
Valkyrie | -1.057 |
Carmen | -1.002 |
Token | now |
Token ID | 783 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
antha | +6.661 |
unction | +5.798 |
arov | +5.780 |
iversal | +5.712 |
atomic | +5.615 |
Neg logit contributions | |
disproportion | -6.286 |
disadvant | -4.548 |
Penet | -4.531 |
Valkyrie | -4.457 |
scapego | -4.198 |
Token | expanded |
Token ID | 9902 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
antha | +3.524 |
arov | +3.067 |
unction | +3.050 |
iversal | +3.040 |
66666666 | +2.938 |
Neg logit contributions | |
disproportion | -3.403 |
Penet | -2.482 |
disadvant | -2.454 |
Valkyrie | -2.413 |
Carmen | -2.287 |
Token | , |
Token ID | 11 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
antha | +4.005 |
iversal | +3.514 |
arov | +3.452 |
unction | +3.446 |
66666666 | +3.300 |
Neg logit contributions | |
disproportion | -4.041 |
Penet | -2.977 |
disadvant | -2.935 |
Valkyrie | -2.889 |
Carmen | -2.736 |
Token | we |
Token ID | 356 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
antha | +0.442 |
iversal | +0.386 |
arov | +0.383 |
unction | +0.382 |
66666666 | +0.368 |
Neg logit contributions | |
disproportion | -0.401 |
Penet | -0.293 |
Valkyrie | -0.283 |
disadvant | -0.282 |
Carmen | -0.265 |
Token | can |
Token ID | 460 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
antha | +0.425 |
iversal | +0.364 |
arov | +0.363 |
unction | +0.359 |
66666666 | +0.345 |
Neg logit contributions | |
disproportion | -0.508 |
Penet | -0.389 |
disadvant | -0.380 |
Valkyrie | -0.380 |
Carmen | -0.359 |
Token | THE |
Token ID | 10970 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
antha | +1.074 |
iversal | +0.897 |
arov | +0.888 |
unction | +0.885 |
66666666 | +0.842 |
Neg logit contributions | |
disproportion | -1.595 |
Penet | -1.251 |
Valkyrie | -1.220 |
disadvant | -1.216 |
Carmen | -1.163 |
Token | G |
Token ID | 402 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
antha | +3.079 |
iversal | +2.690 |
arov | +2.637 |
unction | +2.621 |
66666666 | +2.551 |
Neg logit contributions | |
disproportion | -3.078 |
Penet | -2.270 |
disadvant | -2.209 |
Valkyrie | -2.198 |
Carmen | -2.066 |
Token | EEK |
Token ID | 33823 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
antha | +0.405 |
iversal | +0.351 |
arov | +0.348 |
unction | +0.347 |
66666666 | +0.333 |
Neg logit contributions | |
disproportion | -0.416 |
Penet | -0.311 |
Valkyrie | -0.301 |
disadvant | -0.300 |
Carmen | -0.284 |
Token | Z |
Token ID | 1168 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
antha | +1.492 |
iversal | +1.285 |
arov | +1.265 |
unction | +1.257 |
66666666 | +1.213 |
Neg logit contributions | |
disproportion | -1.773 |
Penet | -1.349 |
disadvant | -1.318 |
Valkyrie | -1.311 |
Carmen | -1.239 |
Token | OD |
Token ID | 3727 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
antha | +1.588 |
unction | +1.321 |
arov | +1.317 |
iversal | +1.317 |
66666666 | +1.278 |
Neg logit contributions | |
disproportion | -2.360 |
disadvant | -1.833 |
Penet | -1.819 |
Valkyrie | -1.781 |
scapego | -1.704 |
Token | I |
Token ID | 40 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
antha | +4.820 |
iversal | +4.049 |
arov | +4.003 |
unction | +3.988 |
66666666 | +3.934 |
Neg logit contributions | |
disproportion | -7.055 |
disadvant | -5.455 |
Penet | -5.421 |
Valkyrie | -5.315 |
Carmen | -5.067 |
Token | AC |
Token ID | 2246 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
antha | +5.200 |
unction | +4.418 |
iversal | +4.369 |
arov | +4.322 |
atomic | +4.231 |
Neg logit contributions | |
disproportion | -7.661 |
disadvant | -5.894 |
Valkyrie | -5.888 |
Penet | -5.809 |
scapego | -5.521 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
antha | +3.341 |
iversal | +2.887 |
unction | +2.845 |
arov | +2.832 |
66666666 | +2.734 |
Neg logit contributions | |
disproportion | -3.514 |
Penet | -2.627 |
disadvant | -2.577 |
Valkyrie | -2.547 |
scapego | -2.384 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
antha | +0.926 |
arov | +0.799 |
unction | +0.788 |
iversal | +0.788 |
66666666 | +0.770 |
Neg logit contributions | |
disproportion | -1.084 |
disadvant | -0.815 |
Penet | -0.808 |
Valkyrie | -0.786 |
scapego | -0.745 |
Token | T |
Token ID | 51 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
antha | +0.927 |
iversal | +0.773 |
arov | +0.766 |
unction | +0.763 |
66666666 | +0.726 |
Neg logit contributions | |
disproportion | -1.380 |
Penet | -1.083 |
Valkyrie | -1.056 |
disadvant | -1.053 |
Carmen | -1.007 |
Token | RE |
Token ID | 2200 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
antha | +2.136 |
iversal | +1.817 |
arov | +1.804 |
unction | +1.801 |
66666666 | +1.714 |
Neg logit contributions | |
disproportion | -2.591 |
Penet | -1.984 |
Valkyrie | -1.929 |
disadvant | -1.923 |
Carmen | -1.825 |
Token | our |
Token ID | 674 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
antha | +0.132 |
iversal | +0.115 |
arov | +0.114 |
unction | +0.114 |
66666666 | +0.110 |
Neg logit contributions | |
disproportion | -0.121 |
Penet | -0.088 |
Valkyrie | -0.085 |
disadvant | -0.085 |
Carmen | -0.080 |
Token | investigation |
Token ID | 3645 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
disproportion | +0.551 |
Penet | +0.414 |
Valkyrie | +0.402 |
disadvant | +0.400 |
Carmen | +0.379 |
Neg logit contributions | |
antha | -0.515 |
iversal | -0.444 |
arov | -0.441 |
unction | -0.439 |
66666666 | -0.422 |
Token | that |
Token ID | 326 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
antha | +0.783 |
iversal | +0.684 |
arov | +0.681 |
unction | +0.680 |
66666666 | +0.657 |
Neg logit contributions | |
disproportion | -0.685 |
Penet | -0.494 |
Valkyrie | -0.479 |
disadvant | -0.479 |
Carmen | -0.445 |
Token | there |
Token ID | 612 |
Feature activation | -7.55e-03 |
Pos logit contributions | |
antha | +1.469 |
iversal | +1.272 |
arov | +1.272 |
unction | +1.262 |
66666666 | +1.218 |
Neg logit contributions | |
disproportion | -1.372 |
Penet | -0.999 |
disadvant | -0.975 |
Valkyrie | -0.964 |
Carmen | -0.905 |
Token | is |
Token ID | 318 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
disproportion | +0.007 |
Penet | +0.005 |
Valkyrie | +0.005 |
disadvant | +0.005 |
Carmen | +0.005 |
Neg logit contributions | |
antha | -0.007 |
iversal | -0.006 |
arov | -0.006 |
unction | -0.006 |
66666666 | -0.006 |
Token | sufficient |
Token ID | 6751 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
antha | +0.484 |
unction | +0.422 |
arov | +0.422 |
iversal | +0.422 |
66666666 | +0.404 |
Neg logit contributions | |
disproportion | -0.427 |
Penet | -0.313 |
Valkyrie | -0.302 |
disadvant | -0.301 |
Carmen | -0.281 |
Token | evidence |
Token ID | 2370 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
antha | +5.937 |
arov | +5.169 |
unction | +5.169 |
iversal | +5.053 |
66666666 | +4.949 |
Neg logit contributions | |
disproportion | -6.447 |
Penet | -4.977 |
disadvant | -4.899 |
Valkyrie | -4.802 |
Carmen | -4.572 |
Token | to |
Token ID | 284 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
antha | +0.725 |
arov | +0.630 |
iversal | +0.629 |
unction | +0.626 |
66666666 | +0.603 |
Neg logit contributions | |
disproportion | -0.701 |
Penet | -0.514 |
Valkyrie | -0.500 |
disadvant | -0.499 |
Carmen | -0.466 |
Token | support |
Token ID | 1104 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
antha | +0.098 |
iversal | +0.086 |
arov | +0.085 |
unction | +0.085 |
66666666 | +0.081 |
Neg logit contributions | |
disproportion | -0.096 |
Penet | -0.071 |
disadvant | -0.069 |
Valkyrie | -0.069 |
Carmen | -0.064 |
Token | one |
Token ID | 530 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
disproportion | +0.602 |
Penet | +0.438 |
Valkyrie | +0.423 |
disadvant | +0.421 |
Carmen | +0.396 |
Neg logit contributions | |
antha | -0.679 |
iversal | -0.594 |
arov | -0.590 |
unction | -0.588 |
66666666 | -0.567 |
Token | of |
Token ID | 286 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
antha | +1.378 |
iversal | +1.209 |
unction | +1.204 |
arov | +1.202 |
66666666 | +1.150 |
Neg logit contributions | |
disproportion | -1.225 |
Penet | -0.894 |
disadvant | -0.860 |
Valkyrie | -0.858 |
Carmen | -0.804 |
Token | draft |
Token ID | 4538 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
antha | +0.947 |
iversal | +0.843 |
arov | +0.839 |
unction | +0.835 |
66666666 | +0.807 |
Neg logit contributions | |
disproportion | -0.607 |
Penet | -0.408 |
Valkyrie | -0.390 |
disadvant | -0.387 |
Carmen | -0.356 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
disproportion | +0.140 |
Penet | +0.101 |
Valkyrie | +0.098 |
disadvant | +0.098 |
Carmen | +0.092 |
Neg logit contributions | |
antha | -0.159 |
iversal | -0.139 |
arov | -0.138 |
unction | -0.138 |
66666666 | -0.133 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
antha | +1.092 |
iversal | +0.941 |
arov | +0.941 |
unction | +0.933 |
66666666 | +0.899 |
Neg logit contributions | |
disproportion | -1.156 |
Penet | -0.863 |
disadvant | -0.842 |
Valkyrie | -0.836 |
Carmen | -0.785 |
Token | ( |
Token ID | 357 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
antha | +0.938 |
iversal | +0.821 |
arov | +0.813 |
unction | +0.812 |
66666666 | +0.784 |
Neg logit contributions | |
disproportion | -0.814 |
Penet | -0.589 |
Valkyrie | -0.569 |
disadvant | -0.565 |
Carmen | -0.531 |
Token | W |
Token ID | 54 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
antha | +1.551 |
iversal | +1.286 |
arov | +1.282 |
unction | +1.269 |
66666666 | +1.212 |
Neg logit contributions | |
disproportion | -2.308 |
Penet | -1.811 |
Valkyrie | -1.763 |
disadvant | -1.760 |
Carmen | -1.681 |
Token | HL |
Token ID | 6581 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
disproportion | +0.123 |
Penet | +0.096 |
Valkyrie | +0.094 |
disadvant | +0.093 |
Carmen | +0.089 |
Neg logit contributions | |
antha | -0.090 |
iversal | -0.076 |
arov | -0.075 |
unction | -0.075 |
66666666 | -0.071 |
Token | teams |
Token ID | 3466 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
antha | +6.599 |
arov | +5.773 |
iversal | +5.710 |
unction | +5.538 |
66666666 | +5.426 |
Neg logit contributions | |
disproportion | -6.166 |
Penet | -4.462 |
disadvant | -4.286 |
Valkyrie | -4.269 |
Carmen | -4.071 |
Token | are |
Token ID | 389 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
antha | +0.375 |
iversal | +0.327 |
arov | +0.326 |
unction | +0.322 |
66666666 | +0.311 |
Neg logit contributions | |
disproportion | -0.340 |
Penet | -0.248 |
Valkyrie | -0.240 |
disadvant | -0.239 |
Carmen | -0.224 |
Token | allowed |
Token ID | 3142 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
antha | +0.684 |
arov | +0.595 |
iversal | +0.593 |
unction | +0.585 |
66666666 | +0.566 |
Neg logit contributions | |
disproportion | -0.625 |
Penet | -0.461 |
Valkyrie | -0.445 |
disadvant | -0.441 |
Carmen | -0.414 |
Token | to |
Token ID | 284 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
antha | +1.580 |
iversal | +1.375 |
arov | +1.372 |
unction | +1.358 |
66666666 | +1.311 |
Neg logit contributions | |
disproportion | -1.495 |
Penet | -1.098 |
Valkyrie | -1.069 |
disadvant | -1.063 |
Carmen | -0.998 |
Token | have |
Token ID | 423 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
antha | +0.048 |
arov | +0.043 |
iversal | +0.042 |
unction | +0.042 |
66666666 | +0.041 |
Neg logit contributions | |
disproportion | -0.039 |
Penet | -0.027 |
Valkyrie | -0.027 |
disadvant | -0.027 |
Carmen | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
antha | +0.127 |
iversal | +0.110 |
arov | +0.109 |
unction | +0.109 |
66666666 | +0.105 |
Neg logit contributions | |
disproportion | -0.122 |
Penet | -0.090 |
Valkyrie | -0.087 |
disadvant | -0.086 |
Carmen | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
antha | +0.601 |
iversal | +0.524 |
arov | +0.521 |
unction | +0.519 |
66666666 | +0.500 |
Neg logit contributions | |
disproportion | -0.549 |
Penet | -0.400 |
Valkyrie | -0.387 |
disadvant | -0.386 |
Carmen | -0.362 |
Token | party |
Token ID | 2151 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
disproportion | +0.417 |
Penet | +0.306 |
Valkyrie | +0.295 |
disadvant | +0.294 |
Carmen | +0.277 |
Neg logit contributions | |
antha | -0.447 |
iversal | -0.388 |
arov | -0.386 |
unction | -0.385 |
66666666 | -0.371 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
antha | +0.190 |
iversal | +0.165 |
arov | +0.164 |
unction | +0.164 |
66666666 | +0.157 |
Neg logit contributions | |
disproportion | -0.174 |
Penet | -0.127 |
disadvant | -0.122 |
Valkyrie | -0.122 |
Carmen | -0.115 |
Token | But |
Token ID | 887 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
antha | +0.276 |
arov | +0.238 |
iversal | +0.236 |
unction | +0.235 |
66666666 | +0.229 |
Neg logit contributions | |
disproportion | -0.290 |
Penet | -0.212 |
disadvant | -0.210 |
Valkyrie | -0.205 |
scapego | -0.196 |
Token | then |
Token ID | 788 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
antha | +0.741 |
iversal | +0.640 |
arov | +0.640 |
unction | +0.634 |
66666666 | +0.616 |
Neg logit contributions | |
disproportion | -0.698 |
Penet | -0.510 |
disadvant | -0.494 |
Valkyrie | -0.493 |
Carmen | -0.462 |
Token | we |
Token ID | 356 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
antha | +5.882 |
arov | +4.913 |
iversal | +4.884 |
unction | +4.866 |
66666666 | +4.759 |
Neg logit contributions | |
disproportion | -6.699 |
disadvant | -4.961 |
Penet | -4.918 |
Valkyrie | -4.743 |
scapego | -4.558 |
Token | hit |
Token ID | 2277 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
antha | +0.311 |
arov | +0.270 |
iversal | +0.269 |
unction | +0.265 |
66666666 | +0.257 |
Neg logit contributions | |
disproportion | -0.319 |
Penet | -0.241 |
disadvant | -0.234 |
Valkyrie | -0.233 |
Carmen | -0.218 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
disproportion | +0.181 |
Penet | +0.131 |
Valkyrie | +0.127 |
disadvant | +0.126 |
Carmen | +0.119 |
Neg logit contributions | |
antha | -0.205 |
iversal | -0.179 |
arov | -0.178 |
unction | -0.177 |
66666666 | -0.171 |
Token | opposite |
Token ID | 6697 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
antha | +1.124 |
iversal | +0.977 |
arov | +0.977 |
unction | +0.972 |
66666666 | +0.940 |
Neg logit contributions | |
disproportion | -0.986 |
Penet | -0.714 |
Valkyrie | -0.692 |
disadvant | -0.689 |
Carmen | -0.649 |
Token | problem |
Token ID | 1917 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
disproportion | +2.633 |
Penet | +1.891 |
Valkyrie | +1.830 |
disadvant | +1.819 |
Carmen | +1.711 |
Neg logit contributions | |
antha | -3.013 |
iversal | -2.651 |
arov | -2.614 |
unction | -2.606 |
66666666 | -2.521 |
Token | 2 |
Token ID | 17 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
antha | +2.452 |
iversal | +2.052 |
arov | +2.019 |
unction | +1.998 |
66666666 | +1.929 |
Neg logit contributions | |
disproportion | -3.738 |
Penet | -2.935 |
disadvant | -2.858 |
Valkyrie | -2.842 |
Carmen | -2.741 |
Token | FACE |
Token ID | 49836 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
disproportion | +0.007 |
Penet | +0.005 |
Valkyrie | +0.005 |
disadvant | +0.005 |
Carmen | +0.005 |
Neg logit contributions | |
antha | -0.006 |
iversal | -0.005 |
arov | -0.005 |
unction | -0.005 |
66666666 | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
antha | +3.629 |
iversal | +3.091 |
arov | +3.061 |
unction | +3.053 |
66666666 | +2.947 |
Neg logit contributions | |
disproportion | -4.638 |
Penet | -3.568 |
disadvant | -3.498 |
Valkyrie | -3.446 |
Carmen | -3.309 |
Token | Lions |
Token ID | 14536 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
disproportion | +0.283 |
Penet | +0.207 |
Valkyrie | +0.200 |
disadvant | +0.200 |
Carmen | +0.188 |
Neg logit contributions | |
antha | -0.304 |
iversal | -0.265 |
arov | -0.263 |
unction | -0.262 |
66666666 | -0.253 |
Token | shaking |
Token ID | 17275 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
disproportion | +1.817 |
Penet | +1.387 |
Valkyrie | +1.352 |
disadvant | +1.330 |
Carmen | +1.268 |
Neg logit contributions | |
antha | -1.585 |
iversal | -1.360 |
arov | -1.334 |
unction | -1.331 |
66666666 | -1.285 |
Token | hands |
Token ID | 2832 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
antha | +2.092 |
iversal | +1.785 |
arov | +1.781 |
unction | +1.758 |
66666666 | +1.699 |
Neg logit contributions | |
disproportion | -2.430 |
Penet | -1.847 |
disadvant | -1.809 |
Valkyrie | -1.784 |
Carmen | -1.695 |
Token |
|
Token ID | 198 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
antha | +5.797 |
iversal | +4.922 |
unction | +4.922 |
arov | +4.882 |
66666666 | +4.706 |
Neg logit contributions | |
disproportion | -6.543 |
Penet | -4.945 |
disadvant | -4.905 |
Valkyrie | -4.806 |
scapego | -4.530 |
Token |
|
Token ID | 198 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
antha | +0.365 |
arov | +0.315 |
iversal | +0.311 |
unction | +0.311 |
66666666 | +0.303 |
Neg logit contributions | |
disproportion | -0.418 |
disadvant | -0.312 |
Penet | -0.311 |
Valkyrie | -0.303 |
scapego | -0.286 |
Token | In |
Token ID | 818 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
disproportion | +0.102 |
Penet | +0.079 |
Valkyrie | +0.077 |
disadvant | +0.077 |
Carmen | +0.074 |
Neg logit contributions | |
antha | -0.073 |
iversal | -0.062 |
arov | -0.061 |
unction | -0.061 |
66666666 | -0.058 |
Token | sports |
Token ID | 5701 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
disproportion | +0.596 |
Penet | +0.435 |
Valkyrie | +0.421 |
disadvant | +0.418 |
Carmen | +0.394 |
Neg logit contributions | |
antha | -0.658 |
iversal | -0.575 |
arov | -0.571 |
unction | -0.569 |
66666666 | -0.549 |
Token | referees |
Token ID | 42692 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
antha | +3.026 |
iversal | +2.622 |
arov | +2.610 |
unction | +2.594 |
atomic | +2.488 |
Neg logit contributions | |
disproportion | -2.870 |
Penet | -2.132 |
disadvant | -2.056 |
Valkyrie | -2.054 |
Carmen | -1.901 |
Token | , |
Token ID | 11 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
disproportion | +1.898 |
Penet | +1.338 |
disadvant | +1.295 |
Valkyrie | +1.293 |
Carmen | +1.223 |
Neg logit contributions | |
antha | -2.378 |
iversal | -2.099 |
arov | -2.083 |
unction | -2.082 |
66666666 | -2.001 |
Token | it |
Token ID | 340 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
antha | +0.712 |
iversal | +0.622 |
arov | +0.618 |
unction | +0.615 |
66666666 | +0.595 |
Neg logit contributions | |
disproportion | -0.639 |
Penet | -0.466 |
Valkyrie | -0.452 |
disadvant | -0.447 |
Carmen | -0.420 |
Token | should |
Token ID | 815 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
antha | +0.192 |
iversal | +0.165 |
arov | +0.165 |
unction | +0.164 |
66666666 | +0.158 |
Neg logit contributions | |
disproportion | -0.195 |
Penet | -0.146 |
Valkyrie | -0.142 |
disadvant | -0.141 |
Carmen | -0.133 |
Token | be |
Token ID | 307 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
antha | +2.496 |
arov | +2.189 |
iversal | +2.169 |
unction | +2.159 |
66666666 | +2.084 |
Neg logit contributions | |
disproportion | -2.307 |
Penet | -1.729 |
Valkyrie | -1.700 |
disadvant | -1.666 |
Carmen | -1.570 |
Token | good |
Token ID | 922 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
antha | +1.704 |
arov | +1.497 |
iversal | +1.486 |
unction | +1.481 |
66666666 | +1.429 |
Neg logit contributions | |
disproportion | -1.548 |
Penet | -1.139 |
Valkyrie | -1.113 |
disadvant | -1.078 |
Carmen | -1.030 |
Token | enough |
Token ID | 1576 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
antha | +3.845 |
iversal | +3.356 |
arov | +3.317 |
unction | +3.303 |
66666666 | +3.198 |
Neg logit contributions | |
disproportion | -3.762 |
Penet | -2.826 |
Valkyrie | -2.746 |
disadvant | -2.689 |
Carmen | -2.534 |
Token | for |
Token ID | 329 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
antha | +5.052 |
iversal | +4.285 |
arov | +4.258 |
unction | +4.218 |
66666666 | +4.045 |
Neg logit contributions | |
disproportion | -7.188 |
Penet | -5.693 |
Valkyrie | -5.587 |
disadvant | -5.456 |
Carmen | -5.183 |
Token | their |
Token ID | 511 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
antha | +2.366 |
iversal | +2.037 |
arov | +2.036 |
unction | +2.020 |
66666666 | +1.968 |
Neg logit contributions | |
disproportion | -2.334 |
Penet | -1.745 |
Valkyrie | -1.702 |
disadvant | -1.672 |
Carmen | -1.565 |
Token | representatives |
Token ID | 10826 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
antha | +1.364 |
arov | +1.185 |
iversal | +1.184 |
unction | +1.172 |
66666666 | +1.144 |
Neg logit contributions | |
disproportion | -1.327 |
Penet | -0.993 |
Valkyrie | -0.961 |
disadvant | -0.946 |
Carmen | -0.893 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
disproportion | +1.926 |
Penet | +1.380 |
Valkyrie | +1.340 |
