Token | through |
Token ID | 832 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
soever | +2.111 |
adversary | +2.049 |
�� | +1.962 |
achine | +1.908 |
anooga | +1.840 |
Neg logit contributions | |
uid | -2.973 |
女 | -2.709 |
quote | -2.598 |
í | -2.489 |
Ladies | -2.406 |
Token | the |
Token ID | 262 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
uid | +1.714 |
女 | +1.531 |
quote | +1.473 |
í | +1.452 |
Ladies | +1.391 |
Neg logit contributions | |
soever | -1.352 |
adversary | -1.302 |
�� | -1.280 |
achine | -1.239 |
anooga | -1.203 |
Token | alleged |
Token ID | 4260 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
uid | +0.042 |
女 | +0.038 |
quote | +0.036 |
í | +0.035 |
Ladies | +0.034 |
Neg logit contributions | |
soever | -0.034 |
adversary | -0.034 |
�� | -0.032 |
achine | -0.031 |
Canaver | -0.031 |
Token | victim |
Token ID | 3117 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
soever | +2.256 |
adversary | +2.253 |
�� | +2.104 |
achine | +2.004 |
Canaver | +1.971 |
Neg logit contributions | |
uid | -3.203 |
女 | -2.930 |
quote | -2.755 |
í | -2.683 |
Ladies | -2.572 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
uid | +0.401 |
女 | +0.358 |
quote | +0.343 |
í | +0.341 |
Ladies | +0.322 |
Neg logit contributions | |
soever | -0.346 |
adversary | -0.334 |
�� | -0.329 |
achine | -0.320 |
Canaver | -0.311 |
Token | lured |
Token ID | 41546 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
soever | +2.086 |
adversary | +2.037 |
�� | +1.914 |
achine | +1.887 |
anooga | +1.841 |
Neg logit contributions | |
uid | -2.765 |
女 | -2.486 |
quote | -2.381 |
í | -2.293 |
Ladies | -2.211 |
Token | Mark |
Token ID | 2940 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
soever | +7.823 |
adversary | +7.638 |
intruder | +6.957 |
�� | +6.894 |
achine | +6.824 |
Neg logit contributions | |
uid | -11.099 |
女 | -10.214 |
quote | -9.622 |
united | -9.263 |
í | -9.192 |
Token | over |
Token ID | 625 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
soever | +3.320 |
adversary | +3.168 |
�� | +3.079 |
achine | +3.016 |
anooga | +2.899 |
Neg logit contributions | |
uid | -5.057 |
女 | -4.609 |
quote | -4.419 |
í | -4.288 |
Ladies | -4.165 |
Token | to |
Token ID | 284 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
soever | +0.833 |
adversary | +0.804 |
�� | +0.790 |
achine | +0.763 |
Canaver | +0.741 |
Neg logit contributions | |
uid | -1.031 |
女 | -0.920 |
quote | -0.885 |
í | -0.872 |
Ladies | -0.835 |
Token | a |
Token ID | 257 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
soever | +1.357 |
adversary | +1.321 |
�� | +1.283 |
achine | +1.250 |
Canaver | +1.207 |
Neg logit contributions | |
uid | -1.756 |
女 | -1.580 |
quote | -1.512 |
í | -1.480 |
Ladies | -1.420 |
Token | house |
Token ID | 2156 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
soever | +1.087 |
adversary | +1.070 |
�� | +1.025 |
achine | +0.992 |
anooga | +0.968 |
Neg logit contributions | |
uid | -1.566 |
女 | -1.419 |
quote | -1.348 |
í | -1.325 |
Ladies | -1.263 |
Token | least |
Token ID | 1551 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
adversary | +0.885 |
soever | +0.876 |
�� | +0.752 |
achine | +0.716 |
Canaver | +0.649 |
Neg logit contributions | |
uid | -3.643 |
女 | -3.361 |
quote | -3.230 |
í | -3.166 |
united | -3.088 |
Token | . |
Token ID | 13 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
soever | +3.769 |
adversary | +3.648 |
�� | +3.581 |
achine | +3.466 |
Canaver | +3.352 |
Neg logit contributions | |
uid | -4.647 |
女 | -4.156 |
quote | -3.980 |
í | -3.890 |
Ladies | -3.737 |
Token | � |
Token ID | 564 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
uid | +2.142 |
女 | +1.881 |
quote | +1.791 |
í | +1.784 |
Ladies | +1.696 |
Neg logit contributions | |
soever | -2.350 |
adversary | -2.317 |
�� | -2.265 |
achine | -2.193 |
anooga | -2.158 |
Token | � |
Token ID | 250 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
uid | +2.336 |
女 | +2.062 |
quote | +1.969 |
í | +1.923 |
Ladies | +1.839 |
Neg logit contributions | |
soever | -2.356 |
adversary | -2.289 |
�� | -2.252 |
achine | -2.180 |
anooga | -2.126 |
Token | Some |
Token ID | 4366 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
uid | +1.228 |
女 | +1.098 |
quote | +1.053 |
í | +1.035 |
Ladies | +0.989 |
Neg logit contributions | |
soever | -1.020 |
adversary | -0.989 |
�� | -0.967 |
achine | -0.938 |
anooga | -0.910 |
Token | implanted |
Token ID | 40740 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
soever | +1.926 |
adversary | +1.875 |
�� | +1.811 |
achine | +1.749 |
Canaver | +1.734 |
Neg logit contributions | |
uid | -2.713 |
女 | -2.459 |
quote | -2.351 |
í | -2.288 |
Ladies | -2.221 |
Token | devices |
Token ID | 4410 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
soever | +8.127 |
adversary | +7.759 |
Canaver | +7.348 |
�� | +7.198 |
decomp | +7.050 |
Neg logit contributions | |
uid | -10.641 |
女 | -9.798 |
quote | -9.404 |
united | -8.784 |
í | -8.728 |
Token | can |
Token ID | 460 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
soever | +3.826 |
adversary | +3.685 |
achine | +3.446 |
Canaver | +3.358 |
�� | +3.327 |
Neg logit contributions | |
uid | -5.810 |
女 | -5.406 |
quote | -5.104 |
united | -4.845 |
Ladies | -4.814 |
Token | work |
Token ID | 670 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
soever | +1.851 |
adversary | +1.823 |
�� | +1.746 |
achine | +1.728 |
anooga | +1.643 |
Neg logit contributions | |
uid | -2.707 |
女 | -2.443 |
quote | -2.356 |
í | -2.262 |
Ladies | -2.240 |
Token | very |
Token ID | 845 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
soever | +0.011 |
adversary | +0.010 |
�� | +0.010 |
achine | +0.010 |
anooga | +0.009 |
Neg logit contributions | |
uid | -0.014 |
女 | -0.013 |
quote | -0.012 |
í | -0.012 |
Ladies | -0.012 |
Token | well |
Token ID | 880 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
soever | +1.852 |
adversary | +1.772 |
�� | +1.689 |
achine | +1.657 |
Canaver | +1.589 |
Neg logit contributions | |
uid | -3.233 |
女 | -2.934 |
quote | -2.831 |
í | -2.760 |
Ladies | -2.677 |
Token | on |
Token ID | 319 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
soever | +1.773 |
adversary | +1.714 |
�� | +1.666 |
achine | +1.618 |
Canaver | +1.564 |
Neg logit contributions | |
uid | -2.217 |
女 | -1.983 |
quote | -1.904 |
í | -1.848 |
Ladies | -1.772 |
Token | May |
Token ID | 1737 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
soever | +0.833 |
adversary | +0.811 |
�� | +0.788 |
achine | +0.766 |
Canaver | +0.744 |
Neg logit contributions | |
uid | -0.945 |
女 | -0.843 |
quote | -0.803 |
í | -0.789 |
Ladies | -0.749 |
Token | 25 |
Token ID | 1679 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
soever | +1.756 |
adversary | +1.655 |
achine | +1.519 |
Canaver | +1.517 |
�� | +1.488 |
Neg logit contributions | |
uid | -3.118 |
女 | -2.851 |
quote | -2.679 |
í | -2.588 |
united | -2.579 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
uid | +1.219 |
女 | +1.085 |
quote | +1.032 |
í | +1.029 |
Ladies | +0.971 |
Neg logit contributions | |
soever | -1.154 |
adversary | -1.113 |
�� | -1.092 |
achine | -1.061 |
Canaver | -1.039 |
Token | ( |
Token ID | 357 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
soever | +1.687 |
adversary | +1.635 |
�� | +1.602 |
achine | +1.564 |
Canaver | +1.522 |
Neg logit contributions | |
uid | -1.648 |
女 | -1.451 |
quote | -1.381 |
í | -1.349 |
Ladies | -1.283 |
Token | John |
Token ID | 7554 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
soever | +1.926 |
adversary | +1.860 |
�� | +1.819 |
achine | +1.760 |
anooga | +1.705 |
Neg logit contributions | |
uid | -2.574 |
女 | -2.313 |
quote | -2.221 |
í | -2.185 |
Ladies | -2.096 |
Token | McDonnell |
Token ID | 39441 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
adversary | +1.415 |
Canaver | +1.311 |
soever | +1.283 |
achine | +1.109 |
McDonnell | +0.965 |
Neg logit contributions | |
uid | -16.478 |
女 | -15.361 |
quote | -14.596 |
united | -14.239 |
nown | -14.093 |
Token | / |
Token ID | 14 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
soever | +1.829 |
adversary | +1.689 |
achine | +1.611 |
Canaver | +1.599 |
�� | +1.562 |
Neg logit contributions | |
uid | -2.920 |
女 | -2.669 |
quote | -2.502 |
í | -2.419 |
united | -2.397 |
Token | The |
Token ID | 464 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
soever | +1.342 |
adversary | +1.270 |
�� | +1.214 |
achine | +1.196 |
anooga | +1.158 |
Neg logit contributions | |
uid | -2.074 |
女 | -1.852 |
quote | -1.760 |
í | -1.745 |
Ladies | -1.729 |
Token | Washington |
Token ID | 2669 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
soever | +1.827 |
adversary | +1.791 |
achine | +1.609 |
�� | +1.594 |
anooga | +1.580 |
Neg logit contributions | |
uid | -3.343 |
女 | -3.058 |
quote | -2.849 |
í | -2.781 |
ú | -2.672 |
Token | Post |
Token ID | 2947 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
soever | +2.379 |
adversary | +2.299 |
Canaver | +2.087 |
achine | +2.064 |
weakness | +2.004 |
Neg logit contributions | |
uid | -4.367 |
女 | -3.994 |
quote | -3.653 |
í | -3.589 |
united | -3.514 |
Token | by |
Token ID | 416 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
soever | +1.041 |
adversary | +1.006 |
�� | +0.977 |
achine | +0.955 |
Canaver | +0.922 |
Neg logit contributions | |
uid | -1.402 |
女 | -1.264 |
quote | -1.216 |
í | -1.200 |
Ladies | -1.144 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
soever | +1.315 |
adversary | +1.274 |
�� | +1.245 |
achine | +1.205 |
anooga | +1.169 |
Neg logit contributions | |
uid | -1.741 |
女 | -1.562 |
quote | -1.503 |
í | -1.480 |
Ladies | -1.418 |
Token | / |
Token ID | 14 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
soever | +2.508 |
adversary | +2.430 |
�� | +2.375 |
achine | +2.297 |
anooga | +2.242 |
Neg logit contributions | |
uid | -3.162 |
女 | -2.832 |
quote | -2.727 |
í | -2.675 |
Ladies | -2.568 |
Token | John |
Token ID | 7554 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
soever | +1.925 |
adversary | +1.838 |
�� | +1.811 |
achine | +1.744 |
anooga | +1.683 |
Neg logit contributions | |
uid | -2.857 |
女 | -2.581 |
quote | -2.471 |
í | -2.435 |
Ladies | -2.354 |
Token | S |
Token ID | 311 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
soever | +6.795 |
�� | +6.403 |
Canaver | +6.303 |
adversary | +6.280 |
achine | +6.219 |
Neg logit contributions | |
uid | -7.948 |
女 | -7.423 |
quote | -6.910 |
í | -6.421 |
united | -6.398 |
Token | omm |
Token ID | 2002 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
soever | +0.808 |
adversary | +0.791 |
�� | +0.779 |
achine | +0.764 |
anooga | +0.750 |
Neg logit contributions | |
uid | -0.385 |
女 | -0.314 |
quote | -0.291 |
í | -0.282 |
Ladies | -0.257 |
Token | ers |
Token ID | 364 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
soever | +6.102 |
achine | +5.701 |
adversary | +5.515 |
anooga | +5.189 |
�� | +4.944 |
Neg logit contributions | |
uid | -11.649 |
女 | -10.755 |
quote | -10.375 |
united | -10.190 |
Ladies | -9.784 |
Token | II |
Token ID | 2873 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
soever | +1.239 |
adversary | +1.211 |
�� | +1.174 |
achine | +1.123 |
anooga | +1.098 |
Neg logit contributions | |
uid | -1.982 |
女 | -1.788 |
quote | -1.726 |
í | -1.708 |
Ladies | -1.643 |
Token | ) |
Token ID | 8 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
soever | +3.099 |
adversary | +2.988 |
�� | +2.919 |
achine | +2.820 |
anooga | +2.726 |
Neg logit contributions | |
uid | -4.488 |
女 | -4.048 |
quote | -3.893 |
í | -3.832 |
Ladies | -3.681 |
Token | Ivanka |
Token ID | 31002 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
uid | +0.825 |
女 | +0.731 |
quote | +0.699 |
í | +0.686 |
Ladies | +0.654 |
Neg logit contributions | |
soever | -0.801 |
adversary | -0.778 |
�� | -0.764 |
achine | -0.742 |
anooga | -0.722 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
uid | +3.678 |
女 | +3.337 |
í | +3.304 |
quote | +3.257 |
Ladies | +3.162 |
Neg logit contributions | |
soever | -3.346 |
�� | -3.270 |
adversary | -3.268 |
achine | -3.184 |
anooga | -3.113 |
Token | that |
Token ID | 326 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
uid | +1.511 |
女 | +1.348 |
quote | +1.291 |
í | +1.271 |
Ladies | +1.216 |
Neg logit contributions | |
soever | -1.301 |
adversary | -1.257 |
�� | -1.234 |
achine | -1.198 |
anooga | -1.164 |
Token | a |
Token ID | 257 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
uid | +1.212 |
女 | +1.089 |
quote | +1.046 |
í | +1.029 |
Ladies | +0.987 |
Neg logit contributions | |
soever | -0.927 |
adversary | -0.895 |
�� | -0.879 |
achine | -0.852 |
anooga | -0.826 |
Token | good |
Token ID | 922 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
soever | +1.121 |
adversary | +1.096 |
�� | +1.060 |
achine | +1.016 |
anooga | +0.987 |
Neg logit contributions | |
uid | -1.571 |
女 | -1.412 |
quote | -1.357 |
í | -1.333 |
Ladies | -1.279 |
Token | idea |
Token ID | 2126 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
soever | +2.305 |
adversary | +2.295 |
�� | +2.178 |
achine | +2.064 |
anooga | +2.030 |
Neg logit contributions | |
uid | -3.341 |
女 | -3.012 |
quote | -2.867 |
í | -2.818 |
Ladies | -2.710 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
soever | +2.220 |
adversary | +2.160 |
�� | +2.065 |
achine | +1.987 |
anooga | +1.924 |
Neg logit contributions | |
uid | -3.513 |
女 | -3.186 |
quote | -3.062 |
í | -2.979 |
Ladies | -2.898 |
Token | especially |
Token ID | 2592 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
soever | +2.103 |
adversary | +2.059 |
�� | +1.945 |
achine | +1.895 |
anooga | +1.849 |
Neg logit contributions | |
uid | -2.928 |
女 | -2.649 |
quote | -2.538 |
í | -2.463 |
Ladies | -2.380 |
Token | a |
Token ID | 257 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
adversary | +6.891 |
soever | +6.727 |
weakness | +5.911 |
exemplary | +5.856 |
achine | +5.835 |
Neg logit contributions | |
uid | -11.291 |
女 | -10.109 |
quote | -9.817 |
í | -9.390 |
united | -9.261 |
Token | big |
Token ID | 1263 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
soever | +1.926 |
adversary | +1.899 |
�� | +1.799 |
achine | +1.743 |
anooga | +1.701 |
Neg logit contributions | |
uid | -2.760 |
女 | -2.486 |
quote | -2.384 |
í | -2.334 |
Ladies | -2.233 |
Token | one |
Token ID | 530 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
soever | +2.880 |
adversary | +2.817 |
�� | +2.662 |
achine | +2.578 |
anooga | +2.529 |
Neg logit contributions | |
uid | -4.425 |
女 | -4.010 |
quote | -3.843 |
í | -3.761 |
Ladies | -3.637 |
Token | , |
Token ID | 11 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
soever | +1.696 |
adversary | +1.639 |
�� | +1.606 |
achine | +1.556 |
anooga | +1.509 |
Neg logit contributions | |
uid | -2.122 |
女 | -1.900 |
quote | -1.822 |
í | -1.794 |
Ladies | -1.716 |
Token | requires |
Token ID | 4433 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
soever | +2.991 |
adversary | +2.922 |
�� | +2.734 |
achine | +2.647 |
anooga | +2.563 |
Neg logit contributions | |
uid | -5.247 |
女 | -4.784 |
quote | -4.613 |
í | -4.428 |
Ladies | -4.344 |
Token | some |
Token ID | 617 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
uid | +0.171 |
女 | +0.153 |
quote | +0.147 |
í | +0.145 |
Ladies | +0.139 |
Neg logit contributions | |
soever | -0.130 |
adversary | -0.125 |
�� | -0.123 |
achine | -0.119 |
anooga | -0.116 |
Token | respects |
Token ID | 19410 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
soever | +1.886 |
adversary | +1.827 |
�� | +1.741 |
achine | +1.693 |
Canaver | +1.630 |
Neg logit contributions | |
uid | -3.145 |
女 | -2.845 |
quote | -2.736 |
í | -2.686 |
Ladies | -2.591 |
Token | and |
Token ID | 290 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
soever | +5.021 |
adversary | +4.799 |
�� | +4.562 |
achine | +4.461 |
Canaver | +4.282 |
Neg logit contributions | |
uid | -7.470 |
女 | -6.618 |
quote | -6.417 |
Ladies | -6.044 |
í | -6.039 |
Token | for |
Token ID | 329 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
soever | +2.522 |
adversary | +2.452 |
�� | +2.301 |
achine | +2.250 |
Canaver | +2.205 |
Neg logit contributions | |
uid | -3.632 |
女 | -3.272 |
quote | -3.124 |
í | -3.051 |
Ladies | -2.946 |
Token | some |
Token ID | 617 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
soever | +1.102 |
adversary | +1.067 |
�� | +1.034 |
achine | +1.004 |
Canaver | +0.969 |
Neg logit contributions | |
uid | -1.587 |
女 | -1.438 |
quote | -1.375 |
í | -1.352 |
Ladies | -1.300 |
Token | periods |
Token ID | 9574 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
soever | +3.830 |
adversary | +3.766 |
�� | +3.525 |
achine | +3.434 |
Canaver | +3.321 |
Neg logit contributions | |
uid | -5.378 |
女 | -4.837 |
quote | -4.640 |
í | -4.505 |
Ladies | -4.344 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
soever | +7.097 |
adversary | +6.797 |
achine | +6.256 |
�� | +6.206 |
Canaver | +6.005 |
Neg logit contributions | |
uid | -10.894 |
女 | -9.681 |
quote | -9.433 |
Ladies | -8.921 |
united | -8.817 |
Token | By |
Token ID | 2750 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
uid | +1.309 |
女 | +1.155 |
quote | +1.101 |
í | +1.077 |
Ladies | +1.024 |
Neg logit contributions | |
soever | -1.324 |
adversary | -1.283 |
�� | -1.257 |
achine | -1.226 |
Canaver | -1.195 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
uid | +0.090 |
女 | +0.081 |
quote | +0.077 |
í | +0.076 |
Ladies | +0.073 |
Neg logit contributions | |
soever | -0.069 |
adversary | -0.066 |
�� | -0.065 |
achine | -0.063 |
anooga | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
soever | +0.629 |
adversary | +0.614 |
�� | +0.604 |
achine | +0.590 |
Canaver | +0.576 |
Neg logit contributions | |
uid | -0.437 |
女 | -0.375 |
quote | -0.355 |
í | -0.344 |
Ladies | -0.324 |
Token | 000 |
Token ID | 830 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
uid | +1.759 |
女 | +1.569 |
quote | +1.483 |
í | +1.482 |
Ladies | +1.406 |
Neg logit contributions | |
soever | -1.594 |
adversary | -1.553 |
�� | -1.516 |
achine | -1.462 |
anooga | -1.460 |
Token | against |
Token ID | 1028 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
soever | +1.846 |
adversary | +1.815 |
�� | +1.711 |
achine | +1.678 |
Canaver | +1.621 |
Neg logit contributions | |
uid | -2.350 |
女 | -2.094 |
quote | -2.017 |
í | -1.954 |
Ladies | -1.889 |
Token | BJP |
Token ID | 18317 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
soever | +1.318 |
adversary | +1.278 |
�� | +1.229 |
achine | +1.191 |
Canaver | +1.156 |
Neg logit contributions | |
uid | -1.895 |
女 | -1.720 |
quote | -1.648 |
í | -1.616 |
Ladies | -1.543 |
Token | MLA |
Token ID | 43265 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
soever | +1.348 |
adversary | +1.308 |
�� | +1.253 |
achine | +1.215 |
Canaver | +1.169 |
Neg logit contributions | |
uid | -1.716 |
女 | -1.541 |
quote | -1.470 |
í | -1.446 |
Ladies | -1.376 |
Token | Narendra |
Token ID | 28113 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
soever | +1.164 |
adversary | +1.124 |
�� | +1.099 |
achine | +1.064 |
Canaver | +1.032 |
Neg logit contributions | |
uid | -1.476 |
女 | -1.323 |
quote | -1.269 |
í | -1.247 |
Ladies | -1.193 |
Token | Me |
Token ID | 2185 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
soever | +3.204 |
adversary | +3.011 |
�� | +2.929 |
achine | +2.919 |
Canaver | +2.849 |
Neg logit contributions | |
uid | -4.509 |
女 | -4.108 |
quote | -3.915 |
í | -3.811 |
Ladies | -3.675 |
Token | ht |
Token ID | 4352 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
soever | +5.710 |
adversary | +5.575 |
achine | +5.504 |
�� | +5.477 |
anooga | +5.299 |
Neg logit contributions | |
uid | -2.307 |
女 | -2.022 |
quote | -1.778 |
í | -1.624 |
Ladies | -1.513 |
Token | a |
Token ID | 64 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
soever | +6.745 |
achine | +6.738 |
adversary | +6.665 |
�� | +6.270 |
anooga | +6.163 |
Neg logit contributions | |
uid | -9.899 |
女 | -9.843 |
quote | -8.846 |
Ladies | -8.678 |
united | -8.484 |
Token | � |
Token ID | 447 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
soever | +2.402 |
adversary | +2.321 |
�� | +2.260 |
achine | +2.181 |
Canaver | +2.096 |
Neg logit contributions | |
uid | -3.325 |
女 | -3.003 |
quote | -2.883 |
í | -2.799 |
Ladies | -2.705 |
Token | � |
Token ID | 247 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
soever | +1.969 |
�� | +1.883 |
adversary | +1.883 |
achine | +1.758 |
anooga | +1.694 |
Neg logit contributions | |
uid | -3.632 |
女 | -3.312 |
quote | -3.220 |
í | -3.130 |
Ladies | -3.057 |
Token | s |
Token ID | 82 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
soever | +1.317 |
adversary | +1.274 |
�� | +1.242 |
achine | +1.205 |
anooga | +1.163 |
Neg logit contributions | |
uid | -1.663 |
女 | -1.493 |
quote | -1.432 |
í | -1.401 |
Ladies | -1.350 |
Token | younger |
Token ID | 7099 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
soever | +0.771 |
adversary | +0.748 |
�� | +0.727 |
achine | +0.705 |
Canaver | +0.682 |
Neg logit contributions | |
uid | -0.968 |
女 | -0.869 |
quote | -0.831 |
í | -0.817 |
Ladies | -0.781 |
Token | CE |
Token ID | 18671 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
soever | +0.398 |
adversary | +0.385 |
�� | +0.376 |
achine | +0.366 |
Canaver | +0.354 |
Neg logit contributions | |
uid | -0.476 |
女 | -0.427 |
quote | -0.408 |
í | -0.399 |
Ladies | -0.383 |
Token | 50 |
Token ID | 1120 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
soever | +1.691 |
adversary | +1.644 |
�� | +1.599 |
achine | +1.558 |
anooga | +1.508 |
Neg logit contributions | |
uid | -2.000 |
女 | -1.796 |
quote | -1.711 |
í | -1.675 |
Ladies | -1.605 |
Token | ( |
Token ID | 357 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
soever | +4.142 |
adversary | +4.030 |
�� | +3.901 |
achine | +3.832 |
Canaver | +3.718 |
Neg logit contributions | |
uid | -5.167 |
女 | -4.675 |
quote | -4.459 |
í | -4.325 |
Ladies | -4.160 |
Token | Ag |
Token ID | 10262 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
soever | +1.736 |
adversary | +1.682 |
�� | +1.646 |
achine | +1.611 |
Canaver | +1.560 |
Neg logit contributions | |
uid | -1.817 |
女 | -1.619 |
quote | -1.534 |
í | -1.508 |
Ladies | -1.448 |
Token | reement |
Token ID | 10237 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
soever | +3.960 |
adversary | +3.854 |
�� | +3.772 |
achine | +3.723 |
anooga | +3.615 |
Neg logit contributions | |
uid | -3.777 |
女 | -3.432 |
