Token | York |
Token ID | 1971 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
azo | +0.647 |
affles | +0.617 |
bugs | +0.611 |
bug | +0.577 |
ception | +0.558 |
Neg logit contributions | |
Franch | -1.119 |
WD | -1.020 |
haar | -0.990 |
wd | -0.987 |
root | -0.978 |
Token | Times |
Token ID | 3782 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
azo | +1.885 |
bugs | +1.783 |
affles | +1.769 |
bug | +1.693 |
ception | +1.631 |
Neg logit contributions | |
Franch | -3.781 |
WD | -3.451 |
haar | -3.419 |
wd | -3.379 |
root | -3.314 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
azo | +1.384 |
affles | +1.351 |
bugs | +1.346 |
bug | +1.306 |
ception | +1.265 |
Neg logit contributions | |
Franch | -1.417 |
WD | -1.254 |
haar | -1.228 |
wd | -1.212 |
root | -1.186 |
Token | You |
Token ID | 921 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
azo | +2.408 |
affles | +2.400 |
bugs | +2.368 |
bug | +2.302 |
ception | +2.246 |
Neg logit contributions | |
Franch | -2.433 |
WD | -2.143 |
haar | -2.122 |
wd | -2.076 |
srf | -2.054 |
Token | may |
Token ID | 743 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
azo | +1.853 |
affles | +1.798 |
bugs | +1.785 |
bug | +1.763 |
ception | +1.685 |
Neg logit contributions | |
Franch | -2.388 |
haar | -2.069 |
WD | -2.053 |
srf | -2.035 |
entin | -2.014 |
Token | opt |
Token ID | 2172 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
azo | +1.306 |
affles | +1.198 |
bugs | +1.178 |
bug | +1.104 |
ception | +1.025 |
Neg logit contributions | |
Franch | -4.593 |
WD | -4.220 |
haar | -4.162 |
wd | -4.115 |
root | -4.097 |
Token | - |
Token ID | 12 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
azo | +4.842 |
affles | +4.559 |
bugs | +4.490 |
bug | +4.409 |
ception | +4.314 |
Neg logit contributions | |
Franch | -8.916 |
srf | -8.080 |
WD | -7.914 |
haar | -7.768 |
entin | -7.584 |
Token | out |
Token ID | 448 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
azo | +3.084 |
affles | +2.972 |
bugs | +2.962 |
bug | +2.871 |
ception | +2.771 |
Neg logit contributions | |
Franch | -4.157 |
WD | -3.646 |
haar | -3.581 |
wd | -3.472 |
root | -3.413 |
Token | at |
Token ID | 379 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
azo | +3.965 |
affles | +3.887 |
bugs | +3.777 |
bug | +3.758 |
ception | +3.661 |
Neg logit contributions | |
Franch | -6.293 |
WD | -5.462 |
haar | -5.460 |
srf | -5.432 |
root | -5.240 |
Token | any |
Token ID | 597 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
azo | +1.890 |
affles | +1.829 |
bugs | +1.824 |
bug | +1.757 |
ception | +1.697 |
Neg logit contributions | |
Franch | -2.822 |
WD | -2.518 |
haar | -2.487 |
wd | -2.431 |
root | -2.405 |
Token | time |
Token ID | 640 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
azo | +4.383 |
affles | +4.235 |
bugs | +4.200 |
bug | +4.141 |
ception | +3.975 |
Neg logit contributions | |
Franch | -6.291 |
haar | -5.581 |
WD | -5.555 |
entin | -5.368 |
srf | -5.351 |
Token | ? |
Token ID | 30 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
Franch | +1.375 |
WD | +1.210 |
haar | +1.191 |
wd | +1.173 |
root | +1.165 |
Neg logit contributions | |
azo | -1.341 |
affles | -1.302 |
bugs | -1.278 |
bug | -1.228 |
ception | -1.212 |
Token |
|
Token ID | 198 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
azo | +0.704 |
affles | +0.681 |
bugs | +0.676 |
bug | +0.650 |
ception | +0.633 |
Neg logit contributions | |
Franch | -0.806 |
WD | -0.720 |
haar | -0.699 |
wd | -0.694 |
root | -0.684 |
Token |
|
Token ID | 198 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
azo | +0.224 |
affles | +0.216 |
bugs | +0.213 |
bug | +0.205 |
ception | +0.199 |
Neg logit contributions | |
Franch | -0.259 |
WD | -0.232 |
haar | -0.224 |
wd | -0.224 |
root | -0.221 |
Token | man |
Token ID | 805 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
azo | +0.436 |
affles | +0.422 |
bugs | +0.418 |
bug | +0.402 |
ception | +0.392 |
Neg logit contributions | |
Franch | -0.478 |
WD | -0.427 |
haar | -0.414 |
wd | -0.411 |
root | -0.405 |
Token | del |
Token ID | 1619 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
azo | +1.332 |
affles | +1.288 |
bugs | +1.282 |
bug | +1.235 |
ception | +1.198 |
Neg logit contributions | |
Franch | -1.491 |
WD | -1.329 |
haar | -1.290 |
wd | -1.274 |
root | -1.256 |
Token | ights |
Token ID | 2337 |
Feature activation | +9.18e+00 |
Pos logit contributions | |
Franch | +0.101 |
WD | +0.091 |
wd | +0.090 |
haar | +0.089 |
root | +0.089 |
Neg logit contributions | |
azo | -0.061 |
affles | -0.058 |
bugs | -0.057 |
bug | -0.054 |
ception | -0.053 |
Token | not |
Token ID | 407 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
azo | +5.271 |
bugs | +5.151 |
affles | +5.032 |
bug | +4.954 |
ception | +4.673 |
Neg logit contributions | |
Franch | -8.184 |
WD | -7.563 |
haar | -7.397 |
wd | -7.190 |
root | -7.060 |
Token | me |
Token ID | 502 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
azo | +0.669 |
affles | +0.645 |
bugs | +0.639 |
bug | +0.613 |
ception | +0.596 |
Neg logit contributions | |
Franch | -0.848 |
WD | -0.761 |
haar | -0.739 |
wd | -0.735 |
root | -0.725 |
Token | ; |
Token ID | 26 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
azo | +1.690 |
affles | +1.637 |
bugs | +1.632 |
bug | +1.573 |
ception | +1.525 |
Neg logit contributions | |
Franch | -1.819 |
WD | -1.621 |
haar | -1.572 |
wd | -1.555 |
root | -1.530 |
Token | no |
Token ID | 645 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
azo | +2.285 |
affles | +2.199 |
bugs | +2.196 |
bug | +2.109 |
ception | +2.034 |
Neg logit contributions | |
Franch | -2.975 |
WD | -2.682 |
haar | -2.612 |
wd | -2.583 |
root | -2.545 |
Token | , |
Token ID | 11 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
azo | +1.969 |
affles | +1.906 |
bugs | +1.901 |
bug | +1.839 |
ception | +1.777 |
Neg logit contributions | |
Franch | -2.068 |
WD | -1.845 |
haar | -1.786 |
wd | -1.767 |
root | -1.739 |
Token | for |
Token ID | 329 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
azo | +0.567 |
affles | +0.549 |
bugs | +0.546 |
bug | +0.526 |
ception | +0.513 |
Neg logit contributions | |
Franch | -0.580 |
WD | -0.514 |
haar | -0.498 |
wd | -0.494 |
root | -0.487 |
Token | $ |
Token ID | 720 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
azo | +2.187 |
affles | +2.114 |
bugs | +2.103 |
bug | +2.023 |
ception | +1.964 |
Neg logit contributions | |
Franch | -2.588 |
WD | -2.323 |
haar | -2.259 |
wd | -2.236 |
root | -2.207 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
azo | +0.408 |
affles | +0.394 |
bugs | +0.391 |
bug | +0.375 |
ception | +0.365 |
Neg logit contributions | |
Franch | -0.477 |
WD | -0.427 |
haar | -0.414 |
wd | -0.412 |
root | -0.406 |
Token | million |
Token ID | 1510 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Franch | +1.046 |
WD | +0.928 |
haar | +0.897 |
wd | +0.891 |
root | +0.878 |
Neg logit contributions | |
azo | -1.125 |
affles | -1.095 |
bugs | -1.084 |
bug | -1.043 |
ception | -1.022 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
azo | +1.858 |
affles | +1.799 |
bugs | +1.791 |
bug | +1.721 |
ception | +1.674 |
Neg logit contributions | |
Franch | -2.080 |
WD | -1.845 |
haar | -1.801 |
wd | -1.781 |
root | -1.749 |
Token | settled |
Token ID | 10282 |
Feature activation | +8.70e+00 |
Pos logit contributions | |
azo | +0.743 |
affles | +0.717 |
bugs | +0.713 |
bug | +0.684 |
ception | +0.665 |
Neg logit contributions | |
Franch | -0.903 |
WD | -0.808 |
haar | -0.784 |
wd | -0.779 |
root | -0.768 |
Token | the |
Token ID | 262 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
azo | +5.241 |
affles | +5.237 |
bugs | +5.134 |
bug | +4.876 |
ception | +4.665 |
Neg logit contributions | |
Franch | -7.548 |
WD | -6.747 |
wd | -6.624 |
haar | -6.622 |
entin | -6.416 |
Token | suit |
Token ID | 6050 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
azo | +3.484 |
affles | +3.385 |
bugs | +3.369 |
bug | +3.250 |
ception | +3.156 |
Neg logit contributions | |
Franch | -3.019 |
WD | -2.681 |
haar | -2.599 |
wd | -2.588 |
root | -2.502 |
Token | on |
Token ID | 319 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
azo | +4.474 |
affles | +4.402 |
bugs | +4.360 |
bug | +4.182 |
ception | +4.038 |
Neg logit contributions | |
Franch | -5.568 |
WD | -4.928 |
haar | -4.803 |
wd | -4.775 |
root | -4.641 |
Token | condition |
Token ID | 4006 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
azo | +1.502 |
affles | +1.465 |
bugs | +1.452 |
bug | +1.396 |
ception | +1.354 |
Neg logit contributions | |
Franch | -1.704 |
WD | -1.533 |
haar | -1.489 |
wd | -1.475 |
root | -1.449 |
Token | of |
Token ID | 286 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
azo | +1.234 |
affles | +1.200 |
bugs | +1.188 |
bug | +1.140 |
ception | +1.105 |
Neg logit contributions | |
Franch | -1.615 |
WD | -1.454 |
haar | -1.418 |
wd | -1.405 |
root | -1.386 |
Token | York |
Token ID | 1971 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
azo | +0.386 |
affles | +0.368 |
bugs | +0.364 |
bug | +0.344 |
ception | +0.333 |
Neg logit contributions | |
Franch | -0.655 |
WD | -0.596 |
haar | -0.578 |
wd | -0.577 |
root | -0.572 |
Token | Times |
Token ID | 3782 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
azo | +1.996 |
bugs | +1.898 |
affles | +1.866 |
bug | +1.795 |
ception | +1.725 |
Neg logit contributions | |
Franch | -4.104 |
WD | -3.752 |
haar | -3.726 |
wd | -3.682 |
root | -3.610 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
azo | +1.429 |
affles | +1.395 |
bugs | +1.390 |
bug | +1.350 |
ception | +1.307 |
Neg logit contributions | |
Franch | -1.470 |
WD | -1.301 |
haar | -1.274 |
wd | -1.259 |
root | -1.231 |
Token | You |
Token ID | 921 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
azo | +2.060 |
affles | +2.045 |
bugs | +2.018 |
bug | +1.961 |
ception | +1.914 |
Neg logit contributions | |
Franch | -2.029 |
WD | -1.789 |
haar | -1.763 |
wd | -1.730 |
root | -1.695 |
Token | may |
Token ID | 743 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
azo | +1.238 |
affles | +1.199 |
bugs | +1.189 |
bug | +1.169 |
ception | +1.122 |
Neg logit contributions | |
Franch | -1.506 |
WD | -1.303 |
haar | -1.301 |
wd | -1.271 |
srf | -1.263 |
Token | opt |
Token ID | 2172 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
azo | +1.089 |
affles | +1.007 |
bugs | +0.993 |
bug | +0.927 |
ception | +0.865 |
Neg logit contributions | |
Franch | -3.631 |
WD | -3.342 |
haar | -3.287 |
wd | -3.258 |
root | -3.238 |
Token | - |
Token ID | 12 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
azo | +4.568 |
affles | +4.302 |
bugs | +4.248 |
bug | +4.154 |
ception | +4.068 |
Neg logit contributions | |
Franch | -8.031 |
srf | -7.151 |
WD | -7.138 |
haar | -6.995 |
entin | -6.800 |
Token | out |
Token ID | 448 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
azo | +2.778 |
affles | +2.678 |
bugs | +2.668 |
bug | +2.580 |
ception | +2.495 |
Neg logit contributions | |
Franch | -3.606 |
WD | -3.176 |
haar | -3.111 |
wd | -3.034 |
root | -2.984 |
Token | at |
Token ID | 379 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
azo | +3.748 |
affles | +3.670 |
bugs | +3.568 |
bug | +3.536 |
ception | +3.448 |
Neg logit contributions | |
Franch | -5.745 |
WD | -4.995 |
haar | -4.973 |
srf | -4.903 |
root | -4.787 |
Token | any |
Token ID | 597 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
azo | +1.591 |
affles | +1.540 |
bugs | +1.536 |
bug | +1.478 |
ception | +1.429 |
Neg logit contributions | |
Franch | -2.328 |
WD | -2.081 |
haar | -2.049 |
wd | -2.009 |
root | -1.986 |
Token | time |
Token ID | 640 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
azo | +4.072 |
affles | +3.938 |
bugs | +3.906 |
bug | +3.839 |
ception | +3.693 |
Neg logit contributions | |
Franch | -5.693 |
WD | -5.034 |
haar | -5.030 |
wd | -4.844 |
entin | -4.831 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
azo | +0.462 |
affles | +0.449 |
bugs | +0.447 |
bug | +0.431 |
ception | +0.420 |
Neg logit contributions | |
Franch | -0.442 |
WD | -0.390 |
haar | -0.379 |
wd | -0.374 |
root | -0.368 |
Token | Drain |
Token ID | 36024 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
azo | +0.822 |
affles | +0.788 |
bugs | +0.781 |
bug | +0.743 |
ception | +0.717 |
Neg logit contributions | |
Franch | -1.387 |
WD | -1.261 |
haar | -1.231 |
wd | -1.223 |
root | -1.207 |
Token | on |
Token ID | 319 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
azo | +2.622 |
bugs | +2.578 |
affles | +2.565 |
bug | +2.510 |
ception | +2.395 |
Neg logit contributions | |
Franch | -2.656 |
WD | -2.340 |
haar | -2.327 |
wd | -2.264 |
entin | -2.214 |
Token | a |
Token ID | 257 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
azo | +1.727 |
affles | +1.681 |
bugs | +1.669 |
bug | +1.612 |
ception | +1.567 |
Neg logit contributions | |
Franch | -1.758 |
WD | -1.554 |
haar | -1.518 |
wd | -1.493 |
root | -1.472 |
Token | paper |
Token ID | 3348 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
azo | +3.778 |
affles | +3.666 |
bugs | +3.660 |
bug | +3.586 |
ception | +3.496 |
Neg logit contributions | |
Franch | -2.421 |
WD | -2.038 |
haar | -1.994 |
wd | -1.942 |
root | -1.911 |
Token | towel |
Token ID | 24808 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
azo | +2.319 |
bugs | +2.010 |
bug | +1.971 |
affles | +1.951 |
ception | +1.680 |
Neg logit contributions | |
Franch | -9.277 |
WD | -8.448 |
haar | -8.431 |
wd | -8.281 |
entin | -8.260 |
Token | - |
Token ID | 12 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
azo | +4.429 |
bugs | +4.255 |
affles | +4.181 |
bug | +4.162 |
ception | +3.975 |
Neg logit contributions | |
Franch | -8.031 |
WD | -7.250 |
srf | -7.225 |
haar | -7.148 |
wd | -6.995 |
Token | lined |
Token ID | 10837 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
azo | +2.310 |
bugs | +2.224 |
affles | +2.213 |
bug | +2.161 |
ception | +2.092 |
Neg logit contributions | |
Franch | -2.631 |
WD | -2.282 |
haar | -2.252 |
wd | -2.182 |
srf | -2.149 |
Token | plate |
Token ID | 7480 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
azo | +2.072 |
bugs | +1.872 |
affles | +1.849 |
bug | +1.810 |
ception | +1.617 |
Neg logit contributions | |
Franch | -7.779 |
WD | -7.222 |
haar | -7.134 |
wd | -7.045 |
root | -6.938 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
azo | +3.051 |
bugs | +2.988 |
affles | +2.971 |
bug | +2.905 |
ception | +2.795 |
Neg logit contributions | |
Franch | -3.513 |
WD | -3.104 |
haar | -3.101 |
srf | -3.067 |
wd | -2.999 |
Token | Serve |
Token ID | 35557 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
azo | +1.916 |
affles | +1.871 |
bugs | +1.866 |
bug | +1.803 |
ception | +1.761 |
Neg logit contributions | |
Franch | -2.084 |
WD | -1.882 |
haar | -1.862 |
wd | -1.813 |
root | -1.789 |
Token | conflicts |
Token ID | 12333 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
azo | +1.355 |
affles | +1.310 |
bugs | +1.302 |
bug | +1.250 |
ception | +1.214 |
Neg logit contributions | |
Franch | -1.584 |
WD | -1.420 |
haar | -1.381 |
wd | -1.369 |
root | -1.346 |
Token | of |
Token ID | 286 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
azo | +1.207 |
affles | +1.166 |
bugs | +1.159 |
bug | +1.113 |
ception | +1.082 |
Neg logit contributions | |
Franch | -1.447 |
WD | -1.294 |
haar | -1.258 |
wd | -1.249 |
root | -1.231 |
Token | interest |
Token ID | 1393 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
azo | +0.189 |
affles | +0.181 |
bugs | +0.179 |
bug | +0.172 |
ception | +0.166 |
Neg logit contributions | |
Franch | -0.225 |
WD | -0.202 |
haar | -0.195 |
wd | -0.194 |
root | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Franch | +0.218 |
WD | +0.192 |
haar | +0.185 |
wd | +0.185 |
root | +0.182 |
Neg logit contributions | |
azo | -0.219 |
affles | -0.212 |
bugs | -0.210 |
bug | -0.203 |
ception | -0.198 |
Token | Penn |
Token ID | 6595 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Franch | +0.586 |
WD | +0.515 |
wd | +0.498 |
haar | +0.497 |
root | +0.493 |
Neg logit contributions | |
azo | -0.518 |
affles | -0.500 |
bugs | -0.495 |
bug | -0.475 |
ception | -0.462 |
Token | settles |
Token ID | 43684 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
azo | +1.002 |
affles | +0.970 |
bugs | +0.961 |
bug | +0.926 |
ception | +0.900 |
Neg logit contributions | |
Franch | -1.149 |
WD | -1.027 |
haar | -0.993 |
wd | -0.988 |
root | -0.976 |
Token | with |
Token ID | 351 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
azo | +5.831 |
affles | +5.592 |
bugs | +5.517 |
bug | +5.263 |
ception | +5.097 |
Neg logit contributions | |
Franch | -6.473 |
WD | -5.880 |
haar | -5.718 |
wd | -5.688 |
entin | -5.418 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
azo | +1.412 |
affles | +1.366 |
bugs | +1.357 |
bug | +1.306 |
ception | +1.271 |
Neg logit contributions | |
Franch | -1.582 |
WD | -1.411 |
haar | -1.369 |
wd | -1.358 |
root | -1.339 |
Token | G |
Token ID | 402 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
azo | +2.061 |
affles | +1.995 |
bugs | +1.982 |
bug | +1.910 |
ception | +1.861 |
Neg logit contributions | |
Franch | -2.140 |
WD | -1.901 |
haar | -1.845 |
wd | -1.830 |
root | -1.800 |
Token | els |
Token ID | 1424 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
azo | +0.928 |
affles | +0.907 |
bugs | +0.904 |
bug | +0.881 |
ception | +0.866 |
Neg logit contributions | |
Franch | -0.361 |
WD | -0.288 |
haar | -0.270 |
wd | -0.265 |
root | -0.257 |
Token | inger |
Token ID | 3889 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
azo | +0.384 |
affles | +0.368 |
bugs | +0.366 |
bug | +0.349 |
ception | +0.337 |
Neg logit contributions | |
Franch | -0.588 |
WD | -0.531 |
haar | -0.517 |
wd | -0.514 |
root | -0.506 |
Token | York |
Token ID | 1971 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
azo | +0.529 |
affles | +0.505 |
bugs | +0.498 |
bug | +0.472 |
ception | +0.456 |
Neg logit contributions | |
Franch | -0.905 |
WD | -0.824 |
haar | -0.799 |
wd | -0.797 |
root | -0.791 |
Token | Times |
Token ID | 3782 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
azo | +2.024 |
bugs | +1.921 |
affles | +1.900 |
bug | +1.817 |
ception | +1.749 |
Neg logit contributions | |
Franch | -4.078 |
WD | -3.722 |
haar | -3.696 |
wd | -3.650 |
root | -3.579 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
azo | +1.379 |
affles | +1.347 |
bugs | +1.343 |
bug | +1.303 |
ception | +1.261 |
Neg logit contributions | |
Franch | -1.413 |
WD | -1.248 |
haar | -1.223 |
wd | -1.206 |
root | -1.181 |
Token | You |
Token ID | 921 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
azo | +2.134 |
affles | +2.115 |
bugs | +2.092 |
bug | +2.034 |
ception | +1.985 |
Neg logit contributions | |
Franch | -2.129 |
WD | -1.872 |
haar | -1.847 |
wd | -1.810 |
entin | -1.782 |
Token | may |
Token ID | 743 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
azo | +1.310 |
affles | +1.268 |
bugs | +1.260 |
bug | +1.240 |
ception | +1.191 |
Neg logit contributions | |
Franch | -1.637 |
haar | -1.417 |
WD | -1.412 |
srf | -1.381 |
wd | -1.380 |
Token | opt |
Token ID | 2172 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
azo | +1.047 |
affles | +0.970 |
bugs | +0.957 |
bug | +0.892 |
ception | +0.833 |
Neg logit contributions | |
Franch | -3.508 |
WD | -3.228 |
haar | -3.179 |
wd | -3.147 |
root | -3.129 |
Token | - |
Token ID | 12 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
azo | +4.457 |
affles | +4.223 |
bugs | +4.172 |
bug | +4.068 |
ception | +3.988 |
Neg logit contributions | |
Franch | -7.855 |
srf | -6.990 |
WD | -6.965 |
haar | -6.853 |
entin | -6.655 |
Token | out |
Token ID | 448 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
azo | +2.685 |
affles | +2.589 |
bugs | +2.577 |
bug | +2.490 |
ception | +2.412 |
Neg logit contributions | |
Franch | -3.429 |
WD | -3.027 |
haar | -2.963 |
wd | -2.896 |
root | -2.850 |
Token | at |
Token ID | 379 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
azo | +3.755 |
affles | +3.661 |
bugs | +3.571 |
bug | +3.540 |
ception | +3.441 |
Neg logit contributions | |
Franch | -5.773 |
haar | -5.012 |
WD | -4.997 |
srf | -4.946 |
root | -4.799 |
Token | any |
Token ID | 597 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
azo | +1.539 |
affles | +1.488 |
bugs | +1.485 |
bug | +1.428 |
ception | +1.380 |
Neg logit contributions | |
Franch | -2.223 |
WD | -1.986 |
haar | -1.956 |
wd | -1.917 |
root | -1.894 |
Token | time |
Token ID | 640 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
azo | +4.118 |
affles | +3.988 |
bugs | +3.948 |
bug | +3.880 |
ception | +3.733 |
Neg logit contributions | |
Franch | -5.793 |
haar | -5.137 |
WD | -5.126 |
wd | -4.935 |
entin | -4.930 |
Token | could |
Token ID | 714 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Franch | +0.853 |
WD | +0.757 |
wd | +0.737 |
haar | +0.732 |
root | +0.726 |
Neg logit contributions | |
azo | -0.727 |
affles | -0.701 |
bugs | -0.693 |
bug | -0.663 |
ception | -0.653 |
Token | not |
Token ID | 407 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Franch | +1.413 |
WD | +1.260 |
wd | +1.235 |
haar | +1.221 |
root | +1.217 |
Neg logit contributions | |
azo | -1.007 |
affles | -0.990 |
bugs | -0.975 |
bug | -0.927 |
ception | -0.896 |
Token | comment |
Token ID | 2912 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
Franch | +1.305 |
WD | +1.165 |
wd | +1.137 |
haar | +1.129 |
root | +1.122 |
Neg logit contributions | |
azo | -1.020 |
affles | -0.993 |
bugs | -0.982 |
bug | -0.940 |
ception | -0.914 |
Token | because |
Token ID | 780 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
azo | +0.610 |
affles | +0.591 |
bugs | +0.588 |
bug | +0.568 |
ception | +0.554 |
Neg logit contributions | |
Franch | -0.567 |
WD | -0.500 |
haar | -0.484 |
wd | -0.480 |
root | -0.472 |
Token | the |
Token ID | 262 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Franch | +0.890 |
WD | +0.788 |
haar | +0.768 |
wd | +0.762 |
root | +0.755 |
Neg logit contributions | |
azo | -0.659 |
affles | -0.632 |
bugs | -0.631 |
bug | -0.604 |
ception | -0.583 |
Token | settlement |
Token ID | 9443 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
azo | +0.518 |
