Token | visualization |
Token ID | 32704 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
llah | +0.489 |
senal | +0.482 |
ibur | +0.413 |
newcom | +0.409 |
dayName | +0.408 |
Neg logit contributions | |
wives | -0.499 |
herself | -0.483 |
anova | -0.475 |
ikawa | -0.472 |
mentation | -0.457 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
llah | +2.294 |
senal | +2.262 |
ibur | +1.999 |
dayName | +1.969 |
newcom | +1.960 |
Neg logit contributions | |
wives | -1.921 |
herself | -1.816 |
anova | -1.800 |
ikawa | -1.786 |
mentation | -1.720 |
Token | I |
Token ID | 314 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
wives | +0.105 |
herself | +0.101 |
anova | +0.099 |
ikawa | +0.098 |
mentation | +0.095 |
Neg logit contributions | |
llah | -0.153 |
senal | -0.152 |
ibur | -0.134 |
newcom | -0.133 |
dayName | -0.133 |
Token | utilized |
Token ID | 21487 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
llah | +2.096 |
senal | +2.072 |
ibur | +1.825 |
newcom | +1.801 |
dayName | +1.797 |
Neg logit contributions | |
wives | -1.630 |
herself | -1.554 |
anova | -1.530 |
ikawa | -1.520 |
mentation | -1.463 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
llah | +2.035 |
senal | +2.006 |
ibur | +1.762 |
newcom | +1.737 |
dayName | +1.733 |
Neg logit contributions | |
wives | -1.740 |
herself | -1.653 |
anova | -1.630 |
ikawa | -1.619 |
mentation | -1.563 |
Token | Census |
Token ID | 20962 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
llah | +1.425 |
senal | +1.408 |
ibur | +1.228 |
newcom | +1.210 |
dayName | +1.210 |
Neg logit contributions | |
wives | -1.265 |
herself | -1.214 |
anova | -1.196 |
ikawa | -1.188 |
mentation | -1.147 |
Token | Bureau |
Token ID | 9840 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
llah | +8.030 |
senal | +7.851 |
ibur | +6.792 |
dayName | +6.697 |
newcom | +6.612 |
Neg logit contributions | |
wives | -9.118 |
ikawa | -8.671 |
anova | -8.593 |
herself | -8.540 |
mentation | -8.437 |
Token | � |
Token ID | 447 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
llah | +4.783 |
senal | +4.736 |
ibur | +4.236 |
dayName | +4.166 |
newcom | +4.153 |
Neg logit contributions | |
wives | -2.946 |
herself | -2.717 |
anova | -2.713 |
ikawa | -2.695 |
mentation | -2.575 |
Token | � |
Token ID | 247 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
senal | +0.679 |
llah | +0.677 |
newcom | +0.557 |
ibur | +0.552 |
dayName | +0.537 |
Neg logit contributions | |
wives | -1.112 |
herself | -1.080 |
anova | -1.069 |
ikawa | -1.058 |
mentation | -1.039 |
Token | s |
Token ID | 82 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
llah | +1.496 |
senal | +1.480 |
ibur | +1.287 |
newcom | +1.272 |
dayName | +1.268 |
Neg logit contributions | |
wives | -1.327 |
herself | -1.276 |
anova | -1.261 |
ikawa | -1.246 |
mentation | -1.203 |
Token | API |
Token ID | 7824 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
llah | +1.686 |
senal | +1.667 |
ibur | +1.452 |
dayName | +1.433 |
newcom | +1.429 |
Neg logit contributions | |
wives | -1.506 |
herself | -1.452 |
anova | -1.428 |
ikawa | -1.418 |
mentation | -1.369 |
Token | advanced |
Token ID | 6190 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
llah | +0.820 |
senal | +0.809 |
ibur | +0.710 |
dayName | +0.700 |
newcom | +0.699 |
Neg logit contributions | |
wives | -0.688 |
herself | -0.658 |
anova | -0.648 |
ikawa | -0.644 |
mentation | -0.620 |
Token | metrics |
Token ID | 20731 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
wives | +2.326 |
herself | +2.317 |
ikawa | +2.217 |
anova | +2.162 |
mentation | +2.157 |
Neg logit contributions | |
senal | -3.997 |
llah | -3.979 |
dayName | -3.481 |
ibur | -3.450 |
newcom | -3.430 |
Token | courtesy |
Token ID | 12537 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
wives | +1.437 |
herself | +1.390 |
ikawa | +1.354 |
anova | +1.347 |
mentation | +1.298 |
Neg logit contributions | |
llah | -1.962 |
senal | -1.961 |
newcom | -1.714 |
ibur | -1.695 |
dayName | -1.685 |
Token | of |
Token ID | 286 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
wives | +3.490 |
herself | +3.344 |
anova | +3.272 |
ikawa | +3.265 |
mentation | +3.149 |
Neg logit contributions | |
llah | -4.384 |
senal | -4.298 |
ibur | -3.775 |
dayName | -3.726 |
newcom | -3.713 |
Token | Pro |
Token ID | 1041 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
wives | +1.423 |
herself | +1.376 |
anova | +1.350 |
ikawa | +1.342 |
mentation | +1.283 |
Neg logit contributions | |
llah | -1.791 |
senal | -1.767 |
ibur | -1.528 |
dayName | -1.524 |
newcom | -1.512 |
Token | Football |
Token ID | 9957 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
llah | +2.184 |
senal | +2.175 |
ibur | +1.934 |
dayName | +1.897 |
newcom | +1.892 |
Neg logit contributions | |
wives | -1.464 |
herself | -1.383 |
anova | -1.369 |
ikawa | -1.359 |
mentation | -1.309 |
Token | Focus |
Token ID | 17061 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
llah | +9.918 |
senal | +9.631 |
ibur | +9.056 |
bedrock | +8.625 |
newcom | +8.449 |
Neg logit contributions | |
wives | -6.371 |
anova | -5.968 |
ikawa | -5.812 |
herself | -5.738 |
weed | -5.624 |
Token | unless |
Token ID | 4556 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
llah | +2.326 |
senal | +2.301 |
ibur | +2.014 |
dayName | +1.985 |
newcom | +1.975 |
Neg logit contributions | |
wives | -2.040 |
herself | -1.936 |
anova | -1.917 |
ikawa | -1.906 |
mentation | -1.842 |
Token | otherwise |
Token ID | 4306 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
herself | +3.895 |
wives | +3.886 |
ikawa | +3.680 |
mentation | +3.637 |
anova | +3.611 |
Neg logit contributions | |
senal | -5.854 |
llah | -5.826 |
ibur | -5.114 |
dayName | -5.106 |
newcom | -5.045 |
Token | indicated |
Token ID | 8203 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
herself | +3.495 |
wives | +3.368 |
ikawa | +3.308 |
anova | +3.222 |
mentation | +3.174 |
Neg logit contributions | |
senal | -5.616 |
llah | -5.483 |
newcom | -4.811 |
ibur | -4.784 |
dayName | -4.701 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
wives | +2.927 |
herself | +2.872 |
ikawa | +2.793 |
anova | +2.787 |
mentation | +2.657 |
Neg logit contributions | |
llah | -4.138 |
senal | -4.110 |
ibur | -3.662 |
dayName | -3.609 |
newcom | -3.587 |
Token | : |
Token ID | 25 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
senal | +0.864 |
llah | +0.862 |
ibur | +0.752 |
newcom | +0.748 |
dayName | +0.742 |
Neg logit contributions | |
wives | -0.690 |
herself | -0.665 |
anova | -0.647 |
ikawa | -0.643 |
mentation | -0.616 |
Token | companies |
Token ID | 2706 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
llah | +2.373 |
senal | +2.344 |
ibur | +2.055 |
newcom | +2.026 |
dayName | +2.024 |
Neg logit contributions | |
wives | -2.000 |
herself | -1.909 |
anova | -1.880 |
ikawa | -1.867 |
mentation | -1.802 |
Token | such |
Token ID | 884 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
llah | +1.862 |
senal | +1.846 |
ibur | +1.611 |
newcom | +1.597 |
dayName | +1.591 |
Neg logit contributions | |
wives | -1.569 |
herself | -1.502 |
anova | -1.475 |
ikawa | -1.465 |
mentation | -1.413 |
Token | as |
Token ID | 355 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
wives | +0.133 |
herself | +0.128 |
anova | +0.124 |
ikawa | +0.123 |
mentation | +0.118 |
Neg logit contributions | |
senal | -0.188 |
llah | -0.186 |
newcom | -0.165 |
ibur | -0.161 |
dayName | -0.161 |
Token | Con |
Token ID | 1482 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
llah | +1.509 |
senal | +1.485 |
ibur | +1.264 |
dayName | +1.257 |
newcom | +1.256 |
Neg logit contributions | |
wives | -1.691 |
herself | -1.628 |
anova | -1.602 |
ikawa | -1.589 |
mentation | -1.544 |
Token | oco |
Token ID | 25634 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
llah | +1.900 |
senal | +1.866 |
newcom | +1.554 |
dayName | +1.552 |
ibur | +1.537 |
Neg logit contributions | |
wives | -2.490 |
herself | -2.403 |
anova | -2.379 |
ikawa | -2.354 |
mentation | -2.280 |
Token | Phill |
Token ID | 41970 |
Feature activation | +9.54e+00 |
Pos logit contributions | |
llah | +5.640 |
senal | +5.396 |
ibur | +4.695 |
dayName | +4.493 |
bedrock | +4.407 |
Neg logit contributions | |
wives | -10.320 |
anova | -9.914 |
ikawa | -9.850 |
herself | -9.743 |
tarians | -9.739 |
Token | ips |
Token ID | 2419 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
llah | +5.431 |
senal | +4.778 |
ibur | +4.756 |
dayName | +4.694 |
bedrock | +4.317 |
Neg logit contributions | |
wives | -8.101 |
herself | -7.847 |
anova | -7.677 |
ikawa | -7.651 |
mentation | -7.596 |
Token | and |
Token ID | 290 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
llah | +2.690 |
senal | +2.657 |
ibur | +2.336 |
newcom | +2.304 |
dayName | +2.300 |
Neg logit contributions | |
wives | -2.169 |
herself | -2.068 |
anova | -2.037 |
ikawa | -2.023 |
mentation | -1.949 |
Token | Marathon |
Token ID | 24828 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
llah | +2.052 |
senal | +2.022 |
ibur | +1.741 |
newcom | +1.712 |
dayName | +1.709 |
Neg logit contributions | |
wives | -2.220 |
herself | -2.131 |
anova | -2.105 |
ikawa | -2.092 |
mentation | -2.027 |
Token | have |
Token ID | 423 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
llah | +1.112 |
senal | +1.105 |
newcom | +0.986 |
dayName | +0.983 |
ibur | +0.973 |
Neg logit contributions | |
wives | -0.648 |
herself | -0.618 |
anova | -0.587 |
ikawa | -0.580 |
mentation | -0.554 |
Token | � |
Token ID | 564 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
senal | +0.616 |
llah | +0.607 |
newcom | +0.537 |
dayName | +0.525 |
ibur | +0.524 |
Neg logit contributions | |
wives | -0.494 |
herself | -0.472 |
anova | -0.461 |
ikawa | -0.459 |
mentation | -0.440 |
Token | � |
Token ID | 250 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
llah | +0.021 |
senal | +0.021 |
ibur | +0.017 |
newcom | +0.017 |
dayName | +0.017 |
Neg logit contributions | |
wives | -0.029 |
herself | -0.028 |
anova | -0.027 |
ikawa | -0.027 |
mentation | -0.026 |
Token | One |
Token ID | 3198 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
llah | +2.144 |
senal | +2.126 |
ibur | +1.847 |
newcom | +1.832 |
dayName | +1.823 |
Neg logit contributions | |
wives | -1.903 |
herself | -1.817 |
anova | -1.792 |
ikawa | -1.778 |
mentation | -1.718 |
Token | of |
Token ID | 286 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
wives | +0.649 |
herself | +0.635 |
anova | +0.616 |
ikawa | +0.607 |
mentation | +0.589 |
Neg logit contributions | |
senal | -0.799 |
llah | -0.793 |
dayName | -0.685 |
newcom | -0.683 |
ibur | -0.673 |
Token | my |
Token ID | 616 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
llah | +0.315 |
senal | +0.314 |
dayName | +0.274 |
ibur | +0.273 |
newcom | +0.272 |
Neg logit contributions | |
wives | -0.246 |
herself | -0.237 |
anova | -0.229 |
ikawa | -0.229 |
mentation | -0.221 |
Token | jobs |
Token ID | 3946 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
senal | +0.731 |
llah | +0.724 |
dayName | +0.622 |
newcom | +0.621 |
ibur | +0.620 |
Neg logit contributions | |
wives | -0.716 |
herself | -0.686 |
anova | -0.671 |
ikawa | -0.665 |
mentation | -0.646 |
Token | at |
Token ID | 379 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
llah | +7.718 |
senal | +7.248 |
ibur | +6.589 |
bedrock | +6.382 |
dayName | +6.361 |
Neg logit contributions | |
wives | -7.716 |
ikawa | -7.448 |
anova | -7.393 |
herself | -7.331 |
mentation | -7.224 |
Token | the |
Token ID | 262 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
llah | +3.998 |
senal | +3.918 |
ibur | +3.502 |
newcom | +3.404 |
dayName | +3.378 |
Neg logit contributions | |
wives | -3.321 |
herself | -3.144 |
anova | -3.124 |
ikawa | -3.115 |
mentation | -2.992 |
Token | time |
Token ID | 640 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
llah | +2.466 |
senal | +2.434 |
ibur | +2.140 |
newcom | +2.107 |
dayName | +2.104 |
Neg logit contributions | |
wives | -2.029 |
herself | -1.935 |
anova | -1.908 |
ikawa | -1.895 |
mentation | -1.827 |
Token | was |
Token ID | 373 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
llah | +1.032 |
senal | +1.027 |
ibur | +0.895 |
newcom | +0.887 |
dayName | +0.881 |
Neg logit contributions | |
wives | -0.862 |
herself | -0.824 |
anova | -0.809 |
ikawa | -0.804 |
mentation | -0.774 |
Token | to |
Token ID | 284 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
llah | +1.853 |
senal | +1.829 |
ibur | +1.596 |
newcom | +1.576 |
dayName | +1.572 |
Neg logit contributions | |
wives | -1.649 |
herself | -1.578 |
anova | -1.553 |
ikawa | -1.543 |
mentation | -1.491 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
wives | +0.764 |
herself | +0.749 |
anova | +0.708 |
ikawa | +0.703 |
mentation | +0.678 |
Neg logit contributions | |
senal | -1.050 |
llah | -1.021 |
ibur | -0.906 |
newcom | -0.904 |
dayName | -0.889 |
Token | � |
Token ID | 447 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
wives | +1.129 |
herself | +1.093 |
anova | +1.071 |
ikawa | +1.065 |
mentation | +1.038 |
Neg logit contributions | |
senal | -0.846 |
llah | -0.818 |
newcom | -0.704 |
ibur | -0.689 |
dayName | -0.670 |
Token | � |
Token ID | 251 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
wives | +1.416 |
herself | +1.366 |
anova | +1.353 |
ikawa | +1.347 |
mentation | +1.310 |
Neg logit contributions | |
llah | -0.912 |
senal | -0.895 |
ibur | -0.741 |
dayName | -0.725 |
newcom | -0.724 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
wives | +1.564 |
herself | +1.503 |
anova | +1.472 |
ikawa | +1.457 |
mentation | +1.405 |
Neg logit contributions | |
senal | -1.819 |
llah | -1.780 |
newcom | -1.574 |
ibur | -1.556 |
dayName | -1.526 |
Token | Power |
Token ID | 13434 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
llah | +1.288 |
senal | +1.273 |
ibur | +1.106 |
newcom | +1.091 |
dayName | +1.088 |
Neg logit contributions | |
wives | -1.216 |
herself | -1.163 |
anova | -1.148 |
ikawa | -1.140 |
mentation | -1.102 |
Token | BI |
Token ID | 20068 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
llah | +0.384 |
senal | +0.381 |
ibur | +0.335 |
newcom | +0.331 |
dayName | +0.329 |
Neg logit contributions | |
wives | -0.297 |
herself | -0.282 |
anova | -0.278 |
ikawa | -0.275 |
mentation | -0.266 |
Token | has |
Token ID | 468 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
senal | +8.285 |
llah | +8.251 |
ibur | +7.444 |
dayName | +7.166 |
bedrock | +7.126 |
Neg logit contributions | |
wives | -7.128 |
ikawa | -6.692 |
herself | -6.642 |
anova | -6.635 |
tarians | -6.461 |
Token | come |
Token ID | 1282 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
llah | +1.280 |
senal | +1.266 |
ibur | +1.103 |
newcom | +1.091 |
dayName | +1.089 |
Neg logit contributions | |
wives | -1.117 |
herself | -1.071 |
anova | -1.053 |
ikawa | -1.043 |
mentation | -1.009 |
Token | a |
Token ID | 257 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
llah | +1.184 |
senal | +1.175 |
ibur | +1.032 |
dayName | +1.021 |
newcom | +1.021 |
Neg logit contributions | |
wives | -0.965 |
herself | -0.926 |
anova | -0.903 |
ikawa | -0.893 |
mentation | -0.866 |
Token | long |
Token ID | 890 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
wives | +2.317 |
herself | +2.188 |
ikawa | +2.144 |
anova | +2.098 |
mentation | +2.000 |
Neg logit contributions | |
senal | -3.805 |
llah | -3.787 |
ibur | -3.424 |
dayName | -3.376 |
newcom | -3.343 |
Token | way |
Token ID | 835 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
wives | +1.260 |
herself | +1.196 |
anova | +1.171 |
ikawa | +1.147 |
mentation | +1.087 |
Neg logit contributions | |
llah | -2.025 |
senal | -2.013 |
ibur | -1.787 |
dayName | -1.762 |
newcom | -1.759 |
Token | States |
Token ID | 1829 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
wives | +0.409 |
herself | +0.388 |
anova | +0.370 |
ikawa | +0.359 |
mentation | +0.343 |
Neg logit contributions | |
senal | -1.039 |
llah | -1.007 |
newcom | -0.939 |
ibur | -0.910 |
dayName | -0.895 |
Token | , |
Token ID | 11 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
wives | +0.438 |
herself | +0.420 |
anova | +0.411 |
ikawa | +0.408 |
mentation | +0.393 |
Neg logit contributions | |
llah | -0.560 |
senal | -0.557 |
ibur | -0.489 |
newcom | -0.483 |
dayName | -0.481 |
Token | according |
Token ID | 1864 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
wives | +0.657 |
herself | +0.638 |
anova | +0.619 |
ikawa | +0.609 |
mentation | +0.589 |
Neg logit contributions | |
senal | -0.839 |
llah | -0.834 |
ibur | -0.726 |
dayName | -0.722 |
newcom | -0.719 |
Token | to |
Token ID | 284 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
llah | +0.676 |
senal | +0.674 |
ibur | +0.583 |
newcom | +0.581 |
dayName | +0.574 |
Neg logit contributions | |
wives | -0.594 |
herself | -0.570 |
anova | -0.560 |
ikawa | -0.556 |
mentation | -0.537 |
Token | the |
Token ID | 262 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
wives | +0.206 |
herself | +0.198 |
anova | +0.195 |
ikawa | +0.193 |
mentation | +0.186 |
Neg logit contributions | |
llah | -0.265 |
senal | -0.263 |
ibur | -0.231 |
dayName | -0.228 |
newcom | -0.227 |
Token | Census |
Token ID | 20962 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
llah | +0.533 |
senal | +0.530 |
ibur | +0.463 |
newcom | +0.457 |
dayName | +0.456 |
Neg logit contributions | |
wives | -0.436 |
herself | -0.419 |
anova | -0.413 |
ikawa | -0.407 |
mentation | -0.394 |
Token | Bureau |
Token ID | 9840 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
llah | +6.583 |
senal | +6.202 |
ibur | +5.249 |
newcom | +5.161 |
bedrock | +5.112 |
Neg logit contributions | |
wives | -8.971 |
ikawa | -8.601 |
anova | -8.379 |
mentation | -8.305 |
herself | -8.239 |
Token | . |
Token ID | 13 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
llah | +2.957 |
senal | +2.891 |
ibur | +2.509 |
dayName | +2.467 |
newcom | +2.455 |
Neg logit contributions | |
wives | -2.747 |
ikawa | -2.576 |
anova | -2.575 |
herself | -2.552 |
tarians | -2.491 |
Token | And |
Token ID | 843 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
senal | +0.762 |
llah | +0.761 |
ibur | +0.659 |
newcom | +0.658 |
dayName | +0.649 |
Neg logit contributions | |
wives | -0.645 |
herself | -0.618 |
anova | -0.606 |
ikawa | -0.601 |
mentation | -0.581 |
Token | while |
Token ID | 981 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
llah | +1.821 |
senal | +1.794 |
ibur | +1.577 |
newcom | +1.551 |
dayName | +1.547 |
Neg logit contributions | |
wives | -1.557 |
herself | -1.483 |
anova | -1.465 |
ikawa | -1.457 |
mentation | -1.404 |
Token | millennials |
Token ID | 30418 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
wives | +1.727 |
herself | +1.694 |
anova | +1.616 |
ikawa | +1.588 |
mentation | +1.563 |
Neg logit contributions | |
senal | -2.212 |
llah | -2.197 |
dayName | -1.927 |
ibur | -1.909 |
newcom | -1.896 |
Token | former |
Token ID | 1966 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
wives | +1.186 |
herself | +1.146 |
anova | +1.126 |
ikawa | +1.113 |
mentation | +1.083 |
Neg logit contributions | |
llah | -1.280 |
senal | -1.272 |
ibur | -1.102 |
dayName | -1.092 |
newcom | -1.080 |
Token | St |
Token ID | 520 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
llah | +1.001 |
senal | +0.990 |
ibur | +0.866 |
dayName | +0.853 |
newcom | +0.853 |
Neg logit contributions | |
wives | -0.862 |
herself | -0.825 |
anova | -0.814 |
ikawa | -0.806 |
mentation | -0.779 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
llah | +2.756 |
senal | +2.693 |
ibur | +2.415 |
dayName | +2.329 |
newcom | +2.311 |
Neg logit contributions | |
wives | -2.565 |
herself | -2.464 |
ikawa | -2.410 |
anova | -2.380 |
mentation | -2.324 |
Token | Louis |
Token ID | 5593 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
llah | +3.425 |
senal | +3.370 |
ibur | +2.986 |
dayName | +2.894 |
newcom | +2.892 |
Neg logit contributions | |
wives | -3.120 |
herself | -2.970 |
ikawa | -2.945 |
anova | -2.883 |
tarians | -2.814 |
Token | Rams |
Token ID | 16077 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
llah | +0.800 |
senal | +0.791 |
ibur | +0.700 |
dayName | +0.694 |
newcom | +0.691 |
Neg logit contributions | |
wives | -0.553 |
herself | -0.524 |
anova | -0.517 |
ikawa | -0.510 |
mentation | -0.492 |
Token | kicker |
Token ID | 38297 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
llah | +3.317 |
senal | +3.253 |
ibur | +2.860 |
newcom | +2.824 |
dayName | +2.785 |
Neg logit contributions | |
wives | -3.110 |
herself | -2.958 |
ikawa | -2.928 |
anova | -2.914 |
mentation | -2.811 |
Token | Brett |
Token ID | 18726 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
llah | +7.743 |
senal | +7.598 |
newcom | +6.784 |
ibur | +6.770 |
bedrock | +6.752 |
Neg logit contributions | |
wives | -7.063 |
ikawa | -6.564 |
anova | -6.433 |
tarians | -6.383 |
herself | -6.364 |
Token | Ba |
Token ID | 8999 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
llah | +2.813 |
senal | +2.736 |
ibur | +2.444 |
newcom | +2.383 |
dayName | +2.366 |
Neg logit contributions | |
wives | -2.262 |
herself | -2.132 |
anova | -2.116 |
ikawa | -2.101 |
mentation | -2.027 |
Token | er |
Token ID | 263 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
llah | +4.551 |
senal | +4.376 |
ibur | +4.011 |
dayName | +3.847 |
bedrock | +3.782 |
Neg logit contributions | |
wives | -4.148 |
herself | -3.926 |
anova | -3.843 |
ikawa | -3.815 |
mentation | -3.740 |
Token | – |
Token ID | 784 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
llah | +3.834 |
senal | +3.750 |
ibur | +3.314 |
dayName | +3.242 |
newcom | +3.238 |
Neg logit contributions | |
wives | -3.357 |
herself | -3.193 |
anova | -3.158 |
ikawa | -3.138 |
mentation | -3.037 |
Token | who |
Token ID | 508 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
wives | +0.598 |
herself | +0.582 |
anova | +0.567 |
ikawa | +0.554 |
mentation | +0.545 |
Neg logit contributions | |
llah | -0.667 |
senal | -0.663 |
ibur | -0.573 |
dayName | -0.571 |
newcom | -0.565 |
Token | the |
Token ID | 262 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
llah | +0.766 |
senal | +0.762 |
ibur | +0.672 |
dayName | +0.664 |
newcom | +0.662 |
Neg logit contributions | |
wives | -0.575 |
herself | -0.554 |
anova | -0.539 |
ikawa | -0.536 |
mentation | -0.519 |
Token | key |
Token ID | 1994 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
senal | +0.433 |
llah | +0.429 |
ibur | +0.372 |
dayName | +0.368 |
newcom | +0.367 |
Neg logit contributions | |
wives | -0.410 |
herself | -0.404 |
anova | -0.390 |
ikawa | -0.389 |
mentation | -0.377 |
Token | northern |
Token ID | 7840 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
wives | +0.855 |
herself | +0.851 |
anova | +0.813 |
ikawa | +0.810 |
mentation | +0.783 |
Neg logit contributions | |
senal | -0.929 |
llah | -0.914 |
dayName | -0.788 |
newcom | -0.787 |
ibur | -0.785 |
Token | city |
Token ID | 1748 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
wives | +0.757 |
herself | +0.739 |
anova | +0.709 |
ikawa | +0.706 |
mentation | +0.691 |
Neg logit contributions | |
senal | -0.854 |
llah | -0.843 |
ibur | -0.733 |
newcom | -0.728 |
dayName | -0.725 |
Token | , |
Token ID | 11 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
wives | +0.738 |
herself | +0.714 |
anova | +0.684 |
ikawa | +0.684 |
mentation | +0.660 |
Neg logit contributions | |
llah | -0.931 |
senal | -0.930 |
ibur | -0.813 |
newcom | -0.809 |
dayName | -0.800 |
Token | AP |