quote | -3.201 |
í | -3.072 |
Ladies | -2.986 |
Token | number |
Token ID | 1271 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
soever | +2.536 |
adversary | +2.466 |
�� | +2.394 |
achine | +2.338 |
anooga | +2.249 |
Neg logit contributions | |
uid | -2.952 |
女 | -2.713 |
quote | -2.545 |
í | -2.463 |
Ladies | -2.374 |
Token | : |
Token ID | 25 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
soever | +7.974 |
adversary | +7.633 |
achine | +7.154 |
�� | +7.092 |
Canaver | +7.075 |
Neg logit contributions | |
uid | -9.046 |
女 | -8.511 |
quote | -7.726 |
united | -7.409 |
í | -7.375 |
Token | 501 |
Token ID | 24555 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
soever | +2.486 |
adversary | +2.411 |
�� | +2.333 |
achine | +2.287 |
Canaver | +2.226 |
Neg logit contributions | |
uid | -2.955 |
女 | -2.684 |
quote | -2.533 |
í | -2.471 |
Ladies | -2.370 |
Token | 20 |
Token ID | 1238 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
uid | +1.341 |
女 | +1.193 |
quote | +1.146 |
í | +1.131 |
Ladies | +1.080 |
Neg logit contributions | |
soever | -1.133 |
adversary | -1.094 |
�� | -1.070 |
achine | -1.034 |
anooga | -1.020 |
Token | 78 |
Token ID | 3695 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
uid | +3.042 |
女 | +2.706 |
quote | +2.602 |
í | +2.579 |
Ladies | +2.467 |
Neg logit contributions | |
soever | -2.480 |
adversary | -2.378 |
�� | -2.356 |
anooga | -2.249 |
achine | -2.236 |
Token | - |
Token ID | 12 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
uid | +3.823 |
女 | +3.394 |
quote | +3.276 |
í | +3.258 |
Ladies | +3.103 |
Neg logit contributions | |
soever | -2.966 |
adversary | -2.839 |
�� | -2.816 |
anooga | -2.683 |
achine | -2.658 |
Token | . |
Token ID | 13 |
Feature activation | +8.06e-03 |
Pos logit contributions | |
uid | +1.190 |
女 | +1.066 |
quote | +1.022 |
í | +1.007 |
Ladies | +0.963 |
Neg logit contributions | |
soever | -0.951 |
adversary | -0.920 |
�� | -0.903 |
achine | -0.874 |
anooga | -0.848 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
soever | +0.041 |
adversary | +0.040 |
�� | +0.039 |
achine | +0.038 |
anooga | +0.037 |
Neg logit contributions | |
uid | -0.040 |
女 | -0.035 |
quote | -0.033 |
í | -0.033 |
Ladies | -0.031 |
Token | E |
Token ID | 36 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
soever | +2.159 |
adversary | +2.084 |
�� | +2.046 |
achine | +1.987 |
anooga | +1.930 |
Neg logit contributions | |
uid | -2.509 |
女 | -2.245 |
quote | -2.126 |
í | -2.104 |
Ladies | -2.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
soever | +0.964 |
adversary | +0.938 |
�� | +0.921 |
achine | +0.897 |
anooga | +0.875 |
Neg logit contributions | |
uid | -0.856 |
女 | -0.750 |
quote | -0.713 |
í | -0.698 |
Ladies | -0.662 |
Token | S |
Token ID | 50 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
soever | +4.326 |
adversary | +4.197 |
�� | +4.072 |
achine | +3.969 |
Canaver | +3.865 |
Neg logit contributions | |
uid | -5.725 |
女 | -5.140 |
quote | -4.913 |
í | -4.808 |
united | -4.588 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
soever | +0.520 |
adversary | +0.509 |
�� | +0.499 |
achine | +0.478 |
anooga | +0.468 |
Neg logit contributions | |
uid | -0.558 |
女 | -0.490 |
quote | -0.469 |
í | -0.467 |
Ladies | -0.439 |
Token | Glover |
Token ID | 43487 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
soever | +7.856 |
adversary | +7.835 |
achine | +7.554 |
�� | +7.505 |
Canaver | +7.330 |
Neg logit contributions | |
uid | -9.326 |
女 | -8.283 |
quote | -7.885 |
í | -7.616 |
united | -7.349 |
Token | 's |
Token ID | 338 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
soever | +0.069 |
adversary | +0.067 |
�� | +0.065 |
achine | +0.063 |
anooga | +0.061 |
Neg logit contributions | |
uid | -0.084 |
女 | -0.075 |
quote | -0.072 |
í | -0.071 |
Ladies | -0.068 |
Token | bird |
Token ID | 6512 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
soever | +0.627 |
adversary | +0.607 |
�� | +0.595 |
achine | +0.577 |
anooga | +0.560 |
Neg logit contributions | |
uid | -0.745 |
女 | -0.665 |
quote | -0.637 |
í | -0.626 |
Ladies | -0.599 |
Token | sey |
Token ID | 4397 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
soever | +1.581 |
adversary | +1.533 |
�� | +1.497 |
achine | +1.453 |
anooga | +1.410 |
Neg logit contributions | |
uid | -1.900 |
女 | -1.699 |
quote | -1.626 |
í | -1.597 |
Ladies | -1.529 |
Token | e |
Token ID | 68 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
soever | +2.566 |
adversary | +2.488 |
�� | +2.431 |
achine | +2.370 |
Canaver | +2.298 |
Neg logit contributions | |
uid | -2.690 |
女 | -2.394 |
quote | -2.281 |
í | -2.236 |
Ladies | -2.133 |
Token | Massachusetts |
Token ID | 10140 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
uid | +0.874 |
女 | +0.779 |
quote | +0.747 |
í | +0.733 |
Ladies | +0.702 |
Neg logit contributions | |
soever | -0.758 |
adversary | -0.732 |
�� | -0.718 |
achine | -0.696 |
anooga | -0.676 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
uid | +4.898 |
女 | +4.485 |
í | +4.201 |
quote | +4.185 |
Ladies | +4.030 |
Neg logit contributions | |
soever | -4.745 |
�� | -4.689 |
adversary | -4.636 |
achine | -4.439 |
Canaver | -4.414 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
uid | +0.963 |
女 | +0.865 |
quote | +0.830 |
í | +0.817 |
Ladies | +0.783 |
Neg logit contributions | |
soever | -0.734 |
adversary | -0.709 |
�� | -0.693 |
achine | -0.671 |
anooga | -0.650 |
Token | John |
Token ID | 1757 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
soever | +0.046 |
adversary | +0.045 |
�� | +0.043 |
achine | +0.042 |
anooga | +0.041 |
Neg logit contributions | |
uid | -0.057 |
女 | -0.051 |
quote | -0.049 |
í | -0.048 |
Ladies | -0.046 |
Token | J |
Token ID | 449 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
soever | +4.234 |
adversary | +4.091 |
�� | +3.973 |
achine | +3.920 |
anooga | +3.774 |
Neg logit contributions | |
uid | -5.016 |
女 | -4.447 |
quote | -4.275 |
í | -4.151 |
Ladies | -3.959 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
soever | +5.468 |
adversary | +5.340 |
�� | +5.168 |
achine | +5.141 |
anooga | +4.953 |
Neg logit contributions | |
uid | -7.053 |
女 | -6.587 |
quote | -6.242 |
í | -5.987 |
Ladies | -5.810 |
Token | Dug |
Token ID | 27436 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
soever | +7.414 |
adversary | +7.316 |
achine | +7.115 |
�� | +6.921 |
Canaver | +6.816 |
Neg logit contributions | |
uid | -9.801 |
女 | -8.717 |
quote | -8.455 |
í | -7.999 |
Ladies | -7.727 |
Token | gan |
Token ID | 1030 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
soever | +8.107 |
adversary | +7.792 |
achine | +7.637 |
�� | +7.508 |
anooga | +7.456 |
Neg logit contributions | |
uid | -3.965 |
女 | -3.935 |
quote | -3.481 |
í | -3.178 |
Ladies | -3.128 |
Token | Middle |
Token ID | 6046 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
soever | +0.339 |
adversary | +0.329 |
�� | +0.324 |
achine | +0.314 |
anooga | +0.306 |
Neg logit contributions | |
uid | -0.347 |
女 | -0.307 |
quote | -0.293 |
í | -0.288 |
Ladies | -0.275 |
Token | School |
Token ID | 3961 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
uid | +3.829 |
女 | +3.261 |
quote | +3.138 |
í | +3.126 |
Ladies | +3.036 |
Neg logit contributions | |
soever | -5.310 |
adversary | -5.159 |
�� | -5.136 |
Canaver | -5.032 |
achine | -5.021 |
Token | will |
Token ID | 481 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
soever | +0.009 |
adversary | +0.009 |
�� | +0.009 |
achine | +0.008 |
anooga | +0.008 |
Neg logit contributions | |
uid | -0.011 |
女 | -0.010 |
quote | -0.009 |
í | -0.009 |
Ladies | -0.009 |
Token | interviewing |
Token ID | 31481 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
uid | +2.133 |
女 | +1.928 |
quote | +1.872 |
í | +1.848 |
Ladies | +1.771 |
Neg logit contributions | |
soever | -1.419 |
adversary | -1.356 |
�� | -1.329 |
achine | -1.286 |
Canaver | -1.252 |
Token | process |
Token ID | 1429 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
soever | +3.988 |
adversary | +3.885 |
�� | +3.687 |
achine | +3.629 |
Canaver | +3.488 |
Neg logit contributions | |
uid | -6.087 |
女 | -5.504 |
quote | -5.223 |
í | -5.079 |
united | -4.922 |
Token | : |
Token ID | 25 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
soever | +1.619 |
adversary | +1.565 |
�� | +1.531 |
achine | +1.487 |
anooga | +1.443 |
Neg logit contributions | |
uid | -1.993 |
女 | -1.783 |
quote | -1.707 |
í | -1.677 |
Ladies | -1.606 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
soever | +0.554 |
adversary | +0.537 |
�� | +0.528 |
achine | +0.513 |
Canaver | +0.501 |
Neg logit contributions | |
uid | -0.528 |
女 | -0.465 |
quote | -0.445 |
í | -0.436 |
Ladies | -0.415 |
Token |
|
Token ID | 198 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
uid | +0.550 |
女 | +0.495 |
quote | +0.465 |
í | +0.450 |
Ladies | +0.441 |
Neg logit contributions | |
soever | -0.458 |
adversary | -0.444 |
achine | -0.429 |
�� | -0.413 |
Canaver | -0.407 |
Token | Interview |
Token ID | 39945 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
soever | +0.157 |
adversary | +0.152 |
�� | +0.149 |
achine | +0.145 |
Canaver | +0.141 |
Neg logit contributions | |
uid | -0.183 |
女 | -0.163 |
quote | -0.156 |
í | -0.153 |
Ladies | -0.146 |
Token | preparation |
Token ID | 11824 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
adversary | +7.519 |
soever | +7.500 |
�� | +7.163 |
achine | +7.012 |
anooga | +7.006 |
Neg logit contributions | |
uid | -9.437 |
女 | -8.626 |
quote | -7.845 |
í | -7.803 |
united | -7.609 |
Token | books |
Token ID | 3835 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
soever | +1.212 |
adversary | +1.174 |
�� | +1.130 |
achine | +1.100 |
anooga | +1.055 |
Neg logit contributions | |
uid | -1.935 |
女 | -1.763 |
quote | -1.683 |
í | -1.655 |
Ladies | -1.596 |
Token | are |
Token ID | 389 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
soever | +0.449 |
adversary | +0.435 |
�� | +0.423 |
achine | +0.412 |
anooga | +0.397 |
Neg logit contributions | |
uid | -0.583 |
女 | -0.526 |
quote | -0.502 |
í | -0.492 |
Ladies | -0.473 |
Token | good |
Token ID | 922 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
uid | +0.064 |
女 | +0.057 |
quote | +0.055 |
í | +0.054 |
Ladies | +0.052 |
Neg logit contributions | |
soever | -0.045 |
adversary | -0.043 |
�� | -0.042 |
achine | -0.041 |
Canaver | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
uid | +0.415 |
女 | +0.372 |
quote | +0.356 |
í | +0.351 |
Ladies | +0.336 |
Neg logit contributions | |
soever | -0.325 |
adversary | -0.314 |
�� | -0.308 |
achine | -0.298 |
anooga | -0.289 |
Token | , |
Token ID | 11 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
uid | +1.280 |
女 | +1.143 |
quote | +1.100 |
í | +1.083 |
Ladies | +1.038 |
Neg logit contributions | |
soever | -1.015 |
adversary | -0.972 |
�� | -0.953 |
achine | -0.919 |
anooga | -0.904 |
Token | for |
Token ID | 329 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
soever | +1.363 |
adversary | +1.326 |
�� | +1.289 |
achine | +1.252 |
Canaver | +1.204 |
Neg logit contributions | |
uid | -1.995 |
女 | -1.802 |
quote | -1.734 |
í | -1.699 |
Ladies | -1.630 |
Token | controlling |
Token ID | 12755 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
soever | +1.926 |
adversary | +1.891 |
�� | +1.824 |
achine | +1.773 |
Canaver | +1.695 |
Neg logit contributions | |
uid | -3.129 |
女 | -2.857 |
quote | -2.728 |
í | -2.684 |
Ladies | -2.566 |
Token | thousands |
Token ID | 4138 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
soever | +1.960 |
adversary | +1.915 |
�� | +1.839 |
achine | +1.807 |
Canaver | +1.737 |
Neg logit contributions | |
uid | -2.761 |
女 | -2.509 |
quote | -2.393 |
í | -2.354 |
Ladies | -2.244 |
Token | of |
Token ID | 286 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
soever | +0.614 |
adversary | +0.593 |
�� | +0.586 |
achine | +0.561 |
Canaver | +0.553 |
Neg logit contributions | |
uid | -0.675 |
女 | -0.598 |
quote | -0.569 |
í | -0.563 |
Ladies | -0.532 |
Token | RGB |
Token ID | 25228 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
uid | +4.087 |
女 | +3.639 |
quote | +3.534 |
í | +3.495 |
Ladies | +3.385 |
Neg logit contributions | |
soever | -2.924 |
�� | -2.778 |
adversary | -2.746 |
achine | -2.616 |
anooga | -2.596 |
Token | LEDs |
Token ID | 33697 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
soever | +6.150 |
adversary | +6.021 |
achine | +5.915 |
�� | +5.615 |
decomp | +5.389 |
Neg logit contributions | |
uid | -10.729 |
女 | -10.013 |
quote | -9.516 |
í | -9.112 |
united | -8.869 |
Token | at |
Token ID | 379 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
soever | +4.484 |
adversary | +4.292 |
achine | +4.183 |
�� | +4.008 |
Canaver | +3.866 |
Neg logit contributions | |
uid | -6.450 |
女 | -5.957 |
quote | -5.721 |
í | -5.469 |
Ladies | -5.333 |
Token | video |
Token ID | 2008 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
soever | +1.298 |
adversary | +1.263 |
�� | +1.227 |
achine | +1.191 |
Canaver | +1.150 |
Neg logit contributions | |
uid | -1.776 |
女 | -1.604 |
quote | -1.537 |
í | -1.506 |
Ladies | -1.446 |
Token | speeds |
Token ID | 12055 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
soever | +1.243 |
adversary | +1.197 |
�� | +1.172 |
achine | +1.131 |
anooga | +1.095 |
Neg logit contributions | |
uid | -1.752 |
女 | -1.577 |
quote | -1.518 |
í | -1.495 |
Ladies | -1.433 |
Token | . |
Token ID | 13 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
soever | +2.150 |
adversary | +2.081 |
�� | +2.011 |
achine | +1.966 |
Canaver | +1.877 |
Neg logit contributions | |
uid | -2.968 |
女 | -2.699 |
quote | -2.571 |
í | -2.514 |
Ladies | -2.425 |
Token | classmates |
Token ID | 28999 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
uid | +0.176 |
女 | +0.158 |
quote | +0.152 |
í | +0.150 |
Ladies | +0.144 |
Neg logit contributions | |
soever | -0.129 |
adversary | -0.124 |
�� | -0.123 |
achine | -0.118 |
anooga | -0.115 |
Token | who |
Token ID | 508 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
soever | +0.514 |
adversary | +0.496 |
�� | +0.482 |
achine | +0.468 |
Canaver | +0.452 |
Neg logit contributions | |
uid | -0.682 |
女 | -0.611 |
quote | -0.588 |
í | -0.573 |
Ladies | -0.554 |
Token | wore |
Token ID | 12408 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
soever | +2.298 |
adversary | +2.219 |
�� | +2.087 |
achine | +2.070 |
Canaver | +2.011 |
Neg logit contributions | |
uid | -2.796 |
女 | -2.495 |
quote | -2.380 |
í | -2.288 |
Ladies | -2.241 |
Token | small |
Token ID | 1402 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
soever | +0.046 |
adversary | +0.044 |
�� | +0.043 |
achine | +0.042 |
anooga | +0.041 |
Neg logit contributions | |
uid | -0.058 |
女 | -0.052 |
quote | -0.050 |
í | -0.049 |
Ladies | -0.047 |
Token | s |
Token ID | 264 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
soever | +1.249 |
adversary | +1.212 |
�� | +1.184 |
achine | +1.147 |
anooga | +1.111 |
Neg logit contributions | |
uid | -1.598 |
女 | -1.431 |
quote | -1.371 |
í | -1.348 |
Ladies | -1.289 |
Token | omb |
Token ID | 2381 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
uid | +5.237 |
女 | +4.540 |
í | +4.495 |
quote | +4.426 |
Ladies | +4.189 |
Neg logit contributions | |
soever | -4.497 |
adversary | -4.427 |
�� | -4.322 |
anooga | -4.160 |
achine | -4.095 |
Token | rero |
Token ID | 34785 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
soever | +7.663 |
adversary | +7.309 |
achine | +7.069 |
�� | +6.862 |
anooga | +6.690 |
Neg logit contributions | |
uid | -8.940 |
女 | -8.583 |
quote | -7.662 |
Ladies | -7.391 |
í | -7.344 |
Token | hats |
Token ID | 23910 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
uid | +0.960 |
女 | +0.856 |
quote | +0.819 |
í | +0.811 |
Ladies | +0.773 |
Neg logit contributions | |
soever | -0.872 |
adversary | -0.843 |
�� | -0.832 |
achine | -0.807 |
anooga | -0.786 |
Token | to |
Token ID | 284 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
uid | +1.032 |
女 | +0.924 |
quote | +0.885 |
í | +0.873 |
Ladies | +0.834 |
Neg logit contributions | |
soever | -0.835 |
adversary | -0.808 |
�� | -0.793 |
achine | -0.767 |
anooga | -0.745 |
Token | a |
Token ID | 257 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
soever | +0.966 |
adversary | +0.942 |
�� | +0.915 |
achine | +0.889 |
Canaver | +0.858 |
Neg logit contributions | |
uid | -1.206 |
女 | -1.081 |
quote | -1.033 |
í | -1.012 |
Ladies | -0.968 |
Token | te |
Token ID | 573 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
soever | +0.118 |
adversary | +0.115 |
�� | +0.112 |
achine | +0.109 |
anooga | +0.105 |
Neg logit contributions | |
uid | -0.142 |
女 | -0.127 |
quote | -0.121 |
í | -0.119 |
Ladies | -0.114 |
Token | Justice |
Token ID | 4796 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
uid | +0.257 |
女 | +0.232 |
quote | +0.219 |
í | +0.219 |
Ladies | +0.211 |
Neg logit contributions | |
soever | -0.220 |
adversary | -0.211 |
�� | -0.209 |
achine | -0.199 |
Canaver | -0.194 |
Token | High |
Token ID | 3334 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
soever | +0.131 |
adversary | +0.126 |
�� | +0.124 |
achine | +0.120 |
anooga | +0.117 |
Neg logit contributions | |
uid | -0.143 |
女 | -0.127 |
quote | -0.121 |
í | -0.119 |
Ladies | -0.114 |
Token | School |
Token ID | 3961 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
uid | +1.079 |
女 | +0.935 |
quote | +0.900 |
í | +0.881 |
Ladies | +0.843 |
Neg logit contributions | |
soever | -1.241 |
adversary | -1.202 |
�� | -1.181 |
achine | -1.157 |
Canaver | -1.130 |
Token | ( |
Token ID | 357 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
soever | +0.204 |
adversary | +0.197 |
�� | +0.192 |
achine | +0.187 |
anooga | +0.181 |
Neg logit contributions | |
uid | -0.263 |
女 | -0.236 |
quote | -0.226 |
í | -0.222 |
Ladies | -0.213 |
Token | SO |
Token ID | 15821 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
soever | +3.037 |
adversary | +2.947 |
�� | +2.889 |
achine | +2.835 |
anooga | +2.738 |
Neg logit contributions | |
uid | -3.640 |
女 | -3.225 |
quote | -3.084 |
í | -3.047 |
Ladies | -2.932 |
Token | JO |
Token ID | 45006 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
soever | +3.120 |
adversary | +3.041 |
�� | +2.924 |
achine | +2.881 |
anooga | +2.748 |
Neg logit contributions | |
uid | -5.520 |
女 | -4.993 |
quote | -4.835 |
í | -4.728 |
Ladies | -4.546 |
Token | ), |
Token ID | 828 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
adversary | +5.548 |
soever | +5.424 |
�� | +5.220 |
achine | +5.151 |
anooga | +4.780 |
Neg logit contributions | |
uid | -11.400 |
女 | -10.308 |
quote | -10.073 |
í | -9.704 |
united | -9.323 |
Token | follows |
Token ID | 5679 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
soever | +2.200 |
adversary | +2.163 |
�� | +2.071 |
achine | +2.035 |
anooga | +1.959 |
Neg logit contributions | |
uid | -3.110 |
女 | -2.824 |
quote | -2.709 |
í | -2.639 |
Ladies | -2.501 |
Token | a |
Token ID | 257 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
soever | +4.988 |
adversary | +4.894 |
�� | +4.671 |
achine | +4.623 |
Canaver | +4.402 |
Neg logit contributions | |
uid | -6.929 |
女 | -6.335 |
quote | -6.023 |
í | -5.894 |
Ladies | -5.590 |
Token | similar |
Token ID | 2092 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
soever | +1.983 |
adversary | +1.960 |
�� | +1.874 |
achine | +1.816 |
Canaver | +1.757 |
Neg logit contributions | |
uid | -2.867 |
女 | -2.580 |
quote | -2.466 |
í | -2.420 |
Ladies | -2.309 |
Token | mission |
Token ID | 4365 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
soever | +1.548 |
adversary | +1.525 |
�� | +1.445 |
achine | +1.403 |
Canaver | +1.356 |
Neg logit contributions | |
uid | -2.460 |
女 | -2.228 |
quote | -2.127 |
í | -2.088 |
Ladies | -2.005 |
Token | to |
Token ID | 284 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
soever | +1.199 |
adversary | +1.170 |
�� | +1.122 |
achine | +1.101 |
Canaver | +1.057 |
Neg logit contributions | |
uid | -1.655 |
女 | -1.510 |
quote | -1.434 |
í | -1.410 |
Ladies | -1.362 |
Token | clear |
Token ID | 1598 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
soever | +0.599 |
adversary | +0.595 |
�� | +0.559 |
achine | +0.555 |
Canaver | +0.532 |
Neg logit contributions | |
uid | -0.783 |
女 | -0.712 |
quote | -0.671 |
í | -0.659 |
Ladies | -0.638 |
Token | the |
Token ID | 262 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
soever | +0.689 |
adversary | +0.670 |
�� | +0.651 |
achine | +0.632 |
anooga | +0.609 |
Neg logit contributions | |
uid | -0.892 |
女 | -0.807 |
quote | -0.770 |
í | -0.758 |
Ladies | -0.727 |
Token | stack |
Token ID | 8931 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
soever | +1.471 |
adversary | +1.466 |
�� | +1.392 |
achine | +1.338 |
Canaver | +1.279 |
Neg logit contributions | |
uid | -2.324 |
女 | -2.131 |
quote | -2.019 |
í | -2.000 |
Ladies | -1.924 |
Token | , |
Token ID | 11 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
uid | +0.312 |
女 | +0.282 |
quote | +0.268 |
í | +0.265 |
Ladies | +0.254 |
Neg logit contributions | |
soever | -0.240 |
adversary | -0.233 |
�� | -0.227 |
achine | -0.220 |
Canaver | -0.213 |
Token | followed |
Token ID | 3940 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
soever | +1.409 |
adversary | +1.375 |
�� | +1.319 |
achine | +1.284 |
Canaver | +1.235 |
Neg logit contributions | |
uid | -2.128 |
女 | -1.941 |
quote | -1.851 |
í | -1.815 |
Ladies | -1.754 |
Token | by |
Token ID | 416 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
soever | +6.045 |
adversary | +5.802 |
�� | +5.581 |
achine | +5.453 |
anooga | +5.189 |
Neg logit contributions | |
uid | -11.241 |
女 | -10.439 |
quote | -9.942 |
í | -9.720 |
Ladies | -9.482 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
soever | +4.439 |
adversary | +4.432 |
�� | +4.230 |
achine | +4.038 |
decomp | +3.991 |
Neg logit contributions | |
uid | -6.110 |
女 | -5.620 |
quote | -5.251 |
í | -5.188 |
united | -5.078 |
Token | return |
Token ID | 1441 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
soever | +0.732 |
adversary | +0.713 |
�� | +0.696 |
achine | +0.670 |
anooga | +0.650 |
Neg logit contributions | |
uid | -0.920 |
女 | -0.828 |
quote | -0.788 |
í | -0.777 |
Ladies | -0.743 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
soever | +1.756 |
adversary | +1.717 |
�� | +1.659 |
achine | +1.591 |
anooga | +1.529 |
Neg logit contributions | |
uid | -2.529 |
女 | -2.334 |
quote | -2.189 |
í | -2.176 |