disadvant | +1.331 |
Carmen | +1.264 |
Neg logit contributions | |
antha | -2.191 |
iversal | -1.922 |
arov | -1.903 |
unction | -1.899 |
66666666 | -1.830 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
antha | +1.096 |
arov | +0.945 |
iversal | +0.936 |
unction | +0.930 |
66666666 | +0.918 |
Neg logit contributions | |
disproportion | -1.222 |
disadvant | -0.895 |
Penet | -0.889 |
Valkyrie | -0.873 |
scapego | -0.832 |
Token | While |
Token ID | 2893 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
disproportion | +0.560 |
Penet | +0.405 |
disadvant | +0.394 |
Valkyrie | +0.392 |
Carmen | +0.367 |
Neg logit contributions | |
antha | -0.620 |
iversal | -0.540 |
arov | -0.537 |
unction | -0.536 |
66666666 | -0.519 |
Token | cleaner |
Token ID | 21723 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
disproportion | +0.105 |
Penet | +0.076 |
Valkyrie | +0.074 |
disadvant | +0.073 |
Carmen | +0.069 |
Neg logit contributions | |
antha | -0.116 |
iversal | -0.102 |
arov | -0.101 |
unction | -0.101 |
66666666 | -0.097 |
Token | at |
Token ID | 379 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
disproportion | +0.134 |
Penet | +0.099 |
Valkyrie | +0.096 |
disadvant | +0.095 |
Carmen | +0.090 |
Neg logit contributions | |
antha | -0.136 |
iversal | -0.118 |
arov | -0.117 |
unction | -0.117 |
66666666 | -0.112 |
Token | the |
Token ID | 262 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
antha | +0.974 |
iversal | +0.851 |
unction | +0.845 |
arov | +0.844 |
66666666 | +0.814 |
Neg logit contributions | |
disproportion | -0.869 |
Penet | -0.634 |
Valkyrie | -0.615 |
disadvant | -0.611 |
Carmen | -0.575 |
Token | sm |
Token ID | 895 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
antha | +0.589 |
iversal | +0.512 |
arov | +0.508 |
unction | +0.506 |
66666666 | +0.488 |
Neg logit contributions | |
disproportion | -0.573 |
Penet | -0.424 |
Valkyrie | -0.409 |
disadvant | -0.407 |
Carmen | -0.384 |
Token | ok |
Token ID | 482 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
disproportion | +1.328 |
Penet | +1.032 |
Valkyrie | +1.002 |
disadvant | +0.993 |
Carmen | +0.957 |
Neg logit contributions | |
antha | -0.956 |
iversal | -0.807 |
arov | -0.797 |
unction | -0.791 |
66666666 | -0.760 |
Token | est |
Token ID | 395 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
antha | +7.322 |
arov | +6.546 |
unction | +6.410 |
iversal | +6.390 |
ysc | +6.331 |
Neg logit contributions | |
disproportion | -5.067 |
Penet | -3.443 |
Valkyrie | -3.355 |
disadvant | -3.318 |
scapego | -3.118 |
Token | ack |
Token ID | 441 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
antha | +0.894 |
iversal | +0.751 |
arov | +0.740 |
unction | +0.729 |
66666666 | +0.706 |
Neg logit contributions | |
disproportion | -1.216 |
Penet | -0.945 |
Valkyrie | -0.919 |
disadvant | -0.907 |
Carmen | -0.878 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
antha | +0.385 |
iversal | +0.335 |
arov | +0.332 |
unction | +0.331 |
66666666 | +0.318 |
Neg logit contributions | |
disproportion | -0.379 |
Penet | -0.281 |
Valkyrie | -0.272 |
disadvant | -0.271 |
Carmen | -0.256 |
Token | natural |
Token ID | 3288 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
antha | +1.311 |
iversal | +1.145 |
unction | +1.136 |
arov | +1.136 |
66666666 | +1.095 |
Neg logit contributions | |
disproportion | -1.162 |
Penet | -0.846 |
Valkyrie | -0.819 |
disadvant | -0.815 |
Carmen | -0.764 |
Token | gas |
Token ID | 3623 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
antha | +2.259 |
iversal | +1.984 |
arov | +1.970 |
unction | +1.965 |
66666666 | +1.903 |
Neg logit contributions | |
disproportion | -1.860 |
Penet | -1.333 |
Valkyrie | -1.285 |
disadvant | -1.280 |
Carmen | -1.197 |
Token | reasons |
Token ID | 3840 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
antha | +2.084 |
iversal | +1.805 |
arov | +1.801 |
unction | +1.787 |
66666666 | +1.721 |
Neg logit contributions | |
disproportion | -1.905 |
Penet | -1.396 |
disadvant | -1.350 |
Valkyrie | -1.341 |
Carmen | -1.259 |
Token | why |
Token ID | 1521 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
antha | +3.681 |
iversal | +3.185 |
arov | +3.149 |
unction | +3.142 |
66666666 | +3.060 |
Neg logit contributions | |
disproportion | -3.860 |
Penet | -2.877 |
disadvant | -2.803 |
Valkyrie | -2.758 |
scapego | -2.618 |
Token | L |
Token ID | 406 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
antha | +0.482 |
iversal | +0.419 |
arov | +0.416 |
unction | +0.415 |
66666666 | +0.400 |
Neg logit contributions | |
disproportion | -0.465 |
Penet | -0.344 |
Valkyrie | -0.332 |
disadvant | -0.331 |
Carmen | -0.312 |
Token | IGHT |
Token ID | 9947 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
antha | +0.474 |
iversal | +0.405 |
arov | +0.403 |
unction | +0.401 |
66666666 | +0.384 |
Neg logit contributions | |
disproportion | -0.551 |
Penet | -0.419 |
Valkyrie | -0.406 |
disadvant | -0.406 |
Carmen | -0.384 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
antha | +2.278 |
iversal | +1.966 |
arov | +1.947 |
unction | +1.932 |
66666666 | +1.858 |
Neg logit contributions | |
disproportion | -2.502 |
Penet | -1.872 |
disadvant | -1.833 |
Valkyrie | -1.818 |
Carmen | -1.724 |
Token | COL |
Token ID | 20444 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
antha | +0.964 |
iversal | +0.839 |
arov | +0.834 |
unction | +0.830 |
66666666 | +0.801 |
Neg logit contributions | |
disproportion | -0.929 |
Penet | -0.685 |
disadvant | -0.663 |
Valkyrie | -0.662 |
Carmen | -0.623 |
Token | OR |
Token ID | 1581 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
antha | +3.896 |
iversal | +3.210 |
arov | +3.201 |
unction | +3.085 |
66666666 | +2.973 |
Neg logit contributions | |
disproportion | -8.312 |
disadvant | -6.596 |
Penet | -6.591 |
Valkyrie | -6.452 |
scapego | -6.356 |
Token | are |
Token ID | 389 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
antha | +1.692 |
iversal | +1.468 |
arov | +1.455 |
unction | +1.450 |
66666666 | +1.397 |
Neg logit contributions | |
disproportion | -1.731 |
Penet | -1.288 |
disadvant | -1.252 |
Valkyrie | -1.250 |
Carmen | -1.178 |
Token | such |
Token ID | 884 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
antha | +0.015 |
iversal | +0.013 |
arov | +0.013 |
unction | +0.013 |
66666666 | +0.012 |
Neg logit contributions | |
disproportion | -0.013 |
Penet | -0.009 |
Valkyrie | -0.009 |
disadvant | -0.009 |
Carmen | -0.008 |
Token | important |
Token ID | 1593 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
disproportion | +0.731 |
Penet | +0.525 |
Valkyrie | +0.506 |
disadvant | +0.503 |
Carmen | +0.472 |
Neg logit contributions | |
antha | -0.873 |
iversal | -0.767 |
arov | -0.761 |
unction | -0.759 |
66666666 | -0.733 |
Token | elements |
Token ID | 4847 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
antha | +1.250 |
iversal | +1.072 |
arov | +1.064 |
unction | +1.060 |
66666666 | +1.018 |
Neg logit contributions | |
disproportion | -1.440 |
Penet | -1.094 |
Valkyrie | -1.063 |
disadvant | -1.059 |
Carmen | -1.006 |
Token | K |
Token ID | 42 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
antha | +1.097 |
iversal | +0.921 |
arov | +0.915 |
unction | +0.911 |
66666666 | +0.869 |
Neg logit contributions | |
disproportion | -1.535 |
Penet | -1.192 |
Valkyrie | -1.162 |
disadvant | -1.161 |
Carmen | -1.106 |
Token | TR |
Token ID | 5446 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
antha | +2.107 |
arov | +1.781 |
iversal | +1.777 |
unction | +1.769 |
66666666 | +1.680 |
Neg logit contributions | |
disproportion | -2.480 |
Penet | -1.886 |
Valkyrie | -1.835 |
disadvant | -1.831 |
scapego | -1.737 |
Token | 024 |
Token ID | 40839 |
Feature activation | +6.46e+00 |
Pos logit contributions | |
antha | +2.270 |
iversal | +1.945 |
arov | +1.932 |
unction | +1.928 |
66666666 | +1.841 |
Neg logit contributions | |
disproportion | -2.696 |
Penet | -2.039 |
disadvant | -1.991 |
Valkyrie | -1.979 |
scapego | -1.869 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
antha | +5.503 |
iversal | +4.718 |
arov | +4.690 |
unction | +4.683 |
66666666 | +4.605 |
Neg logit contributions | |
disproportion | -6.272 |
disadvant | -4.634 |
Penet | -4.626 |
Valkyrie | -4.504 |
scapego | -4.267 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
antha | +1.961 |
arov | +1.707 |
unction | +1.669 |
iversal | +1.648 |
66666666 | +1.648 |
Neg logit contributions | |
disproportion | -2.482 |
disadvant | -1.911 |
Penet | -1.840 |
Valkyrie | -1.793 |
scapego | -1.718 |
Token | Self |
Token ID | 24704 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
antha | +1.776 |
iversal | +1.489 |
arov | +1.482 |
unction | +1.476 |
66666666 | +1.411 |
Neg logit contributions | |
disproportion | -2.500 |
Penet | -1.940 |
disadvant | -1.892 |
Valkyrie | -1.891 |
Carmen | -1.800 |
Token | described |
Token ID | 3417 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
antha | +5.947 |
unction | +5.207 |
iversal | +5.145 |
arov | +5.121 |
66666666 | +4.892 |
Neg logit contributions | |
disproportion | -6.327 |
Penet | -4.642 |
disadvant | -4.549 |
Valkyrie | -4.536 |
Carmen | -4.297 |
Token | as |
Token ID | 355 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
antha | +4.726 |
iversal | +4.070 |
unction | +4.066 |
arov | +4.059 |
66666666 | +3.921 |
Neg logit contributions | |
disproportion | -4.698 |
Penet | -3.465 |
disadvant | -3.391 |
Valkyrie | -3.364 |
Carmen | -3.154 |
Token | " |
Token ID | 366 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
antha | +1.861 |
iversal | +1.624 |
arov | +1.615 |
unction | +1.611 |
66666666 | +1.553 |
Neg logit contributions | |
disproportion | -1.632 |
Penet | -1.178 |
Valkyrie | -1.139 |
disadvant | -1.136 |
Carmen | -1.062 |
Token | f |
Token ID | 69 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
antha | +2.996 |
iversal | +2.516 |
arov | +2.513 |
unction | +2.506 |
atomic | +2.401 |
Neg logit contributions | |
disproportion | -3.964 |
Penet | -3.043 |
disadvant | -2.977 |
Valkyrie | -2.971 |
scapego | -2.817 |
Token | ucked |
Token ID | 17758 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
antha | +1.963 |
iversal | +1.684 |
arov | +1.672 |
unction | +1.671 |
66666666 | +1.590 |
Neg logit contributions | |
disproportion | -2.286 |
Penet | -1.740 |
Valkyrie | -1.691 |
disadvant | -1.687 |
Carmen | -1.597 |
Token | - |
Token ID | 12 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
disproportion | +1.373 |
Penet | +1.039 |
Valkyrie | +1.011 |
disadvant | +1.002 |
Carmen | +0.965 |
Neg logit contributions | |
antha | -1.255 |
iversal | -1.089 |
arov | -1.078 |
unction | -1.070 |
66666666 | -1.039 |
Token | lead |
Token ID | 28230 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
disproportion | +0.714 |
Penet | +0.545 |
Valkyrie | +0.530 |
disadvant | +0.527 |
Carmen | +0.503 |
Neg logit contributions | |
antha | -0.601 |
iversal | -0.515 |
arov | -0.509 |
unction | -0.508 |
66666666 | -0.488 |
Token | author |
Token ID | 1772 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
antha | +1.470 |
iversal | +1.244 |
arov | +1.239 |
unction | +1.231 |
66666666 | +1.181 |
Neg logit contributions | |
disproportion | -1.811 |
Penet | -1.384 |
Valkyrie | -1.346 |
disadvant | -1.343 |
scapego | -1.264 |
Token | Nicholas |
Token ID | 20320 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
antha | +0.368 |
iversal | +0.321 |
arov | +0.319 |
unction | +0.318 |
66666666 | +0.306 |
Neg logit contributions | |
disproportion | -0.335 |
Penet | -0.245 |
Valkyrie | -0.237 |
disadvant | -0.235 |
Carmen | -0.222 |
Token | R |
Token ID | 371 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
antha | +2.805 |
arov | +2.434 |
iversal | +2.413 |
unction | +2.400 |
66666666 | +2.314 |
Neg logit contributions | |
disproportion | -2.618 |
Penet | -1.873 |
disadvant | -1.852 |
Valkyrie | -1.809 |
scapego | -1.715 |
Token | ol |
Token ID | 349 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
disproportion | +1.777 |
Penet | +1.349 |
Valkyrie | +1.309 |
disadvant | +1.298 |
Carmen | +1.246 |
Neg logit contributions | |
antha | -1.611 |
iversal | -1.395 |
unction | -1.371 |
arov | -1.370 |
66666666 | -1.332 |
Token | ston |
Token ID | 3743 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
antha | +5.870 |
arov | +5.023 |
iversal | +4.982 |
unction | +4.938 |
atomic | +4.651 |
Neg logit contributions | |
disproportion | -6.766 |
Penet | -5.081 |
disadvant | -5.049 |
Valkyrie | -4.998 |
scapego | -4.654 |
Token | says |
Token ID | 1139 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
disproportion | +0.068 |
Penet | +0.050 |
Valkyrie | +0.048 |
disadvant | +0.048 |
Carmen | +0.045 |
Neg logit contributions | |
antha | -0.073 |
iversal | -0.064 |
unction | -0.063 |
arov | -0.063 |
66666666 | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
antha | +1.091 |
iversal | +0.952 |
arov | +0.946 |
unction | +0.942 |
66666666 | +0.909 |
Neg logit contributions | |
disproportion | -0.995 |
Penet | -0.726 |
Valkyrie | -0.702 |
disadvant | -0.699 |
Carmen | -0.657 |
Token | scaff |
Token ID | 41498 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
antha | +0.177 |
iversal | +0.153 |
arov | +0.152 |
unction | +0.151 |
66666666 | +0.145 |
Neg logit contributions | |
disproportion | -0.185 |
Penet | -0.139 |
Valkyrie | -0.135 |
disadvant | -0.134 |
Carmen | -0.127 |
Token | old |
Token ID | 727 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
disproportion | +0.002 |
Penet | +0.001 |
Valkyrie | +0.001 |
disadvant | +0.001 |
Carmen | +0.001 |
Neg logit contributions | |
antha | -0.002 |
iversal | -0.002 |
arov | -0.002 |
unction | -0.002 |
66666666 | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
antha | +1.656 |
iversal | +1.411 |
arov | +1.409 |
unction | +1.405 |
66666666 | +1.346 |
Neg logit contributions | |
disproportion | -1.770 |
Penet | -1.323 |
disadvant | -1.285 |
Valkyrie | -1.285 |
Carmen | -1.212 |
Token | Fedora |
Token ID | 32245 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
disproportion | +0.143 |
Penet | +0.101 |
Valkyrie | +0.097 |
disadvant | +0.096 |
Carmen | +0.090 |
Neg logit contributions | |
antha | -0.186 |
iversal | -0.164 |
arov | -0.163 |
unction | -0.163 |
66666666 | -0.157 |
Token | , |
Token ID | 11 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
disproportion | +4.862 |
Penet | +3.693 |
Valkyrie | +3.564 |
disadvant | +3.496 |
Carmen | +3.303 |
Neg logit contributions | |
antha | -4.984 |
iversal | -4.357 |
unction | -4.332 |
arov | -4.289 |
66666666 | -4.158 |
Token | as |
Token ID | 355 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
antha | +0.657 |
iversal | +0.571 |
arov | +0.569 |
unction | +0.566 |
66666666 | +0.547 |
Neg logit contributions | |
disproportion | -0.578 |
Penet | -0.415 |
disadvant | -0.403 |
Valkyrie | -0.401 |
Carmen | -0.375 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
disproportion | +1.674 |
Penet | +1.211 |
Valkyrie | +1.169 |
disadvant | +1.155 |
Carmen | +1.094 |
Neg logit contributions | |
antha | -1.984 |
iversal | -1.751 |
arov | -1.734 |
unction | -1.733 |
66666666 | -1.668 |
Token | dist |
Token ID | 1233 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
antha | +1.095 |
iversal | +0.952 |
arov | +0.949 |
unction | +0.944 |
66666666 | +0.913 |
Neg logit contributions | |
disproportion | -0.953 |
Penet | -0.681 |
disadvant | -0.665 |
Valkyrie | -0.661 |
Carmen | -0.620 |
Token | ro |
Token ID | 305 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
disproportion | +5.676 |
Penet | +3.906 |
Valkyrie | +3.723 |
disadvant | +3.659 |
Carmen | +3.436 |
Neg logit contributions | |
antha | -8.661 |
iversal | -7.723 |
unction | -7.495 |
arov | -7.494 |
66666666 | -7.411 |
Token | will |
Token ID | 481 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
disproportion | +5.231 |
Penet | +3.956 |
Valkyrie | +3.817 |
disadvant | +3.722 |
scapego | +3.593 |
Neg logit contributions | |
antha | -5.041 |
iversal | -4.391 |
unction | -4.350 |
arov | -4.341 |
66666666 | -4.116 |
Token | force |
Token ID | 2700 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
antha | +0.475 |
arov | +0.412 |
iversal | +0.409 |
unction | +0.406 |
66666666 | +0.395 |
Neg logit contributions | |
disproportion | -0.449 |
Penet | -0.331 |
disadvant | -0.327 |
Valkyrie | -0.320 |
Carmen | -0.303 |
Token | you |
Token ID | 345 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
disproportion | +0.685 |
Penet | +0.514 |
Valkyrie | +0.499 |
disadvant | +0.498 |
Carmen | +0.471 |
Neg logit contributions | |
antha | -0.636 |
iversal | -0.548 |
arov | -0.543 |
unction | -0.542 |
66666666 | -0.520 |
Token | to |
Token ID | 284 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
disproportion | +0.215 |
Penet | +0.159 |
Valkyrie | +0.154 |
disadvant | +0.153 |
Carmen | +0.145 |
Neg logit contributions | |
antha | -0.218 |
iversal | -0.189 |
arov | -0.187 |
unction | -0.187 |
66666666 | -0.180 |
Token | organizations |
Token ID | 5745 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
disproportion | +1.148 |
Penet | +0.840 |
Valkyrie | +0.813 |
disadvant | +0.809 |
Carmen | +0.761 |
Neg logit contributions | |
antha | -1.257 |
iversal | -1.096 |
arov | -1.088 |
unction | -1.085 |
66666666 | -1.046 |
Token | with |
Token ID | 351 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
antha | +0.199 |
iversal | +0.173 |
arov | +0.173 |
unction | +0.171 |
66666666 | +0.165 |
Neg logit contributions | |
disproportion | -0.186 |
Penet | -0.137 |
Valkyrie | -0.134 |
disadvant | -0.132 |
Carmen | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
disproportion | +0.315 |
Penet | +0.227 |
Valkyrie | +0.220 |
disadvant | +0.219 |
Carmen | +0.205 |
Neg logit contributions | |
antha | -0.373 |
iversal | -0.327 |
arov | -0.325 |
unction | -0.324 |
66666666 | -0.313 |
Token | history |
Token ID | 2106 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
disproportion | +1.073 |
Penet | +0.786 |
Valkyrie | +0.761 |
disadvant | +0.758 |
Carmen | +0.713 |
Neg logit contributions | |
antha | -1.163 |
iversal | -1.015 |
arov | -1.007 |
unction | -1.004 |
66666666 | -0.968 |
Token | of |
Token ID | 286 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
disproportion | +2.511 |
Penet | +1.794 |
disadvant | +1.725 |
Valkyrie | +1.713 |
scapego | +1.613 |
Neg logit contributions | |
antha | -3.028 |
iversal | -2.650 |
arov | -2.632 |
unction | -2.621 |
66666666 | -2.546 |
Token | dist |
Token ID | 1233 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
disproportion | +2.460 |
Penet | +1.773 |
Valkyrie | +1.707 |
disadvant | +1.707 |
Carmen | +1.598 |
Neg logit contributions | |
antha | -2.848 |
iversal | -2.503 |
arov | -2.480 |
unction | -2.475 |
66666666 | -2.388 |
Token | orting |
Token ID | 24707 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
disproportion | +4.994 |
Penet | +3.236 |
disadvant | +3.134 |
Valkyrie | +3.126 |
Carmen | +2.748 |
Neg logit contributions | |
antha | -8.680 |
iversal | -7.756 |
66666666 | -7.645 |
arov | -7.601 |
unction | -7.519 |
Token | the |
Token ID | 262 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
disproportion | +1.968 |
Penet | +1.413 |
Valkyrie | +1.369 |
disadvant | +1.360 |
Carmen | +1.283 |
Neg logit contributions | |
antha | -2.268 |
iversal | -1.995 |
unction | -1.977 |
arov | -1.973 |
66666666 | -1.897 |
Token | facts |
Token ID | 6419 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
antha | +0.056 |
arov | +0.049 |
iversal | +0.049 |
unction | +0.049 |
66666666 | +0.047 |
Neg logit contributions | |
disproportion | -0.044 |
Penet | -0.031 |
Valkyrie | -0.030 |
disadvant | -0.030 |
Carmen | -0.028 |
Token | are |
Token ID | 389 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
disproportion | +1.312 |
Penet | +0.961 |
Valkyrie | +0.928 |
disadvant | +0.925 |
Carmen | +0.872 |
Neg logit contributions | |
antha | -1.398 |
iversal | -1.217 |
arov | -1.206 |
unction | -1.204 |
66666666 | -1.160 |
Token | used |
Token ID | 973 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
antha | +0.119 |
arov | +0.103 |
iversal | +0.103 |
unction | +0.103 |
66666666 | +0.099 |
Neg logit contributions | |
disproportion | -0.108 |
Penet | -0.080 |
Valkyrie | -0.078 |
disadvant | -0.076 |
Carmen | -0.072 |
Token | scandal |
Token ID | 10731 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
antha | +0.417 |
iversal | +0.363 |
arov | +0.362 |
unction | +0.361 |
66666666 | +0.348 |
Neg logit contributions | |
disproportion | -0.374 |
Penet | -0.271 |
disadvant | -0.262 |
Valkyrie | -0.261 |
Carmen | -0.243 |
Token | - |
Token ID | 12 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
disproportion | +2.568 |
Penet | +1.928 |
Valkyrie | +1.868 |
disadvant | +1.860 |
Carmen | +1.769 |
Neg logit contributions | |
antha | -2.476 |
iversal | -2.146 |
arov | -2.113 |
unction | -2.110 |
66666666 | -2.048 |