affles | +0.503 |
bugs | +0.501 |
bug | +0.485 |
ception | +0.474 |
Neg logit contributions | |
Franch | -0.419 |
WD | -0.363 |
haar | -0.350 |
wd | -0.346 |
root | -0.341 |
Token | did |
Token ID | 750 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
azo | +4.694 |
bugs | +4.611 |
affles | +4.571 |
bug | +4.416 |
ception | +4.274 |
Neg logit contributions | |
Franch | -7.151 |
WD | -6.618 |
haar | -6.376 |
wd | -6.346 |
root | -6.240 |
Token | not |
Token ID | 407 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
azo | +0.496 |
affles | +0.477 |
bugs | +0.472 |
bug | +0.450 |
ception | +0.434 |
Neg logit contributions | |
Franch | -0.803 |
WD | -0.729 |
haar | -0.711 |
wd | -0.707 |
root | -0.698 |
Token | involve |
Token ID | 6211 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
azo | +0.230 |
affles | +0.225 |
bugs | +0.223 |
bug | +0.214 |
ception | +0.208 |
Neg logit contributions | |
Franch | -0.245 |
WD | -0.218 |
haar | -0.213 |
wd | -0.210 |
root | -0.208 |
Token | his |
Token ID | 465 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
Franch | +1.228 |
WD | +1.079 |
haar | +1.049 |
wd | +1.035 |
root | +1.030 |
Neg logit contributions | |
azo | -1.137 |
affles | -1.096 |
bugs | -1.094 |
bug | -1.050 |
ception | -1.025 |
Token | client |
Token ID | 5456 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Franch | +0.698 |
WD | +0.620 |
haar | +0.603 |
wd | +0.596 |
root | +0.589 |
Neg logit contributions | |
azo | -0.558 |
affles | -0.535 |
bugs | -0.533 |
bug | -0.512 |
ception | -0.493 |
Token | week |
Token ID | 1285 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
azo | +1.319 |
bugs | +1.233 |
affles | +1.212 |
bug | +1.203 |
ception | +1.155 |
Neg logit contributions | |
Franch | -2.484 |
WD | -2.276 |
haar | -2.243 |
wd | -2.179 |
root | -2.162 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
azo | +1.024 |
affles | +0.989 |
bugs | +0.985 |
bug | +0.958 |
ception | +0.926 |
Neg logit contributions | |
Franch | -1.094 |
WD | -0.969 |
haar | -0.953 |
wd | -0.931 |
root | -0.915 |
Token | You |
Token ID | 921 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Franch | +0.351 |
WD | +0.310 |
haar | +0.304 |
wd | +0.296 |
root | +0.291 |
Neg logit contributions | |
azo | -0.380 |
affles | -0.373 |
bugs | -0.371 |
bug | -0.360 |
ception | -0.351 |
Token | will |
Token ID | 481 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
azo | +0.689 |
bugs | +0.661 |
affles | +0.656 |
bug | +0.639 |
ception | +0.615 |
Neg logit contributions | |
Franch | -0.993 |
WD | -0.885 |
haar | -0.879 |
wd | -0.846 |
entin | -0.844 |
Token | receive |
Token ID | 3328 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
azo | +1.124 |
affles | +1.022 |
bugs | +0.997 |
bug | +0.982 |
ception | +0.940 |
Neg logit contributions | |
Franch | -2.590 |
haar | -2.339 |
WD | -2.327 |
root | -2.266 |
wd | -2.234 |
Token | occasional |
Token ID | 12209 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
azo | +1.744 |
bugs | +1.701 |
affles | +1.644 |
ception | +1.528 |
bug | +1.525 |
Neg logit contributions | |
Franch | -5.435 |
WD | -4.961 |
haar | -4.940 |
root | -4.860 |
wd | -4.769 |
Token | promotional |
Token ID | 18767 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
azo | +6.602 |
bugs | +6.402 |
affles | +6.353 |
ception | +6.161 |
bug | +6.154 |
Neg logit contributions | |
Franch | -5.124 |
WD | -4.736 |
haar | -4.578 |
wd | -4.373 |
root | -4.302 |
Token | offers |
Token ID | 4394 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
azo | +2.974 |
affles | +2.938 |
bugs | +2.918 |
bug | +2.718 |
ception | +2.604 |
Neg logit contributions | |
Franch | -6.102 |
haar | -5.599 |
WD | -5.580 |
wd | -5.447 |
root | -5.417 |
Token | for |
Token ID | 329 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
azo | +3.249 |
bugs | +3.238 |
affles | +3.148 |
bug | +3.118 |
ception | +2.920 |
Neg logit contributions | |
Franch | -5.884 |
srf | -5.444 |
WD | -5.304 |
haar | -5.286 |
entin | -5.168 |
Token | programs |
Token ID | 4056 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
azo | +3.018 |
affles | +3.001 |
bugs | +2.969 |
bug | +2.828 |
ception | +2.778 |
Neg logit contributions | |
Franch | -3.616 |
haar | -3.209 |
WD | -3.197 |
root | -3.082 |
wd | -3.068 |
Token | that |
Token ID | 326 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
azo | +2.286 |
affles | +2.242 |
bugs | +2.238 |
bug | +2.155 |
ception | +2.067 |
Neg logit contributions | |
Franch | -3.286 |
WD | -2.985 |
haar | -2.941 |
wd | -2.868 |
entin | -2.821 |
Token | the |
Token ID | 262 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Franch | +0.642 |
WD | +0.569 |
haar | +0.550 |
wd | +0.547 |
root | +0.541 |
Neg logit contributions | |
azo | -0.577 |
affles | -0.558 |
bugs | -0.555 |
bug | -0.533 |
ception | -0.519 |
Token | city |
Token ID | 1748 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Franch | +0.270 |
WD | +0.238 |
haar | +0.231 |
wd | +0.228 |
root | +0.227 |
Neg logit contributions | |
azo | -0.254 |
affles | -0.247 |
bugs | -0.245 |
bug | -0.236 |
ception | -0.230 |
Token | held |
Token ID | 2714 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
azo | +1.790 |
affles | +1.732 |
bugs | +1.721 |
bug | +1.658 |
ception | +1.611 |
Neg logit contributions | |
Franch | -2.016 |
WD | -1.805 |
haar | -1.757 |
wd | -1.739 |
root | -1.708 |
Token | . |
Token ID | 13 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
Franch | +0.132 |
WD | +0.117 |
haar | +0.114 |
wd | +0.113 |
root | +0.111 |
Neg logit contributions | |
azo | -0.120 |
affles | -0.116 |
bugs | -0.115 |
bug | -0.111 |
ception | -0.108 |
Token | The |
Token ID | 383 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
azo | +0.599 |
affles | +0.578 |
bugs | +0.575 |
bug | +0.552 |
ception | +0.537 |
Neg logit contributions | |
Franch | -0.694 |
WD | -0.620 |
haar | -0.602 |
wd | -0.598 |
root | -0.589 |
Token | settlement |
Token ID | 9443 |
Feature activation | +7.79e+00 |
Pos logit contributions | |
azo | +0.630 |
affles | +0.612 |
bugs | +0.608 |
bug | +0.586 |
ception | +0.572 |
Neg logit contributions | |
Franch | -0.635 |
WD | -0.563 |
haar | -0.545 |
wd | -0.540 |
root | -0.532 |
Token | was |
Token ID | 373 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
azo | +4.990 |
bugs | +4.840 |
affles | +4.822 |
bug | +4.662 |
ception | +4.493 |
Neg logit contributions | |
Franch | -6.496 |
WD | -5.965 |
haar | -5.811 |
wd | -5.704 |
root | -5.630 |
Token | arguably |
Token ID | 15242 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
Franch | +0.113 |
WD | +0.101 |
haar | +0.097 |
wd | +0.097 |
root | +0.096 |
Neg logit contributions | |
azo | -0.108 |
affles | -0.105 |
bugs | -0.104 |
bug | -0.100 |
ception | -0.098 |
Token | an |
Token ID | 281 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
azo | +0.032 |
affles | +0.031 |
bugs | +0.030 |
bug | +0.029 |
ception | +0.028 |
Neg logit contributions | |
Franch | -0.034 |
WD | -0.030 |
haar | -0.030 |
wd | -0.029 |
root | -0.029 |
Token | inevitable |
Token ID | 13203 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
azo | +0.459 |
affles | +0.446 |
bugs | +0.444 |
bug | +0.427 |
ception | +0.413 |
Neg logit contributions | |
Franch | -0.506 |
WD | -0.450 |
haar | -0.437 |
wd | -0.433 |
root | -0.426 |
Token | in |
Token ID | 287 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Franch | +1.554 |
WD | +1.337 |
haar | +1.289 |
wd | +1.280 |
root | +1.262 |
Neg logit contributions | |
azo | -1.989 |
affles | -1.958 |
bugs | -1.946 |
bug | -1.875 |
ception | -1.820 |
Token | website |
Token ID | 3052 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
azo | +0.091 |
affles | +0.088 |
bugs | +0.087 |
bug | +0.083 |
ception | +0.081 |
Neg logit contributions | |
Franch | -0.104 |
WD | -0.093 |
haar | -0.090 |
wd | -0.089 |
root | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
azo | +1.812 |
affles | +1.758 |
bugs | +1.749 |
bug | +1.688 |
ception | +1.648 |
Neg logit contributions | |
Franch | -1.852 |
WD | -1.626 |
haar | -1.591 |
wd | -1.569 |
root | -1.547 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
azo | +0.017 |
affles | +0.016 |
bugs | +0.016 |
bug | +0.015 |
ception | +0.015 |
Neg logit contributions | |
Franch | -0.018 |
WD | -0.016 |
haar | -0.016 |
wd | -0.016 |
root | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
azo | +0.708 |
affles | +0.683 |
bugs | +0.678 |
bug | +0.651 |
ception | +0.633 |
Neg logit contributions | |
Franch | -0.853 |
WD | -0.764 |
haar | -0.742 |
wd | -0.737 |
root | -0.727 |
Token | M |
Token ID | 44 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
azo | +0.836 |
affles | +0.808 |
bugs | +0.803 |
bug | +0.773 |
ception | +0.752 |
Neg logit contributions | |
Franch | -0.930 |
WD | -0.828 |
haar | -0.805 |
wd | -0.798 |
root | -0.786 |
Token | ISS |
Token ID | 16744 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
Franch | +0.420 |
WD | +0.375 |
haar | +0.362 |
wd | +0.360 |
root | +0.354 |
Neg logit contributions | |
azo | -0.413 |
affles | -0.401 |
bugs | -0.399 |
bug | -0.384 |
ception | -0.375 |
Token | ING |
Token ID | 2751 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
azo | +5.370 |
affles | +5.218 |
bugs | +5.175 |
bug | +5.036 |
ception | +4.903 |
Neg logit contributions | |
Franch | -6.108 |
haar | -5.370 |
WD | -5.305 |
wd | -5.276 |
root | -5.201 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
azo | +2.028 |
affles | +1.967 |
bugs | +1.957 |
bug | +1.887 |
ception | +1.835 |
Neg logit contributions | |
Franch | -2.201 |
WD | -1.954 |
haar | -1.907 |
wd | -1.887 |
root | -1.858 |
Token | - |
Token ID | 12 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
azo | +0.725 |
affles | +0.700 |
bugs | +0.695 |
bug | +0.668 |
ception | +0.651 |
Neg logit contributions | |
Franch | -0.822 |
WD | -0.737 |
haar | -0.711 |
wd | -0.709 |
root | -0.697 |
Token | Y |
Token ID | 56 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
azo | +0.282 |
affles | +0.272 |
bugs | +0.269 |
bug | +0.259 |
ception | +0.252 |
Neg logit contributions | |
Franch | -0.315 |
WD | -0.284 |
wd | -0.273 |
haar | -0.272 |
root | -0.268 |
Token | EAR |
Token ID | 17133 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
azo | +0.741 |
affles | +0.712 |
bugs | +0.704 |
bug | +0.672 |
ception | +0.656 |
Neg logit contributions | |
Franch | -1.157 |
WD | -1.060 |
haar | -1.021 |
wd | -1.020 |
root | -1.010 |
Token | kill |
Token ID | 1494 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Franch | +0.043 |
WD | +0.038 |
wd | +0.037 |
haar | +0.037 |
root | +0.036 |
Neg logit contributions | |
azo | -0.038 |
affles | -0.037 |
bugs | -0.037 |
bug | -0.035 |
ception | -0.034 |
Token | you |
Token ID | 345 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
azo | +0.450 |
affles | +0.437 |
bugs | +0.434 |
bug | +0.419 |
ception | +0.409 |
Neg logit contributions | |
Franch | -0.419 |
WD | -0.369 |
haar | -0.355 |
wd | -0.353 |
root | -0.349 |
Token | ." |
Token ID | 526 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Franch | +0.543 |
WD | +0.489 |
haar | +0.471 |
wd | +0.471 |
root | +0.466 |
Neg logit contributions | |
azo | -0.417 |
affles | -0.402 |
bugs | -0.401 |
bug | -0.382 |
ception | -0.372 |
Token | - |
Token ID | 532 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Franch | +1.114 |
WD | +0.995 |
haar | +0.948 |
wd | +0.947 |
root | +0.943 |
Neg logit contributions | |
azo | -0.894 |
bugs | -0.860 |
affles | -0.849 |
bug | -0.803 |
ception | -0.793 |
Token | T |
Token ID | 51 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
azo | +0.079 |
bugs | +0.076 |
affles | +0.076 |
bug | +0.072 |
ception | +0.071 |
Neg logit contributions | |
Franch | -0.091 |
WD | -0.082 |
haar | -0.079 |
wd | -0.078 |
root | -0.078 |
Token | oad |
Token ID | 1170 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
Franch | +0.158 |
WD | +0.141 |
haar | +0.135 |
wd | +0.134 |
root | +0.132 |
Neg logit contributions | |
azo | -0.172 |
bugs | -0.169 |
affles | -0.168 |
bug | -0.162 |
ception | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
azo | +5.249 |
affles | +5.127 |
bugs | +5.052 |
bug | +4.948 |
ception | +4.730 |
Neg logit contributions | |
Franch | -6.336 |
WD | -5.621 |
haar | -5.528 |
wd | -5.450 |
root | -5.349 |
Token | April |
Token ID | 3035 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
azo | +0.764 |
affles | +0.739 |
bugs | +0.735 |
bug | +0.704 |
ception | +0.688 |
Neg logit contributions | |
Franch | -0.831 |
WD | -0.743 |
haar | -0.713 |
wd | -0.712 |
root | -0.705 |
Token | 18 |
Token ID | 1248 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Franch | +0.288 |
WD | +0.255 |
wd | +0.244 |
haar | +0.244 |
root | +0.243 |
Neg logit contributions | |
azo | -0.286 |
affles | -0.279 |
bugs | -0.274 |
bug | -0.262 |
ception | -0.258 |
Token | th |
Token ID | 400 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
azo | +0.083 |
affles | +0.080 |
bugs | +0.080 |
bug | +0.077 |
ception | +0.075 |
Neg logit contributions | |
Franch | -0.072 |
WD | -0.063 |
haar | -0.061 |
wd | -0.061 |
root | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Franch | +0.446 |
WD | +0.395 |
haar | +0.379 |
wd | +0.377 |
root | +0.371 |
Neg logit contributions | |
azo | -0.496 |
affles | -0.481 |
bugs | -0.478 |
bug | -0.461 |
ception | -0.452 |
Token | dain |
Token ID | 27162 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
azo | +2.077 |
affles | +1.988 |
bugs | +1.985 |
bug | +1.908 |
ception | +1.853 |
Neg logit contributions | |
Franch | -2.494 |
WD | -2.232 |
haar | -2.164 |
wd | -2.146 |
root | -2.110 |
Token | in |
Token ID | 287 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
azo | +0.909 |
affles | +0.882 |
bugs | +0.876 |
bug | +0.845 |
ception | +0.823 |
Neg logit contributions | |
Franch | -0.918 |
WD | -0.813 |
haar | -0.789 |
wd | -0.782 |
root | -0.769 |
Token | public |
Token ID | 1171 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
azo | +0.761 |
affles | +0.736 |
bugs | +0.731 |
bug | +0.704 |
ception | +0.685 |
Neg logit contributions | |
Franch | -0.838 |
WD | -0.747 |
haar | -0.725 |
wd | -0.719 |
root | -0.708 |
Token | — |
Token ID | 960 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
Franch | +1.865 |
WD | +1.639 |
haar | +1.577 |
wd | +1.564 |
root | +1.543 |
Neg logit contributions | |
azo | -2.018 |
bugs | -1.927 |
affles | -1.927 |
bug | -1.861 |
ception | -1.806 |
Token | p |
Token ID | 79 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
azo | +2.028 |
bugs | +1.967 |
affles | +1.966 |
bug | +1.894 |
ception | +1.836 |
Neg logit contributions | |
Franch | -2.320 |
WD | -2.062 |
haar | -2.009 |
wd | -1.987 |
root | -1.943 |
Token | iss |
Token ID | 747 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
Franch | +0.525 |
WD | +0.468 |
wd | +0.452 |
haar | +0.451 |
root | +0.445 |
Neg logit contributions | |
azo | -0.532 |
bugs | -0.517 |
affles | -0.513 |
bug | -0.496 |
ception | -0.480 |
Token | ing |
Token ID | 278 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
azo | +6.984 |
affles | +6.762 |
bugs | +6.698 |
bug | +6.511 |
ception | +6.398 |
Neg logit contributions | |
Franch | -4.617 |
WD | -3.973 |
haar | -3.921 |
wd | -3.780 |
root | -3.633 |
Token | off |
Token ID | 572 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
azo | +1.385 |
affles | +1.341 |
bugs | +1.332 |
bug | +1.280 |
ception | +1.243 |
Neg logit contributions | |
Franch | -1.648 |
WD | -1.476 |
haar | -1.438 |
wd | -1.424 |
root | -1.401 |
Token | one |
Token ID | 530 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
azo | +0.695 |
affles | +0.670 |
bugs | +0.666 |
bug | +0.639 |
ception | +0.622 |
Neg logit contributions | |
Franch | -0.830 |
WD | -0.742 |
haar | -0.721 |
wd | -0.716 |
root | -0.706 |
Token | of |
Token ID | 286 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
azo | +1.530 |
affles | +1.480 |
bugs | +1.471 |
bug | +1.420 |
ception | +1.377 |
Neg logit contributions | |
Franch | -1.793 |
WD | -1.607 |
haar | -1.568 |
wd | -1.552 |
root | -1.528 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
azo | +0.178 |
affles | +0.171 |
bugs | +0.170 |
bug | +0.163 |
ception | +0.158 |
Neg logit contributions | |
Franch | -0.245 |
WD | -0.221 |
haar | -0.214 |
wd | -0.213 |
root | -0.211 |
Token | war |
Token ID | 1175 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Franch | +0.800 |
WD | +0.707 |
haar | +0.676 |
wd | +0.675 |
root | +0.666 |
Neg logit contributions | |
azo | -0.926 |
affles | -0.904 |
bugs | -0.897 |
bug | -0.862 |
ception | -0.840 |
Token | in |
Token ID | 287 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Franch | +0.454 |
WD | +0.407 |
haar | +0.393 |
wd | +0.393 |
root | +0.388 |
Neg logit contributions | |
azo | -0.382 |
affles | -0.371 |
bugs | -0.367 |
bug | -0.351 |
ception | -0.342 |
Token | Iraq |
Token ID | 3908 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Franch | +0.201 |
WD | +0.179 |
haar | +0.174 |
wd | +0.173 |
root | +0.170 |
Neg logit contributions | |
azo | -0.176 |
affles | -0.170 |
bugs | -0.169 |
bug | -0.162 |
ception | -0.158 |
Token | ( |
Token ID | 357 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
azo | +1.346 |
affles | +1.303 |
bugs | +1.302 |
bug | +1.252 |
ception | +1.215 |
Neg logit contributions | |
Franch | -1.444 |
WD | -1.280 |
haar | -1.246 |
wd | -1.233 |
root | -1.211 |
Token | proven |
Token ID | 42874 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Franch | +0.053 |
WD | +0.047 |
haar | +0.046 |
wd | +0.045 |
root | +0.045 |
Neg logit contributions | |
azo | -0.053 |
affles | -0.051 |
bugs | -0.051 |
bug | -0.049 |
ception | -0.048 |
Token | oil |
Token ID | 3056 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
azo | +3.393 |
affles | +3.285 |
bugs | +3.271 |
bug | +3.163 |
ception | +3.067 |
Neg logit contributions | |
Franch | -3.478 |
WD | -3.060 |
haar | -3.023 |
wd | -2.965 |
root | -2.896 |
Token | reserves |
Token ID | 14072 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
azo | +6.623 |
affles | +6.472 |
bugs | +6.472 |
bug | +6.267 |
ception | +6.063 |
Neg logit contributions | |
Franch | -4.832 |
WD | -4.078 |
haar | -4.036 |
wd | -3.895 |
root | -3.820 |
Token | : |
Token ID | 25 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
azo | +3.960 |
affles | +3.815 |
bugs | +3.763 |
bug | +3.652 |
ception | +3.533 |
Neg logit contributions | |
Franch | -4.980 |
WD | -4.369 |
haar | -4.273 |
wd | -4.239 |
root | -4.217 |
Token | 140 |
Token ID | 12713 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
azo | +1.639 |
affles | +1.584 |
bugs | +1.573 |
bug | +1.518 |
ception | +1.476 |
Neg logit contributions | |
Franch | -1.878 |
WD | -1.677 |
haar | -1.633 |
wd | -1.621 |
root | -1.597 |
Token | billion |
Token ID | 2997 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
azo | +1.979 |
affles | +1.909 |
bugs | +1.894 |
bug | +1.832 |
ception | +1.785 |
Neg logit contributions | |
Franch | -2.037 |
WD | -1.783 |
haar | -1.740 |
wd | -1.712 |
root | -1.694 |
Token | barrels |
Token ID | 17907 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
azo | +1.830 |
affles | +1.779 |
bugs | +1.754 |
bug | +1.674 |
ception | +1.618 |
Neg logit contributions | |
Franch | -2.676 |
WD | -2.402 |
haar | -2.348 |
wd | -2.327 |
root | -2.300 |
Token | Del |
Token ID | 4216 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
Franch | +0.126 |
WD | +0.112 |
haar | +0.108 |
wd | +0.108 |
root | +0.106 |
Neg logit contributions | |
azo | -0.110 |
affles | -0.106 |
bugs | -0.104 |
bug | -0.100 |
ception | -0.098 |
Token | ayed |
Token ID | 16548 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
Franch | +0.493 |
WD | +0.432 |
haar | +0.421 |
wd | +0.418 |
root | +0.411 |
Neg logit contributions | |
azo | -0.514 |
affles | -0.498 |
bugs | -0.490 |
bug | -0.472 |
ception | -0.460 |
Token | Until |
Token ID | 14303 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
azo | +3.966 |
affles | +3.898 |
bugs | +3.888 |
bug | +3.773 |
ception | +3.661 |
Neg logit contributions | |
Franch | -4.972 |
WD | -4.548 |
haar | -4.510 |
wd | -4.391 |
root | -4.318 |
Token | At |
Token ID | 1629 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
azo | +0.446 |
affles | +0.432 |
bugs | +0.428 |
bug | +0.412 |
ception | +0.401 |
Neg logit contributions | |
Franch | -0.477 |
WD | -0.423 |
haar | -0.409 |
wd | -0.406 |
root | -0.400 |
Token | Le |
Token ID | 1004 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
azo | +1.758 |
affles | +1.708 |
bugs | +1.699 |
bug | +1.644 |
ception | +1.606 |
Neg logit contributions | |
Franch | -1.501 |
WD | -1.316 |
haar | -1.273 |
wd | -1.260 |
root | -1.235 |
Token | ast |
Token ID | 459 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
azo | +0.482 |
affles | +0.467 |
bugs | +0.464 |
bug | +0.445 |
ception | +0.433 |
Neg logit contributions | |
Franch | -0.552 |
WD | -0.495 |
haar | -0.480 |
wd | -0.479 |
root | -0.470 |
Token | March |
Token ID | 2805 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
azo | +4.913 |
bugs | +4.888 |
affles | +4.773 |
bug | +4.743 |
ception | +4.593 |
Neg logit contributions | |
Franch | -6.165 |
haar | -5.746 |
WD | -5.672 |
srf | -5.589 |
wd | -5.540 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
azo | +0.730 |
affles | +0.710 |
bugs | +0.702 |
bug | +0.673 |
ception | +0.659 |
Neg logit contributions | |
Franch | -0.764 |
WD | -0.676 |
haar | -0.654 |
wd | -0.651 |
root | -0.641 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
azo | +1.542 |
affles | +1.495 |
bugs | +1.488 |
bug | +1.436 |
ception | +1.400 |
Neg logit contributions | |
Franch | -1.503 |
WD | -1.330 |
haar | -1.291 |
wd | -1.278 |
root | -1.258 |
Token |
|
Token ID | 198 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
azo | +2.439 |
affles | +2.353 |
bugs | +2.342 |
bug | +2.261 |
ception | +2.195 |
Neg logit contributions | |
Franch | -3.024 |
WD | -2.708 |
haar | -2.662 |
wd | -2.625 |
root | -2.584 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
azo | +0.335 |
affles | +0.323 |
bugs | +0.320 |
bug | +0.307 |
ception | +0.299 |
Neg logit contributions | |
Franch | -0.397 |
WD | -0.356 |
haar | -0.345 |
wd | -0.344 |