Ladies | -2.089 |
Token |
|
Token ID | 198 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
soever | +1.678 |
adversary | +1.637 |
�� | +1.568 |
achine | +1.532 |
Canaver | +1.503 |
Neg logit contributions | |
uid | -1.741 |
女 | -1.583 |
quote | -1.457 |
í | -1.450 |
united | -1.384 |
Token | .: |
Token ID | 11207 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
soever | +3.030 |
adversary | +2.944 |
�� | +2.900 |
achine | +2.805 |
Canaver | +2.768 |
Neg logit contributions | |
uid | -2.308 |
女 | -1.995 |
quote | -1.890 |
í | -1.853 |
Ladies | -1.735 |
Token | Boston |
Token ID | 6182 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
soever | +0.356 |
adversary | +0.345 |
�� | +0.338 |
achine | +0.329 |
Canaver | +0.320 |
Neg logit contributions | |
uid | -0.374 |
女 | -0.331 |
quote | -0.316 |
í | -0.310 |
Ladies | -0.295 |
Token | police |
Token ID | 1644 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
uid | +0.660 |
女 | +0.586 |
quote | +0.556 |
í | +0.552 |
Ladies | +0.528 |
Neg logit contributions | |
soever | -0.669 |
adversary | -0.648 |
�� | -0.640 |
achine | -0.620 |
Canaver | -0.607 |
Token | commissioner |
Token ID | 16248 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
uid | +1.114 |
女 | +0.995 |
quote | +0.952 |
í | +0.931 |
Ladies | +0.893 |
Neg logit contributions | |
soever | -0.951 |
adversary | -0.924 |
�� | -0.900 |
achine | -0.875 |
anooga | -0.849 |
Token | says |
Token ID | 1139 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
soever | +0.625 |
adversary | +0.603 |
�� | +0.596 |
achine | +0.575 |
anooga | +0.561 |
Neg logit contributions | |
uid | -0.764 |
女 | -0.684 |
quote | -0.653 |
í | -0.649 |
Ladies | -0.623 |
Token | number |
Token ID | 1271 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
soever | +1.219 |
adversary | +1.178 |
�� | +1.140 |
achine | +1.101 |
Canaver | +1.070 |
Neg logit contributions | |
uid | -1.722 |
女 | -1.550 |
quote | -1.489 |
í | -1.458 |
Ladies | -1.403 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
soever | +6.749 |
adversary | +6.720 |
�� | +6.153 |
Canaver | +5.970 |
anooga | +5.960 |
Neg logit contributions | |
uid | -10.242 |
女 | -9.293 |
quote | -9.003 |
í | -8.599 |
Ladies | -8.500 |
Token | fatalities |
Token ID | 30091 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
soever | +0.442 |
adversary | +0.426 |
�� | +0.413 |
achine | +0.398 |
anooga | +0.383 |
Neg logit contributions | |
uid | -0.742 |
女 | -0.674 |
quote | -0.649 |
í | -0.638 |
Ladies | -0.614 |
Token | is |
Token ID | 318 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
soever | +1.630 |
adversary | +1.567 |
�� | +1.475 |
achine | +1.447 |
Canaver | +1.403 |
Neg logit contributions | |
uid | -2.612 |
女 | -2.374 |
quote | -2.285 |
í | -2.220 |
Ladies | -2.153 |
Token | three |
Token ID | 1115 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
soever | +1.019 |
adversary | +0.995 |
�� | +0.953 |
achine | +0.928 |
Canaver | +0.902 |
Neg logit contributions | |
uid | -1.390 |
女 | -1.258 |
quote | -1.204 |
í | -1.173 |
Ladies | -1.129 |
Token | , |
Token ID | 11 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
soever | +1.695 |
adversary | +1.642 |
�� | +1.604 |
achine | +1.554 |
Canaver | +1.503 |
Neg logit contributions | |
uid | -2.150 |
女 | -1.928 |
quote | -1.849 |
í | -1.813 |
Ladies | -1.739 |
Token | . |
Token ID | 13 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
soever | +1.630 |
adversary | +1.588 |
�� | +1.547 |
achine | +1.525 |
anooga | +1.467 |
Neg logit contributions | |
uid | -1.666 |
女 | -1.482 |
quote | -1.431 |
í | -1.372 |
Ladies | -1.319 |
Token | Eng |
Token ID | 1985 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
soever | +3.228 |
adversary | +3.188 |
�� | +3.106 |
achine | +3.073 |
Canaver | +2.953 |
Neg logit contributions | |
uid | -3.368 |
女 | -2.962 |
quote | -2.846 |
í | -2.756 |
Ladies | -2.633 |
Token | l |
Token ID | 75 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
soever | +4.483 |
adversary | +4.338 |
�� | +4.016 |
Canaver | +3.966 |
achine | +3.943 |
Neg logit contributions | |
uid | -4.553 |
女 | -4.255 |
quote | -3.823 |
í | -3.718 |
united | -3.621 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
soever | +5.053 |
adversary | +4.958 |
achine | +4.357 |
weakness | +4.342 |
anooga | +4.235 |
Neg logit contributions | |
uid | -8.684 |
女 | -8.230 |
quote | -7.721 |
united | -7.261 |
Ladies | -7.232 |
Token | J |
Token ID | 449 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
adversary | +3.242 |
soever | +3.239 |
�� | +2.936 |
Canaver | +2.826 |
achine | +2.824 |
Neg logit contributions | |
uid | -7.646 |
女 | -7.142 |
quote | -6.863 |
í | -6.543 |
united | -6.449 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
adversary | +2.940 |
soever | +2.909 |
achine | +2.723 |
�� | +2.670 |
Canaver | +2.577 |
Neg logit contributions | |
uid | -4.473 |
女 | -4.166 |
quote | -3.973 |
í | -3.831 |
united | -3.703 |
Token | Med |
Token ID | 2019 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
adversary | +5.475 |
soever | +5.355 |
�� | +4.939 |
achine | +4.612 |
decomp | +4.593 |
Neg logit contributions | |
uid | -11.316 |
女 | -10.373 |
quote | -10.043 |
í | -9.565 |
tta | -9.338 |
Token | ., |
Token ID | 1539 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
soever | +2.738 |
adversary | +2.647 |
�� | +2.589 |
achine | +2.509 |
anooga | +2.433 |
Neg logit contributions | |
uid | -3.441 |
女 | -3.084 |
quote | -2.958 |
í | -2.906 |
Ladies | -2.782 |
Token | Peter |
Token ID | 5613 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
soever | +2.412 |
adversary | +2.342 |
�� | +2.266 |
achine | +2.193 |
Canaver | +2.159 |
Neg logit contributions | |
uid | -3.070 |
女 | -2.755 |
quote | -2.635 |
í | -2.583 |
Ladies | -2.466 |
Token | Lur |
Token ID | 47851 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
soever | +3.583 |
adversary | +3.446 |
�� | +3.377 |
achine | +3.302 |
Canaver | +3.263 |
Neg logit contributions | |
uid | -4.733 |
女 | -4.291 |
quote | -4.095 |
í | -3.960 |
united | -3.802 |
Token | ie |
Token ID | 494 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
soever | +3.775 |
adversary | +3.671 |
�� | +3.583 |
achine | +3.545 |
anooga | +3.426 |
Neg logit contributions | |
uid | -3.373 |
女 | -3.082 |
quote | -2.860 |
í | -2.687 |
Ladies | -2.658 |
Token | lawyer |
Token ID | 6853 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
soever | +0.814 |
adversary | +0.779 |
�� | +0.772 |
achine | +0.753 |
Canaver | +0.734 |
Neg logit contributions | |
uid | -0.815 |
女 | -0.718 |
quote | -0.690 |
í | -0.679 |
Ladies | -0.642 |
Token | during |
Token ID | 1141 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
uid | +1.496 |
女 | +1.335 |
í | +1.277 |
quote | +1.271 |
Ladies | +1.208 |
Neg logit contributions | |
soever | -1.325 |
adversary | -1.256 |
�� | -1.248 |
achine | -1.214 |
Canaver | -1.191 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
uid | +0.422 |
女 | +0.369 |
quote | +0.360 |
í | +0.355 |
Ladies | +0.339 |
Neg logit contributions | |
soever | -0.366 |
adversary | -0.350 |
�� | -0.345 |
achine | -0.336 |
Canaver | -0.329 |
Token | George |
Token ID | 4502 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
soever | +0.722 |
adversary | +0.690 |
�� | +0.677 |
achine | +0.653 |
anooga | +0.632 |
Neg logit contributions | |
uid | -1.098 |
女 | -0.988 |
quote | -0.955 |
í | -0.941 |
Ladies | -0.906 |
Token | W |
Token ID | 370 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
soever | +0.679 |
adversary | +0.651 |
�� | +0.641 |
achine | +0.622 |
Canaver | +0.603 |
Neg logit contributions | |
uid | -0.990 |
女 | -0.892 |
quote | -0.863 |
í | -0.856 |
Ladies | -0.823 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
soever | +1.644 |
adversary | +1.621 |
achine | +1.515 |
�� | +1.479 |
anooga | +1.431 |
Neg logit contributions | |
uid | -2.398 |
女 | -2.254 |
quote | -2.088 |
í | -2.006 |
Ladies | -1.985 |
Token | Bush |
Token ID | 5511 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
adversary | +2.891 |
soever | +2.592 |
achine | +2.388 |
Canaver | +2.252 |
weakness | +2.180 |
Neg logit contributions | |
uid | -13.716 |
女 | -12.728 |
quote | -12.263 |
nown | -11.666 |
role | -11.605 |
Token | administration |
Token ID | 3662 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
soever | +0.018 |
adversary | +0.017 |
�� | +0.017 |
achine | +0.016 |
Canaver | +0.016 |
Neg logit contributions | |
uid | -0.028 |
女 | -0.025 |
quote | -0.024 |
í | -0.024 |
Ladies | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
uid | +2.865 |
女 | +2.537 |
í | +2.451 |
quote | +2.404 |
Ladies | +2.294 |
Neg logit contributions | |
soever | -2.837 |
�� | -2.676 |
adversary | -2.665 |
achine | -2.581 |
Canaver | -2.573 |
Token | said |
Token ID | 531 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
soever | +0.583 |
adversary | +0.563 |
�� | +0.553 |
achine | +0.535 |
anooga | +0.519 |
Neg logit contributions | |
uid | -0.715 |
女 | -0.639 |
quote | -0.613 |
í | -0.603 |
Ladies | -0.577 |
Token | there |
Token ID | 612 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
soever | +0.783 |
adversary | +0.759 |
�� | +0.737 |
achine | +0.711 |
Canaver | +0.694 |
Neg logit contributions | |
uid | -0.987 |
女 | -0.886 |
quote | -0.843 |
í | -0.829 |
Ladies | -0.793 |
Token | in |
Token ID | 287 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
soever | +2.717 |
adversary | +2.640 |
�� | +2.590 |
achine | +2.514 |
anooga | +2.440 |
Neg logit contributions | |
uid | -2.942 |
女 | -2.628 |
quote | -2.501 |
í | -2.473 |
Ladies | -2.345 |
Token | several |
Token ID | 1811 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
uid | +0.081 |
女 | +0.073 |
quote | +0.071 |
í | +0.069 |
Ladies | +0.067 |
Neg logit contributions | |
soever | -0.059 |
adversary | -0.057 |
�� | -0.056 |
achine | -0.054 |
anooga | -0.052 |
Token | initiatives |
Token ID | 15446 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
soever | +0.789 |
adversary | +0.768 |
�� | +0.739 |
achine | +0.717 |
Canaver | +0.693 |
Neg logit contributions | |
uid | -1.105 |
女 | -0.996 |
quote | -0.954 |
í | -0.937 |
Ladies | -0.897 |
Token | . |
Token ID | 13 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
soever | +0.692 |
adversary | +0.670 |
�� | +0.649 |
achine | +0.632 |
anooga | +0.610 |
Neg logit contributions | |
uid | -0.932 |
女 | -0.836 |
quote | -0.805 |
í | -0.786 |
Ladies | -0.757 |
Token | ( |
Token ID | 357 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
soever | +1.596 |
adversary | +1.548 |
�� | +1.509 |
achine | +1.482 |
Canaver | +1.435 |
Neg logit contributions | |
uid | -1.561 |
女 | -1.375 |
quote | -1.309 |
í | -1.277 |
Ladies | -1.215 |
Token | Nick |
Token ID | 8047 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
soever | +1.919 |
adversary | +1.855 |
�� | +1.815 |
achine | +1.763 |
Canaver | +1.709 |
Neg logit contributions | |
uid | -2.306 |
女 | -2.059 |
quote | -1.972 |
í | -1.938 |
Ladies | -1.854 |
Token | Koz |
Token ID | 40772 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
soever | +7.022 |
achine | +6.718 |
Canaver | +6.683 |
adversary | +6.589 |
�� | +6.415 |
Neg logit contributions | |
女 | -9.327 |
uid | -9.309 |
quote | -8.072 |
Ladies | -7.626 |
í | -7.490 |
Token | ak |
Token ID | 461 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
uid | +0.878 |
女 | +0.748 |
quote | +0.718 |
í | +0.718 |
Ladies | +0.668 |
Neg logit contributions | |
soever | -0.973 |
adversary | -0.942 |
�� | -0.937 |
achine | -0.891 |
Canaver | -0.885 |
Token | file |
Token ID | 2393 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
uid | +0.871 |
女 | +0.746 |
quote | +0.711 |
í | +0.708 |
Ladies | +0.666 |
Neg logit contributions | |
soever | -1.066 |
adversary | -1.037 |
�� | -1.025 |
achine | -0.992 |
Canaver | -0.983 |
Token | photo |
Token ID | 4590 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
soever | +0.618 |
adversary | +0.591 |
�� | +0.589 |
achine | +0.565 |
Canaver | +0.553 |
Neg logit contributions | |
uid | -0.822 |
女 | -0.747 |
quote | -0.720 |
í | -0.704 |
Ladies | -0.676 |
Token | for |
Token ID | 329 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
uid | +1.521 |
女 | +1.382 |
quote | +1.329 |
í | +1.309 |
Ladies | +1.253 |
Neg logit contributions | |
soever | -1.164 |
adversary | -1.124 |
�� | -1.109 |
achine | -1.051 |
Canaver | -1.045 |
Token | find |
Token ID | 1064 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
uid | +0.839 |
女 | +0.754 |
quote | +0.718 |
í | +0.705 |
Ladies | +0.677 |
Neg logit contributions | |
soever | -0.666 |
adversary | -0.644 |
�� | -0.625 |
achine | -0.609 |
anooga | -0.589 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
uid | +2.535 |
女 | +2.255 |
quote | +2.192 |
í | +2.160 |
Ladies | +2.066 |
Neg logit contributions | |
soever | -2.031 |
adversary | -1.930 |
�� | -1.921 |
achine | -1.856 |
Canaver | -1.813 |
Token | email |
Token ID | 3053 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
uid | +1.100 |
女 | +0.991 |
quote | +0.953 |
í | +0.938 |
Ladies | +0.901 |
Neg logit contributions | |
soever | -0.786 |
adversary | -0.757 |
�� | -0.742 |
achine | -0.717 |
anooga | -0.693 |
Token | of |
Token ID | 286 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
uid | +0.582 |
女 | +0.523 |
quote | +0.502 |
í | +0.494 |
Ladies | +0.473 |
Neg logit contributions | |
soever | -0.443 |
adversary | -0.428 |
�� | -0.418 |
achine | -0.405 |
anooga | -0.392 |
Token | a |
Token ID | 257 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
uid | +2.123 |
女 | +1.878 |
quote | +1.827 |
í | +1.790 |
Ladies | +1.712 |
Neg logit contributions | |
soever | -1.748 |
adversary | -1.667 |
�� | -1.662 |
achine | -1.603 |
anooga | -1.555 |
Token | recru |
Token ID | 8921 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
uid | +2.034 |
女 | +1.823 |
quote | +1.754 |
í | +1.724 |
Ladies | +1.653 |
Neg logit contributions | |
soever | -1.554 |
adversary | -1.497 |
�� | -1.469 |
achine | -1.421 |
Canaver | -1.377 |
Token | iter |
Token ID | 2676 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
adversary | +6.658 |
soever | +6.367 |
achine | +6.356 |
anooga | +6.119 |
intruder | +5.812 |
Neg logit contributions | |
uid | -9.462 |
女 | -8.823 |
Ladies | -7.995 |
quote | -7.853 |
ーン | -7.429 |
Token | and |
Token ID | 290 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
soever | +1.284 |
adversary | +1.227 |
�� | +1.169 |
achine | +1.157 |
anooga | +1.109 |
Neg logit contributions | |
uid | -1.849 |
女 | -1.673 |
quote | -1.585 |
í | -1.546 |
Ladies | -1.508 |
Token | send |
Token ID | 3758 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
uid | +0.293 |
女 | +0.263 |
quote | +0.248 |
í | +0.243 |
Ladies | +0.234 |
Neg logit contributions | |
soever | -0.249 |
adversary | -0.243 |
�� | -0.233 |
achine | -0.228 |
Canaver | -0.221 |
Token | them |
Token ID | 606 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
uid | +2.017 |
女 | +1.788 |
quote | +1.745 |
í | +1.708 |
Ladies | +1.623 |
Neg logit contributions | |
soever | -1.695 |
adversary | -1.633 |
�� | -1.627 |
achine | -1.556 |
anooga | -1.520 |
Token | a |
Token ID | 257 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
uid | +1.602 |
女 | +1.434 |
quote | +1.390 |
í | +1.361 |
Ladies | +1.302 |
Neg logit contributions | |
soever | -1.255 |
adversary | -1.210 |
�� | -1.198 |
achine | -1.148 |
anooga | -1.119 |
Token | Mer |
Token ID | 4638 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
uid | +1.697 |
女 | +1.513 |
quote | +1.456 |
í | +1.435 |
Ladies | +1.375 |
Neg logit contributions | |
soever | -1.387 |
adversary | -1.330 |
�� | -1.311 |
achine | -1.269 |
anooga | -1.235 |
Token | rick |
Token ID | 5557 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
soever | +0.418 |
adversary | +0.409 |
�� | +0.400 |
achine | +0.394 |
anooga | +0.384 |
Neg logit contributions | |
uid | -0.340 |
女 | -0.301 |
quote | -0.282 |
í | -0.275 |
Ladies | -0.262 |
Token | Garland |
Token ID | 35466 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
uid | +2.029 |
女 | +1.827 |
quote | +1.766 |
í | +1.759 |
Ladies | +1.687 |
Neg logit contributions | |
soever | -1.313 |
adversary | -1.252 |
�� | -1.236 |
achine | -1.183 |
anooga | -1.151 |
Token | to |
Token ID | 284 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
uid | +4.087 |
女 | +3.618 |
í | +3.466 |
quote | +3.463 |
Ladies | +3.268 |
Neg logit contributions | |
soever | -3.532 |
adversary | -3.358 |
�� | -3.282 |
achine | -3.272 |
anooga | -3.168 |
Token | the |
Token ID | 262 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
uid | +0.984 |
女 | +0.877 |
quote | +0.840 |
í | +0.829 |
Ladies | +0.791 |
Neg logit contributions | |
soever | -0.841 |
adversary | -0.809 |
�� | -0.795 |
achine | -0.773 |
anooga | -0.750 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
uid | +2.612 |
女 | +2.251 |
quote | +2.138 |
í | +2.094 |
Ladies | +1.977 |
Neg logit contributions | |
soever | -3.475 |
adversary | -3.369 |
�� | -3.328 |
achine | -3.248 |
anooga | -3.176 |
Token | Court |
Token ID | 3078 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
uid | +7.662 |
í | +6.083 |
quote | +5.977 |
Ladies | +5.569 |
女 | +5.530 |
Neg logit contributions | |
�� | -17.651 |
soever | -17.593 |
adversary | -16.677 |
achine | -16.530 |
anooga | -16.500 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
uid | +9.135 |
女 | +7.910 |
í | +7.860 |
quote | +7.579 |
Ladies | +7.197 |
Neg logit contributions | |
soever | -9.771 |
�� | -9.230 |
achine | -9.040 |
Canaver | -8.965 |
anooga | -8.939 |
Token | In |
Token ID | 554 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
soever | +0.896 |
adversary | +0.867 |
�� | +0.844 |
achine | +0.830 |
Canaver | +0.830 |
Neg logit contributions | |
uid | -0.930 |
女 | -0.827 |
quote | -0.777 |
í | -0.752 |
united | -0.723 |
Token | March |
Token ID | 2805 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
uid | +0.315 |
女 | +0.282 |
quote | +0.268 |
í | +0.263 |
Ladies | +0.252 |
Neg logit contributions | |
soever | -0.270 |
adversary | -0.265 |
�� | -0.257 |
achine | -0.251 |
Canaver | -0.244 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
soever | +1.000 |
adversary | +0.975 |
�� | +0.952 |
achine | +0.924 |
Canaver | +0.897 |
Neg logit contributions | |
uid | -1.082 |
女 | -0.963 |
quote | -0.915 |
í | -0.898 |
Ladies | -0.859 |
Token | � |
Token ID | 247 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
soever | +2.388 |
�� | +2.310 |
adversary | +2.299 |
achine | +2.142 |
anooga | +2.087 |
Neg logit contributions | |
uid | -3.583 |
女 | -3.251 |
quote | -3.129 |
í | -3.061 |
Ladies | -2.983 |
Token | s |
Token ID | 82 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
soever | +1.622 |
adversary | +1.572 |
�� | +1.528 |
achine | +1.485 |
anooga | +1.439 |
Neg logit contributions | |
uid | -1.952 |
女 | -1.743 |
quote | -1.662 |
í | -1.626 |
Ladies | -1.572 |
Token | nomination |
Token ID | 11872 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
soever | +0.726 |
adversary | +0.707 |
�� | +0.687 |
achine | +0.666 |
Canaver | +0.648 |
Neg logit contributions | |
uid | -0.827 |
女 | -0.740 |
quote | -0.703 |
í | -0.691 |
Ladies | -0.659 |
Token | to |
Token ID | 284 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
uid | +0.515 |
女 | +0.460 |
quote | +0.440 |
í | +0.436 |
Ladies | +0.413 |
Neg logit contributions | |
soever | -0.433 |
adversary | -0.415 |
�� | -0.411 |
achine | -0.397 |
Canaver | -0.386 |
Token | the |
Token ID | 262 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
uid | +1.627 |
女 | +1.443 |
quote | +1.384 |
í | +1.370 |
Ladies | +1.307 |
Neg logit contributions | |
soever | -1.478 |
adversary | -1.408 |
�� | -1.392 |
achine | -1.356 |
anooga | -1.325 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
uid | +2.307 |
女 | +1.939 |
quote | +1.831 |
í | +1.792 |
Ladies | +1.681 |
Neg logit contributions | |
soever | -3.854 |
adversary | -3.732 |
�� | -3.699 |
achine | -3.616 |
anooga | -3.553 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
uid | +7.777 |
í | +6.214 |
quote | +6.068 |
女 | +5.925 |
Ladies | +5.756 |
Neg logit contributions | |
soever | -16.658 |
�� | -16.542 |
adversary | -15.772 |
achine | -15.581 |
anooga | -15.576 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
uid | +8.536 |
女 | +7.413 |
í | +7.297 |
quote | +7.104 |
Ladies | +6.744 |
Neg logit contributions | |
soever | -8.811 |
�� | -8.497 |
adversary | -8.191 |
Canaver | -8.157 |
achine | -8.151 |
Token | In |
Token ID | 554 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
soever | +0.271 |
adversary | +0.262 |
�� | +0.257 |
achine | +0.251 |
Canaver | +0.247 |
Neg logit contributions | |
uid | -0.272 |
女 | -0.241 |
quote | -0.227 |
í | -0.222 |
Ladies | -0.211 |
Token | brief |
Token ID | 4506 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
soever | +0.058 |
adversary | +0.057 |
�� | +0.055 |
achine | +0.054 |
Canaver | +0.052 |
Neg logit contributions | |
uid | -0.075 |
女 | -0.068 |
quote | -0.065 |
í | -0.064 |
Ladies | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
soever | +2.460 |
adversary | +2.397 |
�� | +2.339 |
achine | +2.250 |
anooga | +2.181 |
Neg logit contributions | |
uid | -3.297 |
女 | -2.954 |
quote | -2.822 |
í | -2.772 |
Ladies | -2.661 |
Token | but |
Token ID | 475 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
soever | +0.031 |
adversary | +0.030 |
�� | +0.029 |
achine | +0.028 |
Canaver | +0.027 |
Neg logit contributions | |
uid | -0.050 |
女 | -0.045 |
quote | -0.044 |
í | -0.043 |
Ladies | -0.041 |
Token | related |
Token ID | 3519 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
soever | +0.609 |
adversary | +0.585 |
�� | +0.572 |
achine | +0.551 |
anooga | +0.532 |
Neg logit contributions | |
uid | -0.954 |
女 | -0.863 |
quote | -0.831 |
í | -0.818 |
Ladies | -0.787 |
Token | cases |
Token ID | 2663 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
soever | +0.822 |
adversary | +0.807 |
�� | +0.759 |
achine | +0.737 |
Canaver | +0.709 |
Neg logit contributions | |
uid | -1.430 |
女 | -1.300 |
quote | -1.258 |
í | -1.229 |
Ladies | -1.182 |
Token | , |
Token ID | 11 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
soever | +0.199 |
adversary | +0.193 |
�� | +0.189 |
achine | +0.183 |
anooga | +0.177 |
Neg logit contributions | |
uid | -0.245 |
女 | -0.220 |
quote | -0.210 |
í | -0.207 |
Ladies | -0.198 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
uid | +0.177 |
女 | +0.158 |
quote | +0.152 |
í | +0.149 |
Ladies | +0.143 |