Token | hit |
Token ID | 17945 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
antha | +0.184 |
iversal | +0.156 |
arov | +0.154 |
unction | +0.154 |
66666666 | +0.148 |
Neg logit contributions | |
disproportion | -0.235 |
Penet | -0.182 |
Valkyrie | -0.177 |
disadvant | -0.176 |
Carmen | -0.168 |
Token | former |
Token ID | 1966 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
disproportion | +1.147 |
Penet | +0.837 |
Valkyrie | +0.810 |
disadvant | +0.804 |
Carmen | +0.759 |
Neg logit contributions | |
antha | -1.271 |
iversal | -1.111 |
arov | -1.102 |
unction | -1.099 |
66666666 | -1.059 |
Token | International |
Token ID | 4037 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
disproportion | +1.564 |
Penet | +1.128 |
Valkyrie | +1.090 |
disadvant | +1.081 |
Carmen | +1.018 |
Neg logit contributions | |
antha | -1.834 |
iversal | -1.609 |
arov | -1.596 |
unction | -1.592 |
66666666 | -1.536 |
Token | Monetary |
Token ID | 34112 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
disproportion | +0.749 |
Penet | +0.490 |
Valkyrie | +0.468 |
disadvant | +0.463 |
Carmen | +0.425 |
Neg logit contributions | |
antha | -1.270 |
iversal | -1.136 |
arov | -1.129 |
unction | -1.126 |
66666666 | -1.094 |
Token | Fund |
Token ID | 7557 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
disproportion | +5.452 |
Penet | +3.757 |
Valkyrie | +3.605 |
disadvant | +3.479 |
Carmen | +3.388 |
Neg logit contributions | |
antha | -8.512 |
iversal | -7.605 |
unction | -7.552 |
66666666 | -7.327 |
arov | -7.256 |
Token | chief |
Token ID | 4039 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
disproportion | +2.248 |
Penet | +1.641 |
Valkyrie | +1.586 |
disadvant | +1.575 |
Carmen | +1.502 |
Neg logit contributions | |
antha | -2.482 |
iversal | -2.176 |
arov | -2.149 |
unction | -2.148 |
66666666 | -2.073 |
Token | Domin |
Token ID | 11817 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
antha | +2.107 |
iversal | +1.849 |
arov | +1.847 |
unction | +1.843 |
66666666 | +1.766 |
Neg logit contributions | |
disproportion | -1.650 |
Penet | -1.176 |
disadvant | -1.129 |
Valkyrie | -1.124 |
scapego | -1.010 |
Token | ique |
Token ID | 2350 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
disproportion | +1.889 |
Penet | +1.465 |
Valkyrie | +1.429 |
disadvant | +1.419 |
Carmen | +1.360 |
Neg logit contributions | |
antha | -1.417 |
iversal | -1.204 |
arov | -1.185 |
unction | -1.183 |
66666666 | -1.132 |
Token | Strauss |
Token ID | 42971 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
disproportion | +0.055 |
Penet | +0.037 |
disadvant | +0.036 |
Valkyrie | +0.036 |
Carmen | +0.033 |
Neg logit contributions | |
antha | -0.082 |
iversal | -0.073 |
arov | -0.072 |
unction | -0.072 |
66666666 | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
antha | +0.941 |
iversal | +0.824 |
arov | +0.818 |
unction | +0.813 |
66666666 | +0.786 |
Neg logit contributions | |
disproportion | -0.831 |
Penet | -0.602 |
Valkyrie | -0.583 |
disadvant | -0.580 |
Carmen | -0.545 |
Token | environment |
Token ID | 2858 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
antha | +1.142 |
iversal | +0.993 |
arov | +0.990 |
unction | +0.983 |
66666666 | +0.949 |
Neg logit contributions | |
disproportion | -1.044 |
Penet | -0.763 |
Valkyrie | -0.737 |
disadvant | -0.735 |
Carmen | -0.694 |
Token | 's |
Token ID | 338 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
disproportion | +1.461 |
Penet | +1.069 |
Valkyrie | +1.034 |
disadvant | +1.028 |
Carmen | +0.968 |
Neg logit contributions | |
antha | -1.603 |
iversal | -1.400 |
arov | -1.388 |
unction | -1.385 |
66666666 | -1.335 |
Token | context |
Token ID | 4732 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
antha | +1.506 |
iversal | +1.305 |
arov | +1.301 |
unction | +1.290 |
66666666 | +1.247 |
Neg logit contributions | |
disproportion | -1.416 |
Penet | -1.041 |
Valkyrie | -1.008 |
disadvant | -1.003 |
Carmen | -0.948 |
Token | and |
Token ID | 290 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
antha | +0.679 |
iversal | +0.593 |
arov | +0.588 |
unction | +0.588 |
66666666 | +0.566 |
Neg logit contributions | |
disproportion | -0.621 |
Penet | -0.454 |
Valkyrie | -0.439 |
disadvant | -0.437 |
Carmen | -0.412 |
Token | dist |
Token ID | 1233 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
disproportion | +0.065 |
Penet | +0.048 |
Valkyrie | +0.046 |
disadvant | +0.046 |
Carmen | +0.043 |
Neg logit contributions | |
antha | -0.070 |
iversal | -0.061 |
arov | -0.060 |
unction | -0.060 |
66666666 | -0.058 |
Token | al |
Token ID | 282 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
disproportion | +7.009 |
Penet | +5.231 |
disadvant | +5.116 |
Valkyrie | +5.104 |
Carmen | +4.777 |
Neg logit contributions | |
antha | -6.648 |
iversal | -5.737 |
arov | -5.590 |
66666666 | -5.567 |
unction | -5.528 |
Token | cues |
Token ID | 25288 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
disproportion | +1.856 |
Penet | +1.366 |
Valkyrie | +1.322 |
disadvant | +1.317 |
Carmen | +1.237 |
Neg logit contributions | |
antha | -1.931 |
iversal | -1.682 |
arov | -1.662 |
unction | -1.659 |
66666666 | -1.597 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
disproportion | +2.343 |
Penet | +1.694 |
Valkyrie | +1.632 |
disadvant | +1.625 |
Carmen | +1.528 |
Neg logit contributions | |
antha | -2.717 |
iversal | -2.375 |
arov | -2.357 |
unction | -2.346 |
66666666 | -2.266 |
Token | The |
Token ID | 383 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
disproportion | +1.104 |
Penet | +0.826 |
Valkyrie | +0.800 |
disadvant | +0.793 |
Carmen | +0.753 |
Neg logit contributions | |
antha | -1.090 |
iversal | -0.945 |
arov | -0.936 |
unction | -0.934 |
66666666 | -0.896 |
Token | comparison |
Token ID | 7208 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
disproportion | +0.139 |
Penet | +0.101 |
Valkyrie | +0.098 |
disadvant | +0.097 |
Carmen | +0.092 |
Neg logit contributions | |
antha | -0.154 |
iversal | -0.134 |
arov | -0.133 |
unction | -0.133 |
66666666 | -0.128 |
Token | - |
Token ID | 12 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
antha | +0.829 |
iversal | +0.721 |
arov | +0.715 |
unction | +0.713 |
66666666 | +0.687 |
Neg logit contributions | |
disproportion | -0.793 |
Penet | -0.585 |
Valkyrie | -0.566 |
disadvant | -0.563 |
Carmen | -0.532 |
Token | Car |
Token ID | 9914 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
disproportion | +1.059 |
Penet | +0.816 |
Valkyrie | +0.793 |
disadvant | +0.786 |
Carmen | +0.759 |
Neg logit contributions | |
antha | -0.907 |
iversal | -0.788 |
arov | -0.773 |
unction | -0.772 |
66666666 | -0.752 |
Token | lo |
Token ID | 5439 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
disproportion | +0.497 |
Penet | +0.341 |
Valkyrie | +0.327 |
disadvant | +0.322 |
Carmen | +0.303 |
Neg logit contributions | |
antha | -0.723 |
iversal | -0.644 |
arov | -0.637 |
unction | -0.637 |
66666666 | -0.619 |
Token | . |
Token ID | 13 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
disproportion | +3.269 |
Penet | +2.504 |
Valkyrie | +2.442 |
disadvant | +2.420 |
Carmen | +2.312 |
Neg logit contributions | |
antha | -2.842 |
iversal | -2.453 |
unction | -2.423 |
arov | -2.389 |
66666666 | -2.341 |
Token | We |
Token ID | 775 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
disproportion | +0.681 |
Penet | +0.512 |
Valkyrie | +0.498 |
disadvant | +0.490 |
Carmen | +0.468 |
Neg logit contributions | |
antha | -0.660 |
iversal | -0.571 |
arov | -0.565 |
unction | -0.565 |
66666666 | -0.541 |
Token | spoke |
Token ID | 5158 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
disproportion | +1.970 |
Penet | +1.455 |
Valkyrie | +1.409 |
disadvant | +1.406 |
Carmen | +1.323 |
Neg logit contributions | |
antha | -2.042 |
iversal | -1.776 |
arov | -1.764 |
unction | -1.754 |
66666666 | -1.689 |
Token | to |
Token ID | 284 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
disproportion | +6.316 |
Penet | +4.512 |
Valkyrie | +4.468 |
Carmen | +4.183 |
disadvant | +4.178 |
Neg logit contributions | |
antha | -7.232 |
unction | -6.289 |
arov | -6.276 |
iversal | -6.263 |
66666666 | -6.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
disproportion | +2.870 |
Penet | +2.152 |
Valkyrie | +2.126 |
disadvant | +2.057 |
Carmen | +1.987 |
Neg logit contributions | |
antha | -2.769 |
iversal | -2.394 |
unction | -2.381 |
arov | -2.371 |
66666666 | -2.276 |
Token | Welsh |
Token ID | 22945 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
disproportion | +1.057 |
Penet | +0.775 |
Valkyrie | +0.750 |
disadvant | +0.746 |
Carmen | +0.703 |
Neg logit contributions | |
antha | -1.136 |
iversal | -0.991 |
arov | -0.983 |
unction | -0.980 |
66666666 | -0.945 |
Token | man |
Token ID | 805 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
disproportion | +2.489 |
Penet | +1.864 |
Valkyrie | +1.818 |
disadvant | +1.780 |
Carmen | +1.705 |
Neg logit contributions | |
antha | -2.449 |
iversal | -2.138 |
unction | -2.106 |
arov | -2.092 |
66666666 | -2.022 |
Token | to |
Token ID | 284 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
disproportion | +1.086 |
Penet | +0.795 |
Valkyrie | +0.768 |
disadvant | +0.766 |
Carmen | +0.720 |
Neg logit contributions | |
antha | -1.182 |
iversal | -1.032 |
arov | -1.025 |
unction | -1.021 |
66666666 | -0.985 |
Token |
|
Token ID | 198 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
disproportion | +1.285 |
Penet | +0.944 |
Valkyrie | +0.918 |
disadvant | +0.911 |
Carmen | +0.863 |
Neg logit contributions | |
antha | -1.384 |
iversal | -1.208 |
arov | -1.200 |
unction | -1.194 |
66666666 | -1.156 |
Token |
|
Token ID | 198 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
antha | +0.293 |
arov | +0.252 |
iversal | +0.251 |
unction | +0.250 |
66666666 | +0.242 |
Neg logit contributions | |
disproportion | -0.330 |
Penet | -0.247 |
disadvant | -0.245 |
Valkyrie | -0.240 |
scapego | -0.226 |
Token | Santa |
Token ID | 42694 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
antha | +0.382 |
iversal | +0.322 |
arov | +0.319 |
unction | +0.318 |
66666666 | +0.303 |
Neg logit contributions | |
disproportion | -0.524 |
Penet | -0.407 |
Valkyrie | -0.397 |
disadvant | -0.396 |
Carmen | -0.378 |
Token | Clara |
Token ID | 27443 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
antha | +0.049 |
arov | +0.044 |
iversal | +0.044 |
unction | +0.044 |
66666666 | +0.042 |
Neg logit contributions | |
disproportion | -0.023 |
Penet | -0.014 |
disadvant | -0.013 |
Valkyrie | -0.013 |
scapego | -0.011 |
Token | County |
Token ID | 3418 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
disproportion | +1.502 |
Penet | +1.177 |
Valkyrie | +1.148 |
disadvant | +1.140 |
Carmen | +1.097 |
Neg logit contributions | |
antha | -1.071 |
iversal | -0.895 |
arov | -0.893 |
unction | -0.886 |
66666666 | -0.849 |
Token | v |
Token ID | 410 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
antha | +1.364 |
iversal | +1.183 |
arov | +1.170 |
unction | +1.169 |
66666666 | +1.122 |
Neg logit contributions | |
disproportion | -1.357 |
Penet | -1.004 |
Valkyrie | -0.974 |
disadvant | -0.967 |
Carmen | -0.908 |
Token | . |
Token ID | 13 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
disproportion | +5.555 |
Penet | +4.076 |
Valkyrie | +3.937 |
Carmen | +3.741 |
Rodgers | +3.544 |
Neg logit contributions | |
antha | -7.922 |
iversal | -7.156 |
unction | -6.924 |
arov | -6.880 |
atomic | -6.639 |
Token | Southern |
Token ID | 8050 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
disproportion | +0.060 |
Penet | +0.045 |
Valkyrie | +0.044 |
disadvant | +0.044 |
Carmen | +0.041 |
Neg logit contributions | |
antha | -0.057 |
iversal | -0.049 |
arov | -0.049 |
unction | -0.048 |
66666666 | -0.047 |
Token | Pacific |
Token ID | 8211 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
disproportion | +1.892 |
Penet | +1.470 |
disadvant | +1.443 |
Valkyrie | +1.441 |
Carmen | +1.367 |
Neg logit contributions | |
antha | -1.315 |
iversal | -1.098 |
arov | -1.086 |
unction | -1.082 |
66666666 | -1.032 |
Token | Railroad |
Token ID | 36289 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
disproportion | +0.857 |
Penet | +0.624 |
Valkyrie | +0.600 |
disadvant | +0.598 |
Carmen | +0.562 |
Neg logit contributions | |
antha | -1.001 |
iversal | -0.874 |
arov | -0.871 |
unction | -0.868 |
66666666 | -0.840 |
Token | Company |
Token ID | 5834 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
disproportion | +0.083 |
Penet | +0.058 |
Valkyrie | +0.056 |
disadvant | +0.055 |
Carmen | +0.052 |
Neg logit contributions | |
antha | -0.115 |
iversal | -0.102 |
arov | -0.102 |
unction | -0.101 |
66666666 | -0.098 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
antha | +1.528 |
iversal | +1.335 |
arov | +1.327 |
unction | +1.322 |
66666666 | +1.273 |
Neg logit contributions | |
disproportion | -1.370 |
Penet | -0.997 |
Valkyrie | -0.964 |
disadvant | -0.962 |
Carmen | -0.905 |
Token | last |
Token ID | 938 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
disproportion | +1.513 |
Penet | +1.090 |
Valkyrie | +1.052 |
disadvant | +1.045 |
Carmen | +0.979 |
Neg logit contributions | |
antha | -1.798 |
iversal | -1.570 |
unction | -1.561 |
arov | -1.560 |
66666666 | -1.503 |
Token | year |
Token ID | 614 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
disproportion | +2.967 |
Penet | +2.152 |
Valkyrie | +2.106 |
disadvant | +2.077 |
scapego | +1.950 |
Neg logit contributions | |
antha | -3.364 |
iversal | -2.908 |
unction | -2.890 |
arov | -2.872 |
66666666 | -2.783 |
Token | per |
Token ID | 583 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
disproportion | +3.213 |
Penet | +2.302 |
Valkyrie | +2.232 |
disadvant | +2.204 |
scapego | +2.064 |
Neg logit contributions | |
antha | -3.912 |
iversal | -3.434 |
unction | -3.387 |
arov | -3.369 |
66666666 | -3.279 |
Token | Football |
Token ID | 9957 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
disproportion | +2.619 |
Penet | +1.827 |
Valkyrie | +1.742 |
disadvant | +1.685 |
Carmen | +1.593 |
Neg logit contributions | |
antha | -3.802 |
iversal | -3.374 |
arov | -3.356 |
unction | -3.352 |
66666666 | -3.244 |
Token | Outs |
Token ID | 46580 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
disproportion | +2.819 |
Penet | +2.160 |
Valkyrie | +2.079 |
disadvant | +2.051 |
Carmen | +1.963 |
Neg logit contributions | |
antha | -2.550 |
iversal | -2.202 |
unction | -2.180 |
arov | -2.175 |
66666666 | -2.086 |
Token | iders |
Token ID | 4157 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
disproportion | +4.531 |
Penet | +2.996 |
Valkyrie | +2.759 |
disadvant | +2.478 |
Carmen | +2.397 |
Neg logit contributions | |
antha | -8.894 |
iversal | -7.920 |
unction | -7.816 |
arov | -7.783 |
atomic | -7.584 |
Token | ( |
Token ID | 357 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
disproportion | +2.689 |
Penet | +1.960 |
Valkyrie | +1.882 |
disadvant | +1.859 |
Carmen | +1.751 |
Neg logit contributions | |
antha | -3.232 |
iversal | -2.825 |
unction | -2.806 |
arov | -2.791 |
66666666 | -2.700 |
Token | 56 |
Token ID | 3980 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
antha | +0.125 |
iversal | +0.105 |
arov | +0.104 |
unction | +0.104 |
66666666 | +0.099 |
Neg logit contributions | |
disproportion | -0.181 |
Penet | -0.142 |
Valkyrie | -0.138 |
disadvant | -0.138 |
Carmen | -0.132 |
Token | percent |
Token ID | 1411 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
antha | +0.206 |
iversal | +0.179 |
arov | +0.179 |
unction | +0.177 |
66666666 | +0.171 |
Neg logit contributions | |
disproportion | -0.195 |
Penet | -0.143 |
disadvant | -0.139 |
Valkyrie | -0.138 |
Carmen | -0.131 |
Token | ). |
Token ID | 737 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
disproportion | +2.353 |
Penet | +1.738 |
Valkyrie | +1.690 |
disadvant | +1.666 |
Carmen | +1.572 |
Neg logit contributions | |
antha | -2.464 |
iversal | -2.142 |
unction | -2.123 |
arov | -2.116 |
66666666 | -2.043 |
Token | analysis |
Token ID | 3781 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
disproportion | +2.636 |
Penet | +1.941 |
Valkyrie | +1.881 |
disadvant | +1.862 |
Carmen | +1.781 |
Neg logit contributions | |
antha | -2.748 |
iversal | -2.402 |
arov | -2.377 |
unction | -2.375 |
66666666 | -2.292 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
disproportion | +1.855 |
Penet | +1.355 |
Valkyrie | +1.309 |
disadvant | +1.300 |
Carmen | +1.237 |
Neg logit contributions | |
antha | -2.028 |
iversal | -1.781 |
arov | -1.761 |
unction | -1.760 |
66666666 | -1.687 |
Token | Bureau |
Token ID | 9840 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
disproportion | +1.370 |
Penet | +1.013 |
Valkyrie | +0.980 |
disadvant | +0.974 |
Carmen | +0.929 |
Neg logit contributions | |
antha | -1.399 |
iversal | -1.220 |
arov | -1.212 |
unction | -1.209 |
66666666 | -1.163 |
Token | of |
Token ID | 286 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
disproportion | +2.489 |
Penet | +1.786 |
Valkyrie | +1.706 |
disadvant | +1.690 |
Carmen | +1.656 |
Neg logit contributions | |
antha | -3.132 |
iversal | -2.779 |
arov | -2.757 |
unction | -2.754 |
66666666 | -2.637 |
Token | Labor |
Token ID | 7882 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
disproportion | +2.618 |
Penet | +1.839 |
Valkyrie | +1.749 |
disadvant | +1.699 |
Carmen | +1.662 |
Neg logit contributions | |
antha | -3.622 |
arov | -3.219 |
unction | -3.214 |
iversal | -3.203 |
66666666 | -3.091 |
Token | Statistics |
Token ID | 14370 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
disproportion | +1.759 |
Penet | +0.834 |
Valkyrie | +0.728 |
disadvant | +0.658 |
Carmen | +0.655 |
Neg logit contributions | |
antha | -5.431 |
unction | -4.942 |
iversal | -4.916 |
arov | -4.907 |
66666666 | -4.799 |
Token | , |
Token ID | 11 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
disproportion | +6.702 |
Penet | +5.016 |
Valkyrie | +4.774 |
disadvant | +4.695 |
Carmen | +4.692 |
Neg logit contributions | |
antha | -6.722 |
arov | -5.898 |
iversal | -5.891 |
unction | -5.890 |
66666666 | -5.601 |
Token | Job |
Token ID | 15768 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
disproportion | +0.516 |
Penet | +0.380 |
Valkyrie | +0.368 |
disadvant | +0.367 |
Carmen | +0.345 |
Neg logit contributions | |
antha | -0.536 |
iversal | -0.466 |
arov | -0.462 |
unction | -0.461 |
66666666 | -0.444 |
Token | Open |
Token ID | 4946 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
disproportion | +1.667 |
Penet | +1.303 |
Valkyrie | +1.269 |
disadvant | +1.250 |
Carmen | +1.200 |
Neg logit contributions | |
antha | -1.194 |
iversal | -1.017 |
arov | -1.009 |
unction | -0.996 |
66666666 | -0.959 |
Token | ings |
Token ID | 654 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
disproportion | +2.054 |
Penet | +1.454 |
Valkyrie | +1.378 |
disadvant | +1.357 |
Carmen | +1.285 |
Neg logit contributions | |
antha | -2.775 |
iversal | -2.449 |
arov | -2.433 |
unction | -2.417 |
66666666 | -2.345 |
Token | and |
Token ID | 290 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
disproportion | +1.360 |
Penet | +1.004 |
Valkyrie | +0.968 |
disadvant | +0.959 |
Carmen | +0.912 |
Neg logit contributions | |
antha | -1.439 |
iversal | -1.257 |
arov | -1.247 |
unction | -1.245 |
66666666 | -1.195 |
Token | from |
Token ID | 422 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
disproportion | +2.547 |
Penet | +1.800 |
disadvant | +1.726 |
Valkyrie | +1.723 |
Carmen | +1.614 |
Neg logit contributions | |
antha | -3.263 |
iversal | -2.887 |
unction | -2.860 |
arov | -2.841 |
66666666 | -2.757 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
disproportion | +1.838 |
Penet | +1.343 |
Valkyrie | +1.295 |
disadvant | +1.279 |
Carmen | +1.224 |
Neg logit contributions | |
antha | -2.059 |
iversal | -1.808 |
arov | -1.791 |
unction | -1.787 |
66666666 | -1.725 |
Token | Office |
Token ID | 4452 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
disproportion | +1.767 |
Penet | +1.294 |
Valkyrie | +1.253 |
disadvant | +1.243 |
Carmen | +1.179 |
Neg logit contributions | |
antha | -1.910 |
iversal | -1.672 |
arov | -1.658 |
unction | -1.652 |
66666666 | -1.593 |
Token | for |
Token ID | 329 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
disproportion | +3.307 |
Penet | +2.531 |
Valkyrie | +2.448 |
disadvant | +2.413 |
Carmen | +2.359 |
Neg logit contributions | |
antha | -2.964 |
iversal | -2.537 |
arov | -2.516 |
unction | -2.483 |
66666666 | -2.376 |
Token | National |
Token ID | 2351 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
disproportion | +2.985 |
Penet | +2.257 |
Valkyrie | +2.143 |
disadvant | +2.095 |
Carmen | +2.066 |
Neg logit contributions | |
antha | -2.820 |
arov | -2.460 |
iversal | -2.375 |
unction | -2.366 |
66666666 | -2.301 |