root | -0.339 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
azo | +0.758 |
affles | +0.736 |
bugs | +0.729 |
bug | +0.703 |
ception | +0.685 |
Neg logit contributions | |
Franch | -0.755 |
WD | -0.668 |
haar | -0.647 |
wd | -0.643 |
root | -0.633 |
Token | we |
Token ID | 356 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
azo | +1.156 |
affles | +1.120 |
bugs | +1.112 |
bug | +1.071 |
ception | +1.043 |
Neg logit contributions | |
Franch | -1.228 |
WD | -1.092 |
haar | -1.059 |
wd | -1.051 |
root | -1.034 |
Token | reached |
Token ID | 4251 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
azo | +1.337 |
affles | +1.289 |
bugs | +1.284 |
bug | +1.235 |
ception | +1.199 |
Neg logit contributions | |
Franch | -1.530 |
WD | -1.367 |
haar | -1.328 |
wd | -1.318 |
root | -1.296 |
Token | out |
Token ID | 503 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
azo | +0.393 |
affles | +0.380 |
bugs | +0.378 |
bug | +0.364 |
ception | +0.354 |
Neg logit contributions | |
Franch | -0.425 |
WD | -0.379 |
haar | -0.367 |
wd | -0.365 |
root | -0.359 |
Token | on |
Token ID | 319 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
azo | +1.078 |
affles | +1.038 |
bugs | +1.031 |
bug | +0.986 |
ception | +0.954 |
Neg logit contributions | |
Franch | -1.544 |
WD | -1.393 |
haar | -1.357 |
wd | -1.348 |
root | -1.329 |
Token | Stack |
Token ID | 23881 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
Franch | +0.438 |
WD | +0.389 |
haar | +0.378 |
wd | +0.375 |
root | +0.370 |
Neg logit contributions | |
azo | -0.394 |
affles | -0.381 |
bugs | -0.376 |
bug | -0.363 |
ception | -0.355 |
Token | Over |
Token ID | 3827 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
azo | +4.609 |
bugs | +4.492 |
affles | +4.411 |
bug | +4.275 |
ception | +4.149 |
Neg logit contributions | |
Franch | -7.007 |
WD | -6.291 |
haar | -6.154 |
wd | -6.074 |
root | -5.927 |
Token | flow |
Token ID | 11125 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
azo | +1.103 |
affles | +1.053 |
bugs | +1.037 |
bug | +0.978 |
ception | +0.942 |
Neg logit contributions | |
Franch | -2.183 |
WD | -2.000 |
haar | -1.951 |
wd | -1.940 |
root | -1.924 |
Token | with |
Token ID | 351 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
azo | +1.872 |
affles | +1.808 |
bugs | +1.801 |
bug | +1.724 |
ception | +1.672 |
Neg logit contributions | |
Franch | -2.430 |
WD | -2.179 |
haar | -2.126 |
wd | -2.110 |
root | -2.077 |
Token | our |
Token ID | 674 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
azo | +0.275 |
affles | +0.266 |
bugs | +0.264 |
bug | +0.254 |
ception | +0.248 |
Neg logit contributions | |
Franch | -0.296 |
WD | -0.263 |
haar | -0.255 |
wd | -0.253 |
root | -0.249 |
Token | con |
Token ID | 369 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
azo | +1.351 |
affles | +1.310 |
bugs | +1.304 |
bug | +1.257 |
ception | +1.225 |
Neg logit contributions | |
Franch | -1.329 |
WD | -1.176 |
haar | -1.138 |
wd | -1.130 |
root | -1.110 |
Token | 6 |
Token ID | 718 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Franch | +0.249 |
WD | +0.225 |
haar | +0.219 |
wd | +0.218 |
root | +0.215 |
Neg logit contributions | |
azo | -0.177 |
affles | -0.170 |
bugs | -0.169 |
bug | -0.161 |
ception | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
azo | +0.462 |
affles | +0.449 |
bugs | +0.447 |
bug | +0.431 |
ception | +0.420 |
Neg logit contributions | |
Franch | -0.442 |
WD | -0.390 |
haar | -0.379 |
wd | -0.374 |
root | -0.368 |
Token | Drain |
Token ID | 36024 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
azo | +0.822 |
affles | +0.788 |
bugs | +0.781 |
bug | +0.743 |
ception | +0.717 |
Neg logit contributions | |
Franch | -1.387 |
WD | -1.261 |
haar | -1.231 |
wd | -1.223 |
root | -1.207 |
Token | on |
Token ID | 319 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
azo | +2.622 |
bugs | +2.578 |
affles | +2.565 |
bug | +2.510 |
ception | +2.395 |
Neg logit contributions | |
Franch | -2.656 |
WD | -2.340 |
haar | -2.327 |
wd | -2.264 |
entin | -2.214 |
Token | a |
Token ID | 257 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
azo | +1.727 |
affles | +1.681 |
bugs | +1.669 |
bug | +1.612 |
ception | +1.567 |
Neg logit contributions | |
Franch | -1.758 |
WD | -1.554 |
haar | -1.518 |
wd | -1.493 |
root | -1.472 |
Token | paper |
Token ID | 3348 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
azo | +3.778 |
affles | +3.666 |
bugs | +3.660 |
bug | +3.586 |
ception | +3.496 |
Neg logit contributions | |
Franch | -2.421 |
WD | -2.038 |
haar | -1.994 |
wd | -1.942 |
root | -1.911 |
Token | towel |
Token ID | 24808 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
azo | +2.319 |
bugs | +2.010 |
bug | +1.971 |
affles | +1.951 |
ception | +1.680 |
Neg logit contributions | |
Franch | -9.277 |
WD | -8.448 |
haar | -8.431 |
wd | -8.281 |
entin | -8.260 |
Token | - |
Token ID | 12 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
azo | +4.429 |
bugs | +4.255 |
affles | +4.181 |
bug | +4.162 |
ception | +3.975 |
Neg logit contributions | |
Franch | -8.031 |
WD | -7.250 |
srf | -7.225 |
haar | -7.148 |
wd | -6.995 |
Token | lined |
Token ID | 10837 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
azo | +2.310 |
bugs | +2.224 |
affles | +2.213 |
bug | +2.161 |
ception | +2.092 |
Neg logit contributions | |
Franch | -2.631 |
WD | -2.282 |
haar | -2.252 |
wd | -2.182 |
srf | -2.149 |
Token | plate |
Token ID | 7480 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
azo | +2.072 |
bugs | +1.872 |
affles | +1.849 |
bug | +1.810 |
ception | +1.617 |
Neg logit contributions | |
Franch | -7.779 |
WD | -7.222 |
haar | -7.134 |
wd | -7.045 |
root | -6.938 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
azo | +3.051 |
bugs | +2.988 |
affles | +2.971 |
bug | +2.905 |
ception | +2.795 |
Neg logit contributions | |
Franch | -3.513 |
WD | -3.104 |
haar | -3.101 |
srf | -3.067 |
wd | -2.999 |
Token | 12 |
Token ID | 1065 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
azo | +2.016 |
bugs | +1.959 |
affles | +1.955 |
bug | +1.888 |
ception | +1.833 |
Neg logit contributions | |
Franch | -2.547 |
WD | -2.246 |
haar | -2.224 |
wd | -2.172 |
root | -2.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
azo | +3.009 |
bugs | +2.937 |
affles | +2.904 |
bug | +2.863 |
ception | +2.747 |
Neg logit contributions | |
Franch | -3.407 |
WD | -2.999 |
haar | -2.968 |
srf | -2.939 |
wd | -2.899 |
Token | e |
Token ID | 68 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
azo | +0.602 |
affles | +0.578 |
bugs | +0.576 |
bug | +0.549 |
ception | +0.520 |
Neg logit contributions | |
Franch | -1.091 |
haar | -0.960 |
WD | -0.948 |
wd | -0.927 |
root | -0.917 |
Token | ce |
Token ID | 344 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Franch | +0.589 |
WD | +0.527 |
wd | +0.507 |
haar | +0.507 |
root | +0.498 |
Neg logit contributions | |
azo | -0.575 |
affles | -0.559 |
bugs | -0.553 |
bug | -0.531 |
ception | -0.513 |
Token | / |
Token ID | 14 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
azo | +1.747 |
bugs | +1.670 |
affles | +1.668 |
bug | +1.595 |
ception | +1.545 |
Neg logit contributions | |
Franch | -3.017 |
WD | -2.723 |
haar | -2.669 |
wd | -2.643 |
root | -2.617 |
Token | edd |
Token ID | 6048 |
Feature activation | +7.53e+00 |
Pos logit contributions | |
Franch | +0.824 |
WD | +0.740 |
wd | +0.717 |
haar | +0.717 |
root | +0.705 |
Neg logit contributions | |
azo | -0.754 |
affles | -0.730 |
bugs | -0.724 |
bug | -0.694 |
ception | -0.678 |
Token | 75 |
Token ID | 2425 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
azo | +5.339 |
affles | +5.208 |
bugs | +5.131 |
bug | +5.026 |
ception | +4.823 |
Neg logit contributions | |
Franch | -6.114 |
WD | -5.224 |
haar | -5.187 |
srf | -5.010 |
wd | -4.935 |
Token | / |
Token ID | 14 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
azo | +1.038 |
affles | +0.995 |
bugs | +0.993 |
bug | +0.952 |
ception | +0.915 |
Neg logit contributions | |
Franch | -1.667 |
WD | -1.502 |
haar | -1.471 |
wd | -1.451 |
root | -1.432 |
Token | AUT |
Token ID | 39371 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
bugs | +0.404 |
bug | +0.394 |
azo | +0.393 |
affles | +0.392 |
ception | +0.365 |
Neg logit contributions | |
Franch | -0.418 |
haar | -0.363 |
WD | -0.363 |
wd | -0.359 |
root | -0.345 |
Token | OC |
Token ID | 4503 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
azo | +3.105 |
affles | +2.945 |
bugs | +2.927 |
bug | +2.720 |
UTC | +2.542 |
Neg logit contributions | |
Franch | -8.280 |
haar | -7.639 |
wd | -7.361 |
entin | -7.315 |
WD | -7.273 |
Token | R |
Token ID | 49 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
azo | +3.294 |
bugs | +3.234 |
affles | +3.223 |
bug | +3.118 |
UTC | +2.932 |
Neg logit contributions | |
Franch | -4.799 |
haar | -4.290 |
entin | -4.162 |
srf | -3.954 |
wd | -3.926 |
Token | AA |
Token ID | 15923 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
azo | +1.191 |
affles | +1.157 |
bugs | +1.155 |
bug | +1.120 |
ception | +1.092 |
Neg logit contributions | |
Franch | -0.883 |
WD | -0.763 |
haar | -0.739 |
wd | -0.727 |
root | -0.712 |
Token | on |
Token ID | 319 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
azo | +1.414 |
affles | +1.374 |
bugs | +1.374 |
bug | +1.333 |
ception | +1.291 |
Neg logit contributions | |
Franch | -1.313 |
WD | -1.141 |
haar | -1.124 |
wd | -1.098 |
root | -1.076 |
Token | ( |
Token ID | 357 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
azo | +1.873 |
affles | +1.824 |
bugs | +1.818 |
bug | +1.756 |
ception | +1.698 |
Neg logit contributions | |
Franch | -2.437 |
WD | -2.196 |
haar | -2.158 |
wd | -2.127 |
root | -2.087 |
Token | Anti |
Token ID | 28795 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
azo | +1.016 |
bugs | +0.973 |
affles | +0.971 |
bug | +0.930 |
ception | +0.893 |
Neg logit contributions | |
Franch | -1.661 |
WD | -1.494 |
haar | -1.470 |
wd | -1.454 |
root | -1.429 |
Token | Ali |
Token ID | 37893 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
azo | +2.701 |
bugs | +2.555 |
affles | +2.498 |
bug | +2.427 |
ception | +2.287 |
Neg logit contributions | |
Franch | -6.246 |
WD | -5.676 |
haar | -5.620 |
wd | -5.570 |
srf | -5.455 |
Token | asing |
Token ID | 2313 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
azo | +2.168 |
affles | +1.972 |
bugs | +1.953 |
bug | +1.839 |
ception | +1.724 |
Neg logit contributions | |
Franch | -5.977 |
WD | -5.449 |
haar | -5.367 |
wd | -5.298 |
root | -5.284 |
Token | is |
Token ID | 318 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
azo | +3.558 |
bugs | +3.423 |
affles | +3.348 |
bug | +3.281 |
ception | +3.111 |
Neg logit contributions | |
Franch | -7.812 |
haar | -6.958 |
srf | -6.952 |
WD | -6.916 |
wd | -6.826 |
Token | a |
Token ID | 257 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
azo | +2.861 |
bugs | +2.775 |
affles | +2.759 |
bug | +2.691 |
ception | +2.591 |
Neg logit contributions | |
Franch | -3.308 |
WD | -2.894 |
haar | -2.850 |
wd | -2.787 |
root | -2.770 |
Token | technique |
Token ID | 8173 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
azo | +2.112 |
bugs | +2.004 |
affles | +1.994 |
bug | +1.945 |
ception | +1.885 |
Neg logit contributions | |
Franch | -3.078 |
WD | -2.748 |
haar | -2.691 |
wd | -2.670 |
root | -2.629 |
Token | used |
Token ID | 973 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
azo | +4.508 |
bugs | +4.444 |
affles | +4.377 |
bug | +4.348 |
ception | +4.175 |
Neg logit contributions | |
Franch | -5.936 |
haar | -5.123 |
srf | -5.065 |
WD | -5.045 |
entin | -5.001 |
Token | to |
Token ID | 284 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
azo | +2.211 |
bugs | +2.121 |
affles | +2.112 |
bug | +2.030 |
ception | +1.948 |
Neg logit contributions | |
Franch | -3.588 |
WD | -3.223 |
haar | -3.188 |
wd | -3.129 |
root | -3.088 |
Token | frame |
Token ID | 5739 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
azo | +0.457 |
affles | +0.431 |
bugs | +0.426 |
bug | +0.399 |
ception | +0.381 |
Neg logit contributions | |
Franch | -1.162 |
WD | -1.069 |
haar | -1.047 |
wd | -1.040 |
root | -1.029 |
Token | | |
Token ID | 930 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
azo | +0.497 |
affles | +0.478 |
bugs | +0.475 |
bug | +0.454 |
ception | +0.438 |
Neg logit contributions | |
Franch | -0.750 |
WD | -0.679 |
haar | -0.663 |
wd | -0.657 |
root | -0.648 |
Token | size |
Token ID | 2546 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
Franch | +1.098 |
WD | +0.978 |
wd | +0.941 |
haar | +0.926 |
root | +0.922 |
Neg logit contributions | |
azo | -1.347 |
affles | -1.311 |
bugs | -1.296 |
bug | -1.243 |
ception | -1.217 |
Token | _ |
Token ID | 62 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
azo | +3.050 |
bugs | +2.975 |
affles | +2.922 |
bug | +2.888 |
ception | +2.737 |
Neg logit contributions | |
Franch | -5.555 |
haar | -4.909 |
WD | -4.895 |
srf | -4.873 |
entin | -4.777 |
Token | t |
Token ID | 83 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Franch | +0.649 |
WD | +0.593 |
wd | +0.575 |
haar | +0.574 |
root | +0.573 |
Neg logit contributions | |
azo | -0.493 |
affles | -0.477 |
bugs | -0.469 |
bug | -0.446 |
ception | -0.436 |
Token | count |
Token ID | 954 |
Feature activation | +7.48e+00 |
Pos logit contributions | |
azo | +1.631 |
affles | +1.551 |
bugs | +1.546 |
bug | +1.464 |
ception | +1.408 |
Neg logit contributions | |
Franch | -3.287 |
WD | -2.985 |
haar | -2.932 |
wd | -2.894 |
root | -2.867 |
Token | | |
Token ID | 930 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
bugs | +3.657 |
azo | +3.602 |
bug | +3.487 |
affles | +3.471 |
ception | +3.234 |
Neg logit contributions | |
Franch | -7.576 |
srf | -6.846 |
haar | -6.789 |
WD | -6.716 |
entin | -6.561 |
Token | + |
Token ID | 1343 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Franch | +0.371 |
WD | +0.324 |
haar | +0.312 |
wd | +0.309 |
root | +0.305 |
Neg logit contributions | |
azo | -0.480 |
affles | -0.468 |
bugs | -0.464 |
bug | -0.448 |
ception | -0.439 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
azo | +0.977 |
bugs | +0.938 |
affles | +0.937 |
bug | +0.893 |
ception | +0.849 |
Neg logit contributions | |
Franch | -1.732 |
WD | -1.556 |
haar | -1.528 |
wd | -1.515 |
root | -1.484 |
Token | --+ |
Token ID | 44785 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
azo | +2.082 |
affles | +2.003 |
bugs | +1.997 |
bug | +1.919 |
ception | +1.863 |
Neg logit contributions | |
Franch | -2.550 |
WD | -2.265 |
haar | -2.207 |
wd | -2.188 |
root | -2.158 |
Token | | |
Token ID | 930 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
azo | +0.532 |
affles | +0.511 |
bugs | +0.509 |
bug | +0.486 |
ception | +0.470 |
Neg logit contributions | |
Franch | -0.804 |
WD | -0.727 |
haar | -0.710 |
wd | -0.704 |
root | -0.694 |
Token | and |
Token ID | 290 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Franch | +0.292 |
WD | +0.261 |
haar | +0.254 |
wd | +0.252 |
root | +0.248 |
Neg logit contributions | |
azo | -0.254 |
affles | -0.246 |
bugs | -0.244 |
bug | -0.235 |
ception | -0.229 |
Token | Ros |
Token ID | 10018 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Franch | +0.271 |
WD | +0.242 |
haar | +0.233 |
wd | +0.232 |
root | +0.229 |
Neg logit contributions | |
azo | -0.252 |
affles | -0.243 |
bugs | -0.242 |
bug | -0.233 |
ception | -0.227 |
Token | cos |
Token ID | 6966 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
azo | +0.836 |
affles | +0.809 |
bugs | +0.803 |
bug | +0.774 |
ception | +0.754 |
Neg logit contributions | |
Franch | -0.899 |
WD | -0.800 |
haar | -0.773 |
wd | -0.769 |
root | -0.752 |
Token | mos |
Token ID | 16785 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Franch | +4.434 |
WD | +4.027 |
wd | +3.891 |
haar | +3.863 |
root | +3.758 |
Neg logit contributions | |
azo | -3.494 |
affles | -3.417 |
bugs | -3.417 |
bug | -3.242 |
ception | -3.136 |
Token | cos |
Token ID | 8615 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Franch | +2.427 |
WD | +2.150 |
wd | +2.067 |
haar | +2.053 |
root | +2.049 |
Neg logit contributions | |
azo | -2.466 |
affles | -2.371 |
bugs | -2.357 |
bug | -2.256 |
ception | -2.201 |
Token | mon |
Token ID | 2144 |
Feature activation | -8.54e+00 |
Pos logit contributions | |
Franch | +2.899 |
WD | +2.548 |
root | +2.482 |
wd | +2.462 |
haar | +2.435 |
Neg logit contributions | |
azo | -3.558 |
affles | -3.471 |
bugs | -3.469 |
bug | -3.323 |
haps | -3.216 |
Token | auts |
Token ID | 17712 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Franch | +5.031 |
root | +4.227 |
WD | +4.204 |
haar | +4.072 |
entin | +4.031 |
Neg logit contributions | |
azo | -7.560 |
affles | -7.386 |
bugs | -7.198 |
bug | -6.857 |
haps | -6.831 |
Token | Sergey |
Token ID | 36106 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Franch | +0.816 |
WD | +0.721 |
haar | +0.698 |
wd | +0.694 |
root | +0.683 |
Neg logit contributions | |
azo | -0.787 |
affles | -0.763 |
bugs | -0.759 |
bug | -0.729 |
ception | -0.713 |
Token | Ry |
Token ID | 11089 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
azo | +0.342 |
affles | +0.330 |
bugs | +0.327 |
bug | +0.313 |
ception | +0.308 |
Neg logit contributions | |
Franch | -0.352 |
WD | -0.308 |
haar | -0.298 |
root | -0.297 |
wd | -0.296 |
Token | zh |
Token ID | 23548 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Franch | +1.480 |
haar | +1.273 |
root | +1.265 |
WD | +1.265 |
wd | +1.246 |
Neg logit contributions | |
azo | -1.751 |
bugs | -1.715 |
affles | -1.714 |
ception | -1.639 |
bug | -1.625 |
Token | ik |
Token ID | 1134 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Franch | +2.070 |
WD | +1.817 |
haar | +1.778 |
wd | +1.773 |
root | +1.756 |
Neg logit contributions | |
azo | -2.435 |
affles | -2.378 |
bugs | -2.340 |
bug | -2.234 |
ception | -2.231 |
Token | PC |
Token ID | 5662 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Franch | +3.465 |
WD | +3.181 |
wd | +3.053 |
haar | +3.045 |
root | +3.038 |
Neg logit contributions | |
azo | -2.575 |
affles | -2.510 |
bugs | -2.473 |
bug | -2.350 |
ception | -2.268 |
Token | of |
Token ID | 286 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
azo | +0.375 |
affles | +0.363 |
bugs | +0.360 |
bug | +0.347 |
ception | +0.338 |
Neg logit contributions | |
Franch | -0.399 |
WD | -0.355 |
haar | -0.345 |
wd | -0.342 |
root | -0.337 |
Token | the |
Token ID | 262 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
azo | +0.547 |
affles | +0.527 |
bugs | +0.524 |
bug | +0.502 |
ception | +0.488 |
Neg logit contributions | |
Franch | -0.698 |
WD | -0.627 |
haar | -0.610 |
wd | -0.606 |
root | -0.597 |
Token | Best |
Token ID | 6705 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
azo | +0.537 |
affles | +0.520 |
bugs | +0.517 |
bug | +0.498 |
ception | +0.486 |
Neg logit contributions | |
Franch | -0.540 |
WD | -0.478 |
haar | -0.464 |
wd | -0.460 |
root | -0.453 |
Token | Buy |
Token ID | 11763 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
Franch | +0.340 |
WD | +0.291 |
haar | +0.281 |
wd | +0.278 |
root | +0.273 |
Neg logit contributions | |
azo | -0.483 |
affles | -0.469 |
bugs | -0.466 |
bug | -0.451 |
ception | -0.444 |
Token | Nexus |
Token ID | 16756 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
azo | +0.452 |
affles | +0.439 |
bugs | +0.436 |
bug | +0.421 |
ception | +0.411 |
Neg logit contributions | |
Franch | -0.415 |
WD | -0.365 |
haar | -0.353 |
wd | -0.350 |
root | -0.344 |
Token | 6 |
Token ID | 718 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
Franch | +6.511 |
WD | +5.819 |
root | +5.676 |
haar | +5.542 |
wd | +5.511 |
Neg logit contributions | |
azo | -5.721 |
affles | -5.625 |
bugs | -5.440 |
bug | -5.135 |
ception | -5.049 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Franch | +4.069 |
WD | +3.665 |
haar | +3.512 |
root | +3.472 |
wd | +3.465 |
Neg logit contributions | |
azo | -4.045 |
affles | -3.902 |
bugs | -3.832 |
bug | -3.660 |
ception | -3.601 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Franch | +0.375 |
WD | +0.334 |
haar | +0.322 |
wd | +0.320 |
root | +0.316 |
Neg logit contributions | |
azo | -0.353 |
affles | -0.340 |
bugs | -0.337 |
bug | -0.324 |
ception | -0.316 |
Token |
|
Token ID | 198 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Franch | +1.375 |
WD | +1.241 |
wd | +1.196 |
root | +1.189 |
haar | +1.174 |
Neg logit contributions | |
azo | -1.342 |
affles | -1.294 |
bugs | -1.266 |
bug | -1.208 |
ception | -1.186 |
Token | Any |
Token ID | 7149 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Franch | +1.592 |
WD | +1.464 |
wd | +1.397 |
root | +1.390 |
haar | +1.385 |
Neg logit contributions | |
azo | -1.547 |
affles | -1.498 |
bugs | -1.474 |
bug | -1.412 |
ception | -1.379 |
Token | government |
Token ID | 1230 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
azo | +0.092 |
affles | +0.089 |
bugs | +0.089 |
bug | +0.086 |
ception | +0.083 |
Neg logit contributions | |
Franch | -0.085 |
WD | -0.075 |
wd | -0.072 |
haar | -0.072 |
root | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Franch | +1.515 |
WD | +1.355 |
wd | +1.322 |
haar | +1.297 |
root | +1.290 |
Neg logit contributions | |
azo | -1.340 |
affles | -1.281 |
bugs | -1.260 |
bug | -1.211 |
ception | -1.170 |
Token | much |
Token ID | 881 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Franch | +1.631 |
WD | +1.438 |
wd | +1.384 |
haar | +1.382 |
root | +1.365 |
Neg logit contributions | |
azo | -1.643 |
affles | -1.594 |
bugs | -1.583 |
bug | -1.517 |
ception | -1.467 |
Token | less |
Token ID | 1342 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
Franch | +2.214 |
WD | +1.884 |
wd | +1.812 |
haar | +1.796 |
root | +1.792 |
Neg logit contributions | |
azo | -3.108 |
affles | -3.023 |
bugs | -3.006 |
bug | -2.890 |
ception | -2.821 |
Token | a |
Token ID | 257 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
Franch | +2.988 |
WD | +2.623 |
wd | +2.523 |
root | +2.505 |
haar | +2.494 |
Neg logit contributions | |
azo | -2.920 |
affles | -2.812 |
bugs | -2.799 |
bug | -2.689 |
ception | -2.595 |
Token | Cabinet |
Token ID | 20384 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
Franch | +2.831 |
WD | +2.470 |
wd | +2.371 |
root | +2.332 |