Neg logit contributions | |
soever | -0.142 |
adversary | -0.137 |
�� | -0.135 |
achine | -0.131 |
anooga | -0.127 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
soever | +0.091 |
adversary | +0.089 |
�� | +0.087 |
achine | +0.084 |
Canaver | +0.082 |
Neg logit contributions | |
uid | -0.097 |
女 | -0.086 |
quote | -0.082 |
í | -0.080 |
Ladies | -0.076 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
uid | +7.218 |
í | +5.846 |
quote | +5.509 |
Ladies | +5.391 |
女 | +5.179 |
Neg logit contributions | |
�� | -16.124 |
soever | -15.864 |
anooga | -15.310 |
adversary | -15.023 |
achine | -14.978 |
Token | found |
Token ID | 1043 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
uid | +6.829 |
女 | +5.829 |
í | +5.819 |
quote | +5.731 |
Ladies | +5.613 |
Neg logit contributions | |
soever | -7.013 |
�� | -7.000 |
achine | -6.777 |
adversary | -6.534 |
Canaver | -6.482 |
Token | that |
Token ID | 326 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
uid | +0.872 |
女 | +0.781 |
quote | +0.758 |
í | +0.745 |
Ladies | +0.716 |
Neg logit contributions | |
soever | -0.655 |
adversary | -0.626 |
�� | -0.624 |
achine | -0.605 |
anooga | -0.587 |
Token | while |
Token ID | 981 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
soever | +0.491 |
adversary | +0.472 |
�� | +0.462 |
achine | +0.446 |
anooga | +0.431 |
Neg logit contributions | |
uid | -0.757 |
女 | -0.685 |
quote | -0.660 |
í | -0.650 |
Ladies | -0.625 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
uid | +0.741 |
女 | +0.665 |
quote | +0.643 |
í | +0.634 |
Ladies | +0.608 |
Neg logit contributions | |
soever | -0.535 |
adversary | -0.515 |
�� | -0.511 |
achine | -0.492 |
anooga | -0.480 |
Token | elections |
Token ID | 7024 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
uid | +3.926 |
女 | +3.548 |
quote | +3.407 |
í | +3.390 |
Ladies | +3.260 |
Neg logit contributions | |
soever | -2.993 |
�� | -2.957 |
achine | -2.849 |
adversary | -2.845 |
anooga | -2.786 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
soever | +0.290 |
adversary | +0.281 |
�� | +0.277 |
achine | +0.268 |
anooga | +0.261 |
Neg logit contributions | |
uid | -0.334 |
女 | -0.299 |
quote | -0.285 |
í | -0.282 |
Ladies | -0.268 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
soever | +0.618 |
adversary | +0.592 |
�� | +0.577 |
achine | +0.567 |
Canaver | +0.557 |
Neg logit contributions | |
uid | -0.637 |
女 | -0.564 |
quote | -0.534 |
í | -0.518 |
united | -0.491 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
soever | +1.027 |
adversary | +0.999 |
achine | +0.974 |
Canaver | +0.916 |
weakness | +0.905 |
Neg logit contributions | |
uid | -1.437 |
女 | -1.300 |
quote | -1.217 |
Ladies | -1.158 |
í | -1.157 |
Token | The |
Token ID | 464 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
soever | +0.808 |
adversary | +0.780 |
�� | +0.764 |
achine | +0.740 |
anooga | +0.720 |
Neg logit contributions | |
uid | -0.963 |
女 | -0.862 |
quote | -0.822 |
í | -0.809 |
Ladies | -0.778 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
soever | +0.915 |
adversary | +0.904 |
�� | +0.865 |
achine | +0.840 |
Canaver | +0.814 |
Neg logit contributions | |
uid | -1.201 |
女 | -1.084 |
quote | -1.034 |
í | -1.015 |
Ladies | -0.964 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
uid | +7.506 |
í | +6.079 |
quote | +5.834 |
Ladies | +5.742 |
女 | +5.726 |
Neg logit contributions | |
�� | -15.565 |
soever | -15.394 |
adversary | -14.713 |
achine | -14.598 |
anooga | -14.592 |
Token | � |
Token ID | 447 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
uid | +9.269 |
í | +8.091 |
女 | +8.014 |
quote | +7.880 |
Ladies | +7.717 |
Neg logit contributions | |
soever | -6.956 |
�� | -6.939 |
achine | -6.563 |
adversary | -6.386 |
anooga | -6.312 |
Token | � |
Token ID | 247 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
soever | +0.379 |
adversary | +0.373 |
�� | +0.369 |
achine | +0.348 |
Canaver | +0.341 |
Neg logit contributions | |
uid | -0.366 |
女 | -0.328 |
quote | -0.315 |
í | -0.299 |
Ladies | -0.295 |
Token | s |
Token ID | 82 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
uid | +1.141 |
女 | +1.018 |
quote | +0.978 |
í | +0.967 |
Ladies | +0.920 |
Neg logit contributions | |
soever | -0.906 |
adversary | -0.875 |
�� | -0.872 |
achine | -0.834 |
Canaver | -0.813 |
Token | erroneous |
Token ID | 35366 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
uid | +1.838 |
女 | +1.655 |
quote | +1.593 |
í | +1.569 |
Ladies | +1.508 |
Neg logit contributions | |
soever | -1.271 |
adversary | -1.222 |
�� | -1.199 |
achine | -1.157 |
anooga | -1.120 |
Token | just |
Token ID | 655 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
uid | +3.839 |
女 | +3.434 |
quote | +3.303 |
í | +3.296 |
Ladies | +3.113 |
Neg logit contributions | |
soever | -3.084 |
�� | -2.984 |
adversary | -2.889 |
achine | -2.791 |
anooga | -2.784 |
Token | show |
Token ID | 905 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
uid | +5.319 |
女 | +4.673 |
í | +4.557 |
quote | +4.543 |
Ladies | +4.245 |
Neg logit contributions | |
soever | -4.348 |
�� | -4.145 |
adversary | -4.104 |
achine | -3.932 |
anooga | -3.913 |
Token | up |
Token ID | 510 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
uid | +4.008 |
女 | +3.504 |
quote | +3.402 |
í | +3.364 |
Ladies | +3.226 |
Neg logit contributions | |
soever | -3.111 |
�� | -2.954 |
adversary | -2.904 |
achine | -2.824 |
anooga | -2.785 |
Token | at |
Token ID | 379 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
uid | +3.518 |
女 | +3.138 |
í | +2.998 |
quote | +2.996 |
Ladies | +2.857 |
Neg logit contributions | |
soever | -3.067 |
�� | -2.964 |
adversary | -2.936 |
achine | -2.859 |
Canaver | -2.772 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
uid | +2.696 |
女 | +2.392 |
quote | +2.318 |
í | +2.293 |
Ladies | +2.207 |
Neg logit contributions | |
soever | -2.326 |
�� | -2.223 |
adversary | -2.196 |
achine | -2.142 |
anooga | -2.078 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
uid | +1.088 |
女 | +0.957 |
quote | +0.910 |
í | +0.892 |
Ladies | +0.847 |
Neg logit contributions | |
soever | -1.171 |
adversary | -1.139 |
�� | -1.117 |
achine | -1.088 |
anooga | -1.060 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
uid | +7.346 |
í | +5.827 |
quote | +5.661 |
女 | +5.565 |
Ladies | +5.472 |
Neg logit contributions | |
�� | -15.607 |
soever | -15.561 |
adversary | -14.852 |
achine | -14.804 |
anooga | -14.686 |
Token | building |
Token ID | 2615 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
uid | +9.252 |
女 | +8.147 |
í | +8.069 |
quote | +7.932 |
Ladies | +7.737 |
Neg logit contributions | |
soever | -7.908 |
�� | -7.722 |
achine | -7.454 |
adversary | -7.275 |
anooga | -7.216 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
uid | +1.462 |
女 | +1.312 |
quote | +1.259 |
í | +1.240 |
Ladies | +1.188 |
Neg logit contributions | |
soever | -1.131 |
adversary | -1.092 |
�� | -1.073 |
achine | -1.038 |
anooga | -1.005 |
Token | start |
Token ID | 923 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
uid | +1.787 |
女 | +1.595 |
quote | +1.529 |
í | +1.504 |
Ladies | +1.439 |
Neg logit contributions | |
soever | -1.507 |
adversary | -1.457 |
�� | -1.434 |
achine | -1.388 |
anooga | -1.350 |
Token | working |
Token ID | 1762 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
soever | +0.252 |
adversary | +0.244 |
�� | +0.237 |
achine | +0.230 |
Canaver | +0.223 |
Neg logit contributions | |
uid | -0.334 |
女 | -0.300 |
quote | -0.288 |
í | -0.283 |
Ladies | -0.271 |
Token | filed |
Token ID | 5717 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
uid | +0.404 |
女 | +0.358 |
quote | +0.343 |
í | +0.333 |
Ladies | +0.318 |
Neg logit contributions | |
soever | -0.388 |
adversary | -0.379 |
�� | -0.367 |
achine | -0.358 |
anooga | -0.349 |
Token | . |
Token ID | 13 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
soever | +0.954 |
adversary | +0.920 |
�� | +0.891 |
achine | +0.869 |
anooga | +0.843 |
Neg logit contributions | |
uid | -1.184 |
女 | -1.061 |
quote | -1.021 |
í | -0.995 |
Ladies | -0.958 |
Token | Whatever |
Token ID | 15935 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
soever | +0.483 |
adversary | +0.465 |
�� | +0.454 |
achine | +0.444 |
Canaver | +0.435 |
Neg logit contributions | |
uid | -0.491 |
女 | -0.436 |
quote | -0.413 |
í | -0.402 |
Ladies | -0.381 |
Token | recon |
Token ID | 8195 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
uid | +0.114 |
女 | +0.102 |
quote | +0.098 |
í | +0.097 |
Ladies | +0.093 |
Neg logit contributions | |
soever | -0.088 |
adversary | -0.085 |
�� | -0.083 |
achine | -0.080 |
anooga | -0.078 |
Token | figured |
Token ID | 46296 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
uid | +2.937 |
女 | +2.460 |
quote | +2.352 |
í | +2.335 |
Ladies | +2.123 |
Neg logit contributions | |
soever | -4.559 |
�� | -4.385 |
adversary | -4.377 |
achine | -4.294 |
Canaver | -4.216 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
uid | +1.428 |
女 | +1.272 |
quote | +1.221 |
í | +1.201 |
Ladies | +1.148 |
Neg logit contributions | |
soever | -1.228 |
adversary | -1.185 |
�� | -1.168 |
achine | -1.132 |
anooga | -1.100 |
Token | Court |
Token ID | 3078 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
uid | +7.294 |
í | +5.813 |
女 | +5.709 |
quote | +5.671 |
Ladies | +5.411 |
Neg logit contributions | |
�� | -14.918 |
soever | -14.870 |
adversary | -14.252 |
achine | -14.136 |
anooga | -14.096 |
Token | emerges |
Token ID | 25457 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
uid | +10.583 |
í | +9.461 |
女 | +9.280 |
quote | +8.940 |
Ladies | +8.634 |
Neg logit contributions | |
soever | -8.483 |
�� | -8.356 |
achine | -8.048 |
Canaver | -8.032 |
anooga | -7.893 |
Token | after |
Token ID | 706 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
uid | +0.305 |
女 | +0.274 |
quote | +0.263 |
í | +0.259 |
Ladies | +0.248 |
Neg logit contributions | |
soever | -0.231 |
adversary | -0.223 |
�� | -0.219 |
achine | -0.212 |
anooga | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
soever | +1.109 |
adversary | +1.077 |
�� | +1.045 |
achine | +1.014 |
Canaver | +0.985 |
Neg logit contributions | |
uid | -1.258 |
女 | -1.126 |
quote | -1.072 |
í | -1.050 |
Ladies | -1.004 |
Token | November |
Token ID | 3389 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
uid | +0.137 |
女 | +0.122 |
quote | +0.115 |
í | +0.113 |
Ladies | +0.107 |
Neg logit contributions | |
soever | -0.134 |
adversary | -0.131 |
�� | -0.127 |
achine | -0.124 |
Canaver | -0.121 |
Token | on |
Token ID | 319 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
uid | +2.120 |
女 | +1.867 |
quote | +1.796 |
í | +1.774 |
Ladies | +1.691 |
Neg logit contributions | |
soever | -1.950 |
adversary | -1.882 |
�� | -1.866 |
achine | -1.810 |
anooga | -1.769 |
Token | Aadhaar |
Token ID | 47727 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
soever | +1.165 |
adversary | +1.138 |
�� | +1.108 |
achine | +1.077 |
Canaver | +1.053 |
Neg logit contributions | |
uid | -1.101 |
女 | -0.973 |
quote | -0.922 |
í | -0.902 |
Ladies | -0.850 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
soever | +0.996 |
adversary | +0.961 |
�� | +0.930 |
achine | +0.901 |
Canaver | +0.868 |
Neg logit contributions | |
uid | -1.211 |
女 | -1.091 |
quote | -1.038 |
í | -1.008 |
Ladies | -0.969 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
uid | +0.711 |
女 | +0.626 |
quote | +0.597 |
í | +0.585 |
Ladies | +0.556 |
Neg logit contributions | |
soever | -0.806 |
adversary | -0.788 |
�� | -0.772 |
achine | -0.749 |
Canaver | -0.736 |
Token | The |
Token ID | 464 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
uid | +0.746 |
女 | +0.665 |
quote | +0.638 |
í | +0.627 |
Ladies | +0.598 |
Neg logit contributions | |
soever | -0.640 |
adversary | -0.621 |
�� | -0.608 |
achine | -0.590 |
Canaver | -0.574 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
soever | +0.730 |
adversary | +0.716 |
�� | +0.696 |
achine | +0.680 |
Canaver | +0.663 |
Neg logit contributions | |
uid | -0.583 |
女 | -0.511 |
quote | -0.482 |
í | -0.469 |
Ladies | -0.439 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
uid | +6.572 |
í | +5.307 |
Ladies | +4.968 |
quote | +4.945 |
女 | +4.722 |
Neg logit contributions | |
�� | -15.048 |
soever | -14.907 |
achine | -14.360 |
anooga | -14.298 |
adversary | -14.212 |
Token | of |
Token ID | 286 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
uid | +7.749 |
í | +6.659 |
女 | +6.625 |
quote | +6.567 |
Ladies | +6.453 |
Neg logit contributions | |
�� | -5.842 |
soever | -5.814 |
achine | -5.577 |
adversary | -5.523 |
anooga | -5.433 |
Token | India |
Token ID | 3794 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
uid | +3.512 |
女 | +2.763 |
quote | +2.720 |
í | +2.701 |
Ladies | +2.552 |
Neg logit contributions | |
soever | -5.871 |
�� | -5.703 |
adversary | -5.670 |
Canaver | -5.547 |
anooga | -5.509 |
Token | has |
Token ID | 468 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
uid | +2.664 |
女 | +2.384 |
quote | +2.305 |
í | +2.283 |
Ladies | +2.195 |
Neg logit contributions | |
soever | -1.779 |
adversary | -1.720 |
�� | -1.700 |
achine | -1.634 |
anooga | -1.590 |
Token | time |
Token ID | 640 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
uid | +0.743 |
女 | +0.658 |
quote | +0.628 |
í | +0.613 |
Ladies | +0.584 |
Neg logit contributions | |
soever | -0.736 |
adversary | -0.714 |
�� | -0.694 |
achine | -0.677 |
Canaver | -0.659 |
Token | the |
Token ID | 262 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
uid | +3.154 |
女 | +2.823 |
quote | +2.748 |
í | +2.727 |
Ladies | +2.605 |
Neg logit contributions | |
soever | -2.599 |
�� | -2.502 |
adversary | -2.480 |
achine | -2.424 |
anooga | -2.335 |
Token | first |
Token ID | 717 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
uid | +3.176 |
女 | +2.832 |
quote | +2.765 |
í | +2.729 |
Ladies | +2.634 |
Neg logit contributions | |
soever | -2.338 |
adversary | -2.216 |
�� | -2.207 |
achine | -2.145 |
anooga | -2.086 |
Token | time |
Token ID | 640 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
uid | +1.892 |
女 | +1.703 |
quote | +1.641 |
í | +1.616 |
Ladies | +1.553 |
Neg logit contributions | |
soever | -1.373 |
adversary | -1.321 |
�� | -1.303 |
achine | -1.260 |
anooga | -1.219 |
Token | that |
Token ID | 326 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
uid | +3.289 |
女 | +2.957 |
quote | +2.868 |
í | +2.832 |
Ladies | +2.716 |
Neg logit contributions | |
soever | -2.788 |
adversary | -2.723 |
�� | -2.714 |
achine | -2.640 |
anooga | -2.567 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
uid | +2.149 |
女 | +1.924 |
quote | +1.867 |
í | +1.837 |
Ladies | +1.763 |
Neg logit contributions | |
soever | -1.782 |
adversary | -1.735 |
�� | -1.722 |
achine | -1.673 |
Canaver | -1.626 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
uid | +1.246 |
女 | +1.079 |
quote | +1.021 |
í | +0.998 |
Ladies | +0.942 |
Neg logit contributions | |
soever | -1.622 |
adversary | -1.579 |
�� | -1.553 |
achine | -1.516 |
anooga | -1.481 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
uid | +6.745 |
í | +5.457 |
quote | +5.377 |
女 | +5.241 |
Ladies | +5.117 |
Neg logit contributions | |
soever | -14.319 |
�� | -14.316 |
adversary | -13.759 |
achine | -13.528 |
anooga | -13.420 |
Token | was |
Token ID | 373 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
uid | +8.574 |
í | +7.647 |
quote | +7.583 |
女 | +7.544 |
Ladies | +7.296 |
Neg logit contributions | |
�� | -7.230 |
soever | -6.970 |
achine | -6.914 |
adversary | -6.708 |
Canaver | -6.702 |
Token | reported |
Token ID | 2098 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
uid | +4.567 |
女 | +4.077 |
quote | +3.923 |
í | +3.897 |
Ladies | +3.704 |
Neg logit contributions | |
soever | -4.052 |
�� | -3.936 |
adversary | -3.892 |
achine | -3.792 |
anooga | -3.688 |
Token | to |
Token ID | 284 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
uid | +0.062 |
女 | +0.056 |
quote | +0.053 |
í | +0.053 |
Ladies | +0.050 |
Neg logit contributions | |
soever | -0.048 |
adversary | -0.046 |
�� | -0.045 |
achine | -0.044 |
anooga | -0.043 |
Token | hold |
Token ID | 1745 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uid | +0.108 |
女 | +0.097 |
quote | +0.093 |
í | +0.092 |
Ladies | +0.088 |
Neg logit contributions | |
soever | -0.079 |
adversary | -0.076 |
�� | -0.074 |
achine | -0.072 |
anooga | -0.069 |
Token | awareness |
Token ID | 9359 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
uid | +3.615 |
女 | +3.183 |
í | +3.065 |
quote | +3.029 |
Ladies | +2.876 |
Neg logit contributions | |
soever | -3.359 |
�� | -3.225 |
adversary | -3.203 |
achine | -3.109 |
Canaver | -3.045 |
Token | about |
Token ID | 546 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
uid | +2.815 |
女 | +2.523 |
í | +2.403 |
quote | +2.395 |
Ladies | +2.246 |
Neg logit contributions | |
soever | -2.405 |
adversary | -2.315 |
�� | -2.292 |
achine | -2.197 |
Canaver | -2.169 |
Token | water |
Token ID | 1660 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
uid | +2.383 |
女 | +2.119 |
quote | +2.023 |
í | +2.014 |
Ladies | +1.931 |
Neg logit contributions | |
soever | -2.207 |
adversary | -2.110 |
�� | -2.107 |
achine | -2.043 |
anooga | -2.006 |
Token | scarcity |
Token ID | 35501 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
soever | +0.048 |
adversary | +0.046 |
�� | +0.045 |
achine | +0.043 |
anooga | +0.042 |
Neg logit contributions | |
uid | -0.070 |
女 | -0.063 |
quote | -0.060 |
í | -0.059 |
Ladies | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
uid | +0.763 |
女 | +0.689 |
quote | +0.662 |
í | +0.654 |
Ladies | +0.627 |
Neg logit contributions | |
soever | -0.517 |
adversary | -0.498 |
�� | -0.488 |
achine | -0.470 |
anooga | -0.455 |
Token | mis |
Token ID | 2984 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
uid | +2.335 |
女 | +2.095 |
quote | +2.006 |
í | +1.997 |
Ladies | +1.900 |
Neg logit contributions | |
soever | -1.747 |
�� | -1.687 |
adversary | -1.669 |
achine | -1.609 |
anooga | -1.578 |
Token | management |
Token ID | 27604 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
uid | +8.831 |
quote | +7.575 |
í | +7.482 |
女 | +6.868 |
sell | +6.742 |
Neg logit contributions | |
adversary | -11.526 |
�� | -11.446 |
soever | -11.188 |
achine | -11.053 |
Canaver | -11.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
uid | +2.012 |
女 | +1.808 |
í | +1.754 |
quote | +1.709 |
Ladies | +1.598 |
Neg logit contributions | |
soever | -1.896 |
�� | -1.840 |
adversary | -1.808 |
achine | -1.745 |
Canaver | -1.744 |
Token | waste |
Token ID | 7030 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
soever | +0.234 |
adversary | +0.225 |
�� | +0.220 |
achine | +0.213 |
anooga | +0.206 |
Neg logit contributions | |
uid | -0.330 |
女 | -0.298 |
quote | -0.286 |
í | -0.282 |
Ladies | -0.270 |
Token | may |
Token ID | 743 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
uid | +2.002 |
女 | +1.779 |
quote | +1.719 |
í | +1.709 |
Ladies | +1.606 |
Neg logit contributions | |
soever | -1.611 |
adversary | -1.567 |
�� | -1.532 |
achine | -1.500 |
anooga | -1.457 |
Token | pave |
Token ID | 23000 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
uid | +2.772 |
女 | +2.490 |
quote | +2.382 |
í | +2.372 |
Ladies | +2.236 |
Neg logit contributions | |
soever | -2.234 |
�� | -2.137 |
adversary | -2.128 |
achine | -2.023 |
anooga | -1.994 |
Token | s |
Token ID | 82 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
uid | +4.706 |
í | +3.993 |
女 | +3.981 |
Ladies | +3.905 |
quote | +3.884 |
Neg logit contributions | |
soever | -4.350 |
adversary | -4.206 |
�� | -4.137 |
achine | -4.061 |
Canaver | -4.038 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
uid | +1.137 |
女 | +1.016 |
quote | +0.974 |
í | +0.960 |
Ladies | +0.920 |
Neg logit contributions | |
soever | -0.926 |
adversary | -0.897 |
�� | -0.879 |
achine | -0.852 |
anooga | -0.828 |
Token | Judges |
Token ID | 42495 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
uid | +0.172 |
女 | +0.155 |
quote | +0.148 |
í | +0.144 |
Ladies | +0.137 |
Neg logit contributions | |
soever | -0.141 |
adversary | -0.136 |
�� | -0.133 |
achine | -0.128 |
anooga | -0.124 |
Token | of |
Token ID | 286 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
uid | +4.682 |
女 | +4.045 |
í | +4.008 |
Ladies | +3.911 |
quote | +3.909 |
Neg logit contributions | |
soever | -4.386 |
adversary | -4.354 |
�� | -4.238 |
achine | -4.148 |
Canaver | -4.143 |
Token | the |
Token ID | 262 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
uid | +3.493 |
女 | +2.964 |
í | +2.937 |
quote | +2.926 |
Ladies | +2.898 |
Neg logit contributions | |
soever | -3.364 |
adversary | -3.270 |
�� | -3.251 |
achine | -3.216 |
Canaver | -3.152 |
Token | supreme |
Token ID | 17700 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
uid | +2.609 |
女 | +2.256 |
quote | +2.164 |
í | +2.145 |
Ladies | +2.057 |
Neg logit contributions | |
soever | -2.966 |
adversary | -2.877 |
�� | -2.858 |
achine | -2.800 |
Canaver | -2.734 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
uid | +7.097 |
í | +5.951 |
Ladies | +5.848 |
女 | +5.636 |
quote | +5.484 |
Neg logit contributions | |
�� | -12.561 |
soever | -12.495 |
Canaver | -12.268 |
achine | -12.234 |
anooga | -11.946 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
uid | +6.741 |
女 | +5.723 |
í | +5.691 |
Ladies | +5.591 |
quote | +5.508 |
Neg logit contributions | |
soever | -7.005 |
�� | -6.945 |
adversary | -6.899 |
Canaver | -6.855 |
achine | -6.782 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
uid | +0.950 |
女 | +0.846 |
quote | +0.812 |
í | +0.801 |
Ladies | +0.768 |
Neg logit contributions | |
soever | -0.792 |
adversary | -0.766 |
�� | -0.752 |
achine | -0.730 |
anooga | -0.709 |
Token | all |
Token ID | 477 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
uid | +0.186 |
女 | +0.168 |
quote | +0.162 |
í | +0.158 |
Ladies | +0.150 |
Neg logit contributions | |
soever | -0.124 |
adversary | -0.119 |
�� | -0.115 |
achine | -0.110 |
Canaver | -0.107 |
Token | other |
Token ID | 584 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
uid | +2.760 |
女 | +2.493 |
quote | +2.400 |
í | +2.376 |
Ladies | +2.295 |
Neg logit contributions | |
soever | -1.734 |
adversary | -1.673 |
�� | -1.638 |
achine | -1.585 |
anooga | -1.531 |
Token | stay |
Token ID | 2652 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
soever | +1.377 |
adversary | +1.348 |
�� | +1.293 |
achine | +1.253 |