Token | Statistics |
Token ID | 14370 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
disproportion | +1.389 |
Penet | +0.795 |
disadvant | +0.752 |
Valkyrie | +0.752 |
Carmen | +0.647 |
Neg logit contributions | |
antha | -3.095 |
iversal | -2.800 |
unction | -2.778 |
arov | -2.776 |
66666666 | -2.692 |
Token | said |
Token ID | 531 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
disproportion | +5.365 |
Penet | +3.637 |
disadvant | +3.421 |
Valkyrie | +3.390 |
scapego | +3.271 |
Neg logit contributions | |
antha | -8.176 |
iversal | -7.329 |
unction | -7.304 |
arov | -7.206 |
66666666 | -6.984 |
Token | industrial |
Token ID | 7593 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
antha | +0.021 |
iversal | +0.018 |
arov | +0.018 |
unction | +0.018 |
66666666 | +0.017 |
Neg logit contributions | |
disproportion | -0.019 |
Penet | -0.014 |
Valkyrie | -0.013 |
disadvant | -0.013 |
Carmen | -0.013 |
Token | output |
Token ID | 5072 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
antha | +0.409 |
iversal | +0.339 |
arov | +0.338 |
unction | +0.337 |
66666666 | +0.323 |
Neg logit contributions | |
disproportion | -0.582 |
Penet | -0.456 |
Valkyrie | -0.445 |
disadvant | -0.444 |
Carmen | -0.424 |
Token | rose |
Token ID | 8278 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
disproportion | +1.127 |
Penet | +0.820 |
Valkyrie | +0.792 |
disadvant | +0.789 |
Carmen | +0.742 |
Neg logit contributions | |
antha | -1.246 |
iversal | -1.092 |
arov | -1.081 |
unction | -1.079 |
66666666 | -1.039 |
Token | more |
Token ID | 517 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
disproportion | +0.031 |
Penet | +0.024 |
Valkyrie | +0.023 |
disadvant | +0.023 |
Carmen | +0.022 |
Neg logit contributions | |
antha | -0.027 |
iversal | -0.023 |
arov | -0.023 |
unction | -0.023 |
66666666 | -0.022 |
Token | economic |
Token ID | 17079 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
antha | +0.167 |
iversal | +0.141 |
arov | +0.141 |
unction | +0.139 |
66666666 | +0.134 |
Neg logit contributions | |
disproportion | -0.215 |
Penet | -0.165 |
Valkyrie | -0.160 |
disadvant | -0.160 |
Carmen | -0.153 |
Token | factors |
Token ID | 5087 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
disproportion | +4.117 |
Penet | +2.959 |
disadvant | +2.855 |
Valkyrie | +2.800 |
scapego | +2.691 |
Neg logit contributions | |
antha | -4.675 |
iversal | -4.137 |
arov | -4.066 |
unction | -4.060 |
66666666 | -3.900 |
Token | also |
Token ID | 635 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
disproportion | +0.432 |
Penet | +0.315 |
Valkyrie | +0.306 |
disadvant | +0.303 |
Carmen | +0.286 |
Neg logit contributions | |
antha | -0.479 |
iversal | -0.419 |
arov | -0.416 |
unction | -0.415 |
66666666 | -0.401 |
Token | have |
Token ID | 423 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
disproportion | +2.176 |
Penet | +1.546 |
Valkyrie | +1.487 |
disadvant | +1.481 |
Carmen | +1.387 |
Neg logit contributions | |
antha | -2.675 |
iversal | -2.354 |
arov | -2.333 |
unction | -2.331 |
66666666 | -2.246 |
Token | a |
Token ID | 257 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
disproportion | +1.258 |
Penet | +0.899 |
Valkyrie | +0.868 |
disadvant | +0.860 |
Carmen | +0.807 |
Neg logit contributions | |
antha | -1.552 |
iversal | -1.363 |
arov | -1.356 |
unction | -1.352 |
66666666 | -1.306 |
Token | direct |
Token ID | 1277 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
disproportion | +1.535 |
Penet | +1.064 |
Valkyrie | +1.022 |
disadvant | +1.013 |
Carmen | +0.943 |
Neg logit contributions | |
antha | -2.161 |
iversal | -1.914 |
arov | -1.902 |
unction | -1.899 |
66666666 | -1.840 |
Token | impact |
Token ID | 2928 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
disproportion | +4.793 |
Penet | +2.888 |
disadvant | +2.832 |
Valkyrie | +2.749 |
scapego | +2.517 |
Neg logit contributions | |
antha | -8.819 |
iversal | -8.041 |
arov | -7.916 |
unction | -7.907 |
66666666 | -7.611 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
disproportion | +3.586 |
Penet | +2.423 |
disadvant | +2.381 |
Valkyrie | +2.330 |
disproportionately | +2.205 |
Neg logit contributions | |
antha | -4.770 |
iversal | -4.213 |
arov | -4.192 |
unction | -4.149 |
66666666 | -4.030 |
Token | Lower |
Token ID | 16048 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
disproportion | +2.054 |
Penet | +1.532 |
Valkyrie | +1.479 |
disadvant | +1.455 |
Carmen | +1.394 |
Neg logit contributions | |
antha | -2.144 |
iversal | -1.870 |
arov | -1.849 |
unction | -1.848 |
66666666 | -1.770 |
Token | - |
Token ID | 12 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
disproportion | +1.961 |
Penet | +1.448 |
Valkyrie | +1.396 |
disadvant | +1.382 |
Carmen | +1.319 |
Neg logit contributions | |
antha | -2.024 |
iversal | -1.774 |
unction | -1.750 |
arov | -1.749 |
66666666 | -1.678 |
Token | class |
Token ID | 4871 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
disproportion | +0.905 |
Penet | +0.697 |
Valkyrie | +0.675 |
disadvant | +0.674 |
Carmen | +0.644 |
Neg logit contributions | |
antha | -0.717 |
iversal | -0.612 |
unction | -0.605 |
arov | -0.605 |
66666666 | -0.576 |
Token | pass |
Token ID | 1208 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
disproportion | +0.079 |
Penet | +0.057 |
disadvant | +0.056 |
Valkyrie | +0.056 |
Carmen | +0.053 |
Neg logit contributions | |
antha | -0.085 |
iversal | -0.074 |
arov | -0.074 |
unction | -0.074 |
66666666 | -0.071 |
Token | pressures |
Token ID | 18895 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
disproportion | +1.687 |
Penet | +1.269 |
Valkyrie | +1.230 |
disadvant | +1.222 |
Carmen | +1.157 |
Neg logit contributions | |
antha | -1.586 |
iversal | -1.374 |
unction | -1.354 |
arov | -1.352 |
66666666 | -1.303 |
Token | , |
Token ID | 11 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
antha | +0.390 |
iversal | +0.339 |
arov | +0.338 |
unction | +0.336 |
66666666 | +0.323 |
Neg logit contributions | |
disproportion | -0.362 |
Penet | -0.264 |
Valkyrie | -0.256 |
disadvant | -0.255 |
Carmen | -0.241 |
Token | per |
Token ID | 583 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
antha | +0.493 |
arov | +0.428 |
iversal | +0.428 |
unction | +0.423 |
66666666 | +0.409 |
Neg logit contributions | |
disproportion | -0.449 |
Penet | -0.328 |
Valkyrie | -0.317 |
disadvant | -0.315 |
Carmen | -0.297 |
Token | Football |
Token ID | 9957 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
disproportion | +2.525 |
Penet | +1.761 |
Valkyrie | +1.686 |
disadvant | +1.641 |
Carmen | +1.557 |
Neg logit contributions | |
antha | -3.611 |
iversal | -3.220 |
arov | -3.190 |
unction | -3.188 |
66666666 | -3.076 |
Token | Outs |
Token ID | 46580 |
Feature activation | -7.38e+00 |
Pos logit contributions | |
disproportion | +2.208 |
Penet | +1.696 |
Valkyrie | +1.626 |
disadvant | +1.606 |
Carmen | +1.533 |
Neg logit contributions | |
antha | -2.079 |
iversal | -1.807 |
unction | -1.798 |
arov | -1.778 |
66666666 | -1.728 |
Token | iders |
Token ID | 4157 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
disproportion | +4.549 |
Penet | +2.972 |
Valkyrie | +2.816 |
disadvant | +2.500 |
Carmen | +2.398 |
Neg logit contributions | |
antha | -8.915 |
iversal | -8.045 |
arov | -7.882 |
unction | -7.839 |
atomic | -7.667 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
disproportion | +2.951 |
Penet | +2.157 |
Valkyrie | +2.057 |
disadvant | +2.024 |
Carmen | +1.913 |
Neg logit contributions | |
antha | -3.657 |
iversal | -3.181 |
unction | -3.156 |
arov | -3.142 |
66666666 | -3.030 |
Token | While |
Token ID | 2893 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
disproportion | +0.124 |
Penet | +0.093 |
Valkyrie | +0.090 |
disadvant | +0.089 |
Carmen | +0.085 |
Neg logit contributions | |
antha | -0.120 |
iversal | -0.104 |
arov | -0.103 |
unction | -0.103 |
66666666 | -0.099 |
Token | Wake |
Token ID | 20441 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
disproportion | +0.095 |
Penet | +0.070 |
Valkyrie | +0.068 |
disadvant | +0.068 |
Carmen | +0.064 |
Neg logit contributions | |
antha | -0.100 |
iversal | -0.087 |
arov | -0.086 |
unction | -0.086 |
66666666 | -0.083 |
Token | � |
Token ID | 447 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
antha | +0.794 |
iversal | +0.689 |
arov | +0.687 |
unction | +0.681 |
66666666 | +0.658 |
Neg logit contributions | |
disproportion | -0.790 |
Penet | -0.585 |
Valkyrie | -0.569 |
disadvant | -0.568 |
Carmen | -0.535 |
Token | � |
Token ID | 247 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
disproportion | +0.190 |
Penet | +0.122 |
disadvant | +0.119 |
Valkyrie | +0.117 |
scapego | +0.107 |
Neg logit contributions | |
antha | -0.315 |
arov | -0.283 |
iversal | -0.282 |
unction | -0.280 |
66666666 | -0.274 |
Token | s |
Token ID | 82 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
disproportion | +0.582 |
Penet | +0.447 |
Valkyrie | +0.434 |
disadvant | +0.431 |
Carmen | +0.413 |
Neg logit contributions | |
antha | -0.475 |
iversal | -0.403 |
arov | -0.400 |
unction | -0.398 |
66666666 | -0.382 |
Token | sake |
Token ID | 11060 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
disproportion | +1.844 |
Penet | +1.333 |
Valkyrie | +1.291 |
disadvant | +1.275 |
Carmen | +1.208 |
Neg logit contributions | |
antha | -2.174 |
iversal | -1.909 |
arov | -1.896 |
unction | -1.893 |
66666666 | -1.824 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
antha | +0.417 |
iversal | +0.366 |
arov | +0.364 |
unction | +0.363 |
66666666 | +0.350 |
Neg logit contributions | |
disproportion | -0.341 |
Penet | -0.244 |
Valkyrie | -0.236 |
disadvant | -0.234 |
Carmen | -0.220 |
Token | American |
Token ID | 1605 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
disproportion | +1.369 |
Penet | +1.016 |
Valkyrie | +0.986 |
disadvant | +0.968 |
Carmen | +0.929 |
Neg logit contributions | |
antha | -1.424 |
iversal | -1.246 |
unction | -1.233 |
arov | -1.229 |
66666666 | -1.179 |
Token | Horror |
Token ID | 22732 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
disproportion | +0.744 |
Penet | +0.511 |
Valkyrie | +0.490 |
disadvant | +0.479 |
Carmen | +0.449 |
Neg logit contributions | |
antha | -1.136 |
iversal | -1.010 |
unction | -1.003 |
arov | -1.002 |
66666666 | -0.967 |
Token | Story |
Token ID | 8362 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
disproportion | +5.803 |
Penet | +4.180 |
Valkyrie | +3.975 |
disadvant | +3.816 |
Carmen | +3.696 |
Neg logit contributions | |
antha | -7.587 |
iversal | -6.746 |
arov | -6.649 |
unction | -6.643 |
66666666 | -6.468 |
Token | : |
Token ID | 25 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
disproportion | +1.067 |
Penet | +0.782 |
Valkyrie | +0.757 |
disadvant | +0.754 |
Carmen | +0.710 |
Neg logit contributions | |
antha | -1.143 |
iversal | -0.996 |
arov | -0.989 |
unction | -0.986 |
66666666 | -0.951 |
Token | Murder |
Token ID | 23375 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
antha | +0.092 |
iversal | +0.080 |
arov | +0.079 |
unction | +0.079 |
66666666 | +0.076 |
Neg logit contributions | |
disproportion | -0.090 |
Penet | -0.067 |
Valkyrie | -0.065 |
disadvant | -0.065 |
Carmen | -0.061 |
Token | House |
Token ID | 2097 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
disproportion | +0.854 |
Penet | +0.630 |
Valkyrie | +0.611 |
disadvant | +0.600 |
Carmen | +0.572 |
Neg logit contributions | |
antha | -0.916 |
iversal | -0.797 |
arov | -0.790 |
unction | -0.788 |
66666666 | -0.761 |
Token | opened |
Token ID | 4721 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
disproportion | +1.764 |
Penet | +1.293 |
Valkyrie | +1.249 |
disadvant | +1.240 |
Carmen | +1.169 |
Neg logit contributions | |
antha | -1.927 |
iversal | -1.683 |
arov | -1.666 |
unction | -1.664 |
66666666 | -1.601 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
disproportion | +0.332 |
Penet | +0.243 |
Valkyrie | +0.235 |
disadvant | +0.233 |
Carmen | +0.220 |
Neg logit contributions | |
antha | -0.362 |
iversal | -0.316 |
arov | -0.314 |
unction | -0.313 |
66666666 | -0.302 |
Token | could |
Token ID | 714 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
disproportion | +0.191 |
Penet | +0.140 |
Valkyrie | +0.136 |
disadvant | +0.135 |
Carmen | +0.127 |
Neg logit contributions | |
antha | -0.205 |
iversal | -0.179 |
arov | -0.177 |
unction | -0.177 |
66666666 | -0.170 |
Token | upset |
Token ID | 9247 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
disproportion | +1.626 |
Penet | +1.199 |
Valkyrie | +1.161 |
disadvant | +1.153 |
Carmen | +1.090 |
Neg logit contributions | |
antha | -1.694 |
iversal | -1.474 |
arov | -1.460 |
unction | -1.459 |
66666666 | -1.403 |
Token | Na |
Token ID | 11013 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
disproportion | +0.255 |
Penet | +0.187 |
Valkyrie | +0.181 |
disadvant | +0.180 |
Carmen | +0.169 |
Neg logit contributions | |
antha | -0.276 |
iversal | -0.241 |
arov | -0.239 |
unction | -0.239 |
66666666 | -0.230 |
Token | ` |
Token ID | 63 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
antha | +0.111 |
iversal | +0.093 |
arov | +0.092 |
unction | +0.091 |
66666666 | +0.087 |
Neg logit contributions | |
disproportion | -0.156 |
Penet | -0.121 |
Valkyrie | -0.118 |
disadvant | -0.118 |
Carmen | -0.113 |
Token | Vi |
Token ID | 38432 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
antha | +1.529 |
arov | +1.348 |
iversal | +1.322 |
unction | +1.316 |
atomic | +1.275 |
Neg logit contributions | |
disproportion | -1.441 |
Penet | -1.031 |
disadvant | -1.018 |
Valkyrie | -0.990 |
Carmen | -0.948 |
Token | in |
Token ID | 287 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
disproportion | +6.239 |
Penet | +4.578 |
Valkyrie | +4.458 |
disadvant | +4.297 |
Carmen | +4.063 |
Neg logit contributions | |
antha | -7.035 |
iversal | -6.147 |
arov | -6.128 |
unction | -6.090 |
66666666 | -5.843 |
Token | some |
Token ID | 617 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
antha | +0.492 |
iversal | +0.430 |
arov | +0.428 |
unction | +0.426 |
66666666 | +0.411 |
Neg logit contributions | |
disproportion | -0.441 |
Penet | -0.320 |
Valkyrie | -0.310 |
disadvant | -0.309 |
Carmen | -0.290 |
Token | universe |
Token ID | 6881 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
antha | +0.775 |
iversal | +0.675 |
arov | +0.671 |
unction | +0.666 |
66666666 | +0.643 |
Neg logit contributions | |
disproportion | -0.736 |
Penet | -0.543 |
disadvant | -0.526 |
Valkyrie | -0.524 |
Carmen | -0.493 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
antha | +1.204 |
iversal | +1.057 |
arov | +1.040 |
unction | +1.037 |
66666666 | +1.002 |
Neg logit contributions | |
disproportion | -1.129 |
Penet | -0.832 |
disadvant | -0.801 |
Valkyrie | -0.800 |
Carmen | -0.751 |
Token | but |
Token ID | 475 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
antha | +0.102 |
iversal | +0.089 |
arov | +0.089 |
unction | +0.088 |
66666666 | +0.085 |
Neg logit contributions | |
disproportion | -0.092 |
Penet | -0.067 |
Valkyrie | -0.065 |
disadvant | -0.064 |
Carmen | -0.061 |
Token | group |
Token ID | 1448 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
antha | +0.822 |
iversal | +0.714 |
arov | +0.711 |
unction | +0.707 |
66666666 | +0.683 |
Neg logit contributions | |
disproportion | -0.791 |
Penet | -0.584 |
disadvant | -0.566 |
Valkyrie | -0.566 |
Carmen | -0.529 |
Token | Raqqa |
Token ID | 30391 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
antha | +0.523 |
iversal | +0.456 |
arov | +0.454 |
unction | +0.451 |
66666666 | +0.436 |
Neg logit contributions | |
disproportion | -0.480 |
Penet | -0.350 |
Valkyrie | -0.339 |
disadvant | -0.338 |
Carmen | -0.317 |
Token | is |
Token ID | 318 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
antha | +1.233 |
iversal | +1.073 |
arov | +1.061 |
unction | +1.059 |
66666666 | +1.025 |
Neg logit contributions | |
disproportion | -1.205 |
Penet | -0.887 |
disadvant | -0.863 |
Valkyrie | -0.857 |
scapego | -0.808 |
Token | Being |
Token ID | 11204 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
disproportion | +1.297 |
Penet | +0.904 |
Valkyrie | +0.865 |
disadvant | +0.850 |
Carmen | +0.799 |
Neg logit contributions | |
antha | -1.918 |
iversal | -1.706 |
arov | -1.693 |
unction | -1.670 |
66666666 | -1.621 |
Token | Sl |
Token ID | 3454 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
antha | +0.593 |
arov | +0.510 |
iversal | +0.508 |
unction | +0.504 |
66666666 | +0.486 |
Neg logit contributions | |
disproportion | -0.733 |
disadvant | -0.549 |
Penet | -0.548 |
Valkyrie | -0.538 |
scapego | -0.512 |
Token | aughtered |
Token ID | 32734 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
disproportion | +1.993 |
Penet | +1.450 |
Valkyrie | +1.386 |
disadvant | +1.312 |
Carmen | +1.288 |
Neg logit contributions | |
antha | -2.299 |
iversal | -2.041 |
unction | -2.001 |
arov | -1.994 |
66666666 | -1.976 |
Token | Sil |
Token ID | 4243 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
disproportion | +7.447 |
Penet | +5.915 |
Valkyrie | +5.617 |
disadvant | +5.451 |
Carmen | +5.310 |
Neg logit contributions | |
antha | -5.993 |
iversal | -5.008 |
arov | -4.966 |
unction | -4.807 |
atomic | -4.629 |
Token | ently |
Token ID | 1473 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
antha | +0.625 |
iversal | +0.547 |
unction | +0.543 |
arov | +0.540 |
66666666 | +0.525 |
Neg logit contributions | |
disproportion | -0.567 |
Penet | -0.414 |
disadvant | -0.409 |
Valkyrie | -0.400 |
Carmen | -0.375 |
Token | . |
Token ID | 13 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
disproportion | +1.796 |
Penet | +1.298 |
Valkyrie | +1.252 |
disadvant | +1.243 |
Carmen | +1.170 |
Neg logit contributions | |
antha | -2.095 |
iversal | -1.834 |
arov | -1.820 |
unction | -1.814 |
66666666 | -1.748 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
disproportion | +0.721 |
Penet | +0.543 |
Valkyrie | +0.524 |
disadvant | +0.517 |
Carmen | +0.493 |
Neg logit contributions | |
antha | -0.721 |
iversal | -0.625 |
unction | -0.619 |
arov | -0.616 |
66666666 | -0.591 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
disproportion | +1.463 |
Penet | +1.096 |
Valkyrie | +1.063 |
disadvant | +1.051 |
Carmen | +1.002 |
Neg logit contributions | |
antha | -1.426 |
iversal | -1.235 |
arov | -1.220 |
unction | -1.218 |
66666666 | -1.168 |
Token | lower |
Token ID | 2793 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
antha | +0.168 |
iversal | +0.147 |
arov | +0.146 |
unction | +0.146 |
66666666 | +0.141 |
Neg logit contributions | |
disproportion | -0.136 |
Penet | -0.097 |
Valkyrie | -0.094 |
disadvant | -0.093 |
Carmen | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
disproportion | +1.833 |
Penet | +1.333 |
Valkyrie | +1.284 |
disadvant | +1.275 |
Carmen | +1.210 |
Neg logit contributions | |
antha | -2.055 |
iversal | -1.797 |
arov | -1.781 |
unction | -1.781 |
66666666 | -1.711 |
Token | wife |
Token ID | 3656 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
antha | +0.181 |
iversal | +0.157 |
arov | +0.157 |
unction | +0.157 |
66666666 | +0.151 |
Neg logit contributions | |
disproportion | -0.156 |
Penet | -0.113 |
Valkyrie | -0.109 |
disadvant | -0.109 |
Carmen | -0.102 |
Token | 's |
Token ID | 338 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
disproportion | +0.662 |
Penet | +0.490 |
Valkyrie | +0.474 |
disadvant | +0.471 |
Carmen | +0.446 |
Neg logit contributions | |
antha | -0.681 |
iversal | -0.591 |
arov | -0.587 |
unction | -0.585 |
66666666 | -0.563 |
Token | life |
Token ID | 1204 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
disproportion | +0.701 |
Penet | +0.511 |
Valkyrie | +0.494 |
disadvant | +0.492 |
Carmen | +0.462 |
Neg logit contributions | |
antha | -0.783 |
iversal | -0.682 |
arov | -0.679 |
unction | -0.675 |
66666666 | -0.653 |
Token | expectancy |
Token ID | 29098 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
disproportion | +0.221 |
Penet | +0.154 |
Valkyrie | +0.148 |
disadvant | +0.147 |
Carmen | +0.137 |
Neg logit contributions | |
antha | -0.303 |
iversal | -0.268 |
arov | -0.266 |
unction | -0.266 |
66666666 | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
disproportion | +5.865 |
Penet | +4.148 |
disadvant | +3.932 |
Valkyrie | +3.905 |
Carmen | +3.709 |
Neg logit contributions | |
antha | -7.397 |
arov | -6.564 |
iversal | -6.564 |
unction | -6.495 |
66666666 | -6.218 |
Token | This |
Token ID | 770 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
disproportion | +0.721 |
Penet | +0.535 |
disadvant | +0.521 |
Valkyrie | +0.520 |
Carmen | +0.490 |
Neg logit contributions | |
antha | -0.687 |
iversal | -0.593 |
arov | -0.590 |
unction | -0.587 |
66666666 | -0.566 |
Token | is |
Token ID | 318 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