haar | +2.332 |
Neg logit contributions | |
azo | -2.997 |
affles | -2.915 |
bugs | -2.900 |
bug | -2.760 |
ception | -2.681 |
Token | secretary |
Token ID | 7705 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
Franch | +5.864 |
WD | +5.258 |
wd | +5.034 |
haar | +4.918 |
root | +4.916 |
Neg logit contributions | |
azo | -6.335 |
affles | -6.260 |
bugs | -6.189 |
bug | -5.820 |
ception | -5.663 |
Token | … |
Token ID | 3926 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Franch | +3.451 |
WD | +3.056 |
wd | +2.967 |
haar | +2.910 |
root | +2.900 |
Neg logit contributions | |
azo | -4.019 |
bugs | -3.892 |
affles | -3.880 |
bug | -3.699 |
ception | -3.612 |
Token | had |
Token ID | 550 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Franch | +0.378 |
WD | +0.338 |
haar | +0.327 |
wd | +0.327 |
root | +0.322 |
Neg logit contributions | |
azo | -0.322 |
affles | -0.309 |
bugs | -0.308 |
bug | -0.296 |
ception | -0.286 |
Token | any |
Token ID | 597 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Franch | +1.379 |
WD | +1.224 |
wd | +1.184 |
haar | +1.167 |
root | +1.159 |
Neg logit contributions | |
azo | -1.232 |
bugs | -1.175 |
affles | -1.174 |
bug | -1.129 |
ception | -1.092 |
Token | business |
Token ID | 1597 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Franch | +0.577 |
WD | +0.508 |
haar | +0.492 |
wd | +0.490 |
root | +0.482 |
Neg logit contributions | |
azo | -0.566 |
affles | -0.546 |
bugs | -0.544 |
bug | -0.523 |
ception | -0.510 |
Token | other |
Token ID | 584 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Franch | +0.402 |
WD | +0.356 |
haar | +0.345 |
wd | +0.342 |
root | +0.337 |
Neg logit contributions | |
azo | -0.402 |
affles | -0.389 |
bugs | -0.386 |
bug | -0.372 |
ception | -0.363 |
Token | options |
Token ID | 3689 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Franch | +1.754 |
WD | +1.544 |
haar | +1.489 |
wd | +1.483 |
root | +1.465 |
Neg logit contributions | |
azo | -1.763 |
affles | -1.708 |
bugs | -1.682 |
bug | -1.627 |
ception | -1.595 |
Token | to |
Token ID | 284 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Franch | +1.751 |
WD | +1.564 |
haar | +1.510 |
wd | +1.505 |
root | +1.474 |
Neg logit contributions | |
azo | -1.657 |
affles | -1.591 |
bugs | -1.583 |
bug | -1.521 |
ception | -1.487 |
Token | buy |
Token ID | 2822 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Franch | +0.528 |
WD | +0.469 |
haar | +0.453 |
wd | +0.451 |
root | +0.445 |
Neg logit contributions | |
azo | -0.494 |
affles | -0.480 |
bugs | -0.475 |
bug | -0.457 |
ception | -0.446 |
Token | the |
Token ID | 262 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Franch | +2.032 |
WD | +1.801 |
haar | +1.735 |
wd | +1.732 |
root | +1.713 |
Neg logit contributions | |
azo | -1.927 |
affles | -1.863 |
bugs | -1.843 |
bug | -1.783 |
ception | -1.737 |
Token | Nexus |
Token ID | 16756 |
Feature activation | -8.12e+00 |
Pos logit contributions | |
Franch | +1.595 |
WD | +1.363 |
haar | +1.302 |
wd | +1.288 |
root | +1.278 |
Neg logit contributions | |
azo | -2.340 |
affles | -2.294 |
bugs | -2.269 |
bug | -2.198 |
ception | -2.155 |
Token | 6 |
Token ID | 718 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
Franch | +6.426 |
WD | +5.746 |
root | +5.611 |
wd | +5.509 |
haar | +5.496 |
Neg logit contributions | |
azo | -5.608 |
affles | -5.480 |
bugs | -5.323 |
bug | -5.031 |
ception | -4.933 |
Token | . |
Token ID | 13 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
Franch | +3.335 |
WD | +2.976 |
haar | +2.850 |
wd | +2.841 |
root | +2.826 |
Neg logit contributions | |
azo | -3.513 |
affles | -3.372 |
bugs | -3.329 |
bug | -3.204 |
ception | -3.136 |
Token | No |
Token ID | 1400 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Franch | +0.719 |
WD | +0.637 |
haar | +0.611 |
wd | +0.610 |
root | +0.605 |
Neg logit contributions | |
azo | -0.681 |
affles | -0.654 |
bugs | -0.645 |
bug | -0.619 |
ception | -0.605 |
Token | word |
Token ID | 1573 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
azo | +0.893 |
affles | +0.865 |
bugs | +0.860 |
bug | +0.829 |
ception | +0.807 |
Neg logit contributions | |
Franch | -0.931 |
WD | -0.827 |
haar | -0.802 |
wd | -0.795 |
root | -0.782 |
Token | on |
Token ID | 319 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Franch | +0.106 |
WD | +0.093 |
haar | +0.090 |
wd | +0.089 |
root | +0.088 |
Neg logit contributions | |
azo | -0.121 |
affles | -0.117 |
bugs | -0.116 |
bug | -0.112 |
ception | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Franch | +1.843 |
WD | +1.622 |
haar | +1.571 |
wd | +1.564 |
root | +1.541 |
Neg logit contributions | |
azo | -1.677 |
affles | -1.611 |
bugs | -1.597 |
bug | -1.539 |
ception | -1.495 |
Token | fact |
Token ID | 1109 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
Franch | +1.308 |
WD | +1.152 |
haar | +1.115 |
wd | +1.099 |
root | +1.086 |
Neg logit contributions | |
azo | -1.333 |
affles | -1.292 |
bugs | -1.284 |
bug | -1.238 |
ception | -1.207 |
Token | that |
Token ID | 326 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
Franch | +1.937 |
WD | +1.727 |
haar | +1.663 |
wd | +1.653 |
root | +1.643 |
Neg logit contributions | |
azo | -1.755 |
bugs | -1.686 |
affles | -1.681 |
bug | -1.621 |
ception | -1.566 |
Token | Graham |
Token ID | 11520 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
Franch | +2.250 |
WD | +1.994 |
haar | +1.932 |
wd | +1.921 |
root | +1.885 |
Neg logit contributions | |
azo | -1.981 |
affles | -1.899 |
bugs | -1.891 |
bug | -1.824 |
ception | -1.764 |
Token | - |
Token ID | 12 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Franch | +4.189 |
WD | +3.663 |
wd | +3.547 |
haar | +3.529 |
root | +3.483 |
Neg logit contributions | |
azo | -3.974 |
affles | -3.794 |
bugs | -3.749 |
bug | -3.633 |
ception | -3.542 |
Token | Cass |
Token ID | 43529 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
Franch | +1.697 |
WD | +1.465 |
wd | +1.374 |
haar | +1.373 |
root | +1.346 |
Neg logit contributions | |
azo | -3.024 |
affles | -2.930 |
bugs | -2.904 |
bug | -2.828 |
ception | -2.775 |
Token | idy |
Token ID | 19325 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
Franch | +5.884 |
WD | +5.485 |
haar | +5.397 |
wd | +5.363 |
root | +5.132 |
Neg logit contributions | |
azo | -5.909 |
affles | -5.757 |
bugs | -5.731 |
bug | -5.444 |
ception | -5.222 |
Token | is |
Token ID | 318 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Franch | +3.432 |
WD | +3.034 |
wd | +2.945 |
haar | +2.937 |
root | +2.875 |
Neg logit contributions | |
azo | -2.892 |
affles | -2.821 |
bugs | -2.785 |
bug | -2.677 |
ception | -2.574 |
Token | new |
Token ID | 649 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Franch | +1.817 |
WD | +1.616 |
haar | +1.557 |
wd | +1.557 |
root | +1.522 |
Neg logit contributions | |
azo | -1.597 |
affles | -1.546 |
bugs | -1.539 |
bug | -1.469 |
ception | -1.430 |
Token | isn |
Token ID | 2125 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Franch | +2.554 |
WD | +2.275 |
haar | +2.228 |
wd | +2.225 |
root | +2.182 |
Neg logit contributions | |
azo | -2.334 |
affles | -2.255 |
bugs | -2.216 |
bug | -2.129 |
ception | -2.083 |
Token | � |
Token ID | 447 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
azo | +1.231 |
affles | +1.199 |
bugs | +1.197 |
bug | +1.164 |
ception | +1.137 |
Neg logit contributions | |
Franch | -0.859 |
WD | -0.734 |
haar | -0.712 |
wd | -0.698 |
root | -0.679 |
Token | Republicans |
Token ID | 4734 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Franch | +0.416 |
WD | +0.365 |
haar | +0.353 |
wd | +0.349 |
root | +0.344 |
Neg logit contributions | |
azo | -0.451 |
affles | -0.437 |
bugs | -0.434 |
bug | -0.420 |
ception | -0.410 |
Token | was |
Token ID | 373 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Franch | +2.369 |
WD | +2.108 |
wd | +2.048 |
haar | +2.046 |
root | +2.014 |
Neg logit contributions | |
azo | -2.147 |
affles | -2.082 |
bugs | -2.041 |
bug | -1.961 |
ception | -1.905 |
Token | revealed |
Token ID | 4602 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
azo | +0.934 |
affles | +0.902 |
bugs | +0.895 |
bug | +0.861 |
ception | +0.838 |
Neg logit contributions | |
Franch | -1.120 |
WD | -1.005 |
haar | -0.979 |
wd | -0.970 |
root | -0.954 |
Token | in |
Token ID | 287 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Franch | +0.376 |
WD | +0.335 |
haar | +0.325 |
wd | +0.323 |
root | +0.318 |
Neg logit contributions | |
azo | -0.346 |
affles | -0.335 |
bugs | -0.331 |
bug | -0.319 |
ception | -0.311 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Franch | +1.448 |
WD | +1.278 |
haar | +1.241 |
wd | +1.229 |
root | +1.214 |
Neg logit contributions | |
azo | -1.383 |
affles | -1.338 |
bugs | -1.331 |
bug | -1.281 |
ception | -1.245 |
Token | mon |
Token ID | 937 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
Franch | +1.079 |
WD | +0.944 |
haar | +0.918 |
wd | +0.904 |
root | +0.899 |
Neg logit contributions | |
azo | -1.057 |
affles | -1.030 |
bugs | -1.024 |
bug | -0.982 |
ception | -0.960 |
Token | ologue |
Token ID | 39795 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
Franch | +5.451 |
WD | +4.673 |
wd | +4.649 |
haar | +4.594 |
root | +4.570 |
Neg logit contributions | |
azo | -5.985 |
bugs | -5.890 |
affles | -5.890 |
bug | -5.576 |
UTC | -5.429 |
Token | given |
Token ID | 1813 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Franch | +0.795 |
WD | +0.703 |
haar | +0.680 |
wd | +0.675 |
root | +0.670 |
Neg logit contributions | |
azo | -0.715 |
affles | -0.692 |
bugs | -0.685 |
bug | -0.661 |
ception | -0.640 |
Token | by |
Token ID | 416 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
Franch | +1.744 |
WD | +1.559 |
haar | +1.498 |
wd | +1.496 |
root | +1.476 |
Neg logit contributions | |
azo | -1.596 |
affles | -1.542 |
bugs | -1.527 |
bug | -1.473 |
ception | -1.426 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
azo | +0.064 |
affles | +0.062 |
bugs | +0.062 |
bug | +0.059 |
ception | +0.058 |
Neg logit contributions | |
Franch | -0.060 |
WD | -0.053 |
haar | -0.051 |
wd | -0.051 |
root | -0.050 |
Token | Kimmel |
Token ID | 46552 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
azo | +0.023 |
affles | +0.022 |
bugs | +0.022 |
bug | +0.021 |
ception | +0.020 |
Neg logit contributions | |
Franch | -0.030 |
WD | -0.027 |
haar | -0.026 |
wd | -0.026 |
root | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Franch | +2.152 |
WD | +1.897 |
haar | +1.822 |
wd | +1.798 |
root | +1.778 |
Neg logit contributions | |
azo | -2.343 |
affles | -2.261 |
bugs | -2.229 |
bug | -2.140 |
ception | -2.101 |
Token | we |
Token ID | 356 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
azo | +0.309 |
affles | +0.298 |
bugs | +0.296 |
bug | +0.284 |
ception | +0.276 |
Neg logit contributions | |
Franch | -0.359 |
WD | -0.320 |
haar | -0.311 |
wd | -0.309 |
root | -0.305 |
Token | were |
Token ID | 547 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
azo | +0.475 |
affles | +0.458 |
bugs | +0.456 |
bug | +0.439 |
ception | +0.425 |
Neg logit contributions | |
Franch | -0.568 |
WD | -0.509 |
haar | -0.494 |
wd | -0.491 |
root | -0.484 |
Token | talking |
Token ID | 3375 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
Franch | +1.403 |
WD | +1.255 |
haar | +1.219 |
wd | +1.212 |
root | +1.192 |
Neg logit contributions | |
azo | -1.252 |
affles | -1.215 |
bugs | -1.195 |
bug | -1.146 |
ception | -1.118 |
Token | about |
Token ID | 546 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Franch | +2.323 |
WD | +2.078 |
haar | +2.001 |
wd | +1.972 |
root | +1.960 |
Neg logit contributions | |
azo | -1.990 |
affles | -1.910 |
bugs | -1.886 |
bug | -1.801 |
ception | -1.765 |
Token | Priest |
Token ID | 20876 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
Franch | +1.831 |
WD | +1.626 |
haar | +1.585 |
wd | +1.566 |
root | +1.547 |
Neg logit contributions | |
azo | -1.575 |
affles | -1.524 |
bugs | -1.506 |
bug | -1.450 |
ception | -1.410 |
Token | and |
Token ID | 290 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Franch | +5.624 |
WD | +5.100 |
root | +4.916 |
wd | +4.908 |
haar | +4.866 |
Neg logit contributions | |
azo | -5.754 |
affles | -5.451 |
bugs | -5.374 |
bug | -5.159 |
ception | -5.125 |
Token | upcoming |
Token ID | 7865 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Franch | +0.840 |
WD | +0.750 |
haar | +0.728 |
wd | +0.721 |
root | +0.712 |
Neg logit contributions | |
azo | -0.731 |
affles | -0.708 |
bugs | -0.701 |
bug | -0.673 |
ception | -0.655 |
Token | sets |
Token ID | 5621 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Franch | +0.444 |
WD | +0.395 |
haar | +0.382 |
wd | +0.379 |
root | +0.374 |
Neg logit contributions | |
azo | -0.424 |
affles | -0.411 |
bugs | -0.408 |
bug | -0.392 |
ception | -0.383 |
Token | for |
Token ID | 329 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
azo | +2.186 |
affles | +2.136 |
bugs | +2.114 |
bug | +2.049 |
ception | +1.985 |
Neg logit contributions | |
Franch | -2.409 |
WD | -2.134 |
haar | -2.082 |
wd | -2.070 |
root | -2.034 |
Token | Priest |
Token ID | 20876 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
azo | +1.359 |
affles | +1.318 |
bugs | +1.310 |
bug | +1.257 |
ception | +1.226 |
Neg logit contributions | |
Franch | -1.644 |
WD | -1.473 |
haar | -1.439 |
wd | -1.429 |
root | -1.405 |
Token | one |
Token ID | 530 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Franch | +2.175 |
WD | +1.918 |
haar | +1.871 |
wd | +1.845 |
root | +1.841 |
Neg logit contributions | |
azo | -2.028 |
bugs | -1.968 |
affles | -1.961 |
bug | -1.889 |
ception | -1.836 |
Token | point |
Token ID | 966 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
azo | +1.602 |
affles | +1.555 |
bugs | +1.544 |
bug | +1.499 |
ception | +1.470 |
Neg logit contributions | |
Franch | -1.265 |
WD | -1.102 |
haar | -1.065 |
wd | -1.053 |
root | -1.029 |
Token | thousands |
Token ID | 4138 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
azo | +0.659 |
affles | +0.638 |
bugs | +0.635 |
bug | +0.611 |
ception | +0.595 |
Neg logit contributions | |
Franch | -0.702 |
WD | -0.625 |
haar | -0.608 |
wd | -0.601 |
root | -0.592 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
azo | +0.140 |
affles | +0.135 |
bugs | +0.134 |
bug | +0.129 |
ception | +0.125 |
Neg logit contributions | |
Franch | -0.166 |
WD | -0.148 |
haar | -0.144 |
wd | -0.143 |
root | -0.141 |
Token | protesters |
Token ID | 9584 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Franch | +0.898 |
WD | +0.796 |
haar | +0.767 |
wd | +0.763 |
root | +0.753 |
Neg logit contributions | |
azo | -0.893 |
affles | -0.867 |
bugs | -0.858 |
bug | -0.828 |
ception | -0.808 |
Token | chanting |
Token ID | 31138 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
Franch | +1.623 |
WD | +1.428 |
wd | +1.380 |
haar | +1.376 |
root | +1.365 |
Neg logit contributions | |
azo | -1.573 |
affles | -1.544 |
bugs | -1.516 |
bug | -1.458 |
ception | -1.426 |
Token | � |
Token ID | 564 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Franch | +5.714 |
WD | +4.920 |
root | +4.776 |
wd | +4.770 |
haar | +4.752 |
Neg logit contributions | |
azo | -5.639 |
affles | -5.580 |
bugs | -5.461 |
bug | -5.247 |
ception | -5.147 |
Token | � |
Token ID | 250 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Franch | +0.254 |
WD | +0.230 |
haar | +0.224 |
wd | +0.223 |
root | +0.220 |
Neg logit contributions | |
azo | -0.186 |
affles | -0.179 |
bugs | -0.177 |
bug | -0.170 |
ception | -0.164 |
Token | death |
Token ID | 22595 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Franch | +0.697 |
WD | +0.628 |
haar | +0.609 |
wd | +0.606 |
root | +0.599 |
Neg logit contributions | |
azo | -0.622 |
affles | -0.605 |
bugs | -0.598 |
bug | -0.574 |
ception | -0.558 |
Token | to |
Token ID | 284 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Franch | +0.209 |
WD | +0.188 |
haar | +0.183 |
wd | +0.182 |
root | +0.180 |
Neg logit contributions | |
azo | -0.153 |
affles | -0.147 |
bugs | -0.146 |
bug | -0.139 |
ception | -0.136 |
Token | the |
Token ID | 262 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Franch | +1.814 |
WD | +1.634 |
haar | +1.597 |
root | +1.585 |
wd | +1.578 |
Neg logit contributions | |
azo | -1.101 |
affles | -1.071 |
bugs | -1.052 |
bug | -1.004 |
ception | -0.971 |
Token | packet |
Token ID | 19638 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
azo | +2.146 |
affles | +2.076 |
bugs | +2.066 |
bug | +1.983 |
ception | +1.924 |
Neg logit contributions | |
Franch | -2.486 |
WD | -2.219 |
haar | -2.177 |
wd | -2.148 |
root | -2.115 |
Token | loss |
Token ID | 2994 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
azo | +2.598 |
affles | +2.520 |
bugs | +2.510 |
bug | +2.427 |
ception | +2.372 |
Neg logit contributions | |
Franch | -2.355 |
WD | -2.066 |
haar | -2.003 |
wd | -1.978 |
root | -1.944 |
Token | and |
Token ID | 290 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
azo | +0.117 |
affles | +0.113 |
bugs | +0.112 |
bug | +0.108 |
ception | +0.105 |
Neg logit contributions | |
Franch | -0.128 |
WD | -0.114 |
haar | -0.110 |
wd | -0.110 |
root | -0.108 |
Token | congestion |
Token ID | 28014 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Franch | +0.445 |
WD | +0.397 |
haar | +0.383 |
wd | +0.380 |
root | +0.374 |
Neg logit contributions | |
azo | -0.425 |
affles | -0.414 |
bugs | -0.407 |
bug | -0.392 |
ception | -0.383 |
Token | were |
Token ID | 547 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Franch | +2.310 |
WD | +2.026 |
haar | +1.954 |
wd | +1.954 |
root | +1.927 |
Neg logit contributions | |
azo | -2.480 |
affles | -2.392 |
bugs | -2.335 |
bug | -2.244 |
ception | -2.210 |
Token | synonymous |
Token ID | 33271 |
Feature activation | -7.64e+00 |
Pos logit contributions | |
Franch | +1.312 |
WD | +1.173 |
haar | +1.126 |
wd | +1.123 |
root | +1.105 |
Neg logit contributions | |
azo | -1.274 |
affles | -1.234 |
bugs | -1.216 |
bug | -1.173 |
ception | -1.147 |
Token | due |
Token ID | 2233 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Franch | +5.277 |
WD | +4.654 |
wd | +4.384 |
haar | +4.337 |
root | +4.331 |
Neg logit contributions | |
azo | -6.149 |
affles | -5.963 |
bugs | -5.774 |
bug | -5.618 |
ception | -5.603 |
Token | to |
Token ID | 284 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Franch | +1.879 |
WD | +1.712 |
wd | +1.654 |
haar | +1.647 |
root | +1.626 |
Neg logit contributions | |
azo | -1.432 |
affles | -1.389 |
bugs | -1.376 |
bug | -1.322 |
ception | -1.280 |
Token | technology |
Token ID | 3037 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Franch | +1.496 |
WD | +1.332 |
haar | +1.282 |
wd | +1.271 |
root | +1.253 |
Neg logit contributions | |
azo | -1.437 |
affles | -1.391 |
bugs | -1.375 |
bug | -1.324 |
ception | -1.298 |
Token | limitations |
Token ID | 11247 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
azo | +1.723 |
bugs | +1.671 |
affles | +1.670 |
bug | +1.608 |
ception | +1.555 |
Neg logit contributions | |
Franch | -1.921 |
WD | -1.706 |
haar | -1.667 |
wd | -1.647 |
root | -1.626 |
Token | . |
Token ID | 13 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
azo | +1.328 |
affles | +1.284 |
bugs | +1.281 |
bug | +1.236 |
ception | +1.197 |
Neg logit contributions | |
Franch | -1.409 |
WD | -1.247 |
haar | -1.218 |
wd | -1.201 |
root | -1.185 |
Token | ) |
Token ID | 8 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
azo | +0.711 |
affles | +0.686 |
bugs | +0.681 |
bug | +0.653 |
ception | +0.633 |
Neg logit contributions | |
Franch | -0.951 |
WD | -0.855 |
haar | -0.833 |
wd | -0.826 |
root | -0.814 |
Token |
|
Token ID | 198 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
Franch | +1.253 |
WD | +1.109 |
haar | +1.082 |
wd | +1.069 |
root | +1.057 |
Neg logit contributions | |
azo | -1.098 |
affles | -1.063 |
bugs | -1.056 |
bug | -1.013 |
ception | -0.983 |
Token |
|
Token ID | 198 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
Franch | +0.582 |
WD | +0.522 |
wd | +0.503 |
haar | +0.502 |
root | +0.499 |
Neg logit contributions | |
azo | -0.521 |
affles | -0.503 |
bugs | -0.495 |
bug | -0.474 |
ception | -0.463 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Franch | +0.624 |
WD | +0.575 |
haar | +0.555 |
wd | +0.553 |
root | +0.551 |
Neg logit contributions | |
azo | -0.398 |
affles | -0.384 |
bugs | -0.377 |
bug | -0.357 |
ception | -0.345 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Franch | +0.222 |
WD | +0.196 |
haar | +0.188 |
wd | +0.187 |
root | +0.185 |
Neg logit contributions | |
azo | -0.245 |
affles | -0.237 |
bugs | -0.235 |
bug | -0.226 |
ception | -0.221 |
Token | Finn |
Token ID | 15368 |
Feature activation | -7.55e+00 |
Pos logit contributions | |
Franch | +1.651 |
WD | +1.425 |
haar | +1.388 |
root | +1.373 |
wd | +1.369 |
Neg logit contributions | |
azo | -1.626 |
affles | -1.580 |
bugs | -1.564 |
bug | -1.492 |
ception | -1.455 |
Token | Russell |
Token ID | 11563 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
Franch | +4.334 |
WD | +3.473 |
root | +3.435 |
wd | +3.389 |
haar | +3.239 |
Neg logit contributions | |
azo | -7.108 |
affles | -6.930 |
bugs | -6.851 |
haps | -6.622 |
bug | -6.546 |
Token | ( |
Token ID | 357 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
Franch | +5.105 |
WD | +4.438 |
haar | +4.356 |
root | +4.348 |
wd | +4.307 |
Neg logit contributions | |
azo | -5.743 |
bugs | -5.506 |
affles | -5.477 |
bug | -5.285 |
haps | -5.188 |
Token | 58 |
Token ID | 3365 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Franch | +3.305 |
WD | +3.089 |
wd | +2.937 |
root | +2.928 |
haar | +2.871 |
Neg logit contributions | |
azo | -3.289 |
affles | -3.142 |
bugs | -3.055 |
bug | -2.917 |
haps | -2.894 |
Token | ) |
Token ID | 8 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Franch | +1.597 |
WD | +1.452 |
wd | +1.400 |
root | +1.393 |
haar | +1.382 |
Neg logit contributions | |
azo | -1.389 |
affles | -1.335 |
bugs | -1.309 |
bug | -1.246 |
ception | -1.223 |
Token | ( |
Token ID | 357 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Franch | +1.116 |
WD | +0.993 |
wd | +0.957 |
haar | +0.956 |
root | +0.946 |
Neg logit contributions | |