Canaver | +1.205 |
Neg logit contributions | |
uid | -1.927 |
女 | -1.743 |
quote | -1.663 |
í | -1.640 |
Ladies | -1.567 |
Token | while |
Token ID | 981 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
soever | +2.297 |
adversary | +2.230 |
�� | +2.115 |
achine | +2.067 |
Canaver | +2.011 |
Neg logit contributions | |
uid | -3.180 |
女 | -2.881 |
quote | -2.735 |
í | -2.699 |
Ladies | -2.614 |
Token | it |
Token ID | 340 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
soever | +0.605 |
adversary | +0.585 |
�� | +0.573 |
achine | +0.556 |
anooga | +0.540 |
Neg logit contributions | |
uid | -0.731 |
女 | -0.654 |
quote | -0.626 |
í | -0.616 |
Ladies | -0.589 |
Token | asks |
Token ID | 7893 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
soever | +0.639 |
adversary | +0.624 |
�� | +0.597 |
achine | +0.581 |
Canaver | +0.567 |
Neg logit contributions | |
uid | -0.825 |
女 | -0.739 |
quote | -0.712 |
í | -0.692 |
Ladies | -0.668 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
soever | +2.146 |
adversary | +2.090 |
�� | +2.017 |
achine | +1.958 |
Canaver | +1.893 |
Neg logit contributions | |
uid | -2.784 |
女 | -2.507 |
quote | -2.392 |
í | -2.350 |
Ladies | -2.247 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
soever | +0.853 |
adversary | +0.835 |
�� | +0.810 |
achine | +0.790 |
Canaver | +0.764 |
Neg logit contributions | |
uid | -0.894 |
女 | -0.797 |
quote | -0.755 |
í | -0.741 |
Ladies | -0.703 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
uid | +6.558 |
í | +5.213 |
quote | +5.106 |
女 | +4.885 |
Ladies | +4.876 |
Neg logit contributions | |
�� | -13.919 |
soever | -13.778 |
anooga | -13.221 |
adversary | -13.154 |
achine | -12.991 |
Token | to |
Token ID | 284 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
uid | +5.449 |
女 | +4.692 |
í | +4.631 |
quote | +4.542 |
Ladies | +4.338 |
Neg logit contributions | |
soever | -5.692 |
�� | -5.418 |
adversary | -5.263 |
achine | -5.249 |
Canaver | -5.212 |
Token | hear |
Token ID | 3285 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
uid | +1.865 |
女 | +1.661 |
quote | +1.596 |
í | +1.571 |
Ladies | +1.498 |
Neg logit contributions | |
soever | -1.599 |
adversary | -1.541 |
�� | -1.523 |
achine | -1.469 |
anooga | -1.437 |
Token | its |
Token ID | 663 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
uid | +0.388 |
女 | +0.346 |
quote | +0.333 |
í | +0.329 |
Ladies | +0.315 |
Neg logit contributions | |
soever | -0.306 |
adversary | -0.293 |
�� | -0.290 |
achine | -0.280 |
anooga | -0.275 |
Token | appeal |
Token ID | 5198 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
soever | +1.516 |
adversary | +1.511 |
�� | +1.405 |
achine | +1.365 |
Canaver | +1.316 |
Neg logit contributions | |
uid | -2.403 |
女 | -2.204 |
quote | -2.102 |
í | -2.057 |
Ladies | -1.982 |
Token | sound |
Token ID | 2128 |
Feature activation | -6.94e-03 |
Pos logit contributions | |
uid | +2.527 |
女 | +2.279 |
quote | +2.211 |
í | +2.181 |
Ladies | +2.105 |
Neg logit contributions | |
soever | -1.725 |
adversary | -1.640 |
�� | -1.640 |
achine | -1.582 |
Canaver | -1.531 |
Token | education |
Token ID | 3707 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
uid | +0.041 |
女 | +0.037 |
quote | +0.036 |
í | +0.035 |
Ladies | +0.034 |
Neg logit contributions | |
soever | -0.028 |
adversary | -0.027 |
�� | -0.027 |
achine | -0.026 |
Canaver | -0.025 |
Token | ." |
Token ID | 526 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
soever | +0.776 |
adversary | +0.750 |
�� | +0.736 |
achine | +0.712 |
Canaver | +0.691 |
Neg logit contributions | |
uid | -0.958 |
女 | -0.857 |
quote | -0.822 |
í | -0.809 |
Ladies | -0.773 |
Token |
|
Token ID | 198 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
uid | +0.315 |
女 | +0.276 |
quote | +0.264 |
í | +0.263 |
Ladies | +0.249 |
Neg logit contributions | |
soever | -0.359 |
adversary | -0.352 |
�� | -0.347 |
achine | -0.333 |
Canaver | -0.326 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
soever | +0.405 |
adversary | +0.396 |
achine | +0.382 |
Canaver | +0.360 |
�� | +0.356 |
Neg logit contributions | |
uid | -0.532 |
女 | -0.483 |
quote | -0.452 |
í | -0.433 |
Ladies | -0.430 |
Token | Mis |
Token ID | 31281 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
soever | +0.606 |
adversary | +0.586 |
�� | +0.573 |
achine | +0.557 |
anooga | +0.540 |
Neg logit contributions | |
uid | -0.728 |
女 | -0.650 |
quote | -0.622 |
í | -0.612 |
Ladies | -0.587 |
Token | guided |
Token ID | 23657 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
uid | +9.755 |
quote | +8.714 |
女 | +8.062 |
í | +8.052 |
sell | +7.959 |
Neg logit contributions | |
soever | -9.736 |
adversary | -9.663 |
�� | -9.627 |
Canaver | -9.082 |
achine | -8.775 |
Token | political |
Token ID | 1964 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
uid | +6.320 |
女 | +5.695 |
quote | +5.635 |
í | +5.581 |
Ladies | +5.327 |
Neg logit contributions | |
soever | -4.467 |
�� | -4.292 |
adversary | -4.157 |
achine | -4.148 |
Canaver | -4.057 |
Token | effort |
Token ID | 3626 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
soever | +0.380 |
adversary | +0.365 |
�� | +0.358 |
achine | +0.344 |
anooga | +0.332 |
Neg logit contributions | |
uid | -0.587 |
女 | -0.530 |
quote | -0.511 |
í | -0.504 |
Ladies | -0.484 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
uid | +1.564 |
女 | +1.365 |
quote | +1.293 |
í | +1.271 |
Ladies | +1.195 |
Neg logit contributions | |
soever | -1.895 |
�� | -1.812 |
adversary | -1.808 |
achine | -1.737 |
Canaver | -1.725 |
Token |
|
Token ID | 198 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
uid | +1.916 |
女 | +1.706 |
quote | +1.615 |
í | +1.570 |
Ladies | +1.518 |
Neg logit contributions | |
soever | -1.763 |
adversary | -1.713 |
achine | -1.641 |
�� | -1.628 |
Canaver | -1.587 |
Token | hash |
Token ID | 17831 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
soever | +0.019 |
adversary | +0.018 |
�� | +0.018 |
achine | +0.017 |
anooga | +0.017 |
Neg logit contributions | |
uid | -0.020 |
女 | -0.017 |
quote | -0.017 |
í | -0.016 |
Ladies | -0.016 |
Token | Gh |
Token ID | 11972 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
soever | +3.394 |
adversary | +3.270 |
�� | +3.217 |
achine | +3.130 |
Canaver | +3.051 |
Neg logit contributions | |
uid | -4.132 |
女 | -3.749 |
quote | -3.565 |
í | -3.473 |
Ladies | -3.338 |
Token | ai |
Token ID | 1872 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
uid | +1.441 |
女 | +1.243 |
quote | +1.211 |
í | +1.208 |
Ladies | +1.129 |
Neg logit contributions | |
soever | -1.279 |
adversary | -1.238 |
�� | -1.227 |
achine | -1.162 |
Canaver | -1.148 |
Token | , |
Token ID | 11 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
soever | +3.194 |
adversary | +3.115 |
�� | +3.031 |
achine | +2.956 |
anooga | +2.853 |
Neg logit contributions | |
uid | -3.287 |
女 | -2.945 |
quote | -2.778 |
í | -2.704 |
Ladies | -2.603 |
Token | the |
Token ID | 262 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
soever | +0.339 |
adversary | +0.328 |
�� | +0.322 |
achine | +0.312 |
anooga | +0.303 |
Neg logit contributions | |
uid | -0.409 |
女 | -0.366 |
quote | -0.351 |
í | -0.345 |
Ladies | -0.330 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
soever | +1.123 |
adversary | +1.095 |
�� | +1.059 |
achine | +1.032 |
Canaver | +1.000 |
Neg logit contributions | |
uid | -1.325 |
女 | -1.189 |
quote | -1.134 |
í | -1.113 |
Ladies | -1.056 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
uid | +6.528 |
í | +5.183 |
quote | +5.014 |
Ladies | +4.988 |
女 | +4.823 |
Neg logit contributions | |
soever | -13.348 |
�� | -13.322 |
anooga | -12.753 |
adversary | -12.725 |
achine | -12.705 |
Token | today |
Token ID | 1909 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
uid | +6.944 |
女 | +5.923 |
quote | +5.844 |
í | +5.834 |
Ladies | +5.675 |
Neg logit contributions | |
�� | -6.521 |
soever | -6.489 |
achine | -6.239 |
adversary | -6.168 |
Canaver | -6.073 |
Token | upheld |
Token ID | 24816 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
uid | +1.428 |
女 | +1.263 |
quote | +1.204 |
í | +1.186 |
Ladies | +1.130 |
Neg logit contributions | |
soever | -1.409 |
adversary | -1.368 |
�� | -1.353 |
achine | -1.316 |
anooga | -1.281 |
Token | the |
Token ID | 262 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
uid | +0.028 |
女 | +0.025 |
quote | +0.024 |
í | +0.023 |
Ladies | +0.023 |
Neg logit contributions | |
soever | -0.022 |
adversary | -0.021 |
�� | -0.021 |
achine | -0.020 |
anooga | -0.020 |
Token | Bombay |
Token ID | 48918 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
soever | +1.876 |
adversary | +1.836 |
�� | +1.752 |
achine | +1.698 |
Canaver | +1.648 |
Neg logit contributions | |
uid | -2.482 |
女 | -2.251 |
quote | -2.145 |
í | -2.108 |
united | -1.999 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
soever | +0.796 |
adversary | +0.769 |
�� | +0.755 |
achine | +0.730 |
anooga | +0.707 |
Neg logit contributions | |
uid | -0.993 |
女 | -0.889 |
quote | -0.853 |
í | -0.840 |
Ladies | -0.804 |
Token | American |
Token ID | 1605 |
Feature activation | -7.42e-06 |
Pos logit contributions | |
soever | +0.697 |
adversary | +0.676 |
�� | +0.659 |
achine | +0.639 |
anooga | +0.619 |
Neg logit contributions | |
uid | -0.929 |
女 | -0.834 |
quote | -0.800 |
í | -0.786 |
Ladies | -0.753 |
Token | economy |
Token ID | 3773 |
Feature activation | +9.15e-02 |
Token | and |
Token ID | 290 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
soever | +0.425 |
adversary | +0.409 |
�� | +0.403 |
achine | +0.389 |
Canaver | +0.386 |
Neg logit contributions | |
uid | -0.495 |
女 | -0.444 |
quote | -0.422 |
í | -0.422 |
Ladies | -0.399 |
Token | a |
Token ID | 257 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
soever | +1.176 |
adversary | +1.138 |
�� | +1.102 |
achine | +1.069 |
anooga | +1.038 |
Neg logit contributions | |
uid | -1.513 |
女 | -1.350 |
quote | -1.299 |
í | -1.269 |
Ladies | -1.216 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
soever | +0.156 |
adversary | +0.151 |
�� | +0.148 |
achine | +0.143 |
anooga | +0.138 |
Neg logit contributions | |
uid | -0.210 |
女 | -0.188 |
quote | -0.181 |
í | -0.178 |
Ladies | -0.170 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
uid | +6.733 |
í | +5.432 |
女 | +5.347 |
quote | +5.314 |
Ladies | +4.956 |
Neg logit contributions | |
soever | -13.193 |
�� | -13.124 |
adversary | -12.646 |
achine | -12.451 |
anooga | -12.413 |
Token | remotely |
Token ID | 19863 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
uid | +8.313 |
女 | +7.320 |
í | +7.294 |
quote | +7.079 |
Ladies | +6.762 |
Neg logit contributions | |
soever | -6.792 |
�� | -6.615 |
achine | -6.353 |
Canaver | -6.301 |
anooga | -6.175 |
Token | sympathetic |
Token ID | 22335 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
soever | +1.524 |
adversary | +1.479 |
�� | +1.418 |
achine | +1.362 |
Canaver | +1.315 |
Neg logit contributions | |
uid | -2.494 |
女 | -2.267 |
quote | -2.166 |
í | -2.130 |
Ladies | -2.056 |
Token | to |
Token ID | 284 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
uid | +0.582 |
女 | +0.518 |
í | +0.496 |
quote | +0.488 |
Ladies | +0.462 |
Neg logit contributions | |
soever | -0.525 |
�� | -0.497 |
adversary | -0.497 |
achine | -0.478 |
Canaver | -0.473 |
Token | organized |
Token ID | 8389 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
uid | +0.458 |
女 | +0.410 |
quote | +0.393 |
í | +0.387 |
Ladies | +0.371 |
Neg logit contributions | |
soever | -0.380 |
adversary | -0.366 |
�� | -0.360 |
achine | -0.349 |
anooga | -0.339 |
Token | elect |
Token ID | 1742 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
uid | +2.648 |
女 | +2.374 |
quote | +2.308 |
í | +2.281 |
Ladies | +2.181 |
Neg logit contributions | |
soever | -1.792 |
adversary | -1.694 |
�� | -1.690 |
achine | -1.632 |
anooga | -1.592 |
Token | justices |
Token ID | 27818 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
soever | +0.691 |
adversary | +0.671 |
�� | +0.650 |
achine | +0.628 |
anooga | +0.608 |
Neg logit contributions | |
uid | -0.939 |
女 | -0.849 |
quote | -0.812 |
í | -0.797 |
Ladies | -0.764 |
Token | on |
Token ID | 319 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
uid | +8.245 |
女 | +7.269 |
í | +7.155 |
quote | +6.927 |
Ladies | +6.613 |
Neg logit contributions | |
soever | -7.458 |
adversary | -7.102 |
�� | -7.099 |
achine | -7.063 |
anooga | -6.966 |
Token | the |
Token ID | 262 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
uid | +3.502 |
女 | +3.074 |
quote | +2.987 |
í | +2.978 |
Ladies | +2.870 |
Neg logit contributions | |
soever | -2.880 |
�� | -2.747 |
adversary | -2.694 |
achine | -2.659 |
anooga | -2.619 |
Token | Wisconsin |
Token ID | 9279 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
uid | +3.457 |
女 | +3.053 |
quote | +2.957 |
í | +2.924 |
Ladies | +2.809 |
Neg logit contributions | |
soever | -3.054 |
�� | -2.913 |
adversary | -2.907 |
achine | -2.823 |
anooga | -2.771 |
Token | supreme |
Token ID | 17700 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
uid | +3.577 |
女 | +3.003 |
í | +2.890 |
quote | +2.867 |
Ladies | +2.739 |
Neg logit contributions | |
soever | -5.850 |
�� | -5.763 |
adversary | -5.646 |
achine | -5.598 |
anooga | -5.539 |
Token | court |
Token ID | 2184 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
uid | +8.083 |
í | +6.947 |
女 | +6.932 |
quote | +6.900 |
Ladies | +6.285 |
Neg logit contributions | |
�� | -11.325 |
soever | -11.318 |
Canaver | -10.742 |
achine | -10.705 |
anooga | -10.581 |
Token | majority |
Token ID | 3741 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
uid | +8.548 |
í | +7.528 |
女 | +7.460 |
quote | +7.121 |
Ladies | +6.959 |
Neg logit contributions | |
soever | -8.217 |
�� | -7.878 |
achine | -7.697 |
Canaver | -7.682 |
adversary | -7.626 |
Token | that |
Token ID | 326 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
uid | +4.082 |
女 | +3.621 |
í | +3.505 |
quote | +3.455 |
Ladies | +3.259 |
Neg logit contributions | |
soever | -3.661 |
�� | -3.482 |
adversary | -3.475 |
achine | -3.417 |
Canaver | -3.348 |
Token | not |
Token ID | 407 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
uid | +2.294 |
女 | +2.042 |
quote | +1.958 |
í | +1.934 |
Ladies | +1.844 |
Neg logit contributions | |
soever | -1.972 |
adversary | -1.909 |
�� | -1.881 |
achine | -1.835 |
anooga | -1.784 |
Token | only |
Token ID | 691 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
uid | +1.638 |
女 | +1.473 |
í | +1.434 |
quote | +1.433 |
Ladies | +1.354 |
Neg logit contributions | |
soever | -1.002 |
adversary | -0.962 |
�� | -0.954 |
achine | -0.907 |
Canaver | -0.880 |
Token | all |
Token ID | 477 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
uid | +2.061 |
女 | +1.854 |
quote | +1.789 |
í | +1.766 |
Ladies | +1.703 |
Neg logit contributions | |
soever | -1.509 |
�� | -1.449 |
adversary | -1.447 |
achine | -1.385 |
anooga | -1.347 |
Token | 50 |
Token ID | 2026 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
uid | +0.576 |
女 | +0.516 |
quote | +0.492 |
í | +0.486 |
Ladies | +0.464 |
Neg logit contributions | |
soever | -0.513 |
adversary | -0.496 |
�� | -0.495 |
achine | -0.480 |
Canaver | -0.466 |
Token | states |
Token ID | 2585 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
soever | +1.453 |
adversary | +1.406 |
�� | +1.382 |
achine | +1.344 |
Canaver | +1.307 |
Neg logit contributions | |
uid | -1.592 |
女 | -1.418 |
quote | -1.352 |
í | -1.333 |
Ladies | -1.267 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
soever | +0.848 |
adversary | +0.819 |
�� | +0.798 |
achine | +0.776 |
anooga | +0.751 |
Neg logit contributions | |
uid | -1.037 |
女 | -0.927 |
quote | -0.889 |
í | -0.872 |
Ladies | -0.836 |
Token | The |
Token ID | 383 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
soever | +1.480 |
adversary | +1.385 |
�� | +1.341 |
achine | +1.341 |
Canaver | +1.339 |
Neg logit contributions | |
uid | -1.613 |
女 | -1.415 |
quote | -1.329 |
í | -1.290 |
united | -1.242 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
soever | +0.823 |
adversary | +0.816 |
�� | +0.779 |
achine | +0.758 |
Canaver | +0.732 |
Neg logit contributions | |
uid | -0.986 |
女 | -0.881 |
quote | -0.840 |
í | -0.823 |
Ladies | -0.777 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
uid | +6.712 |
í | +5.353 |
女 | +5.307 |
quote | +5.233 |
Ladies | +4.983 |
Neg logit contributions | |
soever | -13.303 |
�� | -13.243 |
adversary | -12.705 |
achine | -12.580 |
anooga | -12.421 |
Token | obviously |
Token ID | 6189 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
uid | +7.595 |
女 | +6.658 |
í | +6.590 |
quote | +6.553 |
Ladies | +6.323 |
Neg logit contributions | |
�� | -6.531 |
soever | -6.389 |
achine | -6.149 |
adversary | -5.995 |
anooga | -5.921 |
Token | didn |
Token ID | 1422 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
soever | +0.460 |
adversary | +0.448 |
�� | +0.420 |
achine | +0.413 |
Canaver | +0.403 |
Neg logit contributions | |
uid | -0.625 |
女 | -0.562 |
quote | -0.539 |
í | -0.523 |
Ladies | -0.504 |
Token | 't |
Token ID | 470 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
uid | +0.408 |
女 | +0.363 |
quote | +0.337 |
Ladies | +0.326 |
í | +0.317 |
Neg logit contributions | |
soever | -0.372 |
adversary | -0.362 |
achine | -0.349 |
Canaver | -0.337 |
�� | -0.333 |
Token | want |
Token ID | 765 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
soever | +0.985 |
adversary | +0.971 |
achine | +0.903 |
�� | +0.874 |
decomp | +0.856 |
Neg logit contributions | |
uid | -1.303 |
女 | -1.169 |
quote | -1.116 |
í | -1.075 |
Ladies | -1.059 |
Token | . |
Token ID | 13 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
soever | +0.954 |
adversary | +0.920 |
�� | +0.891 |
achine | +0.869 |
anooga | +0.843 |
Neg logit contributions | |
uid | -1.184 |
女 | -1.061 |
quote | -1.021 |
í | -0.995 |
Ladies | -0.958 |
Token | Whatever |
Token ID | 15935 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
soever | +0.483 |
adversary | +0.465 |
�� | +0.454 |
achine | +0.444 |
Canaver | +0.435 |
Neg logit contributions | |
uid | -0.491 |
女 | -0.436 |
quote | -0.413 |
í | -0.402 |
Ladies | -0.381 |
Token | recon |
Token ID | 8195 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
uid | +0.114 |
女 | +0.102 |
quote | +0.098 |
í | +0.097 |
Ladies | +0.093 |
Neg logit contributions | |
soever | -0.088 |
adversary | -0.085 |
�� | -0.083 |
achine | -0.080 |
anooga | -0.078 |
Token | figured |
Token ID | 46296 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
uid | +2.937 |
女 | +2.460 |
quote | +2.352 |
í | +2.335 |
Ladies | +2.123 |
Neg logit contributions | |
soever | -4.559 |
�� | -4.385 |
adversary | -4.377 |
achine | -4.294 |
Canaver | -4.216 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
uid | +1.428 |
女 | +1.272 |
quote | +1.221 |
í | +1.201 |
Ladies | +1.148 |
Neg logit contributions | |
soever | -1.228 |
adversary | -1.185 |
�� | -1.168 |
achine | -1.132 |
anooga | -1.100 |
Token | Court |
Token ID | 3078 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
uid | +7.294 |
í | +5.813 |
女 | +5.709 |
quote | +5.671 |
Ladies | +5.411 |
Neg logit contributions | |
�� | -14.918 |
soever | -14.870 |
adversary | -14.252 |
achine | -14.136 |
anooga | -14.096 |
Token | emerges |
Token ID | 25457 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
uid | +10.583 |
í | +9.461 |
女 | +9.280 |
quote | +8.940 |
Ladies | +8.634 |
Neg logit contributions | |
soever | -8.483 |
�� | -8.356 |
achine | -8.048 |
Canaver | -8.032 |
anooga | -7.893 |
Token | after |
Token ID | 706 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
uid | +0.305 |
女 | +0.274 |
quote | +0.263 |
í | +0.259 |
Ladies | +0.248 |
Neg logit contributions | |
soever | -0.231 |
adversary | -0.223 |
�� | -0.219 |
achine | -0.212 |
anooga | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
soever | +1.109 |
adversary | +1.077 |
�� | +1.045 |
achine | +1.014 |
Canaver | +0.985 |
Neg logit contributions | |
uid | -1.258 |
女 | -1.126 |
quote | -1.072 |
í | -1.050 |
Ladies | -1.004 |
Token | November |
Token ID | 3389 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
uid | +0.137 |
女 | +0.122 |
quote | +0.115 |
í | +0.113 |
Ladies | +0.107 |
Neg logit contributions | |
soever | -0.134 |
adversary | -0.131 |
�� | -0.127 |
achine | -0.124 |
Canaver | -0.121 |
Token | election |
Token ID | 3071 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
uid | +0.946 |
女 | +0.842 |
quote | +0.806 |
í | +0.792 |
Ladies | +0.756 |
Neg logit contributions | |
soever | -0.840 |
adversary | -0.814 |
�� | -0.798 |
achine | -0.775 |
anooga | -0.753 |
Token | coincidence |
Token ID | 21083 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
uid | +4.338 |
女 | +3.874 |
quote | +3.747 |
í | +3.743 |
Ladies | +3.547 |
Neg logit contributions | |
soever | -3.339 |
�� | -3.192 |
adversary | -3.187 |
achine | -3.062 |
anooga | -2.979 |
Token | , |
Token ID | 11 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
uid | +4.902 |
女 | +4.332 |
í | +4.191 |
quote | +4.173 |
Ladies | +3.933 |
Neg logit contributions | |
soever | -4.514 |
�� | -4.432 |
adversary | -4.413 |
achine | -4.259 |
anooga | -4.191 |
Token | natural |
Token ID | 3288 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
uid | +1.643 |
女 | +1.461 |
quote | +1.399 |
í | +1.378 |
Ladies | +1.313 |
Neg logit contributions | |
soever | -1.480 |
adversary | -1.433 |
�� | -1.409 |
achine | -1.367 |
anooga | -1.329 |
Token | occurrence |
Token ID | 19810 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
uid | +3.715 |
女 | +3.370 |
quote | +3.233 |
í | +3.220 |
Ladies | +3.034 |
Neg logit contributions | |
soever | -2.602 |
�� | -2.499 |
adversary | -2.457 |
achine | -2.427 |
anooga | -2.329 |
Token | or |
Token ID | 393 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
uid | +1.198 |
女 | +1.072 |
quote | +1.031 |
í | +1.021 |
Ladies | +0.966 |
Neg logit contributions | |
soever | -1.013 |
adversary | -0.982 |
�� | -0.978 |
achine | -0.940 |
anooga | -0.919 |
Token | mis |
Token ID | 2984 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
uid | +1.027 |
女 | +0.923 |
quote | +0.889 |
í | +0.877 |
Ladies | +0.838 |
Neg logit contributions | |
soever | -0.768 |
adversary | -0.740 |
�� | -0.734 |
achine | -0.708 |
anooga | -0.687 |
Token | ident |
Token ID | 738 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
uid | +8.533 |
quote | +7.635 |
í | +7.322 |
女 | +6.922 |
united | +6.558 |
Neg logit contributions | |
