Token | 2011 |
Token ID | 2813 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
BW | +0.312 |
bons | +0.268 |
nb | +0.267 |
ciating | +0.265 |
Moz | +0.264 |
Neg logit contributions | |
Eng | -0.285 |
millenn | -0.253 |
Gar | -0.249 |
BUG | -0.242 |
cel | -0.241 |
Token | United |
Token ID | 1578 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
BW | +1.535 |
bons | +1.283 |
nb | +1.279 |
ciating | +1.273 |
Moz | +1.264 |
Neg logit contributions | |
Eng | -1.916 |
millenn | -1.738 |
Gar | -1.708 |
BUG | -1.667 |
cel | -1.659 |
Token | States |
Token ID | 1829 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
BW | +0.562 |
bons | +0.471 |
nb | +0.467 |
ciating | +0.467 |
Moz | +0.454 |
Neg logit contributions | |
Eng | -0.819 |
millenn | -0.737 |
Gar | -0.735 |
cel | -0.716 |
BUG | -0.715 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
BW | +2.799 |
Moz | +2.297 |
bons | +2.281 |
nb | +2.278 |
McAuliffe | +2.246 |
Neg logit contributions | |
Eng | -3.352 |
millenn | -3.182 |
Gar | -2.989 |
BUG | -2.944 |
Frameworks | -2.907 |
Token | 12 |
Token ID | 1065 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
BW | +2.338 |
nb | +2.023 |
bons | +2.019 |
ciating | +2.002 |
Moz | +1.979 |
Neg logit contributions | |
Eng | -2.172 |
millenn | -1.973 |
Gar | -1.895 |
BUG | -1.844 |
cel | -1.837 |
Token | Posts |
Token ID | 12043 |
Feature activation | +9.31e+00 |
Pos logit contributions | |
BW | +0.545 |
nb | +0.413 |
bons | +0.412 |
Moz | +0.398 |
ciating | +0.397 |
Neg logit contributions | |
Eng | -1.293 |
millenn | -1.219 |
Gar | -1.183 |
cel | -1.160 |
BUG | -1.158 |
Token | # |
Token ID | 1303 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
BW | +5.245 |
Moz | +4.130 |
nb | +4.119 |
ciating | +4.051 |
bons | +4.047 |
Neg logit contributions | |
Eng | -8.412 |
millenn | -7.641 |
Gar | -7.620 |
BUG | -7.488 |
erness | -7.432 |
Token | 17 |
Token ID | 1558 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
BW | +4.301 |
nb | +3.802 |
bons | +3.783 |
Moz | +3.529 |
boo | +3.439 |
Neg logit contributions | |
millenn | -4.771 |
Eng | -4.157 |
enthusi | -4.117 |
atism | -3.820 |
aminer | -3.806 |
Token | Good |
Token ID | 4599 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
BW | +0.563 |
bons | +0.488 |
nb | +0.487 |
ciating | +0.486 |
Moz | +0.479 |
Neg logit contributions | |
Eng | -0.479 |
millenn | -0.420 |
Gar | -0.415 |
BUG | -0.403 |
cel | -0.400 |
Token | to |
Token ID | 284 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
BW | +0.274 |
ciating | +0.238 |
bons | +0.237 |
nb | +0.236 |
Moz | +0.232 |
Neg logit contributions | |
Eng | -0.255 |
millenn | -0.223 |
Gar | -0.222 |
BUG | -0.216 |
cel | -0.215 |
Token | hear |
Token ID | 3285 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Eng | +1.164 |
Gar | +1.015 |
millenn | +1.006 |
cel | +0.982 |
BUG | +0.980 |
Neg logit contributions | |
BW | -1.261 |
ciating | -1.112 |
bons | -1.103 |
nb | -1.091 |
Moz | -1.074 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
BW | +1.503 |
bons | +1.295 |
nb | +1.291 |
Moz | +1.282 |
ciating | +1.278 |
Neg logit contributions | |
Eng | -1.273 |
millenn | -1.141 |
Gar | -1.105 |
BUG | -1.078 |
cel | -1.066 |
Token | United |
Token ID | 1578 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
BW | +1.759 |
bons | +1.468 |
nb | +1.463 |
ciating | +1.453 |
Moz | +1.451 |
Neg logit contributions | |
Eng | -2.193 |
millenn | -1.997 |
Gar | -1.956 |
BUG | -1.914 |
cel | -1.899 |
Token | States |
Token ID | 1829 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
BW | +0.393 |
bons | +0.329 |
ciating | +0.327 |
nb | +0.326 |
Moz | +0.317 |
Neg logit contributions | |
Eng | -0.581 |
millenn | -0.522 |
Gar | -0.521 |
cel | -0.508 |
BUG | -0.506 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
BW | +2.758 |
Moz | +2.266 |
nb | +2.251 |
bons | +2.250 |
McAuliffe | +2.208 |
Neg logit contributions | |
Eng | -3.308 |
millenn | -3.129 |
Gar | -2.949 |
BUG | -2.909 |
Frameworks | -2.864 |
Token | 53 |
Token ID | 4310 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
BW | +2.046 |
nb | +1.775 |
bons | +1.771 |
ciating | +1.750 |
Moz | +1.747 |
Neg logit contributions | |
Eng | -1.761 |
millenn | -1.596 |
Gar | -1.531 |
BUG | -1.490 |
cel | -1.481 |
Token | Posts |
Token ID | 12043 |
Feature activation | +9.00e+00 |
Pos logit contributions | |
BW | +0.159 |
bons | +0.116 |
nb | +0.115 |
ciating | +0.110 |
Moz | +0.110 |
Neg logit contributions | |
Eng | -0.443 |
millenn | -0.420 |
Gar | -0.406 |
BUG | -0.399 |
cel | -0.399 |
Token | # |
Token ID | 1303 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
BW | +5.398 |
Moz | +4.311 |
nb | +4.306 |
bons | +4.236 |
ciating | +4.232 |
Neg logit contributions | |
Eng | -7.829 |
millenn | -7.125 |
Gar | -7.099 |
BUG | -6.951 |
erness | -6.883 |
Token | 15 |
Token ID | 1314 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
BW | +3.866 |
bons | +3.540 |
nb | +3.479 |
nai | +3.097 |
Moz | +2.988 |
Neg logit contributions | |
millenn | -5.989 |
enthusi | -5.281 |
Eng | -4.808 |
hemor | -4.730 |
atism | -4.557 |
Token | honestly |
Token ID | 12698 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
BW | +0.329 |
bons | +0.287 |
ciating | +0.286 |
nb | +0.286 |
Moz | +0.281 |
Neg logit contributions | |
Eng | -0.267 |
millenn | -0.233 |
Gar | -0.231 |
BUG | -0.223 |
cel | -0.222 |
Token | if |
Token ID | 611 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
BW | +0.977 |
bons | +0.838 |
nb | +0.838 |
ciating | +0.834 |
Moz | +0.825 |
Neg logit contributions | |
Eng | -0.878 |
millenn | -0.776 |
Gar | -0.764 |
BUG | -0.745 |
cel | -0.734 |
Token | we |
Token ID | 356 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
BW | +1.094 |
bons | +0.930 |
nb | +0.928 |
ciating | +0.925 |
Moz | +0.915 |
Neg logit contributions | |
Eng | -1.065 |
millenn | -0.947 |
Gar | -0.935 |
BUG | -0.912 |
cel | -0.900 |
Token | June |
Token ID | 2795 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
BW | +3.411 |
Moz | +2.799 |
nb | +2.759 |
bons | +2.743 |
Grounds | +2.684 |
Neg logit contributions | |
Eng | -4.285 |
millenn | -4.142 |
Gar | -3.839 |
atism | -3.785 |
BUG | -3.750 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
BW | +1.109 |
bons | +0.950 |
nb | +0.949 |
Moz | +0.942 |
ciating | +0.935 |
Neg logit contributions | |
Eng | -0.965 |
millenn | -0.871 |
Gar | -0.842 |
BUG | -0.818 |
cel | -0.810 |
Token | Canada |
Token ID | 3340 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
BW | +1.204 |
bons | +1.013 |
ciating | +1.011 |
nb | +1.010 |
Moz | +0.991 |
Neg logit contributions | |
Eng | -1.492 |
millenn | -1.338 |
Gar | -1.328 |
BUG | -1.294 |
cel | -1.290 |
Token | 16 |
Token ID | 1467 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
BW | +0.980 |
nb | +0.820 |
bons | +0.817 |
Moz | +0.812 |
ciating | +0.804 |
Neg logit contributions | |
Eng | -1.126 |
millenn | -1.035 |
Gar | -1.002 |
BUG | -0.981 |
cel | -0.971 |
Token | 10 |
Token ID | 940 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
BW | +2.371 |
nb | +2.056 |
bons | +2.045 |
Moz | +2.020 |
ciating | +2.014 |
Neg logit contributions | |
Eng | -2.040 |
millenn | -1.881 |
Gar | -1.776 |
BUG | -1.725 |
cel | -1.720 |
Token | Posts |
Token ID | 12043 |
Feature activation | +8.84e+00 |
Pos logit contributions | |
Eng | +0.841 |
millenn | +0.780 |
Gar | +0.770 |
BUG | +0.756 |
cel | +0.755 |
Neg logit contributions | |
BW | -0.321 |
bons | -0.239 |
nb | -0.238 |
ciating | -0.235 |
Moz | -0.229 |
Token | # |
Token ID | 1303 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
BW | +5.185 |
Moz | +4.125 |
nb | +4.120 |
ciating | +4.078 |
bons | +4.040 |
Neg logit contributions | |
Eng | -7.827 |
Gar | -7.098 |
millenn | -7.082 |
BUG | -6.951 |
erness | -6.891 |
Token | 14 |
Token ID | 1415 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
BW | +3.297 |
bons | +2.986 |
nb | +2.974 |
Moz | +2.699 |
boo | +2.579 |
Neg logit contributions | |
millenn | -5.622 |
enthusi | -4.975 |
Eng | -4.496 |
hemor | -4.450 |
atism | -4.358 |
Token | On |
Token ID | 1550 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Eng | +0.087 |
millenn | +0.076 |
Gar | +0.075 |
BUG | +0.073 |
cel | +0.073 |
Neg logit contributions | |
BW | -0.106 |
ciating | -0.093 |
bons | -0.093 |
nb | -0.092 |
Moz | -0.091 |
Token | September |
Token ID | 2693 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
BW | +2.088 |
Moz | +1.741 |
nb | +1.676 |
bons | +1.669 |
boo | +1.626 |
Neg logit contributions | |
Eng | -2.805 |
millenn | -2.672 |
BUG | -2.475 |
Gar | -2.468 |
cel | -2.429 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
BW | +2.736 |
bons | +2.196 |
nb | +2.195 |
ciating | +2.176 |
Moz | +2.120 |
Neg logit contributions | |
Eng | -4.637 |
millenn | -4.238 |
Gar | -4.194 |
BUG | -4.108 |
cel | -4.088 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
BW | +0.404 |
bons | +0.347 |
nb | +0.347 |
ciating | +0.344 |
Moz | +0.343 |
Neg logit contributions | |
Eng | -0.366 |
millenn | -0.326 |
Gar | -0.320 |
BUG | -0.311 |
cel | -0.308 |
Token | United |
Token ID | 1578 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
BW | +1.211 |
bons | +1.018 |
nb | +1.015 |
ciating | +1.014 |
Moz | +0.999 |
Neg logit contributions | |
Eng | -1.492 |
millenn | -1.344 |
Gar | -1.329 |
BUG | -1.296 |
cel | -1.291 |
Token | States |
Token ID | 1829 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
BW | +0.509 |
bons | +0.424 |
ciating | +0.420 |
nb | +0.420 |
Moz | +0.408 |
Neg logit contributions | |
Eng | -0.782 |
millenn | -0.704 |
Gar | -0.703 |
cel | -0.686 |
BUG | -0.684 |
Token | 5 |
Token ID | 642 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
BW | +2.043 |
bons | +1.684 |
Moz | +1.684 |
nb | +1.683 |
McAuliffe | +1.649 |
Neg logit contributions | |
Eng | -2.443 |
millenn | -2.282 |
Gar | -2.175 |
BUG | -2.140 |
Frameworks | -2.105 |
Token | 667 |
Token ID | 28933 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
BW | +1.996 |
nb | +1.730 |
bons | +1.728 |
ciating | +1.712 |
Moz | +1.697 |
Neg logit contributions | |
Eng | -1.806 |
millenn | -1.635 |
Gar | -1.574 |
BUG | -1.531 |
cel | -1.525 |
Token | Posts |
Token ID | 12043 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
BW | +0.055 |
bons | +0.040 |
nb | +0.040 |
ciating | +0.039 |
Moz | +0.038 |
Neg logit contributions | |
Eng | -0.151 |
millenn | -0.142 |
Gar | -0.138 |
BUG | -0.136 |
cel | -0.136 |
Token | # |
Token ID | 1303 |
Feature activation | +6.62e+00 |
Pos logit contributions | |
BW | +5.185 |
Moz | +4.148 |
nb | +4.144 |
ciating | +4.081 |
bons | +4.070 |
Neg logit contributions | |
Eng | -7.721 |
millenn | -7.011 |
Gar | -6.997 |
BUG | -6.851 |
erness | -6.790 |
Token | 12 |
Token ID | 1065 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
BW | +3.919 |
bons | +3.470 |
nb | +3.414 |
Moz | +3.278 |
Grounds | +3.103 |
Neg logit contributions | |
millenn | -6.373 |
enthusi | -5.672 |
Eng | -5.321 |
atism | -5.125 |
cel | -5.124 |
Token | I |
Token ID | 314 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
BW | +0.902 |
bons | +0.783 |
ciating | +0.781 |
nb | +0.780 |
Moz | +0.769 |
Neg logit contributions | |
Eng | -0.752 |
millenn | -0.657 |
Gar | -0.651 |
BUG | -0.630 |
cel | -0.627 |
Token | 'm |
Token ID | 1101 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
BW | +0.825 |
bons | +0.707 |
nb | +0.707 |
ciating | +0.698 |
Moz | +0.695 |
Neg logit contributions | |
Eng | -0.779 |
millenn | -0.695 |
Gar | -0.681 |
BUG | -0.657 |
cel | -0.656 |
Token | glad |
Token ID | 9675 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
BW | +0.474 |
bons | +0.405 |
nb | +0.404 |
ciating | +0.400 |
Moz | +0.398 |
Neg logit contributions | |
Eng | -0.470 |
millenn | -0.418 |
Gar | -0.412 |
BUG | -0.400 |
cel | -0.396 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
BW | +3.156 |
nb | +2.666 |
bons | +2.666 |
Moz | +2.661 |
McAuliffe | +2.602 |
Neg logit contributions | |
Eng | -2.853 |
millenn | -2.627 |
Gar | -2.489 |
BUG | -2.442 |
cel | -2.401 |
Token | United |
Token ID | 1578 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
BW | +2.218 |
nb | +1.835 |
bons | +1.833 |
Moz | +1.832 |
ciating | +1.799 |
Neg logit contributions | |
Eng | -2.787 |
millenn | -2.576 |
Gar | -2.490 |
BUG | -2.442 |
cel | -2.414 |
Token | States |
Token ID | 1829 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
BW | +0.692 |
bons | +0.567 |
ciating | +0.567 |
nb | +0.564 |
Moz | +0.551 |
Neg logit contributions | |
Eng | -1.090 |
millenn | -0.986 |
Gar | -0.982 |
BUG | -0.959 |
cel | -0.958 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
BW | +2.218 |
nb | +1.831 |
Moz | +1.827 |
bons | +1.825 |
ciating | +1.786 |
Neg logit contributions | |
Eng | -2.642 |
millenn | -2.464 |
Gar | -2.351 |
BUG | -2.314 |
cel | -2.284 |
Token | 240 |
Token ID | 16102 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
BW | +2.052 |
nb | +1.689 |
bons | +1.668 |
ciating | +1.653 |
Moz | +1.627 |
Neg logit contributions | |
Eng | -3.237 |
millenn | -2.974 |
Gar | -2.902 |
BUG | -2.865 |
cel | -2.837 |
Token | Posts |
Token ID | 12043 |
Feature activation | +8.75e+00 |
Pos logit contributions | |
Eng | +0.924 |
Gar | +0.846 |
millenn | +0.841 |
cel | +0.830 |
BUG | +0.828 |
Neg logit contributions | |
BW | -0.369 |
ciating | -0.287 |
bons | -0.281 |
nb | -0.277 |
Moz | -0.268 |
Token | # |
Token ID | 1303 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
BW | +5.375 |
nb | +4.362 |
Moz | +4.340 |
bons | +4.251 |
ciating | +4.197 |
Neg logit contributions | |
Eng | -7.526 |
millenn | -6.909 |
Gar | -6.772 |
Frameworks | -6.613 |
erness | -6.596 |
Token | 10 |
Token ID | 940 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
BW | +5.403 |
nb | +4.672 |
bons | +4.592 |
Moz | +4.539 |
Grounds | +4.393 |
Neg logit contributions | |
millenn | -5.483 |
Eng | -5.177 |
enthusi | -4.778 |
atism | -4.683 |
cel | -4.667 |
Token | Happy |
Token ID | 14628 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
BW | +0.750 |
bons | +0.650 |
nb | +0.649 |
ciating | +0.648 |
Moz | +0.638 |
Neg logit contributions | |
Eng | -0.648 |
millenn | -0.568 |
Gar | -0.562 |
BUG | -0.545 |
cel | -0.543 |
Token | it |
Token ID | 340 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
BW | +0.226 |
bons | +0.195 |
ciating | +0.195 |
nb | +0.194 |
Moz | +0.190 |
Neg logit contributions | |
Eng | -0.236 |
millenn | -0.209 |
Gar | -0.208 |
cel | -0.202 |
BUG | -0.202 |
Token | worked |
Token ID | 3111 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
Eng | +0.874 |
Gar | +0.750 |
millenn | +0.744 |
cel | +0.722 |
BUG | +0.722 |
Neg logit contributions | |
BW | -1.123 |
ciating | -0.993 |
bons | -0.989 |
nb | -0.983 |
Moz | -0.967 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Eng | +0.102 |
millenn | +0.090 |
Gar | +0.089 |
BUG | +0.086 |
cel | +0.086 |
Neg logit contributions | |
BW | -0.115 |
bons | -0.099 |
nb | -0.099 |
ciating | -0.098 |
Moz | -0.097 |
Token | United |
Token ID | 1578 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
BW | +1.032 |
bons | +0.871 |
ciating | +0.869 |
nb | +0.867 |
Moz | +0.852 |
Neg logit contributions | |
Eng | -1.254 |
millenn | -1.123 |
Gar | -1.115 |
BUG | -1.086 |
cel | -1.084 |
Token | States |
Token ID | 1829 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
BW | +0.860 |
bons | +0.690 |
nb | +0.690 |
Moz | +0.684 |
ciating | +0.679 |
Neg logit contributions | |
Eng | -1.364 |
millenn | -1.272 |
Gar | -1.229 |
BUG | -1.208 |
cel | -1.202 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
BW | +3.483 |
Moz | +2.850 |
nb | +2.808 |
bons | +2.801 |
McAuliffe | +2.772 |
Neg logit contributions | |
Eng | -4.170 |
millenn | -4.014 |
Gar | -3.727 |
BUG | -3.686 |
Frameworks | -3.632 |
Token | 83 |
Token ID | 5999 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
BW | +2.596 |
nb | +2.259 |
bons | +2.253 |
ciating | +2.227 |
Moz | +2.211 |
Neg logit contributions | |
Eng | -2.226 |
millenn | -2.031 |
Gar | -1.930 |
BUG | -1.882 |
cel | -1.870 |
Token | Posts |
Token ID | 12043 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
BW | +0.213 |
bons | +0.156 |
nb | +0.156 |
ciating | +0.150 |
Moz | +0.150 |
Neg logit contributions | |
Eng | -0.582 |
millenn | -0.549 |
Gar | -0.533 |
cel | -0.524 |
BUG | -0.524 |
Token | Last |
Token ID | 4586 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
BW | +5.041 |
Moz | +4.017 |
nb | +4.010 |
ciating | +3.960 |
bons | +3.957 |
Neg logit contributions | |
Eng | -7.717 |
millenn | -7.028 |
Gar | -7.006 |
BUG | -6.870 |
erness | -6.790 |
Token | Edited |
Token ID | 34212 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
BW | +1.819 |
Moz | +1.277 |
nb | +1.273 |
bons | +1.267 |
Grounds | +1.196 |
Neg logit contributions | |
Eng | -4.125 |
millenn | -4.040 |
Gar | -3.753 |
enthusi | -3.718 |
atism | -3.717 |
Token | : |
Token ID | 25 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
BW | +0.539 |
bons | +0.449 |
nb | +0.448 |
Moz | +0.441 |
ciating | +0.432 |
Neg logit contributions | |
Eng | -0.678 |
millenn | -0.641 |
Gar | -0.603 |
BUG | -0.590 |
cel | -0.588 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
BW | +0.320 |
bons | +0.277 |
Moz | +0.277 |
nb | +0.276 |
McAuliffe | +0.272 |
Neg logit contributions | |
Eng | -0.219 |
millenn | -0.205 |
Gar | -0.187 |
BUG | -0.183 |
atism | -0.179 |
Token | - |
Token ID | 12 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
BW | +0.583 |
bons | +0.511 |
nb | +0.510 |
ciating | +0.508 |
Moz | +0.503 |
Neg logit contributions | |
Eng | -0.419 |
millenn | -0.368 |
Gar | -0.358 |
cel | -0.346 |
BUG | -0.345 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Eng | +0.374 |
millenn | +0.330 |
Gar | +0.326 |
BUG | +0.316 |
cel | +0.315 |
Neg logit contributions | |
BW | -0.418 |
bons | -0.362 |
nb | -0.361 |
ciating | -0.361 |
Moz | -0.356 |
Token | United |
Token ID | 1578 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
BW | +1.198 |
bons | +1.005 |
nb | +1.002 |
ciating | +1.000 |
Moz | +0.988 |
Neg logit contributions | |
Eng | -1.484 |
millenn | -1.340 |
Gar | -1.322 |
BUG | -1.290 |
cel | -1.285 |
Token | States |
Token ID | 1829 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
BW | +0.414 |
bons | +0.347 |
nb | +0.344 |
ciating | +0.344 |
Moz | +0.334 |
Neg logit contributions | |
Eng | -0.610 |
millenn | -0.549 |
Gar | -0.548 |
cel | -0.534 |
BUG | -0.532 |
Token | 228 |
Token ID | 29041 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
BW | +2.527 |
Moz | +2.079 |
bons | +2.066 |
nb | +2.065 |
McAuliffe | +2.033 |
Neg logit contributions | |
Eng | -3.025 |
millenn | -2.848 |
Gar | -2.699 |
BUG | -2.658 |
Frameworks | -2.620 |
Token | 65 |
Token ID | 2996 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
BW | +1.135 |
bons | +0.982 |
nb | +0.982 |
ciating | +0.975 |
Moz | +0.964 |
Neg logit contributions | |
Eng | -1.015 |
millenn | -0.902 |
Gar | -0.884 |
cel | -0.856 |
BUG | -0.856 |
Token | Posts |
Token ID | 12043 |
Feature activation | +8.44e+00 |
Pos logit contributions | |
Eng | +2.068 |
Gar | +1.888 |
BUG | +1.849 |
cel | +1.846 |
millenn | +1.832 |
Neg logit contributions | |
BW | -0.838 |
ciating | -0.672 |
bons | -0.645 |
nb | -0.638 |
enhagen | -0.613 |
Token | # |
Token ID | 1303 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
BW | +4.986 |
Moz | +3.966 |
nb | +3.961 |
ciating | +3.920 |
bons | +3.905 |
Neg logit contributions | |
Eng | -7.494 |
Gar | -6.776 |
millenn | -6.773 |
BUG | -6.642 |
erness | -6.580 |
Token | 13 |
Token ID | 1485 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
BW | +4.064 |
nb | +3.701 |
bons | +3.629 |
Moz | +3.453 |
boo | +3.316 |
Neg logit contributions | |
millenn | -4.629 |
enthusi | -4.009 |
Eng | -3.851 |
atism | -3.638 |
cel | -3.597 |
Token | On |
Token ID | 1550 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
BW | +0.092 |
ciating | +0.080 |
bons | +0.080 |
nb | +0.080 |
Moz | +0.079 |
Neg logit contributions | |
Eng | -0.078 |
millenn | -0.068 |
Gar | -0.067 |
BUG | -0.065 |
cel | -0.065 |
Token | September |
Token ID | 2693 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
BW | +2.275 |
Moz | +1.893 |
nb | +1.821 |
bons | +1.813 |
boo | +1.776 |
Neg logit contributions | |
Eng | -3.026 |
millenn | -2.847 |
Gar | -2.666 |
BUG | -2.664 |
cel | -2.622 |
Token | 20 |
Token ID | 1160 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
BW | +2.341 |
bons | +1.883 |
nb | +1.878 |
ciating | +1.862 |
Moz | +1.828 |
Neg logit contributions | |
Eng | -3.886 |
millenn | -3.558 |
Gar | -3.509 |
BUG | -3.438 |
cel | -3.425 |
Token | 2002 |
Token ID | 6244 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
BW | +0.496 |
bons | +0.428 |
nb | +0.427 |
ciating | +0.426 |
Moz | +0.420 |
Neg logit contributions | |
Eng | -0.453 |
millenn | -0.401 |
Gar | -0.396 |
BUG | -0.384 |
cel | -0.382 |
Token | United |
Token ID | 1578 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
BW | +0.969 |
bons | +0.820 |
ciating | +0.820 |
nb | +0.817 |
Moz | +0.800 |
Neg logit contributions | |
Eng | -1.165 |
millenn | -1.040 |
Gar | -1.035 |
BUG | -1.008 |
cel | -1.006 |
Token | States |
Token ID | 1829 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Eng | +0.123 |
millenn | +0.110 |
Gar | +0.110 |
cel | +0.108 |
BUG | +0.107 |
Neg logit contributions | |
BW | -0.080 |
bons | -0.068 |
ciating | -0.067 |
nb | -0.067 |
Moz | -0.065 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
BW | +1.586 |
bons | +1.318 |
nb | +1.318 |
Moz | +1.309 |
ciating | +1.296 |
Neg logit contributions | |
Eng | -1.860 |
millenn | -1.713 |
Gar | -1.654 |
BUG | -1.621 |
cel | -1.604 |
Token | 472 |
Token ID | 37856 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
BW | +2.423 |
nb | +2.072 |
bons | +2.056 |
ciating | +2.033 |
Moz | +2.018 |
Neg logit contributions | |
Eng | -2.635 |
millenn | -2.421 |
Gar | -2.320 |
BUG | -2.271 |
cel | -2.260 |
Token | Posts |
Token ID | 12043 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