azo | -1.034 |
affles | -0.994 |
bugs | -0.983 |
bug | -0.942 |
ception | -0.920 |
Token | ya |
Token ID | 3972 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Franch | +0.081 |
WD | +0.072 |
wd | +0.069 |
haar | +0.069 |
root | +0.067 |
Neg logit contributions | |
azo | -0.088 |
affles | -0.086 |
bugs | -0.085 |
bug | -0.082 |
ception | -0.080 |
Token | Sabha |
Token ID | 41941 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Franch | +1.697 |
WD | +1.422 |
haar | +1.342 |
wd | +1.342 |
root | +1.315 |
Neg logit contributions | |
azo | -2.845 |
affles | -2.770 |
bugs | -2.762 |
bug | -2.664 |
ception | -2.628 |
Token | member |
Token ID | 2888 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Franch | +2.280 |
WD | +1.990 |
wd | +1.895 |
haar | +1.892 |
root | +1.862 |
Neg logit contributions | |
azo | -2.654 |
affles | -2.562 |
bugs | -2.527 |
bug | -2.428 |
ception | -2.373 |
Token | from |
Token ID | 422 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Franch | +1.598 |
WD | +1.413 |
haar | +1.352 |
wd | +1.343 |
root | +1.332 |
Neg logit contributions | |
azo | -1.564 |
affles | -1.511 |
bugs | -1.505 |
bug | -1.436 |
ception | -1.409 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Franch | +0.151 |
WD | +0.134 |
haar | +0.130 |
wd | +0.128 |
root | +0.127 |
Neg logit contributions | |
azo | -0.146 |
affles | -0.142 |
bugs | -0.141 |
bug | -0.136 |
ception | -0.132 |
Token | Shank |
Token ID | 41595 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
Franch | +0.341 |
WD | +0.304 |
haar | +0.294 |
wd | +0.292 |
root | +0.287 |
Neg logit contributions | |
azo | -0.313 |
affles | -0.302 |
bugs | -0.300 |
bug | -0.288 |
ception | -0.281 |
Token | ar |
Token ID | 283 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
Franch | +4.684 |
WD | +4.111 |
haar | +4.081 |
root | +4.051 |
wd | +3.976 |
Neg logit contributions | |
azo | -6.465 |
bugs | -6.204 |
affles | -6.193 |
bug | -5.937 |
ception | -5.796 |
Token | Bh |
Token ID | 16581 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Franch | +0.699 |
WD | +0.623 |
haar | +0.607 |
wd | +0.599 |
root | +0.596 |
Neg logit contributions | |
azo | -0.619 |
affles | -0.600 |
bugs | -0.596 |
bug | -0.571 |
ception | -0.559 |
Token | ai |
Token ID | 1872 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Franch | +0.403 |
WD | +0.363 |
haar | +0.358 |
root | +0.355 |
wd | +0.353 |
Neg logit contributions | |
azo | -0.293 |
bugs | -0.284 |
affles | -0.284 |
bug | -0.269 |
ception | -0.264 |
Token | Veg |
Token ID | 8427 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Franch | +0.405 |
WD | +0.358 |
haar | +0.349 |
wd | +0.345 |
root | +0.339 |
Neg logit contributions | |
azo | -0.419 |
affles | -0.407 |
bugs | -0.404 |
bug | -0.389 |
ception | -0.381 |
Token | ad |
Token ID | 324 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
azo | +1.332 |
affles | +1.292 |
bugs | +1.284 |
bug | +1.237 |
ception | +1.201 |
Neg logit contributions | |
Franch | -1.411 |
WD | -1.255 |
haar | -1.215 |
wd | -1.207 |
root | -1.185 |
Token | and |
Token ID | 290 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
Franch | +2.830 |
WD | +2.500 |
haar | +2.412 |
wd | +2.381 |
root | +2.365 |
Neg logit contributions | |
azo | -2.922 |
affles | -2.852 |
bugs | -2.811 |
bug | -2.691 |
ception | -2.632 |
Token | non |
Token ID | 1729 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Franch | +0.007 |
WD | +0.006 |
haar | +0.006 |
wd | +0.006 |
root | +0.006 |
Neg logit contributions | |
azo | -0.007 |
affles | -0.007 |
bugs | -0.007 |
bug | -0.006 |
ception | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
azo | +0.246 |
affles | +0.238 |
bugs | +0.236 |
bug | +0.227 |
ception | +0.220 |
Neg logit contributions | |
Franch | -0.307 |
WD | -0.275 |
haar | -0.268 |
wd | -0.266 |
root | -0.262 |
Token | character |
Token ID | 22769 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Franch | +1.134 |
WD | +1.018 |
haar | +0.982 |
wd | +0.975 |
root | +0.965 |
Neg logit contributions | |
azo | -1.109 |
affles | -1.074 |
bugs | -1.058 |
bug | -1.015 |
ception | -0.996 |
Token | war |
Token ID | 1175 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Franch | +2.214 |
WD | +1.955 |
haar | +1.877 |
wd | +1.867 |
root | +1.841 |
Neg logit contributions | |
azo | -2.436 |
affles | -2.377 |
bugs | -2.345 |
bug | -2.253 |
ception | -2.196 |
Token | j |
Token ID | 73 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
azo | +1.171 |
affles | +1.142 |
bugs | +1.138 |
bug | +1.107 |
ception | +1.084 |
Neg logit contributions | |
Franch | -0.692 |
WD | -0.585 |
haar | -0.559 |
wd | -0.552 |
root | -0.539 |
Token | acks |
Token ID | 4595 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Franch | +5.558 |
WD | +5.081 |
wd | +5.002 |
older | +4.961 |
haar | +4.847 |
Neg logit contributions | |
azo | -5.439 |
bugs | -5.182 |
affles | -5.161 |
bug | -4.956 |
ception | -4.891 |
Token | as |
Token ID | 355 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Franch | +0.137 |
WD | +0.122 |
haar | +0.118 |
wd | +0.118 |
root | +0.116 |
Neg logit contributions | |
azo | -0.123 |
affles | -0.119 |
bugs | -0.118 |
bug | -0.114 |
ception | -0.111 |
Token | well |
Token ID | 880 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
Franch | +0.079 |
WD | +0.070 |
haar | +0.068 |
wd | +0.068 |
root | +0.066 |
Neg logit contributions | |
azo | -0.075 |
affles | -0.072 |
bugs | -0.072 |
bug | -0.069 |
ception | -0.067 |
Token | as |
Token ID | 355 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
azo | +2.644 |
affles | +2.541 |
bugs | +2.536 |
bug | +2.454 |
ception | +2.353 |
Neg logit contributions | |
Franch | -3.580 |
WD | -3.223 |
haar | -3.145 |
wd | -3.128 |
root | -3.095 |
Token | all |
Token ID | 477 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
azo | +1.586 |
bugs | +1.529 |
affles | +1.525 |
bug | +1.474 |
ception | +1.424 |
Neg logit contributions | |
Franch | -1.796 |
WD | -1.610 |
haar | -1.569 |
wd | -1.558 |
root | -1.534 |
Token | struct |
Token ID | 2878 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Franch | +1.831 |
WD | +1.641 |
haar | +1.593 |
root | +1.583 |
wd | +1.583 |
Neg logit contributions | |
azo | -2.140 |
affles | -2.126 |
bugs | -2.058 |
bug | -1.986 |
ception | -1.926 |
Token | Guard |
Token ID | 4932 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
Franch | +2.186 |
WD | +1.978 |
wd | +1.920 |
haar | +1.915 |
root | +1.912 |
Neg logit contributions | |
azo | -1.626 |
affles | -1.621 |
bugs | -1.576 |
bug | -1.494 |
ception | -1.445 |
Token | { |
Token ID | 1391 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Franch | +2.437 |
WD | +2.211 |
wd | +2.114 |
haar | +2.106 |
root | +2.093 |
Neg logit contributions | |
azo | -2.635 |
affles | -2.560 |
bugs | -2.517 |
bug | -2.410 |
haps | -2.336 |
Token | ... |
Token ID | 2644 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Franch | +1.756 |
WD | +1.583 |
wd | +1.519 |
haar | +1.515 |
root | +1.508 |
Neg logit contributions | |
azo | -1.889 |
affles | -1.863 |
bugs | -1.816 |
bug | -1.731 |
ception | -1.685 |
Token | } |
Token ID | 1782 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
Franch | +3.111 |
WD | +2.850 |
wd | +2.737 |
root | +2.722 |
haar | +2.717 |
Neg logit contributions | |
azo | -3.314 |
affles | -3.275 |
bugs | -3.170 |
bug | -3.035 |
haps | -2.952 |
Token | pub |
Token ID | 2240 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
Franch | +3.655 |
WD | +3.310 |
wd | +3.186 |
haar | +3.155 |
root | +3.147 |
Neg logit contributions | |
azo | -3.768 |
affles | -3.739 |
bugs | -3.612 |
bug | -3.423 |
haps | -3.376 |
Token | fn |
Token ID | 24714 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Franch | +5.064 |
WD | +4.636 |
root | +4.524 |
wd | +4.511 |
haar | +4.461 |
Neg logit contributions | |
affles | -5.909 |
azo | -5.725 |
bugs | -5.515 |
bug | -5.267 |
haps | -5.182 |
Token | pin |
Token ID | 6757 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Franch | +4.487 |
WD | +4.072 |
root | +4.028 |
wd | +4.001 |
haar | +3.923 |
Neg logit contributions | |
affles | -3.893 |
azo | -3.885 |
bugs | -3.784 |
bug | -3.584 |
ception | -3.465 |
Token | () |
Token ID | 7499 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
azo | +0.780 |
bugs | +0.749 |
affles | +0.749 |
bug | +0.721 |
ception | +0.698 |
Neg logit contributions | |
Franch | -0.975 |
WD | -0.867 |
haar | -0.848 |
wd | -0.834 |
root | -0.822 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Franch | +1.720 |
WD | +1.539 |
wd | +1.494 |
root | +1.465 |
haar | +1.464 |
Neg logit contributions | |
azo | -1.834 |
affles | -1.803 |
bugs | -1.753 |
bug | -1.670 |
ception | -1.640 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Franch | +2.264 |
WD | +1.998 |
haar | +1.944 |
root | +1.923 |
wd | +1.919 |
Neg logit contributions | |
affles | -1.999 |
azo | -1.995 |
bugs | -1.931 |
bug | -1.833 |
ception | -1.789 |
Token | forfeiture |
Token ID | 32075 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
azo | +0.514 |
affles | +0.498 |
bugs | +0.495 |
bug | +0.476 |
ception | +0.463 |
Neg logit contributions | |
Franch | -0.559 |
WD | -0.497 |
haar | -0.483 |
wd | -0.479 |
root | -0.471 |
Token | reporting |
Token ID | 6447 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Franch | +1.273 |
WD | +1.107 |
wd | +1.073 |
haar | +1.068 |
root | +1.054 |
Neg logit contributions | |
azo | -1.366 |
affles | -1.315 |
bugs | -1.296 |
bug | -1.250 |
ception | -1.227 |
Token | requirements |
Token ID | 5359 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
azo | +1.595 |
bugs | +1.554 |
affles | +1.553 |
bug | +1.494 |
ception | +1.440 |
Neg logit contributions | |
Franch | -1.862 |
WD | -1.664 |
haar | -1.623 |
wd | -1.604 |
root | -1.581 |
Token | for |
Token ID | 329 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
azo | +0.934 |
affles | +0.903 |
bugs | +0.899 |
bug | +0.865 |
ception | +0.840 |
Neg logit contributions | |
Franch | -1.074 |
WD | -0.959 |
haar | -0.932 |
wd | -0.924 |
root | -0.911 |
Token | law |
Token ID | 1099 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
azo | +0.767 |
affles | +0.743 |
bugs | +0.738 |
bug | +0.712 |
ception | +0.694 |
Neg logit contributions | |
Franch | -0.762 |
WD | -0.675 |
haar | -0.654 |
wd | -0.649 |
root | -0.638 |
Token | enforcement |
Token ID | 5394 |
Feature activation | -7.38e+00 |
Pos logit contributions | |
Franch | +1.765 |
WD | +1.562 |
haar | +1.517 |
wd | +1.514 |
root | +1.488 |
Neg logit contributions | |
azo | -1.832 |
affles | -1.778 |
bugs | -1.752 |
bug | -1.694 |
ception | -1.662 |
Token | agencies |
Token ID | 5942 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Franch | +5.074 |
WD | +4.284 |
haar | +4.089 |
wd | +4.086 |
root | +3.985 |
Neg logit contributions | |
azo | -6.204 |
affles | -6.031 |
bugs | -5.844 |
ception | -5.678 |
bug | -5.670 |
Token | , |
Token ID | 11 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
Franch | +1.122 |
WD | +0.988 |
wd | +0.951 |
haar | +0.949 |
root | +0.930 |
Neg logit contributions | |
azo | -1.145 |
affles | -1.110 |
bugs | -1.096 |
bug | -1.054 |
ception | -1.035 |
Token | raise |
Token ID | 5298 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
Franch | +0.512 |
WD | +0.454 |
haar | +0.438 |
wd | +0.438 |
root | +0.431 |
Neg logit contributions | |
azo | -0.477 |
affles | -0.463 |
bugs | -0.458 |
bug | -0.440 |
ception | -0.431 |
Token | evident |
Token ID | 10678 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
azo | +2.993 |
affles | +2.904 |
bugs | +2.881 |
bug | +2.785 |
ception | +2.715 |
Neg logit contributions | |
Franch | -2.988 |
WD | -2.663 |
haar | -2.574 |
wd | -2.559 |
root | -2.515 |
Token | iary |
Token ID | 8042 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
azo | +0.649 |
affles | +0.624 |
bugs | +0.618 |
bug | +0.594 |
ception | +0.580 |
Neg logit contributions | |
Franch | -0.873 |
WD | -0.786 |
haar | -0.764 |
wd | -0.756 |
root | -0.741 |
Token | be |
Token ID | 307 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Franch | +1.020 |
WD | +0.911 |
haar | +0.887 |
wd | +0.880 |
root | +0.871 |
Neg logit contributions | |
azo | -0.811 |
affles | -0.783 |
bugs | -0.778 |
bug | -0.745 |
ception | -0.725 |
Token | no |
Token ID | 645 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
azo | +0.179 |
affles | +0.174 |
bugs | +0.173 |
bug | +0.166 |
ception | +0.162 |
Neg logit contributions | |
Franch | -0.194 |
WD | -0.174 |
haar | -0.169 |
wd | -0.167 |
root | -0.164 |
Token | repeat |
Token ID | 9585 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
azo | +1.154 |
affles | +1.122 |
bugs | +1.110 |
bug | +1.074 |
ception | +1.049 |
Neg logit contributions | |
Franch | -1.082 |
WD | -0.965 |
haar | -0.935 |
wd | -0.926 |
root | -0.905 |
Token | of |
Token ID | 286 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Franch | +1.663 |
WD | +1.482 |
haar | +1.433 |
wd | +1.426 |
root | +1.407 |
Neg logit contributions | |
azo | -1.458 |
affles | -1.408 |
bugs | -1.400 |
bug | -1.344 |
ception | -1.302 |
Token | the |
Token ID | 262 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Franch | +2.637 |
WD | +2.299 |
wd | +2.198 |
haar | +2.197 |
root | +2.185 |
Neg logit contributions | |
azo | -2.344 |
bugs | -2.269 |
affles | -2.260 |
bug | -2.181 |
ception | -2.128 |
Token | chaos |
Token ID | 11918 |
Feature activation | -7.37e+00 |
Pos logit contributions | |
Franch | +1.417 |
WD | +1.239 |
haar | +1.193 |
wd | +1.182 |
root | +1.172 |
Neg logit contributions | |
azo | -1.417 |
affles | -1.376 |
bugs | -1.368 |
bug | -1.321 |
ception | -1.288 |
Token | at |
Token ID | 379 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
Franch | +5.690 |
WD | +4.756 |
root | +4.592 |
wd | +4.437 |
haar | +4.429 |
Neg logit contributions | |
azo | -5.512 |
affles | -5.306 |
bugs | -5.240 |
bug | -5.027 |
haps | -5.009 |
Token | Pompe |
Token ID | 36103 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
Franch | +2.794 |
WD | +2.442 |
haar | +2.319 |
wd | +2.318 |
root | +2.309 |
Neg logit contributions | |
azo | -2.573 |
bugs | -2.505 |
affles | -2.499 |
bug | -2.406 |
ception | -2.363 |
Token | y |
Token ID | 88 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Franch | +2.506 |
WD | +2.224 |
wd | +2.120 |
haar | +2.120 |
root | +2.112 |
Neg logit contributions | |
affles | -2.681 |
azo | -2.670 |
bugs | -2.652 |
bug | -2.512 |
ception | -2.484 |
Token | , |
Token ID | 11 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Franch | +1.526 |
WD | +1.342 |
haar | +1.291 |
wd | +1.286 |
root | +1.280 |
Neg logit contributions | |
azo | -1.360 |
affles | -1.318 |
bugs | -1.307 |
bug | -1.256 |
ception | -1.224 |
Token | but |
Token ID | 475 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
azo | +0.185 |
affles | +0.179 |
bugs | +0.178 |
bug | +0.171 |
ception | +0.166 |
Neg logit contributions | |
Franch | -0.217 |
WD | -0.193 |
haar | -0.188 |
wd | -0.186 |
root | -0.184 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
azo | +0.247 |
affles | +0.238 |
bugs | +0.236 |
bug | +0.226 |
ception | +0.220 |
Neg logit contributions | |
Franch | -0.291 |
WD | -0.261 |
haar | -0.252 |
wd | -0.251 |
root | -0.248 |
Token | � |
Token ID | 447 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
azo | +0.090 |
affles | +0.088 |
bugs | +0.087 |
bug | +0.084 |
ception | +0.082 |
Neg logit contributions | |
Franch | -0.094 |
WD | -0.084 |
haar | -0.081 |
wd | -0.080 |
root | -0.079 |
Token | � |
Token ID | 250 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
azo | +0.060 |
affles | +0.058 |
bugs | +0.057 |
bug | +0.055 |
ception | +0.053 |
Neg logit contributions | |
Franch | -0.086 |
WD | -0.078 |
haar | -0.076 |
wd | -0.075 |
root | -0.074 |
Token | Even |
Token ID | 6104 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
Franch | +1.328 |
WD | +1.198 |
haar | +1.148 |
wd | +1.147 |
root | +1.135 |
Neg logit contributions | |
azo | -1.223 |
affles | -1.181 |
bugs | -1.166 |
bug | -1.119 |
ception | -1.090 |
Token | the |
Token ID | 262 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Franch | +3.956 |
WD | +3.508 |
haar | +3.405 |
wd | +3.367 |
root | +3.345 |
Neg logit contributions | |
azo | -3.531 |
affles | -3.419 |
bugs | -3.410 |
bug | -3.278 |
ception | -3.184 |
Token | Mun |
Token ID | 12107 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
Franch | +0.296 |
WD | +0.262 |
haar | +0.253 |
wd | +0.251 |
root | +0.247 |
Neg logit contributions | |
azo | -0.293 |
affles | -0.284 |
bugs | -0.283 |
bug | -0.272 |
ception | -0.265 |
Token | ak |
Token ID | 461 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Franch | +4.939 |
WD | +4.195 |
haar | +4.130 |
wd | +4.116 |
root | +4.017 |
Neg logit contributions | |
azo | -6.125 |
bugs | -5.988 |
affles | -5.910 |
bug | -5.666 |
ception | -5.569 |
Token | Canal |
Token ID | 31314 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Franch | +1.429 |
WD | +1.271 |
haar | +1.230 |
wd | +1.222 |
root | +1.205 |
Neg logit contributions | |
azo | -1.414 |
affles | -1.375 |
bugs | -1.373 |
bug | -1.315 |
ception | -1.277 |
Token | supplying |
Token ID | 28099 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Franch | +0.817 |
WD | +0.729 |
haar | +0.705 |
wd | +0.701 |
root | +0.692 |
Neg logit contributions | |
azo | -0.722 |
affles | -0.700 |
bugs | -0.693 |
bug | -0.666 |
ception | -0.649 |
Token | water |
Token ID | 1660 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
azo | +1.554 |
affles | +1.509 |
bugs | +1.496 |
bug | +1.444 |
ception | +1.406 |
Neg logit contributions | |
Franch | -1.657 |
WD | -1.481 |
haar | -1.439 |
wd | -1.431 |
root | -1.406 |
Token | to |
Token ID | 284 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
azo | +0.576 |
affles | +0.556 |
bugs | +0.552 |
bug | +0.529 |
ception | +0.512 |
Neg logit contributions | |
Franch | -0.788 |
WD | -0.710 |
haar | -0.692 |
wd | -0.687 |
root | -0.677 |
Token | uni |
Token ID | 35657 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Franch | +0.801 |
WD | +0.708 |
haar | +0.693 |
wd | +0.688 |
root | +0.675 |
Neg logit contributions | |
azo | -0.776 |
affles | -0.756 |
bugs | -0.756 |
bug | -0.724 |
ception | -0.707 |
Token | a |
Token ID | 257 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Franch | +0.942 |
WD | +0.840 |
haar | +0.814 |
wd | +0.813 |
root | +0.798 |
Neg logit contributions | |
azo | -0.883 |
affles | -0.862 |
bugs | -0.851 |
bug | -0.819 |
ception | -0.798 |
Token | k |
Token ID | 479 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Franch | +0.940 |
WD | +0.829 |
haar | +0.810 |
wd | +0.804 |
root | +0.789 |
Neg logit contributions | |
azo | -0.972 |
affles | -0.951 |
bugs | -0.942 |
bug | -0.906 |
ception | -0.885 |
Token | ula |
Token ID | 4712 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
Franch | +1.512 |
WD | +1.334 |
haar | +1.324 |
wd | +1.302 |
root | +1.285 |
Neg logit contributions | |
azo | -1.660 |
bugs | -1.638 |
affles | -1.630 |
bug | -1.564 |
ception | -1.537 |
Token | ho |
Token ID | 8169 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
azo | +0.040 |
affles | +0.039 |
bugs | +0.039 |
bug | +0.038 |
ception | +0.037 |
Neg logit contributions | |
Franch | -0.041 |
WD | -0.037 |
haar | -0.036 |
wd | -0.035 |
root | -0.035 |
Token | � |
Token ID | 134 |
Feature activation | -7.35e+00 |
Pos logit contributions | |
Franch | +3.599 |
WD | +3.209 |
haar | +3.150 |
wd | +3.126 |
root | +3.081 |
Neg logit contributions | |
azo | -3.542 |
affles | -3.531 |
bugs | -3.481 |
bug | -3.327 |
ception | -3.271 |
Token | � |
Token ID | 119 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Franch | +5.009 |
WD | +4.616 |
wd | +4.616 |
haar | +4.543 |
root | +4.490 |
Neg logit contributions | |
azo | -5.733 |
affles | -5.540 |
bugs | -5.486 |
bug | -5.253 |
ception | -5.168 |
Token | ā |
Token ID | 10235 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
Franch | +1.936 |
WD | +1.713 |
haar | +1.680 |
wd | +1.676 |
root | +1.649 |
Neg logit contributions | |
azo | -1.956 |
bugs | -1.923 |
affles | -1.921 |
bug | -1.837 |
ception | -1.801 |
Token | man |
Token ID | 805 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Franch | +3.712 |
WD | +3.320 |
wd | +3.284 |
haar | +3.246 |
root | +3.188 |
Neg logit contributions | |
azo | -3.791 |
affles | -3.744 |
bugs | -3.686 |
bug | -3.503 |
ception | -3.459 |
Token | a |
Token ID | 64 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Franch | +1.349 |
WD | +1.201 |
haar | +1.171 |
wd | +1.168 |
root | +1.144 |
Neg logit contributions | |
azo | -1.272 |
affles | -1.245 |
bugs | -1.238 |
bug | -1.185 |
ception | -1.157 |
Token | p |
Token ID | 279 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
Franch | +1.667 |
WD | +1.481 |
haar | +1.445 |
wd | +1.437 |
root | +1.413 |
Neg logit contributions | |
azo | -1.558 |
affles | -1.525 |
bugs | -1.517 |
bug | -1.454 |
ception | -1.417 |
Token | s |
Token ID | 82 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Franch | +0.791 |
WD | +0.706 |
haar | +0.686 |
wd | +0.681 |
root | +0.672 |
Neg logit contributions | |
azo | -0.691 |
affles | -0.668 |
bugs | -0.664 |
bug | -0.638 |
ception | -0.620 |
Token | revenue |
Token ID | 6426 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
azo | +0.227 |
affles | +0.220 |
bugs | +0.218 |
bug | +0.210 |
ception | +0.204 |
Neg logit contributions | |
Franch | -0.249 |
WD | -0.221 |
haar | -0.214 |
wd | -0.212 |
root | -0.209 |
Token | , |
Token ID | 11 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
azo | +1.296 |
affles | +1.257 |
bugs | +1.247 |
bug | +1.202 |
ception | +1.171 |
Neg logit contributions | |
Franch | -1.397 |
WD | -1.241 |
haar | -1.209 |
wd | -1.198 |
root | -1.176 |
Token | fees |
Token ID | 6642 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Franch | +0.417 |
WD | +0.370 |
haar | +0.358 |
wd | +0.356 |
root | +0.352 |
Neg logit contributions | |
azo | -0.359 |
affles | -0.348 |
bugs | -0.346 |
bug | -0.332 |
ception | -0.322 |
Token | for |
Token ID | 329 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
Franch | +0.875 |
WD | +0.775 |
haar | +0.746 |
wd | +0.743 |
root | +0.732 |
Neg logit contributions | |
azo | -0.895 |