Token ID | 3486 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
wives | +0.053 |
herself | +0.051 |
anova | +0.049 |
ikawa | +0.049 |
mentation | +0.047 |
Neg logit contributions | |
llah | -0.065 |
senal | -0.064 |
ibur | -0.056 |
newcom | -0.056 |
dayName | -0.055 |
Token | reports |
Token ID | 3136 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
llah | +7.356 |
senal | +6.988 |
ibur | +6.120 |
newcom | +5.865 |
dayName | +5.783 |
Neg logit contributions | |
wives | -7.811 |
anova | -7.378 |
ikawa | -7.353 |
herself | -7.291 |
tarians | -7.153 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
llah | +4.801 |
senal | +4.639 |
ibur | +4.073 |
dayName | +3.982 |
newcom | +3.949 |
Neg logit contributions | |
wives | -4.634 |
anova | -4.406 |
herself | -4.362 |
ikawa | -4.334 |
mentation | -4.254 |
Token |
|
Token ID | 198 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
llah | +1.392 |
senal | +1.382 |
ibur | +1.204 |
newcom | +1.191 |
dayName | +1.183 |
Neg logit contributions | |
wives | -1.244 |
herself | -1.189 |
anova | -1.171 |
ikawa | -1.164 |
mentation | -1.123 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
senal | +0.627 |
llah | +0.621 |
newcom | +0.536 |
ibur | +0.533 |
dayName | +0.523 |
Neg logit contributions | |
wives | -0.599 |
herself | -0.575 |
anova | -0.565 |
ikawa | -0.561 |
mentation | -0.543 |
Token | Also |
Token ID | 7583 |
Feature activation | +8.46e+00 |
Pos logit contributions | |
senal | +0.166 |
llah | +0.163 |
newcom | +0.143 |
ibur | +0.140 |
dayName | +0.139 |
Neg logit contributions | |
wives | -0.143 |
herself | -0.135 |
anova | -0.134 |
ikawa | -0.132 |
mentation | -0.128 |
Token | this |
Token ID | 428 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
wives | +2.180 |
herself | +2.161 |
anova | +2.063 |
ikawa | +2.025 |
mentation | +1.965 |
Neg logit contributions | |
senal | -3.330 |
llah | -3.311 |
dayName | -2.935 |
ibur | -2.918 |
newcom | -2.882 |
Token | year |
Token ID | 614 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
wives | +0.413 |
herself | +0.396 |
anova | +0.383 |
ikawa | +0.376 |
mentation | +0.360 |
Neg logit contributions | |
llah | -0.748 |
senal | -0.746 |
ibur | -0.664 |
dayName | -0.657 |
newcom | -0.656 |
Token | 's |
Token ID | 338 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
wives | +0.296 |
anova | +0.274 |
herself | +0.274 |
ikawa | +0.271 |
mentation | +0.256 |
Neg logit contributions | |
llah | -0.540 |
senal | -0.534 |
ibur | -0.476 |
dayName | -0.473 |
newcom | -0.473 |
Token | N |
Token ID | 399 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
wives | +0.686 |
herself | +0.669 |
anova | +0.651 |
ikawa | +0.643 |
mentation | +0.624 |
Neg logit contributions | |
senal | -0.881 |
llah | -0.880 |
ibur | -0.770 |
dayName | -0.761 |
newcom | -0.752 |
Token | AB |
Token ID | 6242 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
senal | +0.069 |
llah | +0.069 |
dayName | +0.063 |
newcom | +0.062 |
ibur | +0.061 |
Neg logit contributions | |
wives | -0.039 |
anova | -0.038 |
herself | -0.038 |
ikawa | -0.037 |
mentation | -0.036 |
Token | AFL |
Token ID | 25363 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
llah | +1.939 |
senal | +1.931 |
ibur | +1.713 |
dayName | +1.699 |
newcom | +1.692 |
Neg logit contributions | |
wives | -1.207 |
herself | -1.165 |
anova | -1.122 |
ikawa | -1.115 |
mentation | -1.065 |
Token | Trade |
Token ID | 9601 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
llah | +8.174 |
senal | +7.908 |
newcom | +7.079 |
ibur | +7.039 |
bedrock | +6.990 |
Neg logit contributions | |
wives | -6.775 |
ikawa | -6.529 |
anova | -6.470 |
herself | -6.394 |
tarians | -6.094 |
Token | Period |
Token ID | 18581 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
wives | +0.840 |
herself | +0.801 |
anova | +0.754 |
ikawa | +0.736 |
mentation | +0.731 |
Neg logit contributions | |
llah | -2.028 |
senal | -2.025 |
ibur | -1.830 |
newcom | -1.807 |
dayName | -1.805 |
Token | after |
Token ID | 706 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
llah | +1.753 |
senal | +1.731 |
ibur | +1.522 |
newcom | +1.501 |
dayName | +1.498 |
Neg logit contributions | |
wives | -1.426 |
herself | -1.357 |
anova | -1.340 |
ikawa | -1.331 |
mentation | -1.282 |
Token | playing |
Token ID | 2712 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
wives | +2.902 |
herself | +2.841 |
anova | +2.717 |
ikawa | +2.677 |
mentation | +2.578 |
Neg logit contributions | |
llah | -3.751 |
senal | -3.735 |
dayName | -3.246 |
ibur | -3.210 |
newcom | -3.205 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
wives | +0.043 |
herself | +0.041 |
anova | +0.040 |
ikawa | +0.040 |
mentation | +0.039 |
Neg logit contributions | |
llah | -0.056 |
senal | -0.055 |
ibur | -0.049 |
dayName | -0.048 |
newcom | -0.048 |
Token | Y |
Token ID | 575 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
wives | +0.056 |
herself | +0.053 |
anova | +0.053 |
ikawa | +0.053 |
mentation | +0.051 |
Neg logit contributions | |
llah | -0.067 |
senal | -0.066 |
ibur | -0.058 |
newcom | -0.057 |
dayName | -0.056 |
Token | anda |
Token ID | 5282 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
wives | +1.158 |
herself | +1.100 |
anova | +1.096 |
ikawa | +1.072 |
mentation | +1.030 |
Neg logit contributions | |
llah | -1.728 |
senal | -1.719 |
newcom | -1.507 |
ibur | -1.497 |
dayName | -1.484 |
Token | — |
Token ID | 851 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
wives | +1.032 |
herself | +0.999 |
anova | +0.976 |
ikawa | +0.975 |
mentation | +0.931 |
Neg logit contributions | |
llah | -1.172 |
senal | -1.170 |
ibur | -1.015 |
newcom | -1.004 |
dayName | -1.001 |
Token | per |
Token ID | 583 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
wives | +0.034 |
herself | +0.033 |
anova | +0.032 |
ikawa | +0.032 |
mentation | +0.031 |
Neg logit contributions | |
llah | -0.047 |
senal | -0.047 |
ibur | -0.041 |
dayName | -0.040 |
newcom | -0.040 |
Token | Pro |
Token ID | 1041 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
llah | +0.399 |
senal | +0.396 |
ibur | +0.345 |
dayName | +0.340 |
newcom | +0.340 |
Neg logit contributions | |
wives | -0.351 |
herself | -0.337 |
anova | -0.332 |
ikawa | -0.330 |
mentation | -0.318 |
Token | Football |
Token ID | 9957 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
llah | +1.646 |
senal | +1.636 |
ibur | +1.455 |
dayName | +1.429 |
newcom | +1.424 |
Neg logit contributions | |
wives | -1.111 |
herself | -1.047 |
anova | -1.039 |
ikawa | -1.032 |
mentation | -0.993 |
Token | Focus |
Token ID | 17061 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
llah | +8.867 |
senal | +8.509 |
ibur | +8.126 |
bedrock | +7.689 |
newcom | +7.688 |
Neg logit contributions | |
wives | -5.712 |
anova | -5.332 |
ikawa | -5.195 |
herself | -5.147 |
weed | -5.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
llah | +2.311 |
senal | +2.277 |
ibur | +1.991 |
newcom | +1.971 |
dayName | +1.966 |
Neg logit contributions | |
wives | -2.038 |
herself | -1.924 |
anova | -1.906 |
ikawa | -1.896 |
mentation | -1.835 |
Token |
|
Token ID | 198 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
llah | +1.127 |
senal | +1.114 |
ibur | +0.983 |
newcom | +0.969 |
dayName | +0.967 |
Neg logit contributions | |
wives | -0.864 |
herself | -0.822 |
anova | -0.811 |
ikawa | -0.804 |
mentation | -0.774 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
senal | +0.646 |
llah | +0.645 |
ibur | +0.553 |
newcom | +0.551 |
dayName | +0.542 |
Neg logit contributions | |
wives | -0.632 |
herself | -0.606 |
anova | -0.597 |
ikawa | -0.593 |
mentation | -0.574 |
Token | A |
Token ID | 32 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
llah | +0.886 |
senal | +0.882 |
ibur | +0.758 |
newcom | +0.753 |
dayName | +0.744 |
Neg logit contributions | |
wives | -0.870 |
herself | -0.831 |
anova | -0.823 |
ikawa | -0.815 |
mentation | -0.791 |
Token | Brazilian |
Token ID | 17036 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
wives | +0.894 |
herself | +0.870 |
ikawa | +0.838 |
anova | +0.831 |
mentation | +0.809 |
Neg logit contributions | |
senal | -0.984 |
llah | -0.977 |
dayName | -0.856 |
ibur | -0.841 |
newcom | -0.841 |
Token | prosecutor |
Token ID | 13683 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
wives | +0.857 |
herself | +0.836 |
anova | +0.810 |
ikawa | +0.804 |
mentation | +0.779 |
Neg logit contributions | |
llah | -0.959 |
senal | -0.956 |
dayName | -0.831 |
newcom | -0.824 |
ibur | -0.821 |
Token | that |
Token ID | 326 |
Feature activation | -6.24e-03 |
Pos logit contributions | |
wives | +2.482 |
herself | +2.455 |
anova | +2.305 |
ikawa | +2.301 |
mentation | +2.196 |
Neg logit contributions | |
llah | -3.474 |
senal | -3.456 |
newcom | -3.074 |
dayName | -3.074 |
ibur | -3.063 |
Token | Rolls |
Token ID | 40074 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
wives | +0.004 |
herself | +0.004 |
anova | +0.004 |
ikawa | +0.004 |
mentation | +0.004 |
Neg logit contributions | |
llah | -0.005 |
senal | -0.005 |
ibur | -0.005 |
dayName | -0.005 |
newcom | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
llah | +3.881 |
senal | +3.831 |
ibur | +3.414 |
newcom | +3.336 |
dayName | +3.332 |
Neg logit contributions | |
wives | -2.880 |
herself | -2.721 |
anova | -2.692 |
ikawa | -2.677 |
mentation | -2.576 |
Token | Roy |
Token ID | 32027 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
llah | +2.926 |
senal | +2.916 |
ibur | +2.541 |
dayName | +2.491 |
newcom | +2.485 |
Neg logit contributions | |
wives | -2.694 |
herself | -2.567 |
anova | -2.529 |
ikawa | -2.528 |
mentation | -2.440 |
Token | ce |
Token ID | 344 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
llah | +4.245 |
senal | +3.877 |
ibur | +3.602 |
dayName | +3.196 |
bedrock | +2.998 |
Neg logit contributions | |
wives | -10.277 |
herself | -9.793 |
anova | -9.665 |
ikawa | -9.629 |
mentation | -9.496 |
Token | is |
Token ID | 318 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
llah | +4.070 |
senal | +4.011 |
ibur | +3.566 |
dayName | +3.421 |
newcom | +3.408 |
Neg logit contributions | |
wives | -3.489 |
anova | -3.304 |
ikawa | -3.298 |
herself | -3.281 |
mentation | -3.185 |
Token | co |
Token ID | 763 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
llah | +1.500 |
senal | +1.479 |
ibur | +1.295 |
newcom | +1.272 |
dayName | +1.271 |
Neg logit contributions | |
wives | -1.337 |
herself | -1.275 |
anova | -1.261 |
ikawa | -1.252 |
mentation | -1.211 |
Token | - |
Token ID | 12 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
wives | +0.085 |
herself | +0.081 |
anova | +0.080 |
ikawa | +0.079 |
mentation | +0.076 |
Neg logit contributions | |
llah | -0.118 |
senal | -0.117 |
ibur | -0.104 |
newcom | -0.102 |
dayName | -0.102 |
Token | oper |
Token ID | 3575 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
wives | +1.004 |
herself | +0.946 |
anova | +0.937 |
ikawa | +0.927 |
mentation | +0.900 |
Neg logit contributions | |
llah | -0.999 |
senal | -0.995 |
newcom | -0.856 |
ibur | -0.843 |
dayName | -0.840 |
Token | vy |
Token ID | 7670 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
llah | +1.510 |
senal | +1.494 |
ibur | +1.233 |
newcom | +1.216 |
dayName | +1.208 |
Neg logit contributions | |
wives | -2.254 |
herself | -2.181 |
anova | -2.160 |
ikawa | -2.148 |
mentation | -2.088 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
llah | +0.115 |
senal | +0.115 |
ibur | +0.100 |
dayName | +0.099 |
newcom | +0.099 |
Neg logit contributions | |
wives | -0.090 |
herself | -0.086 |
anova | -0.084 |
ikawa | -0.083 |
mentation | -0.080 |
Token | but |
Token ID | 475 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
llah | +2.071 |
senal | +2.036 |
ibur | +1.799 |
newcom | +1.767 |
dayName | +1.765 |
Neg logit contributions | |
wives | -1.695 |
herself | -1.605 |
anova | -1.595 |
ikawa | -1.585 |
mentation | -1.523 |
Token | his |
Token ID | 465 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
llah | +1.121 |
senal | +1.108 |
ibur | +0.976 |
newcom | +0.963 |
dayName | +0.963 |
Neg logit contributions | |
wives | -0.860 |
herself | -0.820 |
anova | -0.807 |
ikawa | -0.801 |
mentation | -0.771 |
Token | message |
Token ID | 3275 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
llah | +1.247 |
senal | +1.231 |
ibur | +1.079 |
newcom | +1.062 |
dayName | +1.061 |
Neg logit contributions | |
wives | -1.067 |
herself | -1.019 |
anova | -1.004 |
ikawa | -0.998 |
mentation | -0.963 |
Token | reson |
Token ID | 14309 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
llah | +4.322 |
senal | +4.143 |
ibur | +3.717 |
bedrock | +3.636 |
dayName | +3.624 |
Neg logit contributions | |
wives | -4.221 |
anova | -4.015 |
ikawa | -3.992 |
herself | -3.972 |
mentation | -3.828 |
Token | ated |
Token ID | 515 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
llah | +5.339 |
senal | +4.917 |
ibur | +4.393 |
dayName | +4.111 |
bedrock | +4.040 |
Neg logit contributions | |
wives | -9.268 |
herself | -8.894 |
anova | -8.750 |
ikawa | -8.712 |
weed | -8.482 |
Token | with |
Token ID | 351 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
llah | +4.260 |
senal | +4.051 |
ibur | +3.641 |
bedrock | +3.603 |
dayName | +3.569 |
Neg logit contributions | |
wives | -3.803 |
anova | -3.599 |
ikawa | -3.594 |
herself | -3.557 |
mentation | -3.435 |
Token | those |
Token ID | 883 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
llah | +2.347 |
senal | +2.301 |
ibur | +2.050 |
newcom | +2.015 |
dayName | +2.005 |
Neg logit contributions | |
wives | -1.809 |
herself | -1.707 |
anova | -1.698 |
ikawa | -1.687 |
mentation | -1.619 |
Token | who |
Token ID | 508 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
llah | +2.575 |
senal | +2.507 |
ibur | +2.216 |
bedrock | +2.162 |
newcom | +2.161 |
Neg logit contributions | |
wives | -2.471 |
anova | -2.338 |
herself | -2.332 |
ikawa | -2.330 |
mentation | -2.238 |
Token | were |
Token ID | 547 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
llah | +2.413 |
senal | +2.350 |
ibur | +2.081 |
dayName | +2.044 |
newcom | +2.022 |
Neg logit contributions | |
wives | -2.208 |
herself | -2.092 |
anova | -2.083 |
ikawa | -2.073 |
mentation | -1.995 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
llah | +2.436 |
senal | +2.387 |
ibur | +2.099 |
dayName | +2.069 |
newcom | +2.064 |
Neg logit contributions | |
wives | -2.110 |
herself | -2.008 |
anova | -1.990 |
ikawa | -1.981 |
mentation | -1.909 |
Token | � |
Token ID | 447 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
wives | +0.159 |
herself | +0.151 |
anova | +0.148 |
ikawa | +0.146 |
mentation | +0.142 |
Neg logit contributions | |
senal | -0.202 |
llah | -0.198 |
newcom | -0.175 |
ibur | -0.175 |
dayName | -0.171 |
Token | � |
Token ID | 251 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
wives | +0.471 |
herself | +0.457 |
anova | +0.450 |
ikawa | +0.447 |
mentation | +0.437 |
Neg logit contributions | |
senal | -0.331 |
llah | -0.330 |
ibur | -0.275 |
newcom | -0.271 |
dayName | -0.268 |
Token | – |
Token ID | 784 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
wives | +1.167 |
herself | +1.119 |
anova | +1.097 |
ikawa | +1.081 |
mentation | +1.055 |
Neg logit contributions | |
senal | -1.277 |
llah | -1.260 |
ibur | -1.100 |
newcom | -1.099 |
dayName | -1.084 |
Token | Associated |
Token ID | 10575 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
llah | +0.022 |
senal | +0.022 |
ibur | +0.019 |
newcom | +0.019 |
dayName | +0.019 |
Neg logit contributions | |
wives | -0.019 |
herself | -0.018 |
anova | -0.018 |
ikawa | -0.018 |
mentation | -0.017 |
Token | Press |
Token ID | 4332 |
Feature activation | +9.95e+00 |
Pos logit contributions | |
llah | +4.708 |
senal | +4.519 |
ibur | +4.078 |
dayName | +4.044 |
bedrock | +3.955 |
Neg logit contributions | |
wives | -3.300 |
anova | -3.127 |
herself | -3.126 |
ikawa | -3.105 |
tarians | -2.973 |
Token |
|
Token ID | 198 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
llah | +7.217 |
senal | +6.752 |
ibur | +5.943 |
newcom | +5.861 |
dayName | +5.749 |
Neg logit contributions | |
wives | -7.183 |
ikawa | -6.980 |
anova | -6.949 |
herself | -6.873 |
tarians | -6.763 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
llah | +3.124 |
senal | +2.679 |
ibur | +2.622 |
dayName | +2.603 |
bedrock | +2.471 |
Neg logit contributions | |
wives | -3.692 |
anova | -3.531 |
ikawa | -3.521 |
herself | -3.515 |
tarians | -3.435 |
Token | J |
Token ID | 41 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
llah | +2.038 |
senal | +2.005 |
ibur | +1.743 |
dayName | +1.711 |
newcom | +1.710 |
Neg logit contributions | |
wives | -2.019 |
herself | -1.936 |
anova | -1.911 |
ikawa | -1.900 |
mentation | -1.837 |
Token | uan |
Token ID | 7258 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
wives | +0.128 |
herself | +0.119 |
anova | +0.118 |
ikawa | +0.116 |
mentation | +0.106 |
Neg logit contributions | |
senal | -0.409 |
llah | -0.406 |
newcom | -0.369 |
dayName | -0.368 |
ibur | -0.367 |
Token | Guerrero |
Token ID | 49002 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
wives | +1.854 |
herself | +1.814 |
anova | +1.749 |
ikawa | +1.740 |
mentation | +1.676 |
Neg logit contributions | |
senal | -2.382 |
llah | -2.347 |
newcom | -2.078 |
ibur | -2.063 |
dayName | -2.058 |
Token | with |
Token ID | 351 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
wives | +0.358 |
herself | +0.348 |
anova | +0.338 |
ikawa | +0.333 |
mentation | +0.324 |
Neg logit contributions | |
llah | -0.435 |
senal | -0.432 |
ibur | -0.376 |
newcom | -0.374 |
dayName | -0.374 |
Token | traces |
Token ID | 20675 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
wives | +0.467 |
herself | +0.452 |
anova | +0.441 |
ikawa | +0.434 |
mentation | +0.421 |
Neg logit contributions | |
senal | -0.614 |
llah | -0.612 |
ibur | -0.536 |
dayName | -0.534 |
newcom | -0.533 |
Token | of |
Token ID | 286 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
llah | +3.420 |
senal | +3.295 |
ibur | +2.876 |
bedrock | +2.832 |
dayName | +2.828 |
Neg logit contributions | |
wives | -3.566 |
anova | -3.423 |
ikawa | -3.389 |
herself | -3.335 |
mentation | -3.297 |
Token | the |
Token ID | 262 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
llah | +0.227 |
senal | +0.226 |
ibur | +0.197 |
newcom | +0.195 |
dayName | +0.195 |
Neg logit contributions | |
wives | -0.183 |
herself | -0.176 |
anova | -0.173 |
ikawa | -0.172 |
mentation | -0.165 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
llah | +0.672 |
senal | +0.669 |
ibur | +0.586 |
newcom | +0.581 |
dayName | +0.580 |
Neg logit contributions | |
wives | -0.504 |
herself | -0.484 |
anova | -0.473 |
ikawa | -0.470 |
mentation | -0.451 |
Token | Cyr |
Token ID | 40399 |
Feature activation | +9.92e+00 |
Pos logit contributions | |
llah | +1.799 |
senal | +1.781 |
ibur | +1.563 |
dayName | +1.543 |
newcom | +1.543 |
Neg logit contributions | |
wives | -1.453 |
herself | -1.387 |
anova | -1.367 |
ikawa | -1.360 |
mentation | -1.308 |
Token | ill |
Token ID | 359 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
llah | +6.983 |
senal | +6.300 |
ibur | +5.876 |
bedrock | +5.781 |
dayName | +5.487 |
Neg logit contributions | |
wives | -7.391 |
herself | -7.045 |
ikawa | -6.993 |
tarians | -6.835 |
anova | -6.788 |
Token | ic |
Token ID | 291 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
llah | +1.147 |
senal | +1.140 |
ibur | +0.949 |
dayName | +0.944 |
newcom | +0.941 |
Neg logit contributions | |
wives | -1.473 |
herself | -1.430 |
anova | -1.409 |
ikawa | -1.401 |
mentation | -1.360 |
Token | found |
Token ID | 1043 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
llah | +4.544 |
senal | +4.347 |
ibur | +3.919 |
bedrock | +3.841 |
newcom | +3.803 |
Neg logit contributions | |
wives | -4.174 |
anova | -3.924 |
ikawa | -3.895 |
herself | -3.894 |
tarians | -3.773 |
Token | in |
Token ID | 287 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
wives | +1.027 |
herself | +0.996 |
anova | +0.955 |
ikawa | +0.955 |
mentation | +0.920 |
Neg logit contributions | |
senal | -1.289 |
llah | -1.274 |
ibur | -1.113 |
newcom | -1.112 |
dayName | -1.099 |
Token | their |
Token ID | 511 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
llah | +0.253 |
senal | +0.251 |
ibur | +0.221 |
newcom | +0.218 |
dayName | +0.218 |
Neg logit contributions | |
wives | -0.197 |
herself | -0.189 |
anova | -0.185 |
ikawa | -0.183 |
mentation | -0.177 |
Token | � |
Token ID | 447 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
llah | +1.641 |
senal | +1.604 |
ibur | +1.417 |
newcom | +1.401 |
dayName | +1.392 |
Neg logit contributions | |
wives | -1.137 |
anova | -1.063 |
herself | -1.055 |
ikawa | -1.048 |
mentation | -1.005 |
Token | � |
Token ID | 247 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
senal | +0.408 |
llah | +0.398 |
newcom | +0.339 |
ibur | +0.334 |
dayName | +0.326 |
Neg logit contributions | |
wives | -0.522 |
herself | -0.508 |
anova | -0.501 |
ikawa | -0.494 |
mentation | -0.485 |
Token | s |
Token ID | 82 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
wives | +1.115 |
herself | +1.060 |
anova | +1.039 |
ikawa | +1.028 |
mentation | +0.985 |
Neg logit contributions | |
llah | -1.773 |
senal | -1.772 |
ibur | -1.567 |
newcom | -1.560 |
dayName | -1.546 |
Token | take |
Token ID | 1011 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
wives | +0.690 |
herself | +0.677 |
ikawa | +0.649 |
anova | +0.646 |
mentation | +0.621 |
Neg logit contributions | |
senal | -0.974 |
llah | -0.946 |
newcom | -0.833 |
ibur | -0.826 |
dayName | -0.819 |
Token | a |
Token ID | 257 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
llah | +2.082 |
senal | +2.044 |
ibur | +1.806 |
newcom | +1.771 |
dayName | +1.765 |
Neg logit contributions | |
wives | -1.805 |
herself | -1.712 |
anova | -1.696 |
ikawa | -1.688 |
mentation | -1.633 |
Token | moment |
Token ID | 2589 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
llah | +1.891 |
senal | +1.871 |
ibur | +1.662 |
newcom | +1.640 |
dayName | +1.638 |
Neg logit contributions | |
wives | -1.263 |
herself | -1.198 |
anova | -1.177 |
ikawa | -1.169 |
mentation | -1.120 |
Token | to |
Token ID | 284 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
llah | +6.246 |
senal | +5.839 |
dayName | +5.446 |
ibur | +5.239 |
newcom | +5.206 |
Neg logit contributions | |
wives | -7.764 |
anova | -7.307 |
ikawa | -7.243 |
mentation | -7.140 |
tarians | -7.037 |
Token | discuss |
Token ID | 2112 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
senal | +0.881 |
llah | +0.879 |
ibur | +0.769 |
newcom | +0.764 |
dayName | +0.758 |
Neg logit contributions | |
wives | -0.619 |
herself | -0.598 |
anova | -0.580 |
ikawa | -0.578 |
mentation | -0.552 |
Token | some |
Token ID | 617 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
llah | +0.267 |
senal | +0.264 |
ibur | +0.233 |
dayName | +0.230 |
newcom | +0.229 |
Neg logit contributions | |
wives | -0.201 |
herself | -0.193 |
anova | -0.188 |
ikawa | -0.186 |
mentation | -0.180 |
Token | of |
Token ID | 286 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
llah | +1.072 |
senal | +1.061 |
ibur | +0.927 |
dayName | +0.915 |
newcom | +0.913 |
Neg logit contributions | |
wives | -0.916 |
herself | -0.877 |
anova | -0.860 |
ikawa | -0.855 |
mentation | -0.824 |
Token | the |
Token ID | 262 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
llah | +0.778 |
senal | +0.768 |
ibur | +0.676 |
newcom | +0.667 |
dayName | +0.665 |
Neg logit contributions | |