BW | +0.063 |
bons | +0.046 |
nb | +0.046 |
ciating | +0.045 |
Moz | +0.044 |
Neg logit contributions | |
Eng | -0.174 |
millenn | -0.164 |
Gar | -0.160 |
BUG | -0.157 |
cel | -0.157 |
Token | # |
Token ID | 1303 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
BW | +4.778 |
Moz | +3.798 |
nb | +3.790 |
bons | +3.747 |
ciating | +3.730 |
Neg logit contributions | |
Eng | -7.178 |
millenn | -6.525 |
Gar | -6.481 |
BUG | -6.343 |
Frameworks | -6.304 |
Token | 11 |
Token ID | 1157 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
BW | +3.840 |
bons | +3.346 |
nb | +3.278 |
Moz | +3.157 |
@#& | +2.981 |
Neg logit contributions | |
millenn | -6.029 |
Eng | -5.510 |
enthusi | -5.298 |
cel | -5.151 |
atism | -4.988 |
Token | On |
Token ID | 1550 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
BW | +0.057 |
ciating | +0.049 |
bons | +0.049 |
nb | +0.049 |
Moz | +0.048 |
Neg logit contributions | |
Eng | -0.052 |
millenn | -0.046 |
Gar | -0.046 |
cel | -0.044 |
BUG | -0.044 |
Token | September |
Token ID | 2693 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
BW | +2.858 |
bons | +2.385 |
Moz | +2.378 |
nb | +2.361 |
Grounds | +2.325 |
Neg logit contributions | |
Eng | -3.068 |
millenn | -2.771 |
Gar | -2.673 |
atism | -2.630 |
BUG | -2.623 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
BW | +1.331 |
Moz | +1.103 |
nb | +1.102 |
bons | +1.097 |
McAuliffe | +1.072 |
Neg logit contributions | |
Eng | -1.589 |
millenn | -1.504 |
Gar | -1.413 |
BUG | -1.387 |
cel | -1.376 |
Token | TL |
Token ID | 24811 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
BW | +0.712 |
ciating | +0.607 |
bons | +0.605 |
nb | +0.602 |
Moz | +0.587 |
Neg logit contributions | |
Eng | -0.865 |
Gar | -0.768 |
millenn | -0.767 |
cel | -0.747 |
BUG | -0.747 |
Token | AD |
Token ID | 2885 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
BW | +0.107 |
ciating | +0.095 |
bons | +0.095 |
nb | +0.094 |
McAuliffe | +0.092 |
Neg logit contributions | |
Eng | -0.097 |
Gar | -0.084 |
millenn | -0.083 |
BUG | -0.082 |
cel | -0.081 |
Token | T |
Token ID | 51 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
BW | +0.587 |
bons | +0.509 |
ciating | +0.508 |
nb | +0.507 |
Moz | +0.503 |
Neg logit contributions | |
Eng | -0.430 |
millenn | -0.379 |
Gar | -0.365 |
cel | -0.355 |
atism | -0.353 |
Token | 235 |
Token ID | 28878 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
Eng | +0.216 |
Gar | +0.191 |
millenn | +0.190 |
BUG | +0.186 |
cel | +0.186 |
Neg logit contributions | |
BW | -0.195 |
ciating | -0.168 |
bons | -0.167 |
nb | -0.167 |
Moz | -0.163 |
Token | 21 |
Token ID | 2481 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
BW | +0.622 |
bons | +0.543 |
ciating | +0.542 |
nb | +0.541 |
Moz | +0.533 |
Neg logit contributions | |
Eng | -0.511 |
millenn | -0.446 |
Gar | -0.442 |
BUG | -0.428 |
cel | -0.427 |
Token | Posts |
Token ID | 12043 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
Eng | +3.041 |
Gar | +2.782 |
BUG | +2.723 |
cel | +2.716 |
Frameworks | +2.665 |
Neg logit contributions | |
BW | -1.276 |
ciating | -1.063 |
bons | -1.004 |
enhagen | -0.981 |
nb | -0.980 |
Token | # |
Token ID | 1303 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
BW | +4.536 |
Moz | +3.594 |
nb | +3.579 |
bons | +3.536 |
ciating | +3.535 |
Neg logit contributions | |
Eng | -7.079 |
millenn | -6.430 |
Gar | -6.405 |
BUG | -6.294 |
erness | -6.235 |
Token | 18 |
Token ID | 1507 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
BW | +3.456 |
bons | +3.074 |
nb | +3.031 |
Moz | +2.849 |
McAuliffe | +2.763 |
Neg logit contributions | |
millenn | -4.484 |
Eng | -3.979 |
enthusi | -3.905 |
atism | -3.672 |
cel | -3.633 |
Token | Good |
Token ID | 4599 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
Eng | +0.553 |
Gar | +0.481 |
millenn | +0.480 |
cel | +0.467 |
BUG | +0.465 |
Neg logit contributions | |
BW | -0.626 |
ciating | -0.550 |
bons | -0.547 |
nb | -0.545 |
Moz | -0.534 |
Token | stuff |
Token ID | 3404 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
Eng | +0.033 |
millenn | +0.029 |
Gar | +0.029 |
cel | +0.028 |
BUG | +0.028 |
Neg logit contributions | |
BW | -0.034 |
ciating | -0.030 |
bons | -0.029 |
nb | -0.029 |
Moz | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
BW | +0.728 |
bons | +0.632 |
ciating | +0.631 |
nb | +0.631 |
Moz | +0.621 |
Neg logit contributions | |
Eng | -0.618 |
millenn | -0.540 |
Gar | -0.536 |
BUG | -0.519 |
cel | -0.517 |
Token | June |
Token ID | 2795 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
BW | +2.470 |
Moz | +2.034 |
nb | +2.024 |
bons | +2.023 |
McAuliffe | +1.966 |
Neg logit contributions | |
Eng | -3.004 |
millenn | -2.836 |
Gar | -2.681 |
BUG | -2.616 |
atism | -2.615 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
BW | +0.509 |
bons | +0.438 |
nb | +0.437 |
ciating | +0.434 |
Moz | +0.432 |
Neg logit contributions | |
Eng | -0.443 |
millenn | -0.394 |
Gar | -0.386 |
BUG | -0.374 |
cel | -0.372 |
Token | Germany |
Token ID | 4486 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
BW | +1.152 |
ciating | +0.975 |
bons | +0.975 |
nb | +0.971 |
Moz | +0.950 |
Neg logit contributions | |
Eng | -1.395 |
millenn | -1.243 |
Gar | -1.239 |
BUG | -1.207 |
cel | -1.205 |
Token | 247 |
Token ID | 30179 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
BW | +0.613 |
nb | +0.515 |
bons | +0.515 |
ciating | +0.510 |
Moz | +0.508 |
Neg logit contributions | |
Eng | -0.709 |
millenn | -0.643 |
Gar | -0.630 |
BUG | -0.613 |
cel | -0.610 |
Token | 34 |
Token ID | 2682 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
BW | +0.559 |
bons | +0.470 |
nb | +0.469 |
ciating | +0.468 |
Moz | +0.460 |
Neg logit contributions | |
Eng | -0.695 |
millenn | -0.626 |
Gar | -0.618 |
BUG | -0.603 |
cel | -0.602 |
Token | Posts |
Token ID | 12043 |
Feature activation | +7.71e+00 |
Pos logit contributions | |
Eng | +2.065 |
Gar | +1.888 |
BUG | +1.850 |
millenn | +1.849 |
cel | +1.847 |
Neg logit contributions | |
BW | -0.820 |
ciating | -0.644 |
bons | -0.626 |
nb | -0.619 |
Moz | -0.595 |
Token | # |
Token ID | 1303 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
BW | +4.531 |
nb | +3.613 |
Moz | +3.601 |
ciating | +3.561 |
bons | +3.558 |
Neg logit contributions | |
Eng | -6.874 |
millenn | -6.250 |
Gar | -6.223 |
BUG | -6.116 |
Frameworks | -6.034 |
Token | 20 |
Token ID | 1238 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
BW | +2.927 |
nb | +2.521 |
bons | +2.500 |
Moz | +2.349 |
McAuliffe | +2.308 |
Neg logit contributions | |
millenn | -3.488 |
Eng | -3.397 |
enthusi | -3.093 |
Gar | -3.066 |
cel | -3.054 |
Token | Nice |
Token ID | 18460 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
BW | +0.886 |
bons | +0.762 |
nb | +0.761 |
ciating | +0.759 |
Moz | +0.749 |
Neg logit contributions | |
Eng | -0.813 |
millenn | -0.717 |
Gar | -0.709 |
BUG | -0.689 |
cel | -0.684 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
BW | +0.355 |
bons | +0.307 |
nb | +0.307 |
ciating | +0.307 |
Moz | +0.302 |
Neg logit contributions | |
Eng | -0.312 |
millenn | -0.273 |
Gar | -0.271 |
BUG | -0.263 |
cel | -0.262 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
BW | +0.116 |
ciating | +0.102 |
bons | +0.101 |
nb | +0.101 |
Moz | +0.099 |
Neg logit contributions | |
Eng | -0.110 |
Gar | -0.096 |
millenn | -0.096 |
cel | -0.093 |
BUG | -0.093 |
Token | The |
Token ID | 383 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
BW | +0.649 |
ciating | +0.569 |
bons | +0.568 |
nb | +0.565 |
Moz | +0.556 |
Neg logit contributions | |
Eng | -0.532 |
Gar | -0.460 |
millenn | -0.460 |
BUG | -0.445 |
cel | -0.444 |
Token | hefty |
Token ID | 29784 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
BW | +0.712 |
bons | +0.610 |
nb | +0.608 |
ciating | +0.607 |
Moz | +0.602 |
Neg logit contributions | |
Eng | -0.681 |
millenn | -0.599 |
Gar | -0.596 |
BUG | -0.579 |
cel | -0.574 |
Token | mug |
Token ID | 25152 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
BW | +0.966 |
bons | +0.820 |
nb | +0.816 |
ciating | +0.815 |
Moz | +0.811 |
Neg logit contributions | |
Eng | -0.999 |
millenn | -0.884 |
Gar | -0.877 |
BUG | -0.855 |
cel | -0.845 |
Token | is |
Token ID | 318 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
BW | +1.386 |
bons | +1.202 |
nb | +1.200 |
ciating | +1.189 |
Moz | +1.176 |
Neg logit contributions | |
Eng | -1.233 |
millenn | -1.088 |
Gar | -1.072 |
BUG | -1.042 |
cel | -1.034 |
Token | em |
Token ID | 795 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
BW | +0.649 |
bons | +0.557 |
nb | +0.554 |
ciating | +0.552 |
Moz | +0.548 |
Neg logit contributions | |
Eng | -0.622 |
millenn | -0.549 |
Gar | -0.545 |
BUG | -0.531 |
cel | -0.524 |
Token | bl |
Token ID | 2436 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
BW | +0.278 |
bons | +0.234 |
ciating | +0.232 |
nb | +0.232 |
Moz | +0.227 |
Neg logit contributions | |
Eng | -0.375 |
millenn | -0.340 |
Gar | -0.334 |
BUG | -0.328 |
cel | -0.326 |
Token | azon |
Token ID | 5168 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
BW | +4.415 |
nb | +3.785 |
bons | +3.765 |
ciating | +3.756 |
enhagen | +3.523 |
Neg logit contributions | |
Eng | -6.581 |
millenn | -6.514 |
BUG | -6.053 |
Gar | -5.895 |
enthusi | -5.823 |
Token | ed |
Token ID | 276 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
BW | +2.613 |
bons | +2.258 |
nb | +2.231 |
ciating | +2.196 |
Moz | +2.168 |
Neg logit contributions | |
Eng | -2.558 |
millenn | -2.418 |
Gar | -2.238 |
BUG | -2.204 |
Frameworks | -2.145 |
Token | with |
Token ID | 351 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
BW | +2.455 |
bons | +2.111 |
nb | +2.091 |
ciating | +2.074 |
Moz | +2.070 |
Neg logit contributions | |
Eng | -2.268 |
millenn | -1.994 |
Gar | -1.969 |
BUG | -1.922 |
cel | -1.884 |
Token | the |
Token ID | 262 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
BW | +0.632 |
bons | +0.543 |
ciating | +0.542 |
nb | +0.541 |
Moz | +0.531 |
Neg logit contributions | |
Eng | -0.647 |
millenn | -0.572 |
Gar | -0.569 |
BUG | -0.553 |
cel | -0.552 |
Token | word |
Token ID | 1573 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Eng | +0.533 |
millenn | +0.471 |
Gar | +0.468 |
cel | +0.456 |
BUG | +0.455 |
Neg logit contributions | |
BW | -0.517 |
ciating | -0.448 |
bons | -0.446 |
nb | -0.444 |
Moz | -0.433 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
BW | +0.717 |
bons | +0.607 |
nb | +0.607 |
Moz | +0.604 |
ciating | +0.597 |
Neg logit contributions | |
Eng | -0.699 |
millenn | -0.636 |
Gar | -0.615 |
BUG | -0.600 |
cel | -0.594 |
Token | United |
Token ID | 1578 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
BW | +1.237 |
bons | +1.042 |
ciating | +1.040 |
nb | +1.038 |
Moz | +1.020 |
Neg logit contributions | |
Eng | -1.513 |
millenn | -1.358 |
Gar | -1.346 |
BUG | -1.312 |
cel | -1.308 |
Token | States |
Token ID | 1829 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
BW | +0.315 |
bons | +0.263 |
nb | +0.261 |
ciating | +0.261 |
Moz | +0.254 |
Neg logit contributions | |
Eng | -0.469 |
millenn | -0.422 |
Gar | -0.421 |
cel | -0.410 |
BUG | -0.409 |
Token | 21 |
Token ID | 2310 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
BW | +2.462 |
Moz | +2.023 |
bons | +2.012 |
nb | +2.012 |
McAuliffe | +1.980 |
Neg logit contributions | |
Eng | -2.967 |
millenn | -2.796 |
Gar | -2.644 |
BUG | -2.603 |
Frameworks | -2.564 |
Token | 50 |
Token ID | 1120 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
BW | +1.420 |
bons | +1.211 |
ciating | +1.209 |
nb | +1.207 |
Moz | +1.184 |
Neg logit contributions | |
Eng | -1.565 |
millenn | -1.393 |
Gar | -1.383 |
BUG | -1.345 |
cel | -1.343 |
Token | Posts |
Token ID | 12043 |
Feature activation | +7.57e+00 |
Pos logit contributions | |
Eng | +1.721 |
Gar | +1.574 |
millenn | +1.567 |
BUG | +1.544 |
cel | +1.542 |
Neg logit contributions | |
BW | -0.668 |
ciating | -0.508 |
bons | -0.503 |
nb | -0.499 |
Moz | -0.479 |
Token | # |
Token ID | 1303 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
BW | +4.500 |
nb | +3.598 |
Moz | +3.578 |
ciating | +3.557 |
bons | +3.548 |
Neg logit contributions | |
Eng | -6.710 |
millenn | -6.085 |
Gar | -6.062 |
BUG | -5.935 |
erness | -5.878 |
Token | 16 |
Token ID | 1433 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
BW | +4.083 |
nb | +3.665 |
bons | +3.665 |
Moz | +3.388 |
boo | +3.380 |
Neg logit contributions | |
millenn | -4.335 |
Eng | -3.738 |
enthusi | -3.707 |
atism | -3.335 |
aminer | -3.321 |
Token | Glad |
Token ID | 28442 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
BW | +0.846 |
bons | +0.735 |
nb | +0.734 |
ciating | +0.732 |
Moz | +0.723 |
Neg logit contributions | |
Eng | -0.669 |
millenn | -0.585 |
Gar | -0.576 |
BUG | -0.559 |
cel | -0.554 |
Token | to |
Token ID | 284 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
Eng | +0.241 |
Gar | +0.211 |
millenn | +0.211 |
cel | +0.205 |
BUG | +0.205 |
Neg logit contributions | |
BW | -0.242 |
ciating | -0.211 |
bons | -0.211 |
nb | -0.209 |
Moz | -0.205 |
Token | hear |
Token ID | 3285 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Eng | +0.693 |
millenn | +0.604 |
Gar | +0.604 |
cel | +0.585 |
BUG | +0.585 |
Neg logit contributions | |
BW | -0.773 |
ciating | -0.676 |
bons | -0.674 |
nb | -0.669 |
Moz | -0.659 |
Token | United |
Token ID | 1578 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
BW | +2.218 |
nb | +1.835 |
bons | +1.833 |
Moz | +1.832 |
ciating | +1.799 |
Neg logit contributions | |
Eng | -2.787 |
millenn | -2.576 |
Gar | -2.490 |
BUG | -2.442 |
cel | -2.414 |
Token | States |
Token ID | 1829 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
BW | +0.692 |
bons | +0.567 |
ciating | +0.567 |
nb | +0.564 |
Moz | +0.551 |
Neg logit contributions | |
Eng | -1.090 |
millenn | -0.986 |
Gar | -0.982 |
BUG | -0.959 |
cel | -0.958 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
BW | +2.218 |
nb | +1.831 |
Moz | +1.827 |
bons | +1.825 |
ciating | +1.786 |
Neg logit contributions | |
Eng | -2.642 |
millenn | -2.464 |
Gar | -2.351 |
BUG | -2.314 |
cel | -2.284 |
Token | 240 |
Token ID | 16102 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
BW | +2.052 |
nb | +1.689 |
bons | +1.668 |
ciating | +1.653 |
Moz | +1.627 |
Neg logit contributions | |
Eng | -3.237 |
millenn | -2.974 |
Gar | -2.902 |
BUG | -2.865 |
cel | -2.837 |
Token | Posts |
Token ID | 12043 |
Feature activation | +8.75e+00 |
Pos logit contributions | |
Eng | +0.924 |
Gar | +0.846 |
millenn | +0.841 |
cel | +0.830 |
BUG | +0.828 |
Neg logit contributions | |
BW | -0.369 |
ciating | -0.287 |
bons | -0.281 |
nb | -0.277 |
Moz | -0.268 |
Token | # |
Token ID | 1303 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
BW | +5.375 |
nb | +4.362 |
Moz | +4.340 |
bons | +4.251 |
ciating | +4.197 |
Neg logit contributions | |
Eng | -7.526 |
millenn | -6.909 |
Gar | -6.772 |
Frameworks | -6.613 |
erness | -6.596 |
Token | 10 |
Token ID | 940 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
BW | +5.403 |
nb | +4.672 |
bons | +4.592 |
Moz | +4.539 |
Grounds | +4.393 |
Neg logit contributions | |
millenn | -5.483 |
Eng | -5.177 |
enthusi | -4.778 |
atism | -4.683 |
cel | -4.667 |
Token | Happy |
Token ID | 14628 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
BW | +0.750 |
bons | +0.650 |
nb | +0.649 |
ciating | +0.648 |
Moz | +0.638 |
Neg logit contributions | |
Eng | -0.648 |
millenn | -0.568 |
Gar | -0.562 |
BUG | -0.545 |
cel | -0.543 |
Token | it |
Token ID | 340 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
BW | +0.226 |
bons | +0.195 |
ciating | +0.195 |
nb | +0.194 |
Moz | +0.190 |
Neg logit contributions | |
Eng | -0.236 |
millenn | -0.209 |
Gar | -0.208 |
cel | -0.202 |
BUG | -0.202 |
Token | worked |
Token ID | 3111 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
Eng | +0.874 |
Gar | +0.750 |
millenn | +0.744 |
cel | +0.722 |
BUG | +0.722 |
Neg logit contributions | |
BW | -1.123 |
ciating | -0.993 |
bons | -0.989 |
nb | -0.983 |
Moz | -0.967 |
Token | out |
Token ID | 503 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
BW | +0.726 |
bons | +0.619 |
ciating | +0.619 |
nb | +0.618 |
Moz | +0.607 |
Neg logit contributions | |
Eng | -0.762 |
millenn | -0.677 |
Gar | -0.671 |
BUG | -0.653 |
cel | -0.650 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
BW | +1.315 |
bons | +1.149 |
nb | +1.149 |
ciating | +1.138 |
Moz | +1.121 |
Neg logit contributions | |
Eng | -1.135 |
millenn | -1.016 |
Gar | -0.987 |
cel | -0.966 |
BUG | -0.964 |
Token | yr |
Token ID | 42635 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
BW | +3.065 |
ciating | +2.619 |
nb | +2.612 |
bons | +2.595 |
Moz | +2.589 |
Neg logit contributions | |
Eng | -2.641 |
millenn | -2.315 |
Gar | -2.308 |
BUG | -2.251 |
cel | -2.228 |
Token | .) |
Token ID | 2014 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
BW | +2.259 |
bons | +1.988 |
ciating | +1.986 |
nb | +1.981 |
Moz | +1.951 |
Neg logit contributions | |
Eng | -1.623 |
millenn | -1.396 |
Gar | -1.388 |
BUG | -1.339 |
cel | -1.335 |
Token | [ |
Token ID | 685 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
BW | +1.979 |
bons | +1.670 |
ciating | +1.667 |
nb | +1.664 |
Moz | +1.638 |
Neg logit contributions | |
Eng | -2.317 |
millenn | -2.077 |
Gar | -2.059 |
BUG | -2.008 |
cel | -1.998 |
Token | plus |
Token ID | 9541 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Eng | +0.773 |
Gar | +0.663 |
millenn | +0.644 |
BUG | +0.632 |
cel | +0.623 |
Neg logit contributions | |
BW | -1.104 |
ciating | -0.976 |
bons | -0.964 |
nb | -0.957 |
Moz | -0.955 |
Token | ] |
Token ID | 60 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
Eng | +0.118 |
millenn | +0.099 |
Gar | +0.098 |
BUG | +0.094 |
cel | +0.093 |
Neg logit contributions | |
BW | -0.216 |
bons | -0.193 |
ciating | -0.192 |
nb | -0.192 |
Moz | -0.190 |
Token | $ |
Token ID | 720 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
BW | +3.609 |
nb | +2.812 |
bons | +2.811 |
ciating | +2.797 |
Moz | +2.796 |
Neg logit contributions | |
Eng | -7.022 |
millenn | -6.477 |
Gar | -6.404 |
BUG | -6.324 |
atism | -6.226 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
BW | +2.246 |
nb | +1.952 |
bons | +1.944 |
Moz | +1.901 |
ciating | +1.889 |
Neg logit contributions | |
Eng | -2.090 |
millenn | -1.982 |
Gar | -1.831 |
cel | -1.808 |
BUG | -1.792 |
Token | , |
Token ID | 11 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Eng | +0.211 |
millenn | +0.189 |
Gar | +0.183 |
BUG | +0.177 |
cel | +0.177 |
Neg logit contributions | |
BW | -0.254 |
bons | -0.220 |
nb | -0.220 |
ciating | -0.218 |
Moz | -0.217 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
BW | +0.294 |
bons | +0.253 |
ciating | +0.253 |
nb | +0.252 |
Moz | +0.247 |
Neg logit contributions | |
Eng | -0.290 |
Gar | -0.255 |
millenn | -0.254 |
BUG | -0.247 |
cel | -0.247 |
Token | ." |
Token ID | 526 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
BW | +1.210 |
bons | +1.054 |
ciating | +1.052 |
nb | +1.050 |
Moz | +1.034 |
Neg logit contributions | |
Eng | -1.017 |
millenn | -0.887 |
Gar | -0.882 |
BUG | -0.853 |
cel | -0.851 |
Token | ds |
Token ID | 9310 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
BW | +1.293 |
bons | +1.080 |
nb | +1.072 |
ciating | +1.058 |
Moz | +1.033 |
Neg logit contributions | |
Eng | -2.006 |
millenn | -1.834 |
Gar | -1.807 |
cel | -1.767 |
BUG | -1.761 |
Token | ' |
Token ID | 6 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
BW | +1.911 |
nb | +1.593 |
bons | +1.587 |
ciating | +1.576 |
Moz | +1.566 |
Neg logit contributions | |
Eng | -2.457 |
millenn | -2.203 |
Gar | -2.185 |
BUG | -2.133 |
cel | -2.118 |
Token | " |
Token ID | 366 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Eng | +0.242 |
millenn | +0.214 |
Gar | +0.213 |
cel | +0.208 |
BUG | +0.206 |
Neg logit contributions | |
BW | -0.252 |
ciating | -0.221 |
bons | -0.220 |
nb | -0.217 |
Moz | -0.212 |
Token | I |
Token ID | 40 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
BW | +1.812 |
nb | +1.583 |
bons | +1.581 |
ciating | +1.565 |
Moz | +1.553 |
Neg logit contributions | |
Eng | -1.488 |
millenn | -1.329 |
Gar | -1.280 |
cel | -1.258 |
BUG | -1.246 |
Token | 'll |
Token ID | 1183 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
BW | +0.880 |
bons | +0.743 |
ciating | +0.742 |
nb | +0.740 |
Moz | +0.726 |
Neg logit contributions | |
Eng | -1.068 |
millenn | -0.956 |
Gar | -0.949 |
BUG | -0.925 |
cel | -0.923 |
Token | Feel |
Token ID | 18571 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
BW | +0.949 |
ciating | +0.724 |
bons | +0.722 |
nb | +0.721 |
Moz | +0.697 |
Neg logit contributions | |
Eng | -2.241 |
millenn | -2.062 |
Gar | -2.047 |
BUG | -2.007 |
cel | -2.004 |
Token | a |
Token ID | 257 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
BW | +5.144 |
bons | +4.305 |
Moz | +4.296 |
nb | +4.283 |
ciating | +4.281 |
Neg logit contributions | |
Eng | -5.412 |
millenn | -4.976 |
Gar | -4.754 |
BUG | -4.644 |
cel | -4.573 |
Token | Whole |
Token ID | 23431 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
BW | +2.074 |
Moz | +1.716 |
bons | +1.714 |
nb | +1.711 |
ciating | +1.687 |
Neg logit contributions | |
Eng | -2.357 |
millenn | -2.186 |
Gar | -2.073 |
BUG | -2.035 |
cel | -2.020 |
Token | Lot |
Token ID | 15099 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
BW | +1.578 |
nb | +1.362 |
bons | +1.359 |
Moz | +1.359 |
ciating | +1.345 |
Neg logit contributions | |
Eng | -1.165 |
millenn | -1.055 |
Gar | -0.988 |
BUG | -0.968 |
cel | -0.961 |
Token | Better |
Token ID | 11625 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
BW | +0.236 |
ciating | +0.203 |
bons | +0.203 |
nb | +0.201 |
Moz | +0.195 |
Neg logit contributions | |
Eng | -0.286 |
Gar | -0.253 |
millenn | -0.251 |
BUG | -0.248 |
cel | -0.246 |
Token | " |
Token ID | 1 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
BW | +3.684 |