affles | -0.868 |
bugs | -0.865 |
bug | -0.830 |
ception | -0.812 |
Token | lending |
Token ID | 20983 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
Franch | +0.003 |
WD | +0.002 |
haar | +0.002 |
wd | +0.002 |
root | +0.002 |
Neg logit contributions | |
azo | -0.002 |
affles | -0.002 |
bugs | -0.002 |
bug | -0.002 |
ception | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Franch | +5.788 |
WD | +5.100 |
haar | +4.893 |
wd | +4.870 |
root | +4.833 |
Neg logit contributions | |
azo | -5.317 |
affles | -5.059 |
bugs | -5.011 |
bug | -4.848 |
ception | -4.701 |
Token | name |
Token ID | 1438 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Franch | +1.611 |
WD | +1.403 |
haar | +1.351 |
wd | +1.335 |
root | +1.309 |
Neg logit contributions | |
azo | -1.810 |
bugs | -1.748 |
affles | -1.747 |
bug | -1.686 |
ception | -1.638 |
Token | and |
Token ID | 290 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Franch | +2.722 |
WD | +2.424 |
haar | +2.350 |
wd | +2.343 |
root | +2.309 |
Neg logit contributions | |
azo | -2.355 |
affles | -2.257 |
bugs | -2.250 |
bug | -2.158 |
ception | -2.090 |
Token | brand |
Token ID | 4508 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Franch | +1.415 |
WD | +1.235 |
haar | +1.197 |
wd | +1.176 |
root | +1.163 |
Neg logit contributions | |
azo | -1.499 |
bugs | -1.449 |
affles | -1.446 |
bug | -1.392 |
ception | -1.346 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Franch | +1.627 |
WD | +1.450 |
haar | +1.404 |
wd | +1.397 |
root | +1.372 |
Neg logit contributions | |
azo | -1.494 |
affles | -1.441 |
bugs | -1.438 |
bug | -1.384 |
ception | -1.342 |
Token |
|
Token ID | 198 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
Franch | +1.253 |
WD | +1.109 |
haar | +1.082 |
wd | +1.069 |
root | +1.057 |
Neg logit contributions | |
azo | -1.098 |
affles | -1.063 |
bugs | -1.056 |
bug | -1.013 |
ception | -0.983 |
Token |
|
Token ID | 198 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
Franch | +0.582 |
WD | +0.522 |
wd | +0.503 |
haar | +0.502 |
root | +0.499 |
Neg logit contributions | |
azo | -0.521 |
affles | -0.503 |
bugs | -0.495 |
bug | -0.474 |
ception | -0.463 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Franch | +0.624 |
WD | +0.575 |
haar | +0.555 |
wd | +0.553 |
root | +0.551 |
Neg logit contributions | |
azo | -0.398 |
affles | -0.384 |
bugs | -0.377 |
bug | -0.357 |
ception | -0.345 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Franch | +0.222 |
WD | +0.196 |
haar | +0.188 |
wd | +0.187 |
root | +0.185 |
Neg logit contributions | |
azo | -0.245 |
affles | -0.237 |
bugs | -0.235 |
bug | -0.226 |
ception | -0.221 |
Token | Finn |
Token ID | 15368 |
Feature activation | -7.55e+00 |
Pos logit contributions | |
Franch | +1.651 |
WD | +1.425 |
haar | +1.388 |
root | +1.373 |
wd | +1.369 |
Neg logit contributions | |
azo | -1.626 |
affles | -1.580 |
bugs | -1.564 |
bug | -1.492 |
ception | -1.455 |
Token | Russell |
Token ID | 11563 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
Franch | +4.334 |
WD | +3.473 |
root | +3.435 |
wd | +3.389 |
haar | +3.239 |
Neg logit contributions | |
azo | -7.108 |
affles | -6.930 |
bugs | -6.851 |
haps | -6.622 |
bug | -6.546 |
Token | ( |
Token ID | 357 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
Franch | +5.105 |
WD | +4.438 |
haar | +4.356 |
root | +4.348 |
wd | +4.307 |
Neg logit contributions | |
azo | -5.743 |
bugs | -5.506 |
affles | -5.477 |
bug | -5.285 |
haps | -5.188 |
Token | 58 |
Token ID | 3365 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Franch | +3.305 |
WD | +3.089 |
wd | +2.937 |
root | +2.928 |
haar | +2.871 |
Neg logit contributions | |
azo | -3.289 |
affles | -3.142 |
bugs | -3.055 |
bug | -2.917 |
haps | -2.894 |
Token | ) |
Token ID | 8 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Franch | +1.597 |
WD | +1.452 |
wd | +1.400 |
root | +1.393 |
haar | +1.382 |
Neg logit contributions | |
azo | -1.389 |
affles | -1.335 |
bugs | -1.309 |
bug | -1.246 |
ception | -1.223 |
Token | ( |
Token ID | 357 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Franch | +1.116 |
WD | +0.993 |
wd | +0.957 |
haar | +0.956 |
root | +0.946 |
Neg logit contributions | |
azo | -1.034 |
affles | -0.994 |
bugs | -0.983 |
bug | -0.942 |
ception | -0.920 |
Token | 17 |
Token ID | 1558 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
azo | +0.177 |
affles | +0.171 |
bugs | +0.169 |
bug | +0.162 |
ception | +0.157 |
Neg logit contributions | |
Franch | -0.237 |
WD | -0.214 |
haar | -0.207 |
wd | -0.206 |
root | -0.204 |
Token | dehyd |
Token ID | 28151 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
azo | +1.284 |
affles | +1.242 |
bugs | +1.232 |
bug | +1.185 |
ception | +1.150 |
Neg logit contributions | |
Franch | -1.539 |
WD | -1.378 |
haar | -1.341 |
wd | -1.329 |
root | -1.306 |
Token | rated |
Token ID | 4111 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
azo | +1.297 |
affles | +1.251 |
bugs | +1.244 |
bug | +1.200 |
ception | +1.169 |
Neg logit contributions | |
Franch | -1.511 |
WD | -1.341 |
haar | -1.304 |
wd | -1.291 |
root | -1.263 |
Token | k |
Token ID | 479 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
azo | +0.370 |
affles | +0.359 |
bugs | +0.357 |
bug | +0.343 |
ception | +0.335 |
Neg logit contributions | |
Franch | -0.371 |
WD | -0.328 |
haar | -0.318 |
wd | -0.315 |
root | -0.311 |
Token | uz |
Token ID | 10277 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
azo | +0.887 |
affles | +0.863 |
bugs | +0.860 |
bug | +0.830 |
ception | +0.812 |
Neg logit contributions | |
Franch | -0.744 |
WD | -0.651 |
haar | -0.631 |
wd | -0.626 |
root | -0.616 |
Token | u |
Token ID | 84 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Franch | +0.181 |
WD | +0.165 |
haar | +0.162 |
wd | +0.161 |
root | +0.160 |
Neg logit contributions | |
azo | -0.109 |
affles | -0.105 |
bugs | -0.104 |
bug | -0.099 |
ception | -0.096 |
Token | root |
Token ID | 6808 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
Franch | +1.225 |
WD | +1.107 |
haar | +1.076 |
wd | +1.074 |
root | +1.074 |
Neg logit contributions | |
azo | -0.947 |
affles | -0.915 |
bugs | -0.910 |
bug | -0.875 |
ception | -0.848 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Franch | +5.635 |
root | +5.209 |
WD | +5.091 |
wd | +4.940 |
haar | +4.939 |
Neg logit contributions | |
azo | -4.962 |
bugs | -4.719 |
affles | -4.716 |
bug | -4.521 |
ception | -4.397 |
Token | used |
Token ID | 973 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Franch | +0.155 |
WD | +0.138 |
haar | +0.134 |
wd | +0.133 |
root | +0.132 |
Neg logit contributions | |
azo | -0.129 |
affles | -0.125 |
bugs | -0.124 |
bug | -0.119 |
ception | -0.116 |
Token | in |
Token ID | 287 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
azo | +0.727 |
affles | +0.700 |
bugs | +0.695 |
bug | +0.666 |
ception | +0.646 |
Neg logit contributions | |
Franch | -0.968 |
WD | -0.872 |
haar | -0.848 |
wd | -0.842 |
root | -0.831 |
Token | Asian |
Token ID | 7740 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
azo | +0.785 |
affles | +0.756 |
bugs | +0.751 |
bug | +0.719 |
ception | +0.697 |
Neg logit contributions | |
Franch | -1.073 |
WD | -0.966 |
haar | -0.941 |
wd | -0.934 |
root | -0.922 |
Token | cooking |
Token ID | 10801 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
azo | +0.277 |
affles | +0.266 |
bugs | +0.266 |
bug | +0.255 |
ception | +0.246 |
Neg logit contributions | |
Franch | -0.374 |
WD | -0.337 |
haar | -0.326 |
wd | -0.325 |
root | -0.321 |
Token | gains |
Token ID | 8810 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
Franch | +1.524 |
WD | +1.352 |
wd | +1.300 |
haar | +1.293 |
root | +1.277 |
Neg logit contributions | |
azo | -1.598 |
affles | -1.548 |
bugs | -1.528 |
bug | -1.473 |
ception | -1.450 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Franch | +2.257 |
WD | +1.999 |
wd | +1.916 |
haar | +1.891 |
root | +1.879 |
Neg logit contributions | |
azo | -2.475 |
affles | -2.399 |
bugs | -2.385 |
bug | -2.293 |
ception | -2.244 |
Token |
|
Token ID | 198 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
azo | +0.097 |
affles | +0.094 |
bugs | +0.093 |
bug | +0.089 |
ception | +0.087 |
Neg logit contributions | |
Franch | -0.109 |
WD | -0.097 |
haar | -0.093 |
wd | -0.093 |
root | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
azo | +0.435 |
affles | +0.420 |
bugs | +0.416 |
bug | +0.399 |
ception | +0.389 |
Neg logit contributions | |
Franch | -0.516 |
WD | -0.463 |
haar | -0.448 |
wd | -0.446 |
root | -0.440 |
Token | V |
Token ID | 53 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
azo | +0.651 |
affles | +0.629 |
bugs | +0.626 |
bug | +0.603 |
ception | +0.587 |
Neg logit contributions | |
Franch | -0.716 |
WD | -0.632 |
haar | -0.620 |
wd | -0.611 |
root | -0.601 |
Token | enezuel |
Token ID | 12596 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
azo | +0.346 |
affles | +0.335 |
bugs | +0.333 |
bug | +0.321 |
ception | +0.312 |
Neg logit contributions | |
Franch | -0.376 |
WD | -0.334 |
haar | -0.325 |
wd | -0.322 |
root | -0.317 |
Token | a |
Token ID | 64 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
azo | +3.685 |
bugs | +3.513 |
affles | +3.495 |
bug | +3.382 |
ception | +3.254 |
Neg logit contributions | |
Franch | -3.993 |
WD | -3.534 |
haar | -3.450 |
wd | -3.408 |
root | -3.314 |
Token | � |
Token ID | 447 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
azo | +1.638 |
affles | +1.581 |
bugs | +1.577 |
bug | +1.515 |
ception | +1.472 |
Neg logit contributions | |
Franch | -1.793 |
WD | -1.599 |
haar | -1.557 |
wd | -1.539 |
root | -1.514 |
Token | � |
Token ID | 247 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
azo | +1.019 |
affles | +0.985 |
bugs | +0.979 |
bug | +0.940 |
ception | +0.914 |
Neg logit contributions | |
Franch | -1.211 |
WD | -1.079 |
haar | -1.046 |
wd | -1.041 |
root | -1.024 |
Token | s |
Token ID | 82 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
azo | +0.433 |
affles | +0.419 |
bugs | +0.415 |
bug | +0.399 |
ception | +0.388 |
Neg logit contributions | |
Franch | -0.520 |
WD | -0.466 |
haar | -0.453 |
wd | -0.449 |
root | -0.443 |
Token | streets |
Token ID | 6483 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
azo | +0.632 |
affles | +0.613 |
bugs | +0.609 |
bug | +0.588 |
ception | +0.574 |
Neg logit contributions | |
Franch | -0.596 |
WD | -0.525 |
haar | -0.509 |
wd | -0.504 |
root | -0.496 |
Token | brain |
Token ID | 3632 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
azo | +0.714 |
affles | +0.685 |
bugs | +0.684 |
bug | +0.653 |
ception | +0.633 |
Neg logit contributions | |
Franch | -0.884 |
WD | -0.789 |
haar | -0.768 |
wd | -0.761 |
root | -0.755 |
Token | � |
Token ID | 447 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
azo | +0.903 |
affles | +0.875 |
bugs | +0.869 |
bug | +0.837 |
ception | +0.815 |
Neg logit contributions | |
Franch | -0.964 |
WD | -0.857 |
haar | -0.832 |
wd | -0.825 |
root | -0.810 |
Token | � |
Token ID | 247 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
azo | +0.268 |
affles | +0.261 |
bugs | +0.260 |
bug | +0.252 |
ception | +0.247 |
Neg logit contributions | |
Franch | -0.173 |
WD | -0.146 |
haar | -0.140 |
wd | -0.139 |
root | -0.136 |
Token | s |
Token ID | 82 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
azo | +1.180 |
affles | +1.139 |
bugs | +1.134 |
bug | +1.092 |
ception | +1.061 |
Neg logit contributions | |
Franch | -1.419 |
WD | -1.271 |
haar | -1.234 |
wd | -1.224 |
root | -1.199 |
Token | exposed |
Token ID | 7362 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
azo | +0.497 |
affles | +0.478 |
bugs | +0.477 |
bug | +0.457 |
ception | +0.442 |
Neg logit contributions | |
Franch | -0.583 |
WD | -0.520 |
haar | -0.506 |
wd | -0.503 |
root | -0.496 |
Token | surface |
Token ID | 4417 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
azo | +1.681 |
affles | +1.622 |
bugs | +1.610 |
bug | +1.546 |
ception | +1.502 |
Neg logit contributions | |
Franch | -2.101 |
WD | -1.886 |
haar | -1.834 |
wd | -1.820 |
root | -1.794 |
Token | ; |
Token ID | 26 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
azo | +4.010 |
affles | +3.842 |
bugs | +3.819 |
bug | +3.673 |
ception | +3.594 |
Neg logit contributions | |
Franch | -4.696 |
WD | -4.193 |
haar | -4.073 |
wd | -4.058 |
root | -3.951 |
Token | these |
Token ID | 777 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
azo | +2.488 |
affles | +2.402 |
bugs | +2.382 |
bug | +2.276 |
ception | +2.225 |
Neg logit contributions | |
Franch | -3.129 |
WD | -2.820 |
haar | -2.747 |
wd | -2.721 |
root | -2.678 |
Token | sensors |
Token ID | 15736 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
azo | +1.255 |
affles | +1.211 |
bugs | +1.204 |
bug | +1.159 |
ception | +1.126 |
Neg logit contributions | |
Franch | -1.419 |
WD | -1.268 |
haar | -1.230 |
wd | -1.221 |
root | -1.203 |
Token | read |
Token ID | 1100 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
azo | +1.880 |
affles | +1.818 |
bugs | +1.804 |
bug | +1.734 |
ception | +1.690 |
Neg logit contributions | |
Franch | -2.187 |
WD | -1.953 |
haar | -1.900 |
wd | -1.883 |
root | -1.850 |
Token | changes |
Token ID | 2458 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
azo | +0.327 |
affles | +0.315 |
bugs | +0.313 |
bug | +0.301 |
ception | +0.292 |
Neg logit contributions | |
Franch | -0.381 |
WD | -0.340 |
haar | -0.331 |
wd | -0.329 |
root | -0.324 |
Token | fighters |
Token ID | 8486 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
azo | +2.091 |
bugs | +2.033 |
affles | +2.013 |
bug | +1.949 |
ception | +1.893 |
Neg logit contributions | |
Franch | -2.319 |
WD | -2.077 |
haar | -2.032 |
wd | -1.998 |
root | -1.975 |
Token | I |
Token ID | 314 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
azo | +0.510 |
affles | +0.492 |
bugs | +0.486 |
bug | +0.465 |
ception | +0.451 |
Neg logit contributions | |
Franch | -0.705 |
WD | -0.635 |
haar | -0.617 |
wd | -0.615 |
root | -0.607 |
Token | � |
Token ID | 447 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
azo | +1.776 |
bugs | +1.696 |
affles | +1.693 |
bug | +1.642 |
ception | +1.574 |
Neg logit contributions | |
Franch | -2.195 |
WD | -1.954 |
haar | -1.924 |
wd | -1.883 |
root | -1.869 |
Token | � |
Token ID | 247 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
azo | +1.963 |
affles | +1.900 |
bugs | +1.890 |
bug | +1.846 |
ception | +1.798 |
Neg logit contributions | |
Franch | -1.508 |
WD | -1.268 |
haar | -1.226 |
wd | -1.207 |
root | -1.179 |
Token | ve |
Token ID | 303 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
azo | +1.689 |
affles | +1.624 |
bugs | +1.623 |
bug | +1.575 |
ception | +1.530 |
Neg logit contributions | |
Franch | -1.830 |
WD | -1.626 |
haar | -1.584 |
wd | -1.550 |
root | -1.538 |
Token | ever |
Token ID | 1683 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Franch | +0.484 |
WD | +0.441 |
haar | +0.430 |
wd | +0.429 |
root | +0.422 |
Neg logit contributions | |
azo | -0.273 |
affles | -0.262 |
bugs | -0.259 |
bug | -0.246 |
ception | -0.237 |
Token | known |
Token ID | 1900 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
azo | +3.276 |
bugs | +3.130 |
affles | +3.083 |
bug | +3.049 |
ception | +2.928 |
Neg logit contributions | |
Franch | -4.058 |
WD | -3.611 |
haar | -3.549 |
root | -3.444 |
wd | -3.403 |
Token | . |
Token ID | 13 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
azo | +2.434 |
bugs | +2.345 |
affles | +2.339 |
bug | +2.262 |
ception | +2.204 |
Neg logit contributions | |
Franch | -2.544 |
WD | -2.249 |
haar | -2.202 |
wd | -2.164 |
root | -2.128 |
Token | Cancer |
Token ID | 15523 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
azo | +0.498 |
affles | +0.482 |
bugs | +0.479 |
bug | +0.461 |
ception | +0.449 |
Neg logit contributions | |
Franch | -0.521 |
WD | -0.462 |
haar | -0.447 |
wd | -0.445 |
root | -0.438 |
Token | doesn |
Token ID | 1595 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
azo | +1.158 |
affles | +1.118 |
bugs | +1.110 |
bug | +1.067 |
ception | +1.037 |
Neg logit contributions | |
Franch | -1.383 |
WD | -1.239 |
haar | -1.205 |
wd | -1.194 |
root | -1.176 |
Token | � |
Token ID | 447 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
azo | +1.521 |
affles | +1.486 |
bugs | +1.485 |
bug | +1.444 |
ception | +1.410 |
Neg logit contributions | |
Franch | -0.992 |
WD | -0.840 |
haar | -0.818 |
wd | -0.799 |
root | -0.773 |
Token | limits |
Token ID | 49196 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
azo | +0.836 |
affles | +0.796 |
bugs | +0.794 |
bug | +0.752 |
ception | +0.718 |
Neg logit contributions | |
Franch | -1.742 |
WD | -1.592 |
haar | -1.560 |
wd | -1.545 |
root | -1.523 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
azo | +1.572 |
affles | +1.520 |
bugs | +1.518 |
bug | +1.452 |
ception | +1.405 |
Neg logit contributions | |
Franch | -2.185 |
WD | -1.964 |
haar | -1.920 |
wd | -1.899 |
root | -1.873 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Franch | +0.098 |
WD | +0.088 |
haar | +0.085 |
wd | +0.085 |
root | +0.083 |
Neg logit contributions | |
azo | -0.086 |
affles | -0.083 |
bugs | -0.082 |
bug | -0.079 |
ception | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
azo | +0.080 |
affles | +0.077 |
bugs | +0.076 |
bug | +0.073 |
ception | +0.071 |
Neg logit contributions | |
Franch | -0.092 |
WD | -0.083 |
haar | -0.080 |
wd | -0.080 |
root | -0.079 |
Token | La |
Token ID | 14772 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
Franch | +0.010 |
WD | +0.009 |
haar | +0.009 |
wd | +0.009 |
root | +0.008 |
Neg logit contributions | |
azo | -0.010 |
affles | -0.010 |
bugs | -0.009 |
bug | -0.009 |
ception | -0.009 |
Token | ure |
Token ID | 495 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
Franch | +0.653 |
WD | +0.568 |
haar | +0.550 |
wd | +0.544 |
root | +0.536 |
Neg logit contributions | |
azo | -0.798 |
affles | -0.777 |
bugs | -0.772 |
bug | -0.746 |
ception | -0.728 |
Token | nce |
Token ID | 1198 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
azo | +3.919 |
affles | +3.790 |
bugs | +3.763 |
bug | +3.677 |
ception | +3.580 |
Neg logit contributions | |
Franch | -3.477 |
WD | -3.117 |
haar | -2.960 |
wd | -2.922 |
root | -2.866 |
Token | G |
Token ID | 402 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
azo | +3.027 |
affles | +2.929 |
bugs | +2.922 |
bug | +2.831 |
ception | +2.730 |
Neg logit contributions | |
Franch | -3.226 |
WD | -2.926 |
haar | -2.839 |
wd | -2.807 |
root | -2.750 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
azo | +1.301 |
affles | +1.261 |
bugs | +1.254 |
bug | +1.210 |
ception | +1.180 |
Neg logit contributions | |
Franch | -1.241 |
WD | -1.096 |
haar | -1.061 |
wd | -1.052 |
root | -1.035 |
Token | Williams |
Token ID | 6484 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
azo | +1.658 |
affles | +1.606 |
bugs | +1.595 |
bug | +1.537 |
ception | +1.497 |
Neg logit contributions | |
Franch | -1.756 |
WD | -1.562 |
haar | -1.516 |
wd | -1.503 |
root | -1.479 |
Token | , |
Token ID | 11 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Franch | +0.805 |
WD | +0.717 |
haar | +0.696 |
wd | +0.689 |
root | +0.680 |
Neg logit contributions | |
azo | -0.760 |
affles | -0.738 |
bugs | -0.730 |
bug | -0.702 |
ception | -0.687 |
Token | actions |
Token ID | 4028 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Franch | +0.398 |
WD | +0.352 |
haar | +0.340 |
wd | +0.339 |
root | +0.333 |
Neg logit contributions | |
azo | -0.420 |
affles | -0.406 |
bugs | -0.403 |
bug | -0.389 |
ception | -0.380 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Franch | +1.111 |
WD | +0.998 |
wd | +0.968 |
haar | +0.964 |
root | +0.949 |
Neg logit contributions | |
azo | -0.928 |
affles | -0.892 |
bugs | -0.883 |
bug | -0.845 |
ception | -0.830 |
Token | known |
Token ID | 1900 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Franch | +0.929 |
WD | +0.824 |
wd | +0.794 |
haar | +0.789 |
root | +0.778 |
Neg logit contributions | |
azo | -0.988 |
affles | -0.954 |
bugs | -0.947 |
bug | -0.911 |
ception | -0.894 |
Token | as |
Token ID | 355 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Franch | +1.428 |
WD | +1.283 |
haar | +1.236 |
wd | +1.233 |
root | +1.213 |
Neg logit contributions | |
azo | -1.282 |
affles | -1.234 |
bugs | -1.219 |
bug | -1.175 |
ception | -1.147 |
Token | " |
Token ID | 366 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
azo | +0.278 |
affles | +0.269 |
bugs | +0.267 |
bug | +0.257 |
ception | +0.250 |
Neg logit contributions | |
Franch | -0.310 |
WD | -0.277 |
haar | -0.269 |
wd | -0.266 |
root | -0.262 |
Token | extra |
Token ID | 26086 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
azo | +1.567 |
bugs | +1.529 |
affles | +1.522 |
bug | +1.481 |
ception | +1.425 |
Neg logit contributions | |
Franch | -1.563 |
WD | -1.362 |
haar | -1.328 |
wd | -1.303 |
root | -1.271 |
Token | ordinary |
Token ID | 35947 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
azo | +2.922 |
bugs | +2.814 |
affles | +2.763 |
bug | +2.669 |
ception | +2.587 |
Neg logit contributions | |
Franch | -5.097 |
WD | -4.562 |
haar | -4.484 |
wd | -4.373 |
root | -4.293 |
Token | measures |
Token ID | 5260 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
azo | +0.552 |
affles | +0.536 |
bugs | +0.533 |
bug | +0.514 |
ception | +0.502 |
Neg logit contributions | |
Franch | -0.504 |
WD | -0.444 |
haar | -0.430 |
wd | -0.426 |
root | -0.418 |
Token | ," |
Token ID | 553 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
azo | +0.623 |
affles | +0.600 |
bugs | +0.595 |
bug | +0.570 |
ception | +0.554 |
Neg logit contributions | |
Franch | -0.813 |
WD | -0.732 |
haar | -0.712 |
wd | -0.708 |
root | -0.697 |
Token | to |
Token ID | 284 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
azo | +0.601 |
affles | +0.580 |
bugs | +0.575 |
bug | +0.550 |
ception | +0.536 |
Neg logit contributions | |
Franch | -0.773 |
WD | -0.695 |
haar | -0.674 |
wd | -0.673 |
root | -0.662 |
Token | keep |
Token ID | 1394 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
azo | +0.574 |
affles | +0.556 |
bugs | +0.552 |
bug | +0.530 |
ception | +0.518 |
Neg logit contributions | |