wives | -0.622 |
herself | -0.592 |
anova | -0.584 |
ikawa | -0.580 |
mentation | -0.558 |
Token | Jim |
Token ID | 5395 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
llah | +2.679 |
senal | +2.625 |
newcom | +2.318 |
ibur | +2.316 |
bedrock | +2.270 |
Neg logit contributions | |
wives | -2.136 |
herself | -2.028 |
anova | -2.023 |
ikawa | -2.010 |
mentation | -1.935 |
Token | H |
Token ID | 367 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
wives | +2.100 |
herself | +2.048 |
ikawa | +1.981 |
anova | +1.976 |
mentation | +1.904 |
Neg logit contributions | |
senal | -2.708 |
llah | -2.708 |
dayName | -2.373 |
ibur | -2.370 |
newcom | -2.361 |
Token | enson |
Token ID | 19069 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
wives | +0.574 |
herself | +0.497 |
ikawa | +0.497 |
anova | +0.484 |
tarians | +0.416 |
Neg logit contributions | |
senal | -2.758 |
llah | -2.650 |
newcom | -2.497 |
dayName | -2.426 |
ibur | -2.402 |
Token | 's |
Token ID | 338 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
wives | +0.630 |
herself | +0.602 |
anova | +0.582 |
ikawa | +0.576 |
mentation | +0.555 |
Neg logit contributions | |
llah | -0.961 |
senal | -0.955 |
ibur | -0.849 |
dayName | -0.843 |
newcom | -0.840 |
Token | post |
Token ID | 1281 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
wives | +0.369 |
herself | +0.353 |
anova | +0.345 |
ikawa | +0.342 |
mentation | +0.330 |
Neg logit contributions | |
llah | -0.458 |
senal | -0.455 |
ibur | -0.399 |
dayName | -0.397 |
newcom | -0.389 |
Token | hum |
Token ID | 17047 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
llah | +2.712 |
senal | +2.697 |
ibur | +2.376 |
newcom | +2.355 |
dayName | +2.322 |
Neg logit contributions | |
wives | -2.060 |
herself | -1.976 |
ikawa | -1.964 |
anova | -1.961 |
tarians | -1.873 |
Token | ous |
Token ID | 516 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
llah | +6.317 |
senal | +5.711 |
ibur | +5.533 |
dayName | +5.230 |
bedrock | +5.081 |
Neg logit contributions | |
wives | -7.869 |
herself | -7.438 |
anova | -7.201 |
ikawa | -7.174 |
tarians | -7.127 |
Token | induction |
Token ID | 28471 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
llah | +2.141 |
senal | +2.114 |
ibur | +1.868 |
newcom | +1.842 |
dayName | +1.838 |
Neg logit contributions | |
wives | -1.621 |
herself | -1.542 |
anova | -1.520 |
ikawa | -1.509 |
mentation | -1.452 |
Token | as |
Token ID | 355 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
llah | +2.783 |
senal | +2.735 |
ibur | +2.452 |
newcom | +2.403 |
dayName | +2.398 |
Neg logit contributions | |
wives | -1.851 |
herself | -1.751 |
anova | -1.745 |
ikawa | -1.735 |
mentation | -1.656 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
llah | +2.639 |
senal | +2.596 |
ibur | +2.287 |
newcom | +2.265 |
dayName | +2.249 |
Neg logit contributions | |
wives | -2.214 |
herself | -2.096 |
anova | -2.085 |
ikawa | -2.073 |
mentation | -1.996 |
Token | Disney |
Token ID | 8519 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
llah | +1.285 |
senal | +1.269 |
ibur | +1.116 |
newcom | +1.100 |
dayName | +1.098 |
Neg logit contributions | |
wives | -1.042 |
herself | -0.993 |
anova | -0.980 |
ikawa | -0.973 |
mentation | -0.937 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
llah | +2.594 |
senal | +2.462 |
ibur | +2.203 |
dayName | +2.147 |
newcom | +2.137 |
Neg logit contributions | |
wives | -2.486 |
anova | -2.362 |
ikawa | -2.338 |
herself | -2.321 |
mentation | -2.304 |
Token |
|
Token ID | 198 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
llah | +0.096 |
senal | +0.095 |
ibur | +0.083 |
newcom | +0.082 |
dayName | +0.082 |
Neg logit contributions | |
wives | -0.081 |
herself | -0.078 |
anova | -0.076 |
ikawa | -0.076 |
mentation | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
senal | +0.561 |
llah | +0.556 |
newcom | +0.479 |
ibur | +0.477 |
dayName | +0.468 |
Neg logit contributions | |
wives | -0.538 |
herself | -0.517 |
anova | -0.508 |
ikawa | -0.505 |
mentation | -0.489 |
Token | We |
Token ID | 1135 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
llah | +0.529 |
senal | +0.526 |
ibur | +0.463 |
newcom | +0.461 |
dayName | +0.457 |
Neg logit contributions | |
wives | -0.376 |
herself | -0.356 |
anova | -0.350 |
ikawa | -0.347 |
mentation | -0.334 |
Token | ird |
Token ID | 1447 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
senal | +1.460 |
llah | +1.459 |
newcom | +1.277 |
ibur | +1.277 |
dayName | +1.267 |
Neg logit contributions | |
wives | -1.013 |
herself | -0.969 |
anova | -0.951 |
ikawa | -0.940 |
mentation | -0.900 |
Token | News |
Token ID | 3000 |
Feature activation | +9.59e+00 |
Pos logit contributions | |
llah | +1.755 |
senal | +1.733 |
ibur | +1.519 |
newcom | +1.495 |
dayName | +1.494 |
Neg logit contributions | |
wives | -1.504 |
herself | -1.436 |
anova | -1.416 |
ikawa | -1.406 |
mentation | -1.357 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
llah | +6.701 |
senal | +6.322 |
newcom | +5.716 |
ibur | +5.565 |
dayName | +5.461 |
Neg logit contributions | |
wives | -7.286 |
anova | -7.238 |
ikawa | -7.171 |
herself | -7.039 |
mentation | -6.866 |
Token | : |
Token ID | 25 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
llah | +2.603 |
senal | +2.581 |
ibur | +2.258 |
newcom | +2.240 |
dayName | +2.234 |
Neg logit contributions | |
wives | -2.204 |
herself | -2.100 |
anova | -2.062 |
ikawa | -2.043 |
mentation | -1.968 |
Token | Man |
Token ID | 1869 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
wives | +0.656 |
herself | +0.616 |
anova | +0.603 |
ikawa | +0.587 |
mentation | +0.566 |
Neg logit contributions | |
senal | -0.973 |
llah | -0.970 |
newcom | -0.862 |
dayName | -0.860 |
ibur | -0.852 |
Token | Sh |
Token ID | 911 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
llah | +0.635 |
senal | +0.628 |
ibur | +0.556 |
dayName | +0.551 |
newcom | +0.550 |
Neg logit contributions | |
wives | -0.424 |
herself | -0.403 |
anova | -0.395 |
ikawa | -0.391 |
mentation | -0.374 |
Token | oves |
Token ID | 5241 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
wives | +0.853 |
herself | +0.797 |
ikawa | +0.789 |
anova | +0.789 |
mentation | +0.755 |
Neg logit contributions | |
senal | -1.274 |
llah | -1.270 |
newcom | -1.126 |
dayName | -1.118 |
ibur | -1.103 |
Token | companies |
Token ID | 2706 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
llah | +2.373 |
senal | +2.344 |
ibur | +2.055 |
newcom | +2.026 |
dayName | +2.024 |
Neg logit contributions | |
wives | -2.000 |
herself | -1.909 |
anova | -1.880 |
ikawa | -1.867 |
mentation | -1.802 |
Token | such |
Token ID | 884 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
llah | +1.862 |
senal | +1.846 |
ibur | +1.611 |
newcom | +1.597 |
dayName | +1.591 |
Neg logit contributions | |
wives | -1.569 |
herself | -1.502 |
anova | -1.475 |
ikawa | -1.465 |
mentation | -1.413 |
Token | as |
Token ID | 355 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
wives | +0.133 |
herself | +0.128 |
anova | +0.124 |
ikawa | +0.123 |
mentation | +0.118 |
Neg logit contributions | |
senal | -0.188 |
llah | -0.186 |
newcom | -0.165 |
ibur | -0.161 |
dayName | -0.161 |
Token | Con |
Token ID | 1482 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
llah | +1.509 |
senal | +1.485 |
ibur | +1.264 |
dayName | +1.257 |
newcom | +1.256 |
Neg logit contributions | |
wives | -1.691 |
herself | -1.628 |
anova | -1.602 |
ikawa | -1.589 |
mentation | -1.544 |
Token | oco |
Token ID | 25634 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
llah | +1.900 |
senal | +1.866 |
newcom | +1.554 |
dayName | +1.552 |
ibur | +1.537 |
Neg logit contributions | |
wives | -2.490 |
herself | -2.403 |
anova | -2.379 |
ikawa | -2.354 |
mentation | -2.280 |
Token | Phill |
Token ID | 41970 |
Feature activation | +9.54e+00 |
Pos logit contributions | |
llah | +5.640 |
senal | +5.396 |
ibur | +4.695 |
dayName | +4.493 |
bedrock | +4.407 |
Neg logit contributions | |
wives | -10.320 |
anova | -9.914 |
ikawa | -9.850 |
herself | -9.743 |
tarians | -9.739 |
Token | ips |
Token ID | 2419 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
llah | +5.431 |
senal | +4.778 |
ibur | +4.756 |
dayName | +4.694 |
bedrock | +4.317 |
Neg logit contributions | |
wives | -8.101 |
herself | -7.847 |
anova | -7.677 |
ikawa | -7.651 |
mentation | -7.596 |
Token | and |
Token ID | 290 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
llah | +2.690 |
senal | +2.657 |
ibur | +2.336 |
newcom | +2.304 |
dayName | +2.300 |
Neg logit contributions | |
wives | -2.169 |
herself | -2.068 |
anova | -2.037 |
ikawa | -2.023 |
mentation | -1.949 |
Token | Marathon |
Token ID | 24828 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
llah | +2.052 |
senal | +2.022 |
ibur | +1.741 |
newcom | +1.712 |
dayName | +1.709 |
Neg logit contributions | |
wives | -2.220 |
herself | -2.131 |
anova | -2.105 |
ikawa | -2.092 |
mentation | -2.027 |
Token | have |
Token ID | 423 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
llah | +1.112 |
senal | +1.105 |
newcom | +0.986 |
dayName | +0.983 |
ibur | +0.973 |
Neg logit contributions | |
wives | -0.648 |
herself | -0.618 |
anova | -0.587 |
ikawa | -0.580 |
mentation | -0.554 |
Token | each |
Token ID | 1123 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
llah | +0.627 |
senal | +0.621 |
ibur | +0.538 |
newcom | +0.536 |
dayName | +0.535 |
Neg logit contributions | |
wives | -0.549 |
herself | -0.527 |
anova | -0.517 |
ikawa | -0.512 |
mentation | -0.495 |
Token | twitter |
Token ID | 17044 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
llah | +1.418 |
senal | +1.403 |
ibur | +1.199 |
newcom | +1.181 |
dayName | +1.175 |
Neg logit contributions | |
wives | -1.609 |
herself | -1.547 |
anova | -1.527 |
ikawa | -1.517 |
mentation | -1.473 |
Token | . |
Token ID | 13 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
wives | +2.642 |
herself | +2.527 |
anova | +2.477 |
ikawa | +2.460 |
mentation | +2.384 |
Neg logit contributions | |
llah | -3.302 |
senal | -3.287 |
ibur | -2.882 |
newcom | -2.836 |
dayName | -2.823 |
Token | com |
Token ID | 785 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
wives | +1.745 |
herself | +1.620 |
anova | +1.593 |
ikawa | +1.580 |
mentation | +1.518 |
Neg logit contributions | |
senal | -3.356 |
llah | -3.066 |
newcom | -2.953 |
ibur | -2.739 |
bedrock | -2.702 |
Token | / |
Token ID | 14 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
wives | +0.260 |
herself | +0.243 |
anova | +0.238 |
ikawa | +0.236 |
mentation | +0.223 |
Neg logit contributions | |
llah | -0.554 |
senal | -0.548 |
ibur | -0.495 |
newcom | -0.489 |
dayName | -0.489 |
Token | my |
Token ID | 1820 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
llah | +2.849 |
senal | +2.790 |
ibur | +2.466 |
dayName | +2.423 |
newcom | +2.403 |
Neg logit contributions | |
wives | -2.434 |
herself | -2.336 |
anova | -2.295 |
ikawa | -2.284 |
mentation | -2.200 |
Token | SA |
Token ID | 4090 |
Feature activation | +9.51e+00 |
Pos logit contributions | |
llah | +2.883 |
senal | +2.828 |
ibur | +2.496 |
dayName | +2.453 |
newcom | +2.443 |
Neg logit contributions | |
wives | -2.398 |
herself | -2.297 |
anova | -2.255 |
ikawa | -2.245 |
mentation | -2.162 |
Token | _ |
Token ID | 62 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
llah | +7.732 |
senal | +7.358 |
ibur | +6.593 |
dayName | +6.450 |
bedrock | +6.260 |
Neg logit contributions | |
wives | -6.300 |
herself | -6.152 |
anova | -6.009 |
ikawa | -5.979 |
mentation | -5.732 |
Token | d |
Token ID | 67 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
llah | +0.795 |
senal | +0.791 |
ibur | +0.687 |
newcom | +0.686 |
dayName | +0.675 |
Neg logit contributions | |
wives | -0.719 |
herself | -0.681 |
anova | -0.675 |
ikawa | -0.666 |
mentation | -0.647 |
Token | owntown |
Token ID | 22748 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
llah | +2.881 |
senal | +2.827 |
ibur | +2.493 |
dayName | +2.447 |
newcom | +2.439 |
Neg logit contributions | |
wives | -2.468 |
herself | -2.353 |
anova | -2.318 |
ikawa | -2.300 |
mentation | -2.222 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
llah | +2.089 |
senal | +2.059 |
ibur | +1.809 |
dayName | +1.786 |
newcom | +1.783 |
Neg logit contributions | |
wives | -1.716 |
herself | -1.639 |
anova | -1.615 |
ikawa | -1.607 |
mentation | -1.547 |
Token | And |
Token ID | 843 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
llah | +0.521 |
senal | +0.520 |
ibur | +0.457 |
newcom | +0.450 |
dayName | +0.448 |
Neg logit contributions | |
wives | -0.412 |
herself | -0.392 |
anova | -0.386 |
ikawa | -0.383 |
mentation | -0.369 |
Token | in |
Token ID | 287 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
llah | +2.059 |
senal | +2.031 |
ibur | +1.785 |
dayName | +1.756 |
newcom | +1.755 |
Neg logit contributions | |
wives | -1.722 |
herself | -1.640 |
anova | -1.620 |
ikawa | -1.608 |
mentation | -1.551 |
Token | Haiti |
Token ID | 25051 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
wives | +0.529 |
herself | +0.512 |
ikawa | +0.494 |
anova | +0.492 |
mentation | +0.471 |
Neg logit contributions | |
senal | -0.707 |
llah | -0.706 |
ibur | -0.616 |
newcom | -0.614 |
dayName | -0.608 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
llah | +1.499 |
senal | +1.481 |
ibur | +1.301 |
newcom | +1.285 |
dayName | +1.280 |
Neg logit contributions | |
wives | -1.214 |
herself | -1.160 |
anova | -1.140 |
ikawa | -1.134 |
mentation | -1.090 |
Token | the |
Token ID | 262 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
llah | +1.025 |
senal | +1.015 |
ibur | +0.886 |
dayName | +0.877 |
newcom | +0.877 |
Neg logit contributions | |
wives | -0.841 |
herself | -0.806 |
anova | -0.789 |
ikawa | -0.782 |
mentation | -0.754 |
Token | Associated |
Token ID | 10575 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
llah | +2.310 |
senal | +2.285 |
ibur | +2.011 |
newcom | +1.984 |
dayName | +1.981 |
Neg logit contributions | |
wives | -1.810 |
herself | -1.726 |
anova | -1.698 |
ikawa | -1.686 |
mentation | -1.622 |
Token | Press |
Token ID | 4332 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
llah | +3.075 |
senal | +2.979 |
ibur | +2.695 |
dayName | +2.667 |
bedrock | +2.602 |
Neg logit contributions | |
wives | -2.090 |
herself | -1.983 |
anova | -1.967 |
ikawa | -1.955 |
mentation | -1.870 |
Token | reported |
Token ID | 2098 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
llah | +5.747 |
senal | +5.363 |
ibur | +4.729 |
bedrock | +4.495 |
newcom | +4.466 |
Neg logit contributions | |
wives | -8.103 |
anova | -7.823 |
ikawa | -7.819 |
herself | -7.714 |
tarians | -7.648 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
llah | +3.403 |
senal | +3.317 |
ibur | +2.930 |
newcom | +2.869 |
dayName | +2.865 |
Neg logit contributions | |
wives | -3.043 |
herself | -2.892 |
anova | -2.881 |
ikawa | -2.863 |
mentation | -2.793 |
Token | Haitian |
Token ID | 48723 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
llah | +1.204 |
senal | +1.195 |
ibur | +1.041 |
newcom | +1.033 |
dayName | +1.024 |
Neg logit contributions | |
wives | -1.042 |
herself | -0.994 |
anova | -0.979 |
ikawa | -0.972 |
mentation | -0.938 |
Token | government |
Token ID | 1230 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
llah | +2.205 |
senal | +2.175 |
ibur | +1.902 |
newcom | +1.871 |
dayName | +1.868 |
Neg logit contributions | |
wives | -1.991 |
herself | -1.902 |
anova | -1.879 |
ikawa | -1.866 |
mentation | -1.803 |
Token | officials |
Token ID | 2828 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
llah | +1.126 |
senal | +1.117 |
ibur | +0.956 |
newcom | +0.949 |
dayName | +0.947 |
Neg logit contributions | |
wives | -1.164 |
herself | -1.120 |
anova | -1.097 |
ikawa | -1.088 |
mentation | -1.056 |
Token | RI |
Token ID | 7112 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
llah | +0.533 |
senal | +0.529 |
ibur | +0.436 |
newcom | +0.434 |
dayName | +0.429 |
Neg logit contributions | |
wives | -0.740 |
herself | -0.717 |
anova | -0.711 |
ikawa | -0.704 |
mentation | -0.683 |
Token | ), |
Token ID | 828 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
wives | +1.628 |
herself | +1.575 |
anova | +1.537 |
ikawa | +1.522 |
mentation | +1.451 |
Neg logit contributions | |
llah | -2.937 |
senal | -2.909 |
newcom | -2.593 |
ibur | -2.589 |
dayName | -2.589 |
Token | significantly |
Token ID | 5566 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
wives | +2.124 |
herself | +2.074 |
anova | +2.015 |
ikawa | +1.977 |
mentation | +1.923 |
Neg logit contributions | |
senal | -2.902 |
llah | -2.876 |
ibur | -2.493 |
newcom | -2.490 |
dayName | -2.487 |
Token | shortened |
Token ID | 34464 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
wives | +2.228 |
herself | +2.190 |
anova | +2.119 |
ikawa | +2.083 |
mentation | +2.039 |
Neg logit contributions | |
senal | -3.145 |
llah | -3.066 |
ibur | -2.691 |
newcom | -2.666 |
dayName | -2.646 |
Token | imm |
Token ID | 2296 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
wives | +0.638 |
herself | +0.611 |
anova | +0.599 |
ikawa | +0.595 |
mentation | +0.576 |
Neg logit contributions | |
llah | -0.822 |
senal | -0.817 |
ibur | -0.716 |
dayName | -0.707 |
newcom | -0.705 |
Token | ob |
Token ID | 672 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
wives | +2.959 |
anova | +2.824 |
ikawa | +2.768 |
herself | +2.760 |
mentation | +2.712 |
Neg logit contributions | |
senal | -6.805 |
llah | -6.574 |
newcom | -6.089 |
dayName | -5.994 |
behavi | -5.704 |
Token | ility |
Token ID | 879 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
mentation | +5.603 |
anova | +5.331 |
wives | +5.286 |
herself | +5.234 |
ikawa | +5.207 |
Neg logit contributions | |
senal | -12.611 |
llah | -11.670 |
newcom | -10.636 |
dayName | -10.351 |
ibur | -10.071 |
Token | time |
Token ID | 640 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
wives | +3.910 |
herself | +3.851 |
ikawa | +3.737 |
anova | +3.617 |
stage | +3.571 |
Neg logit contributions | |
senal | -6.741 |
llah | -6.532 |
ibur | -5.851 |
dayName | -5.816 |
newcom | -5.767 |
Token | in |
Token ID | 287 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
wives | +2.863 |
herself | +2.794 |
anova | +2.716 |
ikawa | +2.700 |
mentation | +2.624 |
Neg logit contributions | |
senal | -4.357 |
llah | -4.336 |
ibur | -3.794 |
dayName | -3.761 |
newcom | -3.748 |
Token | rats |
Token ID | 13623 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
wives | +2.615 |
herself | +2.560 |
anova | +2.458 |
ikawa | +2.442 |
mentation | +2.354 |
Neg logit contributions | |
senal | -3.778 |
llah | -3.690 |
ibur | -3.287 |
dayName | -3.232 |
newcom | -3.184 |
Token | in |
Token ID | 287 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
wives | +3.737 |
herself | +3.636 |
ikawa | +3.513 |
anova | +3.466 |
mentation | +3.385 |
Neg logit contributions | |
senal | -5.075 |
llah | -5.021 |
ibur | -4.378 |
newcom | -4.378 |
dayName | -4.308 |
Token | an |
Token ID | 272 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
wives | +0.397 |
herself | +0.377 |
anova | +0.372 |
ikawa | +0.371 |
mentation | +0.360 |
Neg logit contributions | |
llah | -0.380 |
senal | -0.380 |
newcom | -0.323 |
ibur | -0.320 |
dayName | -0.320 |
Token | ), |
Token ID | 828 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
llah | +0.030 |
senal | +0.030 |
ibur | +0.026 |
newcom | +0.026 |
dayName | +0.026 |
Neg logit contributions | |
wives | -0.020 |
herself | -0.019 |
anova | -0.019 |
ikawa | -0.019 |
mentation | -0.018 |
Token | eternity |
Token ID | 28989 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
llah | +2.395 |
senal | +2.345 |
ibur | +2.075 |
newcom | +2.034 |
dayName | +2.027 |
Neg logit contributions | |
wives | -2.043 |
anova | -1.942 |
herself | -1.942 |
ikawa | -1.927 |
mentation | -1.861 |
Token | ( |
Token ID | 357 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
llah | +2.817 |
senal | +2.741 |
ibur | +2.468 |
dayName | +2.417 |
newcom | +2.399 |
Neg logit contributions | |
wives | -2.101 |
anova | -2.009 |
herself | -1.987 |
ikawa | -1.978 |
mentation | -1.909 |
Token | M |
Token ID | 44 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
llah | +0.428 |
senal | +0.427 |
ibur | +0.371 |
newcom | +0.371 |
dayName | +0.368 |
Neg logit contributions | |
wives | -0.353 |
herself | -0.335 |
anova | -0.331 |
ikawa | -0.329 |
mentation | -0.317 |
Token | ö |
Token ID | 9101 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
wives | +0.071 |
herself | +0.068 |
anova | +0.067 |
ikawa | +0.067 |
mentation | +0.064 |
Neg logit contributions | |
llah | -0.085 |
senal | -0.084 |
ibur | -0.073 |
newcom | -0.073 |
dayName | -0.073 |
Token | ng |
Token ID | 782 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
wives | +6.756 |
ikawa | +6.431 |
herself | +6.382 |
anova | +6.242 |
mentation | +6.213 |
Neg logit contributions | |
senal | -10.402 |
llah | -9.468 |
newcom | -9.167 |
dayName | -8.762 |
bedrock | -8.450 |
Token | ke |
Token ID | 365 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
wives | +3.676 |
herself | +3.547 |
anova | +3.487 |
ikawa | +3.472 |
mentation | +3.361 |
Neg logit contributions | |
senal | -3.953 |
llah | -3.884 |
newcom | -3.417 |
dayName | -3.375 |
ibur | -3.319 |
Token | ), |
Token ID | 828 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
wives | +0.177 |
herself | +0.168 |
anova | +0.164 |
ikawa | +0.163 |
mentation | +0.157 |
Neg logit contributions | |
llah | -0.264 |
senal | -0.262 |
ibur | -0.232 |
newcom | -0.230 |
dayName | -0.230 |
Token | surplus |
Token ID | 18201 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
llah | +1.284 |
senal | +1.268 |
ibur | +1.115 |
newcom | +1.099 |
dayName | +1.097 |
Neg logit contributions | |
wives | -1.047 |
herself | -0.999 |
anova | -0.985 |
ikawa | -0.978 |
mentation | -0.942 |
Token | ( |
Token ID | 357 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
wives | +1.658 |
herself | +1.584 |
ikawa | +1.537 |
anova | +1.528 |
mentation | +1.483 |
Neg logit contributions | |
senal | -2.140 |
llah | -2.132 |
dayName | -1.849 |
ibur | -1.847 |
newcom | -1.843 |
Token | PC |
Token ID | 5662 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
wives | +2.221 |
herself | +2.096 |
anova | +2.089 |
ikawa | +2.054 |
mentation | +1.985 |
Neg logit contributions | |
llah | -2.335 |
senal | -2.315 |
ibur | -1.992 |
newcom | -1.978 |
dayName | -1.963 |
Token | Game |
Token ID | 3776 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
wives | +2.876 |
herself | +2.786 |
anova | +2.694 |
ikawa | +2.661 |
mentation | +2.513 |
Neg logit contributions | |
llah | -4.892 |
senal | -4.769 |
ibur | -4.240 |
newcom | -4.228 |
dayName | -4.155 |
Token | ] |
Token ID | 60 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
wives | +1.202 |
herself | +1.144 |
anova | +1.134 |
ikawa | +1.109 |
mentation | +1.062 |
Neg logit contributions | |
llah | -1.699 |
senal | -1.671 |
ibur | -1.470 |
newcom | -1.463 |
dayName | -1.445 |
Token |
|
Token ID | 198 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
wives | +0.904 |
herself | +0.870 |
anova | +0.850 |
ikawa | +0.844 |
mentation | +0.804 |
Neg logit contributions | |
llah | -1.145 |
senal | -1.126 |
ibur | -0.980 |
dayName | -0.970 |
newcom | -0.969 |
Token |
|
Token ID | 198 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
wives | +0.169 |
herself | +0.161 |
anova | +0.159 |
ikawa | +0.157 |
mentation | +0.152 |
Neg logit contributions | |
senal | -0.190 |
llah | -0.188 |
newcom | -0.165 |