bons | +3.158 |
ciating | +3.152 |
nb | +3.141 |
Moz | +3.119 |
Neg logit contributions | |
Eng | -3.370 |
millenn | -2.985 |
Gar | -2.943 |
BUG | -2.848 |
cel | -2.832 |
Token | fn |
Token ID | 24714 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
BW | +0.674 |
bons | +0.547 |
nb | +0.545 |
ciating | +0.542 |
Moz | +0.533 |
Neg logit contributions | |
Eng | -1.109 |
millenn | -1.009 |
Gar | -1.002 |
BUG | -0.973 |
cel | -0.972 |
Token | copy |
Token ID | 4866 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
BW | +2.689 |
nb | +2.275 |
bons | +2.273 |
ciating | +2.257 |
Moz | +2.254 |
Neg logit contributions | |
Eng | -2.804 |
Gar | -2.486 |
millenn | -2.481 |
BUG | -2.389 |
Frameworks | -2.377 |
Token | _ |
Token ID | 62 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
BW | +1.830 |
bons | +1.591 |
ciating | +1.590 |
nb | +1.590 |
Moz | +1.562 |
Neg logit contributions | |
Eng | -1.518 |
millenn | -1.327 |
Gar | -1.314 |
cel | -1.270 |
BUG | -1.267 |
Token | board |
Token ID | 3526 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
BW | +0.267 |
bons | +0.228 |
ciating | +0.228 |
nb | +0.227 |
Moz | +0.222 |
Neg logit contributions | |
Eng | -0.293 |
millenn | -0.260 |
Gar | -0.259 |
BUG | -0.252 |
cel | -0.251 |
Token | ( |
Token ID | 357 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
BW | +0.042 |
ciating | +0.036 |
bons | +0.036 |
nb | +0.036 |
Moz | +0.036 |
Neg logit contributions | |
Eng | -0.035 |
millenn | -0.030 |
Gar | -0.030 |
BUG | -0.029 |
cel | -0.029 |
Token | & |
Token ID | 1222 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
BW | +3.768 |
nb | +3.227 |
bons | +3.192 |
ciating | +3.158 |
Moz | +3.127 |
Neg logit contributions | |
Eng | -4.039 |
millenn | -3.636 |
Gar | -3.597 |
Frameworks | -3.449 |
BUG | -3.440 |
Token | self |
Token ID | 2116 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
BW | +5.795 |
nb | +5.028 |
bons | +4.958 |
Moz | +4.898 |
ciating | +4.880 |
Neg logit contributions | |
Eng | -4.766 |
millenn | -4.236 |
Gar | -4.093 |
Frameworks | -3.994 |
ilda | -3.957 |
Token | ) |
Token ID | 1267 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
BW | +2.700 |
nb | +2.284 |
bons | +2.274 |
ciating | +2.270 |
Moz | +2.222 |
Neg logit contributions | |
Eng | -3.092 |
millenn | -2.817 |
Gar | -2.773 |
BUG | -2.694 |
cel | -2.674 |
Token | -> |
Token ID | 4613 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
BW | +2.310 |
nb | +1.918 |
bons | +1.913 |
Moz | +1.898 |
ciating | +1.888 |
Neg logit contributions | |
Eng | -2.751 |
millenn | -2.498 |
Gar | -2.458 |
BUG | -2.400 |
Frameworks | -2.365 |
Token | Board |
Token ID | 5926 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
BW | +3.403 |
Moz | +2.765 |
nb | +2.760 |
bons | +2.750 |
ciating | +2.731 |
Neg logit contributions | |
Eng | -4.361 |
millenn | -3.969 |
Gar | -3.911 |
BUG | -3.761 |
Frameworks | -3.758 |
Token | { |
Token ID | 1391 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
BW | +0.402 |
bons | +0.348 |
ciating | +0.348 |
nb | +0.347 |
Moz | +0.341 |
Neg logit contributions | |
Eng | -0.375 |
millenn | -0.330 |
Gar | -0.328 |
BUG | -0.318 |
cel | -0.317 |
Token | re |
Token ID | 302 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Eng | +0.499 |
millenn | +0.447 |
Gar | +0.445 |
cel | +0.435 |
BUG | +0.433 |
Neg logit contributions | |
BW | -0.398 |
ciating | -0.339 |
bons | -0.337 |
nb | -0.336 |
Moz | -0.327 |
Token | - |
Token ID | 12 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Eng | +1.137 |
Gar | +0.974 |
millenn | +0.970 |
cel | +0.934 |
BUG | +0.932 |
Neg logit contributions | |
BW | -1.633 |
ciating | -1.444 |
bons | -1.438 |
nb | -1.435 |
Moz | -1.417 |
Token | election |
Token ID | 14300 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Eng | +0.219 |
millenn | +0.194 |
Gar | +0.194 |
BUG | +0.188 |
cel | +0.188 |
Neg logit contributions | |
BW | -0.190 |
ciating | -0.162 |
bons | -0.161 |
nb | -0.161 |
Moz | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
BW | +1.404 |
bons | +1.222 |
nb | +1.218 |
ciating | +1.215 |
Moz | +1.200 |
Neg logit contributions | |
Eng | -1.159 |
millenn | -1.017 |
Gar | -1.002 |
BUG | -0.973 |
cel | -0.964 |
Token | Think |
Token ID | 11382 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Eng | +0.477 |
Gar | +0.417 |
millenn | +0.416 |
BUG | +0.403 |
cel | +0.402 |
Neg logit contributions | |
BW | -0.518 |
ciating | -0.450 |
bons | -0.449 |
nb | -0.447 |
Moz | -0.439 |
Token | of |
Token ID | 286 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
BW | +1.640 |
bons | +1.402 |
nb | +1.391 |
ciating | +1.385 |
Moz | +1.377 |
Neg logit contributions | |
Eng | -1.702 |
millenn | -1.514 |
Gar | -1.496 |
BUG | -1.464 |
cel | -1.452 |
Token | how |
Token ID | 703 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
BW | +4.935 |
McAuliffe | +4.206 |
bons | +4.121 |
Moz | +4.112 |
nb | +4.112 |
Neg logit contributions | |
Eng | -5.369 |
millenn | -4.848 |
BUG | -4.737 |
Gar | -4.684 |
erness | -4.655 |
Token | much |
Token ID | 881 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
BW | +2.977 |
McAuliffe | +2.555 |
bons | +2.533 |
Moz | +2.531 |
nb | +2.522 |
Neg logit contributions | |
Eng | -2.682 |
millenn | -2.335 |
Gar | -2.326 |
BUG | -2.296 |
erness | -2.240 |
Token | better |
Token ID | 1365 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
Eng | +0.047 |
millenn | +0.042 |
Gar | +0.041 |
cel | +0.040 |
BUG | +0.040 |
Neg logit contributions | |
BW | -0.050 |
ciating | -0.043 |
bons | -0.043 |
nb | -0.043 |
Moz | -0.042 |
Token | off |
Token ID | 572 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
BW | +0.566 |
bons | +0.485 |
nb | +0.483 |
Moz | +0.479 |
ciating | +0.478 |
Neg logit contributions | |
Eng | -0.535 |
millenn | -0.471 |
Gar | -0.469 |
BUG | -0.458 |
cel | -0.450 |
Token | we |
Token ID | 356 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Eng | +0.895 |
millenn | +0.784 |
Gar | +0.780 |
BUG | +0.757 |
cel | +0.754 |
Neg logit contributions | |
BW | -0.990 |
bons | -0.858 |
ciating | -0.856 |
nb | -0.855 |
Moz | -0.841 |
Token | ome |
Token ID | 462 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
BW | +1.121 |
nb | +0.898 |
ciating | +0.885 |
bons | +0.858 |
McAuliffe | +0.841 |
Neg logit contributions | |
Eng | -2.285 |
millenn | -2.142 |
Gar | -2.097 |
BUG | -2.079 |
Frameworks | -2.039 |
Token | for |
Token ID | 329 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
BW | +0.004 |
bons | +0.004 |
ciating | +0.004 |
nb | +0.004 |
Moz | +0.004 |
Neg logit contributions | |
Eng | -0.003 |
millenn | -0.003 |
Gar | -0.003 |
BUG | -0.003 |
cel | -0.003 |
Token | me |
Token ID | 502 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
BW | +0.254 |
bons | +0.217 |
nb | +0.217 |
ciating | +0.216 |
Moz | +0.214 |
Neg logit contributions | |
Eng | -0.256 |
millenn | -0.227 |
Gar | -0.225 |
BUG | -0.219 |
cel | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
BW | +1.574 |
nb | +1.367 |
bons | +1.367 |
ciating | +1.364 |
Moz | +1.345 |
Neg logit contributions | |
Eng | -1.276 |
millenn | -1.123 |
Gar | -1.103 |
BUG | -1.072 |
cel | -1.059 |
Token | Judging |
Token ID | 47024 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
BW | +0.164 |
bons | +0.141 |
nb | +0.141 |
ciating | +0.141 |
Moz | +0.139 |
Neg logit contributions | |
Eng | -0.151 |
millenn | -0.134 |
Gar | -0.132 |
BUG | -0.128 |
cel | -0.128 |
Token | by |
Token ID | 416 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
Eng | +0.036 |
millenn | +0.032 |
Gar | +0.032 |
BUG | +0.031 |
cel | +0.031 |
Neg logit contributions | |
BW | -0.038 |
bons | -0.033 |
ciating | -0.033 |
nb | -0.033 |
Moz | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
BW | +4.829 |
Moz | +4.037 |
bons | +4.024 |
nb | +4.000 |
McAuliffe | +3.949 |
Neg logit contributions | |
Eng | -5.227 |
millenn | -4.764 |
Gar | -4.701 |
BUG | -4.633 |
Frameworks | -4.522 |
Token | comments |
Token ID | 3651 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
BW | +1.272 |
bons | +1.088 |
nb | +1.084 |
ciating | +1.078 |
Moz | +1.074 |
Neg logit contributions | |
Eng | -1.198 |
millenn | -1.058 |
Gar | -1.057 |
BUG | -1.024 |
cel | -1.004 |
Token | around |
Token ID | 1088 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Eng | +0.608 |
millenn | +0.535 |
Gar | +0.532 |
BUG | +0.516 |
cel | +0.515 |
Neg logit contributions | |
BW | -0.641 |
ciating | -0.554 |
bons | -0.554 |
nb | -0.552 |
Moz | -0.542 |
Token | I |
Token ID | 314 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
BW | +0.121 |
bons | +0.104 |
nb | +0.103 |
ciating | +0.103 |
Moz | +0.102 |
Neg logit contributions | |
Eng | -0.118 |
millenn | -0.104 |
Gar | -0.104 |
BUG | -0.101 |
cel | -0.100 |
Token | � |
Token ID | 447 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Eng | +0.703 |
millenn | +0.616 |
Gar | +0.613 |
BUG | +0.594 |
cel | +0.593 |
Neg logit contributions | |
BW | -0.778 |
bons | -0.675 |
ciating | -0.674 |
nb | -0.672 |
Moz | -0.661 |
Token | a |
Token ID | 257 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
BW | +1.923 |
bons | +1.640 |
nb | +1.630 |
Moz | +1.629 |
ciating | +1.610 |
Neg logit contributions | |
Eng | -1.872 |
millenn | -1.660 |
Gar | -1.640 |
BUG | -1.606 |
cel | -1.567 |
Token | recent |
Token ID | 2274 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
BW | +0.873 |
bons | +0.749 |
nb | +0.745 |
ciating | +0.741 |
Moz | +0.739 |
Neg logit contributions | |
Eng | -0.798 |
millenn | -0.700 |
Gar | -0.694 |
BUG | -0.675 |
cel | -0.666 |
Token | thing |
Token ID | 1517 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
BW | +0.394 |
bons | +0.340 |
nb | +0.339 |
ciating | +0.338 |
Moz | +0.335 |
Neg logit contributions | |
Eng | -0.353 |
millenn | -0.309 |
Gar | -0.308 |
BUG | -0.298 |
cel | -0.296 |
Token | ? |
Token ID | 30 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
BW | +1.570 |
nb | +1.339 |
bons | +1.338 |
ciating | +1.326 |
Moz | +1.323 |
Neg logit contributions | |
Eng | -1.563 |
millenn | -1.397 |
Gar | -1.369 |
BUG | -1.343 |
cel | -1.325 |
Token | Think |
Token ID | 11382 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
BW | +1.591 |
nb | +1.359 |
bons | +1.357 |
Moz | +1.345 |
ciating | +1.340 |
Neg logit contributions | |
Eng | -1.551 |
millenn | -1.408 |
Gar | -1.361 |
BUG | -1.329 |
cel | -1.323 |
Token | again |
Token ID | 757 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
BW | +2.422 |
nb | +2.083 |
bons | +2.081 |
ciating | +2.061 |
Moz | +2.051 |
Neg logit contributions | |
Eng | -2.173 |
millenn | -1.908 |
Gar | -1.887 |
BUG | -1.836 |
cel | -1.822 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
BW | +5.245 |
Moz | +4.417 |
nb | +4.417 |
bons | +4.402 |
McAuliffe | +4.368 |
Neg logit contributions | |
Eng | -4.885 |
millenn | -4.449 |
Gar | -4.250 |
BUG | -4.166 |
Frameworks | -4.118 |
Token | Here |
Token ID | 3423 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
BW | +0.999 |
bons | +0.867 |
nb | +0.865 |
ciating | +0.864 |
Moz | +0.852 |
Neg logit contributions | |
Eng | -0.864 |
millenn | -0.762 |
Gar | -0.750 |
BUG | -0.728 |
cel | -0.726 |
Token | 's |
Token ID | 338 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
BW | +1.048 |
bons | +0.913 |
ciating | +0.912 |
nb | +0.910 |
Moz | +0.896 |
Neg logit contributions | |
Eng | -0.869 |
millenn | -0.757 |
Gar | -0.752 |
BUG | -0.728 |
cel | -0.726 |
Token | how |
Token ID | 703 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
BW | +1.213 |
bons | +1.036 |
ciating | +1.034 |
nb | +1.034 |
Moz | +1.021 |
Neg logit contributions | |
Eng | -1.240 |
millenn | -1.100 |
Gar | -1.091 |
BUG | -1.063 |
cel | -1.055 |
Token | Wales |
Token ID | 11769 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
BW | +0.908 |
bons | +0.773 |
ciating | +0.770 |
nb | +0.769 |
Moz | +0.764 |
Neg logit contributions | |
Eng | -0.935 |
millenn | -0.829 |
Gar | -0.822 |
BUG | -0.802 |
cel | -0.795 |
Token | [ |
Token ID | 58 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
BW | +1.919 |
nb | +1.659 |
bons | +1.650 |
ciating | +1.640 |
Moz | +1.609 |
Neg logit contributions | |
Eng | -1.866 |
millenn | -1.676 |
Gar | -1.645 |
BUG | -1.597 |
cel | -1.587 |
Token | CO |
Token ID | 8220 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
BW | +0.253 |
bons | +0.197 |
ciating | +0.197 |
nb | +0.196 |
Moz | +0.189 |
Neg logit contributions | |
Eng | -0.552 |
millenn | -0.505 |
Gar | -0.503 |
BUG | -0.493 |
cel | -0.492 |
Token | 2 |
Token ID | 362 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
BW | +2.134 |
nb | +1.759 |
bons | +1.758 |
Moz | +1.728 |
bonding | +1.685 |
Neg logit contributions | |
Eng | -2.615 |
millenn | -2.464 |
Gar | -2.348 |
BUG | -2.284 |
acy | -2.245 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
BW | +2.744 |
bons | +2.359 |
nb | +2.342 |
ciating | +2.328 |
Moz | +2.300 |
Neg logit contributions | |
Eng | -2.815 |
millenn | -2.492 |
Gar | -2.485 |
BUG | -2.435 |
cel | -2.395 |
Token | / |
Token ID | 14 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
BW | +2.262 |
bons | +1.968 |
nb | +1.966 |
ciating | +1.934 |
Moz | +1.923 |
Neg logit contributions | |
Eng | -1.990 |
millenn | -1.774 |
Gar | -1.751 |
BUG | -1.698 |
cel | -1.667 |
Token | dt |
Token ID | 28664 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
BW | +2.374 |
nb | +2.031 |
bons | +2.016 |
ciating | +2.003 |
Moz | +1.960 |
Neg logit contributions | |
Eng | -2.719 |
millenn | -2.441 |
Gar | -2.415 |
BUG | -2.367 |
cel | -2.346 |
Token | computed |
Token ID | 29231 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
BW | +5.178 |
nb | +4.467 |
Moz | +4.373 |
bons | +4.366 |
ciating | +4.281 |
Neg logit contributions | |
Eng | -4.703 |
millenn | -4.262 |
Gar | -4.186 |
BUG | -4.035 |
Frameworks | -3.977 |
Token | for |
Token ID | 329 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
BW | +2.506 |
nb | +2.123 |
bons | +2.117 |
Moz | +2.089 |
ciating | +2.054 |
Neg logit contributions | |
Eng | -2.556 |
millenn | -2.335 |
Gar | -2.289 |
BUG | -2.221 |
Frameworks | -2.196 |
Token | d |
Token ID | 288 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
BW | +0.440 |
bons | +0.378 |
nb | +0.376 |
ciating | +0.376 |
Moz | +0.371 |
Neg logit contributions | |
Eng | -0.436 |
millenn | -0.385 |
Gar | -0.382 |
BUG | -0.373 |
cel | -0.368 |
Token | t |
Token ID | 83 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
BW | +0.578 |
bons | +0.499 |
ciating | +0.499 |
nb | +0.498 |
Moz | +0.489 |
Neg logit contributions | |
Eng | -0.547 |
millenn | -0.482 |
Gar | -0.478 |
BUG | -0.464 |
cel | -0.463 |
Token | = |
Token ID | 28 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
BW | +1.012 |
bons | +0.873 |
nb | +0.871 |
ciating | +0.869 |
Moz | +0.854 |
Neg logit contributions | |
Eng | -0.964 |
millenn | -0.852 |
Gar | -0.846 |
BUG | -0.821 |
cel | -0.815 |
Token | ? |
Token ID | 30 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Eng | +1.203 |
Gar | +1.036 |
millenn | +1.031 |
cel | +1.012 |
BUG | +0.993 |
Neg logit contributions | |
BW | -1.454 |
ciating | -1.299 |
bons | -1.284 |
nb | -1.274 |
Moz | -1.248 |
Token | Everything |
Token ID | 11391 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
Eng | +1.873 |
Gar | +1.646 |
millenn | +1.609 |
cel | +1.603 |
BUG | +1.591 |
Neg logit contributions | |
BW | -1.754 |
ciating | -1.531 |
bons | -1.521 |
nb | -1.508 |
enhagen | -1.476 |
Token | is |
Token ID | 318 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
BW | +0.629 |
bons | +0.542 |
nb | +0.540 |
ciating | +0.539 |
Moz | +0.533 |
Neg logit contributions | |
Eng | -0.577 |
millenn | -0.510 |
Gar | -0.503 |
BUG | -0.489 |
cel | -0.486 |
Token | somebody |
Token ID | 8276 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
Eng | +1.348 |
Gar | +1.186 |
millenn | +1.180 |
cel | +1.169 |
BUG | +1.152 |
Neg logit contributions | |
BW | -1.317 |
ciating | -1.161 |
bons | -1.144 |
nb | -1.142 |
Moz | -1.107 |
Token | 's |
Token ID | 338 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
BW | +0.613 |
bons | +0.527 |
ciating | +0.527 |
nb | +0.525 |
Moz | +0.515 |
Neg logit contributions | |
Eng | -0.625 |
millenn | -0.552 |
Gar | -0.550 |
BUG | -0.534 |
cel | -0.533 |
Token | fault |
Token ID | 8046 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
Eng | +2.115 |
millenn | +1.745 |
Gar | +1.741 |
cel | +1.699 |
BUG | +1.655 |
Neg logit contributions | |
BW | -4.105 |
ciating | -3.765 |
bons | -3.724 |
nb | -3.697 |
@#& | -3.615 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Eng | +4.328 |
Gar | +3.709 |
cel | +3.679 |
vag | +3.654 |
BUG | +3.497 |
Neg logit contributions | |
BW | -6.160 |
ciating | -5.705 |
bons | -5.514 |
nb | -5.436 |
enhagen | -5.394 |
Token | dam |
Token ID | 1801 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
Eng | +1.214 |
Gar | +1.061 |
millenn | +1.055 |
cel | +1.035 |
BUG | +1.025 |
Neg logit contributions | |
BW | -1.287 |
ciating | -1.125 |
bons | -1.119 |
nb | -1.115 |
Moz | -1.090 |
Token | mit |
Token ID | 2781 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Eng | +2.122 |
Gar | +1.786 |
millenn | +1.779 |
BUG | +1.722 |
cel | +1.710 |
Neg logit contributions | |
BW | -3.349 |
ciating | -3.020 |
bons | -2.950 |
nb | -2.942 |
Moz | -2.927 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
BW | +0.366 |
ciating | +0.321 |
bons | +0.321 |
nb | +0.320 |
Moz | +0.315 |
Neg logit contributions | |
Eng | -0.273 |
millenn | -0.235 |
Gar | -0.234 |
BUG | -0.226 |
cel | -0.226 |
Token | Probably |
Token ID | 18578 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Eng | +1.322 |
Gar | +1.161 |
millenn | +1.127 |
cel | +1.125 |
BUG | +1.119 |
Neg logit contributions | |
BW | -1.278 |
ciating | -1.120 |
bons | -1.107 |
nb | -1.100 |
enhagen | -1.077 |
Token | them |
Token ID | 606 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Eng | +0.056 |
millenn | +0.049 |
Gar | +0.049 |
BUG | +0.047 |
cel | +0.047 |
Neg logit contributions | |
BW | -0.057 |
bons | -0.049 |
ciating | -0.049 |
nb | -0.049 |
Moz | -0.048 |
Token | ". |
Token ID | 1911 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
BW | +0.242 |
bons | +0.210 |
ciating | +0.210 |
nb | +0.209 |
Moz | +0.206 |
Neg logit contributions | |
Eng | -0.216 |
millenn | -0.190 |
Gar | -0.188 |
BUG | -0.183 |
cel | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Eng | +1.355 |
Gar | +1.159 |
BUG | +1.107 |
cel | +1.105 |
millenn | +1.086 |
Neg logit contributions | |
BW | -1.951 |
ciating | -1.745 |
bons | -1.725 |
nb | -1.711 |
Moz | -1.684 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Eng | +1.327 |
millenn | +1.167 |
Gar | +1.139 |
BUG | +1.101 |
cel | +1.099 |
Neg logit contributions | |
BW | -1.752 |
bons | -1.537 |
nb | -1.533 |
ciating | -1.529 |
Moz | -1.509 |
Token | Topics |
Token ID | 25902 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
Eng | +1.089 |
Gar | +0.943 |
millenn | +0.918 |
BUG | +0.908 |
cel | +0.895 |
Neg logit contributions | |
BW | -1.330 |
ciating | -1.162 |
bons | -1.153 |
nb | -1.145 |
Moz | -1.135 |
Token | : |
Token ID | 25 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
BW | +0.039 |
nb | +0.033 |
bons | +0.032 |
ciating | +0.032 |
Moz | +0.032 |
Neg logit contributions | |
Eng | -0.047 |
millenn | -0.044 |
Gar | -0.042 |
BUG | -0.041 |
cel | -0.041 |
Token | marine |
Token ID | 16050 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Eng | +4.671 |
millenn | +4.207 |
cel | +4.162 |
vag | +4.118 |
Gar | +4.096 |
Neg logit contributions | |
BW | -5.474 |
ciating | -4.957 |
enhagen | -4.922 |
nb | -4.826 |
bons | -4.773 |
Token | - |
Token ID | 12 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Eng | +0.879 |
Gar | +0.749 |
millenn | +0.742 |
cel | +0.719 |
BUG | +0.718 |
Neg logit contributions | |
BW | -1.332 |
ciating | -1.192 |
nb | -1.178 |
bons | -1.175 |
Moz | -1.161 |
Token | biology |
Token ID | 43592 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Eng | +2.322 |
Gar | +2.035 |
BUG | +1.978 |
acy | +1.950 |
cel | +1.917 |
Neg logit contributions | |
BW | -2.606 |
ciating | -2.308 |
McAuliffe | -2.261 |
enhagen | -2.233 |
Moz | -2.219 |
Token | , |
Token ID | 11 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
Eng | +0.365 |
millenn | +0.343 |
Gar | +0.319 |
BUG | +0.307 |
cel | +0.304 |
Neg logit contributions | |
BW | -0.420 |
bons | -0.366 |
nb | -0.362 |
Moz | -0.355 |
McAuliffe | -0.351 |
Token | conservation |
Token ID | 14903 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Eng | +2.632 |
millenn | +2.355 |
Gar | +2.308 |
cel | +2.305 |
vag | +2.266 |
Neg logit contributions | |
BW | -2.774 |
ciating | -2.465 |
nb | -2.410 |
enhagen | -2.403 |
bons | -2.394 |
Token | story |
Token ID | 1621 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
BW | +1.573 |
nb | +1.364 |
bons | +1.358 |
Moz | +1.356 |
ciating | +1.339 |
Neg logit contributions | |
Eng | -1.168 |
millenn | -1.052 |
Gar | -1.008 |
BUG | -0.975 |
cel | -0.970 |
Token | : |
Token ID | 25 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
BW | +0.596 |
bons | +0.503 |
nb | +0.502 |
ciating | +0.495 |
Moz | +0.491 |
Neg logit contributions | |
Eng | -0.733 |
millenn | -0.678 |
Gar | -0.654 |
BUG | -0.637 |
cel | -0.636 |
Token | http |
Token ID | 2638 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Eng | +0.759 |
Gar | +0.651 |
millenn | +0.649 |
cel | +0.637 |
BUG | +0.626 |
Neg logit contributions | |
BW | -0.960 |
bons | -0.848 |
ciating | -0.846 |
nb | -0.840 |
Moz | -0.830 |
Token | :// |
Token ID | 1378 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
Eng | +1.286 |
Gar | +1.093 |
millenn | +1.078 |
BUG | +1.051 |
cel | +1.049 |
Neg logit contributions | |
BW | -1.852 |
ciating | -1.637 |
bons | -1.631 |
nb | -1.622 |
Moz | -1.604 |
Token | usat |
Token ID | 37937 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
Eng | +4.455 |
Gar | +3.917 |
acy | +3.730 |
cel | +3.694 |
aminer | +3.690 |