adversary | -10.541 |
soever | -10.402 |
�� | -10.260 |
achine | -10.193 |
anooga | -9.932 |
Token | ification |
Token ID | 2649 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
uid | +3.035 |
女 | +2.712 |
quote | +2.654 |
í | +2.641 |
Ladies | +2.510 |
Neg logit contributions | |
soever | -1.791 |
adversary | -1.734 |
�� | -1.714 |
achine | -1.623 |
anooga | -1.579 |
Token | and |
Token ID | 290 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
uid | +4.632 |
女 | +4.090 |
í | +3.971 |
quote | +3.968 |
Ladies | +3.701 |
Neg logit contributions | |
soever | -4.246 |
�� | -4.180 |
adversary | -4.129 |
achine | -4.018 |
anooga | -3.928 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
uid | +1.754 |
女 | +1.572 |
quote | +1.513 |
í | +1.493 |
Ladies | +1.424 |
Neg logit contributions | |
soever | -1.391 |
adversary | -1.346 |
�� | -1.329 |
achine | -1.286 |
anooga | -1.250 |
Token | � |
Token ID | 564 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
uid | +0.843 |
女 | +0.759 |
quote | +0.730 |
í | +0.719 |
Ladies | +0.690 |
Neg logit contributions | |
soever | -0.592 |
adversary | -0.571 |
�� | -0.558 |
achine | -0.539 |
anooga | -0.522 |
Token | compiling |
Token ID | 33393 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
uid | +0.406 |
女 | +0.361 |
quote | +0.350 |
í | +0.344 |
Ladies | +0.331 |
Neg logit contributions | |
soever | -0.323 |
�� | -0.307 |
adversary | -0.307 |
achine | -0.294 |
anooga | -0.287 |
Token | a |
Token ID | 257 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
uid | +2.876 |
女 | +2.547 |
quote | +2.475 |
í | +2.434 |
Ladies | +2.358 |
Neg logit contributions | |
soever | -2.408 |
�� | -2.296 |
adversary | -2.262 |
achine | -2.213 |
anooga | -2.160 |
Token | list |
Token ID | 1351 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
uid | +2.360 |
女 | +2.112 |
quote | +2.030 |
í | +1.993 |
Ladies | +1.924 |
Neg logit contributions | |
soever | -1.961 |
adversary | -1.865 |
�� | -1.860 |
achine | -1.794 |
anooga | -1.748 |
Token | of |
Token ID | 286 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
uid | +0.499 |
女 | +0.443 |
quote | +0.425 |
í | +0.418 |
Ladies | +0.395 |
Neg logit contributions | |
soever | -0.450 |
adversary | -0.432 |
�� | -0.428 |
achine | -0.412 |
anooga | -0.404 |
Token | possible |
Token ID | 1744 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
uid | +2.273 |
女 | +2.030 |
quote | +1.958 |
í | +1.940 |
Ladies | +1.875 |
Neg logit contributions | |
soever | -1.722 |
�� | -1.634 |
adversary | -1.618 |
achine | -1.576 |
anooga | -1.529 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
uid | +2.961 |
女 | +2.648 |
quote | +2.580 |
í | +2.525 |
Ladies | +2.462 |
Neg logit contributions | |
soever | -2.211 |
�� | -2.098 |
adversary | -2.057 |
achine | -2.030 |
anooga | -1.965 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
uid | +6.709 |
quote | +5.355 |
í | +5.355 |
女 | +5.350 |
Ladies | +5.079 |
Neg logit contributions | |
�� | -12.910 |
soever | -12.831 |
adversary | -12.466 |
achine | -12.206 |
anooga | -12.129 |
Token | nominees |
Token ID | 26456 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
uid | +7.369 |
í | +6.026 |
女 | +5.946 |
quote | +5.833 |
Ladies | +5.802 |
Neg logit contributions | |
�� | -10.599 |
soever | -10.566 |
achine | -10.313 |
anooga | -10.017 |
adversary | -9.894 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
uid | +3.921 |
女 | +3.509 |
í | +3.336 |
quote | +3.336 |
Ladies | +3.179 |
Neg logit contributions | |
soever | -3.468 |
�� | -3.411 |
adversary | -3.344 |
achine | -3.273 |
anooga | -3.180 |
Token | It |
Token ID | 632 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
uid | +0.543 |
女 | +0.479 |
quote | +0.456 |
í | +0.447 |
Ladies | +0.425 |
Neg logit contributions | |
soever | -0.548 |
adversary | -0.532 |
�� | -0.521 |
achine | -0.508 |
Canaver | -0.495 |
Token | was |
Token ID | 373 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
uid | +0.677 |
女 | +0.605 |
quote | +0.579 |
í | +0.569 |
Ladies | +0.545 |
Neg logit contributions | |
soever | -0.564 |
adversary | -0.546 |
�� | -0.534 |
achine | -0.518 |
anooga | -0.503 |
Token | actions |
Token ID | 4028 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
uid | +2.638 |
女 | +2.331 |
quote | +2.249 |
í | +2.214 |
Ladies | +2.107 |
Neg logit contributions | |
soever | -2.369 |
adversary | -2.281 |
�� | -2.260 |
achine | -2.177 |
anooga | -2.144 |
Token | s |
Token ID | 264 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
uid | +5.664 |
女 | +4.974 |
quote | +4.834 |
í | +4.793 |
Ladies | +4.520 |
Neg logit contributions | |
soever | -5.057 |
�� | -4.873 |
adversary | -4.820 |
anooga | -4.634 |
achine | -4.617 |
Token | ont |
Token ID | 756 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
uid | +6.442 |
í | +5.287 |
女 | +5.155 |
quote | +5.084 |
ú | +4.737 |
Neg logit contributions | |
soever | -8.281 |
�� | -8.269 |
adversary | -8.118 |
Canaver | -7.860 |
anooga | -7.800 |
Token | enc |
Token ID | 2207 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
uid | +0.995 |
女 | +0.885 |
quote | +0.849 |
í | +0.835 |
Ladies | +0.797 |
Neg logit contributions | |
soever | -0.870 |
adversary | -0.840 |
�� | -0.828 |
achine | -0.801 |
anooga | -0.780 |
Token | ore |
Token ID | 382 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
uid | +1.670 |
女 | +1.498 |
quote | +1.455 |
í | +1.443 |
Ladies | +1.377 |
Neg logit contributions | |
soever | -0.925 |
adversary | -0.887 |
�� | -0.874 |
achine | -0.813 |
anooga | -0.803 |
Token | obsc |
Token ID | 10666 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
uid | +2.529 |
女 | +2.217 |
quote | +2.129 |
í | +2.093 |
Ladies | +1.984 |
Neg logit contributions | |
soever | -2.508 |
adversary | -2.434 |
�� | -2.397 |
achine | -2.323 |
anooga | -2.285 |
Token | ures |
Token ID | 942 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
uid | +9.910 |
í | +8.349 |
quote | +7.979 |
ú | +7.923 |
女 | +7.699 |
Neg logit contributions | |
�� | -10.065 |
soever | -9.968 |
adversary | -9.862 |
Canaver | -9.091 |
anooga | -8.967 |
Token | : |
Token ID | 1058 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
uid | +4.538 |
女 | +3.940 |
quote | +3.842 |
í | +3.795 |
Ladies | +3.558 |
Neg logit contributions | |
soever | -4.478 |
adversary | -4.328 |
�� | -4.312 |
achine | -4.145 |
anooga | -4.137 |
Token | les |
Token ID | 10287 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
uid | +2.641 |
女 | +2.341 |
quote | +2.273 |
í | +2.227 |
Ladies | +2.124 |
Neg logit contributions | |
soever | -2.369 |
adversary | -2.277 |
�� | -2.270 |
achine | -2.164 |
anooga | -2.139 |
Token | mut |
Token ID | 4517 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
uid | +5.192 |
女 | +4.620 |
quote | +4.482 |
í | +4.434 |
Ladies | +4.250 |
Neg logit contributions | |
soever | -3.888 |
�� | -3.720 |
adversary | -3.643 |
anooga | -3.544 |
achine | -3.535 |
Token | ins |
Token ID | 1040 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
uid | +3.597 |
女 | +3.072 |
í | +3.039 |
quote | +3.002 |
Ladies | +2.791 |
Neg logit contributions | |
soever | -3.114 |
adversary | -3.018 |
�� | -3.001 |
achine | -2.791 |
Canaver | -2.772 |
Token | come |
Token ID | 1282 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
soever | +0.717 |
adversary | +0.694 |
�� | +0.674 |
achine | +0.654 |
Canaver | +0.634 |
Neg logit contributions | |
uid | -0.980 |
女 | -0.878 |
quote | -0.847 |
í | -0.827 |
Ladies | -0.796 |
Token | in |
Token ID | 287 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
soever | +1.480 |
adversary | +1.426 |
�� | +1.377 |
achine | +1.352 |
anooga | +1.302 |
Neg logit contributions | |
uid | -1.945 |
女 | -1.732 |
quote | -1.679 |
í | -1.636 |
Ladies | -1.571 |
Token | border |
Token ID | 4865 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
uid | +0.684 |
女 | +0.612 |
quote | +0.586 |
í | +0.578 |
Ladies | +0.555 |
Neg logit contributions | |
soever | -0.555 |
adversary | -0.533 |
�� | -0.529 |
achine | -0.507 |
anooga | -0.497 |
Token | cities |
Token ID | 4736 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
soever | +1.868 |
adversary | +1.822 |
�� | +1.735 |
achine | +1.702 |
anooga | +1.645 |
Neg logit contributions | |
uid | -2.705 |
女 | -2.436 |
quote | -2.346 |
í | -2.286 |
Ladies | -2.208 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
soever | +1.747 |
adversary | +1.697 |
�� | +1.634 |
achine | +1.600 |
Canaver | +1.543 |
Neg logit contributions | |
uid | -2.157 |
女 | -1.924 |
quote | -1.852 |
í | -1.799 |
Ladies | -1.735 |
Token | initially |
Token ID | 7317 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
uid | +1.119 |
女 | +1.005 |
quote | +0.964 |
í | +0.953 |
Ladies | +0.911 |
Neg logit contributions | |
soever | -0.851 |
adversary | -0.819 |
�� | -0.807 |
achine | -0.779 |
anooga | -0.756 |
Token | with |
Token ID | 351 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
soever | +4.222 |
adversary | +4.176 |
�� | +3.801 |
achine | +3.800 |
anooga | +3.657 |
Neg logit contributions | |
uid | -5.935 |
女 | -5.206 |
quote | -5.099 |
í | -4.858 |
Ladies | -4.732 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
uid | +1.593 |
女 | +1.426 |
quote | +1.364 |
í | +1.358 |
Ladies | +1.305 |
Neg logit contributions | |
soever | -1.286 |
�� | -1.221 |
adversary | -1.217 |
achine | -1.175 |
anooga | -1.141 |
Token | dispatch |
Token ID | 27965 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
uid | +0.979 |
女 | +0.881 |
quote | +0.849 |
í | +0.837 |
Ladies | +0.805 |
Neg logit contributions | |
soever | -0.702 |
adversary | -0.668 |
�� | -0.659 |
achine | -0.637 |
Canaver | -0.615 |
Token | of |
Token ID | 286 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
uid | +3.292 |
女 | +2.874 |
í | +2.804 |
quote | +2.728 |
ú | +2.518 |
Neg logit contributions | |
soever | -3.522 |
adversary | -3.340 |
�� | -3.264 |
achine | -3.164 |
Canaver | -3.104 |
Token | tanks |
Token ID | 11657 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
uid | +2.525 |
女 | +2.273 |
í | +2.194 |
quote | +2.180 |
Ladies | +2.100 |
Neg logit contributions | |
soever | -1.796 |
�� | -1.682 |
adversary | -1.676 |
achine | -1.623 |
anooga | -1.574 |
Token | bureau |
Token ID | 10583 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
soever | +0.079 |
adversary | +0.077 |
�� | +0.075 |
achine | +0.072 |
anooga | +0.070 |
Neg logit contributions | |
uid | -0.101 |
女 | -0.091 |
quote | -0.087 |
í | -0.085 |
Ladies | -0.081 |
Token | � |
Token ID | 447 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
uid | +4.202 |
女 | +3.641 |
í | +3.541 |
quote | +3.454 |
Ladies | +3.259 |
Neg logit contributions | |
soever | -4.652 |
adversary | -4.507 |
�� | -4.489 |
achine | -4.416 |
Canaver | -4.276 |
Token | � |
Token ID | 247 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
uid | +1.822 |
女 | +1.598 |
quote | +1.521 |
í | +1.474 |
Ladies | +1.404 |
Neg logit contributions | |
soever | -2.172 |
adversary | -2.116 |
�� | -2.085 |
achine | -2.016 |
anooga | -1.970 |
Token | s |
Token ID | 82 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
uid | +2.624 |
女 | +2.316 |
quote | +2.235 |
í | +2.235 |
Ladies | +2.095 |
Neg logit contributions | |
soever | -2.138 |
adversary | -2.071 |
�� | -2.067 |
achine | -1.985 |
Canaver | -1.927 |
Token | many |
Token ID | 867 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
uid | +0.931 |
女 | +0.839 |
quote | +0.804 |
í | +0.782 |
Ladies | +0.754 |
Neg logit contributions | |
soever | -0.706 |
adversary | -0.685 |
�� | -0.660 |
achine | -0.636 |
Canaver | -0.618 |
Token | tech |
Token ID | 7261 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
uid | +1.097 |
女 | +0.986 |
quote | +0.946 |
í | +0.928 |
Ladies | +0.891 |
Neg logit contributions | |
soever | -0.831 |
adversary | -0.804 |
�� | -0.784 |
achine | -0.757 |
anooga | -0.734 |
Token | teams |
Token ID | 3466 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
soever | +3.612 |
adversary | +3.555 |
�� | +3.274 |
anooga | +3.151 |
achine | +3.143 |
Neg logit contributions | |
uid | -5.701 |
女 | -5.209 |
quote | -4.926 |
í | -4.700 |
Ladies | -4.692 |
Token | conduct |
Token ID | 3189 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
soever | +1.595 |
adversary | +1.554 |
achine | +1.423 |
�� | +1.420 |
Canaver | +1.376 |
Neg logit contributions | |
uid | -2.104 |
女 | -1.899 |
quote | -1.811 |
í | -1.728 |
Ladies | -1.703 |
Token | its |
Token ID | 663 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
soever | +0.902 |
adversary | +0.876 |
�� | +0.849 |
achine | +0.817 |
Canaver | +0.791 |
Neg logit contributions | |
uid | -1.295 |
女 | -1.167 |
quote | -1.122 |
í | -1.100 |
Ladies | -1.063 |
Token | own |
Token ID | 898 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
soever | +1.030 |
adversary | +1.004 |
�� | +0.943 |
achine | +0.899 |
Canaver | +0.867 |
Neg logit contributions | |
uid | -1.909 |
女 | -1.741 |
quote | -1.682 |
í | -1.641 |
Ladies | -1.597 |
Token | investigation |
Token ID | 3645 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
soever | +0.132 |
adversary | +0.126 |
�� | +0.122 |
achine | +0.117 |
anooga | +0.112 |
Neg logit contributions | |
uid | -0.251 |
女 | -0.228 |
quote | -0.221 |
í | -0.217 |
Ladies | -0.210 |
Token | then |
Token ID | 788 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
soever | +1.395 |
adversary | +1.349 |
�� | +1.309 |
achine | +1.261 |
Canaver | +1.243 |
Neg logit contributions | |
uid | -1.803 |
女 | -1.614 |
quote | -1.539 |
í | -1.496 |
Ladies | -1.455 |
Token | - |
Token ID | 12 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
soever | +2.911 |
adversary | +2.823 |
�� | +2.699 |
achine | +2.598 |
Canaver | +2.588 |
Neg logit contributions | |
uid | -3.783 |
女 | -3.380 |
quote | -3.212 |
í | -3.118 |
united | -3.034 |
Token | Sea |
Token ID | 37567 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
uid | +1.298 |
女 | +1.152 |
quote | +1.106 |
í | +1.086 |
Ladies | +1.031 |
Neg logit contributions | |
soever | -1.162 |
adversary | -1.121 |
�� | -1.104 |
achine | -1.070 |
Canaver | -1.040 |
Token | World |
Token ID | 10603 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
soever | +2.295 |
adversary | +2.292 |
achine | +2.175 |
�� | +2.145 |
anooga | +2.079 |
Neg logit contributions | |
uid | -2.776 |
女 | -2.508 |
quote | -2.400 |
í | -2.302 |
Ladies | -2.214 |
Token | CEO |
Token ID | 6123 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
uid | +1.842 |
女 | +1.622 |
quote | +1.549 |
í | +1.526 |
Ladies | +1.448 |
Neg logit contributions | |
soever | -1.898 |
adversary | -1.836 |
�� | -1.811 |
achine | -1.760 |
anooga | -1.711 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
soever | +1.347 |
adversary | +1.302 |
�� | +1.266 |
achine | +1.229 |
Canaver | +1.198 |
Neg logit contributions | |
uid | -1.759 |
女 | -1.583 |
quote | -1.517 |
í | -1.484 |
Ladies | -1.419 |
Token | At |
Token ID | 1629 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
soever | +5.612 |
adversary | +5.335 |
Canaver | +5.311 |
achine | +5.231 |
�� | +5.193 |
Neg logit contributions | |
uid | -7.015 |
女 | -6.593 |
quote | -6.140 |
united | -5.714 |
í | -5.692 |
Token | ch |
Token ID | 354 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
soever | +3.308 |
adversary | +3.206 |
achine | +3.109 |
�� | +3.034 |
anooga | +2.932 |
Neg logit contributions | |
uid | -4.333 |
女 | -4.036 |
quote | -3.798 |
í | -3.612 |
Ladies | -3.593 |
Token | ison |
Token ID | 1653 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
soever | +1.983 |
adversary | +1.906 |
�� | +1.856 |
achine | +1.814 |
anooga | +1.740 |
Neg logit contributions | |
uid | -2.881 |
女 | -2.607 |
quote | -2.501 |
í | -2.447 |
Ladies | -2.365 |
Token | said |
Token ID | 531 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
uid | +0.518 |
女 | +0.463 |
quote | +0.443 |
í | +0.434 |
Ladies | +0.416 |
Neg logit contributions | |
soever | -0.427 |
adversary | -0.414 |
�� | -0.404 |
achine | -0.392 |
anooga | -0.381 |
Token | in |
Token ID | 287 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
soever | +0.242 |
adversary | +0.234 |
�� | +0.229 |
achine | +0.221 |
Canaver | +0.215 |
Neg logit contributions | |
uid | -0.301 |
女 | -0.269 |
quote | -0.258 |
í | -0.253 |
Ladies | -0.243 |
Token | ( |
Token ID | 357 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
uid | +2.341 |
女 | +2.075 |
í | +2.010 |
quote | +1.986 |
Ladies | +1.864 |
Neg logit contributions | |
soever | -2.463 |
�� | -2.373 |
adversary | -2.360 |
achine | -2.298 |
anooga | -2.258 |
Token | all |
Token ID | 439 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
soever | +0.738 |
adversary | +0.714 |
�� | +0.698 |
achine | +0.677 |
anooga | +0.656 |
Neg logit contributions | |
uid | -0.912 |
女 | -0.816 |
quote | -0.782 |
í | -0.768 |
Ladies | -0.738 |
Token | pro |
Token ID | 386 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
uid | +0.576 |
女 | +0.517 |
quote | +0.497 |
í | +0.492 |
Ladies | +0.468 |
Neg logit contributions | |
soever | -0.436 |
adversary | -0.422 |
�� | -0.414 |
achine | -0.400 |
anooga | -0.389 |
Token | - |
Token ID | 12 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
soever | +0.042 |
adversary | +0.041 |
�� | +0.041 |
Canaver | +0.040 |
achine | +0.039 |
Neg logit contributions | |
uid | -0.041 |
女 | -0.037 |
í | -0.035 |
quote | -0.035 |
Ladies | -0.032 |
Token | independence |
Token ID | 39894 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
soever | +4.429 |
adversary | +4.259 |
�� | +4.060 |
achine | +3.991 |
anooga | +3.814 |
Neg logit contributions | |
uid | -5.443 |
女 | -4.910 |
quote | -4.657 |
í | -4.539 |
Ladies | -4.503 |
Token | parties |
Token ID | 4671 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
soever | +4.320 |
adversary | +4.157 |
�� | +3.860 |
achine | +3.769 |
Canaver | +3.545 |
Neg logit contributions | |
uid | -6.814 |
女 | -6.056 |
quote | -5.851 |
í | -5.525 |
united | -5.491 |
Token | form |
Token ID | 1296 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
soever | +4.563 |
adversary | +4.433 |
achine | +4.072 |
�� | +3.934 |
Canaver | +3.906 |
Neg logit contributions | |
uid | -6.213 |
女 | -5.540 |
quote | -5.276 |
Ladies | -4.949 |
í | -4.944 |
Token | a |
Token ID | 257 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
soever | +0.404 |
adversary | +0.390 |
�� | +0.381 |
achine | +0.368 |
anooga | +0.356 |
Neg logit contributions | |
uid | -0.561 |
女 | -0.505 |
quote | -0.486 |
í | -0.477 |
Ladies | -0.459 |
Token | legislative |
Token ID | 10828 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
uid | +1.861 |
女 | +1.671 |
quote | +1.599 |
í | +1.580 |
Ladies | +1.509 |
Neg logit contributions | |
soever | -1.510 |
adversary | -1.454 |
�� | -1.431 |
achine | -1.384 |
anooga | -1.349 |
Token | majority |
Token ID | 3741 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
uid | +0.895 |
女 | +0.806 |
quote | +0.775 |
í | +0.763 |
Ladies | +0.732 |
Neg logit contributions | |
soever | -0.636 |
adversary | -0.614 |
�� | -0.600 |
achine | -0.580 |
anooga | -0.561 |
Token | of |
Token ID | 286 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
uid | +1.121 |
女 | +1.005 |
quote | +0.962 |
í | +0.953 |
Ladies | +0.905 |
Neg logit contributions | |
soever | -0.888 |
adversary | -0.855 |
�� | -0.845 |
achine | -0.813 |
anooga | -0.796 |
Token | promotional |
Token ID | 18767 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
uid | +0.036 |
女 | +0.033 |
quote | +0.030 |
í | +0.030 |
Ladies | +0.028 |
Neg logit contributions | |
soever | -0.029 |
adversary | -0.029 |
achine | -0.027 |
�� | -0.027 |
Canaver | -0.026 |
Token | offers |
Token ID | 4394 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
uid | +0.526 |
女 | +0.480 |
quote | +0.459 |
í | +0.452 |
Ladies | +0.431 |
Neg logit contributions | |
soever | -0.297 |
adversary | -0.292 |
achine | -0.273 |
�� | -0.270 |
Canaver | -0.257 |
Token | for |
Token ID | 329 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
uid | +1.513 |
女 | +1.374 |
quote | +1.313 |
í | +1.277 |
Ladies | +1.249 |
Neg logit contributions | |
soever | -0.888 |
adversary | -0.853 |
achine | -0.798 |
�� | -0.794 |
Canaver | -0.763 |
Token | programs |
Token ID | 4056 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
soever | +1.050 |
adversary | +1.017 |
achine | +0.893 |
exemplary | +0.882 |
�� | +0.861 |
Neg logit contributions | |
uid | -2.597 |
女 | -2.385 |
quote | -2.305 |
í | -2.232 |
tta | -2.166 |
Token | that |
Token ID | 326 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
adversary | +2.469 |
soever | +2.428 |
achine | +2.211 |
weakness | +2.207 |
decomp | +2.176 |
Neg logit contributions | |
uid | -6.201 |
女 | -5.753 |
quote | -5.328 |
Ladies | -5.271 |
í | -5.052 |
Token | support |
Token ID | 1104 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
adversary | +2.157 |
soever | +2.040 |
weakness | +1.840 |
decomp | +1.799 |
achine | +1.797 |
Neg logit contributions | |
uid | -4.116 |
女 | -3.815 |
quote | -3.562 |
Ladies | -3.402 |
| -3.359 |
Token | The |
Token ID | 383 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
adversary | +3.578 |
soever | +3.575 |
�� | +3.376 |
achine | +3.346 |
exemplary | +3.213 |
Neg logit contributions | |
uid | -4.944 |
女 | -4.379 |
quote | -4.140 |
í | -3.965 |
sell | -3.810 |
Token | Nation |
Token ID | 8741 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
adversary | +2.509 |
soever | +2.393 |
weakness | +2.134 |
achine | +2.126 |
�� | +2.105 |
Neg logit contributions | |
uid | -4.457 |
女 | -4.165 |
quote | -3.889 |
í | -3.703 |
Ladies | -3.619 |
Token | � |
Token ID | 447 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
adversary | +2.198 |
soever | +2.172 |
achine | +1.975 |
weakness | +1.934 |
intruder | +1.912 |
Neg logit contributions | |
uid | -3.004 |
女 | -2.728 |
quote | -2.579 |
Ladies | -2.449 |
united | -2.409 |
Token | � |
Token ID | 247 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
soever | +3.616 |
adversary | +3.611 |
�� | +3.422 |
achine | +3.247 |
anooga | +3.203 |
Neg logit contributions | |
uid | -4.077 |
女 | -3.785 |
quote | -3.651 |
Ladies | -3.480 |
united | -3.422 |
Token | s |
Token ID | 82 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
soever | +0.138 |
adversary | +0.132 |
achine | +0.126 |
�� | +0.117 |
Canaver | +0.117 |
Neg logit contributions | |
uid | -0.245 |
女 | -0.222 |
quote | -0.213 |
Ladies | -0.206 |
í | -0.202 |
Token | � |
Token ID | 247 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