ibur | -0.161 |
dayName | -0.157 |
Token | Platform |
Token ID | 37148 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
wives | +0.331 |
herself | +0.312 |
anova | +0.311 |
ikawa | +0.308 |
mentation | +0.296 |
Neg logit contributions | |
llah | -0.373 |
senal | -0.372 |
newcom | -0.321 |
ibur | -0.320 |
dayName | -0.315 |
Token | : |
Token ID | 25 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
herself | +6.251 |
wives | +6.225 |
mentation | +6.131 |
anova | +6.129 |
ikawa | +6.108 |
Neg logit contributions | |
llah | -10.416 |
senal | -10.186 |
ibur | -8.918 |
newcom | -8.791 |
dayName | -8.554 |
Token | IBM |
Token ID | 19764 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
wives | +1.617 |
herself | +1.523 |
anova | +1.478 |
ikawa | +1.469 |
mentation | +1.407 |
Neg logit contributions | |
senal | -2.994 |
llah | -2.986 |
newcom | -2.622 |
ibur | -2.622 |
dayName | -2.587 |
Token | PC |
Token ID | 4217 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
wives | +0.340 |
herself | +0.325 |
anova | +0.318 |
ikawa | +0.318 |
mentation | +0.303 |
Neg logit contributions | |
llah | -0.522 |
senal | -0.520 |
ibur | -0.456 |
dayName | -0.456 |
newcom | -0.455 |
Token | Comp |
Token ID | 3082 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
wives | +0.424 |
herself | +0.405 |
anova | +0.399 |
ikawa | +0.396 |
mentation | +0.381 |
Neg logit contributions | |
llah | -0.528 |
senal | -0.521 |
ibur | -0.458 |
dayName | -0.452 |
newcom | -0.451 |
Token | atible |
Token ID | 16873 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
wives | +0.214 |
herself | +0.188 |
anova | +0.184 |
ikawa | +0.176 |
mentation | +0.158 |
Neg logit contributions | |
llah | -1.102 |
senal | -1.100 |
ibur | -1.008 |
newcom | -1.003 |
dayName | -1.000 |
Token | primarily |
Token ID | 7525 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
senal | +0.764 |
llah | +0.760 |
ibur | +0.668 |
newcom | +0.660 |
dayName | +0.656 |
Neg logit contributions | |
wives | -0.621 |
herself | -0.603 |
anova | -0.579 |
ikawa | -0.579 |
mentation | -0.558 |
Token | between |
Token ID | 1022 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
wives | +1.691 |
herself | +1.652 |
ikawa | +1.553 |
anova | +1.530 |
mentation | +1.494 |
Neg logit contributions | |
senal | -2.290 |
llah | -2.231 |
newcom | -1.985 |
ibur | -1.961 |
dayName | -1.945 |
Token | whites |
Token ID | 13216 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
llah | +1.259 |
senal | +1.247 |
ibur | +1.087 |
newcom | +1.072 |
dayName | +1.072 |
Neg logit contributions | |
wives | -1.111 |
herself | -1.064 |
anova | -1.044 |
ikawa | -1.039 |
mentation | -1.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
llah | +0.238 |
senal | +0.237 |
ibur | +0.209 |
newcom | +0.206 |
dayName | +0.206 |
Neg logit contributions | |
wives | -0.173 |
herself | -0.165 |
anova | -0.161 |
ikawa | -0.161 |
mentation | -0.154 |
Token | m |
Token ID | 285 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
llah | +1.012 |
senal | +1.007 |
ibur | +0.876 |
dayName | +0.871 |
newcom | +0.867 |
Neg logit contributions | |
wives | -0.862 |
herself | -0.829 |
anova | -0.806 |
ikawa | -0.803 |
mentation | -0.779 |
Token | est |
Token ID | 395 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
wives | +0.251 |
herself | +0.238 |
anova | +0.234 |
ikawa | +0.233 |
mentation | +0.225 |
Neg logit contributions | |
senal | -0.310 |
llah | -0.308 |
newcom | -0.269 |
dayName | -0.268 |
ibur | -0.266 |
Token | iz |
Token ID | 528 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
wives | +3.983 |
ikawa | +3.291 |
herself | +3.218 |
mentation | +3.198 |
anova | +3.113 |
Neg logit contributions | |
senal | -13.460 |
llah | -13.034 |
dayName | -12.122 |
newcom | -12.112 |
ibur | -11.934 |
Token | os |
Token ID | 418 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
wives | +3.401 |
herself | +3.194 |
anova | +3.170 |
ikawa | +3.113 |
tarians | +3.003 |
Neg logit contributions | |
senal | -5.102 |
llah | -5.003 |
newcom | -4.523 |
ibur | -4.501 |
dayName | -4.462 |
Token | and |
Token ID | 290 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
wives | +1.104 |
herself | +1.049 |
anova | +1.022 |
ikawa | +1.020 |
mentation | +0.980 |
Neg logit contributions | |
senal | -1.520 |
llah | -1.514 |
ibur | -1.330 |
newcom | -1.321 |
dayName | -1.315 |
Token | Af |
Token ID | 2483 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
wives | +1.733 |
herself | +1.679 |
ikawa | +1.597 |
anova | +1.588 |
mentation | +1.573 |
Neg logit contributions | |
senal | -2.058 |
llah | -2.017 |
dayName | -1.764 |
ibur | -1.739 |
newcom | -1.738 |
Token | ro |
Token ID | 305 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
wives | +0.342 |
herself | +0.328 |
anova | +0.324 |
ikawa | +0.322 |
mentation | +0.312 |
Neg logit contributions | |
llah | -0.319 |
senal | -0.314 |
ibur | -0.272 |
dayName | -0.267 |
newcom | -0.266 |
Token | , |
Token ID | 11 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
senal | +0.142 |
llah | +0.139 |
newcom | +0.124 |
ibur | +0.121 |
dayName | +0.119 |
Neg logit contributions | |
wives | -0.104 |
herself | -0.099 |
anova | -0.097 |
ikawa | -0.096 |
mentation | -0.092 |
Token | I |
Token ID | 314 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
wives | +0.519 |
herself | +0.496 |
anova | +0.491 |
ikawa | +0.488 |
mentation | +0.471 |
Neg logit contributions | |
llah | -0.532 |
senal | -0.520 |
ibur | -0.456 |
newcom | -0.447 |
dayName | -0.447 |
Token | think |
Token ID | 892 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
senal | +0.040 |
llah | +0.039 |
newcom | +0.035 |
ibur | +0.034 |
dayName | +0.033 |
Neg logit contributions | |
wives | -0.032 |
herself | -0.031 |
anova | -0.030 |
ikawa | -0.030 |
mentation | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
llah | +1.252 |
senal | +1.231 |
ibur | +1.069 |
newcom | +1.052 |
dayName | +1.048 |
Neg logit contributions | |
wives | -1.251 |
herself | -1.195 |
anova | -1.181 |
ikawa | -1.175 |
mentation | -1.136 |
Token |
|
Token ID | 198 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
llah | +0.695 |
senal | +0.694 |
ibur | +0.595 |
newcom | +0.593 |
dayName | +0.584 |
Neg logit contributions | |
wives | -0.680 |
herself | -0.653 |
anova | -0.643 |
ikawa | -0.638 |
mentation | -0.618 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
llah | +0.078 |
senal | +0.077 |
ibur | +0.071 |
newcom | +0.070 |
dayName | +0.070 |
Neg logit contributions | |
wives | -0.023 |
herself | -0.021 |
anova | -0.020 |
ikawa | -0.020 |
mentation | -0.019 |
Token | : |
Token ID | 25 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
herself | +5.474 |
wives | +5.323 |
ikawa | +4.697 |
anova | +4.653 |
weed | +4.598 |
Neg logit contributions | |
senal | -13.971 |
newcom | -12.492 |
ortunately | -11.893 |
tremend | -11.892 |
pione | -11.532 |
Token | B |
Token ID | 347 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
wives | +5.815 |
herself | +5.799 |
anova | +5.501 |
ikawa | +5.431 |
stage | +5.285 |
Neg logit contributions | |
senal | -6.789 |
llah | -6.750 |
ibur | -5.827 |
dayName | -5.820 |
newcom | -5.614 |
Token | iz |
Token ID | 528 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
wives | +4.546 |
ikawa | +4.408 |
herself | +4.378 |
anova | +4.364 |
weed | +4.139 |
Neg logit contributions | |
senal | -4.868 |
llah | -4.806 |
dayName | -4.156 |
newcom | -4.148 |
ibur | -4.082 |
Token | r |
Token ID | 81 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
wives | +2.515 |
anova | +2.413 |
herself | +2.402 |
ikawa | +2.367 |
mentation | +2.236 |
Neg logit contributions | |
llah | -2.735 |
senal | -2.724 |
ibur | -2.364 |
newcom | -2.359 |
dayName | -2.358 |
Token | Pix |
Token ID | 21642 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
wives | +2.802 |
herself | +2.681 |
anova | +2.649 |
ikawa | +2.640 |
mentation | +2.528 |
Neg logit contributions | |
llah | -3.024 |
senal | -2.982 |
dayName | -2.651 |
newcom | -2.610 |
ibur | -2.607 |
Token | iff |
Token ID | 733 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
wives | +0.481 |
herself | +0.445 |
ikawa | +0.434 |
anova | +0.433 |
mentation | +0.406 |
Neg logit contributions | |
senal | -1.281 |
llah | -1.263 |
newcom | -1.150 |
ibur | -1.132 |
dayName | -1.127 |
Token | Tra |
Token ID | 15721 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
wives | +4.672 |
herself | +4.454 |
anova | +4.310 |
ikawa | +4.296 |
weed | +4.267 |
Neg logit contributions | |
senal | -5.330 |
llah | -4.797 |
newcom | -4.694 |
ortunately | -4.201 |
tremend | -4.190 |
Token | x |
Token ID | 87 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
wives | +0.216 |
herself | +0.205 |
anova | +0.203 |
ikawa | +0.201 |
mentation | +0.194 |
Neg logit contributions | |
senal | -0.247 |
llah | -0.243 |
newcom | -0.215 |
ibur | -0.208 |
dayName | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
wives | +0.900 |
herself | +0.865 |
anova | +0.850 |
ikawa | +0.844 |
mentation | +0.817 |
Neg logit contributions | |
llah | -0.967 |
senal | -0.955 |
ibur | -0.829 |
newcom | -0.822 |
dayName | -0.817 |
Token |
|
Token ID | 198 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
senal | +0.080 |
llah | +0.078 |
newcom | +0.068 |
ibur | +0.067 |
dayName | +0.066 |
Neg logit contributions | |
wives | -0.074 |
herself | -0.071 |
anova | -0.070 |
ikawa | -0.069 |
mentation | -0.067 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
wives | +0.102 |
herself | +0.092 |
anova | +0.090 |
ikawa | +0.088 |
mentation | +0.082 |
Neg logit contributions | |
llah | -0.354 |
senal | -0.353 |
ibur | -0.321 |
newcom | -0.320 |
dayName | -0.318 |
Token | : |
Token ID | 25 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
herself | +5.478 |
wives | +5.331 |
ikawa | +4.709 |
anova | +4.655 |
weed | +4.624 |
Neg logit contributions | |
senal | -13.934 |
newcom | -12.416 |
ortunately | -11.855 |
tremend | -11.805 |
pione | -11.483 |
Token | V |
Token ID | 569 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
wives | +5.801 |
herself | +5.766 |
anova | +5.472 |
ikawa | +5.402 |
stage | +5.254 |
Neg logit contributions | |
senal | -6.727 |
llah | -6.692 |
ibur | -5.772 |
dayName | -5.761 |
newcom | -5.551 |
Token | the |
Token ID | 1169 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
wives | +2.330 |
anova | +2.238 |
ikawa | +2.217 |
herself | +2.206 |
mentation | +2.102 |
Neg logit contributions | |
senal | -2.623 |
llah | -2.616 |
dayName | -2.270 |
newcom | -2.257 |
ibur | -2.207 |
Token | Happy |
Token ID | 25082 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
wives | +3.313 |
anova | +3.116 |
ikawa | +3.092 |
herself | +3.086 |
mentation | +2.970 |
Neg logit contributions | |
llah | -3.540 |
senal | -3.539 |
newcom | -3.083 |
dayName | -3.061 |
ibur | -3.027 |
Token | L |
Token ID | 43 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
wives | +1.086 |
herself | +1.029 |
anova | +1.016 |
ikawa | +1.004 |
mentation | +0.970 |
Neg logit contributions | |
llah | -1.226 |
senal | -1.216 |
ibur | -1.057 |
dayName | -1.052 |
newcom | -1.049 |
Token | er |
Token ID | 263 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
llah | +2.587 |
senal | +2.471 |
ibur | +2.288 |
dayName | +2.234 |
newcom | +2.172 |
Neg logit contributions | |
wives | -1.745 |
herself | -1.640 |
anova | -1.605 |
ikawa | -1.601 |
mentation | -1.527 |
Token | magnet |
Token ID | 19972 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
senal | +0.631 |
llah | +0.630 |
ibur | +0.546 |
newcom | +0.542 |
dayName | +0.539 |
Neg logit contributions | |
wives | -0.542 |
herself | -0.523 |
anova | -0.510 |
ikawa | -0.507 |
mentation | -0.491 |
Token | ? |
Token ID | 30 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
llah | +2.941 |
senal | +2.849 |
ibur | +2.539 |
dayName | +2.494 |
newcom | +2.447 |
Neg logit contributions | |
wives | -2.626 |
anova | -2.485 |
ikawa | -2.482 |
herself | -2.463 |
mentation | -2.348 |
Token |
|
Token ID | 198 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
llah | +1.699 |
senal | +1.626 |
ibur | +1.426 |
newcom | +1.397 |
dayName | +1.394 |
Neg logit contributions | |
wives | -1.774 |
herself | -1.697 |
anova | -1.677 |
ikawa | -1.661 |
tarians | -1.608 |
Token |
|
Token ID | 198 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
senal | +0.429 |
llah | +0.426 |
newcom | +0.367 |
ibur | +0.365 |
dayName | +0.359 |
Neg logit contributions | |
wives | -0.412 |
herself | -0.396 |
anova | -0.389 |
ikawa | -0.386 |
mentation | -0.374 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
wives | +0.228 |
herself | +0.203 |
anova | +0.199 |
ikawa | +0.195 |
mentation | +0.181 |
Neg logit contributions | |
llah | -0.806 |
senal | -0.805 |
ibur | -0.730 |
newcom | -0.729 |
dayName | -0.725 |
Token | : |
Token ID | 25 |
Feature activation | -8.14e+00 |
Pos logit contributions | |
herself | +5.446 |
wives | +5.294 |
ikawa | +4.688 |
anova | +4.650 |
weed | +4.570 |
Neg logit contributions | |
senal | -13.849 |
newcom | -12.357 |
ortunately | -11.786 |
tremend | -11.769 |
pione | -11.449 |
Token | hey |
Token ID | 17207 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
wives | +5.430 |
herself | +5.400 |
anova | +5.130 |
ikawa | +5.064 |
mentation | +4.902 |
Neg logit contributions | |
senal | -6.362 |
llah | -6.303 |
dayName | -5.460 |
ibur | -5.459 |
newcom | -5.268 |
Token | _ |
Token ID | 62 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
wives | +1.460 |
herself | +1.376 |
anova | +1.368 |
ikawa | +1.355 |
mentation | +1.300 |
Neg logit contributions | |
llah | -1.841 |
senal | -1.835 |
dayName | -1.606 |
ibur | -1.593 |
newcom | -1.591 |
Token | ler |
Token ID | 1754 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
wives | +1.862 |
anova | +1.743 |
herself | +1.741 |
ikawa | +1.716 |
mentation | +1.652 |
Neg logit contributions | |
senal | -2.369 |
llah | -2.351 |
newcom | -2.069 |
dayName | -2.050 |
ibur | -2.049 |
Token | oy |
Token ID | 726 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
llah | +1.978 |
senal | +1.949 |
ibur | +1.719 |
newcom | +1.687 |
dayName | +1.684 |
Neg logit contributions | |
wives | -1.634 |
herself | -1.559 |
anova | -1.536 |
ikawa | -1.523 |
mentation | -1.471 |
Token | musical |
Token ID | 10530 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
wives | +4.854 |
herself | +4.701 |
anova | +4.600 |
ikawa | +4.452 |
mentation | +4.344 |
Neg logit contributions | |
senal | -6.862 |
llah | -6.825 |
dayName | -6.007 |
ibur | -5.980 |
newcom | -5.782 |
Token | interpretations |
Token ID | 26146 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
llah | +0.170 |
senal | +0.169 |
ibur | +0.150 |
dayName | +0.148 |
newcom | +0.148 |
Neg logit contributions | |
wives | -0.108 |
herself | -0.103 |
anova | -0.100 |
ikawa | -0.099 |
mentation | -0.096 |
Token | of |
Token ID | 286 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
wives | +1.172 |
herself | +1.127 |
anova | +1.089 |
ikawa | +1.088 |
mentation | +1.039 |
Neg logit contributions | |
llah | -1.625 |
senal | -1.610 |
ibur | -1.419 |
newcom | -1.403 |
dayName | -1.403 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
wives | +1.641 |
herself | +1.585 |
anova | +1.535 |
ikawa | +1.519 |
mentation | +1.458 |
Neg logit contributions | |
llah | -2.150 |
senal | -2.139 |
ibur | -1.886 |
dayName | -1.855 |
newcom | -1.847 |
Token | M |
Token ID | 337 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
wives | +0.607 |
herself | +0.578 |
anova | +0.563 |
ikawa | +0.557 |
mentation | +0.531 |
Neg logit contributions | |
llah | -0.946 |
senal | -0.943 |
ibur | -0.836 |
dayName | -0.826 |
newcom | -0.823 |
Token | oom |
Token ID | 4207 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
wives | +1.195 |
herself | +1.111 |
ikawa | +1.104 |
anova | +1.102 |
mentation | +1.018 |
Neg logit contributions | |
senal | -2.262 |
llah | -2.252 |
dayName | -2.003 |
newcom | -1.999 |
ibur | -1.992 |
Token | ins |
Token ID | 1040 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
wives | +7.843 |
anova | +7.593 |
herself | +7.501 |
ikawa | +7.364 |
mentation | +6.911 |
Neg logit contributions | |
senal | -8.627 |
llah | -8.271 |
dayName | -7.396 |
newcom | -7.383 |
ibur | -7.218 |
Token | have |
Token ID | 423 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
wives | +0.196 |
herself | +0.187 |
anova | +0.184 |
ikawa | +0.182 |
mentation | +0.174 |
Neg logit contributions | |
llah | -0.267 |
senal | -0.265 |
ibur | -0.234 |
dayName | -0.231 |
newcom | -0.231 |
Token | been |
Token ID | 587 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
wives | +1.411 |
herself | +1.366 |
anova | +1.320 |
ikawa | +1.317 |
mentation | +1.266 |
Neg logit contributions | |
llah | -1.725 |
senal | -1.722 |
ibur | -1.500 |
newcom | -1.485 |
dayName | -1.481 |
Token | made |
Token ID | 925 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
wives | +1.294 |
herself | +1.250 |
ikawa | +1.204 |
anova | +1.202 |
mentation | +1.160 |
Neg logit contributions | |
llah | -1.541 |
senal | -1.526 |
ibur | -1.344 |
dayName | -1.322 |
newcom | -1.318 |
Token | for |
Token ID | 329 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
wives | +1.332 |
herself | +1.288 |
anova | +1.240 |
ikawa | +1.226 |
mentation | +1.175 |
Neg logit contributions | |
llah | -1.877 |
senal | -1.873 |
ibur | -1.647 |
dayName | -1.631 |
newcom | -1.631 |
Token | false |
Token ID | 3991 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
wives | +1.445 |
herself | +1.439 |
anova | +1.360 |
ikawa | +1.350 |
mentation | +1.301 |
Neg logit contributions | |
senal | -1.640 |
llah | -1.634 |
newcom | -1.416 |
ibur | -1.413 |
dayName | -1.404 |
Token | . |
Token ID | 13 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
llah | +0.074 |
senal | +0.074 |
ibur | +0.064 |
newcom | +0.064 |
dayName | +0.063 |
Neg logit contributions | |
wives | -0.060 |
herself | -0.058 |
anova | -0.056 |
ikawa | -0.056 |
mentation | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
llah | +0.751 |
senal | +0.740 |
ibur | +0.643 |
newcom | +0.632 |
dayName | +0.632 |
Neg logit contributions | |
wives | -0.733 |
herself | -0.702 |
anova | -0.693 |
ikawa | -0.689 |
mentation | -0.666 |
Token |
|
Token ID | 198 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
wives | +0.680 |
herself | +0.656 |
anova | +0.637 |
ikawa | +0.631 |
mentation | +0.612 |
Neg logit contributions | |
senal | -0.828 |
llah | -0.774 |
newcom | -0.713 |
ibur | -0.670 |
dayName | -0.653 |
Token | M |
Token ID | 44 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
wives | +0.557 |
herself | +0.531 |
anova | +0.523 |
ikawa | +0.518 |
mentation | +0.503 |
Neg logit contributions | |
senal | -0.525 |
llah | -0.517 |
newcom | -0.452 |
ibur | -0.439 |
dayName | -0.432 |
Token | int |
Token ID | 600 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
wives | +0.764 |
herself | +0.733 |
anova | +0.730 |
ikawa | +0.719 |
tarians | +0.683 |
Neg logit contributions | |
senal | -1.335 |
llah | -1.322 |
newcom | -1.174 |
ibur | -1.168 |
dayName | -1.154 |
Token | z |
Token ID | 89 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
wives | +6.070 |
herself | +5.905 |
anova | +5.886 |
ikawa | +5.762 |
mentation | +5.598 |
Neg logit contributions | |
senal | -12.193 |
newcom | -10.826 |
tremend | -9.930 |
ortunately | -9.890 |
behavi | -9.803 |
Token | has |
Token ID | 468 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
herself | +2.798 |
wives | +2.744 |
ikawa | +2.581 |
anova | +2.576 |
mentation | +2.496 |
Neg logit contributions | |
senal | -3.145 |
llah | -2.989 |
newcom | -2.710 |
dayName | -2.609 |
ibur | -2.585 |
Token | denied |
Token ID | 6699 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
wives | +2.074 |
herself | +2.068 |
anova | +1.973 |
ikawa | +1.933 |
mentation | +1.867 |
Neg logit contributions | |
senal | -2.317 |
llah | -2.278 |
newcom | -1.990 |
dayName | -1.973 |
ibur | -1.959 |
Token | he |
Token ID | 339 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
llah | +0.222 |
senal | +0.219 |
ibur | +0.193 |
newcom | +0.192 |
dayName | +0.192 |
Neg logit contributions | |
wives | -0.181 |
herself | -0.175 |
anova | -0.169 |
ikawa | -0.167 |
mentation | -0.161 |
Token | coerced |
Token ID | 48474 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
senal | +0.101 |
llah | +0.100 |
newcom | +0.088 |
ibur | +0.087 |
dayName | +0.086 |
Neg logit contributions | |
wives | -0.089 |
herself | -0.086 |
anova | -0.083 |
ikawa | -0.083 |
mentation | -0.079 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
wives | +0.291 |
herself | +0.282 |
ikawa | +0.272 |
anova | +0.271 |
mentation | +0.263 |
Neg logit contributions | |
senal | -0.312 |
llah | -0.306 |
newcom | -0.265 |
ibur | -0.264 |
dayName | -0.259 |
Token | boys |
Token ID | 13202 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
llah | +2.296 |
senal | +2.205 |
ibur | +2.016 |
dayName | +1.969 |
newcom | +1.924 |
Neg logit contributions | |
wives | -1.555 |
herself | -1.519 |
anova | -1.482 |
ikawa | -1.476 |
mentation | -1.413 |
Token | beware |
Token ID | 40600 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
wives | +0.993 |
herself | +0.954 |
anova | +0.918 |
ikawa | +0.896 |
mentation | +0.869 |
Neg logit contributions | |
senal | -1.686 |
llah | -1.646 |
newcom | -1.477 |
ibur | -1.458 |
dayName | -1.437 |
Token |
|
Token ID | 198 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
llah | +0.496 |
senal | +0.488 |
ibur | +0.423 |
newcom | +0.417 |
dayName | +0.416 |
Neg logit contributions | |
wives | -0.487 |
herself | -0.467 |
anova | -0.460 |
ikawa | -0.458 |
mentation | -0.442 |
Token |
|
Token ID | 198 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
senal | +0.501 |
llah | +0.497 |
newcom | +0.428 |
ibur | +0.426 |
dayName | +0.418 |
Neg logit contributions | |
wives | -0.481 |
herself | -0.461 |
anova | -0.454 |
ikawa | -0.451 |
mentation | -0.437 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
wives | +0.152 |
herself | +0.138 |
anova | +0.134 |
ikawa | +0.132 |
mentation | +0.122 |
Neg logit contributions | |
llah | -0.516 |
senal | -0.513 |
ibur | -0.467 |
newcom | -0.464 |
dayName | -0.463 |
Token | : |
Token ID | 25 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
herself | +5.364 |
wives | +5.240 |
ikawa | +4.666 |
anova | +4.590 |
weed | +4.550 |
Neg logit contributions | |
senal | -13.311 |
newcom | -11.858 |
ortunately | -11.299 |
tremend | -11.262 |
pione | -10.929 |
Token | j |
Token ID | 474 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
wives | +5.548 |
herself | +5.481 |
anova | +5.234 |
ikawa | +5.164 |
mentation | +5.006 |
Neg logit contributions | |
senal | -6.388 |
llah | -6.356 |
ibur | -5.493 |
dayName | -5.477 |
newcom | -5.283 |
Token | wt |
Token ID | 46569 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
wives | +3.854 |
anova | +3.675 |
ikawa | +3.657 |
herself | +3.638 |
weed | +3.456 |
Neg logit contributions | |
senal | -4.545 |
llah | -4.395 |
newcom | -3.928 |
dayName | -3.881 |
bedrock | -3.749 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
wives | +4.430 |
herself | +4.225 |
ikawa | +4.184 |
anova | +4.162 |
weed | +4.027 |
Neg logit contributions | |
senal | -4.763 |
llah | -4.742 |
dayName | -4.150 |
newcom | -4.034 |
ibur | -3.982 |
Token | - |
Token ID | 532 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
wives | +1.280 |
herself | +1.222 |
anova | +1.204 |
ikawa | +1.195 |
mentation | +1.152 |
Neg logit contributions | |
llah | -1.564 |
senal | -1.547 |
ibur | -1.359 |