Neg logit contributions | |
BW | -4.612 |
McAuliffe | -3.976 |
ciating | -3.962 |
Moz | -3.959 |
Grounds | -3.902 |
Token | . |
Token ID | 13 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
Eng | +2.497 |
Gar | +2.096 |
BUG | +2.016 |
cel | +1.983 |
acy | +1.945 |
Neg logit contributions | |
BW | -3.900 |
ciating | -3.509 |
bons | -3.449 |
nb | -3.419 |
Moz | -3.397 |
Token | ly |
Token ID | 306 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Eng | +3.704 |
Gar | +3.043 |
acy | +2.895 |
BUG | +2.856 |
cel | +2.850 |
Neg logit contributions | |
BW | -6.728 |
ciating | -6.049 |
Moz | -5.931 |
@#& | -5.927 |
bons | -5.922 |
Token | / |
Token ID | 14 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Eng | +1.027 |
millenn | +0.919 |
Gar | +0.890 |
cel | +0.863 |
BUG | +0.861 |
Neg logit contributions | |
BW | -1.259 |
bons | -1.099 |
nb | -1.098 |
ciating | -1.087 |
Moz | -1.079 |
Token | 1 |
Token ID | 16 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Eng | +0.954 |
Gar | +0.822 |
millenn | +0.807 |
BUG | +0.792 |
cel | +0.781 |
Neg logit contributions | |
BW | -1.187 |
ciating | -1.038 |
bons | -1.037 |
nb | -1.022 |
Moz | -1.016 |
Token | G |
Token ID | 38 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Eng | +0.225 |
millenn | +0.197 |
Gar | +0.197 |
BUG | +0.191 |
cel | +0.190 |
Neg logit contributions | |
BW | -0.236 |
ciating | -0.204 |
bons | -0.204 |
nb | -0.203 |
Moz | -0.200 |
Token | q |
Token ID | 80 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Eng | +0.959 |
Gar | +0.843 |
millenn | +0.836 |
BUG | +0.818 |
cel | +0.812 |
Neg logit contributions | |
BW | -0.939 |
ciating | -0.808 |
bons | -0.803 |
nb | -0.793 |
Moz | -0.788 |
Token | h |
Token ID | 71 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
Eng | +0.020 |
millenn | +0.017 |
Gar | +0.017 |
BUG | +0.016 |
cel | +0.016 |
Neg logit contributions | |
BW | -0.030 |
bons | -0.026 |
nb | -0.026 |
ciating | -0.026 |
Moz | -0.026 |
Token | irts |
Token ID | 9682 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Eng | +2.356 |
Gar | +2.104 |
BUG | +2.015 |
millenn | +2.007 |
acy | +2.007 |
Neg logit contributions | |
BW | -1.914 |
ciating | -1.671 |
nb | -1.622 |
Moz | -1.621 |
bons | -1.611 |
Token | , |
Token ID | 11 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Eng | +1.499 |
Gar | +1.310 |
millenn | +1.285 |
cel | +1.271 |
BUG | +1.242 |
Neg logit contributions | |
BW | -1.737 |
ciating | -1.544 |
nb | -1.515 |
bons | -1.511 |
Moz | -1.491 |
Token | M |
Token ID | 337 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Eng | +0.425 |
millenn | +0.373 |
Gar | +0.372 |
cel | +0.361 |
BUG | +0.360 |
Neg logit contributions | |
BW | -0.452 |
ciating | -0.393 |
nb | -0.391 |
bons | -0.391 |
Moz | -0.383 |
Token | ardi |
Token ID | 22490 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Eng | +0.924 |
millenn | +0.809 |
Gar | +0.801 |
BUG | +0.777 |
cel | +0.775 |
Neg logit contributions | |
BW | -1.085 |
bons | -0.945 |
nb | -0.942 |
ciating | -0.942 |
Moz | -0.927 |
Token | Gr |
Token ID | 1902 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
BW | +1.373 |
Moz | +1.139 |
bons | +1.139 |
ciating | +1.109 |
McAuliffe | +1.109 |
Neg logit contributions | |
Eng | -1.493 |
millenn | -1.363 |
erness | -1.288 |
acy | -1.286 |
BUG | -1.284 |
Token | as |
Token ID | 292 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Eng | +3.213 |
acy | +2.521 |
Gar | +2.484 |
atism | +2.365 |
cel | +2.350 |
Neg logit contributions | |
BW | -7.200 |
ciating | -6.534 |
enhagen | -6.381 |
nb | -6.377 |
Moz | -6.337 |
Token | beads |
Token ID | 36116 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
BW | +0.164 |
bons | +0.140 |
ciating | +0.140 |
nb | +0.140 |
Moz | +0.137 |
Neg logit contributions | |
Eng | -0.181 |
millenn | -0.161 |
Gar | -0.160 |
BUG | -0.156 |
cel | -0.155 |
Token | and |
Token ID | 290 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Eng | +0.869 |
Gar | +0.760 |
millenn | +0.748 |
cel | +0.736 |
BUG | +0.728 |
Neg logit contributions | |
BW | -0.955 |
ciating | -0.840 |
nb | -0.827 |
bons | -0.824 |
Moz | -0.813 |
Token | CD |
Token ID | 6458 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
BW | +0.252 |
bons | +0.218 |
ciating | +0.217 |
nb | +0.217 |
Moz | +0.213 |
Neg logit contributions | |
Eng | -0.241 |
millenn | -0.212 |
Gar | -0.211 |
BUG | -0.205 |
cel | -0.204 |
Token | � |
Token ID | 447 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
BW | +2.435 |
bons | +2.102 |
nb | +2.042 |
Moz | +2.012 |
ciating | +2.007 |
Neg logit contributions | |
Eng | -2.523 |
millenn | -2.284 |
Gar | -2.213 |
BUG | -2.175 |
atism | -2.130 |
Token | story |
Token ID | 1621 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
BW | +1.829 |
nb | +1.582 |
bons | +1.574 |
Moz | +1.570 |
ciating | +1.551 |
Neg logit contributions | |
Eng | -1.382 |
millenn | -1.250 |
Gar | -1.194 |
BUG | -1.161 |
cel | -1.152 |
Token | : |
Token ID | 25 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
BW | +0.888 |
bons | +0.747 |
nb | +0.746 |
ciating | +0.732 |
Moz | +0.730 |
Neg logit contributions | |
Eng | -1.112 |
millenn | -1.042 |
Gar | -0.994 |
BUG | -0.968 |
cel | -0.967 |
Token | http |
Token ID | 2638 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Eng | +0.690 |
Gar | +0.590 |
millenn | +0.586 |
cel | +0.576 |
BUG | +0.563 |
Neg logit contributions | |
BW | -0.901 |
bons | -0.800 |
ciating | -0.798 |
nb | -0.791 |
Moz | -0.782 |
Token | :// |
Token ID | 1378 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
Eng | +1.188 |
Gar | +1.009 |
millenn | +0.992 |
BUG | +0.970 |
cel | +0.968 |
Neg logit contributions | |
BW | -1.719 |
ciating | -1.521 |
bons | -1.515 |
nb | -1.505 |
Moz | -1.490 |
Token | usat |
Token ID | 37937 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
Eng | +4.119 |
Gar | +3.596 |
acy | +3.452 |
aminer | +3.423 |
millenn | +3.416 |
Neg logit contributions | |
BW | -4.423 |
ciating | -3.790 |
Moz | -3.776 |
McAuliffe | -3.759 |
Grounds | -3.726 |
Token | . |
Token ID | 13 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
Eng | +2.445 |
Gar | +2.051 |
BUG | +1.971 |
cel | +1.940 |
acy | +1.904 |
Neg logit contributions | |
BW | -3.834 |
ciating | -3.456 |
bons | -3.392 |
nb | -3.363 |
Moz | -3.342 |
Token | ly |
Token ID | 306 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Eng | +3.704 |
Gar | +3.058 |
acy | +2.898 |
cel | +2.869 |
BUG | +2.865 |
Neg logit contributions | |
BW | -6.609 |
ciating | -5.928 |
Moz | -5.824 |
nb | -5.821 |
bons | -5.811 |
Token | / |
Token ID | 14 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
Eng | +1.006 |
millenn | +0.904 |
Gar | +0.873 |
cel | +0.847 |
BUG | +0.844 |
Neg logit contributions | |
BW | -1.230 |
bons | -1.073 |
nb | -1.072 |
ciating | -1.060 |
Moz | -1.053 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
Eng | +0.641 |
Gar | +0.552 |
millenn | +0.547 |
BUG | +0.533 |
cel | +0.528 |
Neg logit contributions | |
BW | -0.795 |
ciating | -0.696 |
bons | -0.694 |
nb | -0.687 |
Moz | -0.681 |
Token | f |
Token ID | 69 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
BW | +0.029 |
bons | +0.025 |
ciating | +0.025 |
nb | +0.025 |
Moz | +0.024 |
Neg logit contributions | |
Eng | -0.028 |
millenn | -0.024 |
Gar | -0.024 |
BUG | -0.023 |
cel | -0.023 |
Token | H |
Token ID | 39 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Eng | +0.040 |
millenn | +0.035 |
Gar | +0.035 |
BUG | +0.034 |
cel | +0.034 |
Neg logit contributions | |
BW | -0.045 |
bons | -0.039 |
ciating | -0.039 |
nb | -0.039 |
Moz | -0.038 |
Token | 24 |
Token ID | 1987 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Eng | +0.210 |
millenn | +0.183 |
Gar | +0.182 |
BUG | +0.176 |
cel | +0.176 |
Neg logit contributions | |
BW | -0.249 |
bons | -0.217 |
ciating | -0.216 |
nb | -0.216 |
Moz | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Eng | +0.321 |
millenn | +0.278 |
Gar | +0.276 |
BUG | +0.267 |
cel | +0.266 |
Neg logit contributions | |
BW | -0.422 |
bons | -0.370 |
ciating | -0.370 |
nb | -0.369 |
Moz | -0.363 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Eng | +0.642 |
Gar | +0.546 |
millenn | +0.543 |
BUG | +0.525 |
cel | +0.524 |
Neg logit contributions | |
BW | -0.923 |
ciating | -0.821 |
bons | -0.816 |
nb | -0.811 |
Moz | -0.801 |
Token |
|
Token ID | 198 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
Eng | +0.779 |
millenn | +0.726 |
Gar | +0.673 |
BUG | +0.652 |
cel | +0.652 |
Neg logit contributions | |
BW | -0.983 |
nb | -0.860 |
bons | -0.860 |
Moz | -0.845 |
ciating | -0.840 |
Token | Topics |
Token ID | 25902 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
Eng | +0.459 |
millenn | +0.394 |
Gar | +0.392 |
BUG | +0.377 |
cel | +0.376 |
Neg logit contributions | |
BW | -0.656 |
bons | -0.578 |
ciating | -0.578 |
nb | -0.576 |
Moz | -0.568 |
Token | : |
Token ID | 25 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
BW | +0.065 |
nb | +0.055 |
bons | +0.055 |
ciating | +0.054 |
Moz | +0.054 |
Neg logit contributions | |
Eng | -0.081 |
millenn | -0.075 |
Gar | -0.072 |
BUG | -0.071 |
cel | -0.070 |
Token | beef |
Token ID | 12023 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Eng | +3.993 |
millenn | +3.537 |
cel | +3.518 |
Gar | +3.419 |
vag | +3.394 |
Neg logit contributions | |
BW | -5.934 |
ciating | -5.449 |
enhagen | -5.344 |
nb | -5.311 |
@#& | -5.303 |
Token | - |
Token ID | 12 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Eng | +1.744 |
Gar | +1.491 |
millenn | +1.486 |
cel | +1.439 |
BUG | +1.428 |
Neg logit contributions | |
BW | -2.410 |
ciating | -2.129 |
nb | -2.115 |
bons | -2.104 |
Moz | -2.079 |
Token | c |
Token ID | 66 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Eng | +2.159 |
Gar | +1.884 |
BUG | +1.814 |
millenn | +1.812 |
cel | +1.811 |
Neg logit contributions | |
BW | -2.534 |
ciating | -2.230 |
McAuliffe | -2.165 |
nb | -2.161 |
Moz | -2.156 |
Token | attle |
Token ID | 1999 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
Eng | +0.750 |
Gar | +0.648 |
millenn | +0.639 |
BUG | +0.624 |
cel | +0.621 |
Neg logit contributions | |
BW | -0.940 |
ciating | -0.824 |
bons | -0.821 |
nb | -0.816 |
Moz | -0.808 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
Eng | +2.167 |
Gar | +1.866 |
millenn | +1.818 |
BUG | +1.793 |
cel | +1.775 |
Neg logit contributions | |
BW | -3.145 |
ciating | -2.832 |
nb | -2.777 |
Moz | -2.747 |
bons | -2.732 |
Token | sinks |
Token ID | 38614 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Eng | +1.413 |
millenn | +1.247 |
Gar | +1.238 |
cel | +1.222 |
vag | +1.200 |
Neg logit contributions | |
BW | -1.228 |
ciating | -1.086 |
bons | -1.043 |
nb | -1.039 |
Moz | -1.027 |
Token | . |
Token ID | 13 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Eng | +0.366 |
millenn | +0.317 |
Gar | +0.316 |
BUG | +0.305 |
cel | +0.305 |
Neg logit contributions | |
BW | -0.454 |
ciating | -0.397 |
bons | -0.397 |
nb | -0.396 |
Moz | -0.389 |
Token | The |
Token ID | 383 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
BW | +0.430 |
bons | +0.373 |
nb | +0.372 |
ciating | +0.370 |
Moz | +0.366 |
Neg logit contributions | |
Eng | -0.367 |
millenn | -0.326 |
Gar | -0.320 |
cel | -0.311 |
BUG | -0.310 |
Token | two |
Token ID | 734 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
BW | +0.661 |
bons | +0.570 |
ciating | +0.566 |
nb | +0.565 |
Moz | +0.560 |
Neg logit contributions | |
Eng | -0.586 |
millenn | -0.515 |
Gar | -0.514 |
BUG | -0.496 |
cel | -0.494 |
Token | form |
Token ID | 1296 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
Eng | +0.253 |
millenn | +0.224 |
Gar | +0.223 |
BUG | +0.216 |
cel | +0.216 |
Neg logit contributions | |
BW | -0.243 |
bons | -0.209 |
ciating | -0.209 |
nb | -0.208 |
Moz | -0.204 |
Token | - |
Token ID | 12 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
Eng | +1.869 |
millenn | +1.546 |
Gar | +1.537 |
cel | +1.516 |
BUG | +1.481 |
Neg logit contributions | |
BW | -3.098 |
ciating | -2.780 |
nb | -2.748 |
bons | -2.733 |
Moz | -2.714 |
Token | in |
Token ID | 259 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
Eng | +3.709 |
Gar | +3.073 |
acy | +2.981 |
BUG | +2.929 |
erness | +2.890 |
Neg logit contributions | |
BW | -6.347 |
ciating | -5.649 |
Moz | -5.646 |
McAuliffe | -5.587 |
Ples | -5.481 |
Token | - |
Token ID | 12 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Eng | +1.417 |
Gar | +1.175 |
millenn | +1.172 |
cel | +1.147 |
BUG | +1.119 |
Neg logit contributions | |
BW | -2.302 |
nb | -2.050 |
ciating | -2.050 |
bons | -2.040 |
McAuliffe | -2.022 |
Token | one |
Token ID | 505 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Eng | +1.442 |
Gar | +1.225 |
BUG | +1.183 |
millenn | +1.170 |
acy | +1.163 |
Neg logit contributions | |
BW | -2.108 |
ciating | -1.873 |
McAuliffe | -1.847 |
Moz | -1.832 |
nb | -1.810 |
Token | heat |
Token ID | 4894 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Eng | +1.402 |
millenn | +1.223 |
Gar | +1.215 |
cel | +1.187 |
BUG | +1.178 |
Neg logit contributions | |
BW | -1.523 |
ciating | -1.348 |
nb | -1.335 |
bons | -1.328 |
Moz | -1.301 |
Token | sinks |
Token ID | 38614 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Eng | +1.251 |
millenn | +1.102 |
Gar | +1.094 |
cel | +1.075 |
BUG | +1.066 |
Neg logit contributions | |
BW | -1.122 |
ciating | -0.982 |
bons | -0.956 |
nb | -0.949 |
Moz | -0.944 |
Token | It |
Token ID | 632 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Eng | +0.413 |
Gar | +0.363 |
millenn | +0.360 |
BUG | +0.352 |
cel | +0.352 |
Neg logit contributions | |
BW | -0.400 |
ciating | -0.346 |
bons | -0.345 |
nb | -0.343 |
Moz | -0.336 |
Token | � |
Token ID | 447 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Eng | +1.496 |
Gar | +1.317 |
millenn | +1.285 |
cel | +1.272 |
BUG | +1.271 |
Neg logit contributions | |
BW | -1.538 |
ciating | -1.348 |
bons | -1.332 |
nb | -1.322 |
Moz | -1.307 |
Token | � |
Token ID | 247 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Eng | +0.560 |
millenn | +0.478 |
Gar | +0.462 |
BUG | +0.441 |
cel | +0.441 |
Neg logit contributions | |
BW | -1.049 |
bons | -0.933 |
nb | -0.932 |
ciating | -0.926 |
Moz | -0.915 |
Token | s |
Token ID | 82 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
Eng | +0.237 |
Gar | +0.208 |
millenn | +0.205 |
BUG | +0.201 |
cel | +0.201 |
Neg logit contributions | |
BW | -0.247 |
ciating | -0.214 |
bons | -0.212 |
nb | -0.211 |
Moz | -0.209 |
Token | my |
Token ID | 616 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Eng | +0.437 |
millenn | +0.382 |
Gar | +0.381 |
BUG | +0.369 |
cel | +0.369 |
Neg logit contributions | |
BW | -0.478 |
ciating | -0.415 |
bons | -0.414 |
nb | -0.413 |
Moz | -0.406 |
Token | fault |
Token ID | 8046 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
Eng | +1.140 |
millenn | +0.959 |
Gar | +0.956 |
cel | +0.920 |
BUG | +0.915 |
Neg logit contributions | |
BW | -1.871 |
ciating | -1.669 |
bons | -1.669 |
nb | -1.659 |
Moz | -1.636 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Eng | +4.197 |
Gar | +3.575 |
cel | +3.506 |
vag | +3.446 |
millenn | +3.445 |
Neg logit contributions | |
BW | -5.597 |
ciating | -5.113 |
bons | -5.069 |
nb | -4.954 |
Moz | -4.916 |
Token | # |
Token ID | 1303 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Eng | +1.172 |
Gar | +1.028 |
millenn | +1.001 |
cel | +0.996 |
BUG | +0.994 |
Neg logit contributions | |
BW | -1.186 |
ciating | -1.042 |
bons | -1.035 |
nb | -1.024 |
Moz | -1.004 |
Token | atl |
Token ID | 25864 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
BW | +1.284 |
nb | +1.131 |
bons | +1.127 |
ciating | +1.113 |
Moz | +1.094 |
Neg logit contributions | |
Eng | -1.075 |
millenn | -0.958 |
Gar | -0.929 |
cel | -0.910 |
BUG | -0.903 |
Token | weather |
Token ID | 23563 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
BW | +0.499 |
bons | +0.424 |
ciating | +0.423 |
nb | +0.422 |
Moz | +0.413 |
Neg logit contributions | |
Eng | -0.578 |
millenn | -0.516 |
Gar | -0.512 |
BUG | -0.499 |
cel | -0.498 |
Token | # |
Token ID | 1303 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Eng | +0.352 |
millenn | +0.308 |
Gar | +0.307 |
BUG | +0.297 |
cel | +0.297 |
Neg logit contributions | |
BW | -0.389 |
bons | -0.337 |
ciating | -0.337 |
nb | -0.336 |
Moz | -0.330 |
Token | clothes |
Token ID | 8242 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
BW | +0.928 |
bons | +0.814 |
Moz | +0.800 |
ciating | +0.800 |
nb | +0.799 |
Neg logit contributions | |
Eng | -0.665 |
millenn | -0.576 |
Gar | -0.569 |
BUG | -0.555 |
cel | -0.534 |
Token | , |
Token ID | 11 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Eng | +0.395 |
millenn | +0.348 |
Gar | +0.344 |
BUG | +0.335 |
cel | +0.332 |
Neg logit contributions | |
BW | -0.433 |
bons | -0.375 |
nb | -0.373 |
ciating | -0.373 |
Moz | -0.368 |
Token | no |
Token ID | 645 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
BW | +0.273 |
bons | +0.236 |
ciating | +0.235 |
nb | +0.234 |
Moz | +0.232 |
Neg logit contributions | |
Eng | -0.255 |
millenn | -0.226 |
Gar | -0.223 |
BUG | -0.218 |
cel | -0.214 |
Token | make |
Token ID | 787 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
BW | +0.546 |
bons | +0.479 |
nb | +0.476 |
ciating | +0.473 |
Moz | +0.471 |
Neg logit contributions | |
Eng | -0.418 |
millenn | -0.366 |
Gar | -0.360 |
BUG | -0.352 |
cel | -0.342 |
Token | - |
Token ID | 12 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Eng | +0.696 |
millenn | +0.591 |
Gar | +0.591 |
cel | +0.572 |
BUG | +0.568 |
Neg logit contributions | |
BW | -0.981 |
ciating | -0.867 |
bons | -0.863 |
nb | -0.860 |
Moz | -0.847 |
Token | up |
Token ID | 929 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
Eng | +0.960 |
Gar | +0.772 |
cel | +0.739 |
millenn | +0.729 |
BUG | +0.724 |
Neg logit contributions | |
BW | -1.946 |
ciating | -1.749 |
bons | -1.723 |
nb | -1.718 |
Moz | -1.711 |
Token | and |
Token ID | 290 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Eng | +4.171 |
Gar | +3.589 |
cel | +3.564 |
millenn | +3.523 |
vag | +3.452 |
Neg logit contributions | |
BW | -5.646 |
ciating | -5.121 |
@#& | -4.987 |
nb | -4.975 |
bons | -4.945 |
Token | pulled |
Token ID | 5954 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
BW | +0.402 |
bons | +0.347 |
nb | +0.342 |
Moz | +0.342 |
ciating | +0.341 |
Neg logit contributions | |
Eng | -0.376 |
millenn | -0.332 |
Gar | -0.328 |
BUG | -0.322 |
cel | -0.310 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
BW | +1.162 |
bons | +0.999 |
Moz | +0.985 |
ciating | +0.983 |
McAuliffe | +0.974 |
Neg logit contributions | |
Eng | -1.168 |
millenn | -1.044 |
Gar | -1.029 |
BUG | -1.014 |
atism | -0.982 |
Token | hood |
Token ID | 14263 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
BW | +1.091 |
bons | +0.939 |
Moz | +0.932 |
nb | +0.926 |
ciating | +0.926 |
Neg logit contributions | |
Eng | -1.026 |
millenn | -0.899 |
Gar | -0.897 |
BUG | -0.873 |
Frameworks | -0.852 |
Token | y |
Token ID | 88 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
BW | +0.637 |
nb | +0.540 |
bons | +0.536 |
Moz | +0.526 |
ciating | +0.522 |
Neg logit contributions | |
Eng | -0.779 |
millenn | -0.711 |
Gar | -0.691 |
BUG | -0.680 |
cel | -0.671 |
Token | then |
Token ID | 788 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Eng | +0.260 |
millenn | +0.227 |
Gar | +0.225 |
BUG | +0.218 |
cel | +0.217 |
Neg logit contributions | |
BW | -0.304 |
bons | -0.264 |
ciating | -0.263 |
nb | -0.263 |
Moz | -0.259 |
Token | waking |
Token ID | 23137 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
BW | +0.599 |
nb | +0.517 |
bons | +0.517 |
ciating | +0.514 |
Moz | +0.511 |
Neg logit contributions | |
Eng | -0.494 |
millenn | -0.438 |
Gar | -0.428 |
BUG | -0.413 |
cel | -0.410 |
Token | it |
Token ID | 340 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Eng | +0.785 |
millenn | +0.694 |
Gar | +0.692 |
BUG | +0.672 |
cel | +0.672 |
Neg logit contributions | |
BW | -0.745 |
bons | -0.639 |
ciating | -0.639 |
nb | -0.636 |
Moz | -0.623 |
Token | . |
Token ID | 13 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
Eng | +0.195 |
millenn | +0.175 |
Gar | +0.172 |
BUG | +0.167 |
cel | +0.166 |
Neg logit contributions | |
BW | -0.190 |
bons | -0.162 |
nb | -0.162 |
ciating | -0.161 |
Moz | -0.160 |
Token | W |
Token ID | 370 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Eng | +0.649 |
Gar | +0.567 |
millenn | +0.565 |
BUG | +0.549 |
cel | +0.548 |
Neg logit contributions | |
BW | -0.705 |
ciating | -0.613 |
bons | -0.612 |
nb | -0.609 |
Moz | -0.598 |
Token | ifi |
Token ID | 22238 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
Eng | +1.371 |
Gar | +1.198 |
millenn | +1.192 |
BUG | +1.160 |
cel | +1.155 |
Neg logit contributions | |
BW | -1.492 |
ciating | -1.296 |
bons | -1.293 |
nb | -1.286 |
Moz | -1.269 |
Token | fails |
Token ID | 10143 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Eng | +4.583 |
Gar | +3.964 |
millenn | +3.870 |
BUG | +3.864 |
cel | +3.797 |
Neg logit contributions | |
BW | -5.243 |
ciating | -4.752 |
bons | -4.574 |
nb | -4.532 |
enhagen | -4.495 |
Token | to |
Token ID | 284 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Eng | +1.039 |
millenn | +0.909 |
Gar | +0.909 |
BUG | +0.883 |
cel | +0.882 |
Neg logit contributions | |
BW | -1.085 |
ciating | -0.939 |
bons | -0.938 |
nb | -0.934 |
Moz | -0.918 |
Token | reconnect |
Token ID | 37671 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Eng | +1.345 |
millenn | +1.157 |
Gar | +1.153 |
BUG | +1.114 |
cel | +1.113 |
Neg logit contributions | |
BW | -1.792 |
ciating | -1.576 |
bons | -1.574 |
nb | -1.569 |
Moz | -1.545 |
Token | – |
Token ID | 784 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Eng | +2.898 |
Gar | +2.500 |
cel | +2.445 |
millenn | +2.426 |
BUG | +2.411 |
Neg logit contributions | |
BW | -3.469 |
ciating | -3.078 |
nb | -3.043 |
bons | -3.040 |
Moz | -2.972 |
Token | no |