soever | +1.275 |
�� | +1.244 |
adversary | +1.244 |
achine | +1.157 |
anooga | +1.132 |
Neg logit contributions | |
uid | -1.272 |
女 | -1.128 |
quote | -1.108 |
í | -1.037 |
united | -1.018 |
Token | s |
Token ID | 82 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
uid | +1.583 |
女 | +1.401 |
quote | +1.327 |
í | +1.320 |
Ladies | +1.245 |
Neg logit contributions | |
soever | -1.566 |
adversary | -1.523 |
�� | -1.495 |
achine | -1.458 |
anooga | -1.423 |
Token | a |
Token ID | 257 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
soever | +0.852 |
adversary | +0.823 |
�� | +0.801 |
achine | +0.777 |
Canaver | +0.752 |
Neg logit contributions | |
uid | -1.178 |
女 | -1.057 |
quote | -1.018 |
í | -0.996 |
Ladies | -0.960 |
Token | lot |
Token ID | 1256 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
soever | +0.635 |
adversary | +0.616 |
�� | +0.598 |
achine | +0.578 |
anooga | +0.559 |
Neg logit contributions | |
uid | -0.885 |
女 | -0.793 |
quote | -0.762 |
í | -0.748 |
Ladies | -0.717 |
Token | of |
Token ID | 286 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
soever | +2.100 |
adversary | +2.038 |
�� | +1.987 |
achine | +1.928 |
Canaver | +1.868 |
Neg logit contributions | |
uid | -2.733 |
女 | -2.452 |
quote | -2.351 |
í | -2.303 |
Ladies | -2.221 |
Token | anger |
Token ID | 8993 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
soever | +0.802 |
adversary | +0.784 |
�� | +0.752 |
achine | +0.731 |
Canaver | +0.708 |
Neg logit contributions | |
uid | -1.177 |
女 | -1.063 |
quote | -1.015 |
í | -0.998 |
Ladies | -0.960 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
soever | +1.608 |
adversary | +1.551 |
�� | +1.498 |
achine | +1.481 |
anooga | +1.419 |
Neg logit contributions | |
uid | -2.090 |
女 | -1.868 |
quote | -1.786 |
í | -1.746 |
Ladies | -1.696 |
Token | there |
Token ID | 612 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
soever | +0.934 |
adversary | +0.902 |
�� | +0.871 |
achine | +0.847 |
Canaver | +0.818 |
Neg logit contributions | |
uid | -1.297 |
女 | -1.171 |
quote | -1.119 |
í | -1.094 |
Ladies | -1.056 |
Token | � |
Token ID | 447 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
soever | +0.499 |
adversary | +0.484 |
�� | +0.475 |
achine | +0.461 |
Canaver | +0.447 |
Neg logit contributions | |
uid | -0.574 |
女 | -0.512 |
quote | -0.490 |
í | -0.483 |
Ladies | -0.460 |
Token | � |
Token ID | 247 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
soever | +1.664 |
�� | +1.626 |
adversary | +1.625 |
achine | +1.519 |
Canaver | +1.489 |
Neg logit contributions | |
uid | -1.630 |
女 | -1.441 |
quote | -1.412 |
í | -1.332 |
Ladies | -1.292 |
Token | s |
Token ID | 82 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
uid | +1.204 |
女 | +1.076 |
quote | +1.028 |
í | +1.025 |
Ladies | +0.968 |
Neg logit contributions | |
soever | -0.989 |
adversary | -0.964 |
�� | -0.951 |
achine | -0.917 |
anooga | -0.894 |
Token | � |
Token ID | 447 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
uid | +0.443 |
女 | +0.400 |
quote | +0.383 |
í | +0.382 |
Ladies | +0.362 |
Neg logit contributions | |
soever | -0.321 |
adversary | -0.310 |
�� | -0.305 |
achine | -0.294 |
Canaver | -0.285 |
Token | � |
Token ID | 247 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
soever | +0.461 |
adversary | +0.447 |
�� | +0.442 |
achine | +0.418 |
anooga | +0.409 |
Neg logit contributions | |
uid | -0.434 |
女 | -0.385 |
quote | -0.371 |
í | -0.351 |
united | -0.342 |
Token | s |
Token ID | 82 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
uid | +2.783 |
女 | +2.482 |
quote | +2.380 |
í | +2.377 |
Ladies | +2.235 |
Neg logit contributions | |
soever | -2.282 |
adversary | -2.223 |
�� | -2.212 |
achine | -2.103 |
anooga | -2.066 |
Token | a |
Token ID | 257 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
uid | +0.201 |
女 | +0.180 |
quote | +0.173 |
í | +0.170 |
Ladies | +0.164 |
Neg logit contributions | |
soever | -0.146 |
adversary | -0.141 |
�� | -0.138 |
achine | -0.133 |
anooga | -0.129 |
Token | brilliant |
Token ID | 10457 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
uid | +2.257 |
女 | +2.043 |
quote | +1.962 |
í | +1.941 |
Ladies | +1.865 |
Neg logit contributions | |
soever | -1.620 |
adversary | -1.546 |
�� | -1.534 |
achine | -1.478 |
anooga | -1.434 |
Token | writer |
Token ID | 6260 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
uid | +0.519 |
女 | +0.469 |
quote | +0.451 |
í | +0.444 |
Ladies | +0.428 |
Neg logit contributions | |
soever | -0.328 |
adversary | -0.316 |
�� | -0.307 |
achine | -0.296 |
anooga | -0.286 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
uid | +0.420 |
女 | +0.376 |
quote | +0.359 |
í | +0.356 |
Ladies | +0.338 |
Neg logit contributions | |
soever | -0.359 |
adversary | -0.348 |
�� | -0.344 |
achine | -0.332 |
Canaver | -0.323 |
Token | � |
Token ID | 447 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
uid | +0.636 |
女 | +0.562 |
quote | +0.536 |
í | +0.526 |
Ladies | +0.500 |
Neg logit contributions | |
soever | -0.652 |
adversary | -0.634 |
�� | -0.622 |
achine | -0.605 |
anooga | -0.589 |
Token | � |
Token ID | 251 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
soever | +0.153 |
adversary | +0.149 |
�� | +0.146 |
achine | +0.143 |
anooga | +0.139 |
Neg logit contributions | |
uid | -0.142 |
女 | -0.125 |
quote | -0.119 |
í | -0.117 |
Ladies | -0.111 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
soever | +0.123 |
adversary | +0.119 |
�� | +0.117 |
achine | +0.114 |
anooga | +0.111 |
Neg logit contributions | |
uid | -0.119 |
女 | -0.105 |
quote | -0.100 |
í | -0.098 |
Ladies | -0.093 |
Token | Another |
Token ID | 6610 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
soever | +2.628 |
adversary | +2.532 |
�� | +2.489 |
achine | +2.419 |
anooga | +2.349 |
Neg logit contributions | |
uid | -3.055 |
女 | -2.735 |
quote | -2.580 |
í | -2.559 |
Ladies | -2.470 |
Token | inspired |
Token ID | 7867 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
soever | +3.486 |
adversary | +3.412 |
�� | +3.255 |
achine | +3.169 |
anooga | +3.028 |
Neg logit contributions | |
uid | -4.455 |
女 | -4.024 |
quote | -3.845 |
í | -3.731 |
Ladies | -3.581 |
Token | by |
Token ID | 416 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
soever | +2.747 |
adversary | +2.681 |
�� | +2.525 |
achine | +2.469 |
anooga | +2.369 |
Neg logit contributions | |
uid | -3.869 |
女 | -3.491 |
quote | -3.314 |
í | -3.264 |
united | -3.113 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
soever | +0.962 |
adversary | +0.935 |
�� | +0.908 |
achine | +0.883 |
Canaver | +0.856 |
Neg logit contributions | |
uid | -1.187 |
女 | -1.064 |
quote | -1.014 |
í | -0.997 |
Ladies | -0.951 |
Token | Three |
Token ID | 7683 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
uid | +0.825 |
女 | +0.737 |
quote | +0.712 |
í | +0.700 |
Ladies | +0.673 |
Neg logit contributions | |
soever | -0.654 |
adversary | -0.628 |
�� | -0.621 |
achine | -0.599 |
anooga | -0.582 |
Token | Fl |
Token ID | 1610 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
soever | +0.031 |
adversary | +0.030 |
�� | +0.029 |
achine | +0.029 |
anooga | +0.028 |
Neg logit contributions | |
uid | -0.038 |
女 | -0.034 |
quote | -0.033 |
í | -0.032 |
Ladies | -0.031 |
Token | oy |
Token ID | 726 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
uid | +2.704 |
女 | +2.205 |
í | +2.152 |
quote | +2.146 |
Ladies | +1.986 |
Neg logit contributions | |
soever | -3.172 |
adversary | -3.110 |
�� | -3.061 |
achine | -2.919 |
Canaver | -2.906 |
Token | ds |
Token ID | 9310 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
soever | +0.397 |
adversary | +0.384 |
�� | +0.377 |
achine | +0.365 |
Canaver | +0.355 |
Neg logit contributions | |
uid | -0.512 |
女 | -0.457 |
quote | -0.440 |
í | -0.435 |
Ladies | -0.416 |
Token | - |
Token ID | 12 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
soever | +0.091 |
adversary | +0.088 |
�� | +0.086 |
achine | +0.084 |
anooga | +0.081 |
Neg logit contributions | |
uid | -0.111 |
女 | -0.099 |
quote | -0.095 |
í | -0.093 |
Ladies | -0.089 |
Token | Half |
Token ID | 31305 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
soever | +0.223 |
adversary | +0.216 |
�� | +0.212 |
achine | +0.206 |
anooga | +0.201 |
Neg logit contributions | |
uid | -0.228 |
女 | -0.201 |
quote | -0.192 |
í | -0.189 |
Ladies | -0.180 |
Token | Ac |
Token ID | 4013 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
uid | +3.554 |
女 | +3.127 |
quote | +3.039 |
í | +2.983 |
Ladies | +2.899 |
Neg logit contributions | |
soever | -3.367 |
adversary | -3.298 |
�� | -3.263 |
achine | -3.131 |
Canaver | -3.091 |
Token | re |
Token ID | 260 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
uid | +1.465 |
女 | +1.246 |
quote | +1.186 |
í | +1.180 |
Ladies | +1.087 |
Neg logit contributions | |
soever | -1.747 |
adversary | -1.696 |
�� | -1.690 |
achine | -1.616 |
Canaver | -1.612 |
Token | Bel |
Token ID | 12193 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
uid | +0.396 |
女 | +0.353 |
quote | +0.337 |
í | +0.331 |
Ladies | +0.317 |
Neg logit contributions | |
soever | -0.353 |
adversary | -0.341 |
�� | -0.334 |
achine | -0.325 |
anooga | -0.316 |
Token | ieve |
Token ID | 12311 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
uid | +2.467 |
女 | +2.006 |
í | +1.976 |
quote | +1.933 |
Ladies | +1.748 |
Neg logit contributions | |
soever | -4.676 |
adversary | -4.578 |
�� | -4.549 |
achine | -4.352 |
Canaver | -4.311 |
Token | me |
Token ID | 502 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
soever | +0.174 |
adversary | +0.169 |
�� | +0.166 |
achine | +0.160 |
anooga | +0.156 |
Neg logit contributions | |
uid | -0.239 |
女 | -0.214 |
quote | -0.207 |
í | -0.205 |
Ladies | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
soever | +0.332 |
adversary | +0.322 |
�� | +0.317 |
achine | +0.306 |
anooga | +0.298 |
Neg logit contributions | |
uid | -0.389 |
女 | -0.348 |
quote | -0.333 |
í | -0.328 |
Ladies | -0.315 |
Token | Anna |
Token ID | 11735 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
soever | +0.207 |
adversary | +0.200 |
�� | +0.193 |
achine | +0.189 |
Canaver | +0.184 |
Neg logit contributions | |
uid | -0.244 |
女 | -0.217 |
quote | -0.208 |
í | -0.202 |
Ladies | -0.192 |
Token | . |
Token ID | 13 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
uid | +0.427 |
女 | +0.382 |
quote | +0.364 |
í | +0.364 |
Ladies | +0.348 |
Neg logit contributions | |
soever | -0.395 |
adversary | -0.384 |
�� | -0.380 |
achine | -0.369 |
Canaver | -0.358 |
Token | If |
Token ID | 1002 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
soever | +0.466 |
adversary | +0.441 |
�� | +0.425 |
achine | +0.425 |
Canaver | +0.419 |
Neg logit contributions | |
uid | -0.537 |
女 | -0.471 |
quote | -0.449 |
í | -0.432 |
united | -0.417 |
Token | I |
Token ID | 314 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
soever | +0.455 |
adversary | +0.440 |
�� | +0.430 |
achine | +0.417 |
anooga | +0.404 |
Neg logit contributions | |
uid | -0.577 |
女 | -0.516 |
quote | -0.495 |
í | -0.487 |
Ladies | -0.466 |
Token | want |
Token ID | 765 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
soever | +0.144 |
adversary | +0.142 |
achine | +0.132 |
�� | +0.131 |
Canaver | +0.127 |
Neg logit contributions | |
uid | -0.180 |
女 | -0.162 |
quote | -0.154 |
í | -0.148 |
Ladies | -0.144 |
Token | to |
Token ID | 284 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
soever | +1.862 |
adversary | +1.799 |
�� | +1.762 |
achine | +1.704 |
anooga | +1.654 |
Neg logit contributions | |
uid | -2.377 |
女 | -2.132 |
quote | -2.044 |
í | -2.013 |
Ladies | -1.929 |
Token | get |
Token ID | 651 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
soever | +2.550 |
adversary | +2.521 |
achine | +2.345 |
�� | +2.296 |
decomp | +2.245 |
Neg logit contributions | |
uid | -3.815 |
女 | -3.421 |
quote | -3.272 |
í | -3.163 |
united | -3.076 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
uid | +2.195 |
女 | +1.968 |
quote | +1.894 |
í | +1.860 |
Ladies | +1.780 |
Neg logit contributions | |
soever | -1.783 |
adversary | -1.718 |
�� | -1.687 |
achine | -1.638 |
anooga | -1.591 |
Token | arguments |
Token ID | 7159 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
uid | +1.077 |
女 | +0.970 |
quote | +0.930 |
í | +0.917 |
Ladies | +0.879 |
Neg logit contributions | |
soever | -0.747 |
adversary | -0.724 |
�� | -0.704 |
achine | -0.679 |
Canaver | -0.658 |
Token | against |
Token ID | 1028 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
uid | +0.981 |
女 | +0.879 |
quote | +0.843 |
í | +0.830 |
Ladies | +0.794 |
Neg logit contributions | |
soever | -0.773 |
adversary | -0.748 |
�� | -0.732 |
achine | -0.709 |
anooga | -0.687 |
Token | the |
Token ID | 262 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
soever | +2.066 |
adversary | +2.019 |
�� | +1.962 |
achine | +1.916 |
Canaver | +1.880 |
Neg logit contributions | |
uid | -1.928 |
女 | -1.689 |
quote | -1.595 |
í | -1.567 |
Ladies | -1.480 |
Token | comparison |
Token ID | 7208 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
soever | +0.038 |
adversary | +0.037 |
�� | +0.036 |
achine | +0.035 |
Canaver | +0.034 |
Neg logit contributions | |
uid | -0.045 |
女 | -0.040 |
quote | -0.038 |
í | -0.038 |
Ladies | -0.036 |
Token | instead |
Token ID | 2427 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
uid | +1.347 |
女 | +1.210 |
quote | +1.157 |
í | +1.142 |
Ladies | +1.092 |
Neg logit contributions | |
soever | -1.092 |
adversary | -1.053 |
�� | -1.037 |
achine | -1.002 |
Canaver | -0.973 |
Token | of |
Token ID | 286 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
soever | +1.958 |
adversary | +1.890 |
�� | +1.853 |
achine | +1.800 |
Canaver | +1.748 |
Neg logit contributions | |
uid | -2.235 |
女 | -1.996 |
quote | -1.909 |
í | -1.881 |
Ladies | -1.794 |
Token | , |
Token ID | 11 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
soever | +2.040 |
adversary | +1.996 |
�� | +1.905 |
achine | +1.844 |
Canaver | +1.799 |
Neg logit contributions | |
uid | -2.754 |
女 | -2.446 |
quote | -2.336 |
í | -2.299 |
united | -2.199 |
Token | say |
Token ID | 910 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
uid | +2.790 |
女 | +2.443 |
quote | +2.349 |
í | +2.323 |
Ladies | +2.217 |
Neg logit contributions | |
soever | -2.929 |
adversary | -2.818 |
�� | -2.796 |
achine | -2.711 |
anooga | -2.641 |
Token | , |
Token ID | 11 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
soever | +0.755 |
adversary | +0.733 |
achine | +0.685 |
�� | +0.679 |
Canaver | +0.664 |
Neg logit contributions | |
uid | -1.188 |
女 | -1.071 |
quote | -1.016 |
í | -0.986 |
united | -0.968 |
Token | listing |
Token ID | 13487 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
soever | +0.240 |
adversary | +0.233 |
�� | +0.227 |
achine | +0.220 |
Canaver | +0.213 |
Neg logit contributions | |
uid | -0.308 |
女 | -0.275 |
quote | -0.264 |
í | -0.260 |
Ladies | -0.248 |
Token | oad |
Token ID | 1170 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
uid | +0.086 |
女 | +0.074 |
quote | +0.071 |
í | +0.070 |
Ladies | +0.066 |
Neg logit contributions | |
soever | -0.102 |
adversary | -0.099 |
�� | -0.098 |
achine | -0.095 |
Canaver | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
soever | +3.349 |
adversary | +3.250 |
�� | +3.188 |
achine | +3.127 |
anooga | +3.010 |
Neg logit contributions | |
uid | -3.530 |
女 | -3.126 |
quote | -2.953 |
í | -2.923 |
Ladies | -2.770 |
Token | April |
Token ID | 3035 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
soever | +1.064 |
adversary | +1.041 |
�� | +1.014 |
achine | +0.985 |
Canaver | +0.957 |
Neg logit contributions | |
uid | -1.157 |
女 | -1.021 |
quote | -0.979 |
í | -0.962 |
Ladies | -0.910 |
Token | 18 |
Token ID | 1248 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
soever | +2.560 |
adversary | +2.501 |
�� | +2.363 |
achine | +2.348 |
Canaver | +2.267 |
Neg logit contributions | |
uid | -2.574 |
女 | -2.284 |
quote | -2.091 |
í | -2.034 |
united | -1.959 |
Token | th |
Token ID | 400 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
uid | +4.215 |
女 | +3.700 |
quote | +3.614 |
í | +3.503 |
Ladies | +3.290 |
Neg logit contributions | |
soever | -4.739 |
adversary | -4.572 |
�� | -4.541 |
achine | -4.367 |
anooga | -4.337 |
Token | , |
Token ID | 11 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
uid | +6.185 |
女 | +5.575 |
quote | +5.457 |
í | +5.263 |
Ladies | +5.096 |
Neg logit contributions | |
soever | -6.640 |
�� | -6.340 |
adversary | -6.283 |
Canaver | -6.138 |
achine | -6.075 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
uid | +2.291 |
女 | +1.944 |
quote | +1.832 |
í | +1.785 |
Ladies | +1.673 |
Neg logit contributions | |
soever | -3.852 |
adversary | -3.754 |
�� | -3.723 |
achine | -3.628 |
anooga | -3.568 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
uid | +0.922 |
女 | +0.817 |
quote | +0.780 |
í | +0.765 |
Ladies | +0.727 |
Neg logit contributions | |
soever | -1.011 |
adversary | -0.987 |
�� | -0.969 |
achine | -0.943 |
anooga | -0.923 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
uid | +0.130 |
女 | +0.118 |
quote | +0.110 |
í | +0.106 |
Ladies | +0.104 |
Neg logit contributions | |
soever | -0.104 |
adversary | -0.101 |
achine | -0.098 |
Canaver | -0.093 |
�� | -0.093 |
Token | Ko |
Token ID | 48735 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
uid | +0.626 |
女 | +0.558 |
quote | +0.538 |
í | +0.527 |
Ladies | +0.498 |
Neg logit contributions | |
soever | -0.525 |
adversary | -0.509 |
�� | -0.498 |
achine | -0.481 |
Canaver | -0.472 |
Token | Do |
Token ID | 5211 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
soever | +5.123 |
adversary | +5.000 |
�� | +4.875 |
achine | +4.851 |
anooga | +4.673 |
Neg logit contributions | |
uid | -5.703 |
女 | -5.018 |
quote | -4.823 |
í | -4.653 |
Ladies | -4.529 |
Token | water |
Token ID | 1660 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
soever | +0.184 |
adversary | +0.177 |
�� | +0.173 |
achine | +0.167 |
anooga | +0.161 |
Neg logit contributions | |
uid | -0.271 |
女 | -0.245 |
quote | -0.235 |
í | -0.232 |
Ladies | -0.223 |
Token | supply |
Token ID | 5127 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
uid | +0.662 |
女 | +0.595 |
quote | +0.571 |
í | +0.562 |
Ladies | +0.539 |
Neg logit contributions | |
soever | -0.486 |
adversary | -0.470 |
�� | -0.459 |
achine | -0.444 |
anooga | -0.430 |
Token | from |
Token ID | 422 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
uid | +1.333 |
女 | +1.191 |
quote | +1.143 |
í | +1.132 |
Ladies | +1.075 |
Neg logit contributions | |
soever | -1.114 |
adversary | -1.081 |
�� | -1.070 |
achine | -1.031 |
anooga | -1.004 |
Token | the |
Token ID | 262 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
uid | +2.281 |
女 | +2.033 |
quote | +1.956 |
í | +1.941 |
Ladies | +1.856 |
Neg logit contributions | |
soever | -1.871 |
adversary | -1.807 |
�� | -1.780 |
achine | -1.735 |
anooga | -1.684 |
Token | airport |
Token ID | 9003 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
uid | +2.928 |
女 | +2.610 |
quote | +2.515 |
í | +2.494 |
Ladies | +2.398 |
Neg logit contributions | |
soever | -2.369 |
adversary | -2.281 |
�� | -2.255 |
achine | -2.189 |
anooga | -2.134 |
Token | , |
Token ID | 11 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
uid | +4.507 |
女 | +3.936 |
í | +3.904 |
quote | +3.842 |
Ladies | +3.607 |
Neg logit contributions | |
soever | -4.406 |
�� | -4.347 |
adversary | -4.326 |
achine | -4.191 |
Canaver | -4.157 |
Token | however |
Token ID | 2158 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
uid | +2.100 |
女 | +1.883 |
quote | +1.802 |
í | +1.798 |
Ladies | +1.709 |
Neg logit contributions | |
soever | -1.599 |
adversary | -1.549 |
�� | -1.529 |
achine | -1.478 |
anooga | -1.436 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
soever | +2.149 |
adversary | +2.085 |
�� | +2.041 |
achine | +1.987 |
anooga | +1.928 |
Neg logit contributions | |
uid | -2.452 |
女 | -2.186 |
quote | -2.092 |
í | -2.062 |
Ladies | -1.965 |
Token | The |
Token ID | 383 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
uid | +1.345 |
女 | +1.187 |
quote | +1.132 |
í | +1.106 |
Ladies | +1.054 |
Neg logit contributions | |
soever | -1.338 |
adversary | -1.294 |
�� | -1.268 |
achine | -1.235 |
Canaver | -1.207 |
Token | vast |
Token ID | 5909 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
soever | +0.052 |
adversary | +0.050 |
�� | +0.048 |
achine | +0.046 |
anooga | +0.045 |
Neg logit contributions | |
uid | -0.082 |
女 | -0.074 |
quote | -0.071 |
í | -0.070 |
Ladies | -0.067 |
Token | majority |
Token ID | 3741 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
uid | +2.211 |
女 | +1.957 |
quote | +1.864 |
í | +1.849 |
Ladies | +1.756 |
Neg logit contributions | |
soever | -2.121 |
adversary | -2.033 |
�� | -2.005 |
achine | -1.953 |
Canaver | -1.915 |
Token | real |
Token ID | 1103 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
uid | +0.637 |
女 | +0.574 |
quote | +0.551 |
í | +0.543 |
Ladies | +0.522 |
Neg logit contributions | |
soever | -0.458 |
adversary | -0.441 |
�� | -0.432 |
achine | -0.417 |
anooga | -0.404 |
Token | world |
Token ID | 995 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
uid | +1.219 |
女 | +1.094 |
quote | +1.056 |
í | +1.047 |
Ladies | +1.004 |
Neg logit contributions | |
soever | -0.908 |
�� | -0.861 |
adversary | -0.860 |
achine | -0.824 |
Canaver | -0.803 |
Token | projected |
Token ID | 13301 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
uid | +0.599 |
女 | +0.538 |
quote | +0.516 |
í | +0.508 |
Ladies | +0.487 |
Neg logit contributions | |
soever | -0.454 |
adversary | -0.438 |
�� | -0.430 |
achine | -0.416 |
anooga | -0.403 |
Token | onto |
Token ID | 4291 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
uid | +2.495 |
女 | +2.222 |
quote | +2.134 |
í | +2.105 |
Ladies | +2.007 |
Neg logit contributions | |
soever | -2.297 |
�� | -2.236 |
adversary | -2.197 |
achine | -2.117 |
anooga | -2.078 |
Token | their |
Token ID | 511 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
uid | +2.630 |
女 | +2.347 |
quote | +2.260 |
í | +2.246 |
Ladies | +2.147 |
Neg logit contributions | |
soever | -2.325 |
�� | -2.227 |
adversary | -2.221 |
achine | -2.146 |
anooga | -2.092 |
Token | screen |
Token ID | 3159 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
uid | +1.045 |
女 | +0.931 |
quote | +0.892 |
í | +0.879 |
Ladies | +0.840 |
Neg logit contributions | |
soever | -0.913 |
adversary | -0.881 |