dayName | -1.340 |
newcom | -1.338 |
Token | oxy |
Token ID | 23536 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
wives | +1.483 |
anova | +1.377 |
herself | +1.377 |
ikawa | +1.343 |
mentation | +1.277 |
Neg logit contributions | |
senal | -3.747 |
llah | -3.687 |
newcom | -3.335 |
ibur | -3.281 |
dayName | -3.271 |
Token | - |
Token ID | 12 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
wives | +3.717 |
herself | +3.595 |
anova | +3.461 |
ikawa | +3.433 |
mentation | +3.313 |
Neg logit contributions | |
senal | -6.263 |
llah | -6.118 |
newcom | -5.501 |
dayName | -5.386 |
ibur | -5.306 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
wives | +0.185 |
herself | +0.178 |
anova | +0.175 |
ikawa | +0.174 |
mentation | +0.170 |
Neg logit contributions | |
llah | -0.157 |
senal | -0.156 |
ibur | -0.132 |
newcom | -0.131 |
dayName | -0.130 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
wives | +0.856 |
herself | +0.826 |
anova | +0.800 |
ikawa | +0.789 |
mentation | +0.763 |
Neg logit contributions | |
llah | -1.357 |
senal | -1.356 |
ibur | -1.190 |
newcom | -1.188 |
dayName | -1.180 |
Token | m |
Token ID | 76 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
wives | +0.656 |
herself | +0.625 |
anova | +0.608 |
ikawa | +0.605 |
mentation | +0.578 |
Neg logit contributions | |
llah | -1.100 |
senal | -1.100 |
newcom | -0.970 |
ibur | -0.967 |
dayName | -0.963 |
Token | eth |
Token ID | 2788 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
wives | +1.204 |
herself | +1.146 |
ikawa | +1.116 |
anova | +1.099 |
mentation | +1.056 |
Neg logit contributions | |
senal | -2.115 |
llah | -2.098 |
newcom | -1.866 |
dayName | -1.832 |
ibur | -1.827 |
Token | ox |
Token ID | 1140 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
wives | +5.431 |
herself | +5.183 |
anova | +5.103 |
ikawa | +5.057 |
ylum | +4.809 |
Neg logit contributions | |
senal | -10.922 |
llah | -10.218 |
newcom | -9.678 |
bedrock | -9.035 |
behavi | -8.970 |
Token | ym |
Token ID | 4948 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
wives | +3.097 |
anova | +2.942 |
herself | +2.869 |
ikawa | +2.824 |
ylum | +2.673 |
Neg logit contributions | |
senal | -7.773 |
llah | -7.399 |
newcom | -6.830 |
dayName | -6.665 |
bedrock | -6.505 |
Token | ethyl |
Token ID | 21610 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
wives | +1.567 |
herself | +1.485 |
ikawa | +1.453 |
anova | +1.448 |
mentation | +1.372 |
Neg logit contributions | |
senal | -2.629 |
llah | -2.576 |
newcom | -2.326 |
dayName | -2.268 |
ibur | -2.265 |
Token | phen |
Token ID | 31024 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
wives | +3.260 |
herself | +3.143 |
anova | +3.043 |
ikawa | +2.980 |
mentation | +2.854 |
Neg logit contributions | |
senal | -5.626 |
llah | -5.553 |
newcom | -4.934 |
dayName | -4.845 |
ibur | -4.831 |
Token | yl |
Token ID | 2645 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
wives | +3.065 |
herself | +2.954 |
anova | +2.880 |
ikawa | +2.818 |
ylum | +2.663 |
Neg logit contributions | |
senal | -6.072 |
llah | -5.839 |
newcom | -5.382 |
dayName | -5.161 |
ibur | -5.139 |
Token | quite |
Token ID | 2407 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
wives | +2.241 |
herself | +2.237 |
anova | +2.129 |
mentation | +2.063 |
ikawa | +2.048 |
Neg logit contributions | |
senal | -3.006 |
llah | -2.960 |
newcom | -2.572 |
ibur | -2.572 |
dayName | -2.501 |
Token | even |
Token ID | 772 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
wives | +2.239 |
ikawa | +2.105 |
anova | +2.097 |
herself | +2.087 |
mentation | +2.005 |
Neg logit contributions | |
llah | -2.645 |
senal | -2.595 |
ibur | -2.313 |
newcom | -2.270 |
bedrock | -2.253 |
Token | handed |
Token ID | 10158 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
wives | +2.364 |
anova | +2.253 |
herself | +2.207 |
ikawa | +2.197 |
mentation | +2.087 |
Neg logit contributions | |
llah | -4.021 |
senal | -3.948 |
ibur | -3.580 |
dayName | -3.518 |
bedrock | -3.518 |
Token | ' |
Token ID | 6 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
wives | +1.370 |
herself | +1.322 |
anova | +1.224 |
ikawa | +1.222 |
mentation | +1.165 |
Neg logit contributions | |
senal | -3.011 |
llah | -2.949 |
newcom | -2.661 |
ibur | -2.622 |
dayName | -2.600 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
wives | +1.694 |
herself | +1.623 |
anova | +1.596 |
ikawa | +1.582 |
mentation | +1.529 |
Neg logit contributions | |
llah | -1.920 |
senal | -1.895 |
ibur | -1.658 |
newcom | -1.635 |
dayName | -1.626 |
Token | primary |
Token ID | 4165 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
wives | +1.625 |
herself | +1.546 |
anova | +1.522 |
ikawa | +1.511 |
mentation | +1.454 |
Neg logit contributions | |
llah | -2.167 |
senal | -2.141 |
ibur | -1.892 |
newcom | -1.865 |
dayName | -1.863 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -8.43e+00 |
Pos logit contributions | |
wives | +6.266 |
stage | +6.041 |
herself | +5.918 |
tarians | +5.862 |
anova | +5.796 |
Neg logit contributions | |
senal | -9.995 |
llah | -9.411 |
newcom | -8.757 |
ibur | -8.649 |
dayName | -8.598 |
Token | : |
Token ID | 25 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
herself | +4.692 |
anova | +4.145 |
wives | +4.083 |
stage | +4.031 |
tarians | +3.949 |
Neg logit contributions | |
senal | -8.148 |
llah | -8.074 |
newcom | -7.461 |
dayName | -7.303 |
ibur | -7.212 |
Token | ' |
Token ID | 705 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
wives | +1.382 |
herself | +1.296 |
anova | +1.281 |
ikawa | +1.273 |
mentation | +1.215 |
Neg logit contributions | |
llah | -2.232 |
senal | -2.201 |
ibur | -1.975 |
dayName | -1.948 |
newcom | -1.940 |
Token | Damn |
Token ID | 43343 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
wives | +4.629 |
anova | +4.461 |
herself | +4.458 |
ikawa | +4.295 |
mentation | +4.213 |
Neg logit contributions | |
senal | -6.112 |
llah | -6.071 |
ibur | -5.323 |
newcom | -5.229 |
dayName | -5.096 |
Token | right |
Token ID | 826 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
wives | +3.143 |
herself | +3.091 |
ikawa | +2.906 |
anova | +2.901 |
mentation | +2.827 |
Neg logit contributions | |
llah | -4.452 |
senal | -4.437 |
dayName | -3.872 |
newcom | -3.831 |
ibur | -3.819 |
Token | year |
Token ID | 1941 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
llah | +1.580 |
senal | +1.558 |
ibur | +1.381 |
dayName | +1.361 |
newcom | +1.358 |
Neg logit contributions | |
wives | -1.174 |
herself | -1.117 |
anova | -1.102 |
ikawa | -1.094 |
mentation | -1.051 |
Token | - |
Token ID | 12 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
wives | +0.868 |
herself | +0.820 |
anova | +0.815 |
ikawa | +0.806 |
mentation | +0.774 |
Neg logit contributions | |
llah | -1.195 |
senal | -1.185 |
ibur | -1.049 |
newcom | -1.041 |
dayName | -1.030 |
Token | old |
Token ID | 727 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
wives | +2.860 |
herself | +2.724 |
anova | +2.708 |
ikawa | +2.653 |
weed | +2.589 |
Neg logit contributions | |
senal | -2.356 |
llah | -2.089 |
newcom | -1.959 |
ortunately | -1.714 |
tremend | -1.710 |
Token | , |
Token ID | 11 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
wives | +0.236 |
herself | +0.227 |
anova | +0.222 |
ikawa | +0.221 |
mentation | +0.213 |
Neg logit contributions | |
llah | -0.269 |
senal | -0.266 |
ibur | -0.231 |
dayName | -0.229 |
newcom | -0.228 |
Token | m |
Token ID | 285 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
llah | +0.141 |
senal | +0.139 |
ibur | +0.121 |
dayName | +0.120 |
newcom | +0.119 |
Neg logit contributions | |
wives | -0.121 |
herself | -0.116 |
anova | -0.114 |
ikawa | -0.113 |
mentation | -0.109 |
Token | op |
Token ID | 404 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
wives | +0.344 |
herself | +0.328 |
anova | +0.324 |
ikawa | +0.322 |
mentation | +0.310 |
Neg logit contributions | |
llah | -0.421 |
senal | -0.419 |
newcom | -0.363 |
ibur | -0.362 |
dayName | -0.361 |
Token | - |
Token ID | 12 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
herself | +6.383 |
wives | +6.338 |
ikawa | +6.215 |
stage | +6.070 |
weed | +5.891 |
Neg logit contributions | |
senal | -9.432 |
llah | -9.187 |
dayName | -7.890 |
newcom | -7.777 |
ibur | -7.657 |
Token | headed |
Token ID | 15353 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
llah | +1.327 |
senal | +1.316 |
ibur | +1.169 |
newcom | +1.158 |
dayName | +1.152 |
Neg logit contributions | |
wives | -0.821 |
herself | -0.777 |
anova | -0.762 |
ikawa | -0.756 |
mentation | -0.724 |
Token | father |
Token ID | 2988 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
llah | +0.150 |
senal | +0.149 |
ibur | +0.130 |
dayName | +0.129 |
newcom | +0.128 |
Neg logit contributions | |
wives | -0.127 |
herself | -0.123 |
anova | -0.120 |
ikawa | -0.119 |
mentation | -0.115 |
Token | of |
Token ID | 286 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
llah | +1.102 |
senal | +1.095 |
newcom | +0.957 |
ibur | +0.950 |
dayName | +0.939 |
Neg logit contributions | |
wives | -1.112 |
anova | -1.071 |
ikawa | -1.057 |
herself | -1.036 |
mentation | -1.018 |
Token | three |
Token ID | 1115 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
wives | +2.440 |
herself | +2.376 |
ikawa | +2.177 |
anova | +2.177 |
mentation | +2.052 |
Neg logit contributions | |
senal | -4.468 |
llah | -4.442 |
dayName | -3.970 |
ibur | -3.952 |
newcom | -3.895 |
Token | bad |
Token ID | 2089 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
wives | +0.163 |
herself | +0.157 |
ikawa | +0.152 |
anova | +0.152 |
mentation | +0.147 |
Neg logit contributions | |
senal | -0.220 |
llah | -0.218 |
newcom | -0.191 |
ibur | -0.189 |
dayName | -0.187 |
Token | idea |
Token ID | 2126 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
wives | +1.021 |
herself | +1.011 |
ikawa | +0.944 |
anova | +0.934 |
mentation | +0.898 |
Neg logit contributions | |
senal | -2.435 |
llah | -2.325 |
newcom | -2.138 |
ibur | -2.090 |
dayName | -2.069 |
Token | . |
Token ID | 13 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
wives | +0.275 |
herself | +0.264 |
anova | +0.258 |
ikawa | +0.256 |
mentation | +0.246 |
Neg logit contributions | |
senal | -0.371 |
llah | -0.358 |
newcom | -0.323 |
ibur | -0.314 |
dayName | -0.309 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
wives | +0.404 |
herself | +0.388 |
anova | +0.381 |
ikawa | +0.380 |
mentation | +0.367 |
Neg logit contributions | |
llah | -0.410 |
senal | -0.402 |
ibur | -0.350 |
dayName | -0.345 |
newcom | -0.342 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
wives | +0.816 |
herself | +0.788 |
anova | +0.768 |
ikawa | +0.759 |
mentation | +0.738 |
Neg logit contributions | |
senal | -0.986 |
llah | -0.926 |
newcom | -0.847 |
ibur | -0.800 |
dayName | -0.784 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
wives | +0.461 |
anova | +0.399 |
herself | +0.397 |
ikawa | +0.388 |
mentation | +0.358 |
Neg logit contributions | |
senal | -1.851 |
llah | -1.816 |
newcom | -1.683 |
ibur | -1.645 |
dayName | -1.643 |
Token | : |
Token ID | 25 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
herself | +5.290 |
wives | +5.146 |
anova | +4.592 |
ikawa | +4.588 |
weed | +4.445 |
Neg logit contributions | |
senal | -12.615 |
newcom | -11.202 |
ortunately | -10.637 |
tremend | -10.585 |
llah | -10.418 |
Token | Mike |
Token ID | 4995 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
wives | +5.062 |
herself | +5.034 |
anova | +4.789 |
ikawa | +4.726 |
mentation | +4.565 |
Neg logit contributions | |
senal | -5.939 |
llah | -5.892 |
ibur | -5.101 |
dayName | -5.082 |
newcom | -4.940 |
Token | M |
Token ID | 44 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
wives | +2.556 |
herself | +2.464 |
anova | +2.414 |
ikawa | +2.390 |
mentation | +2.303 |
Neg logit contributions | |
llah | -2.781 |
senal | -2.758 |
ibur | -2.420 |
dayName | -2.403 |
newcom | -2.402 |
Token | anners |
Token ID | 15672 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
wives | +1.889 |
herself | +1.798 |
anova | +1.758 |
ikawa | +1.740 |
mentation | +1.664 |
Neg logit contributions | |
llah | -3.254 |
senal | -3.247 |
ibur | -2.892 |
newcom | -2.869 |
dayName | -2.867 |
Token | - |
Token ID | 532 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
wives | +3.318 |
herself | +3.165 |
anova | +3.125 |
ikawa | +3.065 |
mentation | +2.955 |
Neg logit contributions | |
llah | -3.911 |
senal | -3.851 |
ibur | -3.390 |
dayName | -3.363 |
newcom | -3.316 |
Token | was |
Token ID | 373 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
llah | +0.143 |
senal | +0.142 |
ibur | +0.125 |
newcom | +0.125 |
dayName | +0.124 |
Neg logit contributions | |
wives | -0.097 |
herself | -0.093 |
anova | -0.091 |
ikawa | -0.090 |
mentation | -0.086 |
Token | about |
Token ID | 546 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
wives | +0.840 |
herself | +0.817 |
anova | +0.790 |
ikawa | +0.781 |
mentation | +0.755 |
Neg logit contributions | |
llah | -1.062 |
senal | -1.059 |
ibur | -0.920 |
newcom | -0.917 |
dayName | -0.915 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
llah | +0.663 |
senal | +0.658 |
ibur | +0.575 |
dayName | +0.572 |
newcom | +0.570 |
Neg logit contributions | |
wives | -0.527 |
herself | -0.507 |
anova | -0.495 |
ikawa | -0.490 |
mentation | -0.473 |
Token |
|
Token ID | 198 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
llah | +0.796 |
senal | +0.787 |
ibur | +0.693 |
newcom | +0.684 |
dayName | +0.682 |
Neg logit contributions | |
wives | -0.631 |
herself | -0.602 |
anova | -0.592 |
ikawa | -0.587 |
mentation | -0.566 |
Token |
|
Token ID | 198 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
llah | +0.503 |
senal | +0.495 |
ibur | +0.430 |
dayName | +0.423 |
newcom | +0.422 |
Neg logit contributions | |
wives | -0.506 |
herself | -0.485 |
anova | -0.479 |
ikawa | -0.476 |
mentation | -0.461 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
wives | +0.463 |
herself | +0.439 |
anova | +0.436 |
ikawa | +0.432 |
mentation | +0.418 |
Neg logit contributions | |
senal | -0.516 |
llah | -0.515 |
newcom | -0.445 |
ibur | -0.442 |
dayName | -0.439 |
Token | : |
Token ID | 25 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
herself | +5.581 |
wives | +5.199 |
ikawa | +4.829 |
anova | +4.753 |
mentation | +4.588 |
Neg logit contributions | |
senal | -11.345 |
llah | -10.207 |
newcom | -9.827 |
ibur | -9.174 |
ortunately | -9.121 |
Token | k |
Token ID | 479 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
wives | +4.722 |
herself | +4.664 |
anova | +4.454 |
ikawa | +4.405 |
mentation | +4.258 |
Neg logit contributions | |
senal | -5.465 |
llah | -5.453 |
ibur | -4.689 |
dayName | -4.678 |
newcom | -4.567 |
Token | imp |
Token ID | 11011 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
wives | +2.128 |
anova | +2.011 |
ikawa | +1.999 |
herself | +1.996 |
mentation | +1.903 |
Neg logit contributions | |
senal | -2.558 |
llah | -2.483 |
newcom | -2.203 |
dayName | -2.171 |
ibur | -2.140 |
Token | unk |
Token ID | 2954 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
wives | +3.019 |
anova | +2.889 |
herself | +2.885 |
ikawa | +2.848 |
mentation | +2.755 |
Neg logit contributions | |
senal | -3.424 |
llah | -3.353 |
dayName | -2.931 |
newcom | -2.927 |
ibur | -2.885 |
Token | rock |
Token ID | 10823 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
wives | +1.946 |
herself | +1.850 |
anova | +1.837 |
ikawa | +1.812 |
mentation | +1.734 |
Neg logit contributions | |
senal | -2.467 |
llah | -2.450 |
dayName | -2.141 |
newcom | -2.121 |
ibur | -2.120 |
Token | AND |
Token ID | 5357 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
llah | +2.494 |
senal | +2.453 |
ibur | +2.162 |
dayName | +2.124 |
newcom | +2.124 |
Neg logit contributions | |
wives | -2.071 |
herself | -1.967 |
anova | -1.945 |
ikawa | -1.934 |
mentation | -1.865 |
Token | STEP |
Token ID | 49154 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
wives | +0.816 |
herself | +0.795 |
anova | +0.770 |
ikawa | +0.764 |
mentation | +0.742 |
Neg logit contributions | |
senal | -0.933 |
llah | -0.927 |
ibur | -0.807 |
newcom | -0.802 |
dayName | -0.784 |
Token | H |
Token ID | 39 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
wives | +1.240 |
herself | +1.212 |
anova | +1.203 |
ikawa | +1.149 |
mentation | +1.119 |
Neg logit contributions | |
senal | -1.432 |
llah | -1.426 |
newcom | -1.259 |
ibur | -1.251 |
dayName | -1.232 |
Token | EN |
Token ID | 1677 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
senal | +0.460 |
llah | +0.456 |
newcom | +0.394 |
ibur | +0.390 |
dayName | +0.387 |
Neg logit contributions | |
wives | -0.431 |
herself | -0.424 |
anova | -0.415 |
ikawa | -0.406 |
mentation | -0.392 |
Token | M |
Token ID | 337 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
wives | +0.330 |
herself | +0.320 |
anova | +0.313 |
ikawa | +0.308 |
mentation | +0.299 |
Neg logit contributions | |
senal | -0.389 |
llah | -0.387 |
ibur | -0.338 |
newcom | -0.337 |
dayName | -0.332 |
Token | atur |
Token ID | 2541 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
wives | +2.046 |
herself | +2.013 |
anova | +1.958 |
ikawa | +1.953 |
mentation | +1.885 |
Neg logit contributions | |
senal | -1.962 |
llah | -1.927 |
newcom | -1.685 |
ibur | -1.651 |
dayName | -1.641 |
Token | in |
Token ID | 259 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
wives | +4.890 |
anova | +4.659 |
ikawa | +4.551 |
herself | +4.438 |
mentation | +4.120 |
Neg logit contributions | |
senal | -12.480 |
newcom | -11.003 |
llah | -10.446 |
ortunately | -10.324 |
behavi | -10.170 |
Token | first |
Token ID | 717 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
wives | +1.708 |
herself | +1.675 |
anova | +1.607 |
ikawa | +1.585 |
mentation | +1.522 |
Neg logit contributions | |
senal | -2.175 |
llah | -2.161 |
ibur | -1.887 |
newcom | -1.883 |
dayName | -1.877 |
Token | meet |
Token ID | 1826 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
wives | +0.516 |
herself | +0.504 |
anova | +0.489 |
ikawa | +0.483 |
mentation | +0.469 |
Neg logit contributions | |
senal | -0.546 |
llah | -0.540 |
newcom | -0.463 |
ibur | -0.462 |
dayName | -0.461 |
Token | in |
Token ID | 287 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
wives | +0.596 |
herself | +0.583 |
anova | +0.563 |
ikawa | +0.558 |
mentation | +0.539 |
Neg logit contributions | |
llah | -0.727 |
senal | -0.726 |
ibur | -0.634 |
dayName | -0.631 |
newcom | -0.622 |
Token | April |
Token ID | 3035 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
wives | +0.134 |
herself | +0.130 |
anova | +0.127 |
ikawa | +0.126 |
mentation | +0.121 |
Neg logit contributions | |
llah | -0.162 |
senal | -0.161 |
ibur | -0.140 |
dayName | -0.139 |
newcom | -0.138 |
Token | image |
Token ID | 2939 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
wives | +3.009 |
herself | +2.964 |
ikawa | +2.887 |
anova | +2.849 |
mentation | +2.779 |
Neg logit contributions | |
senal | -3.499 |
llah | -3.338 |
newcom | -2.914 |
ibur | -2.869 |
dayName | -2.813 |
Token | T |
Token ID | 309 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
llah | +0.958 |
senal | +0.950 |
ibur | +0.830 |
newcom | +0.820 |
dayName | +0.814 |
Neg logit contributions | |
wives | -0.804 |
herself | -0.770 |
anova | -0.756 |
ikawa | -0.752 |
mentation | -0.728 |
Token | IFF |
Token ID | 29267 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
wives | +1.847 |
herself | +1.779 |
ikawa | +1.739 |
anova | +1.709 |
tarians | +1.549 |
Neg logit contributions | |
senal | -4.562 |
llah | -4.543 |
newcom | -4.054 |
dayName | -4.042 |
ibur | -3.984 |
Token | original |
Token ID | 2656 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
wives | +2.549 |
herself | +2.454 |
ikawa | +2.378 |
anova | +2.363 |
mentation | +2.280 |
Neg logit contributions | |
llah | -3.215 |
senal | -3.196 |
ibur | -2.749 |
dayName | -2.747 |
newcom | -2.720 |
Token | image |
Token ID | 2939 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
wives | +2.305 |
herself | +2.251 |
anova | +2.174 |
ikawa | +2.171 |
mentation | +2.131 |
Neg logit contributions | |
senal | -2.634 |
llah | -2.529 |
newcom | -2.197 |
ibur | -2.173 |
dayName | -2.143 |
Token | Download |
Token ID | 10472 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
llah | +1.461 |
senal | +1.442 |
ibur | +1.256 |
newcom | +1.240 |
dayName | +1.234 |
Neg logit contributions | |
wives | -1.277 |
herself | -1.224 |
anova | -1.204 |
ikawa | -1.197 |
mentation | -1.159 |
Token | : |
Token ID | 25 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
herself | +4.605 |
wives | +4.527 |
stage | +4.364 |
ikawa | +4.318 |
Pitch | +4.242 |
Neg logit contributions | |
senal | -11.191 |
llah | -10.653 |
newcom | -9.742 |
ibur | -9.634 |
dayName | -9.628 |
Token | Figure |
Token ID | 11291 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
llah | +0.273 |
senal | +0.269 |
ibur | +0.231 |
newcom | +0.227 |
dayName | +0.227 |
Neg logit contributions | |
wives | -0.301 |
herself | -0.288 |
anova | -0.285 |
ikawa | -0.283 |
mentation | -0.274 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
llah | +2.435 |
senal | +2.395 |
ibur | +2.087 |
dayName | +2.034 |
newcom | +2.024 |
Neg logit contributions | |
wives | -2.509 |
herself | -2.383 |
anova | -2.362 |
ikawa | -2.340 |
mentation | -2.273 |
Token | . |
Token ID | 13 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
llah | +2.763 |
senal | +2.726 |
ibur | +2.400 |
dayName | +2.362 |
newcom | +2.320 |
Neg logit contributions | |
wives | -2.744 |
herself | -2.565 |
ikawa | -2.542 |
anova | -2.540 |
tarians | -2.451 |
Token | Maze |
Token ID | 33412 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
wives | +0.618 |
herself | +0.594 |
anova | +0.586 |
ikawa | +0.579 |
mentation | +0.560 |
Neg logit contributions | |
llah | -0.810 |
senal | -0.803 |
ibur | -0.703 |
newcom | -0.698 |
dayName | -0.690 |
Token | Everyone |
Token ID | 16190 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
wives | +3.846 |
anova | +3.617 |
herself | +3.580 |
ikawa | +3.537 |
weed | +3.425 |
Neg logit contributions | |
llah | -4.387 |
senal | -4.333 |
ibur | -3.740 |
newcom | -3.724 |
dayName | -3.688 |
Token | ) |
Token ID | 8 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
wives | +1.611 |
herself | +1.589 |
anova | +1.530 |
ikawa | +1.524 |
mentation | +1.460 |
Neg logit contributions | |
senal | -2.351 |
llah | -2.344 |
newcom | -2.036 |
ibur | -2.035 |
dayName | -2.031 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
wives | +1.964 |
herself | +1.890 |
anova | +1.867 |
ikawa | +1.841 |
mentation | +1.794 |
Neg logit contributions | |
llah | -2.256 |
senal | -2.254 |
ibur | -1.961 |
dayName | -1.940 |
newcom | -1.929 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
wives | +1.496 |
herself | +1.450 |
anova | +1.397 |
ikawa | +1.380 |
mentation | +1.339 |
Neg logit contributions | |
senal | -1.964 |
llah | -1.793 |
newcom | -1.694 |
ibur | -1.553 |
dayName | -1.516 |
Token | System |
Token ID | 11964 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
wives | +1.308 |
herself | +1.236 |
anova | +1.225 |
ikawa | +1.212 |
mentation | +1.173 |
Neg logit contributions | |
senal | -1.579 |
llah | -1.556 |
newcom | -1.367 |
ibur | -1.330 |
dayName | -1.318 |
Token | Requirements |
Token ID | 24422 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
wives | +3.694 |
herself | +3.620 |
anova | +3.534 |
ikawa | +3.521 |
mentation | +3.435 |
Neg logit contributions | |
llah | -4.097 |