Franch | -0.638 |
WD | -0.569 |
haar | -0.551 |
wd | -0.549 |
root | -0.540 |
Token | see |
Token ID | 766 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Franch | +0.478 |
WD | +0.418 |
haar | +0.402 |
wd | +0.400 |
root | +0.396 |
Neg logit contributions | |
azo | -0.535 |
affles | -0.524 |
bugs | -0.516 |
bug | -0.499 |
ception | -0.485 |
Token | them |
Token ID | 606 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
Franch | +0.008 |
WD | +0.007 |
haar | +0.007 |
wd | +0.007 |
root | +0.007 |
Neg logit contributions | |
azo | -0.007 |
affles | -0.007 |
bugs | -0.007 |
bug | -0.007 |
ception | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Franch | +0.553 |
WD | +0.489 |
haar | +0.475 |
wd | +0.472 |
root | +0.466 |
Neg logit contributions | |
azo | -0.530 |
affles | -0.513 |
bugs | -0.508 |
bug | -0.489 |
ception | -0.477 |
Token | the |
Token ID | 262 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Franch | +1.425 |
WD | +1.268 |
haar | +1.228 |
wd | +1.224 |
root | +1.211 |
Neg logit contributions | |
azo | -1.189 |
affles | -1.144 |
bugs | -1.138 |
bug | -1.093 |
ception | -1.060 |
Token | other |
Token ID | 584 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Franch | +0.321 |
WD | +0.288 |
haar | +0.278 |
wd | +0.277 |
root | +0.275 |
Neg logit contributions | |
azo | -0.240 |
affles | -0.231 |
bugs | -0.230 |
bug | -0.220 |
ception | -0.213 |
Token | side |
Token ID | 1735 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
Franch | +1.757 |
WD | +1.549 |
wd | +1.463 |
root | +1.450 |
haar | +1.441 |
Neg logit contributions | |
azo | -1.919 |
affles | -1.858 |
bugs | -1.856 |
bug | -1.782 |
ception | -1.728 |
Token | for |
Token ID | 329 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
azo | +0.360 |
affles | +0.347 |
bugs | +0.346 |
bug | +0.332 |
ception | +0.323 |
Neg logit contributions | |
Franch | -0.419 |
WD | -0.374 |
haar | -0.363 |
wd | -0.361 |
root | -0.356 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
azo | +0.869 |
affles | +0.844 |
bugs | +0.839 |
bug | +0.805 |
ception | +0.784 |
Neg logit contributions | |
Franch | -1.000 |
WD | -0.897 |
haar | -0.872 |
wd | -0.865 |
root | -0.850 |
Token | first |
Token ID | 717 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
azo | +0.922 |
affles | +0.895 |
bugs | +0.889 |
bug | +0.857 |
ception | +0.837 |
Neg logit contributions | |
Franch | -0.900 |
WD | -0.797 |
haar | -0.774 |
wd | -0.767 |
root | -0.753 |
Token | time |
Token ID | 640 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Franch | +0.658 |
WD | +0.581 |
wd | +0.557 |
haar | +0.556 |
root | +0.550 |
Neg logit contributions | |
azo | -0.652 |
affles | -0.629 |
bugs | -0.623 |
bug | -0.599 |
ception | -0.583 |
Token | ." |
Token ID | 526 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Franch | +1.780 |
WD | +1.572 |
wd | +1.521 |
haar | +1.503 |
root | +1.503 |
Neg logit contributions | |
azo | -1.727 |
affles | -1.658 |
bugs | -1.641 |
bug | -1.570 |
ception | -1.542 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Franch | +0.101 |
WD | +0.090 |
haar | +0.087 |
wd | +0.086 |
root | +0.085 |
Neg logit contributions | |
azo | -0.097 |
affles | -0.093 |
bugs | -0.093 |
bug | -0.090 |
ception | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Franch | +0.850 |
WD | +0.750 |
wd | +0.722 |
haar | +0.720 |
root | +0.712 |
Neg logit contributions | |
azo | -0.794 |
affles | -0.762 |
bugs | -0.756 |
bug | -0.726 |
ception | -0.705 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
azo | +0.090 |
affles | +0.087 |
bugs | +0.086 |
bug | +0.082 |
ception | +0.080 |
Neg logit contributions | |
Franch | -0.106 |
WD | -0.095 |
haar | -0.092 |
wd | -0.092 |
root | -0.090 |
Token | Dem |
Token ID | 11522 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
azo | +0.016 |
affles | +0.015 |
bugs | +0.015 |
bug | +0.015 |
ception | +0.014 |
Neg logit contributions | |
Franch | -0.017 |
WD | -0.015 |
haar | -0.014 |
wd | -0.014 |
root | -0.014 |
Token | ocrat |
Token ID | 35128 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
azo | +0.475 |
affles | +0.458 |
bugs | +0.455 |
bug | +0.437 |
ception | +0.425 |
Neg logit contributions | |
Franch | -0.577 |
WD | -0.518 |
haar | -0.503 |
wd | -0.499 |
root | -0.492 |
Token | Eric |
Token ID | 7651 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
azo | +1.741 |
bugs | +1.688 |
affles | +1.685 |
bug | +1.628 |
ception | +1.585 |
Neg logit contributions | |
Franch | -1.980 |
WD | -1.780 |
haar | -1.740 |
wd | -1.711 |
root | -1.682 |
Token | Alter |
Token ID | 32770 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
azo | +0.519 |
affles | +0.502 |
bugs | +0.501 |
bug | +0.483 |
ception | +0.475 |
Neg logit contributions | |
Franch | -0.411 |
WD | -0.350 |
haar | -0.341 |
wd | -0.339 |
root | -0.332 |
Token | man |
Token ID | 805 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
azo | +2.133 |
affles | +2.067 |
bugs | +2.062 |
bug | +2.027 |
ception | +1.931 |
Neg logit contributions | |
Franch | -2.038 |
WD | -1.767 |
haar | -1.713 |
wd | -1.712 |
entin | -1.674 |
Token | writes |
Token ID | 6797 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
azo | +0.587 |
affles | +0.567 |
bugs | +0.564 |
bug | +0.542 |
ception | +0.527 |
Neg logit contributions | |
Franch | -0.663 |
WD | -0.592 |
haar | -0.575 |
wd | -0.570 |
root | -0.561 |
Token | : |
Token ID | 25 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
azo | +1.039 |
affles | +1.005 |
bugs | +0.999 |
bug | +0.962 |
ception | +0.934 |
Neg logit contributions | |
Franch | -1.200 |
WD | -1.074 |
haar | -1.044 |
wd | -1.035 |
root | -1.020 |
Token | " |
Token ID | 366 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
Franch | +0.529 |
WD | +0.471 |
haar | +0.459 |
wd | +0.456 |
root | +0.449 |
Neg logit contributions | |
azo | -0.462 |
affles | -0.444 |
bugs | -0.440 |
bug | -0.422 |
ception | -0.410 |
Token | a |
Token ID | 257 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Franch | +0.537 |
WD | +0.478 |
haar | +0.463 |
wd | +0.460 |
root | +0.454 |
Neg logit contributions | |
azo | -0.487 |
affles | -0.470 |
bugs | -0.467 |
bug | -0.450 |
ception | -0.437 |
Token | Reuters |
Token ID | 8428 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
Franch | +0.123 |
WD | +0.109 |
haar | +0.106 |
wd | +0.105 |
root | +0.104 |
Neg logit contributions | |
azo | -0.114 |
affles | -0.111 |
bugs | -0.110 |
bug | -0.106 |
ception | -0.103 |
Token | report |
Token ID | 989 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
Franch | +0.620 |
WD | +0.554 |
haar | +0.537 |
wd | +0.533 |
root | +0.526 |
Neg logit contributions | |
azo | -0.559 |
affles | -0.547 |
bugs | -0.540 |
bug | -0.514 |
ception | -0.502 |
Token | . |
Token ID | 13 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
azo | +0.524 |
affles | +0.507 |
bugs | +0.506 |
bug | +0.489 |
ception | +0.476 |
Neg logit contributions | |
Franch | -0.521 |
WD | -0.459 |
haar | -0.446 |
wd | -0.442 |
root | -0.434 |
Token | At |
Token ID | 1629 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
Franch | +0.361 |
WD | +0.317 |
haar | +0.307 |
wd | +0.306 |
root | +0.303 |
Neg logit contributions | |
azo | -0.331 |
affles | -0.319 |
bugs | -0.317 |
bug | -0.305 |
ception | -0.295 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Franch | +0.720 |
WD | +0.641 |
haar | +0.622 |
root | +0.617 |
wd | +0.616 |
Neg logit contributions | |
azo | -0.632 |
affles | -0.607 |
bugs | -0.606 |
bug | -0.583 |
ception | -0.566 |
Token | time |
Token ID | 640 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
azo | +0.981 |
affles | +0.949 |
bugs | +0.944 |
bug | +0.908 |
ception | +0.884 |
Neg logit contributions | |
Franch | -1.054 |
WD | -0.937 |
haar | -0.908 |
wd | -0.902 |
root | -0.890 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
azo | +0.152 |
affles | +0.147 |
bugs | +0.146 |
bug | +0.141 |
ception | +0.137 |
Neg logit contributions | |
Franch | -0.150 |
WD | -0.133 |
haar | -0.129 |
wd | -0.128 |
root | -0.126 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
azo | +1.181 |
affles | +1.144 |
bugs | +1.136 |
bug | +1.092 |
ception | +1.066 |
Neg logit contributions | |
Franch | -1.290 |
WD | -1.153 |
haar | -1.119 |
wd | -1.110 |
root | -1.090 |
Token | Korean |
Token ID | 6983 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
azo | +1.343 |
affles | +1.298 |
bugs | +1.287 |
bug | +1.246 |
ception | +1.216 |
Neg logit contributions | |
Franch | -1.361 |
WD | -1.211 |
haar | -1.177 |
wd | -1.165 |
root | -1.144 |
Token | police |
Token ID | 1644 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Franch | +0.167 |
WD | +0.149 |
haar | +0.144 |
wd | +0.143 |
root | +0.141 |
Neg logit contributions | |
azo | -0.144 |
affles | -0.139 |
bugs | -0.138 |
bug | -0.132 |
ception | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
azo | +0.630 |
affles | +0.610 |
bugs | +0.606 |
bug | +0.584 |
ception | +0.570 |
Neg logit contributions | |
Franch | -0.629 |
WD | -0.557 |
haar | -0.540 |
wd | -0.535 |
root | -0.527 |
Token | I |
Token ID | 314 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Franch | +0.930 |
WD | +0.824 |
haar | +0.792 |
wd | +0.790 |
root | +0.782 |
Neg logit contributions | |
azo | -0.877 |
affles | -0.845 |
bugs | -0.838 |
bug | -0.805 |
ception | -0.780 |
Token | � |
Token ID | 447 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Franch | +0.283 |
WD | +0.252 |
haar | +0.244 |
wd | +0.242 |
root | +0.239 |
Neg logit contributions | |
azo | -0.259 |
affles | -0.250 |
bugs | -0.249 |
bug | -0.239 |
ception | -0.233 |
Token | � |
Token ID | 247 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
azo | +1.410 |
affles | +1.353 |
bugs | +1.347 |
bug | +1.298 |
ception | +1.256 |
Neg logit contributions | |
Franch | -1.827 |
WD | -1.617 |
haar | -1.573 |
wd | -1.561 |
root | -1.530 |
Token | ll |
Token ID | 297 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
azo | +0.756 |
affles | +0.728 |
bugs | +0.725 |
bug | +0.699 |
ception | +0.677 |
Neg logit contributions | |
Franch | -0.963 |
WD | -0.864 |
haar | -0.843 |
wd | -0.831 |
root | -0.821 |
Token | admit |
Token ID | 9159 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
azo | +2.155 |
bugs | +2.053 |
affles | +2.045 |
bug | +1.984 |
ception | +1.920 |
Neg logit contributions | |
Franch | -2.649 |
WD | -2.370 |
haar | -2.316 |
wd | -2.274 |
root | -2.246 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
azo | +2.766 |
bugs | +2.654 |
affles | +2.648 |
bug | +2.554 |
ception | +2.480 |
Neg logit contributions | |
Franch | -3.516 |
WD | -3.144 |
haar | -3.083 |
wd | -3.033 |
root | -3.006 |
Token | I |
Token ID | 314 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
azo | +1.511 |
affles | +1.456 |
bugs | +1.447 |
bug | +1.386 |
ception | +1.346 |
Neg logit contributions | |
Franch | -2.027 |
WD | -1.827 |
haar | -1.780 |
wd | -1.765 |
root | -1.741 |
Token | � |
Token ID | 447 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
Franch | +0.887 |
WD | +0.796 |
haar | +0.768 |
wd | +0.766 |
root | +0.753 |
Neg logit contributions | |
azo | -0.789 |
affles | -0.769 |
bugs | -0.762 |
bug | -0.730 |
ception | -0.713 |
Token | � |
Token ID | 247 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
azo | +0.835 |
affles | +0.812 |
bugs | +0.808 |
bug | +0.785 |
ception | +0.768 |
Neg logit contributions | |
Franch | -0.588 |
WD | -0.503 |
haar | -0.484 |
wd | -0.479 |
root | -0.467 |
Token | m |
Token ID | 76 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
azo | +0.439 |
affles | +0.425 |
bugs | +0.424 |
bug | +0.410 |
ception | +0.400 |
Neg logit contributions | |
Franch | -0.404 |
WD | -0.355 |
haar | -0.344 |
wd | -0.339 |
root | -0.333 |
Token | at |
Token ID | 379 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
azo | +0.430 |
affles | +0.415 |
bugs | +0.412 |
bug | +0.395 |
ception | +0.383 |
Neg logit contributions | |
Franch | -0.548 |
WD | -0.492 |
haar | -0.478 |
wd | -0.476 |
root | -0.469 |
Token | Cl |
Token ID | 1012 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
Franch | +3.147 |
WD | +2.761 |
wd | +2.636 |
root | +2.630 |
haar | +2.629 |
Neg logit contributions | |
azo | -2.691 |
bugs | -2.608 |
affles | -2.589 |
bug | -2.488 |
ception | -2.435 |
Token | utch |
Token ID | 7140 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Franch | +0.338 |
WD | +0.293 |
wd | +0.279 |
haar | +0.272 |
root | +0.270 |
Neg logit contributions | |
azo | -0.605 |
bugs | -0.589 |
affles | -0.584 |
bug | -0.567 |
ception | -0.555 |
Token | Con |
Token ID | 3103 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
azo | +1.682 |
affles | +1.623 |
bugs | +1.604 |
bug | +1.538 |
ception | +1.500 |
Neg logit contributions | |
Franch | -2.571 |
WD | -2.316 |
haar | -2.285 |
wd | -2.249 |
root | -2.215 |
Token | definitely |
Token ID | 4753 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Franch | +2.403 |
WD | +2.141 |
wd | +2.063 |
root | +2.037 |
haar | +2.035 |
Neg logit contributions | |
azo | -2.180 |
affles | -2.117 |
bugs | -2.106 |
bug | -2.021 |
ception | -1.952 |
Token | raises |
Token ID | 12073 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
azo | +1.699 |
affles | +1.640 |
bugs | +1.630 |
bug | +1.568 |
ception | +1.523 |
Neg logit contributions | |
Franch | -1.969 |
WD | -1.758 |
haar | -1.718 |
wd | -1.688 |
root | -1.670 |
Token | a |
Token ID | 257 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
azo | +2.978 |
affles | +2.853 |
bugs | +2.841 |
bug | +2.712 |
ception | +2.641 |
Neg logit contributions | |
Franch | -4.184 |
WD | -3.793 |
haar | -3.720 |
wd | -3.681 |
root | -3.581 |
Token | red |
Token ID | 2266 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
azo | +1.911 |
affles | +1.841 |
bugs | +1.833 |
bug | +1.770 |
ception | +1.729 |
Neg logit contributions | |
Franch | -2.319 |
WD | -2.081 |
haar | -2.028 |
wd | -2.012 |
root | -1.972 |
Token | flag |
Token ID | 6056 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
azo | +2.273 |
affles | +2.177 |
bugs | +2.161 |
bug | +2.095 |
ception | +2.033 |
Neg logit contributions | |
Franch | -3.204 |
WD | -2.875 |
haar | -2.808 |
wd | -2.777 |
root | -2.726 |
Token | when |
Token ID | 618 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
azo | +2.514 |
bugs | +2.433 |
affles | +2.431 |
bug | +2.348 |
ception | +2.275 |
Neg logit contributions | |
Franch | -2.988 |
WD | -2.683 |
haar | -2.608 |
wd | -2.589 |
root | -2.536 |
Token | it |
Token ID | 340 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
azo | +0.298 |
affles | +0.289 |
bugs | +0.287 |
bug | +0.276 |
ception | +0.269 |
Neg logit contributions | |
Franch | -0.307 |
WD | -0.273 |
haar | -0.266 |
wd | -0.263 |
root | -0.259 |
Token | rich |
Token ID | 7527 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
azo | +1.782 |
bugs | +1.719 |
affles | +1.719 |
bug | +1.663 |
ception | +1.612 |
Neg logit contributions | |
Franch | -1.812 |
WD | -1.612 |
haar | -1.553 |
wd | -1.535 |
root | -1.517 |
Token | von |
Token ID | 18042 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
azo | +0.171 |
affles | +0.164 |
bugs | +0.162 |
bug | +0.156 |
ception | +0.152 |
Neg logit contributions | |
Franch | -0.222 |
WD | -0.199 |
haar | -0.194 |
wd | -0.192 |
root | -0.190 |
Token | Viet |
Token ID | 8730 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
azo | +1.560 |
affles | +1.511 |
bugs | +1.505 |
bug | +1.449 |
ception | +1.409 |
Neg logit contributions | |
Franch | -1.724 |
WD | -1.544 |
haar | -1.492 |
wd | -1.485 |
root | -1.462 |
Token | ing |
Token ID | 278 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Franch | +0.510 |
WD | +0.453 |
haar | +0.441 |
wd | +0.435 |
root | +0.430 |
Neg logit contributions | |
azo | -0.497 |
affles | -0.483 |
bugs | -0.474 |
bug | -0.455 |
ception | -0.450 |
Token | hoff |
Token ID | 36092 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
azo | +0.084 |
affles | +0.081 |
bugs | +0.081 |
bug | +0.077 |
ception | +0.075 |
Neg logit contributions | |
Franch | -0.099 |
WD | -0.088 |
haar | -0.086 |
wd | -0.085 |
root | -0.084 |
Token | - |
Token ID | 12 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Franch | +2.044 |
WD | +1.824 |
haar | +1.778 |
wd | +1.758 |
root | +1.736 |
Neg logit contributions | |
azo | -1.775 |
affles | -1.735 |
bugs | -1.715 |
bug | -1.628 |
ception | -1.612 |
Token | Sche |
Token ID | 27054 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Franch | +0.482 |
WD | +0.431 |
haar | +0.418 |
wd | +0.415 |
root | +0.408 |
Neg logit contributions | |
azo | -0.438 |
affles | -0.423 |
bugs | -0.419 |
bug | -0.403 |
ception | -0.393 |
Token | el |
Token ID | 417 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
azo | +1.524 |
affles | +1.485 |
bugs | +1.473 |
bug | +1.425 |
ception | +1.389 |
Neg logit contributions | |
Franch | -1.416 |
WD | -1.244 |
haar | -1.201 |
wd | -1.184 |
root | -1.167 |
Token | signed |
Token ID | 4488 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Franch | +1.589 |
WD | +1.413 |
haar | +1.388 |
wd | +1.367 |
root | +1.349 |
Neg logit contributions | |
azo | -1.417 |
affles | -1.384 |
bugs | -1.362 |
bug | -1.299 |
ception | -1.283 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Franch | +0.246 |
WD | +0.217 |
haar | +0.211 |
wd | +0.209 |
root | +0.206 |
Neg logit contributions | |
azo | -0.225 |
affles | -0.219 |
bugs | -0.218 |
bug | -0.209 |
ception | -0.204 |
Token | unconditional |
Token ID | 42423 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Franch | +1.326 |
WD | +1.165 |
haar | +1.134 |
wd | +1.120 |
root | +1.105 |
Neg logit contributions | |
azo | -1.168 |
affles | -1.142 |
bugs | -1.138 |
bug | -1.090 |
ception | -1.054 |
Token | ange |
Token ID | 858 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Franch | +0.650 |
WD | +0.570 |
wd | +0.556 |
haar | +0.547 |
root | +0.546 |
Neg logit contributions | |
azo | -0.745 |
bugs | -0.728 |
affles | -0.714 |
bug | -0.700 |
ception | -0.678 |
Token | Cafe |
Token ID | 26965 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Franch | +0.351 |
WD | +0.312 |
haar | +0.301 |
wd | +0.301 |
root | +0.296 |
Neg logit contributions | |
azo | -0.315 |
affles | -0.304 |
bugs | -0.303 |
bug | -0.291 |
ception | -0.283 |
Token | , |
Token ID | 11 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Franch | +1.590 |
WD | +1.402 |
haar | +1.348 |
wd | +1.348 |
root | +1.330 |
Neg logit contributions | |
azo | -1.503 |
affles | -1.451 |
bugs | -1.451 |
bug | -1.391 |
ception | -1.354 |
Token | Sab |
Token ID | 9910 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Franch | +0.713 |
WD | +0.631 |
haar | +0.609 |
wd | +0.608 |
root | +0.599 |
Neg logit contributions | |
azo | -0.606 |
affles | -0.582 |
bugs | -0.581 |
bug | -0.555 |
ception | -0.541 |
Token | ine |
Token ID | 500 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Franch | +0.741 |
WD | +0.651 |
haar | +0.632 |
wd | +0.627 |
root | +0.619 |
Neg logit contributions | |
azo | -0.824 |
affles | -0.803 |
bugs | -0.801 |
bug | -0.772 |
ception | -0.752 |
Token | , |
Token ID | 11 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Franch | +0.867 |
WD | +0.759 |
haar | +0.732 |
wd | +0.732 |
root | +0.725 |
Neg logit contributions | |
azo | -0.873 |
affles | -0.847 |
bugs | -0.841 |
bug | -0.808 |
ception | -0.790 |
Token | Chef |
Token ID | 26383 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Franch | +0.576 |
WD | +0.509 |
haar | +0.491 |
wd | +0.491 |
root | +0.485 |
Neg logit contributions | |
azo | -0.482 |
affles | -0.464 |
bugs | -0.462 |
bug | -0.442 |
ception | -0.431 |
Token | G |
Token ID | 402 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Franch | +1.889 |
WD | +1.666 |
wd | +1.607 |
haar | +1.602 |
root | +1.598 |
Neg logit contributions | |
azo | -1.696 |
affles | -1.639 |
bugs | -1.624 |
bug | -1.548 |
ception | -1.521 |
Token | .' |
Token ID | 2637 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Franch | +0.996 |
WD | +0.881 |
haar | +0.850 |
wd | +0.846 |
root | +0.837 |
Neg logit contributions | |
azo | -1.008 |
affles | -0.977 |
bugs | -0.976 |
bug | -0.936 |
ception | -0.918 |
Token | s |
Token ID | 82 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
azo | +0.330 |
affles | +0.319 |
bugs | +0.317 |
bug | +0.305 |
ception | +0.296 |
Neg logit contributions | |
Franch | -0.371 |
WD | -0.331 |
haar | -0.321 |
wd | -0.319 |
root | -0.314 |
Token | , |
Token ID | 11 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
azo | +0.335 |
affles | +0.324 |
bugs | +0.322 |
bug | +0.309 |
ception | +0.300 |
Neg logit contributions | |
Franch | -0.397 |
WD | -0.354 |
haar | -0.344 |
wd | -0.342 |
root | -0.337 |
Token | ++ |
Token ID | 19969 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Franch | +0.617 |
WD | +0.554 |
haar | +0.538 |
wd | +0.537 |
root | +0.533 |
Neg logit contributions | |
azo | -0.477 |
affles | -0.465 |
bugs | -0.458 |
bug | -0.437 |
ception | -0.426 |
Token | u |
Token ID | 334 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Franch | +1.042 |
WD | +0.953 |
wd | +0.931 |
haar | +0.929 |
root | +0.926 |
Neg logit contributions | |
azo | -0.593 |
affles | -0.579 |
bugs | -0.564 |
bug | -0.530 |
ception | -0.519 |
Token | Part |
Token ID | 7841 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
Franch | +1.999 |
WD | +1.766 |
wd | +1.694 |
haar | +1.688 |
root | +1.674 |
Neg logit contributions | |
azo | -2.273 |
affles | -2.218 |
bugs | -2.189 |
bug | -2.104 |
ception | -2.057 |
Token | icle |
Token ID | 1548 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Franch | +2.366 |
WD | +2.143 |
haar | +2.102 |
wd | +2.079 |
root | +2.071 |
Neg logit contributions | |
azo | -1.853 |
affles | -1.813 |
bugs | -1.788 |
bug | -1.696 |
ception | -1.650 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
Franch | +0.811 |
WD | +0.718 |
wd | +0.691 |
haar | +0.690 |
root | +0.683 |
Neg logit contributions | |
azo | -0.863 |
affles | -0.843 |
bugs | -0.831 |
bug | -0.799 |
ception | -0.785 |
Token | { |
Token ID | 1391 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Franch | +3.292 |
WD | +2.857 |
wd | +2.750 |
root | +2.739 |
haar | +2.732 |
Neg logit contributions | |
azo | -3.618 |