�� | -0.869 |
achine | -0.844 |
anooga | -0.819 |
Token | via |
Token ID | 2884 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
uid | +1.755 |
女 | +1.552 |
quote | +1.496 |
í | +1.475 |
Ladies | +1.404 |
Neg logit contributions | |
soever | -1.539 |
adversary | -1.494 |
�� | -1.488 |
achine | -1.427 |
Canaver | -1.397 |
Token | their |
Token ID | 511 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
uid | +3.843 |
女 | +3.410 |
quote | +3.302 |
í | +3.277 |
Ladies | +3.153 |
Neg logit contributions | |
soever | -3.267 |
�� | -3.100 |
adversary | -3.093 |
achine | -3.006 |
anooga | -2.940 |
Token | phone |
Token ID | 3072 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
uid | +2.771 |
女 | +2.439 |
quote | +2.347 |
í | +2.325 |
Ladies | +2.218 |
Neg logit contributions | |
soever | -2.634 |
adversary | -2.524 |
�� | -2.509 |
achine | -2.450 |
anooga | -2.381 |
Token | 's |
Token ID | 338 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
uid | +2.419 |
女 | +2.120 |
quote | +2.052 |
í | +2.033 |
Ladies | +1.919 |
Neg logit contributions | |
soever | -2.222 |
adversary | -2.158 |
�� | -2.153 |
achine | -2.073 |
anooga | -2.040 |
Token | camera |
Token ID | 4676 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
uid | +0.569 |
女 | +0.513 |
quote | +0.491 |
í | +0.482 |
Ladies | +0.462 |
Neg logit contributions | |
soever | -0.424 |
adversary | -0.410 |
�� | -0.399 |
achine | -0.386 |
Canaver | -0.373 |
Token | Many |
Token ID | 4650 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
soever | +0.101 |
adversary | +0.098 |
�� | +0.096 |
achine | +0.093 |
anooga | +0.091 |
Neg logit contributions | |
uid | -0.096 |
女 | -0.084 |
quote | -0.080 |
í | -0.079 |
Ladies | -0.075 |
Token | states |
Token ID | 2585 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
uid | +1.128 |
女 | +1.016 |
quote | +0.978 |
í | +0.963 |
Ladies | +0.925 |
Neg logit contributions | |
soever | -0.793 |
adversary | -0.764 |
�� | -0.748 |
achine | -0.723 |
anooga | -0.699 |
Token | and |
Token ID | 290 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
soever | +0.347 |
adversary | +0.338 |
�� | +0.320 |
achine | +0.316 |
Canaver | +0.304 |
Neg logit contributions | |
uid | -0.459 |
女 | -0.414 |
quote | -0.395 |
í | -0.385 |
Ladies | -0.373 |
Token | individuals |
Token ID | 3925 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
soever | +0.282 |
adversary | +0.272 |
�� | +0.266 |
achine | +0.258 |
anooga | +0.250 |
Neg logit contributions | |
uid | -0.367 |
女 | -0.330 |
quote | -0.316 |
í | -0.311 |
Ladies | -0.298 |
Token | brought |
Token ID | 3181 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
soever | +0.723 |
adversary | +0.704 |
�� | +0.660 |
achine | +0.657 |
Canaver | +0.632 |
Neg logit contributions | |
uid | -0.949 |
女 | -0.855 |
quote | -0.815 |
í | -0.793 |
Ladies | -0.770 |
Token | litigation |
Token ID | 19284 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
soever | +0.448 |
adversary | +0.432 |
�� | +0.417 |
achine | +0.403 |
Canaver | +0.388 |
Neg logit contributions | |
uid | -0.749 |
女 | -0.680 |
quote | -0.656 |
í | -0.646 |
Ladies | -0.621 |
Token | against |
Token ID | 1028 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
uid | +2.457 |
女 | +2.190 |
quote | +2.083 |
í | +2.079 |
Ladies | +1.968 |
Neg logit contributions | |
soever | -2.227 |
�� | -2.160 |
adversary | -2.129 |
achine | -2.062 |
anooga | -2.028 |
Token | tobacco |
Token ID | 11219 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
uid | +0.400 |
女 | +0.355 |
quote | +0.344 |
í | +0.338 |
Ladies | +0.325 |
Neg logit contributions | |
soever | -0.337 |
adversary | -0.325 |
�� | -0.322 |
achine | -0.313 |
anooga | -0.304 |
Token | companies |
Token ID | 2706 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
uid | +5.568 |
quote | +4.907 |
女 | +4.898 |
í | +4.893 |
Ladies | +4.606 |
Neg logit contributions | |
soever | -4.780 |
�� | -4.565 |
adversary | -4.494 |
achine | -4.370 |
Canaver | -4.285 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
uid | +0.995 |
女 | +0.892 |
quote | +0.857 |
í | +0.844 |
Ladies | +0.808 |
Neg logit contributions | |
soever | -0.766 |
adversary | -0.740 |
�� | -0.727 |
achine | -0.703 |
anooga | -0.682 |
Token | which |
Token ID | 543 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
uid | +0.935 |
女 | +0.842 |
quote | +0.811 |
í | +0.800 |
Ladies | +0.769 |
Neg logit contributions | |
soever | -0.637 |
adversary | -0.612 |
�� | -0.601 |
achine | -0.579 |
anooga | -0.561 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
uid | +0.928 |
女 | +0.827 |
quote | +0.796 |
í | +0.788 |
Ladies | +0.754 |
Neg logit contributions | |
soever | -0.772 |
adversary | -0.746 |
�� | -0.736 |
achine | -0.713 |
anooga | -0.693 |
Token | the |
Token ID | 262 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
uid | +1.057 |
女 | +0.949 |
quote | +0.913 |
í | +0.899 |
Ladies | +0.862 |
Neg logit contributions | |
soever | -0.793 |
adversary | -0.766 |
�� | -0.751 |
achine | -0.728 |
anooga | -0.705 |
Token | brand |
Token ID | 4508 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
uid | +0.052 |
女 | +0.047 |
quote | +0.045 |
í | +0.044 |
Ladies | +0.042 |
Neg logit contributions | |
soever | -0.042 |
adversary | -0.041 |
�� | -0.040 |
achine | -0.038 |
Canaver | -0.037 |
Token | army |
Token ID | 5428 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
uid | +4.252 |
女 | +3.790 |
quote | +3.696 |
í | +3.657 |
Ladies | +3.495 |
Neg logit contributions | |
soever | -3.203 |
�� | -3.126 |
adversary | -3.078 |
achine | -2.972 |
anooga | -2.889 |
Token | has |
Token ID | 468 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
soever | +0.068 |
adversary | +0.065 |
�� | +0.063 |
achine | +0.061 |
anooga | +0.059 |
Neg logit contributions | |
uid | -0.107 |
女 | -0.097 |
quote | -0.093 |
í | -0.091 |
Ladies | -0.088 |
Token | rights |
Token ID | 2489 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
soever | +0.057 |
adversary | +0.055 |
�� | +0.054 |
achine | +0.052 |
anooga | +0.051 |
Neg logit contributions | |
uid | -0.076 |
女 | -0.068 |
quote | -0.065 |
í | -0.064 |
Ladies | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
uid | +1.833 |
女 | +1.629 |
quote | +1.571 |
í | +1.564 |
Ladies | +1.473 |
Neg logit contributions | |
soever | -1.603 |
�� | -1.556 |
adversary | -1.549 |
achine | -1.499 |
anooga | -1.477 |
Token | enter |
Token ID | 3802 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
uid | +1.852 |
女 | +1.654 |
quote | +1.596 |
í | +1.574 |
Ladies | +1.508 |
Neg logit contributions | |
soever | -1.489 |
adversary | -1.434 |
�� | -1.422 |
achine | -1.375 |
anooga | -1.345 |
Token | shops |
Token ID | 12437 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
soever | +3.262 |
adversary | +3.127 |
�� | +2.908 |
achine | +2.811 |
anooga | +2.745 |
Neg logit contributions | |
uid | -4.456 |
女 | -4.024 |
quote | -3.810 |
í | -3.694 |
Ladies | -3.542 |
Token | and |
Token ID | 290 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
uid | +0.937 |
女 | +0.844 |
quote | +0.808 |
í | +0.791 |
Ladies | +0.761 |
Neg logit contributions | |
soever | -0.695 |
adversary | -0.668 |
�� | -0.647 |
achine | -0.629 |
anooga | -0.607 |
Token | business |
Token ID | 1597 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
uid | +0.317 |
女 | +0.284 |
quote | +0.270 |
í | +0.264 |
Ladies | +0.253 |
Neg logit contributions | |
soever | -0.274 |
adversary | -0.264 |
�� | -0.256 |
achine | -0.249 |
anooga | -0.241 |
Token | hash |
Token ID | 17831 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
soever | +0.019 |
adversary | +0.018 |
�� | +0.018 |
achine | +0.017 |
anooga | +0.017 |
Neg logit contributions | |
uid | -0.020 |
女 | -0.017 |
quote | -0.017 |
í | -0.016 |
Ladies | -0.016 |
Token | Gh |
Token ID | 11972 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
soever | +3.394 |
adversary | +3.270 |
�� | +3.217 |
achine | +3.130 |
Canaver | +3.051 |
Neg logit contributions | |
uid | -4.132 |
女 | -3.749 |
quote | -3.565 |
í | -3.473 |
Ladies | -3.338 |
Token | ai |
Token ID | 1872 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
uid | +1.441 |
女 | +1.243 |
quote | +1.211 |
í | +1.208 |
Ladies | +1.129 |
Neg logit contributions | |
soever | -1.279 |
adversary | -1.238 |
�� | -1.227 |
achine | -1.162 |
Canaver | -1.148 |
Token | , |
Token ID | 11 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
soever | +3.194 |
adversary | +3.115 |
�� | +3.031 |
achine | +2.956 |
anooga | +2.853 |
Neg logit contributions | |
uid | -3.287 |
女 | -2.945 |
quote | -2.778 |
í | -2.704 |
Ladies | -2.603 |
Token | the |
Token ID | 262 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
soever | +0.339 |
adversary | +0.328 |
�� | +0.322 |
achine | +0.312 |
anooga | +0.303 |
Neg logit contributions | |
uid | -0.409 |
女 | -0.366 |
quote | -0.351 |
í | -0.345 |
Ladies | -0.330 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
soever | +1.123 |
adversary | +1.095 |
�� | +1.059 |
achine | +1.032 |
Canaver | +1.000 |
Neg logit contributions | |
uid | -1.325 |
女 | -1.189 |
quote | -1.134 |
í | -1.113 |
Ladies | -1.056 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
uid | +6.528 |
í | +5.183 |
quote | +5.014 |
Ladies | +4.988 |
女 | +4.823 |
Neg logit contributions | |
soever | -13.348 |
�� | -13.322 |
anooga | -12.753 |
adversary | -12.725 |
achine | -12.705 |
Token | today |
Token ID | 1909 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
uid | +6.944 |
女 | +5.923 |
quote | +5.844 |
í | +5.834 |
Ladies | +5.675 |
Neg logit contributions | |
�� | -6.521 |
soever | -6.489 |
achine | -6.239 |
adversary | -6.168 |
Canaver | -6.073 |
Token | upheld |
Token ID | 24816 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
uid | +1.428 |
女 | +1.263 |
quote | +1.204 |
í | +1.186 |
Ladies | +1.130 |
Neg logit contributions | |
soever | -1.409 |
adversary | -1.368 |
�� | -1.353 |
achine | -1.316 |
anooga | -1.281 |
Token | the |
Token ID | 262 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
uid | +0.028 |
女 | +0.025 |
quote | +0.024 |
í | +0.023 |
Ladies | +0.023 |
Neg logit contributions | |
soever | -0.022 |
adversary | -0.021 |
�� | -0.021 |
achine | -0.020 |
anooga | -0.020 |
Token | Bombay |
Token ID | 48918 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
soever | +1.876 |
adversary | +1.836 |
�� | +1.752 |
achine | +1.698 |
Canaver | +1.648 |
Neg logit contributions | |
uid | -2.482 |
女 | -2.251 |
quote | -2.145 |
í | -2.108 |
united | -1.999 |
Token | of |
Token ID | 286 |
Feature activation | -7.90e-03 |
Pos logit contributions | |
soever | +0.192 |
adversary | +0.185 |
�� | +0.181 |
achine | +0.176 |
anooga | +0.170 |
Neg logit contributions | |
uid | -0.236 |
女 | -0.212 |
quote | -0.203 |
í | -0.199 |
Ladies | -0.191 |
Token | the |
Token ID | 262 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
uid | +0.045 |
女 | +0.040 |
quote | +0.038 |
í | +0.038 |
Ladies | +0.036 |
Neg logit contributions | |
soever | -0.035 |
adversary | -0.034 |
�� | -0.033 |
achine | -0.032 |
anooga | -0.031 |
Token | state |
Token ID | 1181 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
uid | +0.384 |
女 | +0.344 |
quote | +0.330 |
í | +0.324 |
Ladies | +0.310 |
Neg logit contributions | |
soever | -0.317 |
adversary | -0.307 |
�� | -0.300 |
achine | -0.291 |
anooga | -0.282 |
Token | ," |
Token ID | 553 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
uid | +2.923 |
女 | +2.567 |
quote | +2.485 |
í | +2.469 |
Ladies | +2.328 |
Neg logit contributions | |
soever | -2.508 |
�� | -2.462 |
adversary | -2.421 |
achine | -2.352 |
Canaver | -2.320 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
uid | +1.963 |
女 | +1.731 |
quote | +1.675 |
í | +1.648 |
Ladies | +1.585 |
Neg logit contributions | |
soever | -1.730 |
adversary | -1.673 |
�� | -1.661 |
achine | -1.631 |
Canaver | -1.581 |
Token | bench |
Token ID | 7624 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
uid | +0.955 |
女 | +0.843 |
quote | +0.816 |
í | +0.800 |
Ladies | +0.770 |
Neg logit contributions | |
soever | -0.850 |
adversary | -0.815 |
�� | -0.808 |
achine | -0.789 |
anooga | -0.767 |
Token | said |
Token ID | 531 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
uid | +6.950 |
quote | +5.902 |
女 | +5.834 |
í | +5.753 |
Ladies | +5.442 |
Neg logit contributions | |
achine | -8.404 |
�� | -8.268 |
soever | -8.264 |
Canaver | -8.007 |
adversary | -7.995 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
uid | +2.293 |
女 | +2.002 |
quote | +1.957 |
í | +1.915 |
Ladies | +1.828 |
Neg logit contributions | |
soever | -2.150 |
adversary | -2.075 |
�� | -2.061 |
achine | -2.046 |
anooga | -1.977 |
Token |
|
Token ID | 198 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
uid | +0.490 |
女 | +0.429 |
quote | +0.414 |
í | +0.406 |
Ladies | +0.386 |
Neg logit contributions | |
soever | -0.528 |
adversary | -0.516 |
�� | -0.505 |
achine | -0.492 |
anooga | -0.481 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
uid | +0.367 |
女 | +0.330 |
quote | +0.309 |
í | +0.300 |
Ladies | +0.292 |
Neg logit contributions | |
soever | -0.298 |
adversary | -0.288 |
achine | -0.277 |
�� | -0.267 |
Canaver | -0.266 |
Token | The |
Token ID | 464 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
soever | +0.021 |
adversary | +0.020 |
�� | +0.020 |
achine | +0.019 |
anooga | +0.019 |
Neg logit contributions | |
uid | -0.026 |
女 | -0.023 |
quote | -0.022 |
í | -0.022 |
Ladies | -0.021 |
Token | Christmas |
Token ID | 44614 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
soever | +1.867 |
adversary | +1.814 |
�� | +1.775 |
achine | +1.728 |
anooga | +1.676 |
Neg logit contributions | |
uid | -2.157 |
女 | -1.927 |
quote | -1.839 |
í | -1.814 |
Ladies | -1.733 |
Token | in |
Token ID | 287 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
soever | +1.797 |
adversary | +1.754 |
�� | +1.680 |
achine | +1.665 |
Canaver | +1.605 |
Neg logit contributions | |
uid | -2.037 |
女 | -1.826 |
quote | -1.734 |
í | -1.684 |
united | -1.585 |
Token | July |
Token ID | 2901 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
uid | +0.223 |
女 | +0.198 |
quote | +0.189 |
í | +0.186 |
Ladies | +0.177 |
Neg logit contributions | |
soever | -0.206 |
adversary | -0.199 |
�� | -0.196 |
achine | -0.190 |
anooga | -0.185 |
Token | " |
Token ID | 1 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
soever | +0.648 |
adversary | +0.625 |
�� | +0.608 |
achine | +0.588 |
anooga | +0.568 |
Neg logit contributions | |
uid | -0.978 |
女 | -0.884 |
quote | -0.849 |
í | -0.836 |
Ladies | -0.802 |
Token | double |
Token ID | 4274 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
soever | +0.107 |
adversary | +0.104 |
�� | +0.101 |
achine | +0.098 |
anooga | +0.095 |
Neg logit contributions | |
uid | -0.147 |
女 | -0.132 |
quote | -0.127 |
í | -0.125 |
Ladies | -0.119 |
Token | - |
Token ID | 12 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
uid | +4.212 |
女 | +3.672 |
quote | +3.587 |
í | +3.539 |
Ladies | +3.381 |
Neg logit contributions | |
soever | -3.771 |
�� | -3.598 |
adversary | -3.565 |
achine | -3.508 |
Canaver | -3.410 |
Token | feature |
Token ID | 30053 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
uid | +7.516 |
quote | +6.253 |
í | +6.037 |
sell | +5.891 |
女 | +5.806 |
Neg logit contributions | |
soever | -8.378 |
adversary | -8.114 |
�� | -8.012 |
Canaver | -7.719 |
achine | -7.603 |
Token | is |
Token ID | 318 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
uid | +2.941 |
女 | +2.635 |
quote | +2.539 |
í | +2.511 |
Ladies | +2.415 |
Neg logit contributions | |
soever | -2.222 |
adversary | -2.114 |
�� | -2.094 |
achine | -2.018 |
anooga | -1.958 |
Token | July |
Token ID | 2901 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
uid | +2.684 |
女 | +2.410 |
quote | +2.298 |
í | +2.273 |
Ladies | +2.187 |
Neg logit contributions | |
soever | -2.291 |
adversary | -2.197 |
�� | -2.189 |
achine | -2.111 |
anooga | -2.053 |
Token | 26 |
Token ID | 2608 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
uid | +2.410 |
女 | +2.174 |
quote | +2.092 |
í | +2.060 |
Ladies | +1.979 |
Neg logit contributions | |
soever | -1.648 |
adversary | -1.588 |
�� | -1.553 |
achine | -1.499 |
anooga | -1.450 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
uid | +5.606 |
女 | +4.969 |
quote | +4.826 |
í | +4.763 |
Ladies | +4.564 |
Neg logit contributions | |
soever | -5.412 |
�� | -5.199 |
adversary | -5.119 |
achine | -4.929 |
anooga | -4.888 |
Token | � |
Token ID | 247 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
soever | +1.063 |
�� | +1.024 |
adversary | +1.022 |
achine | +0.960 |
Canaver | +0.941 |
Neg logit contributions | |
uid | -1.063 |
女 | -0.950 |
quote | -0.913 |
í | -0.881 |
Ladies | -0.848 |
Token | s |
Token ID | 82 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
soever | +0.447 |
adversary | +0.429 |
�� | +0.419 |
achine | +0.407 |
anooga | +0.393 |
Neg logit contributions | |
uid | -0.595 |
女 | -0.535 |
quote | -0.513 |
í | -0.504 |
Ladies | -0.484 |
Token | like |
Token ID | 588 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
soever | +0.697 |
adversary | +0.675 |
�� | +0.652 |
achine | +0.636 |
Canaver | +0.618 |
Neg logit contributions | |
uid | -0.960 |
女 | -0.860 |
quote | -0.826 |
í | -0.803 |
Ladies | -0.773 |
Token | if |
Token ID | 611 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
soever | +1.033 |
adversary | +0.996 |
�� | +0.967 |
achine | +0.934 |
Canaver | +0.914 |
Neg logit contributions | |
uid | -1.367 |
女 | -1.212 |
quote | -1.161 |
í | -1.138 |
Ladies | -1.090 |
Token | Vanilla |
Token ID | 33897 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
soever | +0.801 |
adversary | +0.769 |
�� | +0.747 |
achine | +0.728 |
Canaver | +0.708 |
Neg logit contributions | |
uid | -1.032 |
女 | -0.915 |
quote | -0.877 |
í | -0.859 |
Ladies | -0.823 |
Token | Ice |
Token ID | 6663 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
uid | +4.421 |
女 | +3.734 |
í | +3.622 |
Ladies | +3.602 |
quote | +3.602 |
Neg logit contributions | |
soever | -8.062 |
�� | -8.013 |
adversary | -7.793 |
anooga | -7.665 |
achine | -7.572 |
Token | was |
Token ID | 373 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
uid | +8.990 |
女 | +8.208 |
í | +7.913 |
quote | +7.843 |
Ladies | +7.503 |
Neg logit contributions | |
soever | -7.778 |
�� | -7.668 |
adversary | -7.553 |
achine | -7.286 |
anooga | -7.187 |
Token | slightly |
Token ID | 4622 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
uid | +1.879 |
女 | +1.686 |
quote | +1.618 |
í | +1.592 |
Ladies | +1.526 |
Neg logit contributions | |
soever | -1.441 |
adversary | -1.393 |
�� | -1.362 |
achine | -1.319 |
anooga | -1.278 |
Token | more |
Token ID | 517 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
uid | +3.195 |
女 | +2.881 |
quote | +2.785 |
í | +2.738 |
Ladies | +2.627 |
Neg logit contributions | |
soever | -2.154 |
adversary | -2.074 |
�� | -2.042 |
achine | -1.970 |
anooga | -1.917 |
Token | gang |
Token ID | 7706 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
uid | +3.546 |
女 | +3.168 |
quote | +3.060 |
í | +3.009 |
Ladies | +2.878 |
Neg logit contributions | |
soever | -2.856 |
adversary | -2.756 |
�� | -2.735 |
achine | -2.637 |
anooga | -2.570 |
Token | ster |
Token ID | 1706 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
uid | +1.870 |
女 | +1.601 |
quote | +1.518 |
í | +1.496 |
Ladies | +1.400 |
Neg logit contributions | |
soever | -2.472 |
adversary | -2.391 |
�� | -2.389 |
achine | -2.302 |
Canaver | -2.270 |
Token | N |
Token ID | 45 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
uid | +2.864 |
女 | +2.550 |
quote | +2.473 |
í | +2.459 |
Ladies | +2.320 |
Neg logit contributions | |
soever | -2.202 |
adversary | -1.969 |
�� | -1.943 |
achine | -1.909 |
Canaver | -1.906 |
Token | . |
Token ID | 13 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
uid | +3.647 |
í | +3.040 |
女 | +3.018 |
quote | +2.862 |
Ladies | +2.733 |
Neg logit contributions | |
soever | -4.563 |
�� | -4.410 |
adversary | -4.310 |
Canaver | -4.284 |
achine | -4.256 |
Token | " |
Token ID | 366 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
uid | +3.288 |
女 | +2.936 |
quote | +2.830 |
í | +2.818 |
Ladies | +2.705 |
Neg logit contributions | |
soever | -2.424 |
adversary | -2.283 |
�� | -2.282 |
achine | -2.204 |
Canaver | -2.153 |
Token | special |
Token ID | 20887 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
soever | +1.241 |
adversary | +1.211 |
�� | +1.176 |
achine | +1.145 |
anooga | +1.116 |
Neg logit contributions | |
uid | -1.314 |
女 | -1.178 |
quote | -1.117 |
í | -1.096 |
Ladies | -1.054 |
Token | rapport |
Token ID | 49498 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
uid | +2.052 |
女 | +1.822 |
quote | +1.767 |
í | +1.755 |
Ladies | +1.680 |
Neg logit contributions | |
soever | -1.536 |
�� | -1.457 |
adversary | -1.455 |
achine | -1.393 |
Canaver | -1.367 |
Token | eur |
Token ID | 23365 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
uid | +1.517 |
女 | +1.345 |
quote | +1.290 |
í | +1.284 |
Ladies | +1.217 |
Neg logit contributions | |
soever | -1.223 |
adversary | -1.162 |
�� | -1.148 |
achine | -1.109 |
Canaver | -1.085 |
Token | " |
Token ID | 1 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
uid | +6.921 |
í | +6.091 |
女 | +6.020 |
quote | +5.855 |
Ladies | +5.537 |
Neg logit contributions | |
soever | -7.368 |
�� | -7.118 |
adversary | -6.691 |
achine | -6.602 |
Canaver | -6.565 |
Token | for |
Token ID | 329 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
uid | +4.134 |
女 | +3.640 |
í | +3.524 |
quote | +3.511 |
Ladies | +3.330 |
Neg logit contributions | |
soever | -3.963 |
�� | -3.816 |
adversary | -3.691 |
achine | -3.612 |
anooga | -3.550 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
uid | +2.760 |
女 | +2.458 |
quote | +2.370 |
í | +2.347 |
Ladies | +2.257 |
Neg logit contributions | |
soever | -2.157 |
�� | -2.071 |
adversary | -2.054 |
achine | -1.991 |
anooga | -1.950 |
Token | protection |
Token ID | 4800 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
uid | +0.682 |
女 | +0.615 |
quote | +0.591 |
í | +0.581 |
Ladies | +0.556 |
Neg logit contributions | |
soever | -0.489 |
adversary | -0.474 |
�� | -0.461 |
achine | -0.446 |
anooga | -0.431 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
uid | +2.563 |
女 | +2.302 |
í | +2.151 |
quote | +2.146 |
Ladies | +1.992 |
Neg logit contributions | |
soever | -2.788 |
�� | -2.672 |
adversary | -2.633 |
Canaver | -2.547 |
achine | -2.544 |