senal | -4.083 |
newcom | -3.494 |
ibur | -3.471 |
dayName | -3.401 |
Token | : |
Token ID | 25 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
wives | +5.886 |
herself | +5.734 |
ikawa | +5.583 |
mentation | +5.526 |
anova | +5.389 |
Neg logit contributions | |
llah | -9.334 |
senal | -9.165 |
dayName | -8.147 |
ibur | -8.144 |
newcom | -8.089 |
Token | Microsoft |
Token ID | 5413 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
wives | +1.507 |
herself | +1.440 |
anova | +1.414 |
ikawa | +1.399 |
mentation | +1.350 |
Neg logit contributions | |
llah | -2.071 |
senal | -2.061 |
ibur | -1.801 |
dayName | -1.799 |
newcom | -1.790 |
Token | ® |
Token ID | 7461 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
wives | +0.532 |
herself | +0.512 |
anova | +0.496 |
ikawa | +0.494 |
mentation | +0.480 |
Neg logit contributions | |
senal | -0.745 |
llah | -0.745 |
dayName | -0.651 |
ibur | -0.647 |
newcom | -0.641 |
Token | Windows |
Token ID | 3964 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
llah | +2.872 |
senal | +2.834 |
ibur | +2.503 |
newcom | +2.464 |
dayName | +2.459 |
Neg logit contributions | |
wives | -2.246 |
herself | -2.137 |
anova | -2.108 |
ikawa | -2.093 |
mentation | -2.013 |
Token | ® |
Token ID | 7461 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
llah | +1.097 |
senal | +1.085 |
ibur | +0.901 |
dayName | +0.892 |
newcom | +0.892 |
Neg logit contributions | |
wives | -1.521 |
herself | -1.470 |
anova | -1.449 |
ikawa | -1.439 |
mentation | -1.407 |
Token | quite |
Token ID | 2407 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
wives | +2.090 |
herself | +2.069 |
anova | +1.986 |
ikawa | +1.923 |
mentation | +1.920 |
Neg logit contributions | |
senal | -2.692 |
llah | -2.672 |
ibur | -2.319 |
newcom | -2.304 |
dayName | -2.249 |
Token | even |
Token ID | 772 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
wives | +2.304 |
ikawa | +2.168 |
anova | +2.157 |
herself | +2.142 |
mentation | +2.063 |
Neg logit contributions | |
llah | -2.624 |
senal | -2.576 |
ibur | -2.294 |
newcom | -2.256 |
bedrock | -2.236 |
Token | handed |
Token ID | 10158 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
wives | +2.393 |
anova | +2.278 |
herself | +2.235 |
ikawa | +2.226 |
mentation | +2.118 |
Neg logit contributions | |
llah | -4.103 |
senal | -4.033 |
ibur | -3.654 |
dayName | -3.593 |
bedrock | -3.588 |
Token | ' |
Token ID | 6 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
wives | +1.326 |
herself | +1.276 |
anova | +1.192 |
ikawa | +1.186 |
mentation | +1.132 |
Neg logit contributions | |
senal | -2.856 |
llah | -2.808 |
newcom | -2.526 |
ibur | -2.498 |
dayName | -2.473 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
wives | +1.753 |
herself | +1.695 |
anova | +1.652 |
ikawa | +1.623 |
mentation | +1.577 |
Neg logit contributions | |
llah | -2.049 |
senal | -2.017 |
ibur | -1.774 |
newcom | -1.752 |
dayName | -1.723 |
Token | primary |
Token ID | 4165 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
wives | +1.440 |
herself | +1.369 |
anova | +1.348 |
ikawa | +1.333 |
mentation | +1.289 |
Neg logit contributions | |
llah | -2.030 |
senal | -2.011 |
ibur | -1.778 |
newcom | -1.749 |
dayName | -1.747 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -8.22e+00 |
Pos logit contributions | |
wives | +6.256 |
herself | +5.960 |
stage | +5.873 |
tarians | +5.774 |
anova | +5.751 |
Neg logit contributions | |
senal | -9.469 |
llah | -9.053 |
newcom | -8.281 |
ibur | -8.200 |
dayName | -8.161 |
Token | : |
Token ID | 25 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
herself | +4.531 |
anova | +4.099 |
wives | +3.990 |
tarians | +3.871 |
stage | +3.851 |
Neg logit contributions | |
senal | -7.946 |
llah | -7.878 |
newcom | -7.268 |
dayName | -7.126 |
ibur | -6.985 |
Token | ' |
Token ID | 705 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
wives | +1.410 |
herself | +1.325 |
anova | +1.308 |
ikawa | +1.298 |
mentation | +1.239 |
Neg logit contributions | |
llah | -2.268 |
senal | -2.240 |
ibur | -2.006 |
dayName | -1.979 |
newcom | -1.972 |
Token | Damn |
Token ID | 43343 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
wives | +4.689 |
herself | +4.533 |
anova | +4.531 |
ikawa | +4.354 |
mentation | +4.273 |
Neg logit contributions | |
senal | -6.080 |
llah | -6.061 |
ibur | -5.284 |
newcom | -5.195 |
dayName | -5.064 |
Token | right |
Token ID | 826 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
wives | +3.025 |
herself | +2.964 |
ikawa | +2.783 |
anova | +2.781 |
mentation | +2.710 |
Neg logit contributions | |
llah | -4.292 |
senal | -4.274 |
dayName | -3.729 |
newcom | -3.693 |
ibur | -3.683 |
Token | : |
Token ID | 25 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
wives | +0.035 |
herself | +0.034 |
anova | +0.033 |
ikawa | +0.033 |
mentation | +0.032 |
Neg logit contributions | |
senal | -0.044 |
llah | -0.043 |
newcom | -0.038 |
ibur | -0.037 |
dayName | -0.036 |
Token | 48 |
Token ID | 2780 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
wives | +0.284 |
herself | +0.271 |
anova | +0.271 |
ikawa | +0.267 |
mentation | +0.261 |
Neg logit contributions | |
llah | -0.273 |
senal | -0.261 |
ibur | -0.231 |
dayName | -0.225 |
newcom | -0.222 |
Token | ] |
Token ID | 60 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
wives | +1.464 |
herself | +1.424 |
anova | +1.340 |
ikawa | +1.323 |
mentation | +1.257 |
Neg logit contributions | |
senal | -3.051 |
llah | -2.752 |
newcom | -2.691 |
tremend | -2.478 |
ortunately | -2.456 |
Token | < |
Token ID | 1279 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
wives | +1.763 |
herself | +1.738 |
anova | +1.673 |
ikawa | +1.669 |
mentation | +1.595 |
Neg logit contributions | |
senal | -2.129 |
llah | -1.964 |
newcom | -1.793 |
ibur | -1.691 |
dayName | -1.662 |
Token | m |
Token ID | 76 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
wives | +1.639 |
herself | +1.553 |
anova | +1.549 |
ikawa | +1.521 |
mentation | +1.466 |
Neg logit contributions | |
senal | -2.013 |
llah | -1.983 |
newcom | -1.741 |
ibur | -1.717 |
dayName | -1.697 |
Token | ew |
Token ID | 413 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
wives | +2.008 |
ikawa | +1.919 |
herself | +1.909 |
anova | +1.896 |
mentation | +1.809 |
Neg logit contributions | |
senal | -2.520 |
llah | -2.470 |
newcom | -2.199 |
dayName | -2.174 |
ibur | -2.128 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
wives | +7.267 |
anova | +6.990 |
herself | +6.874 |
ikawa | +6.873 |
mentation | +6.585 |
Neg logit contributions | |
senal | -8.527 |
llah | -7.629 |
newcom | -7.263 |
dayName | -6.887 |
behavi | -6.687 |
Token | king |
Token ID | 3364 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
llah | +1.552 |
senal | +1.521 |
ibur | +1.350 |
dayName | +1.324 |
newcom | +1.315 |
Neg logit contributions | |
wives | -1.256 |
herself | -1.201 |
anova | -1.180 |
ikawa | -1.174 |
mentation | -1.133 |
Token | > |
Token ID | 29 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
llah | +0.911 |
senal | +0.890 |
ibur | +0.789 |
dayName | +0.772 |
newcom | +0.769 |
Neg logit contributions | |
wives | -0.764 |
herself | -0.731 |
anova | -0.716 |
ikawa | -0.714 |
mentation | -0.692 |
Token | OM |
Token ID | 32468 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
llah | +0.048 |
senal | +0.048 |
ibur | +0.041 |
dayName | +0.041 |
newcom | +0.041 |
Neg logit contributions | |
wives | -0.042 |
herself | -0.041 |
anova | -0.040 |
ikawa | -0.040 |
mentation | -0.038 |
Token | FG |
Token ID | 30386 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
wives | +1.477 |
herself | +1.435 |
ikawa | +1.425 |
anova | +1.396 |
mentation | +1.343 |
Neg logit contributions | |
llah | -1.765 |
senal | -1.749 |
dayName | -1.524 |
ibur | -1.517 |
newcom | -1.513 |
Token | FBI |
Token ID | 5349 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
wives | +0.621 |
herself | +0.601 |
anova | +0.581 |
ikawa | +0.573 |
mentation | +0.561 |
Neg logit contributions | |
senal | -0.722 |
llah | -0.718 |
ibur | -0.625 |
dayName | -0.621 |
newcom | -0.618 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
llah | +0.072 |
senal | +0.071 |
ibur | +0.060 |
newcom | +0.060 |
dayName | +0.059 |
Neg logit contributions | |
wives | -0.091 |
herself | -0.088 |
anova | -0.086 |
ikawa | -0.085 |
mentation | -0.083 |
Token | There |
Token ID | 1318 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
wives | +0.821 |
herself | +0.782 |
anova | +0.761 |
ikawa | +0.750 |
mentation | +0.729 |
Neg logit contributions | |
senal | -1.146 |
llah | -1.112 |
newcom | -1.008 |
ibur | -0.988 |
dayName | -0.971 |
Token | is |
Token ID | 318 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
wives | +2.240 |
herself | +2.188 |
ikawa | +2.119 |
anova | +2.115 |
mentation | +2.056 |
Neg logit contributions | |
senal | -2.277 |
llah | -2.263 |
newcom | -1.963 |
ibur | -1.952 |
dayName | -1.932 |
Token | no |
Token ID | 645 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
wives | +1.235 |
herself | +1.206 |
anova | +1.176 |
ikawa | +1.155 |
mentation | +1.117 |
Neg logit contributions | |
llah | -1.579 |
senal | -1.578 |
newcom | -1.377 |
dayName | -1.365 |
ibur | -1.365 |
Token | more |
Token ID | 517 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
llah | +2.062 |
senal | +2.032 |
ibur | +1.780 |
newcom | +1.749 |
dayName | +1.747 |
Neg logit contributions | |
wives | -1.863 |
herself | -1.779 |
anova | -1.759 |
ikawa | -1.747 |
mentation | -1.686 |
Token | powerful |
Token ID | 3665 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
llah | +4.892 |
senal | +4.740 |
ibur | +4.229 |
bedrock | +4.197 |
dayName | +4.084 |
Neg logit contributions | |
wives | -4.767 |
anova | -4.526 |
ikawa | -4.502 |
herself | -4.452 |
mentation | -4.326 |
Token | federal |
Token ID | 2717 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
llah | +3.284 |
senal | +3.213 |
ibur | +2.845 |
bedrock | +2.770 |
newcom | +2.746 |
Neg logit contributions | |
wives | -3.251 |
anova | -3.081 |
ikawa | -3.066 |
herself | -3.057 |
mentation | -2.939 |
Token | agency |
Token ID | 4086 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
llah | +3.498 |
senal | +3.403 |
ibur | +2.978 |
newcom | +2.884 |
dayName | +2.861 |
Neg logit contributions | |
wives | -3.972 |
herself | -3.764 |
anova | -3.761 |
ikawa | -3.744 |
mentation | -3.604 |
Token | in |
Token ID | 287 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
senal | +0.096 |
llah | +0.095 |
newcom | +0.083 |
ibur | +0.083 |
dayName | +0.083 |
Neg logit contributions | |
wives | -0.075 |
herself | -0.073 |
anova | -0.070 |
ikawa | -0.070 |
mentation | -0.068 |
Token | this |
Token ID | 428 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
llah | +1.085 |
senal | +1.073 |
ibur | +0.941 |
newcom | +0.928 |
dayName | +0.928 |
Neg logit contributions | |
wives | -0.899 |
herself | -0.861 |
anova | -0.848 |
ikawa | -0.840 |
mentation | -0.812 |
Token | Bor |
Token ID | 12182 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
llah | +0.519 |
senal | +0.515 |
ibur | +0.451 |
newcom | +0.447 |
dayName | +0.446 |
Neg logit contributions | |
wives | -0.409 |
herself | -0.390 |
anova | -0.384 |
ikawa | -0.381 |
mentation | -0.367 |
Token | as |
Token ID | 292 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
llah | +0.286 |
senal | +0.283 |
ibur | +0.247 |
newcom | +0.244 |
dayName | +0.243 |
Neg logit contributions | |
wives | -0.252 |
herself | -0.241 |
anova | -0.238 |
ikawa | -0.237 |
mentation | -0.228 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
llah | +1.565 |
senal | +1.539 |
ibur | +1.351 |
dayName | +1.327 |
newcom | +1.326 |
Neg logit contributions | |
wives | -1.387 |
herself | -1.322 |
anova | -1.307 |
ikawa | -1.297 |
mentation | -1.257 |
Token | With |
Token ID | 2080 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
wives | +0.401 |
herself | +0.384 |
anova | +0.377 |
ikawa | +0.375 |
mentation | +0.362 |
Neg logit contributions | |
senal | -0.471 |
llah | -0.469 |
ibur | -0.407 |
newcom | -0.406 |
dayName | -0.397 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
llah | +2.536 |
senal | +2.499 |
ibur | +2.216 |
newcom | +2.182 |
dayName | +2.174 |
Neg logit contributions | |
wives | -1.964 |
herself | -1.857 |
anova | -1.839 |
ikawa | -1.830 |
mentation | -1.762 |
Token | slot |
Token ID | 10852 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
llah | +1.217 |
senal | +1.210 |
ibur | +1.062 |
newcom | +1.046 |
dayName | +1.044 |
Neg logit contributions | |
wives | -0.961 |
herself | -0.920 |
anova | -0.901 |
ikawa | -0.894 |
mentation | -0.862 |
Token | ting |
Token ID | 889 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
llah | +4.461 |
senal | +4.390 |
ibur | +3.754 |
newcom | +3.686 |
dayName | +3.651 |
Neg logit contributions | |
wives | -5.258 |
herself | -5.029 |
anova | -4.989 |
ikawa | -4.967 |
mentation | -4.789 |
Token | system |
Token ID | 1080 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
llah | +2.762 |
senal | +2.726 |
ibur | +2.390 |
newcom | +2.353 |
dayName | +2.346 |
Neg logit contributions | |
wives | -2.423 |
herself | -2.305 |
anova | -2.285 |
ikawa | -2.272 |
mentation | -2.190 |
Token | for |
Token ID | 329 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
llah | +2.018 |
senal | +1.993 |
ibur | +1.746 |
newcom | +1.720 |
dayName | +1.717 |
Neg logit contributions | |
wives | -1.750 |
herself | -1.668 |
anova | -1.650 |
ikawa | -1.638 |
mentation | -1.581 |
Token | picks |
Token ID | 11103 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
llah | +0.763 |
senal | +0.757 |
ibur | +0.661 |
dayName | +0.651 |
newcom | +0.649 |
Neg logit contributions | |
wives | -0.644 |
herself | -0.618 |
anova | -0.605 |
ikawa | -0.602 |
mentation | -0.581 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
llah | +5.114 |
senal | +5.000 |
ibur | +4.365 |
bedrock | +4.312 |
newcom | +4.309 |
Neg logit contributions | |
wives | -4.651 |
herself | -4.389 |
ikawa | -4.375 |
anova | -4.362 |
mentation | -4.222 |
Token | it |
Token ID | 340 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
senal | +0.118 |
llah | +0.118 |
ibur | +0.103 |
newcom | +0.102 |
dayName | +0.102 |
Neg logit contributions | |
wives | -0.091 |
herself | -0.087 |
anova | -0.084 |
ikawa | -0.084 |
mentation | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
wives | +1.946 |
herself | +1.936 |
anova | +1.801 |
ikawa | +1.791 |
mentation | +1.730 |
Neg logit contributions | |
senal | -2.813 |
llah | -2.733 |
newcom | -2.414 |
ibur | -2.382 |
dayName | -2.349 |
Token |
|
Token ID | 198 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
wives | +0.240 |
herself | +0.229 |
anova | +0.224 |
ikawa | +0.220 |
mentation | +0.215 |
Neg logit contributions | |
senal | -0.287 |
llah | -0.281 |
newcom | -0.248 |
ibur | -0.244 |
dayName | -0.241 |
Token |
|
Token ID | 198 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
wives | +0.637 |
herself | +0.616 |
anova | +0.598 |
ikawa | +0.594 |
mentation | +0.576 |
Neg logit contributions | |
senal | -0.762 |
llah | -0.719 |
newcom | -0.657 |
ibur | -0.621 |
dayName | -0.607 |
Token | Read |
Token ID | 5569 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
wives | +0.463 |
herself | +0.439 |
anova | +0.434 |
ikawa | +0.428 |
mentation | +0.417 |
Neg logit contributions | |
senal | -0.535 |
llah | -0.529 |
newcom | -0.463 |
ibur | -0.455 |
dayName | -0.451 |
Token | or |
Token ID | 393 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
wives | +2.253 |
herself | +2.176 |
anova | +2.118 |
ikawa | +2.093 |
mentation | +2.028 |
Neg logit contributions | |
llah | -3.386 |
senal | -3.382 |
ibur | -2.995 |
dayName | -2.961 |
newcom | -2.940 |
Token | Share |
Token ID | 8734 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
llah | +5.044 |
senal | +4.807 |
ibur | +4.306 |
dayName | +4.289 |
newcom | +4.233 |
Neg logit contributions | |
wives | -5.243 |
anova | -4.964 |
herself | -4.851 |
ikawa | -4.843 |
mentation | -4.689 |
Token | this |
Token ID | 428 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
llah | +2.533 |
senal | +2.474 |
ibur | +2.146 |
dayName | +2.108 |
bedrock | +2.105 |
Neg logit contributions | |
wives | -2.592 |
herself | -2.463 |
anova | -2.451 |
ikawa | -2.446 |
mentation | -2.390 |
Token | story |
Token ID | 1621 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
wives | +1.741 |
herself | +1.707 |
anova | +1.653 |
ikawa | +1.613 |
mentation | +1.559 |
Neg logit contributions | |
senal | -2.439 |
llah | -2.386 |
newcom | -2.100 |
dayName | -2.064 |
ibur | -2.063 |
Token | : |
Token ID | 25 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
herself | +1.805 |
wives | +1.804 |
anova | +1.672 |
ikawa | +1.618 |
mentation | +1.580 |
Neg logit contributions | |
senal | -2.886 |
llah | -2.717 |
newcom | -2.564 |
ibur | -2.401 |
dayName | -2.333 |
Token | http |
Token ID | 2638 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
wives | +0.589 |
herself | +0.571 |
anova | +0.565 |
ikawa | +0.558 |
mentation | +0.544 |
Neg logit contributions | |
llah | -0.375 |
senal | -0.371 |
ibur | -0.302 |
newcom | -0.300 |
dayName | -0.298 |
Token | others |
Token ID | 1854 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
llah | +2.456 |
senal | +2.402 |
ibur | +2.124 |
newcom | +2.080 |
dayName | +2.079 |
Neg logit contributions | |
wives | -2.109 |
herself | -2.007 |
anova | -1.996 |
ikawa | -1.982 |
mentation | -1.912 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
llah | +4.018 |
senal | +3.814 |
ibur | +3.404 |
bedrock | +3.307 |
dayName | +3.306 |
Neg logit contributions | |
wives | -3.726 |
anova | -3.553 |
ikawa | -3.547 |
herself | -3.501 |
mentation | -3.409 |
Token |
|
Token ID | 198 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
senal | +0.937 |
llah | +0.930 |
newcom | +0.813 |
ibur | +0.810 |
dayName | +0.798 |
Neg logit contributions | |
wives | -0.783 |
herself | -0.751 |
anova | -0.733 |
ikawa | -0.725 |
mentation | -0.702 |
Token |
|
Token ID | 198 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
senal | +0.665 |
llah | +0.661 |
newcom | +0.568 |
ibur | +0.567 |
dayName | +0.556 |
Neg logit contributions | |
wives | -0.642 |
herself | -0.616 |
anova | -0.606 |
ikawa | -0.602 |
mentation | -0.583 |
Token | Yet |
Token ID | 11486 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
senal | +0.287 |
llah | +0.280 |
newcom | +0.249 |
ibur | +0.243 |
dayName | +0.241 |
Neg logit contributions | |
wives | -0.224 |
herself | -0.211 |
anova | -0.208 |
ikawa | -0.205 |
mentation | -0.199 |
Token | being |
Token ID | 852 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
llah | +0.563 |
senal | +0.563 |
ibur | +0.491 |
dayName | +0.487 |
newcom | +0.486 |
Neg logit contributions | |
wives | -0.448 |
herself | -0.432 |
anova | -0.420 |
ikawa | -0.417 |
mentation | -0.401 |
Token | right |
Token ID | 826 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
llah | +4.803 |
senal | +4.620 |
ibur | +4.101 |
bedrock | +4.053 |
newcom | +4.001 |
Neg logit contributions | |
wives | -4.554 |
anova | -4.351 |
ikawa | -4.323 |
herself | -4.240 |
mentation | -4.173 |
Token | isn |
Token ID | 2125 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
llah | +2.248 |
senal | +2.219 |
ibur | +1.954 |
newcom | +1.925 |
dayName | +1.923 |
Neg logit contributions | |
wives | -1.791 |
herself | -1.706 |
anova | -1.682 |
ikawa | -1.670 |
mentation | -1.609 |
Token | � |
Token ID | 447 |
Feature activation | -9.44e-03 |
Pos logit contributions | |
llah | +1.124 |
senal | +1.121 |
ibur | +0.991 |
newcom | +0.987 |
dayName | +0.976 |
Neg logit contributions | |
wives | -0.712 |
herself | -0.675 |
anova | -0.662 |
ikawa | -0.657 |
mentation | -0.629 |
Token | � |
Token ID | 247 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
wives | +0.008 |
herself | +0.008 |
anova | +0.008 |
ikawa | +0.007 |
mentation | +0.007 |
Neg logit contributions | |
senal | -0.006 |
llah | -0.006 |
newcom | -0.005 |
ibur | -0.005 |
dayName | -0.005 |
Token | t |
Token ID | 83 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
llah | +1.383 |
senal | +1.374 |
ibur | +1.230 |
newcom | +1.222 |
dayName | +1.216 |
Neg logit contributions | |
wives | -0.703 |
herself | -0.662 |
anova | -0.650 |
ikawa | -0.642 |
mentation | -0.612 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
wives | +0.250 |
herself | +0.237 |
anova | +0.232 |
ikawa | +0.230 |
mentation | +0.220 |
Neg logit contributions | |
senal | -0.353 |
llah | -0.352 |
ibur | -0.308 |
newcom | -0.307 |
dayName | -0.306 |
Token | As |
Token ID | 1081 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
wives | +0.126 |
herself | +0.120 |
anova | +0.117 |
ikawa | +0.115 |
mentation | +0.112 |
Neg logit contributions | |
senal | -0.160 |
llah | -0.156 |
newcom | -0.139 |
ibur | -0.136 |
dayName | -0.135 |
Token | for |
Token ID | 329 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
llah | +0.855 |
senal | +0.848 |
ibur | +0.742 |
newcom | +0.734 |
dayName | +0.734 |
Neg logit contributions | |
wives | -0.694 |
herself | -0.661 |
anova | -0.651 |
ikawa | -0.644 |
mentation | -0.623 |
Token | who |
Token ID | 508 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
llah | +0.490 |
senal | +0.487 |
ibur | +0.424 |
dayName | +0.420 |
newcom | +0.419 |
Neg logit contributions | |
wives | -0.415 |
herself | -0.399 |
anova | -0.390 |
ikawa | -0.387 |
mentation | -0.374 |
Token | gets |
Token ID | 3011 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
llah | +1.250 |
senal | +1.247 |
ibur | +1.088 |
newcom | +1.085 |
dayName | +1.077 |
Neg logit contributions | |
wives | -0.992 |
herself | -0.952 |
anova | -0.930 |
ikawa | -0.921 |
mentation | -0.890 |
Token | jobs |
Token ID | 3946 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
llah | +1.305 |
senal | +1.292 |
ibur | +1.129 |
newcom | +1.118 |
dayName | +1.117 |
Neg logit contributions | |
wives | -1.103 |
herself | -1.056 |
anova | -1.037 |
ikawa | -1.028 |
mentation | -0.996 |
Token | , |
Token ID | 11 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
llah | +4.619 |
senal | +4.381 |
ibur | +3.974 |
bedrock | +3.866 |
dayName | +3.847 |
Neg logit contributions | |
wives | -4.095 |
ikawa | -3.924 |
anova | -3.902 |
herself | -3.846 |
mentation | -3.726 |
Token | we |
Token ID | 356 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
llah | +0.153 |
senal | +0.153 |
ibur | +0.133 |
dayName | +0.132 |
newcom | +0.132 |
Neg logit contributions | |
wives | -0.122 |
herself | -0.117 |
anova | -0.114 |
ikawa | -0.113 |
mentation | -0.110 |
Token | have |
Token ID | 423 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
senal | +0.363 |
llah | +0.363 |
newcom | +0.317 |
ibur | +0.316 |
dayName | +0.313 |
Neg logit contributions | |
wives | -0.274 |
herself | -0.263 |
anova | -0.256 |
ikawa | -0.254 |
mentation | -0.245 |
Token | a |
Token ID | 257 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
llah | +0.580 |
senal | +0.573 |
ibur | +0.500 |
newcom | +0.495 |
dayName | +0.494 |
Neg logit contributions | |
wives | -0.500 |
herself | -0.478 |
anova | -0.471 |
ikawa | -0.467 |
mentation | -0.452 |
Token | " |
Token ID | 366 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
llah | +2.154 |
senal | +2.125 |
ibur | +1.858 |
newcom | +1.829 |
dayName | +1.827 |
Neg logit contributions | |
wives | -1.915 |
herself | -1.829 |
anova | -1.806 |
ikawa | -1.793 |
mentation | -1.731 |
Token | have |
Token ID | 423 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
wives | +0.289 |
herself | +0.280 |