Token ID | 645 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Eng | +0.733 |
millenn | +0.647 |
Gar | +0.641 |
BUG | +0.621 |
cel | +0.619 |
Neg logit contributions | |
BW | -0.772 |
bons | -0.666 |
ciating | -0.664 |
nb | -0.663 |
Moz | -0.652 |
Token | 366 |
Token ID | 44856 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
BW | +0.392 |
nb | +0.328 |
Moz | +0.326 |
bons | +0.325 |
ciating | +0.324 |
Neg logit contributions | |
Eng | -0.451 |
millenn | -0.410 |
Gar | -0.401 |
cel | -0.388 |
BUG | -0.387 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
BW | +1.449 |
nb | +1.265 |
bons | +1.256 |
ciating | +1.251 |
Moz | +1.247 |
Neg logit contributions | |
Eng | -1.138 |
millenn | -1.003 |
Gar | -0.991 |
BUG | -0.949 |
cel | -0.949 |
Token |
|
Token ID | 198 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
BW | +1.379 |
bons | +1.214 |
nb | +1.212 |
ciating | +1.211 |
Moz | +1.195 |
Neg logit contributions | |
Eng | -0.951 |
millenn | -0.821 |
Gar | -0.810 |
BUG | -0.781 |
cel | -0.779 |
Token |
|
Token ID | 198 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
Eng | +0.493 |
millenn | +0.469 |
Gar | +0.427 |
BUG | +0.414 |
cel | +0.414 |
Neg logit contributions | |
BW | -0.608 |
nb | -0.532 |
bons | -0.530 |
Moz | -0.522 |
ciating | -0.515 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Eng | +0.002 |
millenn | +0.002 |
Gar | +0.002 |
cel | +0.002 |
BUG | +0.002 |
Neg logit contributions | |
BW | -0.003 |
nb | -0.002 |
bons | -0.002 |
ciating | -0.002 |
Moz | -0.002 |
Token | : |
Token ID | 25 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
BW | +0.137 |
nb | +0.116 |
bons | +0.115 |
ciating | +0.113 |
Moz | +0.113 |
Neg logit contributions | |
Eng | -0.169 |
millenn | -0.156 |
Gar | -0.151 |
BUG | -0.148 |
cel | -0.146 |
Token | community |
Token ID | 2055 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Eng | +4.235 |
millenn | +3.749 |
cel | +3.675 |
Gar | +3.644 |
vag | +3.616 |
Neg logit contributions | |
BW | -5.476 |
ciating | -4.945 |
enhagen | -4.827 |
bons | -4.818 |
nb | -4.808 |
Token | - |
Token ID | 12 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Eng | +2.126 |
millenn | +1.837 |
Gar | +1.817 |
BUG | +1.751 |
cel | +1.744 |
Neg logit contributions | |
BW | -2.981 |
bons | -2.624 |
ciating | -2.616 |
nb | -2.614 |
Moz | -2.575 |
Token | and |
Token ID | 392 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Eng | +1.847 |
Gar | +1.591 |
millenn | +1.540 |
BUG | +1.530 |
cel | +1.523 |
Neg logit contributions | |
BW | -2.287 |
ciating | -2.017 |
nb | -1.979 |
Moz | -1.974 |
McAuliffe | -1.968 |
Token | - |
Token ID | 12 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Eng | +1.214 |
millenn | +1.067 |
Gar | +1.040 |
BUG | +1.004 |
cel | +0.997 |
Neg logit contributions | |
BW | -1.630 |
bons | -1.432 |
nb | -1.429 |
ciating | -1.418 |
Moz | -1.402 |
Token | soc |
Token ID | 35634 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Eng | +0.453 |
millenn | +0.410 |
Gar | +0.407 |
BUG | +0.398 |
cel | +0.397 |
Neg logit contributions | |
BW | -0.293 |
bons | -0.241 |
ciating | -0.241 |
nb | -0.240 |
Moz | -0.234 |
Token | Hill |
Token ID | 3327 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Eng | +1.572 |
Gar | +1.379 |
millenn | +1.360 |
BUG | +1.329 |
cel | +1.325 |
Neg logit contributions | |
BW | -1.564 |
ciating | -1.360 |
bons | -1.354 |
nb | -1.349 |
Moz | -1.315 |
Token | ] |
Token ID | 60 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Eng | +0.696 |
Gar | +0.574 |
millenn | +0.573 |
BUG | +0.547 |
cel | +0.545 |
Neg logit contributions | |
BW | -1.280 |
ciating | -1.152 |
bons | -1.150 |
nb | -1.142 |
Moz | -1.125 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
BW | +0.471 |
ciating | +0.421 |
bons | +0.420 |
nb | +0.417 |
Moz | +0.411 |
Neg logit contributions | |
Eng | -0.293 |
Gar | -0.246 |
millenn | -0.244 |
cel | -0.234 |
BUG | -0.234 |
Token | L |
Token ID | 43 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
BW | +0.416 |
bons | +0.366 |
nb | +0.366 |
ciating | +0.364 |
Moz | +0.358 |
Neg logit contributions | |
Eng | -0.324 |
millenn | -0.287 |
Gar | -0.278 |
cel | -0.272 |
BUG | -0.270 |
Token | ONDON |
Token ID | 47383 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
Eng | +0.677 |
millenn | +0.594 |
Gar | +0.591 |
BUG | +0.573 |
cel | +0.572 |
Neg logit contributions | |
BW | -0.739 |
bons | -0.640 |
ciating | -0.640 |
nb | -0.638 |
Moz | -0.627 |
Token | : |
Token ID | 25 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
Eng | +0.659 |
millenn | +0.569 |
Gar | +0.568 |
BUG | +0.550 |
cel | +0.550 |
Neg logit contributions | |
BW | -0.811 |
ciating | -0.714 |
bons | -0.712 |
nb | -0.707 |
Moz | -0.695 |
Token | British |
Token ID | 3517 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Eng | +4.630 |
Gar | +4.031 |
cel | +3.841 |
BUG | +3.812 |
Frameworks | +3.767 |
Neg logit contributions | |
BW | -4.931 |
ciating | -4.534 |
bons | -4.462 |
nb | -4.391 |
enhagen | -4.349 |
Token | Police |
Token ID | 4287 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
BW | +0.128 |
bons | +0.110 |
ciating | +0.110 |
nb | +0.110 |
Moz | +0.109 |
Neg logit contributions | |
Eng | -0.112 |
millenn | -0.098 |
Gar | -0.097 |
BUG | -0.094 |
cel | -0.094 |
Token | has |
Token ID | 468 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
Eng | +1.099 |
millenn | +0.955 |
Gar | +0.952 |
cel | +0.922 |
BUG | +0.919 |
Neg logit contributions | |
BW | -1.313 |
ciating | -1.153 |
bons | -1.151 |
nb | -1.143 |
Moz | -1.122 |
Token | identified |
Token ID | 5174 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Eng | +0.047 |
millenn | +0.041 |
Gar | +0.041 |
BUG | +0.040 |
cel | +0.040 |
Neg logit contributions | |
BW | -0.047 |
bons | -0.041 |
ciating | -0.041 |
nb | -0.041 |
Moz | -0.040 |
Token | one |
Token ID | 530 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
BW | +0.174 |
bons | +0.150 |
ciating | +0.149 |
nb | +0.149 |
Moz | +0.146 |
Neg logit contributions | |
Eng | -0.180 |
millenn | -0.159 |
Gar | -0.158 |
BUG | -0.154 |
cel | -0.153 |
Token | 03 |
Token ID | 3070 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
Eng | +0.153 |
Gar | +0.132 |
millenn | +0.130 |
BUG | +0.127 |
cel | +0.127 |
Neg logit contributions | |
BW | -0.193 |
ciating | -0.170 |
nb | -0.168 |
bons | -0.168 |
Moz | -0.166 |
Token | , |
Token ID | 11 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Eng | +2.254 |
millenn | +1.981 |
Gar | +1.957 |
cel | +1.938 |
BUG | +1.875 |
Neg logit contributions | |
BW | -2.704 |
ciating | -2.395 |
nb | -2.378 |
bons | -2.370 |
McAuliffe | -2.295 |
Token | when |
Token ID | 618 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Eng | +0.580 |
millenn | +0.511 |
Gar | +0.509 |
BUG | +0.495 |
cel | +0.491 |
Neg logit contributions | |
BW | -0.583 |
bons | -0.501 |
ciating | -0.500 |
nb | -0.499 |
Moz | -0.492 |
Token | they |
Token ID | 484 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Eng | +1.517 |
millenn | +1.345 |
Gar | +1.336 |
cel | +1.310 |
BUG | +1.287 |
Neg logit contributions | |
BW | -1.501 |
ciating | -1.306 |
bons | -1.300 |
nb | -1.296 |
McAuliffe | -1.255 |
Token | made |
Token ID | 925 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Eng | +0.870 |
millenn | +0.755 |
Gar | +0.752 |
cel | +0.729 |
BUG | +0.727 |
Neg logit contributions | |
BW | -1.051 |
bons | -0.917 |
ciating | -0.917 |
nb | -0.914 |
Moz | -0.898 |
Token | up |
Token ID | 510 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
Eng | +1.734 |
millenn | +1.525 |
Gar | +1.518 |
cel | +1.498 |
BUG | +1.465 |
Neg logit contributions | |
BW | -1.798 |
ciating | -1.568 |
nb | -1.563 |
bons | -1.558 |
McAuliffe | -1.505 |
Token | 13 |
Token ID | 1511 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Eng | +4.604 |
cel | +4.020 |
Gar | +4.015 |
millenn | +4.012 |
acy | +3.877 |
Neg logit contributions | |
BW | -4.941 |
ciating | -4.495 |
bons | -4.378 |
nb | -4.371 |
@#& | -4.221 |
Token | % |
Token ID | 4 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Eng | +0.950 |
millenn | +0.794 |
Gar | +0.791 |
cel | +0.762 |
BUG | +0.756 |
Neg logit contributions | |
BW | -1.628 |
ciating | -1.449 |
bons | -1.449 |
nb | -1.439 |
Moz | -1.417 |
Token | of |
Token ID | 286 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Eng | +0.820 |
millenn | +0.726 |
Gar | +0.717 |
cel | +0.700 |
BUG | +0.688 |
Neg logit contributions | |
BW | -0.850 |
ciating | -0.740 |
bons | -0.739 |
nb | -0.733 |
Moz | -0.716 |
Token | Brazil |
Token ID | 7595 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
BW | +1.093 |
bons | +0.932 |
ciating | +0.922 |
nb | +0.922 |
Moz | +0.916 |
Neg logit contributions | |
Eng | -1.202 |
millenn | -1.065 |
Gar | -1.061 |
BUG | -1.038 |
cel | -1.021 |
Token | ians |
Token ID | 1547 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
BW | +0.311 |
bons | +0.271 |
ciating | +0.271 |
nb | +0.270 |
Moz | +0.266 |
Neg logit contributions | |
Eng | -0.258 |
millenn | -0.224 |
Gar | -0.223 |
BUG | -0.216 |
cel | -0.215 |
Token | - |
Token ID | 532 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
BW | +0.432 |
bons | +0.368 |
nb | +0.367 |
ciating | +0.366 |
Moz | +0.362 |
Neg logit contributions | |
Eng | -0.455 |
millenn | -0.408 |
Gar | -0.401 |
BUG | -0.391 |
cel | -0.389 |
Token | January |
Token ID | 3269 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Eng | +0.714 |
millenn | +0.637 |
Gar | +0.636 |
BUG | +0.620 |
cel | +0.619 |
Neg logit contributions | |
BW | -0.563 |
ciating | -0.474 |
bons | -0.474 |
nb | -0.471 |
Moz | -0.462 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Eng | +1.444 |
millenn | +1.311 |
Gar | +1.275 |
BUG | +1.245 |
cel | +1.235 |
Neg logit contributions | |
BW | -1.337 |
bons | -1.137 |
nb | -1.133 |
ciating | -1.127 |
Moz | -1.114 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Eng | +0.942 |
millenn | +0.836 |
Gar | +0.814 |
BUG | +0.787 |
cel | +0.787 |
Neg logit contributions | |
BW | -1.163 |
bons | -1.016 |
nb | -1.013 |
ciating | -1.008 |
Moz | -0.996 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Eng | +1.338 |
Gar | +1.163 |
cel | +1.138 |
BUG | +1.131 |
millenn | +1.114 |
Neg logit contributions | |
BW | -1.428 |
ciating | -1.284 |
nb | -1.247 |
bons | -1.247 |
enhagen | -1.222 |
Token | Que |
Token ID | 15681 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
Eng | +1.714 |
Gar | +1.507 |
millenn | +1.499 |
BUG | +1.465 |
cel | +1.457 |
Neg logit contributions | |
BW | -1.675 |
ciating | -1.443 |
bons | -1.437 |
nb | -1.430 |
Moz | -1.408 |
Token | er |
Token ID | 263 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Eng | +4.399 |
Gar | +3.860 |
erness | +3.762 |
cel | +3.723 |
BUG | +3.674 |
Neg logit contributions | |
BW | -5.265 |
ciating | -4.746 |
bons | -4.580 |
Moz | -4.563 |
enhagen | -4.515 |
Token | magnet |
Token ID | 19972 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
Eng | +1.932 |
millenn | +1.724 |
Gar | +1.719 |
cel | +1.681 |
BUG | +1.677 |
Neg logit contributions | |
BW | -1.515 |
ciating | -1.286 |
bons | -1.278 |
nb | -1.276 |
Moz | -1.242 |
Token | ? |
Token ID | 30 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Eng | +3.587 |
millenn | +3.104 |
Gar | +3.060 |
cel | +3.021 |
vag | +2.991 |
Neg logit contributions | |
BW | -4.515 |
ciating | -4.084 |
nb | -4.015 |
bons | -3.991 |
McAuliffe | -3.945 |
Token |
|
Token ID | 198 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
Eng | +1.240 |
millenn | +1.040 |
Gar | +1.038 |
cel | +1.008 |
BUG | +0.998 |
Neg logit contributions | |
BW | -1.969 |
bons | -1.788 |
ciating | -1.780 |
nb | -1.772 |
McAuliffe | -1.737 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Eng | +0.584 |
millenn | +0.541 |
Gar | +0.504 |
BUG | +0.489 |
cel | +0.488 |
Neg logit contributions | |
BW | -0.738 |
bons | -0.645 |
nb | -0.644 |
Moz | -0.635 |
ciating | -0.631 |
Token |
|
Token ID | 198 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
BW | +0.640 |
nb | +0.560 |
bons | +0.557 |
Moz | +0.550 |
McAuliffe | +0.538 |
Neg logit contributions | |
Eng | -0.526 |
millenn | -0.514 |
Gar | -0.453 |
cel | -0.451 |
atism | -0.447 |
Token | P |
Token ID | 47 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
BW | +0.406 |
nb | +0.357 |
bons | +0.357 |
ciating | +0.351 |
Moz | +0.347 |
Neg logit contributions | |
Eng | -0.349 |
millenn | -0.320 |
Gar | -0.302 |
cel | -0.299 |
BUG | -0.294 |
Token | AS |
Token ID | 1921 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
Eng | +1.613 |
Gar | +1.411 |
millenn | +1.397 |
BUG | +1.364 |
cel | +1.362 |
Neg logit contributions | |
BW | -1.669 |
ciating | -1.431 |
bons | -1.427 |
nb | -1.419 |
Moz | -1.400 |
Token | AD |
Token ID | 2885 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Eng | +1.813 |
Gar | +1.470 |
BUG | +1.417 |
millenn | +1.376 |
cel | +1.371 |
Neg logit contributions | |
BW | -3.930 |
ciating | -3.626 |
bons | -3.560 |
nb | -3.551 |
enhagen | -3.525 |
Token | ENA |
Token ID | 45510 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
Eng | +2.824 |
Gar | +2.487 |
millenn | +2.436 |
BUG | +2.425 |
cel | +2.390 |
Neg logit contributions | |
BW | -2.688 |
ciating | -2.355 |
bons | -2.333 |
nb | -2.312 |
Moz | -2.266 |
Token | , |
Token ID | 11 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
Eng | +2.919 |
Gar | +2.500 |
millenn | +2.455 |
BUG | +2.418 |
cel | +2.417 |
Neg logit contributions | |
BW | -4.057 |
ciating | -3.664 |
bons | -3.629 |
nb | -3.579 |
@#& | -3.496 |
Token | Calif |
Token ID | 3192 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Eng | +4.200 |
Gar | +3.530 |
cel | +3.522 |
BUG | +3.455 |
vag | +3.425 |
Neg logit contributions | |
BW | -5.266 |
ciating | -4.813 |
bons | -4.657 |
enhagen | -4.651 |
@#& | -4.594 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
Eng | +1.196 |
Gar | +1.015 |
millenn | +1.012 |
cel | +0.974 |
BUG | +0.973 |
Neg logit contributions | |
BW | -1.773 |
ciating | -1.571 |
bons | -1.562 |
nb | -1.557 |
Moz | -1.536 |
Token | -- |
Token ID | 1377 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
Eng | +2.869 |
Gar | +2.457 |
BUG | +2.356 |
cel | +2.341 |
millenn | +2.326 |
Neg logit contributions | |
BW | -3.950 |
ciating | -3.589 |
bons | -3.497 |
nb | -3.476 |
enhagen | -3.404 |
Token | The |
Token ID | 383 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Eng | +2.663 |
Gar | +2.307 |
cel | +2.220 |
BUG | +2.206 |
millenn | +2.166 |
Neg logit contributions | |
BW | -3.134 |
ciating | -2.796 |
nb | -2.750 |
bons | -2.749 |
enhagen | -2.693 |
Token | first |
Token ID | 717 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
Eng | +1.190 |
millenn | +1.031 |
Gar | +1.028 |
cel | +1.004 |
BUG | +0.991 |
Neg logit contributions | |
BW | -1.442 |
ciating | -1.266 |
bons | -1.262 |
nb | -1.261 |
Moz | -1.227 |
Token | x |
Token ID | 87 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Eng | +0.693 |
millenn | +0.669 |
Gar | +0.625 |
cel | +0.617 |
BUG | +0.614 |
Neg logit contributions | |
BW | -0.433 |
nb | -0.364 |
bons | -0.359 |
ciating | -0.345 |
Moz | -0.344 |
Token | . |
Token ID | 13 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
BW | +0.130 |
nb | +0.115 |
bons | +0.114 |
Moz | +0.112 |
ciating | +0.110 |
Neg logit contributions | |
Eng | -0.099 |
millenn | -0.096 |
Gar | -0.085 |
cel | -0.083 |
BUG | -0.083 |
Token | 139 |
Token ID | 20219 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
BW | +0.705 |
nb | +0.606 |
bons | +0.604 |
ciating | +0.600 |
Moz | +0.592 |
Neg logit contributions | |
Eng | -0.775 |
millenn | -0.699 |
Gar | -0.686 |
BUG | -0.668 |
cel | -0.668 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Eng | +0.330 |
millenn | +0.294 |
Gar | +0.294 |
BUG | +0.286 |
cel | +0.286 |
Neg logit contributions | |
BW | -0.261 |
ciating | -0.220 |
bons | -0.220 |
nb | -0.219 |
Moz | -0.214 |
Token | 64 |
Token ID | 2414 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
BW | +1.058 |
nb | +0.930 |
bons | +0.923 |
Moz | +0.908 |
ciating | +0.908 |
Neg logit contributions | |
Eng | -0.883 |
millenn | -0.823 |
Gar | -0.765 |
cel | -0.749 |
BUG | -0.738 |
Token | 659 |
Token ID | 36445 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
Eng | +1.451 |
Gar | +1.273 |
BUG | +1.234 |
cel | +1.217 |
millenn | +1.210 |
Neg logit contributions | |
BW | -1.422 |
ciating | -1.231 |
bons | -1.221 |
nb | -1.206 |
enhagen | -1.191 |
Token | x |
Token ID | 2124 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Eng | +4.713 |
Gar | +4.111 |
cel | +4.077 |
vag | +3.985 |
BUG | +3.982 |
Neg logit contributions | |
BW | -4.640 |
ciating | -4.281 |
bons | -4.127 |
nb | -4.046 |
enhagen | -4.040 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Eng | +1.702 |
Gar | +1.442 |
millenn | +1.401 |
BUG | +1.385 |
cel | +1.380 |
Neg logit contributions | |
BW | -2.539 |
ciating | -2.261 |
bons | -2.243 |
nb | -2.231 |
Moz | -2.203 |
Token | x |
Token ID | 87 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Eng | +1.924 |
millenn | +1.759 |
Gar | +1.728 |
BUG | +1.688 |
cel | +1.688 |
Neg logit contributions | |
BW | -1.294 |
bons | -1.071 |
nb | -1.069 |
ciating | -1.063 |
Moz | -1.039 |
Token | . |
Token ID | 13 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
Eng | +1.025 |
millenn | +0.924 |
Gar | +0.876 |
cel | +0.847 |
BUG | +0.847 |
Neg logit contributions | |
BW | -1.443 |
nb | -1.272 |
bons | -1.271 |
ciating | -1.255 |
Moz | -1.249 |
Token | x |
Token ID | 87 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Eng | +0.857 |
millenn | +0.810 |
Gar | +0.771 |
cel | +0.758 |
BUG | +0.756 |
Neg logit contributions | |
BW | -0.548 |
nb | -0.459 |
bons | -0.455 |
ciating | -0.442 |
Moz | -0.438 |
Token | community |
Token ID | 2055 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
Eng | +1.409 |
Gar | +1.208 |
millenn | +1.195 |
cel | +1.172 |
BUG | +1.154 |
Neg logit contributions | |
BW | -1.766 |
bons | -1.561 |
ciating | -1.559 |
nb | -1.547 |
McAuliffe | -1.514 |
Token | . |
Token ID | 13 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Eng | +0.530 |
millenn | +0.459 |
Gar | +0.456 |
BUG | +0.441 |
cel | +0.440 |
Neg logit contributions | |
BW | -0.678 |
bons | -0.594 |
ciating | -0.594 |
nb | -0.592 |
Moz | -0.582 |
Token | This |
Token ID | 770 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Eng | +0.363 |
millenn | +0.319 |
Gar | +0.317 |
BUG | +0.308 |
cel | +0.307 |
Neg logit contributions | |
BW | -0.388 |
bons | -0.335 |
ciating | -0.335 |
nb | -0.334 |
Moz | -0.328 |
Token | is |
Token ID | 318 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Eng | +0.834 |
millenn | +0.726 |
Gar | +0.721 |
BUG | +0.698 |
cel | +0.694 |
Neg logit contributions | |
BW | -1.017 |
bons | -0.886 |
ciating | -0.884 |
nb | -0.884 |
Moz | -0.871 |
Token | one |
Token ID | 530 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
Eng | +0.223 |
millenn | +0.197 |
Gar | +0.195 |
BUG | +0.190 |
cel | +0.188 |
Neg logit contributions | |
BW | -0.238 |
bons | -0.205 |
nb | -0.205 |
ciating | -0.204 |
Moz | -0.202 |
Token | area |
Token ID | 1989 |
Feature activation | -6.36e+00 |
Pos logit contributions | |
Eng | +0.718 |
millenn | +0.629 |
Gar | +0.627 |
cel | +0.611 |
BUG | +0.609 |
Neg logit contributions | |
BW | -0.747 |
bons | -0.648 |
ciating | -0.647 |
nb | -0.645 |
Moz | -0.630 |
Token | where |
Token ID | 810 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
Eng | +3.938 |
Gar | +3.371 |
cel | +3.285 |
millenn | +3.260 |
BUG | +3.252 |
Neg logit contributions | |
BW | -5.203 |
ciating | -4.772 |
bons | -4.687 |
nb | -4.662 |
@#& | -4.639 |
Token | Power |
Token ID | 4333 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
Eng | +3.952 |
Gar | +3.443 |
millenn | +3.384 |
cel | +3.363 |
BUG | +3.357 |
Neg logit contributions | |
BW | -4.059 |
ciating | -3.608 |
bons | -3.607 |
nb | -3.567 |
@#& | -3.516 |
Token | BI |
Token ID | 20068 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Eng | +2.237 |
Gar | +1.972 |
BUG | +1.960 |
cel | +1.929 |
millenn | +1.927 |
Neg logit contributions | |
BW | -1.821 |
ciating | -1.593 |
bons | -1.569 |
nb | -1.556 |
McAuliffe | -1.532 |
Token | beats |
Token ID | 17825 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Eng | +1.406 |
millenn | +1.218 |
Gar | +1.215 |
cel | +1.178 |
BUG | +1.177 |
Neg logit contributions | |
BW | -1.666 |
ciating | -1.467 |
bons | -1.457 |
nb | -1.452 |
Moz | -1.420 |
Token | other |
Token ID | 584 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Eng | +1.705 |
Gar | +1.489 |
millenn | +1.474 |
cel | +1.456 |
BUG | +1.435 |
Neg logit contributions | |
BW | -1.741 |
ciating | -1.532 |
bons | -1.527 |
nb | -1.517 |
McAuliffe | -1.473 |
Token | its |
Token ID | 663 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
BW | +0.891 |
bons | +0.768 |
nb | +0.767 |
ciating | +0.766 |
Moz | +0.765 |
Neg logit contributions | |
Eng | -0.765 |
millenn | -0.677 |
Gar | -0.665 |
BUG | -0.648 |
cel | -0.641 |
Token | inventor |
Token ID | 33475 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Eng | +0.618 |
millenn | +0.540 |
Gar | +0.537 |
BUG | +0.519 |
cel | +0.519 |
Neg logit contributions | |
BW | -0.722 |
bons | -0.628 |
ciating | -0.628 |
nb | -0.626 |
Moz | -0.616 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
BW | +0.808 |
bons | +0.698 |
ciating | +0.696 |
nb | +0.695 |
Moz | +0.691 |
Neg logit contributions | |
Eng | -0.723 |
millenn | -0.642 |
Gar | -0.630 |
BUG | -0.614 |
cel | -0.608 |
Token | Bern |
Token ID | 6206 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Eng | +1.566 |
Gar | +1.401 |
millenn | +1.393 |
cel | +1.361 |
BUG | +1.356 |
Neg logit contributions | |
BW | -1.123 |
ciating | -0.948 |
bons | -0.941 |
nb | -0.940 |
Moz | -0.905 |
Token | ers |
Token ID | 364 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
BW | +1.143 |
bons | +0.960 |
nb | +0.953 |
ciating | +0.939 |
Moz | +0.934 |
Neg logit contributions | |
Eng | -1.569 |