disproportion | +0.167 |
Penet | +0.125 |
Valkyrie | +0.120 |
disadvant | +0.120 |
Carmen | +0.113 |
Neg logit contributions | |
antha | -0.171 |
iversal | -0.148 |
arov | -0.148 |
unction | -0.147 |
66666666 | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
disproportion | +1.041 |
Penet | +0.754 |
Valkyrie | +0.727 |
disadvant | +0.723 |
Carmen | +0.679 |
Neg logit contributions | |
antha | -1.208 |
iversal | -1.057 |
arov | -1.052 |
unction | -1.048 |
66666666 | -1.012 |
Token | case |
Token ID | 1339 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
antha | +0.151 |
arov | +0.131 |
iversal | +0.131 |
unction | +0.131 |
66666666 | +0.126 |
Neg logit contributions | |
disproportion | -0.118 |
Penet | -0.084 |
Valkyrie | -0.080 |
disadvant | -0.080 |
Carmen | -0.074 |
Token | Washington |
Token ID | 2669 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
disproportion | +0.849 |
Penet | +0.609 |
Valkyrie | +0.587 |
disadvant | +0.581 |
Carmen | +0.548 |
Neg logit contributions | |
antha | -1.037 |
iversal | -0.913 |
arov | -0.906 |
unction | -0.903 |
66666666 | -0.871 |
Token | Post |
Token ID | 2947 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
disproportion | +1.302 |
Penet | +0.926 |
Valkyrie | +0.895 |
disadvant | +0.893 |
Carmen | +0.833 |
Neg logit contributions | |
antha | -1.589 |
iversal | -1.398 |
arov | -1.386 |
unction | -1.384 |
66666666 | -1.338 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
disproportion | +1.648 |
Penet | +1.184 |
Valkyrie | +1.137 |
disadvant | +1.130 |
Carmen | +1.068 |
Neg logit contributions | |
antha | -2.024 |
iversal | -1.770 |
arov | -1.763 |
unction | -1.754 |
66666666 | -1.699 |
Token | The |
Token ID | 383 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
disproportion | +0.127 |
Penet | +0.094 |
Valkyrie | +0.091 |
disadvant | +0.091 |
Carmen | +0.086 |
Neg logit contributions | |
antha | -0.129 |
iversal | -0.112 |
arov | -0.111 |
unction | -0.111 |
66666666 | -0.106 |
Token | Daily |
Token ID | 6714 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
disproportion | +0.598 |
Penet | +0.434 |
Valkyrie | +0.419 |
disadvant | +0.416 |
Carmen | +0.392 |
Neg logit contributions | |
antha | -0.685 |
iversal | -0.601 |
arov | -0.596 |
unction | -0.594 |
66666666 | -0.573 |
Token | Beast |
Token ID | 10984 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
disproportion | +1.970 |
Penet | +1.378 |
Valkyrie | +1.322 |
disadvant | +1.309 |
Carmen | +1.224 |
Neg logit contributions | |
antha | -2.695 |
iversal | -2.388 |
arov | -2.372 |
unction | -2.366 |
66666666 | -2.291 |
Token | , |
Token ID | 11 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
disproportion | +5.589 |
Penet | +3.969 |
Valkyrie | +3.760 |
disadvant | +3.732 |
Carmen | +3.572 |
Neg logit contributions | |
antha | -7.645 |
arov | -6.642 |
iversal | -6.630 |
unction | -6.590 |
66666666 | -6.434 |
Token | Politico |
Token ID | 27096 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
disproportion | +0.760 |
Penet | +0.564 |
Valkyrie | +0.547 |
disadvant | +0.543 |
Carmen | +0.515 |
Neg logit contributions | |
antha | -0.771 |
iversal | -0.669 |
arov | -0.664 |
unction | -0.662 |
66666666 | -0.636 |
Token | , |
Token ID | 11 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
disproportion | +2.491 |
Penet | +1.784 |
Valkyrie | +1.708 |
disadvant | +1.702 |
Carmen | +1.606 |
Neg logit contributions | |
antha | -3.103 |
iversal | -2.705 |
arov | -2.697 |
unction | -2.685 |
66666666 | -2.598 |
Token | Buzz |
Token ID | 15753 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
disproportion | +0.590 |
Penet | +0.435 |
Valkyrie | +0.421 |
disadvant | +0.418 |
Carmen | +0.395 |
Neg logit contributions | |
antha | -0.622 |
iversal | -0.541 |
arov | -0.537 |
unction | -0.535 |
66666666 | -0.516 |
Token | feed |
Token ID | 12363 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
disproportion | +2.534 |
Penet | +1.764 |
Valkyrie | +1.685 |
disadvant | +1.668 |
Carmen | +1.566 |
Neg logit contributions | |
antha | -3.559 |
iversal | -3.125 |
unction | -3.115 |
arov | -3.109 |
66666666 | -3.009 |
Token | ). |
Token ID | 737 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
antha | +0.360 |
iversal | +0.312 |
arov | +0.310 |
unction | +0.309 |
66666666 | +0.297 |
Neg logit contributions | |
disproportion | -0.361 |
Penet | -0.270 |
Valkyrie | -0.259 |
disadvant | -0.259 |
Carmen | -0.242 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
antha | +1.371 |
arov | +1.179 |
iversal | +1.171 |
unction | +1.167 |
66666666 | +1.134 |
Neg logit contributions | |
disproportion | -1.549 |
Penet | -1.147 |
disadvant | -1.141 |
Valkyrie | -1.113 |
scapego | -1.058 |
Token |
|
Token ID | 198 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
antha | +0.877 |
arov | +0.758 |
unction | +0.748 |
iversal | +0.746 |
66666666 | +0.732 |
Neg logit contributions | |
disproportion | -1.035 |
disadvant | -0.779 |
Penet | -0.770 |
Valkyrie | -0.751 |
scapego | -0.713 |
Token | F |
Token ID | 37 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
antha | +0.544 |
iversal | +0.457 |
arov | +0.454 |
unction | +0.452 |
66666666 | +0.432 |
Neg logit contributions | |
disproportion | -0.751 |
Penet | -0.584 |
Valkyrie | -0.568 |
disadvant | -0.567 |
Carmen | -0.540 |
Token | iled |
Token ID | 3902 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
antha | +1.056 |
iversal | +0.908 |
arov | +0.904 |
unction | +0.903 |
66666666 | +0.863 |
Neg logit contributions | |
disproportion | -1.159 |
Penet | -0.873 |
Valkyrie | -0.848 |
disadvant | -0.845 |
Carmen | -0.798 |
Token | Under |
Token ID | 4698 |
Feature activation | -7.25e+00 |
Pos logit contributions | |
disproportion | +0.919 |
Penet | +0.685 |
Valkyrie | +0.662 |
disadvant | +0.650 |
Carmen | +0.623 |
Neg logit contributions | |
antha | -0.931 |
iversal | -0.810 |
arov | -0.806 |
unction | -0.793 |
66666666 | -0.767 |
Token | : |
Token ID | 25 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
disproportion | +5.782 |
Penet | +4.230 |
Valkyrie | +3.998 |
Carmen | +3.870 |
disadvant | +3.804 |
Neg logit contributions | |
antha | -7.515 |
arov | -6.563 |
unction | -6.515 |
iversal | -6.508 |
66666666 | -6.346 |
Token | c |
Token ID | 269 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
disproportion | +0.605 |
Penet | +0.445 |
Valkyrie | +0.431 |
disadvant | +0.428 |
Carmen | +0.404 |
Neg logit contributions | |
antha | -0.643 |
iversal | -0.560 |
arov | -0.556 |
unction | -0.554 |
66666666 | -0.534 |
Token | bp |
Token ID | 46583 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
disproportion | +2.123 |
Penet | +1.638 |
Valkyrie | +1.592 |
disadvant | +1.573 |
Carmen | +1.517 |
Neg logit contributions | |
antha | -1.724 |
iversal | -1.470 |
arov | -1.450 |
unction | -1.441 |
66666666 | -1.387 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
antha | +0.133 |
iversal | +0.115 |
arov | +0.115 |
unction | +0.114 |
66666666 | +0.110 |
Neg logit contributions | |
disproportion | -0.135 |
Penet | -0.100 |
Valkyrie | -0.097 |
disadvant | -0.097 |
Carmen | -0.091 |
Token | d |
Token ID | 288 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
disproportion | +0.957 |
Penet | +0.698 |
Valkyrie | +0.675 |
disadvant | +0.671 |
Carmen | +0.633 |
Neg logit contributions | |
antha | -1.061 |
iversal | -0.927 |
arov | -0.920 |
unction | -0.917 |
66666666 | -0.884 |
Token | stepped |
Token ID | 10764 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
disproportion | +1.549 |
Penet | +1.124 |
Valkyrie | +1.086 |
disadvant | +1.080 |
Carmen | +1.016 |
Neg logit contributions | |
antha | -1.756 |
iversal | -1.536 |
arov | -1.525 |
unction | -1.521 |
66666666 | -1.467 |
Token | away |
Token ID | 1497 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
disproportion | +0.575 |
Penet | +0.422 |
Valkyrie | +0.411 |
disadvant | +0.406 |
Carmen | +0.384 |
Neg logit contributions | |
antha | -0.600 |
iversal | -0.521 |
arov | -0.517 |
unction | -0.516 |
66666666 | -0.496 |
Token | from |
Token ID | 422 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
antha | +0.844 |
iversal | +0.732 |
arov | +0.726 |
unction | +0.724 |
66666666 | +0.696 |
Neg logit contributions | |
disproportion | -0.846 |
Penet | -0.629 |
Valkyrie | -0.610 |
disadvant | -0.607 |
Carmen | -0.574 |
Token | their |
Token ID | 511 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
antha | +0.379 |
iversal | +0.332 |
arov | +0.329 |
unction | +0.329 |
66666666 | +0.317 |
Neg logit contributions | |
disproportion | -0.328 |
Penet | -0.238 |
Valkyrie | -0.229 |
disadvant | -0.228 |
Carmen | -0.213 |
Token | original |
Token ID | 2656 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
antha | +1.294 |
iversal | +1.135 |
arov | +1.131 |
unction | +1.123 |
66666666 | +1.088 |
Neg logit contributions | |
disproportion | -1.018 |
Penet | -0.726 |
Valkyrie | -0.698 |
disadvant | -0.697 |
Carmen | -0.649 |
Token | dist |
Token ID | 1233 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
antha | +1.088 |
iversal | +0.947 |
arov | +0.944 |
unction | +0.939 |
66666666 | +0.908 |
Neg logit contributions | |
disproportion | -0.954 |
Penet | -0.693 |
disadvant | -0.670 |
Valkyrie | -0.670 |
Carmen | -0.626 |
Token | aste |
Token ID | 4594 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
disproportion | +5.284 |
Penet | +3.614 |
Valkyrie | +3.499 |
disadvant | +3.475 |
Carmen | +3.210 |
Neg logit contributions | |
antha | -7.643 |
iversal | -6.768 |
arov | -6.696 |
66666666 | -6.646 |
unction | -6.632 |
Token | for |
Token ID | 329 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
disproportion | +0.847 |
Penet | +0.636 |
Valkyrie | +0.618 |
disadvant | +0.614 |
Carmen | +0.584 |
Neg logit contributions | |
antha | -0.778 |
iversal | -0.667 |
arov | -0.664 |
unction | -0.659 |
66666666 | -0.633 |
Token | the |
Token ID | 262 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
disproportion | +0.642 |
Penet | +0.459 |
Valkyrie | +0.443 |
disadvant | +0.442 |
Carmen | +0.411 |
Neg logit contributions | |
antha | -0.786 |
iversal | -0.691 |
arov | -0.687 |
unction | -0.685 |
66666666 | -0.662 |
Token | sub |
Token ID | 850 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
disproportion | +0.432 |
Penet | +0.319 |
Valkyrie | +0.309 |
disadvant | +0.308 |
Carmen | +0.290 |
Neg logit contributions | |
antha | -0.449 |
iversal | -0.390 |
arov | -0.387 |
unction | -0.386 |
66666666 | -0.372 |
Token | culture |
Token ID | 25584 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
antha | +0.092 |
iversal | +0.077 |
arov | +0.076 |
unction | +0.076 |
66666666 | +0.072 |
Neg logit contributions | |
disproportion | -0.131 |
Penet | -0.102 |
Valkyrie | -0.100 |
disadvant | -0.100 |
Carmen | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
antha | +0.062 |
iversal | +0.055 |
arov | +0.054 |
unction | +0.054 |
66666666 | +0.052 |
Neg logit contributions | |
disproportion | -0.051 |
Penet | -0.036 |
disadvant | -0.035 |
Valkyrie | -0.035 |
Carmen | -0.033 |
Token | air |
Token ID | 1633 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
disproportion | +0.084 |
Penet | +0.057 |
disadvant | +0.055 |
Valkyrie | +0.054 |
Carmen | +0.051 |
Neg logit contributions | |
antha | -0.120 |
arov | -0.106 |
unction | -0.106 |
iversal | -0.106 |
66666666 | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
disproportion | +0.205 |
Penet | +0.149 |
Valkyrie | +0.143 |
disadvant | +0.143 |
Carmen | +0.134 |
Neg logit contributions | |
antha | -0.236 |
iversal | -0.206 |
arov | -0.204 |
unction | -0.204 |
66666666 | -0.197 |
Token | Per |
Token ID | 2448 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
antha | +0.216 |
iversal | +0.186 |
arov | +0.185 |
unction | +0.184 |
66666666 | +0.177 |
Neg logit contributions | |
disproportion | -0.242 |
Penet | -0.181 |
disadvant | -0.178 |
Valkyrie | -0.176 |
Carmen | -0.167 |
Token | Football |
Token ID | 9957 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
disproportion | +1.991 |
Penet | +1.393 |
Valkyrie | +1.336 |
disadvant | +1.311 |
Carmen | +1.236 |
Neg logit contributions | |
antha | -2.730 |
iversal | -2.422 |
arov | -2.404 |
unction | -2.399 |
66666666 | -2.321 |
Token | Outs |
Token ID | 46580 |
Feature activation | -7.20e+00 |
Pos logit contributions | |
disproportion | +1.737 |
Penet | +1.327 |
Valkyrie | +1.277 |
disadvant | +1.267 |
Carmen | +1.207 |
Neg logit contributions | |
antha | -1.581 |
iversal | -1.366 |
unction | -1.354 |
arov | -1.348 |
66666666 | -1.300 |
Token | iders |
Token ID | 4157 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
disproportion | +4.411 |
Penet | +2.941 |
Valkyrie | +2.710 |
disadvant | +2.426 |
Carmen | +2.388 |
Neg logit contributions | |
antha | -8.599 |
iversal | -7.692 |
unction | -7.572 |
arov | -7.546 |
atomic | -7.328 |
Token | chart |
Token ID | 8262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
disproportion | +2.526 |
Penet | +1.817 |
Valkyrie | +1.738 |
disadvant | +1.703 |
Carmen | +1.613 |
Neg logit contributions | |
antha | -3.367 |
iversal | -2.923 |
unction | -2.917 |
arov | -2.907 |
66666666 | -2.808 |
Token | ing |
Token ID | 278 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
disproportion | +1.086 |
Penet | +0.797 |
Valkyrie | +0.767 |
disadvant | +0.763 |
Carmen | +0.718 |
Neg logit contributions | |
antha | -1.193 |
iversal | -1.045 |
unction | -1.032 |
arov | -1.029 |
66666666 | -0.995 |
Token | , |
Token ID | 11 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
disproportion | +0.692 |
Penet | +0.510 |
Valkyrie | +0.494 |
disadvant | +0.491 |
Carmen | +0.463 |
Neg logit contributions | |
antha | -0.724 |
iversal | -0.630 |
arov | -0.624 |
unction | -0.623 |
66666666 | -0.600 |
Token | the |
Token ID | 262 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
disproportion | +1.475 |
Penet | +1.116 |
Valkyrie | +1.083 |
disadvant | +1.072 |
Carmen | +1.017 |
Neg logit contributions | |
antha | -1.350 |
iversal | -1.159 |
arov | -1.144 |
unction | -1.143 |
66666666 | -1.098 |
Token | States |
Token ID | 1829 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
disproportion | +1.990 |
Penet | +1.598 |
Valkyrie | +1.573 |
disadvant | +1.547 |
Carmen | +1.508 |
Neg logit contributions | |
antha | -1.141 |
iversal | -0.938 |
unction | -0.920 |
arov | -0.898 |
66666666 | -0.872 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
antha | +1.350 |
iversal | +1.178 |
arov | +1.170 |
unction | +1.169 |
66666666 | +1.120 |
Neg logit contributions | |
disproportion | -1.269 |
Penet | -0.931 |
Valkyrie | -0.899 |
disadvant | -0.892 |
Carmen | -0.836 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
antha | +0.240 |
iversal | +0.207 |
arov | +0.205 |
unction | +0.204 |
66666666 | +0.196 |
Neg logit contributions | |
disproportion | -0.259 |
Penet | -0.194 |
disadvant | -0.188 |
Valkyrie | -0.188 |
Carmen | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
disproportion | +0.269 |
Penet | +0.201 |
disadvant | +0.198 |
Valkyrie | +0.195 |
Carmen | +0.184 |
Neg logit contributions | |
antha | -0.244 |
arov | -0.210 |
iversal | -0.209 |
unction | -0.208 |
66666666 | -0.201 |
Token | Pan |
Token ID | 15730 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
disproportion | +0.342 |
Penet | +0.267 |
Valkyrie | +0.261 |
disadvant | +0.259 |
Carmen | +0.248 |
Neg logit contributions | |
antha | -0.246 |
iversal | -0.207 |
arov | -0.204 |
unction | -0.204 |
66666666 | -0.194 |
Token | orama |
Token ID | 36161 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
antha | +0.259 |
iversal | +0.210 |
arov | +0.207 |
unction | +0.207 |
66666666 | +0.193 |
Neg logit contributions | |
disproportion | -0.488 |
Penet | -0.392 |
disadvant | -0.385 |
Valkyrie | -0.383 |
Carmen | -0.366 |
Token | : |
Token ID | 25 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
disproportion | +6.378 |
Penet | +4.803 |
Valkyrie | +4.591 |
disadvant | +4.480 |
Carmen | +4.364 |
Neg logit contributions | |
antha | -6.664 |
iversal | -5.840 |
unction | -5.769 |
arov | -5.685 |
66666666 | -5.579 |
Token | How |
Token ID | 1374 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
antha | +0.863 |
iversal | +0.749 |
arov | +0.747 |
unction | +0.743 |
66666666 | +0.714 |
Neg logit contributions | |
disproportion | -0.814 |
Penet | -0.592 |
disadvant | -0.577 |
Valkyrie | -0.573 |
Carmen | -0.536 |
Token | Rolls |
Token ID | 40074 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
disproportion | +0.611 |
Penet | +0.443 |
Valkyrie | +0.428 |
disadvant | +0.427 |
Carmen | +0.401 |
Neg logit contributions | |
antha | -0.689 |
iversal | -0.602 |
arov | -0.598 |
unction | -0.596 |
66666666 | -0.575 |
Token | - |
Token ID | 12 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
disproportion | +2.183 |
Penet | +1.657 |
Valkyrie | +1.618 |
disadvant | +1.587 |
Carmen | +1.523 |
Neg logit contributions | |
antha | -2.006 |
iversal | -1.734 |
unction | -1.703 |
arov | -1.694 |
66666666 | -1.628 |
Token | Roy |
Token ID | 32027 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
disproportion | +0.604 |
Penet | +0.506 |
disadvant | +0.498 |
Valkyrie | +0.497 |
Carmen | +0.482 |
Neg logit contributions | |
antha | -0.146 |
iversal | -0.096 |
arov | -0.096 |
unction | -0.093 |
66666666 | -0.082 |
Token | 't |
Token ID | 470 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
disproportion | +0.555 |
Penet | +0.424 |
Valkyrie | +0.412 |
disadvant | +0.410 |
Carmen | +0.390 |
Neg logit contributions | |
antha | -0.468 |
iversal | -0.400 |
arov | -0.396 |
unction | -0.395 |
66666666 | -0.378 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
disproportion | +0.849 |
Penet | +0.626 |
Valkyrie | +0.605 |
disadvant | +0.604 |
Carmen | +0.567 |
Neg logit contributions | |
antha | -0.888 |
iversal | -0.771 |
arov | -0.767 |
unction | -0.763 |
66666666 | -0.736 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
disproportion | +1.075 |
Penet | +0.788 |
Valkyrie | +0.765 |
disadvant | +0.760 |
Carmen | +0.720 |
Neg logit contributions | |
antha | -1.139 |
iversal | -0.992 |
arov | -0.986 |
unction | -0.981 |
66666666 | -0.943 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
disproportion | +1.041 |
Penet | +0.790 |
Valkyrie | +0.766 |
disadvant | +0.735 |
Carmen | +0.729 |
Neg logit contributions | |
antha | -1.083 |
iversal | -0.946 |
unction | -0.935 |
arov | -0.932 |
66666666 | -0.892 |
Token | D |
Token ID | 35 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
disproportion | +1.153 |
Penet | +0.904 |
Valkyrie | +0.884 |
disadvant | +0.875 |
Carmen | +0.841 |
Neg logit contributions | |
antha | -0.828 |
iversal | -0.699 |
arov | -0.687 |
unction | -0.686 |
66666666 | -0.651 |
Token | IL |
Token ID | 4146 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
antha | +2.438 |
iversal | +2.077 |
arov | +2.061 |
unction | +2.044 |
66666666 | +1.958 |
Neg logit contributions | |
disproportion | -3.009 |
Penet | -2.299 |
Valkyrie | -2.236 |
disadvant | -2.227 |
Carmen | -2.116 |
Token | IP |
Token ID | 4061 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
antha | +4.974 |
iversal | +4.167 |
unction | +4.157 |
arov | +4.102 |
66666666 | +3.957 |
Neg logit contributions | |
disproportion | -6.172 |
Penet | -4.643 |
disadvant | -4.595 |
Valkyrie | -4.562 |
scapego | -4.342 |
Token | S |
Token ID | 311 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
antha | +2.580 |
iversal | +2.223 |
arov | +2.209 |
unction | +2.201 |
66666666 | +2.114 |
Neg logit contributions | |
disproportion | -2.859 |
Penet | -2.140 |
disadvant | -2.100 |
Valkyrie | -2.065 |
scapego | -1.959 |
Token | ARD |
Token ID | 9795 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
antha | +0.265 |
iversal | +0.227 |
arov | +0.225 |
unction | +0.224 |
66666666 | +0.215 |
Neg logit contributions | |
disproportion | -0.314 |
Penet | -0.239 |
Valkyrie | -0.233 |
disadvant | -0.232 |
Carmen | -0.221 |
Token | ES |
Token ID | 1546 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
antha | +0.378 |
iversal | +0.320 |
arov | +0.316 |
unction | +0.315 |
66666666 | +0.301 |
Neg logit contributions | |
disproportion | -0.499 |
Penet | -0.387 |
Valkyrie | -0.377 |
disadvant | -0.375 |
Carmen | -0.358 |
Token | AI |
Token ID | 20185 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
antha | +3.575 |
arov | +3.096 |
iversal | +3.091 |
unction | +3.050 |
66666666 | +2.963 |
Neg logit contributions | |
disproportion | -3.649 |
Penet | -2.674 |
disadvant | -2.626 |
Valkyrie | -2.588 |
scapego | -2.431 |
Token | allied |
Token ID | 22034 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
antha | +0.812 |
iversal | +0.698 |
arov | +0.694 |
unction | +0.686 |
66666666 | +0.665 |
Neg logit contributions | |
disproportion | -0.845 |
Penet | -0.633 |
Valkyrie | -0.615 |
disadvant | -0.614 |
Carmen | -0.579 |
Token | committees |