anova | +0.271 |
ikawa | +0.269 |
mentation | +0.259 |
Neg logit contributions | |
senal | -0.352 |
llah | -0.347 |
ibur | -0.302 |
newcom | -0.302 |
dayName | -0.298 |
Token | a |
Token ID | 257 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
llah | +0.005 |
senal | +0.005 |
ibur | +0.004 |
dayName | +0.004 |
newcom | +0.004 |
Neg logit contributions | |
wives | -0.004 |
herself | -0.004 |
anova | -0.004 |
ikawa | -0.004 |
mentation | -0.003 |
Token | copy |
Token ID | 4866 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
wives | +0.384 |
herself | +0.368 |
ikawa | +0.357 |
anova | +0.357 |
mentation | +0.341 |
Neg logit contributions | |
llah | -0.521 |
senal | -0.520 |
ibur | -0.456 |
dayName | -0.454 |
newcom | -0.447 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
senal | +0.813 |
llah | +0.813 |
ibur | +0.705 |
newcom | +0.699 |
dayName | +0.696 |
Neg logit contributions | |
wives | -0.670 |
herself | -0.647 |
anova | -0.627 |
ikawa | -0.625 |
mentation | -0.604 |
Token | my |
Token ID | 616 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
llah | +1.007 |
senal | +0.998 |
ibur | +0.876 |
dayName | +0.863 |
newcom | +0.859 |
Neg logit contributions | |
wives | -0.840 |
herself | -0.805 |
anova | -0.790 |
ikawa | -0.785 |
mentation | -0.757 |
Token | collection |
Token ID | 4947 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
llah | +0.481 |
senal | +0.477 |
ibur | +0.419 |
dayName | +0.414 |
newcom | +0.412 |
Neg logit contributions | |
wives | -0.393 |
herself | -0.377 |
anova | -0.369 |
ikawa | -0.368 |
mentation | -0.353 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
senal | +0.338 |
llah | +0.336 |
ibur | +0.295 |
newcom | +0.293 |
dayName | +0.291 |
Neg logit contributions | |
wives | -0.259 |
herself | -0.251 |
anova | -0.241 |
ikawa | -0.241 |
mentation | -0.232 |
Token | it |
Token ID | 340 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
wives | +1.147 |
herself | +1.102 |
anova | +1.074 |
ikawa | +1.072 |
mentation | +1.030 |
Neg logit contributions | |
senal | -1.583 |
llah | -1.563 |
newcom | -1.378 |
ibur | -1.369 |
dayName | -1.361 |
Token | is |
Token ID | 318 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
wives | +0.516 |
herself | +0.500 |
anova | +0.487 |
ikawa | +0.486 |
mentation | +0.468 |
Neg logit contributions | |
senal | -0.611 |
llah | -0.605 |
newcom | -0.526 |
ibur | -0.522 |
dayName | -0.517 |
Token | one |
Token ID | 530 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
wives | +1.177 |
herself | +1.146 |
anova | +1.105 |
ikawa | +1.097 |
mentation | +1.049 |
Neg logit contributions | |
senal | -1.451 |
llah | -1.441 |
newcom | -1.255 |
ibur | -1.250 |
dayName | -1.249 |
Token | of |
Token ID | 286 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
wives | +2.046 |
herself | +1.973 |
anova | +1.928 |
ikawa | +1.914 |
mentation | +1.840 |
Neg logit contributions | |
llah | -2.690 |
senal | -2.678 |
ibur | -2.333 |
dayName | -2.319 |
newcom | -2.311 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
llah | +0.491 |
senal | +0.490 |
ibur | +0.428 |
newcom | +0.424 |
dayName | +0.421 |
Neg logit contributions | |
wives | -0.395 |
herself | -0.380 |
anova | -0.369 |
ikawa | -0.366 |
mentation | -0.352 |
Token | At |
Token ID | 1629 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
llah | +1.803 |
senal | +1.797 |
ibur | +1.564 |
newcom | +1.554 |
dayName | +1.539 |
Neg logit contributions | |
wives | -1.491 |
herself | -1.426 |
anova | -1.400 |
ikawa | -1.387 |
mentation | -1.339 |
Token | the |
Token ID | 262 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
llah | +1.235 |
senal | +1.230 |
ibur | +1.067 |
newcom | +1.060 |
dayName | +1.056 |
Neg logit contributions | |
wives | -0.988 |
herself | -0.946 |
anova | -0.929 |
ikawa | -0.917 |
mentation | -0.887 |
Token | party |
Token ID | 2151 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
senal | +0.523 |
llah | +0.521 |
ibur | +0.455 |
newcom | +0.451 |
dayName | +0.446 |
Neg logit contributions | |
wives | -0.414 |
herself | -0.398 |
anova | -0.390 |
ikawa | -0.386 |
mentation | -0.372 |
Token | � |
Token ID | 447 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
wives | +3.669 |
herself | +3.623 |
anova | +3.485 |
mentation | +3.326 |
ikawa | +3.305 |
Neg logit contributions | |
senal | -5.001 |
llah | -4.846 |
newcom | -4.255 |
dayName | -4.186 |
ibur | -4.170 |
Token | � |
Token ID | 247 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
wives | +0.096 |
herself | +0.093 |
anova | +0.092 |
ikawa | +0.091 |
mentation | +0.090 |
Neg logit contributions | |
senal | -0.062 |
llah | -0.062 |
newcom | -0.052 |
ibur | -0.050 |
dayName | -0.050 |
Token | s |
Token ID | 82 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
llah | +0.719 |
senal | +0.715 |
ibur | +0.626 |
newcom | +0.619 |
dayName | +0.617 |
Neg logit contributions | |
wives | -0.564 |
herself | -0.537 |
anova | -0.531 |
ikawa | -0.524 |
mentation | -0.507 |
Token | con |
Token ID | 369 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
wives | +1.242 |
herself | +1.208 |
anova | +1.173 |
ikawa | +1.148 |
mentation | +1.122 |
Neg logit contributions | |
senal | -1.570 |
llah | -1.553 |
ibur | -1.348 |
newcom | -1.342 |
dayName | -1.336 |
Token | |
Token ID | 3907 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
wives | +0.094 |
herself | +0.091 |
anova | +0.089 |
ikawa | +0.089 |
mentation | +0.086 |
Neg logit contributions | |
llah | -0.090 |
senal | -0.089 |
ibur | -0.076 |
newcom | -0.076 |
dayName | -0.075 |
Token | ven |
Token ID | 574 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
llah | +5.520 |
senal | +5.268 |
ibur | +4.952 |
dayName | +4.732 |
bedrock | +4.627 |
Neg logit contributions | |
wives | -3.972 |
herself | -3.790 |
anova | -3.739 |
ikawa | -3.687 |
mentation | -3.524 |
Token | |
Token ID | 3907 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
llah | +0.729 |
senal | +0.729 |
ibur | +0.617 |
newcom | +0.616 |
dayName | +0.608 |
Neg logit contributions | |
wives | -0.772 |
herself | -0.743 |
anova | -0.732 |
ikawa | -0.726 |
mentation | -0.709 |
Token | a |
Token ID | 257 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
llah | +1.307 |
senal | +1.292 |
ibur | +1.139 |
newcom | +1.122 |
dayName | +1.121 |
Neg logit contributions | |
wives | -1.021 |
herself | -0.973 |
anova | -0.958 |
ikawa | -0.951 |
mentation | -0.916 |
Token | middle |
Token ID | 3504 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
llah | +0.516 |
senal | +0.516 |
ibur | +0.445 |
dayName | +0.441 |
newcom | +0.440 |
Neg logit contributions | |
wives | -0.464 |
herself | -0.452 |
anova | -0.438 |
ikawa | -0.437 |
mentation | -0.420 |
Token | way |
Token ID | 835 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
wives | +0.724 |
herself | +0.705 |
anova | +0.684 |
ikawa | +0.679 |
mentation | +0.661 |
Neg logit contributions | |
llah | -0.616 |
senal | -0.613 |
ibur | -0.517 |
dayName | -0.509 |
newcom | -0.508 |
Token | between |
Token ID | 1022 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
wives | +1.604 |
herself | +1.600 |
anova | +1.501 |
ikawa | +1.473 |
mentation | +1.408 |
Neg logit contributions | |
senal | -2.267 |
llah | -2.232 |
ibur | -1.974 |
newcom | -1.958 |
dayName | -1.935 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
llah | +1.179 |
senal | +1.166 |
ibur | +1.023 |
dayName | +1.008 |
newcom | +1.008 |
Neg logit contributions | |
wives | -0.976 |
herself | -0.935 |
anova | -0.919 |
ikawa | -0.912 |
mentation | -0.879 |
Token | earliest |
Token ID | 14555 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
llah | +1.364 |
senal | +1.349 |
ibur | +1.184 |
dayName | +1.168 |
newcom | +1.167 |
Neg logit contributions | |
wives | -1.118 |
herself | -1.069 |
anova | -1.051 |
ikawa | -1.043 |
mentation | -1.005 |
Token | feminist |
Token ID | 14314 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
wives | +0.018 |
herself | +0.017 |
anova | +0.017 |
ikawa | +0.017 |
mentation | +0.016 |
Neg logit contributions | |
llah | -0.022 |
senal | -0.022 |
ibur | -0.019 |
dayName | -0.019 |
newcom | -0.019 |
Token | views |
Token ID | 5009 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
llah | +0.371 |
senal | +0.367 |
ibur | +0.321 |
dayName | +0.317 |
newcom | +0.317 |
Neg logit contributions | |
wives | -0.311 |
herself | -0.299 |
anova | -0.293 |
ikawa | -0.289 |
mentation | -0.280 |
Token | according |
Token ID | 1864 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
llah | +1.130 |
senal | +1.116 |
ibur | +0.982 |
newcom | +0.967 |
dayName | +0.965 |
Neg logit contributions | |
wives | -0.916 |
herself | -0.872 |
anova | -0.862 |
ikawa | -0.856 |
mentation | -0.825 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
senal | +0.474 |
llah | +0.470 |
newcom | +0.409 |
ibur | +0.407 |
dayName | +0.401 |
Neg logit contributions | |
wives | -0.403 |
herself | -0.389 |
anova | -0.379 |
ikawa | -0.376 |
mentation | -0.363 |
Token | which |
Token ID | 543 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
wives | +0.649 |
herself | +0.630 |
anova | +0.605 |
ikawa | +0.596 |
mentation | +0.572 |
Neg logit contributions | |
llah | -0.886 |
senal | -0.884 |
ibur | -0.778 |
dayName | -0.768 |
newcom | -0.767 |
Token | by |
Token ID | 416 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
wives | +1.116 |
herself | +1.063 |
anova | +1.039 |
ikawa | +1.032 |
mentation | +0.983 |
Neg logit contributions | |
llah | -1.744 |
senal | -1.726 |
ibur | -1.533 |
newcom | -1.520 |
dayName | -1.515 |
Token | And |
Token ID | 843 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
wives | +1.308 |
herself | +1.264 |
anova | +1.219 |
ikawa | +1.205 |
mentation | +1.169 |
Neg logit contributions | |
llah | -1.606 |
senal | -1.603 |
dayName | -1.391 |
ibur | -1.382 |
newcom | -1.381 |
Token | rey |
Token ID | 4364 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
wives | +0.675 |
herself | +0.647 |
anova | +0.642 |
ikawa | +0.636 |
mentation | +0.615 |
Neg logit contributions | |
llah | -0.728 |
senal | -0.728 |
ibur | -0.624 |
dayName | -0.621 |
newcom | -0.620 |
Token | uk |
Token ID | 2724 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
wives | +0.423 |
herself | +0.404 |
anova | +0.400 |
ikawa | +0.397 |
mentation | +0.379 |
Neg logit contributions | |
senal | -0.583 |
llah | -0.570 |
newcom | -0.508 |
ibur | -0.498 |
dayName | -0.497 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
llah | +0.852 |
senal | +0.844 |
ibur | +0.742 |
newcom | +0.734 |
dayName | +0.732 |
Neg logit contributions | |
wives | -0.659 |
herself | -0.630 |
anova | -0.617 |
ikawa | -0.614 |
mentation | -0.590 |
Token | When |
Token ID | 1649 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
llah | +0.864 |
senal | +0.855 |
ibur | +0.743 |
newcom | +0.734 |
dayName | +0.730 |
Neg logit contributions | |
wives | -0.815 |
herself | -0.780 |
anova | -0.770 |
ikawa | -0.764 |
mentation | -0.739 |
Token | an |
Token ID | 281 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
llah | +0.981 |
senal | +0.968 |
ibur | +0.829 |
newcom | +0.816 |
dayName | +0.815 |
Neg logit contributions | |
wives | -1.101 |
herself | -1.059 |
anova | -1.045 |
ikawa | -1.039 |
mentation | -1.008 |
Token | O |
Token ID | 440 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
wives | +0.627 |
herself | +0.610 |
anova | +0.606 |
ikawa | +0.594 |
mentation | +0.573 |
Neg logit contributions | |
senal | -0.726 |
llah | -0.716 |
newcom | -0.614 |
ibur | -0.614 |
dayName | -0.611 |
Token | CC |
Token ID | 4093 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
wives | +0.621 |
herself | +0.596 |
ikawa | +0.593 |
anova | +0.591 |
tarians | +0.561 |
Neg logit contributions | |
senal | -0.658 |
llah | -0.653 |
dayName | -0.568 |
newcom | -0.567 |
ibur | -0.557 |
Token | RP |
Token ID | 20031 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
llah | +3.394 |
senal | +3.317 |
ibur | +2.901 |
newcom | +2.852 |
dayName | +2.839 |
Neg logit contributions | |
wives | -3.325 |
herself | -3.136 |
anova | -3.116 |
ikawa | -3.110 |
mentation | -2.985 |
Token | reporter |
Token ID | 9095 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
llah | +3.346 |
senal | +3.290 |
ibur | +2.891 |
newcom | +2.833 |
dayName | +2.821 |
Neg logit contributions | |
wives | -2.987 |
herself | -2.839 |
anova | -2.804 |
ikawa | -2.788 |
mentation | -2.685 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
wives | +1.672 |
herself | +1.644 |
ikawa | +1.561 |
anova | +1.542 |
mentation | +1.501 |
Neg logit contributions | |
senal | -2.413 |
llah | -2.373 |
ibur | -2.093 |
dayName | -2.079 |
newcom | -2.056 |
Token | defects |
Token ID | 22448 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
wives | +0.932 |
herself | +0.890 |
anova | +0.862 |
ikawa | +0.861 |
mentation | +0.833 |
Neg logit contributions | |
senal | -1.131 |
llah | -1.111 |
ibur | -0.970 |
newcom | -0.957 |
dayName | -0.956 |
Token | caused |
Token ID | 4073 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
wives | +1.178 |
herself | +1.145 |
anova | +1.098 |
ikawa | +1.095 |
mentation | +1.056 |
Neg logit contributions | |
senal | -1.496 |
llah | -1.488 |
ibur | -1.303 |
dayName | -1.290 |
newcom | -1.290 |
Token | by |
Token ID | 416 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
wives | +2.852 |
herself | +2.726 |
anova | +2.652 |
ikawa | +2.643 |
mentation | +2.528 |
Neg logit contributions | |
llah | -4.401 |
senal | -4.355 |
ibur | -3.876 |
newcom | -3.829 |
dayName | -3.827 |
Token | the |
Token ID | 262 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
wives | +1.068 |
herself | +1.041 |
anova | +1.005 |
ikawa | +0.995 |
mentation | +0.948 |
Neg logit contributions | |
senal | -1.523 |
llah | -1.517 |
ibur | -1.335 |
dayName | -1.322 |
newcom | -1.321 |
Token | Zika |
Token ID | 30861 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
llah | +1.632 |
senal | +1.618 |
ibur | +1.439 |
newcom | +1.421 |
dayName | +1.419 |
Neg logit contributions | |
wives | -1.043 |
herself | -0.990 |
anova | -0.970 |
ikawa | -0.964 |
mentation | -0.922 |
Token | virus |
Token ID | 9471 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
wives | +0.021 |
herself | +0.020 |
anova | +0.019 |
ikawa | +0.019 |
mentation | +0.018 |
Neg logit contributions | |
llah | -0.036 |
senal | -0.036 |
ibur | -0.032 |
newcom | -0.032 |
dayName | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
wives | +1.818 |
herself | +1.772 |
anova | +1.702 |
ikawa | +1.690 |
mentation | +1.627 |
Neg logit contributions | |
llah | -2.346 |
senal | -2.344 |
ibur | -2.048 |
newcom | -2.037 |
dayName | -2.026 |
Token | Thousands |
Token ID | 30405 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
wives | +0.191 |
herself | +0.183 |
anova | +0.179 |
ikawa | +0.177 |
mentation | +0.170 |
Neg logit contributions | |
senal | -0.246 |
llah | -0.244 |
newcom | -0.215 |
ibur | -0.214 |
dayName | -0.210 |
Token | of |
Token ID | 286 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
llah | +0.594 |
senal | +0.584 |
ibur | +0.513 |
dayName | +0.505 |
newcom | +0.504 |
Neg logit contributions | |
wives | -0.519 |
herself | -0.495 |
anova | -0.490 |
ikawa | -0.487 |
mentation | -0.470 |
Token | our |
Token ID | 674 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
wives | +0.924 |
herself | +0.897 |
anova | +0.858 |
ikawa | +0.853 |
mentation | +0.815 |
Neg logit contributions | |
senal | -1.359 |
llah | -1.341 |
ibur | -1.178 |
dayName | -1.174 |
newcom | -1.171 |
Token | put |
Token ID | 1234 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
wives | +1.244 |
herself | +1.212 |
anova | +1.168 |
ikawa | +1.150 |
mentation | +1.105 |
Neg logit contributions | |
senal | -1.832 |
llah | -1.802 |
newcom | -1.606 |
dayName | -1.574 |
ibur | -1.573 |
Token | on |
Token ID | 319 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
llah | +0.604 |
senal | +0.599 |
ibur | +0.527 |
dayName | +0.523 |
newcom | +0.521 |
Neg logit contributions | |
wives | -0.460 |
herself | -0.441 |
anova | -0.432 |
ikawa | -0.426 |
mentation | -0.412 |
Token | them |
Token ID | 606 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
wives | +0.867 |
herself | +0.844 |
anova | +0.816 |
ikawa | +0.808 |
mentation | +0.781 |
Neg logit contributions | |
llah | -1.142 |
senal | -1.139 |
dayName | -1.002 |
ibur | -0.995 |
newcom | -0.982 |
Token | are |
Token ID | 389 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
wives | +0.359 |
herself | +0.346 |
anova | +0.337 |
ikawa | +0.332 |
mentation | +0.319 |
Neg logit contributions | |
senal | -0.460 |
llah | -0.458 |
newcom | -0.401 |
ibur | -0.399 |
dayName | -0.397 |
Token | really |
Token ID | 1107 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
wives | +0.220 |
herself | +0.213 |
anova | +0.208 |
ikawa | +0.205 |
mentation | +0.198 |
Neg logit contributions | |
llah | -0.265 |
senal | -0.263 |
dayName | -0.229 |
newcom | -0.228 |
ibur | -0.228 |
Token | just |
Token ID | 655 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
llah | +0.664 |
senal | +0.659 |
ibur | +0.571 |
dayName | +0.567 |
newcom | +0.566 |
Neg logit contributions | |
wives | -0.597 |
herself | -0.575 |
anova | -0.565 |
ikawa | -0.560 |
mentation | -0.540 |
Token | about |
Token ID | 546 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
wives | +1.484 |
herself | +1.459 |
anova | +1.407 |
ikawa | +1.388 |
mentation | +1.341 |
Neg logit contributions | |
llah | -1.818 |
senal | -1.801 |
dayName | -1.583 |
newcom | -1.567 |
ibur | -1.555 |
Token | mitigating |
Token ID | 47165 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
llah | +0.899 |
senal | +0.890 |
ibur | +0.773 |
dayName | +0.764 |
newcom | +0.764 |
Neg logit contributions | |
wives | -0.811 |
herself | -0.779 |
anova | -0.765 |
ikawa | -0.760 |
mentation | -0.734 |
Token | some |
Token ID | 617 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
llah | +1.373 |
senal | +1.356 |
ibur | +1.193 |
newcom | +1.176 |
dayName | +1.175 |
Neg logit contributions | |
wives | -1.108 |
herself | -1.056 |
anova | -1.041 |
ikawa | -1.033 |
mentation | -0.996 |
Token | of |
Token ID | 286 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
llah | +1.285 |
senal | +1.269 |
ibur | +1.110 |
newcom | +1.094 |
dayName | +1.093 |
Neg logit contributions | |
wives | -1.115 |
herself | -1.065 |
anova | -1.050 |
ikawa | -1.043 |
mentation | -1.006 |
Token | that |
Token ID | 326 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
wives | +1.030 |
herself | +0.992 |
anova | +0.968 |
ikawa | +0.959 |
mentation | +0.929 |
Neg logit contributions | |
llah | -1.382 |
senal | -1.368 |
dayName | -1.207 |
ibur | -1.202 |
newcom | -1.188 |
Token | Cross |
Token ID | 21544 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
wives | +0.986 |
herself | +0.933 |
anova | +0.926 |
ikawa | +0.906 |
mentation | +0.887 |
Neg logit contributions | |
senal | -1.139 |
llah | -1.118 |
newcom | -0.986 |
ibur | -0.962 |
dayName | -0.955 |
Token | - |
Token ID | 12 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
wives | +1.580 |
herself | +1.519 |
anova | +1.471 |
ikawa | +1.445 |
mentation | +1.423 |
Neg logit contributions | |
llah | -2.733 |
senal | -2.703 |
ibur | -2.409 |
dayName | -2.402 |
newcom | -2.380 |
Token | d |
Token ID | 67 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
wives | +1.486 |
herself | +1.400 |
anova | +1.373 |
ikawa | +1.345 |
mentation | +1.320 |
Neg logit contributions | |
llah | -2.547 |
senal | -2.527 |
ibur | -2.236 |
newcom | -2.228 |
dayName | -2.218 |
Token | ressing |
Token ID | 11697 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
wives | +0.319 |
herself | +0.304 |
anova | +0.299 |
ikawa | +0.296 |
mentation | +0.286 |
Neg logit contributions | |
llah | -0.450 |
senal | -0.448 |
ibur | -0.391 |
dayName | -0.390 |
newcom | -0.390 |
Token | : |
Token ID | 25 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
llah | +1.300 |
senal | +1.283 |
ibur | +1.128 |
newcom | +1.111 |
dayName | +1.110 |
Neg logit contributions | |
wives | -1.063 |
herself | -1.013 |
anova | -0.999 |
ikawa | -0.993 |
mentation | -0.956 |
Token | Cross |
Token ID | 6372 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
llah | +0.946 |
senal | +0.943 |
ibur | +0.815 |
newcom | +0.810 |
dayName | +0.805 |
Neg logit contributions | |
wives | -0.863 |
herself | -0.827 |
anova | -0.814 |
ikawa | -0.805 |
mentation | -0.782 |
Token | - |
Token ID | 12 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
wives | +1.026 |
anova | +0.970 |
herself | +0.969 |
ikawa | +0.963 |
tarians | +0.911 |
Neg logit contributions | |
llah | -1.458 |
senal | -1.440 |
ibur | -1.282 |
newcom | -1.267 |
dayName | -1.256 |
Token | d |
Token ID | 67 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
wives | +0.774 |
herself | +0.737 |
anova | +0.729 |
ikawa | +0.725 |
mentation | +0.690 |
Neg logit contributions | |
llah | -1.021 |
senal | -1.007 |
ibur | -0.894 |
dayName | -0.879 |
newcom | -0.878 |
Token | ressing |
Token ID | 11697 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
wives | +0.789 |
herself | +0.752 |
anova | +0.734 |
ikawa | +0.733 |
mentation | +0.702 |
Neg logit contributions | |
senal | -1.143 |
llah | -1.138 |
newcom | -0.995 |
ibur | -0.987 |
dayName | -0.987 |
Token | people |
Token ID | 661 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
llah | +0.549 |
senal | +0.547 |
ibur | +0.479 |
newcom | +0.474 |
dayName | +0.472 |
Neg logit contributions | |
wives | -0.424 |
herself | -0.406 |
anova | -0.398 |
ikawa | -0.393 |
mentation | -0.381 |
Token | wear |
Token ID | 5806 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
llah | +3.204 |
senal | +3.060 |
ibur | +2.795 |
dayName | +2.715 |
bedrock | +2.695 |
Neg logit contributions | |
wives | -2.692 |
ikawa | -2.531 |
anova | -2.524 |
herself | -2.515 |
mentation | -2.406 |
Token | A |
Token ID | 32 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
senal | +0.369 |
llah | +0.367 |
newcom | +0.320 |
ibur | +0.317 |
dayName | +0.313 |
Neg logit contributions | |
wives | -0.318 |
herself | -0.300 |
anova | -0.298 |
ikawa | -0.294 |
mentation | -0.285 |
Token | map |
Token ID | 3975 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
llah | +1.556 |
senal | +1.552 |
ibur | +1.355 |
dayName | +1.345 |
newcom | +1.337 |
Neg logit contributions | |
wives | -1.293 |
herself | -1.246 |
anova | -1.217 |
ikawa | -1.217 |
mentation | -1.174 |
Token | of |
Token ID | 286 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
llah | +2.232 |
senal | +2.201 |
ibur | +1.935 |
newcom | +1.904 |
dayName | +1.903 |
Neg logit contributions | |
wives | -1.865 |
herself | -1.777 |
anova | -1.754 |
ikawa | -1.742 |
mentation | -1.679 |
Token | Australia |
Token ID | 4505 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
llah | +2.151 |
senal | +2.121 |
ibur | +1.872 |
newcom | +1.846 |
dayName | +1.842 |
Neg logit contributions | |
wives | -1.673 |
herself | -1.590 |
anova | -1.569 |
ikawa | -1.558 |
mentation | -1.499 |
Token | 's |
Token ID | 338 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
llah | +3.512 |
senal | +3.460 |
ibur | +3.087 |
dayName | +3.062 |
newcom | +3.037 |
Neg logit contributions | |
wives | -2.249 |
herself | -2.098 |
anova | -2.092 |
ikawa | -2.073 |
mentation | -1.977 |
Token | states |
Token ID | 2585 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
llah | +0.418 |
senal | +0.417 |
ibur | +0.363 |
dayName | +0.358 |
newcom | +0.355 |
Neg logit contributions | |
wives | -0.358 |
herself | -0.348 |