millenn | -1.435 |
Gar | -1.400 |
cel | -1.375 |
BUG | -1.374 |
Token | - |
Token ID | 12 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
Eng | +1.627 |
Gar | +1.392 |
millenn | +1.365 |
cel | +1.335 |
BUG | +1.319 |
Neg logit contributions | |
BW | -2.419 |
ciating | -2.169 |
bons | -2.159 |
nb | -2.140 |
Moz | -2.098 |
Token | Lee |
Token ID | 24338 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Eng | +4.179 |
Gar | +3.644 |
cel | +3.354 |
Frameworks | +3.230 |
Maker | +3.199 |
Neg logit contributions | |
BW | -5.239 |
ciating | -4.929 |
nb | -4.717 |
@#& | -4.646 |
bons | -4.645 |
Token | has |
Token ID | 468 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Eng | +0.174 |
millenn | +0.152 |
Gar | +0.151 |
cel | +0.147 |
BUG | +0.147 |
Neg logit contributions | |
BW | -0.198 |
ciating | -0.172 |
bons | -0.172 |
nb | -0.171 |
Moz | -0.168 |
Token | written |
Token ID | 3194 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
BW | +1.355 |
bons | +1.170 |
nb | +1.163 |
ciating | +1.157 |
Moz | +1.153 |
Neg logit contributions | |
Eng | -1.251 |
millenn | -1.116 |
Gar | -1.096 |
BUG | -1.067 |
cel | -1.051 |
Token | an |
Token ID | 281 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Eng | +0.890 |
Gar | +0.778 |
millenn | +0.774 |
cel | +0.758 |
BUG | +0.756 |
Neg logit contributions | |
BW | -0.911 |
ciating | -0.796 |
bons | -0.793 |
nb | -0.789 |
Moz | -0.765 |
Token | open |
Token ID | 1280 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
BW | +0.028 |
bons | +0.024 |
ciating | +0.024 |
nb | +0.024 |
Moz | +0.024 |
Neg logit contributions | |
Eng | -0.021 |
millenn | -0.018 |
Gar | -0.018 |
BUG | -0.017 |
cel | -0.017 |
Token | j |
Token ID | 474 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
Eng | +1.541 |
millenn | +1.344 |
Gar | +1.337 |
cel | +1.302 |
BUG | +1.295 |
Neg logit contributions | |
BW | -1.764 |
ciating | -1.544 |
bons | -1.537 |
nb | -1.534 |
Moz | -1.504 |
Token | agg |
Token ID | 9460 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Eng | +0.512 |
millenn | +0.449 |
Gar | +0.432 |
cel | +0.415 |
BUG | +0.414 |
Neg logit contributions | |
BW | -0.813 |
bons | -0.723 |
nb | -0.722 |
ciating | -0.718 |
Moz | -0.708 |
Token | ies |
Token ID | 444 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
BW | +0.090 |
bons | +0.079 |
nb | +0.078 |
ciating | +0.077 |
Moz | +0.077 |
Neg logit contributions | |
Eng | -0.084 |
millenn | -0.078 |
Gar | -0.074 |
BUG | -0.071 |
cel | -0.071 |
Token | at |
Token ID | 379 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
Eng | +1.556 |
Gar | +1.346 |
millenn | +1.329 |
cel | +1.328 |
BUG | +1.295 |
Neg logit contributions | |
BW | -1.739 |
ciating | -1.539 |
nb | -1.513 |
bons | -1.512 |
Moz | -1.490 |
Token | all |
Token ID | 477 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Eng | +1.859 |
millenn | +1.601 |
Gar | +1.600 |
cel | +1.564 |
BUG | +1.534 |
Neg logit contributions | |
BW | -2.335 |
ciating | -2.072 |
bons | -2.048 |
nb | -2.043 |
Moz | -2.013 |
Token | even |
Token ID | 772 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
Eng | +1.308 |
Gar | +1.114 |
millenn | +1.092 |
cel | +1.084 |
BUG | +1.064 |
Neg logit contributions | |
BW | -1.794 |
ciating | -1.597 |
bons | -1.579 |
nb | -1.578 |
Moz | -1.557 |
Token | with |
Token ID | 351 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
Eng | +3.695 |
Gar | +3.098 |
cel | +3.082 |
millenn | +3.026 |
vag | +2.991 |
Neg logit contributions | |
BW | -5.405 |
ciating | -4.945 |
bons | -4.869 |
nb | -4.846 |
@#& | -4.773 |
Token | no |
Token ID | 645 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Eng | +2.285 |
millenn | +2.004 |
cel | +1.992 |
Gar | +1.987 |
BUG | +1.917 |
Neg logit contributions | |
BW | -2.421 |
ciating | -2.163 |
nb | -2.132 |
bons | -2.116 |
Moz | -2.072 |
Token | AA |
Token ID | 15923 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Eng | +1.793 |
millenn | +1.571 |
Gar | +1.560 |
cel | +1.545 |
BUG | +1.512 |
Neg logit contributions | |
BW | -1.840 |
ciating | -1.624 |
nb | -1.606 |
bons | -1.599 |
Moz | -1.564 |
Token | running |
Token ID | 2491 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Eng | +0.190 |
millenn | +0.165 |
Gar | +0.164 |
BUG | +0.159 |
cel | +0.158 |
Neg logit contributions | |
BW | -0.235 |
bons | -0.205 |
ciating | -0.205 |
nb | -0.205 |
Moz | -0.201 |
Token | but |
Token ID | 475 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
BW | +0.998 |
bons | +0.859 |
nb | +0.846 |
Moz | +0.843 |
ciating | +0.834 |
Neg logit contributions | |
Eng | -0.902 |
millenn | -0.810 |
Gar | -0.792 |
BUG | -0.774 |
cel | -0.748 |
Token | FILE |
Token ID | 45811 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Eng | +3.013 |
Gar | +2.629 |
millenn | +2.473 |
BUG | +2.450 |
cel | +2.434 |
Neg logit contributions | |
BW | -3.880 |
ciating | -3.617 |
bons | -3.533 |
nb | -3.470 |
nai | -3.446 |
Token | ID |
Token ID | 4522 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Eng | +1.633 |
Gar | +1.410 |
millenn | +1.361 |
BUG | +1.355 |
cel | +1.347 |
Neg logit contributions | |
BW | -2.061 |
ciating | -1.860 |
bons | -1.831 |
nb | -1.823 |
enhagen | -1.779 |
Token | : |
Token ID | 25 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
Eng | +1.338 |
Gar | +1.184 |
millenn | +1.180 |
BUG | +1.153 |
cel | +1.145 |
Neg logit contributions | |
BW | -1.178 |
ciating | -1.012 |
bons | -1.010 |
nb | -1.001 |
Moz | -0.984 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Eng | +2.958 |
Gar | +2.606 |
millenn | +2.566 |
BUG | +2.532 |
cel | +2.515 |
Neg logit contributions | |
BW | -2.712 |
ciating | -2.414 |
bons | -2.394 |
nb | -2.345 |
Moz | -2.327 |
Token | 23 |
Token ID | 1954 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
Eng | +0.691 |
Gar | +0.598 |
millenn | +0.589 |
BUG | +0.577 |
cel | +0.574 |
Neg logit contributions | |
BW | -0.829 |
ciating | -0.730 |
bons | -0.727 |
nb | -0.719 |
Moz | -0.710 |
Token | 22 |
Token ID | 1828 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
Eng | +1.922 |
Gar | +1.660 |
BUG | +1.603 |
cel | +1.586 |
millenn | +1.576 |
Neg logit contributions | |
BW | -2.304 |
ciating | -2.065 |
bons | -2.038 |
enhagen | -2.002 |
nb | -2.001 |
Token | 62 |
Token ID | 5237 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
Eng | +4.273 |
Gar | +3.708 |
BUG | +3.484 |
cel | +3.476 |
LAB | +3.410 |
Neg logit contributions | |
BW | -4.736 |
ciating | -4.551 |
enhagen | -4.380 |
bons | -4.368 |
bonding | -4.230 |
Token | 13 |
Token ID | 1485 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Eng | +2.688 |
Gar | +2.337 |
cel | +2.197 |
BUG | +2.182 |
vag | +2.145 |
Neg logit contributions | |
BW | -2.866 |
ciating | -2.701 |
bons | -2.614 |
enhagen | -2.565 |
nb | -2.560 |
Token | ( |
Token ID | 357 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Eng | +1.458 |
Gar | +1.261 |
millenn | +1.239 |
BUG | +1.211 |
cel | +1.210 |
Neg logit contributions | |
BW | -1.727 |
ciating | -1.536 |
bons | -1.522 |
nb | -1.513 |
Moz | -1.474 |
Token | Photo |
Token ID | 6191 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Eng | +1.149 |
millenn | +0.996 |
Gar | +0.984 |
BUG | +0.954 |
cel | +0.954 |
Neg logit contributions | |
BW | -1.578 |
nb | -1.382 |
bons | -1.380 |
ciating | -1.378 |
Moz | -1.359 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Eng | +3.142 |
Gar | +2.649 |
cel | +2.610 |
BUG | +2.577 |
millenn | +2.567 |
Neg logit contributions | |
BW | -3.492 |
ciating | -3.290 |
bons | -3.185 |
nb | -3.081 |
enhagen | -3.053 |
Token | Cavs |
Token ID | 38943 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Eng | +0.522 |
millenn | +0.467 |
Gar | +0.466 |
cel | +0.457 |
BUG | +0.454 |
Neg logit contributions | |
BW | -0.381 |
ciating | -0.322 |
bons | -0.320 |
nb | -0.318 |
Moz | -0.309 |
Token | ' |
Token ID | 6 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
Eng | +0.979 |
millenn | +0.862 |
Gar | +0.861 |
cel | +0.839 |
BUG | +0.837 |
Neg logit contributions | |
BW | -0.932 |
ciating | -0.808 |
bons | -0.802 |
nb | -0.799 |
Moz | -0.782 |
Token | J |
Token ID | 449 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Eng | +0.753 |
millenn | +0.667 |
Gar | +0.664 |
cel | +0.648 |
BUG | +0.645 |
Neg logit contributions | |
BW | -0.692 |
ciating | -0.595 |
bons | -0.593 |
nb | -0.590 |
Moz | -0.576 |
Token | . |
Token ID | 13 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Eng | +0.362 |
millenn | +0.321 |
Gar | +0.310 |
cel | +0.300 |
BUG | +0.299 |
Neg logit contributions | |
BW | -0.506 |
bons | -0.444 |
nb | -0.444 |
ciating | -0.440 |
Moz | -0.437 |
Token | R |
Token ID | 49 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
BW | +0.330 |
bons | +0.287 |
nb | +0.286 |
Moz | +0.284 |
McAuliffe | +0.280 |
Neg logit contributions | |
Eng | -0.269 |
millenn | -0.252 |
Gar | -0.231 |
cel | -0.229 |
BUG | -0.227 |
Token | . |
Token ID | 13 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
BW | +3.512 |
Moz | +3.035 |
nb | +3.035 |
bons | +3.003 |
McAuliffe | +2.970 |
Neg logit contributions | |
millenn | -3.141 |
Eng | -2.974 |
enthusi | -2.708 |
Gar | -2.599 |
atism | -2.584 |
Token | Smith |
Token ID | 4176 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
BW | +3.968 |
Moz | +3.452 |
McAuliffe | +3.343 |
nb | +3.290 |
bons | +3.260 |
Neg logit contributions | |
millenn | -4.002 |
Eng | -3.670 |
enthusi | -3.452 |
atism | -3.286 |
Gar | -3.284 |
Token | ( |
Token ID | 357 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
BW | +0.199 |
ciating | +0.174 |
bons | +0.174 |
nb | +0.174 |
Moz | +0.171 |
Neg logit contributions | |
Eng | -0.162 |
millenn | -0.141 |
Gar | -0.140 |
BUG | -0.136 |
cel | -0.135 |
Token | 5 |
Token ID | 20 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
BW | +1.259 |
nb | +1.100 |
bons | +1.091 |
Moz | +1.072 |
ciating | +1.069 |
Neg logit contributions | |
Eng | -1.144 |
millenn | -1.049 |
Gar | -0.999 |
cel | -0.982 |
BUG | -0.971 |
Token | ) |
Token ID | 8 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
BW | +1.879 |
nb | +1.639 |
bons | +1.636 |
ciating | +1.627 |
Moz | +1.605 |
Neg logit contributions | |
Eng | -1.514 |
millenn | -1.335 |
Gar | -1.311 |
BUG | -1.267 |
cel | -1.260 |
Token | after |
Token ID | 706 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
BW | +1.341 |
bons | +1.156 |
nb | +1.152 |
ciating | +1.140 |
Moz | +1.140 |
Neg logit contributions | |
Eng | -1.189 |
millenn | -1.061 |
Gar | -1.038 |
BUG | -1.007 |
cel | -0.998 |
Token | completely |
Token ID | 3190 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
BW | +0.050 |
ciating | +0.043 |
bons | +0.042 |
nb | +0.042 |
Moz | +0.041 |
Neg logit contributions | |
Eng | -0.053 |
Gar | -0.047 |
millenn | -0.047 |
BUG | -0.046 |
cel | -0.045 |
Token | understand |
Token ID | 1833 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Eng | +0.416 |
Gar | +0.364 |
millenn | +0.363 |
cel | +0.356 |
BUG | +0.354 |
Neg logit contributions | |
BW | -0.425 |
ciating | -0.369 |
bons | -0.368 |
nb | -0.366 |
Moz | -0.358 |
Token | what |
Token ID | 644 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
BW | +1.125 |
bons | +0.960 |
Moz | +0.956 |
nb | +0.956 |
ciating | +0.954 |
Neg logit contributions | |
Eng | -1.063 |
millenn | -0.958 |
Gar | -0.935 |
BUG | -0.907 |
cel | -0.896 |
Token | you |
Token ID | 345 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
BW | +1.501 |
Moz | +1.245 |
bons | +1.241 |
nb | +1.235 |
ciating | +1.226 |
Neg logit contributions | |
Eng | -1.935 |
millenn | -1.758 |
Gar | -1.728 |
BUG | -1.697 |
cel | -1.663 |
Token | are |
Token ID | 389 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
BW | +0.107 |
ciating | +0.093 |
bons | +0.092 |
nb | +0.092 |
Moz | +0.090 |
Neg logit contributions | |
Eng | -0.099 |
millenn | -0.087 |
Gar | -0.087 |
cel | -0.084 |
BUG | -0.084 |
Token | feeling |
Token ID | 4203 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
BW | +2.452 |
Moz | +2.046 |
bonding | +2.043 |
nb | +2.022 |
bons | +2.018 |
Neg logit contributions | |
Eng | -2.988 |
millenn | -2.778 |
Gar | -2.692 |
BUG | -2.637 |
atism | -2.593 |
Token | right |
Token ID | 826 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
BW | +4.300 |
Moz | +3.682 |
bons | +3.618 |
ciating | +3.608 |
nb | +3.605 |
Neg logit contributions | |
Eng | -4.354 |
millenn | -4.079 |
Gar | -3.888 |
BUG | -3.777 |
cel | -3.704 |
Token | now |
Token ID | 783 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
BW | +0.999 |
bons | +0.763 |
nb | +0.755 |
ciating | +0.751 |
Moz | +0.742 |
Neg logit contributions | |
Eng | -2.300 |
millenn | -2.131 |
Gar | -2.101 |
BUG | -2.060 |
cel | -2.047 |
Token | because |
Token ID | 780 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
BW | +1.382 |
bons | +1.196 |
ciating | +1.195 |
nb | +1.192 |
Moz | +1.178 |
Neg logit contributions | |
Eng | -1.239 |
millenn | -1.099 |
Gar | -1.081 |
BUG | -1.048 |
cel | -1.041 |
Token | I |
Token ID | 314 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
BW | +0.652 |
bons | +0.552 |
nb | +0.550 |
ciating | +0.550 |
Moz | +0.545 |
Neg logit contributions | |
Eng | -0.728 |
millenn | -0.654 |
Gar | -0.647 |
BUG | -0.629 |
cel | -0.622 |
Token | also |
Token ID | 635 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
BW | +1.053 |
nb | +0.900 |
bons | +0.898 |
ciating | +0.890 |
Moz | +0.885 |
Neg logit contributions | |
Eng | -1.100 |
millenn | -0.999 |
Gar | -0.971 |
BUG | -0.942 |
cel | -0.930 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
BW | +0.832 |
bons | +0.727 |
ciating | +0.727 |
nb | +0.725 |
Moz | +0.714 |
Neg logit contributions | |
Eng | -0.659 |
millenn | -0.572 |
Gar | -0.568 |
BUG | -0.549 |
cel | -0.548 |
Token | fn |
Token ID | 24714 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
BW | +1.587 |
bons | +1.292 |
nb | +1.285 |
ciating | +1.277 |
Moz | +1.256 |
Neg logit contributions | |
Eng | -2.647 |
millenn | -2.401 |
Gar | -2.393 |
BUG | -2.328 |
cel | -2.317 |
Token | apply |
Token ID | 4174 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
BW | +2.896 |
nb | +2.463 |
bons | +2.458 |
Moz | +2.434 |
McAuliffe | +2.408 |
Neg logit contributions | |
Eng | -2.969 |
millenn | -2.636 |
Gar | -2.630 |
Frameworks | -2.516 |
BUG | -2.514 |
Token | _ |
Token ID | 62 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
BW | +0.014 |
nb | +0.012 |
bons | +0.012 |
ciating | +0.012 |
Moz | +0.012 |
Neg logit contributions | |
Eng | -0.008 |
millenn | -0.007 |
Gar | -0.007 |
BUG | -0.006 |
cel | -0.006 |
Token | move |
Token ID | 21084 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
BW | +0.332 |
ciating | +0.263 |
bons | +0.262 |
nb | +0.259 |
Moz | +0.253 |
Neg logit contributions | |
Eng | -0.661 |
millenn | -0.600 |
Gar | -0.600 |
BUG | -0.589 |
cel | -0.587 |
Token | ( |
Token ID | 357 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
BW | +1.355 |
ciating | +1.188 |
bons | +1.188 |
nb | +1.181 |
Moz | +1.164 |
Neg logit contributions | |
Eng | -1.062 |
millenn | -0.919 |
Gar | -0.915 |
BUG | -0.885 |
cel | -0.884 |
Token | & |
Token ID | 1222 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
BW | +3.848 |
nb | +3.264 |
bons | +3.228 |
ciating | +3.192 |
Moz | +3.185 |
Neg logit contributions | |
Eng | -4.386 |
Gar | -3.961 |
millenn | -3.961 |
Frameworks | -3.798 |
BUG | -3.791 |
Token | mut |
Token ID | 4517 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
BW | +4.669 |
nb | +3.973 |
ciating | +3.941 |
bons | +3.933 |
Moz | +3.914 |
Neg logit contributions | |
Eng | -4.923 |
millenn | -4.364 |
Gar | -4.359 |
BUG | -4.210 |
Frameworks | -4.182 |
Token | self |
Token ID | 2116 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
BW | +1.786 |
bons | +1.511 |
ciating | +1.509 |
nb | +1.506 |
Moz | +1.479 |
Neg logit contributions | |
Eng | -2.055 |
millenn | -1.835 |
Gar | -1.827 |
BUG | -1.773 |
cel | -1.765 |
Token | ) |
Token ID | 1267 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
BW | +2.784 |
bons | +2.368 |
nb | +2.367 |
ciating | +2.365 |
Moz | +2.313 |
Neg logit contributions | |
Eng | -3.112 |
millenn | -2.779 |
Gar | -2.771 |
BUG | -2.695 |
cel | -2.681 |
Token | { |
Token ID | 1391 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
BW | +3.542 |
nb | +2.985 |
bons | +2.974 |
ciating | +2.957 |
Moz | +2.928 |
Neg logit contributions | |
Eng | -4.117 |
millenn | -3.695 |
Gar | -3.672 |
BUG | -3.580 |
cel | -3.534 |
Token | s |
Token ID | 82 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
BW | +0.742 |
ciating | +0.648 |
bons | +0.641 |
nb | +0.637 |
Moz | +0.628 |
Neg logit contributions | |
Eng | -0.712 |
Gar | -0.624 |
millenn | -0.618 |
BUG | -0.602 |
cel | -0.600 |
Token | )} |
Token ID | 38165 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Eng | +0.436 |
millenn | +0.391 |
Gar | +0.373 |
BUG | +0.361 |
cel | +0.361 |
Neg logit contributions | |
BW | -0.594 |
bons | -0.520 |
nb | -0.518 |
ciating | -0.513 |
Moz | -0.512 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
BW | +2.138 |
nb | +1.800 |
bons | +1.794 |
ciating | +1.780 |
Moz | +1.771 |
Neg logit contributions | |
Eng | -2.345 |
millenn | -2.113 |
Gar | -2.067 |
BUG | -2.018 |
cel | -1.996 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
BW | +1.039 |
nb | +0.914 |
bons | +0.914 |
Moz | +0.896 |
ciating | +0.886 |
Neg logit contributions | |
Eng | -0.779 |
millenn | -0.740 |
Gar | -0.668 |
BUG | -0.652 |
cel | -0.651 |
Token | N |
Token ID | 399 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
BW | +1.199 |
bons | +1.015 |
nb | +1.014 |
ciating | +1.012 |
Moz | +1.000 |
Neg logit contributions | |
Eng | -1.288 |
millenn | -1.152 |
Gar | -1.135 |
BUG | -1.107 |
cel | -1.098 |
Token | f |
Token ID | 69 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
BW | +1.614 |
nb | +1.391 |
bons | +1.378 |
ciating | +1.356 |
Moz | +1.328 |
Neg logit contributions | |
Eng | -1.972 |
millenn | -1.820 |
Gar | -1.745 |
cel | -1.718 |
BUG | -1.706 |
Token | 3 |
Token ID | 18 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
BW | +4.562 |
nb | +3.960 |
bons | +3.942 |
Moz | +3.833 |
ciating | +3.776 |
Neg logit contributions | |
Eng | -3.994 |
millenn | -3.808 |
BUG | -3.480 |
Gar | -3.471 |
erness | -3.433 |
Token | { |
Token ID | 1391 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
BW | +0.747 |
bons | +0.651 |
ciating | +0.651 |
nb | +0.649 |
Moz | +0.638 |
Neg logit contributions | |
Eng | -0.637 |
millenn | -0.556 |
Gar | -0.553 |
BUG | -0.535 |
cel | -0.534 |
Token | ( |
Token ID | 7 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
BW | +1.589 |
nb | +1.394 |
bons | +1.381 |
Moz | +1.349 |
McAuliffe | +1.300 |
Neg logit contributions | |
millenn | -1.565 |
Eng | -1.545 |
enthusi | -1.368 |
cel | -1.348 |
Gar | -1.340 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Eng | +0.338 |
Gar | +0.289 |
millenn | +0.288 |
BUG | +0.279 |
cel | +0.278 |
Neg logit contributions | |
BW | -0.459 |
ciating | -0.405 |
bons | -0.403 |
nb | -0.400 |
Moz | -0.395 |
Token | s |
Token ID | 82 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
BW | +1.067 |
nb | +0.922 |
bons | +0.921 |
Moz | +0.887 |
McAuliffe | +0.862 |
Neg logit contributions | |
Eng | -1.188 |
millenn | -1.164 |
Gar | -1.049 |
cel | -1.038 |
BUG | -1.033 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
BW | +1.510 |
nb | +1.247 |
bons | +1.238 |
ciating | +1.219 |
Moz | +1.197 |
Neg logit contributions | |
Eng | -2.434 |
millenn | -2.322 |
BUG | -2.153 |
Gar | -2.149 |
cel | -2.139 |
Token | or |
Token ID | 393 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Eng | +0.241 |
millenn | +0.214 |
Gar | +0.208 |
BUG | +0.202 |
cel | +0.202 |
Neg logit contributions | |
BW | -0.294 |
bons | -0.257 |
nb | -0.256 |
ciating | -0.255 |
Moz | -0.253 |
Token | more |
Token ID | 517 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
BW | +1.223 |
bons | +1.040 |
ciating | +1.036 |
nb | +1.036 |
Moz | +1.019 |
Neg logit contributions | |
Eng | -1.354 |
millenn | -1.210 |
Gar | -1.197 |
BUG | -1.166 |
cel | -1.163 |
Token | to |
Token ID | 284 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
BW | +0.722 |
bons | +0.612 |
nb | +0.611 |
ciating | +0.610 |
Moz | +0.599 |
Neg logit contributions | |
Eng | -0.843 |
millenn | -0.758 |
Gar | -0.749 |
BUG | -0.730 |
cel | -0.727 |
Token | help |
Token ID | 1037 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
BW | +2.284 |
nb | +2.009 |
bons | +2.004 |
ciating | +1.981 |
Moz | +1.970 |
Neg logit contributions | |
Eng | -1.641 |
millenn | -1.482 |
Gar | -1.443 |
BUG | -1.396 |
cel | -1.357 |
Token | us |
Token ID | 514 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
BW | +1.393 |
ciating | +1.196 |
bons | +1.194 |
nb | +1.187 |
Moz | +1.164 |
Neg logit contributions | |
Eng | -1.445 |
millenn | -1.267 |
Gar | -1.265 |
cel | -1.233 |
BUG | -1.229 |
Token | continue |
Token ID | 2555 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
BW | +4.949 |
nb | +4.387 |
bons | +4.328 |
Moz | +4.290 |
ciating | +4.272 |
Neg logit contributions | |
Eng | -3.520 |
millenn | -3.338 |
Gar | -3.125 |
BUG | -3.090 |
Frameworks | -2.973 |
Token | to |
Token ID | 284 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
BW | +0.695 |
nb | +0.579 |
ciating | +0.576 |
bons | +0.574 |
Moz | +0.571 |
Neg logit contributions | |
Eng | -0.868 |
millenn | -0.797 |
Gar | -0.770 |
BUG | -0.765 |
cel | -0.749 |
Token | write |
Token ID | 3551 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
BW | +1.252 |
nb | +1.085 |
ciating | +1.077 |
bons | +1.076 |
Moz | +1.068 |
Neg logit contributions | |
Eng | -1.127 |
millenn | -1.030 |
Gar | -0.987 |
BUG | -0.971 |
cel | -0.945 |
Token | about |
Token ID | 546 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
Eng | +0.852 |
Gar | +0.749 |
millenn | +0.747 |
BUG | +0.729 |
cel | +0.727 |
Neg logit contributions | |
BW | -0.808 |
ciating | -0.698 |
bons | -0.697 |
nb | -0.692 |
Moz | -0.677 |
Token | the |