Token ID | 17460 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
disproportion | +0.266 |
Penet | +0.197 |
disadvant | +0.191 |
Valkyrie | +0.191 |
Carmen | +0.179 |
Neg logit contributions | |
antha | -0.269 |
iversal | -0.233 |
arov | -0.232 |
unction | -0.230 |
66666666 | -0.223 |
Token | can |
Token ID | 460 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
disproportion | +0.067 |
Penet | +0.049 |
Valkyrie | +0.048 |
disadvant | +0.047 |
Carmen | +0.045 |
Neg logit contributions | |
antha | -0.072 |
iversal | -0.063 |
arov | -0.062 |
unction | -0.062 |
66666666 | -0.060 |
Token | do |
Token ID | 466 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
disproportion | +1.074 |
Penet | +0.798 |
Valkyrie | +0.774 |
disadvant | +0.771 |
Carmen | +0.727 |
Neg logit contributions | |
antha | -1.105 |
iversal | -0.961 |
arov | -0.958 |
unction | -0.950 |
66666666 | -0.915 |
Token | the |
Token ID | 262 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
antha | +1.120 |
iversal | +0.989 |
arov | +0.979 |
unction | +0.978 |
66666666 | +0.941 |
Neg logit contributions | |
disproportion | -1.002 |
Penet | -0.734 |
Valkyrie | -0.706 |
disadvant | -0.704 |
Carmen | -0.658 |
Token | same |
Token ID | 976 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
disproportion | +0.054 |
Penet | +0.041 |
Valkyrie | +0.040 |
disadvant | +0.040 |
Carmen | +0.038 |
Neg logit contributions | |
antha | -0.046 |
iversal | -0.039 |
arov | -0.039 |
unction | -0.038 |
66666666 | -0.037 |
Token | this |
Token ID | 428 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
antha | +3.910 |
iversal | +3.414 |
unction | +3.365 |
arov | +3.350 |
66666666 | +3.211 |
Neg logit contributions | |
disproportion | -4.126 |
Penet | -3.149 |
Valkyrie | -3.057 |
disadvant | -2.981 |
Carmen | -2.855 |
Token | year |
Token ID | 614 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
antha | +0.213 |
iversal | +0.186 |
arov | +0.184 |
unction | +0.184 |
66666666 | +0.177 |
Neg logit contributions | |
disproportion | -0.191 |
Penet | -0.139 |
Valkyrie | -0.134 |
disadvant | -0.133 |
Carmen | -0.126 |
Token | with |
Token ID | 351 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
disproportion | +1.687 |
Penet | +1.212 |
Valkyrie | +1.173 |
disadvant | +1.167 |
Carmen | +1.099 |
Neg logit contributions | |
antha | -1.964 |
iversal | -1.715 |
arov | -1.707 |
unction | -1.698 |
66666666 | -1.644 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
antha | +0.025 |
iversal | +0.021 |
arov | +0.021 |
unction | +0.021 |
66666666 | +0.020 |
Neg logit contributions | |
disproportion | -0.022 |
Penet | -0.016 |
Valkyrie | -0.016 |
disadvant | -0.016 |
Carmen | -0.015 |
Token | Koch |
Token ID | 17009 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
disproportion | +0.299 |
Penet | +0.224 |
Valkyrie | +0.217 |
disadvant | +0.216 |
Carmen | +0.205 |
Neg logit contributions | |
antha | -0.280 |
iversal | -0.240 |
arov | -0.240 |
unction | -0.238 |
66666666 | -0.229 |
Token | The |
Token ID | 383 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
antha | +2.619 |
iversal | +2.231 |
unction | +2.205 |
arov | +2.202 |
66666666 | +2.118 |
Neg logit contributions | |
disproportion | -2.922 |
Penet | -2.214 |
disadvant | -2.161 |
Valkyrie | -2.149 |
scapego | -2.011 |
Token | Associated |
Token ID | 10575 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
antha | +0.239 |
iversal | +0.202 |
arov | +0.200 |
unction | +0.199 |
66666666 | +0.189 |
Neg logit contributions | |
disproportion | -0.322 |
Penet | -0.250 |
Valkyrie | -0.244 |
disadvant | -0.242 |
Carmen | -0.232 |
Token | Press |
Token ID | 4332 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
antha | +1.831 |
arov | +1.586 |
unction | +1.549 |
iversal | +1.542 |
66666666 | +1.517 |
Neg logit contributions | |
disproportion | -2.288 |
disadvant | -1.746 |
Penet | -1.683 |
Valkyrie | -1.647 |
scapego | -1.588 |
Token | . |
Token ID | 13 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
antha | +0.054 |
iversal | +0.047 |
arov | +0.047 |
unction | +0.047 |
66666666 | +0.045 |
Neg logit contributions | |
disproportion | -0.054 |
Penet | -0.039 |
disadvant | -0.039 |
Valkyrie | -0.038 |
scapego | -0.036 |
Token | All |
Token ID | 1439 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
antha | +0.817 |
iversal | +0.712 |
arov | +0.709 |
unction | +0.705 |
66666666 | +0.682 |
Neg logit contributions | |
disproportion | -0.765 |
Penet | -0.551 |
disadvant | -0.542 |
Valkyrie | -0.536 |
scapego | -0.501 |
Token | Rights |
Token ID | 6923 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
antha | +2.154 |
iversal | +1.727 |
arov | +1.691 |
unction | +1.678 |
66666666 | +1.604 |
Neg logit contributions | |
disproportion | -4.199 |
disadvant | -3.316 |
Penet | -3.307 |
Valkyrie | -3.283 |
Carmen | -3.135 |
Token | Reserved |
Token ID | 33876 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
antha | +3.413 |
arov | +2.756 |
iversal | +2.714 |
unction | +2.697 |
66666666 | +2.694 |
Neg logit contributions | |
disproportion | -5.860 |
disadvant | -4.791 |
Penet | -4.497 |
Valkyrie | -4.448 |
scapego | -4.308 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
antha | +2.039 |
arov | +1.764 |
unction | +1.753 |
iversal | +1.740 |
66666666 | +1.733 |
Neg logit contributions | |
disproportion | -2.123 |
disadvant | -1.582 |
Penet | -1.516 |
Valkyrie | -1.489 |
scapego | -1.419 |
Token | This |
Token ID | 770 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
disproportion | +0.542 |
Penet | +0.413 |
Valkyrie | +0.403 |
disadvant | +0.402 |
Carmen | +0.381 |
Neg logit contributions | |
antha | -0.449 |
iversal | -0.383 |
arov | -0.380 |
unction | -0.379 |
66666666 | -0.363 |
Token | material |
Token ID | 2587 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
antha | +1.013 |
iversal | +0.886 |
arov | +0.879 |
unction | +0.879 |
66666666 | +0.850 |
Neg logit contributions | |
disproportion | -0.826 |
Penet | -0.585 |
disadvant | -0.571 |
Valkyrie | -0.569 |
Carmen | -0.526 |
Token | may |
Token ID | 743 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
antha | +2.638 |
iversal | +2.205 |
arov | +2.167 |
unction | +2.146 |
66666666 | +2.090 |
Neg logit contributions | |
disproportion | -3.461 |
disadvant | -2.737 |
Penet | -2.703 |
Valkyrie | -2.681 |
Carmen | -2.486 |
Token | 's |
Token ID | 338 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
disproportion | +0.856 |
Penet | +0.639 |
Valkyrie | +0.620 |
disadvant | +0.617 |
Carmen | +0.584 |
Neg logit contributions | |
antha | -0.832 |
iversal | -0.720 |
arov | -0.714 |
unction | -0.712 |
66666666 | -0.685 |
Token | there |
Token ID | 612 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
antha | +1.990 |
iversal | +1.727 |
arov | +1.727 |
unction | +1.721 |
66666666 | +1.670 |
Neg logit contributions | |
disproportion | -1.831 |
Penet | -1.345 |
disadvant | -1.295 |
Valkyrie | -1.288 |
Carmen | -1.204 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
antha | +1.103 |
iversal | +0.960 |
unction | +0.953 |
arov | +0.951 |
66666666 | +0.916 |
Neg logit contributions | |
disproportion | -1.042 |
Penet | -0.766 |
Valkyrie | -0.739 |
disadvant | -0.738 |
Carmen | -0.693 |
Token | because |
Token ID | 780 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
antha | +0.469 |
iversal | +0.407 |
arov | +0.405 |
unction | +0.404 |
66666666 | +0.389 |
Neg logit contributions | |
disproportion | -0.451 |
Penet | -0.332 |
Valkyrie | -0.321 |
disadvant | -0.321 |
Carmen | -0.301 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
disproportion | +3.214 |
Penet | +2.358 |
Valkyrie | +2.271 |
disadvant | +2.246 |
Carmen | +2.145 |
Neg logit contributions | |
antha | -3.570 |
iversal | -3.132 |
arov | -3.101 |
unction | -3.074 |
66666666 | -2.943 |
Token | well |
Token ID | 880 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
antha | +1.235 |
iversal | +1.070 |
arov | +1.066 |
unction | +1.060 |
66666666 | +1.026 |
Neg logit contributions | |
disproportion | -1.150 |
Penet | -0.839 |
disadvant | -0.812 |
Valkyrie | -0.811 |
Carmen | -0.760 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
antha | +4.757 |
iversal | +4.160 |
unction | +4.139 |
arov | +4.098 |
66666666 | +3.972 |
Neg logit contributions | |
disproportion | -4.415 |
Penet | -3.198 |
disadvant | -3.077 |
Valkyrie | -3.076 |
Carmen | -2.879 |
Token | Google |
Token ID | 3012 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
disproportion | +0.134 |
Penet | +0.099 |
Valkyrie | +0.096 |
disadvant | +0.095 |
Carmen | +0.090 |
Neg logit contributions | |
antha | -0.138 |
iversal | -0.120 |
arov | -0.119 |
unction | -0.119 |
66666666 | -0.115 |
Token | might |
Token ID | 1244 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
antha | +1.448 |
iversal | +1.253 |
arov | +1.246 |
unction | +1.244 |
66666666 | +1.199 |
Neg logit contributions | |
disproportion | -1.512 |
Penet | -1.131 |
Valkyrie | -1.101 |
disadvant | -1.093 |
Carmen | -1.031 |
Token | take |
Token ID | 1011 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
antha | +0.672 |
iversal | +0.584 |
arov | +0.584 |
unction | +0.581 |
66666666 | +0.559 |
Neg logit contributions | |
disproportion | -0.630 |
Penet | -0.464 |
Valkyrie | -0.450 |
disadvant | -0.448 |
Carmen | -0.421 |
Token | notice |
Token ID | 4003 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
antha | +1.780 |
iversal | +1.540 |
unction | +1.529 |
arov | +1.529 |
66666666 | +1.468 |
Neg logit contributions | |
disproportion | -1.809 |
Penet | -1.350 |
Valkyrie | -1.305 |
disadvant | -1.298 |
Carmen | -1.223 |
Token | naming |
Token ID | 19264 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
disproportion | +1.621 |
Penet | +1.190 |
Valkyrie | +1.150 |
disadvant | +1.144 |
Carmen | +1.094 |
Neg logit contributions | |
antha | -1.722 |
iversal | -1.511 |
unction | -1.497 |
arov | -1.488 |
66666666 | -1.432 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
disproportion | +1.551 |
Penet | +1.118 |
Valkyrie | +1.079 |
disadvant | +1.075 |
Carmen | +1.023 |
Neg logit contributions | |
antha | -1.783 |
iversal | -1.568 |
unction | -1.549 |
arov | -1.546 |
66666666 | -1.488 |
Token | VP |
Token ID | 23342 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
antha | +1.272 |
iversal | +1.108 |
arov | +1.107 |
unction | +1.101 |
66666666 | +1.062 |
Neg logit contributions | |
disproportion | -1.159 |
Penet | -0.849 |
Valkyrie | -0.823 |
disadvant | -0.818 |
Carmen | -0.766 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
antha | +0.565 |
iversal | +0.487 |
arov | +0.483 |
unction | +0.481 |
66666666 | +0.463 |
Neg logit contributions | |
disproportion | -0.606 |
Penet | -0.457 |
Valkyrie | -0.443 |
disadvant | -0.441 |
Carmen | -0.418 |
Token | the |
Token ID | 262 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
antha | +1.362 |
iversal | +1.181 |
arov | +1.179 |
unction | +1.169 |
66666666 | +1.129 |
Neg logit contributions | |
disproportion | -1.317 |
Penet | -0.974 |
Valkyrie | -0.941 |
disadvant | -0.927 |
Carmen | -0.881 |
Token | subsequent |
Token ID | 8840 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
antha | +0.485 |
iversal | +0.422 |
arov | +0.419 |
unction | +0.417 |
66666666 | +0.402 |
Neg logit contributions | |
disproportion | -0.458 |
Penet | -0.337 |
Valkyrie | -0.326 |
disadvant | -0.324 |
Carmen | -0.306 |
Token | convention |
Token ID | 9831 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
antha | +4.432 |
arov | +3.857 |
iversal | +3.829 |
unction | +3.807 |
66666666 | +3.710 |
Neg logit contributions | |
disproportion | -3.920 |
Penet | -2.867 |
Valkyrie | -2.762 |
disadvant | -2.703 |
Carmen | -2.592 |
Token | aren |
Token ID | 3588 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
antha | +3.213 |
iversal | +2.786 |
arov | +2.759 |
unction | +2.741 |
66666666 | +2.663 |
Neg logit contributions | |
disproportion | -3.281 |
Penet | -2.467 |
Valkyrie | -2.376 |
disadvant | -2.356 |
Carmen | -2.244 |
Token | � |
Token ID | 447 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
antha | +1.724 |
arov | +1.518 |
unction | +1.493 |
iversal | +1.490 |
66666666 | +1.471 |
Neg logit contributions | |
disproportion | -1.741 |
disadvant | -1.280 |
Penet | -1.262 |
Valkyrie | -1.225 |
scapego | -1.160 |
Token | � |
Token ID | 247 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
antha | +0.507 |
arov | +0.453 |
iversal | +0.449 |
unction | +0.449 |
66666666 | +0.437 |
Neg logit contributions | |
disproportion | -0.341 |
Penet | -0.230 |
disadvant | -0.223 |
Valkyrie | -0.221 |
scapego | -0.205 |
Token | t |
Token ID | 83 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
antha | +0.796 |
iversal | +0.694 |
arov | +0.689 |
unction | +0.688 |
66666666 | +0.662 |
Neg logit contributions | |
disproportion | -0.742 |
Penet | -0.545 |
Valkyrie | -0.528 |
disadvant | -0.525 |
Carmen | -0.494 |
Token | They |
Token ID | 1119 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
antha | +0.042 |
iversal | +0.036 |
arov | +0.036 |
unction | +0.036 |
66666666 | +0.035 |
Neg logit contributions | |
disproportion | -0.042 |
Penet | -0.031 |
disadvant | -0.030 |
Valkyrie | -0.030 |
scapego | -0.028 |
Token | 've |
Token ID | 1053 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
antha | +1.420 |
arov | +1.232 |
iversal | +1.224 |
unction | +1.220 |
66666666 | +1.173 |
Neg logit contributions | |
disproportion | -1.461 |
Penet | -1.101 |
disadvant | -1.068 |
Valkyrie | -1.066 |
Carmen | -1.000 |
Token | got |
Token ID | 1392 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
antha | +1.892 |
arov | +1.650 |
unction | +1.635 |
iversal | +1.627 |
66666666 | +1.575 |
Neg logit contributions | |
disproportion | -1.844 |
Penet | -1.371 |
disadvant | -1.322 |
Valkyrie | -1.317 |
Carmen | -1.237 |
Token | a |
Token ID | 257 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
antha | +1.375 |
iversal | +1.198 |
arov | +1.197 |
unction | +1.194 |
66666666 | +1.156 |
Neg logit contributions | |
disproportion | -1.221 |
Penet | -0.886 |
disadvant | -0.849 |
Valkyrie | -0.849 |
Carmen | -0.798 |
Token | big |
Token ID | 1263 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
disproportion | +0.666 |
Penet | +0.483 |
Valkyrie | +0.466 |
disadvant | +0.465 |
Carmen | +0.436 |
Neg logit contributions | |
antha | -0.762 |
iversal | -0.667 |
arov | -0.662 |
unction | -0.661 |
66666666 | -0.638 |
Token | bath |
Token ID | 7837 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
disproportion | +3.101 |
Penet | +2.260 |
Valkyrie | +2.212 |
disadvant | +2.170 |
Carmen | +2.055 |
Neg logit contributions | |
antha | -3.344 |
iversal | -2.917 |
arov | -2.885 |
unction | -2.862 |
66666666 | -2.745 |
Token | tub |
Token ID | 37995 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
antha | +3.134 |
unction | +2.706 |
iversal | +2.688 |
arov | +2.679 |
atomic | +2.566 |
Neg logit contributions | |
disproportion | -3.367 |
Penet | -2.542 |
disadvant | -2.472 |
Valkyrie | -2.456 |
Carmen | -2.305 |
Token | full |
Token ID | 1336 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
antha | +2.056 |
iversal | +1.782 |
unction | +1.774 |
arov | +1.764 |
66666666 | +1.703 |
Neg logit contributions | |
disproportion | -1.989 |
Penet | -1.474 |
disadvant | -1.421 |
Valkyrie | -1.421 |
Carmen | -1.338 |
Token | of |
Token ID | 286 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
antha | +0.243 |
iversal | +0.212 |
arov | +0.210 |
unction | +0.210 |
66666666 | +0.202 |
Neg logit contributions | |
disproportion | -0.222 |
Penet | -0.163 |
Valkyrie | -0.157 |
disadvant | -0.157 |
Carmen | -0.147 |
Token | liquids |
Token ID | 38236 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
disproportion | +0.885 |
Penet | +0.647 |
Valkyrie | +0.626 |
disadvant | +0.622 |
Carmen | +0.586 |
Neg logit contributions | |
antha | -0.971 |
iversal | -0.848 |
arov | -0.841 |
unction | -0.839 |
66666666 | -0.808 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
antha | +1.495 |
iversal | +1.296 |
arov | +1.292 |
unction | +1.288 |
66666666 | +1.241 |
Neg logit contributions | |
disproportion | -1.433 |
Penet | -1.059 |
Valkyrie | -1.024 |
disadvant | -1.021 |
Carmen | -0.959 |
Token | among |
Token ID | 1871 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
disproportion | +0.113 |
Penet | +0.082 |
disadvant | +0.079 |
Valkyrie | +0.079 |
Carmen | +0.074 |
Neg logit contributions | |
antha | -0.125 |
arov | -0.109 |
iversal | -0.109 |
unction | -0.108 |
66666666 | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
disproportion | +0.476 |
Penet | +0.345 |
Valkyrie | +0.333 |
disadvant | +0.332 |
Carmen | +0.310 |
Neg logit contributions | |
antha | -0.548 |
iversal | -0.480 |
arov | -0.476 |
unction | -0.474 |
66666666 | -0.458 |
Token | hundreds |
Token ID | 5179 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
antha | +1.790 |
arov | +1.560 |
iversal | +1.550 |
unction | +1.530 |
66666666 | +1.486 |
Neg logit contributions | |
disproportion | -1.439 |
Penet | -1.033 |
disadvant | -1.004 |
Valkyrie | -0.993 |
Carmen | -0.909 |
Token | of |
Token ID | 286 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
antha | +3.185 |
arov | +2.746 |
iversal | +2.718 |
unction | +2.674 |
66666666 | +2.599 |
Neg logit contributions | |
disproportion | -3.190 |
Penet | -2.385 |
Valkyrie | -2.300 |
disadvant | -2.294 |
Carmen | -2.153 |
Token | Toledo |
Token ID | 36026 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
antha | +0.721 |
iversal | +0.635 |
arov | +0.634 |
unction | +0.628 |
66666666 | +0.612 |
Neg logit contributions | |
disproportion | -0.513 |
Penet | -0.355 |
disadvant | -0.344 |
Valkyrie | -0.337 |
Carmen | -0.310 |
Token | youths |
Token ID | 28247 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
antha | +1.968 |
iversal | +1.725 |
arov | +1.718 |
unction | +1.699 |
66666666 | +1.642 |
Neg logit contributions | |
disproportion | -1.704 |
Penet | -1.227 |
disadvant | -1.203 |
Valkyrie | -1.185 |
Carmen | -1.099 |
Token | who |
Token ID | 508 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
antha | +1.949 |
arov | +1.676 |
iversal | +1.648 |
unction | +1.625 |
66666666 | +1.582 |
Neg logit contributions | |
disproportion | -2.082 |
Penet | -1.587 |
Valkyrie | -1.541 |
disadvant | -1.524 |
Carmen | -1.432 |
Token | have |
Token ID | 423 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
disproportion | +0.064 |
Penet | +0.047 |
Valkyrie | +0.046 |
disadvant | +0.046 |
Carmen | +0.043 |
Neg logit contributions | |
antha | -0.068 |
iversal | -0.059 |
arov | -0.059 |
unction | -0.058 |
66666666 | -0.056 |
Token | discovered |
Token ID | 5071 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
disproportion | +0.076 |
Penet | +0.055 |
disadvant | +0.054 |
Valkyrie | +0.054 |
Carmen | +0.050 |
Neg logit contributions | |
antha | -0.087 |
arov | -0.075 |
iversal | -0.075 |
unction | -0.075 |
66666666 | -0.072 |
Token | boxing |
Token ID | 21576 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
disproportion | +1.087 |
Penet | +0.788 |
Valkyrie | +0.762 |
disadvant | +0.756 |
Carmen | +0.712 |
Neg logit contributions | |
antha | -1.243 |
iversal | -1.089 |
arov | -1.081 |
unction | -1.078 |
66666666 | -1.039 |
Token | this |
Token ID | 428 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
antha | +1.434 |
arov | +1.236 |
iversal | +1.234 |
unction | +1.223 |
66666666 | +1.181 |
Neg logit contributions | |
disproportion | -1.469 |
Penet | -1.099 |
Valkyrie | -1.065 |
disadvant | -1.063 |
Carmen | -1.002 |
Token | , |
Token ID | 11 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
antha | +3.426 |
arov | +2.981 |
iversal | +2.980 |
unction | +2.966 |
66666666 | +2.855 |
Neg logit contributions | |
disproportion | -3.297 |
Penet | -2.442 |
disadvant | -2.354 |
Valkyrie | -2.340 |
Carmen | -2.180 |
Token | which |
Token ID | 543 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
disproportion | +0.033 |
Penet | +0.024 |
Valkyrie | +0.023 |
disadvant | +0.023 |
Carmen | +0.022 |
Neg logit contributions | |
antha | -0.038 |
iversal | -0.033 |
arov | -0.033 |
unction | -0.033 |
66666666 | -0.032 |
Token | she |
Token ID | 673 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
disproportion | +0.208 |
Penet | +0.155 |
Valkyrie | +0.151 |
disadvant | +0.150 |
Carmen | +0.142 |
Neg logit contributions | |
antha | -0.204 |
iversal | -0.176 |
arov | -0.175 |
unction | -0.175 |
66666666 | -0.168 |
Token | is |
Token ID | 318 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
disproportion | +0.333 |
Penet | +0.252 |
Valkyrie | +0.245 |
disadvant | +0.244 |
Carmen | +0.231 |
Neg logit contributions | |
antha | -0.299 |
iversal | -0.257 |
arov | -0.255 |
unction | -0.254 |
66666666 | -0.244 |
Token | allergic |
Token ID | 31856 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
disproportion | +0.537 |
Penet | +0.395 |
Valkyrie | +0.383 |