affles | -3.525 |
bugs | -3.488 |
bug | -3.361 |
ception | -3.280 |
Token | // |
Token ID | 3373 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
Franch | +1.096 |
WD | +0.963 |
haar | +0.927 |
wd | +0.926 |
root | +0.918 |
Neg logit contributions | |
azo | -1.143 |
affles | -1.112 |
bugs | -1.100 |
bug | -1.059 |
ception | -1.032 |
Token | For |
Token ID | 1114 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
azo | +0.049 |
affles | +0.047 |
bugs | +0.047 |
bug | +0.045 |
ception | +0.044 |
Neg logit contributions | |
Franch | -0.051 |
WD | -0.046 |
haar | -0.044 |
wd | -0.044 |
root | -0.043 |
Token | each |
Token ID | 1123 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
azo | +0.053 |
affles | +0.051 |
bugs | +0.051 |
bug | +0.049 |
ception | +0.047 |
Neg logit contributions | |
Franch | -0.064 |
WD | -0.058 |
haar | -0.056 |
wd | -0.056 |
root | -0.055 |
Token | particle |
Token ID | 18758 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Franch | +0.730 |
WD | +0.634 |
haar | +0.612 |
wd | +0.606 |
root | +0.596 |
Neg logit contributions | |
azo | -0.927 |
affles | -0.903 |
bugs | -0.898 |
bug | -0.868 |
ception | -0.848 |
Token | in |
Token ID | 287 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Franch | +3.087 |
WD | +2.719 |
haar | +2.643 |
root | +2.630 |
wd | +2.628 |
Neg logit contributions | |
azo | -3.003 |
affles | -2.926 |
bugs | -2.884 |
bug | -2.762 |
ception | -2.691 |
Token | by |
Token ID | 416 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
azo | +0.951 |
affles | +0.925 |
bugs | +0.918 |
bug | +0.885 |
ception | +0.863 |
Neg logit contributions | |
Franch | -0.984 |
WD | -0.872 |
haar | -0.848 |
wd | -0.839 |
root | -0.826 |
Token | comparing |
Token ID | 14176 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Franch | +0.086 |
WD | +0.075 |
haar | +0.073 |
wd | +0.072 |
root | +0.071 |
Neg logit contributions | |
azo | -0.094 |
affles | -0.091 |
bugs | -0.090 |
bug | -0.087 |
ception | -0.085 |
Token | him |
Token ID | 683 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
azo | +0.583 |
affles | +0.558 |
bugs | +0.554 |
bug | +0.525 |
ception | +0.506 |
Neg logit contributions | |
Franch | -1.038 |
WD | -0.944 |
haar | -0.921 |
wd | -0.916 |
root | -0.906 |
Token | to |
Token ID | 284 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
azo | +0.119 |
affles | +0.115 |
bugs | +0.113 |
bug | +0.109 |
ception | +0.105 |
Neg logit contributions | |
Franch | -0.161 |
WD | -0.145 |
haar | -0.141 |
wd | -0.140 |
root | -0.138 |
Token | Barry |
Token ID | 14488 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Franch | +0.593 |
WD | +0.521 |
haar | +0.503 |
wd | +0.499 |
root | +0.493 |
Neg logit contributions | |
azo | -0.607 |
affles | -0.588 |
bugs | -0.585 |
bug | -0.565 |
ception | -0.549 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
azo | +1.091 |
affles | +1.057 |
bugs | +1.050 |
bug | +1.013 |
ception | +0.986 |
Neg logit contributions | |
Franch | -1.158 |
WD | -1.031 |
haar | -1.000 |
wd | -0.991 |
root | -0.975 |
Token | . |
Token ID | 13 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
Franch | +0.301 |
WD | +0.267 |
haar | +0.259 |
wd | +0.257 |
root | +0.252 |
Neg logit contributions | |
azo | -0.297 |
affles | -0.288 |
bugs | -0.286 |
bug | -0.276 |
ception | -0.269 |
Token | Said |
Token ID | 23885 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
azo | +0.551 |
affles | +0.530 |
bugs | +0.526 |
bug | +0.505 |
ception | +0.490 |
Neg logit contributions | |
Franch | -0.686 |
WD | -0.614 |
haar | -0.595 |
wd | -0.592 |
root | -0.584 |
Token | South |
Token ID | 2520 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
azo | +0.166 |
affles | +0.158 |
bugs | +0.157 |
bug | +0.148 |
ception | +0.143 |
Neg logit contributions | |
Franch | -0.319 |
WD | -0.291 |
haar | -0.284 |
wd | -0.283 |
root | -0.280 |
Token | Carolina |
Token ID | 5913 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
azo | +1.420 |
affles | +1.371 |
bugs | +1.370 |
bug | +1.321 |
ception | +1.280 |
Neg logit contributions | |
Franch | -1.413 |
WD | -1.244 |
haar | -1.232 |
wd | -1.205 |
root | -1.182 |
Token | coach |
Token ID | 3985 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
azo | +0.725 |
affles | +0.701 |
bugs | +0.697 |
bug | +0.671 |
ception | +0.653 |
Neg logit contributions | |
Franch | -0.817 |
WD | -0.729 |
haar | -0.711 |
wd | -0.703 |
root | -0.692 |
Token | decide |
Token ID | 5409 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
Franch | +0.841 |
WD | +0.743 |
haar | +0.718 |
wd | +0.716 |
root | +0.706 |
Neg logit contributions | |
azo | -0.787 |
affles | -0.766 |
bugs | -0.756 |
bug | -0.726 |
ception | -0.712 |
Token | almost |
Token ID | 2048 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
azo | +0.449 |
affles | +0.434 |
bugs | +0.431 |
bug | +0.414 |
ception | +0.403 |
Neg logit contributions | |
Franch | -0.518 |
WD | -0.463 |
haar | -0.450 |
wd | -0.446 |
root | -0.439 |
Token | immediately |
Token ID | 3393 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
Franch | +1.407 |
WD | +1.261 |
haar | +1.223 |
wd | +1.217 |
root | +1.208 |
Neg logit contributions | |
azo | -1.125 |
affles | -1.079 |
bugs | -1.075 |
bug | -1.028 |
ception | -0.997 |
Token | into |
Token ID | 656 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
azo | +0.662 |
affles | +0.639 |
bugs | +0.636 |
bug | +0.611 |
ception | +0.593 |
Neg logit contributions | |
Franch | -0.768 |
WD | -0.687 |
haar | -0.668 |
wd | -0.662 |
root | -0.652 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
azo | +0.062 |
affles | +0.060 |
bugs | +0.060 |
bug | +0.057 |
ception | +0.056 |
Neg logit contributions | |
Franch | -0.074 |
WD | -0.066 |
haar | -0.064 |
wd | -0.064 |
root | -0.063 |
Token | offseason |
Token ID | 16349 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
azo | +0.036 |
affles | +0.035 |
bugs | +0.035 |
bug | +0.034 |
ception | +0.033 |
Neg logit contributions | |
Franch | -0.037 |
WD | -0.032 |
haar | -0.031 |
wd | -0.031 |
root | -0.031 |
Token | whether |
Token ID | 1771 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Franch | +0.249 |
WD | +0.221 |
haar | +0.215 |
wd | +0.213 |
root | +0.210 |
Neg logit contributions | |
azo | -0.220 |
affles | -0.213 |
bugs | -0.211 |
bug | -0.203 |
ception | -0.198 |
Token | they |
Token ID | 484 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
azo | +2.424 |
affles | +2.339 |
bugs | +2.324 |
bug | +2.226 |
ception | +2.142 |
Neg logit contributions | |
Franch | -3.343 |
WD | -3.050 |
haar | -2.990 |
wd | -2.944 |
root | -2.905 |
Token | 're |
Token ID | 821 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
azo | +1.397 |
affles | +1.342 |
bugs | +1.338 |
bug | +1.287 |
ception | +1.237 |
Neg logit contributions | |
Franch | -1.804 |
WD | -1.622 |
haar | -1.586 |
wd | -1.564 |
root | -1.543 |
Token | interested |
Token ID | 4609 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
azo | +1.312 |
affles | +1.272 |
bugs | +1.265 |
bug | +1.220 |
ception | +1.189 |
Neg logit contributions | |
Franch | -1.286 |
WD | -1.138 |
haar | -1.103 |
wd | -1.093 |
root | -1.075 |
Token | in |
Token ID | 287 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
azo | +0.254 |
affles | +0.244 |
bugs | +0.242 |
bug | +0.232 |
ception | +0.225 |
Neg logit contributions | |
Franch | -0.364 |
WD | -0.329 |
haar | -0.319 |
wd | -0.318 |
root | -0.314 |
Token | than |
Token ID | 621 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Franch | +0.226 |
WD | +0.199 |
wd | +0.191 |
haar | +0.190 |
root | +0.186 |
Neg logit contributions | |
azo | -0.259 |
affles | -0.251 |
bugs | -0.248 |
bug | -0.240 |
ception | -0.235 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
azo | +1.276 |
affles | +1.238 |
bugs | +1.231 |
bug | +1.188 |
ception | +1.157 |
Neg logit contributions | |
Franch | -1.290 |
WD | -1.145 |
haar | -1.113 |
wd | -1.102 |
root | -1.082 |
Token | probably |
Token ID | 2192 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Franch | +0.299 |
WD | +0.265 |
haar | +0.256 |
wd | +0.255 |
root | +0.252 |
Neg logit contributions | |
azo | -0.282 |
affles | -0.272 |
bugs | -0.270 |
bug | -0.259 |
ception | -0.253 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
azo | +1.540 |
affles | +1.492 |
bugs | +1.484 |
bug | +1.431 |
ception | +1.395 |
Neg logit contributions | |
Franch | -1.530 |
WD | -1.355 |
haar | -1.314 |
wd | -1.302 |
root | -1.281 |
Token | a |
Token ID | 257 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
azo | +1.647 |
affles | +1.595 |
bugs | +1.590 |
bug | +1.532 |
ception | +1.490 |
Neg logit contributions | |
Franch | -1.812 |
WD | -1.619 |
haar | -1.576 |
wd | -1.559 |
root | -1.531 |
Token | mid |
Token ID | 3095 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Franch | +0.002 |
WD | +0.002 |
haar | +0.002 |
wd | +0.002 |
root | +0.002 |
Neg logit contributions | |
azo | -0.002 |
affles | -0.002 |
bugs | -0.002 |
bug | -0.002 |
ception | -0.002 |
Token | - |
Token ID | 12 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Franch | +3.251 |
WD | +2.920 |
root | +2.857 |
wd | +2.833 |
haar | +2.814 |
Neg logit contributions | |
affles | -3.174 |
azo | -3.099 |
bugs | -3.012 |
bug | -2.879 |
haps | -2.818 |
Token | April |
Token ID | 16784 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Franch | +1.089 |
WD | +0.958 |
wd | +0.915 |
haar | +0.911 |
root | +0.908 |
Neg logit contributions | |
azo | -1.442 |
affles | -1.413 |
bugs | -1.387 |
bug | -1.339 |
ception | -1.318 |
Token | launch |
Token ID | 4219 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Franch | +1.449 |
WD | +1.300 |
wd | +1.256 |
haar | +1.245 |
root | +1.233 |
Neg logit contributions | |
azo | -1.350 |
affles | -1.322 |
bugs | -1.290 |
bug | -1.225 |
ception | -1.212 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Franch | +1.192 |
WD | +1.081 |
wd | +1.043 |
haar | +1.037 |
root | +1.025 |
Neg logit contributions | |
azo | -0.979 |
affles | -0.950 |
bugs | -0.935 |
bug | -0.889 |
ception | -0.867 |
Token | � |
Token ID | 447 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Franch | +0.190 |
WD | +0.168 |
haar | +0.161 |
wd | +0.161 |
root | +0.159 |
Neg logit contributions | |
azo | -0.188 |
affles | -0.182 |
bugs | -0.180 |
bug | -0.173 |
ception | -0.169 |
Token | ation |
Token ID | 341 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
Franch | +2.365 |
WD | +2.110 |
haar | +2.057 |
wd | +2.056 |
root | +2.001 |
Neg logit contributions | |
azo | -2.076 |
affles | -2.033 |
bugs | -2.009 |
bug | -1.924 |
ception | -1.839 |
Token | we |
Token ID | 356 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
Franch | +2.998 |
WD | +2.647 |
haar | +2.563 |
wd | +2.550 |
root | +2.543 |
Neg logit contributions | |
azo | -2.842 |
affles | -2.759 |
bugs | -2.690 |
bug | -2.579 |
ception | -2.543 |
Token | are |
Token ID | 389 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Franch | +0.474 |
WD | +0.422 |
haar | +0.410 |
wd | +0.406 |
root | +0.401 |
Neg logit contributions | |
azo | -0.442 |
affles | -0.428 |
bugs | -0.425 |
bug | -0.408 |
ception | -0.399 |
Token | about |
Token ID | 546 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Franch | +1.086 |
WD | +0.972 |
haar | +0.942 |
wd | +0.936 |
root | +0.921 |
Neg logit contributions | |
azo | -0.993 |
affles | -0.972 |
bugs | -0.952 |
bug | -0.912 |
ception | -0.894 |
Token | to |
Token ID | 284 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Franch | +0.238 |
WD | +0.215 |
haar | +0.210 |
wd | +0.209 |
root | +0.206 |
Neg logit contributions | |
azo | -0.177 |
affles | -0.171 |
bugs | -0.169 |
bug | -0.161 |
ception | -0.157 |
Token | birth |
Token ID | 4082 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
Franch | +2.588 |
WD | +2.296 |
haar | +2.189 |
root | +2.187 |
wd | +2.176 |
Neg logit contributions | |
azo | -2.779 |
affles | -2.763 |
bugs | -2.701 |
bug | -2.569 |
ception | -2.540 |
Token | upon |
Token ID | 2402 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Franch | +4.805 |
WD | +4.288 |
root | +4.201 |
haar | +4.198 |
wd | +4.154 |
Neg logit contributions | |
azo | -4.727 |
affles | -4.576 |
bugs | -4.457 |
bug | -4.255 |
ception | -4.189 |
Token | you |
Token ID | 345 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
Franch | +2.768 |
WD | +2.429 |
haar | +2.374 |
wd | +2.358 |
root | +2.349 |
Neg logit contributions | |
azo | -2.477 |
affles | -2.387 |
bugs | -2.360 |
bug | -2.257 |
ception | -2.195 |
Token | will |
Token ID | 481 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Franch | +0.586 |
WD | +0.520 |
haar | +0.506 |
wd | +0.503 |
root | +0.497 |
Neg logit contributions | |
azo | -0.529 |
affles | -0.513 |
bugs | -0.505 |
bug | -0.485 |
ception | -0.474 |
Token | no |
Token ID | 645 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
azo | +0.320 |
affles | +0.309 |
bugs | +0.307 |
bug | +0.294 |
ception | +0.286 |
Neg logit contributions | |
Franch | -0.397 |
WD | -0.356 |
haar | -0.346 |
wd | -0.343 |
root | -0.338 |
Token | doubt |
Token ID | 4719 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
azo | +1.613 |
affles | +1.568 |
bugs | +1.558 |
bug | +1.505 |
ception | +1.463 |
Neg logit contributions | |
Franch | -1.571 |
WD | -1.388 |
haar | -1.346 |
wd | -1.331 |
root | -1.309 |
Token | ." |
Token ID | 526 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
azo | +0.495 |
affles | +0.477 |
bugs | +0.474 |
bug | +0.453 |
ception | +0.439 |
Neg logit contributions | |
Franch | -0.685 |
WD | -0.618 |
haar | -0.602 |
wd | -0.597 |
root | -0.589 |
Token | Yes |
Token ID | 3363 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Franch | +1.065 |
WD | +0.941 |
wd | +0.908 |
haar | +0.903 |
root | +0.894 |
Neg logit contributions | |
azo | -0.964 |
affles | -0.929 |
bugs | -0.923 |
bug | -0.885 |
ception | -0.859 |
Token | , |
Token ID | 11 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
Franch | +1.407 |
WD | +1.248 |
haar | +1.207 |
wd | +1.199 |
root | +1.177 |
Neg logit contributions | |
azo | -1.478 |
affles | -1.434 |
bugs | -1.425 |
bug | -1.373 |
ception | -1.341 |
Token | they |
Token ID | 484 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
azo | +0.316 |
affles | +0.306 |
bugs | +0.304 |
bug | +0.292 |
ception | +0.284 |
Neg logit contributions | |
Franch | -0.361 |
WD | -0.323 |
haar | -0.314 |
wd | -0.311 |
root | -0.306 |
Token | will |
Token ID | 481 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
Franch | +2.009 |
WD | +1.791 |
wd | +1.731 |
haar | +1.729 |
root | +1.698 |
Neg logit contributions | |
azo | -1.963 |
affles | -1.914 |
bugs | -1.893 |
bug | -1.813 |
ception | -1.785 |
Token | learn |
Token ID | 2193 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
Franch | +2.169 |
WD | +1.927 |
wd | +1.875 |
haar | +1.857 |
root | +1.839 |
Neg logit contributions | |
azo | -2.013 |
affles | -1.974 |
bugs | -1.944 |
bug | -1.856 |
ception | -1.820 |
Token | language |
Token ID | 3303 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
Franch | +3.645 |
WD | +3.203 |
wd | +3.110 |
haar | +3.070 |
root | +3.057 |
Neg logit contributions | |
azo | -3.282 |
affles | -3.137 |
bugs | -3.123 |
bug | -2.984 |
ception | -2.918 |
Token | arts |
Token ID | 10848 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Franch | +2.236 |
WD | +1.984 |
wd | +1.900 |
haar | +1.887 |
root | +1.867 |
Neg logit contributions | |
azo | -2.392 |
affles | -2.294 |
bugs | -2.274 |
bug | -2.180 |
ception | -2.149 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Franch | +1.052 |
WD | +0.934 |
haar | +0.902 |
wd | +0.900 |
root | +0.884 |
Neg logit contributions | |
azo | -1.072 |
affles | -1.036 |
bugs | -1.028 |
bug | -0.990 |
ception | -0.968 |
Token | But |
Token ID | 887 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Franch | +0.829 |
WD | +0.731 |
haar | +0.704 |
wd | +0.704 |
root | +0.693 |
Neg logit contributions | |
azo | -0.817 |
affles | -0.791 |
bugs | -0.784 |
bug | -0.753 |
ception | -0.735 |
Token | basic |
Token ID | 4096 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
Franch | +1.647 |
WD | +1.464 |
wd | +1.418 |
haar | +1.409 |
root | +1.391 |
Neg logit contributions | |
azo | -1.463 |
affles | -1.416 |
bugs | -1.404 |
bug | -1.349 |
ception | -1.312 |
Token | an |
Token ID | 281 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
Franch | +0.903 |
WD | +0.798 |
haar | +0.772 |
wd | +0.765 |
root | +0.754 |
Neg logit contributions | |
azo | -0.943 |
affles | -0.914 |
bugs | -0.910 |
bug | -0.877 |
ception | -0.855 |
Token | engineer |
Token ID | 11949 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Franch | +0.046 |
WD | +0.041 |
haar | +0.040 |
wd | +0.040 |
root | +0.039 |
Neg logit contributions | |
azo | -0.043 |
affles | -0.042 |
bugs | -0.042 |
bug | -0.040 |
ception | -0.039 |
Token | in |
Token ID | 287 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
Franch | +1.811 |
WD | +1.603 |
wd | +1.540 |
haar | +1.537 |
root | +1.523 |
Neg logit contributions | |
azo | -1.832 |
affles | -1.770 |
bugs | -1.754 |
bug | -1.680 |
ception | -1.640 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Franch | +0.577 |
WD | +0.516 |
haar | +0.502 |
wd | +0.497 |
root | +0.491 |
Neg logit contributions | |
azo | -0.471 |
affles | -0.455 |
bugs | -0.453 |
bug | -0.434 |
ception | -0.421 |
Token | Space |
Token ID | 4687 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
Franch | +1.244 |
WD | +1.105 |
haar | +1.072 |
wd | +1.062 |
root | +1.046 |
Neg logit contributions | |
azo | -1.154 |
affles | -1.117 |
bugs | -1.112 |
bug | -1.068 |
ception | -1.039 |
Token | Physics |
Token ID | 23123 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
Franch | +2.349 |
WD | +2.092 |
haar | +2.016 |
wd | +1.992 |
root | +1.980 |
Neg logit contributions | |
azo | -2.186 |
affles | -2.127 |
bugs | -2.093 |
bug | -1.996 |
ception | -1.955 |
Token | Research |
Token ID | 4992 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Franch | +3.376 |
WD | +2.937 |
wd | +2.797 |
haar | +2.789 |
root | +2.748 |
Neg logit contributions | |
azo | -3.433 |
affles | -3.382 |
bugs | -3.311 |
bug | -3.183 |
ception | -3.080 |
Token | Laboratory |
Token ID | 18643 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Franch | +0.804 |
WD | +0.706 |
haar | +0.680 |
wd | +0.674 |
root | +0.664 |
Neg logit contributions | |
azo | -0.844 |
affles | -0.821 |
bugs | -0.813 |
bug | -0.784 |
ception | -0.763 |
Token | who |
Token ID | 508 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Franch | +2.053 |
WD | +1.820 |
haar | +1.753 |
wd | +1.741 |
root | +1.717 |
Neg logit contributions | |
azo | -2.034 |
affles | -1.970 |
bugs | -1.956 |
bug | -1.880 |
ception | -1.836 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
azo | +0.371 |
affles | +0.359 |
bugs | +0.357 |
bug | +0.343 |
ception | +0.334 |
Neg logit contributions | |
Franch | -0.406 |
WD | -0.361 |
haar | -0.351 |
wd | -0.348 |
root | -0.342 |
Token | with |
Token ID | 351 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Franch | +1.136 |
WD | +0.995 |
haar | +0.957 |
wd | +0.948 |
root | +0.935 |
Neg logit contributions | |
azo | -1.349 |
affles | -1.308 |
bugs | -1.298 |
bug | -1.253 |
ception | -1.226 |
Token | [ |
Token ID | 685 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Franch | +0.189 |
WD | +0.169 |
haar | +0.164 |
wd | +0.163 |
root | +0.160 |
Neg logit contributions | |
azo | -0.174 |
affles | -0.169 |
bugs | -0.168 |
bug | -0.161 |
ception | -0.157 |
Token | text |
Token ID | 5239 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
azo | +0.806 |
affles | +0.780 |
bugs | +0.778 |
bug | +0.754 |
ception | +0.734 |
Neg logit contributions | |
Franch | -0.746 |
WD | -0.651 |
haar | -0.634 |
wd | -0.623 |
root | -0.610 |
Token | ] |
Token ID | 60 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Franch | +2.566 |
WD | +2.345 |
wd | +2.289 |
haar | +2.265 |
root | +2.263 |
Neg logit contributions | |
azo | -1.993 |
affles | -1.919 |
bugs | -1.892 |
bug | -1.810 |
ception | -1.751 |
Token | { |
Token ID | 90 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
azo | +0.144 |
affles | +0.139 |
bugs | +0.138 |
bug | +0.133 |
ception | +0.129 |
Neg logit contributions | |
Franch | -0.161 |
WD | -0.144 |
haar | -0.140 |
wd | -0.139 |
root | -0.137 |
Token | white |
Token ID | 11186 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Franch | +0.111 |
WD | +0.098 |
haar | +0.094 |
wd | +0.093 |
root | +0.092 |
Neg logit contributions | |
azo | -0.133 |
affles | -0.129 |
bugs | -0.128 |
bug | -0.124 |
ception | -0.121 |
Token | }{ |
Token ID | 18477 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
azo | +1.438 |
bugs | +1.388 |
affles | +1.388 |
bug | +1.340 |
ception | +1.306 |
Neg logit contributions | |
Franch | -1.529 |
WD | -1.344 |
haar | -1.309 |
wd | -1.290 |
root | -1.265 |
Token | vi |
Token ID | 8903 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Franch | +3.992 |
WD | +3.710 |
root | +3.649 |
wd | +3.629 |
haar | +3.584 |
Neg logit contributions | |
azo | -3.398 |
affles | -3.289 |
bugs | -3.223 |
bug | -3.043 |
ception | -3.031 |
Token | : |
Token ID | 25 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Franch | +1.815 |
WD | +1.638 |
wd | +1.582 |
haar | +1.572 |
root | +1.552 |
Neg logit contributions | |
azo | -1.883 |
affles | -1.837 |
bugs | -1.817 |
bug | -1.746 |
ception | -1.696 |
Token | | |
Token ID | 91 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Franch | +1.381 |
WD | +1.240 |
wd | +1.199 |
haar | +1.189 |
root | +1.182 |
Neg logit contributions | |
azo | -1.455 |
affles | -1.409 |
bugs | -1.398 |
bug | -1.342 |
ception | -1.313 |
Token | vim |
Token ID | 31124 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Franch | +1.938 |
WD | +1.751 |
wd | +1.706 |
haar | +1.684 |
root | +1.680 |
Neg logit contributions | |
azo | -1.921 |
affles | -1.857 |
bugs | -1.836 |
bug | -1.760 |
ception | -1.718 |
Token | : |
Token ID | 25 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
azo | +1.275 |
affles | +1.232 |
bugs | +1.227 |
bug | +1.185 |
ception | +1.158 |
Neg logit contributions | |
Franch | -1.395 |
WD | -1.231 |
haar | -1.200 |
wd | -1.178 |
root | -1.162 |