Token ID | 262 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Eng | +0.458 |
millenn | +0.408 |
Gar | +0.404 |
BUG | +0.394 |
cel | +0.392 |
Neg logit contributions | |
BW | -0.431 |
bons | -0.369 |
nb | -0.368 |
ciating | -0.366 |
Moz | -0.362 |
Token | them |
Token ID | 606 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Eng | +0.599 |
millenn | +0.528 |
Gar | +0.525 |
BUG | +0.510 |
cel | +0.509 |
Neg logit contributions | |
BW | -0.605 |
bons | -0.521 |
ciating | -0.521 |
nb | -0.519 |
Moz | -0.509 |
Token | before |
Token ID | 878 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
Eng | +0.925 |
millenn | +0.805 |
Gar | +0.805 |
cel | +0.780 |
BUG | +0.779 |
Neg logit contributions | |
BW | -1.045 |
ciating | -0.911 |
bons | -0.911 |
nb | -0.907 |
Moz | -0.891 |
Token | deciding |
Token ID | 14615 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
BW | +0.664 |
bons | +0.564 |
nb | +0.563 |
ciating | +0.561 |
Moz | +0.560 |
Neg logit contributions | |
Eng | -0.655 |
millenn | -0.586 |
Gar | -0.575 |
BUG | -0.561 |
cel | -0.556 |
Token | on |
Token ID | 319 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
BW | +0.508 |
bons | +0.435 |
nb | +0.433 |
ciating | +0.433 |
Moz | +0.428 |
Neg logit contributions | |
Eng | -0.502 |
millenn | -0.446 |
Gar | -0.440 |
BUG | -0.429 |
cel | -0.425 |
Token | his |
Token ID | 465 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
BW | +2.518 |
bons | +2.139 |
Moz | +2.123 |
ciating | +2.102 |
nb | +2.088 |
Neg logit contributions | |
Eng | -2.460 |
millenn | -2.236 |
Gar | -2.154 |
BUG | -2.102 |
Frameworks | -2.091 |
Token | hero |
Token ID | 4293 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
BW | +2.314 |
bons | +1.945 |
Moz | +1.931 |
nb | +1.924 |
boo | +1.885 |
Neg logit contributions | |
Eng | -2.227 |
millenn | -1.998 |
Gar | -1.943 |
Frameworks | -1.903 |
BUG | -1.899 |
Token | picks |
Token ID | 11103 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
BW | +3.550 |
bons | +3.000 |
nb | +2.944 |
Moz | +2.928 |
McAuliffe | +2.908 |
Neg logit contributions | |
Eng | -3.323 |
millenn | -3.028 |
Gar | -2.880 |
BUG | -2.791 |
Frameworks | -2.785 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
BW | +2.051 |
nb | +1.765 |
bons | +1.757 |
ciating | +1.746 |
Moz | +1.736 |
Neg logit contributions | |
Eng | -1.709 |
millenn | -1.539 |
Gar | -1.480 |
BUG | -1.440 |
cel | -1.421 |
Token | Ferrari |
Token ID | 23502 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
Eng | +0.011 |
millenn | +0.010 |
Gar | +0.009 |
BUG | +0.009 |
cel | +0.009 |
Neg logit contributions | |
BW | -0.012 |
bons | -0.010 |
nb | -0.010 |
ciating | -0.010 |
Moz | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Eng | +0.060 |
millenn | +0.052 |
Gar | +0.052 |
BUG | +0.051 |
cel | +0.051 |
Neg logit contributions | |
BW | -0.063 |
ciating | -0.054 |
bons | -0.054 |
nb | -0.054 |
Moz | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
Eng | +0.175 |
millenn | +0.154 |
Gar | +0.153 |
BUG | +0.149 |
cel | +0.149 |
Neg logit contributions | |
BW | -0.181 |
bons | -0.156 |
ciating | -0.156 |
nb | -0.155 |
Moz | -0.152 |
Token | harsh |
Token ID | 11859 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
BW | +0.763 |
bons | +0.660 |
ciating | +0.657 |
nb | +0.655 |
Moz | +0.648 |
Neg logit contributions | |
Eng | -0.668 |
millenn | -0.585 |
Gar | -0.581 |
BUG | -0.563 |
cel | -0.558 |
Token | environments |
Token ID | 12493 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
Eng | +0.251 |
millenn | +0.220 |
Gar | +0.218 |
cel | +0.212 |
BUG | +0.211 |
Neg logit contributions | |
BW | -0.284 |
bons | -0.247 |
ciating | -0.247 |
nb | -0.246 |
Moz | -0.242 |
Token | and |
Token ID | 290 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
BW | +0.535 |
bons | +0.456 |
nb | +0.454 |
ciating | +0.454 |
Moz | +0.453 |
Neg logit contributions | |
Eng | -0.507 |
millenn | -0.453 |
Gar | -0.446 |
BUG | -0.434 |
cel | -0.427 |
Token | long |
Token ID | 890 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
BW | +0.291 |
bons | +0.251 |
ciating | +0.251 |
nb | +0.250 |
Moz | +0.247 |
Neg logit contributions | |
Eng | -0.268 |
millenn | -0.235 |
Gar | -0.234 |
BUG | -0.227 |
cel | -0.225 |
Token | separ |
Token ID | 2880 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
BW | +1.818 |
ciating | +1.549 |
bons | +1.543 |
nb | +1.537 |
Moz | +1.514 |
Neg logit contributions | |
Eng | -1.904 |
millenn | -1.686 |
Gar | -1.673 |
BUG | -1.631 |
cel | -1.591 |
Token | ations |
Token ID | 602 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
BW | +0.166 |
bons | +0.139 |
ciating | +0.138 |
nb | +0.138 |
Moz | +0.135 |
Neg logit contributions | |
Eng | -0.231 |
millenn | -0.209 |
Gar | -0.207 |
BUG | -0.202 |
cel | -0.201 |
Token | from |
Token ID | 422 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
BW | +1.216 |
bons | +1.041 |
ciating | +1.030 |
nb | +1.029 |
Moz | +1.027 |
Neg logit contributions | |
Eng | -1.139 |
millenn | -1.025 |
Gar | -1.005 |
BUG | -0.982 |
cel | -0.956 |
Token | family |
Token ID | 1641 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
BW | +0.037 |
bons | +0.033 |
ciating | +0.032 |
nb | +0.032 |
Moz | +0.032 |
Neg logit contributions | |
Eng | -0.033 |
millenn | -0.029 |
Gar | -0.029 |
BUG | -0.028 |
cel | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
BW | +0.799 |
bons | +0.686 |
nb | +0.681 |
ciating | +0.677 |
Moz | +0.673 |
Neg logit contributions | |
Eng | -0.772 |
millenn | -0.687 |
Gar | -0.681 |
BUG | -0.665 |
cel | -0.650 |
Token | workers |
Token ID | 3259 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
BW | +2.807 |
bons | +2.397 |
Moz | +2.378 |
McAuliffe | +2.366 |
nb | +2.365 |
Neg logit contributions | |
Eng | -2.331 |
millenn | -2.089 |
Gar | -2.036 |
BUG | -2.014 |
Frameworks | -1.967 |
Token | endure |
Token ID | 21178 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Eng | +0.299 |
millenn | +0.256 |
Gar | +0.256 |
cel | +0.248 |
BUG | +0.246 |
Neg logit contributions | |
BW | -0.401 |
ciating | -0.353 |
bons | -0.353 |
nb | -0.351 |
Moz | -0.346 |
Token | it |
Token ID | 270 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
BW | +1.372 |
nb | +1.194 |
bons | +1.186 |
ciating | +1.177 |
Moz | +1.158 |
Neg logit contributions | |
Eng | -1.356 |
millenn | -1.229 |
Gar | -1.189 |
BUG | -1.162 |
cel | -1.160 |
Token | en |
Token ID | 268 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Eng | +1.834 |
Gar | +1.616 |
millenn | +1.589 |
BUG | +1.577 |
cel | +1.564 |
Neg logit contributions | |
BW | -1.595 |
ciating | -1.422 |
bons | -1.362 |
nb | -1.348 |
McAuliffe | -1.329 |
Token | hu |
Token ID | 13415 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Eng | +0.170 |
millenn | +0.152 |
Gar | +0.151 |
BUG | +0.148 |
cel | +0.147 |
Neg logit contributions | |
BW | -0.136 |
ciating | -0.115 |
bons | -0.115 |
nb | -0.114 |
Moz | -0.112 |
Token | ber |
Token ID | 527 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
BW | +0.932 |
nb | +0.789 |
bons | +0.786 |
Moz | +0.772 |
ciating | +0.770 |
Neg logit contributions | |
Eng | -1.108 |
millenn | -1.016 |
Gar | -0.984 |
cel | -0.962 |
BUG | -0.959 |
Token | won |
Token ID | 1839 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
BW | +2.299 |
bons | +1.985 |
nb | +1.982 |
Moz | +1.965 |
ciating | +1.923 |
Neg logit contributions | |
Eng | -2.058 |
millenn | -1.860 |
Gar | -1.792 |
cel | -1.734 |
BUG | -1.728 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
BW | +0.031 |
ciating | +0.027 |
bons | +0.027 |
nb | +0.027 |
Moz | +0.026 |
Neg logit contributions | |
Eng | -0.031 |
millenn | -0.027 |
Gar | -0.027 |
BUG | -0.027 |
cel | -0.027 |
Token | competition |
Token ID | 5449 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
BW | +0.856 |
bons | +0.733 |
ciating | +0.730 |
nb | +0.729 |
Moz | +0.721 |
Neg logit contributions | |
Eng | -0.859 |
millenn | -0.760 |
Gar | -0.755 |
BUG | -0.734 |
cel | -0.731 |
Token | for |
Token ID | 329 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
BW | +0.032 |
bons | +0.028 |
ciating | +0.028 |
nb | +0.028 |
Moz | +0.027 |
Neg logit contributions | |
Eng | -0.031 |
millenn | -0.027 |
Gar | -0.027 |
BUG | -0.027 |
cel | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Eng | +0.013 |
millenn | +0.012 |
Gar | +0.012 |
BUG | +0.011 |
cel | +0.011 |
Neg logit contributions | |
BW | -0.014 |
ciating | -0.012 |
bons | -0.012 |
nb | -0.012 |
Moz | -0.012 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
BW | +1.198 |
bons | +1.018 |
Moz | +1.015 |
nb | +1.014 |
ciating | +0.999 |
Neg logit contributions | |
Eng | -1.125 |
millenn | -0.992 |
Gar | -0.991 |
BUG | -0.961 |
cel | -0.946 |
Token | design |
Token ID | 1486 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
BW | +2.036 |
Moz | +1.709 |
bons | +1.698 |
nb | +1.693 |
McAuliffe | +1.659 |
Neg logit contributions | |
Eng | -2.223 |
millenn | -1.994 |
Gar | -1.985 |
BUG | -1.923 |
cel | -1.900 |
Token | are |
Token ID | 389 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
BW | +0.000 |
bons | +0.000 |
nb | +0.000 |
ciating | +0.000 |
Moz | +0.000 |
Neg logit contributions | |
Eng | -0.000 |
millenn | -0.000 |
Gar | -0.000 |
BUG | -0.000 |
cel | -0.000 |
Token | likely |
Token ID | 1884 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
BW | +0.030 |
bons | +0.026 |
nb | +0.026 |
ciating | +0.026 |
Moz | +0.025 |
Neg logit contributions | |
Eng | -0.026 |
millenn | -0.023 |
Gar | -0.023 |
BUG | -0.022 |
cel | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
BW | +1.564 |
ciating | +1.333 |
bons | +1.333 |
nb | +1.327 |
Moz | +1.301 |
Neg logit contributions | |
Eng | -1.760 |
millenn | -1.568 |
Gar | -1.558 |
BUG | -1.515 |
cel | -1.514 |
Token | range |
Token ID | 2837 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
BW | +1.565 |
nb | +1.341 |
bons | +1.339 |
Moz | +1.324 |
ciating | +1.318 |
Neg logit contributions | |
Eng | -1.530 |
millenn | -1.374 |
Gar | -1.349 |
BUG | -1.311 |
cel | -1.291 |
Token | from |
Token ID | 422 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
BW | +0.195 |
ciating | +0.169 |
bons | +0.168 |
nb | +0.168 |
Moz | +0.164 |
Neg logit contributions | |
Eng | -0.185 |
millenn | -0.164 |
Gar | -0.162 |
cel | -0.158 |
BUG | -0.157 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
BW | +1.057 |
bons | +0.909 |
nb | +0.906 |
ciating | +0.904 |
Moz | +0.899 |
Neg logit contributions | |
Eng | -0.955 |
millenn | -0.835 |
Gar | -0.832 |
BUG | -0.806 |
cel | -0.795 |
Token | mundane |
Token ID | 30741 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
BW | +0.852 |
bons | +0.736 |
ciating | +0.733 |
nb | +0.733 |
Moz | +0.726 |
Neg logit contributions | |
Eng | -0.751 |
millenn | -0.656 |
Gar | -0.653 |
BUG | -0.633 |
cel | -0.625 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
BW | +2.771 |
bons | +2.336 |
nb | +2.333 |
Moz | +2.331 |
ciating | +2.309 |
Neg logit contributions | |
Eng | -2.971 |
millenn | -2.623 |
Gar | -2.616 |
BUG | -2.545 |
cel | -2.488 |
Token | in |
Token ID | 287 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
BW | +0.840 |
bons | +0.719 |
nb | +0.718 |
ciating | +0.716 |
Moz | +0.711 |
Neg logit contributions | |
Eng | -0.802 |
millenn | -0.706 |
Gar | -0.702 |
BUG | -0.684 |
cel | -0.674 |
Token | the |
Token ID | 262 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
BW | +0.400 |
bons | +0.346 |
ciating | +0.346 |
nb | +0.345 |
Moz | +0.340 |
Neg logit contributions | |
Eng | -0.367 |
millenn | -0.323 |
Gar | -0.321 |
BUG | -0.311 |
cel | -0.310 |
Token | case |
Token ID | 1339 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
BW | +0.569 |
bons | +0.493 |
ciating | +0.492 |
nb | +0.492 |
Moz | +0.485 |
Neg logit contributions | |
Eng | -0.509 |
millenn | -0.445 |
Gar | -0.443 |
BUG | -0.430 |
cel | -0.427 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Eng | +0.492 |
millenn | +0.429 |
Gar | +0.427 |
BUG | +0.415 |
cel | +0.415 |
Neg logit contributions | |
BW | -0.544 |
ciating | -0.475 |
bons | -0.474 |
nb | -0.471 |
Moz | -0.462 |
Token | Wh |
Token ID | 854 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Eng | +0.169 |
millenn | +0.148 |
Gar | +0.147 |
BUG | +0.143 |
cel | +0.142 |
Neg logit contributions | |
BW | -0.186 |
bons | -0.161 |
ciating | -0.161 |
nb | -0.161 |
Moz | -0.158 |
Token | oles |
Token ID | 4316 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Eng | +0.715 |
Gar | +0.616 |
millenn | +0.614 |
BUG | +0.594 |
cel | +0.592 |
Neg logit contributions | |
BW | -0.929 |
bons | -0.813 |
ciating | -0.810 |
nb | -0.807 |
Moz | -0.798 |
Token | ale |
Token ID | 1000 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
BW | +0.846 |
bons | +0.730 |
nb | +0.729 |
ciating | +0.729 |
Moz | +0.715 |
Neg logit contributions | |
Eng | -0.825 |
millenn | -0.729 |
Gar | -0.723 |
BUG | -0.702 |
cel | -0.699 |
Token | & |
Token ID | 1222 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
Eng | +0.572 |
Gar | +0.503 |
millenn | +0.503 |
BUG | +0.488 |
cel | +0.488 |
Neg logit contributions | |
BW | -0.550 |
ciating | -0.476 |
bons | -0.474 |
nb | -0.472 |
Moz | -0.461 |
Token | Role |
Token ID | 20934 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
BW | +0.577 |
bons | +0.495 |
nb | +0.494 |
ciating | +0.491 |
Moz | +0.489 |
Neg logit contributions | |
Eng | -0.521 |
millenn | -0.464 |
Gar | -0.455 |
BUG | -0.444 |
cel | -0.439 |
Token | Based |
Token ID | 13403 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
BW | +1.290 |
ciating | +1.057 |
nb | +1.053 |
bons | +1.053 |
Moz | +1.032 |
Neg logit contributions | |
Eng | -1.965 |
millenn | -1.810 |
Gar | -1.766 |
cel | -1.733 |
BUG | -1.732 |
Token | Pricing |
Token ID | 45030 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Eng | +1.662 |
Gar | +1.465 |
millenn | +1.451 |
cel | +1.426 |
BUG | +1.420 |
Neg logit contributions | |
BW | -1.459 |
ciating | -1.274 |
nb | -1.256 |
bons | -1.255 |
enhagen | -1.218 |
Token | plugin |
Token ID | 13877 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Eng | +0.529 |
millenn | +0.466 |
Gar | +0.463 |
BUG | +0.449 |
cel | +0.448 |
Neg logit contributions | |
BW | -0.568 |
bons | -0.491 |
nb | -0.489 |
ciating | -0.489 |
Moz | -0.481 |
Token | offers |
Token ID | 4394 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Eng | +0.519 |
millenn | +0.453 |
Gar | +0.452 |
cel | +0.439 |
BUG | +0.439 |
Neg logit contributions | |
BW | -0.563 |
ciating | -0.492 |
bons | -0.489 |
nb | -0.487 |
Moz | -0.478 |
Token | a |
Token ID | 257 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
BW | +0.925 |
bons | +0.791 |
nb | +0.788 |
ciating | +0.785 |
Moz | +0.783 |
Neg logit contributions | |
Eng | -0.892 |
millenn | -0.793 |
Gar | -0.785 |
BUG | -0.761 |
cel | -0.753 |
Token | be |
Token ID | 307 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Eng | +1.424 |
Gar | +1.246 |
millenn | +1.240 |
cel | +1.223 |
BUG | +1.217 |
Neg logit contributions | |
BW | -1.353 |
ciating | -1.180 |
bons | -1.169 |
nb | -1.156 |
Moz | -1.136 |
Token | up |
Token ID | 510 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Eng | +1.273 |
millenn | +1.115 |
Gar | +1.113 |
cel | +1.084 |
BUG | +1.079 |
Neg logit contributions | |
BW | -1.319 |
ciating | -1.146 |
bons | -1.142 |
nb | -1.137 |
Moz | -1.115 |
Token | shortly |
Token ID | 8972 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Eng | +1.532 |
Gar | +1.328 |
millenn | +1.322 |
cel | +1.288 |
BUG | +1.287 |
Neg logit contributions | |
BW | -1.792 |
ciating | -1.573 |
bons | -1.561 |
nb | -1.553 |
Moz | -1.529 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Eng | +1.440 |
Gar | +1.237 |
millenn | +1.222 |
cel | +1.198 |
BUG | +1.195 |
Neg logit contributions | |
BW | -1.859 |
ciating | -1.653 |
bons | -1.646 |
nb | -1.626 |
Moz | -1.606 |
Token |
|
Token ID | 198 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Eng | +0.166 |
Gar | +0.144 |
millenn | +0.144 |
BUG | +0.140 |
cel | +0.139 |
Neg logit contributions | |
BW | -0.199 |
ciating | -0.175 |
bons | -0.174 |
nb | -0.173 |
Moz | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
BW | +0.423 |
nb | +0.370 |
bons | +0.368 |
Moz | +0.362 |
McAuliffe | +0.353 |
Neg logit contributions | |
Eng | -0.357 |
millenn | -0.357 |
Gar | -0.310 |
enthusi | -0.307 |
cel | -0.303 |
Token | Feature |
Token ID | 38816 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
BW | +0.524 |
bons | +0.458 |
nb | +0.458 |
ciating | +0.453 |
Moz | +0.446 |
Neg logit contributions | |
Eng | -0.436 |
millenn | -0.389 |
Gar | -0.377 |
cel | -0.369 |
BUG | -0.364 |
Token | match |
Token ID | 2872 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Eng | +0.636 |
Gar | +0.564 |
millenn | +0.559 |
BUG | +0.550 |
cel | +0.548 |
Neg logit contributions | |
BW | -0.557 |
ciating | -0.482 |
bons | -0.479 |
nb | -0.477 |
Moz | -0.466 |
Token | : |
Token ID | 25 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Eng | +0.439 |
millenn | +0.381 |
Gar | +0.379 |
BUG | +0.369 |
cel | +0.368 |
Neg logit contributions | |
BW | -0.524 |
ciating | -0.460 |
bons | -0.458 |
nb | -0.455 |
Moz | -0.448 |
Token | Let |
Token ID | 3914 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Eng | +0.970 |
Gar | +0.841 |
millenn | +0.839 |
cel | +0.817 |
BUG | +0.817 |
Neg logit contributions | |
BW | -1.124 |
ciating | -0.990 |
bons | -0.987 |
nb | -0.980 |
Moz | -0.963 |
Token | � |
Token ID | 447 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
BW | +0.683 |
bons | +0.593 |
ciating | +0.593 |
nb | +0.591 |
Moz | +0.581 |
Neg logit contributions | |
Eng | -0.604 |
millenn | -0.528 |
Gar | -0.526 |
BUG | -0.509 |
cel | -0.508 |
Token | and |
Token ID | 290 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
BW | +1.295 |
bons | +1.109 |
nb | +1.101 |
ciating | +1.097 |
Moz | +1.092 |
Neg logit contributions | |
Eng | -1.316 |
millenn | -1.170 |
Gar | -1.158 |
BUG | -1.131 |
cel | -1.118 |
Token | destroy |
Token ID | 4117 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
BW | +0.403 |
bons | +0.346 |
nb | +0.345 |
ciating | +0.344 |
Moz | +0.339 |
Neg logit contributions | |
Eng | -0.406 |
millenn | -0.360 |
Gar | -0.357 |
BUG | -0.347 |
cel | -0.345 |
Token | [ |
Token ID | 685 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
Eng | +0.105 |
millenn | +0.092 |
Gar | +0.092 |
cel | +0.089 |
BUG | +0.089 |
Neg logit contributions | |
BW | -0.111 |
ciating | -0.097 |
bons | -0.097 |
nb | -0.096 |
Moz | -0.094 |
Token | the |
Token ID | 1169 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
BW | +0.766 |
bons | +0.668 |
nb | +0.666 |
ciating | +0.663 |
Moz | +0.653 |
Neg logit contributions | |
Eng | -0.671 |
millenn | -0.594 |
Gar | -0.584 |
cel | -0.568 |
BUG | -0.567 |
Token | ] |
Token ID | 60 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Eng | +0.097 |
millenn | +0.084 |
Gar | +0.084 |
cel | +0.081 |
BUG | +0.080 |
Neg logit contributions | |
BW | -0.122 |
ciating | -0.107 |
bons | -0.107 |
nb | -0.106 |
Moz | -0.104 |
Token | enemy |
Token ID | 4472 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
BW | +0.398 |
bons | +0.345 |
ciating | +0.344 |
nb | +0.343 |
Moz | +0.338 |
Neg logit contributions | |
Eng | -0.356 |
millenn | -0.312 |
Gar | -0.310 |
BUG | -0.300 |
cel | -0.299 |
Token | grouping |
Token ID | 36115 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
Eng | +0.448 |
Gar | +0.392 |
millenn | +0.392 |
cel | +0.379 |
BUG | +0.378 |
Neg logit contributions | |
BW | -0.482 |
ciating | -0.420 |
nb | -0.418 |
bons | -0.418 |
Moz | -0.409 |
Token | near |
Token ID | 1474 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Eng | +0.665 |
millenn | +0.582 |
Gar | +0.581 |
cel | +0.563 |
BUG | +0.562 |
Neg logit contributions | |
BW | -0.708 |
ciating | -0.617 |
bons | -0.614 |
nb | -0.613 |
Moz | -0.600 |
Token | Su |
Token ID | 1778 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Eng | +0.922 |
Gar | +0.810 |
millenn | +0.803 |
cel | +0.788 |
BUG | +0.775 |
Neg logit contributions | |
BW | -0.905 |
ciating | -0.797 |
bons | -0.784 |
nb | -0.784 |
McAuliffe | -0.757 |
Token | wa |
Token ID | 10247 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Eng | +1.787 |
Gar | +1.587 |
millenn | +1.555 |
cel | +1.522 |
BUG | +1.515 |
Neg logit contributions | |
BW | -1.725 |
ciating | -1.485 |
bons | -1.469 |
nb | -1.449 |
Moz | -1.442 |
Token | ł |
Token ID | 41615 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
BW | +0.889 |
bons | +0.765 |
ciating | +0.764 |
nb | +0.764 |
Moz | +0.753 |
Neg logit contributions | |
Eng | -0.828 |
millenn | -0.730 |
Gar | -0.721 |
BUG | -0.703 |
cel | -0.698 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
BW | +0.642 |
bons | +0.550 |
ciating | +0.546 |
nb | +0.545 |
Moz | +0.540 |
Neg logit contributions | |
Eng | -0.642 |
millenn | -0.570 |
Gar | -0.563 |
BUG | -0.551 |
cel | -0.544 |
Token | power |
Token ID | 1176 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
BW | +0.238 |
bons | +0.205 |
nb | +0.204 |
ciating | +0.204 |
Moz | +0.202 |
Neg logit contributions | |
Eng | -0.208 |
millenn | -0.183 |
Gar | -0.181 |
BUG | -0.176 |
cel | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Eng | +1.744 |
Gar | +1.527 |
millenn | +1.518 |
cel | +1.490 |
BUG | +1.481 |
Neg logit contributions | |
BW | -1.823 |
ciating | -1.599 |
bons | -1.582 |
nb | -1.575 |
Moz | -1.554 |
Token | Nothing |
Token ID | 10528 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
Eng | +0.102 |
millenn | +0.091 |
Gar | +0.089 |
BUG | +0.087 |
cel | +0.087 |
Neg logit contributions | |
BW | -0.106 |
bons | -0.091 |
nb | -0.091 |
ciating | -0.091 |
Moz | -0.090 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
BW | +0.675 |
bons | +0.582 |
nb | +0.579 |
Moz | +0.578 |
ciating | +0.578 |
Neg logit contributions | |
Eng | -0.560 |
millenn | -0.491 |
Gar | -0.485 |
BUG | -0.472 |
cel | -0.462 |
Token | right |
Token ID | 826 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