disadvant | +0.381 |
Carmen | +0.359 |
Neg logit contributions | |
antha | -0.568 |
iversal | -0.495 |
arov | -0.491 |
unction | -0.490 |
66666666 | -0.472 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
antha | +2.175 |
iversal | +1.886 |
arov | +1.868 |
unction | +1.866 |
66666666 | +1.795 |
Neg logit contributions | |
disproportion | -2.232 |
Penet | -1.666 |
Valkyrie | -1.615 |
disadvant | -1.607 |
Carmen | -1.517 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
antha | +0.993 |
iversal | +0.867 |
unction | +0.859 |
arov | +0.858 |
66666666 | +0.829 |
Neg logit contributions | |
disproportion | -0.907 |
Penet | -0.663 |
Valkyrie | -0.642 |
disadvant | -0.640 |
Carmen | -0.600 |
Token | She |
Token ID | 1375 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
antha | +0.363 |
iversal | +0.312 |
arov | +0.312 |
unction | +0.310 |
66666666 | +0.300 |
Neg logit contributions | |
disproportion | -0.383 |
Penet | -0.282 |
disadvant | -0.278 |
Valkyrie | -0.275 |
scapego | -0.260 |
Token | doesn |
Token ID | 1595 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
disproportion | +0.963 |
Penet | +0.723 |
Valkyrie | +0.701 |
disadvant | +0.698 |
Carmen | +0.661 |
Neg logit contributions | |
antha | -0.911 |
iversal | -0.785 |
arov | -0.780 |
unction | -0.777 |
66666666 | -0.747 |
Token | 't |
Token ID | 470 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
disproportion | +0.493 |
Penet | +0.371 |
disadvant | +0.365 |
Valkyrie | +0.361 |
Carmen | +0.341 |
Neg logit contributions | |
antha | -0.432 |
iversal | -0.370 |
arov | -0.370 |
unction | -0.368 |
66666666 | -0.356 |
Token | cook |
Token ID | 4255 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
disproportion | +0.413 |
Penet | +0.306 |
Valkyrie | +0.296 |
disadvant | +0.296 |
Carmen | +0.276 |
Neg logit contributions | |
antha | -0.439 |
iversal | -0.382 |
arov | -0.381 |
unction | -0.379 |
66666666 | -0.366 |
Token | be |
Token ID | 307 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
antha | +0.205 |
arov | +0.179 |
iversal | +0.178 |
unction | +0.176 |
66666666 | +0.170 |
Neg logit contributions | |
disproportion | -0.186 |
Penet | -0.135 |
Valkyrie | -0.133 |
disadvant | -0.133 |
Carmen | -0.124 |
Token | issued |
Token ID | 4884 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
antha | +2.029 |
arov | +1.795 |
iversal | +1.756 |
unction | +1.756 |
66666666 | +1.695 |
Neg logit contributions | |
disproportion | -1.953 |
Penet | -1.437 |
Valkyrie | -1.404 |
disadvant | -1.391 |
Carmen | -1.302 |
Token | in |
Token ID | 287 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
disproportion | +0.766 |
Penet | +0.580 |
Valkyrie | +0.562 |
disadvant | +0.560 |
Carmen | +0.532 |
Neg logit contributions | |
antha | -0.682 |
iversal | -0.586 |
arov | -0.581 |
unction | -0.580 |
66666666 | -0.555 |
Token | December |
Token ID | 3426 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
antha | +0.235 |
iversal | +0.201 |
unction | +0.201 |
arov | +0.200 |
66666666 | +0.193 |
Neg logit contributions | |
disproportion | -0.240 |
Penet | -0.179 |
disadvant | -0.175 |
Valkyrie | -0.173 |
scapego | -0.163 |
Token | — |
Token ID | 960 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
disproportion | +0.278 |
Penet | +0.205 |
Valkyrie | +0.199 |
disadvant | +0.198 |
Carmen | +0.187 |
Neg logit contributions | |
antha | -0.287 |
iversal | -0.249 |
arov | -0.247 |
unction | -0.247 |
66666666 | -0.237 |
Token | and |
Token ID | 392 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
antha | +1.115 |
iversal | +0.919 |
arov | +0.918 |
unction | +0.913 |
66666666 | +0.865 |
Neg logit contributions | |
disproportion | -1.748 |
Penet | -1.380 |
Valkyrie | -1.349 |
disadvant | -1.341 |
Carmen | -1.286 |
Token | with |
Token ID | 351 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
antha | +1.054 |
iversal | +0.917 |
arov | +0.909 |
unction | +0.906 |
66666666 | +0.875 |
Neg logit contributions | |
disproportion | -1.020 |
Penet | -0.755 |
Valkyrie | -0.728 |
disadvant | -0.726 |
Carmen | -0.682 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
antha | +0.039 |
iversal | +0.034 |
arov | +0.034 |
unction | +0.034 |
66666666 | +0.032 |
Neg logit contributions | |
disproportion | -0.036 |
Penet | -0.027 |
Valkyrie | -0.026 |
disadvant | -0.026 |
Carmen | -0.024 |
Token | EPA |
Token ID | 10193 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
antha | +0.012 |
iversal | +0.011 |
arov | +0.011 |
unction | +0.011 |
66666666 | +0.010 |
Neg logit contributions | |
disproportion | -0.012 |
Penet | -0.009 |
Valkyrie | -0.009 |
disadvant | -0.009 |
Carmen | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
antha | +2.186 |
iversal | +1.898 |
arov | +1.883 |
unction | +1.882 |
66666666 | +1.809 |
Neg logit contributions | |
disproportion | -2.190 |
Penet | -1.622 |
Valkyrie | -1.577 |
disadvant | -1.569 |
Carmen | -1.474 |
Token | � |
Token ID | 247 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
antha | +0.991 |
arov | +0.892 |
iversal | +0.886 |
unction | +0.885 |
66666666 | +0.865 |
Neg logit contributions | |
disproportion | -0.582 |
Penet | -0.376 |
disadvant | -0.366 |
Valkyrie | -0.358 |
scapego | -0.326 |
Token | the |
Token ID | 262 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
antha | +0.645 |
iversal | +0.561 |
arov | +0.557 |
unction | +0.556 |
66666666 | +0.535 |
Neg logit contributions | |
disproportion | -0.605 |
Penet | -0.444 |
Valkyrie | -0.430 |
disadvant | -0.428 |
Carmen | -0.403 |
Token | island |
Token ID | 7022 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
disproportion | +0.496 |
Penet | +0.376 |
Valkyrie | +0.365 |
disadvant | +0.364 |
Carmen | +0.345 |
Neg logit contributions | |
antha | -0.441 |
iversal | -0.379 |
arov | -0.375 |
unction | -0.374 |
66666666 | -0.359 |
Token | that |
Token ID | 326 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
disproportion | +1.214 |
Penet | +0.879 |
Valkyrie | +0.849 |
disadvant | +0.845 |
Carmen | +0.802 |
Neg logit contributions | |
antha | -1.384 |
iversal | -1.214 |
arov | -1.205 |
unction | -1.201 |
66666666 | -1.160 |
Token | had |
Token ID | 550 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
antha | +0.319 |
iversal | +0.277 |
arov | +0.275 |
unction | +0.273 |
66666666 | +0.265 |
Neg logit contributions | |
disproportion | -0.288 |
Penet | -0.210 |
Valkyrie | -0.204 |
disadvant | -0.203 |
Carmen | -0.190 |
Token | been |
Token ID | 587 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
disproportion | +0.174 |
Penet | +0.125 |
Valkyrie | +0.121 |
disadvant | +0.121 |
Carmen | +0.113 |
Neg logit contributions | |
antha | -0.208 |
iversal | -0.182 |
arov | -0.181 |
unction | -0.180 |
66666666 | -0.174 |
Token | disturbed |
Token ID | 24069 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
antha | +0.022 |
arov | +0.019 |
iversal | +0.019 |
unction | +0.019 |
66666666 | +0.018 |
Neg logit contributions | |
disproportion | -0.021 |
Penet | -0.015 |
Valkyrie | -0.015 |
disadvant | -0.015 |
Carmen | -0.014 |
Token | by |
Token ID | 416 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
antha | +0.518 |
iversal | +0.445 |
arov | +0.442 |
unction | +0.440 |
66666666 | +0.422 |
Neg logit contributions | |
disproportion | -0.587 |
Penet | -0.444 |
Valkyrie | -0.431 |
disadvant | -0.429 |
Carmen | -0.408 |
Token | human |
Token ID | 1692 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
antha | +0.564 |
iversal | +0.492 |
arov | +0.488 |
unction | +0.487 |
66666666 | +0.469 |
Neg logit contributions | |
disproportion | -0.526 |
Penet | -0.386 |
Valkyrie | -0.373 |
disadvant | -0.372 |
Carmen | -0.350 |
Token | activity |
Token ID | 3842 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
antha | +1.174 |
iversal | +0.994 |
arov | +0.985 |
unction | +0.981 |
66666666 | +0.937 |
Neg logit contributions | |
disproportion | -1.526 |
Penet | -1.179 |
Valkyrie | -1.148 |
disadvant | -1.143 |
Carmen | -1.091 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
disproportion | +0.186 |
Penet | +0.135 |
Valkyrie | +0.131 |
disadvant | +0.131 |
Carmen | +0.123 |
Neg logit contributions | |
antha | -0.207 |
iversal | -0.181 |
arov | -0.179 |
unction | -0.179 |
66666666 | -0.172 |
Token | He |
Token ID | 679 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
antha | +0.230 |
iversal | +0.198 |
arov | +0.197 |
unction | +0.196 |
66666666 | +0.188 |
Neg logit contributions | |
disproportion | -0.241 |
Penet | -0.180 |
Valkyrie | -0.175 |
disadvant | -0.174 |
Carmen | -0.165 |
Token | inaug |
Token ID | 14243 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
disproportion | +1.283 |
Penet | +0.960 |
Valkyrie | +0.932 |
disadvant | +0.927 |
Carmen | +0.879 |
Neg logit contributions | |
antha | -1.222 |
iversal | -1.056 |
arov | -1.044 |
unction | -1.044 |
66666666 | -1.003 |
Token | urate |
Token ID | 15537 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
disproportion | +3.143 |
Penet | +2.384 |
Valkyrie | +2.377 |
disadvant | +2.255 |
Carmen | +2.214 |
Neg logit contributions | |
antha | -2.803 |
iversal | -2.427 |
arov | -2.381 |
unction | -2.358 |
66666666 | -2.273 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
disproportion | +3.385 |
Penet | +2.417 |
Valkyrie | +2.350 |
disadvant | +2.284 |
Carmen | +2.230 |
Neg logit contributions | |
antha | -4.252 |
iversal | -3.763 |
unction | -3.732 |
arov | -3.702 |
66666666 | -3.585 |
Token | $ |
Token ID | 720 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
disproportion | +0.897 |
Penet | +0.651 |
Valkyrie | +0.629 |
disadvant | +0.624 |
Carmen | +0.590 |
Neg logit contributions | |
antha | -1.022 |
iversal | -0.895 |
arov | -0.887 |
unction | -0.885 |
66666666 | -0.855 |
Token | 900 |
Token ID | 12865 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
antha | +1.328 |
arov | +1.086 |
iversal | +1.077 |
unction | +1.072 |
66666666 | +1.048 |
Neg logit contributions | |
disproportion | -2.327 |
Penet | -1.828 |
disadvant | -1.814 |
Valkyrie | -1.781 |
scapego | -1.709 |
Token | million |
Token ID | 1510 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
antha | +0.754 |
iversal | +0.656 |
arov | +0.652 |
unction | +0.648 |
66666666 | +0.626 |
Neg logit contributions | |
disproportion | -0.715 |
Penet | -0.526 |
Valkyrie | -0.508 |
disadvant | -0.507 |
Carmen | -0.475 |
Token | port |
Token ID | 2493 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
disproportion | +1.428 |
Penet | +1.067 |
Valkyrie | +1.035 |
disadvant | +1.023 |
Carmen | +0.980 |
Neg logit contributions | |
antha | -1.405 |
iversal | -1.221 |
arov | -1.209 |
unction | -1.205 |
66666666 | -1.157 |
Token | project |
Token ID | 1628 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
disproportion | +1.187 |
Penet | +0.884 |
Valkyrie | +0.858 |
disadvant | +0.856 |
Carmen | +0.814 |
Neg logit contributions | |
antha | -1.169 |
iversal | -1.013 |
arov | -1.004 |
unction | -0.998 |
66666666 | -0.965 |
Token | largely |
Token ID | 5688 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
disproportion | +0.588 |
Penet | +0.433 |
Valkyrie | +0.421 |
disadvant | +0.419 |
Carmen | +0.396 |
Neg logit contributions | |
antha | -0.609 |
iversal | -0.529 |
arov | -0.524 |
unction | -0.522 |
66666666 | -0.504 |
Token | funded |
Token ID | 10588 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
antha | +0.319 |
iversal | +0.280 |
arov | +0.279 |
unction | +0.278 |
66666666 | +0.268 |
Neg logit contributions | |
disproportion | -0.270 |
Penet | -0.195 |
Valkyrie | -0.188 |
disadvant | -0.186 |
Carmen | -0.175 |
Token | by |
Token ID | 416 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
antha | +0.294 |
iversal | +0.250 |
arov | +0.246 |
unction | +0.246 |
66666666 | +0.236 |
Neg logit contributions | |
disproportion | -0.365 |
Penet | -0.278 |
Valkyrie | -0.272 |
disadvant | -0.270 |
Carmen | -0.259 |
Token | it |
Token ID | 340 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
disproportion | +2.628 |
Penet | +1.892 |
Valkyrie | +1.828 |
disadvant | +1.809 |
Carmen | +1.724 |
Neg logit contributions | |
antha | -3.131 |
iversal | -2.760 |
arov | -2.732 |
unction | -2.723 |
66666666 | -2.617 |
Token | takes |
Token ID | 2753 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
antha | +0.434 |
iversal | +0.374 |
arov | +0.372 |
unction | +0.371 |
66666666 | +0.358 |
Neg logit contributions | |
disproportion | -0.463 |
Penet | -0.348 |
Valkyrie | -0.339 |
disadvant | -0.338 |
Carmen | -0.318 |
Token | 30 |
Token ID | 1542 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
antha | +2.033 |
iversal | +1.766 |
arov | +1.764 |
unction | +1.760 |
66666666 | +1.702 |
Neg logit contributions | |
disproportion | -1.934 |
Penet | -1.416 |
Valkyrie | -1.371 |
disadvant | -1.367 |
scapego | -1.276 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
antha | +1.383 |
iversal | +1.190 |
arov | +1.182 |
unction | +1.178 |
66666666 | +1.131 |
Neg logit contributions | |
disproportion | -1.612 |
Penet | -1.220 |
Valkyrie | -1.190 |
disadvant | -1.187 |
Carmen | -1.120 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
antha | +2.254 |
iversal | +1.951 |
arov | +1.945 |
unction | +1.945 |
66666666 | +1.874 |
Neg logit contributions | |
disproportion | -2.253 |
Penet | -1.676 |
Valkyrie | -1.625 |
disadvant | -1.613 |
Carmen | -1.515 |
Token | you |
Token ID | 345 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
antha | +1.167 |
arov | +1.010 |
iversal | +1.007 |
unction | +1.004 |
66666666 | +0.977 |
Neg logit contributions | |
disproportion | -1.135 |
Penet | -0.839 |
Valkyrie | -0.813 |
disadvant | -0.807 |
scapego | -0.752 |
Token | � |
Token ID | 447 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
antha | +0.181 |
arov | +0.157 |
iversal | +0.156 |
unction | +0.156 |
66666666 | +0.150 |
Neg logit contributions | |
disproportion | -0.183 |
Penet | -0.137 |
disadvant | -0.133 |
Valkyrie | -0.133 |
Carmen | -0.124 |
Token | � |
Token ID | 247 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
antha | +0.791 |
arov | +0.698 |
iversal | +0.696 |
unction | +0.694 |
66666666 | +0.675 |
Neg logit contributions | |
disproportion | -0.630 |
Penet | -0.445 |
disadvant | -0.431 |
Valkyrie | -0.430 |
Carmen | -0.402 |
Token | ve |
Token ID | 303 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
antha | +0.547 |
iversal | +0.468 |
unction | +0.464 |
arov | +0.464 |
66666666 | +0.445 |
Neg logit contributions | |
disproportion | -0.635 |
Penet | -0.483 |
Valkyrie | -0.471 |
disadvant | -0.470 |
Carmen | -0.445 |
Token | got |
Token ID | 1392 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
disproportion | +0.507 |
Penet | +0.381 |
Valkyrie | +0.370 |
disadvant | +0.369 |
Carmen | +0.348 |
Neg logit contributions | |
antha | -0.471 |
iversal | -0.405 |
arov | -0.403 |
unction | -0.402 |
66666666 | -0.387 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
disproportion | +0.191 |
Penet | +0.141 |
Valkyrie | +0.136 |
disadvant | +0.136 |
Carmen | +0.127 |
Neg logit contributions | |
antha | -0.198 |
iversal | -0.172 |
arov | -0.171 |
unction | -0.171 |
66666666 | -0.165 |
Token | their |
Token ID | 511 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
disproportion | +1.601 |
Penet | +1.168 |
Valkyrie | +1.132 |
disadvant | +1.123 |
Carmen | +1.063 |
Neg logit contributions | |
antha | -1.770 |
iversal | -1.545 |
arov | -1.531 |
unction | -1.530 |
66666666 | -1.471 |
Token | own |
Token ID | 898 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
disproportion | +0.217 |
Penet | +0.156 |
Valkyrie | +0.151 |
disadvant | +0.150 |
Carmen | +0.140 |
Neg logit contributions | |
antha | -0.257 |
iversal | -0.225 |
arov | -0.224 |
unction | -0.223 |
66666666 | -0.215 |
Token | beverages |
Token ID | 24173 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
antha | +2.450 |
arov | +2.156 |
iversal | +2.134 |
unction | +2.120 |
66666666 | +2.075 |
Neg logit contributions | |
disproportion | -2.159 |
Penet | -1.576 |
disadvant | -1.509 |
Valkyrie | -1.499 |
Carmen | -1.390 |
Token | and |
Token ID | 290 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
disproportion | +1.711 |
Penet | +1.259 |
Valkyrie | +1.222 |
disadvant | +1.214 |
Carmen | +1.148 |
Neg logit contributions | |
antha | -1.793 |
iversal | -1.561 |
arov | -1.546 |
unction | -1.542 |
66666666 | -1.486 |
Token | red |
Token ID | 2266 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
disproportion | +0.384 |
Penet | +0.282 |
Valkyrie | +0.271 |
disadvant | +0.269 |
Carmen | +0.253 |
Neg logit contributions | |
antha | -0.411 |
arov | -0.359 |
iversal | -0.356 |
unction | -0.354 |
66666666 | -0.344 |
Token | Solo |
Token ID | 20284 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
disproportion | +2.959 |
Penet | +2.173 |
Valkyrie | +2.102 |
disadvant | +2.091 |
Carmen | +1.983 |
Neg logit contributions | |
antha | -3.181 |
iversal | -2.773 |
arov | -2.720 |
unction | -2.716 |
66666666 | -2.635 |
Token | cups |
Token ID | 14180 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
disproportion | +0.988 |
Penet | +0.724 |
Valkyrie | +0.700 |
disadvant | +0.696 |
Carmen | +0.656 |
Neg logit contributions | |
antha | -1.067 |
iversal | -0.930 |
arov | -0.923 |
unction | -0.920 |
66666666 | -0.887 |
Token | and |
Token ID | 290 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
disproportion | +1.347 |
Penet | +0.997 |
Valkyrie | +0.966 |
disadvant | +0.961 |
Carmen | +0.908 |
Neg logit contributions | |
antha | -1.376 |
iversal | -1.195 |
arov | -1.185 |
unction | -1.182 |
66666666 | -1.137 |
Token | even |
Token ID | 772 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
disproportion | +0.736 |
Penet | +0.539 |
Valkyrie | +0.518 |
disadvant | +0.517 |
Carmen | +0.484 |
Neg logit contributions | |
antha | -0.804 |
arov | -0.700 |
iversal | -0.699 |
unction | -0.693 |
66666666 | -0.672 |
Token | made |
Token ID | 925 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
disproportion | +0.836 |
Penet | +0.603 |
Valkyrie | +0.580 |
disadvant | +0.579 |
Carmen | +0.539 |
Neg logit contributions | |
antha | -0.966 |
arov | -0.846 |
iversal | -0.844 |
unction | -0.838 |
66666666 | -0.812 |
Token | a |
Token ID | 257 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
disproportion | +0.454 |
Penet | +0.330 |
disadvant | +0.318 |
Valkyrie | +0.318 |
Carmen | +0.296 |
Neg logit contributions | |
antha | -0.509 |
iversal | -0.445 |
arov | -0.443 |
unction | -0.441 |
66666666 | -0.426 |
Token | the |
Token ID | 262 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
disproportion | +0.080 |
Penet | +0.058 |
Valkyrie | +0.056 |
disadvant | +0.056 |
Carmen | +0.052 |
Neg logit contributions | |
antha | -0.091 |
iversal | -0.080 |
arov | -0.079 |
unction | -0.079 |
66666666 | -0.076 |
Token | recent |
Token ID | 2274 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
disproportion | +0.084 |
Penet | +0.061 |
Valkyrie | +0.059 |
disadvant | +0.059 |
Carmen | +0.055 |
Neg logit contributions | |
antha | -0.092 |
iversal | -0.080 |
arov | -0.079 |
unction | -0.079 |
66666666 | -0.076 |
Token | debates |
Token ID | 15389 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
antha | +0.203 |
iversal | +0.179 |
arov | +0.177 |
unction | +0.177 |
66666666 | +0.171 |
Neg logit contributions | |
disproportion | -0.168 |
Penet | -0.120 |
Valkyrie | -0.116 |
disadvant | -0.115 |
Carmen | -0.108 |
Token | with |
Token ID | 351 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
disproportion | +1.785 |
Penet | +1.306 |
Valkyrie | +1.273 |
disadvant | +1.267 |
Carmen | +1.202 |
Neg logit contributions | |
antha | -1.882 |
iversal | -1.642 |
unction | -1.623 |
arov | -1.621 |
66666666 | -1.559 |
Token | Republican |
Token ID | 3415 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
disproportion | +1.232 |
Penet | +0.929 |
Valkyrie | +0.904 |
disadvant | +0.897 |
Carmen | +0.857 |
Neg logit contributions | |
antha | -1.115 |
iversal | -0.963 |
unction | -0.954 |
arov | -0.953 |
66666666 | -0.912 |
Token | nominee |
Token ID | 10429 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
disproportion | +0.925 |
Penet | +0.697 |
Valkyrie | +0.678 |
disadvant | +0.676 |
Carmen | +0.644 |
Neg logit contributions | |
antha | -0.834 |
iversal | -0.724 |
unction | -0.716 |
arov | -0.714 |
66666666 | -0.686 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
disproportion | +0.171 |
Penet | +0.130 |
Valkyrie | +0.127 |
disadvant | +0.126 |
Carmen | +0.122 |
Neg logit contributions | |
antha | -0.150 |
iversal | -0.129 |
unction | -0.128 |
arov | -0.127 |
66666666 | -0.122 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
antha | +1.565 |
arov | +1.350 |
iversal | +1.327 |
unction | +1.311 |
66666666 | +1.284 |
Neg logit contributions | |
disproportion | -1.894 |
disadvant | -1.424 |
Penet | -1.416 |
Valkyrie | -1.379 |
scapego | -1.303 |
Token | Donald |