anova | -0.336 |
ikawa | -0.334 |
mentation | -0.325 |
Token | and |
Token ID | 290 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
wives | +1.064 |
herself | +1.028 |
ikawa | +0.993 |
anova | +0.988 |
mentation | +0.951 |
Neg logit contributions | |
senal | -1.551 |
llah | -1.549 |
ibur | -1.366 |
newcom | -1.354 |
dayName | -1.334 |
Token | territories |
Token ID | 16771 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
wives | +1.590 |
herself | +1.555 |
anova | +1.495 |
ikawa | +1.488 |
mentation | +1.449 |
Neg logit contributions | |
senal | -1.843 |
llah | -1.827 |
ibur | -1.597 |
dayName | -1.577 |
newcom | -1.562 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
llah | +1.795 |
senal | +1.775 |
ibur | +1.566 |
newcom | +1.546 |
dayName | +1.541 |
Neg logit contributions | |
wives | -1.351 |
herself | -1.288 |
anova | -1.266 |
ikawa | -1.257 |
mentation | -1.209 |
Token |
|
Token ID | 198 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
llah | +1.395 |
senal | +1.343 |
ibur | +1.188 |
dayName | +1.170 |
newcom | +1.142 |
Neg logit contributions | |
wives | -1.444 |
herself | -1.380 |
anova | -1.369 |
ikawa | -1.362 |
mentation | -1.317 |
Token | Australia |
Token ID | 27429 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
senal | +0.473 |
llah | +0.471 |
newcom | +0.409 |
ibur | +0.406 |
dayName | +0.401 |
Neg logit contributions | |
wives | -0.412 |
herself | -0.389 |
anova | -0.387 |
ikawa | -0.381 |
mentation | -0.370 |
Token | eager |
Token ID | 11069 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
wives | +0.032 |
herself | +0.031 |
anova | +0.030 |
ikawa | +0.030 |
mentation | +0.029 |
Neg logit contributions | |
senal | -0.039 |
llah | -0.039 |
dayName | -0.034 |
ibur | -0.034 |
newcom | -0.033 |
Token | ness |
Token ID | 1108 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
wives | +1.383 |
herself | +1.287 |
anova | +1.225 |
mentation | +1.223 |
ikawa | +1.219 |
Neg logit contributions | |
senal | -3.556 |
llah | -3.531 |
newcom | -3.211 |
dayName | -3.197 |
ibur | -3.195 |
Token | to |
Token ID | 284 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
wives | +2.678 |
herself | +2.600 |
anova | +2.476 |
ikawa | +2.473 |
mentation | +2.404 |
Neg logit contributions | |
senal | -3.515 |
llah | -3.463 |
newcom | -3.040 |
ibur | -3.023 |
dayName | -3.013 |
Token | challenge |
Token ID | 4427 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
wives | +1.078 |
herself | +1.062 |
anova | +1.013 |
ikawa | +1.010 |
mentation | +0.972 |
Neg logit contributions | |
senal | -1.393 |
llah | -1.371 |
newcom | -1.196 |
ibur | -1.186 |
dayName | -1.176 |
Token | the |
Token ID | 262 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
wives | +0.015 |
herself | +0.014 |
anova | +0.014 |
ikawa | +0.014 |
mentation | +0.013 |
Neg logit contributions | |
llah | -0.019 |
senal | -0.019 |
ibur | -0.017 |
newcom | -0.016 |
dayName | -0.016 |
Token | dominance |
Token ID | 18648 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
wives | +0.235 |
herself | +0.229 |
anova | +0.221 |
ikawa | +0.218 |
mentation | +0.209 |
Neg logit contributions | |
llah | -0.362 |
senal | -0.361 |
ibur | -0.318 |
newcom | -0.318 |
dayName | -0.316 |
Token | of |
Token ID | 286 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
wives | +0.800 |
herself | +0.765 |
anova | +0.761 |
ikawa | +0.758 |
mentation | +0.731 |
Neg logit contributions | |
llah | -0.855 |
senal | -0.850 |
ibur | -0.740 |
newcom | -0.729 |
dayName | -0.725 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
wives | +0.138 |
herself | +0.134 |
anova | +0.130 |
ikawa | +0.128 |
mentation | +0.124 |
Neg logit contributions | |
llah | -0.172 |
senal | -0.170 |
ibur | -0.149 |
dayName | -0.148 |
newcom | -0.148 |
Token | United |
Token ID | 1578 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
llah | +0.015 |
senal | +0.015 |
ibur | +0.014 |
dayName | +0.014 |
newcom | +0.014 |
Neg logit contributions | |
wives | -0.009 |
herself | -0.009 |
anova | -0.008 |
ikawa | -0.008 |
mentation | -0.008 |
Token | States |
Token ID | 1829 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
wives | +1.153 |
herself | +1.073 |
anova | +1.037 |
ikawa | +0.990 |
mentation | +0.952 |
Neg logit contributions | |
senal | -3.659 |
llah | -3.474 |
newcom | -3.344 |
ibur | -3.134 |
dayName | -3.127 |
Token | . |
Token ID | 13 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
wives | +2.037 |
herself | +2.012 |
ikawa | +1.887 |
anova | +1.879 |
mentation | +1.793 |
Neg logit contributions | |
llah | -3.081 |
senal | -3.079 |
newcom | -2.704 |
dayName | -2.698 |
ibur | -2.667 |
Token | reement |
Token ID | 10237 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
wives | +1.468 |
herself | +1.373 |
ikawa | +1.354 |
anova | +1.352 |
mentation | +1.327 |
Neg logit contributions | |
senal | -2.335 |
llah | -2.300 |
newcom | -2.041 |
ibur | -2.040 |
dayName | -2.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
wives | +2.823 |
herself | +2.759 |
anova | +2.634 |
ikawa | +2.613 |
mentation | +2.540 |
Neg logit contributions | |
senal | -4.308 |
llah | -4.109 |
ibur | -3.741 |
newcom | -3.714 |
dayName | -3.664 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
wives | +0.948 |
herself | +0.908 |
anova | +0.890 |
ikawa | +0.877 |
mentation | +0.847 |
Neg logit contributions | |
senal | -1.403 |
llah | -1.392 |
ibur | -1.233 |
dayName | -1.226 |
newcom | -1.213 |
Token | some |
Token ID | 617 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
wives | +0.837 |
herself | +0.809 |
anova | +0.795 |
ikawa | +0.782 |
mentation | +0.759 |
Neg logit contributions | |
senal | -0.995 |
llah | -0.992 |
ibur | -0.870 |
newcom | -0.850 |
dayName | -0.847 |
Token | cases |
Token ID | 2663 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
llah | +2.317 |
senal | +2.258 |
ibur | +1.949 |
dayName | +1.913 |
newcom | +1.912 |
Neg logit contributions | |
wives | -2.643 |
herself | -2.529 |
anova | -2.506 |
ikawa | -2.499 |
mentation | -2.427 |
Token | they |
Token ID | 484 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
wives | +0.626 |
herself | +0.600 |
anova | +0.592 |
ikawa | +0.584 |
mentation | +0.559 |
Neg logit contributions | |
senal | -0.843 |
llah | -0.839 |
ibur | -0.739 |
dayName | -0.733 |
newcom | -0.729 |
Token | seemed |
Token ID | 3947 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
wives | +0.223 |
herself | +0.217 |
anova | +0.212 |
ikawa | +0.210 |
mentation | +0.203 |
Neg logit contributions | |
senal | -0.268 |
llah | -0.264 |
newcom | -0.231 |
ibur | -0.229 |
dayName | -0.226 |
Token | to |
Token ID | 284 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
llah | +1.672 |
senal | +1.629 |
ibur | +1.427 |
dayName | +1.403 |
newcom | +1.398 |
Neg logit contributions | |
wives | -1.608 |
herself | -1.518 |
anova | -1.516 |
ikawa | -1.506 |
mentation | -1.454 |
Token | reflect |
Token ID | 4079 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
llah | +0.929 |
senal | +0.924 |
ibur | +0.807 |
newcom | +0.798 |
dayName | +0.794 |
Neg logit contributions | |
wives | -0.764 |
herself | -0.732 |
anova | -0.719 |
ikawa | -0.714 |
mentation | -0.688 |
Token | alternate |
Token ID | 13527 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
llah | +1.047 |
senal | +1.036 |
ibur | +0.903 |
newcom | +0.890 |
dayName | +0.889 |
Neg logit contributions | |
wives | -0.946 |
herself | -0.906 |
anova | -0.892 |
ikawa | -0.886 |
mentation | -0.857 |
Token | interpretations |
Token ID | 26146 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
wives | +1.408 |
herself | +1.362 |
anova | +1.309 |
ikawa | +1.308 |
mentation | +1.269 |
Neg logit contributions | |
senal | -1.817 |
llah | -1.782 |
ibur | -1.560 |
newcom | -1.556 |
dayName | -1.540 |
Token | work |
Token ID | 670 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
llah | +0.766 |
senal | +0.757 |
ibur | +0.670 |
dayName | +0.661 |
newcom | +0.659 |
Neg logit contributions | |
wives | -0.548 |
herself | -0.522 |
anova | -0.512 |
ikawa | -0.509 |
mentation | -0.489 |
Token | based |
Token ID | 1912 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
llah | +0.429 |
senal | +0.424 |
ibur | +0.373 |
newcom | +0.368 |
dayName | +0.367 |
Neg logit contributions | |
wives | -0.342 |
herself | -0.326 |
anova | -0.321 |
ikawa | -0.319 |
mentation | -0.307 |
Token | on |
Token ID | 319 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
wives | +0.333 |
herself | +0.318 |
anova | +0.316 |
ikawa | +0.313 |
mentation | +0.304 |
Neg logit contributions | |
llah | -0.301 |
senal | -0.297 |
ibur | -0.253 |
newcom | -0.252 |
dayName | -0.250 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
wives | +0.662 |
herself | +0.635 |
anova | +0.620 |
ikawa | +0.616 |
mentation | +0.590 |
Neg logit contributions | |
llah | -0.867 |
senal | -0.858 |
ibur | -0.758 |
dayName | -0.745 |
newcom | -0.743 |
Token | M |
Token ID | 337 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
llah | +0.219 |
senal | +0.218 |
ibur | +0.192 |
dayName | +0.189 |
newcom | +0.188 |
Neg logit contributions | |
wives | -0.169 |
herself | -0.161 |
anova | -0.158 |
ikawa | -0.157 |
mentation | -0.151 |
Token | oom |
Token ID | 4207 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
wives | +0.694 |
herself | +0.666 |
anova | +0.655 |
ikawa | +0.649 |
mentation | +0.630 |
Neg logit contributions | |
llah | -0.710 |
senal | -0.695 |
ibur | -0.608 |
newcom | -0.597 |
dayName | -0.595 |
Token | in |
Token ID | 259 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
wives | +4.670 |
herself | +4.426 |
anova | +4.407 |
ikawa | +4.330 |
mentation | +4.102 |
Neg logit contributions | |
senal | -7.370 |
llah | -7.363 |
ibur | -6.473 |
dayName | -6.460 |
newcom | -6.447 |
Token | compositions |
Token ID | 33543 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
wives | +0.489 |
herself | +0.466 |
anova | +0.457 |
ikawa | +0.452 |
mentation | +0.433 |
Neg logit contributions | |
llah | -0.710 |
senal | -0.701 |
ibur | -0.622 |
dayName | -0.617 |
newcom | -0.615 |
Token | of |
Token ID | 286 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
wives | +0.169 |
herself | +0.162 |
anova | +0.159 |
ikawa | +0.158 |
mentation | +0.152 |
Neg logit contributions | |
llah | -0.218 |
senal | -0.215 |
ibur | -0.190 |
newcom | -0.187 |
dayName | -0.187 |
Token | composer |
Token ID | 26777 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
wives | +1.318 |
herself | +1.280 |
anova | +1.233 |
ikawa | +1.222 |
mentation | +1.181 |
Neg logit contributions | |
llah | -1.624 |
senal | -1.615 |
ibur | -1.423 |
dayName | -1.405 |
newcom | -1.393 |
Token | and |
Token ID | 290 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
wives | +0.994 |
herself | +0.965 |
anova | +0.932 |
ikawa | +0.927 |
mentation | +0.893 |
Neg logit contributions | |
senal | -1.225 |
llah | -1.222 |
ibur | -1.067 |
newcom | -1.061 |
dayName | -1.057 |
Token | Fund |
Token ID | 7557 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
wives | +0.020 |
herself | +0.019 |
anova | +0.018 |
ikawa | +0.018 |
mentation | +0.018 |
Neg logit contributions | |
llah | -0.029 |
senal | -0.029 |
ibur | -0.025 |
newcom | -0.025 |
dayName | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
wives | +2.628 |
herself | +2.600 |
anova | +2.501 |
ikawa | +2.427 |
mentation | +2.383 |
Neg logit contributions | |
senal | -3.527 |
llah | -3.486 |
newcom | -3.030 |
dayName | -3.010 |
ibur | -2.991 |
Token | a |
Token ID | 257 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
wives | +0.498 |
herself | +0.478 |
anova | +0.469 |
ikawa | +0.461 |
mentation | +0.448 |
Neg logit contributions | |
llah | -0.627 |
senal | -0.620 |
ibur | -0.543 |
dayName | -0.538 |
newcom | -0.537 |
Token | political |
Token ID | 1964 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
wives | +1.646 |
herself | +1.614 |
anova | +1.553 |
ikawa | +1.537 |
mentation | +1.495 |
Neg logit contributions | |
llah | -2.076 |
senal | -2.071 |
dayName | -1.801 |
ibur | -1.775 |
newcom | -1.757 |
Token | action |
Token ID | 2223 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
llah | +0.003 |
senal | +0.003 |
ibur | +0.003 |
dayName | +0.003 |
newcom | +0.003 |
Neg logit contributions | |
wives | -0.003 |
herself | -0.003 |
anova | -0.003 |
ikawa | -0.003 |
mentation | -0.003 |
Token | committee |
Token ID | 5583 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
wives | +1.423 |
herself | +1.420 |
anova | +1.330 |
ikawa | +1.305 |
mentation | +1.286 |
Neg logit contributions | |
llah | -3.188 |
senal | -3.177 |
ibur | -2.819 |
dayName | -2.794 |
newcom | -2.748 |
Token | dedicated |
Token ID | 7256 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
wives | +3.979 |
herself | +3.976 |
anova | +3.773 |
mentation | +3.634 |
ikawa | +3.614 |
Neg logit contributions | |
senal | -5.706 |
llah | -5.645 |
dayName | -4.932 |
newcom | -4.832 |
ibur | -4.806 |
Token | to |
Token ID | 284 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
wives | +1.897 |
herself | +1.804 |
anova | +1.792 |
ikawa | +1.781 |
mentation | +1.714 |
Neg logit contributions | |
llah | -2.043 |
senal | -2.021 |
ibur | -1.763 |
newcom | -1.734 |
dayName | -1.731 |
Token | defending |
Token ID | 11749 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
wives | +2.263 |
herself | +2.214 |
anova | +2.108 |
ikawa | +2.098 |
mentation | +2.038 |
Neg logit contributions | |
senal | -2.750 |
llah | -2.747 |
dayName | -2.364 |
ibur | -2.338 |
newcom | -2.320 |
Token | House |
Token ID | 2097 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
wives | +0.403 |
herself | +0.389 |
anova | +0.375 |
ikawa | +0.371 |
mentation | +0.357 |
Neg logit contributions | |
llah | -0.567 |
senal | -0.566 |
ibur | -0.492 |
dayName | -0.492 |
newcom | -0.489 |
Token | Republicans |
Token ID | 4734 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
wives | +0.160 |
herself | +0.146 |
anova | +0.141 |
ikawa | +0.138 |
mentation | +0.131 |
Neg logit contributions | |
llah | -0.376 |
senal | -0.375 |
ibur | -0.333 |
dayName | -0.332 |
newcom | -0.332 |
Token | I |
Token ID | 314 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
llah | +0.098 |
senal | +0.098 |
dayName | +0.085 |
ibur | +0.085 |
newcom | +0.084 |
Neg logit contributions | |
wives | -0.073 |
herself | -0.070 |
anova | -0.069 |
ikawa | -0.068 |
mentation | -0.066 |
Token | shared |
Token ID | 4888 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
senal | +0.359 |
llah | +0.355 |
newcom | +0.308 |
ibur | +0.306 |
dayName | +0.302 |
Neg logit contributions | |
wives | -0.300 |
herself | -0.293 |
anova | -0.282 |
ikawa | -0.281 |
mentation | -0.272 |
Token | this |
Token ID | 428 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
llah | +0.683 |
senal | +0.676 |
ibur | +0.592 |
newcom | +0.584 |
dayName | +0.583 |
Neg logit contributions | |
wives | -0.566 |
herself | -0.541 |
anova | -0.532 |
ikawa | -0.528 |
mentation | -0.509 |
Token | perspective |
Token ID | 6650 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
wives | +0.795 |
herself | +0.779 |
anova | +0.752 |
ikawa | +0.747 |
mentation | +0.719 |
Neg logit contributions | |
senal | -1.013 |
llah | -1.010 |
ibur | -0.872 |
newcom | -0.871 |
dayName | -0.871 |
Token | with |
Token ID | 351 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
wives | +0.892 |
herself | +0.867 |
anova | +0.831 |
ikawa | +0.823 |
mentation | +0.793 |
Neg logit contributions | |
senal | -1.196 |
llah | -1.190 |
ibur | -1.044 |
newcom | -1.038 |
dayName | -1.026 |
Token | Gary |
Token ID | 10936 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
wives | +1.332 |
herself | +1.290 |
anova | +1.244 |
ikawa | +1.221 |
mentation | +1.198 |
Neg logit contributions | |
llah | -1.658 |
senal | -1.658 |
dayName | -1.439 |
ibur | -1.427 |
newcom | -1.420 |
Token | during |
Token ID | 1141 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
herself | +4.283 |
wives | +4.281 |
anova | +4.055 |
ikawa | +4.008 |
tarians | +3.852 |
Neg logit contributions | |
llah | -5.263 |
senal | -5.261 |
ibur | -4.624 |
dayName | -4.605 |
newcom | -4.529 |
Token | our |
Token ID | 674 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
wives | +1.975 |
herself | +1.924 |
anova | +1.853 |
ikawa | +1.833 |
mentation | +1.794 |
Neg logit contributions | |
senal | -2.768 |
llah | -2.767 |
dayName | -2.394 |
ibur | -2.390 |
newcom | -2.381 |
Token | interview |
Token ID | 2720 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
wives | +1.913 |
herself | +1.864 |
anova | +1.795 |
ikawa | +1.773 |
mentation | +1.743 |
Neg logit contributions | |
llah | -2.445 |
senal | -2.443 |
dayName | -2.094 |
ibur | -2.090 |
newcom | -2.083 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
wives | +2.426 |
herself | +2.329 |
anova | +2.262 |
ikawa | +2.219 |
mentation | +2.158 |
Neg logit contributions | |
senal | -3.411 |
llah | -3.408 |
ibur | -2.984 |
dayName | -2.974 |
newcom | -2.957 |
Token | he |
Token ID | 339 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
wives | +1.574 |
herself | +1.511 |
anova | +1.451 |
ikawa | +1.436 |
mentation | +1.418 |
Neg logit contributions | |
senal | -2.534 |
llah | -2.526 |
dayName | -2.247 |
ibur | -2.238 |
newcom | -2.206 |
Token | road |
Token ID | 2975 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
wives | +0.929 |
herself | +0.905 |
ikawa | +0.865 |
anova | +0.857 |
mentation | +0.840 |
Neg logit contributions | |
senal | -1.100 |
llah | -1.086 |
ibur | -0.939 |
dayName | -0.934 |
newcom | -0.924 |
Token | ! |
Token ID | 0 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
wives | +1.074 |
herself | +1.039 |
anova | +0.998 |
ikawa | +0.995 |
mentation | +0.960 |
Neg logit contributions | |
senal | -1.434 |
llah | -1.426 |
ibur | -1.242 |
newcom | -1.237 |
dayName | -1.230 |
Token |
|
Token ID | 198 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
llah | +0.334 |
senal | +0.330 |
ibur | +0.287 |
newcom | +0.283 |
dayName | +0.282 |
Neg logit contributions | |
wives | -0.318 |
herself | -0.305 |
anova | -0.301 |
ikawa | -0.299 |
mentation | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
senal | +0.193 |
llah | +0.189 |
newcom | +0.166 |
ibur | +0.162 |
dayName | +0.159 |
Neg logit contributions | |
wives | -0.177 |
herself | -0.170 |
anova | -0.167 |
ikawa | -0.166 |
mentation | -0.160 |
Token | F |
Token ID | 37 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
wives | +0.706 |
herself | +0.670 |
anova | +0.663 |
ikawa | +0.656 |
mentation | +0.638 |
Neg logit contributions | |
senal | -0.789 |
llah | -0.787 |
newcom | -0.684 |
ibur | -0.669 |
dayName | -0.659 |
Token | ully |
Token ID | 2132 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
llah | +0.714 |
senal | +0.707 |
ibur | +0.617 |
dayName | +0.612 |
newcom | +0.611 |
Neg logit contributions | |
wives | -0.585 |
herself | -0.558 |
anova | -0.552 |
ikawa | -0.548 |
mentation | -0.529 |
Token | detailed |
Token ID | 6496 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
wives | +4.332 |
herself | +4.327 |
anova | +4.187 |
mentation | +4.089 |
ikawa | +4.086 |
Neg logit contributions | |
llah | -5.343 |
senal | -5.296 |
dayName | -4.652 |
ibur | -4.591 |
newcom | -4.526 |
Token | - |
Token ID | 532 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
wives | +2.723 |
herself | +2.697 |
ikawa | +2.561 |
anova | +2.524 |
mentation | +2.485 |
Neg logit contributions | |
llah | -3.373 |
senal | -3.353 |
dayName | -2.907 |
newcom | -2.889 |
ibur | -2.860 |
Token | All |
Token ID | 1439 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
wives | +0.119 |
herself | +0.115 |
anova | +0.113 |
ikawa | +0.111 |
mentation | +0.108 |
Neg logit contributions | |
llah | -0.146 |
senal | -0.144 |
ibur | -0.126 |
dayName | -0.124 |
newcom | -0.124 |
Token | vehicles |
Token ID | 5672 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
llah | +0.113 |
senal | +0.112 |
ibur | +0.097 |
dayName | +0.096 |
newcom | +0.096 |
Neg logit contributions | |
wives | -0.102 |
herself | -0.099 |
anova | -0.096 |
ikawa | -0.096 |
mentation | -0.093 |
Token | have |
Token ID | 423 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
llah | +0.098 |
senal | +0.098 |
ibur | +0.086 |
newcom | +0.085 |
dayName | +0.084 |
Neg logit contributions | |
wives | -0.077 |
herself | -0.074 |
anova | -0.072 |
ikawa | -0.072 |
mentation | -0.069 |
Token | break |
Token ID | 2270 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
wives | +0.747 |
herself | +0.731 |
anova | +0.701 |
ikawa | +0.700 |
mentation | +0.671 |
Neg logit contributions | |
llah | -0.998 |
senal | -0.988 |
ibur | -0.863 |
dayName | -0.855 |
newcom | -0.847 |
Token | d |
Token ID | 67 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
wives | +1.014 |
herself | +0.981 |
anova | +0.949 |
ikawa | +0.942 |
mentation | +0.917 |
Neg logit contributions | |
senal | -1.428 |
llah | -1.425 |
ibur | -1.251 |
newcom | -1.245 |
dayName | -1.243 |
Token | ancing |
Token ID | 5077 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
llah | +0.575 |
senal | +0.569 |
ibur | +0.513 |
newcom | +0.507 |
dayName | +0.506 |
Neg logit contributions | |
wives | -0.282 |
herself | -0.264 |
anova | -0.259 |
ikawa | -0.257 |
mentation | -0.244 |
Token | , |
Token ID | 11 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
llah | +0.599 |
senal | +0.595 |
ibur | +0.520 |
newcom | +0.516 |
dayName | +0.513 |
Neg logit contributions | |
wives | -0.476 |
herself | -0.459 |
ikawa | -0.443 |
anova | -0.443 |
mentation | -0.426 |
Token | although |
Token ID | 3584 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
wives | +0.056 |
herself | +0.054 |
anova | +0.053 |
ikawa | +0.052 |
mentation | +0.050 |
Neg logit contributions | |
llah | -0.075 |
senal | -0.074 |
ibur | -0.065 |
newcom | -0.064 |
dayName | -0.064 |
Token | Night |
Token ID | 5265 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
wives | +1.601 |
herself | +1.573 |
ikawa | +1.508 |
anova | +1.502 |
mentation | +1.448 |
Neg logit contributions | |
llah | -2.116 |
senal | -2.087 |
ibur | -1.820 |
dayName | -1.816 |
newcom | -1.800 |
Token | c |
Token ID | 66 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
wives | +4.241 |
herself | +4.086 |
anova | +3.860 |
ikawa | +3.824 |
mentation | +3.635 |
Neg logit contributions | |
senal | -7.449 |
llah | -6.826 |
newcom | -6.596 |
bedrock | -5.978 |
dayName | -5.955 |
Token | rawler |
Token ID | 39464 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
wives | +1.994 |
herself | +1.964 |
anova | +1.910 |
ikawa | +1.907 |
mentation | +1.832 |
Neg logit contributions | |
senal | -1.880 |
llah | -1.797 |
newcom | -1.560 |
dayName | -1.488 |
ibur | -1.470 |
Token | � |
Token ID | 447 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
herself | +1.798 |
wives | +1.790 |
ikawa | +1.675 |
anova | +1.671 |
mentation | +1.595 |
Neg logit contributions | |
senal | -2.407 |
llah | -2.352 |
newcom | -2.083 |
dayName | -2.041 |
ibur | -2.029 |
Token | � |
Token ID | 247 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
wives | +0.600 |
herself | +0.589 |
anova | +0.578 |
ikawa | +0.567 |
mentation | +0.559 |
Neg logit contributions | |
senal | -0.476 |
llah | -0.471 |
newcom | -0.401 |
ibur | -0.396 |
dayName | -0.389 |
Token | s |
Token ID | 82 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
wives | +0.465 |
herself | +0.450 |
anova | +0.434 |
ikawa | +0.429 |
mentation | +0.413 |
Neg logit contributions | |
senal | -0.760 |
llah | -0.759 |
newcom | -0.672 |
ibur | -0.668 |
dayName | -0.662 |