BW | +2.440 |
bons | +2.058 |
Moz | +2.056 |
McAuliffe | +2.022 |
nb | +2.020 |
Neg logit contributions | |
Eng | -2.522 |
millenn | -2.277 |
Gar | -2.237 |
BUG | -2.195 |
erness | -2.135 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Eng | +0.401 |
Gar | +0.344 |
millenn | +0.343 |
cel | +0.334 |
BUG | +0.331 |
Neg logit contributions | |
BW | -0.516 |
ciating | -0.454 |
bons | -0.454 |
nb | -0.452 |
Moz | -0.443 |
Token | and |
Token ID | 290 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
BW | +1.724 |
bons | +1.479 |
ciating | +1.466 |
nb | +1.461 |
Moz | +1.455 |
Neg logit contributions | |
Eng | -1.650 |
millenn | -1.470 |
Gar | -1.442 |
BUG | -1.410 |
cel | -1.378 |
Token | the |
Token ID | 262 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
BW | +1.227 |
bons | +1.040 |
nb | +1.030 |
Moz | +1.029 |
ciating | +1.023 |
Neg logit contributions | |
Eng | -1.286 |
millenn | -1.148 |
Gar | -1.131 |
BUG | -1.105 |
Frameworks | -1.081 |
Token | plane |
Token ID | 6614 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Eng | +0.027 |
millenn | +0.024 |
Gar | +0.024 |
BUG | +0.023 |
cel | +0.023 |
Neg logit contributions | |
BW | -0.032 |
bons | -0.028 |
ciating | -0.028 |
nb | -0.028 |
Moz | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Eng | +0.896 |
millenn | +0.777 |
Gar | +0.773 |
BUG | +0.747 |
cel | +0.746 |
Neg logit contributions | |
BW | -1.134 |
ciating | -0.994 |
bons | -0.993 |
nb | -0.990 |
Moz | -0.974 |
Token | stand |
Token ID | 1481 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Eng | +1.421 |
Gar | +1.254 |
millenn | +1.215 |
cel | +1.213 |
acy | +1.210 |
Neg logit contributions | |
BW | -1.303 |
ciating | -1.127 |
bons | -1.101 |
nb | -1.094 |
McAuliffe | -1.084 |
Token | into |
Token ID | 656 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
BW | +0.146 |
ciating | +0.126 |
bons | +0.126 |
nb | +0.125 |
Moz | +0.123 |
Neg logit contributions | |
Eng | -0.142 |
millenn | -0.125 |
Gar | -0.125 |
cel | -0.121 |
BUG | -0.121 |
Token | Vern |
Token ID | 23092 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Eng | +2.038 |
Gar | +1.773 |
millenn | +1.758 |
cel | +1.750 |
vag | +1.711 |
Neg logit contributions | |
BW | -2.138 |
ciating | -1.906 |
bons | -1.888 |
nb | -1.877 |
@#& | -1.825 |
Token | un |
Token ID | 403 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Eng | +0.948 |
Gar | +0.836 |
millenn | +0.830 |
BUG | +0.811 |
cel | +0.810 |
Neg logit contributions | |
BW | -0.858 |
ciating | -0.735 |
bons | -0.730 |
nb | -0.726 |
Moz | -0.712 |
Token | ft |
Token ID | 701 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Eng | +0.973 |
Gar | +0.843 |
millenn | +0.842 |
cel | +0.819 |
BUG | +0.818 |
Neg logit contributions | |
BW | -1.048 |
bons | -0.913 |
ciating | -0.908 |
nb | -0.905 |
McAuliffe | -0.883 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
BW | +0.236 |
ciating | +0.206 |
bons | +0.206 |
nb | +0.205 |
Moz | +0.201 |
Neg logit contributions | |
Eng | -0.202 |
millenn | -0.175 |
Gar | -0.175 |
cel | -0.169 |
BUG | -0.169 |
Token | the |
Token ID | 262 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
Eng | +1.976 |
Gar | +1.712 |
millenn | +1.690 |
cel | +1.676 |
vag | +1.639 |
Neg logit contributions | |
BW | -2.072 |
ciating | -1.843 |
bons | -1.830 |
nb | -1.825 |
enhagen | -1.765 |
Token | cognitive |
Token ID | 10870 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Eng | +0.440 |
millenn | +0.385 |
Gar | +0.383 |
cel | +0.372 |
BUG | +0.371 |
Neg logit contributions | |
BW | -0.489 |
ciating | -0.425 |
bons | -0.425 |
nb | -0.423 |
Moz | -0.414 |
Token | ability |
Token ID | 2694 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
BW | +0.370 |
bons | +0.320 |
nb | +0.319 |
ciating | +0.318 |
Moz | +0.315 |
Neg logit contributions | |
Eng | -0.337 |
millenn | -0.297 |
Gar | -0.295 |
BUG | -0.287 |
cel | -0.283 |
Token | to |
Token ID | 284 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
BW | +1.151 |
bons | +0.983 |
ciating | +0.983 |
nb | +0.982 |
Moz | +0.969 |
Neg logit contributions | |
Eng | -1.182 |
millenn | -1.050 |
Gar | -1.042 |
BUG | -1.014 |
cel | -1.005 |
Token | understand |
Token ID | 1833 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
BW | +0.847 |
bons | +0.732 |
ciating | +0.730 |
nb | +0.729 |
Moz | +0.719 |
Neg logit contributions | |
Eng | -0.782 |
millenn | -0.691 |
Gar | -0.685 |
BUG | -0.664 |
cel | -0.659 |
Token | ets |
Token ID | 1039 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
BW | +1.688 |
bons | +1.458 |
nb | +1.457 |
ciating | +1.455 |
Moz | +1.431 |
Neg logit contributions | |
Eng | -1.570 |
millenn | -1.389 |
Gar | -1.370 |
BUG | -1.334 |
cel | -1.327 |
Token | bass |
Token ID | 12702 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Eng | +0.317 |
millenn | +0.279 |
Gar | +0.278 |
BUG | +0.270 |
cel | +0.270 |
Neg logit contributions | |
BW | -0.321 |
ciating | -0.277 |
bons | -0.277 |
nb | -0.276 |
Moz | -0.270 |
Token | - |
Token ID | 12 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Eng | +1.612 |
millenn | +1.424 |
Gar | +1.419 |
cel | +1.393 |
BUG | +1.376 |
Neg logit contributions | |
BW | -1.581 |
ciating | -1.388 |
nb | -1.358 |
bons | -1.345 |
Moz | -1.326 |
Token | heavy |
Token ID | 23701 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Eng | +0.967 |
Gar | +0.845 |
millenn | +0.835 |
BUG | +0.822 |
cel | +0.813 |
Neg logit contributions | |
BW | -1.029 |
ciating | -0.894 |
bons | -0.882 |
nb | -0.878 |
Moz | -0.868 |
Token | music |
Token ID | 2647 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Eng | +0.440 |
millenn | +0.389 |
Gar | +0.387 |
cel | +0.378 |
BUG | +0.375 |
Neg logit contributions | |
BW | -0.430 |
ciating | -0.374 |
bons | -0.372 |
nb | -0.371 |
Moz | -0.360 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Eng | +0.762 |
millenn | +0.670 |
Gar | +0.668 |
cel | +0.649 |
BUG | +0.647 |
Neg logit contributions | |
BW | -0.812 |
ciating | -0.707 |
bons | -0.703 |
nb | -0.702 |
Moz | -0.687 |
Token | pushed |
Token ID | 7121 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Eng | +1.051 |
millenn | +0.920 |
Gar | +0.919 |
cel | +0.900 |
BUG | +0.890 |
Neg logit contributions | |
BW | -1.086 |
ciating | -0.954 |
bons | -0.949 |
nb | -0.946 |
McAuliffe | -0.912 |
Token | them |
Token ID | 606 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
BW | +0.398 |
bons | +0.341 |
ciating | +0.340 |
nb | +0.340 |
Moz | +0.335 |
Neg logit contributions | |
Eng | -0.399 |
millenn | -0.353 |
Gar | -0.350 |
BUG | -0.340 |
cel | -0.339 |
Token | well |
Token ID | 880 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Eng | +0.672 |
millenn | +0.589 |
Gar | +0.587 |
cel | +0.570 |
BUG | +0.570 |
Neg logit contributions | |
BW | -0.711 |
ciating | -0.618 |
bons | -0.616 |
nb | -0.614 |
Moz | -0.601 |
Token | beyond |
Token ID | 3675 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
BW | +0.162 |
bons | +0.140 |
ciating | +0.140 |
nb | +0.140 |
Moz | +0.137 |
Neg logit contributions | |
Eng | -0.148 |
millenn | -0.130 |
Gar | -0.129 |
BUG | -0.125 |
cel | -0.125 |
Token | 90 |
Token ID | 4101 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
BW | +0.099 |
ciating | +0.086 |
bons | +0.085 |
nb | +0.085 |
Moz | +0.083 |
Neg logit contributions | |
Eng | -0.096 |
millenn | -0.085 |
Gar | -0.084 |
cel | -0.082 |
BUG | -0.082 |
Token | very |
Token ID | 845 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
BW | +0.646 |
bons | +0.561 |
ciating | +0.559 |
nb | +0.559 |
Moz | +0.549 |
Neg logit contributions | |
Eng | -0.576 |
millenn | -0.505 |
Gar | -0.501 |
BUG | -0.485 |
cel | -0.484 |
Token | well |
Token ID | 880 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
BW | +0.655 |
bons | +0.560 |
nb | +0.557 |
ciating | +0.554 |
Moz | +0.547 |
Neg logit contributions | |
Eng | -0.711 |
millenn | -0.636 |
Gar | -0.628 |
BUG | -0.608 |
cel | -0.607 |
Token | be |
Token ID | 307 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
BW | +0.798 |
bons | +0.688 |
nb | +0.686 |
ciating | +0.685 |
Moz | +0.674 |
Neg logit contributions | |
Eng | -0.769 |
millenn | -0.680 |
Gar | -0.673 |
BUG | -0.654 |
cel | -0.650 |
Token | his |
Token ID | 465 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
BW | +0.751 |
bons | +0.648 |
ciating | +0.646 |
nb | +0.645 |
Moz | +0.634 |
Neg logit contributions | |
Eng | -0.726 |
millenn | -0.640 |
Gar | -0.636 |
BUG | -0.618 |
cel | -0.616 |
Token | magn |
Token ID | 7842 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
BW | +0.087 |
bons | +0.076 |
nb | +0.076 |
ciating | +0.076 |
Moz | +0.075 |
Neg logit contributions | |
Eng | -0.066 |
millenn | -0.057 |
Gar | -0.056 |
BUG | -0.055 |
cel | -0.054 |
Token | um |
Token ID | 388 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
Eng | +0.713 |
millenn | +0.625 |
Gar | +0.617 |
BUG | +0.596 |
cel | +0.595 |
Neg logit contributions | |
BW | -0.868 |
bons | -0.756 |
nb | -0.755 |
ciating | -0.755 |
Moz | -0.743 |
Token | op |
Token ID | 1034 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Eng | +4.367 |
Gar | +3.977 |
millenn | +3.965 |
acy | +3.852 |
cel | +3.849 |
Neg logit contributions | |
BW | -2.809 |
ciating | -2.421 |
bons | -2.363 |
nb | -2.336 |
Moz | -2.255 |
Token | us |
Token ID | 385 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Eng | +1.578 |
millenn | +1.407 |
Gar | +1.400 |
BUG | +1.363 |
cel | +1.360 |
Neg logit contributions | |
BW | -1.353 |
ciating | -1.148 |
bons | -1.147 |
nb | -1.143 |
Moz | -1.122 |
Token | . |
Token ID | 13 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
Eng | +0.868 |
Gar | +0.740 |
millenn | +0.734 |
cel | +0.716 |
BUG | +0.708 |
Neg logit contributions | |
BW | -1.239 |
ciating | -1.106 |
nb | -1.097 |
bons | -1.097 |
Moz | -1.069 |
Token | A |
Token ID | 317 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Eng | +0.579 |
Gar | +0.506 |
millenn | +0.499 |
BUG | +0.488 |
cel | +0.488 |
Neg logit contributions | |
BW | -0.609 |
ciating | -0.532 |
bons | -0.529 |
nb | -0.526 |
Moz | -0.514 |
Token | mel |
Token ID | 7758 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Eng | +0.338 |
millenn | +0.298 |
Gar | +0.297 |
cel | +0.289 |
BUG | +0.287 |
Neg logit contributions | |
BW | -0.354 |
ciating | -0.309 |
bons | -0.306 |
nb | -0.305 |
Moz | -0.298 |
Token | manager |
Token ID | 37153 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
Eng | +0.308 |
millenn | +0.268 |
Gar | +0.268 |
BUG | +0.260 |
cel | +0.259 |
Neg logit contributions | |
BW | -0.355 |
ciating | -0.309 |
bons | -0.309 |
nb | -0.307 |
Moz | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
Eng | +1.893 |
millenn | +1.636 |
Gar | +1.627 |
cel | +1.602 |
BUG | +1.591 |
Neg logit contributions | |
BW | -2.346 |
ciating | -2.088 |
bons | -2.078 |
nb | -2.051 |
Moz | -2.023 |
Token | service |
Token ID | 15271 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Eng | +0.291 |
millenn | +0.245 |
Gar | +0.245 |
cel | +0.236 |
BUG | +0.235 |
Neg logit contributions | |
BW | -0.468 |
bons | -0.416 |
ciating | -0.416 |
nb | -0.413 |
Moz | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Eng | +0.828 |
millenn | +0.714 |
Gar | +0.711 |
cel | +0.692 |
BUG | +0.690 |
Neg logit contributions | |
BW | -1.076 |
ciating | -0.949 |
bons | -0.948 |
nb | -0.942 |
Moz | -0.926 |
Token |
|
Token ID | 198 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
Eng | +0.106 |
millenn | +0.102 |
Gar | +0.092 |
BUG | +0.089 |
cel | +0.089 |
Neg logit contributions | |
BW | -0.129 |
nb | -0.113 |
bons | -0.113 |
Moz | -0.111 |
McAuliffe | -0.109 |
Token | You |
Token ID | 1639 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
Eng | +0.586 |
millenn | +0.509 |
Gar | +0.508 |
BUG | +0.492 |
cel | +0.490 |
Neg logit contributions | |
BW | -0.696 |
ciating | -0.607 |
bons | -0.606 |
nb | -0.603 |
Moz | -0.595 |
Token | should |
Token ID | 815 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
Eng | +2.400 |
Gar | +2.103 |
cel | +2.049 |
BUG | +2.038 |
millenn | +2.029 |
Neg logit contributions | |
BW | -2.895 |
ciating | -2.599 |
bons | -2.534 |
nb | -2.504 |
Moz | -2.479 |
Token | notice |
Token ID | 4003 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
Eng | +3.336 |
Gar | +2.980 |
cel | +2.959 |
BUG | +2.946 |
vag | +2.911 |
Neg logit contributions | |
BW | -2.518 |
ciating | -2.189 |
bons | -2.133 |
nb | -2.086 |
Moz | -2.078 |
Token | network |
Token ID | 3127 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Eng | +0.574 |
millenn | +0.505 |
Gar | +0.502 |
BUG | +0.487 |
cel | +0.486 |
Neg logit contributions | |
BW | -0.600 |
bons | -0.517 |
ciating | -0.516 |
nb | -0.515 |
Moz | -0.507 |
Token | manager |
Token ID | 4706 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Eng | +1.652 |
millenn | +1.451 |
Gar | +1.447 |
cel | +1.405 |
BUG | +1.405 |
Neg logit contributions | |
BW | -1.686 |
ciating | -1.459 |
bons | -1.452 |
nb | -1.447 |
Moz | -1.421 |
Token | drop |
Token ID | 4268 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Eng | +1.420 |
millenn | +1.229 |
Gar | +1.228 |
BUG | +1.190 |
cel | +1.188 |
Neg logit contributions | |
BW | -1.723 |
ciating | -1.510 |
bons | -1.506 |
nb | -1.500 |
Moz | -1.477 |
Token | what |
Token ID | 644 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
BW | +0.600 |
bons | +0.515 |
nb | +0.513 |
ciating | +0.511 |
Moz | +0.506 |
Neg logit contributions | |
Eng | -0.595 |
millenn | -0.530 |
Gar | -0.524 |
BUG | -0.510 |
cel | -0.505 |
Token | we |
Token ID | 356 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
BW | +0.661 |
bons | +0.575 |
nb | +0.573 |
ciating | +0.571 |
Moz | +0.566 |
Neg logit contributions | |
Eng | -0.542 |
millenn | -0.474 |
Gar | -0.469 |
BUG | -0.454 |
cel | -0.451 |
Token | now |
Token ID | 783 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
Eng | +0.038 |
millenn | +0.033 |
Gar | +0.033 |
cel | +0.033 |
BUG | +0.032 |
Neg logit contributions | |
BW | -0.033 |
ciating | -0.028 |
bons | -0.028 |
nb | -0.028 |
Moz | -0.027 |
Token | know |
Token ID | 760 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
BW | +0.643 |
bons | +0.539 |
nb | +0.538 |
ciating | +0.538 |
Moz | +0.526 |
Neg logit contributions | |
Eng | -0.820 |
millenn | -0.740 |
Gar | -0.731 |
BUG | -0.714 |
cel | -0.708 |
Token | about |
Token ID | 546 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Eng | +0.023 |
Gar | +0.020 |
millenn | +0.020 |
cel | +0.020 |
BUG | +0.020 |
Neg logit contributions | |
BW | -0.025 |
ciating | -0.022 |
bons | -0.021 |
nb | -0.021 |
Moz | -0.021 |
Token | Ign |
Token ID | 16583 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
BW | +0.169 |
bons | +0.146 |
ciating | +0.146 |
nb | +0.145 |
Moz | +0.143 |
Neg logit contributions | |
Eng | -0.162 |
millenn | -0.142 |
Gar | -0.141 |
BUG | -0.137 |
cel | -0.137 |
Token | at |
Token ID | 265 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Eng | +2.805 |
Gar | +2.388 |
acy | +2.336 |
atism | +2.295 |
cel | +2.290 |
Neg logit contributions | |
BW | -4.119 |
ciating | -3.687 |
bons | -3.579 |
Moz | -3.562 |
nb | -3.562 |
Token | ie |
Token ID | 494 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
Eng | +1.420 |
millenn | +1.291 |
Gar | +1.261 |
BUG | +1.230 |
cel | +1.229 |
Neg logit contributions | |
BW | -1.185 |
bons | -1.005 |
nb | -1.002 |
ciating | -0.999 |
Moz | -0.979 |
Token | ff |
Token ID | 487 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
Eng | +0.682 |
millenn | +0.640 |
Gar | +0.614 |
BUG | +0.601 |
cel | +0.599 |
Neg logit contributions | |
BW | -0.456 |
bons | -0.380 |
nb | -0.378 |
ciating | -0.369 |
Moz | -0.364 |
Token | � |
Token ID | 447 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Eng | +2.252 |
Gar | +1.933 |
millenn | +1.908 |
cel | +1.871 |
acy | +1.855 |
Neg logit contributions | |
BW | -2.699 |
ciating | -2.385 |
bons | -2.374 |
nb | -2.358 |
Moz | -2.315 |
Token | � |
Token ID | 247 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Eng | +0.135 |
millenn | +0.112 |
Gar | +0.111 |
BUG | +0.106 |
cel | +0.106 |
Neg logit contributions | |
BW | -0.249 |
bons | -0.222 |
ciating | -0.222 |
nb | -0.222 |
Moz | -0.218 |
Token | an |
Token ID | 272 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
Eng | +0.819 |
millenn | +0.719 |
Gar | +0.716 |
BUG | +0.694 |
cel | +0.693 |
Neg logit contributions | |
BW | -0.868 |
ciating | -0.750 |
bons | -0.750 |
nb | -0.746 |
Moz | -0.735 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
BW | +0.578 |
bons | +0.498 |
nb | +0.497 |
ciating | +0.497 |
Moz | +0.489 |
Neg logit contributions | |
Eng | -0.543 |
millenn | -0.478 |
Gar | -0.475 |
BUG | -0.462 |
cel | -0.459 |
Token | in |
Token ID | 287 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
Eng | +1.477 |
Gar | +1.289 |
millenn | +1.286 |
cel | +1.266 |
BUG | +1.237 |
Neg logit contributions | |
BW | -1.467 |
ciating | -1.302 |
bons | -1.282 |
nb | -1.275 |
enhagen | -1.234 |
Token | Kang |
Token ID | 27504 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
Eng | +1.684 |
Gar | +1.458 |
millenn | +1.451 |
cel | +1.428 |
BUG | +1.384 |
Neg logit contributions | |
BW | -1.883 |
ciating | -1.690 |
nb | -1.654 |
bons | -1.652 |
McAuliffe | -1.606 |
Token | won |
Token ID | 26502 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
BW | +0.049 |
ciating | +0.042 |
bons | +0.042 |
nb | +0.041 |
Moz | +0.041 |
Neg logit contributions | |
Eng | -0.055 |
Gar | -0.049 |
millenn | -0.049 |
cel | -0.047 |
BUG | -0.047 |
Token | Province |
Token ID | 22783 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
BW | +0.137 |
ciating | +0.117 |
bons | +0.117 |
nb | +0.117 |
Moz | +0.115 |
Neg logit contributions | |
Eng | -0.148 |
millenn | -0.131 |
Gar | -0.131 |
BUG | -0.127 |
cel | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Eng | +2.130 |
Gar | +1.832 |
millenn | +1.808 |
cel | +1.789 |
vag | +1.734 |
Neg logit contributions | |
BW | -2.831 |
ciating | -2.569 |
bons | -2.520 |
nb | -2.490 |
enhagen | -2.446 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Eng | +1.891 |
millenn | +1.651 |
Gar | +1.648 |
cel | +1.626 |
BUG | +1.582 |
Neg logit contributions | |
BW | -1.905 |
ciating | -1.696 |
bons | -1.671 |
nb | -1.662 |
enhagen | -1.610 |
Token | , |
Token ID | 11 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
BW | +1.874 |
nb | +1.615 |
bons | +1.613 |
ciating | +1.607 |
Moz | +1.601 |
Neg logit contributions | |
Eng | -1.594 |
millenn | -1.403 |
Gar | -1.391 |
BUG | -1.348 |
cel | -1.325 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
BW | +0.404 |
bons | +0.348 |
ciating | +0.348 |
nb | +0.346 |
Moz | +0.339 |
Neg logit contributions | |
Eng | -0.415 |
millenn | -0.366 |
Gar | -0.365 |
BUG | -0.354 |
cel | -0.354 |
Token | people |
Token ID | 661 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
BW | +1.046 |
bons | +0.898 |
nb | +0.897 |
ciating | +0.892 |
Moz | +0.889 |
Neg logit contributions | |
Eng | -0.944 |
millenn | -0.832 |
Gar | -0.827 |
BUG | -0.801 |
cel | -0.792 |
Token | new |
Token ID | 649 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Eng | +0.800 |
millenn | +0.693 |
Gar | +0.689 |
BUG | +0.666 |
cel | +0.665 |
Neg logit contributions | |
BW | -1.019 |
ciating | -0.892 |
bons | -0.892 |
nb | -0.890 |
Moz | -0.875 |
Token | universe |
Token ID | 6881 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
BW | +0.678 |
bons | +0.579 |
nb | +0.577 |
ciating | +0.573 |
Moz | +0.572 |
Neg logit contributions | |
Eng | -0.630 |
millenn | -0.556 |
Gar | -0.553 |
BUG | -0.534 |
cel | -0.525 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
BW | +0.802 |
bons | +0.687 |
nb | +0.684 |
ciating | +0.680 |
Moz | +0.679 |
Neg logit contributions | |
Eng | -0.736 |
millenn | -0.651 |
Gar | -0.647 |
BUG | -0.622 |
cel | -0.615 |
Token | We |
Token ID | 775 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Eng | +1.143 |
Gar | +0.999 |
millenn | +0.977 |
BUG | +0.968 |
cel | +0.967 |
Neg logit contributions | |
BW | -1.167 |
ciating | -1.022 |
bons | -1.014 |
nb | -1.009 |
Moz | -0.983 |
Token | can |
Token ID | 460 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Eng | +0.863 |
millenn | +0.750 |
Gar | +0.748 |
BUG | +0.725 |
cel | +0.725 |
Neg logit contributions | |
BW | -1.005 |
ciating | -0.876 |
bons | -0.875 |
nb | -0.872 |
Moz | -0.857 |
Token | 't |
Token ID | 470 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
Eng | +2.199 |
Gar | +1.899 |
cel | +1.879 |
millenn | +1.859 |
BUG | +1.855 |
Neg logit contributions | |
BW | -2.376 |
ciating | -2.104 |
bons | -2.076 |
nb | -2.062 |
Moz | -2.028 |
Token | wait |
Token ID | 4043 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
Eng | +2.274 |
Gar | +1.943 |
cel | +1.933 |
millenn | +1.906 |
BUG | +1.889 |
Neg logit contributions | |
BW | -2.764 |
ciating | -2.463 |
bons | -2.433 |
nb | -2.411 |
Moz | -2.375 |
Token | for |
Token ID | 329 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
BW | +0.596 |
bons | +0.510 |
ciating | +0.510 |
nb | +0.508 |
Moz | +0.498 |
Neg logit contributions | |
Eng | -0.646 |
millenn | -0.573 |
Gar | -0.570 |
BUG | -0.554 |
cel | -0.554 |
Token | you |
Token ID | 345 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
BW | +0.367 |
bons | +0.310 |
ciating | +0.309 |
nb | +0.308 |
Moz | +0.305 |
Neg logit contributions | |
Eng | -0.408 |
millenn | -0.366 |
Gar | -0.363 |
BUG | -0.354 |
cel | -0.350 |
Token | to |
Token ID | 284 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
Eng | +1.800 |
Gar | +1.583 |
millenn | +1.565 |
cel | +1.545 |
BUG | +1.540 |
Neg logit contributions | |
BW | -1.895 |
ciating | -1.655 |
bons | -1.651 |
nb | -1.643 |
Moz | -1.605 |
Token | see |
Token ID | 766 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
Eng | +0.687 |
millenn | +0.609 |
Gar | +0.604 |
BUG | +0.586 |
cel | +0.585 |
Neg logit contributions | |
BW | -0.669 |
bons | -0.574 |
ciating | -0.573 |
nb | -0.572 |
Moz | -0.562 |