Token ID | 3759 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
antha | +1.173 |
iversal | +0.992 |
arov | +0.988 |
unction | +0.978 |
66666666 | +0.937 |
Neg logit contributions | |
disproportion | -1.518 |
Penet | -1.173 |
Valkyrie | -1.141 |
disadvant | -1.137 |
Carmen | -1.079 |
Token | John |
Token ID | 1757 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
antha | +4.251 |
arov | +3.659 |
unction | +3.635 |
iversal | +3.615 |
66666666 | +3.414 |
Neg logit contributions | |
disproportion | -4.193 |
disadvant | -3.076 |
Penet | -2.972 |
Valkyrie | -2.906 |
scapego | -2.729 |
Token | Trump |
Token ID | 1301 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
antha | +1.531 |
unction | +1.266 |
iversal | +1.262 |
arov | +1.261 |
66666666 | +1.209 |
Neg logit contributions | |
disproportion | -1.952 |
Penet | -1.506 |
disadvant | -1.495 |
Valkyrie | -1.472 |
scapego | -1.393 |
Token | called |
Token ID | 7174 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
disproportion | +2.160 |
Penet | +1.645 |
Valkyrie | +1.601 |
disadvant | +1.588 |
Carmen | +1.516 |
Neg logit contributions | |
antha | -1.846 |
iversal | -1.580 |
arov | -1.564 |
unction | -1.559 |
66666666 | -1.494 |
Token | Mid |
Token ID | 7215 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
antha | +0.884 |
iversal | +0.769 |
arov | +0.763 |
unction | +0.763 |
66666666 | +0.735 |
Neg logit contributions | |
disproportion | -0.805 |
Penet | -0.587 |
Valkyrie | -0.568 |
disadvant | -0.568 |
Carmen | -0.531 |
Token | - |
Token ID | 12 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
antha | +0.112 |
iversal | +0.096 |
arov | +0.095 |
unction | +0.095 |
66666666 | +0.091 |
Neg logit contributions | |
disproportion | -0.132 |
Penet | -0.101 |
Valkyrie | -0.098 |
disadvant | -0.098 |
Carmen | -0.093 |
Token | western |
Token ID | 14197 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
disproportion | +0.154 |
Penet | +0.120 |
Valkyrie | +0.117 |
disadvant | +0.116 |
Carmen | +0.111 |
Neg logit contributions | |
antha | -0.111 |
iversal | -0.093 |
arov | -0.092 |
unction | -0.092 |
66666666 | -0.088 |
Token | group |
Token ID | 1448 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
disproportion | +2.309 |
Penet | +1.687 |
Valkyrie | +1.625 |
disadvant | +1.612 |
Carmen | +1.523 |
Neg logit contributions | |
antha | -2.563 |
iversal | -2.249 |
arov | -2.233 |
unction | -2.222 |
66666666 | -2.149 |
Token | , |
Token ID | 11 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
antha | +0.772 |
iversal | +0.675 |
unction | +0.668 |
arov | +0.668 |
66666666 | +0.641 |
Neg logit contributions | |
disproportion | -0.696 |
Penet | -0.508 |
Valkyrie | -0.491 |
disadvant | -0.488 |
Carmen | -0.458 |
Token | although |
Token ID | 3584 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
disproportion | +0.425 |
Penet | +0.310 |
Valkyrie | +0.300 |
disadvant | +0.298 |
Carmen | +0.280 |
Neg logit contributions | |
antha | -0.471 |
iversal | -0.411 |
arov | -0.407 |
unction | -0.407 |
66666666 | -0.392 |
Token | they |
Token ID | 484 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
disproportion | +0.685 |
Penet | +0.496 |
Valkyrie | +0.479 |
disadvant | +0.477 |
Carmen | +0.448 |
Neg logit contributions | |
antha | -0.788 |
iversal | -0.690 |
arov | -0.685 |
unction | -0.683 |
66666666 | -0.659 |
Token | cast |
Token ID | 3350 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
antha | +2.759 |
iversal | +2.404 |
arov | +2.403 |
unction | +2.373 |
66666666 | +2.295 |
Neg logit contributions | |
disproportion | -2.386 |
Penet | -1.765 |
Valkyrie | -1.728 |
disadvant | -1.709 |
Carmen | -1.608 |
Token | their |
Token ID | 511 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
disproportion | +1.046 |
Penet | +0.754 |
Valkyrie | +0.730 |
disadvant | +0.725 |
Carmen | +0.682 |
Neg logit contributions | |
antha | -1.209 |
iversal | -1.059 |
arov | -1.051 |
unction | -1.048 |
66666666 | -1.011 |
Token | vote |
Token ID | 3015 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
antha | +1.288 |
iversal | +1.100 |
arov | +1.091 |
unction | +1.086 |
66666666 | +1.051 |
Neg logit contributions | |
disproportion | -1.541 |
Penet | -1.189 |
disadvant | -1.148 |
Valkyrie | -1.147 |
Carmen | -1.095 |
Token | Alfred |
Token ID | 22044 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
antha | +1.200 |
iversal | +1.072 |
arov | +1.064 |
unction | +1.061 |
66666666 | +1.030 |
Neg logit contributions | |
disproportion | -0.768 |
Penet | -0.517 |
Valkyrie | -0.494 |
disadvant | -0.489 |
Carmen | -0.455 |
Token | Nobel |
Token ID | 20715 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
disproportion | +2.936 |
Penet | +2.289 |
Valkyrie | +2.222 |
disadvant | +2.184 |
Carmen | +2.115 |
Neg logit contributions | |
antha | -2.258 |
iversal | -1.929 |
arov | -1.897 |
unction | -1.892 |
66666666 | -1.807 |
Token |
|
Token ID | 198 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
antha | +0.391 |
iversal | +0.340 |
arov | +0.337 |
unction | +0.337 |
66666666 | +0.324 |
Neg logit contributions | |
disproportion | -0.368 |
Penet | -0.270 |
Valkyrie | -0.261 |
disadvant | -0.260 |
Carmen | -0.245 |
Token |
|
Token ID | 198 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
disproportion | +0.533 |
Penet | +0.398 |
disadvant | +0.390 |
Valkyrie | +0.387 |
Carmen | +0.365 |
Neg logit contributions | |
antha | -0.491 |
iversal | -0.422 |
arov | -0.422 |
unction | -0.419 |
66666666 | -0.405 |
Token | A |
Token ID | 32 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
disproportion | +0.583 |
Penet | +0.457 |
Valkyrie | +0.446 |
disadvant | +0.444 |
Carmen | +0.425 |
Neg logit contributions | |
antha | -0.400 |
iversal | -0.335 |
arov | -0.331 |
unction | -0.330 |
66666666 | -0.314 |
Token | ward |
Token ID | 904 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
antha | +0.525 |
iversal | +0.454 |
arov | +0.452 |
unction | +0.450 |
66666666 | +0.432 |
Neg logit contributions | |
disproportion | -0.503 |
Penet | -0.372 |
Valkyrie | -0.360 |
disadvant | -0.359 |
Carmen | -0.338 |
Token | ed |
Token ID | 276 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
disproportion | +4.463 |
Penet | +3.306 |
Valkyrie | +3.168 |
disadvant | +3.134 |
Carmen | +2.998 |
Neg logit contributions | |
antha | -4.679 |
iversal | -4.126 |
arov | -4.054 |
unction | -4.031 |
66666666 | -3.958 |
Token | to |
Token ID | 284 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
disproportion | +0.448 |
Penet | +0.335 |
Valkyrie | +0.322 |
disadvant | +0.320 |
Carmen | +0.305 |
Neg logit contributions | |
antha | -0.437 |
iversal | -0.377 |
arov | -0.374 |
unction | -0.373 |
66666666 | -0.359 |
Token | 79 |
Token ID | 9225 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
disproportion | +0.352 |
Penet | +0.265 |
Valkyrie | +0.257 |
disadvant | +0.256 |
Carmen | +0.244 |
Neg logit contributions | |
antha | -0.329 |
iversal | -0.284 |
arov | -0.281 |
unction | -0.280 |
66666666 | -0.270 |
Token | Laure |
Token ID | 13826 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
antha | +1.368 |
iversal | +1.186 |
arov | +1.180 |
unction | +1.170 |
66666666 | +1.124 |
Neg logit contributions | |
disproportion | -1.387 |
Penet | -1.030 |
Valkyrie | -1.003 |
disadvant | -1.001 |
Carmen | -0.936 |
Token | ates |
Token ID | 689 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
antha | +1.015 |
arov | +0.858 |
iversal | +0.855 |
unction | +0.853 |
atomic | +0.810 |
Neg logit contributions | |
disproportion | -1.272 |
Penet | -0.967 |
disadvant | -0.958 |
Valkyrie | -0.946 |
scapego | -0.895 |
Token | , |
Token ID | 11 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
disproportion | +1.492 |
Penet | +1.079 |
Valkyrie | +1.044 |
disadvant | +1.031 |
Carmen | +0.970 |
Neg logit contributions | |
antha | -1.763 |
iversal | -1.539 |
arov | -1.529 |
unction | -1.524 |
66666666 | -1.476 |
Token | with |
Token ID | 351 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
antha | +0.290 |
arov | +0.251 |
iversal | +0.251 |
unction | +0.249 |
66666666 | +0.241 |
Neg logit contributions | |
disproportion | -0.271 |
Penet | -0.198 |
disadvant | -0.191 |
Valkyrie | -0.191 |
Carmen | -0.180 |
Token | just |
Token ID | 655 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
disproportion | +0.841 |
Penet | +0.610 |
disadvant | +0.589 |
Valkyrie | +0.589 |
Carmen | +0.551 |
Neg logit contributions | |
antha | -0.946 |
iversal | -0.826 |
arov | -0.823 |
unction | -0.818 |
66666666 | -0.790 |
Token | two |
Token ID | 734 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
antha | +1.792 |
arov | +1.574 |
iversal | +1.554 |
unction | +1.549 |
66666666 | +1.513 |
Neg logit contributions | |
disproportion | -1.565 |
Penet | -1.125 |
disadvant | -1.091 |
Valkyrie | -1.075 |
Carmen | -0.997 |
Token | games |
Token ID | 1830 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
disproportion | +0.285 |
Penet | +0.210 |
Valkyrie | +0.203 |
disadvant | +0.203 |
Carmen | +0.192 |
Neg logit contributions | |
antha | -0.296 |
iversal | -0.257 |
arov | -0.256 |
unction | -0.255 |
66666666 | -0.245 |
Token | under |
Token ID | 739 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
antha | +0.025 |
iversal | +0.022 |
arov | +0.022 |
unction | +0.022 |
66666666 | +0.021 |
Neg logit contributions | |
disproportion | -0.025 |
Penet | -0.019 |
Valkyrie | -0.018 |
disadvant | -0.018 |
Carmen | -0.017 |
Token | 20 |
Token ID | 1160 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
disproportion | +3.290 |
Penet | +2.336 |
Valkyrie | +2.249 |
disadvant | +2.218 |
Carmen | +2.079 |
Neg logit contributions | |
antha | -4.370 |
iversal | -3.846 |
unction | -3.825 |
arov | -3.805 |
66666666 | -3.682 |
Token | points |
Token ID | 2173 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
antha | +1.464 |
iversal | +1.269 |
arov | +1.259 |
unction | +1.250 |
66666666 | +1.202 |
Neg logit contributions | |
disproportion | -1.500 |
Penet | -1.106 |
disadvant | -1.076 |
Valkyrie | -1.076 |
Carmen | -1.021 |
Token | in |
Token ID | 287 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
antha | +1.259 |
arov | +1.089 |
iversal | +1.079 |
unction | +1.065 |
66666666 | +1.030 |
Neg logit contributions | |
disproportion | -1.310 |
Penet | -0.977 |
Valkyrie | -0.941 |
disadvant | -0.938 |
Carmen | -0.894 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
antha | +1.495 |
arov | +1.308 |
iversal | +1.305 |
unction | +1.290 |
66666666 | +1.246 |
Neg logit contributions | |
disproportion | -1.376 |
Penet | -1.000 |
disadvant | -0.969 |
Valkyrie | -0.964 |
Carmen | -0.910 |
Token | standard |
Token ID | 3210 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
antha | +1.173 |
arov | +1.031 |
iversal | +1.030 |
unction | +1.021 |
66666666 | +0.987 |
Neg logit contributions | |
disproportion | -1.058 |
Penet | -0.765 |
disadvant | -0.742 |
Valkyrie | -0.736 |
Carmen | -0.699 |
Token | big |
Token ID | 1263 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
antha | +2.646 |
iversal | +2.299 |
arov | +2.286 |
unction | +2.282 |
66666666 | +2.191 |
Neg logit contributions | |
disproportion | -2.504 |
Penet | -1.849 |
Valkyrie | -1.792 |
disadvant | -1.772 |
Carmen | -1.680 |
Token | yo |
Token ID | 27406 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
antha | +0.613 |
iversal | +0.534 |
arov | +0.532 |
unction | +0.531 |
66666666 | +0.512 |
Neg logit contributions | |
disproportion | -0.552 |
Penet | -0.403 |
Valkyrie | -0.390 |
disadvant | -0.387 |
Carmen | -0.366 |
Token | - |
Token ID | 12 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
disproportion | +0.478 |
Penet | +0.365 |
Valkyrie | +0.355 |
disadvant | +0.354 |
Carmen | +0.335 |
Neg logit contributions | |
antha | -0.406 |
iversal | -0.347 |
arov | -0.345 |
unction | -0.343 |
66666666 | -0.329 |
Token | yo |
Token ID | 8226 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
disproportion | +0.188 |
Penet | +0.136 |
Valkyrie | +0.131 |
disadvant | +0.131 |
Carmen | +0.123 |
Neg logit contributions | |
antha | -0.217 |
iversal | -0.190 |
arov | -0.189 |
unction | -0.188 |
66666666 | -0.181 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
antha | +1.225 |
iversal | +1.072 |
arov | +1.067 |
unction | +1.061 |
66666666 | +1.022 |
Neg logit contributions | |
disproportion | -1.148 |
Penet | -0.847 |
Valkyrie | -0.821 |
disadvant | -0.810 |
Carmen | -0.768 |
Token | depending |
Token ID | 6906 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
antha | +0.126 |
iversal | +0.110 |
arov | +0.109 |
unction | +0.109 |
66666666 | +0.105 |
Neg logit contributions | |
disproportion | -0.117 |
Penet | -0.086 |
Valkyrie | -0.083 |
disadvant | -0.083 |
Carmen | -0.078 |
Token | on |
Token ID | 319 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
disproportion | +3.836 |
Penet | +2.628 |
Valkyrie | +2.523 |
disadvant | +2.497 |
Carmen | +2.327 |
Neg logit contributions | |
antha | -5.258 |
unction | -4.632 |
iversal | -4.627 |
arov | -4.627 |
66666666 | -4.465 |
Token | what |
Token ID | 644 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
antha | +1.827 |
iversal | +1.598 |
arov | +1.592 |
unction | +1.575 |
66666666 | +1.525 |
Neg logit contributions | |
disproportion | -1.603 |
Penet | -1.164 |
Valkyrie | -1.129 |
disadvant | -1.127 |
Carmen | -1.053 |
Token | type |
Token ID | 2099 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
disproportion | +0.051 |
Penet | +0.038 |
Valkyrie | +0.037 |
disadvant | +0.037 |
Carmen | +0.035 |
Neg logit contributions | |
antha | -0.049 |
iversal | -0.042 |
arov | -0.042 |
unction | -0.041 |
66666666 | -0.040 |
Token | of |
Token ID | 286 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
antha | +2.832 |
iversal | +2.457 |
arov | +2.446 |
unction | +2.434 |
66666666 | +2.348 |
Neg logit contributions | |
disproportion | -2.708 |
Penet | -1.997 |
Valkyrie | -1.932 |
disadvant | -1.918 |
Carmen | -1.812 |
Token | player |
Token ID | 2137 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
antha | +1.400 |
iversal | +1.210 |
arov | +1.207 |
unction | +1.199 |
66666666 | +1.156 |
Neg logit contributions | |
disproportion | -1.370 |
Penet | -1.018 |
Valkyrie | -0.986 |
disadvant | -0.978 |
Carmen | -0.925 |
Token | don |
Token ID | 836 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
antha | +1.095 |
arov | +0.954 |
iversal | +0.946 |
unction | +0.940 |
66666666 | +0.909 |
Neg logit contributions | |
disproportion | -1.085 |
Penet | -0.819 |
Valkyrie | -0.800 |
disadvant | -0.797 |
Carmen | -0.733 |
Token | � |
Token ID | 447 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
antha | +0.484 |
arov | +0.417 |
unction | +0.412 |
iversal | +0.412 |
66666666 | +0.402 |
Neg logit contributions | |
disproportion | -0.584 |
disadvant | -0.440 |
Penet | -0.438 |
Valkyrie | -0.427 |
scapego | -0.405 |
Token | � |
Token ID | 247 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
antha | +0.295 |
arov | +0.261 |
iversal | +0.260 |
unction | +0.260 |
66666666 | +0.253 |
Neg logit contributions | |
disproportion | -0.220 |
Penet | -0.153 |
disadvant | -0.147 |
Valkyrie | -0.147 |
scapego | -0.136 |
Token | t |
Token ID | 83 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
antha | +1.148 |
unction | +0.996 |
iversal | +0.994 |
arov | +0.989 |
66666666 | +0.952 |
Neg logit contributions | |
disproportion | -1.187 |
Penet | -0.890 |
Valkyrie | -0.867 |
disadvant | -0.864 |
Carmen | -0.804 |
Token | really |
Token ID | 1107 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
antha | +0.813 |
arov | +0.710 |
iversal | +0.708 |
unction | +0.705 |
66666666 | +0.680 |
Neg logit contributions | |
disproportion | -0.833 |
Penet | -0.627 |
Valkyrie | -0.612 |
disadvant | -0.610 |
Carmen | -0.566 |
Token | speak |
Token ID | 2740 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
disproportion | +1.116 |
Penet | +0.844 |
Valkyrie | +0.822 |
disadvant | +0.818 |
Carmen | +0.771 |
Neg logit contributions | |
antha | -1.013 |
iversal | -0.875 |
arov | -0.873 |
unction | -0.866 |
66666666 | -0.835 |
Token | up |
Token ID | 510 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
disproportion | +5.394 |
Penet | +3.866 |
Valkyrie | +3.722 |
disadvant | +3.678 |
Carmen | +3.563 |
Neg logit contributions | |
antha | -6.287 |
iversal | -5.485 |
unction | -5.429 |
arov | -5.414 |
66666666 | -5.182 |
Token | necessarily |
Token ID | 6646 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
antha | +1.328 |
iversal | +1.157 |
unction | +1.150 |
arov | +1.146 |
66666666 | +1.111 |
Neg logit contributions | |
disproportion | -1.300 |
Penet | -0.974 |
Valkyrie | -0.935 |
disadvant | -0.933 |
Carmen | -0.867 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
disproportion | +0.910 |
Penet | +0.665 |
Valkyrie | +0.644 |
disadvant | +0.639 |
Carmen | +0.600 |
Neg logit contributions | |
antha | -1.007 |
iversal | -0.879 |
arov | -0.875 |
unction | -0.872 |
66666666 | -0.842 |
Token | We |
Token ID | 775 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
disproportion | +1.867 |
Penet | +1.382 |
Valkyrie | +1.337 |
disadvant | +1.325 |
Carmen | +1.258 |
Neg logit contributions | |
antha | -1.949 |
iversal | -1.698 |
arov | -1.680 |
unction | -1.678 |
66666666 | -1.611 |
Token | don |
Token ID | 836 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
disproportion | +1.318 |
Penet | +0.974 |
Valkyrie | +0.944 |
disadvant | +0.940 |
Carmen | +0.881 |
Neg logit contributions | |
antha | -1.390 |
iversal | -1.211 |
arov | -1.207 |
unction | -1.198 |
66666666 | -1.155 |
Token | matched |
Token ID | 14451 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
disproportion | +2.650 |
Penet | +1.952 |
Valkyrie | +1.884 |
disadvant | +1.865 |
Carmen | +1.794 |
Neg logit contributions | |
antha | -2.804 |
iversal | -2.467 |
unction | -2.438 |
arov | -2.419 |
66666666 | -2.325 |
Token | the |
Token ID | 262 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
disproportion | +0.024 |
Penet | +0.018 |
Valkyrie | +0.017 |
disadvant | +0.017 |
Carmen | +0.016 |
Neg logit contributions | |
antha | -0.026 |
iversal | -0.023 |
unction | -0.023 |
arov | -0.023 |
66666666 | -0.022 |
Token | number |
Token ID | 1271 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
disproportion | +0.298 |
Penet | +0.214 |
Valkyrie | +0.207 |
disadvant | +0.206 |
Carmen | +0.193 |
Neg logit contributions | |
antha | -0.351 |
iversal | -0.307 |
arov | -0.305 |
unction | -0.304 |
66666666 | -0.294 |
Token | of |
Token ID | 286 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
disproportion | +1.795 |
Penet | +1.291 |
Valkyrie | +1.250 |
disadvant | +1.234 |
Carmen | +1.178 |
Neg logit contributions | |
antha | -2.146 |
iversal | -1.892 |
unction | -1.873 |
arov | -1.856 |
66666666 | -1.798 |
Token | a |
Token ID | 257 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
antha | +0.619 |
iversal | +0.537 |
arov | +0.537 |
unction | +0.533 |
66666666 | +0.514 |
Neg logit contributions | |
disproportion | -0.581 |
Penet | -0.425 |
Valkyrie | -0.412 |
disadvant | -0.412 |
Carmen | -0.386 |
Token | number |
Token ID | 1271 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
disproportion | +1.383 |
Penet | +1.008 |
Valkyrie | +0.975 |
disadvant | +0.968 |
Carmen | +0.913 |
Neg logit contributions | |
antha | -1.540 |
iversal | -1.348 |
arov | -1.334 |
unction | -1.332 |
66666666 | -1.284 |
Token | of |
Token ID | 286 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
disproportion | +3.542 |
Penet | +2.558 |
Valkyrie | +2.487 |
disadvant | +2.457 |
Carmen | +2.355 |
Neg logit contributions | |
antha | -4.113 |
iversal | -3.632 |
unction | -3.591 |
arov | -3.527 |
66666666 | -3.447 |
Token | firms |
Token ID | 9611 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
disproportion | +1.015 |
Penet | +0.742 |
Valkyrie | +0.718 |
disadvant | +0.716 |
Carmen | +0.673 |
Neg logit contributions | |
antha | -1.098 |
iversal | -0.956 |
arov | -0.952 |
unction | -0.947 |
66666666 | -0.913 |
Token | run |
Token ID | 1057 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
disproportion | +1.281 |
Penet | +0.940 |
Valkyrie | +0.910 |
disadvant | +0.906 |
Carmen | +0.855 |
Neg logit contributions | |
antha | -1.373 |
iversal | -1.198 |
unction | -1.185 |
arov | -1.185 |
66666666 | -1.141 |
Token | by |
Token ID | 416 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
disproportion | +1.592 |
Penet | +1.218 |
Valkyrie | +1.182 |
disadvant | +1.174 |
Carmen | +1.134 |
Neg logit contributions | |
antha | -1.280 |
iversal | -1.100 |
unction | -1.076 |
arov | -1.070 |
66666666 | -1.032 |
Token | And |
Token ID | 843 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
disproportion | +1.452 |
Penet | +1.075 |
Valkyrie | +1.037 |
disadvant | +1.030 |
Carmen | +0.975 |
Neg logit contributions | |
antha | -1.529 |
iversal | -1.335 |
unction | -1.318 |
arov | -1.311 |
66666666 | -1.265 |